From 2d12df47eafe74bf2e22cbbebc0265db7cd47082 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 6 Oct 2018 18:40:59 +0200 Subject: PM / AVS: SmartReflex: remove unused function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit omap_sr_register_pmic() was introduced in 2010 in commit 984aa6dbf4ca ("OMAP3: PM: Adding smartreflex driver support.") . There was never any caller of this function in mainline resulting in a warning sr_init: No PMIC hook to init smartreflex for each machine where this driver is enabled. So remove the unused function and the pr_warn. Signed-off-by: Uwe Kleine-König Signed-off-by: Rafael J. Wysocki --- include/linux/power/smartreflex.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power/smartreflex.h b/include/linux/power/smartreflex.h index 7b81dad712de..a586976f4784 100644 --- a/include/linux/power/smartreflex.h +++ b/include/linux/power/smartreflex.h @@ -303,9 +303,6 @@ void omap_sr_enable(struct voltagedomain *voltdm); void omap_sr_disable(struct voltagedomain *voltdm); void omap_sr_disable_reset_volt(struct voltagedomain *voltdm); -/* API to register the pmic specific data with the smartreflex driver. */ -void omap_sr_register_pmic(struct omap_sr_pmic_data *pmic_data); - /* Smartreflex driver hooks to be called from Smartreflex class driver */ int sr_enable(struct omap_sr *sr, unsigned long volt); void sr_disable(struct omap_sr *sr); @@ -320,7 +317,5 @@ static inline void omap_sr_enable(struct voltagedomain *voltdm) {} static inline void omap_sr_disable(struct voltagedomain *voltdm) {} static inline void omap_sr_disable_reset_volt( struct voltagedomain *voltdm) {} -static inline void omap_sr_register_pmic( - struct omap_sr_pmic_data *pmic_data) {} #endif #endif -- cgit v1.2.3 From 23c42a403a9cfdbad6004a556c927be7dd61a8ee Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 27 Oct 2018 15:07:40 +0200 Subject: netfilter: ipset: Introduction of new commands and protocol version 7 Two new commands (IPSET_CMD_GET_BYNAME, IPSET_CMD_GET_BYINDEX) are introduced. The new commands makes possible to eliminate the getsockopt operation (in iptables set/SET match/target) and thus use only netlink communication between userspace and kernel for ipset. With the new protocol version, userspace can exactly know which functionality is supported by the running kernel. Both the kernel and userspace is fully backward compatible. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34fc80f3eb90..c4ce07402c24 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -303,11 +303,11 @@ ip_set_put_flags(struct sk_buff *skb, struct ip_set *set) /* Netlink CB args */ enum { IPSET_CB_NET = 0, /* net namespace */ + IPSET_CB_PROTO, /* ipset protocol */ IPSET_CB_DUMP, /* dump single set/all sets */ IPSET_CB_INDEX, /* set index */ IPSET_CB_PRIVATE, /* set private data */ IPSET_CB_ARG0, /* type specific */ - IPSET_CB_ARG1, }; /* register and unregister set references */ -- cgit v1.2.3 From e38f89d310fcc543b0b94594a92db1d6cfbd9376 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 13 Jun 2018 20:22:04 +0530 Subject: PM / Domains: Add genpd_opp_to_performance_state() The OPP core currently stores the performance state in the consumer device's OPP table, but that is going to change going forward and performance state will rather be set directly in the genpd's OPP table. For that we need to get the performance state for genpd's device structure (genpd->dev) instead of the consumer device's structure. Add a new helper to do that. Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar --- include/linux/pm_domain.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 3b5d7280e52e..4f803f934308 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -258,6 +258,8 @@ int of_genpd_add_subdomain(struct of_phandle_args *parent, struct generic_pm_domain *of_genpd_remove_last(struct device_node *np); int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n); +unsigned int pm_genpd_opp_to_performance_state(struct device *genpd_dev, + struct dev_pm_opp *opp); unsigned int of_genpd_opp_to_performance_state(struct device *dev, struct device_node *np); @@ -299,6 +301,13 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn, return -ENODEV; } +static inline unsigned int +pm_genpd_opp_to_performance_state(struct device *genpd_dev, + struct dev_pm_opp *opp) +{ + return 0; +} + static inline unsigned int of_genpd_opp_to_performance_state(struct device *dev, struct device_node *np) -- cgit v1.2.3 From 4f018bc0e1cfdec2e25072db9fecc1f363ba79ea Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 26 Jun 2018 16:29:34 +0530 Subject: OPP: Add dev_pm_opp_{set|put}_genpd_virt_dev() helper Multiple generic power domains for a consumer device are supported with the help of virtual devices, which are created for each consumer device - genpd pair. These are the device structures which are attached to the power domain and are required by the OPP core to set the performance state of the genpd. The helpers added by this commit are required to be called once for each of these virtual devices. These are required only if multiple domains are available for a device, otherwise the actual device structure will be used instead by the OPP core. The new helpers also support the complex cases where the consumer device wouldn't always require all the domains. For example, a camera may require only one power domain during normal operations but two during high resolution operations. The consumer driver can call dev_pm_opp_put_genpd_virt_dev(high_resolution_genpd_virt_dev) if it is currently operating in the normal mode and doesn't have any performance requirements from the genpd which manages high resolution power requirements. The consumer driver can later call dev_pm_opp_set_genpd_virt_dev(high_resolution_genpd_virt_dev) once it switches back to the high resolution mode. The new helpers differ from other OPP set/put helpers as the new ones can be called with OPPs initialized for the table as we may need to call them on the fly because of the complex case explained above. For this reason it is possible that the genpd virt_dev structure may be used in parallel while the new helpers are running and a new mutex is added to protect against that. We didn't use the existing opp_table->lock mutex as that is widely used in the OPP core and we will need this lock in the dev_pm_opp_set_rate() helper while changing OPP and we need to make sure there is not much contention while doing that as that's the hotpath. Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 5d399eeef172..8fed222c089b 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -126,6 +126,8 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); +struct opp_table *dev_pm_opp_set_genpd_virt_dev(struct device *dev, struct device *virt_dev, int index); +void dev_pm_opp_put_genpd_virt_dev(struct opp_table *opp_table, struct device *virt_dev); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -272,6 +274,12 @@ static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} +static inline struct opp_table *dev_pm_opp_set_genpd_virt_dev(struct device *dev, struct device *virt_dev, int index) +{ + return ERR_PTR(-ENOTSUPP); +} + +static inline void dev_pm_opp_put_genpd_virt_dev(struct opp_table *opp_table, struct device *virt_dev) {} static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { return -ENOTSUPP; -- cgit v1.2.3 From 4c6a343e57fe241fa30ab31ac4969561272cc6b2 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Jun 2018 16:29:50 +0530 Subject: OPP: Rename and relocate of_genpd_opp_to_performance_state() The OPP core already has the performance state values for each of the genpd's OPPs and there is no need to call the genpd callback again to get the performance state for the case where the end device doesn't have an OPP table and has the "required-opps" property directly in its node. This commit renames of_genpd_opp_to_performance_state() as of_get_required_opp_performance_state() and moves it to the OPP core, as it is all about OPP stuff now. Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar --- include/linux/pm_domain.h | 9 --------- include/linux/pm_opp.h | 5 +++++ 2 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 4f803f934308..642036952553 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -260,8 +260,6 @@ int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n); unsigned int pm_genpd_opp_to_performance_state(struct device *genpd_dev, struct dev_pm_opp *opp); -unsigned int of_genpd_opp_to_performance_state(struct device *dev, - struct device_node *np); int genpd_dev_pm_attach(struct device *dev); struct device *genpd_dev_pm_attach_by_id(struct device *dev, @@ -308,13 +306,6 @@ pm_genpd_opp_to_performance_state(struct device *genpd_dev, return 0; } -static inline unsigned int -of_genpd_opp_to_performance_state(struct device *dev, - struct device_node *np) -{ - return 0; -} - static inline int genpd_dev_pm_attach(struct device *dev) { return 0; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 8fed222c089b..889bb347fbd9 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -315,6 +315,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); +unsigned int of_get_required_opp_performance_state(struct device_node *np, int index); #else static inline int dev_pm_opp_of_add_table(struct device *dev) { @@ -357,6 +358,10 @@ static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) { return NULL; } +static inline unsigned int of_get_required_opp_performance_state(struct device_node *np, int index) +{ + return 0; +} #endif #endif /* __LINUX_OPP_H__ */ -- cgit v1.2.3 From 534245cc69c2a3597d8ed0e7782ae3f563e92c68 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Jun 2018 16:33:25 +0530 Subject: OPP: Remove of_dev_pm_opp_find_required_opp() This isn't used anymore, remove it. Reviewed-by: Ulf Hansson Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 889bb347fbd9..2b2c3fd985ab 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -313,7 +313,6 @@ int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask); int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); -struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); unsigned int of_get_required_opp_performance_state(struct device_node *np, int index); #else @@ -350,10 +349,6 @@ static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device return NULL; } -static inline struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev, struct device_node *np) -{ - return NULL; -} static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) { return NULL; -- cgit v1.2.3 From 48207d7595d2be604e21228e5a93aaff17e4b808 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 5 Oct 2018 21:42:06 +0200 Subject: gpio: drop devm_gpiochip_remove() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is hardly any reason to call devm_gpiochip_remove() because the driver core handles calling gpiochip_remove() automatically. To make it harder to introduce new (and probably unneeded) callers, drop the function. Signed-off-by: Uwe Kleine-König Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 2db62b550b95..f70d976e1395 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -422,7 +422,6 @@ static inline int gpiochip_add(struct gpio_chip *chip) extern void gpiochip_remove(struct gpio_chip *chip); extern int devm_gpiochip_add_data(struct device *dev, struct gpio_chip *chip, void *data); -extern void devm_gpiochip_remove(struct device *dev, struct gpio_chip *chip); extern struct gpio_chip *gpiochip_find(void *data, int (*match)(struct gpio_chip *chip, void *data)); -- cgit v1.2.3 From 18534df419041e6c1f4b41af56ee7d41f757815c Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 1 Nov 2018 21:12:50 +0800 Subject: gpiolib: Fix possible use after free on label gpiod_request_commit() copies the pointer to the label passed as an argument only to be used later. But there's a chance the caller could immediately free the passed string(e.g., local variable). This could trigger a use after free when we use gpio label(e.g., gpiochip_unlock_as_irq(), gpiochip_is_requested()). To be on the safe side: duplicate the string with kstrdup_const() so that if an unaware user passes an address to a stack-allocated buffer, we won't get the arbitrary label. Also fix gpiod_set_consumer_name(). Signed-off-by: Muchun Song Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index f2f887795d43..ed070512b40e 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -162,7 +162,7 @@ int gpiod_is_active_low(const struct gpio_desc *desc); int gpiod_cansleep(const struct gpio_desc *desc); int gpiod_to_irq(const struct gpio_desc *desc); -void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name); +int gpiod_set_consumer_name(struct gpio_desc *desc, const char *name); /* Convert between the old gpio_ and new gpiod_ interfaces */ struct gpio_desc *gpio_to_desc(unsigned gpio); @@ -495,10 +495,12 @@ static inline int gpiod_to_irq(const struct gpio_desc *desc) return -EINVAL; } -static inline void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name) +static inline int gpiod_set_consumer_name(struct gpio_desc *desc, + const char *name) { /* GPIO can never have been requested */ WARN_ON(1); + return -EINVAL; } static inline struct gpio_desc *gpio_to_desc(unsigned gpio) -- cgit v1.2.3 From b0e137ad24b6cc36a4ab09558a401e124163eefb Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 15 Oct 2018 21:41:28 +0200 Subject: mtd: rawnand: Provide helper for polling GPIO R/B pin Each controller driver having access to NAND R/B pin over GPIO would have to reimplement the polling loop otherwise. Suggested-by: Boris Brezillon Signed-off-by: Janusz Krzysztofik Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e10b126e148f..4e91a70ede10 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1346,4 +1346,8 @@ void nand_release(struct nand_chip *chip); */ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms); +struct gpio_desc; +int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, + unsigned long timeout_ms); + #endif /* __LINUX_MTD_RAWNAND_H */ -- cgit v1.2.3 From 6da4b3ab9a6e9b1b5f90322ab3fa3a7dd18edb19 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 2 Nov 2018 22:59:51 +0800 Subject: genirq/affinity: Add support for allocating interrupt sets A driver may have a need to allocate multiple sets of MSI/MSI-X interrupts, and have them appropriately affinitized. Add support for defining a number of sets in the irq_affinity structure, of varying sizes, and get each set affinitized correctly across the machine. [ tglx: Minor changelog tweaks ] Signed-off-by: Jens Axboe Signed-off-by: Ming Lei Signed-off-by: Thomas Gleixner Reviewed-by: Hannes Reinecke Reviewed-by: Ming Lei Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Cc: linux-block@vger.kernel.org Link: https://lkml.kernel.org/r/20181102145951.31979-5-ming.lei@redhat.com --- include/linux/interrupt.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 1d6711c28271..ca397ff40836 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -247,10 +247,14 @@ struct irq_affinity_notify { * the MSI(-X) vector space * @post_vectors: Don't apply affinity to @post_vectors at end of * the MSI(-X) vector space + * @nr_sets: Length of passed in *sets array + * @sets: Number of affinitized sets */ struct irq_affinity { int pre_vectors; int post_vectors; + int nr_sets; + int *sets; }; #if defined(CONFIG_SMP) -- cgit v1.2.3 From 4c0608f4a0e76dfb82d3accd20081f4bf47ed143 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 30 Oct 2018 09:45:55 -0400 Subject: XArray: Regularise xa_reserve The xa_reserve() function was a little unusual in that it attempted to be callable for all kinds of locking scenarios. Make it look like the other APIs with __xa_reserve, xa_reserve_bh and xa_reserve_irq variants. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 80 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 79 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index d9514928ddac..c2cb0426c60c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -291,7 +291,6 @@ void *xa_load(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_reserve(struct xarray *, unsigned long index, gfp_t); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -455,6 +454,7 @@ 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_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); @@ -621,6 +621,84 @@ static inline int xa_alloc_irq(struct xarray *xa, u32 *id, u32 max, void *entry, return err; } +/** + * xa_reserve() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * Ensures there is somewhere to store an entry at @index in the array. + * If there is already something stored at @index, this function does + * nothing. If there was nothing there, the entry is marked as reserved. + * Loading from a reserved entry returns a %NULL pointer. + * + * If you do not use the entry that you have reserved, call xa_release() + * or xa_erase() to free any unnecessary memory. + * + * Context: Any context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock(xa); + + return ret; +} + +/** + * xa_reserve_bh() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * A softirq-disabling version of xa_reserve(). + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock_bh(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock_bh(xa); + + return ret; +} + +/** + * xa_reserve_irq() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * An interrupt-disabling version of xa_reserve(). + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock_irq(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock_irq(xa); + + return ret; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* -- cgit v1.2.3 From c5beb07e7a06b24f4f27304f6282b5dbd929543b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 31 Oct 2018 14:39:28 -0400 Subject: XArray: Unify xa_cmpxchg and __xa_cmpxchg xa_cmpxchg() was one of the largest functions in the xarray implementation. By turning it into a wrapper and having the callers take the lock (like several other functions), we save 160 bytes on a tinyconfig build and reduce the duplication in xarray.c. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 113 ++++++++++++++++++++++++++++++------------------- 1 file changed, 69 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index c2cb0426c60c..8e59d4fbd55e 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -289,8 +289,6 @@ struct xarray { 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_cmpxchg(struct xarray *, unsigned long index, - void *old, void *entry, gfp_t); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -359,48 +357,6 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) return xa_store(xa, index, NULL, 0); } -/** - * 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: Process 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; -} - -/** - * xa_release() - Release a reserved entry. - * @xa: XArray. - * @index: Index of entry. - * - * After calling xa_reserve(), you can call this function to release the - * reservation. If the entry at @index has been stored to, this function - * will do nothing. - */ -static inline void xa_release(struct xarray *xa, unsigned long index) -{ - xa_cmpxchg(xa, index, NULL, NULL, 0); -} - /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. @@ -534,6 +490,61 @@ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) return entry; } +/** + * xa_cmpxchg() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * If the entry at @index is the same as @old, replace it with @entry. + * If the return value is equal to @old, then the exchange was successful. + * + * Context: Any context. Takes and releases the xa_lock. May sleep + * if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock(xa); + + return curr; +} + +/** + * 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: Process 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; +} + /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. @@ -699,6 +710,20 @@ int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) return ret; } +/** + * xa_release() - Release a reserved entry. + * @xa: XArray. + * @index: Index of entry. + * + * After calling xa_reserve(), you can call this function to release the + * reservation. If the entry at @index has been stored to, this function + * will do nothing. + */ +static inline void xa_release(struct xarray *xa, unsigned long index) +{ + xa_cmpxchg(xa, index, NULL, NULL, 0); +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* -- cgit v1.2.3 From 9c16bb88905456a9b1299338041f05fa7699971b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Nov 2018 15:48:49 -0500 Subject: XArray: Turn xa_erase into an exported function Make xa_erase() take the spinlock and then call __xa_erase(), but make it out of line since it's such a common function. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 8e59d4fbd55e..4c839c17a99b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -289,6 +289,7 @@ struct xarray { 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); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -340,23 +341,6 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) return xa->xa_flags & XA_FLAGS_MARK(mark); } -/** - * xa_erase() - Erase this entry from the XArray. - * @xa: XArray. - * @index: Index of entry. - * - * This function is the equivalent of calling xa_store() with %NULL as - * the third argument. The XArray does not need to allocate memory, so - * the user does not need to provide GFP flags. - * - * Context: Process context. Takes and releases the xa_lock. - * Return: The entry which used to be at this index. - */ -static inline void *xa_erase(struct xarray *xa, unsigned long index) -{ - return xa_store(xa, index, NULL, 0); -} - /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. -- cgit v1.2.3 From 84e5acb76dacb8ebd648a86a53907ce0dd616534 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 14:41:29 -0400 Subject: XArray: Add xa_store_bh() and xa_store_irq() These convenience wrappers disable interrupts while taking the spinlock. A number of drivers would otherwise have to open-code these functions. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4c839c17a99b..52d9732e4ec4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -426,6 +426,58 @@ static inline int __xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_store_bh() - Store this entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_store() except it disables softirqs + * while holding the array lock. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: The entry which used to be at this index. + */ +static inline void *xa_store_bh(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_bh(xa); + curr = __xa_store(xa, index, entry, gfp); + xa_unlock_bh(xa); + + return curr; +} + +/** + * xa_store_irq() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_store() except it disables interrupts + * while holding the array lock. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: The entry which used to be at this index. + */ +static inline void *xa_store_irq(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_irq(xa); + curr = __xa_store(xa, index, entry, gfp); + xa_unlock_irq(xa); + + return curr; +} + /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. -- cgit v1.2.3 From 804dfaf01bcc9daa4298c608ba9018abf616ec48 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Nov 2018 16:37:15 -0500 Subject: XArray: Fix Documentation Minor fixes. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 52d9732e4ec4..564892e19f8c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -487,7 +487,7 @@ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, * the third argument. The XArray does not need to allocate memory, so * the user does not need to provide GFP flags. * - * Context: Process context. Takes and releases the xa_lock while + * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ @@ -622,7 +622,7 @@ static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, * Updates the @id pointer with the index, then stores the entry at that * index. A concurrent lookup will not see an uninitialised @id. * - * Context: Process context. Takes and releases the xa_lock while + * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if * there is no more space in the XArray. -- cgit v1.2.3 From 61d0de0543a6e982918c6054a6a12cfbdd73018a Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Tue, 30 Oct 2018 09:55:07 -0500 Subject: regulator: pfuze100-regulator: add coin support to PF0100 The driver currently supports coin cell / super cap charging, so this patch extends it to support PF0100. Signed-off-by: Adam Ford Reviewed-by: Fabio Estevam Signed-off-by: Mark Brown --- include/linux/regulator/pfuze100.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h index cb5aecd40f07..331d7d940c7a 100644 --- a/include/linux/regulator/pfuze100.h +++ b/include/linux/regulator/pfuze100.h @@ -33,7 +33,8 @@ #define PFUZE100_VGEN4 12 #define PFUZE100_VGEN5 13 #define PFUZE100_VGEN6 14 -#define PFUZE100_MAX_REGULATOR 15 +#define PFUZE100_COIN 15 +#define PFUZE100_MAX_REGULATOR 16 #define PFUZE200_SW1AB 0 #define PFUZE200_SW2 1 -- cgit v1.2.3 From 5e1abdc3fe56939d9ac34209706b1a527b77b61b Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 6 Nov 2018 10:45:36 -0500 Subject: net: skbuff.h: remove unnecessary unlikely() WARN_ON() already contains an unlikely(), so it's not necessary to use unlikely. Signed-off-by: Yangtao Li Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0ba687454267..7dcfb5591dc3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2508,10 +2508,8 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { - if (unlikely(skb_is_nonlinear(skb))) { - WARN_ON(1); + if (WARN_ON(skb_is_nonlinear(skb))) return; - } skb->len = len; skb_set_tail_pointer(skb, len); } -- cgit v1.2.3 From 99b77fef3c6c69bb7664f1ac97a69d5b17968dae Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 31 Oct 2018 12:20:28 +0200 Subject: net/mlx5: Fix XRC SRQ umem valid bits Adapt XRC SRQ to the latest HW specification with fixed definition around umem valid bits. The previous definition relied on a bit which was taken for other purposes in legacy FW. Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dbff9ff28f2c..34e17e6f8942 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 dbr_umem_valid[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_at_46[0x2]; + u8 reserved_at_46[0x1]; + u8 dbr_umem_valid[0x1]; u8 cqn[0x18]; u8 reserved_at_60[0x20]; @@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; + u8 xrc_srq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; -- cgit v1.2.3 From 23b5f73266e59a598c1e5dd435d87651b5a7626b Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 1 Oct 2018 12:45:00 -0700 Subject: usb: typec: tcpm: Do not disconnect link for self powered devices During HARD_RESET the data link is disconnected. For self powered device, the spec is advising against doing that. >From USB_PD_R3_0 7.1.5 Response to Hard Resets Device operation during and after a Hard Reset is defined as follows: Self-powered devices Should Not disconnect from USB during a Hard Reset (see Section 9.1.2). Bus powered devices will disconnect from USB during a Hard Reset due to the loss of their power source. Tackle this by letting TCPM know whether the device is self or bus powered. This overcomes unnecessary port disconnections from hard reset. Also, speeds up the enumeration time when connected to Type-A ports. Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Heikki Krogerus --------- Version history: V3: Rebase on top of usb-next V2: Based on feedback from heikki.krogerus@linux.intel.com - self_powered added to the struct tcpm_port which is populated from a. "connector" node of the device tree in tcpm_fw_get_caps() b. "self_powered" node of the tcpc_config in tcpm_copy_caps Based on feedbase from linux@roeck-us.net - Code was refactored - SRC_HARD_RESET_VBUS_OFF sets the link state to false based on self_powered flag V1 located here: https://lkml.org/lkml/2018/9/13/94 Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 7e7fbfb84e8e..50c74a77db55 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -89,6 +89,7 @@ struct tcpc_config { enum typec_port_data data; enum typec_role default_role; bool try_role_hw; /* try.{src,snk} implemented in hardware */ + bool self_powered; /* port belongs to a self powered device */ const struct typec_altmode_desc *alt_modes; }; -- cgit v1.2.3 From 781f0766cc41a9dd2e5d118ef4b1d5d89430257b Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 19 Oct 2018 16:14:50 +0800 Subject: USB: Wait for extra delay time after USB_PORT_FEAT_RESET for quirky hub Devices connected under Terminus Technology Inc. Hub (1a40:0101) may fail to work after the system resumes from suspend: [ 206.063325] usb 3-2.4: reset full-speed USB device number 4 using xhci_hcd [ 206.143691] usb 3-2.4: device descriptor read/64, error -32 [ 206.351671] usb 3-2.4: device descriptor read/64, error -32 Info for this hub: T: Bus=03 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 2 Spd=480 MxCh= 4 D: Ver= 2.00 Cls=09(hub ) Sub=00 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=1a40 ProdID=0101 Rev=01.11 S: Product=USB 2.0 Hub C: #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=100mA I: If#= 0 Alt= 0 #EPs= 1 Cls=09(hub ) Sub=00 Prot=00 Driver=hub Some expirements indicate that the USB devices connected to the hub are innocent, it's the hub itself is to blame. The hub needs extra delay time after it resets its port. Hence wait for extra delay, if the device is connected to this quirky hub. Signed-off-by: Kai-Heng Feng Cc: stable Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index b7a99ce56bc9..a1be64c9940f 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -66,4 +66,7 @@ /* Device needs a pause after every control message. */ #define USB_QUIRK_DELAY_CTRL_MSG BIT(13) +/* Hub needs extra delay after resetting its port. */ +#define USB_QUIRK_HUB_SLOW_RESET BIT(14) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 5132b3d283710d196cd8af99b5585507e8b30709 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 1 Nov 2018 22:25:04 +0100 Subject: spi: gpio: Support 3WIRE high-impedance turn-around Some devices such as the TPO TPG110 display panel require a "high-impedance turn-around", in effect a clock cycle after switching the line from output to input mode. Support this in the GPIO driver to begin with. Other driver may implement it if they can, it is unclear if this can be achieved with anything else than GPIO bit-banging. Cc: Andrzej Hajda Acked-by: Lorenzo Bianconi Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 6be77fa5ab90..3ced58eebe1b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -155,6 +155,7 @@ struct spi_device { #define SPI_RX_DUAL 0x400 /* receive with 2 wires */ #define SPI_RX_QUAD 0x800 /* receive with 4 wires */ #define SPI_CS_WORD 0x1000 /* toggle cs after each word */ +#define SPI_3WIRE_HIZ 0x2000 /* high impedance turnaround */ int irq; void *controller_state; void *controller_data; -- cgit v1.2.3 From dedf7dce4cec5c0abe69f4fa6938d5100398220b Mon Sep 17 00:00:00 2001 From: "Woods, Brian" Date: Tue, 6 Nov 2018 20:08:14 +0000 Subject: hwmon/k10temp, x86/amd_nb: Consolidate shared device IDs Consolidate shared PCI_DEVICE_IDs that were scattered through k10temp and amd_nb, and move them into pci_ids. Signed-off-by: Brian Woods Signed-off-by: Borislav Petkov Acked-by: Guenter Roeck CC: Bjorn Helgaas CC: Clemens Ladisch CC: "H. Peter Anvin" CC: Ingo Molnar CC: Jean Delvare CC: Jia Zhang CC: CC: CC: Pu Wen CC: Thomas Gleixner CC: x86-ml Link: http://lkml.kernel.org/r/20181106200754.60722-2-brian.woods@amd.com --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 69f0abe1ba1a..78d5cd29778a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -545,6 +545,8 @@ #define PCI_DEVICE_ID_AMD_16H_NB_F4 0x1534 #define PCI_DEVICE_ID_AMD_16H_M30H_NB_F3 0x1583 #define PCI_DEVICE_ID_AMD_16H_M30H_NB_F4 0x1584 +#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 -- cgit v1.2.3 From be3518a16ef270e3b030a6ae96055f83f51bd3dd Mon Sep 17 00:00:00 2001 From: "Woods, Brian" Date: Tue, 6 Nov 2018 20:08:18 +0000 Subject: x86/amd_nb: Add PCI device IDs for family 17h, model 30h Add the PCI device IDs for family 17h model 30h, since they are needed for accessing various registers via the data fabric/SMN interface. Signed-off-by: Brian Woods Signed-off-by: Borislav Petkov CC: Bjorn Helgaas CC: Clemens Ladisch CC: Guenter Roeck CC: "H. Peter Anvin" CC: Ingo Molnar CC: Jean Delvare CC: Jia Zhang CC: CC: CC: Pu Wen CC: Thomas Gleixner CC: x86-ml Link: http://lkml.kernel.org/r/20181106200754.60722-4-brian.woods@amd.com --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 78d5cd29778a..349276fbd269 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -547,6 +547,7 @@ #define PCI_DEVICE_ID_AMD_16H_M30H_NB_F4 0x1584 #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb +#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F3 0x1493 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 -- cgit v1.2.3 From 600335205b8d162891b5ef2e32343f5b8020efd8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Oct 2018 09:53:52 -0600 Subject: ide: convert to blk-mq ide-disk and ide-cd tested as working just fine, ide-tape and ide-floppy haven't. But the latter don't require changes, so they should work without issue. Add helper function to insert a request from a work queue, since we cannot invoke the blk-mq request insertion from IRQ context. Cc: David Miller Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/ide.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index c74b0321922a..079f8bc0b0f4 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include @@ -529,6 +529,10 @@ struct ide_drive_s { struct request_queue *queue; /* request queue */ + int (*prep_rq)(struct ide_drive_s *, struct request *); + + struct blk_mq_tag_set tag_set; + struct request *rq; /* current request */ void *driver_data; /* extra driver data */ u16 *id; /* identification info */ @@ -612,6 +616,10 @@ struct ide_drive_s { bool sense_rq_armed; struct request *sense_rq; struct request_sense sense_data; + + /* async sense insertion */ + struct work_struct rq_work; + struct list_head rq_list; }; typedef struct ide_drive_s ide_drive_t; @@ -1089,6 +1097,7 @@ extern int ide_pci_clk; int ide_end_rq(ide_drive_t *, struct request *, blk_status_t, unsigned int); void ide_kill_rq(ide_drive_t *, struct request *); +void ide_insert_request_head(ide_drive_t *, struct request *); void __ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); void ide_set_handler(ide_drive_t *, ide_handler_t *, unsigned int); @@ -1208,7 +1217,7 @@ 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 void do_ide_request(struct request_queue *); +extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); 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 9ba20527f4d1430b5f3e5f566be5af3e156a3284 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 10:15:10 -0600 Subject: blk-mq: provide mq_ops->busy() hook We'll hook into this from blk_lld_busy(), allowing blk-mq to also return whether or not a given queue currently has requests in progress. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2286dc12c6bc..5c8418ebbfd6 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -114,6 +114,7 @@ typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, typedef void (busy_tag_iter_fn)(struct request *, void *, bool); typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int); typedef int (map_queues_fn)(struct blk_mq_tag_set *set); +typedef bool (busy_fn)(struct request_queue *); struct blk_mq_ops { @@ -165,6 +166,11 @@ struct blk_mq_ops { /* Called from inside blk_get_request() */ void (*initialize_rq_fn)(struct request *rq); + /* + * If set, returns whether or not this queue currently is busy + */ + busy_fn *busy; + map_queues_fn *map_queues; #ifdef CONFIG_BLK_DEBUG_FS -- cgit v1.2.3 From c6f2882691e8fd128083abdcc3c5aa5b410c2367 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 10:22:19 -0600 Subject: block: remove q->lld_busy_fn() Nobody is using the legacy path for blk_lld_busy() anymore, remove it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4293dc1cd160..e867733b761d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -320,7 +320,6 @@ typedef void (unprep_rq_fn) (struct request_queue *, struct request *); struct bio_vec; typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); -typedef int (lld_busy_fn) (struct request_queue *q); typedef int (bsg_job_fn) (struct bsg_job *); typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); typedef void (exit_rq_fn)(struct request_queue *, struct request *); @@ -466,7 +465,6 @@ struct request_queue { softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; - lld_busy_fn *lld_busy_fn; /* Called just after a request is allocated */ init_rq_fn *init_rq_fn; /* Called just before a request is freed */ @@ -1255,7 +1253,6 @@ extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern int blk_queue_dma_drain(struct request_queue *q, dma_drain_needed_fn *dma_drain_needed, void *buf, unsigned int size); -extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); -- cgit v1.2.3 From aae3b069d5ce865ca5ef2902c2a22cef7ab4f3a2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Oct 2018 11:26:25 -0600 Subject: bsg: pass in desired timeout handler This will ease in the conversion to blk-mq, where we can't set a timeout handler after queue init. Cc: Johannes Thumshirn Cc: linux-scsi@vger.kernel.org Reviewed-by: Hannes Reinecke Tested-by: Benjamin Block Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/bsg-lib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 6aeaf6472665..b13ae143e7ef 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -72,7 +72,7 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, int dd_job_size); + bsg_job_fn *job_fn, rq_timed_out_fn *timeout, int dd_job_size); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); -- cgit v1.2.3 From 5e28b8d8a1b03ce86f33d38a64a4983d2b5c7679 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Oct 2018 11:27:02 -0600 Subject: bsg: provide bsg_remove_queue() helper All drivers do unregister + cleanup, provide a helper for that. Cc: linux-scsi@vger.kernel.org Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Tested-by: Benjamin Block Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/bsg-lib.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index b13ae143e7ef..9c9b134b1fa5 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -73,6 +73,7 @@ void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, bsg_job_fn *job_fn, rq_timed_out_fn *timeout, int dd_job_size); +void bsg_remove_queue(struct request_queue *q); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); -- cgit v1.2.3 From 771a93c489bf486b957c7399f89ee06d43ba2d93 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 22 Oct 2018 05:12:32 -0600 Subject: block: remove blk_complete_request() It's now unused. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e867733b761d..6baea6563364 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1203,7 +1203,6 @@ extern bool __blk_end_request(struct request *rq, blk_status_t error, extern void __blk_end_request_all(struct request *rq, blk_status_t error); extern bool __blk_end_request_cur(struct request *rq, blk_status_t error); -extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); extern void blk_unprep_request(struct request *); -- cgit v1.2.3 From 7ca01926463a15f5d2681458643b2453930b873a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Oct 2018 03:39:36 -0600 Subject: block: remove legacy rq tagging It's now unused, kill it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 35 ----------------------------------- 1 file changed, 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6baea6563364..8afe3331777e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -85,8 +85,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_SORTED ((__force req_flags_t)(1 << 0)) /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* uses tagged queueing */ -#define RQF_QUEUED ((__force req_flags_t)(1 << 2)) /* may not be passed by ioscheduler */ #define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ @@ -336,15 +334,6 @@ enum blk_queue_state { Queue_up, }; -struct blk_queue_tag { - struct request **tag_index; /* map of busy tags */ - unsigned long *tag_map; /* bit map of free/busy tags */ - int max_depth; /* what we will send to device */ - int real_max_depth; /* what the array can hold */ - atomic_t refcnt; /* map can be shared */ - int alloc_policy; /* tag allocation policy */ - int next_tag; /* next tag */ -}; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ @@ -568,8 +557,6 @@ struct request_queue { unsigned int dma_pad_mask; unsigned int dma_alignment; - struct blk_queue_tag *queue_tags; - unsigned int nr_sorted; unsigned int in_flight[2]; @@ -680,7 +667,6 @@ struct request_queue { u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -#define QUEUE_FLAG_QUEUED 0 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ #define QUEUE_FLAG_DYING 2 /* queue being torn down */ #define QUEUE_FLAG_BYPASS 3 /* act as dumb FIFO queue */ @@ -724,7 +710,6 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); -#define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) @@ -1359,26 +1344,6 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } -/* - * tag stuff - */ -extern int blk_queue_start_tag(struct request_queue *, struct request *); -extern struct request *blk_queue_find_tag(struct request_queue *, int); -extern void blk_queue_end_tag(struct request_queue *, struct request *); -extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int); -extern void blk_queue_free_tags(struct request_queue *); -extern int blk_queue_resize_tags(struct request_queue *, int); -extern struct blk_queue_tag *blk_init_tags(int, int); -extern void blk_free_tags(struct blk_queue_tag *); - -static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, - int tag) -{ - if (unlikely(bqt == NULL || tag >= bqt->real_max_depth)) - return NULL; - return bqt->tag_index[tag]; -} - extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); -- cgit v1.2.3 From a1ce35fa49852db60fc6e268038530be533c5b15 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 10:23:51 -0600 Subject: block: remove dead elevator code This removes a bunch of core and elevator related code. On the core front, we remove anything related to queue running, draining, initialization, plugging, and congestions. We also kill anything related to request allocation, merging, retrieval, and completion. Remove any checking for single queue IO schedulers, as they no longer exist. This means we can also delete a bunch of code related to request issue, adding, completion, etc - and all the SQ related ops and helpers. Also kill the load_default_modules(), as all that did was provide for a way to load the default single queue elevator. Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 93 ++---------------------------------------------- include/linux/elevator.h | 90 +--------------------------------------------- include/linux/init.h | 1 - 3 files changed, 3 insertions(+), 181 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8afe3331777e..a9f6db8abcda 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -58,9 +58,6 @@ struct blk_stat_callback; typedef void (rq_end_io_fn)(struct request *, blk_status_t); -#define BLK_RL_SYNCFULL (1U << 0) -#define BLK_RL_ASYNCFULL (1U << 1) - struct request_list { struct request_queue *q; /* the queue this rl belongs to */ #ifdef CONFIG_BLK_CGROUP @@ -309,11 +306,8 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; -typedef void (request_fn_proc) (struct request_queue *q); typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); -typedef int (prep_rq_fn) (struct request_queue *, struct request *); -typedef void (unprep_rq_fn) (struct request_queue *, struct request *); struct bio_vec; typedef void (softirq_done_fn)(struct request *); @@ -432,8 +426,6 @@ struct request_queue { struct list_head queue_head; struct request *last_merge; struct elevator_queue *elevator; - int nr_rqs[2]; /* # allocated [a]sync rqs */ - int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ struct blk_queue_stats *stats; struct rq_qos *rq_qos; @@ -446,11 +438,8 @@ struct request_queue { */ struct request_list root_rl; - request_fn_proc *request_fn; make_request_fn *make_request_fn; poll_q_fn *poll_fn; - prep_rq_fn *prep_rq_fn; - unprep_rq_fn *unprep_rq_fn; softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; @@ -458,8 +447,6 @@ struct request_queue { init_rq_fn *init_rq_fn; /* Called just before a request is freed */ exit_rq_fn *exit_rq_fn; - /* Called from inside blk_get_request() */ - void (*initialize_rq_fn)(struct request *rq); const struct blk_mq_ops *mq_ops; @@ -475,17 +462,6 @@ struct request_queue { struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; - /* - * Dispatch queue sorting - */ - sector_t end_sector; - struct request *boundary_rq; - - /* - * Delayed queue handling - */ - struct delayed_work delay_work; - struct backing_dev_info *backing_dev_info; /* @@ -548,9 +524,6 @@ struct request_queue { * queue settings */ unsigned long nr_requests; /* Max # of requests */ - unsigned int nr_congestion_on; - unsigned int nr_congestion_off; - unsigned int nr_batching; unsigned int dma_drain_size; void *dma_drain_buffer; @@ -560,13 +533,6 @@ struct request_queue { unsigned int nr_sorted; unsigned int in_flight[2]; - /* - * Number of active block driver functions for which blk_drain_queue() - * must wait. Must be incremented around functions that unlock the - * queue_lock internally, e.g. scsi_request_fn(). - */ - unsigned int request_fn_active; - unsigned int rq_timeout; int poll_nsec; @@ -740,11 +706,6 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -static inline int queue_in_flight(struct request_queue *q) -{ - return q->in_flight[0] + q->in_flight[1]; -} - static inline bool blk_account_rq(struct request *rq) { return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); @@ -765,7 +726,7 @@ static inline bool blk_account_rq(struct request *rq) */ static inline bool queue_is_rq_based(struct request_queue *q) { - return q->request_fn || q->mq_ops; + return q->mq_ops; } static inline unsigned int blk_queue_cluster(struct request_queue *q) @@ -828,27 +789,6 @@ static inline bool rq_is_sync(struct request *rq) return op_is_sync(rq->cmd_flags); } -static inline bool blk_rl_full(struct request_list *rl, bool sync) -{ - unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; - - return rl->flags & flag; -} - -static inline void blk_set_rl_full(struct request_list *rl, bool sync) -{ - unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; - - rl->flags |= flag; -} - -static inline void blk_clear_rl_full(struct request_list *rl, bool sync) -{ - unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; - - rl->flags &= ~flag; -} - static inline bool rq_mergeable(struct request *rq) { if (blk_rq_is_passthrough(rq)) @@ -969,7 +909,6 @@ extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); -extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, @@ -979,7 +918,6 @@ extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); -extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_queue_split(struct request_queue *, struct bio **); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); @@ -992,15 +930,7 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); -extern void blk_start_queue(struct request_queue *q); -extern void blk_start_queue_async(struct request_queue *q); -extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); -extern void __blk_stop_queue(struct request_queue *q); -extern void __blk_run_queue(struct request_queue *q); -extern void __blk_run_queue_uncond(struct request_queue *q); -extern void blk_run_queue(struct request_queue *); -extern void blk_run_queue_async(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); @@ -1155,13 +1085,6 @@ static inline unsigned int blk_rq_count_bios(struct request *rq) return nr_bios; } -/* - * Request issue related functions. - */ -extern struct request *blk_peek_request(struct request_queue *q); -extern void blk_start_request(struct request *rq); -extern struct request *blk_fetch_request(struct request_queue *q); - void blk_steal_bios(struct bio_list *list, struct request *rq); /* @@ -1179,9 +1102,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq); */ extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_finish_request(struct request *rq, blk_status_t error); -extern bool blk_end_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes); extern void blk_end_request_all(struct request *rq, blk_status_t error); extern bool __blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); @@ -1190,15 +1110,10 @@ extern bool __blk_end_request_cur(struct request *rq, blk_status_t error); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); -extern void blk_unprep_request(struct request *); /* * Access functions for manipulating queue properties */ -extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, - spinlock_t *lock, int node_id); -extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); -extern int blk_init_allocated_queue(struct request_queue *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); @@ -1239,8 +1154,6 @@ extern int blk_queue_dma_drain(struct request_queue *q, void *buf, unsigned int size); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); -extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); -extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); @@ -1298,7 +1211,6 @@ extern void blk_set_queue_dying(struct request_queue *); * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { - struct list_head list; /* requests */ struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ }; @@ -1339,8 +1251,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) struct blk_plug *plug = tsk->plug; return plug && - (!list_empty(&plug->list) || - !list_empty(&plug->mq_list) || + (!list_empty(&plug->mq_list) || !list_empty(&plug->cb_list)); } diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 015bb59c0331..158004f1754d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -23,74 +23,6 @@ enum elv_merge { ELEVATOR_DISCARD_MERGE = 3, }; -typedef enum elv_merge (elevator_merge_fn) (struct request_queue *, struct request **, - struct bio *); - -typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, struct request *); - -typedef void (elevator_merged_fn) (struct request_queue *, struct request *, enum elv_merge); - -typedef int (elevator_allow_bio_merge_fn) (struct request_queue *, - struct request *, struct bio *); - -typedef int (elevator_allow_rq_merge_fn) (struct request_queue *, - struct request *, struct request *); - -typedef void (elevator_bio_merged_fn) (struct request_queue *, - struct request *, struct bio *); - -typedef int (elevator_dispatch_fn) (struct request_queue *, int); - -typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); -typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *); -typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *); -typedef int (elevator_may_queue_fn) (struct request_queue *, unsigned int); - -typedef void (elevator_init_icq_fn) (struct io_cq *); -typedef void (elevator_exit_icq_fn) (struct io_cq *); -typedef int (elevator_set_req_fn) (struct request_queue *, struct request *, - struct bio *, gfp_t); -typedef void (elevator_put_req_fn) (struct request *); -typedef void (elevator_activate_req_fn) (struct request_queue *, struct request *); -typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct request *); - -typedef int (elevator_init_fn) (struct request_queue *, - struct elevator_type *e); -typedef void (elevator_exit_fn) (struct elevator_queue *); -typedef void (elevator_registered_fn) (struct request_queue *); - -struct elevator_ops -{ - elevator_merge_fn *elevator_merge_fn; - elevator_merged_fn *elevator_merged_fn; - elevator_merge_req_fn *elevator_merge_req_fn; - elevator_allow_bio_merge_fn *elevator_allow_bio_merge_fn; - elevator_allow_rq_merge_fn *elevator_allow_rq_merge_fn; - elevator_bio_merged_fn *elevator_bio_merged_fn; - - elevator_dispatch_fn *elevator_dispatch_fn; - elevator_add_req_fn *elevator_add_req_fn; - elevator_activate_req_fn *elevator_activate_req_fn; - elevator_deactivate_req_fn *elevator_deactivate_req_fn; - - elevator_completed_req_fn *elevator_completed_req_fn; - - elevator_request_list_fn *elevator_former_req_fn; - elevator_request_list_fn *elevator_latter_req_fn; - - elevator_init_icq_fn *elevator_init_icq_fn; /* see iocontext.h */ - elevator_exit_icq_fn *elevator_exit_icq_fn; /* ditto */ - - elevator_set_req_fn *elevator_set_req_fn; - elevator_put_req_fn *elevator_put_req_fn; - - elevator_may_queue_fn *elevator_may_queue_fn; - - elevator_init_fn *elevator_init_fn; - elevator_exit_fn *elevator_exit_fn; - elevator_registered_fn *elevator_registered_fn; -}; - struct blk_mq_alloc_data; struct blk_mq_hw_ctx; @@ -138,16 +70,15 @@ struct elevator_type /* fields provided by elevator implementation */ union { - struct elevator_ops sq; struct elevator_mq_ops mq; } ops; + size_t icq_size; /* see iocontext.h */ size_t icq_align; /* ditto */ struct elv_fs_entry *elevator_attrs; char elevator_name[ELV_NAME_MAX]; const char *elevator_alias; struct module *elevator_owner; - bool uses_mq; #ifdef CONFIG_BLK_DEBUG_FS const struct blk_mq_debugfs_attr *queue_debugfs_attrs; const struct blk_mq_debugfs_attr *hctx_debugfs_attrs; @@ -175,40 +106,25 @@ struct elevator_queue struct kobject kobj; struct mutex sysfs_lock; unsigned int registered:1; - unsigned int uses_mq:1; DECLARE_HASHTABLE(hash, ELV_HASH_BITS); }; /* * block elevator interface */ -extern void elv_dispatch_sort(struct request_queue *, struct request *); -extern void elv_dispatch_add_tail(struct request_queue *, struct request *); -extern void elv_add_request(struct request_queue *, struct request *, int); -extern void __elv_add_request(struct request_queue *, struct request *, int); extern enum elv_merge elv_merge(struct request_queue *, struct request **, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, enum elv_merge); -extern void elv_bio_merged(struct request_queue *q, struct request *, - struct bio *); extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); -extern void elv_requeue_request(struct request_queue *, struct request *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); -extern int elv_may_queue(struct request_queue *, unsigned int); -extern void elv_completed_request(struct request_queue *, struct request *); -extern int elv_set_request(struct request_queue *q, struct request *rq, - struct bio *bio, gfp_t gfp_mask); -extern void elv_put_request(struct request_queue *, struct request *); -extern void elv_drain_elevator(struct request_queue *); /* * io scheduler registration */ -extern void __init load_default_elevator_module(void); extern int elv_register(struct elevator_type *); extern void elv_unregister(struct elevator_type *); @@ -260,9 +176,5 @@ enum { #define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist) #define rq_fifo_clear(rq) list_del_init(&(rq)->queuelist) -#else /* CONFIG_BLOCK */ - -static inline void load_default_elevator_module(void) { } - #endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/init.h b/include/linux/init.h index 9c2aba1dbabf..5255069f5a9f 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -146,7 +146,6 @@ extern unsigned int reset_devices; /* used by init/main.c */ void setup_arch(char **); void prepare_namespace(void); -void __init load_default_modules(void); int __init init_rootfs(void); #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX) -- cgit v1.2.3 From f9cd4bfe96955e7a1d3ec54b393dee87b815ba3b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 1 Nov 2018 16:41:41 -0600 Subject: block: get rid of MQ scheduler ops union This is a remnant of when we had ops for both SQ and MQ schedulers. Now it's just MQ, so get rid of the union. Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/elevator.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 158004f1754d..2e9e2763bf47 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -69,9 +69,7 @@ struct elevator_type struct kmem_cache *icq_cache; /* fields provided by elevator implementation */ - union { - struct elevator_mq_ops mq; - } ops; + struct elevator_mq_ops ops; size_t icq_size; /* see iocontext.h */ size_t icq_align; /* ditto */ -- cgit v1.2.3 From 92bc5a24844ada9b010f03c49a493e3edeadaa54 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Oct 2018 13:52:28 -0600 Subject: block: remove __blk_put_request() Now there's no difference between blk_put_request() and __blk_put_request() anymore, get rid of the underscore version and convert the few callers. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a9f6db8abcda..c502a7f40e84 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -906,7 +906,6 @@ extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); -extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); extern int blk_lld_busy(struct request_queue *q); -- cgit v1.2.3 From 4316b79e4321d4140164e42f228778e5bc66c84f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 10:25:07 -0600 Subject: block: kill legacy parts of timeout handling The only user of legacy timing now is BSG, which is invoked from the mq timeout handler. Kill the legacy code, and rename the q->rq_timed_out_fn to q->bsg_job_timeout_fn. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c502a7f40e84..0364fc53f5c8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -441,7 +441,6 @@ struct request_queue { make_request_fn *make_request_fn; poll_q_fn *poll_fn; softirq_done_fn *softirq_done_fn; - rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; /* Called just after a request is allocated */ init_rq_fn *init_rq_fn; @@ -541,7 +540,6 @@ struct request_queue { struct timer_list timeout; struct work_struct timeout_work; - struct list_head timeout_list; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP @@ -601,6 +599,7 @@ struct request_queue { #if defined(CONFIG_BLK_DEV_BSG) bsg_job_fn *bsg_job_fn; + rq_timed_out_fn *bsg_job_timeout_fn; struct bsg_class_device bsg_dev; #endif @@ -1156,7 +1155,6 @@ extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); -extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); -- cgit v1.2.3 From 1028e4b335665290dc563d5272f3c6b84e7fd66e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 09:47:17 -0600 Subject: bsg: move bsg-lib parts outside of request queue Get rid of the special bsg job fn and timeout handler, move them into a private bsg_set instead. Mostly from Christoph, with fixes for error handling and cleanups. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ----- include/linux/bsg-lib.h | 5 ++++- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0364fc53f5c8..877a3d235c45 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -312,7 +312,6 @@ typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); -typedef int (bsg_job_fn) (struct bsg_job *); typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); typedef void (exit_rq_fn)(struct request_queue *, struct request *); @@ -321,8 +320,6 @@ enum blk_eh_timer_return { BLK_EH_RESET_TIMER, /* reset timer and try again */ }; -typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *); - enum blk_queue_state { Queue_down, Queue_up, @@ -598,8 +595,6 @@ struct request_queue { atomic_t mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) - bsg_job_fn *bsg_job_fn; - rq_timed_out_fn *bsg_job_timeout_fn; struct bsg_class_device bsg_dev; #endif diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 9c9b134b1fa5..b356e0006731 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -31,6 +31,9 @@ struct device; struct scatterlist; struct request_queue; +typedef int (bsg_job_fn) (struct bsg_job *); +typedef enum blk_eh_timer_return (bsg_timeout_fn)(struct request *); + struct bsg_buffer { unsigned int payload_len; int sg_cnt; @@ -72,7 +75,7 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, rq_timed_out_fn *timeout, int dd_job_size); + bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size); void bsg_remove_queue(struct request_queue *q); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); -- cgit v1.2.3 From db6d995235606191fa9db0c717e9d843200b71ea Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 2 Nov 2018 08:46:15 -0600 Subject: block: remove request_list code It's now dead code, nobody uses it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 97 ---------------------------------------------- include/linux/blkdev.h | 34 ---------------- 2 files changed, 131 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6d766a19f2bb..1b299e025e83 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -122,9 +122,6 @@ struct blkcg_gq { /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; - /* request allocation list for this blkcg-q pair */ - struct request_list rl; - /* reference count */ atomic_t refcnt; @@ -515,94 +512,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -/** - * blk_get_rl - get request_list to use - * @q: request_queue of interest - * @bio: bio which will be attached to the allocated request (may be %NULL) - * - * The caller wants to allocate a request from @q to use for @bio. Find - * the request_list to use and obtain a reference on it. Should be called - * under queue_lock. This function is guaranteed to return non-%NULL - * request_list. - */ -static inline struct request_list *blk_get_rl(struct request_queue *q, - struct bio *bio) -{ - struct blkcg *blkcg; - struct blkcg_gq *blkg; - - rcu_read_lock(); - - blkcg = bio_blkcg(bio); - - /* bypass blkg lookup and use @q->root_rl directly for root */ - if (blkcg == &blkcg_root) - goto root_rl; - - /* - * Try to use blkg->rl. blkg lookup may fail under memory pressure - * or if either the blkcg or queue is going away. Fall back to - * root_rl in such cases. - */ - blkg = blkg_lookup(blkcg, q); - if (unlikely(!blkg)) - goto root_rl; - - blkg_get(blkg); - rcu_read_unlock(); - return &blkg->rl; -root_rl: - rcu_read_unlock(); - return &q->root_rl; -} - -/** - * blk_put_rl - put request_list - * @rl: request_list to put - * - * Put the reference acquired by blk_get_rl(). Should be called under - * queue_lock. - */ -static inline void blk_put_rl(struct request_list *rl) -{ - if (rl->blkg->blkcg != &blkcg_root) - blkg_put(rl->blkg); -} - -/** - * blk_rq_set_rl - associate a request with a request_list - * @rq: request of interest - * @rl: target request_list - * - * Associate @rq with @rl so that accounting and freeing can know the - * request_list @rq came from. - */ -static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) -{ - rq->rl = rl; -} - -/** - * blk_rq_rl - return the request_list a request came from - * @rq: request of interest - * - * Return the request_list @rq is allocated from. - */ -static inline struct request_list *blk_rq_rl(struct request *rq) -{ - return rq->rl; -} - -struct request_list *__blk_queue_next_rl(struct request_list *rl, - struct request_queue *q); -/** - * blk_queue_for_each_rl - iterate through all request_lists of a request_queue - * - * Should be used under queue_lock. - */ -#define blk_queue_for_each_rl(rl, q) \ - for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q))) - static inline int blkg_stat_init(struct blkg_stat *stat, gfp_t gfp) { int ret; @@ -939,12 +848,6 @@ static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } -static inline struct request_list *blk_get_rl(struct request_queue *q, - struct bio *bio) { return &q->root_rl; } -static inline void blk_put_rl(struct request_list *rl) { } -static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } -static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } - static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 877a3d235c45..e0c661a95c39 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -58,22 +58,6 @@ struct blk_stat_callback; typedef void (rq_end_io_fn)(struct request *, blk_status_t); -struct request_list { - struct request_queue *q; /* the queue this rl belongs to */ -#ifdef CONFIG_BLK_CGROUP - struct blkcg_gq *blkg; /* blkg this request pool belongs to */ -#endif - /* - * count[], starved[], and wait[] are indexed by - * BLK_RW_SYNC/BLK_RW_ASYNC - */ - int count[2]; - int starved[2]; - mempool_t *rq_pool; - wait_queue_head_t wait[2]; - unsigned int flags; -}; - /* * request flags */ typedef __u32 __bitwise req_flags_t; @@ -259,10 +243,6 @@ struct request { /* for bidi */ struct request *next_rq; - -#ifdef CONFIG_BLK_CGROUP - struct request_list *rl; /* rl this rq is alloced from */ -#endif }; static inline bool blk_op_is_scsi(unsigned int op) @@ -312,8 +292,6 @@ typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); -typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); -typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ @@ -427,22 +405,10 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; - /* - * If blkcg is not used, @q->root_rl serves all requests. If blkcg - * is used, root blkg allocates from @q->root_rl and all other - * blkgs from their own blkg->rl. Which one to use should be - * determined using bio_request_list(). - */ - struct request_list root_rl; - make_request_fn *make_request_fn; poll_q_fn *poll_fn; softirq_done_fn *softirq_done_fn; dma_drain_needed_fn *dma_drain_needed; - /* Called just after a request is allocated */ - init_rq_fn *init_rq_fn; - /* Called just before a request is freed */ - exit_rq_fn *exit_rq_fn; const struct blk_mq_ops *mq_ops; -- cgit v1.2.3 From 7d692330e7cd581ccfee982334bf06b236cb999a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Oct 2018 10:48:12 -0600 Subject: block: get rid of blk_queued_rq() No point in hiding what this does, just open code it in the one spot where we are still using it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e0c661a95c39..c675e2b5af62 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -673,8 +673,6 @@ static inline bool blk_account_rq(struct request *rq) #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) -/* rq->queuelist of dequeued request must be list_empty() */ -#define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist)) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -- cgit v1.2.3 From c7bb9ad1744ea14e61e5fff99ee5282709b0c9d9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 31 Oct 2018 09:43:30 -0600 Subject: block: get rid of q->softirq_done_fn() With the legacy path gone, all we do is funnel it through the mq_ops->complete() operation. Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 ++- include/linux/blkdev.h | 3 --- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 5c8418ebbfd6..9dd574e5436a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -115,6 +115,7 @@ typedef void (busy_tag_iter_fn)(struct request *, void *, bool); typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int); typedef int (map_queues_fn)(struct blk_mq_tag_set *set); typedef bool (busy_fn)(struct request_queue *); +typedef void (complete_fn)(struct request *); struct blk_mq_ops { @@ -142,7 +143,7 @@ struct blk_mq_ops { */ poll_fn *poll; - softirq_done_fn *complete; + complete_fn *complete; /* * Called when the block layer side of a hardware queue has been diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c675e2b5af62..d4104844d6bb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -290,7 +290,6 @@ typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; -typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); enum blk_eh_timer_return { @@ -407,7 +406,6 @@ struct request_queue { make_request_fn *make_request_fn; poll_q_fn *poll_fn; - softirq_done_fn *softirq_done_fn; dma_drain_needed_fn *dma_drain_needed; const struct blk_mq_ops *mq_ops; @@ -1113,7 +1111,6 @@ extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); -extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); -- cgit v1.2.3 From 9cf2bab6307659b940da65d16dcc8f82c69f3a97 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 31 Oct 2018 17:01:22 -0600 Subject: block: kill request ->cpu member This was used for completion placement for the legacy path, but for mq we have rq->mq_ctx->cpu for that. Add a helper to get the request CPU assignment, as the mq_ctx type is private to blk-mq. Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ include/linux/blkdev.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9dd574e5436a..d83a26fb37e5 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -300,6 +300,8 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); +unsigned int blk_mq_rq_cpu(struct request *rq); + /** * blk_mq_mark_complete() - Set request state to complete * @rq: request to set to complete state diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d4104844d6bb..c8fa4d3d7fee 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -130,7 +130,6 @@ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; - int cpu; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; @@ -669,7 +668,6 @@ static inline bool blk_account_rq(struct request *rq) return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); } -#define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -- cgit v1.2.3 From a8908939af569ce2419f43fd56eeaf003bc3d85d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2018 14:23:06 -0600 Subject: blk-mq: kill q->mq_map It's just a pointer to set->mq_map, use that instead. Move the assignment a bit earlier, so we always know it's valid. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Bart Van Assche Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c8fa4d3d7fee..2ae7465d68ab 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -409,8 +409,6 @@ struct request_queue { const struct blk_mq_ops *mq_ops; - unsigned int *mq_map; - /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; unsigned int nr_queues; -- cgit v1.2.3 From ed76e329d74a4b15ac0f5fd3adbd52ec0178a134 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 13:06:14 -0600 Subject: blk-mq: abstract out queue map This is in preparation for allowing multiple sets of maps per queue, if so desired. Reviewed-by: Hannes Reinecke Reviewed-by: Bart Van Assche Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq-pci.h | 4 ++-- include/linux/blk-mq-virtio.h | 4 ++-- include/linux/blk-mq.h | 15 ++++++++++++--- 3 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h index 9f4c17f0d2d8..0b1f45c62623 100644 --- a/include/linux/blk-mq-pci.h +++ b/include/linux/blk-mq-pci.h @@ -2,10 +2,10 @@ #ifndef _LINUX_BLK_MQ_PCI_H #define _LINUX_BLK_MQ_PCI_H -struct blk_mq_tag_set; +struct blk_mq_queue_map; struct pci_dev; -int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev, +int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, int offset); #endif /* _LINUX_BLK_MQ_PCI_H */ diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h index 69b4da262c45..687ae287e1dc 100644 --- a/include/linux/blk-mq-virtio.h +++ b/include/linux/blk-mq-virtio.h @@ -2,10 +2,10 @@ #ifndef _LINUX_BLK_MQ_VIRTIO_H #define _LINUX_BLK_MQ_VIRTIO_H -struct blk_mq_tag_set; +struct blk_mq_queue_map; struct virtio_device; -int blk_mq_virtio_map_queues(struct blk_mq_tag_set *set, +int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, struct virtio_device *vdev, int first_vec); #endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d83a26fb37e5..176164888628 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -74,10 +74,19 @@ struct blk_mq_hw_ctx { struct srcu_struct srcu[0]; }; +struct blk_mq_queue_map { + unsigned int *mq_map; + unsigned int nr_queues; +}; + +enum { + HCTX_MAX_TYPES = 1, +}; + struct blk_mq_tag_set { - unsigned int *mq_map; + struct blk_mq_queue_map map[HCTX_MAX_TYPES]; const struct blk_mq_ops *ops; - unsigned int nr_hw_queues; + unsigned int nr_hw_queues; /* nr hw queues across maps */ unsigned int queue_depth; /* max hw supported */ unsigned int reserved_tags; unsigned int cmd_size; /* per-request extra data */ @@ -295,7 +304,7 @@ void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_map_queues(struct blk_mq_tag_set *set); +int blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); -- cgit v1.2.3 From f31967f0e455d08d3ea1d2f849bf62dafc92dbf4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 13:13:29 -0600 Subject: blk-mq: allow software queue to map to multiple hardware queues The mapping used to be dependent on just the CPU location, but now it's a tuple of (type, cpu) instead. This is a prep patch for allowing a single software queue to map to multiple hardware queues. No functional changes in this patch. This changes the software queue count to an unsigned short to save a bit of space. We can still support 64K-1 CPUs, which should be enough. Add a check to catch a wrap. Reviewed-by: Hannes Reinecke Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 176164888628..6c39d546c50b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -37,7 +37,8 @@ struct blk_mq_hw_ctx { struct blk_mq_ctx *dispatch_from; unsigned int dispatch_busy; - unsigned int nr_ctx; + unsigned short type; + unsigned short nr_ctx; struct blk_mq_ctx **ctxs; spinlock_t dispatch_wait_lock; -- cgit v1.2.3 From b3c661b15d5ab11d982e58bee23e05c1780528a1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 30 Oct 2018 10:36:06 -0600 Subject: blk-mq: support multiple hctx maps Add support for the tag set carrying multiple queue maps, and for the driver to inform blk-mq how many it wishes to support through setting set->nr_maps. This adds an mq_ops helper for drivers that support more than 1 map, mq_ops->rq_flags_to_type(). The function takes request/bio flags and CPU, and returns a queue map index for that. We then use the type information in blk_mq_map_queue() to index the map set. Reviewed-by: Hannes Reinecke Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 6c39d546c50b..8994c95056a8 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -85,7 +85,14 @@ enum { }; struct blk_mq_tag_set { + /* + * map[] holds ctx -> hctx mappings, one map exists for each type + * that the driver wishes to support. There are no restrictions + * on maps being of the same size, and it's perfectly legal to + * share maps between types. + */ struct blk_mq_queue_map map[HCTX_MAX_TYPES]; + unsigned int nr_maps; /* nr entries in map[] */ const struct blk_mq_ops *ops; unsigned int nr_hw_queues; /* nr hw queues across maps */ unsigned int queue_depth; /* max hw supported */ @@ -109,6 +116,8 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +/* takes rq->cmd_flags as input, returns a hardware type index */ +typedef int (rq_flags_to_type_fn)(struct request_queue *, unsigned int); typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *); typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); @@ -134,6 +143,11 @@ struct blk_mq_ops { */ queue_rq_fn *queue_rq; + /* + * Return a queue map type for the given request/bio flags + */ + rq_flags_to_type_fn *rq_flags_to_type; + /* * Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the -- cgit v1.2.3 From ea4f995ee8b8f0578b3319949f2edd5d812fdb0a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 15:06:13 -0600 Subject: blk-mq: cache request hardware queue mapping We call blk_mq_map_queue() a lot, at least two times for each request per IO, sometimes more. Since we now have an indirect call as well in that function. cache the mapping so we don't have to re-call blk_mq_map_queue() for the same request multiple times. Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2ae7465d68ab..9b1f470cc784 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -129,6 +129,7 @@ enum mq_rq_state { struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; + struct blk_mq_hw_ctx *mq_hctx; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; -- cgit v1.2.3 From 843477d4cc5c4bb4e346c561ecd3b9d0bd67e8c8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Oct 2018 13:16:11 -0600 Subject: blk-mq: initial support for multiple queue maps Add a queue offset to the tag map. This enables users to map iteratively, for each queue map type they support. Bump maximum number of supported maps to 2, we're now fully able to support more than 1 map. Reviewed-by: Hannes Reinecke Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8994c95056a8..729ce0f00433 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -78,10 +78,11 @@ struct blk_mq_hw_ctx { struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; + unsigned int queue_offset; }; enum { - HCTX_MAX_TYPES = 1, + HCTX_MAX_TYPES = 2, }; struct blk_mq_tag_set { -- cgit v1.2.3 From d1e36282b0bbd5de6a9c4d5275e94ef3b3438f48 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 29 Aug 2018 10:36:56 -0600 Subject: block: add REQ_HIPRI and inherit it from IOCB_HIPRI We use IOCB_HIPRI to poll for IO in the caller instead of scheduling. This information is not available for (or after) IO submission. The driver may make different queue choices based on the type of IO, so make the fact that we will poll for this IO known to the lower layers as well. Reviewed-by: Hannes Reinecke Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1dcf652ba0aa..dbdbfbd6a987 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -323,6 +323,8 @@ enum req_flag_bits { /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ + __REQ_HIPRI, + /* for driver use */ __REQ_DRV, __REQ_SWAP, /* swapping request. */ @@ -343,8 +345,8 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) - #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) +#define REQ_HIPRI (1ULL << __REQ_HIPRI) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) -- cgit v1.2.3 From 4b04cc6a8f86c4842314def22332de1f15de8523 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 5 Nov 2018 12:44:33 -0700 Subject: nvme: add separate poll queue map Adds support for defining a variable number of poll queues, currently configurable with the 'poll_queues' module parameter. Defaults to a single poll queue. And now we finally have poll support without triggering interrupts! Reviewed-by: Hannes Reinecke Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 729ce0f00433..9f5e93f40857 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -82,7 +82,7 @@ struct blk_mq_queue_map { }; enum { - HCTX_MAX_TYPES = 2, + HCTX_MAX_TYPES = 3, }; struct blk_mq_tag_set { -- cgit v1.2.3 From 24c9d423e86b17b25b4b510e81f10aa232fdaa60 Mon Sep 17 00:00:00 2001 From: "Luck, Tony" Date: Tue, 6 Nov 2018 10:39:15 -0800 Subject: EDAC, skx: Fix randconfig builds in a better way It was previously noted that Kconfig complained about unmet dependencies when trying to configure skx_edac together with CONFIG_ACPI=n. First fix for this checked for ACPI when doing select ACPI_ADXL but this required stub functions for the case where ACPI wasn't selected. It also allowed building a driver that didn't actually work for a system that has non-volatile DIMMs. Arnd Bergmann pointed out that the right fix is to make EDAC_SKX "depend on ACPI". Fixes: a324e9396ca3 ("EDAC, skx: Fix randconfig builds") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov CC: "Rafael J. Wysocki" CC: Arnd Bergmann CC: Mauro Carvalho Chehab CC: linux-edac CC: qiuxu.zhuo@intel.com Link: http://lkml.kernel.org/r/20181106183914.GA26731@agluck-desk --- include/linux/adxl.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/adxl.h b/include/linux/adxl.h index 2d29f55923e3..2a629acb4c3f 100644 --- a/include/linux/adxl.h +++ b/include/linux/adxl.h @@ -7,12 +7,7 @@ #ifndef _LINUX_ADXL_H #define _LINUX_ADXL_H -#ifdef CONFIG_ACPI_ADXL const char * const *adxl_get_component_names(void); int adxl_decode(u64 addr, u64 component_values[]); -#else -static inline const char * const *adxl_get_component_names(void) { return NULL; } -static inline int adxl_decode(u64 addr, u64 component_values[]) { return -EOPNOTSUPP; } -#endif #endif /* _LINUX_ADXL_H */ -- cgit v1.2.3 From 60fb9567bf30937e6bedfa939d7c8fd4ee6a1b1c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 7 Nov 2018 12:38:28 +0100 Subject: udp: implement complete book-keeping for encap_needed The *encap_needed static keys are enabled by UDP tunnels and several UDP encapsulations type, but they are never turned off. This can cause unneeded overall performance degradation for systems where such features are used transiently. This patch introduces complete book-keeping for such keys, decreasing the usage at socket destruction time, if needed, and avoiding that the same socket could increase the key usage multiple times. rfc v3 -> v1: - add socket lock around udp_tunnel_encap_enable() rfc v2 -> rfc v3: - use udp_tunnel_encap_enable() in setsockopt() Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/udp.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 320d49d85484..a4dafff407fb 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -49,7 +49,12 @@ struct udp_sock { unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */ + no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ + encap_enabled:1; /* This socket enabled encap + * processing; UDP tunnels and + * different encapsulation layer set + * this + */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. -- cgit v1.2.3 From e20cf8d3f1f763ad28a9cb3b41305b8a8a42653e Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 7 Nov 2018 12:38:29 +0100 Subject: udp: implement GRO for plain UDP sockets. This is the RX counterpart of commit bec1f6f69736 ("udp: generate gso with UDP_SEGMENT"). When UDP_GRO is enabled, such socket is also eligible for GRO in the rx path: UDP segments directed to such socket are assembled into a larger GSO_UDP_L4 packet. The core UDP GRO support is enabled with setsockopt(UDP_GRO). Initial benchmark numbers: Before: udp rx: 1079 MB/s 769065 calls/s After: udp rx: 1466 MB/s 24877 calls/s This change introduces a side effect in respect to UDP tunnels: after a UDP tunnel creation, now the kernel performs a lookup per ingress UDP packet, while before such lookup happened only if the ingress packet carried a valid internal header csum. rfc v2 -> rfc v3: - fixed typos in macro name and comments - really enforce UDP_GRO_CNT_MAX, instead of UDP_GRO_CNT_MAX + 1 - acquire socket lock in UDP_GRO setsockopt rfc v1 -> rfc v2: - use a new option to enable UDP GRO - use static keys to protect the UDP GRO socket lookup Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/udp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index a4dafff407fb..f613b329852e 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -50,11 +50,12 @@ struct udp_sock { __u8 encap_type; /* Is this an Encapsulation socket? */ unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ - encap_enabled:1; /* This socket enabled encap + encap_enabled:1, /* This socket enabled encap * processing; UDP tunnels and * different encapsulation layer set * this */ + gro_enabled:1; /* Can accept GRO packets */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. -- cgit v1.2.3 From bcd1665e3569b0a6f569514f023a41fc7df0b4a3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 7 Nov 2018 12:38:30 +0100 Subject: udp: add support for UDP_GRO cmsg When UDP GRO is enabled, the UDP_GRO cmsg will carry the ingress datagram size. User-space can use such info to compute the original packets layout. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/udp.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index f613b329852e..e23d5024f42f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -121,6 +121,17 @@ static inline bool udp_get_no_check6_rx(struct sock *sk) return udp_sk(sk)->no_check6_rx; } +static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ + int gso_size; + + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { + gso_size = skb_shinfo(skb)->gso_size; + put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size); + } +} + #define udp_portaddr_for_each_entry(__sk, list) \ hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node) -- cgit v1.2.3 From cf329aa42b6659204fee865bbce0ea20462552eb Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 7 Nov 2018 12:38:33 +0100 Subject: udp: cope with UDP GRO packet misdirection In some scenarios, the GRO engine can assemble an UDP GRO packet that ultimately lands on a non GRO-enabled socket. This patch tries to address the issue explicitly checking for the UDP socket features before enqueuing the packet, and eventually segmenting the unexpected GRO packet, as needed. We must also cope with re-insertion requests: after segmentation the UDP code calls the helper introduced by the previous patches, as needed. Segmentation is performed by a common helper, which takes care of updating socket and protocol stats is case of failure. rfc v3 -> v1 - fix compile issues with rxrpc - when gso_segment returns NULL, treat is as an error - added 'ipv4' argument to udp_rcv_segment() rfc v2 -> rfc v3 - moved udp_rcv_segment() into net/udp.h, account errors to socket and ns, always return NULL or segs list Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/udp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index e23d5024f42f..0a9c54e76305 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -132,6 +132,12 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) +{ + return !udp_sk(sk)->gro_enabled && skb_is_gso(skb) && + skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4; +} + #define udp_portaddr_for_each_entry(__sk, list) \ hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node) -- cgit v1.2.3 From 8572a1b4dbc0e03d7082d8e8f7a282c0f55c3ca5 Mon Sep 17 00:00:00 2001 From: Justin Chen Date: Tue, 6 Nov 2018 16:37:44 -0800 Subject: net: phy: bcm7xxx: Add entry for BCM7255 Add support for BCM7255 EPHY. Signed-off-by: Justin Chen Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 949e9af8d9d6..9cd00a37b8d3 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -28,6 +28,7 @@ #define PHY_ID_BCM89610 0x03625cd0 #define PHY_ID_BCM7250 0xae025280 +#define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 #define PHY_ID_BCM7268 0xae025090 #define PHY_ID_BCM7271 0xae0253b0 -- cgit v1.2.3 From a3320bcf28e07163354b0acfad874bf46209df63 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 7 Nov 2018 08:15:58 +0100 Subject: net: phy: make phy_trigger_machine static phy_trigger_machine() is used in phy.c only, so we can make it static. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3ea87f774a76..9e4d49ef4bca 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1054,7 +1054,6 @@ void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -void phy_trigger_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); -- cgit v1.2.3 From c8accd5a0a6abfc0405a331afa5bfc06ee92623a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 7 Nov 2018 18:07:02 +0100 Subject: net/vlan: introduce __vlan_hwaccel_clear_tag() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 83ea4df6ab81..c438fa0a1c6a 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -461,6 +461,17 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, return skb; } +/** + * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info + * @skb: skbuff to clear + * + * Clears the VLAN information from @skb + */ +static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) +{ + skb->vlan_tci = 0; +} + /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag @@ -475,7 +486,7 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (likely(skb)) - skb->vlan_tci = 0; + __vlan_hwaccel_clear_tag(skb); return skb; } -- cgit v1.2.3 From e0a6b8097351255a2dbbb45274a8b9c52850cbb6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 7 Nov 2018 18:07:02 +0100 Subject: net/vlan: introduce __vlan_hwaccel_copy_tag() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c438fa0a1c6a..941da4bf3929 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -472,6 +472,19 @@ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) skb->vlan_tci = 0; } +/** + * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb + * @dst: skbuff to copy to + * @src: skbuff to copy from + * + * Copies VLAN information from @src to @dst (for branchless code) + */ +static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) +{ + dst->vlan_proto = src->vlan_proto; + dst->vlan_tci = src->vlan_tci; +} + /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag -- cgit v1.2.3 From 9b319148cb34ecccacff09eca87765c87d5e19ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 7 Nov 2018 18:07:03 +0100 Subject: net/vlan: include the shift in skb_vlan_tag_get_prio() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 941da4bf3929..b14bf87999aa 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -81,7 +81,7 @@ static inline bool is_vlan_dev(const struct net_device *dev) #define skb_vlan_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) -#define skb_vlan_tag_get_prio(__skb) ((__skb)->vlan_tci & VLAN_PRIO_MASK) +#define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) { -- cgit v1.2.3 From 295d072a42fe1a654e765fffcaadb2f08a692dd0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 7 Nov 2018 18:07:03 +0100 Subject: net/vlan: remove unused #define HAVE_VLAN_GET_TAG MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index b14bf87999aa..03b08ffded07 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -555,8 +555,6 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, } } -#define HAVE_VLAN_GET_TAG - /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query -- cgit v1.2.3 From 40c223efaa17e9bc3d964ee285967ebbe09c3e12 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 5 Oct 2018 18:36:33 +0300 Subject: regulator: core: Limit regulators coupling to a single couple Device tree binding was changed in a way that now max-spread values must be defied per regulator pair. Limit number of pairs in order to adapt to the new binding without changing regulators code. Signed-off-by: Dmitry Osipenko Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index a9c030192147..a05d37d0efa1 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -15,7 +15,7 @@ #ifndef __LINUX_REGULATOR_DRIVER_H_ #define __LINUX_REGULATOR_DRIVER_H_ -#define MAX_COUPLED 4 +#define MAX_COUPLED 2 #include #include -- cgit v1.2.3 From 85254bcf394f93a8955814da1eef4d477b63eb84 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 5 Oct 2018 18:36:35 +0300 Subject: regulator: core: Add new max_uV_step constraint On NVIDIA Tegra30 there is a requirement for regulator "A" to have voltage higher than voltage of regulator "B" by N microvolts, the N value changes depending on the voltage of regulator "B". This is similar to min-spread between voltages of regulators, the difference is that the spread value isn't fixed. This means that extra carefulness is required for regulator "A" to drop its voltage without violating the requirement, hence its voltage should be changed in steps so that its couple "B" could follow (there is also max-spread requirement). Add new "max_uV_step" constraint that breaks voltage change into several steps, each step is limited by the max_uV_step value. Signed-off-by: Dmitry Osipenko Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index a459a5e973a7..1d34a70ffda2 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -158,6 +158,9 @@ struct regulation_constraints { /* used for coupled regulators */ int max_spread; + /* used for changing voltage in steps */ + int max_uV_step; + /* valid regulator operating modes for this machine */ unsigned int valid_modes_mask; -- cgit v1.2.3 From 7baa85727d0406ffd2b2303cd803a145aa35c505 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 8 Nov 2018 10:24:07 -0700 Subject: blk-mq-tag: change busy_iter_fn to return whether to continue or not We have this functionality in sbitmap, but we don't export it in blk-mq for users of the tags busy iteration. This can be useful for stopping the iteration, if the caller doesn't need to find more requests. Reviewed-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9f5e93f40857..ff497dfcbbf9 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -129,9 +129,9 @@ typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *, typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *, unsigned int); -typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, +typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); -typedef void (busy_tag_iter_fn)(struct request *, void *, bool); +typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int); typedef int (map_queues_fn)(struct blk_mq_tag_set *set); typedef bool (busy_fn)(struct request_queue *); -- cgit v1.2.3 From ae8799125d565c798e49dcab4bf182dbfc483524 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 8 Nov 2018 09:03:51 -0700 Subject: blk-mq: provide a helper to check if a queue is busy Returns true if the queue currently has requests pending, false if not. DM can use this to replace the atomic_inc/dec they do per device to see if a device is busy. Reviewed-by: Mike Snitzer Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ff497dfcbbf9..929e8abc5535 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -250,6 +250,8 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_free_request(struct request *rq); bool blk_mq_can_queue(struct blk_mq_hw_ctx *); +bool blk_mq_queue_busy(struct request_queue *q); + enum { /* return when out of requests */ BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), -- cgit v1.2.3 From 5cf8114d6e90b3822be5eb6a2faedf99d1c08f77 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 8 Nov 2018 10:08:46 -0500 Subject: cpuset: Expose cpuset.cpus.subpartitions with cgroup_debug For debugging purpose, it will be useful to expose the content of the subparts_cpus as a read-only file to see if the code work correctly. However, subparts_cpus will not be used at all in most use cases. So adding a new cpuset file that clutters the cgroup directory may not be desirable. This is now being done by using the hidden "cgroup_debug" kernel command line option to expose a new "cpuset.cpus.subpartitions" file. That option was originally used by the debug controller to expose itself when configured into the kernel. This is now extended to set an internal flag used by cgroup_addrm_files(). A new CFTYPE_DEBUG flag can now be used to specify that a cgroup file should only be created when the "cgroup_debug" option is specified. Signed-off-by: Waiman Long Acked-by: Peter Zijlstra (Intel) Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 5e1694fe035b..8fcbae1b8db0 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -92,6 +92,7 @@ enum { CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ + CFTYPE_DEBUG = (1 << 5), /* create when cgroup_debug */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ -- cgit v1.2.3 From 85a1f31d6392fb2c6726fcc4e072de008e3f0656 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 7 Nov 2018 20:46:51 +0100 Subject: net: phy: remove state PHY_AN After the recent changes in the state machine state PHY_AN isn't used any longer and can be removed. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9e4d49ef4bca..2090277eac4f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -178,7 +178,6 @@ static inline const char *phy_modes(phy_interface_t interface) #define PHY_INIT_TIMEOUT 100000 #define PHY_STATE_TIME 1 #define PHY_FORCE_TIMEOUT 10 -#define PHY_AN_TIMEOUT 10 #define PHY_MAX_ADDR 32 @@ -297,24 +296,10 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * * UP: The PHY and attached device are ready to do work. * Interrupts should be started here. - * - timer moves to AN - * - * AN: The PHY is currently negotiating the link state. Link is - * therefore down for now. phy_timer will set this state when it - * detects the state is UP. config_aneg will set this state - * whenever called with phydev->autoneg set to AUTONEG_ENABLE. - * - If autonegotiation finishes, but there's no link, it sets - * the state to NOLINK. - * - If aneg finishes with link, it sets the state to RUNNING, - * and calls adjust_link - * - If autonegotiation did not finish after an arbitrary amount - * of time, autonegotiation should be tried again if the PHY - * supports "magic" autonegotiation (back to AN) - * - If it didn't finish, and no magic_aneg, move to FORCING. + * - timer moves to NOLINK or RUNNING * * NOLINK: PHY is up, but not currently plugged in. * - If the timer notes that the link comes back, we move to RUNNING - * - config_aneg moves to AN * - phy_stop moves to HALTED * * FORCING: PHY is being configured with forced settings @@ -329,7 +314,6 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * link state is polled every other cycle of this state machine, * which makes it every other second) * - irq will set CHANGELINK - * - config_aneg will set AN * - phy_stop moves to HALTED * * CHANGELINK: PHY experienced a change in link state @@ -353,7 +337,6 @@ enum phy_state { PHY_READY, PHY_PENDING, PHY_UP, - PHY_AN, PHY_RUNNING, PHY_NOLINK, PHY_FORCING, -- cgit v1.2.3 From a36e185e8c85523413c1ae3e03a0bdde5501f403 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 8 Nov 2018 12:19:14 +0100 Subject: udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio Reviewed-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/linux/udp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 0a9c54e76305..2725c83395bf 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -77,6 +77,7 @@ struct udp_sock { * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk); /* GRO functions for UDP socket */ -- cgit v1.2.3 From c74d90c11c05bdfd78f8e29ee96b8a6f23daea99 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 7 Nov 2018 20:31:37 +0200 Subject: net/mlx5: Fix offsets of ifc reserved fields Fix wrong offsets of reserved fields in ifc file. Issues found using pahole. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 34e17e6f8942..6f64e814cc10 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -349,7 +349,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reformat_l3_tunnel_to_l2[0x1]; u8 reformat_l2_to_l3_tunnel[0x1]; u8 reformat_and_modify_action[0x1]; - u8 reserved_at_14[0xb]; + u8 reserved_at_15[0xb]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; @@ -586,7 +586,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 fdb_multi_path_to_table[0x1]; u8 reserved_at_1d[0x1]; u8 multi_fdb_encap[0x1]; - u8 reserved_at_1e[0x1e1]; + u8 reserved_at_1f[0x1e1]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; @@ -829,7 +829,7 @@ struct mlx5_ifc_vector_calc_cap_bits { struct mlx5_ifc_calc_op calc2; struct mlx5_ifc_calc_op calc3; - u8 reserved_at_e0[0x720]; + u8 reserved_at_c0[0x720]; }; enum { @@ -5567,7 +5567,7 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits { struct mlx5_ifc_modify_nic_vport_field_select_bits { u8 reserved_at_0[0x12]; u8 affiliation[0x1]; - u8 reserved_at_e[0x1]; + u8 reserved_at_13[0x1]; u8 disable_uc_local_lb[0x1]; u8 disable_mc_local_lb[0x1]; u8 node_guid[0x1]; @@ -9028,7 +9028,7 @@ struct mlx5_ifc_dcbx_param_bits { u8 dcbx_cee_cap[0x1]; u8 dcbx_ieee_cap[0x1]; u8 dcbx_standby_cap[0x1]; - u8 reserved_at_0[0x5]; + u8 reserved_at_3[0x5]; u8 port_number[0x8]; u8 reserved_at_10[0xa]; u8 max_application_table_size[6]; -- cgit v1.2.3 From e7946760de5852f32c4e52ce47f37e85346981b9 Mon Sep 17 00:00:00 2001 From: Ivan Khoronzhuk Date: Thu, 8 Nov 2018 22:27:54 +0200 Subject: net: core: dev_addr_lists: add auxiliary func to handle reference address updates In order to avoid all table update, and only remove or add new address, the auxiliary function exists, named __hw_addr_sync_dev(). It allows end driver do nothing when nothing changed and add/rm when concrete address is firstly added or lastly removed. But it doesn't include cases when an address of real device or vlan was reused by other vlans or vlan/macval devices. For handaling events when address was reused/unreused the patch adds new auxiliary routine - __hw_addr_ref_sync_dev(). It allows to do nothing when nothing was changed and do updates only for an address being added/reused/deleted/unreused. Thus, clone address changes for vlans can be mirrored in the table. The function is exclusive with __hw_addr_sync_dev(). It's responsibility of the end driver to identify address vlan device, if it needs so. Signed-off-by: Ivan Khoronzhuk Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 857f8abf7b91..487fa5e0e165 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4068,6 +4068,16 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)); +int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*sync)(struct net_device *, + const unsigned char *, int), + int (*unsync)(struct net_device *, + const unsigned char *, int)); +void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *, int)); void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, -- cgit v1.2.3 From 960abf68d2023f0d0b08c6f5d05971630496cfb0 Mon Sep 17 00:00:00 2001 From: Ivan Khoronzhuk Date: Thu, 8 Nov 2018 22:27:55 +0200 Subject: net: 8021q: vlan_core: allow use list of vlans for real device It's redundancy for the drivers to hold the list of vlans when absolutely the same list exists in vlan core. In most cases it's needed only to traverse the vlan devices, their vids and sync some settings with h/w, so add API to simplify this. At least some of these drivers also can benefit: grep "for_each.*vid" -r drivers/net/ethernet/ drivers/net/ethernet/hisilicon/hns3/hns3_enet.c: drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c: drivers/net/ethernet/qlogic/qlge/qlge_main.c: drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c: drivers/net/ethernet/via/via-rhine.c: drivers/net/ethernet/via/via-velocity.c: drivers/net/ethernet/intel/igb/igb_main.c: drivers/net/ethernet/intel/ice/ice_main.c: drivers/net/ethernet/intel/e1000/e1000_main.c: drivers/net/ethernet/intel/i40e/i40e_main.c: drivers/net/ethernet/intel/e1000e/netdev.c: drivers/net/ethernet/intel/igbvf/netdev.c: drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c: drivers/net/ethernet/intel/ixgb/ixgb_main.c: drivers/net/ethernet/intel/ixgbe/ixgbe_main.c: drivers/net/ethernet/amd/xgbe/xgbe-dev.c: drivers/net/ethernet/emulex/benet/be_main.c: drivers/net/ethernet/neterion/vxge/vxge-main.c: drivers/net/ethernet/adaptec/starfire.c: drivers/net/ethernet/brocade/bna/bnad.c: Reviewed-by: Grygorii Strashko Signed-off-by: Ivan Khoronzhuk Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 03b08ffded07..1be5230921b5 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -133,6 +133,9 @@ struct vlan_pcpu_stats { extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); +extern int vlan_for_each(struct net_device *dev, + int (*action)(struct net_device *dev, int vid, + void *arg), void *arg); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); @@ -236,6 +239,14 @@ __vlan_find_dev_deep_rcu(struct net_device *real_dev, return NULL; } +static inline int +vlan_for_each(struct net_device *dev, + int (*action)(struct net_device *dev, int vid, void *arg), + void *arg) +{ + return 0; +} + static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); -- cgit v1.2.3 From 309ba859b95085f61f4f2a154df6be9cb9713a12 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 11 Jul 2018 14:36:49 -0700 Subject: rcu: Eliminate synchronize_rcu_mult() Now that synchronize_rcu() waits for both RCU read-side critical sections and preempt-disabled regions of code, the sole caller of synchronize_rcu_mult() can be replaced by synchronize_rcu(). This patch makes this change and removes synchronize_rcu_mult(). Note that _wait_rcu_gp() still supports synchronize_rcu_mult(), and thus might be simplified in the future to take only take a single call_rcu() function rather than the current list of them. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_wait.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index 8a16c3eb3dd0..c0578ba23c1a 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -31,21 +31,4 @@ do { \ #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) -/** - * synchronize_rcu_mult - Wait concurrently for multiple grace periods - * @...: List of call_rcu() functions for different grace periods to wait on - * - * This macro waits concurrently for multiple types of RCU grace periods. - * For example, synchronize_rcu_mult(call_rcu, call_rcu_tasks) would wait - * on concurrent RCU and RCU-tasks grace periods. Waiting on a give SRCU - * domain requires you to write a wrapper function for that SRCU domain's - * call_srcu() function, supplying the corresponding srcu_struct. - * - * If Tiny RCU, tell _wait_rcu_gp() does not bother waiting for RCU, - * given that anywhere synchronize_rcu_mult() can be called is automatically - * a grace period. - */ -#define synchronize_rcu_mult(...) \ - _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) - #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */ -- cgit v1.2.3 From f3e763c3e544b73ae5c4a3842cedb9ff6ca37715 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Sep 2018 12:45:45 -0700 Subject: srcu: Fix kernel-doc missing notation Fix kernel-doc warnings for missing parameter descriptions: ../include/linux/srcu.h:175: warning: Function parameter or member 'p' not described in 'srcu_dereference_notrace' ../include/linux/srcu.h:175: warning: Function parameter or member 'sp' not described in 'srcu_dereference_notrace' Fixes: 0b764a6e4e19d ("srcu: Add notrace variant of srcu_dereference") Signed-off-by: Randy Dunlap Cc: Lai Jiangshan Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 67135d4a8a30..ebd5f1511690 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -171,6 +171,9 @@ static inline int srcu_read_lock_held(const struct srcu_struct *sp) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here + * @p: the pointer to fetch and protect for later dereferencing + * @sp: pointer to the srcu_struct, which is used to check that we + * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, sp) srcu_dereference_check((p), (sp), 1) -- cgit v1.2.3 From 144552c786925314c1e7cb8f91a71dae1aca8798 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Thu, 4 Oct 2018 20:24:17 -0700 Subject: of: overlay: add tests to validate kfrees from overlay removal Add checks: - attempted kfree due to refcount reaching zero before overlay is removed - properties linked to an overlay node when the node is removed - node refcount > one during node removal in a changeset destroy, if the node was created by the changeset After applying this patch, several validation warnings will be reported from the devicetree unittest during boot due to pre-existing devicetree bugs. The warnings will be similar to: OF: ERROR: of_node_release(), unexpected properties in /testcase-data/overlay-node/test-bus/test-unittest11 OF: ERROR: memory leak, expected refcount 1 instead of 2, of_node_get()/of_node_put() unbalanced - destroy cset entry: attach overlay node /testcase-data-2/substation@100/ hvac-medium-2 Tested-by: Alan Tull Signed-off-by: Frank Rowand --- include/linux/of.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index a5aee3c438ad..664cd5573ae2 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -138,11 +138,16 @@ extern struct device_node *of_aliases; extern struct device_node *of_stdout; extern raw_spinlock_t devtree_lock; -/* flag descriptions (need to be visible even when !CONFIG_OF) */ -#define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */ -#define OF_DETACHED 2 /* node has been detached from the device tree */ -#define OF_POPULATED 3 /* device already created for the node */ -#define OF_POPULATED_BUS 4 /* of_platform_populate recursed to children of this node */ +/* + * struct device_node flag descriptions + * (need to be visible even when !CONFIG_OF) + */ +#define OF_DYNAMIC 1 /* (and properties) allocated via kmalloc */ +#define OF_DETACHED 2 /* detached from the device tree */ +#define OF_POPULATED 3 /* device already created */ +#define OF_POPULATED_BUS 4 /* platform bus created for children */ +#define OF_OVERLAY 5 /* allocated for an overlay */ +#define OF_OVERLAY_FREE_CSET 6 /* in overlay cset being freed */ #define OF_BAD_ADDR ((u64)-1) -- cgit v1.2.3 From 6f75118800acf77f8ad6afec61ca1b2349ade371 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Thu, 4 Oct 2018 20:32:04 -0700 Subject: of: overlay: validate overlay properties #address-cells and #size-cells If overlay properties #address-cells or #size-cells are already in the live devicetree for any given node, then the values in the overlay must match the values in the live tree. If the properties are already in the live tree then there is no need to create a changeset entry to add them since they must have the same value. This reduces the memory used by the changeset and eliminates a possible memory leak. Tested-by: Alan Tull Signed-off-by: Frank Rowand --- include/linux/of.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 664cd5573ae2..18ac8921e90c 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -990,6 +990,12 @@ static inline int of_map_rid(struct device_node *np, u32 rid, #define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) #endif +static inline int of_prop_val_eq(struct property *p1, struct property *p2) +{ + return p1->length == p2->length && + !memcmp(p1->value, p2->value, (size_t)p1->length); +} + #if defined(CONFIG_OF) && defined(CONFIG_NUMA) extern int of_node_to_nid(struct device_node *np); #else -- cgit v1.2.3 From e647815a4d3b3be9d85b5750ed0f2947fd78fac7 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Thu, 8 Nov 2018 04:08:42 -0500 Subject: bpf: let verifier to calculate and record max_pkt_offset In check_packet_access, update max_pkt_offset after the offset has passed __check_packet_access. It should be safe to use u32 for max_pkt_offset as explained in code comment. Also, when there is tail call, the max_pkt_offset of the called program is unknown, so conservatively set max_pkt_offset to MAX_PACKET_OFF for such case. Reviewed-by: Jakub Kicinski Signed-off-by: Jiong Wang Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 33014ae73103..b6a296e01f6a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -293,6 +293,7 @@ struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; + u32 max_pkt_offset; u32 stack_depth; u32 id; u32 func_cnt; -- cgit v1.2.3 From 801f87469ee8d97af5997ef52188bb0e1908b110 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 Aug 2018 10:48:13 +0200 Subject: netlink: add nl_set_extack_cookie_u64() Add a helper function nl_set_extack_cookie_u64() to use a u64 as the netlink extended ACK cookie, to avoid having to open-code it in any users of the cookie. A u64 should be sufficient for most subsystems though we allow for up to 20 bytes right now. This also matches the cookies in nl80211 where I intend to use this. Signed-off-by: Johannes Berg Acked-by: David S. Miller Signed-off-by: Johannes Berg --- include/linux/netlink.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 4da90a6ab536..0b83dbae0a57 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -110,6 +110,15 @@ struct netlink_ext_ack { } \ } while (0) +static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, + u64 cookie) +{ + u64 __cookie = cookie; + + memcpy(extack->cookie, &__cookie, sizeof(__cookie)); + extack->cookie_len = sizeof(__cookie); +} + extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); -- cgit v1.2.3 From dbdaee7aa6e61f56aac61b71a7807e76f92cc895 Mon Sep 17 00:00:00 2001 From: Bob Copeland Date: Thu, 25 Oct 2018 15:48:53 -0400 Subject: {nl,mac}80211: report gate connectivity in station info Capture the current state of gate connectivity from the mesh formation field in mesh config whenever we receive a beacon, and report that via GET_STATION. This allows applications doing mesh peering in userspace to make peering decisions based on peers' current upstream connectivity. Signed-off-by: Bob Copeland Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0ef67f837ae1..407d6fd66fa9 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -812,6 +812,8 @@ enum mesh_config_capab_flags { IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL = 0x40, }; +#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 + /** * mesh channel switch parameters element's flag indicator * -- cgit v1.2.3 From a4310fa2f24687888ce80fdb0e88583561a23700 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 31 Oct 2018 10:37:46 +0100 Subject: can: dev: can_get_echo_skb(): factor out non sending code to __can_get_echo_skb() This patch factors out all non sending parts of can_get_echo_skb() into a seperate function __can_get_echo_skb(), so that it can be re-used in an upcoming patch. Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index a83e1f632eb7..f01623aef2f7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -169,6 +169,7 @@ void can_change_state(struct net_device *dev, struct can_frame *cf, void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx); +struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); -- cgit v1.2.3 From 55059f2b7f868cd43b3ad30e28e18347e1b46ace Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 18 Sep 2018 11:40:38 +0200 Subject: can: rx-offload: introduce can_rx_offload_get_echo_skb() and can_rx_offload_queue_sorted() functions Current CAN framework can't guarantee proper/chronological order of RX and TX-ECHO messages. To make this possible, drivers should use this functions instead of can_get_echo_skb(). Signed-off-by: Oleksij Rempel Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index cb31683bbe15..01a7c9e5d8d8 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -41,6 +41,10 @@ int can_rx_offload_add_timestamp(struct net_device *dev, struct can_rx_offload * int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight); int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); +int can_rx_offload_queue_sorted(struct can_rx_offload *offload, + struct sk_buff *skb, u32 timestamp); +unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, + unsigned int idx, u32 timestamp); int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb); void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); -- cgit v1.2.3 From 4530ec36bb1e0d24f41c33229694adacda3d5d89 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 18 Sep 2018 11:40:40 +0200 Subject: can: rx-offload: rename can_rx_offload_irq_queue_err_skb() to can_rx_offload_queue_tail() This function has nothing todo with error. Signed-off-by: Oleksij Rempel Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 01a7c9e5d8d8..8268811a697e 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -45,7 +45,8 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp); -int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb); +int can_rx_offload_queue_tail(struct can_rx_offload *offload, + struct sk_buff *skb); void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -- cgit v1.2.3 From 347a28b586802d09604a149c1a1f6de5dccbe6fa Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Tue, 30 Oct 2018 12:35:45 +0100 Subject: writeback: don't decrement wb->refcnt if !wb->bdi This happened while running in qemu-system-aarch64, the AMBA PL011 UART driver when enabling CONFIG_DEBUG_TEST_DRIVER_REMOVE. arch_initcall(pl011_init) came before subsys_initcall(default_bdi_init), devtmpfs' handle_remove() crashes because the reference count is a NULL pointer only because wb->bdi hasn't been initialized yet. Rework so that wb_put have an extra check if wb->bdi before decrement wb->refcnt and also add a WARN_ON_ONCE to get a warning if it happens again in other drivers. Fixes: 52ebea749aae ("writeback: make backing_dev_info host cgroup-specific bdi_writebacks") Co-developed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann Signed-off-by: Anders Roxell Signed-off-by: Greg Kroah-Hartman --- include/linux/backing-dev-defs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 9a6bc0951cfa..c31157135598 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -258,6 +258,14 @@ static inline void wb_get(struct bdi_writeback *wb) */ static inline void wb_put(struct bdi_writeback *wb) { + if (WARN_ON_ONCE(!wb->bdi)) { + /* + * A driver bug might cause a file to be removed before bdi was + * initialized. + */ + return; + } + if (wb != &wb->bdi->wb) percpu_ref_put(&wb->refcnt); } -- cgit v1.2.3 From d6e1935819db0c91ce4a5af82466f3ab50d17346 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 30 Oct 2018 15:11:04 -0700 Subject: serial: core: Allow processing sysrq at port unlock time Right now serial drivers process sysrq keys deep in their character receiving code. This means that they've already grabbed their port->lock spinlock. This can end up getting in the way if we've go to do serial stuff (especially kgdb) in response to the sysrq. Serial drivers have various hacks in them to handle this. Looking at '8250_port.c' you can see that the console_write() skips locking if we're in the sysrq handler. Looking at 'msm_serial.c' you can see that the port lock is dropped around uart_handle_sysrq_char(). It turns out that these hacks aren't exactly perfect. If you have lockdep turned on and use something like the 8250_port hack you'll get a splat that looks like: WARNING: possible circular locking dependency detected [...] is trying to acquire lock: ... (console_owner){-.-.}, at: console_unlock+0x2e0/0x5e4 but task is already holding lock: ... (&port_lock_key){-.-.}, at: serial8250_handle_irq+0x30/0xe4 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&port_lock_key){-.-.}: _raw_spin_lock_irqsave+0x58/0x70 serial8250_console_write+0xa8/0x250 univ8250_console_write+0x40/0x4c console_unlock+0x528/0x5e4 register_console+0x2c4/0x3b0 uart_add_one_port+0x350/0x478 serial8250_register_8250_port+0x350/0x3a8 dw8250_probe+0x67c/0x754 platform_drv_probe+0x58/0xa4 really_probe+0x150/0x294 driver_probe_device+0xac/0xe8 __driver_attach+0x98/0xd0 bus_for_each_dev+0x84/0xc8 driver_attach+0x2c/0x34 bus_add_driver+0xf0/0x1ec driver_register+0xb4/0x100 __platform_driver_register+0x60/0x6c dw8250_platform_driver_init+0x20/0x28 ... -> #0 (console_owner){-.-.}: lock_acquire+0x1e8/0x214 console_unlock+0x35c/0x5e4 vprintk_emit+0x230/0x274 vprintk_default+0x7c/0x84 vprintk_func+0x190/0x1bc printk+0x80/0xa0 __handle_sysrq+0x104/0x21c handle_sysrq+0x30/0x3c serial8250_read_char+0x15c/0x18c serial8250_rx_chars+0x34/0x74 serial8250_handle_irq+0x9c/0xe4 dw8250_handle_irq+0x98/0xcc serial8250_interrupt+0x50/0xe8 ... other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&port_lock_key); lock(console_owner); lock(&port_lock_key); lock(console_owner); *** DEADLOCK *** The hack used in 'msm_serial.c' doesn't cause the above splats but it seems a bit ugly to unlock / lock our spinlock deep in our irq handler. It seems like we could defer processing the sysrq until the end of the interrupt handler right after we've unlocked the port. With this scheme if a whole batch of sysrq characters comes in one irq then we won't handle them all, but that seems like it should be a fine compromise. Signed-off-by: Douglas Anderson Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 047fa67d039b..78de9d929762 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -175,6 +175,7 @@ struct uart_port { struct console *cons; /* struct console, if any */ #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(SUPPORT_SYSRQ) unsigned long sysrq; /* sysrq timeout */ + unsigned int sysrq_ch; /* char for sysrq */ #endif /* flags must be updated while holding port mutex */ @@ -485,8 +486,42 @@ uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) } return 0; } +static inline int +uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) +{ + if (port->sysrq) { + if (ch && time_before(jiffies, port->sysrq)) { + port->sysrq_ch = ch; + port->sysrq = 0; + return 1; + } + port->sysrq = 0; + } + return 0; +} +static inline void +uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) +{ + int sysrq_ch; + + sysrq_ch = port->sysrq_ch; + port->sysrq_ch = 0; + + spin_unlock_irqrestore(&port->lock, irqflags); + + if (sysrq_ch) + handle_sysrq(sysrq_ch); +} #else -#define uart_handle_sysrq_char(port,ch) ({ (void)port; 0; }) +static inline int +uart_handle_sysrq_char(struct uart_port *port, unsigned int ch) { return 0; } +static inline int +uart_prepare_sysrq_char(struct uart_port *port, unsigned int ch) { return 0; } +static inline void +uart_unlock_and_check_sysrq(struct uart_port *port, unsigned long irqflags) +{ + spin_unlock_irqrestore(&port->lock, irqflags); +} #endif /* -- cgit v1.2.3 From 3e6f88068314ffdba61a19f48ab0118f50424348 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 30 Oct 2018 15:11:06 -0700 Subject: serial: core: Include console.h from serial_core.h In the static inline function uart_handle_break() in serial_core.h we dereference port->cons. That gives an error unless console.h is also included. This error hasn't shown up till now because everyone who has defined SUPPORT_SYSRQ has also included console.h, but it's a bit ugly to make this requirement. Let's make the include explicit. Signed-off-by: Douglas Anderson Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 78de9d929762..5fe2b037e833 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -22,6 +22,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From 9d037ad707ed6069fbea4e38e6ee37e027b13f1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 19:37:44 +0100 Subject: block: remove req->timeout_list Unused now that the legacy request path is gone. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9b1f470cc784..dc2a6f625ecb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -228,8 +228,6 @@ struct request { /* access through blk_rq_set_deadline, blk_rq_deadline */ unsigned long __deadline; - struct list_head timeout_list; - union { struct __call_single_data csd; u64 fifo_time; -- cgit v1.2.3 From 4c96499c39e31b5a12f37c2396a5f81d1b6be1ab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 19:39:03 +0100 Subject: USB: remove the unused struct hcd_timeout definition No users of this type anywhere in the tree. Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 97e2ddec18b1..7dc3a411bece 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -235,11 +235,6 @@ static inline struct usb_hcd *bus_to_hcd(struct usb_bus *bus) return container_of(bus, struct usb_hcd, self); } -struct hcd_timeout { /* timeouts we allocate */ - struct list_head timeout_list; - struct timer_list timer; -}; - /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From 1ae367a2451e0b249074461d2d8ac76d8e929a53 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 6 Nov 2018 18:07:37 -0600 Subject: of/pdt: Remove unused of_pdt_build_more function ptr There are no users of of_pdt_build_more since 2012, so remove it. Cc: Frank Rowand Signed-off-by: Rob Herring --- include/linux/of_pdt.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_pdt.h b/include/linux/of_pdt.h index d0b183ab65c6..89e4eb076a01 100644 --- a/include/linux/of_pdt.h +++ b/include/linux/of_pdt.h @@ -35,6 +35,4 @@ extern void *prom_early_alloc(unsigned long size); /* for building the device tree */ extern void of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops); -extern void (*of_pdt_build_more)(struct device_node *dp); - #endif /* _LINUX_OF_PDT_H */ -- cgit v1.2.3 From 86131d933f9a9502d877fb37b90a856e6a8a7ed8 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 5 Nov 2018 15:39:07 +0800 Subject: power: supply: core: Add one field to present the battery internal resistance Add one field for 'struct power_supply_battery_info' to present the battery factory internal resistance. Signed-off-by: Baolin Wang Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index f80769175c56..d089566828be 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -326,6 +326,7 @@ struct power_supply_battery_info { int charge_term_current_ua; /* microAmps */ int constant_charge_current_max_ua; /* microAmps */ int constant_charge_voltage_max_uv; /* microVolts */ + int factory_internal_resistance_uohm; /* microOhms */ }; extern struct atomic_notifier_head power_supply_notifier; -- cgit v1.2.3 From 3afb50d7125bcdbf71df843134e96ceffc78c8b8 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 5 Nov 2018 15:39:09 +0800 Subject: power: supply: core: Add some helpers to use the battery OCV capacity table We have introduced some battery properties to present the OCV table temperatures and OCV capacity table values. Thus this patch add OCV temperature and OCV table for battery information, as well as providing some helper functions to use the OCV capacity table for users. Signed-off-by: Baolin Wang Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index d089566828be..84fe93f674a0 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -309,6 +309,13 @@ struct power_supply_info { int use_for_apm; }; +struct power_supply_battery_ocv_table { + int ocv; /* microVolts */ + int capacity; /* percent */ +}; + +#define POWER_SUPPLY_OCV_TEMP_MAX 20 + /* * This is the recommended struct to manage static battery parameters, * populated by power_supply_get_battery_info(). Most platform drivers should @@ -327,6 +334,9 @@ struct power_supply_battery_info { int constant_charge_current_max_ua; /* microAmps */ int constant_charge_voltage_max_uv; /* microVolts */ int factory_internal_resistance_uohm; /* microOhms */ + int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX];/* celsius */ + struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX]; + int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; }; extern struct atomic_notifier_head power_supply_notifier; @@ -350,6 +360,15 @@ devm_power_supply_get_by_phandle(struct device *dev, const char *property) extern int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); +extern void power_supply_put_battery_info(struct power_supply *psy, + struct power_supply_battery_info *info); +extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, + int table_len, int ocv); +extern struct power_supply_battery_ocv_table * +power_supply_find_ocv2cap_table(struct power_supply_battery_info *info, + int temp, int *table_len); +extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info, + int ocv, int temp); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); extern int power_supply_set_input_current_limit_from_supplier( -- cgit v1.2.3 From 535ac5d3fe63b9ea1dda379f606f9d0d377d7184 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 14:42:35 +0100 Subject: ide: cleanup ->prep_rq calling convention The return value is just used as a binary yes/no decision, so switch it to a bool instead of the old BLKPREP_* values returned as an int. Also clean up a few related comments. Reviewed-by: Bart Van Assche Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/ide.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 079f8bc0b0f4..272704ff21ee 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -529,7 +529,7 @@ struct ide_drive_s { struct request_queue *queue; /* request queue */ - int (*prep_rq)(struct ide_drive_s *, struct request *); + bool (*prep_rq)(struct ide_drive_s *, struct request *); struct blk_mq_tag_set tag_set; -- cgit v1.2.3 From 0e17e06cbf7ede285ab74bab44d888b40c21f828 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 14:42:41 +0100 Subject: block: remove the BLKPREP_* values. Unused now. Reviewed-by: Johannes Thumshirn Reviewed-by: Bart Van Assche Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dc2a6f625ecb..e67ad2dd025e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -776,16 +776,6 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) return q->nr_requests; } -/* - * q->prep_rq_fn return values - */ -enum { - BLKPREP_OK, /* serve it */ - BLKPREP_KILL, /* fatal error, kill, return -EIO */ - BLKPREP_DEFER, /* leave on queue */ - BLKPREP_INVALID, /* invalid command, kill, return -EREMOTEIO */ -}; - extern unsigned long blk_max_low_pfn, blk_max_pfn; /* -- cgit v1.2.3 From 361800876f80da3915c46e388fc682532228b2c3 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 9 Nov 2018 11:14:44 +0100 Subject: ptp: add PTP_SYS_OFFSET_EXTENDED ioctl The PTP_SYS_OFFSET ioctl, which can be used to measure the offset between a PHC and the system clock, includes the total time that the driver needs to read the PHC timestamp. This typically involves reading of multiple PCI registers (sometimes in multiple iterations) and the register that contains the lowest bits of the timestamp is not read in the middle between the two readings of the system clock. This asymmetry causes the measured offset to have a significant error. Introduce a new ioctl, driver function, and helper functions, which allow the reading of the lowest register to be isolated from the other readings in order to reduce the asymmetry. The ioctl returns three timestamps for each measurement: - system time right before reading the lowest bits of the PHC timestamp - PHC time - system time immediately after reading the lowest bits of the PHC timestamp Cc: Richard Cochran Cc: Jacob Keller Cc: Marcelo Tosatti Signed-off-by: Miroslav Lichvar Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 51349d124ee5..a1ec0448e341 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -39,6 +39,15 @@ struct ptp_clock_request { }; struct system_device_crosststamp; + +/** + * struct ptp_system_timestamp - system time corresponding to a PHC timestamp + */ +struct ptp_system_timestamp { + struct timespec64 pre_ts; + struct timespec64 post_ts; +}; + /** * struct ptp_clock_info - decribes a PTP hardware clock * @@ -75,6 +84,14 @@ struct system_device_crosststamp; * @gettime64: Reads the current time from the hardware clock. * parameter ts: Holds the result. * + * @gettimex64: Reads the current time from the hardware clock and optionally + * also the system clock. + * parameter ts: Holds the PHC timestamp. + * parameter sts: If not NULL, it holds a pair of timestamps from + * the system clock. The first reading is made right before + * reading the lowest bits of the PHC timestamp and the second + * reading immediately follows that. + * * @getcrosststamp: Reads the current time from the hardware clock and * system clock simultaneously. * parameter cts: Contains timestamp (device,system) pair, @@ -124,6 +141,8 @@ struct ptp_clock_info { int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*gettimex64)(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts); int (*getcrosststamp)(struct ptp_clock_info *ptp, struct system_device_crosststamp *cts); int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); @@ -247,4 +266,16 @@ static inline int ptp_schedule_worker(struct ptp_clock *ptp, #endif +static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts) +{ + if (sts) + ktime_get_real_ts64(&sts->pre_ts); +} + +static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts) +{ + if (sts) + ktime_get_real_ts64(&sts->post_ts); +} + #endif -- cgit v1.2.3 From 916444df305ef5b8a7d824aac7dd2aeba3a4db3b Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 9 Nov 2018 11:14:45 +0100 Subject: ptp: deprecate gettime64() in favor of gettimex64() When a driver provides gettimex64(), use it in the PTP_SYS_OFFSET ioctl and POSIX clock's gettime() instead of gettime64(). Drivers should provide only one of the functions. Cc: Richard Cochran Cc: Jacob Keller Signed-off-by: Miroslav Lichvar Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index a1ec0448e341..7121bbe76979 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -82,6 +82,8 @@ struct ptp_system_timestamp { * parameter delta: Desired change in nanoseconds. * * @gettime64: Reads the current time from the hardware clock. + * This method is deprecated. New drivers should implement + * the @gettimex64 method instead. * parameter ts: Holds the result. * * @gettimex64: Reads the current time from the hardware clock and optionally -- cgit v1.2.3 From 695bce8fd8e994999f40ee279e2fa9979cbae87a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 9 Nov 2018 18:35:52 +0100 Subject: net: phy: improve struct phy_device member interrupts handling As a heritage from the very early days of phylib member interrupts is defined as u32 even though it's just a flag whether interrupts are enabled. So we can change it to a bitfield member. In addition change the code dealing with this member in a way that it's clear we're dealing with a bool value. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2090277eac4f..3299ec6e69f3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -263,8 +263,8 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); -#define PHY_INTERRUPT_DISABLED 0x0 -#define PHY_INTERRUPT_ENABLED 0x80000000 +#define PHY_INTERRUPT_DISABLED false +#define PHY_INTERRUPT_ENABLED true /* PHY state machine states: * @@ -410,6 +410,9 @@ struct phy_device { /* The most recently read link state */ unsigned link:1; + /* Interrupts are enabled */ + unsigned interrupts:1; + enum phy_state state; u32 dev_flags; @@ -425,9 +428,6 @@ struct phy_device { int pause; int asym_pause; - /* Enabled Interrupts */ - u32 interrupts; - /* Union of PHY and Attached devices' supported modes */ /* See mii.h for more info */ u32 supported; -- cgit v1.2.3 From 457937bd2e8e70d3a37eee3eaa45d86d169a6762 Mon Sep 17 00:00:00 2001 From: Kyle Roeschley Date: Fri, 9 Nov 2018 12:48:03 -0600 Subject: net: phy: leds: Don't make our own link speed names The phy core provides a handy phy_speed_to_str() helper, so use that instead of doing our own formatting of the different known link speeds. To do this, increase PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE to 11 so we can fit 'Unsupported' if necessary. Signed-off-by: Kyle Roeschley Signed-off-by: David S. Miller --- include/linux/phy_led_triggers.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h index b37b05bfd1a6..4587ce362535 100644 --- a/include/linux/phy_led_triggers.h +++ b/include/linux/phy_led_triggers.h @@ -20,7 +20,7 @@ struct phy_device; #include #include -#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10 +#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 11 #define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \ FIELD_SIZEOF(struct mdio_device, addr)+\ -- cgit v1.2.3 From 22ce0a7ccf23d55d1fdaa2974002f8b5ae765665 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 10 Nov 2018 09:30:49 +0100 Subject: ide: don't use req->special Just replace it with a field of the same name in struct ide_req. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 272704ff21ee..e7d29ae633cd 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -50,6 +50,7 @@ struct ide_request { struct scsi_request sreq; u8 sense[SCSI_SENSE_BUFFERSIZE]; u8 type; + void *special; }; static inline struct ide_request *ide_req(struct request *rq) -- cgit v1.2.3 From 1385d755cfb42f596ef1cf9f5c761010ff3b34e7 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 9 Nov 2018 13:03:25 +0000 Subject: bpf: pass a struct with offload callbacks to bpf_offload_dev_create() For passing device functions for offloaded eBPF programs, there used to be no place where to store the pointer without making the non-offloaded programs pay a memory price. As a consequence, three functions were called with ndo_bpf() through specific commands. Now that we have struct bpf_offload_dev, and since none of those operations rely on RTNL, we can turn these three commands into hooks inside the struct bpf_prog_offload_ops, and pass them as part of bpf_offload_dev_create(). This commit effectively passes a pointer to the struct to bpf_offload_dev_create(). We temporarily have two struct bpf_prog_offload_ops instances, one under offdev->ops and one under offload->dev_ops. The next patches will make the transition towards the former, so that offload->dev_ops can be removed, and callbacks relying on ndo_bpf() added to offdev->ops as well. While at it, rename "nfp_bpf_analyzer_ops" as "nfp_bpf_dev_ops" (and similarly for netdevsim). Suggested-by: Jakub Kicinski Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b6a296e01f6a..c0197c37b2b2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -692,7 +692,8 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); -struct bpf_offload_dev *bpf_offload_dev_create(void); +struct bpf_offload_dev * +bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); -- cgit v1.2.3 From 341b3e7b7b89315c43d262da3199098bcf9bbe57 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 9 Nov 2018 13:03:26 +0000 Subject: bpf: call verify_insn from its callback in struct bpf_offload_dev We intend to remove the dev_ops in struct bpf_prog_offload, and to only keep the ops in struct bpf_offload_dev instead, which is accessible from more locations for passing function pointers. But dev_ops is used for calling the verify_insn hook. Switch to the newly added ops in struct bpf_prog_offload instead. To avoid table lookups for each eBPF instruction to verify, we remember the offdev attached to a netdev and modify bpf_offload_find_netdev() to avoid performing more than once a lookup for a given offload object. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c0197c37b2b2..672714cd904f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -273,6 +273,7 @@ struct bpf_prog_offload_ops { struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; + struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; -- cgit v1.2.3 From 00db12c3d141356a4d1e6b6f688e0d5ed3b1f757 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 9 Nov 2018 13:03:28 +0000 Subject: bpf: call verifier_prep from its callback in struct bpf_offload_dev In a way similar to the change previously brought to the verify_insn hook and to the finalize callback, switch to the newly added ops in struct bpf_prog_offload for calling the functions used to prepare driver verifiers. Since the dev_ops pointer in struct bpf_prog_offload is no longer used by any callback, we can now remove it from struct bpf_prog_offload. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- include/linux/netdevice.h | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 672714cd904f..f250494a4f56 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -268,6 +268,7 @@ struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); + int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env); }; struct bpf_prog_offload { @@ -277,7 +278,6 @@ struct bpf_prog_offload { void *dev_priv; struct list_head offloads; bool dev_state; - const struct bpf_prog_offload_ops *dev_ops; void *jited_image; u32 jited_len; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 857f8abf7b91..0fa2c2744928 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -863,7 +863,6 @@ enum bpf_netdev_command { XDP_QUERY_PROG, XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ - BPF_OFFLOAD_VERIFIER_PREP, BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, @@ -891,11 +890,6 @@ struct netdev_bpf { /* flags with which program was installed */ u32 prog_flags; }; - /* BPF_OFFLOAD_VERIFIER_PREP */ - struct { - struct bpf_prog *prog; - const struct bpf_prog_offload_ops *ops; /* callee set */ - } verifier; /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */ struct { struct bpf_prog *prog; -- cgit v1.2.3 From b07ade27e93360197e453e5ca80eebdc9099dcb5 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 9 Nov 2018 13:03:29 +0000 Subject: bpf: pass translate() as a callback and remove its ndo_bpf subcommand As part of the transition from ndo_bpf() to callbacks attached to struct bpf_offload_dev for some of the eBPF offload operations, move the functions related to code translation to the struct and remove the subcommand that was used to call them through the NDO. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/netdevice.h | 3 +-- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f250494a4f56..d1eb3c8a3fa9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -269,6 +269,7 @@ struct bpf_prog_offload_ops { int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env); + int (*translate)(struct net_device *netdev, struct bpf_prog *prog); }; struct bpf_prog_offload { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0fa2c2744928..27499127e038 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -863,7 +863,6 @@ enum bpf_netdev_command { XDP_QUERY_PROG, XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ - BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, @@ -890,7 +889,7 @@ struct netdev_bpf { /* flags with which program was installed */ u32 prog_flags; }; - /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */ + /* BPF_OFFLOAD_DESTROY */ struct { struct bpf_prog *prog; } offload; -- cgit v1.2.3 From eb9119471efbf730c8f830f706026b486eb701dd Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 9 Nov 2018 13:03:30 +0000 Subject: bpf: pass destroy() as a callback and remove its ndo_bpf subcommand As part of the transition from ndo_bpf() to callbacks attached to struct bpf_offload_dev for some of the eBPF offload operations, move the functions related to program destruction to the struct and remove the subcommand that was used to call them through the NDO. Remove function __bpf_offload_ndo(), which is no longer used. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/netdevice.h | 5 ----- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d1eb3c8a3fa9..867d2801db64 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -270,6 +270,7 @@ struct bpf_prog_offload_ops { int (*finalize)(struct bpf_verifier_env *env); int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env); int (*translate)(struct net_device *netdev, struct bpf_prog *prog); + void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 27499127e038..17d52a647fe5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -863,7 +863,6 @@ enum bpf_netdev_command { XDP_QUERY_PROG, XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ - BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, XDP_QUERY_XSK_UMEM, @@ -889,10 +888,6 @@ struct netdev_bpf { /* flags with which program was installed */ u32 prog_flags; }; - /* BPF_OFFLOAD_DESTROY */ - struct { - struct bpf_prog *prog; - } offload; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; -- cgit v1.2.3 From a40a26322a83d4a26a99ad2616cbd77394c19587 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 9 Nov 2018 13:03:31 +0000 Subject: bpf: pass prog instead of env to bpf_prog_offload_verifier_prep() Function bpf_prog_offload_verifier_prep(), called from the kernel BPF verifier to run a driver-specific callback for preparing for the verification step for offloaded programs, takes a pointer to a struct bpf_verifier_env object. However, no driver callback needs the whole structure at this time: the two drivers supporting this, nfp and netdevsim, only need a pointer to the struct bpf_prog instance held by env. Update the callback accordingly, on kernel side and in these two drivers. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- include/linux/bpf_verifier.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 867d2801db64..888111350d0e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -268,7 +268,7 @@ struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); - int (*prepare)(struct net_device *netdev, struct bpf_verifier_env *env); + int (*prepare)(struct net_device *netdev, struct bpf_prog *prog); int (*translate)(struct net_device *netdev, struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d93e89761a8b..11f5df1092d9 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -245,7 +245,7 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) return cur_func(env)->regs; } -int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); +int bpf_prog_offload_verifier_prep(struct bpf_prog *prog); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int bpf_prog_offload_finalize(struct bpf_verifier_env *env); -- cgit v1.2.3 From 16a8cb5cffd0a2929ae97bc258d2d9c92a4e7f6d Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Fri, 9 Nov 2018 13:03:32 +0000 Subject: bpf: do not pass netdev to translate() and prepare() offload callbacks The kernel functions to prepare verifier and translate for offloaded program retrieve "offload" from "prog", and "netdev" from "offload". Then both "prog" and "netdev" are passed to the callbacks. Simplify this by letting the drivers retrieve the net device themselves from the offload object attached to prog - if they need it at all. There is currently no need to pass the netdev as an argument to those functions. Signed-off-by: Quentin Monnet Reviewed-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 888111350d0e..987815152629 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -268,8 +268,8 @@ struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); - int (*prepare)(struct net_device *netdev, struct bpf_prog *prog); - int (*translate)(struct net_device *netdev, struct bpf_prog *prog); + int (*prepare)(struct bpf_prog *prog); + int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); }; -- cgit v1.2.3 From 46f53a65d2de3e1591636c22b626b09d8684fd71 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Sat, 10 Nov 2018 22:15:13 -0800 Subject: bpf: Allow narrow loads with offset > 0 Currently BPF verifier allows narrow loads for a context field only with offset zero. E.g. if there is a __u32 field then only the following loads are permitted: * off=0, size=1 (narrow); * off=0, size=2 (narrow); * off=0, size=4 (full). On the other hand LLVM can generate a load with offset different than zero that make sense from program logic point of view, but verifier doesn't accept it. E.g. tools/testing/selftests/bpf/sendmsg4_prog.c has code: #define DST_IP4 0xC0A801FEU /* 192.168.1.254 */ ... if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) && where ctx is struct bpf_sock_addr. Some versions of LLVM can produce the following byte code for it: 8: 71 12 07 00 00 00 00 00 r2 = *(u8 *)(r1 + 7) 9: 67 02 00 00 18 00 00 00 r2 <<= 24 10: 18 03 00 00 00 00 00 fe 00 00 00 00 00 00 00 00 r3 = 4261412864 ll 12: 5d 32 07 00 00 00 00 00 if r2 != r3 goto +7 where `*(u8 *)(r1 + 7)` means narrow load for ctx->user_ip4 with size=1 and offset=3 (7 - sizeof(ctx->user_family) = 3). This load is currently rejected by verifier. Verifier code that rejects such loads is in bpf_ctx_narrow_access_ok() what means any is_valid_access implementation, that uses the function, works this way, e.g. bpf_skb_is_valid_access() for __sk_buff or sock_addr_is_valid_access() for bpf_sock_addr. The patch makes such loads supported. Offset can be in [0; size_default) but has to be multiple of load size. E.g. for __u32 field the following loads are supported now: * off=0, size=1 (narrow); * off=1, size=1 (narrow); * off=2, size=1 (narrow); * off=3, size=1 (narrow); * off=0, size=2 (narrow); * off=2, size=2 (narrow); * off=0, size=4 (full). Reported-by: Yonghong Song Signed-off-by: Andrey Ignatov Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index de629b706d1d..cc17f5f32fbb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -668,24 +668,10 @@ static inline u32 bpf_ctx_off_adjust_machine(u32 size) return size; } -static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access, - u32 size_default) -{ - size_default = bpf_ctx_off_adjust_machine(size_default); - size_access = bpf_ctx_off_adjust_machine(size_access); - -#ifdef __LITTLE_ENDIAN - return (off & (size_default - 1)) == 0; -#else - return (off & (size_default - 1)) + size_access == size_default; -#endif -} - static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { - return bpf_ctx_narrow_align_ok(off, size, size_default) && - size <= size_default && (size & (size - 1)) == 0; + return size <= size_default && (size & (size - 1)) == 0; } #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -- cgit v1.2.3 From 9be92baa4772a315ff258f59d87a8427d5015a7c Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 8 Nov 2018 06:32:44 +0000 Subject: dmaengine: sh: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto Signed-off-by: Vinod Koul --- include/linux/shdma-base.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shdma-base.h b/include/linux/shdma-base.h index d927647e6350..6dfd05ef5c2d 100644 --- a/include/linux/shdma-base.h +++ b/include/linux/shdma-base.h @@ -1,4 +1,5 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * Dmaengine driver base library for DMA controllers, found on SH-based SoCs * * extracted from shdma.c and headers @@ -7,10 +8,6 @@ * Copyright (C) 2009 Nobuhiro Iwamatsu * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved. * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved. - * - * This is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. */ #ifndef SHDMA_BASE_H -- cgit v1.2.3 From bc822e80170d672dd8ff0d07c521cf72f491cb6c Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 6 Nov 2018 13:45:10 +0000 Subject: dmaengine: sa11x0: unexport sa11x0_dma_filter_fn and clean up As we now have no users of sa11x0_dma_filter_fn() in the tree, we can unexport this function, and remove the now unused header file. Signed-off-by: Russell King Signed-off-by: Vinod Koul --- include/linux/sa11x0-dma.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/sa11x0-dma.h (limited to 'include/linux') diff --git a/include/linux/sa11x0-dma.h b/include/linux/sa11x0-dma.h deleted file mode 100644 index 65839a58b8e5..000000000000 --- a/include/linux/sa11x0-dma.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * SA11x0 DMA Engine support - * - * Copyright (C) 2012 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef __LINUX_SA11X0_DMA_H -#define __LINUX_SA11X0_DMA_H - -struct dma_chan; - -#if defined(CONFIG_DMA_SA11X0) || defined(CONFIG_DMA_SA11X0_MODULE) -bool sa11x0_dma_filter_fn(struct dma_chan *, void *); -#else -static inline bool sa11x0_dma_filter_fn(struct dma_chan *c, void *d) -{ - return false; -} -#endif - -#endif -- cgit v1.2.3 From a4307c0ec66131e722a8fa0f1da09646c46ee924 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 9 Nov 2018 18:17:22 +0100 Subject: net: phy: remove flag PHY_HAS_INTERRUPT from driver configs Now that flag PHY_HAS_INTERRUPT has been replaced with a check for callbacks config_intr and ack_interrupt, we can remove setting this flag from all driver configs. Last but not least remove flag PHY_HAS_INTERRUPT completely. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3299ec6e69f3..59bb31ee132f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -66,9 +66,8 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_POLL -1 #define PHY_IGNORE_INTERRUPT -2 -#define PHY_HAS_INTERRUPT 0x00000001 -#define PHY_IS_INTERNAL 0x00000002 -#define PHY_RST_AFTER_CLK_EN 0x00000004 +#define PHY_IS_INTERNAL 0x00000001 +#define PHY_RST_AFTER_CLK_EN 0x00000002 #define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ -- cgit v1.2.3 From 8deeb6309cc447b9b35939558f18e2164dd110df Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 9 Nov 2018 18:55:50 +0100 Subject: net: phy: don't set state PHY_CHANGELINK in phy_change State PHY_CHANGELINK isn't needed here, we can call the state machine directly. We just have to remove the check for phy_polling_mode() to make this work also in interrupt mode. Removing this check doesn't cause any overhead because when not polling the state machine is called only if required by some event. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 59bb31ee132f..7db07e69c88f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -298,7 +298,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * - timer moves to NOLINK or RUNNING * * NOLINK: PHY is up, but not currently plugged in. - * - If the timer notes that the link comes back, we move to RUNNING + * - irq or timer will set RUNNING if link comes back * - phy_stop moves to HALTED * * FORCING: PHY is being configured with forced settings @@ -309,10 +309,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * * RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets - * - timer will set CHANGELINK if we're polling (this ensures the - * link state is polled every other cycle of this state machine, - * which makes it every other second) - * - irq will set CHANGELINK + * - irq or timer will set NOLINK if link goes down * - phy_stop moves to HALTED * * CHANGELINK: PHY experienced a change in link state -- cgit v1.2.3 From d73a2156bdad6bdf7e0c42051c5ebbea11f6271e Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 9 Nov 2018 18:56:52 +0100 Subject: net: phy: simplify phy_mac_interrupt and related functions When using phy_mac_interrupt() the irq number is set to PHY_IGNORE_INTERRUPT, therefore phy_interrupt_is_valid() returns false. As a result phy_change() effectively just calls phy_trigger_machine() when called from phy_mac_interrupt() via phy_change_work(). So we can call phy_trigger_machine() from phy_mac_interrupt() directly and remove some now unneeded code. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 7db07e69c88f..17d1f64723e4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -369,7 +369,6 @@ struct phy_c45_device_ids { * giving up on the current attempt at acquiring a link * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine - * phy_queue: A work_queue for the phy_mac_interrupt * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. @@ -454,7 +453,6 @@ struct phy_device { void *priv; /* Interrupt and Polling infrastructure */ - struct work_struct phy_queue; struct delayed_work state_queue; struct mutex lock; @@ -1029,7 +1027,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); -void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -- cgit v1.2.3 From aa2af2eb447c9a21c8c9e8d2336672bb620cf900 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 10 Nov 2018 00:39:14 +0100 Subject: net: phy: add macros for PHYID matching Add macros for PHYID matching to be used in PHY driver configs. By using these macros some boilerplate code can be avoided. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 17d1f64723e4..03005c65e02d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -651,6 +651,10 @@ struct phy_driver { #define PHY_ANY_ID "MATCH ANY PHY" #define PHY_ANY_UID 0xffffffff +#define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) +#define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) +#define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) + /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; -- cgit v1.2.3 From 899a3cbbf77a2a3d6d53d67ff6f10ad59eb03605 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 10 Nov 2018 23:40:50 +0100 Subject: net: phy: remove states PHY_STARTING and PHY_PENDING Both states aren't used. Most likely they result from an idea that never materialized. So remove them. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 03005c65e02d..a5bcb4aaa48e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -270,29 +270,13 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); * DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. - * - PHY driver probe function will, depending on the PHY, set - * the state to STARTING or READY - * - * STARTING: PHY device is coming up, and the ethernet driver is - * not ready. PHY drivers may set this in the probe function. - * If they do, they are responsible for making sure the state is - * eventually set to indicate whether the PHY is UP or READY, - * depending on the state when the PHY is done starting up. - * - PHY driver will set the state to READY - * - start will set the state to PENDING + * - PHY driver probe function will set the state to READY * * READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement - * probe will be set to this state by phy_probe(). If the PHY - * driver knows the PHY is ready, and the PHY state is STARTING, - * then it sets this STATE. + * probe will be set to this state by phy_probe(). * - start will set the state to UP * - * PENDING: PHY device is coming up, but the ethernet driver is - * ready. phy_start will set this state if the PHY state is - * STARTING. - * - PHY driver will set the state to UP when the PHY is ready - * * UP: The PHY and attached device are ready to do work. * Interrupts should be started here. * - timer moves to NOLINK or RUNNING @@ -329,9 +313,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); */ enum phy_state { PHY_DOWN = 0, - PHY_STARTING, PHY_READY, - PHY_PENDING, PHY_UP, PHY_RUNNING, PHY_NOLINK, -- cgit v1.2.3 From 3c1bcc8614db10803f1f57ef0295363917448cb2 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 10 Nov 2018 23:43:33 +0100 Subject: net: ethernet: Convert phydev advertize and supported from u32 to link mode There are a few MAC/PHYs combinations which now support > 1Gbps. These may need to make use of link modes with bits > 31. Thus their supported PHY features or advertised features cannot be implemented using the current bitmap in a u32. Convert to using a linkmode bitmap, which can support all the currently devices link modes, and is future proof as more modes are added. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii.h | 14 ++++++++------ include/linux/phy.h | 18 ++++++++++++------ 2 files changed, 20 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 2da85b02e1c0..aaa458bbef2a 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -385,19 +385,21 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, } /** - * ethtool_adv_to_lcl_adv_t - * @advertising:pointer to ethtool advertising + * linkmode_adv_to_lcl_adv_t + * @advertising:pointer to linkmode advertising * - * A small helper function that translates ethtool advertising to LVL + * A small helper function that translates linkmode advertising to LVL * pause capabilities. */ -static inline u32 ethtool_adv_to_lcl_adv_t(u32 advertising) +static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) { u32 lcl_adv = 0; - if (advertising & ADVERTISED_Pause) + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + advertising)) lcl_adv |= ADVERTISE_PAUSE_CAP; - if (advertising & ADVERTISED_Asym_Pause) + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + advertising)) lcl_adv |= ADVERTISE_PAUSE_ASYM; return lcl_adv; diff --git a/include/linux/phy.h b/include/linux/phy.h index a5bcb4aaa48e..cbc66ac3b560 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -58,6 +58,11 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) +extern const int phy_10_100_features_array[4]; +extern const int phy_basic_t1_features_array[2]; +extern const int phy_gbit_features_array[2]; +extern const int phy_10gbit_features_array[1]; + /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_IGNORE_INTERRUPT if @@ -405,10 +410,11 @@ struct phy_device { int pause; int asym_pause; - /* Union of PHY and Attached devices' supported modes */ - /* See mii.h for more info */ - u32 supported; - u32 advertising; + /* Union of PHY and Attached devices' supported link modes */ + /* See ethtool.h for more info */ + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + u32 lp_advertising; /* Energy efficient ethernet modes which should be prohibited */ @@ -660,9 +666,9 @@ struct phy_setting { const struct phy_setting * phy_lookup_setting(int speed, int duplex, const unsigned long *mask, - size_t maxbit, bool exact); + bool exact); size_t phy_speeds(unsigned int *speeds, size_t size, - unsigned long *mask, size_t maxbit); + unsigned long *mask); void phy_resolve_aneg_linkmode(struct phy_device *phydev); -- cgit v1.2.3 From c0ec3c2736774c69bf5c641aea7712132c0f0eba Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 10 Nov 2018 23:43:34 +0100 Subject: net: phy: Convert u32 phydev->lp_advertising to linkmode Convert phy drivers to report the link partner advertised modes using a linkmode bitmap. This allows them to report the higher speeds which don't fit in a u32. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii.h | 36 ++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 3 +-- 2 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index aaa458bbef2a..e7112e878bb0 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -287,6 +287,25 @@ static inline u32 mii_stat1000_to_ethtool_lpa_t(u32 lpa) return result; } +/** + * mii_stat1000_to_linkmode_lpa_t + * @advertising: target the linkmode advertisement settings + * @adv: value of the MII_STAT1000 register + * + * A small helper function that translates MII_STAT1000 bits, when in + * 1000Base-T mode, to linkmode advertisement settings. + */ +static inline void mii_stat1000_to_linkmode_lpa_t(unsigned long *advertising, + u32 lpa) +{ + if (lpa & LPA_1000HALF) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + advertising); + if (lpa & LPA_1000FULL) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + advertising); +} + /** * ethtool_adv_to_mii_adv_x * @ethadv: the ethtool advertisement settings @@ -384,6 +403,23 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); } +/** + * mii_lpa_to_linkmode_lpa_t + * @adv: value of the MII_LPA register + * + * A small helper function that translates MII_LPA bits, when in + * 1000Base-T mode, to linkmode LP advertisement settings. + */ +static inline void mii_lpa_to_linkmode_lpa_t(unsigned long *lp_advertising, + u32 lpa) +{ + if (lpa & LPA_LPACK) + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lp_advertising); + + mii_adv_to_linkmode_adv_t(lp_advertising, lpa); +} + /** * linkmode_adv_to_lcl_adv_t * @advertising:pointer to linkmode advertising diff --git a/include/linux/phy.h b/include/linux/phy.h index cbc66ac3b560..8f927246acdb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -414,8 +414,7 @@ struct phy_device { /* See ethtool.h for more info */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); - - u32 lp_advertising; + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; -- cgit v1.2.3 From fe1919147c69c3b820f801eb99bcc50cec0fb5a5 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 10 Nov 2018 23:43:35 +0100 Subject: net: phy: Fixup kerneldoc markup. Add missing markup for function parameters Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index e7112e878bb0..fb7ae4ae8ce3 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -209,7 +209,7 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) /** * linkmode_adv_to_mii_ctrl1000_t - * advertising: the linkmode advertisement settings + * @advertising: the linkmode advertisement settings * * A small helper function that translates linkmode advertisement * settings to phy autonegotiation advertisements for the -- cgit v1.2.3 From 9206eb0bc5679d06d2f54b9db86fe2b9a55e07e4 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 11 Nov 2018 20:31:21 +0100 Subject: PCI: add USR vendor id and use it in r8169 and w6692 driver The PCI vendor id of U.S. Robotics isn't defined in pci_ids.h so far, only ISDN driver w6692 has a private definition. Move the definition to pci_ids.h and use it in the r8169 driver too. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 69f0abe1ba1a..144de2e89531 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2359,6 +2359,8 @@ #define PCI_VENDOR_ID_SYNOPSYS 0x16c3 +#define PCI_VENDOR_ID_USR 0x16ec + #define PCI_VENDOR_ID_VITESSE 0x1725 #define PCI_DEVICE_ID_VITESSE_VSC7174 0x7174 -- cgit v1.2.3 From d19f9130b814d33c03118493c17454f7d90075d1 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sat, 10 Nov 2018 04:22:09 +0100 Subject: x86/ptrace: Fix documentation for tracehook_report_syscall_entry() tracehook_report_syscall_entry() is called not only if %TIF_SYSCALL_TRACE is set, but also if %TIF_SYSCALL_EMU is set, as appears from x86's entry code. Signed-off-by: Elvira Khabirova Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: ldv@altlinux.org Cc: oleg@redhat.com Cc: rostedt@goodmis.org Link: http://lkml.kernel.org/r/20181110042209.26333972@akathisia Signed-off-by: Ingo Molnar --- include/linux/tracehook.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 40b0b4c1bf7b..df20f8bdbfa3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -83,8 +83,8 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * - * This will be called if %TIF_SYSCALL_TRACE has been set, when the - * current task has just entered the kernel for a system call. + * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, + * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. -- cgit v1.2.3 From 3a379bbcea0af6280e1ca0d1edfcf4e68cde6ee0 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 19 Jul 2017 11:52:29 +0200 Subject: i3c: Add core I3C infrastructure Add core infrastructure to support I3C in Linux and document it. This infrastructure adds basic I3C support. Advanced features will be added afterwards. There are a few design choices that are worth mentioning because they impact the way I3C device drivers can interact with their devices: - all functions used to send I3C/I2C frames must be called in non-atomic context. Mainly done this way to ease implementation, but this is not set in stone, and if anyone needs async support, new functions can be added later on. - the bus element is a separate object, but it's tightly coupled with the master object. We thus have a 1:1 relationship between i3c_bus and i3c_master_controller objects, and if 2 master controllers are connected to the same bus and both exposed to the same Linux instance they will appear as two distinct busses, and devices on this bus will be exposed twice. - I2C backward compatibility has been designed to be transparent to I2C drivers and the I2C subsystem. The I3C master just registers an I2C adapter which creates a new I2C bus. I'd say that, from a representation PoV it's not ideal because what should appear as a single I3C bus exposing I3C and I2C devices here appears as 2 different buses connected to each other through the parenting (the I3C master is the parent of the I2C and I3C busses). On the other hand, I don't see a better solution if we want something that is not invasive. Missing features: - I3C HDR modes are not supported - no support for multi-master and the associated concepts (mastership handover, support for secondary masters, ...) - I2C devices can only be described using DT because this is the only use case I have. However, the framework can easily be extended with ACPI and board info support - I3C slave framework. This has been completely omitted, but shouldn't have a huge impact on the I3C framework because I3C slaves don't see the whole bus, it's only about handling master requests and generating IBIs. Some of the struct, constant and enum definitions could be shared, but most of the I3C slave framework logic will be different Signed-off-by: Boris Brezillon Reviewed-by: Arnd Bergmann Acked-by: Greg Kroah-Hartman --- include/linux/i3c/ccc.h | 385 ++++++++++++++++++++++++ include/linux/i3c/device.h | 331 ++++++++++++++++++++ include/linux/i3c/master.h | 648 ++++++++++++++++++++++++++++++++++++++++ include/linux/mod_devicetable.h | 17 ++ 4 files changed, 1381 insertions(+) create mode 100644 include/linux/i3c/ccc.h create mode 100644 include/linux/i3c/device.h create mode 100644 include/linux/i3c/master.h (limited to 'include/linux') diff --git a/include/linux/i3c/ccc.h b/include/linux/i3c/ccc.h new file mode 100644 index 000000000000..73b0982cc519 --- /dev/null +++ b/include/linux/i3c/ccc.h @@ -0,0 +1,385 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Cadence Design Systems Inc. + * + * Author: Boris Brezillon + */ + +#ifndef I3C_CCC_H +#define I3C_CCC_H + +#include +#include + +/* I3C CCC (Common Command Codes) related definitions */ +#define I3C_CCC_DIRECT BIT(7) + +#define I3C_CCC_ID(id, broadcast) \ + ((id) | ((broadcast) ? 0 : I3C_CCC_DIRECT)) + +/* Commands valid in both broadcast and unicast modes */ +#define I3C_CCC_ENEC(broadcast) I3C_CCC_ID(0x0, broadcast) +#define I3C_CCC_DISEC(broadcast) I3C_CCC_ID(0x1, broadcast) +#define I3C_CCC_ENTAS(as, broadcast) I3C_CCC_ID(0x2 + (as), broadcast) +#define I3C_CCC_RSTDAA(broadcast) I3C_CCC_ID(0x6, broadcast) +#define I3C_CCC_SETMWL(broadcast) I3C_CCC_ID(0x9, broadcast) +#define I3C_CCC_SETMRL(broadcast) I3C_CCC_ID(0xa, broadcast) +#define I3C_CCC_SETXTIME(broadcast) ((broadcast) ? 0x28 : 0x98) +#define I3C_CCC_VENDOR(id, broadcast) ((id) + ((broadcast) ? 0x61 : 0xe0)) + +/* Broadcast-only commands */ +#define I3C_CCC_ENTDAA I3C_CCC_ID(0x7, true) +#define I3C_CCC_DEFSLVS I3C_CCC_ID(0x8, true) +#define I3C_CCC_ENTTM I3C_CCC_ID(0xb, true) +#define I3C_CCC_ENTHDR(x) I3C_CCC_ID(0x20 + (x), true) + +/* Unicast-only commands */ +#define I3C_CCC_SETDASA I3C_CCC_ID(0x7, false) +#define I3C_CCC_SETNEWDA I3C_CCC_ID(0x8, false) +#define I3C_CCC_GETMWL I3C_CCC_ID(0xb, false) +#define I3C_CCC_GETMRL I3C_CCC_ID(0xc, false) +#define I3C_CCC_GETPID I3C_CCC_ID(0xd, false) +#define I3C_CCC_GETBCR I3C_CCC_ID(0xe, false) +#define I3C_CCC_GETDCR I3C_CCC_ID(0xf, false) +#define I3C_CCC_GETSTATUS I3C_CCC_ID(0x10, false) +#define I3C_CCC_GETACCMST I3C_CCC_ID(0x11, false) +#define I3C_CCC_SETBRGTGT I3C_CCC_ID(0x13, false) +#define I3C_CCC_GETMXDS I3C_CCC_ID(0x14, false) +#define I3C_CCC_GETHDRCAP I3C_CCC_ID(0x15, false) +#define I3C_CCC_GETXTIME I3C_CCC_ID(0x19, false) + +#define I3C_CCC_EVENT_SIR BIT(0) +#define I3C_CCC_EVENT_MR BIT(1) +#define I3C_CCC_EVENT_HJ BIT(3) + +/** + * struct i3c_ccc_events - payload passed to ENEC/DISEC CCC + * + * @events: bitmask of I3C_CCC_EVENT_xxx events. + * + * Depending on the CCC command, the specific events coming from all devices + * (broadcast version) or a specific device (unicast version) will be + * enabled (ENEC) or disabled (DISEC). + */ +struct i3c_ccc_events { + u8 events; +}; + +/** + * struct i3c_ccc_mwl - payload passed to SETMWL/GETMWL CCC + * + * @len: maximum write length in bytes + * + * The maximum write length is only applicable to SDR private messages or + * extended Write CCCs (like SETXTIME). + */ +struct i3c_ccc_mwl { + __be16 len; +}; + +/** + * struct i3c_ccc_mrl - payload passed to SETMRL/GETMRL CCC + * + * @len: maximum read length in bytes + * @ibi_len: maximum IBI payload length + * + * The maximum read length is only applicable to SDR private messages or + * extended Read CCCs (like GETXTIME). + * The IBI length is only valid if the I3C slave is IBI capable + * (%I3C_BCR_IBI_REQ_CAP is set). + */ +struct i3c_ccc_mrl { + __be16 read_len; + u8 ibi_len; +} __packed; + +/** + * struct i3c_ccc_dev_desc - I3C/I2C device descriptor used for DEFSLVS + * + * @dyn_addr: dynamic address assigned to the I3C slave or 0 if the entry is + * describing an I2C slave. + * @dcr: DCR value (not applicable to entries describing I2C devices) + * @lvr: LVR value (not applicable to entries describing I3C devices) + * @bcr: BCR value or 0 if this entry is describing an I2C slave + * @static_addr: static address or 0 if the device does not have a static + * address + * + * The DEFSLVS command should be passed an array of i3c_ccc_dev_desc + * descriptors (one entry per I3C/I2C dev controlled by the master). + */ +struct i3c_ccc_dev_desc { + u8 dyn_addr; + union { + u8 dcr; + u8 lvr; + }; + u8 bcr; + u8 static_addr; +}; + +/** + * struct i3c_ccc_defslvs - payload passed to DEFSLVS CCC + * + * @count: number of dev descriptors + * @master: descriptor describing the current master + * @slaves: array of descriptors describing slaves controlled by the + * current master + * + * Information passed to the broadcast DEFSLVS to propagate device + * information to all masters currently acting as slaves on the bus. + * This is only meaningful if you have more than one master. + */ +struct i3c_ccc_defslvs { + u8 count; + struct i3c_ccc_dev_desc master; + struct i3c_ccc_dev_desc slaves[0]; +} __packed; + +/** + * enum i3c_ccc_test_mode - enum listing all available test modes + * + * @I3C_CCC_EXIT_TEST_MODE: exit test mode + * @I3C_CCC_VENDOR_TEST_MODE: enter vendor test mode + */ +enum i3c_ccc_test_mode { + I3C_CCC_EXIT_TEST_MODE, + I3C_CCC_VENDOR_TEST_MODE, +}; + +/** + * struct i3c_ccc_enttm - payload passed to ENTTM CCC + * + * @mode: one of the &enum i3c_ccc_test_mode modes + * + * Information passed to the ENTTM CCC to instruct an I3C device to enter a + * specific test mode. + */ +struct i3c_ccc_enttm { + u8 mode; +}; + +/** + * struct i3c_ccc_setda - payload passed to SETNEWDA and SETDASA CCCs + * + * @addr: dynamic address to assign to an I3C device + * + * Information passed to the SETNEWDA and SETDASA CCCs to assign/change the + * dynamic address of an I3C device. + */ +struct i3c_ccc_setda { + u8 addr; +}; + +/** + * struct i3c_ccc_getpid - payload passed to GETPID CCC + * + * @pid: 48 bits PID in big endian + */ +struct i3c_ccc_getpid { + u8 pid[6]; +}; + +/** + * struct i3c_ccc_getbcr - payload passed to GETBCR CCC + * + * @bcr: BCR (Bus Characteristic Register) value + */ +struct i3c_ccc_getbcr { + u8 bcr; +}; + +/** + * struct i3c_ccc_getdcr - payload passed to GETDCR CCC + * + * @dcr: DCR (Device Characteristic Register) value + */ +struct i3c_ccc_getdcr { + u8 dcr; +}; + +#define I3C_CCC_STATUS_PENDING_INT(status) ((status) & GENMASK(3, 0)) +#define I3C_CCC_STATUS_PROTOCOL_ERROR BIT(5) +#define I3C_CCC_STATUS_ACTIVITY_MODE(status) \ + (((status) & GENMASK(7, 6)) >> 6) + +/** + * struct i3c_ccc_getstatus - payload passed to GETSTATUS CCC + * + * @status: status of the I3C slave (see I3C_CCC_STATUS_xxx macros for more + * information). + */ +struct i3c_ccc_getstatus { + __be16 status; +}; + +/** + * struct i3c_ccc_getaccmst - payload passed to GETACCMST CCC + * + * @newmaster: address of the master taking bus ownership + */ +struct i3c_ccc_getaccmst { + u8 newmaster; +}; + +/** + * struct i3c_ccc_bridged_slave_desc - bridged slave descriptor + * + * @addr: dynamic address of the bridged device + * @id: ID of the slave device behind the bridge + */ +struct i3c_ccc_bridged_slave_desc { + u8 addr; + __be16 id; +} __packed; + +/** + * struct i3c_ccc_setbrgtgt - payload passed to SETBRGTGT CCC + * + * @count: number of bridged slaves + * @bslaves: bridged slave descriptors + */ +struct i3c_ccc_setbrgtgt { + u8 count; + struct i3c_ccc_bridged_slave_desc bslaves[0]; +} __packed; + +/** + * enum i3c_sdr_max_data_rate - max data rate values for private SDR transfers + */ +enum i3c_sdr_max_data_rate { + I3C_SDR0_FSCL_MAX, + I3C_SDR1_FSCL_8MHZ, + I3C_SDR2_FSCL_6MHZ, + I3C_SDR3_FSCL_4MHZ, + I3C_SDR4_FSCL_2MHZ, +}; + +/** + * enum i3c_tsco - clock to data turn-around + */ +enum i3c_tsco { + I3C_TSCO_8NS, + I3C_TSCO_9NS, + I3C_TSCO_10NS, + I3C_TSCO_11NS, + I3C_TSCO_12NS, +}; + +#define I3C_CCC_MAX_SDR_FSCL_MASK GENMASK(2, 0) +#define I3C_CCC_MAX_SDR_FSCL(x) ((x) & I3C_CCC_MAX_SDR_FSCL_MASK) + +/** + * struct i3c_ccc_getmxds - payload passed to GETMXDS CCC + * + * @maxwr: write limitations + * @maxrd: read limitations + * @maxrdturn: maximum read turn-around expressed micro-seconds and + * little-endian formatted + */ +struct i3c_ccc_getmxds { + u8 maxwr; + u8 maxrd; + u8 maxrdturn[3]; +} __packed; + +#define I3C_CCC_HDR_MODE(mode) BIT(mode) + +/** + * struct i3c_ccc_gethdrcap - payload passed to GETHDRCAP CCC + * + * @modes: bitmap of supported HDR modes + */ +struct i3c_ccc_gethdrcap { + u8 modes; +} __packed; + +/** + * enum i3c_ccc_setxtime_subcmd - SETXTIME sub-commands + */ +enum i3c_ccc_setxtime_subcmd { + I3C_CCC_SETXTIME_ST = 0x7f, + I3C_CCC_SETXTIME_DT = 0xbf, + I3C_CCC_SETXTIME_ENTER_ASYNC_MODE0 = 0xdf, + I3C_CCC_SETXTIME_ENTER_ASYNC_MODE1 = 0xef, + I3C_CCC_SETXTIME_ENTER_ASYNC_MODE2 = 0xf7, + I3C_CCC_SETXTIME_ENTER_ASYNC_MODE3 = 0xfb, + I3C_CCC_SETXTIME_ASYNC_TRIGGER = 0xfd, + I3C_CCC_SETXTIME_TPH = 0x3f, + I3C_CCC_SETXTIME_TU = 0x9f, + I3C_CCC_SETXTIME_ODR = 0x8f, +}; + +/** + * struct i3c_ccc_setxtime - payload passed to SETXTIME CCC + * + * @subcmd: one of the sub-commands ddefined in &enum i3c_ccc_setxtime_subcmd + * @data: sub-command payload. Amount of data is determined by + * &i3c_ccc_setxtime->subcmd + */ +struct i3c_ccc_setxtime { + u8 subcmd; + u8 data[0]; +} __packed; + +#define I3C_CCC_GETXTIME_SYNC_MODE BIT(0) +#define I3C_CCC_GETXTIME_ASYNC_MODE(x) BIT((x) + 1) +#define I3C_CCC_GETXTIME_OVERFLOW BIT(7) + +/** + * struct i3c_ccc_getxtime - payload retrieved from GETXTIME CCC + * + * @supported_modes: bitmap describing supported XTIME modes + * @state: current status (enabled mode and overflow status) + * @frequency: slave's internal oscillator frequency in 500KHz steps + * @inaccuracy: slave's internal oscillator inaccuracy in 0.1% steps + */ +struct i3c_ccc_getxtime { + u8 supported_modes; + u8 state; + u8 frequency; + u8 inaccuracy; +} __packed; + +/** + * struct i3c_ccc_cmd_payload - CCC payload + * + * @len: payload length + * @data: payload data. This buffer must be DMA-able + */ +struct i3c_ccc_cmd_payload { + u16 len; + void *data; +}; + +/** + * struct i3c_ccc_cmd_dest - CCC command destination + * + * @addr: can be an I3C device address or the broadcast address if this is a + * broadcast CCC + * @payload: payload to be sent to this device or broadcasted + */ +struct i3c_ccc_cmd_dest { + u8 addr; + struct i3c_ccc_cmd_payload payload; +}; + +/** + * struct i3c_ccc_cmd - CCC command + * + * @rnw: true if the CCC should retrieve data from the device. Only valid for + * unicast commands + * @id: CCC command id + * @ndests: number of destinations. Should always be one for broadcast commands + * @dests: array of destinations and associated payload for this CCC. Most of + * the time, only one destination is provided + * @err: I3C error code + */ +struct i3c_ccc_cmd { + u8 rnw; + u8 id; + unsigned int ndests; + struct i3c_ccc_cmd_dest *dests; + enum i3c_error_code err; +}; + +#endif /* I3C_CCC_H */ diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h new file mode 100644 index 000000000000..5ecb055fd375 --- /dev/null +++ b/include/linux/i3c/device.h @@ -0,0 +1,331 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Cadence Design Systems Inc. + * + * Author: Boris Brezillon + */ + +#ifndef I3C_DEV_H +#define I3C_DEV_H + +#include +#include +#include +#include +#include +#include + +/** + * enum i3c_error_code - I3C error codes + * + * These are the standard error codes as defined by the I3C specification. + * When -EIO is returned by the i3c_device_do_priv_xfers() or + * i3c_device_send_hdr_cmds() one can check the error code in + * &struct_i3c_priv_xfer.err or &struct i3c_hdr_cmd.err to get a better idea of + * what went wrong. + * + * @I3C_ERROR_UNKNOWN: unknown error, usually means the error is not I3C + * related + * @I3C_ERROR_M0: M0 error + * @I3C_ERROR_M1: M1 error + * @I3C_ERROR_M2: M2 error + */ +enum i3c_error_code { + I3C_ERROR_UNKNOWN = 0, + I3C_ERROR_M0 = 1, + I3C_ERROR_M1, + I3C_ERROR_M2, +}; + +/** + * enum i3c_hdr_mode - HDR mode ids + * @I3C_HDR_DDR: DDR mode + * @I3C_HDR_TSP: TSP mode + * @I3C_HDR_TSL: TSL mode + */ +enum i3c_hdr_mode { + I3C_HDR_DDR, + I3C_HDR_TSP, + I3C_HDR_TSL, +}; + +/** + * struct i3c_priv_xfer - I3C SDR private transfer + * @rnw: encodes the transfer direction. true for a read, false for a write + * @len: transfer length in bytes of the transfer + * @data: input/output buffer + * @data.in: input buffer. Must point to a DMA-able buffer + * @data.out: output buffer. Must point to a DMA-able buffer + * @err: I3C error code + */ +struct i3c_priv_xfer { + u8 rnw; + u16 len; + union { + void *in; + const void *out; + } data; + enum i3c_error_code err; +}; + +/** + * enum i3c_dcr - I3C DCR values + * @I3C_DCR_GENERIC_DEVICE: generic I3C device + */ +enum i3c_dcr { + I3C_DCR_GENERIC_DEVICE = 0, +}; + +#define I3C_PID_MANUF_ID(pid) (((pid) & GENMASK_ULL(47, 33)) >> 33) +#define I3C_PID_RND_LOWER_32BITS(pid) (!!((pid) & BIT_ULL(32))) +#define I3C_PID_RND_VAL(pid) ((pid) & GENMASK_ULL(31, 0)) +#define I3C_PID_PART_ID(pid) (((pid) & GENMASK_ULL(31, 16)) >> 16) +#define I3C_PID_INSTANCE_ID(pid) (((pid) & GENMASK_ULL(15, 12)) >> 12) +#define I3C_PID_EXTRA_INFO(pid) ((pid) & GENMASK_ULL(11, 0)) + +#define I3C_BCR_DEVICE_ROLE(bcr) ((bcr) & GENMASK(7, 6)) +#define I3C_BCR_I3C_SLAVE (0 << 6) +#define I3C_BCR_I3C_MASTER (1 << 6) +#define I3C_BCR_HDR_CAP BIT(5) +#define I3C_BCR_BRIDGE BIT(4) +#define I3C_BCR_OFFLINE_CAP BIT(3) +#define I3C_BCR_IBI_PAYLOAD BIT(2) +#define I3C_BCR_IBI_REQ_CAP BIT(1) +#define I3C_BCR_MAX_DATA_SPEED_LIM BIT(0) + +/** + * struct i3c_device_info - I3C device information + * @pid: Provisional ID + * @bcr: Bus Characteristic Register + * @dcr: Device Characteristic Register + * @static_addr: static/I2C address + * @dyn_addr: dynamic address + * @hdr_cap: supported HDR modes + * @max_read_ds: max read speed information + * @max_write_ds: max write speed information + * @max_ibi_len: max IBI payload length + * @max_read_turnaround: max read turn-around time in micro-seconds + * @max_read_len: max private SDR read length in bytes + * @max_write_len: max private SDR write length in bytes + * + * These are all basic information that should be advertised by an I3C device. + * Some of them are optional depending on the device type and device + * capabilities. + * For each I3C slave attached to a master with + * i3c_master_add_i3c_dev_locked(), the core will send the relevant CCC command + * to retrieve these data. + */ +struct i3c_device_info { + u64 pid; + u8 bcr; + u8 dcr; + u8 static_addr; + u8 dyn_addr; + u8 hdr_cap; + u8 max_read_ds; + u8 max_write_ds; + u8 max_ibi_len; + u32 max_read_turnaround; + u16 max_read_len; + u16 max_write_len; +}; + +/* + * I3C device internals are kept hidden from I3C device users. It's just + * simpler to refactor things when everything goes through getter/setters, and + * I3C device drivers should not have to worry about internal representation + * anyway. + */ +struct i3c_device; + +/* These macros should be used to i3c_device_id entries. */ +#define I3C_MATCH_MANUF_AND_PART (I3C_MATCH_MANUF | I3C_MATCH_PART) + +#define I3C_DEVICE(_manufid, _partid, _drvdata) \ + { \ + .match_flags = I3C_MATCH_MANUF_AND_PART, \ + .manuf_id = _manufid, \ + .part_id = _partid, \ + .data = _drvdata, \ + } + +#define I3C_DEVICE_EXTRA_INFO(_manufid, _partid, _info, _drvdata) \ + { \ + .match_flags = I3C_MATCH_MANUF_AND_PART | \ + I3C_MATCH_EXTRA_INFO, \ + .manuf_id = _manufid, \ + .part_id = _partid, \ + .extra_info = _info, \ + .data = _drvdata, \ + } + +#define I3C_CLASS(_dcr, _drvdata) \ + { \ + .match_flags = I3C_MATCH_DCR, \ + .dcr = _dcr, \ + } + +/** + * struct i3c_driver - I3C device driver + * @driver: inherit from device_driver + * @probe: I3C device probe method + * @remove: I3C device remove method + * @id_table: I3C device match table. Will be used by the framework to decide + * which device to bind to this driver + */ +struct i3c_driver { + struct device_driver driver; + int (*probe)(struct i3c_device *dev); + int (*remove)(struct i3c_device *dev); + const struct i3c_device_id *id_table; +}; + +static inline struct i3c_driver *drv_to_i3cdrv(struct device_driver *drv) +{ + return container_of(drv, struct i3c_driver, driver); +} + +struct device *i3cdev_to_dev(struct i3c_device *i3cdev); +struct i3c_device *dev_to_i3cdev(struct device *dev); + +static inline void i3cdev_set_drvdata(struct i3c_device *i3cdev, + void *data) +{ + struct device *dev = i3cdev_to_dev(i3cdev); + + dev_set_drvdata(dev, data); +} + +static inline void *i3cdev_get_drvdata(struct i3c_device *i3cdev) +{ + struct device *dev = i3cdev_to_dev(i3cdev); + + return dev_get_drvdata(dev); +} + +int i3c_driver_register_with_owner(struct i3c_driver *drv, + struct module *owner); +void i3c_driver_unregister(struct i3c_driver *drv); + +#define i3c_driver_register(__drv) \ + i3c_driver_register_with_owner(__drv, THIS_MODULE) + +/** + * module_i3c_driver() - Register a module providing an I3C driver + * @__drv: the I3C driver to register + * + * Provide generic init/exit functions that simply register/unregister an I3C + * driver. + * Should be used by any driver that does not require extra init/cleanup steps. + */ +#define module_i3c_driver(__drv) \ + module_driver(__drv, i3c_driver_register, i3c_driver_unregister) + +/** + * i3c_i2c_driver_register() - Register an i2c and an i3c driver + * @i3cdrv: the I3C driver to register + * @i2cdrv: the I2C driver to register + * + * This function registers both @i2cdev and @i3cdev, and fails if one of these + * registrations fails. This is mainly useful for devices that support both I2C + * and I3C modes. + * Note that when CONFIG_I3C is not enabled, this function only registers the + * I2C driver. + * + * Return: 0 if both registrations succeeds, a negative error code otherwise. + */ +static inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv, + struct i2c_driver *i2cdrv) +{ + int ret; + + ret = i2c_add_driver(i2cdrv); + if (ret || !IS_ENABLED(CONFIG_I3C)) + return ret; + + ret = i3c_driver_register(i3cdrv); + if (ret) + i2c_del_driver(i2cdrv); + + return ret; +} + +/** + * i3c_i2c_driver_unregister() - Unregister an i2c and an i3c driver + * @i3cdrv: the I3C driver to register + * @i2cdrv: the I2C driver to register + * + * This function unregisters both @i3cdrv and @i2cdrv. + * Note that when CONFIG_I3C is not enabled, this function only unregisters the + * @i2cdrv. + */ +static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv, + struct i2c_driver *i2cdrv) +{ + if (IS_ENABLED(CONFIG_I3C)) + i3c_driver_unregister(i3cdrv); + + i2c_del_driver(i2cdrv); +} + +/** + * module_i3c_i2c_driver() - Register a module providing an I3C and an I2C + * driver + * @__i3cdrv: the I3C driver to register + * @__i2cdrv: the I3C driver to register + * + * Provide generic init/exit functions that simply register/unregister an I3C + * and an I2C driver. + * This macro can be used even if CONFIG_I3C is disabled, in this case, only + * the I2C driver will be registered. + * Should be used by any driver that does not require extra init/cleanup steps. + */ +#define module_i3c_i2c_driver(__i3cdrv, __i2cdrv) \ + module_driver(__i3cdrv, \ + i3c_i2c_driver_register, \ + i3c_i2c_driver_unregister) + +int i3c_device_do_priv_xfers(struct i3c_device *dev, + struct i3c_priv_xfer *xfers, + int nxfers); + +void i3c_device_get_info(struct i3c_device *dev, struct i3c_device_info *info); + +struct i3c_ibi_payload { + unsigned int len; + const void *data; +}; + +/** + * struct i3c_ibi_setup - IBI setup object + * @max_payload_len: maximum length of the payload associated to an IBI. If one + * IBI appears to have a payload that is bigger than this + * number, the IBI will be rejected. + * @num_slots: number of pre-allocated IBI slots. This should be chosen so that + * the system never runs out of IBI slots, otherwise you'll lose + * IBIs. + * @handler: IBI handler, every time an IBI is received. This handler is called + * in a workqueue context. It is allowed to sleep and send new + * messages on the bus, though it's recommended to keep the + * processing done there as fast as possible to avoid delaying + * processing of other queued on the same workqueue. + * + * Temporary structure used to pass information to i3c_device_request_ibi(). + * This object can be allocated on the stack since i3c_device_request_ibi() + * copies every bit of information and do not use it after + * i3c_device_request_ibi() has returned. + */ +struct i3c_ibi_setup { + unsigned int max_payload_len; + unsigned int num_slots; + void (*handler)(struct i3c_device *dev, + const struct i3c_ibi_payload *payload); +}; + +int i3c_device_request_ibi(struct i3c_device *dev, + const struct i3c_ibi_setup *setup); +void i3c_device_free_ibi(struct i3c_device *dev); +int i3c_device_enable_ibi(struct i3c_device *dev); +int i3c_device_disable_ibi(struct i3c_device *dev); + +#endif /* I3C_DEV_H */ diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h new file mode 100644 index 000000000000..f13fd8b1dd79 --- /dev/null +++ b/include/linux/i3c/master.h @@ -0,0 +1,648 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Cadence Design Systems Inc. + * + * Author: Boris Brezillon + */ + +#ifndef I3C_MASTER_H +#define I3C_MASTER_H + +#include + +#include +#include +#include +#include +#include +#include +#include + +#define I3C_HOT_JOIN_ADDR 0x2 +#define I3C_BROADCAST_ADDR 0x7e +#define I3C_MAX_ADDR GENMASK(6, 0) + +struct i3c_master_controller; +struct i3c_bus; +struct i2c_device; +struct i3c_device; + +/** + * struct i3c_i2c_dev_desc - Common part of the I3C/I2C device descriptor + * @node: node element used to insert the slot into the I2C or I3C device + * list + * @master: I3C master that instantiated this device. Will be used to do + * I2C/I3C transfers + * @master_priv: master private data assigned to the device. Can be used to + * add master specific information + * + * This structure is describing common I3C/I2C dev information. + */ +struct i3c_i2c_dev_desc { + struct list_head node; + struct i3c_master_controller *master; + void *master_priv; +}; + +#define I3C_LVR_I2C_INDEX_MASK GENMASK(7, 5) +#define I3C_LVR_I2C_INDEX(x) ((x) << 5) +#define I3C_LVR_I2C_FM_MODE BIT(4) + +#define I2C_MAX_ADDR GENMASK(9, 0) + +/** + * struct i2c_dev_boardinfo - I2C device board information + * @node: used to insert the boardinfo object in the I2C boardinfo list + * @base: regular I2C board information + * @lvr: LVR (Legacy Virtual Register) needed by the I3C core to know about + * the I2C device limitations + * + * This structure is used to attach board-level information to an I2C device. + * Each I2C device connected on the I3C bus should have one. + */ +struct i2c_dev_boardinfo { + struct list_head node; + struct i2c_board_info base; + u8 lvr; +}; + +/** + * struct i2c_dev_desc - I2C device descriptor + * @common: common part of the I2C device descriptor + * @boardinfo: pointer to the boardinfo attached to this I2C device + * @dev: I2C device object registered to the I2C framework + * + * Each I2C device connected on the bus will have an i2c_dev_desc. + * This object is created by the core and later attached to the controller + * using &struct_i3c_master_controller->ops->attach_i2c_dev(). + * + * &struct_i2c_dev_desc is the internal representation of an I2C device + * connected on an I3C bus. This object is also passed to all + * &struct_i3c_master_controller_ops hooks. + */ +struct i2c_dev_desc { + struct i3c_i2c_dev_desc common; + const struct i2c_dev_boardinfo *boardinfo; + struct i2c_client *dev; +}; + +/** + * struct i3c_ibi_slot - I3C IBI (In-Band Interrupt) slot + * @work: work associated to this slot. The IBI handler will be called from + * there + * @dev: the I3C device that has generated this IBI + * @len: length of the payload associated to this IBI + * @data: payload buffer + * + * An IBI slot is an object pre-allocated by the controller and used when an + * IBI comes in. + * Every time an IBI comes in, the I3C master driver should find a free IBI + * slot in its IBI slot pool, retrieve the IBI payload and queue the IBI using + * i3c_master_queue_ibi(). + * + * How IBI slots are allocated is left to the I3C master driver, though, for + * simple kmalloc-based allocation, the generic IBI slot pool can be used. + */ +struct i3c_ibi_slot { + struct work_struct work; + struct i3c_dev_desc *dev; + unsigned int len; + void *data; +}; + +/** + * struct i3c_device_ibi_info - IBI information attached to a specific device + * @all_ibis_handled: used to be informed when no more IBIs are waiting to be + * processed. Used by i3c_device_disable_ibi() to wait for + * all IBIs to be dequeued + * @pending_ibis: count the number of pending IBIs. Each pending IBI has its + * work element queued to the controller workqueue + * @max_payload_len: maximum payload length for an IBI coming from this device. + * this value is specified when calling + * i3c_device_request_ibi() and should not change at run + * time. All messages IBIs exceeding this limit should be + * rejected by the master + * @num_slots: number of IBI slots reserved for this device + * @enabled: reflect the IBI status + * @handler: IBI handler specified at i3c_device_request_ibi() call time. This + * handler will be called from the controller workqueue, and as such + * is allowed to sleep (though it is recommended to process the IBI + * as fast as possible to not stall processing of other IBIs queued + * on the same workqueue). + * New I3C messages can be sent from the IBI handler + * + * The &struct_i3c_device_ibi_info object is allocated when + * i3c_device_request_ibi() is called and attached to a specific device. This + * object is here to manage IBIs coming from a specific I3C device. + * + * Note that this structure is the generic view of the IBI management + * infrastructure. I3C master drivers may have their own internal + * representation which they can associate to the device using + * controller-private data. + */ +struct i3c_device_ibi_info { + struct completion all_ibis_handled; + atomic_t pending_ibis; + unsigned int max_payload_len; + unsigned int num_slots; + unsigned int enabled; + void (*handler)(struct i3c_device *dev, + const struct i3c_ibi_payload *payload); +}; + +/** + * struct i3c_dev_boardinfo - I3C device board information + * @node: used to insert the boardinfo object in the I3C boardinfo list + * @init_dyn_addr: initial dynamic address requested by the FW. We provide no + * guarantee that the device will end up using this address, + * but try our best to assign this specific address to the + * device + * @static_addr: static address the I3C device listen on before it's been + * assigned a dynamic address by the master. Will be used during + * bus initialization to assign it a specific dynamic address + * before starting DAA (Dynamic Address Assignment) + * @pid: I3C Provisional ID exposed by the device. This is a unique identifier + * that may be used to attach boardinfo to i3c_dev_desc when the device + * does not have a static address + * @of_node: optional DT node in case the device has been described in the DT + * + * This structure is used to attach board-level information to an I3C device. + * Not all I3C devices connected on the bus will have a boardinfo. It's only + * needed if you want to attach extra resources to a device or assign it a + * specific dynamic address. + */ +struct i3c_dev_boardinfo { + struct list_head node; + u8 init_dyn_addr; + u8 static_addr; + u64 pid; + struct device_node *of_node; +}; + +/** + * struct i3c_dev_desc - I3C device descriptor + * @common: common part of the I3C device descriptor + * @info: I3C device information. Will be automatically filled when you create + * your device with i3c_master_add_i3c_dev_locked() + * @ibi_lock: lock used to protect the &struct_i3c_device->ibi + * @ibi: IBI info attached to a device. Should be NULL until + * i3c_device_request_ibi() is called + * @dev: pointer to the I3C device object exposed to I3C device drivers. This + * should never be accessed from I3C master controller drivers. Only core + * code should manipulate it in when updating the dev <-> desc link or + * when propagating IBI events to the driver + * @boardinfo: pointer to the boardinfo attached to this I3C device + * + * Internal representation of an I3C device. This object is only used by the + * core and passed to I3C master controller drivers when they're requested to + * do some operations on the device. + * The core maintains the link between the internal I3C dev descriptor and the + * object exposed to the I3C device drivers (&struct_i3c_device). + */ +struct i3c_dev_desc { + struct i3c_i2c_dev_desc common; + struct i3c_device_info info; + struct mutex ibi_lock; + struct i3c_device_ibi_info *ibi; + struct i3c_device *dev; + const struct i3c_dev_boardinfo *boardinfo; +}; + +/** + * struct i3c_device - I3C device object + * @dev: device object to register the I3C dev to the device model + * @desc: pointer to an i3c device descriptor object. This link is updated + * every time the I3C device is rediscovered with a different dynamic + * address assigned + * @bus: I3C bus this device is attached to + * + * I3C device object exposed to I3C device drivers. The takes care of linking + * this object to the relevant &struct_i3c_dev_desc one. + * All I3C devs on the I3C bus are represented, including I3C masters. For each + * of them, we have an instance of &struct i3c_device. + */ +struct i3c_device { + struct device dev; + struct i3c_dev_desc *desc; + struct i3c_bus *bus; +}; + +/* + * The I3C specification says the maximum number of devices connected on the + * bus is 11, but this number depends on external parameters like trace length, + * capacitive load per Device, and the types of Devices present on the Bus. + * I3C master can also have limitations, so this number is just here as a + * reference and should be adjusted on a per-controller/per-board basis. + */ +#define I3C_BUS_MAX_DEVS 11 + +#define I3C_BUS_MAX_I3C_SCL_RATE 12900000 +#define I3C_BUS_TYP_I3C_SCL_RATE 12500000 +#define I3C_BUS_I2C_FM_PLUS_SCL_RATE 1000000 +#define I3C_BUS_I2C_FM_SCL_RATE 400000 +#define I3C_BUS_TLOW_OD_MIN_NS 200 + +/** + * enum i3c_bus_mode - I3C bus mode + * @I3C_BUS_MODE_PURE: only I3C devices are connected to the bus. No limitation + * expected + * @I3C_BUS_MODE_MIXED_FAST: I2C devices with 50ns spike filter are present on + * the bus. The only impact in this mode is that the + * high SCL pulse has to stay below 50ns to trick I2C + * devices when transmitting I3C frames + * @I3C_BUS_MODE_MIXED_SLOW: I2C devices without 50ns spike filter are present + * on the bus + */ +enum i3c_bus_mode { + I3C_BUS_MODE_PURE, + I3C_BUS_MODE_MIXED_FAST, + I3C_BUS_MODE_MIXED_SLOW, +}; + +/** + * enum i3c_addr_slot_status - I3C address slot status + * @I3C_ADDR_SLOT_FREE: address is free + * @I3C_ADDR_SLOT_RSVD: address is reserved + * @I3C_ADDR_SLOT_I2C_DEV: address is assigned to an I2C device + * @I3C_ADDR_SLOT_I3C_DEV: address is assigned to an I3C device + * @I3C_ADDR_SLOT_STATUS_MASK: address slot mask + * + * On an I3C bus, addresses are assigned dynamically, and we need to know which + * addresses are free to use and which ones are already assigned. + * + * Addresses marked as reserved are those reserved by the I3C protocol + * (broadcast address, ...). + */ +enum i3c_addr_slot_status { + I3C_ADDR_SLOT_FREE, + I3C_ADDR_SLOT_RSVD, + I3C_ADDR_SLOT_I2C_DEV, + I3C_ADDR_SLOT_I3C_DEV, + I3C_ADDR_SLOT_STATUS_MASK = 3, +}; + +/** + * struct i3c_bus - I3C bus object + * @cur_master: I3C master currently driving the bus. Since I3C is multi-master + * this can change over the time. Will be used to let a master + * know whether it needs to request bus ownership before sending + * a frame or not + * @id: bus ID. Assigned by the framework when register the bus + * @addrslots: a bitmap with 2-bits per-slot to encode the address status and + * ease the DAA (Dynamic Address Assignment) procedure (see + * &enum i3c_addr_slot_status) + * @mode: bus mode (see &enum i3c_bus_mode) + * @scl_rate.i3c: maximum rate for the clock signal when doing I3C SDR/priv + * transfers + * @scl_rate.i2c: maximum rate for the clock signal when doing I2C transfers + * @scl_rate: SCL signal rate for I3C and I2C mode + * @devs.i3c: contains a list of I3C device descriptors representing I3C + * devices connected on the bus and successfully attached to the + * I3C master + * @devs.i2c: contains a list of I2C device descriptors representing I2C + * devices connected on the bus and successfully attached to the + * I3C master + * @devs: 2 lists containing all I3C/I2C devices connected to the bus + * @lock: read/write lock on the bus. This is needed to protect against + * operations that have an impact on the whole bus and the devices + * connected to it. For example, when asking slaves to drop their + * dynamic address (RSTDAA CCC), we need to make sure no one is trying + * to send I3C frames to these devices. + * Note that this lock does not protect against concurrency between + * devices: several drivers can send different I3C/I2C frames through + * the same master in parallel. This is the responsibility of the + * master to guarantee that frames are actually sent sequentially and + * not interlaced + * + * The I3C bus is represented with its own object and not implicitly described + * by the I3C master to cope with the multi-master functionality, where one bus + * can be shared amongst several masters, each of them requesting bus ownership + * when they need to. + */ +struct i3c_bus { + struct i3c_dev_desc *cur_master; + int id; + unsigned long addrslots[((I2C_MAX_ADDR + 1) * 2) / BITS_PER_LONG]; + enum i3c_bus_mode mode; + struct { + unsigned long i3c; + unsigned long i2c; + } scl_rate; + struct { + struct list_head i3c; + struct list_head i2c; + } devs; + struct rw_semaphore lock; +}; + +/** + * struct i3c_master_controller_ops - I3C master methods + * @bus_init: hook responsible for the I3C bus initialization. You should at + * least call master_set_info() from there and set the bus mode. + * You can also put controller specific initialization in there. + * This method is mandatory. + * @bus_cleanup: cleanup everything done in + * &i3c_master_controller_ops->bus_init(). + * This method is optional. + * @attach_i3c_dev: called every time an I3C device is attached to the bus. It + * can be after a DAA or when a device is statically declared + * by the FW, in which case it will only have a static address + * and the dynamic address will be 0. + * When this function is called, device information have not + * been retrieved yet. + * This is a good place to attach master controller specific + * data to I3C devices. + * This method is optional. + * @reattach_i3c_dev: called every time an I3C device has its addressed + * changed. It can be because the device has been powered + * down and has lost its address, or it can happen when a + * device had a static address and has been assigned a + * dynamic address with SETDASA. + * This method is optional. + * @detach_i3c_dev: called when an I3C device is detached from the bus. Usually + * happens when the master device is unregistered. + * This method is optional. + * @do_daa: do a DAA (Dynamic Address Assignment) procedure. This is procedure + * should send an ENTDAA CCC command and then add all devices + * discovered sure the DAA using i3c_master_add_i3c_dev_locked(). + * Add devices added with i3c_master_add_i3c_dev_locked() will then be + * attached or re-attached to the controller. + * This method is mandatory. + * @supports_ccc_cmd: should return true if the CCC command is supported, false + * otherwise. + * This method is optional, if not provided the core assumes + * all CCC commands are supported. + * @send_ccc_cmd: send a CCC command + * This method is mandatory. + * @priv_xfers: do one or several private I3C SDR transfers + * This method is mandatory. + * @attach_i2c_dev: called every time an I2C device is attached to the bus. + * This is a good place to attach master controller specific + * data to I2C devices. + * This method is optional. + * @detach_i2c_dev: called when an I2C device is detached from the bus. Usually + * happens when the master device is unregistered. + * This method is optional. + * @i2c_xfers: do one or several I2C transfers. Note that, unlike i3c + * transfers, the core does not guarantee that buffers attached to + * the transfers are DMA-safe. If drivers want to have DMA-safe + * buffers, they should use the i2c_get_dma_safe_msg_buf() + * and i2c_put_dma_safe_msg_buf() helpers provided by the I2C + * framework. + * This method is mandatory. + * @i2c_funcs: expose the supported I2C functionalities. + * This method is mandatory. + * @request_ibi: attach an IBI handler to an I3C device. This implies defining + * an IBI handler and the constraints of the IBI (maximum payload + * length and number of pre-allocated slots). + * Some controllers support less IBI-capable devices than regular + * devices, so this method might return -%EBUSY if there's no + * more space for an extra IBI registration + * This method is optional. + * @free_ibi: free an IBI previously requested with ->request_ibi(). The IBI + * should have been disabled with ->disable_irq() prior to that + * This method is mandatory only if ->request_ibi is not NULL. + * @enable_ibi: enable the IBI. Only valid if ->request_ibi() has been called + * prior to ->enable_ibi(). The controller should first enable + * the IBI on the controller end (for example, unmask the hardware + * IRQ) and then send the ENEC CCC command (with the IBI flag set) + * to the I3C device. + * This method is mandatory only if ->request_ibi is not NULL. + * @disable_ibi: disable an IBI. First send the DISEC CCC command with the IBI + * flag set and then deactivate the hardware IRQ on the + * controller end. + * This method is mandatory only if ->request_ibi is not NULL. + * @recycle_ibi_slot: recycle an IBI slot. Called every time an IBI has been + * processed by its handler. The IBI slot should be put back + * in the IBI slot pool so that the controller can re-use it + * for a future IBI + * This method is mandatory only if ->request_ibi is not + * NULL. + */ +struct i3c_master_controller_ops { + int (*bus_init)(struct i3c_master_controller *master); + void (*bus_cleanup)(struct i3c_master_controller *master); + int (*attach_i3c_dev)(struct i3c_dev_desc *dev); + int (*reattach_i3c_dev)(struct i3c_dev_desc *dev, u8 old_dyn_addr); + void (*detach_i3c_dev)(struct i3c_dev_desc *dev); + int (*do_daa)(struct i3c_master_controller *master); + bool (*supports_ccc_cmd)(struct i3c_master_controller *master, + const struct i3c_ccc_cmd *cmd); + int (*send_ccc_cmd)(struct i3c_master_controller *master, + struct i3c_ccc_cmd *cmd); + int (*priv_xfers)(struct i3c_dev_desc *dev, + struct i3c_priv_xfer *xfers, + int nxfers); + int (*attach_i2c_dev)(struct i2c_dev_desc *dev); + void (*detach_i2c_dev)(struct i2c_dev_desc *dev); + int (*i2c_xfers)(struct i2c_dev_desc *dev, + const struct i2c_msg *xfers, int nxfers); + u32 (*i2c_funcs)(struct i3c_master_controller *master); + int (*request_ibi)(struct i3c_dev_desc *dev, + const struct i3c_ibi_setup *req); + void (*free_ibi)(struct i3c_dev_desc *dev); + int (*enable_ibi)(struct i3c_dev_desc *dev); + int (*disable_ibi)(struct i3c_dev_desc *dev); + void (*recycle_ibi_slot)(struct i3c_dev_desc *dev, + struct i3c_ibi_slot *slot); +}; + +/** + * struct i3c_master_controller - I3C master controller object + * @dev: device to be registered to the device-model + * @this: an I3C device object representing this master. This device will be + * added to the list of I3C devs available on the bus + * @i2c: I2C adapter used for backward compatibility. This adapter is + * registered to the I2C subsystem to be as transparent as possible to + * existing I2C drivers + * @ops: master operations. See &struct i3c_master_controller_ops + * @secondary: true if the master is a secondary master + * @init_done: true when the bus initialization is done + * @boardinfo.i3c: list of I3C boardinfo objects + * @boardinfo.i2c: list of I2C boardinfo objects + * @boardinfo: board-level information attached to devices connected on the bus + * @bus: I3C bus exposed by this master + * @wq: workqueue used to execute IBI handlers. Can also be used by master + * drivers if they need to postpone operations that need to take place + * in a thread context. Typical examples are Hot Join processing which + * requires taking the bus lock in maintenance, which in turn, can only + * be done from a sleep-able context + * + * A &struct i3c_master_controller has to be registered to the I3C subsystem + * through i3c_master_register(). None of &struct i3c_master_controller fields + * should be set manually, just pass appropriate values to + * i3c_master_register(). + */ +struct i3c_master_controller { + struct device dev; + struct i3c_dev_desc *this; + struct i2c_adapter i2c; + const struct i3c_master_controller_ops *ops; + unsigned int secondary : 1; + unsigned int init_done : 1; + struct { + struct list_head i3c; + struct list_head i2c; + } boardinfo; + struct i3c_bus bus; + struct workqueue_struct *wq; +}; + +/** + * i3c_bus_for_each_i2cdev() - iterate over all I2C devices present on the bus + * @bus: the I3C bus + * @dev: an I2C device descriptor pointer updated to point to the current slot + * at each iteration of the loop + * + * Iterate over all I2C devs present on the bus. + */ +#define i3c_bus_for_each_i2cdev(bus, dev) \ + list_for_each_entry(dev, &(bus)->devs.i2c, common.node) + +/** + * i3c_bus_for_each_i3cdev() - iterate over all I3C devices present on the bus + * @bus: the I3C bus + * @dev: and I3C device descriptor pointer updated to point to the current slot + * at each iteration of the loop + * + * Iterate over all I3C devs present on the bus. + */ +#define i3c_bus_for_each_i3cdev(bus, dev) \ + list_for_each_entry(dev, &(bus)->devs.i3c, common.node) + +int i3c_master_do_i2c_xfers(struct i3c_master_controller *master, + const struct i2c_msg *xfers, + int nxfers); + +int i3c_master_disec_locked(struct i3c_master_controller *master, u8 addr, + u8 evts); +int i3c_master_enec_locked(struct i3c_master_controller *master, u8 addr, + u8 evts); +int i3c_master_entdaa_locked(struct i3c_master_controller *master); +int i3c_master_defslvs_locked(struct i3c_master_controller *master); + +int i3c_master_get_free_addr(struct i3c_master_controller *master, + u8 start_addr); + +int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master, + u8 addr); +int i3c_master_do_daa(struct i3c_master_controller *master); + +int i3c_master_set_info(struct i3c_master_controller *master, + const struct i3c_device_info *info); + +int i3c_master_register(struct i3c_master_controller *master, + struct device *parent, + const struct i3c_master_controller_ops *ops, + bool secondary); +int i3c_master_unregister(struct i3c_master_controller *master); + +/** + * i3c_dev_get_master_data() - get master private data attached to an I3C + * device descriptor + * @dev: the I3C device descriptor to get private data from + * + * Return: the private data previously attached with i3c_dev_set_master_data() + * or NULL if no data has been attached to the device. + */ +static inline void *i3c_dev_get_master_data(const struct i3c_dev_desc *dev) +{ + return dev->common.master_priv; +} + +/** + * i3c_dev_set_master_data() - attach master private data to an I3C device + * descriptor + * @dev: the I3C device descriptor to attach private data to + * @data: private data + * + * This functions allows a master controller to attach per-device private data + * which can then be retrieved with i3c_dev_get_master_data(). + */ +static inline void i3c_dev_set_master_data(struct i3c_dev_desc *dev, + void *data) +{ + dev->common.master_priv = data; +} + +/** + * i2c_dev_get_master_data() - get master private data attached to an I2C + * device descriptor + * @dev: the I2C device descriptor to get private data from + * + * Return: the private data previously attached with i2c_dev_set_master_data() + * or NULL if no data has been attached to the device. + */ +static inline void *i2c_dev_get_master_data(const struct i2c_dev_desc *dev) +{ + return dev->common.master_priv; +} + +/** + * i2c_dev_set_master_data() - attach master private data to an I2C device + * descriptor + * @dev: the I2C device descriptor to attach private data to + * @data: private data + * + * This functions allows a master controller to attach per-device private data + * which can then be retrieved with i2c_device_get_master_data(). + */ +static inline void i2c_dev_set_master_data(struct i2c_dev_desc *dev, + void *data) +{ + dev->common.master_priv = data; +} + +/** + * i3c_dev_get_master() - get master used to communicate with a device + * @dev: I3C dev + * + * Return: the master controller driving @dev + */ +static inline struct i3c_master_controller * +i3c_dev_get_master(struct i3c_dev_desc *dev) +{ + return dev->common.master; +} + +/** + * i2c_dev_get_master() - get master used to communicate with a device + * @dev: I2C dev + * + * Return: the master controller driving @dev + */ +static inline struct i3c_master_controller * +i2c_dev_get_master(struct i2c_dev_desc *dev) +{ + return dev->common.master; +} + +/** + * i3c_master_get_bus() - get the bus attached to a master + * @master: master object + * + * Return: the I3C bus @master is connected to + */ +static inline struct i3c_bus * +i3c_master_get_bus(struct i3c_master_controller *master) +{ + return &master->bus; +} + +struct i3c_generic_ibi_pool; + +struct i3c_generic_ibi_pool * +i3c_generic_ibi_alloc_pool(struct i3c_dev_desc *dev, + const struct i3c_ibi_setup *req); +void i3c_generic_ibi_free_pool(struct i3c_generic_ibi_pool *pool); + +struct i3c_ibi_slot * +i3c_generic_ibi_get_free_slot(struct i3c_generic_ibi_pool *pool); +void i3c_generic_ibi_recycle_slot(struct i3c_generic_ibi_pool *pool, + struct i3c_ibi_slot *slot); + +void i3c_master_queue_ibi(struct i3c_dev_desc *dev, struct i3c_ibi_slot *slot); + +struct i3c_ibi_slot *i3c_master_get_free_ibi_slot(struct i3c_dev_desc *dev); + +#endif /* I3C_MASTER_H */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 01797cb4587e..cbd94df31743 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -448,6 +448,23 @@ struct pci_epf_device_id { kernel_ulong_t driver_data; }; +/* i3c */ + +#define I3C_MATCH_DCR 0x1 +#define I3C_MATCH_MANUF 0x2 +#define I3C_MATCH_PART 0x4 +#define I3C_MATCH_EXTRA_INFO 0x8 + +struct i3c_device_id { + __u8 match_flags; + __u8 dcr; + __u16 manuf_id; + __u16 part_id; + __u16 extra_info; + + const void *data; +}; + /* spi */ #define SPI_NAME_SIZE 32 -- cgit v1.2.3 From daedaa33d9c578220b311fbad3748d3ecd5a8f66 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 12 Nov 2018 14:40:08 +0800 Subject: iommu/vtd: Cleanup dma_remapping.h header Commit e61d98d8dad00 ("x64, x2apic/intr-remap: Intel vt-d, IOMMU code reorganization") moved dma_remapping.h from drivers/pci/ to current place. It is entirely VT-d specific, but uses a generic name. This merges dma_remapping.h with include/linux/intel-iommu.h and removes dma_remapping.h as the result. Cc: Ashok Raj Cc: Jacob Pan Cc: Sohil Mehta Suggested-by: Christoph Hellwig Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Liu, Yi L Signed-off-by: Joerg Roedel --- include/linux/dma_remapping.h | 58 ------------------------------------------- include/linux/intel-iommu.h | 49 ++++++++++++++++++++++++++++++++++-- 2 files changed, 47 insertions(+), 60 deletions(-) delete mode 100644 include/linux/dma_remapping.h (limited to 'include/linux') diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h deleted file mode 100644 index 21b3e7d33d68..000000000000 --- a/include/linux/dma_remapping.h +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _DMA_REMAPPING_H -#define _DMA_REMAPPING_H - -/* - * VT-d hardware uses 4KiB page size regardless of host page size. - */ -#define VTD_PAGE_SHIFT (12) -#define VTD_PAGE_SIZE (1UL << VTD_PAGE_SHIFT) -#define VTD_PAGE_MASK (((u64)-1) << VTD_PAGE_SHIFT) -#define VTD_PAGE_ALIGN(addr) (((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK) - -#define VTD_STRIDE_SHIFT (9) -#define VTD_STRIDE_MASK (((u64)-1) << VTD_STRIDE_SHIFT) - -#define DMA_PTE_READ (1) -#define DMA_PTE_WRITE (2) -#define DMA_PTE_LARGE_PAGE (1 << 7) -#define DMA_PTE_SNP (1 << 11) - -#define CONTEXT_TT_MULTI_LEVEL 0 -#define CONTEXT_TT_DEV_IOTLB 1 -#define CONTEXT_TT_PASS_THROUGH 2 -/* Extended context entry types */ -#define CONTEXT_TT_PT_PASID 4 -#define CONTEXT_TT_PT_PASID_DEV_IOTLB 5 -#define CONTEXT_TT_MASK (7ULL << 2) - -#define CONTEXT_DINVE (1ULL << 8) -#define CONTEXT_PRS (1ULL << 9) -#define CONTEXT_PASIDE (1ULL << 11) - -struct intel_iommu; -struct dmar_domain; -struct root_entry; - - -#ifdef CONFIG_INTEL_IOMMU -extern int iommu_calculate_agaw(struct intel_iommu *iommu); -extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); -extern int dmar_disabled; -extern int intel_iommu_enabled; -extern int intel_iommu_tboot_noforce; -#else -static inline int iommu_calculate_agaw(struct intel_iommu *iommu) -{ - return 0; -} -static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) -{ - return 0; -} -#define dmar_disabled (1) -#define intel_iommu_enabled (0) -#endif - - -#endif diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b0ae25837361..a58bc05d6798 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -37,9 +36,36 @@ #include /* - * Intel IOMMU register specification per version 1.0 public spec. + * VT-d hardware uses 4KiB page size regardless of host page size. */ +#define VTD_PAGE_SHIFT (12) +#define VTD_PAGE_SIZE (1UL << VTD_PAGE_SHIFT) +#define VTD_PAGE_MASK (((u64)-1) << VTD_PAGE_SHIFT) +#define VTD_PAGE_ALIGN(addr) (((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK) + +#define VTD_STRIDE_SHIFT (9) +#define VTD_STRIDE_MASK (((u64)-1) << VTD_STRIDE_SHIFT) + +#define DMA_PTE_READ (1) +#define DMA_PTE_WRITE (2) +#define DMA_PTE_LARGE_PAGE (1 << 7) +#define DMA_PTE_SNP (1 << 11) + +#define CONTEXT_TT_MULTI_LEVEL 0 +#define CONTEXT_TT_DEV_IOTLB 1 +#define CONTEXT_TT_PASS_THROUGH 2 +/* Extended context entry types */ +#define CONTEXT_TT_PT_PASID 4 +#define CONTEXT_TT_PT_PASID_DEV_IOTLB 5 +#define CONTEXT_TT_MASK (7ULL << 2) + +#define CONTEXT_DINVE (1ULL << 8) +#define CONTEXT_PRS (1ULL << 9) +#define CONTEXT_PASIDE (1ULL << 11) +/* + * Intel IOMMU register specification per version 1.0 public spec. + */ #define DMAR_VER_REG 0x0 /* Arch version supported by this IOMMU */ #define DMAR_CAP_REG 0x8 /* Hardware supported capabilities */ #define DMAR_ECAP_REG 0x10 /* Extended capabilities supported */ @@ -632,4 +658,23 @@ bool context_present(struct context_entry *context); struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, u8 devfn, int alloc); +#ifdef CONFIG_INTEL_IOMMU +extern int iommu_calculate_agaw(struct intel_iommu *iommu); +extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); +extern int dmar_disabled; +extern int intel_iommu_enabled; +extern int intel_iommu_tboot_noforce; +#else +static inline int iommu_calculate_agaw(struct intel_iommu *iommu) +{ + return 0; +} +static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) +{ + return 0; +} +#define dmar_disabled (1) +#define intel_iommu_enabled (0) +#endif + #endif -- cgit v1.2.3 From 05f415715ce45da07a0b1a5eac842765b733157f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 16 Oct 2018 04:12:58 -0700 Subject: rcu: Speed up expedited GPs when interrupting RCU reader In PREEMPT kernels, an expedited grace period might send an IPI to a CPU that is executing an RCU read-side critical section. In that case, it would be nice if the rcu_read_unlock() directly interacted with the RCU core code to immediately report the quiescent state. And this does happen in the case where the reader has been preempted. But it would also be a nice performance optimization if immediate reporting also happened in the preemption-free case. This commit therefore adds an ->exp_hint field to the task_struct structure's ->rcu_read_unlock_special field. The IPI handler sets this hint when it has interrupted an RCU read-side critical section, and this causes the outermost rcu_read_unlock() call to invoke rcu_read_unlock_special(), which, if preemption is enabled, reports the quiescent state immediately. If preemption is disabled, then the report is required to be deferred until preemption (or bottom halves or interrupts or whatever) is re-enabled. Because this is a hint, it does nothing for more complicated cases. For example, if the IPI interrupts an RCU reader, but interrupts are disabled across the rcu_read_unlock(), but another rcu_read_lock() is executed before interrupts are re-enabled, the hint will already have been cleared. If you do crazy things like this, reporting will be deferred until some later RCU_SOFTIRQ handler, context switch, cond_resched(), or similar. Reported-by: Joel Fernandes Signed-off-by: Paul E. McKenney Acked-by: Joel Fernandes (Google) --- include/linux/sched.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..e4c7b6241088 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -572,8 +572,10 @@ union rcu_special { struct { u8 blocked; u8 need_qs; + u8 exp_hint; /* Hint for performance. */ + u8 pad; /* No garbage from compiler! */ } b; /* Bits. */ - u16 s; /* Set of bits. */ + u32 s; /* Set of bits. */ }; enum perf_event_task_context { -- cgit v1.2.3 From 27e95603f4dfec470c6d26bea5174aa71b30e971 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Thu, 8 Nov 2018 21:10:10 +0200 Subject: net/mlx5: Add interface to hold and release core resources Sometimes upper layers may want to prevent the destruction of a core resource for a period of time while work on that resource is in progress. Add API to support this. Signed-off-by: Moni Shoua Signed-off-by: Leon Romanovsky --- include/linux/mlx5/qp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index fbe322c966bc..b26ea9077384 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -596,6 +596,11 @@ int mlx5_core_dealloc_q_counter(struct mlx5_core_dev *dev, u16 counter_id); int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id, int reset, void *out, int out_size); +struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev, + int res_num, + enum mlx5_res_type res_type); +void mlx5_core_res_put(struct mlx5_core_rsc_common *res); + static inline const char *mlx5_qp_type_str(int type) { switch (type) { -- cgit v1.2.3 From c99fefea2cc907c98e7f39b3571bb697c8d42106 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Thu, 8 Nov 2018 21:10:11 +0200 Subject: net/mlx5: Enumerate page fault types Give meaningful names to type of WQE page faults. Signed-off-by: Moni Shoua Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index b4c0457fbebd..e326524bafcc 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -212,6 +212,13 @@ enum { MLX5_PFAULT_SUBTYPE_RDMA = 1, }; +enum wqe_page_fault_type { + MLX5_WQE_PF_TYPE_RMP = 0, + MLX5_WQE_PF_TYPE_REQ_SEND_OR_WRITE = 1, + MLX5_WQE_PF_TYPE_RESP = 2, + MLX5_WQE_PF_TYPE_REQ_READ_OR_ATOMIC = 3, +}; + enum { MLX5_PERM_LOCAL_READ = 1 << 2, MLX5_PERM_LOCAL_WRITE = 1 << 3, -- cgit v1.2.3 From 03f39f47dc86fc4defbf9b97f8417f192d1ccba6 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sat, 10 Nov 2018 21:25:44 +0100 Subject: rtc: class: remove devm_rtc_device_unregister devm_rtc_device_unregister is not used by any driver and should not be used by any new driver. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index c8bb4a2b48c3..311375dbb673 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -173,8 +173,6 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev, struct module *owner); struct rtc_device *devm_rtc_allocate_device(struct device *dev); int __rtc_register_device(struct module *owner, struct rtc_device *rtc); -extern void devm_rtc_device_unregister(struct device *dev, - struct rtc_device *rtc); extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); -- cgit v1.2.3 From cfd74017191036871af68368559330507209777c Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 8 Nov 2018 06:39:20 +0000 Subject: mtd: rawnand: sh_flctl: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. As original license mentioned, it is GPL-2.0 in SPDX. Then, MODULE_LICENSE() should be "GPL v2" instead of "GPL". See ${LINUX}/include/linux/module.h "GPL" [GNU Public License v2 or later] "GPL v2" [GNU Public License v2] Signed-off-by: Kuninori Morimoto Signed-off-by: Miquel Raynal --- include/linux/mtd/sh_flctl.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index c759d403cbc0..78fc2d4218c8 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -1,20 +1,8 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * SuperH FLCTL nand controller * * Copyright © 2008 Renesas Solutions Corp. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __SH_FLCTL_H__ -- cgit v1.2.3 From 95adc6b410b7aa895dcf5ed9cb7dc4a20a3d5c5a Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Fri, 19 Oct 2018 21:23:07 +0300 Subject: tpm: use u32 instead of int for PCR index The TPM specs defines PCR index as a positive number, and there is no reason to use a signed number. It is also a possible security issue as currently no functions check for a negative index, which may become a large number when converted to u32. Adjust the API to use u32 instead of int in all PCR related functions. Signed-off-by: Tomas Winkler Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4609b94142d4..b49a55cf775f 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -53,8 +53,8 @@ struct tpm_class_ops { #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); -extern int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf); -extern int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash); +extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf); +extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash); extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); extern int tpm_seal_trusted(struct tpm_chip *chip, @@ -69,15 +69,18 @@ static inline int tpm_is_tpm2(struct tpm_chip *chip) { return -ENODEV; } -static inline int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf) + +static inline int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf) { return -ENODEV; } -static inline int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, + +static inline int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash) { return -ENODEV; } + static inline int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen) { return -ENODEV; -- cgit v1.2.3 From 0914ade209c452cff6a29b1c0ae6fff3167fa1d0 Mon Sep 17 00:00:00 2001 From: Nayna Jain Date: Tue, 9 Oct 2018 23:00:33 +0530 Subject: x86/ima: define arch_ima_get_secureboot Distros are concerned about totally disabling the kexec_load syscall. As a compromise, the kexec_load syscall will only be disabled when CONFIG_KEXEC_VERIFY_SIG is configured and the system is booted with secureboot enabled. This patch defines the new arch specific function called arch_ima_get_secureboot() to retrieve the secureboot state of the system. Signed-off-by: Nayna Jain Suggested-by: Seth Forshee Cc: David Howells Cc: Eric Biederman Cc: Peter Jones Cc: Vivek Goyal Cc: Dave Young Signed-off-by: Mimi Zohar --- include/linux/ima.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 97914a2833d1..948135fb60f1 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -30,6 +30,15 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern void ima_add_kexec_buffer(struct kimage *image); #endif +#ifdef CONFIG_X86 +extern bool arch_ima_get_secureboot(void); +#else +static inline bool arch_ima_get_secureboot(void) +{ + return false; +} +#endif + #else static inline int ima_bprm_check(struct linux_binprm *bprm) { -- cgit v1.2.3 From 9b076f1c0f4869b838a1b7aa0edb5664d47ec8aa Mon Sep 17 00:00:00 2001 From: Matthew Bobrowski Date: Thu, 8 Nov 2018 14:07:14 +1100 Subject: fanotify: introduce new event mask FAN_OPEN_EXEC A new event mask FAN_OPEN_EXEC has been defined so that users have the ability to receive events specifically when a file has been opened with the intent to be executed. Events of FAN_OPEN_EXEC type will be generated when a file has been opened using either execve(), execveat() or uselib() system calls. The feature is implemented within fsnotify_open() by generating the FAN_OPEN_EXEC event type if __FMODE_EXEC is set within file->f_flags. Signed-off-by: Matthew Bobrowski Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 2 +- include/linux/fsnotify.h | 2 ++ include/linux/fsnotify_backend.h | 7 +++++-- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index a5a60691e48b..c521e4264f2b 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -37,7 +37,7 @@ /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FAN_ACCESS | FAN_MODIFY | \ - FAN_CLOSE | FAN_OPEN) + FAN_CLOSE | FAN_OPEN | FAN_OPEN_EXEC) /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index fd1ce10553bf..1fe5ac93b252 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -215,6 +215,8 @@ static inline void fsnotify_open(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; + if (file->f_flags & __FMODE_EXEC) + mask |= FS_OPEN_EXEC; fsnotify_parent(path, NULL, mask); fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 135b973e44d1..39d94e62a836 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -38,6 +38,7 @@ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ +#define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ @@ -62,7 +63,8 @@ #define FS_EVENTS_POSS_ON_CHILD (FS_ACCESS | FS_MODIFY | FS_ATTRIB |\ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN |\ FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE |\ - FS_DELETE | FS_OPEN_PERM | FS_ACCESS_PERM) + FS_DELETE | FS_OPEN_PERM | FS_ACCESS_PERM | \ + FS_OPEN_EXEC) #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) @@ -74,7 +76,8 @@ FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \ FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ - FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME) + FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME | \ + FS_OPEN_EXEC) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ -- cgit v1.2.3 From a704bba5e3ec3eedddad3c2baa9b7cfa0e2b3388 Mon Sep 17 00:00:00 2001 From: Matthew Bobrowski Date: Thu, 8 Nov 2018 14:10:03 +1100 Subject: fsnotify: refactor fsnotify_parent()/fsnotify() paired calls when event is on path A wrapper function fsnotify_path() has been defined to simplify the paired calls to fsnotify_parent()/fsnotify(). All hooks that made use these paired calls and passed FSNOTIFY_EVENT_PATH have been updated accordingly. Signed-off-by: Matthew Bobrowski Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1fe5ac93b252..c29f2f072c2c 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,13 +26,26 @@ static inline int fsnotify_parent(const struct path *path, struct dentry *dentry return __fsnotify_parent(path, dentry, mask); } +/* + * Simple wrapper to consolidate calls fsnotify_parent()/fsnotify() when + * an event is on a path. + */ +static inline int fsnotify_path(struct inode *inode, const struct path *path, + __u32 mask) +{ + int ret = fsnotify_parent(path, NULL, mask); + + if (ret) + return ret; + return fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); +} + /* simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { const struct path *path = &file->f_path; struct inode *inode = file_inode(file); __u32 fsnotify_mask = 0; - int ret; if (file->f_mode & FMODE_NONOTIFY) return 0; @@ -45,11 +58,7 @@ static inline int fsnotify_perm(struct file *file, int mask) else BUG(); - ret = fsnotify_parent(path, NULL, fsnotify_mask); - if (ret) - return ret; - - return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + return fsnotify_path(inode, path, fsnotify_mask); } /* @@ -180,10 +189,8 @@ static inline void fsnotify_access(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); - } + if (!(file->f_mode & FMODE_NONOTIFY)) + fsnotify_path(inode, path, mask); } /* @@ -198,10 +205,8 @@ static inline void fsnotify_modify(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); - } + if (!(file->f_mode & FMODE_NONOTIFY)) + fsnotify_path(inode, path, mask); } /* @@ -218,8 +223,7 @@ static inline void fsnotify_open(struct file *file) if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); + fsnotify_path(inode, path, mask); } /* @@ -235,10 +239,8 @@ static inline void fsnotify_close(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - if (!(file->f_mode & FMODE_NONOTIFY)) { - fsnotify_parent(path, NULL, mask); - fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); - } + if (!(file->f_mode & FMODE_NONOTIFY)) + fsnotify_path(inode, path, mask); } /* -- cgit v1.2.3 From 66917a3130f218dcef9eeab4fd11a71cd00cd7c9 Mon Sep 17 00:00:00 2001 From: Matthew Bobrowski Date: Thu, 8 Nov 2018 14:12:44 +1100 Subject: fanotify: introduce new event mask FAN_OPEN_EXEC_PERM A new event mask FAN_OPEN_EXEC_PERM has been defined. This allows users to receive events and grant access to files that are intending to be opened for execution. Events of FAN_OPEN_EXEC_PERM type will be generated when a file has been opened by using either execve(), execveat() or uselib() system calls. This acts in the same manner as previous permission event mask, meaning that an access response is required from the user application in order to permit any further operations on the file. Signed-off-by: Matthew Bobrowski Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 3 ++- include/linux/fsnotify.h | 17 ++++++++++++----- include/linux/fsnotify_backend.h | 8 +++++--- 3 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index c521e4264f2b..9e2142795335 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -40,7 +40,8 @@ FAN_CLOSE | FAN_OPEN | FAN_OPEN_EXEC) /* Events that require a permission response from user */ -#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) +#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ + FAN_OPEN_EXEC_PERM) /* Extra flags that may be reported with event or control handling of events */ #define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index c29f2f072c2c..2ccb08cb5d6a 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -40,9 +40,10 @@ static inline int fsnotify_path(struct inode *inode, const struct path *path, return fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } -/* simple call site for access decisions */ +/* Simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { + int ret; const struct path *path = &file->f_path; struct inode *inode = file_inode(file); __u32 fsnotify_mask = 0; @@ -51,12 +52,18 @@ static inline int fsnotify_perm(struct file *file, int mask) return 0; if (!(mask & (MAY_READ | MAY_OPEN))) return 0; - if (mask & MAY_OPEN) + if (mask & MAY_OPEN) { fsnotify_mask = FS_OPEN_PERM; - else if (mask & MAY_READ) + + if (file->f_flags & __FMODE_EXEC) { + ret = fsnotify_path(inode, path, FS_OPEN_EXEC_PERM); + + if (ret) + return ret; + } + } else if (mask & MAY_READ) { fsnotify_mask = FS_ACCESS_PERM; - else - BUG(); + } return fsnotify_path(inode, path, fsnotify_mask); } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 39d94e62a836..7639774e7475 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -46,6 +46,7 @@ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ +#define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ #define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ @@ -64,11 +65,12 @@ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN |\ FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE |\ FS_DELETE | FS_OPEN_PERM | FS_ACCESS_PERM | \ - FS_OPEN_EXEC) + FS_OPEN_EXEC | FS_OPEN_EXEC_PERM) #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) -#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM) +#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ + FS_OPEN_EXEC_PERM) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ @@ -77,7 +79,7 @@ FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME | \ - FS_OPEN_EXEC) + FS_OPEN_EXEC | FS_OPEN_EXEC_PERM) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ -- cgit v1.2.3 From ec93cb6f827b3e1a81b0721b8c893d2a5e37e7d6 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Tue, 13 Nov 2018 11:22:25 +0100 Subject: spi: pxa2xx: Add slave mode support Tested on an OLPC XO-1.75 machine, where the Embedded Controller happens to be a SPI master. Signed-off-by: Lubomir Rintel Acked-by: Pavel Machek Signed-off-by: Mark Brown --- include/linux/spi/pxa2xx_spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index 9ec4c147abbc..b0674e330ef6 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -25,6 +25,7 @@ struct dma_chan; struct pxa2xx_spi_master { u16 num_chipselect; u8 enable_dma; + bool is_slave; /* DMA engine specific config */ bool (*dma_filter)(struct dma_chan *chan, void *param); -- cgit v1.2.3 From 861e6ed667c83d64a42b0db41a22d6b4de4e913f Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 6 Nov 2018 12:35:21 +0100 Subject: EDAC: Drop per-memory controller buses ... and use the single edac_subsys object returned from subsys_system_register(). The idea is to have a single bus and multiple devices on it. Signed-off-by: Borislav Petkov Acked-by: Mauro Carvalho Chehab CC: Aristeu Rozanski Filho CC: Greg KH CC: Justin Ernst CC: linux-edac CC: Mauro Carvalho Chehab CC: Russ Anderson Cc: Tony Luck Link: https://lkml.kernel.org/r/20180926152752.GG5584@zn.tnic --- include/linux/edac.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 1d0c9ea8825d..342dabda9c7e 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -669,10 +669,4 @@ struct mem_ctl_info { bool fake_inject_ue; u16 fake_inject_count; }; - -/* - * Maximum number of memory controllers in the coherent fabric. - */ -#define EDAC_MAX_MCS 2 * MAX_NUMNODES - #endif -- cgit v1.2.3 From 3501ce96bf5d9dd8563dd94595436d3757ec817e Mon Sep 17 00:00:00 2001 From: "A.s. Dong" Date: Thu, 1 Nov 2018 15:19:58 +0000 Subject: firmware: imx: remove resource id enums We already export resource id in dt-bindings headfile which can also be used by drivers. So no need keep the same definitions in regular headfile anymore. Cc: Shawn Guo Cc: Sascha Hauer Cc: Fabio Estevam Reviewed-by: Ulf Hansson Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- include/linux/firmware/imx/types.h | 552 ------------------------------------- 1 file changed, 552 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/imx/types.h b/include/linux/firmware/imx/types.h index 9cbf0c4a6069..80821100e85f 100644 --- a/include/linux/firmware/imx/types.h +++ b/include/linux/firmware/imx/types.h @@ -9,558 +9,6 @@ #ifndef _SC_TYPES_H #define _SC_TYPES_H -/* - * This type is used to indicate a resource. Resources include peripherals - * and bus masters (but not memory regions). Note items from list should - * never be changed or removed (only added to at the end of the list). - */ -enum imx_sc_rsrc { - IMX_SC_R_A53 = 0, - IMX_SC_R_A53_0 = 1, - IMX_SC_R_A53_1 = 2, - IMX_SC_R_A53_2 = 3, - IMX_SC_R_A53_3 = 4, - IMX_SC_R_A72 = 5, - IMX_SC_R_A72_0 = 6, - IMX_SC_R_A72_1 = 7, - IMX_SC_R_A72_2 = 8, - IMX_SC_R_A72_3 = 9, - IMX_SC_R_CCI = 10, - IMX_SC_R_DB = 11, - IMX_SC_R_DRC_0 = 12, - IMX_SC_R_DRC_1 = 13, - IMX_SC_R_GIC_SMMU = 14, - IMX_SC_R_IRQSTR_M4_0 = 15, - IMX_SC_R_IRQSTR_M4_1 = 16, - IMX_SC_R_SMMU = 17, - IMX_SC_R_GIC = 18, - IMX_SC_R_DC_0_BLIT0 = 19, - IMX_SC_R_DC_0_BLIT1 = 20, - IMX_SC_R_DC_0_BLIT2 = 21, - IMX_SC_R_DC_0_BLIT_OUT = 22, - IMX_SC_R_DC_0_CAPTURE0 = 23, - IMX_SC_R_DC_0_CAPTURE1 = 24, - IMX_SC_R_DC_0_WARP = 25, - IMX_SC_R_DC_0_INTEGRAL0 = 26, - IMX_SC_R_DC_0_INTEGRAL1 = 27, - IMX_SC_R_DC_0_VIDEO0 = 28, - IMX_SC_R_DC_0_VIDEO1 = 29, - IMX_SC_R_DC_0_FRAC0 = 30, - IMX_SC_R_DC_0_FRAC1 = 31, - IMX_SC_R_DC_0 = 32, - IMX_SC_R_GPU_2_PID0 = 33, - IMX_SC_R_DC_0_PLL_0 = 34, - IMX_SC_R_DC_0_PLL_1 = 35, - IMX_SC_R_DC_1_BLIT0 = 36, - IMX_SC_R_DC_1_BLIT1 = 37, - IMX_SC_R_DC_1_BLIT2 = 38, - IMX_SC_R_DC_1_BLIT_OUT = 39, - IMX_SC_R_DC_1_CAPTURE0 = 40, - IMX_SC_R_DC_1_CAPTURE1 = 41, - IMX_SC_R_DC_1_WARP = 42, - IMX_SC_R_DC_1_INTEGRAL0 = 43, - IMX_SC_R_DC_1_INTEGRAL1 = 44, - IMX_SC_R_DC_1_VIDEO0 = 45, - IMX_SC_R_DC_1_VIDEO1 = 46, - IMX_SC_R_DC_1_FRAC0 = 47, - IMX_SC_R_DC_1_FRAC1 = 48, - IMX_SC_R_DC_1 = 49, - IMX_SC_R_GPU_3_PID0 = 50, - IMX_SC_R_DC_1_PLL_0 = 51, - IMX_SC_R_DC_1_PLL_1 = 52, - IMX_SC_R_SPI_0 = 53, - IMX_SC_R_SPI_1 = 54, - IMX_SC_R_SPI_2 = 55, - IMX_SC_R_SPI_3 = 56, - IMX_SC_R_UART_0 = 57, - IMX_SC_R_UART_1 = 58, - IMX_SC_R_UART_2 = 59, - IMX_SC_R_UART_3 = 60, - IMX_SC_R_UART_4 = 61, - IMX_SC_R_EMVSIM_0 = 62, - IMX_SC_R_EMVSIM_1 = 63, - IMX_SC_R_DMA_0_CH0 = 64, - IMX_SC_R_DMA_0_CH1 = 65, - IMX_SC_R_DMA_0_CH2 = 66, - IMX_SC_R_DMA_0_CH3 = 67, - IMX_SC_R_DMA_0_CH4 = 68, - IMX_SC_R_DMA_0_CH5 = 69, - IMX_SC_R_DMA_0_CH6 = 70, - IMX_SC_R_DMA_0_CH7 = 71, - IMX_SC_R_DMA_0_CH8 = 72, - IMX_SC_R_DMA_0_CH9 = 73, - IMX_SC_R_DMA_0_CH10 = 74, - IMX_SC_R_DMA_0_CH11 = 75, - IMX_SC_R_DMA_0_CH12 = 76, - IMX_SC_R_DMA_0_CH13 = 77, - IMX_SC_R_DMA_0_CH14 = 78, - IMX_SC_R_DMA_0_CH15 = 79, - IMX_SC_R_DMA_0_CH16 = 80, - IMX_SC_R_DMA_0_CH17 = 81, - IMX_SC_R_DMA_0_CH18 = 82, - IMX_SC_R_DMA_0_CH19 = 83, - IMX_SC_R_DMA_0_CH20 = 84, - IMX_SC_R_DMA_0_CH21 = 85, - IMX_SC_R_DMA_0_CH22 = 86, - IMX_SC_R_DMA_0_CH23 = 87, - IMX_SC_R_DMA_0_CH24 = 88, - IMX_SC_R_DMA_0_CH25 = 89, - IMX_SC_R_DMA_0_CH26 = 90, - IMX_SC_R_DMA_0_CH27 = 91, - IMX_SC_R_DMA_0_CH28 = 92, - IMX_SC_R_DMA_0_CH29 = 93, - IMX_SC_R_DMA_0_CH30 = 94, - IMX_SC_R_DMA_0_CH31 = 95, - IMX_SC_R_I2C_0 = 96, - IMX_SC_R_I2C_1 = 97, - IMX_SC_R_I2C_2 = 98, - IMX_SC_R_I2C_3 = 99, - IMX_SC_R_I2C_4 = 100, - IMX_SC_R_ADC_0 = 101, - IMX_SC_R_ADC_1 = 102, - IMX_SC_R_FTM_0 = 103, - IMX_SC_R_FTM_1 = 104, - IMX_SC_R_CAN_0 = 105, - IMX_SC_R_CAN_1 = 106, - IMX_SC_R_CAN_2 = 107, - IMX_SC_R_DMA_1_CH0 = 108, - IMX_SC_R_DMA_1_CH1 = 109, - IMX_SC_R_DMA_1_CH2 = 110, - IMX_SC_R_DMA_1_CH3 = 111, - IMX_SC_R_DMA_1_CH4 = 112, - IMX_SC_R_DMA_1_CH5 = 113, - IMX_SC_R_DMA_1_CH6 = 114, - IMX_SC_R_DMA_1_CH7 = 115, - IMX_SC_R_DMA_1_CH8 = 116, - IMX_SC_R_DMA_1_CH9 = 117, - IMX_SC_R_DMA_1_CH10 = 118, - IMX_SC_R_DMA_1_CH11 = 119, - IMX_SC_R_DMA_1_CH12 = 120, - IMX_SC_R_DMA_1_CH13 = 121, - IMX_SC_R_DMA_1_CH14 = 122, - IMX_SC_R_DMA_1_CH15 = 123, - IMX_SC_R_DMA_1_CH16 = 124, - IMX_SC_R_DMA_1_CH17 = 125, - IMX_SC_R_DMA_1_CH18 = 126, - IMX_SC_R_DMA_1_CH19 = 127, - IMX_SC_R_DMA_1_CH20 = 128, - IMX_SC_R_DMA_1_CH21 = 129, - IMX_SC_R_DMA_1_CH22 = 130, - IMX_SC_R_DMA_1_CH23 = 131, - IMX_SC_R_DMA_1_CH24 = 132, - IMX_SC_R_DMA_1_CH25 = 133, - IMX_SC_R_DMA_1_CH26 = 134, - IMX_SC_R_DMA_1_CH27 = 135, - IMX_SC_R_DMA_1_CH28 = 136, - IMX_SC_R_DMA_1_CH29 = 137, - IMX_SC_R_DMA_1_CH30 = 138, - IMX_SC_R_DMA_1_CH31 = 139, - IMX_SC_R_UNUSED1 = 140, - IMX_SC_R_UNUSED2 = 141, - IMX_SC_R_UNUSED3 = 142, - IMX_SC_R_UNUSED4 = 143, - IMX_SC_R_GPU_0_PID0 = 144, - IMX_SC_R_GPU_0_PID1 = 145, - IMX_SC_R_GPU_0_PID2 = 146, - IMX_SC_R_GPU_0_PID3 = 147, - IMX_SC_R_GPU_1_PID0 = 148, - IMX_SC_R_GPU_1_PID1 = 149, - IMX_SC_R_GPU_1_PID2 = 150, - IMX_SC_R_GPU_1_PID3 = 151, - IMX_SC_R_PCIE_A = 152, - IMX_SC_R_SERDES_0 = 153, - IMX_SC_R_MATCH_0 = 154, - IMX_SC_R_MATCH_1 = 155, - IMX_SC_R_MATCH_2 = 156, - IMX_SC_R_MATCH_3 = 157, - IMX_SC_R_MATCH_4 = 158, - IMX_SC_R_MATCH_5 = 159, - IMX_SC_R_MATCH_6 = 160, - IMX_SC_R_MATCH_7 = 161, - IMX_SC_R_MATCH_8 = 162, - IMX_SC_R_MATCH_9 = 163, - IMX_SC_R_MATCH_10 = 164, - IMX_SC_R_MATCH_11 = 165, - IMX_SC_R_MATCH_12 = 166, - IMX_SC_R_MATCH_13 = 167, - IMX_SC_R_MATCH_14 = 168, - IMX_SC_R_PCIE_B = 169, - IMX_SC_R_SATA_0 = 170, - IMX_SC_R_SERDES_1 = 171, - IMX_SC_R_HSIO_GPIO = 172, - IMX_SC_R_MATCH_15 = 173, - IMX_SC_R_MATCH_16 = 174, - IMX_SC_R_MATCH_17 = 175, - IMX_SC_R_MATCH_18 = 176, - IMX_SC_R_MATCH_19 = 177, - IMX_SC_R_MATCH_20 = 178, - IMX_SC_R_MATCH_21 = 179, - IMX_SC_R_MATCH_22 = 180, - IMX_SC_R_MATCH_23 = 181, - IMX_SC_R_MATCH_24 = 182, - IMX_SC_R_MATCH_25 = 183, - IMX_SC_R_MATCH_26 = 184, - IMX_SC_R_MATCH_27 = 185, - IMX_SC_R_MATCH_28 = 186, - IMX_SC_R_LCD_0 = 187, - IMX_SC_R_LCD_0_PWM_0 = 188, - IMX_SC_R_LCD_0_I2C_0 = 189, - IMX_SC_R_LCD_0_I2C_1 = 190, - IMX_SC_R_PWM_0 = 191, - IMX_SC_R_PWM_1 = 192, - IMX_SC_R_PWM_2 = 193, - IMX_SC_R_PWM_3 = 194, - IMX_SC_R_PWM_4 = 195, - IMX_SC_R_PWM_5 = 196, - IMX_SC_R_PWM_6 = 197, - IMX_SC_R_PWM_7 = 198, - IMX_SC_R_GPIO_0 = 199, - IMX_SC_R_GPIO_1 = 200, - IMX_SC_R_GPIO_2 = 201, - IMX_SC_R_GPIO_3 = 202, - IMX_SC_R_GPIO_4 = 203, - IMX_SC_R_GPIO_5 = 204, - IMX_SC_R_GPIO_6 = 205, - IMX_SC_R_GPIO_7 = 206, - IMX_SC_R_GPT_0 = 207, - IMX_SC_R_GPT_1 = 208, - IMX_SC_R_GPT_2 = 209, - IMX_SC_R_GPT_3 = 210, - IMX_SC_R_GPT_4 = 211, - IMX_SC_R_KPP = 212, - IMX_SC_R_MU_0A = 213, - IMX_SC_R_MU_1A = 214, - IMX_SC_R_MU_2A = 215, - IMX_SC_R_MU_3A = 216, - IMX_SC_R_MU_4A = 217, - IMX_SC_R_MU_5A = 218, - IMX_SC_R_MU_6A = 219, - IMX_SC_R_MU_7A = 220, - IMX_SC_R_MU_8A = 221, - IMX_SC_R_MU_9A = 222, - IMX_SC_R_MU_10A = 223, - IMX_SC_R_MU_11A = 224, - IMX_SC_R_MU_12A = 225, - IMX_SC_R_MU_13A = 226, - IMX_SC_R_MU_5B = 227, - IMX_SC_R_MU_6B = 228, - IMX_SC_R_MU_7B = 229, - IMX_SC_R_MU_8B = 230, - IMX_SC_R_MU_9B = 231, - IMX_SC_R_MU_10B = 232, - IMX_SC_R_MU_11B = 233, - IMX_SC_R_MU_12B = 234, - IMX_SC_R_MU_13B = 235, - IMX_SC_R_ROM_0 = 236, - IMX_SC_R_FSPI_0 = 237, - IMX_SC_R_FSPI_1 = 238, - IMX_SC_R_IEE = 239, - IMX_SC_R_IEE_R0 = 240, - IMX_SC_R_IEE_R1 = 241, - IMX_SC_R_IEE_R2 = 242, - IMX_SC_R_IEE_R3 = 243, - IMX_SC_R_IEE_R4 = 244, - IMX_SC_R_IEE_R5 = 245, - IMX_SC_R_IEE_R6 = 246, - IMX_SC_R_IEE_R7 = 247, - IMX_SC_R_SDHC_0 = 248, - IMX_SC_R_SDHC_1 = 249, - IMX_SC_R_SDHC_2 = 250, - IMX_SC_R_ENET_0 = 251, - IMX_SC_R_ENET_1 = 252, - IMX_SC_R_MLB_0 = 253, - IMX_SC_R_DMA_2_CH0 = 254, - IMX_SC_R_DMA_2_CH1 = 255, - IMX_SC_R_DMA_2_CH2 = 256, - IMX_SC_R_DMA_2_CH3 = 257, - IMX_SC_R_DMA_2_CH4 = 258, - IMX_SC_R_USB_0 = 259, - IMX_SC_R_USB_1 = 260, - IMX_SC_R_USB_0_PHY = 261, - IMX_SC_R_USB_2 = 262, - IMX_SC_R_USB_2_PHY = 263, - IMX_SC_R_DTCP = 264, - IMX_SC_R_NAND = 265, - IMX_SC_R_LVDS_0 = 266, - IMX_SC_R_LVDS_0_PWM_0 = 267, - IMX_SC_R_LVDS_0_I2C_0 = 268, - IMX_SC_R_LVDS_0_I2C_1 = 269, - IMX_SC_R_LVDS_1 = 270, - IMX_SC_R_LVDS_1_PWM_0 = 271, - IMX_SC_R_LVDS_1_I2C_0 = 272, - IMX_SC_R_LVDS_1_I2C_1 = 273, - IMX_SC_R_LVDS_2 = 274, - IMX_SC_R_LVDS_2_PWM_0 = 275, - IMX_SC_R_LVDS_2_I2C_0 = 276, - IMX_SC_R_LVDS_2_I2C_1 = 277, - IMX_SC_R_M4_0_PID0 = 278, - IMX_SC_R_M4_0_PID1 = 279, - IMX_SC_R_M4_0_PID2 = 280, - IMX_SC_R_M4_0_PID3 = 281, - IMX_SC_R_M4_0_PID4 = 282, - IMX_SC_R_M4_0_RGPIO = 283, - IMX_SC_R_M4_0_SEMA42 = 284, - IMX_SC_R_M4_0_TPM = 285, - IMX_SC_R_M4_0_PIT = 286, - IMX_SC_R_M4_0_UART = 287, - IMX_SC_R_M4_0_I2C = 288, - IMX_SC_R_M4_0_INTMUX = 289, - IMX_SC_R_M4_0_SIM = 290, - IMX_SC_R_M4_0_WDOG = 291, - IMX_SC_R_M4_0_MU_0B = 292, - IMX_SC_R_M4_0_MU_0A0 = 293, - IMX_SC_R_M4_0_MU_0A1 = 294, - IMX_SC_R_M4_0_MU_0A2 = 295, - IMX_SC_R_M4_0_MU_0A3 = 296, - IMX_SC_R_M4_0_MU_1A = 297, - IMX_SC_R_M4_1_PID0 = 298, - IMX_SC_R_M4_1_PID1 = 299, - IMX_SC_R_M4_1_PID2 = 300, - IMX_SC_R_M4_1_PID3 = 301, - IMX_SC_R_M4_1_PID4 = 302, - IMX_SC_R_M4_1_RGPIO = 303, - IMX_SC_R_M4_1_SEMA42 = 304, - IMX_SC_R_M4_1_TPM = 305, - IMX_SC_R_M4_1_PIT = 306, - IMX_SC_R_M4_1_UART = 307, - IMX_SC_R_M4_1_I2C = 308, - IMX_SC_R_M4_1_INTMUX = 309, - IMX_SC_R_M4_1_SIM = 310, - IMX_SC_R_M4_1_WDOG = 311, - IMX_SC_R_M4_1_MU_0B = 312, - IMX_SC_R_M4_1_MU_0A0 = 313, - IMX_SC_R_M4_1_MU_0A1 = 314, - IMX_SC_R_M4_1_MU_0A2 = 315, - IMX_SC_R_M4_1_MU_0A3 = 316, - IMX_SC_R_M4_1_MU_1A = 317, - IMX_SC_R_SAI_0 = 318, - IMX_SC_R_SAI_1 = 319, - IMX_SC_R_SAI_2 = 320, - IMX_SC_R_IRQSTR_SCU2 = 321, - IMX_SC_R_IRQSTR_DSP = 322, - IMX_SC_R_UNUSED5 = 323, - IMX_SC_R_UNUSED6 = 324, - IMX_SC_R_AUDIO_PLL_0 = 325, - IMX_SC_R_PI_0 = 326, - IMX_SC_R_PI_0_PWM_0 = 327, - IMX_SC_R_PI_0_PWM_1 = 328, - IMX_SC_R_PI_0_I2C_0 = 329, - IMX_SC_R_PI_0_PLL = 330, - IMX_SC_R_PI_1 = 331, - IMX_SC_R_PI_1_PWM_0 = 332, - IMX_SC_R_PI_1_PWM_1 = 333, - IMX_SC_R_PI_1_I2C_0 = 334, - IMX_SC_R_PI_1_PLL = 335, - IMX_SC_R_SC_PID0 = 336, - IMX_SC_R_SC_PID1 = 337, - IMX_SC_R_SC_PID2 = 338, - IMX_SC_R_SC_PID3 = 339, - IMX_SC_R_SC_PID4 = 340, - IMX_SC_R_SC_SEMA42 = 341, - IMX_SC_R_SC_TPM = 342, - IMX_SC_R_SC_PIT = 343, - IMX_SC_R_SC_UART = 344, - IMX_SC_R_SC_I2C = 345, - IMX_SC_R_SC_MU_0B = 346, - IMX_SC_R_SC_MU_0A0 = 347, - IMX_SC_R_SC_MU_0A1 = 348, - IMX_SC_R_SC_MU_0A2 = 349, - IMX_SC_R_SC_MU_0A3 = 350, - IMX_SC_R_SC_MU_1A = 351, - IMX_SC_R_SYSCNT_RD = 352, - IMX_SC_R_SYSCNT_CMP = 353, - IMX_SC_R_DEBUG = 354, - IMX_SC_R_SYSTEM = 355, - IMX_SC_R_SNVS = 356, - IMX_SC_R_OTP = 357, - IMX_SC_R_VPU_PID0 = 358, - IMX_SC_R_VPU_PID1 = 359, - IMX_SC_R_VPU_PID2 = 360, - IMX_SC_R_VPU_PID3 = 361, - IMX_SC_R_VPU_PID4 = 362, - IMX_SC_R_VPU_PID5 = 363, - IMX_SC_R_VPU_PID6 = 364, - IMX_SC_R_VPU_PID7 = 365, - IMX_SC_R_VPU_UART = 366, - IMX_SC_R_VPUCORE = 367, - IMX_SC_R_VPUCORE_0 = 368, - IMX_SC_R_VPUCORE_1 = 369, - IMX_SC_R_VPUCORE_2 = 370, - IMX_SC_R_VPUCORE_3 = 371, - IMX_SC_R_DMA_4_CH0 = 372, - IMX_SC_R_DMA_4_CH1 = 373, - IMX_SC_R_DMA_4_CH2 = 374, - IMX_SC_R_DMA_4_CH3 = 375, - IMX_SC_R_DMA_4_CH4 = 376, - IMX_SC_R_ISI_CH0 = 377, - IMX_SC_R_ISI_CH1 = 378, - IMX_SC_R_ISI_CH2 = 379, - IMX_SC_R_ISI_CH3 = 380, - IMX_SC_R_ISI_CH4 = 381, - IMX_SC_R_ISI_CH5 = 382, - IMX_SC_R_ISI_CH6 = 383, - IMX_SC_R_ISI_CH7 = 384, - IMX_SC_R_MJPEG_DEC_S0 = 385, - IMX_SC_R_MJPEG_DEC_S1 = 386, - IMX_SC_R_MJPEG_DEC_S2 = 387, - IMX_SC_R_MJPEG_DEC_S3 = 388, - IMX_SC_R_MJPEG_ENC_S0 = 389, - IMX_SC_R_MJPEG_ENC_S1 = 390, - IMX_SC_R_MJPEG_ENC_S2 = 391, - IMX_SC_R_MJPEG_ENC_S3 = 392, - IMX_SC_R_MIPI_0 = 393, - IMX_SC_R_MIPI_0_PWM_0 = 394, - IMX_SC_R_MIPI_0_I2C_0 = 395, - IMX_SC_R_MIPI_0_I2C_1 = 396, - IMX_SC_R_MIPI_1 = 397, - IMX_SC_R_MIPI_1_PWM_0 = 398, - IMX_SC_R_MIPI_1_I2C_0 = 399, - IMX_SC_R_MIPI_1_I2C_1 = 400, - IMX_SC_R_CSI_0 = 401, - IMX_SC_R_CSI_0_PWM_0 = 402, - IMX_SC_R_CSI_0_I2C_0 = 403, - IMX_SC_R_CSI_1 = 404, - IMX_SC_R_CSI_1_PWM_0 = 405, - IMX_SC_R_CSI_1_I2C_0 = 406, - IMX_SC_R_HDMI = 407, - IMX_SC_R_HDMI_I2S = 408, - IMX_SC_R_HDMI_I2C_0 = 409, - IMX_SC_R_HDMI_PLL_0 = 410, - IMX_SC_R_HDMI_RX = 411, - IMX_SC_R_HDMI_RX_BYPASS = 412, - IMX_SC_R_HDMI_RX_I2C_0 = 413, - IMX_SC_R_ASRC_0 = 414, - IMX_SC_R_ESAI_0 = 415, - IMX_SC_R_SPDIF_0 = 416, - IMX_SC_R_SPDIF_1 = 417, - IMX_SC_R_SAI_3 = 418, - IMX_SC_R_SAI_4 = 419, - IMX_SC_R_SAI_5 = 420, - IMX_SC_R_GPT_5 = 421, - IMX_SC_R_GPT_6 = 422, - IMX_SC_R_GPT_7 = 423, - IMX_SC_R_GPT_8 = 424, - IMX_SC_R_GPT_9 = 425, - IMX_SC_R_GPT_10 = 426, - IMX_SC_R_DMA_2_CH5 = 427, - IMX_SC_R_DMA_2_CH6 = 428, - IMX_SC_R_DMA_2_CH7 = 429, - IMX_SC_R_DMA_2_CH8 = 430, - IMX_SC_R_DMA_2_CH9 = 431, - IMX_SC_R_DMA_2_CH10 = 432, - IMX_SC_R_DMA_2_CH11 = 433, - IMX_SC_R_DMA_2_CH12 = 434, - IMX_SC_R_DMA_2_CH13 = 435, - IMX_SC_R_DMA_2_CH14 = 436, - IMX_SC_R_DMA_2_CH15 = 437, - IMX_SC_R_DMA_2_CH16 = 438, - IMX_SC_R_DMA_2_CH17 = 439, - IMX_SC_R_DMA_2_CH18 = 440, - IMX_SC_R_DMA_2_CH19 = 441, - IMX_SC_R_DMA_2_CH20 = 442, - IMX_SC_R_DMA_2_CH21 = 443, - IMX_SC_R_DMA_2_CH22 = 444, - IMX_SC_R_DMA_2_CH23 = 445, - IMX_SC_R_DMA_2_CH24 = 446, - IMX_SC_R_DMA_2_CH25 = 447, - IMX_SC_R_DMA_2_CH26 = 448, - IMX_SC_R_DMA_2_CH27 = 449, - IMX_SC_R_DMA_2_CH28 = 450, - IMX_SC_R_DMA_2_CH29 = 451, - IMX_SC_R_DMA_2_CH30 = 452, - IMX_SC_R_DMA_2_CH31 = 453, - IMX_SC_R_ASRC_1 = 454, - IMX_SC_R_ESAI_1 = 455, - IMX_SC_R_SAI_6 = 456, - IMX_SC_R_SAI_7 = 457, - IMX_SC_R_AMIX = 458, - IMX_SC_R_MQS_0 = 459, - IMX_SC_R_DMA_3_CH0 = 460, - IMX_SC_R_DMA_3_CH1 = 461, - IMX_SC_R_DMA_3_CH2 = 462, - IMX_SC_R_DMA_3_CH3 = 463, - IMX_SC_R_DMA_3_CH4 = 464, - IMX_SC_R_DMA_3_CH5 = 465, - IMX_SC_R_DMA_3_CH6 = 466, - IMX_SC_R_DMA_3_CH7 = 467, - IMX_SC_R_DMA_3_CH8 = 468, - IMX_SC_R_DMA_3_CH9 = 469, - IMX_SC_R_DMA_3_CH10 = 470, - IMX_SC_R_DMA_3_CH11 = 471, - IMX_SC_R_DMA_3_CH12 = 472, - IMX_SC_R_DMA_3_CH13 = 473, - IMX_SC_R_DMA_3_CH14 = 474, - IMX_SC_R_DMA_3_CH15 = 475, - IMX_SC_R_DMA_3_CH16 = 476, - IMX_SC_R_DMA_3_CH17 = 477, - IMX_SC_R_DMA_3_CH18 = 478, - IMX_SC_R_DMA_3_CH19 = 479, - IMX_SC_R_DMA_3_CH20 = 480, - IMX_SC_R_DMA_3_CH21 = 481, - IMX_SC_R_DMA_3_CH22 = 482, - IMX_SC_R_DMA_3_CH23 = 483, - IMX_SC_R_DMA_3_CH24 = 484, - IMX_SC_R_DMA_3_CH25 = 485, - IMX_SC_R_DMA_3_CH26 = 486, - IMX_SC_R_DMA_3_CH27 = 487, - IMX_SC_R_DMA_3_CH28 = 488, - IMX_SC_R_DMA_3_CH29 = 489, - IMX_SC_R_DMA_3_CH30 = 490, - IMX_SC_R_DMA_3_CH31 = 491, - IMX_SC_R_AUDIO_PLL_1 = 492, - IMX_SC_R_AUDIO_CLK_0 = 493, - IMX_SC_R_AUDIO_CLK_1 = 494, - IMX_SC_R_MCLK_OUT_0 = 495, - IMX_SC_R_MCLK_OUT_1 = 496, - IMX_SC_R_PMIC_0 = 497, - IMX_SC_R_PMIC_1 = 498, - IMX_SC_R_SECO = 499, - IMX_SC_R_CAAM_JR1 = 500, - IMX_SC_R_CAAM_JR2 = 501, - IMX_SC_R_CAAM_JR3 = 502, - IMX_SC_R_SECO_MU_2 = 503, - IMX_SC_R_SECO_MU_3 = 504, - IMX_SC_R_SECO_MU_4 = 505, - IMX_SC_R_HDMI_RX_PWM_0 = 506, - IMX_SC_R_A35 = 507, - IMX_SC_R_A35_0 = 508, - IMX_SC_R_A35_1 = 509, - IMX_SC_R_A35_2 = 510, - IMX_SC_R_A35_3 = 511, - IMX_SC_R_DSP = 512, - IMX_SC_R_DSP_RAM = 513, - IMX_SC_R_CAAM_JR1_OUT = 514, - IMX_SC_R_CAAM_JR2_OUT = 515, - IMX_SC_R_CAAM_JR3_OUT = 516, - IMX_SC_R_VPU_DEC_0 = 517, - IMX_SC_R_VPU_ENC_0 = 518, - IMX_SC_R_CAAM_JR0 = 519, - IMX_SC_R_CAAM_JR0_OUT = 520, - IMX_SC_R_PMIC_2 = 521, - IMX_SC_R_DBLOGIC = 522, - IMX_SC_R_HDMI_PLL_1 = 523, - IMX_SC_R_BOARD_R0 = 524, - IMX_SC_R_BOARD_R1 = 525, - IMX_SC_R_BOARD_R2 = 526, - IMX_SC_R_BOARD_R3 = 527, - IMX_SC_R_BOARD_R4 = 528, - IMX_SC_R_BOARD_R5 = 529, - IMX_SC_R_BOARD_R6 = 530, - IMX_SC_R_BOARD_R7 = 531, - IMX_SC_R_MJPEG_DEC_MP = 532, - IMX_SC_R_MJPEG_ENC_MP = 533, - IMX_SC_R_VPU_TS_0 = 534, - IMX_SC_R_VPU_MU_0 = 535, - IMX_SC_R_VPU_MU_1 = 536, - IMX_SC_R_VPU_MU_2 = 537, - IMX_SC_R_VPU_MU_3 = 538, - IMX_SC_R_VPU_ENC_1 = 539, - IMX_SC_R_VPU = 540, - IMX_SC_R_LAST -}; - -/* NOTE - please add by replacing some of the UNUSED from above! */ - /* * This type is used to indicate a control. */ -- cgit v1.2.3 From 0a914a4948d4604c08750ae67dc33f8b5702402f Mon Sep 17 00:00:00 2001 From: "A.s. Dong" Date: Thu, 1 Nov 2018 15:20:08 +0000 Subject: firmware: imx: add pm svc headfile Add SCU PM SVC related protocol definitions which will be used by a number of PM functions like Power Domain, Clock, Reset and etc. The detailed implementation of each function will put in the individual function drivers. Cc: Shawn Guo Cc: Sascha Hauer Reviewed-by: Ulf Hansson Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- include/linux/firmware/imx/sci.h | 1 + include/linux/firmware/imx/svc/pm.h | 85 +++++++++++++++++++++++++++++++++++++ 2 files changed, 86 insertions(+) create mode 100644 include/linux/firmware/imx/svc/pm.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index 29ada609de03..ebc55098faee 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -14,4 +14,5 @@ #include #include +#include #endif /* _SC_SCI_H */ diff --git a/include/linux/firmware/imx/svc/pm.h b/include/linux/firmware/imx/svc/pm.h new file mode 100644 index 000000000000..1f6975dd37b0 --- /dev/null +++ b/include/linux/firmware/imx/svc/pm.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017-2018 NXP + * + * Header file containing the public API for the System Controller (SC) + * Power Management (PM) function. This includes functions for power state + * control, clock control, reset control, and wake-up event control. + * + * PM_SVC (SVC) Power Management Service + * + * Module for the Power Management (PM) service. + */ + +#ifndef _SC_PM_API_H +#define _SC_PM_API_H + +#include + +/* + * This type is used to indicate RPC PM function calls. + */ +enum imx_sc_pm_func { + IMX_SC_PM_FUNC_UNKNOWN = 0, + IMX_SC_PM_FUNC_SET_SYS_POWER_MODE = 19, + IMX_SC_PM_FUNC_SET_PARTITION_POWER_MODE = 1, + IMX_SC_PM_FUNC_GET_SYS_POWER_MODE = 2, + IMX_SC_PM_FUNC_SET_RESOURCE_POWER_MODE = 3, + IMX_SC_PM_FUNC_GET_RESOURCE_POWER_MODE = 4, + IMX_SC_PM_FUNC_REQ_LOW_POWER_MODE = 16, + IMX_SC_PM_FUNC_SET_CPU_RESUME_ADDR = 17, + IMX_SC_PM_FUNC_REQ_SYS_IF_POWER_MODE = 18, + IMX_SC_PM_FUNC_SET_CLOCK_RATE = 5, + IMX_SC_PM_FUNC_GET_CLOCK_RATE = 6, + IMX_SC_PM_FUNC_CLOCK_ENABLE = 7, + IMX_SC_PM_FUNC_SET_CLOCK_PARENT = 14, + IMX_SC_PM_FUNC_GET_CLOCK_PARENT = 15, + IMX_SC_PM_FUNC_RESET = 13, + IMX_SC_PM_FUNC_RESET_REASON = 10, + IMX_SC_PM_FUNC_BOOT = 8, + IMX_SC_PM_FUNC_REBOOT = 9, + IMX_SC_PM_FUNC_REBOOT_PARTITION = 12, + IMX_SC_PM_FUNC_CPU_START = 11, +}; + +/* + * Defines for ALL parameters + */ +#define IMX_SC_PM_CLK_ALL UINT8_MAX /* All clocks */ + +/* + * Defines for SC PM Power Mode + */ +#define IMX_SC_PM_PW_MODE_OFF 0 /* Power off */ +#define IMX_SC_PM_PW_MODE_STBY 1 /* Power in standby */ +#define IMX_SC_PM_PW_MODE_LP 2 /* Power in low-power */ +#define IMX_SC_PM_PW_MODE_ON 3 /* Power on */ + +/* + * Defines for SC PM CLK + */ +#define IMX_SC_PM_CLK_SLV_BUS 0 /* Slave bus clock */ +#define IMX_SC_PM_CLK_MST_BUS 1 /* Master bus clock */ +#define IMX_SC_PM_CLK_PER 2 /* Peripheral clock */ +#define IMX_SC_PM_CLK_PHY 3 /* Phy clock */ +#define IMX_SC_PM_CLK_MISC 4 /* Misc clock */ +#define IMX_SC_PM_CLK_MISC0 0 /* Misc 0 clock */ +#define IMX_SC_PM_CLK_MISC1 1 /* Misc 1 clock */ +#define IMX_SC_PM_CLK_MISC2 2 /* Misc 2 clock */ +#define IMX_SC_PM_CLK_MISC3 3 /* Misc 3 clock */ +#define IMX_SC_PM_CLK_MISC4 4 /* Misc 4 clock */ +#define IMX_SC_PM_CLK_CPU 2 /* CPU clock */ +#define IMX_SC_PM_CLK_PLL 4 /* PLL */ +#define IMX_SC_PM_CLK_BYPASS 4 /* Bypass clock */ + +/* + * Defines for SC PM CLK Parent + */ +#define IMX_SC_PM_PARENT_XTAL 0 /* Parent is XTAL. */ +#define IMX_SC_PM_PARENT_PLL0 1 /* Parent is PLL0 */ +#define IMX_SC_PM_PARENT_PLL1 2 /* Parent is PLL1 or PLL0/2 */ +#define IMX_SC_PM_PARENT_PLL2 3 /* Parent in PLL2 or PLL0/4 */ +#define IMX_SC_PM_PARENT_BYPS 4 /* Parent is a bypass clock. */ + +#endif /* _SC_PM_API_H */ -- cgit v1.2.3 From 475b08734edb3695b9396950c87e75d7c72278a8 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 7 Nov 2018 18:49:38 -0800 Subject: platform/chrome: straighten out cros_ec_get_{next,host}_event() error codes cros_ec_get_next_event() is documented to return 0 for success and negative for errors. It currently returns negative for some errors, and non-negative (number of bytes received) for success (including some "no data available" responses as zero). This mostly works out OK, because the callers were more or less ignoring the documentation, and only treating positive values as success (and indepdently checking the modification of 'wakeup'). Let's button this up by avoiding pretending to handle event/wakeup distinctions when no event info was retrieved (i.e., returned 0 bytes). And fix the documentation of cros_ec_get_host_event() and cros_ec_get_next_event() to accurately describe their behavior. Signed-off-by: Brian Norris Acked-by: Lee Jones Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index e44e3ec8a9c7..de8b588c8776 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -317,7 +317,9 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev); * @wake_event: Pointer to a bool set to true upon return if the event might be * treated as a wake event. Ignored if null. * - * Return: 0 on success or negative error code. + * Return: negative error code on errors; 0 for no data; or else number of + * bytes received (i.e., an event was retrieved successfully). Event types are + * written out to @ec_dev->event_data.event_type on success. */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); @@ -329,7 +331,7 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); * events raised and call the functions in the ec notifier. This function * is a helper to know which events are raised. * - * Return: 0 on success or negative error code. + * Return: 0 on error or non-zero bitmask of one or more EC_HOST_EVENT_*. */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); -- cgit v1.2.3 From 98b0e5f6842a9982a793f0837b1bd1495542a3d8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 12 Nov 2018 14:58:10 -0800 Subject: net: sched: provide notification for graft on root Drivers are currently not notified when a Qdisc is grafted as root. This requires special casing Qdiscs added with parent = TC_H_ROOT in the driver. Also there is no notification sent to the driver when an existing Qdisc is grafted as root. Add this very simple notifications, drivers should now be able to track their Qdisc tree fully. Signed-off-by: Jakub Kicinski Reviewed-by: John Hurley Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 487fa5e0e165..97b4233120e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -845,6 +845,7 @@ enum tc_setup_type { TC_SETUP_QDISC_PRIO, TC_SETUP_QDISC_MQ, TC_SETUP_QDISC_ETF, + TC_SETUP_ROOT_QDISC, }; /* These structures hold the attributes of bpf state that are being passed -- cgit v1.2.3 From c4fe17e0e3a346cc855b7b41c00ff7b04c56d32b Mon Sep 17 00:00:00 2001 From: Arun Kumar Neelakantam Date: Wed, 3 Oct 2018 11:10:02 +0530 Subject: soc: qcom: qmi_interface: Limit txn ids to U16_MAX Txn IDs created up to INT_MAX cause overflow while storing the IDs in u16 type supported by QMI header. Limit the txn IDs max value to U16_MAX to avoid overflow. Signed-off-by: Arun Kumar Neelakantam Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/soc/qcom/qmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/qmi.h b/include/linux/soc/qcom/qmi.h index f4de33654a60..5efa2b67fa55 100644 --- a/include/linux/soc/qcom/qmi.h +++ b/include/linux/soc/qcom/qmi.h @@ -166,7 +166,7 @@ struct qmi_ops { struct qmi_txn { struct qmi_handle *qmi; - int id; + u16 id; struct mutex lock; struct completion completion; -- cgit v1.2.3 From c9a983058ad6ffa59b950b87e4888a43c12ebb26 Mon Sep 17 00:00:00 2001 From: Alice Michael Date: Fri, 26 Oct 2018 14:33:30 -0700 Subject: virtchnl: white space and reorder White space change. Move the check on the virtchnl_vsi_queue_config_info struct to be close to the struct like all the other similar checks. This keeps it clearer and easier to read. Signed-off-by: Alice Michael Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b2488055fd1d..3130dec40b93 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -171,7 +171,7 @@ struct virtchnl_msg { VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_msg); -/* Message descriptions and data structures.*/ +/* Message descriptions and data structures. */ /* VIRTCHNL_OP_VERSION * VF posts its version number to the PF. PF responds with its version number @@ -342,6 +342,8 @@ struct virtchnl_vsi_queue_config_info { struct virtchnl_queue_pair_info qpair[1]; }; +VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); + /* VIRTCHNL_OP_REQUEST_QUEUES * VF sends this message to request the PF to allocate additional queues to * this VF. Each VF gets a guaranteed number of queues on init but asking for @@ -357,8 +359,6 @@ struct virtchnl_vf_res_request { u16 num_queue_pairs; }; -VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); - /* VIRTCHNL_OP_CONFIG_IRQ_MAP * VF uses this message to map vectors to queues. * The rxq_map and txq_map fields are bitmaps used to indicate which queues -- cgit v1.2.3 From 843faff87af261bf55eda719a06087af0486a168 Mon Sep 17 00:00:00 2001 From: Alice Michael Date: Fri, 26 Oct 2018 14:33:31 -0700 Subject: virtchnl: Fix off by one error When calculating the valid length for a VIRTCHNL_OP_ENABLE_CHANNELS message, we accidentally allowed messages with one extra virtchnl_channel_info structure on the end. This happened due to an off by one error, because we forgot that valid_len already accounted for one virtchnl_channel_info structure, so we need to subtract one from the num_tc value. Signed-off-by: Alice Michael Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 3130dec40b93..7605b5919c3a 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -819,8 +819,8 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, if (msglen >= valid_len) { struct virtchnl_tc_info *vti = (struct virtchnl_tc_info *)msg; - valid_len += vti->num_tc * - sizeof(struct virtchnl_channel_info); + valid_len += (vti->num_tc - 1) * + sizeof(struct virtchnl_channel_info); if (vti->num_tc == 0) err_msg_format = true; } -- cgit v1.2.3 From 43fac3238c1d9363b2a93d8d56c2be0c29c64e6c Mon Sep 17 00:00:00 2001 From: Tony Xie Date: Tue, 30 Oct 2018 18:07:56 +0800 Subject: regmap: add a new macro:REGMAP_IRQ_REG_LINE(_id, _reg_bits) if there are lots of irqs for a device and the register addresses for these irqs is continuous, we can use this macro to initialize regmap_irq value. Signed-off-by: Tony Xie Signed-off-by: Mark Brown --- include/linux/regmap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index a367d59c301d..3930f3331652 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1110,6 +1110,12 @@ struct regmap_irq { #define REGMAP_IRQ_REG(_irq, _off, _mask) \ [_irq] = { .reg_offset = (_off), .mask = (_mask) } +#define REGMAP_IRQ_REG_LINE(_id, _reg_bits) \ + [_id] = { \ + .mask = BIT((_id) % (_reg_bits)), \ + .reg_offset = (_id) / (_reg_bits), \ + } + /** * struct regmap_irq_chip - Description of a generic regmap irq_chip. * -- cgit v1.2.3 From 7ff4f8035695984c513598e2d49c8277d5d234ca Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 14 Nov 2018 15:22:49 -0700 Subject: block: remove dead queue members No more users of ->in_flight[] or ->nr_sorted, get rid of them. Fixes: a1ce35fa4985 ("block: remove dead elevator code") Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e67ad2dd025e..c961329be96b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -486,9 +486,6 @@ struct request_queue { unsigned int dma_pad_mask; unsigned int dma_alignment; - unsigned int nr_sorted; - unsigned int in_flight[2]; - unsigned int rq_timeout; int poll_nsec; -- cgit v1.2.3 From 1be7aa9b6eb91975800b880481f077c01ae01a26 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 15 Nov 2018 09:48:18 -0800 Subject: Input: ad7879 - drop platform data support This driver supports configuration via platform data but absolutely nothing in the upstream kernel uses it. Since this configuration allows harmful practices such as encoding the GPIO base for the chip, delete platform data support so that no new platform using it gets introduced. Also: include the right driver header, not . Signed-off-by: Linus Walleij Acked-by: Michael Hennerich Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/ad7879.h | 42 ------------------------------------ 1 file changed, 42 deletions(-) delete mode 100644 include/linux/platform_data/ad7879.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ad7879.h b/include/linux/platform_data/ad7879.h deleted file mode 100644 index 6655cc8453ac..000000000000 --- a/include/linux/platform_data/ad7879.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* linux/platform_data/ad7879.h */ - -/* Touchscreen characteristics vary between boards and models. The - * platform_data for the device's "struct device" holds this information. - * - * It's OK if the min/max values are zero. - */ -struct ad7879_platform_data { - u16 model; /* 7879 */ - u16 x_plate_ohms; - u16 x_min, x_max; - u16 y_min, y_max; - u16 pressure_min, pressure_max; - - bool swap_xy; /* swap x and y axes */ - - /* [0..255] 0=OFF Starts at 1=550us and goes - * all the way to 9.440ms in steps of 35us. - */ - u8 pen_down_acc_interval; - /* [0..15] Starts at 0=128us and goes all the - * way to 4.096ms in steps of 128us. - */ - u8 first_conversion_delay; - /* [0..3] 0 = 2us, 1 = 4us, 2 = 8us, 3 = 16us */ - u8 acquisition_time; - /* [0..3] Average X middle samples 0 = 2, 1 = 4, 2 = 8, 3 = 16 */ - u8 averaging; - /* [0..3] Perform X measurements 0 = OFF, - * 1 = 4, 2 = 8, 3 = 16 (median > averaging) - */ - u8 median; - /* 1 = AUX/VBAT/GPIO export GPIO to gpiolib - * requires CONFIG_GPIOLIB - */ - bool gpio_export; - /* identifies the first GPIO number handled by this chip; - * or, if negative, requests dynamic ID allocation. - */ - s32 gpio_base; -}; -- cgit v1.2.3 From 8f4236d9008b0973a8281256ccfde6913cdec6cb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:04 +0100 Subject: block: remove QUEUE_FLAG_BYPASS and ->bypass Unused since the removal of the legacy request code. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 6 +----- include/linux/blkdev.h | 3 --- 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1b299e025e83..2c68efc603bd 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -325,16 +325,12 @@ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. This function should be called - * under RCU read lock and is guaranteed to return %NULL if @q is bypassing - * - see blk_queue_bypass_start() for details. + * under RCU read loc. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); - - if (unlikely(blk_queue_bypass(q))) - return NULL; return __blkg_lookup(blkcg, q, false); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c961329be96b..dd1e53fd4acf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct mutex sysfs_lock; - int bypass_depth; atomic_t mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) @@ -586,7 +585,6 @@ struct request_queue { #define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ #define QUEUE_FLAG_DYING 2 /* queue being torn down */ -#define QUEUE_FLAG_BYPASS 3 /* act as dumb FIFO queue */ #define QUEUE_FLAG_BIDI 4 /* queue supports bidi requests */ #define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ @@ -630,7 +628,6 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) -#define blk_queue_bypass(q) test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ -- cgit v1.2.3 From 079076b3416e78ba2bb3ce38e05e320c388c3120 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:05 +0100 Subject: block: remove deadline __deadline manipulation helpers No users left since the removal of the legacy request interface, we can remove all the magic bit stealing now and make it a normal field. But use WRITE_ONCE/READ_ONCE on the new deadline field, given that we don't seem to have any mechanism to guarantee a new value actually gets seen by other threads. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dd1e53fd4acf..60507ab7b358 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -224,9 +224,7 @@ struct request { refcount_t ref; unsigned int timeout; - - /* access through blk_rq_set_deadline, blk_rq_deadline */ - unsigned long __deadline; + unsigned long deadline; union { struct __call_single_data csd; -- cgit v1.2.3 From 57d74df90783f6a6b3e79dfdd2a567ce5db3b790 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:07 +0100 Subject: block: use atomic bitops for ->queue_flags ->queue_flags is generally not set or cleared in the fast path, and also generally set or cleared one flag at a time. Make use of the normal atomic bitops for it so that we don't need to take the queue_lock, which is otherwise mostly unused in the core block layer now. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60507ab7b358..30d8e0fbd104 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -621,7 +621,6 @@ struct request_queue { void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); -bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) -- cgit v1.2.3 From 6d46964230d182c4b6097379738849a809d791dc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:18 +0100 Subject: block: remove the lock argument to blk_alloc_queue_node With the legacy request path gone there is no real need to override the queue_lock. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 30d8e0fbd104..c4a3a660e3f0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1122,8 +1122,7 @@ extern long nr_blockdev_pages(void); bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); -struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, - spinlock_t *lock); +struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); -- cgit v1.2.3 From 0d945c1f966b2bcb67bb12be749da0a7fb00201b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Nov 2018 12:17:28 -0700 Subject: block: remove the queue_lock indirection With the legacy request path gone there is no good reason to keep queue_lock as a pointer, we can always use the embedded lock now. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Fixed floppy and blk-cgroup missing conversions and half done edits. Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 4 ++-- include/linux/blkdev.h | 8 +------- 2 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 2c68efc603bd..a9e2e2037129 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -717,11 +717,11 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_create(blkcg, q); if (IS_ERR(blkg)) blkg = NULL; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } throtl = blk_throtl_bio(q, blkg, bio); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c4a3a660e3f0..1d185f1fc333 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -446,13 +446,7 @@ struct request_queue { */ gfp_t bounce_gfp; - /* - * protects queue structures from reentrancy. ->__queue_lock should - * _never_ be used directly, it is queue private. always use - * ->queue_lock. - */ - spinlock_t __queue_lock; - spinlock_t *queue_lock; + spinlock_t queue_lock; /* * queue kobject -- cgit v1.2.3 From 7fe50ac83f4319c18ed7c634d85cad16bd0bf509 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 12 Nov 2018 14:47:18 -0800 Subject: net: dump more useful information in netdev_rx_csum_fault() Currently netdev_rx_csum_fault() only shows a device name, we need more information about the skb for debugging csum failures. Sample output: ens3: hw csum failure dev features: 0x0000000000014b89 skb len=84 data_len=0 pkt_type=0 gso_size=0 gso_type=0 nr_frags=0 ip_summed=0 csum=0 csum_complete_sw=0 csum_valid=0 csum_level=0 Note, I use pr_err() just to be consistent with the existing one. Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 97b4233120e4..917ae7b6263e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4343,9 +4343,10 @@ static inline bool can_checksum_protocol(netdev_features_t features, } #ifdef CONFIG_BUG -void netdev_rx_csum_fault(struct net_device *dev); +void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb); #else -static inline void netdev_rx_csum_fault(struct net_device *dev) +static inline void netdev_rx_csum_fault(struct net_device *dev, + struct sk_buff *skb) { } #endif -- cgit v1.2.3 From 1d2f46814d20a55c45ac171739b6885826e0c793 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 15 Nov 2018 09:01:18 +0100 Subject: regulator: wm8994: Pass descriptor instead of GPIO number Instead of passing a global GPIO number for the enable GPIO, pass a descriptor looked up from the device tree node or the board file decriptor table for the regulator. There is a single board file passing the GPIOs for LDO1 and LDO2 through platform data, so augment this to pass descriptors associated with the i2c device as well. The special GPIO enable DT property for the enable GPIO is nonstandard but this was accomodated in commit 6a537d48461deacc57c07ed86d9915e5aa4b3539 "gpio: of: Support regulator nonstandard GPIO properties". Cc: patches@opensource.cirrus.com Acked-by: Charles Keepax Acked-by: Lee Jones Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/mfd/wm8994/pdata.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h index b19c370fe81a..f346167c0e00 100644 --- a/include/linux/mfd/wm8994/pdata.h +++ b/include/linux/mfd/wm8994/pdata.h @@ -20,9 +20,6 @@ #define WM8994_NUM_AIF 3 struct wm8994_ldo_pdata { - /** GPIOs to enable regulator, 0 or less if not available */ - int enable; - const struct regulator_init_data *init_data; }; -- cgit v1.2.3 From 0a020d416d0af0b0c782e2a8363896e756e9121e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Nov 2018 08:22:28 +0000 Subject: lib: introduce initial implementation of object aggregation manager This lib tracks objects which could be of two types: 1) root object 2) nested object - with a "delta" which differentiates it from the associated root object The objects are tracked by a hashtable and reference-counted. User is responsible of implementing callbacks to create/destroy root entity related to each root object and callback to create/destroy nested object delta. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/objagg.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 include/linux/objagg.h (limited to 'include/linux') diff --git a/include/linux/objagg.h b/include/linux/objagg.h new file mode 100644 index 000000000000..34f38c186ea0 --- /dev/null +++ b/include/linux/objagg.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */ + +#ifndef _OBJAGG_H +#define _OBJAGG_H + +struct objagg_ops { + size_t obj_size; + void * (*delta_create)(void *priv, void *parent_obj, void *obj); + void (*delta_destroy)(void *priv, void *delta_priv); + void * (*root_create)(void *priv, void *obj); + void (*root_destroy)(void *priv, void *root_priv); +}; + +struct objagg; +struct objagg_obj; + +const void *objagg_obj_root_priv(const struct objagg_obj *objagg_obj); +const void *objagg_obj_delta_priv(const struct objagg_obj *objagg_obj); +const void *objagg_obj_raw(const struct objagg_obj *objagg_obj); + +struct objagg_obj *objagg_obj_get(struct objagg *objagg, void *obj); +void objagg_obj_put(struct objagg *objagg, struct objagg_obj *objagg_obj); +struct objagg *objagg_create(const struct objagg_ops *ops, void *priv); +void objagg_destroy(struct objagg *objagg); + +struct objagg_obj_stats { + unsigned int user_count; + unsigned int delta_user_count; /* includes delta object users */ +}; + +struct objagg_obj_stats_info { + struct objagg_obj_stats stats; + struct objagg_obj *objagg_obj; /* associated object */ + bool is_root; +}; + +struct objagg_stats { + unsigned int stats_info_count; + struct objagg_obj_stats_info stats_info[]; +}; + +const struct objagg_stats *objagg_stats_get(struct objagg *objagg); +void objagg_stats_put(const struct objagg_stats *objagg_stats); + +#endif -- cgit v1.2.3 From 0145b50566e7de5637e80ecba96c7f0e6fff1aad Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 31 Oct 2018 15:20:05 +0100 Subject: iio/hid-sensors: Fix IIO_CHAN_INFO_RAW returning wrong values for signed numbers Before this commit sensor_hub_input_attr_get_raw_value() failed to take the signedness of 16 and 8 bit values into account, returning e.g. 65436 instead of -100 for the z-axis reading of an accelerometer. This commit adds a new is_signed parameter to the function and makes all callers pass the appropriate value for this. While at it, this commit also fixes up some neighboring lines where statements were needlessly split over 2 lines to improve readability. Signed-off-by: Hans de Goede Acked-by: Srinivas Pandruvada Acked-by: Benjamin Tissoires Cc: Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-hub.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 331dc377c275..dc12f5c4b076 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -177,6 +177,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @attr_usage_id: Attribute usage id as per spec * @report_id: Report id to look for * @flag: Synchronous or asynchronous read +* @is_signed: If true then fields < 32 bits will be sign-extended * * Issues a synchronous or asynchronous read request for an input attribute. * Returns data upto 32 bits. @@ -190,7 +191,8 @@ enum sensor_hub_read_flags { int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag + enum sensor_hub_read_flags flag, + bool is_signed ); /** -- cgit v1.2.3 From 344e9ffcbd1898e1dc04085564a6e05c30ea8199 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Nov 2018 12:22:51 -0700 Subject: block: add queue_is_mq() helper Various spots check for q->mq_ops being non-NULL, but provide a helper to do this instead. Where the ->mq_ops != NULL check is redundant, remove it. Since mq == rq-based now that legacy is gone, get rid of the queue_is_rq_based() and just use queue_is_mq() everywhere. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1d185f1fc333..41aaa05e42c1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -656,11 +656,7 @@ static inline bool blk_account_rq(struct request *rq) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) -/* - * Driver can handle struct request, if it either has an old style - * request_fn defined, or is blk-mq based. - */ -static inline bool queue_is_rq_based(struct request_queue *q) +static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; } -- cgit v1.2.3 From 0619317ff8baa2da9238191ad5167ed3618c16d9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 13 Nov 2018 21:16:54 -0700 Subject: block: add polled wakeup task helper If we're polling for IO on a device that doesn't use interrupts, then IO completion loop (and wake of task) is done by submitting task itself. If that is the case, then we don't need to enter the wake_up_process() function, we can simply mark ourselves as TASK_RUNNING. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 41aaa05e42c1..91c44f7a7f62 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1772,4 +1772,17 @@ static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, #endif /* CONFIG_BLOCK */ +static inline void blk_wake_io_task(struct task_struct *waiter) +{ + /* + * If we're polling, the task itself is doing the completions. For + * that case, we don't need to signal a wakeup, it's enough to just + * mark us as RUNNING. + */ + if (waiter == current) + __set_current_state(TASK_RUNNING); + else + wake_up_process(waiter); +} + #endif -- cgit v1.2.3 From 2b78eae147a13ab2ca7caa121dd3fca2eecf8613 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 16 Nov 2018 09:10:01 +0100 Subject: block: remove the rq_alloc_data request_queue field Reviewed-by: Omar Sandoval Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 91c44f7a7f62..1ad6eafc43f2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -567,7 +567,6 @@ struct request_queue { bool mq_sysfs_init_done; size_t cmd_size; - void *rq_alloc_data; struct work_struct release_work; -- cgit v1.2.3 From 49b623732e4af1853186ecf859e2c371228074af Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Wed, 7 Nov 2018 16:45:21 +0100 Subject: iio: st-accel: add support for lis3de This commit add support for STMicroelectronics lis3de accelerometer. Datasheet for this device can be found here: https://www.st.com/resource/en/datasheet/lis3de.pdf Signed-off-by: Heiko Stuebner Acked-by: Rob Herring Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index f9bd6e8ab138..8092b8e7f37e 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -40,7 +40,7 @@ #define ST_SENSORS_DEFAULT_STAT_ADDR 0x27 #define ST_SENSORS_MAX_NAME 17 -#define ST_SENSORS_MAX_4WAI 7 +#define ST_SENSORS_MAX_4WAI 8 #define ST_SENSORS_LSM_CHANNELS(device_type, mask, index, mod, \ ch2, s, endian, rbits, sbits, addr) \ -- cgit v1.2.3 From c91c1c844ebd868ad15bcfc866879fca1079234a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 11 Nov 2018 15:15:33 +0100 Subject: iio: imu: st_lsm6dsx: add i2c embedded controller support i2c controller embedded in lsm6dx series can connect up to four slave devices using accelerometer sensor as trigger for i2c read/write operations. Introduce sensor hub support for lsm6dso sensor. Add register map for lis2mdl magnetometer sensor. In order to perform single read/write operations st_lsm6dsx driver relies on SLV0 channel (hw FIFO is not supported yet) Signed-off-by: Lorenzo Bianconi Signed-off-by: Jonathan Cameron --- include/linux/platform_data/st_sensors_pdata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h index f8274b0c6888..728193111c2f 100644 --- a/include/linux/platform_data/st_sensors_pdata.h +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -18,11 +18,13 @@ * Accelerometer DRDY on LSM330 available only on pin 1 (see datasheet). * @open_drain: set the interrupt line to be open drain if possible. * @spi_3wire: enable spi-3wire mode. + * @pullups: enable/disable i2c controller pullup resistors. */ struct st_sensors_platform_data { u8 drdy_int_pin; bool open_drain; bool spi_3wire; + bool pullups; }; #endif /* ST_SENSORS_PDATA_H */ -- cgit v1.2.3 From eee3919c5f2949a8b7b1e9fa239d153be1538656 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 12 Nov 2018 15:10:28 +0100 Subject: gpio: drop broken to_gpio_irq_chip() helper Drop the broken to_gpio_irq_chip() container_of() helper, which would break the build for anyone who tries to use it. Specifically, struct gpio_irq_chip only holds a pointer to a struct irq_chip so using container_of() on an irq-chip pointer makes no sense. Fixes: da80ff81a8f5 ("gpio: Move irqchip into struct gpio_irq_chip") Cc: Thierry Reding Cc: Grygorii Strashko Signed-off-by: Johan Hovold Reviewed-by: Bartosz Golaszewski Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f70d976e1395..9c8d5d491680 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -166,11 +166,6 @@ struct gpio_irq_chip { */ void (*irq_disable)(struct irq_data *data); }; - -static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *chip) -{ - return container_of(chip, struct gpio_irq_chip, chip); -} #endif /** -- cgit v1.2.3 From 5109f9fd6a76116090b34a192d4a957d2ad0621e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Sat, 10 Nov 2018 19:58:34 +0100 Subject: net/skbuff: add macros for VLAN_PRESENT bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Wrap VLAN_PRESENT bit using macro like PKT_TYPE_* and CLONED_*, as used by BPF code. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7dcfb5591dc3..99f38779332c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -816,6 +816,12 @@ struct sk_buff { __u32 priority; int skb_iif; __u32 hash; +#define PKT_VLAN_PRESENT_BIT 4 // CFI (12-th bit) in TCI +#ifdef __BIG_ENDIAN +#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, vlan_tci) +#else +#define PKT_VLAN_PRESENT_OFFSET() (offsetof(struct sk_buff, vlan_tci) + 1) +#endif __be16 vlan_proto; __u16 vlan_tci; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) -- cgit v1.2.3 From 0c4b2d370514cb4f3454dd3b18f031d2651fab73 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Sat, 10 Nov 2018 19:58:36 +0100 Subject: net: remove VLAN_TAG_PRESENT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace VLAN_TAG_PRESENT with single bit flag and free up VLAN.CFI overload. Now VLAN.CFI is visible in networking stack and can be passed around intact. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 11 ++++++----- include/linux/skbuff.h | 16 +++++++++------- 2 files changed, 15 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 1be5230921b5..7a541eadf78e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -66,7 +66,6 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator */ -#define VLAN_TAG_PRESENT VLAN_CFI_MASK #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 @@ -78,8 +77,8 @@ static inline bool is_vlan_dev(const struct net_device *dev) return dev->priv_flags & IFF_802_1Q_VLAN; } -#define skb_vlan_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT) -#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) +#define skb_vlan_tag_present(__skb) ((__skb)->vlan_present) +#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) @@ -480,7 +479,7 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { - skb->vlan_tci = 0; + skb->vlan_present = 0; } /** @@ -492,6 +491,7 @@ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { + dst->vlan_present = src->vlan_present; dst->vlan_proto = src->vlan_proto; dst->vlan_tci = src->vlan_tci; } @@ -526,7 +526,8 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; - skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci; + skb->vlan_tci = vlan_tci; + skb->vlan_present = 1; } /** diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 99f38779332c..b9aa0d1b21cf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -777,6 +777,14 @@ struct sk_buff { __u8 encap_hdr_csum:1; __u8 csum_valid:1; +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_VLAN_PRESENT_BIT 7 +#else +#define PKT_VLAN_PRESENT_BIT 0 +#endif +#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) + __u8 __pkt_vlan_present_offset[0]; + __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; @@ -784,8 +792,8 @@ struct sk_buff { #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif - __u8 ipvs_property:1; + __u8 ipvs_property:1; __u8 inner_protocol_type:1; __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV @@ -816,12 +824,6 @@ struct sk_buff { __u32 priority; int skb_iif; __u32 hash; -#define PKT_VLAN_PRESENT_BIT 4 // CFI (12-th bit) in TCI -#ifdef __BIG_ENDIAN -#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, vlan_tci) -#else -#define PKT_VLAN_PRESENT_OFFSET() (offsetof(struct sk_buff, vlan_tci) + 1) -#endif __be16 vlan_proto; __u16 vlan_tci; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) -- cgit v1.2.3 From 7f600f14dfac4ba4aee6283a415cdad2925d7791 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 12 Nov 2018 18:05:24 -0800 Subject: net: remove unused skb_send_sock() Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b9aa0d1b21cf..a2e8297a5b00 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3335,7 +3335,6 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); -int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, -- cgit v1.2.3 From f0aef2d018643187101199d8af1dd5ea3a43a3b7 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 13 Nov 2018 13:20:24 +0200 Subject: iio: ad_sigma_delta: Allow to provide custom data register address Some newer devices from the Sigma-Delta ADC family do have their data register at a different address than the current default address. Add a parameter to the ad_sigma_delta_info struct which allows to override the default address. Signed-off-by: Lars-Peter Clausen Signed-off-by: Stefan Popa Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 730ead1a46df..7e84351fa2c0 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -39,6 +39,8 @@ struct iio_dev; * if there is just one read-only sample data shift register. * @addr_shift: Shift of the register address in the communications register. * @read_mask: Mask for the communications register having the read bit set. + * @data_reg: Address of the data register, if 0 the default address of 0x3 will + * be used. */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); @@ -47,6 +49,7 @@ struct ad_sigma_delta_info { bool has_registers; unsigned int addr_shift; unsigned int read_mask; + unsigned int data_reg; }; /** -- cgit v1.2.3 From 9a5ee462302512b7f3929c19f0711715613ac418 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 16 Nov 2018 07:24:24 -0800 Subject: net: align pcpu_sw_netstats and pcpu_lstats structs Do not risk spanning these small structures on two cache lines, it is absolutely not worth it. For 32bit arches, the hint might not be enough, but we do not really care anymore. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 917ae7b6263e..086e64d88597 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2389,13 +2389,13 @@ struct pcpu_sw_netstats { u64 tx_packets; u64 tx_bytes; struct u64_stats_sync syncp; -}; +} __aligned(4 * sizeof(u64)); struct pcpu_lstats { u64 packets; u64 bytes; struct u64_stats_sync syncp; -}; +} __aligned(2 * sizeof(u64)); #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ -- cgit v1.2.3 From 0c5eaa7749726b2e4667a5e3668c3eb8516e7440 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 16 Nov 2018 15:06:55 -0600 Subject: of: Drop full path from full_name for PDT systems Now that there are no more users of path_component_name for Sparc outside of the PDT code and all users of device_node.full_name are converted to use "%pOF" printf specifier, we can align Sparc with FDT and store just the base node name and unit address in full_name. This makes path_component_name redundant, so it can be removed. As full_name is used by printf specifiers, set it as early as possible. Cc: Frank Rowand Signed-off-by: Rob Herring Signed-off-by: David S. Miller --- 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 a5aee3c438ad..0fe5bef81a7e 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -66,7 +66,6 @@ struct device_node { unsigned long _flags; void *data; #if defined(CONFIG_SPARC) - const char *path_component_name; unsigned int unique_id; struct of_irq_controller *irq_trans; #endif -- cgit v1.2.3 From f8702f9e4aa7b45131af3df5531d6e3835269141 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 19 Nov 2018 00:56:17 +0300 Subject: regulator: core: Use ww_mutex for regulators locking Wait/wound mutex shall be used in order to avoid lockups on locking of coupled regulators. Signed-off-by: Dmitry Osipenko Suggested-by: Lucas Stach Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index a05d37d0efa1..7065031f0846 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -20,6 +20,7 @@ #include #include #include +#include struct gpio_desc; struct regmap; @@ -462,7 +463,7 @@ struct regulator_dev { struct coupling_desc coupling_desc; struct blocking_notifier_head notifier; - struct mutex mutex; /* consumer lock */ + struct ww_mutex mutex; /* consumer lock */ struct task_struct *mutex_owner; int ref_cnt; struct module *owner; @@ -545,4 +546,7 @@ int regulator_set_active_discharge_regmap(struct regulator_dev *rdev, bool enable); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data); +void regulator_lock(struct regulator_dev *rdev); +void regulator_unlock(struct regulator_dev *rdev); + #endif -- cgit v1.2.3 From 85f4d4b65fdd67f1d6dc9eeb1d91923cef07eb6a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 6 Nov 2018 13:30:55 -0700 Subject: block: have ->poll_fn() return number of entries polled We currently only really support sync poll, ie poll with 1 IO in flight. This prepares us for supporting async poll. Note that the returned value isn't necessarily 100% accurate. If poll races with IRQ completion, we assume that the fact that the task is now runnable means we found at least one entry. In reality it could be more than 1, or not even 1. This is fine, the caller will just need to take this into account. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1ad6eafc43f2..e97c0a3b2262 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -283,7 +283,7 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); -typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); +typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; typedef int (dma_drain_needed_fn)(struct request *); -- cgit v1.2.3 From 0fe3c7fceb500de2d0adfb9dcf292580cd43ea38 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Fri, 16 Nov 2018 12:16:35 -0500 Subject: audit: localize audit_log_session_info prototype The audit_log_session_info() function is only used in kernel/audit*, so move its prototype to kernel/audit.h Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 9334fbef7bae..58cf665f597e 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -115,8 +115,6 @@ extern int audit_classify_compat_syscall(int abi, unsigned syscall); struct filename; -extern void audit_log_session_info(struct audit_buffer *ab); - #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 -- cgit v1.2.3 From 92f806d678e5136e4777b21e5ed5368482ac9ea9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 19 Nov 2018 11:37:31 -0700 Subject: nvme-fc: remove ->poll implementation It's specifically looking for a given request, which we will not be supporting going forward. Also kill the qla2xxx poll implementation as that's the only user of the nvme-fc poll, and the now unused ->poll_queue() hook. Reviewed-by: Christoph Hellwig Reviewed-by: James Smart Signed-off-by: Jens Axboe --- include/linux/nvme-fc-driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 496ff759f84c..f4ab3b1925ac 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -403,7 +403,6 @@ struct nvme_fc_port_template { void **handle); void (*delete_queue)(struct nvme_fc_local_port *, unsigned int qidx, void *handle); - void (*poll_queue)(struct nvme_fc_local_port *, void *handle); int (*ls_req)(struct nvme_fc_local_port *, struct nvme_fc_remote_port *, struct nvmefc_ls_req *); -- cgit v1.2.3 From e2b3fa5af70c1e646270f6c7c799414f5e904d7a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 20 Nov 2018 10:52:34 +0900 Subject: block: Remove bio->bi_ioc bio->bi_ioc is never set so always NULL. Remove references to it in bio_disassociate_task() and in rq_ioc() and delete this field from struct bio. With this change, rq_ioc() always returns current->io_context without the need for a bio argument. Further simplify the code and make it more readable by also removing this helper, which also allows to simplify blk_mq_sched_assign_ioc() by removing its bio argument. Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Adam Manzanares Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index dbdbfbd6a987..c0ba1a038ff3 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -174,10 +174,9 @@ struct bio { void *bi_private; #ifdef CONFIG_BLK_CGROUP /* - * Optional ioc and css associated with this bio. Put on bio + * Optional css associated with this bio. Put on bio * release. Read comment on top of bio_associate_current(). */ - struct io_context *bi_ioc; struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; -- cgit v1.2.3 From 64845a1ddd655574886eb48e9a5eaeeb9b05bf0d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 20 Nov 2018 10:52:35 +0900 Subject: block: Introduce get_current_ioprio() Define get_current_ioprio() as an inline helper to obtain the caller I/O priority from its task I/O context. Use this helper in blk_init_request_from_bio() to set a request ioprio. Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/ioprio.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 9e30ed6443db..e9bfe6972aed 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -70,6 +70,19 @@ static inline int task_nice_ioclass(struct task_struct *task) return IOPRIO_CLASS_BE; } +/* + * If the calling process has set an I/O priority, use that. Otherwise, return + * the default I/O priority. + */ +static inline int get_current_ioprio(void) +{ + struct io_context *ioc = current->io_context; + + if (ioc) + return ioc->ioprio; + return IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); +} + /* * For inheritance, return the highest of the two given priorities */ -- cgit v1.2.3 From 20578bdfd0418efb11ec316229e670d085cd574a Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 20 Nov 2018 10:52:38 +0900 Subject: block: Initialize BIO I/O priority early For the synchronous I/O path case (read(), write() etc system calls), a BIO I/O priority is not initialized until the execution of blk_init_request_from_bio() when the BIO is submitted and a request initialized for the BIO execution. This is due to the ki_ioprio field of the struct kiocb defined on stack being always initialized to IOPRIO_CLASS_NONE, regardless of the calling process I/O context ioprio value set with ioprio_set(). This late initialization can result in the BIO being merged to pending requests even when the I/O priorities differ. Fix this by initializing the ki_iopriority field of on stack struct kiocb using the get_current_ioprio() helper, ensuring that all BIOs allocated and submitted for the system call execution see the correct intended I/O priority early. With this, since a BIO I/O priority is always set to the intended effective value for both the sync and async path, blk_init_request_from_bio() can be simplified. Reviewed-by: Christoph Hellwig Reviewed-by: Adam Manzanares Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c95c0807471f..a1ab233e6469 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2021,7 +2021,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) .ki_filp = filp, .ki_flags = iocb_flags(filp), .ki_hint = ki_hint_validate(file_write_hint(filp)), - .ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0), + .ki_ioprio = get_current_ioprio(), }; } -- cgit v1.2.3 From 890d8d23ec3c9eca847be0593c0cf5f650b97271 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 19 Nov 2018 15:21:42 -0800 Subject: net: sched: gred: add basic Qdisc offload Add basic offload for the GRED Qdisc. Inform the drivers any time Qdisc or virtual queue configuration changes. Signed-off-by: Jakub Kicinski Reviewed-by: John Hurley Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 086e64d88597..4b4207ebd5c0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -846,6 +846,7 @@ enum tc_setup_type { TC_SETUP_QDISC_MQ, TC_SETUP_QDISC_ETF, TC_SETUP_ROOT_QDISC, + TC_SETUP_QDISC_GRED, }; /* These structures hold the attributes of bpf state that are being passed -- cgit v1.2.3 From f1abf67217de91f5cd3c757ae857632ca565099a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 16 Nov 2018 19:19:30 -0800 Subject: regulator: Fix return value of _set_load() stub The stub implementation of _set_load() returns a mode value which is within the bounds of valid return codes for success (the documentation just says that failures are negative error codes) but not sensible or what the actual implementation does. Fix it to just return 0. Reported-by: Cheng-Yi Chiang Signed-off-by: Mark Brown Reviewed-by: Douglas Anderson Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 25602afd4844..f3f76051e8b0 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -508,7 +508,7 @@ static inline int regulator_get_error_flags(struct regulator *regulator, static inline int regulator_set_load(struct regulator *regulator, int load_uA) { - return REGULATOR_MODE_NORMAL; + return 0; } static inline int regulator_allow_bypass(struct regulator *regulator, -- cgit v1.2.3 From 01598ba6b1a863fbd819fc5c36c27886e5072164 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sun, 11 Nov 2018 18:48:44 +0200 Subject: docs/mm: update kmalloc kernel-doc description Add references to GFP documentation and the memory-allocation.rst and remove GFP_USER, GFP_DMA and GFP_NOIO descriptions. While on it slightly change the formatting so that the list of GFP flags will be rendered as "description" in the generated html. Signed-off-by: Mike Rapoport Signed-off-by: Jonathan Corbet --- include/linux/slab.h | 55 ++++++++++++++++++++++++++-------------------------- 1 file changed, 27 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 918f374e7156..4a342eb488f6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -486,48 +486,47 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * - * The @flags argument may be one of: + * The @flags argument may be one of the GFP flags defined at + * include/linux/gfp.h and described at + * :ref:`Documentation/core-api/mm-api.rst ` * - * %GFP_USER - Allocate memory on behalf of user. May sleep. + * The recommended usage of the @flags is described at + * :ref:`Documentation/core-api/memory-allocation.rst ` * - * %GFP_KERNEL - Allocate normal kernel ram. May sleep. + * Below is a brief outline of the most useful GFP flags * - * %GFP_ATOMIC - Allocation will not sleep. May use emergency pools. - * For example, use this inside interrupt handlers. + * %GFP_KERNEL + * Allocate normal kernel ram. May sleep. * - * %GFP_HIGHUSER - Allocate pages from high memory. + * %GFP_NOWAIT + * Allocation will not sleep. * - * %GFP_NOIO - Do not do any I/O at all while trying to get memory. + * %GFP_ATOMIC + * Allocation will not sleep. May use emergency pools. * - * %GFP_NOFS - Do not make any fs calls while trying to get memory. - * - * %GFP_NOWAIT - Allocation will not sleep. - * - * %__GFP_THISNODE - Allocate node-local memory only. - * - * %GFP_DMA - Allocation suitable for DMA. - * Should only be used for kmalloc() caches. Otherwise, use a - * slab created with SLAB_DMA. + * %GFP_HIGHUSER + * Allocate memory from high memory on behalf of user. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * - * %__GFP_HIGH - This allocation has high priority and may use emergency pools. - * - * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail - * (think twice before using). + * %__GFP_HIGH + * This allocation has high priority and may use emergency pools. * - * %__GFP_NORETRY - If memory is not immediately available, - * then give up at once. + * %__GFP_NOFAIL + * Indicate that this allocation is in no way allowed to fail + * (think twice before using). * - * %__GFP_NOWARN - If allocation fails, don't issue any warnings. + * %__GFP_NORETRY + * If memory is not immediately available, + * then give up at once. * - * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail - * eventually. + * %__GFP_NOWARN + * If allocation fails, don't issue any warnings. * - * There are other flags available as well, but these are not intended - * for general use, and so are not documented here. For a full list of - * potential flags, always refer to linux/gfp.h. + * %__GFP_RETRY_MAYFAIL + * Try really hard to succeed the allocation but fail + * eventually. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { -- cgit v1.2.3 From 6afe76a6723975391d06c42a422370a588395f84 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 6 Nov 2018 17:05:30 +0100 Subject: spi: spi-mem: Add missing word in the SPI_MEM_DATA_OUT description Missing 'to' in the SPI_MEM_DATA_OUT description. Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 69ee30456864..867839cc69a7 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -58,7 +58,7 @@ * enum spi_mem_data_dir - describes the direction of a SPI memory data * transfer from the controller perspective * @SPI_MEM_DATA_IN: data coming from the SPI memory - * @SPI_MEM_DATA_OUT: data sent the SPI memory + * @SPI_MEM_DATA_OUT: data sent to the SPI memory */ enum spi_mem_data_dir { SPI_MEM_DATA_IN, -- cgit v1.2.3 From 0ebb261a0b2d090de618a383d2378d4a00834958 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 6 Nov 2018 17:05:31 +0100 Subject: spi: spi-mem: Add SPI_MEM_NO_DATA to the spi_mem_data_dir enum When defining spi_mem_op templates we don't necessarily know the size that will be passed when the template is actually used, and basing the supports_op() check on op->data.nbytes to know whether there will be data transferred for a specific operation is this not possible. Add SPI_MEM_NO_DATA to the spi_mem_data_dir enum so that we can base our checks on op->data.dir instead of op->data.nbytes. Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 867839cc69a7..250b6f5c47c2 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -57,10 +57,12 @@ /** * enum spi_mem_data_dir - describes the direction of a SPI memory data * transfer from the controller perspective + * @SPI_MEM_NO_DATA: no data transferred * @SPI_MEM_DATA_IN: data coming from the SPI memory * @SPI_MEM_DATA_OUT: data sent to the SPI memory */ enum spi_mem_data_dir { + SPI_MEM_NO_DATA, SPI_MEM_DATA_IN, SPI_MEM_DATA_OUT, }; -- cgit v1.2.3 From aa167f3fed0c37e0e4c707d4331d827661f46644 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 6 Nov 2018 17:05:33 +0100 Subject: spi: spi-mem: Add a new API to support direct mapping Most modern SPI controllers can directly map a SPI memory (or a portion of the SPI memory) in the CPU address space. Most of the time this brings significant performance improvements as it automates the whole process of sending SPI memory operations every time a new region is accessed. This new API allows SPI memory drivers to create direct mappings and then use them to access the memory instead of using spi_mem_exec_op(). Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 80 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 250b6f5c47c2..3fe24500c5ee 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -124,6 +124,49 @@ struct spi_mem_op { .data = __data, \ } +/** + * struct spi_mem_dirmap_info - Direct mapping information + * @op_tmpl: operation template that should be used by the direct mapping when + * the memory device is accessed + * @offset: absolute offset this direct mapping is pointing to + * @length: length in byte of this direct mapping + * + * These information are used by the controller specific implementation to know + * the portion of memory that is directly mapped and the spi_mem_op that should + * be used to access the device. + * A direct mapping is only valid for one direction (read or write) and this + * direction is directly encoded in the ->op_tmpl.data.dir field. + */ +struct spi_mem_dirmap_info { + struct spi_mem_op op_tmpl; + u64 offset; + u64 length; +}; + +/** + * struct spi_mem_dirmap_desc - Direct mapping descriptor + * @mem: the SPI memory device this direct mapping is attached to + * @info: information passed at direct mapping creation time + * @nodirmap: set to 1 if the SPI controller does not implement + * ->mem_ops->dirmap_create() or when this function returned an + * error. If @nodirmap is true, all spi_mem_dirmap_{read,write}() + * calls will use spi_mem_exec_op() to access the memory. This is a + * degraded mode that allows spi_mem drivers to use the same code + * no matter whether the controller supports direct mapping or not + * @priv: field pointing to controller specific data + * + * Common part of a direct mapping descriptor. This object is created by + * spi_mem_dirmap_create() and controller implementation of ->create_dirmap() + * can create/attach direct mapping resources to the descriptor in the ->priv + * field. + */ +struct spi_mem_dirmap_desc { + struct spi_mem *mem; + struct spi_mem_dirmap_info info; + unsigned int nodirmap; + void *priv; +}; + /** * struct spi_mem - describes a SPI memory device * @spi: the underlying SPI device @@ -179,10 +222,32 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem) * Note that if the implementation of this function allocates memory * dynamically, then it should do so with devm_xxx(), as we don't * have a ->free_name() function. + * @dirmap_create: create a direct mapping descriptor that can later be used to + * access the memory device. This method is optional + * @dirmap_destroy: destroy a memory descriptor previous created by + * ->dirmap_create() + * @dirmap_read: read data from the memory device using the direct mapping + * created by ->dirmap_create(). The function can return less + * data than requested (for example when the request is crossing + * the currently mapped area), and the caller of + * spi_mem_dirmap_read() is responsible for calling it again in + * this case. + * @dirmap_write: write data to the memory device using the direct mapping + * created by ->dirmap_create(). The function can return less + * data than requested (for example when the request is crossing + * the currently mapped area), and the caller of + * spi_mem_dirmap_write() is responsible for calling it again in + * this case. * * This interface should be implemented by SPI controllers providing an * high-level interface to execute SPI memory operation, which is usually the * case for QSPI controllers. + * + * Note on ->dirmap_{read,write}(): drivers should avoid accessing the direct + * mapping from the CPU because doing that can stall the CPU waiting for the + * SPI mem transaction to finish, and this will make real-time maintainers + * unhappy and might make your system less reactive. Instead, drivers should + * use DMA to access this direct mapping. */ struct spi_controller_mem_ops { int (*adjust_op_size)(struct spi_mem *mem, struct spi_mem_op *op); @@ -191,6 +256,12 @@ struct spi_controller_mem_ops { int (*exec_op)(struct spi_mem *mem, const struct spi_mem_op *op); const char *(*get_name)(struct spi_mem *mem); + int (*dirmap_create)(struct spi_mem_dirmap_desc *desc); + void (*dirmap_destroy)(struct spi_mem_dirmap_desc *desc); + ssize_t (*dirmap_read)(struct spi_mem_dirmap_desc *desc, + u64 offs, size_t len, void *buf); + ssize_t (*dirmap_write)(struct spi_mem_dirmap_desc *desc, + u64 offs, size_t len, const void *buf); }; /** @@ -251,6 +322,15 @@ int spi_mem_exec_op(struct spi_mem *mem, const char *spi_mem_get_name(struct spi_mem *mem); +struct spi_mem_dirmap_desc * +spi_mem_dirmap_create(struct spi_mem *mem, + const struct spi_mem_dirmap_info *info); +void spi_mem_dirmap_destroy(struct spi_mem_dirmap_desc *desc); +ssize_t spi_mem_dirmap_read(struct spi_mem_dirmap_desc *desc, + u64 offs, size_t len, void *buf); +ssize_t spi_mem_dirmap_write(struct spi_mem_dirmap_desc *desc, + u64 offs, size_t len, const void *buf); + int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv, struct module *owner); -- cgit v1.2.3 From 1e86ace4c140fd5a693e266c9b23409358f25381 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:31 -0800 Subject: net/mlx5: EQ, Use the right place to store/read IRQ affinity hint Currently the cpu affinity hint mask for completion EQs is stored and read from the wrong place, since reading and storing is done from the same index, there is no actual issue with that, but internal irq_info for completion EQs stars at MLX5_EQ_VEC_COMP_BASE offset in irq_info array, this patch changes the code to use the correct offset to store and read the IRQ affinity hint. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index aa5963b5d38e..7d4ed995b4ce 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1309,7 +1309,7 @@ enum { static inline const struct cpumask * mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector) { - return dev->priv.irq_info[vector].mask; + return dev->priv.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask; } #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From 4de45c758636c37efd313589f91c739f613fbe7d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:32 -0800 Subject: net/mlx5: EQ, Remove unused fields and structures Some fields and structures are not referenced nor used by the driver, remove them. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7d4ed995b4ce..15cf6727a62d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -398,7 +398,6 @@ struct mlx5_eq { unsigned int irqn; u8 eqn; int nent; - u64 mask; struct list_head list; int index; struct mlx5_rsc_debug *dbg; @@ -478,8 +477,6 @@ struct mlx5_core_srq { }; struct mlx5_eq_table { - void __iomem *update_ci; - void __iomem *update_arm_ci; struct list_head comp_eqs_list; struct mlx5_eq pages_eq; struct mlx5_eq async_eq; -- cgit v1.2.3 From 2883f352571b9b830561ca21b8a666936366a120 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:33 -0800 Subject: net/mlx5: EQ, No need to store eq index as a field eq->index is used only for completion EQs and is assigned to be the completion eq index, it is used only when traversing the completion eqs list, and it can be calculated dynamically, thus remove the eq->index field. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 15cf6727a62d..4b62d71825c1 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -399,7 +399,6 @@ struct mlx5_eq { u8 eqn; int nent; struct list_head list; - int index; struct mlx5_rsc_debug *dbg; enum mlx5_eq_type type; union { -- cgit v1.2.3 From aaa553a64438640ee4e41a2c1027c3435a75c0e7 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:34 -0800 Subject: net/mlx5: EQ, Remove redundant completion EQ list lock Completion EQs list is only modified on driver load/unload, locking is not required, remove it. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4b62d71825c1..852e397c7624 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -484,9 +484,6 @@ struct mlx5_eq_table { struct mlx5_eq pfault_eq; #endif int num_comp_vectors; - /* protect EQs list - */ - spinlock_t lock; }; struct mlx5_uars_page { -- cgit v1.2.3 From d674a9aa434409826b2408609be493739e61e6f6 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:37 -0800 Subject: net/mlx5: EQ, irq_info and rmap belong to eq_table irq_info and rmap are EQ properties of the driver, and only needed for EQ objects, move them to the eq_table EQs database structure. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 852e397c7624..dcc3f7aa8572 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -484,6 +484,10 @@ struct mlx5_eq_table { struct mlx5_eq pfault_eq; #endif int num_comp_vectors; + struct mlx5_irq_info *irq_info; +#ifdef CONFIG_RFS_ACCEL + struct cpu_rmap *rmap; +#endif }; struct mlx5_uars_page { @@ -640,7 +644,6 @@ struct mlx5_port_module_event_stats { struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; - struct mlx5_irq_info *irq_info; /* pages stuff */ struct workqueue_struct *pg_wq; @@ -851,9 +854,6 @@ struct mlx5_core_dev { } roce; #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; -#endif -#ifdef CONFIG_RFS_ACCEL - struct cpu_rmap *rmap; #endif struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; @@ -1302,7 +1302,7 @@ enum { static inline const struct cpumask * mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector) { - return dev->priv.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask; + return dev->priv.eq_table.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask; } #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From f2f3df5501391bc784c8462dc97d989c2194fb74 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:38 -0800 Subject: net/mlx5: EQ, Privatize eq_table and friends Move unnecessary EQ table structures and declaration from the public include/linux/mlx5/driver.h into the private area of mlx5_core and into eq.c/eq.h. Introduce new mlx5 EQ APIs: mlx5_comp_vectors_count(dev); mlx5_comp_irq_get_affinity_mask(dev, vector); And use them from mlx5_ib or mlx5e netdevice instead of direct access to mlx5_core internal structures. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 87 +++------------------------------------------ 1 file changed, 5 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index dcc3f7aa8572..4d6246cb6c19 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -84,18 +84,6 @@ enum { MLX5_MAX_PORTS = 2, }; -enum { - MLX5_EQ_VEC_PAGES = 0, - MLX5_EQ_VEC_CMD = 1, - MLX5_EQ_VEC_ASYNC = 2, - MLX5_EQ_VEC_PFAULT = 3, - MLX5_EQ_VEC_COMP_BASE, -}; - -enum { - MLX5_MAX_IRQ_NAME = 32 -}; - enum { MLX5_ATOMIC_MODE_OFFSET = 16, MLX5_ATOMIC_MODE_IB_COMP = 1, @@ -366,49 +354,6 @@ struct mlx5_frag_buf_ctrl { u8 log_frag_strides; }; -struct mlx5_eq_tasklet { - struct list_head list; - struct list_head process_list; - struct tasklet_struct task; - /* lock on completion tasklet list */ - spinlock_t lock; -}; - -struct mlx5_eq_pagefault { - struct work_struct work; - /* Pagefaults lock */ - spinlock_t lock; - struct workqueue_struct *wq; - mempool_t *pool; -}; - -struct mlx5_cq_table { - /* protect radix tree */ - spinlock_t lock; - struct radix_tree_root tree; -}; - -struct mlx5_eq { - struct mlx5_core_dev *dev; - struct mlx5_cq_table cq_table; - __be32 __iomem *doorbell; - u32 cons_index; - struct mlx5_frag_buf buf; - int size; - unsigned int irqn; - u8 eqn; - int nent; - struct list_head list; - struct mlx5_rsc_debug *dbg; - enum mlx5_eq_type type; - union { - struct mlx5_eq_tasklet tasklet_ctx; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - struct mlx5_eq_pagefault pf_ctx; -#endif - }; -}; - struct mlx5_core_psv { u32 psv_idx; struct psv_layout { @@ -475,21 +420,6 @@ struct mlx5_core_srq { u16 uid; }; -struct mlx5_eq_table { - struct list_head comp_eqs_list; - struct mlx5_eq pages_eq; - struct mlx5_eq async_eq; - struct mlx5_eq cmd_eq; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - struct mlx5_eq pfault_eq; -#endif - int num_comp_vectors; - struct mlx5_irq_info *irq_info; -#ifdef CONFIG_RFS_ACCEL - struct cpu_rmap *rmap; -#endif -}; - struct mlx5_uars_page { void __iomem *map; bool wc; @@ -572,11 +502,6 @@ struct mlx5_core_sriov { int enabled_vfs; }; -struct mlx5_irq_info { - cpumask_var_t mask; - char name[MLX5_MAX_IRQ_NAME]; -}; - struct mlx5_fc_stats { spinlock_t counters_idr_lock; /* protects counters_idr */ struct idr counters_idr; @@ -594,6 +519,7 @@ struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; struct mlx5_pagefault; +struct mlx5_eq_table; struct mlx5_rate_limit { u32 rate; @@ -643,7 +569,7 @@ struct mlx5_port_module_event_stats { struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; - struct mlx5_eq_table eq_table; + struct mlx5_eq_table *eq_table; /* pages stuff */ struct workqueue_struct *pg_wq; @@ -1148,6 +1074,9 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg, bool map_wc, bool fast_path); void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg); +unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev); +struct cpumask * +mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector); unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev); int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index, u8 roce_version, u8 roce_l3_type, const u8 *gid, @@ -1299,10 +1228,4 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; -static inline const struct cpumask * -mlx5_get_vector_affinity_hint(struct mlx5_core_dev *dev, int vector) -{ - return dev->priv.eq_table.irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask; -} - #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From 16d760839ceef510cf95cbfadc069c4473c7a277 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:39 -0800 Subject: net/mlx5: EQ, Different EQ types In mlx5 we have three types of usages for EQs, 1. Asynchronous EQs, used internally by mlx5 core for a. FW command completions b. FW page requests c. one EQ for all other Asynchronous events 2. Completion EQs, used for CQ completion (we create one per core) 3. *Special type of EQ (page fault) used for RDMA on demand paging (ODP). *The 3rd type shouldn't be special at least in mlx5 core, it is yet another async events EQ with specific use case, it will be removed in the next two patches, and will completely move its logic to mlx5_ib, as it is rdma specific. In this patch we remove use case (eq type) specific fields from struct mlx5_eq into a new eq type specific structures. struct mlx5_eq_async; truct mlx5_eq_comp; struct mlx5_eq_pagefault; Separate between their type specific flows. In the future we will allow users to create there own generic EQs. for now we will allow only one for ODP in next patches. We will introduce event listeners registration API for those who want to receive mlx5 async events. After that mlx5 eq handling will be clean from feature/user specific handling. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cq.h | 2 +- include/linux/mlx5/driver.h | 10 +--------- 2 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 31a750570c38..28b757a64029 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -60,7 +60,7 @@ struct mlx5_core_cq { } tasklet_ctx; int reset_notify_added; struct list_head reset_notify; - struct mlx5_eq *eq; + struct mlx5_eq_comp *eq; u16 uid; }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4d6246cb6c19..fe9b552aa649 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -210,14 +210,6 @@ enum mlx5_port_status { MLX5_PORT_DOWN = 2, }; -enum mlx5_eq_type { - MLX5_EQ_TYPE_COMP, - MLX5_EQ_TYPE_ASYNC, -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - MLX5_EQ_TYPE_PF, -#endif -}; - struct mlx5_bfreg_info { u32 *sys_pages; int num_low_latency_bfregs; @@ -692,7 +684,7 @@ struct mlx5_pagefault { } rdma; }; - struct mlx5_eq *eq; + struct mlx5_eq_pagefault *eq; struct work_struct work; }; -- cgit v1.2.3 From 7701707cb94ed4d1e63ae4fa5ef62a2345ef9db7 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:40 -0800 Subject: net/mlx5: EQ, Generic EQ Add mlx5_eq_{create/destroy}_generic APIs and EQE access methods, for mlx5 core consumers generic EQs. This API will be used in downstream patch to move page fault (RDMA ODP) EQ logic into mlx5_ib rdma driver, hence it will use a generic EQ. Current mlx5 EQ allocation scheme: On load mlx5 allocates 4 (for async) + #cores (for data completions) MSIX vectors, mlx5 core will assign 3 MSIX vectors for internal async EQs and will use all of the #cores MSIX vectors for completion EQs, (One vector is going to be reserved for a generic EQ). After this patch an external user (e.g mlx5_ib) of mlx5_core can use this new API to create new generic EQs with the reserved msix vector index for that eq. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Signed-off-by: Leon Romanovsky --- include/linux/mlx5/eq.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/mlx5/eq.h (limited to 'include/linux') diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h new file mode 100644 index 000000000000..c733673ba5f6 --- /dev/null +++ b/include/linux/mlx5/eq.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2018 Mellanox Technologies. */ + +#ifndef MLX5_CORE_EQ_H +#define MLX5_CORE_EQ_H + +#include + +enum { + MLX5_EQ_PAGEREQ_IDX = 0, + MLX5_EQ_CMD_IDX = 1, + MLX5_EQ_ASYNC_IDX = 2, + /* reserved to be used by mlx5_core ulps (mlx5e/mlx5_ib) */ + MLX5_EQ_PFAULT_IDX = 3, + MLX5_EQ_MAX_ASYNC_EQS, + /* completion eqs vector indices start here */ + MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS, +}; + +struct mlx5_eq; + +struct mlx5_eq_param { + u8 index; + int nent; + u64 mask; + void *context; + irq_handler_t handler; +}; + +struct mlx5_eq * +mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name, + struct mlx5_eq_param *param); +int +mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq); + +struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc); +void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm); + +#endif /* MLX5_CORE_EQ_H */ -- cgit v1.2.3 From d5d284b829a6eb7127df24d1bd3896a698981e62 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 19 Nov 2018 10:52:41 -0800 Subject: {net,IB}/mlx5: Move Page fault EQ and ODP logic to RDMA Use the new generic EQ API to move all ODP RDMA data structures and logic form mlx5 core driver into mlx5_ib driver. Signed-off-by: Saeed Mahameed Reviewed-by: Leon Romanovsky Reviewed-by: Tariq Toukan Acked-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 49 --------------------------------------------- include/linux/mlx5/eq.h | 21 +++++++++++++++++++ 2 files changed, 21 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fe9b552aa649..f41e6713df10 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -510,7 +510,6 @@ struct mlx5_fc_stats { struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; -struct mlx5_pagefault; struct mlx5_eq_table; struct mlx5_rate_limit { @@ -619,13 +618,6 @@ struct mlx5_priv { struct mlx5_port_module_event_stats pme_stats; -#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING - void (*pfault)(struct mlx5_core_dev *dev, - void *context, - struct mlx5_pagefault *pfault); - void *pfault_ctx; - struct srcu_struct pfault_srcu; -#endif struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; }; @@ -650,44 +642,6 @@ enum mlx5_pagefault_type_flags { MLX5_PFAULT_RDMA = 1 << 2, }; -/* Contains the details of a pagefault. */ -struct mlx5_pagefault { - u32 bytes_committed; - u32 token; - u8 event_subtype; - u8 type; - union { - /* Initiator or send message responder pagefault details. */ - struct { - /* Received packet size, only valid for responders. */ - u32 packet_size; - /* - * Number of resource holding WQE, depends on type. - */ - u32 wq_num; - /* - * WQE index. Refers to either the send queue or - * receive queue, according to event_subtype. - */ - u16 wqe_index; - } wqe; - /* RDMA responder pagefault details */ - struct { - u32 r_key; - /* - * Received packet size, minimal size page fault - * resolution required for forward progress. - */ - u32 packet_size; - u32 rdma_op_len; - u64 rdma_va; - } rdma; - }; - - struct mlx5_eq_pagefault *eq; - struct work_struct work; -}; - struct mlx5_td { struct list_head tirs_list; u32 tdn; @@ -1118,9 +1072,6 @@ struct mlx5_interface { void (*detach)(struct mlx5_core_dev *dev, void *context); void (*event)(struct mlx5_core_dev *dev, void *context, enum mlx5_dev_event event, unsigned long param); - void (*pfault)(struct mlx5_core_dev *dev, - void *context, - struct mlx5_pagefault *pfault); void * (*get_dev)(void *context); int protocol; struct list_head list; diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index c733673ba5f6..71d82c5a1a02 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -17,6 +17,10 @@ enum { MLX5_EQ_VEC_COMP_BASE = MLX5_EQ_MAX_ASYNC_EQS, }; +#define MLX5_NUM_CMD_EQE (32) +#define MLX5_NUM_ASYNC_EQE (0x1000) +#define MLX5_NUM_SPARE_EQE (0x80) + struct mlx5_eq; struct mlx5_eq_param { @@ -36,4 +40,21 @@ mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq); struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc); void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm); +/* The HCA will think the queue has overflowed if we + * don't tell it we've been processing events. We + * create EQs with MLX5_NUM_SPARE_EQE extra entries, + * so we must update our consumer index at + * least that often. + * + * mlx5_eq_update_cc must be called on every EQE @EQ irq handler + */ +static inline u32 mlx5_eq_update_cc(struct mlx5_eq *eq, u32 cc) +{ + if (unlikely(cc >= MLX5_NUM_SPARE_EQE)) { + mlx5_eq_update_ci(eq, cc, 0); + cc = 0; + } + return cc; +} + #endif /* MLX5_CORE_EQ_H */ -- cgit v1.2.3 From 838e96904ff3fc6c30e5ebbc611474669856e3c0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 19 Nov 2018 15:29:11 -0800 Subject: bpf: Introduce bpf_func_info This patch added interface to load a program with the following additional information: . prog_btf_fd . func_info, func_info_rec_size and func_info_cnt where func_info will provide function range and type_id corresponding to each function. The func_info_rec_size is introduced in the UAPI to specify struct bpf_func_info size passed from user space. This intends to make bpf_func_info structure growable in the future. If the kernel gets a different bpf_func_info size from userspace, it will try to handle user request with part of bpf_func_info it can understand. In this patch, kernel can understand struct bpf_func_info { __u32 insn_offset; __u32 type_id; }; If user passed a bpf func_info record size of 16 bytes, the kernel can still handle part of records with the above definition. If verifier agrees with function range provided by the user, the bpf_prog ksym for each function will use the func name provided in the type_id, which is supposed to provide better encoding as it is not limited by 16 bytes program name limitation and this is better for bpf program which contains multiple subprograms. The bpf_prog_info interface is also extended to return btf_id, func_info, func_info_rec_size and func_info_cnt to userspace, so userspace can print out the function prototype for each xlated function. The insn_offset in the returned func_info corresponds to the insn offset for xlated functions. With other jit related fields in bpf_prog_info, userspace can also print out function prototypes for each jited function. Signed-off-by: Yonghong Song Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 ++++- include/linux/bpf_verifier.h | 1 + include/linux/btf.h | 2 ++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 987815152629..7f0e225bf630 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -316,6 +316,8 @@ struct bpf_prog_aux { void *security; #endif struct bpf_prog_offload *offload; + struct btf *btf; + u32 type_id; /* type id for this prog/func */ union { struct work_struct work; struct rcu_head rcu; @@ -527,7 +529,8 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, + union bpf_attr __user *uattr); void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); /* Map specifics */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 11f5df1092d9..204382f46fd8 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -204,6 +204,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u16 stack_depth; /* max. stack depth used by this function */ + u32 type_id; /* btf type_id for this subprog */ }; /* single container for all structs diff --git a/include/linux/btf.h b/include/linux/btf.h index e076c4697049..7f2c0a4a45ea 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -46,5 +46,7 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); int btf_get_fd_by_id(u32 id); u32 btf_id(const struct btf *btf); +const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); +const char *btf_name_by_offset(const struct btf *btf, u32 offset); #endif -- cgit v1.2.3 From f6161a8f3036caa45f225486be39783e99e0fa29 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 20 Nov 2018 14:08:20 -0800 Subject: bpf: fix a compilation error when CONFIG_BPF_SYSCALL is not defined Kernel test robot (lkp@intel.com) reports a compilation error at https://www.spinics.net/lists/netdev/msg534913.html introduced by commit 838e96904ff3 ("bpf: Introduce bpf_func_info"). If CONFIG_BPF is defined and CONFIG_BPF_SYSCALL is not defined, the following error will appear: kernel/bpf/core.c:414: undefined reference to `btf_type_by_id' kernel/bpf/core.c:415: undefined reference to `btf_name_by_offset' When CONFIG_BPF_SYSCALL is not defined, let us define stub inline functions for btf_type_by_id() and btf_name_by_offset() in include/linux/btf.h. This way, the compilation failure can be avoided. Fixes: 838e96904ff3 ("bpf: Introduce bpf_func_info") Reported-by: kbuild test robot Cc: Martin KaFai Lau Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 7f2c0a4a45ea..8c2199b5d250 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -46,7 +46,21 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); int btf_get_fd_by_id(u32 id); u32 btf_id(const struct btf *btf); + +#ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); +#else +static inline const struct btf_type *btf_type_by_id(const struct btf *btf, + u32 type_id) +{ + return NULL; +} +static inline const char *btf_name_by_offset(const struct btf *btf, + u32 offset) +{ + return NULL; +} +#endif #endif -- cgit v1.2.3 From 1db4909e76f64a85f4aaa187f0f683f5c85a471d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 20 Nov 2018 09:44:35 +0800 Subject: blk-mq: not embed .mq_kobj and ctx->kobj into queue instance Even though .mq_kobj, ctx->kobj and q->kobj share same lifetime from block layer's view, actually they don't because userspace may grab one kobject anytime via sysfs. This patch fixes the issue by the following approach: 1) introduce 'struct blk_mq_ctxs' for holding .mq_kobj and managing all ctxs 2) free all allocated ctxs and the 'blk_mq_ctxs' instance in release handler of .mq_kobj 3) grab one ref of .mq_kobj before initializing each ctx->kobj, so that .mq_kobj is always released after all ctxs are freed. This patch fixes kernel panic issue during booting when DEBUG_KOBJECT_RELEASE is enabled. Reported-by: Guenter Roeck Cc: "jianchao.wang" Tested-by: Guenter Roeck Reviewed-by: Greg Kroah-Hartman Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e97c0a3b2262..9b53db06ad08 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -456,7 +456,7 @@ struct request_queue { /* * mq queue kobject */ - struct kobject mq_kobj; + struct kobject *mq_kobj; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; -- cgit v1.2.3 From 342e53bd8548e07c6a734d2d3a6437ad6e6d3b09 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Oct 2018 13:28:07 +0100 Subject: arm64: perf: Add support for Armv8.1 PMCEID register format Armv8.1 allocated the upper 32-bits of the PMCEID registers to describe the common architectural and microarchitecture events beginning at 0x4000. Add support for these registers to our probing code, so that we can advertise the SPE events when they are supported by the CPU. Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index bf309ff6f244..4641e850b204 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -102,8 +102,10 @@ struct arm_pmu { int (*filter_match)(struct perf_event *event); int num_events; bool secure_access; /* 32-bit ARM only */ -#define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 +#define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); +#define ARMV8_PMUV3_EXT_COMMON_EVENT_BASE 0x4000 + DECLARE_BITMAP(pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); struct platform_device *plat_device; struct pmu_hw_events __percpu *hw_events; struct hlist_node node; -- cgit v1.2.3 From cbb72a3c19eff0ea3ccb0b068eca189063c86174 Mon Sep 17 00:00:00 2001 From: Hoan Tran Date: Wed, 7 Nov 2018 19:40:58 +0000 Subject: drivers/perf: xgene: Add CPU hotplug support If the CPU assigned to the xgene PMU is taken offline, then subsequent perf invocations on the PMU will fail: # echo 0 > /sys/devices/system/cpu/cpu0/online # perf stat -a -e l3c0/cycle-count/,l3c0/write/ sleep 1 Error: The sys_perf_event_open() syscall returned with 19 (No such device) for event (l3c0/cycle-count/). /bin/dmesg may provide additional information. No CONFIG_PERF_EVENTS=y kernel support configured? This patch implements a hotplug notifier in the xgene PMU driver so that the PMU context is migrated to another online CPU should its assigned CPU disappear. Acked-by: Mark Rutland Signed-off-by: Hoan Tran [will: Made naming of new cpuhp_state enum entry consistent] Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index e0cd2baa8380..d007a319dfd4 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -164,6 +164,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, + CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, -- cgit v1.2.3 From b34087157dd76e8d96e5e52808134a791ac61e57 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 21 Nov 2018 16:00:50 +0000 Subject: dma-direct: Make DIRECT_MAPPING_ERROR viable for SWIOTLB With the overflow buffer removed, we no longer have a unique address which is guaranteed not to be a valid DMA target to use as an error token. The DIRECT_MAPPING_ERROR value of 0 tries to at least represent an unlikely DMA target, but unfortunately there are already SWIOTLB users with DMA-able memory at physical address 0 which now gets falsely treated as a mapping failure and leads to all manner of misbehaviour. The best we can do to mitigate that is flip DIRECT_MAPPING_ERROR to the other commonly-used error value of all-bits-set, since the last single byte of memory is by far the least-likely-valid DMA target. Fixes: dff8d6c1ed58 ("swiotlb: remove the overflow buffer") Reported-by: John Stultz Tested-by: John Stultz Acked-by: Konrad Rzeszutek Wilk Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index bd73e7a91410..9e66bfe369aa 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,7 +5,7 @@ #include #include -#define DIRECT_MAPPING_ERROR 0 +#define DIRECT_MAPPING_ERROR (~(dma_addr_t)0) #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include -- cgit v1.2.3 From a2e768b861108d846b6df21074cff738660b45b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Tue, 20 Nov 2018 13:20:31 +0100 Subject: net/vlan: introduce skb_vlan_tag_get_cfi() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Abstract CFI/DEI bit access consistently with other VLAN tag fields. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 7a541eadf78e..4cca4da7a6de 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -65,7 +65,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 -#define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator */ +#define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 @@ -80,6 +80,7 @@ static inline bool is_vlan_dev(const struct net_device *dev) #define skb_vlan_tag_present(__skb) ((__skb)->vlan_present) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) +#define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) #define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) -- cgit v1.2.3 From 86de5921a3d5dd246df661e09bdd0a6131b39ae3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Nov 2018 05:53:59 -0800 Subject: tcp: defer SACK compression after DupThresh Jean-Louis reported a TCP regression and bisected to recent SACK compression. After a loss episode (receiver not able to keep up and dropping packets because its backlog is full), linux TCP stack is sending a single SACK (DUPACK). Sender waits a full RTO timer before recovering losses. While RFC 6675 says in section 5, "Algorithm Details", (2) If DupAcks < DupThresh but IsLost (HighACK + 1) returns true -- indicating at least three segments have arrived above the current cumulative acknowledgment point, which is taken to indicate loss -- go to step (4). ... (4) Invoke fast retransmit and enter loss recovery as follows: there are old TCP stacks not implementing this strategy, and still counting the dupacks before starting fast retransmit. While these stacks probably perform poorly when receivers implement LRO/GRO, we should be a little more gentle to them. This patch makes sure we do not enable SACK compression unless 3 dupacks have been sent since last rcv_nxt update. Ideally we should even rearm the timer to send one or two more DUPACK if no more packets are coming, but that will be work aiming for linux-4.21. Many thanks to Jean-Louis for bisecting the issue, providing packet captures and testing this patch. Fixes: 5d9f4262b7ea ("tcp: add SACK compression") Reported-by: Jean-Louis Dupond Tested-by: Jean-Louis Dupond Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8ed77bb4ed86..a9b0280687d5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -196,6 +196,7 @@ struct tcp_sock { u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ + u32 compressed_ack_rcv_nxt; u32 tsoffset; /* timestamp offset */ -- cgit v1.2.3 From 085ddc87d05fdf649ccee7a7da42110e9e1c6311 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Nov 2018 08:02:41 +0000 Subject: bridge: Allow querying bridge port flags Allow querying bridge port flags so that drivers capable of performing VxLAN learning will update the bridge driver only if learning is enabled on its bridge port corresponding to the VxLAN device. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index c20c7e197d07..ef7c3d376b21 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -119,6 +119,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct net_device *br_fdb_find_port(const struct net_device *br_dev, const unsigned char *addr, __u16 vid); +bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -127,6 +128,11 @@ br_fdb_find_port(const struct net_device *br_dev, { return NULL; } +static inline bool +br_port_flag_is_set(const struct net_device *dev, unsigned long flag) +{ + return false; +} #endif #endif -- cgit v1.2.3 From f1539a0c2545d7bd82e451bd1464f2a820f55de4 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 21 Nov 2018 16:27:11 +0100 Subject: Revert "HID: input: Create a utility class for counting scroll events" This reverts commit 1ff2e1a44e02d4bdbb9be67c7d9acc240a67141f. It turns out the current API is not that compatible with some Microsoft mice, so better start again from scratch. Signed-off-by: Benjamin Tissoires Acked-by: Harry Cutts Acked-by: Dmitry Torokhov Acked-by: Jiri Kosina --- include/linux/hid.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 387c70df6f29..a355d61940f2 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1139,34 +1139,6 @@ static inline u32 hid_report_len(struct hid_report *report) int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt); - -/** - * struct hid_scroll_counter - Utility class for processing high-resolution - * scroll events. - * @dev: the input device for which events should be reported. - * @microns_per_hi_res_unit: the amount moved by the user's finger for each - * high-resolution unit reported by the mouse, in - * microns. - * @resolution_multiplier: the wheel's resolution in high-resolution mode as a - * multiple of its lower resolution. For example, if - * moving the wheel by one "notch" would result in a - * value of 1 in low-resolution mode but 8 in - * high-resolution, the multiplier is 8. - * @remainder: counts the number of high-resolution units moved since the last - * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should - * only be used by class methods. - */ -struct hid_scroll_counter { - struct input_dev *dev; - int microns_per_hi_res_unit; - int resolution_multiplier; - - int remainder; -}; - -void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, - int hi_res_value); - /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); int hid_quirks_init(char **quirks_param, __u16 bus, int count); -- cgit v1.2.3 From d491324f966518fbd3f4c627a3e9766d018a4eef Mon Sep 17 00:00:00 2001 From: Songjun Wu Date: Thu, 22 Nov 2018 15:47:35 +0800 Subject: include: Add lantiq.h in include/linux/ In some existing lantiq driver, the C codes include lantiq_soc.h header file directly. ./arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h ./arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h Those drivers need to be extended to support more platform. lantiq.h is added in include/linux/ to make it globally available and provides some wrapper codes. Signed-off-by: Songjun Wu Signed-off-by: Greg Kroah-Hartman --- include/linux/lantiq.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/lantiq.h (limited to 'include/linux') diff --git a/include/linux/lantiq.h b/include/linux/lantiq.h new file mode 100644 index 000000000000..67921169d84d --- /dev/null +++ b/include/linux/lantiq.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_LANTIQ_H +#define __LINUX_LANTIQ_H + +#ifdef CONFIG_LANTIQ +#include +#else + +#ifndef LTQ_EARLY_ASC +#define LTQ_EARLY_ASC 0 +#endif + +#ifndef CPHYSADDR +#define CPHYSADDR(a) 0 +#endif + +static inline struct clk *clk_get_fpi(void) +{ + return NULL; +} +#endif /* CONFIG_LANTIQ */ +#endif /* __LINUX_LANTIQ_H */ -- cgit v1.2.3 From 5451781dadf85000665e0e2c3288e9e0f34b860a Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 20 Nov 2018 09:52:53 -0800 Subject: regulator: core: Only count load for enabled consumers In general when the consumer of a regulator requests that the regulator be disabled it no longer will be drawing much load from the regulator--it should just be the leakage current and that should be very close to 0. Up to this point the regulator framework has continued to count a consumer's load request for disabled regulators. This has led to code patterns that look like this: enable_my_thing(): regular_set_load(reg, load_uA) regulator_enable(reg) disable_my_thing(): regulator_disable(reg) regulator_set_load(reg, 0) Sometimes disable_my_thing() sets a nominal (<= 100 uA) load instead of setting a 0 uA load. I will make the assertion that nearly all (if not all) places where we set a nominal load of 100 uA or less we end up with a result that is the same as if we had set a load of 0 uA. Specifically: - The whole point of setting the load is to help set the operating mode of the regulator. Higher loads may need less efficient operating modes. - The only time this matters at all is if there is another consumer of the regulator that wants the regulator on. If there are no other consumers of the regulator then the regulator will turn off and we don't care about the operating mode. - If there's another consumer that actually wants the regulator on then presumably it is requesting a load that makes our nominal <= 100 uA load insignificant. A quick survey of the existing callers to regulator_set_load() to see how everyone uses it: Signed-off-by: Douglas Anderson Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 7065031f0846..389bcaf7900f 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -474,7 +474,6 @@ struct regulator_dev { struct regmap *regmap; struct delayed_work disable_work; - int deferred_disables; void *reg_data; /* regulator_dev data */ -- cgit v1.2.3 From 41c9e132c5cc3e5f28cf44032ff82f7614a42989 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sat, 10 Nov 2018 21:29:03 +0100 Subject: rtc: nvmem: remove nvmem from struct rtc_device Using devm_nvmem_register allows to avoid tracking the nvmem pointer in the rtc_device structure. This ultimately allows to register multiple nvmem devices from an RTC driver. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 311375dbb673..58147b057acd 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -138,7 +138,6 @@ struct rtc_device { bool registered; - struct nvmem_device *nvmem; /* Old ABI support */ bool nvram_old_abi; struct bin_attribute *nvram; -- cgit v1.2.3 From 6fe07ce35e8ad870ba1cf82e0481e0fc0f526eff Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Wed, 21 Nov 2018 20:28:39 +0000 Subject: x86/resctrl: Rename the config option INTEL_RDT to RESCTRL The resource control feature is supported by both Intel and AMD. So, rename CONFIG_INTEL_RDT to the vendor-neutral CONFIG_RESCTRL. Now CONFIG_RESCTRL will be used for both Intel and AMD to enable Resource Control support. Update the texts in config and condition accordingly. [ bp: Simplify Kconfig text. ] Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Brijesh Singh Cc: "Chang S. Bae" Cc: David Miller Cc: David Woodhouse Cc: Dmitry Safonov Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jann Horn Cc: Joerg Roedel Cc: Jonathan Corbet Cc: Josh Poimboeuf Cc: Kate Stewart Cc: "Kirill A. Shutemov" Cc: Cc: Mauro Carvalho Chehab Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Philippe Ombredanne Cc: Pu Wen Cc: Cc: "Rafael J. Wysocki" Cc: Reinette Chatre Cc: Rian Hunter Cc: Sherry Hurwitz Cc: Suravee Suthikulpanit Cc: Thomas Gleixner Cc: Thomas Lendacky Cc: Tony Luck Cc: Vitaly Kuznetsov Cc: Link: https://lkml.kernel.org/r/20181121202811.4492-9-babu.moger@amd.com --- 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 a51c13c2b1a0..7952dfba2c76 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -993,7 +993,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_INTEL_RDT +#ifdef CONFIG_RESCTRL u32 closid; u32 rmid; #endif -- cgit v1.2.3 From 0211dda68a4f6531923a2f72d8e8959207f59fba Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Wed, 21 Nov 2018 16:28:23 +0200 Subject: net/dim: Update DIM start sample after each DIM iteration On every iteration of net_dim, the algorithm may choose to check for the system state by comparing current data sample with previous data sample. After each of these comparison, regardless of the action taken, the sample used as baseline is needed to be updated. This patch fixes a bug that causes DIM to take wrong decisions, due to never updating the baseline sample for comparison between iterations. This way, DIM always compares current sample with zeros. Although this is a functional fix, it also improves and stabilizes performance as the algorithm works properly now. Performance: Tested single UDP TX stream with pktgen: samples/pktgen/pktgen_sample03_burst_single_flow.sh -i p4p2 -d 1.1.1.1 -m 24:8a:07:88:26:8b -f 3 -b 128 ConnectX-5 100GbE packet rate improved from 15-19Mpps to 19-20Mpps. Also, toggling between profiles is less frequent with the fix. Fixes: 8115b750dbcb ("net/dim: use struct net_dim_sample as arg to net_dim") Signed-off-by: Tal Gilboa Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/net_dim.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index c79e859408e6..fd458389f7d1 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -406,6 +406,8 @@ static inline void net_dim(struct net_dim *dim, } /* fall through */ case NET_DIM_START_MEASURE: + net_dim_sample(end_sample.event_ctr, end_sample.pkt_ctr, end_sample.byte_ctr, + &dim->start_sample); dim->state = NET_DIM_MEASURE_IN_PROGRESS; break; case NET_DIM_APPLY_NEW_PROFILE: -- cgit v1.2.3 From e45678973dcbb131f29a6c90b0ea3829f38eeab8 Mon Sep 17 00:00:00 2001 From: Daniel Jurgens Date: Wed, 21 Nov 2018 17:12:05 +0200 Subject: {net, IB}/mlx4: Initialize CQ buffers in the driver when possible Perform CQ initialization in the driver when the capability is supported by the FW. When passing the CQ to HW indicate that the CQ buffer has been pre-initialized. Doing so decreases CQ creation time. Testing on P8 showed a single 2048 entry CQ creation time was reduced from ~395us to ~170us, which is 2.3x faster. Signed-off-by: Daniel Jurgens Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index dca6ab4eaa99..36e412c3d657 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -226,6 +226,7 @@ enum { MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37, MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38, MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW = 1ULL << 39, + MLX4_DEV_CAP_FLAG2_SW_CQ_INIT = 1ULL << 40, }; enum { @@ -1136,7 +1137,8 @@ void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres, int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq, - unsigned vector, int collapsed, int timestamp_en); + unsigned int vector, int collapsed, int timestamp_en, + void *buf_addr, bool user_cq); void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq); int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base, u8 flags, u8 usage); -- cgit v1.2.3 From 89f579ce99f7e028e81885d3965f973c0f787611 Mon Sep 17 00:00:00 2001 From: Yi Wang Date: Thu, 22 Nov 2018 10:04:09 +0800 Subject: x86/headers: Fix -Wmissing-prototypes warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When building the kernel with W=1 we get a lot of -Wmissing-prototypes warnings, which are trivial in nature and easy to fix - and which may mask some real future bugs if the prototypes get out of sync with the function definition. This patch fixes most of -Wmissing-prototypes warnings which are in the root directory of arch/x86/kernel, not including the subdirectories. These are the warnings fixed in this patch: arch/x86/kernel/signal.c:865:17: warning: no previous prototype for ‘sys32_x32_rt_sigreturn’ [-Wmissing-prototypes] arch/x86/kernel/signal_compat.c:164:6: warning: no previous prototype for ‘sigaction_compat_abi’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:625:46: warning: no previous prototype for ‘sync_regs’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:640:24: warning: no previous prototype for ‘fixup_bad_iret’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:929:13: warning: no previous prototype for ‘trap_init’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:270:28: warning: no previous prototype for ‘smp_x86_platform_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:301:16: warning: no previous prototype for ‘smp_kvm_posted_intr_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:314:16: warning: no previous prototype for ‘smp_kvm_posted_intr_wakeup_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:328:16: warning: no previous prototype for ‘smp_kvm_posted_intr_nested_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq_work.c:16:28: warning: no previous prototype for ‘smp_irq_work_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/irqinit.c:79:13: warning: no previous prototype for ‘init_IRQ’ [-Wmissing-prototypes] arch/x86/kernel/quirks.c:672:13: warning: no previous prototype for ‘early_platform_quirks’ [-Wmissing-prototypes] arch/x86/kernel/tsc.c:1499:15: warning: no previous prototype for ‘calibrate_delay_is_known’ [-Wmissing-prototypes] arch/x86/kernel/process.c:653:13: warning: no previous prototype for ‘arch_post_acpi_subsys_init’ [-Wmissing-prototypes] arch/x86/kernel/process.c:717:15: warning: no previous prototype for ‘arch_randomize_brk’ [-Wmissing-prototypes] arch/x86/kernel/process.c:784:6: warning: no previous prototype for ‘do_arch_prctl_common’ [-Wmissing-prototypes] arch/x86/kernel/reboot.c:869:6: warning: no previous prototype for ‘nmi_panic_self_stop’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:176:27: warning: no previous prototype for ‘smp_reboot_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:260:28: warning: no previous prototype for ‘smp_reschedule_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:281:28: warning: no previous prototype for ‘smp_call_function_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:291:28: warning: no previous prototype for ‘smp_call_function_single_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:840:6: warning: no previous prototype for ‘arch_ftrace_update_trampoline’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:934:7: warning: no previous prototype for ‘arch_ftrace_trampoline_func’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:946:6: warning: no previous prototype for ‘arch_ftrace_trampoline_free’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:114:6: warning: no previous prototype for ‘crash_smp_send_stop’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:351:5: warning: no previous prototype for ‘crash_setup_memmap_entries’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:424:5: warning: no previous prototype for ‘crash_load_segments’ [-Wmissing-prototypes] arch/x86/kernel/machine_kexec_64.c:372:7: warning: no previous prototype for ‘arch_kexec_kernel_image_load’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:12:16: warning: no previous prototype for ‘__native_queued_spin_unlock’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:18:6: warning: no previous prototype for ‘pv_is_native_spin_unlock’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:24:16: warning: no previous prototype for ‘__native_vcpu_is_preempted’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:30:6: warning: no previous prototype for ‘pv_is_native_vcpu_is_preempted’ [-Wmissing-prototypes] arch/x86/kernel/kvm.c:258:1: warning: no previous prototype for ‘do_async_page_fault’ [-Wmissing-prototypes] arch/x86/kernel/jailhouse.c:200:6: warning: no previous prototype for ‘jailhouse_paravirt’ [-Wmissing-prototypes] arch/x86/kernel/check.c:91:13: warning: no previous prototype for ‘setup_bios_corruption_check’ [-Wmissing-prototypes] arch/x86/kernel/check.c:139:6: warning: no previous prototype for ‘check_for_bios_corruption’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:32:13: warning: no previous prototype for ‘early_init_dt_scan_chosen_arch’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:42:13: warning: no previous prototype for ‘add_dtb’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:108:6: warning: no previous prototype for ‘x86_of_pci_init’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:314:13: warning: no previous prototype for ‘x86_dtb_init’ [-Wmissing-prototypes] arch/x86/kernel/tracepoint.c:16:5: warning: no previous prototype for ‘trace_pagefault_reg’ [-Wmissing-prototypes] arch/x86/kernel/tracepoint.c:22:6: warning: no previous prototype for ‘trace_pagefault_unreg’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:113:22: warning: no previous prototype for ‘__startup_64’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:262:15: warning: no previous prototype for ‘__startup_secondary_64’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:350:12: warning: no previous prototype for ‘early_make_pgtable’ [-Wmissing-prototypes] [ mingo: rewrote the changelog, fixed build errors. ] Signed-off-by: Yi Wang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akataria@vmware.com Cc: akpm@linux-foundation.org Cc: andy.shevchenko@gmail.com Cc: anton@enomsg.org Cc: ard.biesheuvel@linaro.org Cc: bhe@redhat.com Cc: bhelgaas@google.com Cc: bp@alien8.de Cc: ccross@android.com Cc: devicetree@vger.kernel.org Cc: douly.fnst@cn.fujitsu.com Cc: dwmw@amazon.co.uk Cc: dyoung@redhat.com Cc: ebiederm@xmission.com Cc: frank.rowand@sony.com Cc: frowand.list@gmail.com Cc: ivan.gorinov@intel.com Cc: jailhouse-dev@googlegroups.com Cc: jan.kiszka@siemens.com Cc: jgross@suse.com Cc: jroedel@suse.de Cc: keescook@chromium.org Cc: kexec@lists.infradead.org Cc: konrad.wilk@oracle.com Cc: kvm@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: luto@kernel.org Cc: m.mizuma@jp.fujitsu.com Cc: namit@vmware.com Cc: oleg@redhat.com Cc: pasha.tatashin@oracle.com Cc: pbonzini@redhat.com Cc: prarit@redhat.com Cc: pravin.shedge4linux@gmail.com Cc: rajvi.jingar@intel.com Cc: rkrcmar@redhat.com Cc: robh+dt@kernel.org Cc: robh@kernel.org Cc: rostedt@goodmis.org Cc: takahiro.akashi@linaro.org Cc: thomas.lendacky@amd.com Cc: tony.luck@intel.com Cc: up2wing@gmail.com Cc: virtualization@lists.linux-foundation.org Cc: zhe.he@windriver.com Cc: zhong.weidong@zte.com.cn Link: http://lkml.kernel.org/r/1542852249-19820-1-git-send-email-wang.yi59@zte.com.cn Signed-off-by: Ingo Molnar --- include/linux/ftrace.h | 3 +++ include/linux/kexec.h | 1 + include/linux/of_fdt.h | 1 + include/linux/ptrace.h | 1 + 4 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a397907e8d72..182d669cc918 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -420,6 +420,9 @@ enum { }; void arch_ftrace_update_code(int command); +void arch_ftrace_update_trampoline(struct ftrace_ops *ops); +void *arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec); +void arch_ftrace_trampoline_free(struct ftrace_ops *ops); struct ftrace_rec_iter; diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9e4e638fb505..53efedae3d5b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -174,6 +174,7 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); +void * __weak arch_kexec_kernel_image_load(struct kimage *image); int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, const Elf_Shdr *relsec, diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index b9cd9ebdf9b9..a713e5d156d8 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -76,6 +76,7 @@ extern int early_init_dt_scan_memory(unsigned long node, const char *uname, extern int early_init_dt_scan_chosen_stdout(void); extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); +extern void __init early_init_dt_scan_chosen_arch(unsigned long node); extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern int early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size); extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 6c2ffed907f5..a37d7c00da65 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -428,4 +428,5 @@ extern int task_current_syscall(struct task_struct *target, long *callno, unsigned long args[6], unsigned int maxargs, unsigned long *sp, unsigned long *pc); +extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); #endif -- cgit v1.2.3 From 58c5fc2b96e4ae65068d815a1c3ca81da92fa1c9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 31 Oct 2018 19:21:08 +0100 Subject: time: Remove useless filenames in top level comments Remove the pointless filenames in the top level comments. They have no value at all and just occupy space. While at it tidy up some of the comments and remove a stale one. Signed-off-by: Thomas Gleixner Acked-by: Nicolas Pitre Acked-by: Kees Cook Acked-by: Ingo Molnar Acked-by: John Stultz Acked-by: Corey Minyard Cc: Peter Zijlstra Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Peter Anvin Cc: Russell King Cc: Richard Cochran Cc: "Paul E. McKenney" Cc: David Riley Cc: Colin Cross Cc: Mark Brown Link: https://lkml.kernel.org/r/20181031182252.794898238@linutronix.de --- include/linux/hrtimer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 3892e9c8b2de..50ebe2ad43e0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -1,6 +1,4 @@ /* - * include/linux/hrtimer.h - * * hrtimers - High-resolution kernel timers * * Copyright(C) 2005, Thomas Gleixner -- cgit v1.2.3 From 35728b8209ee7d25b6241a56304ee926469bd154 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 31 Oct 2018 19:21:09 +0100 Subject: time: Add SPDX license identifiers Update the time(r) core files files with the correct SPDX license identifier based on the license text in the file itself. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This work is based on a script and data from Philippe Ombredanne, Kate Stewart and myself. The data has been created with two independent license scanners and manual inspection. The following files do not contain any direct license information and have been omitted from the big initial SPDX changes: timeconst.bc: The .bc files were not touched time.c, timer.c, timekeeping.c: Licence was deduced from EXPORT_SYMBOL_GPL As those files do not contain direct license references they fall under the project license, i.e. GPL V2 only. Signed-off-by: Thomas Gleixner Acked-by: Kees Cook Acked-by: Ingo Molnar Acked-by: John Stultz Acked-by: Corey Minyard Cc: Peter Zijlstra Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Russell King Cc: Richard Cochran Cc: Nicolas Pitre Cc: David Riley Cc: Colin Cross Cc: Mark Brown Cc: H. Peter Anvin Cc: Paul E. McKenney Link: https://lkml.kernel.org/r/20181031182252.879109557@linutronix.de --- include/linux/hrtimer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 50ebe2ad43e0..851e4231d3ab 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * hrtimers - High-resolution kernel timers * -- cgit v1.2.3 From f49c174b5f431db9fa17315269e288d4548b651c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 31 Oct 2018 19:21:10 +0100 Subject: hrtimers/tick/clockevents: Remove sloppy license references "For licencing details see kernel-base/COPYING" and similar license references have no value over the SPDX identifier. Remove them. Signed-off-by: Thomas Gleixner Acked-by: Kees Cook Acked-by: Ingo Molnar Acked-by: John Stultz Acked-by: Corey Minyard Cc: Peter Zijlstra Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Peter Anvin Cc: Russell King Cc: Richard Cochran Cc: "Paul E. McKenney" Cc: Nicolas Pitre Cc: David Riley Cc: Colin Cross Cc: Mark Brown Link: https://lkml.kernel.org/r/20181031182252.963632760@linutronix.de --- include/linux/hrtimer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 851e4231d3ab..2e8957eac4d4 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -8,8 +8,6 @@ * data type definitions, declarations, prototypes * * Started by: Thomas Gleixner and Ingo Molnar - * - * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H -- cgit v1.2.3 From 5cd8d46ea1562be80063f53c7c6a5f40224de623 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 20 Nov 2018 13:00:18 -0500 Subject: packet: copy user buffers before orphan or clone tpacket_snd sends packets with user pages linked into skb frags. It notifies that pages can be reused when the skb is released by setting skb->destructor to tpacket_destruct_skb. This can cause data corruption if the skb is orphaned (e.g., on transmit through veth) or cloned (e.g., on mirror to another psock). Create a kernel-private copy of data in these cases, same as tun/tap zerocopy transmission. Reuse that infrastructure: mark the skb as SKBTX_ZEROCOPY_FRAG, which will trigger copy in skb_orphan_frags(_rx). Unlike other zerocopy packets, do not set shinfo destructor_arg to struct ubuf_info. tpacket_destruct_skb already uses that ptr to notify when the original skb is released and a timestamp is recorded. Do not change this timestamp behavior. The ubuf_info->callback is not needed anyway, as no zerocopy notification is expected. Mark destructor_arg as not-a-uarg by setting the lower bit to 1. The resulting value is not a valid ubuf_info pointer, nor a valid tpacket_snd frame address. Add skb_zcopy_.._nouarg helpers for this. The fix relies on features introduced in commit 52267790ef52 ("sock: add MSG_ZEROCOPY"), so can be backported as is only to 4.14. Tested with from `./in_netns.sh ./txring_overwrite` from http://github.com/wdebruij/kerneltools/tests Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Reported-by: Anand H. Krishnan Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0ba687454267..0d1b2c3f127b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1326,6 +1326,22 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) } } +static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) +{ + skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; +} + +static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) +{ + return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; +} + +static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) +{ + return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); +} + /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) { @@ -1335,7 +1351,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) if (uarg->callback == sock_zerocopy_callback) { uarg->zerocopy = uarg->zerocopy && zerocopy; sock_zerocopy_put(uarg); - } else { + } else if (!skb_zcopy_is_nouarg(skb)) { uarg->callback(uarg, zerocopy); } -- cgit v1.2.3 From 7b0c03ecc42fb223baf015877fee9d517c2c8af1 Mon Sep 17 00:00:00 2001 From: Christian Lamparter Date: Sat, 17 Nov 2018 17:17:21 +0100 Subject: dmaengine: dw-dmac: implement dma protection control setting This patch adds a new device-tree property that allows to specify the dma protection control bits for the all of the DMA controller's channel uniformly. Setting the "correct" bits can have a huge impact on the PPC460EX and APM82181 that use this DMA engine in combination with a DesignWare' SATA-II core (sata_dwc_460ex driver). In the OpenWrt Forum, the user takimata reported that: |It seems your patch unleashed the full power of the SATA port. |Where I was previously hitting a really hard limit at around |82 MB/s for reading and 27 MB/s for writing, I am now getting this: | |root@OpenWrt:/mnt# time dd if=/dev/zero of=tempfile bs=1M count=1024 |1024+0 records in |1024+0 records out |real 0m 13.65s |user 0m 0.01s |sys 0m 11.89s | |root@OpenWrt:/mnt# time dd if=tempfile of=/dev/null bs=1M count=1024 |1024+0 records in |1024+0 records out |real 0m 8.41s |user 0m 0.01s |sys 0m 4.70s | |This means: 121 MB/s reading and 75 MB/s writing! | |The drive is a WD Green WD10EARX taken from an older MBL Single. |I repeated the test a few times with even larger files to rule out |any caching, I'm still seeing the same great performance. OpenWrt is |now completely on par with the original MBL firmware's performance. Another user And.short reported: |I can report that your fix worked! Boots up fine with two |drives even with more partitions, and no more reboot on |concurrent disk access! A closer look into the sata_dwc_460ex code revealed that the driver did initally set the correct protection control bits. However, this feature was lost when the sata_dwc_460ex driver was converted to the generic DMA driver framework. BugLink: https://forum.openwrt.org/t/wd-mybook-live-duo-two-disks/16195/55 BugLink: https://forum.openwrt.org/t/wd-mybook-live-duo-two-disks/16195/50 Fixes: 8b3444852a2b ("sata_dwc_460ex: move to generic DMA driver") Reviewed-by: Andy Shevchenko Signed-off-by: Christian Lamparter Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 896cb71a382c..1a1d58ebffbf 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -49,6 +49,7 @@ struct dw_dma_slave { * @data_width: Maximum data width supported by hardware per AHB master * (in bytes, power of 2) * @multi_block: Multi block transfers supported by hardware per channel. + * @protctl: Protection control signals setting per channel. */ struct dw_dma_platform_data { unsigned int nr_channels; @@ -65,6 +66,11 @@ struct dw_dma_platform_data { unsigned char nr_masters; unsigned char data_width[DW_DMA_MAX_NR_MASTERS]; unsigned char multi_block[DW_DMA_MAX_NR_CHANNELS]; +#define CHAN_PROTCTL_PRIVILEGED BIT(0) +#define CHAN_PROTCTL_BUFFERABLE BIT(1) +#define CHAN_PROTCTL_CACHEABLE BIT(2) +#define CHAN_PROTCTL_MASK GENMASK(2, 0) + unsigned char protctl; }; #endif /* _PLATFORM_DATA_DMA_DW_H */ -- cgit v1.2.3 From 2183435c251e09df11e1b431c84416424b5fd2ac Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 24 Nov 2018 12:01:41 +0300 Subject: net: fixup type in netdev_start_xmit() Return code should be formally "netdev_tx_t". Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4b4207ebd5c0..1eeb019d85a3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4373,7 +4373,7 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi struct netdev_queue *txq, bool more) { const struct net_device_ops *ops = dev->netdev_ops; - int rc; + netdev_tx_t rc; rc = __netdev_start_xmit(ops, skb, dev, more); if (rc == NETDEV_TX_OK) -- cgit v1.2.3 From 620344c43edfa020bbadfd81a144ebe5181fc94f Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 25 Nov 2018 14:30:29 +0100 Subject: net: core: add __netdev_sent_queue as variant of __netdev_tx_sent_queue Similar to netdev_sent_queue add helper __netdev_sent_queue as variant of __netdev_tx_sent_queue. Signed-off-by: Heiner Kallweit 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 1eeb019d85a3..9b00043effa3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3226,6 +3226,14 @@ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); } +static inline bool __netdev_sent_queue(struct net_device *dev, + unsigned int bytes, + bool xmit_more) +{ + return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes, + xmit_more); +} + static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { -- cgit v1.2.3 From 4bffc669d6248d655aeb985a0e51bfaaf21c8b40 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 25 Nov 2018 08:26:23 -0800 Subject: net: remove unsafe skb_insert() I do not see how one can effectively use skb_insert() without holding some kind of lock. Otherwise other cpus could have changed the list right before we have a chance of acquiring list->lock. Only existing user is in drivers/infiniband/hw/nes/nes_mgt.c and this one probably meant to use __skb_insert() since it appears nesqp->pau_list is protected by nesqp->pau_lock. This looks like nesqp->pau_lock could be removed, since nesqp->pau_list.lock could be used instead. Signed-off-by: Eric Dumazet Cc: Faisal Latif Cc: Doug Ledford Cc: Jason Gunthorpe Cc: linux-rdma Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f17a7452ac7b..73902acf2b71 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1749,8 +1749,6 @@ static inline void skb_queue_head_init_class(struct sk_buff_head *list, * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ -void skb_insert(struct sk_buff *old, struct sk_buff *newsk, - struct sk_buff_head *list); static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) -- cgit v1.2.3 From 7f7c548c5f652375a61c1072bac3db11f7a48326 Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Tue, 9 Oct 2018 14:43:18 +0000 Subject: usb: gadget: f_fs: Add support for CCID descriptors. Nothing to remap, only check length. Define a minimal structure for CCID descriptor only used to check length. As this descriptor shares the same value as HID descriptors, keep track and compare current interface's class to expected HID and CCID standard values. Signed-off-by: Vincent Pelletier Signed-off-by: Felipe Balbi --- include/linux/usb/ccid.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 include/linux/usb/ccid.h (limited to 'include/linux') diff --git a/include/linux/usb/ccid.h b/include/linux/usb/ccid.h new file mode 100644 index 000000000000..3431446d6864 --- /dev/null +++ b/include/linux/usb/ccid.h @@ -0,0 +1,51 @@ +/* + * Copyright (c) 2018 Vincent Pelletier + */ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#ifndef __CCID_H +#define __CCID_H + +#include + +#define USB_INTERFACE_CLASS_CCID 0x0b + +struct ccid_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __le16 bcdCCID; + __u8 bMaxSlotIndex; + __u8 bVoltageSupport; + __le32 dwProtocols; + __le32 dwDefaultClock; + __le32 dwMaximumClock; + __u8 bNumClockSupported; + __le32 dwDataRate; + __le32 dwMaxDataRate; + __u8 bNumDataRatesSupported; + __le32 dwMaxIFSD; + __le32 dwSynchProtocols; + __le32 dwMechanical; + __le32 dwFeatures; + __le32 dwMaxCCIDMessageLength; + __u8 bClassGetResponse; + __u8 bClassEnvelope; + __le16 wLcdLayout; + __u8 bPINSupport; + __u8 bMaxCCIDBusySlots; +} __attribute__ ((packed)); + +#endif /* __CCID_H */ -- cgit v1.2.3 From 89259088c1b7fecb43e8e245dc931909132a4e03 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 17 Nov 2018 11:32:29 +0100 Subject: netfilter: nfnetlink_cttimeout: fetch timeouts for udplite and gre, too syzbot was able to trigger the WARN in cttimeout_default_get() by passing UDPLITE as l4protocol. Alias UDPLITE to UDP, both use same timeout values. Furthermore, also fetch GRE timeouts. GRE is a bit more complicated, as it still can be a module and its netns_proto_gre struct layout isn't visible outside of the gre module. Can't move timeouts around, it appears conntrack sysctl unregister assumes net_generic() returns nf_proto_net, so we get crash. Expose layout of netns_proto_gre instead. A followup nf-next patch could make gre tracker be built-in as well if needed, its not that large. Last, make the WARN() mention the missing protocol value in case anything else is missing. Reported-by: syzbot+2fae8fa157dd92618cae@syzkaller.appspotmail.com Fixes: 8866df9264a3 ("netfilter: nfnetlink_cttimeout: pass default timeout policy to obj_to_nlattr") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index b8d95564bd53..14edb795ab43 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -21,6 +21,19 @@ struct nf_ct_gre_keymap { struct nf_conntrack_tuple tuple; }; +enum grep_conntrack { + GRE_CT_UNREPLIED, + GRE_CT_REPLIED, + GRE_CT_MAX +}; + +struct netns_proto_gre { + struct nf_proto_net nf; + rwlock_t keymap_lock; + struct list_head keymap_list; + unsigned int gre_timeouts[GRE_CT_MAX]; +}; + /* add new tuple->key_reply pair to keymap */ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); -- cgit v1.2.3 From 786a9ab1330169f2602238822b4df5d5c4c98f6c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Nov 2018 10:35:17 +0100 Subject: gpio: davinci: restore a way to manually specify the GPIO base Commit 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") broke the network support in legacy boot mode for da850-evm since we can no longer request the MDIO clock GPIO. Other boards may be broken too, which I haven't tested. The problem is in the fact that most board files still use the legacy GPIO API where lines are requested by numbers rather than descriptors. While this should be fixed eventually, in order to unbreak the board for now - provide a way to manually specify the GPIO base in platform data. Fixes: 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski Acked-by: Linus Walleij Signed-off-by: Sekhar Nori --- include/linux/platform_data/gpio-davinci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index f92a47e18034..a93841bfb9f7 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -17,6 +17,8 @@ #define __DAVINCI_GPIO_PLATFORM_H struct davinci_gpio_platform_data { + bool no_auto_base; + u32 base; u32 ngpio; u32 gpio_unbanked; }; -- cgit v1.2.3 From 1052b8ac5282daf35df331edcbdb645839d17e6a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Nov 2018 08:21:49 -0700 Subject: blk-mq: when polling for IO, look for any completion If we want to support async IO polling, then we have to allow finding completions that aren't just for the one we are looking for. Always pass in -1 to the mq_ops->poll() helper, and have that return how many events were found in this poll loop. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9b53db06ad08..f3015e9b5ae3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -867,7 +867,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); -bool blk_poll(struct request_queue *q, blk_qc_t cookie); +int blk_poll(struct request_queue *q, blk_qc_t cookie); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { -- cgit v1.2.3 From 9743139c5d11ab170f70a308dcb88c342390adfb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 16 Nov 2018 09:48:21 -0700 Subject: blk-mq: remove 'tag' parameter from mq_ops->poll() We always pass in -1 now and none of the callers use the tag value, remove the parameter. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 929e8abc5535..ca0520ca6437 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -132,7 +132,7 @@ typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *, typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); -typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int); +typedef int (poll_fn)(struct blk_mq_hw_ctx *); typedef int (map_queues_fn)(struct blk_mq_tag_set *set); typedef bool (busy_fn)(struct request_queue *); typedef void (complete_fn)(struct request *); -- cgit v1.2.3 From 0a1b8b87d064a47fad9ec475316002da28559207 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Nov 2018 08:24:43 -0700 Subject: block: make blk_poll() take a parameter on whether to spin or not blk_poll() has always kept spinning until it found an IO. This is fine for SYNC polling, since we need to find one request we have pending, but in preparation for ASYNC polling it can be beneficial to just check if we have any entries available or not. Existing callers are converted to pass in 'spin == true', to retain the old behavior. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3015e9b5ae3..e3c0a8ec16a7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -283,7 +283,7 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); -typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t); +typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t, bool spin); struct bio_vec; typedef int (dma_drain_needed_fn)(struct request *); @@ -867,7 +867,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); -int blk_poll(struct request_queue *q, blk_qc_t cookie); +int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { -- cgit v1.2.3 From 7847a1455fc4574d53e349d60feb1e1106cdc012 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Fri, 9 Nov 2018 17:21:35 +0300 Subject: ACPI / glue: Add acpi_platform_notify() function Instead of relying on the "platform_notify" callback hook, introducing separate notification function acpi_platform_notify() and calling that directly from drivers core when device entries are added and removed. Signed-off-by: Heikki Krogerus Acked-by: Linus Walleij Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ed80f147bd50..4ba2e2d24676 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1313,4 +1313,14 @@ static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) } #endif +#ifdef CONFIG_ACPI +extern int acpi_platform_notify(struct device *dev, enum kobject_action action); +#else +static inline int +acpi_platform_notify(struct device *dev, enum kobject_action action) +{ + return 0; +} +#endif + #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From 59abd83672f70cac4b6bf9b237506c5bc6837606 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Fri, 9 Nov 2018 17:21:36 +0300 Subject: drivers: base: Introducing software nodes to the firmware node framework Software node is a new struct fwnode_handle type that can be used to describe devices in kernel (software). It is meant to complement fwnodes representing real firmware nodes when they are incomplete (for example missing device properties) and to supply the primary fwnode when the firmware lacks hardware description for a device completely. The software node type is really meant to replace the currently used "property_set" struct fwnode_handle type. The handling of struct property_set is glued to the generic device property handling code, and it is not possible to create a struct property_set independently from the device that it is bind to. struct property_set is only created when device properties are added to already initialized struct device, and control of it is only possible from the generic property handling code. Software nodes are instead designed to be created independently from the device entries (struct device). It makes them much more flexible, as then the device meant to be bind to the node can be created at a later time, and from another location. It is also possible to bind multiple devices to a single software node if needed. The software node implementation also includes support for node hierarchy, which was the main motivation for this commit. The node hierarchy was something that was requested for the struct property_set, but it did not seem reasonable to try to extend the property_set support for that purpose. struct property_set was really meant only for device property handling like the name suggests. Support for struct property_set is not yet removed in this commit, but it will be in the following one. Signed-off-by: Heikki Krogerus Acked-by: Linus Walleij Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index ac8a1ebc4c1b..3789ec755fb6 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -311,4 +311,16 @@ fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port, int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); +/* -------------------------------------------------------------------------- */ +/* Software fwnode support - when HW description is incomplete or missing */ + +bool is_software_node(const struct fwnode_handle *fwnode); + +int software_node_notify(struct device *dev, unsigned long action); + +struct fwnode_handle * +fwnode_create_software_node(const struct property_entry *properties, + const struct fwnode_handle *parent); +void fwnode_remove_software_node(struct fwnode_handle *fwnode); + #endif /* _LINUX_PROPERTY_H_ */ -- cgit v1.2.3 From f8c6d1402b89f22a3647705d63cbd171aa19a77e Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 23 Nov 2018 23:07:14 +0300 Subject: ACPI: fix acpi_find_child_device() invocation in acpi_preset_companion() acpi_find_child_device() accepts boolean not pointer as last argument. Signed-off-by: Alexey Dobriyan [ rjw: Subject ] Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ed80f147bd50..f788cdbbd1b0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -101,7 +101,7 @@ static inline bool has_acpi_companion(struct device *dev) static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { - ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, NULL)); + ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, false)); } static inline const char *acpi_dev_name(struct acpi_device *adev) -- cgit v1.2.3 From 16c15eb16a793f2d81ae52f41f43fb6831b34212 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 26 Nov 2018 09:54:28 -0700 Subject: blk-mq: Return true if request was completed A driver may have internal state to cleanup if we're pretending a request didn't complete. Return 'false' if the command wasn't actually completed due to the timeout error injection, and true otherwise. Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ca0520ca6437..6e3da356a8eb 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -298,7 +298,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); -void blk_mq_complete_request(struct request *rq); +bool blk_mq_complete_request(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio); bool blk_mq_queue_stopped(struct request_queue *q); -- cgit v1.2.3 From af78ff7c6e66832afcdf5418f67b11c409f9e7a1 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 26 Nov 2018 09:54:30 -0700 Subject: blk-mq: Simplify request completion state There are no more users relying on blk-mq request states to prevent double completions, so replace the relatively expensive cmpxchg operation with WRITE_ONCE. Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 6e3da356a8eb..b8de11e0603b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -329,20 +329,6 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); -/** - * blk_mq_mark_complete() - Set request state to complete - * @rq: request to set to complete state - * - * Returns true if request state was successfully set to complete. If - * successful, the caller is responsibile for seeing this request is ended, as - * blk_mq_complete_request will not work again. - */ -static inline bool blk_mq_mark_complete(struct request *rq) -{ - return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) == - MQ_RQ_IN_FLIGHT; -} - /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. -- cgit v1.2.3 From 5f0ed774ed2914decfd397569fface997532e94d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Nov 2018 22:04:33 -0700 Subject: block: sum requests in the plug structure This isn't exactly the same as the previous count, as it includes requests for all devices. But that really doesn't matter, if we have more than the threshold (16) queued up, flush it. It's not worth it to have an expensive list loop for this. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e3c0a8ec16a7..02732cae6080 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1130,6 +1130,7 @@ extern void blk_set_queue_dying(struct request_queue *); struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ + unsigned short rq_count; }; #define BLK_MAX_REQUEST_COUNT 16 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) -- cgit v1.2.3 From 7ca5ce896524f5292e610b27d168269e5ab74951 Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Tue, 13 Nov 2018 12:14:01 -0600 Subject: firmware: add Intel Stratix10 service layer driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some features of the Intel Stratix10 SoC require a level of privilege higher than the kernel is granted. Such secure features include FPGA programming. In terms of the ARMv8 architecture, the kernel runs at Exception Level 1 (EL1), access to the features requires Exception Level 3 (EL3). The Intel Stratix10 SoC service layer provides an in kernel API for drivers to request access to the secure features. The requests are queued and processed one by one. ARM’s SMCCC is used to pass the execution of the requests on to a secure monitor (EL3). The header file stratix10-sve-client.h defines the interface between service providers (FPGA manager is one of them) and service layer. The header file stratix10-smc.h defines the secure monitor call (SMC) message protocols used for service layer driver in normal world (EL1) to communicate with secure monitor SW in secure monitor exception level 3 (EL3). Signed-off-by: Richard Gong Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/intel/stratix10-smc.h | 265 +++++++++++++++++++++ .../linux/firmware/intel/stratix10-svc-client.h | 201 ++++++++++++++++ 2 files changed, 466 insertions(+) create mode 100644 include/linux/firmware/intel/stratix10-smc.h create mode 100644 include/linux/firmware/intel/stratix10-svc-client.h (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h new file mode 100644 index 000000000000..a109e4ccbc7e --- /dev/null +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -0,0 +1,265 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2017-2018, Intel Corporation + */ + +#ifndef __STRATIX10_SMC_H +#define __STRATIX10_SMC_H + +#include +#include + +/** + * This file defines the Secure Monitor Call (SMC) message protocol used for + * service layer driver in normal world (EL1) to communicate with secure + * monitor software in Secure Monitor Exception Level 3 (EL3). + * + * This file is shared with secure firmware (FW) which is out of kernel tree. + * + * An ARM SMC instruction takes a function identifier and up to 6 64-bit + * register values as arguments, and can return up to 4 64-bit register + * value. The operation of the secure monitor is determined by the parameter + * values passed in through registers. + * + * EL1 and EL3 communicates pointer as physical address rather than the + * virtual address. + * + * Functions specified by ARM SMC Calling convention: + * + * FAST call executes atomic operations, returns when the requested operation + * has completed. + * STD call starts a operation which can be preempted by a non-secure + * interrupt. The call can return before the requested operation has + * completed. + * + * a0..a7 is used as register names in the descriptions below, on arm32 + * that translates to r0..r7 and on arm64 to w0..w7. + */ + +/** + * @func_num: function ID + */ +#define INTEL_SIP_SMC_STD_CALL_VAL(func_num) \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_SIP, (func_num)) + +#define INTEL_SIP_SMC_FAST_CALL_VAL(func_num) \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_SIP, (func_num)) + +/** + * Return values in INTEL_SIP_SMC_* call + * + * INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION: + * Secure monitor software doesn't recognize the request. + * + * INTEL_SIP_SMC_STATUS_OK: + * FPGA configuration completed successfully, + * In case of FPGA configuration write operation, it means secure monitor + * software can accept the next chunk of FPGA configuration data. + * + * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY: + * In case of FPGA configuration write operation, it means secure monitor + * software is still processing previous data & can't accept the next chunk + * of data. Service driver needs to issue + * INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE call to query the + * completed block(s). + * + * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR: + * There is error during the FPGA configuration process. + */ +#define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF +#define INTEL_SIP_SMC_STATUS_OK 0x0 +#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY 0x1 +#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_REJECTED 0x2 +#define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR 0x4 +#define INTEL_SIP_SMC_REG_ERROR 0x5 + +/** + * Request INTEL_SIP_SMC_FPGA_CONFIG_START + * + * Sync call used by service driver at EL1 to request the FPGA in EL3 to + * be prepare to receive a new configuration. + * + * Call register usage: + * a0: INTEL_SIP_SMC_FPGA_CONFIG_START. + * a1: flag for full or partial configuration. 0 for full and 1 for partial + * configuration. + * a2-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK, or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a1-3: not used. + */ +#define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_START 1 +#define INTEL_SIP_SMC_FPGA_CONFIG_START \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_START) + +/** + * Request INTEL_SIP_SMC_FPGA_CONFIG_WRITE + * + * Async call used by service driver at EL1 to provide FPGA configuration data + * to secure world. + * + * Call register usage: + * a0: INTEL_SIP_SMC_FPGA_CONFIG_WRITE. + * a1: 64bit physical address of the configuration data memory block + * a2: Size of configuration data block. + * a3-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or + * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a1: 64bit physical address of 1st completed memory block if any completed + * block, otherwise zero value. + * a2: 64bit physical address of 2nd completed memory block if any completed + * block, otherwise zero value. + * a3: 64bit physical address of 3rd completed memory block if any completed + * block, otherwise zero value. + */ +#define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_WRITE 2 +#define INTEL_SIP_SMC_FPGA_CONFIG_WRITE \ + INTEL_SIP_SMC_STD_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_WRITE) + +/** + * Request INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE + * + * Sync call used by service driver at EL1 to track the completed write + * transactions. This request is called after INTEL_SIP_SMC_FPGA_CONFIG_WRITE + * call returns INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY. + * + * Call register usage: + * a0: INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE. + * a1-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or + * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a1: 64bit physical address of 1st completed memory block. + * a2: 64bit physical address of 2nd completed memory block if + * any completed block, otherwise zero value. + * a3: 64bit physical address of 3rd completed memory block if + * any completed block, otherwise zero value. + */ +#define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE 3 +#define INTEL_SIP_SMC_FPGA_CONFIG_COMPLETED_WRITE \ +INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) + +/** + * Request INTEL_SIP_SMC_FPGA_CONFIG_ISDONE + * + * Sync call used by service driver at EL1 to inform secure world that all + * data are sent, to check whether or not the secure world had completed + * the FPGA configuration process. + * + * Call register usage: + * a0: INTEL_SIP_SMC_FPGA_CONFIG_ISDONE. + * a1-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FPGA_CONFIG_STATUS_BUSY or + * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a1-3: not used. + */ +#define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_ISDONE 4 +#define INTEL_SIP_SMC_FPGA_CONFIG_ISDONE \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_ISDONE) + +/** + * Request INTEL_SIP_SMC_FPGA_CONFIG_GET_MEM + * + * Sync call used by service driver at EL1 to query the physical address of + * memory block reserved by secure monitor software. + * + * Call register usage: + * a0:INTEL_SIP_SMC_FPGA_CONFIG_GET_MEM. + * a1-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a1: start of physical address of reserved memory block. + * a2: size of reserved memory block. + * a3: not used. + */ +#define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_GET_MEM 5 +#define INTEL_SIP_SMC_FPGA_CONFIG_GET_MEM \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_GET_MEM) + +/** + * Request INTEL_SIP_SMC_FPGA_CONFIG_LOOPBACK + * + * For SMC loop-back mode only, used for internal integration, debugging + * or troubleshooting. + * + * Call register usage: + * a0: INTEL_SIP_SMC_FPGA_CONFIG_LOOPBACK. + * a1-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR. + * a1-3: not used. + */ +#define INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_LOOPBACK 6 +#define INTEL_SIP_SMC_FPGA_CONFIG_LOOPBACK \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_LOOPBACK) + +/* + * Request INTEL_SIP_SMC_REG_READ + * + * Read a protected register at EL3 + * + * Call register usage: + * a0: INTEL_SIP_SMC_REG_READ. + * a1: register address. + * a2-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_REG_ERROR. + * a1: value in the register + * a2-3: not used. + */ +#define INTEL_SIP_SMC_FUNCID_REG_READ 7 +#define INTEL_SIP_SMC_REG_READ \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_READ) + +/* + * Request INTEL_SIP_SMC_REG_WRITE + * + * Write a protected register at EL3 + * + * Call register usage: + * a0: INTEL_SIP_SMC_REG_WRITE. + * a1: register address + * a2: value to program into register. + * a3-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_REG_ERROR. + * a1-3: not used. + */ +#define INTEL_SIP_SMC_FUNCID_REG_WRITE 8 +#define INTEL_SIP_SMC_REG_WRITE \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_WRITE) + +/* + * Request INTEL_SIP_SMC_FUNCID_REG_UPDATE + * + * Update one or more bits in a protected register at EL3 using a + * read-modify-write operation. + * + * Call register usage: + * a0: INTEL_SIP_SMC_REG_UPDATE. + * a1: register address + * a2: write Mask. + * a3: value to write. + * a4-7: not used. + * + * Return status: + * a0: INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_REG_ERROR. + * a1-3: Not used. + */ +#define INTEL_SIP_SMC_FUNCID_REG_UPDATE 9 +#define INTEL_SIP_SMC_REG_UPDATE \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_UPDATE) + +#endif diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h new file mode 100644 index 000000000000..f2fda7e1ca52 --- /dev/null +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -0,0 +1,201 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2017-2018, Intel Corporation + */ + +#ifndef __STRATIX10_SVC_CLIENT_H +#define __STRATIX10_SVC_CLIENT_H + +/** + * Service layer driver supports client names + * + * fpga: for FPGA configuration + */ +#define SVC_CLIENT_FPGA "fpga" + +/** + * Status of the sent command, in bit number + * + * SVC_COMMAND_STATUS_RECONFIG_REQUEST_OK: + * Secure firmware accepts the request of FPGA reconfiguration. + * + * SVC_STATUS_RECONFIG_BUFFER_SUBMITTED: + * Service client successfully submits FPGA configuration + * data buffer to secure firmware. + * + * SVC_COMMAND_STATUS_RECONFIG_BUFFER_DONE: + * Secure firmware completes data process, ready to accept the + * next WRITE transaction. + * + * SVC_COMMAND_STATUS_RECONFIG_COMPLETED: + * Secure firmware completes FPGA configuration successfully, FPGA should + * be in user mode. + * + * SVC_COMMAND_STATUS_RECONFIG_BUSY: + * FPGA configuration is still in process. + * + * SVC_COMMAND_STATUS_RECONFIG_ERROR: + * Error encountered during FPGA configuration. + */ +#define SVC_STATUS_RECONFIG_REQUEST_OK 0 +#define SVC_STATUS_RECONFIG_BUFFER_SUBMITTED 1 +#define SVC_STATUS_RECONFIG_BUFFER_DONE 2 +#define SVC_STATUS_RECONFIG_COMPLETED 3 +#define SVC_STATUS_RECONFIG_BUSY 4 +#define SVC_STATUS_RECONFIG_ERROR 5 + +/** + * Flag bit for COMMAND_RECONFIG + * + * COMMAND_RECONFIG_FLAG_PARTIAL: + * Set to FPGA configuration type (full or partial), the default + * is full reconfig. + */ +#define COMMAND_RECONFIG_FLAG_PARTIAL 0 + +/** + * Timeout settings for service clients: + * timeout value used in Stratix10 FPGA manager driver. + */ +#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 100 +#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 240 + +struct stratix10_svc_chan; + +/** + * enum stratix10_svc_command_code - supported service commands + * + * @COMMAND_NOOP: do 'dummy' request for integration/debug/trouble-shooting + * + * @COMMAND_RECONFIG: ask for FPGA configuration preparation, return status + * is SVC_STATUS_RECONFIG_REQUEST_OK + * + * @COMMAND_RECONFIG_DATA_SUBMIT: submit buffer(s) of bit-stream data for the + * FPGA configuration, return status is SVC_STATUS_RECONFIG_BUFFER_SUBMITTED, + * or SVC_STATUS_RECONFIG_ERROR + * + * @COMMAND_RECONFIG_DATA_CLAIM: check the status of the configuration, return + * status is SVC_STATUS_RECONFIG_COMPLETED, or SVC_STATUS_RECONFIG_BUSY, or + * SVC_STATUS_RECONFIG_ERROR + * + * @COMMAND_RECONFIG_STATUS: check the status of the configuration, return + * status is SVC_STATUS_RECONFIG_COMPLETED, or SVC_STATUS_RECONFIG_BUSY, or + * SVC_STATUS_RECONFIG_ERROR + */ +enum stratix10_svc_command_code { + COMMAND_NOOP = 0, + COMMAND_RECONFIG, + COMMAND_RECONFIG_DATA_SUBMIT, + COMMAND_RECONFIG_DATA_CLAIM, + COMMAND_RECONFIG_STATUS +}; + +/** + * struct stratix10_svc_client_msg - message sent by client to service + * @payload: starting address of data need be processed + * @payload_length: data size in bytes + * @command: service command + * @arg: args to be passed via registers and not physically mapped buffers + */ +struct stratix10_svc_client_msg { + void *payload; + size_t payload_length; + enum stratix10_svc_command_code command; + u64 arg[3]; +}; + +/** + * struct stratix10_svc_command_config_type - config type + * @flags: flag bit for the type of FPGA configuration + */ +struct stratix10_svc_command_config_type { + u32 flags; +}; + +/** + * struct stratix10_svc_cb_data - callback data structure from service layer + * @status: the status of sent command + * @kaddr1: address of 1st completed data block + * @kaddr2: address of 2nd completed data block + * @kaddr3: address of 3rd completed data block + */ +struct stratix10_svc_cb_data { + u32 status; + void *kaddr1; + void *kaddr2; + void *kaddr3; +}; + +/** + * struct stratix10_svc_client - service client structure + * @dev: the client device + * @receive_cb: callback to provide service client the received data + * @priv: client private data + */ +struct stratix10_svc_client { + struct device *dev; + void (*receive_cb)(struct stratix10_svc_client *client, + struct stratix10_svc_cb_data *cb_data); + void *priv; +}; + +/** + * stratix10_svc_request_channel_byname() - request service channel + * @client: identity of the client requesting the channel + * @name: supporting client name defined above + * + * Return: a pointer to channel assigned to the client on success, + * or ERR_PTR() on error. + */ +struct stratix10_svc_chan +*stratix10_svc_request_channel_byname(struct stratix10_svc_client *client, + const char *name); + +/** + * stratix10_svc_free_channel() - free service channel. + * @chan: service channel to be freed + */ +void stratix10_svc_free_channel(struct stratix10_svc_chan *chan); + +/** + * stratix10_svc_allocate_memory() - allocate the momory + * @chan: service channel assigned to the client + * @size: number of bytes client requests + * + * Service layer allocates the requested number of bytes from the memory + * pool for the client. + * + * Return: the starting address of allocated memory on success, or + * ERR_PTR() on error. + */ +void *stratix10_svc_allocate_memory(struct stratix10_svc_chan *chan, + size_t size); + +/** + * stratix10_svc_free_memory() - free allocated memory + * @chan: service channel assigned to the client + * @kaddr: starting address of memory to be free back to pool + */ +void stratix10_svc_free_memory(struct stratix10_svc_chan *chan, void *kaddr); + +/** + * stratix10_svc_send() - send a message to the remote + * @chan: service channel assigned to the client + * @msg: message data to be sent, in the format of + * struct stratix10_svc_client_msg + * + * Return: 0 for success, -ENOMEM or -ENOBUFS on error. + */ +int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg); + +/** + * intel_svc_done() - complete service request + * @chan: service channel assigned to the client + * + * This function is used by service client to inform service layer that + * client's service requests are completed, or there is an error in the + * request process. + */ +void stratix10_svc_done(struct stratix10_svc_chan *chan); +#endif + -- cgit v1.2.3 From 6b50d882d38d5a1e4c0c476712384067c19c744b Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Tue, 13 Nov 2018 12:14:06 -0600 Subject: firmware: add remote status update client support Extend Intel Stratix10 service layer to support the second service layer client, Remote Status Update (RSU). RSU is used to provide our customers with protection against loading bad bitstreams onto their devices when those devices are booting from flash. Signed-off-by: Richard Gong Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/intel/stratix10-smc.h | 47 ++++++++++++++++++++++ .../linux/firmware/intel/stratix10-svc-client.h | 20 ++++++++- 2 files changed, 65 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index a109e4ccbc7e..5be5dab50b13 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -67,6 +67,12 @@ * * INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR: * There is error during the FPGA configuration process. + * + * INTEL_SIP_SMC_REG_ERROR: + * There is error during a read or write operation of the protected registers. + * + * INTEL_SIP_SMC_RSU_ERROR: + * There is error during a remote status update. */ #define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF #define INTEL_SIP_SMC_STATUS_OK 0x0 @@ -74,6 +80,7 @@ #define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_REJECTED 0x2 #define INTEL_SIP_SMC_FPGA_CONFIG_STATUS_ERROR 0x4 #define INTEL_SIP_SMC_REG_ERROR 0x5 +#define INTEL_SIP_SMC_RSU_ERROR 0x7 /** * Request INTEL_SIP_SMC_FPGA_CONFIG_START @@ -262,4 +269,44 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_REG_UPDATE \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_UPDATE) +/* + * Request INTEL_SIP_SMC_RSU_STATUS + * + * Request remote status update boot log, call is synchronous. + * + * Call register usage: + * a0 INTEL_SIP_SMC_RSU_STATUS + * a1-7 not used + * + * Return status + * a0: Current Image + * a1: Last Failing Image + * a2: Version | State + * a3: Error details | Error location + * + * Or + * + * a0: INTEL_SIP_SMC_RSU_ERROR + */ +#define INTEL_SIP_SMC_FUNCID_RSU_STATUS 11 +#define INTEL_SIP_SMC_RSU_STATUS \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_STATUS) + +/* + * Request INTEL_SIP_SMC_RSU_UPDATE + * + * Request to set the offset of the bitstream to boot after reboot, call + * is synchronous. + * + * Call register usage: + * a0 INTEL_SIP_SMC_RSU_UPDATE + * a1 64bit physical address of the configuration data memory in flash + * a2-7 not used + * + * Return status + * a0 INTEL_SIP_SMC_STATUS_OK + */ +#define INTEL_SIP_SMC_FUNCID_RSU_UPDATE 12 +#define INTEL_SIP_SMC_RSU_UPDATE \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_UPDATE) #endif diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index f2fda7e1ca52..e521f172a47a 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -10,8 +10,10 @@ * Service layer driver supports client names * * fpga: for FPGA configuration + * rsu: for remote status update */ #define SVC_CLIENT_FPGA "fpga" +#define SVC_CLIENT_RSU "rsu" /** * Status of the sent command, in bit number @@ -36,6 +38,9 @@ * * SVC_COMMAND_STATUS_RECONFIG_ERROR: * Error encountered during FPGA configuration. + * + * SVC_STATUS_RSU_OK: + * Secure firmware accepts the request of remote status update (RSU). */ #define SVC_STATUS_RECONFIG_REQUEST_OK 0 #define SVC_STATUS_RECONFIG_BUFFER_SUBMITTED 1 @@ -43,7 +48,8 @@ #define SVC_STATUS_RECONFIG_COMPLETED 3 #define SVC_STATUS_RECONFIG_BUSY 4 #define SVC_STATUS_RECONFIG_ERROR 5 - +#define SVC_STATUS_RSU_OK 6 +#define SVC_STATUS_RSU_ERROR 7 /** * Flag bit for COMMAND_RECONFIG * @@ -56,9 +62,11 @@ /** * Timeout settings for service clients: * timeout value used in Stratix10 FPGA manager driver. + * timeout value used in RSU driver */ #define SVC_RECONFIG_REQUEST_TIMEOUT_MS 100 #define SVC_RECONFIG_BUFFER_TIMEOUT_MS 240 +#define SVC_RSU_REQUEST_TIMEOUT_MS 300 struct stratix10_svc_chan; @@ -81,13 +89,21 @@ struct stratix10_svc_chan; * @COMMAND_RECONFIG_STATUS: check the status of the configuration, return * status is SVC_STATUS_RECONFIG_COMPLETED, or SVC_STATUS_RECONFIG_BUSY, or * SVC_STATUS_RECONFIG_ERROR + * + * @COMMAND_RSU_STATUS: request remote system update boot log, return status + * is log data or SVC_STATUS_RSU_ERROR + * + * @COMMAND_RSU_UPDATE: set the offset of the bitstream to boot after reboot, + * return status is SVC_STATUS_RSU_OK or SVC_STATUS_RSU_ERROR */ enum stratix10_svc_command_code { COMMAND_NOOP = 0, COMMAND_RECONFIG, COMMAND_RECONFIG_DATA_SUBMIT, COMMAND_RECONFIG_DATA_CLAIM, - COMMAND_RECONFIG_STATUS + COMMAND_RECONFIG_STATUS, + COMMAND_RSU_STATUS, + COMMAND_RSU_UPDATE }; /** -- cgit v1.2.3 From 4d3c5c69191f98c7f7e699ff08d2fd96d7070ddb Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 26 Nov 2018 02:17:56 +0000 Subject: Drivers: hv: vmbus: Remove the useless API vmbus_get_outgoing_channel() Commit d86adf482b84 ("scsi: storvsc: Enable multi-queue support") removed the usage of the API in Jan 2017, and the API is not used since then. netvsc and storvsc have their own algorithms to determine the outgoing channel, so this API is useless. And the API is potentially unsafe, because it reads primary->num_sc without any lock held. This can be risky considering the RESCIND-OFFER message. Let's remove the API. Cc: Long Li Cc: Stephen Hemminger Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b3e24368930a..07a367f5e22f 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -830,15 +830,6 @@ struct vmbus_channel { * All Sub-channels of a primary channel are linked here. */ struct list_head sc_list; - /* - * Current number of sub-channels. - */ - int num_sc; - /* - * Number of a sub-channel (position within sc_list) which is supposed - * to be used as the next outgoing channel. - */ - int next_oc; /* * The primary channel this sub-channel belongs to. * This will be NULL for the primary channel. @@ -965,14 +956,6 @@ void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel, void (*chn_rescind_cb)(struct vmbus_channel *)); -/* - * Retrieve the (sub) channel on which to send an outgoing request. - * When a primary channel has multiple sub-channels, we choose a - * channel whose VCPU binding is closest to the VCPU on which - * this call is being made. - */ -struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary); - /* * Check if sub-channels have already been offerred. This API will be useful * when the driver is unloaded after establishing sub-channels. In this case, -- cgit v1.2.3 From 8114865ff82e200b383e46821c25cb0625b842b5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 18 Nov 2018 17:10:15 -0500 Subject: function_graph: Create function_graph_enter() to consolidate architecture code Currently all the architectures do basically the same thing in preparing the function graph tracer on entry to a function. This code can be pulled into a generic location and then this will allow the function graph tracer to be fixed, as well as extended. Create a new function graph helper function_graph_enter() that will call the hook function (ftrace_graph_entry) and the shadow stack operation (ftrace_push_return_trace), and remove the need of the architecture code to manage the shadow stack. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a397907e8d72..5717e8f81c59 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -779,6 +779,9 @@ extern void return_to_handler(void); extern int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long frame_pointer, unsigned long *retp); +extern int +function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); -- cgit v1.2.3 From 0f597ed435b9ea1296e25474b762bedceba97a50 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 20 Nov 2018 14:12:18 -0800 Subject: net/mlx5: EQ, Introduce atomic notifier chain subscription API Use atomic_notifier_chain to fire firmware events at internal mlx5 core components such as eswitch/fpga/clock/FW tracer/etc.., this is to avoid explicit calls from low level mlx5_core to upper components and to simplify the mlx5_core API for future developments. Simply provide register/unregister notifiers API and call the notifier chain on firmware async events. Example: to subscribe to a FW event: struct mlx5_nb port_event; MLX5_NB_INIT(&port_event, port_event_handler, PORT_CHANGE); mlx5_eq_notifier_register(mdev, &port_event); where: - port_event_handler is the notifier block callback. - PORT_EVENT is the suffix of MLX5_EVENT_TYPE_PORT_CHANGE. The above will guarantee that port_event_handler will receive all FW events of the type MLX5_EVENT_TYPE_PORT_CHANGE. To receive all FW/HW events one can subscribe to MLX5_EVENT_TYPE_NOTIFY_ANY. The next few patches will start moving all mlx5 core components to use this new API and cleanup mlx5_eq_async_int misx handler from component explicit calls and specific logic. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 10 +++++++++- include/linux/mlx5/eq.h | 16 ++++++++++++++-- 2 files changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index e326524bafcc..f7c8bebfe472 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -301,9 +301,15 @@ enum { MLX5_EVENT_QUEUE_TYPE_DCT = 6, }; +/* mlx5 components can subscribe to any one of these events via + * mlx5_eq_notifier_register API. + */ enum mlx5_event { + /* Special value to subscribe to any event */ + MLX5_EVENT_TYPE_NOTIFY_ANY = 0x0, + /* HW events enum start: comp events are not subscribable */ MLX5_EVENT_TYPE_COMP = 0x0, - + /* HW Async events enum start: subscribable events */ MLX5_EVENT_TYPE_PATH_MIG = 0x01, MLX5_EVENT_TYPE_COMM_EST = 0x02, MLX5_EVENT_TYPE_SQ_DRAINED = 0x03, @@ -341,6 +347,8 @@ enum mlx5_event { MLX5_EVENT_TYPE_FPGA_QP_ERROR = 0x21, MLX5_EVENT_TYPE_DEVICE_TRACER = 0x26, + + MLX5_EVENT_TYPE_MAX = MLX5_EVENT_TYPE_DEVICE_TRACER + 1, }; enum { diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 71d82c5a1a02..00045cc4ea11 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -4,8 +4,6 @@ #ifndef MLX5_CORE_EQ_H #define MLX5_CORE_EQ_H -#include - enum { MLX5_EQ_PAGEREQ_IDX = 0, MLX5_EQ_CMD_IDX = 1, @@ -22,6 +20,7 @@ enum { #define MLX5_NUM_SPARE_EQE (0x80) struct mlx5_eq; +struct mlx5_core_dev; struct mlx5_eq_param { u8 index; @@ -57,4 +56,17 @@ static inline u32 mlx5_eq_update_cc(struct mlx5_eq *eq, u32 cc) return cc; } +struct mlx5_nb { + struct notifier_block nb; + u8 event_type; +}; + +#define mlx5_nb_cof(ptr, type, member) \ + (container_of(container_of(ptr, struct mlx5_nb, nb), type, member)) + +#define MLX5_NB_INIT(name, handler, event) do { \ + (name)->nb.notifier_call = handler; \ + (name)->event_type = MLX5_EVENT_TYPE_##event; \ +} while (0) + #endif /* MLX5_CORE_EQ_H */ -- cgit v1.2.3 From 41069256e93045a45a2c359c9715439be0b47bf4 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 20 Nov 2018 14:12:21 -0800 Subject: net/mlx5: Clock, Use async events chain Remove the explicit call to mlx5_pps_event on MLX5_EVENT_TYPE_PPS_EVENT and let clock logic to register its own handler when its ready. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f41e6713df10..99a23db9a929 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -50,6 +50,7 @@ #include #include #include +#include #include #include @@ -671,6 +672,8 @@ struct mlx5_pps { }; struct mlx5_clock { + struct mlx5_core_dev *mdev; + struct mlx5_nb pps_nb; seqlock_t lock; struct cyclecounter cycles; struct timecounter tc; @@ -678,7 +681,6 @@ struct mlx5_clock { u32 nominal_c_mult; unsigned long overflow_period; struct delayed_work overflow_work; - struct mlx5_core_dev *mdev; struct ptp_clock *ptp; struct ptp_clock_info ptp_info; struct mlx5_pps pps_info; -- cgit v1.2.3 From 0cf53c1247565b339a23d82a1853a0c41e9a2a34 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 20 Nov 2018 14:12:23 -0800 Subject: net/mlx5: FWPage, Use async events chain Remove the explicit call to mlx5_core_req_pages_handler on MLX5_EVENT_TYPE_PAGE_REQUEST and let FW page logic to register its own handler when its ready. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 99a23db9a929..61088ad33500 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -564,6 +564,7 @@ struct mlx5_priv { struct mlx5_eq_table *eq_table; /* pages stuff */ + struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct rb_root page_root; int fw_pages; @@ -962,9 +963,9 @@ int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, u16 opmod, u8 port); -void mlx5_pagealloc_init(struct mlx5_core_dev *dev); +int mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); -int mlx5_pagealloc_start(struct mlx5_core_dev *dev); +void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s32 npages); -- cgit v1.2.3 From 71edc69ca1a78ce18411a540c550a4ef1eb017cd Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 20 Nov 2018 14:12:24 -0800 Subject: net/mlx5: CmdIF, Use async events chain Remove the explicit call to mlx5_cmd_comp_handler on MLX5_EVENT_TYPE_CMD and let command interface to register its own handler when its ready. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 61088ad33500..a8d638134fc8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -278,6 +278,8 @@ struct mlx5_cmd_stats { }; struct mlx5_cmd { + struct mlx5_nb nb; + void *cmd_alloc_buf; dma_addr_t alloc_dma; int alloc_size; -- cgit v1.2.3 From 221c14f3d12489ced0f2ca8b31b2221c5dbbf145 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 20 Nov 2018 14:12:25 -0800 Subject: net/mlx5: Resource tables, Use async events chain Remove the explicit call to QP/SRQ resources events handlers on several FW events and let resources logic register resources events notifiers via the new API. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a8d638134fc8..afba0864f45c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -464,6 +464,8 @@ struct mlx5_core_health { }; struct mlx5_qp_table { + struct mlx5_nb nb; + /* protect radix tree */ spinlock_t lock; @@ -471,6 +473,8 @@ struct mlx5_qp_table { }; struct mlx5_srq_table { + struct mlx5_nb catas_err_nb; + struct mlx5_nb rq_limit_nb; /* protect radix tree */ spinlock_t lock; @@ -978,8 +982,6 @@ void mlx5_unregister_debugfs(void); void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); -void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type); -void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type); struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn); -- cgit v1.2.3 From 69c1280b1f3b9123bc5154b2062507abcc14c3ef Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 20 Nov 2018 14:12:27 -0800 Subject: net/mlx5: Device events, Use async events chain Move all the generic async events handling into new specific events handling file events.c to keep eq.c file clean from concrete event logic handling. Use new API to register for NOTIFY_ANY to handle generic events and dispatch allowed events to mlx5_core consumers (mlx5_ib and mlx5e) Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 29 ++--------------------------- include/linux/mlx5/port.h | 3 --- 2 files changed, 2 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index afba0864f45c..ba64ecf72478 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -514,6 +514,7 @@ struct mlx5_fc_stats { unsigned long sampling_interval; /* jiffies */ }; +struct mlx5_events; struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; @@ -540,31 +541,6 @@ struct mlx5_rl_table { struct mlx5_rl_entry *rl_entry; }; -enum port_module_event_status_type { - MLX5_MODULE_STATUS_PLUGGED = 0x1, - MLX5_MODULE_STATUS_UNPLUGGED = 0x2, - MLX5_MODULE_STATUS_ERROR = 0x3, - MLX5_MODULE_STATUS_NUM = 0x3, -}; - -enum port_module_event_error_type { - MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED, - MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE, - MLX5_MODULE_EVENT_ERROR_BUS_STUCK, - MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT, - MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST, - MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER, - MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE, - MLX5_MODULE_EVENT_ERROR_BAD_CABLE, - MLX5_MODULE_EVENT_ERROR_UNKNOWN, - MLX5_MODULE_EVENT_ERROR_NUM, -}; - -struct mlx5_port_module_event_stats { - u64 status_counters[MLX5_MODULE_STATUS_NUM]; - u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM]; -}; - struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table *eq_table; @@ -614,6 +590,7 @@ struct mlx5_priv { struct list_head waiting_events_list; bool is_accum_events; + struct mlx5_events *events; struct mlx5_flow_steering *steering; struct mlx5_mpfs *mpfs; @@ -624,8 +601,6 @@ struct mlx5_priv { struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; - struct mlx5_port_module_event_stats pme_stats; - struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 34aed6032f86..bf4bc01ffb0c 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -107,9 +107,6 @@ enum mlx5e_connector_type { #define MLX5E_PROT_MASK(link_mode) (1 << link_mode) -#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF -#define PORT_MODULE_EVENT_ERROR_TYPE_MASK 0xF - int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int ptys_size, int proto_mask, u8 local_port); -- cgit v1.2.3 From b1ab95c63622e9d9bd0ce685e149034d393afc2e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 5 Nov 2018 14:54:27 -0800 Subject: arch: Make phys_initrd_start and phys_initrd_size global variables Make phys_initrd_start and phys_initrd_size global variables declared in init/do_mounts_initrd.c such that we can later have generic code in drivers/of/fdt.c populate those variables for us. This requires both the ARM and unicore32 implementations to be properly guarded against CONFIG_BLK_DEV_INITRD, and also initialize the variables to the expected default values (unicore32). Signed-off-by: Florian Fainelli Reviewed-by: Mike Rapoport Signed-off-by: Rob Herring --- include/linux/initrd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 84b423044088..14beaff9b445 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -21,4 +21,7 @@ extern int initrd_below_start_ok; extern unsigned long initrd_start, initrd_end; extern void free_initrd_mem(unsigned long, unsigned long); +extern phys_addr_t phys_initrd_start; +extern unsigned long phys_initrd_size; + extern unsigned int real_root_dev; -- cgit v1.2.3 From 2a1fe215e7300c7ebd6a7a24afcab71db5107bb0 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Mon, 26 Nov 2018 18:40:07 -0500 Subject: audit: use current whenever possible There are many places, notably audit_log_task_info() and audit_log_exit(), that take task_struct pointers but in reality they are always working on the current task. This patch eliminates the task_struct arguments and uses current directly which allows a number of cleanups as well. Acked-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 58cf665f597e..a625c29a2ea2 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -151,8 +151,7 @@ extern void audit_log_link_denied(const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); -extern void audit_log_task_info(struct audit_buffer *ab, - struct task_struct *tsk); +extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); @@ -200,8 +199,7 @@ static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } -static inline void audit_log_task_info(struct audit_buffer *ab, - struct task_struct *tsk) +static inline void audit_log_task_info(struct audit_buffer *ab) { } #define audit_enabled AUDIT_OFF #endif /* CONFIG_AUDIT */ -- cgit v1.2.3 From e2c95a61656d29ceaac97b6a975c8a1f26e26f15 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 26 Nov 2018 14:05:38 +0100 Subject: bpf, ppc64: generalize fetching subprog into bpf_jit_get_func_addr Make fetching of the BPF call address from ppc64 JIT generic. ppc64 was using a slightly different variant rather than through the insns' imm field encoding as the target address would not fit into that space. Therefore, the target subprog number was encoded into the insns' offset and fetched through fp->aux->func[off]->bpf_func instead. Given there are other JITs with this issue and the mechanism of fetching the address is JIT-generic, move it into the core as a helper instead. On the JIT side, we get information on whether the retrieved address is a fixed one, that is, not changing through JIT passes, or a dynamic one. For the former, JITs can optimize their imm emission because this doesn't change jump offsets throughout JIT process. Signed-off-by: Daniel Borkmann Reviewed-by: Sandipan Das Tested-by: Sandipan Das Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index de629b706d1d..448dcc448f1f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -866,6 +866,10 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr); void bpf_jit_free(struct bpf_prog *fp); +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed); + struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); -- cgit v1.2.3 From ba64e7d8525236aa56ab58ba3a3a71615c4ee289 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 24 Nov 2018 23:20:44 -0800 Subject: bpf: btf: support proper non-jit func info Commit 838e96904ff3 ("bpf: Introduce bpf_func_info") added bpf func info support. The userspace is able to get better ksym's for bpf programs with jit, and is able to print out func prototypes. For a program containing func-to-func calls, the existing implementation returns user specified number of function calls and BTF types if jit is enabled. If the jit is not enabled, it only returns the type for the main function. This is undesirable. Interpreter may still be used and we should keep feature identical regardless of whether jit is enabled or not. This patch fixed this discrepancy. Fixes: 838e96904ff3 ("bpf: Introduce bpf_func_info") Signed-off-by: Yonghong Song Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++-- include/linux/bpf_verifier.h | 1 - 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7f0e225bf630..e82b7039fc66 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -299,7 +299,8 @@ struct bpf_prog_aux { u32 max_pkt_offset; u32 stack_depth; u32 id; - u32 func_cnt; + u32 func_cnt; /* used by non-func prog as the number of func progs */ + u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ bool offload_requested; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ @@ -317,7 +318,8 @@ struct bpf_prog_aux { #endif struct bpf_prog_offload *offload; struct btf *btf; - u32 type_id; /* type id for this prog/func */ + struct bpf_func_info *func_info; + u32 func_info_cnt; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 204382f46fd8..11f5df1092d9 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -204,7 +204,6 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u16 stack_depth; /* max. stack depth used by this function */ - u32 type_id; /* btf type_id for this subprog */ }; /* single container for all structs -- cgit v1.2.3 From c9d76d0655c06b8c1f944e46c4fd9e9cf4b331c0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Wed, 29 Aug 2018 23:29:21 +0200 Subject: dma-mapping: fix return type of dma_set_max_seg_size() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The function dma_set_max_seg_size() can return either 0 on success or -EIO on error. Change its return type from unsigned int to int to capture this. Signed-off-by: Niklas Söderlund Reviewed-by: Geert Uytterhoeven Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 15bd41447025..0f81c713f6e9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -676,8 +676,7 @@ static inline unsigned int dma_get_max_seg_size(struct device *dev) return SZ_64K; } -static inline unsigned int dma_set_max_seg_size(struct device *dev, - unsigned int size) +static inline int dma_set_max_seg_size(struct device *dev, unsigned int size) { if (dev->dma_parms) { dev->dma_parms->max_segment_size = size; -- cgit v1.2.3 From 7440172974e85b1828bdd84ac6b23b5bcad9c5eb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 6 Nov 2018 18:44:52 -0800 Subject: tracing: Replace synchronize_sched() and call_rcu_sched() Now that synchronize_rcu() waits for preempt-disable regions of code as well as RCU read-side critical sections, synchronize_sched() can be replaced by synchronize_rcu(). Similarly, call_rcu_sched() can be replaced by call_rcu(). This commit therefore makes these changes. Signed-off-by: Paul E. McKenney Cc: Ingo Molnar Cc: Acked-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 538ba1a58f5b..432080b59c26 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -82,7 +82,7 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb) static inline void tracepoint_synchronize_unregister(void) { synchronize_srcu(&tracepoint_srcu); - synchronize_sched(); + synchronize_rcu(); } #else static inline void tracepoint_synchronize_unregister(void) -- cgit v1.2.3 From aacb5d91ab1bfbb0e8123da59a2e333d52ba7f60 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 28 Oct 2018 10:32:51 -0700 Subject: srcu: Use "ssp" instead of "sp" for srcu_struct pointer In RCU, the distinction between "rsp", "rnp", and "rdp" has served well for a great many years, but in SRCU, "sp" vs. "sdp" has proven confusing. This commit therefore renames SRCU's "sp" pointers to "ssp", so that there is "ssp" for srcu_struct pointer, "snp" for srcu_node pointer, and "sdp" for srcu_data pointer. Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 78 ++++++++++++++++++++++++------------------------ include/linux/srcutiny.h | 24 +++++++-------- include/linux/srcutree.h | 8 ++--- 3 files changed, 55 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index ebd5f1511690..c614375cd264 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -38,20 +38,20 @@ struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC -int __init_srcu_struct(struct srcu_struct *sp, const char *name, +int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); -#define init_srcu_struct(sp) \ +#define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ - __init_srcu_struct((sp), #sp, &__srcu_key); \ + __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -int init_srcu_struct(struct srcu_struct *sp); +int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -67,28 +67,28 @@ int init_srcu_struct(struct srcu_struct *sp); struct srcu_struct { }; #endif -void call_srcu(struct srcu_struct *sp, struct rcu_head *head, +void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); -void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced); -int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); -void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); -void synchronize_srcu(struct srcu_struct *sp); +void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced); +int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); +void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); +void synchronize_srcu(struct srcu_struct *ssp); /** * cleanup_srcu_struct - deconstruct a sleep-RCU structure - * @sp: structure to clean up. + * @ssp: structure to clean up. * * Must invoke this after you are finished using a given srcu_struct that * was initialized via init_srcu_struct(), else you leak memory. */ -static inline void cleanup_srcu_struct(struct srcu_struct *sp) +static inline void cleanup_srcu_struct(struct srcu_struct *ssp) { - _cleanup_srcu_struct(sp, false); + _cleanup_srcu_struct(ssp, false); } /** * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure - * @sp: structure to clean up. + * @ssp: structure to clean up. * * Must invoke this after you are finished using a given srcu_struct that * was initialized via init_srcu_struct(), else you leak memory. Also, @@ -103,16 +103,16 @@ static inline void cleanup_srcu_struct(struct srcu_struct *sp) * (with high probability, anyway), and will also cause the srcu_struct * to be leaked. */ -static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *sp) +static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *ssp) { - _cleanup_srcu_struct(sp, true); + _cleanup_srcu_struct(ssp, true); } #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? - * @sp: The srcu_struct structure to check + * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, @@ -126,16 +126,16 @@ static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *sp) * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ -static inline int srcu_read_lock_held(const struct srcu_struct *sp) +static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; - return lock_is_held(&sp->dep_map); + return lock_is_held(&ssp->dep_map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -static inline int srcu_read_lock_held(const struct srcu_struct *sp) +static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } @@ -145,7 +145,7 @@ static inline int srcu_read_lock_held(const struct srcu_struct *sp) /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing - * @sp: pointer to the srcu_struct, which is used to check that we + * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * @@ -154,32 +154,32 @@ static inline int srcu_read_lock_held(const struct srcu_struct *sp) * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ -#define srcu_dereference_check(p, sp, c) \ - __rcu_dereference_check((p), (c) || srcu_read_lock_held(sp), __rcu) +#define srcu_dereference_check(p, ssp, c) \ + __rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing - * @sp: pointer to the srcu_struct, which is used to check that we + * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ -#define srcu_dereference(p, sp) srcu_dereference_check((p), (sp), 0) +#define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing - * @sp: pointer to the srcu_struct, which is used to check that we + * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ -#define srcu_dereference_notrace(p, sp) srcu_dereference_check((p), (sp), 1) +#define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. - * @sp: srcu_struct in which to register the new reader. + * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to @@ -194,44 +194,44 @@ static inline int srcu_read_lock_held(const struct srcu_struct *sp) * srcu_read_unlock() in an irq handler if the matching srcu_read_lock() * was invoked in process context. */ -static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) +static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; - retval = __srcu_read_lock(sp); - rcu_lock_acquire(&(sp)->dep_map); + retval = __srcu_read_lock(ssp); + rcu_lock_acquire(&(ssp)->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int -srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp) +srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; - retval = __srcu_read_lock(sp); + retval = __srcu_read_lock(ssp); return retval; } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. - * @sp: srcu_struct in which to unregister the old reader. + * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ -static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) - __releases(sp) +static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) + __releases(ssp) { - rcu_lock_release(&(sp)->dep_map); - __srcu_read_unlock(sp, idx); + rcu_lock_release(&(ssp)->dep_map); + __srcu_read_unlock(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void -srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp) +srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { - __srcu_read_unlock(sp, idx); + __srcu_read_unlock(ssp, idx); } /** diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index f41d2fb09f87..b19216aaaef2 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -60,7 +60,7 @@ void srcu_drive_gp(struct work_struct *wp); #define DEFINE_STATIC_SRCU(name) \ static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) -void synchronize_srcu(struct srcu_struct *sp); +void synchronize_srcu(struct srcu_struct *ssp); /* * Counts the new reader in the appropriate per-CPU element of the @@ -68,36 +68,36 @@ void synchronize_srcu(struct srcu_struct *sp); * __srcu_read_unlock() must be in the same handler instance. Returns an * index that must be passed to the matching srcu_read_unlock(). */ -static inline int __srcu_read_lock(struct srcu_struct *sp) +static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; - idx = READ_ONCE(sp->srcu_idx); - WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1); + idx = READ_ONCE(ssp->srcu_idx); + WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1); return idx; } -static inline void synchronize_srcu_expedited(struct srcu_struct *sp) +static inline void synchronize_srcu_expedited(struct srcu_struct *ssp) { - synchronize_srcu(sp); + synchronize_srcu(ssp); } -static inline void srcu_barrier(struct srcu_struct *sp) +static inline void srcu_barrier(struct srcu_struct *ssp) { - synchronize_srcu(sp); + synchronize_srcu(ssp); } /* Defined here to avoid size increase for non-torture kernels. */ -static inline void srcu_torture_stats_print(struct srcu_struct *sp, +static inline void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf) { int idx; - idx = READ_ONCE(sp->srcu_idx) & 0x1; + idx = READ_ONCE(ssp->srcu_idx) & 0x1; pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", tt, tf, idx, - READ_ONCE(sp->srcu_lock_nesting[!idx]), - READ_ONCE(sp->srcu_lock_nesting[idx])); + READ_ONCE(ssp->srcu_lock_nesting[!idx]), + READ_ONCE(ssp->srcu_lock_nesting[idx])); } #endif diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 0ae91b3a7406..6f292bd3e7db 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -51,7 +51,7 @@ struct srcu_data { unsigned long grpmask; /* Mask for leaf srcu_node */ /* ->srcu_data_have_cbs[]. */ int cpu; - struct srcu_struct *sp; + struct srcu_struct *ssp; }; /* @@ -138,8 +138,8 @@ struct srcu_struct { #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) -void synchronize_srcu_expedited(struct srcu_struct *sp); -void srcu_barrier(struct srcu_struct *sp); -void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf); +void synchronize_srcu_expedited(struct srcu_struct *ssp); +void srcu_barrier(struct srcu_struct *ssp); +void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf); #endif -- cgit v1.2.3 From 70d188041e6f1f92004f1d5d7ddfd5013273b7a5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 14 Nov 2018 16:09:03 +0100 Subject: serdev: make synchronous write helper interruptible Allow the synchronous serdev_device_write() helper to be interrupted. This is useful for cases where I/O is performed on behalf of user space and we don't want to block indefinitely when using flow control. Signed-off-by: Johan Hovold Reviewed-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- include/linux/serdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serdev.h b/include/linux/serdev.h index f153b2c7f0cd..070bf4e92df7 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -210,7 +210,7 @@ void serdev_device_wait_until_sent(struct serdev_device *, long); int serdev_device_get_tiocm(struct serdev_device *); int serdev_device_set_tiocm(struct serdev_device *, int, int); void serdev_device_write_wakeup(struct serdev_device *); -int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, unsigned long); +int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, long); void serdev_device_write_flush(struct serdev_device *); int serdev_device_write_room(struct serdev_device *); -- cgit v1.2.3 From d125f3f866df88da5a85df00291f88f0baa89f7c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 07:40:39 -0500 Subject: function_graph: Make ftrace_push_return_trace() static As all architectures now call function_graph_enter() to do the entry work, no architecture should ever call ftrace_push_return_trace(). Make it static. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 5717e8f81c59..dd16e8218db3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -776,9 +776,6 @@ struct ftrace_ret_stack { */ extern void return_to_handler(void); -extern int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer, unsigned long *retp); extern int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp); -- cgit v1.2.3 From 39eb456dacb543de90d3bc6a8e0ac5cf51ac475e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 08:07:12 -0500 Subject: function_graph: Use new curr_ret_depth to manage depth instead of curr_ret_stack Currently, the depth of the ret_stack is determined by curr_ret_stack index. The issue is that there's a race between setting of the curr_ret_stack and calling of the callback attached to the return of the function. Commit 03274a3ffb44 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") moved the calling of the callback to after the setting of the curr_ret_stack, even stating that it was safe to do so, when in fact, it was the reason there was a barrier() there (yes, I should have commented that barrier()). Not only does the curr_ret_stack keep track of the current call graph depth, it also keeps the ret_stack content from being overwritten by new data. The function profiler, uses the "subtime" variable of ret_stack structure and by moving the curr_ret_stack, it allows for interrupts to use the same structure it was using, corrupting the data, and breaking the profiler. To fix this, there needs to be two variables to handle the call stack depth and the pointer to where the ret_stack is being used, as they need to change at two different locations. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d6183a55e8eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1116,6 +1116,7 @@ struct task_struct { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; + int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; -- cgit v1.2.3 From 321a874a7ef85655e93b3206d0f36b4a6097f948 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:38 +0100 Subject: sched/smt: Expose sched_smt_present static key Make the scheduler's 'sched_smt_present' static key globaly available, so it can be used in the x86 speculation control code. Provide a query function and a stub for the CONFIG_SMP=n case. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.430168326@linutronix.de --- include/linux/sched/smt.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/sched/smt.h (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h new file mode 100644 index 000000000000..c9e0be514110 --- /dev/null +++ b/include/linux/sched/smt.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_SMT_H +#define _LINUX_SCHED_SMT_H + +#include + +#ifdef CONFIG_SCHED_SMT +extern struct static_key_false sched_smt_present; + +static __always_inline bool sched_smt_active(void) +{ + return static_branch_likely(&sched_smt_present); +} +#else +static inline bool sched_smt_active(void) { return false; } +#endif + +#endif -- cgit v1.2.3 From a74cfffb03b73d41e08f84c2e5c87dec0ce3db9f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:39 +0100 Subject: x86/speculation: Rework SMT state change arch_smt_update() is only called when the sysfs SMT control knob is changed. This means that when SMT is enabled in the sysfs control knob the system is considered to have SMT active even if all siblings are offline. To allow finegrained control of the speculation mitigations, the actual SMT state is more interesting than the fact that siblings could be enabled. Rework the code, so arch_smt_update() is invoked from each individual CPU hotplug function, and simplify the update function while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.521974984@linutronix.de --- include/linux/sched/smt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index c9e0be514110..59d3736c454c 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -15,4 +15,6 @@ static __always_inline bool sched_smt_active(void) static inline bool sched_smt_active(void) { return false; } #endif +void arch_smt_update(void); + #endif -- cgit v1.2.3 From 46f7ecb1e7359f183f5bbd1e08b90e10e52164f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:50 +0100 Subject: ptrace: Remove unused ptrace_may_access_sched() and MODE_IBRS The IBPB control code in x86 removed the usage. Remove the functionality which was introduced for this. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.559149393@linutronix.de --- include/linux/ptrace.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 6c2ffed907f5..de20ede2c5c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -64,15 +64,12 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 -#define PTRACE_MODE_SCHED 0x20 -#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) -#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -90,20 +87,6 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); -/** - * ptrace_may_access - check whether the caller is permitted to access - * a target task. - * @task: target task - * @mode: selects type of access and caller credentials - * - * Returns true on success, false on denial. - * - * Similar to ptrace_may_access(). Only to be called from context switch - * code. Does not call into audit and the regular LSM hooks due to locking - * constraints. - */ -extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); - static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); -- cgit v1.2.3 From 9137bb27e60e554dab694eafa4cca241fa3a694f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:53 +0100 Subject: x86/speculation: Add prctl() control for indirect branch speculation Add the PR_SPEC_INDIRECT_BRANCH option for the PR_GET_SPECULATION_CTRL and PR_SET_SPECULATION_CTRL prctls to allow fine grained per task control of indirect branch speculation via STIBP and IBPB. Invocations: Check indirect branch speculation status with - prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); Enable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); Disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); Force disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); See Documentation/userspace-api/spec_ctrl.rst. Signed-off-by: Tim Chen Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.866780996@linutronix.de --- include/linux/sched.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d607db5fcc6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1453,6 +1453,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1484,6 +1486,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { -- cgit v1.2.3 From faa2541f5b1afa8b6d777a73bc2f27d5c8c98695 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 26 Nov 2018 17:47:44 +0100 Subject: leds: trigger: Introduce audio mute LED trigger MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a new LED trigger for coupling the audio mixer change with the LED on laptops or other devices. Currently there are two trigger types, "audio-mute" and "audio-micmute". The audio driver triggers the LED brightness change via ledtrig_audio_set() call with the proper type (either mute or mic-mute). OTOH, the consumers may call ledtrig_audio_get() for the initial brightness value that may have been set by the audio driver beforehand. This new stuff will be used by HD-audio codec driver and some platform drivers (thinkpad_acpi and dell-laptop, also upcoming huawei-wmi). Acked-by: Jacek Anaszewski Acked-by: Pavel Machek Acked-by: Pali Rohár Signed-off-by: Takashi Iwai --- include/linux/leds.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 7393a316d9fa..580cbaef789a 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -487,4 +487,24 @@ struct led_pattern { int brightness; }; +enum led_audio { + LED_AUDIO_MUTE, /* master mute LED */ + LED_AUDIO_MICMUTE, /* mic mute LED */ + NUM_AUDIO_LEDS +}; + +#if IS_ENABLED(CONFIG_LEDS_TRIGGER_AUDIO) +enum led_brightness ledtrig_audio_get(enum led_audio type); +void ledtrig_audio_set(enum led_audio type, enum led_brightness state); +#else +static inline enum led_brightness ledtrig_audio_get(enum led_audio type) +{ + return LED_OFF; +} +static inline void ledtrig_audio_set(enum led_audio type, + enum led_brightness state) +{ +} +#endif + #endif /* __LINUX_LEDS_H_INCLUDED */ -- cgit v1.2.3 From bc184549853133303cf08d1f19477f9c87ef39fb Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 16 Nov 2018 15:41:41 +0200 Subject: ASoC: davinci-mcasp: Implement configurable dismod handling If the dismod is specified in the DT node, use the specified custom value to configure the drive on state of the inactive TX slots. If the dismod is not present or booted in legacy mode, the dismod is set to low as it was the original behavior. Signed-off-by: Peter Ujfalusi Signed-off-by: Mark Brown --- include/linux/platform_data/davinci_asp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index 85ad68f9206a..7fe80f1c7e08 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -79,6 +79,7 @@ struct davinci_mcasp_pdata { /* McASP specific fields */ int tdm_slots; u8 op_mode; + u8 dismod; u8 num_serializer; u8 *serial_dir; u8 version; -- cgit v1.2.3 From 3f2b7b9035107d6096ea438ea3d97dcf0481b6d2 Mon Sep 17 00:00:00 2001 From: "kiran.modukuri" Date: Mon, 26 Nov 2018 15:41:48 +0000 Subject: fscache: Fix race in fscache_op_complete() due to split atomic_sub & read The code in fscache_retrieval_complete is using atomic_sub followed by an atomic_read: atomic_sub(n_pages, &op->n_pages); if (atomic_read(&op->n_pages) <= 0) fscache_op_complete(&op->op, true); This causes two threads doing a decrement of n_pages to race with each other seeing the op->refcount 0 at same time - and they end up calling fscache_op_complete() in both the threads leading to an assertion failure. Fix this by using atomic_sub_return_relaxed() instead of two calls. Note that I'm using 'relaxed' rather than, say, 'release' as there aren't multiple variables that appear to need ordering across the release. The oops looks something like: FS-Cache: Assertion failed FS-Cache: 0 > 0 is false ... kernel BUG at /usr/src/linux-4.4.0/fs/fscache/operation.c:449! ... Workqueue: fscache_operation fscache_op_work_func [fscache] ... RIP: 0010:[] fscache_op_complete+0x10d/0x180 [fscache] ... Call Trace: [] cachefiles_read_copier+0x3a9/0x410 [cachefiles] [] fscache_op_work_func+0x22/0x50 [fscache] [] process_one_work+0x150/0x3f0 [] worker_thread+0x11a/0x470 [] ? __schedule+0x359/0x980 [] ? rescuer_thread+0x310/0x310 [] kthread+0xd6/0xf0 [] ? kthread_park+0x60/0x60 [] ret_from_fork+0x3f/0x70 [] ? kthread_park+0x60/0x60 This seen this in 4.4.x kernels and the same bug affects fscache in latest upstreams kernels. Fixes: 1bb4b7f98f36 ("FS-Cache: The retrieval remaining-pages counter needs to be atomic_t") Signed-off-by: Kiran Kumar Modukuri Signed-off-by: David Howells --- include/linux/fscache-cache.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 34cf0fdd7dc7..610815e3f1aa 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -196,8 +196,7 @@ static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) static inline void fscache_retrieval_complete(struct fscache_retrieval *op, int n_pages) { - atomic_sub(n_pages, &op->n_pages); - if (atomic_read(&op->n_pages) <= 0) + if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) fscache_op_complete(&op->op, false); } -- cgit v1.2.3 From 94a2c3a32b62e868dc1e3d854326745a7f1b8c7a Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Wed, 28 Nov 2018 16:42:01 +0800 Subject: block: use rcu_work instead of call_rcu to avoid sleep in softirq We recently got a stack by syzkaller like this: BUG: sleeping function called from invalid context at mm/slab.h:361 in_atomic(): 1, irqs_disabled(): 0, pid: 6644, name: blkid INFO: lockdep is turned off. CPU: 1 PID: 6644 Comm: blkid Not tainted 4.4.163-514.55.6.9.x86_64+ #76 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 0000000000000000 5ba6a6b879e50c00 ffff8801f6b07b10 ffffffff81cb2194 0000000041b58ab3 ffffffff833c7745 ffffffff81cb2080 5ba6a6b879e50c00 0000000000000000 0000000000000001 0000000000000004 0000000000000000 Call Trace: [] __dump_stack lib/dump_stack.c:15 [inline] [] dump_stack+0x114/0x1a0 lib/dump_stack.c:51 [] ___might_sleep+0x291/0x490 kernel/sched/core.c:7675 [] __might_sleep+0xb3/0x270 kernel/sched/core.c:7637 [] slab_pre_alloc_hook mm/slab.h:361 [inline] [] slab_alloc_node mm/slub.c:2610 [inline] [] slab_alloc mm/slub.c:2692 [inline] [] kmem_cache_alloc_trace+0x2c3/0x5c0 mm/slub.c:2709 [] kmalloc include/linux/slab.h:479 [inline] [] kzalloc include/linux/slab.h:623 [inline] [] kobject_uevent_env+0x2c7/0x1150 lib/kobject_uevent.c:227 [] kobject_uevent+0x1f/0x30 lib/kobject_uevent.c:374 [] kobject_cleanup lib/kobject.c:633 [inline] [] kobject_release+0x229/0x440 lib/kobject.c:675 [] kref_sub include/linux/kref.h:73 [inline] [] kref_put include/linux/kref.h:98 [inline] [] kobject_put+0x72/0xd0 lib/kobject.c:692 [] put_device+0x25/0x30 drivers/base/core.c:1237 [] delete_partition_rcu_cb+0x1d4/0x2f0 block/partition-generic.c:232 [] __rcu_reclaim kernel/rcu/rcu.h:118 [inline] [] rcu_do_batch kernel/rcu/tree.c:2705 [inline] [] invoke_rcu_callbacks kernel/rcu/tree.c:2973 [inline] [] __rcu_process_callbacks kernel/rcu/tree.c:2940 [inline] [] rcu_process_callbacks+0x59c/0x1c70 kernel/rcu/tree.c:2957 [] __do_softirq+0x299/0xe20 kernel/softirq.c:273 [] invoke_softirq kernel/softirq.c:350 [inline] [] irq_exit+0x216/0x2c0 kernel/softirq.c:391 [] exiting_irq arch/x86/include/asm/apic.h:652 [inline] [] smp_apic_timer_interrupt+0x8b/0xc0 arch/x86/kernel/apic/apic.c:926 [] apic_timer_interrupt+0xa5/0xb0 arch/x86/entry/entry_64.S:746 [] ? audit_kill_trees+0x180/0x180 [] fd_install+0x57/0x80 fs/file.c:626 [] do_sys_open+0x45e/0x550 fs/open.c:1043 [] SYSC_open fs/open.c:1055 [inline] [] SyS_open+0x32/0x40 fs/open.c:1050 [] entry_SYSCALL_64_fastpath+0x1e/0x9a In softirq context, we call rcu callback function delete_partition_rcu_cb(), which may allocate memory by kzalloc with GFP_KERNEL flag. If the allocation cannot be satisfied, it may sleep. However, That is not allowed in softirq contex. Although we found this problem on linux 4.4, the latest kernel version seems to have this problem as well. And it is very similar to the previous one: https://lkml.org/lkml/2018/7/9/391 Fix it by using RCU workqueue, which allows sleep. Reviewed-by: Paul E. McKenney Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 70fc838e6773..0c5ee17b4d88 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -129,7 +129,7 @@ struct hd_struct { struct disk_stats dkstats; #endif struct percpu_ref ref; - struct rcu_head rcu_head; + struct rcu_work rcu_work; }; #define GENHD_FL_REMOVABLE 1 -- cgit v1.2.3 From f783e128a6f1484d72ceab06d483ea32df0ce333 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 26 Nov 2018 17:47:46 +0100 Subject: platform/x86: dell-laptop: Drop superfluous exported function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since we've switched to the LED trigger for binding with HD-audio, we can drop the exported function as well as the whole linux/dell-led.h. Acked-by: Jacek Anaszewski Acked-by: Pavel Machek Acked-by: Andy Shevchenko Acked-by: Pali Rohár Signed-off-by: Takashi Iwai --- include/linux/dell-led.h | 7 ------- 1 file changed, 7 deletions(-) delete mode 100644 include/linux/dell-led.h (limited to 'include/linux') diff --git a/include/linux/dell-led.h b/include/linux/dell-led.h deleted file mode 100644 index 92521471517f..000000000000 --- a/include/linux/dell-led.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __DELL_LED_H__ -#define __DELL_LED_H__ - -int dell_micmute_led_set(int on); - -#endif -- cgit v1.2.3 From 9e908a180e6a90fa102d5d3f96ca86825f43e4fb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 26 Nov 2018 17:47:47 +0100 Subject: platform/x86: thinkpad_acpi: Drop superfluous exported function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since we've switched to the LED trigger for binding with HD-audio, we can drop the exported function as well as the whole linux/thinkpad_acpi.h. The own TPACPI_LED_MUTE and TPACPI_LED_MICMUTE definitions are replaced with the identical ones for LEDS, i.e. LED_AUDIO_MUTE and LED_AUDIO_MICMUTE, respectively. They are no longer needed as referred only locally. Acked-by: Jacek Anaszewski Acked-by: Pavel Machek Acked-by: Andy Shevchenko Acked-by: Henrique de Moraes Holschuh Acked-by: Pali Rohár Signed-off-by: Takashi Iwai --- include/linux/thinkpad_acpi.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/thinkpad_acpi.h (limited to 'include/linux') diff --git a/include/linux/thinkpad_acpi.h b/include/linux/thinkpad_acpi.h deleted file mode 100644 index 9fb317970c01..000000000000 --- a/include/linux/thinkpad_acpi.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __THINKPAD_ACPI_H__ -#define __THINKPAD_ACPI_H__ - -/* These two functions return 0 if success, or negative error code - (e g -ENODEV if no led present) */ - -enum { - TPACPI_LED_MUTE, - TPACPI_LED_MICMUTE, - TPACPI_LED_MAX, -}; - -int tpacpi_led_set(int whichled, bool on); - -#endif -- cgit v1.2.3 From 97bce63408f192712574a4d9d6dcab794eed3a79 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 27 Nov 2018 11:11:35 -0500 Subject: svcrdma: Optimize the logic that selects the R_key to invalidate o Select the R_key to invalidate while the CPU cache still contains the received RPC Call transport header, rather than waiting until we're about to send the RPC Reply. o Choose Send With Invalidate if there is exactly one distinct R_key in the received transport header. If there's more than one, the client will have to perform local invalidation after it has already waited for remote invalidation. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index e6e26918504c..7e22681333d0 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -135,6 +135,7 @@ struct svc_rdma_recv_ctxt { u32 rc_byte_len; unsigned int rc_page_count; unsigned int rc_hdr_count; + u32 rc_inv_rkey; struct page *rc_pages[RPCSVC_MAXPAGES]; }; -- cgit v1.2.3 From 9adcfaffc34d53e498637237fb3701560359d50b Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sat, 24 Nov 2018 13:10:25 +0900 Subject: printk: Make printk_emit() local function. printk_emit() is called from only devkmsg_write() in the same file. Save object size by making it a local function. Link: http://lkml.kernel.org/r/5cc99d2c-c408-34f7-d1fc-e1cd2a9e31da@i-love.sakura.ne.jp Cc: Steven Rostedt Signed-off-by: Tetsuo Handa Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index cf3eccfe1543..55aa96975fa2 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -166,11 +166,6 @@ int vprintk_emit(int facility, int level, asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); -asmlinkage __printf(5, 6) __cold -int printk_emit(int facility, int level, - const char *dict, size_t dictlen, - const char *fmt, ...); - asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); -- cgit v1.2.3 From 58d81d64e06ffaea6bddc85ae2b7295c371bcc55 Mon Sep 17 00:00:00 2001 From: Priit Laes Date: Mon, 19 Nov 2018 20:01:22 +0200 Subject: lib: cordic: Move cordic macros and defines to header file Now that these macros are in header file, we can eventually clean up the duplicate macros present in the drivers that utilize the same cordic algorithm implementation. Also add CORDIC_ prefix to nonprefixed macros. Reviewed-by: Arend van Spriel Signed-off-by: Priit Laes Acked-by: Larry Finger Signed-off-by: Kalle Valo --- include/linux/cordic.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cordic.h b/include/linux/cordic.h index cf68ca4a508c..3d656f54d64f 100644 --- a/include/linux/cordic.h +++ b/include/linux/cordic.h @@ -18,6 +18,15 @@ #include +#define CORDIC_ANGLE_GEN 39797 +#define CORDIC_PRECISION_SHIFT 16 +#define CORDIC_NUM_ITER (CORDIC_PRECISION_SHIFT + 2) + +#define CORDIC_FIXED(X) ((s32)((X) << CORDIC_PRECISION_SHIFT)) +#define CORDIC_FLOAT(X) (((X) >= 0) \ + ? ((((X) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1) \ + : -((((-(X)) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1)) + /** * struct cordic_iq - i/q coordinate. * -- cgit v1.2.3 From ce5b009cff1961137127edf91f44effd0eec8ffd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 27 Nov 2018 17:13:56 -0700 Subject: block: improve logic around when to sort a plug list Only do it if we have requests for multiple queues in the same plug. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 02732cae6080..08d940f85fa0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1131,6 +1131,7 @@ struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ unsigned short rq_count; + bool multiple_queues; }; #define BLK_MAX_REQUEST_COUNT 16 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) -- cgit v1.2.3 From d666ba98f849ad44c4405ecc2180390ebe80f4f9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 27 Nov 2018 17:02:25 -0700 Subject: blk-mq: add mq_ops->commit_rqs() blk-mq passes information to the hardware about any given request being the last that we will issue in this sequence. The point is that hardware can defer costly doorbell type writes to the last request. But if we run into errors issuing a sequence of requests, we may never send the request with bd->last == true set. For that case, we need a hook that tells the hardware that nothing else is coming right now. For failures returned by the drivers ->queue_rq() hook, the driver is responsible for flushing pending requests, if it uses bd->last to optimize that part. This works like before, no changes there. Reviewed-by: Omar Sandoval Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b8de11e0603b..467f1dd21ccf 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -117,6 +117,7 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *); /* takes rq->cmd_flags as input, returns a hardware type index */ typedef int (rq_flags_to_type_fn)(struct request_queue *, unsigned int); typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *); @@ -144,6 +145,15 @@ struct blk_mq_ops { */ queue_rq_fn *queue_rq; + /* + * If a driver uses bd->last to judge when to submit requests to + * hardware, it must define this function. In case of errors that + * make us stop issuing further requests, this hook serves the + * purpose of kicking the hardware (which the last request otherwise + * would have done). + */ + commit_rqs_fn *commit_rqs; + /* * Return a queue map type for the given request/bio flags */ -- cgit v1.2.3 From 90230968f102acbe103fbf7c03d41addfef5f153 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 29 Nov 2018 12:00:05 +0200 Subject: net: phy: sfp: correct location of SFP standards SFP standards are now available from the SNIA (Storage Networking Industry Association) website. Cc: Andrew Lunn Cc: Florian Fainelli Signed-off-by: Baruch Siach Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index d37518e89db2..d9d9de3fcf8e 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -224,7 +224,7 @@ struct sfp_eeprom_ext { * * See the SFF-8472 specification and related documents for the definition * of these structure members. This can be obtained from - * ftp://ftp.seagate.com/sff + * https://www.snia.org/technology-communities/sff/specifications */ struct sfp_eeprom_id { struct sfp_eeprom_base base; -- cgit v1.2.3 From 89d328f637b9904b6d4c9af73c8a608b8dd4d6f8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 16:17:22 -0700 Subject: pstore/ram: Correctly calculate usable PRZ bytes The actual number of bytes stored in a PRZ is smaller than the bytes requested by platform data, since there is a header on each PRZ. Additionally, if ECC is enabled, there are trailing bytes used as well. Normally this mismatch doesn't matter since PRZs are circular buffers and the leading "overflow" bytes are just thrown away. However, in the case of a compressed record, this rather badly corrupts the results. This corruption was visible with "ramoops.mem_size=204800 ramoops.ecc=1". Any stored crashes would not be uncompressable (producing a pstorefs "dmesg-*.enc.z" file), and triggering errors at boot: [ 2.790759] pstore: crypto_comp_decompress failed, ret = -22! Backporting this depends on commit 70ad35db3321 ("pstore: Convert console write to use ->write_buf") Reported-by: Joel Fernandes Fixes: b0aad7a99c1d ("pstore: Add compression support to pstore") Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) --- include/linux/pstore.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index a15bc4d48752..30fcec375a3a 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -90,7 +90,10 @@ struct pstore_record { * * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer - * @bufsize: size of @buf available for crash dump writes + * @bufsize: size of @buf available for crash dump bytes (must match + * smallest number of bytes available for writing to a + * backend entry, since compressed bytes don't take kindly + * to being truncated) * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for -- cgit v1.2.3 From 20902be46c4da59b1891d238801146134e0e06b5 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 26 Nov 2018 14:38:56 -0800 Subject: net/mlx5: Driver events notifier API Use atomic notifier chain to fire events to mlx5 core driver consumers (mlx5e/mlx5_ib) and provide mlx5 register/unregister notifier API. This API will replace the current mlx5_interface->event callback and all the logic around it, especially the delayed events logic introduced by commit 97834eba7c19 ("net/mlx5: Delay events till ib registration ends") Which is not needed anymore with this new API where the mlx5 interface can dynamically register/unregister its notifier. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ba64ecf72478..b96929d0cc9c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -46,6 +46,7 @@ #include #include #include +#include #include #include @@ -1062,6 +1063,9 @@ struct mlx5_interface { void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); +int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); + int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 58d180b34e98698fec178a469b700f1bb5a32c1f Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 26 Nov 2018 14:38:59 -0800 Subject: net/mlx5: Forward all mlx5 events to mlx5 notifiers chain This to allow seamless migration to the new notifier chain API, and to eventually deprecate interfaces dev->event callback. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index b96929d0cc9c..14ca74707275 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -195,7 +195,7 @@ struct mlx5_rsc_debug { }; enum mlx5_dev_event { - MLX5_DEV_EVENT_SYS_ERROR, + MLX5_DEV_EVENT_SYS_ERROR = 128, /* 0 - 127 are FW events */ MLX5_DEV_EVENT_PORT_UP, MLX5_DEV_EVENT_PORT_DOWN, MLX5_DEV_EVENT_PORT_INITIALIZED, -- cgit v1.2.3 From 02039fb659b366011f55b15890136754f3d82e2d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 26 Nov 2018 14:39:01 -0800 Subject: net/mlx5: Remove unused events callback and logic The mlx5_interface->event callback is not used by mlx5e/mlx5_ib anymore. We totally remove the delayed events logic work around, since with the dynamic notifier registration API it is not needed anymore, mlx5_ib can register its notifier and start receiving events exactly at the moment it is ready to handle them. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 14ca74707275..d3ffc64f9a75 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -588,10 +588,7 @@ struct mlx5_priv { struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; - - struct list_head waiting_events_list; - bool is_accum_events; - struct mlx5_events *events; + struct mlx5_events *events; struct mlx5_flow_steering *steering; struct mlx5_mpfs *mpfs; @@ -696,9 +693,6 @@ struct mlx5_core_dev { /* sync interface state */ struct mutex intf_state_mutex; unsigned long intf_state; - void (*event) (struct mlx5_core_dev *dev, - enum mlx5_dev_event event, - unsigned long param); struct mlx5_priv priv; struct mlx5_profile *profile; atomic_t num_qps; @@ -1053,8 +1047,6 @@ struct mlx5_interface { void (*remove)(struct mlx5_core_dev *dev, void *context); int (*attach)(struct mlx5_core_dev *dev, void *context); void (*detach)(struct mlx5_core_dev *dev, void *context); - void (*event)(struct mlx5_core_dev *dev, void *context, - enum mlx5_dev_event event, unsigned long param); void * (*get_dev)(void *context); int protocol; struct list_head list; -- cgit v1.2.3 From b8267cd765b333673e05696b517d38a1a7eb5b2e Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 26 Nov 2018 14:39:05 -0800 Subject: net/mlx5: Remove all deprecated software versions of FW events Before the new mlx5 event notification infrastructure and API, mlx5_core used to process all events before forwarding them to mlx5 interfaces (mlx5e/mlx5_ib) and used to translate the event type enum to a software defined enum, this is not needed anymore since it is ok for mlx5e and mlx5_ib to receive FW events as is, at least the few ones mlx5 core allows. mlx5e and mlx5_ib already moved to use the new API and they only handle FW events types, it is now safe to remove all equivalent software defined events and the logic around them. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d3ffc64f9a75..a77bedb8a556 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -196,15 +196,6 @@ struct mlx5_rsc_debug { enum mlx5_dev_event { MLX5_DEV_EVENT_SYS_ERROR = 128, /* 0 - 127 are FW events */ - MLX5_DEV_EVENT_PORT_UP, - MLX5_DEV_EVENT_PORT_DOWN, - MLX5_DEV_EVENT_PORT_INITIALIZED, - MLX5_DEV_EVENT_LID_CHANGE, - MLX5_DEV_EVENT_PKEY_CHANGE, - MLX5_DEV_EVENT_GUID_CHANGE, - MLX5_DEV_EVENT_CLIENT_REREG, - MLX5_DEV_EVENT_PPS, - MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, }; enum mlx5_port_status { -- cgit v1.2.3 From 451be51c0b474f790e9833cd575fd9a6fbd679df Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 26 Nov 2018 14:39:06 -0800 Subject: net/mlx5: Forward QP/WorkQueues resource events Allow forwarding QP and WQ events to mlx5_core interfaces, e.g. mlx5_ib Use mlx5_notifier_register/unregister in qp.c in order to allow seamless transition of qp.c to infiniband subsystem. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a77bedb8a556..4f078b7f6620 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -456,7 +456,7 @@ struct mlx5_core_health { }; struct mlx5_qp_table { - struct mlx5_nb nb; + struct notifier_block nb; /* protect radix tree */ -- cgit v1.2.3 From 4e2df04ad25ab8e627878817e56d6a27645ca4a8 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 26 Nov 2018 14:39:07 -0800 Subject: net/mlx5: Forward SRQ resource events Allow forwarding of SRQ events to mlx5_core interfaces, e.g. mlx5_ib. Use mlx5_notifier_register/unregister in srq.c in order to allow seamless transition of srq.c to infiniband subsystem. Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4f078b7f6620..27a481b159ed 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -465,8 +465,7 @@ struct mlx5_qp_table { }; struct mlx5_srq_table { - struct mlx5_nb catas_err_nb; - struct mlx5_nb rq_limit_nb; + struct notifier_block nb; /* protect radix tree */ spinlock_t lock; -- cgit v1.2.3 From 0c7a52e4d4b5c4d35b31f3c3ad32af814f1bf491 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Wed, 28 Nov 2018 03:35:23 +0000 Subject: tracepoint: Use __idx instead of idx in DO_TRACE macro to make it unique After enabling KVM event tracing, almost all of trace_kvm_exit()'s printk shows "kvm_exit: IRQ: ..." even if the actual exception_type is NOT IRQ. More specifically, trace_kvm_exit() is defined in virt/kvm/arm/trace.h by TRACE_EVENT. This slight problem may have existed after commit e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU"). There are two variables in trace_kvm_exit() and __DO_TRACE() which have the same name, *idx*. Thus the actual value of *idx* will be overwritten when tracing. Fix it by adding a simple prefix. Cc: Joel Fernandes Cc: Wang Haibin Cc: linux-trace-devel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Reviewed-by: Joel Fernandes (Google) Signed-off-by: Zenghui Yu Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 538ba1a58f5b..e9de8ad0bad7 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -166,7 +166,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ - int __maybe_unused idx = 0; \ + int __maybe_unused __idx = 0; \ \ if (!(cond)) \ return; \ @@ -182,7 +182,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * doesn't work from the idle path. \ */ \ if (rcuidle) { \ - idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ rcu_irq_enter_irqson(); \ } \ \ @@ -198,7 +198,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ - srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ } \ \ preempt_enable_notrace(); \ -- cgit v1.2.3 From 23621fac32ec9dbc4afada344cbf82b0f6281be3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 18 Nov 2018 18:32:40 -0500 Subject: function_graph: Remove unused task_curr_ret_stack() The static inline function task_curr_ret_stack() is unused, remove it. Reviewed-by: Joel Fernandes (Google) Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index dd16e8218db3..10bd46434908 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -809,11 +809,6 @@ extern void ftrace_graph_init_task(struct task_struct *t); extern void ftrace_graph_exit_task(struct task_struct *t); extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu); -static inline int task_curr_ret_stack(struct task_struct *t) -{ - return t->curr_ret_stack; -} - static inline void pause_graph_tracing(void) { atomic_inc(¤t->tracing_graph_pause); @@ -838,11 +833,6 @@ static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc, } static inline void unregister_ftrace_graph(void) { } -static inline int task_curr_ret_stack(struct task_struct *tsk) -{ - return -1; -} - static inline unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp) -- cgit v1.2.3 From 47c33a095e1fae376d74b4160a0d73c1a4e73969 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Prakhya Date: Thu, 29 Nov 2018 18:12:25 +0100 Subject: x86/efi: Move efi__boot_services() to arch/x86 efi__boot_services() are x86 specific quirks and as such should be in asm/efi.h, so move them from linux/efi.h. Also, call efi_free_boot_services() from __efi_enter_virtual_mode() as it is x86 specific call and ideally shouldn't be part of init/main.c Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Ard Biesheuvel Acked-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Arend van Spriel Cc: Bhupesh Sharma Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Snowberg Cc: Hans de Goede Cc: Joe Perches Cc: Jon Hunter Cc: Julien Thierry Cc: Linus Torvalds Cc: Marc Zyngier Cc: Matt Fleming Cc: Nathan Chancellor Cc: Peter Zijlstra Cc: Sedat Dilek Cc: YiFei Zhu Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20181129171230.18699-7-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 100ce4a4aff6..2b3b33c83b05 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1000,13 +1000,11 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); extern void efi_gettimeofday (struct timespec64 *ts); extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #ifdef CONFIG_X86 -extern void efi_free_boot_services(void); extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, bool nonblocking); extern void efi_find_mirror(void); #else -static inline void efi_free_boot_services(void) {} static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, @@ -1046,7 +1044,6 @@ extern void efi_mem_reserve(phys_addr_t addr, u64 size); extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); -extern void efi_reserve_boot_services(void); extern int efi_get_fdt_params(struct efi_fdt_params *params); extern struct kobject *efi_kobj; -- cgit v1.2.3 From 5f0b0ecf043a5319e729c11a53bc8294df12dab3 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 29 Nov 2018 18:12:28 +0100 Subject: efi: Permit multiple entries in persistent memreserve data structure In preparation of updating efi_mem_reserve_persistent() to cause less fragmentation when dealing with many persistent reservations, update the struct definition and the code that handles it currently so it can describe an arbitrary number of reservations using a single linked list entry. The actual optimization will be implemented in a subsequent patch. Tested-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Cc: Andy Lutomirski Cc: Arend van Spriel Cc: Bhupesh Sharma Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Snowberg Cc: Hans de Goede Cc: Joe Perches Cc: Jon Hunter Cc: Julien Thierry Cc: Linus Torvalds Cc: Matt Fleming Cc: Nathan Chancellor Cc: Peter Zijlstra Cc: Sai Praneeth Prakhya Cc: Sedat Dilek Cc: Thomas Gleixner Cc: YiFei Zhu Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20181129171230.18699-10-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 2b3b33c83b05..4f27640fdcdc 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1712,9 +1712,16 @@ extern struct efi_runtime_work efi_rts_work; extern struct workqueue_struct *efi_rts_wq; struct linux_efi_memreserve { - phys_addr_t next; - phys_addr_t base; - phys_addr_t size; + int size; // allocated size of the array + atomic_t count; // number of entries used + phys_addr_t next; // pa of next struct instance + struct { + phys_addr_t base; + phys_addr_t size; + } entry[0]; }; +#define EFI_MEMRESERVE_SIZE(count) (sizeof(struct linux_efi_memreserve) + \ + (count) * sizeof(((struct linux_efi_memreserve *)0)->entry[0])) + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 80424b02d42bb22f8ff8839cb93a84ade53b39c0 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 29 Nov 2018 18:12:29 +0100 Subject: efi: Reduce the amount of memblock reservations for persistent allocations The current implementation of efi_mem_reserve_persistent() is rather naive, in the sense that for each invocation, it creates a separate linked list entry to describe the reservation. Since the linked list entries themselves need to persist across subsequent kexec reboots, every reservation created this way results in two memblock_reserve() calls at the next boot. On arm64 systems with 100s of CPUs, this may result in a excessive number of memblock reservations, and needless fragmentation. So instead, make use of the newly updated struct linux_efi_memreserve layout to put multiple reservations into a single linked list entry. This should get rid of the numerous tiny memblock reservations, and effectively cut the total number of reservations in half on arm64 systems with many CPUs. [ mingo: build warning fix. ] Tested-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Cc: Andy Lutomirski Cc: Arend van Spriel Cc: Bhupesh Sharma Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Snowberg Cc: Hans de Goede Cc: Joe Perches Cc: Jon Hunter Cc: Julien Thierry Cc: Linus Torvalds Cc: Matt Fleming Cc: Nathan Chancellor Cc: Peter Zijlstra Cc: Sai Praneeth Prakhya Cc: Sedat Dilek Cc: Thomas Gleixner Cc: YiFei Zhu Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20181129171230.18699-11-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 4f27640fdcdc..becd5d76a207 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1724,4 +1724,7 @@ struct linux_efi_memreserve { #define EFI_MEMRESERVE_SIZE(count) (sizeof(struct linux_efi_memreserve) + \ (count) * sizeof(((struct linux_efi_memreserve *)0)->entry[0])) +#define EFI_MEMRESERVE_COUNT(size) (((size) - sizeof(struct linux_efi_memreserve)) \ + / sizeof(((struct linux_efi_memreserve *)0)->entry[0])) + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From ad697a1aecac19ec351063b5d8e6fc9d4bca7ee5 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 15 Nov 2018 22:41:58 +0000 Subject: linkage: add generic GLOBAL() macro Declaring a global symbol in assembly is tedious, error-prone, and painful to read. While ENTRY() exists, this is supposed to be used for function entry points, and this affects alignment in a potentially undesireable manner. Instead, let's add a generic GLOBAL() macro for this, as x86 added locally in commit: 95695547a7db44b8 ("x86: asm linkage - introduce GLOBAL macro") ... thus allowing us to use this more freely in the kernel. Signed-off-by: Mark Rutland Cc: AKASHI Takahiro Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: Torsten Duwe Cc: Will Deacon Signed-off-by: Will Deacon --- include/linux/linkage.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 7c47b1a471d4..7e020782ade2 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -79,6 +79,12 @@ #define ALIGN __ALIGN #define ALIGN_STR __ALIGN_STR +#ifndef GLOBAL +#define GLOBAL(name) \ + .globl name ASM_NL \ + name: +#endif + #ifndef ENTRY #define ENTRY(name) \ .globl name ASM_NL \ -- cgit v1.2.3 From ada5c1da8660ecae24b3e75c18ee77d79e099fee Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 30 Nov 2018 10:04:08 +1100 Subject: fs/locks: rename some lists and pointers. struct file lock contains an 'fl_next' pointer which is used to point to the lock that this request is blocked waiting for. So rename it to fl_blocker. The fl_blocked list_head in an active lock is the head of a list of blocked requests. In a request it is a node in that list. These are two distinct uses, so replace with two list_heads with different names. fl_blocked_requests is the head of a list of blocked requests fl_blocked_member is a node in a member of that list. The two different list_heads are never used at the same time, but that will change in a future patch. Note that a tracepoint is changed to report fl_blocker instead of fl_next. Signed-off-by: NeilBrown Reviewed-by: J. Bruce Fields Signed-off-by: Jeff Layton --- include/linux/fs.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c95c0807471f..16df3a7df378 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1044,10 +1044,15 @@ bool opens_in_grace(struct net *); * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock { - struct file_lock *fl_next; /* singly linked list for this inode */ + struct file_lock *fl_blocker; /* The lock, that is blocking us */ struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ - struct list_head fl_block; /* circular list of blocked processes */ + struct list_head fl_blocked_requests; /* list of requests with + * ->fl_blocker pointing here + */ + struct list_head fl_blocked_member; /* node in + * ->fl_blocker->fl_blocked_requests + */ fl_owner_t fl_owner; unsigned int fl_flags; unsigned char fl_type; -- cgit v1.2.3 From 36907cd5cd720c5a6d36670b49eba3b1f7f4d8fe Mon Sep 17 00:00:00 2001 From: Ariel Elior Date: Wed, 28 Nov 2018 18:16:02 +0200 Subject: qed: Add doorbell overflow recovery mechanism Add the database used to register doorbelling entities, and APIs for adding and deleting entries, and logic for traversing the database and doorbelling once on behalf of all entities. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Tomer Tayar Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index a47321a0d572..eb851f89f417 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -47,6 +47,7 @@ #include #include #include +#include enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, @@ -448,11 +449,24 @@ struct qed_mfw_tlv_iscsi { bool tx_bytes_set; }; +enum qed_db_rec_width { + DB_REC_WIDTH_32B, + DB_REC_WIDTH_64B, +}; + +enum qed_db_rec_space { + DB_REC_KERNEL, + DB_REC_USER, +}; + #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ (void __iomem *)(reg_addr)) #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) +#define DIRECT_REG_WR64(reg_addr, val) writeq((u32)val, \ + (void __iomem *)(reg_addr)) + #define QED_COALESCE_MAX 0x1FF #define QED_DEFAULT_RX_USECS 12 #define QED_DEFAULT_TX_USECS 48 -- cgit v1.2.3 From 0e1f10447e2aa79ba7d8960e5d0ed3cf2ea8356e Mon Sep 17 00:00:00 2001 From: Ariel Elior Date: Wed, 28 Nov 2018 18:16:06 +0200 Subject: qed: Expose the doorbell overflow recovery mechanism to the protocol drivers Most of the doorbelling entities are outside of the core module. L2 queues, Roce queues, iscsi and fcoe all need to register. Make the APIs available for these drivers. Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: Tomer Tayar Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index eb851f89f417..91c536a01b56 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1029,6 +1029,33 @@ struct qed_common_ops { */ int (*set_led)(struct qed_dev *cdev, enum qed_led_mode mode); +/** + * @brief db_recovery_add - add doorbell information to the doorbell + * recovery mechanism. + * + * @param cdev + * @param db_addr - doorbell address + * @param db_data - address of where db_data is stored + * @param db_is_32b - doorbell is 32b pr 64b + * @param db_is_user - doorbell recovery addresses are user or kernel space + */ + int (*db_recovery_add)(struct qed_dev *cdev, + void __iomem *db_addr, + void *db_data, + enum qed_db_rec_width db_width, + enum qed_db_rec_space db_space); + +/** + * @brief db_recovery_del - remove doorbell information from the doorbell + * recovery mechanism. db_data serves as key (db_addr is not unique). + * + * @param cdev + * @param db_addr - doorbell address + * @param db_data - address where db_data is stored. Serves as key for the + * entry to delete. + */ + int (*db_recovery_del)(struct qed_dev *cdev, + void __iomem *db_addr, void *db_data); /** * @brief update_drv_state - API to inform the change in the driver state. -- cgit v1.2.3 From ea86ea2cdced20057da4d2c32965c1219c238197 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 30 Nov 2018 13:18:06 -0700 Subject: sbitmap: ammortize cost of clearing bits sbitmap maintains a set of words that we use to set and clear bits, with each bit representing a tag for blk-mq. Even though we spread the bits out and maintain a hint cache, one particular bit allocated will end up being cleared in the exact same spot. This introduces batched clearing of bits. Instead of clearing a given bit, the same bit is set in a cleared/free mask instead. If we fail allocating a bit from a given word, then we check the free mask, and batch move those cleared bits at that time. This trades 64 atomic bitops for 2 cmpxchg(). In a threaded poll test case, half the overhead of getting and clearing tags is removed with this change. On another poll test case with a single thread, performance is unchanged. Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 804a50983ec5..81359d45751e 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -30,14 +30,24 @@ struct seq_file; */ struct sbitmap_word { /** - * @word: The bitmap word itself. + * @depth: Number of bits being used in @word/@cleared */ - unsigned long word; + unsigned long depth; /** - * @depth: Number of bits being used in @word. + * @word: word holding free bits */ - unsigned long depth; + unsigned long word ____cacheline_aligned_in_smp; + + /** + * @cleared: word holding cleared bits + */ + unsigned long cleared ____cacheline_aligned_in_smp; + + /** + * @swap_lock: Held while swapping word <-> cleared + */ + spinlock_t swap_lock; } ____cacheline_aligned_in_smp; /** @@ -310,6 +320,19 @@ static inline void sbitmap_clear_bit(struct sbitmap *sb, unsigned int bitnr) clear_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } +/* + * This one is special, since it doesn't actually clear the bit, rather it + * sets the corresponding bit in the ->cleared mask instead. Paired with + * the caller doing sbitmap_batch_clear() if a given index is full, which + * will clear the previously freed entries in the corresponding ->word. + */ +static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bitnr) +{ + unsigned long *addr = &sb->map[SB_NR_TO_INDEX(sb, bitnr)].cleared; + + set_bit(SB_NR_TO_BIT(sb, bitnr), addr); +} + static inline void sbitmap_clear_bit_unlock(struct sbitmap *sb, unsigned int bitnr) { @@ -321,8 +344,6 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); } -unsigned int sbitmap_weight(const struct sbitmap *sb); - /** * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file. * @sb: Bitmap to show. -- cgit v1.2.3 From 5d2ee7122c73be6a3b6bfe90d237e8aed737cfaa Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 29 Nov 2018 17:36:41 -0700 Subject: sbitmap: optimize wakeup check Even if we have no waiters on any of the sbitmap_queue wait states, we still have to loop every entry to check. We do this for every IO, so the cost adds up. Shift a bit of the cost to the slow path, when we actually have waiters. Wrap prepare_to_wait_exclusive() and finish_wait(), so we can maintain an internal count of how many are currently active. Then we can simply check this count in sbq_wake_ptr() and not have to loop if we don't have any sleepers. Convert the two users of sbitmap with waiting, blk-mq-tag and iSCSI. Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 81359d45751e..92806a2dbab7 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -135,6 +135,11 @@ struct sbitmap_queue { */ struct sbq_wait_state *ws; + /* + * @ws_active: count of currently active ws waitqueues + */ + atomic_t ws_active; + /** * @round_robin: Allocate bits in strict round-robin order. */ @@ -552,4 +557,33 @@ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); */ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m); +struct sbq_wait { + int accounted; + struct wait_queue_entry wait; +}; + +#define DEFINE_SBQ_WAIT(name) \ + struct sbq_wait name = { \ + .accounted = 0, \ + .wait = { \ + .private = current, \ + .func = autoremove_wake_function, \ + .entry = LIST_HEAD_INIT((name).wait.entry), \ + } \ + } + +/* + * Wrapper around prepare_to_wait_exclusive(), which maintains some extra + * internal state. + */ +void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq, + struct sbq_wait_state *ws, + struct sbq_wait *sbq_wait, int state); + +/* + * Must be paired with sbitmap_prepare_to_wait(). + */ +void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, + struct sbq_wait *sbq_wait); + #endif /* __LINUX_SCALE_BITMAP_H */ -- cgit v1.2.3 From e0c274472d5d27f277af722e017525e0b33784cd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 30 Nov 2018 14:09:58 -0800 Subject: psi: make disabling/enabling easier for vendor kernels Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others. With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier: 1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time. To avoid double negatives, rename psi_disabled= to psi=. 2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled. In terms of numbers before and after this patch, Mel says: : The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so; Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner Tested-by: Mel Gorman Reported-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/psi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h index 8e0725aac0aa..7006008d5b72 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H +#include #include #include @@ -9,7 +10,7 @@ struct css_set; #ifdef CONFIG_PSI -extern bool psi_disabled; +extern struct static_key_false psi_disabled; void psi_init(void); -- cgit v1.2.3 From b7df9ada9a7700dbcca1ba53d217c01e3d48179c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 1 Dec 2018 01:18:53 +0100 Subject: bpf: fix pointer offsets in context for 32 bit Currently, pointer offsets in three BPF context structures are broken in two scenarios: i) 32 bit compiled applications running on 64 bit kernels, and ii) LLVM compiled BPF programs running on 32 bit kernels. The latter is due to BPF target machine being strictly 64 bit. So in each of the cases the offsets will mismatch in verifier when checking / rewriting context access. Fix this by providing a helper macro __bpf_md_ptr() that will enforce padding up to 64 bit and proper alignment, and for context access a macro bpf_ctx_range_ptr() which will cover full 64 bit member range on 32 bit archs. For flow_keys, we additionally need to force the size check to sizeof(__u64) as with other pointer types. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data") Fixes: 2dbb9b9e6df6 ("bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT") Reported-by: David S. Miller Signed-off-by: Daniel Borkmann Acked-by: David S. Miller Tested-by: David S. Miller Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 448dcc448f1f..795ff0b869bb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -449,6 +449,13 @@ struct sock_reuseport; offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 +#if BITS_PER_LONG == 64 +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 +#else +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 +#endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ -- cgit v1.2.3 From bbda5ec671d3fe62faefa1cab7270aa586042a4b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 30 Nov 2018 10:05:26 +0900 Subject: kbuild: simplify dependency generation for CONFIG_TRIM_UNUSED_KSYMS My main motivation of this commit is to clean up scripts/Kbuild.include and scripts/Makefile.build. Currently, CONFIG_TRIM_UNUSED_KSYMS works with a tricky gimmick; possibly exported symbols are detected by letting $(CPP) replace EXPORT_SYMBOL* with a special string '=== __KSYM_*===', which is post-processed by sed, and passed to fixdep. The extra preprocessing is costly, and hacking cmd_and_fixdep is ugly. I came up with a new way to find exported symbols; insert a dummy symbol __ksym_marker_* to each potentially exported symbol. Those dummy symbols are picked up by $(NM), post-processed by sed, then appended to .*.cmd files. I collected the post-process part to a new shell script scripts/gen_ksymdeps.sh for readability. The dummy symbols are put into the .discard.* section so that the linker script rips them off the final vmlinux or modules. A nice side-effect is building with CONFIG_TRIM_UNUSED_KSYMS will be much faster. Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Pitre --- include/linux/export.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index ce764a5d2ee4..fd8711ed9ac4 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -92,22 +92,22 @@ struct kernel_symbol { */ #define __EXPORT_SYMBOL(sym, sec) -#elif defined(__KSYM_DEPS__) +#elif defined(CONFIG_TRIM_UNUSED_KSYMS) + +#include /* * For fine grained build dependencies, we want to tell the build system * about each possible exported symbol even if they're not actually exported. - * We use a string pattern that is unlikely to be valid code that the build - * system filters out from the preprocessor output (see ksym_dep_filter - * in scripts/Kbuild.include). + * We use a symbol pattern __ksym_marker_ that the build system filters + * from the $(NM) output (see scripts/gen_ksymdeps.sh). These symbols are + * discarded in the final link stage. */ -#define __EXPORT_SYMBOL(sym, sec) === __KSYM_##sym === - -#elif defined(CONFIG_TRIM_UNUSED_KSYMS) - -#include +#define __ksym_marker(sym) \ + static int __ksym_marker_##sym[0] __section(".discard.ksym") __used #define __EXPORT_SYMBOL(sym, sec) \ + __ksym_marker(sym); \ __cond_export_sym(sym, sec, __is_defined(__KSYM_##sym)) #define __cond_export_sym(sym, sec, conf) \ ___cond_export_sym(sym, sec, conf) -- cgit v1.2.3 From b18814e767a445534ab9ccba02e82a31208f85d6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 4 Nov 2018 17:27:56 +0100 Subject: dma-direct: provide page based alloc/free helpers Some architectures support remapping highmem into DMA coherent allocations. To use the common code for them we need variants of dma_direct_{alloc,free}_pages that do not use kernel virtual addresses. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-direct.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 9e66bfe369aa..61b78f934f64 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -67,6 +67,9 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); +struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); +void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page); dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs); -- cgit v1.2.3 From 0c3b3171ceccb8830c2bb5adff1b4e9b204c1450 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 4 Nov 2018 20:29:28 +0100 Subject: dma-mapping: move the arm64 noncoherent alloc/free support to common code The arm64 codebase to implement coherent dma allocation for architectures with non-coherent DMA is a good start for a generic implementation, given that is uses the generic remap helpers, provides the atomic pool for allocations that can't sleep and still is realtively simple and well tested. Move it to kernel/dma and allow architectures to opt into it using a config symbol. Architectures just need to provide a new arch_dma_prep_coherent helper to writeback an invalidate the caches for any memory that gets remapped for uncached access. Signed-off-by: Christoph Hellwig Reviewed-by: Will Deacon Reviewed-by: Robin Murphy --- include/linux/dma-mapping.h | 5 +++++ include/linux/dma-noncoherent.h | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0f81c713f6e9..1a0edcde7d14 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -455,6 +455,11 @@ void *dma_common_pages_remap(struct page **pages, size_t size, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags); +int __init dma_atomic_pool_init(gfp_t gfp, pgprot_t prot); +bool dma_in_atomic_pool(void *start, size_t size); +void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags); +bool dma_free_from_pool(void *start, size_t size); + /** * dma_mmap_attrs - map a coherent DMA allocation into user space * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 9051b055beec..306557331d7d 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -69,4 +69,6 @@ static inline void arch_sync_dma_for_cpu_all(struct device *dev) } #endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ +void arch_dma_prep_coherent(struct page *page, size_t size); + #endif /* _LINUX_DMA_NONCOHERENT_H */ -- cgit v1.2.3 From e3e740544173ef0dd8bffbf158182a7748e6c678 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 7 Nov 2018 13:53:34 -0800 Subject: percpu-rwsem: Replace synchronize_sched() with synchronize_rcu() Now that synchronize_rcu() waits for preempt-disable regions of code as well as RCU read-side critical sections, synchronize_sched() can be replaced by synchronize_rcu(). This commit therefore makes this change, even though it is but a comment. Signed-off-by: Paul E. McKenney Cc: Dennis Zhou Cc: Christoph Lameter Acked-by: Tejun Heo --- include/linux/percpu-rwsem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 79b99d653e03..71b75643c432 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -41,7 +41,7 @@ static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore * * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() - * and that one the synchronize_sched() is done, the writer will see + * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ __this_cpu_inc(*sem->read_count); -- cgit v1.2.3 From d5cccfc7b772b8a20b06557f1b7c066e7fc2c393 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 7 Nov 2018 14:01:39 -0800 Subject: types: Remove call_rcu_bh() and call_rcu_sched() Now that call_rcu()'s callback is not invoked until after bh-disable and preempt-disable regions of code have completed (in addition to explicitly marked RCU read-side critical sections), call_rcu() can be used in place of call_rcu_bh() and call_rcu_sched(). This commit therefore removes these two API members from the callback_head structure's header comment. Signed-off-by: Paul E. McKenney Cc: Andrew Morton Cc: Pekka Enberg Cc: Masahiro Yamada Cc: Alexey Dobriyan --- include/linux/types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index 9834e90aa010..c2615d6a019e 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -212,8 +212,8 @@ struct ustat { * weird ABI and we need to ask it explicitly. * * The alignment is required to guarantee that bit 0 of @next will be - * clear under normal conditions -- as long as we use call_rcu(), - * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback. + * clear under normal conditions -- as long as we use call_rcu() or + * call_srcu() to queue the callback. * * This guarantee is important for few reasons: * - future call_rcu_lazy() will make use of lower bits in the pointer; -- cgit v1.2.3 From 4348433d8c0234f44adb6e12112e69343f50f0c5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Sun, 18 Nov 2018 21:18:30 +0100 Subject: mtd: fix mtd_oobavail() incoherent returned value mtd_oobavail() returns either mtd->oovabail or mtd->oobsize. Both values are unsigned 32-bit entities, so there is no reason to pretend returning a signed one. Signed-off-by: Miquel Raynal Signed-off-by: Boris Brezillon --- include/linux/mtd/mtd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index cd0be91bdefa..035d641e8847 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -386,7 +386,7 @@ static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd) return dev_of_node(&mtd->dev); } -static inline int mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops) +static inline u32 mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops) { return ops->mode == MTD_OPS_AUTO_OOB ? mtd->oobavail : mtd->oobsize; } -- cgit v1.2.3 From 1186af457cc186c5ed01708da71b1ffbdf0a2638 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 20 Nov 2018 09:55:45 +0100 Subject: mtd: keep original flags for every struct mtd_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When allocating a new partition mtd subsystem runs internal tests in the allocate_partition(). They may result in modifying specified flags (e.g. dropping some /features/ like write access). Those constraints don't have to be necessary true for subpartitions. It may happen parent partition isn't block aligned (effectively disabling write access) while subpartition may fit blocks nicely. In such case all checks should be run again (starting with original flags value). Signed-off-by: Rafał Miłecki Signed-off-by: Boris Brezillon --- include/linux/mtd/mtd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 035d641e8847..ba8fa9072aca 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -207,6 +207,7 @@ struct mtd_debug_info { struct mtd_info { u_char type; uint32_t flags; + uint32_t orig_flags; /* Flags as before running mtd checks */ uint64_t size; // Total size of the MTD /* "Major" erase size for the device. Naïve users may take this -- cgit v1.2.3 From 71700bb96047f68a0aae3932466fc7c9ad5ce6c0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Nov 2018 16:11:15 -0500 Subject: SUNRPC: Fix a memory leak in call_encode() If we retransmit an RPC request, we currently end up clobbering the value of req->rq_rcv_buf.bvec that was allocated by the initial call to xprt_request_prepare(req). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 43106ffa6788..2ec128060239 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -72,7 +72,6 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) buf->head[0].iov_base = start; buf->head[0].iov_len = len; buf->tail[0].iov_len = 0; - buf->bvec = NULL; buf->pages = NULL; buf->page_len = 0; buf->flags = 0; -- cgit v1.2.3 From 576f1b4bc80220e1f88f1de5ecb25d99a6e9fa04 Mon Sep 17 00:00:00 2001 From: Houlong Wei Date: Thu, 29 Nov 2018 11:37:09 +0800 Subject: soc: mediatek: Add Mediatek CMDQ helper Add Mediatek CMDQ helper to create CMDQ packet and assemble GCE op code. Signed-off-by: Houlong Wei Signed-off-by: HS Liao Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 133 ++++++++++++++++++++++++++++++++++ 1 file changed, 133 insertions(+) create mode 100644 include/linux/soc/mediatek/mtk-cmdq.h (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h new file mode 100644 index 000000000000..54ade13a9b15 --- /dev/null +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018 MediaTek Inc. + * + */ + +#ifndef __MTK_CMDQ_H__ +#define __MTK_CMDQ_H__ + +#include +#include +#include + +#define CMDQ_NO_TIMEOUT 0xffffffffu + +/** cmdq event maximum */ +#define CMDQ_MAX_EVENT 0x3ff + +struct cmdq_pkt; + +struct cmdq_client { + spinlock_t lock; + u32 pkt_cnt; + struct mbox_client client; + struct mbox_chan *chan; + struct timer_list timer; + u32 timeout_ms; /* in unit of microsecond */ +}; + +/** + * cmdq_mbox_create() - create CMDQ mailbox client and channel + * @dev: device of CMDQ mailbox client + * @index: index of CMDQ mailbox channel + * @timeout: timeout of a pkt execution by GCE, in unit of microsecond, set + * CMDQ_NO_TIMEOUT if a timer is not used. + * + * Return: CMDQ mailbox client pointer + */ +struct cmdq_client *cmdq_mbox_create(struct device *dev, int index, + u32 timeout); + +/** + * cmdq_mbox_destroy() - destroy CMDQ mailbox client and channel + * @client: the CMDQ mailbox client + */ +void cmdq_mbox_destroy(struct cmdq_client *client); + +/** + * cmdq_pkt_create() - create a CMDQ packet + * @client: the CMDQ mailbox client + * @size: required CMDQ buffer size + * + * Return: CMDQ packet pointer + */ +struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size); + +/** + * cmdq_pkt_destroy() - destroy the CMDQ packet + * @pkt: the CMDQ packet + */ +void cmdq_pkt_destroy(struct cmdq_pkt *pkt); + +/** + * cmdq_pkt_write() - append write command to the CMDQ packet + * @pkt: the CMDQ packet + * @value: the specified target register value + * @subsys: the CMDQ sub system code + * @offset: register offset from CMDQ sub system + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_write(struct cmdq_pkt *pkt, u32 value, u32 subsys, u32 offset); + +/** + * cmdq_pkt_write_mask() - append write command with mask to the CMDQ packet + * @pkt: the CMDQ packet + * @value: the specified target register value + * @subsys: the CMDQ sub system code + * @offset: register offset from CMDQ sub system + * @mask: the specified target register mask + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u32 value, + u32 subsys, u32 offset, u32 mask); + +/** + * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet + * @pkt: the CMDQ packet + * @event: the desired event type to "wait and CLEAR" + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u32 event); + +/** + * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet + * @pkt: the CMDQ packet + * @event: the desired event to be cleared + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u32 event); + +/** + * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ + * packet and call back at the end of done packet + * @pkt: the CMDQ packet + * @cb: called at the end of done packet + * @data: this data will pass back to cb + * + * Return: 0 for success; else the error code is returned + * + * Trigger CMDQ to asynchronously execute the CMDQ packet and call back + * at the end of done packet. Note that this is an ASYNC function. When the + * function returned, it may or may not be finished. + */ +int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb, + void *data); + +/** + * cmdq_pkt_flush() - trigger CMDQ to execute the CMDQ packet + * @pkt: the CMDQ packet + * + * Return: 0 for success; else the error code is returned + * + * Trigger CMDQ to execute the CMDQ packet. Note that this is a + * synchronous flush function. When the function returned, the recorded + * commands have been done. + */ +int cmdq_pkt_flush(struct cmdq_pkt *pkt); + +#endif /* __MTK_CMDQ_H__ */ -- cgit v1.2.3 From 7ed98dddb764eebf2783881a17dc4980181a6e1a Mon Sep 17 00:00:00 2001 From: Eddie James Date: Thu, 8 Nov 2018 15:05:21 -0600 Subject: fsi: Add On-Chip Controller (OCC) driver The OCC is a device embedded on a POWER processor that collects and aggregates sensor data from the processor and system. The OCC can provide the raw sensor data as well as perform thermal and power management on the system. This driver provides an atomic communications channel between a service processor (e.g. a BMC) and the OCC. The driver is dependent on the FSI SBEFIFO driver to get hardware access through the SBE to the OCC SRAM. Commands are issued to the SBE to send or fetch data to the SRAM. Signed-off-by: Eddie James Signed-off-by: Andrew Jeffery Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Joel Stanley Signed-off-by: Guenter Roeck --- include/linux/fsi-occ.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/fsi-occ.h (limited to 'include/linux') diff --git a/include/linux/fsi-occ.h b/include/linux/fsi-occ.h new file mode 100644 index 000000000000..d4cdc2aa6e33 --- /dev/null +++ b/include/linux/fsi-occ.h @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef LINUX_FSI_OCC_H +#define LINUX_FSI_OCC_H + +struct device; + +#define OCC_RESP_CMD_IN_PRG 0xFF +#define OCC_RESP_SUCCESS 0 +#define OCC_RESP_CMD_INVAL 0x11 +#define OCC_RESP_CMD_LEN_INVAL 0x12 +#define OCC_RESP_DATA_INVAL 0x13 +#define OCC_RESP_CHKSUM_ERR 0x14 +#define OCC_RESP_INT_ERR 0x15 +#define OCC_RESP_BAD_STATE 0x16 +#define OCC_RESP_CRIT_EXCEPT 0xE0 +#define OCC_RESP_CRIT_INIT 0xE1 +#define OCC_RESP_CRIT_WATCHDOG 0xE2 +#define OCC_RESP_CRIT_OCB 0xE3 +#define OCC_RESP_CRIT_HW 0xE4 + +int fsi_occ_submit(struct device *dev, const void *request, size_t req_len, + void *response, size_t *resp_len); + +#endif /* LINUX_FSI_OCC_H */ -- cgit v1.2.3 From 37c2578c0c40e286bc0d30bdc05290b2058cf66e Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 3 Dec 2018 00:54:35 +0000 Subject: Drivers: hv: vmbus: Offload the handling of channels to two workqueues vmbus_process_offer() mustn't call channel->sc_creation_callback() directly for sub-channels, because sc_creation_callback() -> vmbus_open() may never get the host's response to the OPEN_CHANNEL message (the host may rescind a channel at any time, e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() may not wake up the vmbus_open() as it's blocked due to a non-zero vmbus_connection.offer_in_progress, and finally we have a deadlock. The above is also true for primary channels, if the related device drivers use sync probing mode by default. And, usually the handling of primary channels and sub-channels can depend on each other, so we should offload them to different workqueues to avoid possible deadlock, e.g. in sync-probing mode, NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> rtnl_lock(), and causes deadlock: the former gets the rtnl_lock and waits for all the sub-channels to appear, but the latter can't get the rtnl_lock and this blocks the handling of sub-channels. The patch can fix the multiple-NIC deadlock described above for v3.x kernels (e.g. RHEL 7.x) which don't support async-probing of devices, and v4.4, v4.9, v4.14 and v4.18 which support async-probing but don't enable async-probing for Hyper-V drivers (yet). The patch can also fix the hang issue in sub-channel's handling described above for all versions of kernels, including v4.19 and v4.20-rc4. So actually the patch should be applied to all the existing kernels, not only the kernels that have 8195b1396ec8. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Cc: stable@vger.kernel.org Cc: Stephen Hemminger Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b3e24368930a..14131b6fae68 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -905,6 +905,13 @@ struct vmbus_channel { bool probe_done; + /* + * We must offload the handling of the primary/sub channels + * from the single-threaded vmbus_connection.work_queue to + * two different workqueue, otherwise we can block + * vmbus_connection.work_queue and hang: see vmbus_process_offer(). + */ + struct work_struct add_channel_work; }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From dfcb245e28481256a10a9133441baf2a93d26642 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 3 Dec 2018 10:05:56 +0100 Subject: sched: Fix various typos in comments Go over the scheduler source code and fix common typos in comments - and a typo in an actual variable name. No change in functionality intended. Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Linus Torvalds Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- include/linux/sched/isolation.h | 4 ++-- include/linux/sched/mm.h | 2 +- include/linux/sched/stat.h | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 291a9bd5b97f..b8c7ba0e3796 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -176,7 +176,7 @@ struct task_group; * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can - * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not + * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * @@ -515,7 +515,7 @@ struct sched_dl_entity { /* * Actual scheduling parameters. Initialized with the values above, - * they are continously updated during task execution. Note that + * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 4a6582c27dea..b0fb1446fe04 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -16,7 +16,7 @@ enum hk_flags { }; #ifdef CONFIG_CPU_ISOLATION -DECLARE_STATIC_KEY_FALSE(housekeeping_overriden); +DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); extern int housekeeping_any_cpu(enum hk_flags flags); extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); @@ -43,7 +43,7 @@ static inline void housekeeping_init(void) { } static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) { #ifdef CONFIG_CPU_ISOLATION - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) return housekeeping_test_cpu(cpu, flags); #endif return true; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aebb370a0006..3bfa6a0cbba4 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -153,7 +153,7 @@ static inline gfp_t current_gfp_context(gfp_t flags) { /* * NOIO implies both NOIO and NOFS and it is a weaker context - * so always make sure it makes precendence + * so always make sure it makes precedence */ if (unlikely(current->flags & PF_MEMALLOC_NOIO)) flags &= ~(__GFP_IO | __GFP_FS); diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index f30954cc059d..568286411b43 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -8,7 +8,7 @@ * Various counters maintained by the scheduler and fork(), * exposed via /proc, sys.c or used by drivers via these APIs. * - * ( Note that all these values are aquired without locking, + * ( Note that all these values are acquired without locking, * so they can only be relied on in narrow circumstances. ) */ -- cgit v1.2.3 From 078dec3326e2244c62e8a8d970ba24359e3464be Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 3 Dec 2018 13:36:14 +0100 Subject: dma-buf: add dma_fence_get_stub MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extract of useful code from the timeline work. This provides a function to return a stub or dummy fence which is always signaled. Signed-off-by: Christian König Reviewed-by: Chris Wilson Reviewed-by: Chunming Zhou Link: https://patchwork.freedesktop.org/patch/265248/ --- include/linux/dma-fence.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 02dba8cd033d..999e4b104410 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -541,6 +541,7 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr) return ret < 0 ? ret : 0; } +struct dma_fence *dma_fence_get_stub(void); u64 dma_fence_context_alloc(unsigned num); #define DMA_FENCE_TRACE(f, fmt, args...) \ -- cgit v1.2.3 From 6b03061f882de49b83ccf44beb3a12c920a2da1b Mon Sep 17 00:00:00 2001 From: Yogesh Narayan Gaur Date: Mon, 3 Dec 2018 08:39:06 +0000 Subject: spi: add support for octal mode I/O data transfer Add flags for Octal mode I/O data transfer Required for the SPI controller which can do the data transfer (TX/RX) on 8 data lines e.g. NXP FlexSPI controller. SPI_TX_OCTAL: transmit with 8 wires SPI_RX_OCTAL: receive with 8 wires Signed-off-by: Yogesh Gaur Reviewed-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 6be77fa5ab90..0c1ca5dedbb4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -154,7 +154,9 @@ struct spi_device { #define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ #define SPI_RX_DUAL 0x400 /* receive with 2 wires */ #define SPI_RX_QUAD 0x800 /* receive with 4 wires */ -#define SPI_CS_WORD 0x1000 /* toggle cs after each word */ +#define SPI_CS_WORD 0x1000 /* toggle cs after each word */ +#define SPI_TX_OCTAL 0x2000 /* transmit with 8 wires */ +#define SPI_RX_OCTAL 0x4000 /* receive with 8 wires */ int irq; void *controller_state; void *controller_data; -- cgit v1.2.3 From e983da27f70e8d29f4ae7262d52e4d07129498f3 Mon Sep 17 00:00:00 2001 From: "A.s. Dong" Date: Wed, 14 Nov 2018 13:01:39 +0000 Subject: clk: fractional-divider: add CLK_FRAC_DIVIDER_ZERO_BASED flag support Adding CLK_FRAC_DIVIDER_ZERO_BASED flag to indicate the numerator and denominator value in register are start from 0. This can be used to support frac dividers like below: Divider output clock = Divider input clock x [(frac +1) / (div +1)] where frac/div in register is: 000b - Divide by 1. 001b - Divide by 2. 010b - Divide by 3. Cc: Stephen Boyd Cc: Michael Turquette Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 60c51871b04b..fa0bad94f26b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -601,6 +601,12 @@ void clk_hw_unregister_fixed_factor(struct clk_hw *hw); * @lock: register lock * * Clock with adjustable fractional divider affecting its output frequency. + * + * Flags: + * CLK_FRAC_DIVIDER_ZERO_BASED - by default the numerator and denominator + * is the value read from the register. If CLK_FRAC_DIVIDER_ZERO_BASED + * is set then the numerator and denominator are both the value read + * plus one. */ struct clk_fractional_divider { struct clk_hw hw; @@ -620,6 +626,8 @@ struct clk_fractional_divider { #define to_clk_fd(_hw) container_of(_hw, struct clk_fractional_divider, hw) +#define CLK_FRAC_DIVIDER_ZERO_BASED BIT(0) + extern const struct clk_ops clk_fractional_divider_ops; struct clk *clk_register_fractional_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, -- cgit v1.2.3 From 0d5102fe85302aa06a3e5fd8e63b09294aed4c48 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 28 Nov 2018 13:45:29 +0200 Subject: i2c: acpi: Introduce i2c_acpi_get_i2c_resource() helper Besides current two users one more is coming. Definitely makes sense to introduce a helper. No functional change intended. Signed-off-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Reviewed-by: Hans de Goede Acked-by: Mika Westerberg Acked-by: Wolfram Sang --- include/linux/acpi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ed80f147bd50..6afc6e3c4c5c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1054,6 +1054,17 @@ static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) } #endif +#if defined(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C) +bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, + struct acpi_resource_i2c_serialbus **i2c); +#else +static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, + struct acpi_resource_i2c_serialbus **i2c) +{ + return false; +} +#endif + /* Device properties */ #ifdef CONFIG_ACPI -- cgit v1.2.3 From c2a70a319afb9e3dee16567cec4d9bf8dd358b59 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sun, 17 Jun 2018 19:02:15 +0200 Subject: dmaengine: pxa: make the filter function internal As the pxa architecture and all its related drivers do not rely anymore on the filter function, thanks to the slave map conversion, make pxad_filter_fn() static, and remove it from the global namespace. Signed-off-by: Robert Jarzmik Acked-by: Vinod Koul --- include/linux/dma/pxa-dma.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma/pxa-dma.h b/include/linux/dma/pxa-dma.h index 9fc594f69eff..fceb5df07097 100644 --- a/include/linux/dma/pxa-dma.h +++ b/include/linux/dma/pxa-dma.h @@ -23,15 +23,4 @@ struct pxad_param { enum pxad_chan_prio prio; }; -struct dma_chan; - -#ifdef CONFIG_PXA_DMA -bool pxad_filter_fn(struct dma_chan *chan, void *param); -#else -static inline bool pxad_filter_fn(struct dma_chan *chan, void *param) -{ - return false; -} -#endif - #endif /* _PXA_DMA_H_ */ -- cgit v1.2.3 From 82208d0d54ab85d8fedbb1c9a1960bd401a4ca1a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 30 Nov 2018 10:26:50 +1100 Subject: rhashtable: detect when object movement between tables might have invalidated a lookup Some users of rhashtables might need to move an object from one table to another - this appears to be the reason for the incomplete usage of NULLS markers. To support these, we store a unique NULLS_MARKER at the end of each chain, and when a search fails to find a match, we check if the NULLS marker found was the expected one. If not, the search may not have examined all objects in the target bucket, so it is repeated. The unique NULLS_MARKER is derived from the address of the head of the chain. As this cannot be derived at load-time the static rhnull in rht_bucket_nested() needs to be initialised at run time. Any caller of a lookup function must still be prepared for the possibility that the object returned is in a different table - it might have been there for some time. Note that this does NOT provide support for other uses of NULLS_MARKERs such as allocating with SLAB_TYPESAFE_BY_RCU or changing the key of an object and re-inserting it in the same table. These could only be done safely if new objects were inserted at the *start* of a hash chain, and that is not currently the case. Signed-off-by: NeilBrown Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index eb7111039247..20f9c6af7473 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -75,8 +75,19 @@ struct bucket_table { struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; +/* + * NULLS_MARKER() expects a hash value with the low + * bits mostly likely to be significant, and it discards + * the msb. + * We git it an address, in which the bottom 2 bits are + * always 0, and the msb might be significant. + * So we shift the address down one bit to align with + * expectations and avoid losing a significant bit. + */ +#define RHT_NULLS_MARKER(ptr) \ + ((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1)) #define INIT_RHT_NULLS_HEAD(ptr) \ - ((ptr) = (typeof(ptr)) NULLS_MARKER(0)) + ((ptr) = RHT_NULLS_MARKER(&(ptr))) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { @@ -471,6 +482,7 @@ static inline struct rhash_head *__rhashtable_lookup( .ht = ht, .key = key, }; + struct rhash_head __rcu * const *head; struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; @@ -478,13 +490,19 @@ static inline struct rhash_head *__rhashtable_lookup( tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); - rht_for_each_rcu(he, tbl, hash) { - if (params.obj_cmpfn ? - params.obj_cmpfn(&arg, rht_obj(ht, he)) : - rhashtable_compare(&arg, rht_obj(ht, he))) - continue; - return he; - } + head = rht_bucket(tbl, hash); + do { + rht_for_each_rcu_continue(he, *head, tbl, hash) { + if (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, he)) : + rhashtable_compare(&arg, rht_obj(ht, he))) + continue; + return he; + } + /* An object might have been moved to a different hash chain, + * while we walk along it - better check and retry. + */ + } while (he != RHT_NULLS_MARKER(head)); /* Ensure we see any new tables. */ smp_rmb(); -- cgit v1.2.3 From 0e839df92cf37be4adef7e661813206cd2b32d66 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 30 Nov 2018 09:20:57 +0100 Subject: net: ethernet: provide nvmem_get_mac_address() We already have of_get_nvmem_mac_address() but some non-DT systems want to read the MAC address from NVMEM too. Implement a generalized routine that takes struct device as argument. Signed-off-by: Bartosz Golaszewski Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 572e11bb8696..2c0af7b00715 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -32,6 +32,7 @@ struct device; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); +int nvmem_get_mac_address(struct device *dev, void *addrbuf); u32 eth_get_headlen(void *data, unsigned int max_len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; -- cgit v1.2.3 From afa64a72b862a7a9d04f8d07fba632eaf06b23f8 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 30 Nov 2018 09:20:59 +0100 Subject: of: net: kill of_get_nvmem_mac_address() We've switched all users to nvmem_get_mac_address(). Remove the now dead code. Signed-off-by: Bartosz Golaszewski Reviewed-by: Rob Herring Signed-off-by: David S. Miller --- include/linux/of_net.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 90d81ee9e6a0..9cd72aab76fe 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -13,7 +13,6 @@ struct net_device; extern int of_get_phy_mode(struct device_node *np); extern const void *of_get_mac_address(struct device_node *np); -extern int of_get_nvmem_mac_address(struct device_node *np, void *addr); extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else static inline int of_get_phy_mode(struct device_node *np) @@ -26,11 +25,6 @@ static inline const void *of_get_mac_address(struct device_node *np) return NULL; } -static inline int of_get_nvmem_mac_address(struct device_node *np, void *addr) -{ - return -ENODEV; -} - static inline struct net_device *of_find_net_device_by_node(struct device_node *np) { return NULL; -- cgit v1.2.3 From b5947e5d1e710c35ea281247bd27e6975250285c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 30 Nov 2018 15:32:39 -0500 Subject: udp: msg_zerocopy Extend zerocopy to udp sockets. Allow setting sockopt SO_ZEROCOPY and interpret flag MSG_ZEROCOPY. This patch was previously part of the zerocopy RFC patchsets. Zerocopy is not effective at small MTU. With segmentation offload building larger datagrams, the benefit of page flipping outweights the cost of generating a completion notification. tools/testing/selftests/net/msg_zerocopy.sh after applying follow-on test patch and making skb_orphan_frags_rx same as skb_orphan_frags: ipv4 udp -t 1 tx=191312 (11938 MB) txc=0 zc=n rx=191312 (11938 MB) ipv4 udp -z -t 1 tx=304507 (19002 MB) txc=304507 zc=y rx=304507 (19002 MB) ok ipv6 udp -t 1 tx=174485 (10888 MB) txc=0 zc=n rx=174485 (10888 MB) ipv6 udp -z -t 1 tx=294801 (18396 MB) txc=294801 zc=y rx=294801 (18396 MB) ok Changes v1 -> v2 - Fixup reverse christmas tree violation v2 -> v3 - Split refcount avoidance optimization into separate patch - Fix refcount leak on error in fragmented case (thanks to Paolo Abeni for pointing this one out!) - Fix refcount inc on zero - Test sock_flag SOCK_ZEROCOPY directly in __ip_append_data. This is needed since commit 5cf4a8532c99 ("tcp: really ignore MSG_ZEROCOPY if no SO_ZEROCOPY") did the same for tcp. Signed-off-by: Willem de Bruijn Acked-by: Paolo Abeni 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 73902acf2b71..04f52e719571 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -485,6 +485,7 @@ void sock_zerocopy_put_abort(struct ubuf_info *uarg); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); +int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg); -- cgit v1.2.3 From 52900d22288e7d45846037e1db277c665bbc40db Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 30 Nov 2018 15:32:40 -0500 Subject: udp: elide zerocopy operation in hot path With MSG_ZEROCOPY, each skb holds a reference to a struct ubuf_info. Release of its last reference triggers a completion notification. The TCP stack in tcp_sendmsg_locked holds an extra ref independent of the skbs, because it can build, send and free skbs within its loop, possibly reaching refcount zero and freeing the ubuf_info too soon. The UDP stack currently also takes this extra ref, but does not need it as all skbs are sent after return from __ip(6)_append_data. Avoid the extra refcount_inc and refcount_dec_and_test, and generally the sock_zerocopy_put in the common path, by passing the initial reference to the first skb. This approach is taken instead of initializing the refcount to 0, as that would generate error "refcount_t: increment on 0" on the next skb_zcopy_set. Changes v3 -> v4 - Move skb_zcopy_set below the only kfree_skb that might cause a premature uarg destroy before skb_zerocopy_put_abort - Move the entire skb_shinfo assignment block, to keep that cacheline access in one place Signed-off-by: Willem de Bruijn Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 04f52e719571..75d50ab7997c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -481,7 +481,7 @@ static inline void sock_zerocopy_get(struct ubuf_info *uarg) } void sock_zerocopy_put(struct ubuf_info *uarg); -void sock_zerocopy_put_abort(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); @@ -1326,10 +1326,14 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } -static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, + bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { - sock_zerocopy_get(uarg); + if (unlikely(have_ref && *have_ref)) + *have_ref = false; + else + sock_zerocopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; } @@ -1374,7 +1378,7 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { - sock_zerocopy_put_abort(uarg); + sock_zerocopy_put_abort(uarg, false); skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } } -- cgit v1.2.3 From 8c2def893afc60d88160d524acf345765cf0c447 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 3 Dec 2018 14:45:43 -0800 Subject: sbitmap: fix sbitmap_for_each_set() We need to ignore bits in the cleared mask when iterating over all set bits. Fixes: ea86ea2cdced ("sbitmap: ammortize cost of clearing bits") Reported-by: Jens Axboe@kernel.dk> Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 92806a2dbab7..03f50fcedc79 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -265,12 +265,14 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb, nr = SB_NR_TO_BIT(sb, start); while (scanned < sb->depth) { - struct sbitmap_word *word = &sb->map[index]; - unsigned int depth = min_t(unsigned int, word->depth - nr, + unsigned long word; + unsigned int depth = min_t(unsigned int, + sb->map[index].depth - nr, sb->depth - scanned); scanned += depth; - if (!word->word) + word = sb->map[index].word & ~sb->map[index].cleared; + if (!word) goto next; /* @@ -280,7 +282,7 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb, */ depth += nr; while (1) { - nr = find_next_bit(&word->word, depth, nr); + nr = find_next_bit(&word, depth, nr); if (nr >= depth) break; if (!fn(sb, (index << sb->shift) + nr, data)) -- cgit v1.2.3 From 4c05ec47384ab3627b62814e8f886e90cc38ce15 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 26 Nov 2018 20:03:30 +0900 Subject: netfilter: nf_tables: fix suspicious RCU usage in nft_chain_stats_replace() basechain->stats is rcu protected data which is updated from nft_chain_stats_replace(). This function is executed from the commit phase which holds the pernet nf_tables commit mutex - not the global nfnetlink subsystem mutex. Test commands to reproduce the problem are: %iptables-nft -I INPUT %iptables-nft -Z %iptables-nft -Z This patch uses RCU calls to handle basechain->stats updates to fix a splat that looks like: [89279.358755] ============================= [89279.363656] WARNING: suspicious RCU usage [89279.368458] 4.20.0-rc2+ #44 Tainted: G W L [89279.374661] ----------------------------- [89279.379542] net/netfilter/nf_tables_api.c:1404 suspicious rcu_dereference_protected() usage! [...] [89279.406556] 1 lock held by iptables-nft/5225: [89279.411728] #0: 00000000bf45a000 (&net->nft.commit_mutex){+.+.}, at: nf_tables_valid_genid+0x1f/0x70 [nf_tables] [89279.424022] stack backtrace: [89279.429236] CPU: 0 PID: 5225 Comm: iptables-nft Tainted: G W L 4.20.0-rc2+ #44 [89279.430135] Call Trace: [89279.430135] dump_stack+0xc9/0x16b [89279.430135] ? show_regs_print_info+0x5/0x5 [89279.430135] ? lockdep_rcu_suspicious+0x117/0x160 [89279.430135] nft_chain_commit_update+0x4ea/0x640 [nf_tables] [89279.430135] ? sched_clock_local+0xd4/0x140 [89279.430135] ? check_flags.part.35+0x440/0x440 [89279.430135] ? __rhashtable_remove_fast.constprop.67+0xec0/0xec0 [nf_tables] [89279.430135] ? sched_clock_cpu+0x126/0x170 [89279.430135] ? find_held_lock+0x39/0x1c0 [89279.430135] ? hlock_class+0x140/0x140 [89279.430135] ? is_bpf_text_address+0x5/0xf0 [89279.430135] ? check_flags.part.35+0x440/0x440 [89279.430135] ? __lock_is_held+0xb4/0x140 [89279.430135] nf_tables_commit+0x2555/0x39c0 [nf_tables] Fixes: f102d66b335a4 ("netfilter: nf_tables: use dedicated mutex to guard transactions") Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 4a520d3304a2..cf09ab37b45b 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -62,18 +62,6 @@ static inline bool lockdep_nfnl_is_held(__u8 subsys_id) } #endif /* CONFIG_PROVE_LOCKING */ -/* - * nfnl_dereference - fetch RCU pointer when updates are prevented by subsys mutex - * - * @p: The pointer to read, prior to dereferencing - * @ss: The nfnetlink subsystem ID - * - * Return the value of the specified RCU-protected pointer, but omit - * the READ_ONCE(), because caller holds the NFNL subsystem mutex. - */ -#define nfnl_dereference(p, ss) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(ss)) - #define MODULE_ALIAS_NFNL_SUBSYS(subsys) \ MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys)) -- cgit v1.2.3 From 7684bd334d9d4ca4f09873e88d9c0131a2cf6c3b Mon Sep 17 00:00:00 2001 From: Peng Wang Date: Tue, 30 Oct 2018 15:52:34 +0800 Subject: pstore: Avoid duplicate call of persistent_ram_zap() When initialing a prz, if invalid data is found (no PERSISTENT_RAM_SIG), the function call path looks like this: ramoops_init_prz -> persistent_ram_new -> persistent_ram_post_init -> persistent_ram_zap persistent_ram_zap As we can see, persistent_ram_zap() is called twice. We can avoid this by adding an option to persistent_ram_new(), and only call persistent_ram_zap() when it is needed. Signed-off-by: Peng Wang [kees: minor tweak to exit path and commit log] Signed-off-by: Kees Cook --- include/linux/pstore_ram.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 602d64725222..6e94980357d2 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -30,6 +30,7 @@ * PRZ_FLAG_NO_LOCK is used. For all other cases, locking is required. */ #define PRZ_FLAG_NO_LOCK BIT(0) +#define PRZ_FLAG_ZAP_OLD BIT(1) struct persistent_ram_buffer; struct rs_control; -- cgit v1.2.3 From c208f7d4b037e1c71e5c839bb5dfcc3e0df19890 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 15:11:47 -0700 Subject: pstore/ram: Add kern-doc for struct persistent_ram_zone The struct persistent_ram_zone wasn't well documented. This adds kern-doc for it. Signed-off-by: Kees Cook --- include/linux/pstore_ram.h | 46 +++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 43 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 6e94980357d2..5d10ad51c1c4 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -30,6 +30,10 @@ * PRZ_FLAG_NO_LOCK is used. For all other cases, locking is required. */ #define PRZ_FLAG_NO_LOCK BIT(0) +/* + * If a PRZ should only have a single-boot lifetime, this marks it as + * getting wiped after its contents get copied out after boot. + */ #define PRZ_FLAG_ZAP_OLD BIT(1) struct persistent_ram_buffer; @@ -43,17 +47,53 @@ struct persistent_ram_ecc_info { uint16_t *par; }; +/** + * struct persistent_ram_zone - Details of a persistent RAM zone (PRZ) + * used as a pstore backend + * + * @paddr: physical address of the mapped RAM area + * @size: size of mapping + * @label: unique name of this PRZ + * @flags: holds PRZ_FLAGS_* bits + * + * @buffer_lock: + * locks access to @buffer "size" bytes and "start" offset + * @buffer: + * pointer to actual RAM area managed by this PRZ + * @buffer_size: + * bytes in @buffer->data (not including any trailing ECC bytes) + * + * @par_buffer: + * pointer into @buffer->data containing ECC bytes for @buffer->data + * @par_header: + * pointer into @buffer->data containing ECC bytes for @buffer header + * (i.e. all fields up to @data) + * @rs_decoder: + * RSLIB instance for doing ECC calculations + * @corrected_bytes: + * ECC corrected bytes accounting since boot + * @bad_blocks: + * ECC uncorrectable bytes accounting since boot + * @ecc_info: + * ECC configuration details + * + * @old_log: + * saved copy of @buffer->data prior to most recent wipe + * @old_log_size: + * bytes contained in @old_log + * + */ struct persistent_ram_zone { phys_addr_t paddr; size_t size; void *vaddr; char *label; - struct persistent_ram_buffer *buffer; - size_t buffer_size; u32 flags; + raw_spinlock_t buffer_lock; + struct persistent_ram_buffer *buffer; + size_t buffer_size; - /* ECC correction */ char *par_buffer; char *par_header; struct rs_control *rs_decoder; -- cgit v1.2.3 From 0eed84ffb094bbddfb4b9378ef0a2eccf4dda99c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 14:03:07 -0700 Subject: pstore: Improve and update some comments and status output This improves and updates some comments: - dump handler comment out of sync from calling convention - fix kern-doc typo and improves status output: - reminder that only kernel crash dumps are compressed - do not be silent about ECC infrastructure failures Signed-off-by: Kees Cook --- include/linux/pstore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 30fcec375a3a..81669aa80027 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -85,7 +85,7 @@ struct pstore_record { /** * struct pstore_info - backend pstore driver structure * - * @owner: module which is repsonsible for this backend driver + * @owner: module which is responsible for this backend driver * @name: name of the backend driver * * @buf_lock: spinlock to serialize access to @buf -- cgit v1.2.3 From 4af62a6423d0ad98e3eee2bec4305dde8deefefe Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 15:30:05 -0700 Subject: pstore: Replace open-coded << with BIT() Minor clean-up to use BIT() (as already done in pstore_ram.h). Signed-off-by: Kees Cook --- include/linux/pstore.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 81669aa80027..f46e5df76b58 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -192,10 +192,10 @@ struct pstore_info { }; /* Supported frontends */ -#define PSTORE_FLAGS_DMESG (1 << 0) -#define PSTORE_FLAGS_CONSOLE (1 << 1) -#define PSTORE_FLAGS_FTRACE (1 << 2) -#define PSTORE_FLAGS_PMSG (1 << 3) +#define PSTORE_FLAGS_DMESG BIT(0) +#define PSTORE_FLAGS_CONSOLE BIT(1) +#define PSTORE_FLAGS_FTRACE BIT(2) +#define PSTORE_FLAGS_PMSG BIT(3) extern int pstore_register(struct pstore_info *); extern void pstore_unregister(struct pstore_info *); -- cgit v1.2.3 From f0f23e5469dc80b482d985898a930be0e249a162 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Sat, 3 Nov 2018 16:38:16 -0700 Subject: pstore: Map PSTORE_TYPE_* to strings In later patches we will need to map types to names, so create a constant table for that which can also be used in different parts of old and new code. This saves the type in the PRZ which will be useful in later patches. Instead of having an explicit PSTORE_TYPE_UNKNOWN, just use ..._MAX. This includes removing the now redundant filename templates which can use a single format string. Also, there's no reason to limit the "is it still compressed?" test to only PSTORE_TYPE_DMESG when building the pstorefs filename. Records are zero-initialized, so a backend would need to have explicitly set compressed=1. Signed-off-by: Joel Fernandes (Google) Co-developed-by: Kees Cook Signed-off-by: Kees Cook --- include/linux/pstore.h | 17 ++++++++++++++--- include/linux/pstore_ram.h | 3 +++ 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index f46e5df76b58..a9ec285d85d1 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -32,21 +32,32 @@ struct module; -/* pstore record types (see fs/pstore/inode.c for filename templates) */ +/* + * pstore record types (see fs/pstore/platform.c for pstore_type_names[]) + * These values may be written to storage (see EFI vars backend), so + * they are kind of an ABI. Be careful changing the mappings. + */ enum pstore_type_id { + /* Frontend storage types */ PSTORE_TYPE_DMESG = 0, PSTORE_TYPE_MCE = 1, PSTORE_TYPE_CONSOLE = 2, PSTORE_TYPE_FTRACE = 3, - /* PPC64 partition types */ + + /* PPC64-specific partition types */ PSTORE_TYPE_PPC_RTAS = 4, PSTORE_TYPE_PPC_OF = 5, PSTORE_TYPE_PPC_COMMON = 6, PSTORE_TYPE_PMSG = 7, PSTORE_TYPE_PPC_OPAL = 8, - PSTORE_TYPE_UNKNOWN = 255 + + /* End of the list */ + PSTORE_TYPE_MAX }; +const char *pstore_type_to_name(enum pstore_type_id type); +enum pstore_type_id pstore_name_to_type(const char *name); + struct pstore_info; /** * struct pstore_record - details of a pstore record entry diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 5d10ad51c1c4..337971c41980 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -22,6 +22,7 @@ #include #include #include +#include #include /* @@ -54,6 +55,7 @@ struct persistent_ram_ecc_info { * @paddr: physical address of the mapped RAM area * @size: size of mapping * @label: unique name of this PRZ + * @type: frontend type for this PRZ * @flags: holds PRZ_FLAGS_* bits * * @buffer_lock: @@ -88,6 +90,7 @@ struct persistent_ram_zone { size_t size; void *vaddr; char *label; + enum pstore_type_id type; u32 flags; raw_spinlock_t buffer_lock; -- cgit v1.2.3 From ea84b580b95521644429cc6748b6c2bf27c8b0f3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 30 Nov 2018 14:36:58 -0800 Subject: pstore: Convert buf_lock to semaphore Instead of running with interrupts disabled, use a semaphore. This should make it easier for backends that may need to sleep (e.g. EFI) when performing a write: |BUG: sleeping function called from invalid context at kernel/sched/completion.c:99 |in_atomic(): 1, irqs_disabled(): 1, pid: 2236, name: sig-xstate-bum |Preemption disabled at: |[] pstore_dump+0x72/0x330 |CPU: 26 PID: 2236 Comm: sig-xstate-bum Tainted: G D 4.20.0-rc3 #45 |Call Trace: | dump_stack+0x4f/0x6a | ___might_sleep.cold.91+0xd3/0xe4 | __might_sleep+0x50/0x90 | wait_for_completion+0x32/0x130 | virt_efi_query_variable_info+0x14e/0x160 | efi_query_variable_store+0x51/0x1a0 | efivar_entry_set_safe+0xa3/0x1b0 | efi_pstore_write+0x109/0x140 | pstore_dump+0x11c/0x330 | kmsg_dump+0xa4/0xd0 | oops_exit+0x22/0x30 ... Reported-by: Sebastian Andrzej Siewior Fixes: 21b3ddd39fee ("efi: Don't use spinlocks for efi vars") Signed-off-by: Kees Cook --- include/linux/pstore.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index a9ec285d85d1..b146181e8709 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include @@ -99,7 +99,7 @@ struct pstore_record { * @owner: module which is responsible for this backend driver * @name: name of the backend driver * - * @buf_lock: spinlock to serialize access to @buf + * @buf_lock: semaphore to serialize access to @buf * @buf: preallocated crash dump buffer * @bufsize: size of @buf available for crash dump bytes (must match * smallest number of bytes available for writing to a @@ -184,7 +184,7 @@ struct pstore_info { struct module *owner; char *name; - spinlock_t buf_lock; + struct semaphore buf_lock; char *buf; size_t bufsize; @@ -210,7 +210,6 @@ struct pstore_info { extern int pstore_register(struct pstore_info *); extern void pstore_unregister(struct pstore_info *); -extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason); struct pstore_ftrace_record { unsigned long ip; -- cgit v1.2.3 From 96f1e097457506f215adfe3c47aacc15a88f6dd7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 3 Dec 2018 23:16:07 -0500 Subject: jbd2: avoid long hold times of j_state_lock while committing a transaction We can hold j_state_lock for writing at the beginning of jbd2_journal_commit_transaction() for a rather long time (reportedly for 30 ms) due cleaning revoke bits of all revoked buffers under it. The handling of revoke tables as well as cleaning of t_reserved_list, and checkpoint lists does not need j_state_lock for anything. It is only needed to prevent new handles from joining the transaction. Generally T_LOCKED transaction state prevents new handles from joining the transaction - except for reserved handles which have to allowed to join while we wait for other handles to complete. To prevent reserved handles from joining the transaction while cleaning up lists, add new transaction state T_SWITCH and watch for it when starting reserved handles. With this we can just drop the lock for operations that don't need it. Reported-and-tested-by: Adrian Hunter Suggested-by: "Theodore Y. Ts'o" Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index b708e5169d1d..118d00a64184 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -575,6 +575,7 @@ struct transaction_s enum { T_RUNNING, T_LOCKED, + T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, -- cgit v1.2.3 From 32ea275008d8c76fa3f40d10d0ffc694a214dfef Mon Sep 17 00:00:00 2001 From: Alexander Lochmann Date: Tue, 4 Dec 2018 00:30:22 -0500 Subject: jbd2: update locking documentation for transaction_t The following members of struct transaction_s aka transaction_t were turned into lock-free variables in the past: - t_updates - t_outstanding_credits - t_handle_count However, the documentation has not been updated yet. This commit replaced the annotated lock by [none]. Found by LockDoc (Alexander Lochmann, Horst Schirmeier and Olaf Spinczyk) Signed-off-by: Alexander Lochmann Signed-off-by: Horst Schirmeier Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 118d00a64184..0f919d5fe84f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -663,13 +663,13 @@ struct transaction_s /* * Number of outstanding updates running on this transaction - * [t_handle_lock] + * [none] */ atomic_t t_updates; /* * Number of buffers reserved for use by all handles in this transaction - * handle but not yet modified. [t_handle_lock] + * handle but not yet modified. [none] */ atomic_t t_outstanding_credits; @@ -691,7 +691,7 @@ struct transaction_s ktime_t t_start_time; /* - * How many handles used this transaction? [t_handle_lock] + * How many handles used this transaction? [none] */ atomic_t t_handle_count; -- cgit v1.2.3 From 6cd0014ab90f6959fa1f8cc8b3f38d302457c919 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 28 Nov 2018 20:53:33 +0200 Subject: net/mlx5: Align SRQ licenses and copyright information Ensure that both RDMA and netdev parts of SRQ implementation has same copyright and license information annotated by SPDX tags. Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- include/linux/mlx5/srq.h | 31 ++----------------------------- 1 file changed, 2 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 1b1f3c20c6a3..77bc4264066d 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -1,33 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. + * Copyright (c) 2013-2018, Mellanox Technologies. All rights reserved. */ #ifndef MLX5_SRQ_H -- cgit v1.2.3 From 5b5f0f16276021794038f12adc56df70cec42b4f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 28 Nov 2018 20:53:34 +0200 Subject: net/mlx5: Remove dead transobj code Delete functions which are not called and not needed. Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- include/linux/mlx5/transobj.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 7f5ca2cd3a32..39ebb699875b 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -63,11 +63,6 @@ int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen, int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen); int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn); int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out); -int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm); -int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen, - u32 *rmpn); -int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 rmpn); -int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm); int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqtn); -- cgit v1.2.3 From f02d0d6e53ac2c8a75b6cc87dc86675a9351d84d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 28 Nov 2018 20:53:37 +0200 Subject: net/mlx5: Move SRQ functions to RDMA part There is no need to keep SRQ which is RDMA object in mlx5_core. In this patch, we partially move the execution code, while next patches will move table initialization/release logic too. Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 8 -------- include/linux/mlx5/srq.h | 31 ------------------------------- include/linux/mlx5/transobj.h | 6 ------ 3 files changed, 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 27a481b159ed..1096da4fb368 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -904,13 +904,6 @@ struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, gfp_t flags, int npages); void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *head); -int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_srq_attr *in); -int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq); -int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_srq_attr *out); -int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - u16 lwm, int is_srq); void mlx5_init_mkey_table(struct mlx5_core_dev *dev); void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev); int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, @@ -942,7 +935,6 @@ void mlx5_unregister_debugfs(void); void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); -struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 77bc4264066d..9343306cd188 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -6,37 +6,6 @@ #ifndef MLX5_SRQ_H #define MLX5_SRQ_H -#include - -enum { - MLX5_SRQ_FLAG_ERR = (1 << 0), - MLX5_SRQ_FLAG_WQ_SIG = (1 << 1), - MLX5_SRQ_FLAG_RNDV = (1 << 2), -}; - -struct mlx5_srq_attr { - u32 type; - u32 flags; - u32 log_size; - u32 wqe_shift; - u32 log_page_size; - u32 wqe_cnt; - u32 srqn; - u32 xrcd; - u32 page_offset; - u32 cqn; - u32 pd; - u32 lwm; - u32 user_index; - u64 db_record; - __be64 *pas; - u32 tm_log_list_size; - u32 tm_next_tag; - u32 tm_hw_phase_cnt; - u32 tm_sw_phase_cnt; - u16 uid; -}; - struct mlx5_core_dev; void mlx5_init_srq_table(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 39ebb699875b..a261d5528ff7 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -58,12 +58,6 @@ int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen, int mlx5_core_modify_tis(struct mlx5_core_dev *dev, u32 tisn, u32 *in, int inlen); void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn); -int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen, - u32 *rmpn); -int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen); -int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn); -int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out); - int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqtn); int mlx5_core_modify_rqt(struct mlx5_core_dev *dev, u32 rqtn, u32 *in, -- cgit v1.2.3 From f3da6577da67a3cd44610ca54e308c6838c92157 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 28 Nov 2018 20:53:41 +0200 Subject: RDMA/mlx5: Initialize SRQ tables on mlx5_ib Transfer initialization and cleanup from mlx5_priv struct of mlx5_core_dev to be part of mlx5_ib_dev. This completes removal of SRQ from mlx5_core. Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 25 ------------------------- include/linux/mlx5/srq.h | 14 -------------- 2 files changed, 39 deletions(-) delete mode 100644 include/linux/mlx5/srq.h (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1096da4fb368..584d8a5df7eb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -50,7 +50,6 @@ #include #include -#include #include #include #include @@ -393,20 +392,6 @@ struct mlx5_core_rsc_common { struct completion free; }; -struct mlx5_core_srq { - struct mlx5_core_rsc_common common; /* must be first */ - u32 srqn; - int max; - size_t max_gs; - size_t max_avail_gather; - int wqe_shift; - void (*event) (struct mlx5_core_srq *, enum mlx5_event); - - atomic_t refcount; - struct completion free; - u16 uid; -}; - struct mlx5_uars_page { void __iomem *map; bool wc; @@ -464,14 +449,6 @@ struct mlx5_qp_table { struct radix_tree_root tree; }; -struct mlx5_srq_table { - struct notifier_block nb; - /* protect radix tree - */ - spinlock_t lock; - struct radix_tree_root tree; -}; - struct mlx5_mkey_table { /* protect radix tree */ @@ -547,8 +524,6 @@ struct mlx5_priv { struct mlx5_core_health health; - struct mlx5_srq_table srq_table; - /* start: qp staff */ struct mlx5_qp_table qp_table; struct dentry *qp_debugfs; diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h deleted file mode 100644 index 9343306cd188..000000000000 --- a/include/linux/mlx5/srq.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* - * Copyright (c) 2013-2018, Mellanox Technologies. All rights reserved. - */ - -#ifndef MLX5_SRQ_H -#define MLX5_SRQ_H - -struct mlx5_core_dev; - -void mlx5_init_srq_table(struct mlx5_core_dev *dev); -void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev); - -#endif /* MLX5_SRQ_H */ -- cgit v1.2.3 From 9d43faac02e3a4a26171f96f4de69fa650d3b6f6 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 26 Nov 2018 08:28:32 +0200 Subject: net/mlx5: Update mlx5_ifc with DEVX UCTX capabilities bits Expose device capabilities for DEVX user context, it includes which caps the device is supported and a matching bit to set as part of user context creation. Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6f64e814cc10..ece1b606c909 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -883,6 +883,10 @@ enum { MLX5_CAP_UMR_FENCE_NONE = 0x2, }; +enum { + MLX5_UCTX_CAP_RAW_TX = 1UL << 0, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1193,7 +1197,13 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 num_vhca_ports[0x8]; u8 reserved_at_618[0x6]; u8 sw_owner_id[0x1]; - u8 reserved_at_61f[0x1e1]; + u8 reserved_at_61f[0x1]; + + u8 reserved_at_620[0x80]; + + u8 uctx_cap[0x20]; + + u8 reserved_at_6c0[0x140]; }; enum mlx5_flow_destination_type { @@ -9276,7 +9286,9 @@ struct mlx5_ifc_umem_bits { struct mlx5_ifc_uctx_bits { u8 modify_field_select[0x40]; - u8 reserved_at_40[0x1c0]; + u8 cap[0x20]; + + u8 reserved_at_60[0x1a0]; }; struct mlx5_ifc_create_umem_in_bits { -- cgit v1.2.3 From 875e8939953483d856de226b72d14c6a000f9457 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 4 Dec 2018 08:15:10 +0000 Subject: skbuff: Rename 'offload_mr_fwd_mark' to 'offload_l3_fwd_mark' Commit abf4bb6b63d0 ("skbuff: Add the offload_mr_fwd_mark field") added the 'offload_mr_fwd_mark' field to indicate that a packet has already undergone L3 multicast routing by a capable device. The field is used to prevent the kernel from forwarding a packet through a netdev through which the device has already forwarded the packet. Currently, no unicast packet is routed by both the device and the kernel, but this is about to change by subsequent patches and we need to be able to mark such packets, so that they will no be forwarded twice. Instead of adding yet another field to 'struct sk_buff', we can just rename 'offload_mr_fwd_mark' to 'offload_l3_fwd_mark', as a packet either has a multicast or a unicast destination IP. While at it, add a comment about both 'offload_fwd_mark' and 'offload_l3_fwd_mark'. Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 75d50ab7997c..b1831a5ca173 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -616,6 +616,8 @@ typedef unsigned char *sk_buff_data_t; * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @offload_fwd_mark: Packet was L2-forwarded in hardware + * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @tc_redirected: packet was redirected by a tc action @@ -799,7 +801,7 @@ struct sk_buff { __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; - __u8 offload_mr_fwd_mark:1; + __u8 offload_l3_fwd_mark:1; #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; -- cgit v1.2.3 From b3ed2ce024c36054e51cca2eb31a1cdbe4a5f11e Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 4 Dec 2018 10:31:11 -0800 Subject: acpi/nfit: Add support for Intel DSM 1.8 commands Add command definition for security commands defined in Intel DSM specification v1.8 [1]. This includes "get security state", "set passphrase", "unlock unit", "freeze lock", "secure erase", "overwrite", "overwrite query", "master passphrase enable/disable", and "master erase", . Since this adds several Intel definitions, move the relevant bits to their own header. These commands mutate physical data, but that manipulation is not cache coherent. The requirement to flush and invalidate caches makes these commands unsuitable to be called from userspace, so extra logic is added to detect and block these commands from being submitted via the ioctl command submission path. Lastly, the commands may contain sensitive key material that should not be dumped in a standard debug session. Update the nvdimm-command payload-dump facility to move security command payloads behind a default-off compile time switch. [1]: http://pmem.io/documents/NVDIMM_DSM_Interface-V1.8.pdf Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 097072c5a852..472171af7f60 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -87,7 +87,7 @@ struct nvdimm_bus_descriptor { ndctl_fn ndctl; int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc); int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc, - struct nvdimm *nvdimm, unsigned int cmd); + struct nvdimm *nvdimm, unsigned int cmd, void *data); }; struct nd_cmd_desc { -- cgit v1.2.3 From e20ba6e1da029136ded295f33076483d65ddf50a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 2 Dec 2018 17:46:16 +0100 Subject: block: move queues types to the block layer Having another indirect all in the fast path doesn't really help in our post-spectre world. Also having too many queue type is just going to create confusion, so I'd rather manage them centrally. Note that the queue type naming and ordering changes a bit - the first index now is the default queue for everything not explicitly marked, the optional ones are read and poll queues. Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 467f1dd21ccf..57eda7b20243 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -81,8 +81,12 @@ struct blk_mq_queue_map { unsigned int queue_offset; }; -enum { - HCTX_MAX_TYPES = 3, +enum hctx_type { + HCTX_TYPE_DEFAULT, /* all I/O not otherwise accounted for */ + HCTX_TYPE_READ, /* just for READ I/O */ + HCTX_TYPE_POLL, /* polled I/O of any kind */ + + HCTX_MAX_TYPES, }; struct blk_mq_tag_set { @@ -118,8 +122,6 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *); -/* takes rq->cmd_flags as input, returns a hardware type index */ -typedef int (rq_flags_to_type_fn)(struct request_queue *, unsigned int); typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *); typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); @@ -154,11 +156,6 @@ struct blk_mq_ops { */ commit_rqs_fn *commit_rqs; - /* - * Return a queue map type for the given request/bio flags - */ - rq_flags_to_type_fn *rq_flags_to_type; - /* * Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the -- cgit v1.2.3 From 529262d56dbebe6a26df5d2fd24cc0e1bc8579e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 2 Dec 2018 17:46:26 +0100 Subject: block: remove ->poll_fn This was intended to support users like nvme multipath, but is just getting in the way and adding another indirect call. Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 08d940f85fa0..0b3874bdbc6a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -283,7 +283,6 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); -typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t, bool spin); struct bio_vec; typedef int (dma_drain_needed_fn)(struct request *); @@ -401,7 +400,6 @@ struct request_queue { struct rq_qos *rq_qos; make_request_fn *make_request_fn; - poll_q_fn *poll_fn; dma_drain_needed_fn *dma_drain_needed; const struct blk_mq_ops *mq_ops; -- cgit v1.2.3 From 719598c98d1961e78e2ad514a2cc15deb5e41db5 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 26 Nov 2018 08:28:37 +0200 Subject: IB/mlx5: Update the supported DEVX commands Update the supported DEVX commands, it includes adding to the query/modify command's list and to the encoding handling. In addition, a valid range for general commands was added to be used for future commands. Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ece1b606c909..171d68663640 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -144,6 +144,9 @@ enum { MLX5_CMD_OP_DESTROY_XRQ = 0x718, MLX5_CMD_OP_QUERY_XRQ = 0x719, MLX5_CMD_OP_ARM_XRQ = 0x71a, + MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY = 0x725, + MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY = 0x726, + MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS = 0x727, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT = 0x752, @@ -245,6 +248,7 @@ enum { MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c, MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT = 0x93d, MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT = 0x93e, + MLX5_CMD_OP_QUERY_PACKET_REFORMAT_CONTEXT = 0x93f, MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT = 0x942, @@ -260,6 +264,12 @@ enum { MLX5_CMD_OP_MAX }; +/* Valid range for general commands that don't work over an object */ +enum { + MLX5_CMD_OP_GENERAL_START = 0xb00, + MLX5_CMD_OP_GENERAL_END = 0xd00, +}; + struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_dmac[0x1]; u8 outer_smac[0x1]; -- cgit v1.2.3 From 27359fd6e5f3c5db8fe544b63238b6170e8806d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 30 Nov 2018 11:05:06 -0500 Subject: dax: Fix unlock mismatch with updated API Internal to dax_unlock_mapping_entry(), dax_unlock_entry() is used to store a replacement entry in the Xarray at the given xas-index with the DAX_LOCKED bit clear. When called, dax_unlock_entry() expects the unlocked value of the entry relative to the current Xarray state to be specified. In most contexts dax_unlock_entry() is operating in the same scope as the matched dax_lock_entry(). However, in the dax_unlock_mapping_entry() case the implementation needs to recall the original entry. In the case where the original entry is a 'pmd' entry it is possible that the pfn performed to do the lookup is misaligned to the value retrieved in the Xarray. Change the api to return the unlock cookie from dax_lock_page() and pass it to dax_unlock_page(). This fixes a bug where dax_unlock_page() was assuming that the page was PMD-aligned if the entry was a PMD entry with signatures like: WARNING: CPU: 38 PID: 1396 at fs/dax.c:340 dax_insert_entry+0x2b2/0x2d0 RIP: 0010:dax_insert_entry+0x2b2/0x2d0 [..] Call Trace: dax_iomap_pte_fault.isra.41+0x791/0xde0 ext4_dax_huge_fault+0x16f/0x1f0 ? up_read+0x1c/0xa0 __do_fault+0x1f/0x160 __handle_mm_fault+0x1033/0x1490 handle_mm_fault+0x18b/0x3d0 Link: https://lkml.kernel.org/r/20181130154902.GL10377@bombadil.infradead.org Fixes: 9f32d221301c ("dax: Convert dax_lock_mapping_entry to XArray") Reported-by: Dan Williams Signed-off-by: Matthew Wilcox Tested-by: Dan Williams Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- include/linux/dax.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 450b28db9533..0dd316a74a29 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,6 +7,8 @@ #include #include +typedef unsigned long dax_entry_t; + struct iomap_ops; struct dax_device; struct dax_operations { @@ -88,8 +90,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); -bool dax_lock_mapping_entry(struct page *page); -void dax_unlock_mapping_entry(struct page *page); +dax_entry_t dax_lock_page(struct page *page); +void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) @@ -122,14 +124,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping, return -EOPNOTSUPP; } -static inline bool dax_lock_mapping_entry(struct page *page) +static inline dax_entry_t dax_lock_page(struct page *page) { if (IS_DAX(page->mapping->host)) - return true; - return false; + return ~0UL; + return 0; } -static inline void dax_unlock_mapping_entry(struct page *page) +static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } #endif -- cgit v1.2.3 From 770399df90b6e43bd086653f0a35888dca056576 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Tue, 6 Nov 2018 13:01:36 +0800 Subject: dmaengine: sprd: Support DMA 2-stage transfer mode The Spreadtrum DMA controller supports channel 2-stage tansfer mode, that means we can request 2 dma channels, one for source channel, and another one for destination channel. Once the source channel's transaction is done, it will trigger the destination channel's transaction automatically by hardware signal. Signed-off-by: Eric Long Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- include/linux/dma/sprd-dma.h | 62 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 59 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h index b42b80e52cc2..ab82df64682a 100644 --- a/include/linux/dma/sprd-dma.h +++ b/include/linux/dma/sprd-dma.h @@ -3,9 +3,65 @@ #ifndef _SPRD_DMA_H_ #define _SPRD_DMA_H_ -#define SPRD_DMA_REQ_SHIFT 16 -#define SPRD_DMA_FLAGS(req_mode, int_type) \ - ((req_mode) << SPRD_DMA_REQ_SHIFT | (int_type)) +#define SPRD_DMA_REQ_SHIFT 8 +#define SPRD_DMA_TRG_MODE_SHIFT 16 +#define SPRD_DMA_CHN_MODE_SHIFT 24 +#define SPRD_DMA_FLAGS(chn_mode, trg_mode, req_mode, int_type) \ + ((chn_mode) << SPRD_DMA_CHN_MODE_SHIFT | \ + (trg_mode) << SPRD_DMA_TRG_MODE_SHIFT | \ + (req_mode) << SPRD_DMA_REQ_SHIFT | (int_type)) + +/* + * The Spreadtrum DMA controller supports channel 2-stage tansfer, that means + * we can request 2 dma channels, one for source channel, and another one for + * destination channel. Each channel is independent, and has its own + * configurations. Once the source channel's transaction is done, it will + * trigger the destination channel's transaction automatically by hardware + * signal. + * + * To support 2-stage tansfer, we must configure the channel mode and trigger + * mode as below definition. + */ + +/* + * enum sprd_dma_chn_mode: define the DMA channel mode for 2-stage transfer + * @SPRD_DMA_CHN_MODE_NONE: No channel mode setting which means channel doesn't + * support the 2-stage transfer. + * @SPRD_DMA_SRC_CHN0: Channel used as source channel 0. + * @SPRD_DMA_SRC_CHN1: Channel used as source channel 1. + * @SPRD_DMA_DST_CHN0: Channel used as destination channel 0. + * @SPRD_DMA_DST_CHN1: Channel used as destination channel 1. + * + * Now the DMA controller can supports 2 groups 2-stage transfer. + */ +enum sprd_dma_chn_mode { + SPRD_DMA_CHN_MODE_NONE, + SPRD_DMA_SRC_CHN0, + SPRD_DMA_SRC_CHN1, + SPRD_DMA_DST_CHN0, + SPRD_DMA_DST_CHN1, +}; + +/* + * enum sprd_dma_trg_mode: define the DMA channel trigger mode for 2-stage + * transfer + * @SPRD_DMA_NO_TRG: No trigger setting. + * @SPRD_DMA_FRAG_DONE_TRG: Trigger the transaction of destination channel + * automatically once the source channel's fragment request is done. + * @SPRD_DMA_BLOCK_DONE_TRG: Trigger the transaction of destination channel + * automatically once the source channel's block request is done. + * @SPRD_DMA_TRANS_DONE_TRG: Trigger the transaction of destination channel + * automatically once the source channel's transfer request is done. + * @SPRD_DMA_LIST_DONE_TRG: Trigger the transaction of destination channel + * automatically once the source channel's link-list request is done. + */ +enum sprd_dma_trg_mode { + SPRD_DMA_NO_TRG, + SPRD_DMA_FRAG_DONE_TRG, + SPRD_DMA_BLOCK_DONE_TRG, + SPRD_DMA_TRANS_DONE_TRG, + SPRD_DMA_LIST_DONE_TRG, +}; /* * enum sprd_dma_req_mode: define the DMA request mode -- cgit v1.2.3 From 617654aae50eb59dd98aa53fb562e850937f4cde Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 16 Aug 2018 12:28:48 +0300 Subject: PCI / ACPI: Identify untrusted PCI devices A malicious PCI device may use DMA to attack the system. An external Thunderbolt port is a convenient point to attach such a device. The OS may use IOMMU to defend against DMA attacks. Some BIOSes mark these externally facing root ports with this ACPI _DSD [1]: Name (_DSD, Package () { ToUUID ("efcc06cc-73ac-4bc3-bff0-76143807c389"), Package () { Package () {"ExternalFacingPort", 1}, Package () {"UID", 0 } } }) If we find such a root port, mark it and all its children as untrusted. The rest of the OS may use this information to enable DMA protection against malicious devices. For instance the device may be put behind an IOMMU to keep it from accessing memory outside of what the driver has allocated for it. While at it, add a comment on top of prp_guids array explaining the possible caveat resulting when these GUIDs are treated equivalent. [1] https://docs.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports#identifying-externally-exposed-pcie-root-ports Signed-off-by: Mika Westerberg Acked-by: Rafael J. Wysocki Acked-by: Bjorn Helgaas --- include/linux/pci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 11c71c4ecf75..c786a2f27bee 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -396,6 +396,14 @@ struct pci_dev { unsigned int is_hotplug_bridge:1; unsigned int shpc_managed:1; /* SHPC owned by shpchp */ unsigned int is_thunderbolt:1; /* Thunderbolt controller */ + /* + * Devices marked being untrusted are the ones that can potentially + * execute DMA attacks and similar. They are typically connected + * through external ports such as Thunderbolt but not limited to + * that. When an IOMMU is enabled they should be getting full + * mappings to make sure they cannot access arbitrary memory. + */ + unsigned int untrusted:1; unsigned int __aer_firmware_first_valid:1; unsigned int __aer_firmware_first:1; unsigned int broken_intx_masking:1; /* INTx masking can't be used */ -- cgit v1.2.3 From 89a6079df791aeace2044ea93be1b397195824ec Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 23 Oct 2018 15:45:01 +0800 Subject: iommu/vt-d: Force IOMMU on for platform opt in hint Intel VT-d spec added a new DMA_CTRL_PLATFORM_OPT_IN_FLAG flag in DMAR ACPI table [1] for BIOS to report compliance about platform initiated DMA restricted to RMRR ranges when transferring control to the OS. This means that during OS boot, before it enables IOMMU none of the connected devices can bypass DMA protection for instance by overwriting the data structures used by the IOMMU. The OS also treats this as a hint that the IOMMU should be enabled to prevent DMA attacks from possible malicious devices. A use of this flag is Kernel DMA protection for Thunderbolt [2] which in practice means that IOMMU should be enabled for PCIe devices connected to the Thunderbolt ports. With IOMMU enabled for these devices, all DMA operations are limited in the range reserved for it, thus the DMA attacks are prevented. All these devices are enumerated in the PCI/PCIe module and marked with an untrusted flag. This forces IOMMU to be enabled if DMA_CTRL_PLATFORM_OPT_IN_FLAG is set in DMAR ACPI table and there are PCIe devices marked as untrusted in the system. This can be turned off by adding "intel_iommu=off" in the kernel command line, if any problems are found. [1] https://software.intel.com/sites/default/files/managed/c5/15/vt-directed-io-spec.pdf [2] https://docs.microsoft.com/en-us/windows/security/information-protection/kernel-dma-protection-for-thunderbolt Cc: Jacob Pan Cc: Sohil Mehta Signed-off-by: Lu Baolu Signed-off-by: Mika Westerberg Reviewed-by: Ashok Raj Reviewed-by: Joerg Roedel Acked-by: Joerg Roedel --- include/linux/dmar.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 843a41ba7e28..f8af1d770520 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -39,6 +39,7 @@ struct acpi_dmar_header; /* DMAR Flags */ #define DMAR_INTR_REMAP 0x1 #define DMAR_X2APIC_OPT_OUT 0x2 +#define DMAR_PLATFORM_OPT_IN 0x4 struct intel_iommu; @@ -170,6 +171,8 @@ static inline int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert) { return 0; } #endif /* CONFIG_IRQ_REMAP */ +extern bool dmar_platform_optin(void); + #else /* CONFIG_DMAR_TABLE */ static inline int dmar_device_add(void *handle) @@ -182,6 +185,11 @@ static inline int dmar_device_remove(void *handle) return 0; } +static inline bool dmar_platform_optin(void) +{ + return false; +} + #endif /* CONFIG_DMAR_TABLE */ struct irte { -- cgit v1.2.3 From 6b69753fa0078c5222d6b4aeb5017c5503e0dc8e Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Thu, 15 Nov 2018 19:03:21 -0800 Subject: usb: gadget: Introduce frame_number to usb_request Add a field frame_number to the usb_request to report the interval number in (micro)frames in which the isochronous transfer was transmitted or received. The gadget driver can use this knowledge to synchronize with the host. Also, this option is useful for debugging purposes. Signed-off-by: Thinh Nguyen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index e5cd84a0f84a..7595056b96c1 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -61,6 +61,8 @@ struct usb_ep; * invalidated by the error may first be dequeued. * @context: For use by the completion callback * @list: For use by the gadget driver. + * @frame_number: Reports the interval number in (micro)frame in which the + * isochronous transfer was transmitted or received. * @status: Reports completion code, zero or a negative errno. * Normally, faults block the transfer queue from advancing until * the completion callback returns. @@ -112,6 +114,8 @@ struct usb_request { void *context; struct list_head list; + unsigned frame_number; /* ISO ONLY */ + int status; unsigned actual; }; -- cgit v1.2.3 From f51ccf46217c28758b1f3b5bc0ccfc00eca658b2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Dec 2018 17:00:36 +0100 Subject: USB: serial: console: fix reported terminal settings The USB-serial console implementation has never reported the actual terminal settings used. Despite storing the corresponding cflags in its struct console, these were never honoured on later tty open() where the tty termios would be left initialised to the driver defaults. Unlike the serial console implementation, the USB-serial code calls subdriver open() already at console setup. While calling set_termios() and write() before open() looks like it could work for some USB-serial drivers, others definitely do not expect this, so modelling this after serial core is going to be intrusive, if at all possible. Instead, use a (renamed) tty helper to save the termios data used at console setup so that the tty termios reflects the actual terminal settings after a subsequent tty open(). Note that the calls to tty_init_termios() (tty_driver_install()) and tty_save_termios() are serialised using the disconnect mutex. This specifically fixes a regression that was triggered by a recent change adding software flow control to the pl2303 driver: a getty trying to disable flow control while leaving the baud rate unchanged would now also set the baud rate to the driver default (prior to the flow-control change this had been a noop). Fixes: 7041d9c3f01b ("USB: serial: pl2303: add support for tx xon/xoff flow control") Cc: stable # 4.18 Cc: Florian Zumbiehl Reported-by: Jarkko Nikula Tested-by: Jarkko Nikula Acked-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 414db2bce715..392138fe59b6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -556,6 +556,7 @@ extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); extern void tty_release_struct(struct tty_struct *tty, int idx); extern int tty_release(struct inode *inode, struct file *filp); extern void tty_init_termios(struct tty_struct *tty); +extern void tty_save_termios(struct tty_struct *tty); extern int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); -- cgit v1.2.3 From c96cf923a98d1b094df9f0cf97a83e118817e31b Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Thu, 1 Nov 2018 00:24:48 +0000 Subject: tty: Don't block on IO when ldisc change is pending There might be situations where tty_ldisc_lock() has blocked, but there is already IO on tty and it prevents line discipline changes. It might theoretically turn into dead-lock. Basically, provide more priority to pending tty_ldisc_lock() than to servicing reads/writes over tty. User-visible issue was reported by Mikulas where on pa-risc with Debian 5 reboot took either 80 seconds, 3 minutes or 3:25 after proper locking in tty_reopen(). Cc: Jiri Slaby Reported-by: Mikulas Patocka Signed-off-by: Dmitry Safonov Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 414db2bce715..80ae5528ef8e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -366,6 +366,7 @@ struct tty_file_private { #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ #define TTY_HUPPED 18 /* Post driver->hangup() */ #define TTY_HUPPING 19 /* Hangup in progress */ +#define TTY_LDISC_CHANGING 20 /* Change pending - non-block IO */ #define TTY_LDISC_HALTED 22 /* Line discipline is halted */ /* Values for tty->flow_change */ @@ -383,6 +384,12 @@ static inline void tty_set_flow_change(struct tty_struct *tty, int val) smp_mb(); } +static inline bool tty_io_nonblock(struct tty_struct *tty, struct file *file) +{ + return file->f_flags & O_NONBLOCK || + test_bit(TTY_LDISC_CHANGING, &tty->flags); +} + static inline bool tty_io_error(struct tty_struct *tty) { return test_bit(TTY_IO_ERROR, &tty->flags); -- cgit v1.2.3 From 2fc00c1e0f9d2abe0df74c33cf9f40d12b9b892f Mon Sep 17 00:00:00 2001 From: Chris Chiu Date: Mon, 3 Dec 2018 14:46:20 +0800 Subject: HID: use macros in IS_INPUT_APPLICATION Add missing definition for HID_DG_WHITEBOARD then replace the hid usage hex with macros for better readibility. Signed-off-by: Chris Chiu Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index a355d61940f2..ce5f996c8d3d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -238,6 +238,7 @@ struct hid_item { #define HID_DG_LIGHTPEN 0x000d0003 #define HID_DG_TOUCHSCREEN 0x000d0004 #define HID_DG_TOUCHPAD 0x000d0005 +#define HID_DG_WHITEBOARD 0x000d0006 #define HID_DG_STYLUS 0x000d0020 #define HID_DG_PUCK 0x000d0021 #define HID_DG_FINGER 0x000d0022 @@ -836,7 +837,10 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev, /* Applications from HID Usage Tables 4/8/99 Version 1.1 */ /* We ignore a few input applications that are not widely used */ -#define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001) || ((a >= 0x000d0002) && (a <= 0x000d0006))) +#define IS_INPUT_APPLICATION(a) \ + (((a >= HID_UP_GENDESK) && (a <= HID_GD_MULTIAXIS)) \ + || ((a >= HID_DG_PEN) && (a <= HID_DG_WHITEBOARD)) \ + || (a == HID_GD_SYSTEM_CONTROL) || (a == HID_CP_CONSUMER_CONTROL)) /* HID core API */ -- cgit v1.2.3 From 7f5592742a429b4de770fc5b796d18de43a15fdc Mon Sep 17 00:00:00 2001 From: Chris Chiu Date: Mon, 3 Dec 2018 14:46:21 +0800 Subject: HID: input: support Microsoft wireless radio control hotkey The ASUS laptops start to support the airplane mode radio management to replace the original mechanism of airplane mode toggle hotkey. On the ASUS P5440FF, it presents as a HID device connecting via I2C, named i2c-AMPD0001. When pressing it, the Embedded Controller send hid report via I2C and switch the airplane mode indicator LED based on the status. However, it's not working because it fails to be identified as a hidinput device. It fails in hidinput_connect() due to the macro IS_INPUT_APPLICATION doesn't have HID_GD_WIRELESS_RADIO_CTLS as a legit application code. It's easy to add the HID I2C vendor and product id to the quirk list and apply HID_QUIRK_HIDINPUT_FORCE to make it work. But it makes more sense to support it as a generic input application. Signed-off-by: Chris Chiu Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index ce5f996c8d3d..42079116fb61 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -840,7 +840,8 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev, #define IS_INPUT_APPLICATION(a) \ (((a >= HID_UP_GENDESK) && (a <= HID_GD_MULTIAXIS)) \ || ((a >= HID_DG_PEN) && (a <= HID_DG_WHITEBOARD)) \ - || (a == HID_GD_SYSTEM_CONTROL) || (a == HID_CP_CONSUMER_CONTROL)) + || (a == HID_GD_SYSTEM_CONTROL) || (a == HID_CP_CONSUMER_CONTROL) \ + || (a == HID_GD_WIRELESS_RADIO_CTLS)) /* HID core API */ -- cgit v1.2.3 From 51eb78098ab79bba8b1df24da2304e61deb74629 Mon Sep 17 00:00:00 2001 From: tom Date: Tue, 4 Dec 2018 18:27:34 +0000 Subject: iommu: Change tlb_range_add to iotlb_range_add and tlb_sync to iotlb_sync Someone forgot to update this comment. Signed-off-by: Tom Murphy Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a1d28f42cb77..11db18b9ffe8 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -168,8 +168,8 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain - * @tlb_range_add: Add a given iova range to the flush queue for this domain - * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush + * @iotlb_range_add: Add a given iova range to the flush queue for this domain + * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping -- cgit v1.2.3 From 7693b5643fd2d682de90733b67fc8032b9646911 Mon Sep 17 00:00:00 2001 From: Oskari Lemmela Date: Tue, 20 Nov 2018 19:52:09 +0200 Subject: power: supply: add AC power supply driver for AXP813 AXP813 and AXP803 PMICs can control input current and minimum voltage. Both of these values are configurable. Signed-off-by: Oskari Lemmela Reviewed-by: Quentin Schulz Reviewed-by: Chen-Yu Tsai Acked-by: Lee Jones Signed-off-by: Sebastian Reichel --- include/linux/mfd/axp20x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 517e60eecbcb..2302b620d238 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -266,6 +266,7 @@ enum axp20x_variants { #define AXP288_RT_BATT_V_H 0xa0 #define AXP288_RT_BATT_V_L 0xa1 +#define AXP813_ACIN_PATH_CTRL 0x3a #define AXP813_ADC_RATE 0x85 /* Fuel Gauge */ -- cgit v1.2.3 From 704620afc70cf47abb9d6a1a57f3825d2bca49cf Mon Sep 17 00:00:00 2001 From: Mathias Payer Date: Wed, 5 Dec 2018 21:19:59 +0100 Subject: USB: check usb_get_extra_descriptor for proper size When reading an extra descriptor, we need to properly check the minimum and maximum size allowed, to prevent from invalid data being sent by a device. Reported-by: Hui Peng Reported-by: Mathias Payer Co-developed-by: Linus Torvalds Signed-off-by: Hui Peng Signed-off-by: Mathias Payer Signed-off-by: Linus Torvalds Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 4cdd515a4385..5e49e82c4368 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -407,11 +407,11 @@ struct usb_host_bos { }; int __usb_get_extra_descriptor(char *buffer, unsigned size, - unsigned char type, void **ptr); + unsigned char type, void **ptr, size_t min); #define usb_get_extra_descriptor(ifpoint, type, ptr) \ __usb_get_extra_descriptor((ifpoint)->extra, \ (ifpoint)->extralen, \ - type, (void **)ptr) + type, (void **)ptr, sizeof(**(ptr))) /* ----------------------------------------------------------------------- */ -- cgit v1.2.3 From 16ad9501b1f2edebe24f8cf3c09da0695871986b Mon Sep 17 00:00:00 2001 From: Jonathan Marek Date: Wed, 21 Nov 2018 21:32:25 -0500 Subject: firmware: qcom: scm: fix compilation error when disabled This fixes the case when CONFIG_QCOM_SCM is not enabled, and linux/errno.h has not been included previously. Signed-off-by: Jonathan Marek Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom_scm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 06996ad4f2bc..1637385bcc17 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -67,6 +67,9 @@ extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val); extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); #else + +#include + static inline int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus) { -- cgit v1.2.3 From 2f0799a0ffc033bf3cc82d5032acc3ec633464c2 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 5 Dec 2018 15:45:54 -0800 Subject: mm, thp: restore node-local hugepage allocations This is a full revert of ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") and a partial revert of 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). By not setting __GFP_THISNODE, applications can allocate remote hugepages when the local node is fragmented or low on memory when either the thp defrag setting is "always" or the vma has been madvised with MADV_HUGEPAGE. Remote access to hugepages often has much higher latency than local pages of the native page size. On Haswell, ac5b2c18911f was shown to have a 13.9% access regression after this commit for binaries that remap their text segment to be backed by transparent hugepages. The intent of ac5b2c18911f is to address an issue where a local node is low on memory or fragmented such that a hugepage cannot be allocated. In every scenario where this was described as a fix, there is abundant and unfragmented remote memory available to allocate from, even with a greater access latency. If remote memory is also low or fragmented, not setting __GFP_THISNODE was also measured on Haswell to have a 40% regression in allocation latency. Restore __GFP_THISNODE for thp allocations. Fixes: ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Vlastimil Babka Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index bac395f1d00a..5228c62af416 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,8 +139,6 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); -struct mempolicy *get_vma_policy(struct vm_area_struct *vma, - unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); -- cgit v1.2.3 From 5f15eed245bc6d7c82d44f0ebcaf62071a9d55bd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 5 Dec 2018 21:49:40 +0100 Subject: net: mii: Fix autoneg in mii_lpa_to_linkmode_lpa_t() mii_adv_to_linkmode_adv_t() clears all bits before setting it needs to set. This means the freshly set Autoneg gets cleared. Change the order, and add comments about it clearing the old content of the bitmap. Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode") Reported-by: Heiner Kallweit Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index fb7ae4ae8ce3..57365224306c 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -378,7 +378,8 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) * @adv: value of the MII_ADVERTISE register * * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings. + * to linkmode advertisement settings. Clears the old value + * of advertising. */ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, u32 adv) @@ -408,16 +409,18 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, * @adv: value of the MII_LPA register * * A small helper function that translates MII_LPA bits, when in - * 1000Base-T mode, to linkmode LP advertisement settings. + * 1000Base-T mode, to linkmode LP advertisement settings. Clears the + * old value of advertising */ static inline void mii_lpa_to_linkmode_lpa_t(unsigned long *lp_advertising, u32 lpa) { + mii_adv_to_linkmode_adv_t(lp_advertising, lpa); + if (lpa & LPA_LPACK) linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, lp_advertising); - mii_adv_to_linkmode_adv_t(lp_advertising, lpa); } /** -- cgit v1.2.3 From 78a24df370072ea3b7c0a466efd776fc8f87c73a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 5 Dec 2018 21:49:41 +0100 Subject: net: mii: Rename mii_stat1000_to_linkmode_lpa_t Rename mii_stat1000_to_linkmode_lpa_t to mii_stat1000_mod_linkmode_lpa_t to indicate it modifies the passed linkmode bitmap, without clearing any other bits. Add a helper to set/clear bits in a linkmode. Use this helper to ensure bit are clear which the stat1000 indicates should not be set. Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode") Suggested-by: Heiner Kallweit Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/linkmode.h | 9 +++++++++ include/linux/mii.h | 20 ++++++++++---------- 2 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 22443d7fb5cd..a99c58866860 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -57,6 +57,15 @@ static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) __clear_bit(nr, addr); } +static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, + int set) +{ + if (set) + linkmode_set_bit(nr, addr); + else + linkmode_clear_bit(nr, addr); +} + static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) { __change_bit(nr, addr); diff --git a/include/linux/mii.h b/include/linux/mii.h index 57365224306c..b915ef6c3692 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -288,22 +288,22 @@ static inline u32 mii_stat1000_to_ethtool_lpa_t(u32 lpa) } /** - * mii_stat1000_to_linkmode_lpa_t + * mii_stat1000_mod_linkmode_lpa_t * @advertising: target the linkmode advertisement settings * @adv: value of the MII_STAT1000 register * * A small helper function that translates MII_STAT1000 bits, when in - * 1000Base-T mode, to linkmode advertisement settings. + * 1000Base-T mode, to linkmode advertisement settings. Other bits in + * advertising are not changes. */ -static inline void mii_stat1000_to_linkmode_lpa_t(unsigned long *advertising, - u32 lpa) +static inline void mii_stat1000_mod_linkmode_lpa_t(unsigned long *advertising, + u32 lpa) { - if (lpa & LPA_1000HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - advertising); - if (lpa & LPA_1000FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - advertising); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + advertising, lpa & LPA_1000HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + advertising, lpa & LPA_1000FULL); } /** -- cgit v1.2.3 From d3351931a37bdb329b5ea761424579fa91c866ee Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 5 Dec 2018 21:49:43 +0100 Subject: net: mii: Add mii_lpa_mod_linkmode_lpa_t Add a _mod_ variant of mii_lpa_to_linkmode_lpa_t. Use this to fix the genphy_read_status() where the 1G link partner features are getting lost. Fixes: c0ec3c273677 ("net: phy: Convert u32 phydev->lp_advertising to linkmode") Reported-by: Heiner Kallweit Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii.h | 68 ++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 52 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index b915ef6c3692..e72447778a08 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -372,6 +372,36 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) return result | mii_adv_to_ethtool_adv_x(lpa); } +/** + * mii_adv_mod_linkmode_adv_t + * @advertising:pointer to destination link mode. + * @adv: value of the MII_ADVERTISE register + * + * A small helper function that translates MII_ADVERTISE bits to + * linkmode advertisement settings. Leaves other bits unchanged. + */ +static inline void mii_adv_mod_linkmode_adv_t(unsigned long *advertising, + u32 adv) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + advertising, adv & ADVERTISE_10HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + advertising, adv & ADVERTISE_10FULL); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + advertising, adv & ADVERTISE_100HALF); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + advertising, adv & ADVERTISE_100FULL); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising, + adv & ADVERTISE_PAUSE_CAP); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + advertising, adv & ADVERTISE_PAUSE_ASYM); +} + /** * mii_adv_to_linkmode_adv_t * @advertising:pointer to destination link mode. @@ -386,22 +416,7 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, { linkmode_zero(advertising); - if (adv & ADVERTISE_10HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - advertising); - if (adv & ADVERTISE_10FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - advertising); - if (adv & ADVERTISE_100HALF) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - advertising); - if (adv & ADVERTISE_100FULL) - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - advertising); - if (adv & ADVERTISE_PAUSE_CAP) - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising); - if (adv & ADVERTISE_PAUSE_ASYM) - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); + mii_adv_mod_linkmode_adv_t(advertising, adv); } /** @@ -423,6 +438,27 @@ static inline void mii_lpa_to_linkmode_lpa_t(unsigned long *lp_advertising, } +/** + * mii_lpa_mod_linkmode_lpa_t + * @adv: value of the MII_LPA register + * + * A small helper function that translates MII_LPA bits, when in + * 1000Base-T mode, to linkmode LP advertisement settings. Leaves + * other bits unchanged. + */ +static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising, + u32 lpa) +{ + mii_adv_mod_linkmode_adv_t(lp_advertising, lpa); + + if (lpa & LPA_LPACK) + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lp_advertising); + else + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lp_advertising); +} + /** * linkmode_adv_to_lcl_adv_t * @advertising:pointer to linkmode advertising -- cgit v1.2.3 From 6dbd0090f999c443763c0742b574da1ce189404c Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 5 Dec 2018 21:49:44 +0100 Subject: net: mii: mii_lpa_mod_linkmode_lpa_t: Make use of linkmode_mod_bit helper Replace the if else code structure with a call to the helper linkmode_mod_bit. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mii.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index e72447778a08..6fee8b1a4400 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -451,12 +451,8 @@ static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising, { mii_adv_mod_linkmode_adv_t(lp_advertising, lpa); - if (lpa & LPA_LPACK) - linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - lp_advertising); - else - linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - lp_advertising); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lp_advertising, lpa & LPA_LPACK); } /** -- cgit v1.2.3 From 186bddb28ff9f61250d1b33554321d0bf5d085f6 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Mon, 3 Dec 2018 13:44:35 -0300 Subject: kref/kobject: Improve documentation The current kref and kobject documentation may be insufficient to understand these common pitfalls regarding object lifetime and object releasing. Add a bit more documentation and improve the warnings seen by the user, pointing to the right piece of documentation. Also, it's important to understand that making fun of people publicly is not at all helpful, doesn't provide any value, and it's not a healthy way of encouraging developers to do better. "Mocking mercilessly" will, if anything, make developers feel bad and go away. This kind of behavior should not be encouraged or justified. Signed-off-by: Ezequiel Garcia Signed-off-by: Enric Balletbo i Serra Signed-off-by: Gustavo Padovan Signed-off-by: Matthias Brugger Acked-by: Daniel Vetter Acked-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- include/linux/kref.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kref.h b/include/linux/kref.h index 29220724bf1c..cb00a0268061 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -53,10 +53,7 @@ static inline void kref_get(struct kref *kref) * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree - * in as this function. If the caller does pass kfree to this - * function, you will be publicly mocked mercilessly by the kref - * maintainer, and anyone else who happens to notice it. You have - * been warned. + * in as this function. * * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this -- cgit v1.2.3 From 69c32972d59388c041268e8206e8eb1acff29b9a Mon Sep 17 00:00:00 2001 From: "Kulkarni, Ganapatrao" Date: Thu, 6 Dec 2018 11:51:31 +0000 Subject: drivers/perf: Add Cavium ThunderX2 SoC UNCORE PMU driver This patch adds a perf driver for the PMU UNCORE devices DDR4 Memory Controller(DMC) and Level 3 Cache(L3C). Each PMU supports up to 4 counters. All counters lack overflow interrupt and are sampled periodically. Reviewed-by: Suzuki K Poulose Signed-off-by: Ganapatrao Kulkarni [will: consistent enum cpuhp_state naming] Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d007a319dfd4..fd586d0301e7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -165,6 +165,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, + CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, -- cgit v1.2.3 From 55f3f7eab75c10d9b33d122670b5935ab64db50f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 26 Nov 2018 16:08:43 -0500 Subject: XArray: Add xa_cmpxchg_irq and xa_cmpxchg_bh These convenience wrappers match the other _irq and _bh wrappers we already have. It turns out I'd already open-coded xa_cmpxchg_irq() in the shmem code, so convert that. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 564892e19f8c..f492e21c4aa2 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -553,6 +553,60 @@ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, return curr; } +/** + * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_cmpxchg() except it disables softirqs + * while holding the array lock. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_bh(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock_bh(xa); + + return curr; +} + +/** + * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_cmpxchg() except it disables interrupts + * while holding the array lock. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_irq(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock_irq(xa); + + return curr; +} + /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. -- cgit v1.2.3 From 92a98a2b9f64a8b3c200a7709ceae04d09c39451 Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Thu, 15 Nov 2018 14:52:41 +0900 Subject: kexec_file: make kexec_image_post_load_cleanup_default() global Change this function from static to global so that arm64 can implement its own arch_kimage_file_post_load_cleanup() later using kexec_image_post_load_cleanup_default(). Signed-off-by: AKASHI Takahiro Acked-by: Dave Young Cc: Vivek Goyal Cc: Baoquan He Signed-off-by: Will Deacon --- include/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9e4e638fb505..49ab758f4d91 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -143,6 +143,7 @@ extern const struct kexec_file_ops * const kexec_file_loaders[]; int kexec_image_probe_default(struct kimage *image, void *buf, unsigned long buf_len); +int kexec_image_post_load_cleanup_default(struct kimage *image); /** * struct kexec_buf - parameters for finding a place for a buffer in memory -- cgit v1.2.3 From b6664ba42f1424d2768b605dd60cecc4428d9364 Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Thu, 15 Nov 2018 14:52:42 +0900 Subject: s390, kexec_file: drop arch_kexec_mem_walk() Since s390 already knows where to locate buffers, calling arch_kexec_mem_walk() has no sense. So we can just drop it as kbuf->mem indicates this while all other architectures sets it to 0 initially. This change is a preparatory work for the next patch, where all the variant memory walks, either on system resource or memblock, will be put in one common place so that it will satisfy all the architectures' need. Signed-off-by: AKASHI Takahiro Reviewed-by: Philipp Rudo Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Dave Young Cc: Vivek Goyal Cc: Baoquan He Signed-off-by: Will Deacon --- include/linux/kexec.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 49ab758f4d91..f378cb786f1b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -145,6 +145,14 @@ int kexec_image_probe_default(struct kimage *image, void *buf, unsigned long buf_len); int kexec_image_post_load_cleanup_default(struct kimage *image); +/* + * If kexec_buf.mem is set to this value, kexec_locate_mem_hole() + * will try to allocate free memory. Arch may overwrite it. + */ +#ifndef KEXEC_BUF_MEM_UNKNOWN +#define KEXEC_BUF_MEM_UNKNOWN 0 +#endif + /** * struct kexec_buf - parameters for finding a place for a buffer in memory * @image: kexec image in which memory to search. -- cgit v1.2.3 From 735c2f90e333b3d0adee52a8e7e855a0c0eca284 Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Thu, 15 Nov 2018 14:52:43 +0900 Subject: powerpc, kexec_file: factor out memblock-based arch_kexec_walk_mem() Memblock list is another source for usable system memory layout. So move powerpc's arch_kexec_walk_mem() to common code so that other memblock-based architectures, particularly arm64, can also utilise it. A moved function is now renamed to kexec_walk_memblock() and integrated into kexec_locate_mem_hole(), which will now be usable for all architectures with no need for overriding arch_kexec_walk_mem(). With this change, arch_kexec_walk_mem() need no longer be a weak function, and was now renamed to kexec_walk_resources(). Since powerpc doesn't support kdump in its kexec_file_load(), the current kexec_walk_memblock() won't work for kdump either in this form, this will be fixed in the next patch. Signed-off-by: AKASHI Takahiro Cc: "Eric W. Biederman" Acked-by: Dave Young Cc: Vivek Goyal Cc: Baoquan He Acked-by: James Morse Signed-off-by: Will Deacon --- include/linux/kexec.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index f378cb786f1b..d58d1f2fab10 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -192,8 +192,6 @@ int __weak arch_kexec_apply_relocations(struct purgatory_info *pi, const Elf_Shdr *relsec, const Elf_Shdr *symtab); -int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, - int (*func)(struct resource *, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); -- cgit v1.2.3 From 702ed5bb75306c030ab6598b24b56ba8d21a48dd Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Thu, 15 Nov 2018 14:52:53 +0900 Subject: include: pe.h: remove message[] from mz header definition message[] field won't be part of the definition of mz header. This change is crucial for enabling kexec_file_load on arm64 because arm64's "Image" binary, as in PE format, doesn't have any data for it and accordingly the following check in pefile_parse_binary() will fail: chkaddr(cursor, mz->peaddr, sizeof(*pe)); Signed-off-by: AKASHI Takahiro Reviewed-by: Ard Biesheuvel Cc: David Howells Cc: Vivek Goyal Cc: Herbert Xu Cc: David S. Miller Signed-off-by: Will Deacon --- include/linux/pe.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pe.h b/include/linux/pe.h index 143ce75be5f0..3482b18a48b5 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -166,7 +166,7 @@ struct mz_hdr { uint16_t oem_info; /* oem specific */ uint16_t reserved1[10]; /* reserved */ uint32_t peaddr; /* address of pe header */ - char message[64]; /* message to print */ + char message[]; /* message to print */ }; struct mz_reloc { -- cgit v1.2.3 From 16688453661b6d5159be558a1f8c1f54463a420f Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 30 Nov 2018 11:53:20 +0000 Subject: nvmem: add type attribute Add a type attribute so userspace is able to know how the data is stored as this can help taking the correct decision when selecting which device to use. This will also help program display the proper warnings when burning fuses for example. Signed-off-by: Alexandre Belloni Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 1e3283c2af77..00ff92571683 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -19,6 +19,20 @@ typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, void *val, size_t bytes); +enum nvmem_type { + NVMEM_TYPE_UNKNOWN = 0, + NVMEM_TYPE_EEPROM, + NVMEM_TYPE_OTP, + NVMEM_TYPE_BATTERY_BACKED, +}; + +static const char * const nvmem_type_str[] = { + [NVMEM_TYPE_UNKNOWN] = "Unknown", + [NVMEM_TYPE_EEPROM] = "EEPROM", + [NVMEM_TYPE_OTP] = "OTP", + [NVMEM_TYPE_BATTERY_BACKED] = "Battery backed", +}; + /** * struct nvmem_config - NVMEM device configuration * @@ -28,6 +42,7 @@ typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, * @owner: Pointer to exporter module. Used for refcounting. * @cells: Optional array of pre-defined NVMEM cells. * @ncells: Number of elements in cells. + * @type: Type of the nvmem storage * @read_only: Device is read-only. * @root_only: Device is accessibly to root only. * @reg_read: Callback to read data. @@ -51,6 +66,7 @@ struct nvmem_config { struct module *owner; const struct nvmem_cell_info *cells; int ncells; + enum nvmem_type type; bool read_only; bool root_only; nvmem_reg_read_t reg_read; -- cgit v1.2.3 From a8b44d5d2e38e94e4c20a3fba294c3375753b469 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 30 Nov 2018 11:53:24 +0000 Subject: nvmem: Move nvmem_type_str array to its only user Since we put static variable to a header file it's copied to each module that includes the header. But not all of them are actually using it. Move nvmem_type_str array to its only user to make a compiler happy: In file included from include/linux/rtc.h:18, from drivers/rtc/rtc-proc.c:15: include/linux/nvmem-provider.h:29:27: warning: 'nvmem_type_str' defined but not used [-Wunused-const-variable=] static const char * const nvmem_type_str[] = { ^~~~~~~~~~~~~~ Suggested-by: Alexandre Belloni Suggested-by: Joe Perches Cc: Srinivas Kandagatla Signed-off-by: Andy Shevchenko Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 00ff92571683..5b2dd0a987d2 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -26,13 +26,6 @@ enum nvmem_type { NVMEM_TYPE_BATTERY_BACKED, }; -static const char * const nvmem_type_str[] = { - [NVMEM_TYPE_UNKNOWN] = "Unknown", - [NVMEM_TYPE_EEPROM] = "EEPROM", - [NVMEM_TYPE_OTP] = "OTP", - [NVMEM_TYPE_BATTERY_BACKED] = "Battery backed", -}; - /** * struct nvmem_config - NVMEM device configuration * -- cgit v1.2.3 From 517f14d9cf3533d5ab4fded195ab6f80a92e378f Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 30 Nov 2018 11:53:25 +0000 Subject: nvmem: add new config option We want to add nvmem support for MTD. TI DaVinci is the first platform that will be using it, but only in non-DT mode. In order not to introduce any new interface to supporting of which we would have to commit - add a new config option that tells nvmem not to use the DT node of the parent device. This way we won't be creating nvmem devices corresponding with MTD partitions defined in device tree. By default MTD will set this new field to true. Once a set of bindings for MTD nvmem cells is agreed upon, we'll be able to remove this option. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 5b2dd0a987d2..fe051323be0a 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -38,6 +38,7 @@ enum nvmem_type { * @type: Type of the nvmem storage * @read_only: Device is read-only. * @root_only: Device is accessibly to root only. + * @no_of_node: Device should not use the parent's of_node even if it's !NULL. * @reg_read: Callback to read data. * @reg_write: Callback to write data. * @size: Device size. @@ -62,6 +63,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; int size; -- cgit v1.2.3 From c4dfa25ab307a277eafa7067cd927fbe4d9be4ba Mon Sep 17 00:00:00 2001 From: Alban Bedel Date: Tue, 13 Nov 2018 15:01:10 +0100 Subject: mtd: add support for reading MTD devices via the nvmem API Allow drivers that use the nvmem API to read data stored on MTD devices. For this the mtd devices are registered as read-only NVMEM providers. We don't support device tree systems for now. Signed-off-by: Alban Bedel [Bartosz: - include linux/nvmem-provider.h - set the name of the nvmem provider - set no_of_node to true in nvmem_config - don't check the return value of nvmem_unregister() - it cannot fail - tweaked the commit message] Signed-off-by: Bartosz Golaszewski Acked-by: Boris Brezillon Signed-off-by: Greg Kroah-Hartman --- include/linux/mtd/mtd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index cd0be91bdefa..545070c2ee64 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -341,6 +342,7 @@ struct mtd_info { struct device dev; int usecount; struct mtd_debug_info dbg; + struct nvmem_device *nvmem; }; int mtd_ooblayout_ecc(struct mtd_info *mtd, int section, -- cgit v1.2.3 From d693eb39f5f8500ac950378b010fba78452fcf14 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 15 Nov 2018 12:12:12 +0000 Subject: bus: fsl-mc: explicitly define the fsl_mc_command endianness Both the header and the command parameters of the fsl_mc_command are 64-bit little-endian words. Use the appropriate type to explicitly specify their endianness. Signed-off-by: Ioana Ciornei Reviewed-by: Laurentiu Tudor Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 9d3f668df7df..741f567253ef 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -210,8 +210,8 @@ struct mc_cmd_header { }; struct fsl_mc_command { - u64 header; - u64 params[MC_CMD_NUM_OF_PARAMS]; + __le64 header; + __le64 params[MC_CMD_NUM_OF_PARAMS]; }; enum mc_cmd_status { @@ -238,11 +238,11 @@ enum mc_cmd_status { /* Command completion flag */ #define MC_CMD_FLAG_INTR_DIS 0x01 -static inline u64 mc_encode_cmd_header(u16 cmd_id, - u32 cmd_flags, - u16 token) +static inline __le64 mc_encode_cmd_header(u16 cmd_id, + u32 cmd_flags, + u16 token) { - u64 header = 0; + __le64 header = 0; struct mc_cmd_header *hdr = (struct mc_cmd_header *)&header; hdr->cmd_id = cpu_to_le16(cmd_id); -- cgit v1.2.3 From 42ee3cae0ed38b6c04038bf851ea2496da2135bb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Nov 2018 18:52:35 +0100 Subject: dma-mapping: provide a generic DMA_MAPPING_ERROR Error handling of the dma_map_single and dma_map_page APIs is a little problematic at the moment, in that we use different encodings in the returned dma_addr_t to indicate an error. That means we require an additional indirect call to figure out if a dma mapping call returned an error, and a lot of boilerplate code to implement these semantics. Instead return the maximum addressable value as the error. As long as we don't allow mapping single-byte ranges with single-byte alignment this value can never be a valid return. Additionaly if drivers do not check the return value from the dma_map* routines this values means they will generally not be pointed to actual memory. Once the default value is added here we can start removing the various mapping_error methods and just rely on this generic check. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Acked-by: Russell King Acked-by: Linus Torvalds --- include/linux/dma-mapping.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1a0edcde7d14..f89d277cc8ed 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -133,6 +133,8 @@ struct dma_map_ops { u64 (*get_required_mask)(struct device *dev); }; +#define DMA_MAPPING_ERROR (~(dma_addr_t)0) + extern const struct dma_map_ops dma_direct_ops; extern const struct dma_map_ops dma_virt_ops; @@ -581,8 +583,11 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) const struct dma_map_ops *ops = get_dma_ops(dev); debug_dma_mapping_error(dev, dma_addr); + if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); + if (dma_addr == DMA_MAPPING_ERROR) + return 1; return 0; } -- cgit v1.2.3 From b0cbeae4944924640bf550b75487729a20204c14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Nov 2018 18:52:35 +0100 Subject: dma-direct: remove the mapping_error dma_map_ops method The dma-direct code already returns (~(dma_addr_t)0x0) on mapping failures, so we can switch over to returning DMA_MAPPING_ERROR and let the core dma-mapping code handle the rest. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/dma-direct.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 61b78f934f64..6e5a47ae7d64 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,8 +5,6 @@ #include #include -#define DIRECT_MAPPING_ERROR (~(dma_addr_t)0) - #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else @@ -76,5 +74,4 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); -int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr); #endif /* _LINUX_DMA_DIRECT_H */ -- cgit v1.2.3 From cad34be747b8a92146e71c8267f2c1d6794e34c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Nov 2018 19:35:19 +0100 Subject: iommu/dma-iommu: remove the mapping_error dma_map_ops method Return DMA_MAPPING_ERROR instead of 0 on a dma mapping failure and let the core dma-mapping code handle the rest. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/dma-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index e8ca5e654277..e760dc5d1fa8 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -69,7 +69,6 @@ dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs); -int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); /* The DMA API isn't _quite_ the whole story, though... */ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg); -- cgit v1.2.3 From 68c9ac1d1fd51233cfac15484c6153b90aaa4ca4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 4 Dec 2018 14:33:24 -0800 Subject: dma-mapping: remove the mapping_error dma_map_ops method No users left except for vmd which just forwards it. Signed-off-by: Christoph Hellwig Acked-by: Linus Torvalds --- include/linux/dma-mapping.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index f89d277cc8ed..f4ac26d5294a 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -128,7 +128,6 @@ struct dma_map_ops { enum dma_data_direction dir); void (*cache_sync)(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction); - int (*mapping_error)(struct device *dev, dma_addr_t dma_addr); int (*dma_supported)(struct device *dev, u64 mask); u64 (*get_required_mask)(struct device *dev); }; @@ -580,12 +579,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size, static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - const struct dma_map_ops *ops = get_dma_ops(dev); - debug_dma_mapping_error(dev, dma_addr); - if (ops->mapping_error) - return ops->mapping_error(dev, dma_addr); if (dma_addr == DMA_MAPPING_ERROR) return 1; return 0; -- cgit v1.2.3 From b14b9d25a3c707c85e7e31e15766a71365b52ab7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 30 Nov 2018 10:59:37 +0100 Subject: dma-mapping: return an error code from dma_mapping_error Currently dma_mapping_error returns a boolean as int, with 1 meaning error. This is rather unusual and many callers have to convert it to errno value. The callers are highly inconsistent with error codes ranging from -ENOMEM over -EIO, -EINVAL and -EFAULT ranging to -EAGAIN. Return -ENOMEM which seems to be what the largest number of callers convert it to, and which also matches the typical error case where we are out of resources. Signed-off-by: Christoph Hellwig Acked-by: Russell King Acked-by: Linus Torvalds --- include/linux/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index f4ac26d5294a..7799c2b27849 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -582,7 +582,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) debug_dma_mapping_error(dev, dma_addr); if (dma_addr == DMA_MAPPING_ERROR) - return 1; + return -ENOMEM; return 0; } -- cgit v1.2.3 From 7c703e54cc71df5baa962e24a5663d88173bba5c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 09:51:00 +0100 Subject: arch: switch the default on ARCH_HAS_SG_CHAIN These days architectures are mostly out of the business of dealing with struct scatterlist at all, unless they have architecture specific iommu drivers. Replace the ARCH_HAS_SG_CHAIN symbol with a ARCH_NO_SG_CHAIN one only enabled for architectures with horrible legacy iommu drivers like alpha and parisc, and conditionally for arm which wants to keep it disable for legacy platforms. Signed-off-by: Christoph Hellwig Reviewed-by: Palmer Dabbelt --- include/linux/scatterlist.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 093aa57120b0..b96f0d0b5b8f 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -324,10 +324,10 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, * Like SG_CHUNK_SIZE, but for archs that have sg chaining. This limit * is totally arbitrary, a setting of 2048 will get you at least 8mb ios. */ -#ifdef CONFIG_ARCH_HAS_SG_CHAIN -#define SG_MAX_SEGMENTS 2048 -#else +#ifdef CONFIG_ARCH_NO_SG_CHAIN #define SG_MAX_SEGMENTS SG_CHUNK_SIZE +#else +#define SG_MAX_SEGMENTS 2048 #endif #ifdef CONFIG_SG_POOL -- cgit v1.2.3 From ded653ccbec0335a78fa7a7aff3ec9870349fafb Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 19 Sep 2018 21:41:04 -0700 Subject: signal: Add set_user_sigmask() Refactor reading sigset from userspace and updating sigmask into an api. This is useful for versions of syscalls that pass in the sigmask and expect the current->sigmask to be changed during, and restored after, the execution of the syscall. With the advent of new y2038 syscalls in the subsequent patches, we add two more new versions of the syscalls (for pselect, ppoll, and io_pgetevents) in addition to the existing native and compat versions. Adding such an api reduces the logic that would need to be replicated otherwise. Note that the calls to sigprocmask() ignored the return value from the api as the function only returns an error on an invalid first argument that is hardcoded at these call sites. The updated logic uses set_current_blocked() instead. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 4 ++++ include/linux/signal.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 88720b443cd6..17c497b82690 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -169,6 +169,10 @@ typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; +int set_compat_user_sigmask(const compat_sigset_t __user *usigmask, + sigset_t *set, sigset_t *oldset, + size_t sigsetsize); + struct compat_sigaction { #ifndef __ARCH_HAS_IRIX_SIGACTION compat_uptr_t sa_handler; diff --git a/include/linux/signal.h b/include/linux/signal.h index f428e86f4800..ce14b951befb 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -273,6 +273,8 @@ extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); +extern int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set, + sigset_t *oldset, size_t sigsetsize); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -- cgit v1.2.3 From 854a6ed56839a40f6b5d02a2962f48841482eec4 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 19 Sep 2018 21:41:05 -0700 Subject: signal: Add restore_user_sigmask() Refactor the logic to restore the sigmask before the syscall returns into an api. This is useful for versions of syscalls that pass in the sigmask and expect the current->sigmask to be changed during the execution and restored after the execution of the syscall. With the advent of new y2038 syscalls in the subsequent patches, we add two more new versions of the syscalls (for pselect, ppoll and io_pgetevents) in addition to the existing native and compat versions. Adding such an api reduces the logic that would need to be replicated otherwise. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/signal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index ce14b951befb..cc7e2c1cd444 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -275,6 +275,8 @@ extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struc extern int sigprocmask(int, sigset_t *, sigset_t *); extern int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set, sigset_t *oldset, size_t sigsetsize); +extern void restore_user_sigmask(const void __user *usigmask, + sigset_t *sigsaved); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -- cgit v1.2.3 From 8bd27a3004e80d3d0962534c97e5a841262d5093 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 19 Sep 2018 21:41:06 -0700 Subject: ppoll: use __kernel_timespec struct timespec is not y2038 safe. struct __kernel_timespec is the new y2038 safe structure for all syscalls that are using struct timespec. Update ppoll interfaces to use struct __kernel_timespec. sigset_t also has different representations on 32 bit and 64 bit architectures. Hence, we need to support the following different syscalls: New y2038 safe syscalls: (Controlled by CONFIG_64BIT_TIME for 32 bit ABIs) Native 64 bit(unchanged) and native 32 bit : sys_ppoll Compat : compat_sys_ppoll_time64 Older y2038 unsafe syscalls: (Controlled by CONFIG_32BIT_COMPAT_TIME for 32 bit ABIs) Native 32 bit : ppoll_time32 Compat : compat_sys_ppoll Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 5 +++++ include/linux/syscalls.h | 5 ++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 17c497b82690..f309a524a4b7 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -652,6 +652,11 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); +asmlinkage long compat_sys_ppoll_time64(struct pollfd __user *ufds, + unsigned int nfds, + struct __kernel_timespec __user *tsp, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize); /* fs/signalfd.c */ asmlinkage long compat_sys_signalfd4(int ufd, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2ac3d13a915b..4575ea1f22cd 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -469,7 +469,10 @@ asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, fd_set __user *, struct timespec __user *, void __user *); asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, - struct timespec __user *, const sigset_t __user *, + struct __kernel_timespec __user *, const sigset_t __user *, + size_t); +asmlinkage long sys_ppoll_time32(struct pollfd __user *, unsigned int, + struct old_timespec32 __user *, const sigset_t __user *, size_t); /* fs/signalfd.c */ -- cgit v1.2.3 From e024707bccae15abd493265ea0b72f46a4920727 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 19 Sep 2018 21:41:07 -0700 Subject: pselect6: use __kernel_timespec struct timespec is not y2038 safe. struct __kernel_timespec is the new y2038 safe structure for all syscalls that are using struct timespec. Update pselect interfaces to use struct __kernel_timespec. sigset_t also has different representations on 32 bit and 64 bit architectures. Hence, we need to support the following different syscalls: New y2038 safe syscalls: (Controlled by CONFIG_64BIT_TIME for 32 bit ABIs) Native 64 bit(unchanged) and native 32 bit : sys_pselect6 Compat : compat_sys_pselect6_time64 Older y2038 unsafe syscalls: (Controlled by CONFIG_32BIT_COMPAT_TIME for 32 bit ABIs) Native 32 bit : pselect6_time32 Compat : compat_sys_pselect6 Note that all other versions of select syscalls will not have y2038 safe versions. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 5 +++++ include/linux/syscalls.h | 5 ++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index f309a524a4b7..5776733b763f 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -647,6 +647,11 @@ asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, compat_ulong_t __user *exp, struct old_timespec32 __user *tsp, void __user *sig); +asmlinkage long compat_sys_pselect6_time64(int n, compat_ulong_t __user *inp, + compat_ulong_t __user *outp, + compat_ulong_t __user *exp, + struct __kernel_timespec __user *tsp, + void __user *sig); asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, struct old_timespec32 __user *tsp, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4575ea1f22cd..934e58e0dfa4 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -466,7 +466,10 @@ asmlinkage long sys_sendfile64(int out_fd, int in_fd, /* fs/select.c */ asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, - fd_set __user *, struct timespec __user *, + fd_set __user *, struct __kernel_timespec __user *, + void __user *); +asmlinkage long sys_pselect6_time32(int, fd_set __user *, fd_set __user *, + fd_set __user *, struct old_timespec32 __user *, void __user *); asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, struct __kernel_timespec __user *, const sigset_t __user *, -- cgit v1.2.3 From 7a35397f8c06bffd4c747537095321ff971045a5 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 19 Sep 2018 21:41:08 -0700 Subject: io_pgetevents: use __kernel_timespec struct timespec is not y2038 safe. struct __kernel_timespec is the new y2038 safe structure for all syscalls that are using struct timespec. Update io_pgetevents interfaces to use struct __kernel_timespec. sigset_t also has different representations on 32 bit and 64 bit architectures. Hence, we need to support the following different syscalls: New y2038 safe syscalls: (Controlled by CONFIG_64BIT_TIME for 32 bit ABIs) Native 64 bit(unchanged) and native 32 bit : sys_io_pgetevents Compat : compat_sys_io_pgetevents_time64 Older y2038 unsafe syscalls: (Controlled by CONFIG_32BIT_COMPAT_TIME for 32 bit ABIs) Native 32 bit : sys_io_pgetevents_time32 Compat : compat_sys_io_pgetevents Note that io_getevents syscalls do not have a y2038 safe solution. Signed-off-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 6 ++++++ include/linux/syscalls.h | 10 ++++++++-- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 5776733b763f..8be8daa38c9a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -562,6 +562,12 @@ asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, struct io_event __user *events, struct old_timespec32 __user *timeout, const struct __compat_aio_sigset __user *usig); +asmlinkage long compat_sys_io_pgetevents_time64(compat_aio_context_t ctx_id, + compat_long_t min_nr, + compat_long_t nr, + struct io_event __user *events, + struct __kernel_timespec __user *timeout, + const struct __compat_aio_sigset __user *usig); /* fs/cookies.c */ asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 934e58e0dfa4..a27cf407de92 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -296,12 +296,18 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id, long min_nr, long nr, struct io_event __user *events, - struct timespec __user *timeout); + struct __kernel_timespec __user *timeout); asmlinkage long sys_io_pgetevents(aio_context_t ctx_id, long min_nr, long nr, struct io_event __user *events, - struct timespec __user *timeout, + struct __kernel_timespec __user *timeout, + const struct __aio_sigset *sig); +asmlinkage long sys_io_pgetevents_time32(aio_context_t ctx_id, + long min_nr, + long nr, + struct io_event __user *events, + struct old_timespec32 __user *timeout, const struct __aio_sigset *sig); /* fs/xattr.c */ -- cgit v1.2.3 From 7cb3026411cf2b64797eb6b1caacfba6ca4258d9 Mon Sep 17 00:00:00 2001 From: Benjamin Young Date: Sat, 1 Dec 2018 08:07:11 -0800 Subject: PCI: Remove unnecessary space before function pointer arguments Make spacing more consistent in the code for function pointer declarations based on checkpatch.pl. Signed-off-by: Benjamin Young [bhelgaas: make similar changes in include/linux/pci.h] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 11c71c4ecf75..a6cd567c3fc1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -764,9 +764,9 @@ struct pci_driver { int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ int (*suspend_late)(struct pci_dev *dev, pm_message_t state); int (*resume_early)(struct pci_dev *dev); - int (*resume) (struct pci_dev *dev); /* Device woken up */ - void (*shutdown) (struct pci_dev *dev); - int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* On PF */ + int (*resume)(struct pci_dev *dev); /* Device woken up */ + void (*shutdown)(struct pci_dev *dev); + int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */ const struct pci_error_handlers *err_handler; const struct attribute_group **groups; struct device_driver driver; -- cgit v1.2.3 From 00f54e68924eaf075f3f24be18557899d347bc4a Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 6 Dec 2018 17:05:36 +0000 Subject: net: core: dev: Add extack argument to dev_open() In order to pass extack together with NETDEV_PRE_UP notifications, it's necessary to route the extack to __dev_open() from diverse (possibly indirect) callers. One prominent API through which the notification is invoked is dev_open(). Therefore extend dev_open() with and extra extack argument and update all users. Most of the calls end up just encoding NULL, but bond and team drivers have the extack readily available. Signed-off-by: Petr Machata Acked-by: Jiri Pirko Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 94fb2e12f117..d79be3055f5f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2605,7 +2605,7 @@ struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); -int dev_open(struct net_device *dev); +int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); -- cgit v1.2.3 From 567c5e13be5cc74d24f5eb54cf353c2e2277189b Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 6 Dec 2018 17:05:42 +0000 Subject: net: core: dev: Add extack argument to dev_change_flags() In order to pass extack together with NETDEV_PRE_UP notifications, it's necessary to route the extack to __dev_open() from diverse (possibly indirect) callers. One prominent API through which the notification is invoked is dev_change_flags(). Therefore extend dev_change_flags() with and extra extack argument and update all users. Most of the calls end up just encoding NULL, but several sites (VLAN, ipvlan, VRF, rtnetlink) do have extack available. Since the function declaration line is changed anyway, name the other function arguments to placate checkpatch. Signed-off-by: Petr Machata Acked-by: Jiri Pirko Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d79be3055f5f..18cf464450ee 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3612,7 +3612,8 @@ int dev_ifconf(struct net *net, struct ifconf *, int); int dev_ethtool(struct net *net, struct ifreq *); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *, unsigned int flags); -int dev_change_flags(struct net_device *, unsigned int); +int dev_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack); void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); int dev_change_name(struct net_device *, const char *); -- cgit v1.2.3 From 6d0403216d030e5623de3911168fceeaac2e14d6 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 6 Dec 2018 17:05:43 +0000 Subject: net: core: dev: Add extack argument to __dev_change_flags() In order to pass extack together with NETDEV_PRE_UP notifications, it's necessary to route the extack to __dev_open() from diverse (possibly indirect) callers. The last missing API is __dev_change_flags(). Therefore extend __dev_change_flags() with and extra extack argument and update the two existing users. Since the function declaration line is changed anyway, name the struct net_device argument to placate checkpatch. Signed-off-by: Petr Machata Acked-by: Jiri Pirko Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 18cf464450ee..fc6ba71513be 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3611,7 +3611,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, int dev_ifconf(struct net *net, struct ifconf *, int); int dev_ethtool(struct net *net, struct ifreq *); unsigned int dev_get_flags(const struct net_device *); -int __dev_change_flags(struct net_device *, unsigned int flags); +int __dev_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); void __dev_notify_flags(struct net_device *, unsigned int old_flags, -- cgit v1.2.3 From 3fd3c80acc172fcaab2356c15e5e3c05758a9d51 Mon Sep 17 00:00:00 2001 From: Danit Goldberg Date: Fri, 30 Nov 2018 13:22:04 +0200 Subject: net/mlx5: Expose packet based credit mode Packet based credit mode bit determines whether the credit mode is done per message or packet. Expose the QP creation flag and the HCA capability. Signed-off-by: Danit Goldberg Reviewed-by: Majd Dibbiny Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ece1b606c909..91d6e85e3cef 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1047,7 +1047,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vector_calc[0x1]; u8 umr_ptr_rlky[0x1]; u8 imaicl[0x1]; - u8 reserved_at_232[0x4]; + u8 qp_packet_based[0x1]; + u8 reserved_at_233[0x3]; u8 qkv[0x1]; u8 pkv[0x1]; u8 set_deth_sqpn[0x1]; @@ -2259,7 +2260,8 @@ struct mlx5_ifc_qpc_bits { u8 st[0x8]; u8 reserved_at_10[0x3]; u8 pm_state[0x2]; - u8 reserved_at_15[0x3]; + u8 reserved_at_15[0x1]; + u8 req_e2e_credit_mode[0x2]; u8 offload_type[0x4]; u8 end_padding_mode[0x2]; u8 reserved_at_1e[0x2]; -- cgit v1.2.3 From 2ced26078fcff26db532d6300a1b5f8ffd11a5e1 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 29 Nov 2018 14:42:16 +0000 Subject: crypto: user - made crypto_user_stat optional Even if CRYPTO_STATS is set to n, some part of CRYPTO_STATS are compiled. This patch made all part of crypto_user_stat uncompiled in that case. Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 3634ad6fe202..3e05053b8d57 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -515,6 +515,7 @@ struct crypto_alg { struct module *cra_module; +#ifdef CONFIG_CRYPTO_STATS union { atomic_t encrypt_cnt; atomic_t compress_cnt; @@ -552,6 +553,7 @@ struct crypto_alg { atomic_t compute_shared_secret_cnt; }; atomic_t sign_cnt; +#endif /* CONFIG_CRYPTO_STATS */ } CRYPTO_MINALIGN_ATTR; -- cgit v1.2.3 From 6e8e72cd206e2ba68801e4f2490f639d41808c8d Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 29 Nov 2018 14:42:18 +0000 Subject: crypto: user - convert all stats from u32 to u64 All the 32-bit fields need to be 64-bit. In some cases, UINT32_MAX crypto operations can be done in seconds. Reported-by: Eric Biggers Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 3e05053b8d57..b109b50906e7 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -517,11 +517,11 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS union { - atomic_t encrypt_cnt; - atomic_t compress_cnt; - atomic_t generate_cnt; - atomic_t hash_cnt; - atomic_t setsecret_cnt; + atomic64_t encrypt_cnt; + atomic64_t compress_cnt; + atomic64_t generate_cnt; + atomic64_t hash_cnt; + atomic64_t setsecret_cnt; }; union { atomic64_t encrypt_tlen; @@ -530,29 +530,29 @@ struct crypto_alg { atomic64_t hash_tlen; }; union { - atomic_t akcipher_err_cnt; - atomic_t cipher_err_cnt; - atomic_t compress_err_cnt; - atomic_t aead_err_cnt; - atomic_t hash_err_cnt; - atomic_t rng_err_cnt; - atomic_t kpp_err_cnt; + atomic64_t akcipher_err_cnt; + atomic64_t cipher_err_cnt; + atomic64_t compress_err_cnt; + atomic64_t aead_err_cnt; + atomic64_t hash_err_cnt; + atomic64_t rng_err_cnt; + atomic64_t kpp_err_cnt; }; union { - atomic_t decrypt_cnt; - atomic_t decompress_cnt; - atomic_t seed_cnt; - atomic_t generate_public_key_cnt; + atomic64_t decrypt_cnt; + atomic64_t decompress_cnt; + atomic64_t seed_cnt; + atomic64_t generate_public_key_cnt; }; union { atomic64_t decrypt_tlen; atomic64_t decompress_tlen; }; union { - atomic_t verify_cnt; - atomic_t compute_shared_secret_cnt; + atomic64_t verify_cnt; + atomic64_t compute_shared_secret_cnt; }; - atomic_t sign_cnt; + atomic64_t sign_cnt; #endif /* CONFIG_CRYPTO_STATS */ } CRYPTO_MINALIGN_ATTR; @@ -983,9 +983,9 @@ static inline void crypto_stat_ablkcipher_encrypt(struct ablkcipher_request *req crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); if (ret && ret != -EINPROGRESS && ret != -EBUSY) { - atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + atomic64_inc(&crt->base->base.__crt_alg->cipher_err_cnt); } else { - atomic_inc(&crt->base->base.__crt_alg->encrypt_cnt); + atomic64_inc(&crt->base->base.__crt_alg->encrypt_cnt); atomic64_add(req->nbytes, &crt->base->base.__crt_alg->encrypt_tlen); } #endif @@ -999,9 +999,9 @@ static inline void crypto_stat_ablkcipher_decrypt(struct ablkcipher_request *req crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); if (ret && ret != -EINPROGRESS && ret != -EBUSY) { - atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + atomic64_inc(&crt->base->base.__crt_alg->cipher_err_cnt); } else { - atomic_inc(&crt->base->base.__crt_alg->decrypt_cnt); + atomic64_inc(&crt->base->base.__crt_alg->decrypt_cnt); atomic64_add(req->nbytes, &crt->base->base.__crt_alg->decrypt_tlen); } #endif -- cgit v1.2.3 From f7d76e05d058b832b373237566cc1af8251371b5 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 29 Nov 2018 14:42:21 +0000 Subject: crypto: user - fix use_after_free of struct xxx_request All crypto_stats functions use the struct xxx_request for feeding stats, but in some case this structure could already be freed. For fixing this, the needed parameters (len and alg) will be stored before the request being executed. Fixes: cac5818c25d0 ("crypto: user - Implement a generic crypto statistics") Reported-by: syzbot Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 105 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 71 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index b109b50906e7..e2fd24714e00 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -557,6 +557,69 @@ struct crypto_alg { } CRYPTO_MINALIGN_ATTR; +#ifdef CONFIG_CRYPTO_STATS +void crypto_stats_get(struct crypto_alg *alg); +void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); +void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); +void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); +void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); +void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); +void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg); +void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg); +void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg); +void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg); +void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg); +void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg); +void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg); +void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret); +void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret); +void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret); +void crypto_stats_rng_seed(struct crypto_alg *alg, int ret); +void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret); +void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); +void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); +#else +static inline void crypto_stats_get(struct crypto_alg *alg) +{} +static inline void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) +{} +static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) +{} +static inline void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_ahash_final(unsigned int nbytes, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_akcipher_encrypt(unsigned int src_len, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_akcipher_decrypt(unsigned int src_len, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_akcipher_sign(int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_akcipher_verify(int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_compress(unsigned int slen, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_decompress(unsigned int slen, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_kpp_set_secret(struct crypto_alg *alg, int ret) +{} +static inline void crypto_stats_kpp_generate_public_key(struct crypto_alg *alg, int ret) +{} +static inline void crypto_stats_kpp_compute_shared_secret(struct crypto_alg *alg, int ret) +{} +static inline void crypto_stats_rng_seed(struct crypto_alg *alg, int ret) +{} +static inline void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int ret) +{} +static inline void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) +{} +static inline void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg) +{} +#endif /* * A helper struct for waiting for completion of async crypto ops */ @@ -975,38 +1038,6 @@ static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm( return __crypto_ablkcipher_cast(req->base.tfm); } -static inline void crypto_stat_ablkcipher_encrypt(struct ablkcipher_request *req, - int ret) -{ -#ifdef CONFIG_CRYPTO_STATS - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - - if (ret && ret != -EINPROGRESS && ret != -EBUSY) { - atomic64_inc(&crt->base->base.__crt_alg->cipher_err_cnt); - } else { - atomic64_inc(&crt->base->base.__crt_alg->encrypt_cnt); - atomic64_add(req->nbytes, &crt->base->base.__crt_alg->encrypt_tlen); - } -#endif -} - -static inline void crypto_stat_ablkcipher_decrypt(struct ablkcipher_request *req, - int ret) -{ -#ifdef CONFIG_CRYPTO_STATS - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - - if (ret && ret != -EINPROGRESS && ret != -EBUSY) { - atomic64_inc(&crt->base->base.__crt_alg->cipher_err_cnt); - } else { - atomic64_inc(&crt->base->base.__crt_alg->decrypt_cnt); - atomic64_add(req->nbytes, &crt->base->base.__crt_alg->decrypt_tlen); - } -#endif -} - /** * crypto_ablkcipher_encrypt() - encrypt plaintext * @req: reference to the ablkcipher_request handle that holds all information @@ -1022,10 +1053,13 @@ static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + struct crypto_alg *alg = crt->base->base.__crt_alg; + unsigned int nbytes = req->nbytes; int ret; + crypto_stats_get(alg); ret = crt->encrypt(req); - crypto_stat_ablkcipher_encrypt(req, ret); + crypto_stats_ablkcipher_encrypt(nbytes, ret, alg); return ret; } @@ -1044,10 +1078,13 @@ static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + struct crypto_alg *alg = crt->base->base.__crt_alg; + unsigned int nbytes = req->nbytes; int ret; + crypto_stats_get(alg); ret = crt->decrypt(req); - crypto_stat_ablkcipher_decrypt(req, ret); + crypto_stats_ablkcipher_decrypt(nbytes, ret, alg); return ret; } -- cgit v1.2.3 From 17c18f9e33282a170458cb5ea20759bfcb0da7d8 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 29 Nov 2018 14:42:24 +0000 Subject: crypto: user - Split stats in multiple structures Like for userspace, this patch splits stats into multiple structures, one for each algorithm class. Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 180 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 118 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index e2fd24714e00..8a46ab35479e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -369,6 +369,115 @@ struct compress_alg { unsigned int slen, u8 *dst, unsigned int *dlen); }; +#ifdef CONFIG_CRYPTO_STATS +/* + * struct crypto_istat_aead - statistics for AEAD algorithm + * @encrypt_cnt: number of encrypt requests + * @encrypt_tlen: total data size handled by encrypt requests + * @decrypt_cnt: number of decrypt requests + * @decrypt_tlen: total data size handled by decrypt requests + * @aead_err_cnt: number of error for AEAD requests + */ +struct crypto_istat_aead { + atomic64_t encrypt_cnt; + atomic64_t encrypt_tlen; + atomic64_t decrypt_cnt; + atomic64_t decrypt_tlen; + atomic64_t aead_err_cnt; +}; + +/* + * struct crypto_istat_akcipher - statistics for akcipher algorithm + * @encrypt_cnt: number of encrypt requests + * @encrypt_tlen: total data size handled by encrypt requests + * @decrypt_cnt: number of decrypt requests + * @decrypt_tlen: total data size handled by decrypt requests + * @verify_cnt: number of verify operation + * @sign_cnt: number of sign requests + * @akcipher_err_cnt: number of error for akcipher requests + */ +struct crypto_istat_akcipher { + atomic64_t encrypt_cnt; + atomic64_t encrypt_tlen; + atomic64_t decrypt_cnt; + atomic64_t decrypt_tlen; + atomic64_t verify_cnt; + atomic64_t sign_cnt; + atomic64_t akcipher_err_cnt; +}; + +/* + * struct crypto_istat_cipher - statistics for cipher algorithm + * @encrypt_cnt: number of encrypt requests + * @encrypt_tlen: total data size handled by encrypt requests + * @decrypt_cnt: number of decrypt requests + * @decrypt_tlen: total data size handled by decrypt requests + * @cipher_err_cnt: number of error for cipher requests + */ +struct crypto_istat_cipher { + atomic64_t encrypt_cnt; + atomic64_t encrypt_tlen; + atomic64_t decrypt_cnt; + atomic64_t decrypt_tlen; + atomic64_t cipher_err_cnt; +}; + +/* + * struct crypto_istat_compress - statistics for compress algorithm + * @compress_cnt: number of compress requests + * @compress_tlen: total data size handled by compress requests + * @decompress_cnt: number of decompress requests + * @decompress_tlen: total data size handled by decompress requests + * @compress_err_cnt: number of error for compress requests + */ +struct crypto_istat_compress { + atomic64_t compress_cnt; + atomic64_t compress_tlen; + atomic64_t decompress_cnt; + atomic64_t decompress_tlen; + atomic64_t compress_err_cnt; +}; + +/* + * struct crypto_istat_hash - statistics for has algorithm + * @hash_cnt: number of hash requests + * @hash_tlen: total data size hashed + * @hash_err_cnt: number of error for hash requests + */ +struct crypto_istat_hash { + atomic64_t hash_cnt; + atomic64_t hash_tlen; + atomic64_t hash_err_cnt; +}; + +/* + * struct crypto_istat_kpp - statistics for KPP algorithm + * @setsecret_cnt: number of setsecrey operation + * @generate_public_key_cnt: number of generate_public_key operation + * @compute_shared_secret_cnt: number of compute_shared_secret operation + * @kpp_err_cnt: number of error for KPP requests + */ +struct crypto_istat_kpp { + atomic64_t setsecret_cnt; + atomic64_t generate_public_key_cnt; + atomic64_t compute_shared_secret_cnt; + atomic64_t kpp_err_cnt; +}; + +/* + * struct crypto_istat_rng: statistics for RNG algorithm + * @generate_cnt: number of RNG generate requests + * @generate_tlen: total data size of generated data by the RNG + * @seed_cnt: number of times the RNG was seeded + * @rng_err_cnt: number of error for RNG requests + */ +struct crypto_istat_rng { + atomic64_t generate_cnt; + atomic64_t generate_tlen; + atomic64_t seed_cnt; + atomic64_t rng_err_cnt; +}; +#endif /* CONFIG_CRYPTO_STATS */ #define cra_ablkcipher cra_u.ablkcipher #define cra_blkcipher cra_u.blkcipher @@ -454,32 +563,7 @@ struct compress_alg { * @cra_refcnt: internally used * @cra_destroy: internally used * - * All following statistics are for this crypto_alg - * @encrypt_cnt: number of encrypt requests - * @decrypt_cnt: number of decrypt requests - * @compress_cnt: number of compress requests - * @decompress_cnt: number of decompress requests - * @generate_cnt: number of RNG generate requests - * @seed_cnt: number of times the rng was seeded - * @hash_cnt: number of hash requests - * @sign_cnt: number of sign requests - * @setsecret_cnt: number of setsecrey operation - * @generate_public_key_cnt: number of generate_public_key operation - * @verify_cnt: number of verify operation - * @compute_shared_secret_cnt: number of compute_shared_secret operation - * @encrypt_tlen: total data size handled by encrypt requests - * @decrypt_tlen: total data size handled by decrypt requests - * @compress_tlen: total data size handled by compress requests - * @decompress_tlen: total data size handled by decompress requests - * @generate_tlen: total data size of generated data by the RNG - * @hash_tlen: total data size hashed - * @akcipher_err_cnt: number of error for akcipher requests - * @cipher_err_cnt: number of error for akcipher requests - * @compress_err_cnt: number of error for akcipher requests - * @aead_err_cnt: number of error for akcipher requests - * @hash_err_cnt: number of error for akcipher requests - * @rng_err_cnt: number of error for akcipher requests - * @kpp_err_cnt: number of error for akcipher requests + * @stats: union of all possible crypto_istat_xxx structures * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not @@ -517,42 +601,14 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS union { - atomic64_t encrypt_cnt; - atomic64_t compress_cnt; - atomic64_t generate_cnt; - atomic64_t hash_cnt; - atomic64_t setsecret_cnt; - }; - union { - atomic64_t encrypt_tlen; - atomic64_t compress_tlen; - atomic64_t generate_tlen; - atomic64_t hash_tlen; - }; - union { - atomic64_t akcipher_err_cnt; - atomic64_t cipher_err_cnt; - atomic64_t compress_err_cnt; - atomic64_t aead_err_cnt; - atomic64_t hash_err_cnt; - atomic64_t rng_err_cnt; - atomic64_t kpp_err_cnt; - }; - union { - atomic64_t decrypt_cnt; - atomic64_t decompress_cnt; - atomic64_t seed_cnt; - atomic64_t generate_public_key_cnt; - }; - union { - atomic64_t decrypt_tlen; - atomic64_t decompress_tlen; - }; - union { - atomic64_t verify_cnt; - atomic64_t compute_shared_secret_cnt; - }; - atomic64_t sign_cnt; + struct crypto_istat_aead aead; + struct crypto_istat_akcipher akcipher; + struct crypto_istat_cipher cipher; + struct crypto_istat_compress compress; + struct crypto_istat_hash hash; + struct crypto_istat_rng rng; + struct crypto_istat_kpp kpp; + } stats; #endif /* CONFIG_CRYPTO_STATS */ } CRYPTO_MINALIGN_ATTR; -- cgit v1.2.3 From 44f13133cb03ec32fc88a533673248ef5c0617e3 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 29 Nov 2018 14:42:25 +0000 Subject: crypto: user - rename err_cnt parameter Since now all crypto stats are on their own structures, it is now useless to have the algorithm name in the err_cnt member. Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 8a46ab35479e..a2967c1a08b1 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -376,14 +376,14 @@ struct compress_alg { * @encrypt_tlen: total data size handled by encrypt requests * @decrypt_cnt: number of decrypt requests * @decrypt_tlen: total data size handled by decrypt requests - * @aead_err_cnt: number of error for AEAD requests + * @err_cnt: number of error for AEAD requests */ struct crypto_istat_aead { atomic64_t encrypt_cnt; atomic64_t encrypt_tlen; atomic64_t decrypt_cnt; atomic64_t decrypt_tlen; - atomic64_t aead_err_cnt; + atomic64_t err_cnt; }; /* @@ -394,7 +394,7 @@ struct crypto_istat_aead { * @decrypt_tlen: total data size handled by decrypt requests * @verify_cnt: number of verify operation * @sign_cnt: number of sign requests - * @akcipher_err_cnt: number of error for akcipher requests + * @err_cnt: number of error for akcipher requests */ struct crypto_istat_akcipher { atomic64_t encrypt_cnt; @@ -403,7 +403,7 @@ struct crypto_istat_akcipher { atomic64_t decrypt_tlen; atomic64_t verify_cnt; atomic64_t sign_cnt; - atomic64_t akcipher_err_cnt; + atomic64_t err_cnt; }; /* @@ -412,14 +412,14 @@ struct crypto_istat_akcipher { * @encrypt_tlen: total data size handled by encrypt requests * @decrypt_cnt: number of decrypt requests * @decrypt_tlen: total data size handled by decrypt requests - * @cipher_err_cnt: number of error for cipher requests + * @err_cnt: number of error for cipher requests */ struct crypto_istat_cipher { atomic64_t encrypt_cnt; atomic64_t encrypt_tlen; atomic64_t decrypt_cnt; atomic64_t decrypt_tlen; - atomic64_t cipher_err_cnt; + atomic64_t err_cnt; }; /* @@ -428,26 +428,26 @@ struct crypto_istat_cipher { * @compress_tlen: total data size handled by compress requests * @decompress_cnt: number of decompress requests * @decompress_tlen: total data size handled by decompress requests - * @compress_err_cnt: number of error for compress requests + * @err_cnt: number of error for compress requests */ struct crypto_istat_compress { atomic64_t compress_cnt; atomic64_t compress_tlen; atomic64_t decompress_cnt; atomic64_t decompress_tlen; - atomic64_t compress_err_cnt; + atomic64_t err_cnt; }; /* * struct crypto_istat_hash - statistics for has algorithm * @hash_cnt: number of hash requests * @hash_tlen: total data size hashed - * @hash_err_cnt: number of error for hash requests + * @err_cnt: number of error for hash requests */ struct crypto_istat_hash { atomic64_t hash_cnt; atomic64_t hash_tlen; - atomic64_t hash_err_cnt; + atomic64_t err_cnt; }; /* @@ -455,13 +455,13 @@ struct crypto_istat_hash { * @setsecret_cnt: number of setsecrey operation * @generate_public_key_cnt: number of generate_public_key operation * @compute_shared_secret_cnt: number of compute_shared_secret operation - * @kpp_err_cnt: number of error for KPP requests + * @err_cnt: number of error for KPP requests */ struct crypto_istat_kpp { atomic64_t setsecret_cnt; atomic64_t generate_public_key_cnt; atomic64_t compute_shared_secret_cnt; - atomic64_t kpp_err_cnt; + atomic64_t err_cnt; }; /* @@ -469,13 +469,13 @@ struct crypto_istat_kpp { * @generate_cnt: number of RNG generate requests * @generate_tlen: total data size of generated data by the RNG * @seed_cnt: number of times the RNG was seeded - * @rng_err_cnt: number of error for RNG requests + * @err_cnt: number of error for RNG requests */ struct crypto_istat_rng { atomic64_t generate_cnt; atomic64_t generate_tlen; atomic64_t seed_cnt; - atomic64_t rng_err_cnt; + atomic64_t err_cnt; }; #endif /* CONFIG_CRYPTO_STATS */ -- cgit v1.2.3 From 1f6669b9716c6c98391b0f756e060892b32b8ca7 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 29 Nov 2018 14:42:26 +0000 Subject: crypto: user - Add crypto_stats_init This patch add the crypto_stats_init() function. This will permit to remove some ifdef from __crypto_register_alg(). Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index a2967c1a08b1..9850b41e38ae 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -614,6 +614,7 @@ struct crypto_alg { } CRYPTO_MINALIGN_ATTR; #ifdef CONFIG_CRYPTO_STATS +void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); @@ -635,6 +636,8 @@ void crypto_stats_rng_generate(struct crypto_alg *alg, unsigned int dlen, int re void crypto_stats_skcipher_encrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); void crypto_stats_skcipher_decrypt(unsigned int cryptlen, int ret, struct crypto_alg *alg); #else +static inline void crypto_stats_init(struct crypto_alg *alg) +{} static inline void crypto_stats_get(struct crypto_alg *alg) {} static inline void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg) -- cgit v1.2.3 From 10949af1681d5bb5cdbcc012815c6e40eec17d02 Mon Sep 17 00:00:00 2001 From: Schrempf Frieder Date: Thu, 8 Nov 2018 08:32:11 +0000 Subject: mtd: spinand: Add initial support for Toshiba TC58CVG2S0H MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add minimal support for the Toshiba TC58CVG2S0H SPI NAND chip. Signed-off-by: Frieder Schrempf Acked-by: Clément Péron Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 088ff96c3eb6..816c4b00abca 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -196,6 +196,7 @@ struct spinand_manufacturer { /* SPI NAND manufacturers */ extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; +extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; /** -- cgit v1.2.3 From 1f2d29e634b3e7abc7b62adf6bb4a676615c02ef Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:06 +0100 Subject: mtd: rawnand: Move nand_exec_op() to internal.h nand_exec_op() is only used by core code (nand_xxx.c files). Let's move this inline function in drivers/mtd/nand/raw/internals.h. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 4e91a70ede10..85dd89abcd22 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1098,15 +1098,6 @@ struct nand_chip { } manufacturer; }; -static inline int nand_exec_op(struct nand_chip *chip, - const struct nand_operation *op) -{ - if (!chip->exec_op) - return -ENOTSUPP; - - return chip->exec_op(chip, op, false); -} - extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops; -- cgit v1.2.3 From 336058c8f4c2c7991427304c8bde05acef156054 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:07 +0100 Subject: mtd: rawnand: Remove unused NAND_CONTROLLER_ALLOC flag Looks like NAND_CONTROLLER_ALLOC has been introduced a long time ago back when the dummy nand_hw_ctrl object was dynamically allocated instead of being embedded in nand_chip. We can safely get rid of this unused flag. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 85dd89abcd22..2a3dd3e633f1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -203,10 +203,6 @@ enum nand_ecc_algo { */ #define NAND_IS_BOOT_MEDIUM 0x00400000 -/* Options set by nand scan */ -/* Nand scan has allocated controller struct */ -#define NAND_CONTROLLER_ALLOC 0x80000000 - /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C -- cgit v1.2.3 From 1d0178593d148e88d2ac1e3f09c7f7eb1c20796b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:14 +0100 Subject: mtd: rawnand: Add nand_[de]select_target() helpers Add a wrapper to prevent drivers and core code from directly calling the ->select_chip hook which we are about to deprecate. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2a3dd3e633f1..def6dff11e8b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1332,9 +1332,12 @@ void nand_release(struct nand_chip *chip); * instruction and have no physical pin to check it. */ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms); - struct gpio_desc; int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, unsigned long timeout_ms); +/* Select/deselect a NAND target. */ +void nand_select_target(struct nand_chip *chip, unsigned int cs); +void nand_deselect_target(struct nand_chip *chip); + #endif /* __LINUX_MTD_RAWNAND_H */ -- cgit v1.2.3 From ae2294b10b0f066ef500954b36c94ee11c4ef20f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:15 +0100 Subject: mtd: rawnand: Pass the CS line to be selected in struct nand_operation In order to deprecate the ->select_chip hook we need to pass the CS line a NAND operations are targeting. This is done through the addition of a cs field to the nand_operation struct. We also need to keep track of the currently selected target to properly initialize op->cs, hence the ->cur_cs field addition to the nand_chip struct. Note that op->cs is not assigned in nand_exec_op() because we might rework the way we execute NAND operations in the future (adopt a queuing mechanism instead of the serialization we have right now). Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index def6dff11e8b..aa1512df38a9 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -875,18 +875,21 @@ struct nand_op_parser { /** * struct nand_operation - NAND operation descriptor + * @cs: the CS line to select for this NAND operation * @instrs: array of instructions to execute * @ninstrs: length of the @instrs array * * The actual operation structure that will be passed to chip->exec_op(). */ struct nand_operation { + unsigned int cs; const struct nand_op_instr *instrs; unsigned int ninstrs; }; -#define NAND_OPERATION(_instrs) \ +#define NAND_OPERATION(_cs, _instrs) \ { \ + .cs = _cs, \ .instrs = _instrs, \ .ninstrs = ARRAY_SIZE(_instrs), \ } @@ -1008,6 +1011,10 @@ struct nand_legacy { * this nand device will encounter their life times. * @blocks_per_die: [INTERN] The number of PEBs in a die * @data_interface: [INTERN] NAND interface timing information + * @cur_cs: currently selected target. -1 means no target selected, + * otherwise we should always have cur_cs >= 0 && + * cur_cs < numchips. NAND Controller drivers should not + * modify this value, but they're allowed to read it. * @read_retries: [INTERN] the number of read retry modes supported * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this @@ -1069,6 +1076,8 @@ struct nand_chip { struct nand_data_interface data_interface; + int cur_cs; + int read_retries; flstate_t state; -- cgit v1.2.3 From 7d6c37e90cf9013bd18240cd861b9ae7b006f91f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:22 +0100 Subject: mtd: rawnand: Deprecate the ->select_chip() hook Now that the CS line to be selected is passed to ->exec_op() and stored in chip->cur_cs and after patching all drivers implementing ->exec_op() to stop implementing this method, we can deprecate it by moving it to the nand_legacy structure. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index aa1512df38a9..40b74fb1792d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -902,6 +902,7 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * struct nand_legacy - NAND chip legacy fields/hooks * @IO_ADDR_R: address to read the 8 I/O lines of the flash device * @IO_ADDR_W: address to write the 8 I/O lines of the flash device + * @select_chip: select/deselect a specific target/die * @read_byte: read one byte from the chip * @write_byte: write a single byte to the chip on the low 8 I/O lines * @write_buf: write data from the buffer to the chip @@ -927,6 +928,7 @@ int nand_op_parser_exec_op(struct nand_chip *chip, struct nand_legacy { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; + void (*select_chip)(struct nand_chip *chip, int cs); u8 (*read_byte)(struct nand_chip *chip); void (*write_byte)(struct nand_chip *chip, u8 byte); void (*write_buf)(struct nand_chip *chip, const u8 *buf, int len); @@ -954,7 +956,6 @@ struct nand_legacy { * you're modifying an existing driver that is using those * fields/hooks, you should consider reworking the driver * avoid using them. - * @select_chip: [REPLACEABLE] select chip nr * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), * ->legacy.{read,write}_{buf,byte,word}(), @@ -1040,7 +1041,6 @@ struct nand_chip { struct nand_legacy legacy; - void (*select_chip)(struct nand_chip *chip, int cs); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); -- cgit v1.2.3 From f2abfeb2078b9682bfeb77f91816fcf2177b3051 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:23 +0100 Subject: mtd: rawnand: Move the ->exec_op() method to nand_controller_ops ->exec_op() is a controller method and has nothing to do in the nand_chip struct. Let's move it to the nand_controller_ops struct and adjust the core and drivers accordingly. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 99 ++++++++++++++++++++++----------------------- 1 file changed, 49 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 40b74fb1792d..297b40c56403 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -240,49 +240,6 @@ struct nand_id { int len; }; -/** - * struct nand_controller_ops - Controller operations - * - * @attach_chip: this method is called after the NAND detection phase after - * flash ID and MTD fields such as erase size, page size and OOB - * size have been set up. ECC requirements are available if - * provided by the NAND chip or device tree. Typically used to - * choose the appropriate ECC configuration and allocate - * associated resources. - * This hook is optional. - * @detach_chip: free all resources allocated/claimed in - * nand_controller_ops->attach_chip(). - * This hook is optional. - */ -struct nand_controller_ops { - int (*attach_chip)(struct nand_chip *chip); - void (*detach_chip)(struct nand_chip *chip); -}; - -/** - * struct nand_controller - Structure used to describe a NAND controller - * - * @lock: protection lock - * @active: the mtd device which holds the controller currently - * @wq: wait queue to sleep on if a NAND operation is in - * progress used instead of the per chip wait queue - * when a hw controller is available. - * @ops: NAND controller operations. - */ -struct nand_controller { - spinlock_t lock; - struct nand_chip *active; - wait_queue_head_t wq; - const struct nand_controller_ops *ops; -}; - -static inline void nand_controller_init(struct nand_controller *nfc) -{ - nfc->active = NULL; - spin_lock_init(&nfc->lock); - init_waitqueue_head(&nfc->wq); -} - /** * struct nand_ecc_step_info - ECC step information of ECC engine * @stepsize: data bytes per ECC step @@ -897,6 +854,55 @@ struct nand_operation { int nand_op_parser_exec_op(struct nand_chip *chip, const struct nand_op_parser *parser, const struct nand_operation *op, bool check_only); +/** + * struct nand_controller_ops - Controller operations + * + * @attach_chip: this method is called after the NAND detection phase after + * flash ID and MTD fields such as erase size, page size and OOB + * size have been set up. ECC requirements are available if + * provided by the NAND chip or device tree. Typically used to + * choose the appropriate ECC configuration and allocate + * associated resources. + * This hook is optional. + * @detach_chip: free all resources allocated/claimed in + * nand_controller_ops->attach_chip(). + * This hook is optional. + * @exec_op: controller specific method to execute NAND operations. + * This method replaces chip->legacy.cmdfunc(), + * chip->legacy.{read,write}_{buf,byte,word}(), + * chip->legacy.dev_ready() and chip->legacy.waifunc(). + */ +struct nand_controller_ops { + int (*attach_chip)(struct nand_chip *chip); + void (*detach_chip)(struct nand_chip *chip); + int (*exec_op)(struct nand_chip *chip, + const struct nand_operation *op, + bool check_only); +}; + +/** + * struct nand_controller - Structure used to describe a NAND controller + * + * @lock: protection lock + * @active: the mtd device which holds the controller currently + * @wq: wait queue to sleep on if a NAND operation is in + * progress used instead of the per chip wait queue + * when a hw controller is available. + * @ops: NAND controller operations. + */ +struct nand_controller { + spinlock_t lock; + struct nand_chip *active; + wait_queue_head_t wq; + const struct nand_controller_ops *ops; +}; + +static inline void nand_controller_init(struct nand_controller *nfc) +{ + nfc->active = NULL; + spin_lock_init(&nfc->lock); + init_waitqueue_head(&nfc->wq); +} /** * struct nand_legacy - NAND chip legacy fields/hooks @@ -956,10 +962,6 @@ struct nand_legacy { * you're modifying an existing driver that is using those * fields/hooks, you should consider reworking the driver * avoid using them. - * @exec_op: controller specific method to execute NAND operations. - * This method replaces ->cmdfunc(), - * ->legacy.{read,write}_{buf,byte,word}(), - * ->legacy.dev_ready() and ->waifunc(). * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure @@ -1041,9 +1043,6 @@ struct nand_chip { struct nand_legacy legacy; - int (*exec_op)(struct nand_chip *chip, - const struct nand_operation *op, - bool check_only); int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); -- cgit v1.2.3 From 7a08dbaedd365fa4eb7c9cd504c075e3336eb0c6 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:24 +0100 Subject: mtd: rawnand: Move ->setup_data_interface() to nand_controller_ops ->setup_data_interface() is a controller specific method and should thus be placed in nand_controller_ops. In order to make that work with controllers that support keeping pre-configured timings we need to add a new NAND_KEEP_TIMINGS flag to inform the core it should skip the timings selection step. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 297b40c56403..f50f40643895 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -203,6 +203,13 @@ enum nand_ecc_algo { */ #define NAND_IS_BOOT_MEDIUM 0x00400000 +/* + * Do not try to tweak the timings at runtime. This is needed when the + * controller initializes the timings on itself or when it relies on + * configuration done by the bootloader. + */ +#define NAND_KEEP_TIMINGS 0x00800000 + /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C @@ -871,6 +878,11 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * This method replaces chip->legacy.cmdfunc(), * chip->legacy.{read,write}_{buf,byte,word}(), * chip->legacy.dev_ready() and chip->legacy.waifunc(). + * @setup_data_interface: setup the data interface and timing. If + * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this + * means the configuration should not be applied but + * only checked. + * This hook is optional. */ struct nand_controller_ops { int (*attach_chip)(struct nand_chip *chip); @@ -878,6 +890,8 @@ struct nand_controller_ops { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); + int (*setup_data_interface)(struct nand_chip *chip, int chipnr, + const struct nand_data_interface *conf); }; /** @@ -1019,10 +1033,6 @@ struct nand_legacy { * cur_cs < numchips. NAND Controller drivers should not * modify this value, but they're allowed to read it. * @read_retries: [INTERN] the number of read retry modes supported - * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If - * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this - * means the configuration should not be applied but - * only checked. * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -1044,8 +1054,6 @@ struct nand_chip { struct nand_legacy legacy; int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); - int (*setup_data_interface)(struct nand_chip *chip, int chipnr, - const struct nand_data_interface *conf); unsigned int options; unsigned int bbt_options; -- cgit v1.2.3 From 7b6a9b28ecf2fd2e2f5dcdb6d4fa8044b48bdb74 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:39 +0100 Subject: mtd: rawnand: Deprecate the dummy_controller field We try to force NAND controller drivers to properly separate the NAND controller object from the NAND chip one, so let's deprecate the dummy controller object embedded in nand_chip to encourage them to create their own instance. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f50f40643895..33e240acdc6d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -941,6 +941,8 @@ static inline void nand_controller_init(struct nand_controller *nfc) * @get_features: get the NAND chip features * @chip_delay: chip dependent delay for transferring data from array to read * regs (tR). + * @dummy_controller: dummy controller implementation for drivers that can + * only control a single chip * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -966,6 +968,7 @@ struct nand_legacy { int (*get_features)(struct nand_chip *chip, int feature_addr, u8 *subfeature_para); int chip_delay; + struct nand_controller dummy_controller; }; /** @@ -980,8 +983,6 @@ struct nand_legacy { * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buf_align: minimum buffer alignment required by a platform - * @dummy_controller: dummy controller implementation for drivers that can - * only control a single chip * @state: [INTERN] the current state of the NAND device * @oob_poi: "poison value buffer," used for laying out OOB data * before writing @@ -1094,7 +1095,6 @@ struct nand_chip { struct nand_ecc_ctrl ecc; unsigned long buf_align; - struct nand_controller dummy_controller; uint8_t *bbt; struct nand_bbt_descr *bbt_td; -- cgit v1.2.3 From c93c613214ac70c87beab5422a60077bf126b855 Mon Sep 17 00:00:00 2001 From: Chuanhong Guo Date: Wed, 28 Nov 2018 21:07:25 +0800 Subject: mtd: spinand: add support for GigaDevice GD5FxGQ4xA Add support for GigaDevice GD5F1G/2G/4GQ4xA SPI NAND. Signed-off-by: Chuanhong Guo Reviewed-by: Frieder Schrempf Signed-off-by: Miquel Raynal --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 816c4b00abca..b92e2aa955b6 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -194,6 +194,7 @@ struct spinand_manufacturer { }; /* SPI NAND manufacturers */ +extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; -- cgit v1.2.3 From cb03f94ffb070b13bc0fa58b4ef4fdb558418d27 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 30 Nov 2018 10:04:08 +1100 Subject: fs/locks: merge posix_unblock_lock() and locks_delete_block() posix_unblock_lock() is not specific to posix locks, and behaves nearly identically to locks_delete_block() - the former returning a status while the later doesn't. So discard posix_unblock_lock() and use locks_delete_block() instead, after giving that function an appropriate return value. Signed-off-by: NeilBrown Reviewed-by: J. Bruce Fields Signed-off-by: Jeff Layton --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 16df3a7df378..26a8607b3c3c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1124,7 +1124,7 @@ extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); -extern int posix_unblock_lock(struct file_lock *); +extern int locks_delete_block(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); @@ -1214,7 +1214,7 @@ static inline int posix_lock_file(struct file *filp, struct file_lock *fl, return -ENOLCK; } -static inline int posix_unblock_lock(struct file_lock *waiter) +static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } -- cgit v1.2.3 From 08861d33d680838753f1f9d3ba9480d3651b764d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 19 Sep 2018 13:39:26 +0100 Subject: preempt: Move PREEMPT_NEED_RESCHED definition into arch code PREEMPT_NEED_RESCHED is never used directly, so move it into the arch code where it can potentially be implemented using either a different bit in the preempt count or as an entirely separate entity. Cc: Robert Love Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Martin Schwidefsky Acked-by: Peter Zijlstra (Intel) Signed-off-by: Will Deacon --- include/linux/preempt.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index c01813c3fbe9..dd92b1a93919 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -53,9 +53,6 @@ #define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) -/* We use the MSB mostly because its available */ -#define PREEMPT_NEED_RESCHED 0x80000000 - #define PREEMPT_DISABLED (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED) /* -- cgit v1.2.3 From c53431eb696f3c64c12c00afb81048af54b61532 Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Wed, 5 Dec 2018 10:42:22 +1000 Subject: HID: core: store the collections as a basic tree For each collection parsed, store a pointer to the parent collection (if any). This makes it a lot easier to look up which collection(s) any given item is part of Signed-off-by: Peter Hutterer Verified-by: Harry Cutts Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index a355d61940f2..fdfda898656c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -427,6 +427,7 @@ struct hid_local { */ struct hid_collection { + struct hid_collection *parent; unsigned type; unsigned usage; unsigned level; @@ -650,6 +651,7 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; + struct hid_collection *active_collection; struct hid_device *device; unsigned int scan_flags; }; -- cgit v1.2.3 From 5a4abb36f312cf83206b1b7d1308ba47cba0b3cc Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Wed, 5 Dec 2018 10:42:23 +1000 Subject: HID: core: process the Resolution Multiplier The Resolution Multiplier is a feature report that modifies the value of Usages within the same Logical Collection. If the multiplier is set to anything but 1, the hardware reports (value * multiplier) for the same amount of physical movement, i.e. the value we receive in the kernel is pre-multiplied. The hardware may either send a single (value * multiplier), or by sending multiplier as many reports with the same value, or a combination of these two options. For example, when the Microsoft Sculpt Ergonomic mouse Resolution Multiplier is set to 12, the Wheel sends out 12 for every detent but AC Pan sends out a value of 3 at 4 times the frequency. The effective multiplier is based on the physical min/max of the multiplier field, a logical min/max of [0,1] with a physical min/max of [1,8] means the multiplier is either 1 or 8. The Resolution Multiplier was introduced for high-resolution scrolling in Windows Vista and is commonly used on Microsoft mice. The recommendation for the Resolution Multiplier is to default to 1 for backwards compatibility. This patch adds an arbitrary upper limit at 255. The only known use case for the Resolution Multiplier is for scroll wheels where the multiplier has to be a fraction of 120 to work with Windows. Signed-off-by: Peter Hutterer Verified-by: Harry Cutts Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index fdfda898656c..fd8d860365a4 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -219,6 +219,7 @@ struct hid_item { #define HID_GD_VBRZ 0x00010045 #define HID_GD_VNO 0x00010046 #define HID_GD_FEATURE 0x00010047 +#define HID_GD_RESOLUTION_MULTIPLIER 0x00010048 #define HID_GD_SYSTEM_CONTROL 0x00010080 #define HID_GD_UP 0x00010090 #define HID_GD_DOWN 0x00010091 @@ -437,6 +438,8 @@ struct hid_usage { unsigned hid; /* hid usage code */ unsigned collection_index; /* index into collection array */ unsigned usage_index; /* index into usage array */ + __s8 resolution_multiplier;/* Effective Resolution Multiplier + (HUT v1.12, 4.3.1), default: 1 */ /* hidinput data */ __u16 code; /* input driver code */ __u8 type; /* input driver type */ @@ -894,6 +897,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid, unsigned int type, unsigned int id, unsigned int field_index, unsigned int report_counts); + +void hid_setup_resolution_multiplier(struct hid_device *hid); int hid_open_report(struct hid_device *device); int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); -- cgit v1.2.3 From 2dc702c991e3774af9d7ce410eef410ca9e2357e Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Wed, 5 Dec 2018 10:42:24 +1000 Subject: HID: input: use the Resolution Multiplier for high-resolution scrolling Windows uses a magic number of 120 for a wheel click. High-resolution scroll wheels are supposed to use a fraction of 120 to signal smaller scroll steps. This is implemented by the Resolution Multiplier in the device itself. If the multiplier is present in the report descriptor, set it to the logical max and then use the resolution multiplier to calculate the high-resolution events. This is the recommendation by Microsoft, see http://msdn.microsoft.com/en-us/windows/hardware/gg487477.aspx Note that all mice encountered so far have a logical min/max of 0/1, so it's a binary "yes or no" to high-res scrolling anyway. To make userspace simpler, always enable the REL_WHEEL_HI_RES bit. Where the device doesn't support high-resolution scrolling, the value for the high-res data will simply be a multiple of 120 every time. For userspace, if REL_WHEEL_HI_RES is available that is the one to be used. Potential side-effect: a device with a Resolution Multiplier applying to other Input items will have those items set to the logical max as well. This cannot easily be worked around but it is doubtful such devices exist. Signed-off-by: Peter Hutterer Verified-by: Harry Cutts Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index fd8d860365a4..93db548f8761 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -233,6 +233,7 @@ struct hid_item { #define HID_DC_BATTERYSTRENGTH 0x00060020 #define HID_CP_CONSUMER_CONTROL 0x000c0001 +#define HID_CP_AC_PAN 0x000c0238 #define HID_DG_DIGITIZER 0x000d0001 #define HID_DG_PEN 0x000d0002 @@ -441,11 +442,13 @@ struct hid_usage { __s8 resolution_multiplier;/* Effective Resolution Multiplier (HUT v1.12, 4.3.1), default: 1 */ /* hidinput data */ + __s8 wheel_factor; /* 120/resolution_multiplier */ __u16 code; /* input driver code */ __u8 type; /* input driver type */ __s8 hat_min; /* hat switch fun */ __s8 hat_max; /* ditto */ __s8 hat_dir; /* ditto */ + __s16 wheel_accumulated; /* hi-res wheel */ }; struct hid_input; -- cgit v1.2.3 From 43920edf3b24b0a3d136019c816e84ffcbef83ab Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Fri, 7 Dec 2018 19:55:07 +0000 Subject: bridge: Add br_fdb_clear_offload() When a driver unoffloads all FDB entries en bloc, it's inefficient to send the switchdev notification one by one. Add a helper that unsets the offload flag on FDB entries on a given bridge port and VLAN. Signed-off-by: Petr Machata Acked-by: Nikolay Aleksandrov Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index ef7c3d376b21..627b788ba0ff 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -119,6 +119,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, struct net_device *br_fdb_find_port(const struct net_device *br_dev, const unsigned char *addr, __u16 vid); +void br_fdb_clear_offload(const struct net_device *dev, u16 vid); bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); #else static inline struct net_device * @@ -128,6 +129,11 @@ br_fdb_find_port(const struct net_device *br_dev, { return NULL; } + +static inline void br_fdb_clear_offload(const struct net_device *dev, u16 vid) +{ +} + static inline bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag) { -- cgit v1.2.3 From 04e7712f4460585e5eed5b853fd8b82a9943958f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 16:31:07 +0200 Subject: y2038: futex: Move compat implementation into futex.c We are going to share the compat_sys_futex() handler between 64-bit architectures and 32-bit architectures that need to deal with both 32-bit and 64-bit time_t, and this is easier if both entry points are in the same file. In fact, most other system call handlers do the same thing these days, so let's follow the trend here and merge all of futex_compat.c into futex.c. In the process, a few minor changes have to be done to make sure everything still makes sense: handle_futex_death() and futex_cmpxchg_enabled() become local symbol, and the compat version of the fetch_robust_entry() function gets renamed to compat_fetch_robust_entry() to avoid a symbol clash. This is intended as a purely cosmetic patch, no behavior should change. Signed-off-by: Arnd Bergmann --- include/linux/futex.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 821ae502d3d8..ccaef0097785 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -9,9 +9,6 @@ struct inode; struct mm_struct; struct task_struct; -extern int -handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi); - /* * Futexes are matched on equal values of this key. * The key type depends on whether it's a shared or private mapping. @@ -55,11 +52,6 @@ extern void exit_robust_list(struct task_struct *curr); long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); -#ifdef CONFIG_HAVE_FUTEX_CMPXCHG -#define futex_cmpxchg_enabled 1 -#else -extern int futex_cmpxchg_enabled; -#endif #else static inline void exit_robust_list(struct task_struct *curr) { -- cgit v1.2.3 From bec2f7cbb73eadf5e1cc7d54ecb0980ede244257 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 17:23:35 +0200 Subject: y2038: futex: Add support for __kernel_timespec This prepares sys_futex for y2038 safe calling: the native syscall is changed to receive a __kernel_timespec argument, which will be switched to 64-bit time_t in the future. All the internal time handling gets changed to timespec64, and the compat_sys_futex entry point is moved under the CONFIG_COMPAT_32BIT_TIME check to provide compatibility for existing 32-bit architectures. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a27cf407de92..247ad9eca955 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -553,7 +553,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags); /* kernel/futex.c */ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, - struct timespec __user *utime, u32 __user *uaddr2, + struct __kernel_timespec __user *utime, u32 __user *uaddr2, u32 val3); asmlinkage long sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, -- cgit v1.2.3 From 60a89a3ce0cce515dc663bc1b45ac89202ad6c79 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 4 Dec 2018 20:58:33 -0500 Subject: scsi: t10-pi: Return correct ref tag when queue has no integrity profile Commit ddd0bc756983 ("block: move ref_tag calculation func to the block layer") moved ref tag calculation from SCSI to a library function. However, this change broke returning the correct ref tag for devices operating in DIF mode since these do not have an associated block integrity profile. This in turn caused read/write failures on PI-formatted disks attached to an mpt3sas controller. Fixes: ddd0bc756983 ("block: move ref_tag calculation func to the block layer") Cc: stable@vger.kernel.org # 4.19+ Reported-by: John Garry Tested-by: Xiang Chen Signed-off-by: Martin K. Petersen --- include/linux/t10-pi.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index b9626aa7e90c..3e2a80cc7b56 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -39,12 +39,13 @@ struct t10_pi_tuple { static inline u32 t10_pi_ref_tag(struct request *rq) { + unsigned int shift = ilog2(queue_logical_block_size(rq->q)); + #ifdef CONFIG_BLK_DEV_INTEGRITY - return blk_rq_pos(rq) >> - (rq->q->integrity.interval_exp - 9) & 0xffffffff; -#else - return -1U; + if (rq->q->integrity.interval_exp) + shift = rq->q->integrity.interval_exp; #endif + return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff; } extern const struct blk_integrity_profile t10_pi_type1_crc; -- cgit v1.2.3 From 6e0de61107f03c3222550d9b548cd331d31d82d1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 5 Dec 2018 06:50:40 -0700 Subject: blk-mq: remove QUEUE_FLAG_POLL from default MQ flags We only support polling if we have poll queues now, but the flag is being set by default. Remove the default QUEUE_FLAG_POLL setting, we'll set it in blk_mq_init_allocated_queue() if we have poll queues available for this device. Fixes: 6544d229bf43 ("block: enable polling by default if a poll map is initalized") Reported-by: Kirill Tkhai Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0b3874bdbc6a..81f1b105946b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -606,8 +606,7 @@ struct request_queue { (1 << QUEUE_FLAG_ADD_RANDOM)) #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP) | \ - (1 << QUEUE_FLAG_POLL)) + (1 << QUEUE_FLAG_SAME_COMP)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); -- cgit v1.2.3 From 0fe061b9f03c27d0370888efc22d4b3ac7af90cf Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:26 -0500 Subject: blkcg: fix ref count issue with bio_blkcg() using task_css The bio_blkcg() function turns out to be inconsistent and consequently dangerous to use. The first part returns a blkcg where a reference is owned by the bio meaning it does not need to be rcu protected. However, the third case, the last line, is problematic: return css_to_blkcg(task_css(current, io_cgrp_id)); This can race against task migration and the cgroup dying. It is also semantically different as it must be called rcu protected and is susceptible to failure when trying to get a reference to it. This patch adds association ahead of calling bio_blkcg() rather than after. This makes association a required and explicit step along the code paths for calling bio_blkcg(). In blk-iolatency, association is moved above the bio_blkcg() call to ensure it will not return %NULL. BFQ uses the old bio_blkcg() function, but I do not want to address it in this series due to the complexity. I have created a private version documenting the inconsistency and noting not to use it. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 98 ++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 90 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a9e2e2037129..f619307171a6 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -227,22 +227,103 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); +/** + * blkcg_css - find the current css + * + * Find the css associated with either the kthread or the current task. + * This may return a dying css, so it is up to the caller to use tryget logic + * to confirm it is alive and well. + */ +static inline struct cgroup_subsys_state *blkcg_css(void) +{ + struct cgroup_subsys_state *css; + + css = kthread_blkcg(); + if (css) + return css; + return task_css(current, io_cgrp_id); +} + +/** + * blkcg_get_css - find and get a reference to the css + * + * Find the css associated with either the kthread or the current task. + * This takes a reference on the blkcg which will need to be managed by the + * caller. + */ +static inline struct cgroup_subsys_state *blkcg_get_css(void) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + + css = kthread_blkcg(); + if (css) { + css_get(css); + } else { + /* + * This is a bit complicated. It is possible task_css() is + * seeing an old css pointer here. This is caused by the + * current thread migrating away from this cgroup and this + * cgroup dying. css_tryget() will fail when trying to take a + * ref on a cgroup that's ref count has hit 0. + * + * Therefore, if it does fail, this means current must have + * been swapped away already and this is waiting for it to + * propagate on the polling cpu. Hence the use of cpu_relax(). + */ + while (true) { + css = task_css(current, io_cgrp_id); + if (likely(css_tryget(css))) + break; + cpu_relax(); + } + } + + rcu_read_unlock(); + + return css; +} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -static inline struct blkcg *bio_blkcg(struct bio *bio) +/** + * __bio_blkcg - internal, inconsistent version to get blkcg + * + * DO NOT USE. + * This function is inconsistent and consequently is dangerous to use. The + * first part of the function returns a blkcg where a reference is owned by the + * bio. This means it does not need to be rcu protected as it cannot go away + * with the bio owning a reference to it. However, the latter potentially gets + * it from task_css(). This can race against task migration and the cgroup + * dying. It is also semantically different as it must be called rcu protected + * and is susceptible to failure when trying to get a reference to it. + * Therefore, it is not ok to assume that *_get() will always succeed on the + * blkcg returned here. + */ +static inline struct blkcg *__bio_blkcg(struct bio *bio) { - struct cgroup_subsys_state *css; + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + return css_to_blkcg(blkcg_css()); +} +/** + * bio_blkcg - grab the blkcg associated with a bio + * @bio: target bio + * + * This returns the blkcg associated with a bio, %NULL if not associated. + * Callers are expected to either handle %NULL or know association has been + * done prior to calling this. + */ +static inline struct blkcg *bio_blkcg(struct bio *bio) +{ if (bio && bio->bi_css) return css_to_blkcg(bio->bi_css); - css = kthread_blkcg(); - if (css) - return css_to_blkcg(css); - return css_to_blkcg(task_css(current, io_cgrp_id)); + return NULL; } static inline bool blk_cgroup_congested(void) @@ -710,10 +791,10 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, bool throtl = false; rcu_read_lock(); - blkcg = bio_blkcg(bio); /* associate blkcg if bio hasn't attached one */ - bio_associate_blkcg(bio, &blkcg->css); + bio_associate_blkcg(bio, NULL); + blkcg = bio_blkcg(bio); blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { @@ -835,6 +916,7 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } +static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, -- cgit v1.2.3 From b978962ad4f7f9c06e5aa07b2a9b22f6d600456c Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:27 -0500 Subject: blkcg: update blkg_lookup_create() to do locking To know when to create a blkg, the general pattern is to do a blkg_lookup() and if that fails, lock and do the lookup again, and if that fails finally create. It doesn't make much sense for everyone who wants to do creation to write this themselves. This changes blkg_lookup_create() to do locking and implement this pattern. The old blkg_lookup_create() is renamed to __blkg_lookup_create(). If a call site wants to do its own error handling or already owns the queue lock, they can use __blkg_lookup_create(). This will be used in upcoming patches. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Reviewed-by: Liu Bo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f619307171a6..b3b1a8187d23 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -181,6 +181,8 @@ extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); +struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); @@ -799,7 +801,7 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { spin_lock_irq(&q->queue_lock); - blkg = blkg_lookup_create(blkcg, q); + blkg = __blkg_lookup_create(blkcg, q); if (IS_ERR(blkg)) blkg = NULL; spin_unlock_irq(&q->queue_lock); -- cgit v1.2.3 From beea9da07d8a6228a7e4a31a83f9478d513bf03f Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:28 -0500 Subject: blkcg: convert blkg_lookup_create() to find closest blkg There are several scenarios where blkg_lookup_create() can fail such as the blkcg dying, request_queue is dying, or simply being OOM. Most handle this by simply falling back to the q->root_blkg and calling it a day. This patch implements the notion of closest blkg. During blkg_lookup_create(), if it fails to create, return the closest blkg found or the q->root_blkg. blkg_try_get_closest() is introduced and used during association so a bio is always attached to a blkg. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b3b1a8187d23..c08e96e521ed 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -545,6 +545,20 @@ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) return NULL; } +/** + * blkg_try_get_closest - try and get a blkg ref on the closet blkg + * @blkg: blkg to get + * + * This walks up the blkg tree to find the closest non-dying blkg and returns + * the blkg that it did association with as it may not be the passed in blkg. + */ +static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) +{ + while (!atomic_inc_not_zero(&blkg->refcnt)) + blkg = blkg->parent; + + return blkg; +} void __blkg_release_rcu(struct rcu_head *rcu); @@ -797,15 +811,7 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, /* associate blkcg if bio hasn't attached one */ bio_associate_blkcg(bio, NULL); blkcg = bio_blkcg(bio); - - blkg = blkg_lookup(blkcg, q); - if (unlikely(!blkg)) { - spin_lock_irq(&q->queue_lock); - blkg = __blkg_lookup_create(blkcg, q); - if (IS_ERR(blkg)) - blkg = NULL; - spin_unlock_irq(&q->queue_lock); - } + blkg = blkg_lookup_create(blkcg, q); throtl = blk_throtl_bio(q, blkg, bio); -- cgit v1.2.3 From 2268c0feb0ffb1c1bb6e1d4d5505d30f485aa77b Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:29 -0500 Subject: blkcg: introduce common blkg association logic There are 3 ways blkg association can happen: association with the current css, with the page css (swap), or from the wbc css (writeback). This patch handles how association is done for the first case where we are associating bsaed on the current css. If there is already a blkg associated, the css will be reused and association will be redone as the request_queue may have changed. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 056fb627edb3..62715a5a4f32 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -511,12 +511,15 @@ static inline int bio_associate_blkcg_from_page(struct bio *bio, #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); -int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); +void bio_disassociate_blkg(struct bio *bio); +void bio_associate_blkg(struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } +static inline void bio_disassociate_blkg(struct bio *bio) { } +static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { } -- cgit v1.2.3 From 5cdf2e3fea5ee37b66842d76a9b06e6dac0b933d Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:31 -0500 Subject: blkcg: associate blkg when associating a device Previously, blkg association was handled by controller specific code in blk-throttle and blk-iolatency. However, because a blkg represents a relationship between a blkcg and a request_queue, it makes sense to keep the blkg->q and bio->bi_disk->queue consistent. This patch moves association into the bio_set_dev macro(). This should cover the majority of cases where the device is set/changed keeping the two pointers consistent. Fallback code is added to blkcg_bio_issue_check() to catch any missing paths. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/blk-cgroup.h | 18 ++++++++++-------- 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 62715a5a4f32..6ee2ea8b378a 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -491,12 +491,14 @@ do { \ bio_clear_flag(bio, BIO_THROTTLED);\ (bio)->bi_disk = (bdev)->bd_disk; \ (bio)->bi_partno = (bdev)->bd_partno; \ + bio_associate_blkg(bio); \ } while (0) #define bio_copy_dev(dst, src) \ do { \ (dst)->bi_disk = (src)->bi_disk; \ (dst)->bi_partno = (src)->bi_partno; \ + bio_clone_blkcg_association(dst, src); \ } while (0) #define bio_dev(bio) \ diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index c08e96e521ed..f09752968c2a 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -21,6 +21,7 @@ #include #include #include +#include /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) @@ -802,21 +803,23 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { - struct blkcg *blkcg; struct blkcg_gq *blkg; bool throtl = false; - rcu_read_lock(); + if (!bio->bi_blkg) { + char b[BDEVNAME_SIZE]; + + WARN_ONCE(1, + "no blkg associated for bio on block-device: %s\n", + bio_devname(bio, b)); + bio_associate_blkg(bio); + } - /* associate blkcg if bio hasn't attached one */ - bio_associate_blkcg(bio, NULL); - blkcg = bio_blkcg(bio); - blkg = blkg_lookup_create(blkcg, q); + blkg = bio->bi_blkg; throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { - blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the @@ -828,7 +831,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } - rcu_read_unlock(); return !throtl; } -- cgit v1.2.3 From e439bedf6b24264f620cc05627e23a90054bde41 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:32 -0500 Subject: blkcg: consolidate bio_issue_init() to be a part of core bio_issue_init among other things initializes the timestamp for an IO. Rather than have this logic handled by policies, this consolidates it to be on the init paths (normal, clone, bounce clone). Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Liu Bo Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f09752968c2a..8b069c3775ee 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -800,6 +800,12 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif + +static inline void blkcg_bio_issue_init(struct bio *bio) +{ + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); +} + static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { @@ -831,6 +837,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } + blkcg_bio_issue_init(bio); + return !throtl; } @@ -936,6 +944,7 @@ static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } +static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } -- cgit v1.2.3 From 6a7f6d86a561473032287c8e4583eac5853c6efa Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:33 -0500 Subject: blkcg: associate a blkg for pages being evicted by swap A prior patch in this series added blkg association to bios issued by cgroups. There are two other paths that we want to attribute work back to the appropriate cgroup: swap and writeback. Here we modify the way swap tags bios to include the blkg. Writeback will be tackle in the next patch. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 6ee2ea8b378a..f13572c254a7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -505,10 +505,10 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); +void bio_associate_blkg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkcg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline void bio_associate_blkg_from_page(struct bio *bio, + struct page *page) { } #endif #ifdef CONFIG_BLK_CGROUP -- cgit v1.2.3 From fd42df305f804ddc0d5ac028e944784283b2f92d Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:34 -0500 Subject: blkcg: associate writeback bios with a blkg One of the goals of this series is to remove a separate reference to the css of the bio. This can and should be accessed via bio_blkcg(). In this patch, wbc_init_bio() now requires a bio to have a device associated with it. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 +++++ include/linux/writeback.h | 5 +++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index f13572c254a7..f0438061a5a3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -515,6 +515,8 @@ static inline void bio_associate_blkg_from_page(struct bio *bio, int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); void bio_disassociate_blkg(struct bio *bio); void bio_associate_blkg(struct bio *bio); +void bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ @@ -522,6 +524,9 @@ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } static inline void bio_disassociate_blkg(struct bio *bio) { } static inline void bio_associate_blkg(struct bio *bio) { } +static inline void bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ } static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { } diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fdfd04e348f6..738a0c24874f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,7 +246,8 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. + * writeback context. Must be called after the bio has been associated with + * a device. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -257,7 +258,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkcg(bio, wbc->wb->blkcg_css); + bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ -- cgit v1.2.3 From db6638d7d177a8bc74c9e539e2e0d7d061c767b1 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:35 -0500 Subject: blkcg: remove bio->bi_css and instead use bio->bi_blkg Prior patches ensured that any bio that interacts with a request_queue is properly associated with a blkg. This makes bio->bi_css unnecessary as blkg maintains a reference to blkcg already. This removes the bio field bi_css and transfers corresponding uses to access via bi_blkg. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 11 ++++------- include/linux/blk-cgroup.h | 8 ++++---- include/linux/blk_types.h | 7 ++++--- 3 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index f0438061a5a3..84e1c4dc703a 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -498,7 +498,7 @@ do { \ do { \ (dst)->bi_disk = (src)->bi_disk; \ (dst)->bi_partno = (src)->bi_partno; \ - bio_clone_blkcg_association(dst, src); \ + bio_clone_blkg_association(dst, src); \ } while (0) #define bio_dev(bio) \ @@ -512,24 +512,21 @@ static inline void bio_associate_blkg_from_page(struct bio *bio, #endif #ifdef CONFIG_BLK_CGROUP -int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); void bio_disassociate_blkg(struct bio *bio); void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkcg_association(struct bio *dst, struct bio *src); +void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkcg(struct bio *bio, - struct cgroup_subsys_state *blkcg_css) { return 0; } static inline void bio_disassociate_blkg(struct bio *bio) { } static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkcg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 8b069c3775ee..f11c37f8ce09 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -309,8 +309,8 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) */ static inline struct blkcg *__bio_blkcg(struct bio *bio) { - if (bio && bio->bi_css) - return css_to_blkcg(bio->bi_css); + if (bio && bio->bi_blkg) + return bio->bi_blkg->blkcg; return css_to_blkcg(blkcg_css()); } @@ -324,8 +324,8 @@ static inline struct blkcg *__bio_blkcg(struct bio *bio) */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_css) - return css_to_blkcg(bio->bi_css); + if (bio && bio->bi_blkg) + return bio->bi_blkg->blkcg; return NULL; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index c0ba1a038ff3..46c005d601ac 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -174,10 +174,11 @@ struct bio { void *bi_private; #ifdef CONFIG_BLK_CGROUP /* - * Optional css associated with this bio. Put on bio - * release. Read comment on top of bio_associate_current(). + * Represents the association of the css and request_queue for the bio. + * If a bio goes direct to device, it will not have a blkg as it will + * not have a request_queue associated with it. The reference is put + * on release of the bio. */ - struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif -- cgit v1.2.3 From fc5a828bfad628c1092194f2814604943561c52d Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:36 -0500 Subject: blkcg: remove additional reference to the css The previous patch in this series removed carrying around a pointer to the css in blkg. However, the blkg association logic still relied on taking a reference on the css to ensure we wouldn't fail in getting a reference for the blkg. Here the implicit dependency on the css is removed. The association continues to rely on the tryget logic walking up the blkg tree. This streamlines the three ways that association can happen: normal, swap, and writeback. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 41 ----------------------------------------- include/linux/cgroup.h | 2 ++ 2 files changed, 2 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f11c37f8ce09..284819a4d122 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -247,47 +247,6 @@ static inline struct cgroup_subsys_state *blkcg_css(void) return task_css(current, io_cgrp_id); } -/** - * blkcg_get_css - find and get a reference to the css - * - * Find the css associated with either the kthread or the current task. - * This takes a reference on the blkcg which will need to be managed by the - * caller. - */ -static inline struct cgroup_subsys_state *blkcg_get_css(void) -{ - struct cgroup_subsys_state *css; - - rcu_read_lock(); - - css = kthread_blkcg(); - if (css) { - css_get(css); - } else { - /* - * This is a bit complicated. It is possible task_css() is - * seeing an old css pointer here. This is caused by the - * current thread migrating away from this cgroup and this - * cgroup dying. css_tryget() will fail when trying to take a - * ref on a cgroup that's ref count has hit 0. - * - * Therefore, if it does fail, this means current must have - * been swapped away already and this is waiting for it to - * propagate on the polling cpu. Hence the use of cpu_relax(). - */ - while (true) { - css = task_css(current, io_cgrp_id); - if (likely(css_tryget(css))) - break; - cpu_relax(); - } - } - - rcu_read_unlock(); - - return css; -} - static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9d12757a65b0..9968332cceed 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,6 +93,8 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); +struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, + struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, -- cgit v1.2.3 From 6f70fb66182b02e50deea65e9a3a86b7bf659a39 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:37 -0500 Subject: blkcg: remove bio_disassociate_task() Now that a bio only holds a blkg reference, so clean up is simply putting back that reference. Remove bio_disassociate_task() as it just calls bio_disassociate_blkg() and call the latter directly. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 84e1c4dc703a..7380b094dcca 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -516,7 +516,6 @@ void bio_disassociate_blkg(struct bio *bio); void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); -void bio_disassociate_task(struct bio *bio); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline void bio_disassociate_blkg(struct bio *bio) { } @@ -524,7 +523,6 @@ static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { } -static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ -- cgit v1.2.3 From 7fcf2b033b84e261dca283bc2911aaea4b07b525 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:38 -0500 Subject: blkcg: change blkg reference counting to use percpu_ref Every bio is now associated with a blkg putting blkg_get, blkg_try_get, and blkg_put on the hot path. Switch over the refcnt in blkg to use percpu_ref. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 284819a4d122..d19ef15a673d 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -124,7 +124,7 @@ struct blkcg_gq { struct blkcg_gq *parent; /* reference count */ - atomic_t refcnt; + struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -487,8 +487,7 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); - atomic_inc(&blkg->refcnt); + percpu_ref_get(&blkg->refcnt); } /** @@ -500,7 +499,7 @@ static inline void blkg_get(struct blkcg_gq *blkg) */ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - if (atomic_inc_not_zero(&blkg->refcnt)) + if (percpu_ref_tryget(&blkg->refcnt)) return blkg; return NULL; } @@ -514,23 +513,19 @@ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) */ static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) { - while (!atomic_inc_not_zero(&blkg->refcnt)) + while (!percpu_ref_tryget(&blkg->refcnt)) blkg = blkg->parent; return blkg; } -void __blkg_release_rcu(struct rcu_head *rcu); - /** * blkg_put - put a blkg reference * @blkg: blkg to put */ static inline void blkg_put(struct blkcg_gq *blkg) { - WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); - if (atomic_dec_and_test(&blkg->refcnt)) - call_rcu(&blkg->rcu_head, __blkg_release_rcu); + percpu_ref_put(&blkg->refcnt); } /** -- cgit v1.2.3 From 7754f669ffde3919e398a9e591cd7510d6cf4e73 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 5 Dec 2018 12:10:39 -0500 Subject: blkcg: rename blkg_try_get() to blkg_tryget() blkg reference counting now uses percpu_ref rather than atomic_t. Let's make this consistent with css_tryget. This renames blkg_try_get to blkg_tryget and now returns a bool rather than the blkg or %NULL. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index d19ef15a673d..752de1becb5c 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -491,27 +491,25 @@ static inline void blkg_get(struct blkcg_gq *blkg) } /** - * blkg_try_get - try and get a blkg reference + * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) +static inline bool blkg_tryget(struct blkcg_gq *blkg) { - if (percpu_ref_tryget(&blkg->refcnt)) - return blkg; - return NULL; + return percpu_ref_tryget(&blkg->refcnt); } /** - * blkg_try_get_closest - try and get a blkg ref on the closet blkg + * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @blkg: blkg to get * * This walks up the blkg tree to find the closest non-dying blkg and returns * the blkg that it did association with as it may not be the passed in blkg. */ -static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) { while (!percpu_ref_tryget(&blkg->refcnt)) blkg = blkg->parent; -- cgit v1.2.3 From 4705de735b3383792c84a92e57508d6865caa85f Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Thu, 6 Dec 2018 12:49:38 -0500 Subject: blkcg: put back rcu lock in blkcg_bio_issue_check() I was a little overzealous in removing the rcu_read_lock() call from blkcg_bio_issue_check() and it broke blk-throttle. Put it back. Fixes: e35403a034bf ("blkcg: associate blkg when associating a device") Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 752de1becb5c..bf13ecb0fe4f 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -764,6 +764,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, struct blkcg_gq *blkg; bool throtl = false; + rcu_read_lock(); + if (!bio->bi_blkg) { char b[BDEVNAME_SIZE]; @@ -791,6 +793,7 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkcg_bio_issue_init(bio); + rcu_read_unlock(); return !throtl; } -- cgit v1.2.3 From 12b2117161ddbdcdb69777404c5aa2a9fe6ad7d5 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 2 Nov 2018 10:28:12 -0700 Subject: nvme: introduce ctrl attributes enumeration We are growing more controller attributes, so use a proper enumeration for it. For now just add the 128-bit hostid which we support. Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 818dbe9331be..753c83a5c01f 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -198,6 +198,10 @@ enum { NVME_PS_FLAGS_NON_OP_STATE = 1 << 1, }; +enum nvme_ctrl_attr { + NVME_CTRL_ATTR_HID_128_BIT = (1 << 0), +}; + struct nvme_id_ctrl { __le16 vid; __le16 ssvid; -- cgit v1.2.3 From 6e3ca03ee934572d5de4fb2224c01e12c4d422c8 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 2 Nov 2018 10:28:15 -0700 Subject: nvme: support traffic based keep-alive If the controller supports traffic based keep alive, we restart the keep alive timer if any admin or io commands was completed during the kato period. This prevents a possible starvation of keep alive commands in the presence of heavy traffic as in such case, we already have a health indication from the host perspective. Only set a comp_seen indicator in case the controller supports keep alive to minimize the overhead for pci controllers. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 753c83a5c01f..429c4cf90899 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -200,6 +200,7 @@ enum { enum nvme_ctrl_attr { NVME_CTRL_ATTR_HID_128_BIT = (1 << 0), + NVME_CTRL_ATTR_TBKAS = (1 << 6), }; struct nvme_id_ctrl { -- cgit v1.2.3 From 7114ddeb40c0ccc584d86df598da4054ca4cd79f Mon Sep 17 00:00:00 2001 From: Jay Sternberg Date: Mon, 12 Nov 2018 13:56:34 -0800 Subject: nvmet: change aen mask functions to use bit numbers Functions nvmet_aen_disabled and nvmet_clear_aen were using values not bit numbers ie 1 << 9 not 9 for bit function clear_bit and test_and_set_bit. Signed-off-by: Jay Sternberg Reviewed-by: Phil Cayton Reviewed-by: Christoph Hellwig Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 429c4cf90899..d6cfa194be80 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -489,9 +489,15 @@ enum { }; enum { - NVME_AEN_CFG_NS_ATTR = 1 << 8, - NVME_AEN_CFG_FW_ACT = 1 << 9, - NVME_AEN_CFG_ANA_CHANGE = 1 << 11, + NVME_AEN_BIT_NS_ATTR = 8, + NVME_AEN_BIT_FW_ACT = 9, + NVME_AEN_BIT_ANA_CHANGE = 11, +}; + +enum { + NVME_AEN_CFG_NS_ATTR = 1 << NVME_AEN_BIT_NS_ATTR, + NVME_AEN_CFG_FW_ACT = 1 << NVME_AEN_BIT_FW_ACT, + NVME_AEN_CFG_ANA_CHANGE = 1 << NVME_AEN_BIT_ANA_CHANGE, }; struct nvme_lba_range_type { -- cgit v1.2.3 From f301c2b1368905340133ff8ef4485befdd0b7e2d Mon Sep 17 00:00:00 2001 From: Jay Sternberg Date: Mon, 12 Nov 2018 13:56:37 -0800 Subject: nvmet: add defines for discovery change async events Add AEN/AER values as defined by the specification Signed-off-by: Jay Sternberg Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d6cfa194be80..77d320d32ee5 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -486,18 +486,21 @@ enum { NVME_AER_NOTICE_NS_CHANGED = 0x00, NVME_AER_NOTICE_FW_ACT_STARTING = 0x01, NVME_AER_NOTICE_ANA = 0x03, + NVME_AER_NOTICE_DISC_CHANGED = 0xf0, }; enum { NVME_AEN_BIT_NS_ATTR = 8, NVME_AEN_BIT_FW_ACT = 9, NVME_AEN_BIT_ANA_CHANGE = 11, + NVME_AEN_BIT_DISC_CHANGE = 31, }; enum { NVME_AEN_CFG_NS_ATTR = 1 << NVME_AEN_BIT_NS_ATTR, NVME_AEN_CFG_FW_ACT = 1 << NVME_AEN_BIT_FW_ACT, NVME_AEN_CFG_ANA_CHANGE = 1 << NVME_AEN_BIT_ANA_CHANGE, + NVME_AEN_CFG_DISC_CHANGE = 1 << NVME_AEN_BIT_DISC_CHANGE, }; struct nvme_lba_range_type { -- cgit v1.2.3 From 6e2e312ea7ff73acfafaa5c9851e151e9483c761 Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 14 Nov 2018 15:57:46 -0800 Subject: nvmet-fc: remove the IN_ISR deferred scheduling options All target lldd's call the cmd receive and op completions in non-isr thread contexts. As such the IN_ISR options are not necessary. Remove the functionality and flags, which also removes cpu assignments to queues. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc-driver.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index f4ab3b1925ac..91745cc3704c 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -648,22 +648,6 @@ enum { * sequence in one LLDD operation. Errors during Data * sequence transmit must not allow RSP sequence to be sent. */ - NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 1), - /* Bit 2: When 0, the LLDD is calling the cmd rcv handler - * in a non-isr context, allowing the transport to finish - * op completion in the calling context. When 1, the LLDD - * is calling the cmd rcv handler in an ISR context, - * requiring the transport to transition to a workqueue - * for op completion. - */ - NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 2), - /* Bit 3: When 0, the LLDD is calling the op done handler - * in a non-isr context, allowing the transport to finish - * op completion in the calling context. When 1, the LLDD - * is calling the op done handler in an ISR context, - * requiring the transport to transition to a workqueue - * for op completion. - */ }; -- cgit v1.2.3 From e6a622fd6d66b83779357e3400f487fc159a7d83 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 19 Nov 2018 14:11:12 -0800 Subject: nvmet: support fabrics sq flow control Technical proposal 8005 "fabrics SQ flow control" introduces a mode where a host and controller agree to omit sq_head pointer updates when sending nvme completions. In case the host indicated desire to operate in this mode (connect attribute) the controller will return back a connect completion with sq_head value of 0xffff as indication that it will omit sq_head pointer updates. This mode saves us an atomic update in the I/O path. Reviewed-by: Hannes Reinecke [hch: suggested better implementation] Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 77d320d32ee5..e7d731776f62 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1044,6 +1044,10 @@ struct nvmf_disc_rsp_page_hdr { struct nvmf_disc_rsp_page_entry entries[0]; }; +enum { + NVME_CONNECT_DISABLE_SQFLOW = (1 << 2), +}; + struct nvmf_connect_command { __u8 opcode; __u8 resv1; -- cgit v1.2.3 From 0445e1b5a2fed4612b7f72d9a56889c026b60aa9 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 19 Nov 2018 14:11:13 -0800 Subject: nvmet: don't override treq upon modification. Only override the allowed parts of it. Reviewed-by: Hannes Reinecke Signed-off-by: Sagi Grimberg [hch: slight tweak to the NVME_TREQ_SECURE_CHANNEL_MASK definition] Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index e7d731776f62..4fc48071e5ea 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -61,6 +61,8 @@ enum { NVMF_TREQ_NOT_SPECIFIED = 0, /* Not specified */ NVMF_TREQ_REQUIRED = 1, /* Required */ NVMF_TREQ_NOT_REQUIRED = 2, /* Not Required */ +#define NVME_TREQ_SECURE_CHANNEL_MASK \ + (NVMF_TREQ_REQUIRED | NVMF_TREQ_NOT_REQUIRED) }; /* RDMA QP Service Type codes for Discovery Log Page entry TSAS -- cgit v1.2.3 From 9b95d2fb857f242aacbf4e205656818b0ef067e1 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 20 Nov 2018 10:34:19 +0100 Subject: nvmet: expose support for fabrics SQ flow control disable in treq Technical Proposal introduces an indication for SQ flow control disable support. Expose it since we are able to operate in this mode. Reviewed-by: Hannes Reinecke Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fc48071e5ea..c03973c215ad 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -58,11 +58,13 @@ enum { /* Transport Requirements codes for Discovery Log Page entry TREQ field */ enum { - NVMF_TREQ_NOT_SPECIFIED = 0, /* Not specified */ - NVMF_TREQ_REQUIRED = 1, /* Required */ - NVMF_TREQ_NOT_REQUIRED = 2, /* Not Required */ + NVMF_TREQ_NOT_SPECIFIED = 0, /* Not specified */ + NVMF_TREQ_REQUIRED = 1, /* Required */ + NVMF_TREQ_NOT_REQUIRED = 2, /* Not Required */ #define NVME_TREQ_SECURE_CHANNEL_MASK \ (NVMF_TREQ_REQUIRED | NVMF_TREQ_NOT_REQUIRED) + + NVMF_TREQ_DISABLE_SQFLOW = (1 << 2), /* Supports SQ flow control disable */ }; /* RDMA QP Service Type codes for Discovery Log Page entry TSAS -- cgit v1.2.3 From 49cd84b6f8b677ef45731ed56ddb802cdbb94c9e Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 27 Nov 2018 09:40:57 -0700 Subject: nvme: implement Enhanced Command Retry A controller may have an internal state that is not able to successfully process commands for a short duration. In such states, an immediate command requeue is expected to fail. The driver may exceed its max retry count, which permanently ends the command in failure when the same command would succeed after waiting for the controller to be ready. NVMe ratified TP 4033 provides a delay hint in the completion status code for failed commands. Implement the retry delay based on the command completion status and the controller's requested delay. Note that requeued commands are handled per request_queue, not per individual request. If multiple commands fail, the controller should consistently report the desired delay time for retryable commands in all CQEs, otherwise the requeue list may be kicked too soon. Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index c03973c215ad..88812cb15be0 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -223,7 +223,11 @@ struct nvme_id_ctrl { __le32 rtd3e; __le32 oaes; __le32 ctratt; - __u8 rsvd100[156]; + __u8 rsvd100[28]; + __le16 crdt1; + __le16 crdt2; + __le16 crdt3; + __u8 rsvd134[122]; __le16 oacs; __u8 acl; __u8 aerl; @@ -756,6 +760,15 @@ enum { NVME_HOST_MEM_RETURN = (1 << 1), }; +struct nvme_feat_host_behavior { + __u8 acre; + __u8 resv1[511]; +}; + +enum { + NVME_ENABLE_ACRE = 1, +}; + /* Admin commands */ enum nvme_admin_opcode { @@ -810,6 +823,7 @@ enum { NVME_FEAT_RRL = 0x12, NVME_FEAT_PLM_CONFIG = 0x13, NVME_FEAT_PLM_WINDOW = 0x14, + NVME_FEAT_HOST_BEHAVIOR = 0x16, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, @@ -1265,6 +1279,7 @@ enum { NVME_SC_ANA_TRANSITION = 0x303, NVME_SC_HOST_PATH_ERROR = 0x370, + NVME_SC_CRD = 0x1800, NVME_SC_DNR = 0x4000, }; -- cgit v1.2.3 From ad3bc25a320742f42b3015115384f5aec69c7ce2 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 5 Dec 2018 00:34:56 +0100 Subject: x86/kernel: Fix more -Wmissing-prototypes warnings ... with the goal of eventually enabling -Wmissing-prototypes by default. At least on x86. Make functions static where possible, otherwise add prototypes or make them visible through includes. asm/trace/ changes courtesy of Steven Rostedt . Signed-off-by: Borislav Petkov Reviewed-by: Masami Hiramatsu Reviewed-by: Ingo Molnar Acked-by: Rafael J. Wysocki # ACPI + cpufreq bits Cc: Andrew Banman Cc: Dimitri Sivanich Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Mike Travis Cc: "Steven Rostedt (VMware)" Cc: Thomas Gleixner Cc: Yi Wang Cc: linux-acpi@vger.kernel.org --- include/linux/kprobes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e909413e4e38..e64b26c81c2f 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -379,6 +379,9 @@ int enable_kprobe(struct kprobe *kp); void dump_kprobe(struct kprobe *kp); +void *alloc_insn_page(void); +void free_insn_page(void *page); + #else /* !CONFIG_KPROBES: */ static inline int kprobes_built_in(void) -- cgit v1.2.3 From 356ff8a9a78fb35d6482584d260c3754dcbdf669 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 7 Dec 2018 14:50:16 -0800 Subject: Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask" This reverts commit 89c83fb539f95491be80cdd5158e6f0ce329e317. This should have been done as part of 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations"). The movement of the thp allocation policy from alloc_pages_vma() to alloc_hugepage_direct_gfpmask() was intended to only set __GFP_THISNODE for mempolicies that are not MPOL_BIND whereas the revert could set this regardless of mempolicy. While the check for MPOL_BIND between alloc_hugepage_direct_gfpmask() and alloc_pages_vma() was racy, that has since been removed since the revert. What is left is the possibility to use __GFP_THISNODE in policy_node() when it is unexpected because the special handling for hugepages in alloc_pages_vma() was removed as part of the consolidation. Secondly, prior to 89c83fb539f9, alloc_pages_vma() implemented a somewhat different policy for hugepage allocations, which were allocated through alloc_hugepage_vma(). For hugepage allocations, if the allocating process's node is in the set of allowed nodes, allocate with __GFP_THISNODE for that node (for MPOL_PREFERRED, use that node with __GFP_THISNODE instead). This was changed for shmem_alloc_hugepage() to allow fallback to other nodes in 89c83fb539f9 as it did for new_page() in mm/mempolicy.c which is functionally different behavior and removes the requirement to only allocate hugepages locally. So this commit does a full revert of 89c83fb539f9 instead of the partial revert that was done in 2f0799a0ffc0. The result is the same thp allocation policy for 4.20 that was in 4.19. Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Fixes: 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations") Signed-off-by: David Rientjes Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 76f8db0b0e71..0705164f928c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,18 +510,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node); + int node, bool hugepage); +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ + alloc_pages(gfp_mask, order) +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node) + alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -- cgit v1.2.3 From 761efe8a94cfcd0a3dd90f2008411550f3520b63 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 18 Nov 2018 18:44:04 -0500 Subject: function_graph: Remove the use of FTRACE_NOTRACE_DEPTH The curr_ret_stack is no longer set to a negative value when a function is not to be traced by the function graph tracer. Remove the usage of FTRACE_NOTRACE_DEPTH, as it is no longer needed. Reviewed-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 10bd46434908..98625f10d982 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -790,7 +790,6 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, */ #define __notrace_funcgraph notrace -#define FTRACE_NOTRACE_DEPTH 65536 #define FTRACE_RETFUNC_DEPTH 50 #define FTRACE_RETSTACK_ALLOC_SIZE 32 extern int register_ftrace_graph(trace_func_graph_ret_t retfunc, -- cgit v1.2.3 From 688f7089d8851b1a81106f0c0b9b29181b2f2dc8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 15 Nov 2018 14:06:47 -0500 Subject: fgraph: Add new fgraph_ops structure to enable function graph hooks Currently the registering of function graph is to pass in a entry and return function. We need to have a way to associate those functions together where the entry can determine to run the return hook. Having a structure that contains both functions will facilitate the process of converting the code to be able to do such. This is similar to the way function hooks are enabled (it passes in ftrace_ops). Instead of passing in the functions to use, a single structure is passed in to the registering function. The unregister function is now passed in the fgraph_ops handle. When we allow more than one callback to the function graph hooks, this will let the system know which one to remove. Reviewed-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 98625f10d982..21c80491ccde 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -749,6 +749,11 @@ typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER +struct fgraph_ops { + trace_func_graph_ent_t entryfunc; + trace_func_graph_ret_t retfunc; +}; + /* * Stack of return addresses for functions * of a thread. @@ -792,8 +797,9 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, #define FTRACE_RETFUNC_DEPTH 50 #define FTRACE_RETSTACK_ALLOC_SIZE 32 -extern int register_ftrace_graph(trace_func_graph_ret_t retfunc, - trace_func_graph_ent_t entryfunc); + +extern int register_ftrace_graph(struct fgraph_ops *ops); +extern void unregister_ftrace_graph(struct fgraph_ops *ops); extern bool ftrace_graph_is_dead(void); extern void ftrace_graph_stop(void); @@ -802,8 +808,6 @@ extern void ftrace_graph_stop(void); extern trace_func_graph_ret_t ftrace_graph_return; extern trace_func_graph_ent_t ftrace_graph_entry; -extern void unregister_ftrace_graph(void); - extern void ftrace_graph_init_task(struct task_struct *t); extern void ftrace_graph_exit_task(struct task_struct *t); extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu); @@ -825,12 +829,9 @@ static inline void ftrace_graph_init_task(struct task_struct *t) { } static inline void ftrace_graph_exit_task(struct task_struct *t) { } static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { } -static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc, - trace_func_graph_ent_t entryfunc) -{ - return -1; -} -static inline void unregister_ftrace_graph(void) { } +/* Define as macros as fgraph_ops may not be defined */ +#define register_ftrace_graph(ops) ({ -1; }) +#define unregister_ftrace_graph(ops) do { } while (0) static inline unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, -- cgit v1.2.3 From b0e21a61d3196762b61f43ae994ffd255f646774 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 20:54:08 -0500 Subject: function_graph: Have profiler use new helper ftrace_graph_get_ret_stack() The ret_stack processing is going to change, and that is going to break anything that is accessing the ret_stack directly. One user is the function graph profiler. By using the ftrace_graph_get_ret_stack() helper function, the profiler can access the ret_stack entry without relying on the implementation details of the stack itself. Reviewed-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 21c80491ccde..98e141c71ad0 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -785,6 +785,9 @@ extern int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp); +struct ftrace_ret_stack * +ftrace_graph_get_ret_stack(struct task_struct *task, int idx); + unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); -- cgit v1.2.3 From 2c2b0a78b373908926e4683ea5571332f63c0eb5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 29 Nov 2018 20:32:26 -0500 Subject: ring-buffer: Add percentage of ring buffer full to wake up reader Instead of just waiting for a page to be full before waking up a pending reader, allow the reader to pass in a "percentage" of pages that have content before waking up a reader. This should help keep the process of reading the events not cause wake ups that constantly cause reading of the buffer. Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 0940fda59872..5b9ae62272bb 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) -int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full); +int ring_buffer_wait(struct ring_buffer *buffer, int cpu, int full); __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table); @@ -189,6 +189,8 @@ bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer); size_t ring_buffer_page_len(void *page); +size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu); +size_t ring_buffer_nr_dirty_pages(struct ring_buffer *buffer, int cpu); void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu); void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data); -- cgit v1.2.3 From fc800a10be26017f8f338bc8e500d48e3e6429d9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 5 Nov 2018 18:00:43 +0900 Subject: tracing: Lock event_mutex before synth_event_mutex synthetic event is using synth_event_mutex for protecting synth_event_list, and event_trigger_write() path acquires locks as below order. event_trigger_write(event_mutex) ->trigger_process_regex(trigger_cmd_mutex) ->event_hist_trigger_func(synth_event_mutex) On the other hand, synthetic event creation and deletion paths call trace_add_event_call() and trace_remove_event_call() which acquires event_mutex. In that case, if we keep the synth_event_mutex locked while registering/unregistering synthetic events, its dependency will be inversed. To avoid this issue, current synthetic event is using a 2 phase process to create/delete events. For example, it searches existing events under synth_event_mutex to check for event-name conflicts, and unlocks synth_event_mutex, then registers a new event under event_mutex locked. Finally, it locks synth_event_mutex and tries to add the new event to the list. But it can introduce complexity and a chance for name conflicts. To solve this simpler, this introduces trace_add_event_call_nolock() and trace_remove_event_call_nolock() which don't acquire event_mutex inside. synthetic event can lock event_mutex before synth_event_mutex to solve the lock dependency issue simpler. Link: http://lkml.kernel.org/r/154140844377.17322.13781091165954002713.stgit@devbox Reviewed-by: Tom Zanussi Tested-by: Tom Zanussi Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 4130a5497d40..3aa05593a53f 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -529,6 +529,8 @@ extern int trace_event_raw_init(struct trace_event_call *call); extern int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type); +extern int trace_add_event_call_nolock(struct trace_event_call *call); +extern int trace_remove_event_call_nolock(struct trace_event_call *call); extern int trace_add_event_call(struct trace_event_call *call); extern int trace_remove_event_call(struct trace_event_call *call); extern int trace_event_get_offsets(struct trace_event_call *call); -- cgit v1.2.3 From 04fa26bab06d9335f15a5d529c4bba25cd507a34 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 8 Dec 2018 16:12:12 +0100 Subject: net: phy: mdio-gpio: Add platform_data support for phy_mask It is sometimes necessary to instantiate a bit-banging MDIO bus as a platform device, without the aid of device tree. When device tree is being used, the bus is not scanned for devices, only those devices which are in device tree are probed. Without device tree, by default, all addresses on the bus are scanned. This may then find a device which is not a PHY, e.g. a switch. And the switch may have registers containing values which look like a PHY. So during the scan, a PHY device is wrongly created. After the bus has been registered, a search is made for mdio_board_info structures which indicates devices on the bus, and the driver which should be used for them. This is typically used to instantiate Ethernet switches from platform drivers. However, if the scanning of the bus has created a PHY device at the same location as indicated into the board info for a switch, the switch device is not created, since the address is already busy. This can be avoided by setting the phy_mask of the mdio bus. This mask prevents addresses on the bus being scanned. v2 Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/platform_data/mdio-gpio.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h new file mode 100644 index 000000000000..a5d5ff5e174c --- /dev/null +++ b/include/linux/platform_data/mdio-gpio.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * MDIO-GPIO bus platform data structure + */ + +#ifndef __LINUX_MDIO_GPIO_PDATA_H +#define __LINUX_MDIO_GPIO_PDATA_H + +struct mdio_gpio_platform_data { + u32 phy_mask; +}; + +#endif /* __LINUX_MDIO_GPIO_PDATA_H */ -- cgit v1.2.3 From dc9d38cec71c508963b8f41c9d6d9cfd7e4ee393 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 8 Dec 2018 16:12:13 +0100 Subject: net: phy: mdio-gpio: Add phy_ignore_ta_mask to platform data The Marvell 6390 Ethernet switch family does not perform MDIO turnaround correctly. Many hardware MDIO bus masters don't care about this, but the bitbangging implementation in Linux does by default. Add phy_ignore_ta_mask to the platform data so that the bitbangging code can be told which devices are known to get TA wrong. v2 Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h index a5d5ff5e174c..13874fa6e767 100644 --- a/include/linux/platform_data/mdio-gpio.h +++ b/include/linux/platform_data/mdio-gpio.h @@ -8,6 +8,7 @@ struct mdio_gpio_platform_data { u32 phy_mask; + u32 phy_ignore_ta_mask; }; #endif /* __LINUX_MDIO_GPIO_PDATA_H */ -- cgit v1.2.3 From c454a46b5efd8eff8880e88ece2976e60a26bf35 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 7 Dec 2018 16:42:25 -0800 Subject: bpf: Add bpf_line_info support This patch adds bpf_line_info support. It accepts an array of bpf_line_info objects during BPF_PROG_LOAD. The "line_info", "line_info_cnt" and "line_info_rec_size" are added to the "union bpf_attr". The "line_info_rec_size" makes bpf_line_info extensible in the future. The new "check_btf_line()" ensures the userspace line_info is valid for the kernel to use. When the verifier is translating/patching the bpf_prog (through "bpf_patch_insn_single()"), the line_infos' insn_off is also adjusted by the newly added "bpf_adj_linfo()". If the bpf_prog is jited, this patch also provides the jited addrs (in aux->jited_linfo) for the corresponding line_info.insn_off. "bpf_prog_fill_jited_linfo()" is added to fill the aux->jited_linfo. It is currently called by the x86 jit. Other jits can also use "bpf_prog_fill_jited_linfo()" and it will be done in the followup patches. In the future, if it deemed necessary, a particular jit could also provide its own "bpf_prog_fill_jited_linfo()" implementation. A few "*line_info*" fields are added to the bpf_prog_info such that the user can get the xlated line_info back (i.e. the line_info with its insn_off reflecting the translated prog). The jited_line_info is available if the prog is jited. It is an array of __u64. If the prog is not jited, jited_line_info_cnt is 0. The verifier's verbose log with line_info will be done in a follow up patch. Signed-off-by: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 21 +++++++++++++++++++++ include/linux/bpf_verifier.h | 1 + include/linux/btf.h | 1 + include/linux/filter.h | 7 +++++++ 4 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e82b7039fc66..0c992b86eb2c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -319,7 +319,28 @@ struct bpf_prog_aux { struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; + /* bpf_line_info loaded from userspace. linfo->insn_off + * has the xlated insn offset. + * Both the main and sub prog share the same linfo. + * The subprog can access its first linfo by + * using the linfo_idx. + */ + struct bpf_line_info *linfo; + /* jited_linfo is the jited addr of the linfo. It has a + * one to one mapping to linfo: + * jited_linfo[i] is the jited addr for the linfo[i]->insn_off. + * Both the main and sub prog share the same jited_linfo. + * The subprog can access its first jited_linfo by + * using the linfo_idx. + */ + void **jited_linfo; u32 func_info_cnt; + u32 nr_linfo; + /* subprog can use linfo_idx to access its first linfo and + * jited_linfo. + * main prog always has linfo_idx == 0 + */ + u32 linfo_idx; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 11f5df1092d9..c736945be7c5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -203,6 +203,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ + u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ }; diff --git a/include/linux/btf.h b/include/linux/btf.h index 8c2199b5d250..b98405a56383 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -46,6 +46,7 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); int btf_get_fd_by_id(u32 id); u32 btf_id(const struct btf *btf); +bool btf_name_offset_valid(const struct btf *btf, u32 offset); #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); diff --git a/include/linux/filter.h b/include/linux/filter.h index d16deead65c6..29f21f9d7f68 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -718,6 +718,13 @@ void bpf_prog_free(struct bpf_prog *fp); bool bpf_opcode_in_insntable(u8 code); +void bpf_prog_free_linfo(struct bpf_prog *prog); +void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, + const u32 *insn_to_jit_off); +int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog); +void bpf_prog_free_jited_linfo(struct bpf_prog *prog); +void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog); + struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); -- cgit v1.2.3 From 6254adeb1f6943a66cbed892a5f683400b9db194 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 4 Dec 2018 18:03:01 -0800 Subject: net/mlx5: Use helper to get CQE opcode Introduce and use a helper that extracts the opcode from a CQE (completion queue entry) structure. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f7c8bebfe472..c66867c8fc2f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -781,6 +781,11 @@ static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) return (cqe->op_own >> 2) & 0x3; } +static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) +{ + return cqe->op_own >> 4; +} + static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro_tcppsh_abort_dupack >> 6) & 1; -- cgit v1.2.3 From 4addd2640fcaeb150b42a8a352b6c9d13d6c00af Mon Sep 17 00:00:00 2001 From: Chanho Min Date: Mon, 10 Dec 2018 16:49:54 +0900 Subject: exec: make prepare_bprm_creds static prepare_bprm_creds is not used outside exec.c, so there's no reason for it to have external linkage. Signed-off-by: Chanho Min Signed-off-by: Al Viro --- include/linux/binfmts.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index e9f5fe69df31..6a9e43d98c3d 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -138,7 +138,6 @@ extern int transfer_args_to_stack(struct linux_binprm *bprm, extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); -extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); -- cgit v1.2.3 From 112f158f66cbe25fd561a5dfe9c3826e06abf757 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 6 Dec 2018 11:41:18 -0500 Subject: block: stop passing 'cpu' to all percpu stats methods All of part_stat_* and related methods are used with preempt disabled, so there is no need to pass cpu around to allow of them. Just call smp_processor_id() as needed. Suggested-by: Jens Axboe Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/genhd.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0c5ee17b4d88..1677cd2a4c4e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -295,8 +295,8 @@ extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, #define part_stat_lock() ({ rcu_read_lock(); get_cpu(); }) #define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) -#define __part_stat_add(cpu, part, field, addnd) \ - (per_cpu_ptr((part)->dkstats, (cpu))->field += (addnd)) +#define __part_stat_add(part, field, addnd) \ + (per_cpu_ptr((part)->dkstats, smp_processor_id())->field += (addnd)) #define part_stat_read(part, field) \ ({ \ @@ -333,7 +333,7 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_lock() ({ rcu_read_lock(); 0; }) #define part_stat_unlock() rcu_read_unlock() -#define __part_stat_add(cpu, part, field, addnd) \ +#define __part_stat_add(part, field, addnd) \ ((part)->dkstats.field += addnd) #define part_stat_read(part, field) ((part)->dkstats.field) @@ -362,19 +362,19 @@ static inline void free_part_stats(struct hd_struct *part) part_stat_read(part, field[STAT_WRITE]) + \ part_stat_read(part, field[STAT_DISCARD])) -#define part_stat_add(cpu, part, field, addnd) do { \ - __part_stat_add((cpu), (part), field, addnd); \ +#define part_stat_add(part, field, addnd) do { \ + __part_stat_add((part), field, addnd); \ if ((part)->partno) \ - __part_stat_add((cpu), &part_to_disk((part))->part0, \ + __part_stat_add(&part_to_disk((part))->part0, \ field, addnd); \ } while (0) -#define part_stat_dec(cpu, gendiskp, field) \ - part_stat_add(cpu, gendiskp, field, -1) -#define part_stat_inc(cpu, gendiskp, field) \ - part_stat_add(cpu, gendiskp, field, 1) -#define part_stat_sub(cpu, gendiskp, field, subnd) \ - part_stat_add(cpu, gendiskp, field, -subnd) +#define part_stat_dec(gendiskp, field) \ + part_stat_add(gendiskp, field, -1) +#define part_stat_inc(gendiskp, field) \ + part_stat_add(gendiskp, field, 1) +#define part_stat_sub(gendiskp, field, subnd) \ + part_stat_add(gendiskp, field, -subnd) void part_in_flight(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]); @@ -399,7 +399,7 @@ static inline void free_part_info(struct hd_struct *part) } /* block/blk-core.c */ -extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part); +extern void part_round_stats(struct request_queue *q, struct hd_struct *part); /* block/genhd.c */ extern void device_add_disk(struct device *parent, struct gendisk *disk, -- cgit v1.2.3 From 5b18b5a737600fd20ba2045f320d5926ebbf341a Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 6 Dec 2018 11:41:19 -0500 Subject: block: delete part_round_stats and switch to less precise counting We want to convert to per-cpu in_flight counters. The function part_round_stats needs the in_flight counter every jiffy, it would be too costly to sum all the percpu variables every jiffy, so it must be deleted. part_round_stats is used to calculate two counters - time_in_queue and io_ticks. time_in_queue can be calculated without part_round_stats, by adding the duration of the I/O when the I/O ends (the value is almost as exact as the previously calculated value, except that time for in-progress I/Os is not counted). io_ticks can be approximated by increasing the value when I/O is started or ended and the jiffies value has changed. If the I/Os take less than a jiffy, the value is as exact as the previously calculated value. If the I/Os take more than a jiffy, io_ticks can drift behind the previously calculated value. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/genhd.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 1677cd2a4c4e..838c2a7a40c5 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -398,8 +398,7 @@ static inline void free_part_info(struct hd_struct *part) kfree(part->info); } -/* block/blk-core.c */ -extern void part_round_stats(struct request_queue *q, struct hd_struct *part); +void update_io_ticks(struct hd_struct *part, unsigned long now); /* block/genhd.c */ extern void device_add_disk(struct device *parent, struct gendisk *disk, -- cgit v1.2.3 From 1226b8dd0e91331cfab500f305b2c264445a0392 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 6 Dec 2018 11:41:20 -0500 Subject: block: switch to per-cpu in-flight counters Now when part_round_stats is gone, we can switch to per-cpu in-flight counters. We use the local-atomic type local_t, so that if part_inc_in_flight or part_dec_in_flight is reentrantly called from an interrupt, the value will be correct. The other counters could be corrupted due to reentrant interrupt, but the corruption only results in slight counter skew - the in_flight counter must be exact, so it needs local_t. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/genhd.h | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 838c2a7a40c5..636b4f687e35 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -17,6 +17,7 @@ #include #include #include +#include #ifdef CONFIG_BLOCK @@ -89,6 +90,7 @@ struct disk_stats { unsigned long merges[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; + local_t in_flight[2]; }; #define PARTITION_META_INFO_VOLNAMELTH 64 @@ -122,7 +124,6 @@ struct hd_struct { int make_it_fail; #endif unsigned long stamp; - atomic_t in_flight[2]; #ifdef CONFIG_SMP struct disk_stats __percpu *dkstats; #else @@ -295,8 +296,11 @@ extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, #define part_stat_lock() ({ rcu_read_lock(); get_cpu(); }) #define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0) -#define __part_stat_add(part, field, addnd) \ - (per_cpu_ptr((part)->dkstats, smp_processor_id())->field += (addnd)) +#define part_stat_get_cpu(part, field, cpu) \ + (per_cpu_ptr((part)->dkstats, (cpu))->field) + +#define part_stat_get(part, field) \ + part_stat_get_cpu(part, field, smp_processor_id()) #define part_stat_read(part, field) \ ({ \ @@ -333,10 +337,9 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_lock() ({ rcu_read_lock(); 0; }) #define part_stat_unlock() rcu_read_unlock() -#define __part_stat_add(part, field, addnd) \ - ((part)->dkstats.field += addnd) - -#define part_stat_read(part, field) ((part)->dkstats.field) +#define part_stat_get(part, field) ((part)->dkstats.field) +#define part_stat_get_cpu(part, field, cpu) part_stat_get(part, field) +#define part_stat_read(part, field) part_stat_get(part, field) static inline void part_stat_set_all(struct hd_struct *part, int value) { @@ -362,6 +365,9 @@ static inline void free_part_stats(struct hd_struct *part) part_stat_read(part, field[STAT_WRITE]) + \ part_stat_read(part, field[STAT_DISCARD])) +#define __part_stat_add(part, field, addnd) \ + (part_stat_get(part, field) += (addnd)) + #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ if ((part)->partno) \ @@ -376,6 +382,15 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(gendiskp, field, subnd) \ part_stat_add(gendiskp, field, -subnd) +#define part_stat_local_dec(gendiskp, field) \ + local_dec(&(part_stat_get(gendiskp, field))) +#define part_stat_local_inc(gendiskp, field) \ + local_inc(&(part_stat_get(gendiskp, field))) +#define part_stat_local_read(gendiskp, field) \ + local_read(&(part_stat_get(gendiskp, field))) +#define part_stat_local_read_cpu(gendiskp, field, cpu) \ + local_read(&(part_stat_get_cpu(gendiskp, field, cpu))) + void part_in_flight(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]); void part_in_flight_rw(struct request_queue *q, struct hd_struct *part, -- cgit v1.2.3 From e016b78201a2d9ff40f3f0da072292689af24c7f Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 6 Dec 2018 11:41:21 -0500 Subject: block: return just one value from part_in_flight The previous patches deleted all the code that needed the second value returned from part_in_flight - now the kernel only uses the first value. Consequently, part_in_flight (and blk_mq_in_flight) may be changed so that it only returns one value. This patch just refactors the code, there's no functional change. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/genhd.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 636b4f687e35..06c0fd594097 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -391,8 +391,7 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_local_read_cpu(gendiskp, field, cpu) \ local_read(&(part_stat_get_cpu(gendiskp, field, cpu))) -void part_in_flight(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]); +unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part); void part_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]); void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, -- cgit v1.2.3 From 7e1413edd6194a9807aa5f3ac0378b9b4b9da879 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 4 Dec 2018 13:35:45 -0500 Subject: tracing: Consolidate trace_add/remove_event_call back to the nolock functions The trace_add/remove_event_call_nolock() functions were added to allow the tace_add/remove_event_call() code be called when the event_mutex lock was already taken. Now that all callers are done within the event_mutex, there's no reason to have two different interfaces. Remove the current wrapper trace_add/remove_event_call()s and rename the _nolock versions back to the original names. Link: http://lkml.kernel.org/r/154140866955.17322.2081425494660638846.stgit@devbox Acked-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3aa05593a53f..4130a5497d40 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -529,8 +529,6 @@ extern int trace_event_raw_init(struct trace_event_call *call); extern int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type); -extern int trace_add_event_call_nolock(struct trace_event_call *call); -extern int trace_remove_event_call_nolock(struct trace_event_call *call); extern int trace_add_event_call(struct trace_event_call *call); extern int trace_remove_event_call(struct trace_event_call *call); extern int trace_event_get_offsets(struct trace_event_call *call); -- cgit v1.2.3 From a0572f687fb3c46e15554f4789797a077cc393b4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 5 Dec 2018 12:48:53 -0500 Subject: ftrace: Allow ftrace_replace_code() to be schedulable The function ftrace_replace_code() is the ftrace engine that does the work to modify all the nops into the calls to the function callback in all the functions being traced. The generic version which is normally called from stop machine, but an architecture can implement a non stop machine version and still use the generic ftrace_replace_code(). When an architecture does this, ftrace_replace_code() may be called from a schedulable context, where it can allow the code to be preemptible, and schedule out. In order to allow an architecture to make ftrace_replace_code() schedulable, a new command flag is added called: FTRACE_MAY_SLEEP Which can be or'd to the command that is passed to ftrace_modify_all_code() that calls ftrace_replace_code() and will have it call cond_resched() in the loop that modifies the nops into the calls to the ftrace trampolines. Link: http://lkml.kernel.org/r/20181204192903.8193-1-anders.roxell@linaro.org Link: http://lkml.kernel.org/r/20181205183303.828422192@goodmis.org Reported-by: Anders Roxell Tested-by: Anders Roxell Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 98e141c71ad0..13485a19e964 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -389,6 +389,7 @@ enum { FTRACE_UPDATE_TRACE_FUNC = (1 << 2), FTRACE_START_FUNC_RET = (1 << 3), FTRACE_STOP_FUNC_RET = (1 << 4), + FTRACE_MAY_SLEEP = (1 << 5), }; /* -- cgit v1.2.3 From 02d31765bb35101d711b862fc619a49857bb9070 Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Mon, 10 Dec 2018 10:29:58 +0100 Subject: led: triggers: Add LED_INIT_DEFAULT_TRIGGER flag Add the flag LED_INIT_DEFAULT_TRIGGER for indicating that trigger being set is a default trigger for the LED class device, and thus it should be initialized with settings provided in the fwnode. Set the flag in the led_trigger_set_default(). It is expected to be cleared in the activate() op of a trigger after trigger fwnode initialization data is parsed and applied. This should happen only once after LED class device registration, to allow leaving triggers in the idle state on re-apply and let the users apply their own settings without interference from the default ones. Signed-off-by: Jacek Anaszewski Acked-by: Pavel Machek Signed-off-by: Krzysztof Kozlowski --- include/linux/leds.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 7393a316d9fa..6f05a5816371 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -51,6 +51,7 @@ struct led_classdev { #define LED_PANIC_INDICATOR BIT(20) #define LED_BRIGHT_HW_CHANGED BIT(21) #define LED_RETAIN_AT_SHUTDOWN BIT(22) +#define LED_INIT_DEFAULT_TRIGGER BIT(23) /* set_brightness_work / blink_timer flags, atomic, private. */ unsigned long work_flags; -- cgit v1.2.3 From 0005aad094538e1c290b1cdb5b940e4a16f405b0 Mon Sep 17 00:00:00 2001 From: Yogesh Narayan Gaur Date: Fri, 12 Oct 2018 02:23:08 +0000 Subject: mtd: spi-nor: add macros related to MICRON flash Some MICRON related macros in spi-nor domain were ST. Rename entries related to STMicroelectronics under macro SNOR_MFR_ST. Added entry of MFR Id for Micron flashes, 0x002C. Signed-off-by: Yogesh Gaur Reviewed-by: Tudor Ambarus Signed-off-by: Boris Brezillon --- include/linux/mtd/cfi.h | 1 + include/linux/mtd/spi-nor.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index 9b57a9b1b081..cbf77168658c 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -377,6 +377,7 @@ struct cfi_fixup { #define CFI_MFR_SHARP 0x00B0 #define CFI_MFR_SST 0x00BF #define CFI_MFR_ST 0x0020 /* STMicroelectronics */ +#define CFI_MFR_MICRON 0x002C /* Micron */ #define CFI_MFR_TOSHIBA 0x0098 #define CFI_MFR_WINBOND 0x00DA diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 7f0c7303575e..8b1acf68b7ac 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -23,7 +23,8 @@ #define SNOR_MFR_ATMEL CFI_MFR_ATMEL #define SNOR_MFR_GIGADEVICE 0xc8 #define SNOR_MFR_INTEL CFI_MFR_INTEL -#define SNOR_MFR_MICRON CFI_MFR_ST /* ST Micro <--> Micron */ +#define SNOR_MFR_ST CFI_MFR_ST /* ST Micro */ +#define SNOR_MFR_MICRON CFI_MFR_MICRON /* Micron */ #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST -- cgit v1.2.3 From 548ed6847f5303e4f33ecd6de5670cac15bfe6ac Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Dec 2018 11:37:34 +0100 Subject: mtd: spi-nor: Add the SNOR_F_4B_OPCODES flag Some flash_info entries have the SPI_NOR_4B_OPCODES flag set to let the core know that the flash supports 4B opcode. While this solution works fine for id-based caps detection, it doesn't work that well when relying on SFDP-based caps detection. Let's add an SNOR_F_4B_OPCODES flag so that the SFDP parsing code can set it when appropriate. Signed-off-by: Boris Brezillon Reviewed-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 8b1acf68b7ac..981d628305a2 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -237,6 +237,7 @@ enum spi_nor_option_flags { SNOR_F_READY_XSR_RDY = BIT(4), SNOR_F_USE_CLSR = BIT(5), SNOR_F_BROKEN_RESET = BIT(6), + SNOR_F_4B_OPCODES = BIT(7), }; /** -- cgit v1.2.3 From e9f3a2bcc3742960e28c8d37165406c6c55500b9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Dec 2018 11:41:20 +0100 Subject: mtd: spi-nor: Add an SPDX tag to spi-nor.{c,h} Add SPDX tags to replace the license boiler-plate and fix the MODULE_LICENSE() definition in spi-nor.c to match the license text (GPL v2). Interestingly, spi-nor.h and spi-nor.c do not use the same license (GPL v2+ for spi-nor.h, GPL v2 for spi-nor.c). Signed-off-by: Boris Brezillon Reviewed-by: Tudor Ambarus --- include/linux/mtd/spi-nor.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 981d628305a2..5f177aa39f68 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -1,10 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (C) 2014 Freescale Semiconductor, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __LINUX_MTD_SPI_NOR_H -- cgit v1.2.3 From 816873eaeec63ba2e58bbd514d15a7efc6e572f7 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Thu, 6 Dec 2018 14:43:39 +0000 Subject: mtd: spi-nor: parse SFDP 4-byte Address Instruction Table Add support for SFDP (JESD216B) 4-byte Address Instruction Table. This table is optional but when available, we parse it to get the 4-byte address op codes supported by the memory. Using these op codes is stateless as opposed to entering the 4-byte address mode or setting the Base Address Register (BAR). Flashes that have the 4BAIT table declared can now support SPINOR_OP_PP_1_1_4_4B and SPINOR_OP_PP_1_4_4_4B opcodes. Tested on MX25L25673G. Signed-off-by: Cyrille Pitchen [tudor.ambarus@microchip.com: - rework erase and page program logic, - pass DMA-able buffer to spi_nor_read_sfdp(), - introduce SPI_NOR_HAS_4BAIT - various minor updates.] Signed-off-by: Tudor Ambarus Signed-off-by: Boris Brezillon --- include/linux/mtd/spi-nor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 5f177aa39f68..fa2d89e38e40 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -234,6 +234,7 @@ enum spi_nor_option_flags { SNOR_F_USE_CLSR = BIT(5), SNOR_F_BROKEN_RESET = BIT(6), SNOR_F_4B_OPCODES = BIT(7), + SNOR_F_HAS_4BAIT = BIT(8), }; /** -- cgit v1.2.3 From fd4572b3ff3ff57ca7fa612f9ea42b90afdd8bff Mon Sep 17 00:00:00 2001 From: Eyal Davidovich Date: Mon, 10 Dec 2018 13:15:12 -0800 Subject: net/mlx5: Add monitor commands layout and event data Will be used in downstream patch to monitor counter changes by the HCA and report it to the driver by an event. The driver will update its counters cached data accordingly. Signed-off-by: Eyal Davidovich Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 1 + include/linux/mlx5/mlx5_ifc.h | 87 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 87 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index c66867c8fc2f..4674b9e99f45 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -330,6 +330,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_TEMP_WARN_EVENT = 0x17, MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19, MLX5_EVENT_TYPE_GENERAL_EVENT = 0x22, + MLX5_EVENT_TYPE_MONITOR_COUNTER = 0x24, MLX5_EVENT_TYPE_PPS_EVENT = 0x25, MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 91d6e85e3cef..9f7cc26bfb3b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -161,6 +161,8 @@ enum { MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771, MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772, MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773, + MLX5_CMD_OP_SET_MONITOR_COUNTER = 0x774, + MLX5_CMD_OP_ARM_MONITOR_COUNTER = 0x775, MLX5_CMD_OP_SET_PP_RATE_LIMIT = 0x780, MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781, MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782, @@ -1200,7 +1202,13 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 sw_owner_id[0x1]; u8 reserved_at_61f[0x1]; - u8 reserved_at_620[0x80]; + u8 max_num_of_monitor_counters[0x10]; + u8 num_ppcnt_monitor_counters[0x10]; + + u8 reserved_at_640[0x10]; + u8 num_q_monitor_counters[0x10]; + + u8 reserved_at_660[0x40]; u8 uctx_cap[0x20]; @@ -3808,6 +3816,83 @@ enum { MLX5_VPORT_STATE_OP_MOD_ESW_VPORT = 0x1, }; +struct mlx5_ifc_arm_monitor_counter_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_arm_monitor_counter_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +enum { + MLX5_QUERY_MONITOR_CNT_TYPE_PPCNT = 0x0, + MLX5_QUERY_MONITOR_CNT_TYPE_Q_COUNTER = 0x1, +}; + +enum mlx5_monitor_counter_ppcnt { + MLX5_QUERY_MONITOR_PPCNT_IN_RANGE_LENGTH_ERRORS = 0X0, + MLX5_QUERY_MONITOR_PPCNT_OUT_OF_RANGE_LENGTH_FIELD = 0X1, + MLX5_QUERY_MONITOR_PPCNT_FRAME_TOO_LONG_ERRORS = 0X2, + MLX5_QUERY_MONITOR_PPCNT_FRAME_CHECK_SEQUENCE_ERRORS = 0X3, + MLX5_QUERY_MONITOR_PPCNT_ALIGNMENT_ERRORS = 0X4, + MLX5_QUERY_MONITOR_PPCNT_IF_OUT_DISCARDS = 0X5, +}; + +enum { + MLX5_QUERY_MONITOR_Q_COUNTER_RX_OUT_OF_BUFFER = 0X4, +}; + +struct mlx5_ifc_monitor_counter_output_bits { + u8 reserved_at_0[0x4]; + u8 type[0x4]; + u8 reserved_at_8[0x8]; + u8 counter[0x10]; + + u8 counter_group_id[0x20]; +}; + +#define MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 (6) +#define MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1 (1) +#define MLX5_CMD_SET_MONITOR_NUM_COUNTER (MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 +\ + MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1) + +struct mlx5_ifc_set_monitor_counter_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 num_of_counters[0x10]; + + u8 reserved_at_60[0x20]; + + struct mlx5_ifc_monitor_counter_output_bits monitor_counter[MLX5_CMD_SET_MONITOR_NUM_COUNTER]; +}; + +struct mlx5_ifc_set_monitor_counter_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_query_vport_state_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; -- cgit v1.2.3 From 5886a96ad19dacebe6c4f7f8c001d489b06125dc Mon Sep 17 00:00:00 2001 From: Oz Shlomo Date: Mon, 10 Dec 2018 13:15:13 -0800 Subject: net/mlx5: Revise gre and nvgre key formats GRE RFC defines a 32 bit key field. NVGRE RFC splits the 32 bit key field to 24 bit VSID (gre_key_h) and 8 bit flow entropy (gre_key_l). Define the two key parsing alternatives in a union, thus enabling both access methods. Signed-off-by: Oz Shlomo Reviewed-by: Eli Britstein Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9f7cc26bfb3b..688a549e74f1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -423,6 +423,16 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; }; +struct mlx5_ifc_nvgre_key_bits { + u8 hi[0x18]; + u8 lo[0x8]; +}; + +union mlx5_ifc_gre_key_bits { + struct mlx5_ifc_nvgre_key_bits nvgre; + u8 key[0x20]; +}; + struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_0[0x8]; u8 source_sqn[0x18]; @@ -444,8 +454,7 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_64[0xc]; u8 gre_protocol[0x10]; - u8 gre_key_h[0x18]; - u8 gre_key_l[0x8]; + union mlx5_ifc_gre_key_bits gre_key; u8 vxlan_vni[0x18]; u8 reserved_at_b8[0x8]; -- cgit v1.2.3 From 1b115498598f25d578cfc0df7b7aea9772bae0a1 Mon Sep 17 00:00:00 2001 From: Eli Britstein Date: Mon, 10 Dec 2018 13:15:14 -0800 Subject: net/mlx5: Introduce extended destination fields Extended destinations provide the ability to configure different encapsulation properties per destination on a single FTE. This is needed for use-cases such as remote mirroring over tunneled networks. Signed-off-by: Eli Britstein Reviewed-by: Or Gerlitz Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 688a549e74f1..60c1d49eb40c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -621,7 +621,9 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vxlan_encap_decap[0x1]; u8 nvgre_encap_decap[0x1]; - u8 reserved_at_22[0x9]; + u8 reserved_at_22[0x1]; + u8 log_max_fdb_encap_uplink[0x5]; + u8 reserved_at_21[0x3]; u8 log_max_packet_reformat_context[0x5]; u8 reserved_2b[0x6]; u8 max_encap_header_size[0xa]; @@ -1237,8 +1239,10 @@ enum mlx5_flow_destination_type { struct mlx5_ifc_dest_format_struct_bits { u8 destination_type[0x8]; u8 destination_id[0x18]; + u8 destination_eswitch_owner_vhca_id_valid[0x1]; - u8 reserved_at_21[0xf]; + u8 packet_reformat[0x1]; + u8 reserved_at_22[0xe]; u8 destination_eswitch_owner_vhca_id[0x10]; }; @@ -1248,6 +1252,14 @@ struct mlx5_ifc_flow_counter_list_bits { u8 reserved_at_20[0x20]; }; +struct mlx5_ifc_extended_dest_format_bits { + struct mlx5_ifc_dest_format_struct_bits destination_entry; + + u8 packet_reformat_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits { struct mlx5_ifc_dest_format_struct_bits dest_format_struct; struct mlx5_ifc_flow_counter_list_bits flow_counter_list; @@ -2469,7 +2481,8 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_60[0x10]; u8 action[0x10]; - u8 reserved_at_80[0x8]; + u8 extended_destination[0x1]; + u8 reserved_at_80[0x7]; u8 destination_list_size[0x18]; u8 reserved_at_a0[0x8]; -- cgit v1.2.3 From aa39c2c0e44d16b5804f8fb6b5350cdf4e33b4c3 Mon Sep 17 00:00:00 2001 From: Eli Britstein Date: Mon, 10 Dec 2018 13:15:15 -0800 Subject: net/mlx5: E-Switch, Change vhca id valid bool field to bit flag Change the driver flow destination struct to use bit flags with the vhca id valid being the 1st one. The flags field is more extendable and will be used in downstream patch. Signed-off-by: Eli Britstein Reviewed-by: Or Gerlitz Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 5660f07d3be0..25ffd8018b72 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -86,6 +86,10 @@ struct mlx5_flow_spec { u32 match_value[MLX5_ST_SZ_DW(fte_match_param)]; }; +enum { + MLX5_FLOW_DEST_VPORT_VHCA_ID = BIT(0), +}; + struct mlx5_flow_destination { enum mlx5_flow_destination_type type; union { @@ -96,7 +100,7 @@ struct mlx5_flow_destination { struct { u16 num; u16 vhca_id; - bool vhca_id_valid; + u8 flags; } vport; }; }; -- cgit v1.2.3 From a2c6162b12f15fbbbe38d0eb3a38186bcfc79c0f Mon Sep 17 00:00:00 2001 From: Eli Britstein Date: Mon, 10 Dec 2018 13:15:16 -0800 Subject: net/mlx5: Support extended destination format in flow steering command Update the flow steering command formatting according to the extended destination API. Note that the FW dictates that multi destination FTEs that involve at least one encap must use the extended destination format, while single destination ones must use the legacy format. Using extended destination format requires FW support. Check for its capabilities and return error if not supported. Signed-off-by: Eli Britstein Reviewed-by: Or Gerlitz Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 25ffd8018b72..9df51da04621 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -88,6 +88,7 @@ struct mlx5_flow_spec { enum { MLX5_FLOW_DEST_VPORT_VHCA_ID = BIT(0), + MLX5_FLOW_DEST_VPORT_REFORMAT_ID = BIT(1), }; struct mlx5_flow_destination { @@ -100,6 +101,7 @@ struct mlx5_flow_destination { struct { u16 num; u16 vhca_id; + u32 reformat_id; u8 flags; } vport; }; -- cgit v1.2.3 From 6c22a11957f46ca7e9b8db20ac7c6b05441c55ed Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Mon, 10 Dec 2018 13:15:17 -0800 Subject: net/mlx5: Remove the get protocol device interface entry This isn't used anywhere across the mlx5 driver stack, remove it. Signed-off-by: Or Gerlitz Reviewed-by: Saeed Mahameed Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 584d8a5df7eb..cc29e880c733 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1004,12 +1004,10 @@ struct mlx5_interface { void (*remove)(struct mlx5_core_dev *dev, void *context); int (*attach)(struct mlx5_core_dev *dev, void *context); void (*detach)(struct mlx5_core_dev *dev, void *context); - void * (*get_dev)(void *context); int protocol; struct list_head list; }; -void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); -- cgit v1.2.3 From fe6c473e3e41114301bfbf5710be56bf0eb233dc Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 6 Dec 2018 13:43:42 +0100 Subject: gpio: Export gpiod_get_from_of_node() This function already exist inside gpiolib, we were just reluctant to make it available to the kernel at large as the devm_* seemed to be enough for anyone. However we found out that regulators need to do their own lifecycle/refcounting on GPIO descriptors and explicitly call gpiod_put() when done with a descriptor, so export this function so we can hand the refcounting over to the regulator core for these descriptors after retrieveal. Signed-off-by: Linus Walleij Reviewed-by: Marek Szyprowski Tested-by: Marek Szyprowski Reviewed-by: Charles Keepax Signed-off-by: Mark Brown --- include/linux/gpio/consumer.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index f2f887795d43..348885f2f3d3 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -172,6 +172,10 @@ int desc_to_gpio(const struct gpio_desc *desc); struct device_node; struct fwnode_handle; +struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, + const char *propname, int index, + enum gpiod_flags dflags, + const char *label); struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, struct device_node *node, const char *propname, int index, @@ -517,6 +521,15 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) struct device_node; struct fwnode_handle; +static inline +struct gpio_desc *gpiod_get_from_of_node(struct device_node *node, + const char *propname, int index, + enum gpiod_flags dflags, + const char *label) +{ + return ERR_PTR(-ENOSYS); +} + static inline struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, struct device_node *node, -- cgit v1.2.3 From 891ddbc79a61eb5b919cf56202ecaf7259878cb2 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 6 Dec 2018 13:43:46 +0100 Subject: gpio: Add devm_gpiod_unhinge() This adds a function named devm_gpiod_unhinge() that removes the resource management from a GPIO descriptor. I am not sure if this is the best anglosaxon name for the function, no other managed resources have an equivalent currently, but I chose "unhinge" as the closest intuitive thing I could imagine that fits Rusty Russell's API design criterions "the obvious use is the correct one" and "the name tells you how to use it". The idea came out of a remark from Mark Brown that it should be possible to handle over management of a resource from devres to the regulator core, and indeed we can do that. Signed-off-by: Linus Walleij Reviewed-by: Marek Szyprowski Tested-by: Marek Szyprowski Reviewed-by: Charles Keepax Signed-off-by: Mark Brown --- include/linux/gpio/consumer.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 348885f2f3d3..8aebcf822082 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -104,6 +104,7 @@ struct gpio_descs *__must_check devm_gpiod_get_array_optional(struct device *dev, const char *con_id, enum gpiod_flags flags); void devm_gpiod_put(struct device *dev, struct gpio_desc *desc); +void devm_gpiod_unhinge(struct device *dev, struct gpio_desc *desc); void devm_gpiod_put_array(struct device *dev, struct gpio_descs *descs); int gpiod_get_direction(struct gpio_desc *desc); @@ -249,6 +250,15 @@ static inline void gpiod_put(struct gpio_desc *desc) WARN_ON(1); } +static inline void devm_gpiod_unhinge(struct device *dev, + struct gpio_desc *desc) +{ + might_sleep(); + + /* GPIO can never have been requested */ + WARN_ON(1); +} + static inline void gpiod_put_array(struct gpio_descs *descs) { might_sleep(); -- cgit v1.2.3 From 014abe34a9095daaa6cbb2693ee90bbb54674693 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Mon, 15 Oct 2018 17:02:57 +0800 Subject: usb: chipidea: add flag for imx hsic implementation NXP (Freecale) imx HSIC design has some special requirements, add some flags at host code to handle them. Reviewed-by: Frieder Schrempf Tested-by: Frieder Schrempf Signed-off-by: Peter Chen --- include/linux/usb/chipidea.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 63758c399e4e..911e05af671e 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -60,9 +60,12 @@ struct ci_hdrc_platform_data { #define CI_HDRC_OVERRIDE_RX_BURST BIT(11) #define CI_HDRC_OVERRIDE_PHY_CONTROL BIT(12) /* Glue layer manages phy */ #define CI_HDRC_REQUIRES_ALIGNED_DMA BIT(13) +#define CI_HDRC_IMX_IS_HSIC BIT(14) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 +#define CI_HDRC_IMX_HSIC_ACTIVE_EVENT 2 +#define CI_HDRC_IMX_HSIC_SUSPEND_EVENT 3 int (*notify_event) (struct ci_hdrc *ci, unsigned event); struct regulator *reg_vbus; struct usb_otg_caps ci_otg_caps; -- cgit v1.2.3 From 83f8ca45afbf041e312909f442128b99657d90b7 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 5 Dec 2018 12:05:53 +0100 Subject: PM / devfreq: add support for suspend/resume of a devfreq device The patch prepares devfreq device for handling suspend/resume functionality. The new fields will store needed information during this process. Devfreq framework handles opp-suspend DT entry and there is no need of modyfications in the drivers code. It uses atomic variables to make sure no race condition affects the process. Suggested-by: Tobias Jakobi Suggested-by: Chanwoo Choi Signed-off-by: Lukasz Luba Reviewed-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index e4963b0f45da..d98519996927 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -131,6 +131,9 @@ struct devfreq_dev_profile { * @scaling_min_freq: Limit minimum frequency requested by OPP interface * @scaling_max_freq: Limit maximum frequency requested by OPP interface * @stop_polling: devfreq polling status of a device. + * @suspend_freq: frequency of a device set during suspend phase. + * @resume_freq: frequency of a device set in resume phase. + * @suspend_count: suspend requests counter for a device. * @total_trans: Number of devfreq transitions * @trans_table: Statistics of devfreq transitions * @time_in_state: Statistics of devfreq states @@ -167,6 +170,10 @@ struct devfreq { unsigned long scaling_max_freq; bool stop_polling; + unsigned long suspend_freq; + unsigned long resume_freq; + atomic_t suspend_count; + /* information for device frequency transition */ unsigned int total_trans; unsigned int *trans_table; -- cgit v1.2.3 From 5903195605287681f55094bbcdf8711ea109969b Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 5 Dec 2018 12:05:54 +0100 Subject: PM / devfreq: add devfreq_suspend/resume() functions This patch adds implementation for global suspend/resume for devfreq framework. System suspend will next use these functions. Suggested-by: Tobias Jakobi Suggested-by: Chanwoo Choi Signed-off-by: Lukasz Luba Reviewed-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index d98519996927..fbffa74bfc1b 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -205,6 +205,9 @@ extern void devm_devfreq_remove_device(struct device *dev, extern int devfreq_suspend_device(struct devfreq *devfreq); extern int devfreq_resume_device(struct devfreq *devfreq); +extern void devfreq_suspend(void); +extern void devfreq_resume(void); + /** * update_devfreq() - Reevaluate the device and configure frequency * @devfreq: the devfreq device @@ -331,6 +334,9 @@ static inline int devfreq_resume_device(struct devfreq *devfreq) return 0; } +static inline void devfreq_suspend(void) {} +static inline void devfreq_resume(void) {} + static inline struct dev_pm_opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq, u32 flags) { -- cgit v1.2.3 From 765b6a98c1de3d84dfdae344cc4ee4c24d9447f7 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:58:55 +0800 Subject: iommu/vt-d: Enumerate the scalable mode capability The Intel vt-d spec rev3.0 introduces a new translation mode called scalable mode, which enables PASID-granular translations for first level, second level, nested and pass-through modes. At the same time, the previous Extended Context (ECS) mode is deprecated (no production ever implements ECS). This patch adds enumeration for Scalable Mode and removes the deprecated ECS enumeration. It provides a boot time option to disable scalable mode even hardware claims to support it. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Ashok Raj Reviewed-by: Kevin Tian Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index a58bc05d6798..8c9b6063d275 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -177,6 +177,7 @@ * Extended Capability Register */ +#define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) ((e >> 41) & 0x1) #define ecap_pasid(e) ((e >> 40) & 0x1) #define ecap_pss(e) ((e >> 35) & 0x1f) -- cgit v1.2.3 From 4f2ed183cfebf42b29ed8fe442169de97bc0fe61 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:58:57 +0800 Subject: iommu/vt-d: Move page table helpers into header So that they could also be used in other source files. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Cc: Sanjay Kumar Signed-off-by: Lu Baolu Reviewed-by: Ashok Raj Reviewed-by: Kevin Tian Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 8c9b6063d275..b4da61385ebf 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -590,6 +590,49 @@ static inline void __iommu_flush_cache( clflush_cache_range(addr, size); } +/* + * 0: readable + * 1: writable + * 2-6: reserved + * 7: super page + * 8-10: available + * 11: snoop behavior + * 12-63: Host physcial address + */ +struct dma_pte { + u64 val; +}; + +static inline void dma_clear_pte(struct dma_pte *pte) +{ + pte->val = 0; +} + +static inline u64 dma_pte_addr(struct dma_pte *pte) +{ +#ifdef CONFIG_64BIT + return pte->val & VTD_PAGE_MASK; +#else + /* Must have a full atomic 64-bit read */ + return __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK; +#endif +} + +static inline bool dma_pte_present(struct dma_pte *pte) +{ + return (pte->val & 3) != 0; +} + +static inline bool dma_pte_superpage(struct dma_pte *pte) +{ + return (pte->val & DMA_PTE_LARGE_PAGE); +} + +static inline int first_pte_in_page(struct dma_pte *pte) +{ + return !((unsigned long)pte & ~VTD_PAGE_MASK); +} + extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); extern int dmar_find_matched_atsr_unit(struct pci_dev *dev); -- cgit v1.2.3 From 5d308fc1ecf5351418a4f003ccb74dc91b424bd1 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:58:58 +0800 Subject: iommu/vt-d: Add 256-bit invalidation descriptor support Intel vt-d spec rev3.0 requires software to use 256-bit descriptors in invalidation queue. As the spec reads in section 6.5.2: Remapping hardware supporting Scalable Mode Translations (ECAP_REG.SMTS=1) allow software to additionally program the width of the descriptors (128-bits or 256-bits) that will be written into the Queue. Software should setup the Invalidation Queue for 256-bit descriptors before progra- mming remapping hardware for scalable-mode translation as 128-bit descriptors are treated as invalid descriptors (see Table 21 in Section 6.5.2.10) in scalable-mode. This patch adds 256-bit invalidation descriptor support if the hardware presents scalable mode capability. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b4da61385ebf..08ff588a4df7 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -401,13 +401,18 @@ enum { #define QI_GRAN_NONG_PASID 2 #define QI_GRAN_PSI_PASID 3 +#define qi_shift(iommu) (DMAR_IQ_SHIFT + !!ecap_smts((iommu)->ecap)) + struct qi_desc { - u64 low, high; + u64 qw0; + u64 qw1; + u64 qw2; + u64 qw3; }; struct q_inval { raw_spinlock_t q_lock; - struct qi_desc *desc; /* invalidation queue */ + void *desc; /* invalidation queue */ int *desc_status; /* desc status */ int free_head; /* first free entry */ int free_tail; /* last free entry */ -- cgit v1.2.3 From 6f7db75e1c469057fe7588ed959328ead771ccc7 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:59:00 +0800 Subject: iommu/vt-d: Add second level page table interface This adds the interfaces to setup or tear down the structures for second level page table translations. This includes types of second level only translation and pass through. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Ashok Raj Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 08ff588a4df7..cb3ebda47fa7 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -177,6 +177,8 @@ * Extended Capability Register */ +#define ecap_smpwc(e) (((e) >> 48) & 0x1) +#define ecap_slts(e) (((e) >> 46) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) ((e >> 41) & 0x1) #define ecap_pasid(e) ((e >> 40) & 0x1) @@ -662,6 +664,7 @@ void free_pgtable_page(void *vaddr); struct intel_iommu *domain_get_iommu(struct dmar_domain *domain); int for_each_device_domain(int (*fn)(struct device_domain_info *info, void *data), void *data); +void iommu_flush_write_buffer(struct intel_iommu *iommu); #ifdef CONFIG_INTEL_IOMMU_SVM int intel_svm_init(struct intel_iommu *iommu); -- cgit v1.2.3 From 7373a8cc381978cfafa4b0285cdd935682f1b2d2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:59:03 +0800 Subject: iommu/vt-d: Setup context and enable RID2PASID support This patch enables the translation for requests without PASID in the scalable mode by setting up the root and context entries. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Ashok Raj Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index cb3ebda47fa7..5fdd33ed2cce 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -258,6 +258,7 @@ /* DMA_RTADDR_REG */ #define DMA_RTADDR_RTT (((u64)1) << 11) +#define DMA_RTADDR_SMT (((u64)1) << 10) /* CCMD_REG */ #define DMA_CCMD_ICC (((u64)1) << 63) -- cgit v1.2.3 From 437f35e1cd4c8d043633bb72f4260369af68fbf7 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:59:04 +0800 Subject: iommu/vt-d: Add first level page table interface This adds an interface to setup the PASID entries for first level page table translation. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Ashok Raj Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 5fdd33ed2cce..4ad62396e81e 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -178,6 +178,7 @@ */ #define ecap_smpwc(e) (((e) >> 48) & 0x1) +#define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) ((e >> 41) & 0x1) -- cgit v1.2.3 From 1c4f88b7f1f9298b56c7dac18c0bcd8d2f75059a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:59:05 +0800 Subject: iommu/vt-d: Shared virtual address in scalable mode This patch enables the current SVA (Shared Virtual Address) implementation to work in the scalable mode. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu Reviewed-by: Ashok Raj Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4ad62396e81e..cfcf9c1e1872 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -54,14 +54,7 @@ #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 #define CONTEXT_TT_PASS_THROUGH 2 -/* Extended context entry types */ -#define CONTEXT_TT_PT_PASID 4 -#define CONTEXT_TT_PT_PASID_DEV_IOTLB 5 -#define CONTEXT_TT_MASK (7ULL << 2) - -#define CONTEXT_DINVE (1ULL << 8) -#define CONTEXT_PRS (1ULL << 9) -#define CONTEXT_PASIDE (1ULL << 11) +#define CONTEXT_PASIDE BIT_ULL(3) /* * Intel IOMMU register specification per version 1.0 public spec. -- cgit v1.2.3 From 6d68b88e0993d67e9ebb1240f84240b712fbc8a4 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 10 Dec 2018 09:59:06 +0800 Subject: iommu/vt-d: Remove deferred invalidation Deferred invalidation is an ECS specific feature. It will not be supported when IOMMU works in scalable mode. As we deprecated the ECS support, remove deferred invalidation and cleanup the code. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Cc: Sanjay Kumar Signed-off-by: Lu Baolu Reviewed-by: Ashok Raj Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index cfcf9c1e1872..0605f3bf6e79 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -541,15 +541,8 @@ struct intel_iommu { struct iommu_flush flush; #endif #ifdef CONFIG_INTEL_IOMMU_SVM - /* These are large and need to be contiguous, so we allocate just - * one for now. We'll maybe want to rethink that if we truly give - * devices away to userspace processes (e.g. for DPDK) and don't - * want to trust that userspace will use *only* the PASID it was - * told to. But while it's all driver-arbitrated, we're fine. */ - struct pasid_state_entry *pasid_state_table; struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ - u32 pasid_max; #endif struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ @@ -663,7 +656,6 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu); #ifdef CONFIG_INTEL_IOMMU_SVM int intel_svm_init(struct intel_iommu *iommu); -int intel_svm_exit(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); -- cgit v1.2.3 From 6191706246de99ff2fac4b6f157f20205a0943cd Mon Sep 17 00:00:00 2001 From: Nayna Jain Date: Tue, 9 Oct 2018 23:00:36 +0530 Subject: ima: add support for arch specific policies Builtin IMA policies can be enabled on the boot command line, and replaced with a custom policy, normally during early boot in the initramfs. Build time IMA policy rules were recently added. These rules are automatically enabled on boot and persist after loading a custom policy. There is a need for yet another type of policy, an architecture specific policy, which is derived at runtime during kernel boot, based on the runtime secure boot flags. Like the build time policy rules, these rules persist after loading a custom policy. This patch adds support for loading an architecture specific IMA policy. Signed-off-by: Nayna Jain Co-Developed-by: Mimi Zohar Signed-off-by: Mimi Zohar --- include/linux/ima.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 948135fb60f1..62c5241b0899 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -39,6 +39,11 @@ static inline bool arch_ima_get_secureboot(void) } #endif +static inline const char * const *arch_get_ima_policy(void) +{ + return NULL; +} + #else static inline int ima_bprm_check(struct linux_binprm *bprm) { -- cgit v1.2.3 From d958083a8f6408e76850bc7394976050d7e43173 Mon Sep 17 00:00:00 2001 From: Eric Richter Date: Tue, 9 Oct 2018 23:00:37 +0530 Subject: x86/ima: define arch_get_ima_policy() for x86 On x86, there are two methods of verifying a kexec'ed kernel image signature being loaded via the kexec_file_load syscall - an architecture specific implementaton or a IMA KEXEC_KERNEL_CHECK appraisal rule. Neither of these methods verify the kexec'ed kernel image signature being loaded via the kexec_load syscall. Secure boot enabled systems require kexec images to be signed. Therefore, this patch loads an IMA KEXEC_KERNEL_CHECK policy rule on secure boot enabled systems not configured with CONFIG_KEXEC_VERIFY_SIG enabled. When IMA_APPRAISE_BOOTPARAM is configured, different IMA appraise modes (eg. fix, log) can be specified on the boot command line, allowing unsigned or invalidly signed kernel images to be kexec'ed. This patch permits enabling IMA_APPRAISE_BOOTPARAM or IMA_ARCH_POLICY, but not both. Signed-off-by: Eric Richter Signed-off-by: Nayna Jain Cc: David Howells Cc: Eric Biederman Cc: Peter Jones Cc: Vivek Goyal Cc: Dave Young Signed-off-by: Mimi Zohar --- include/linux/ima.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 62c5241b0899..5ab9134d4fd7 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -32,17 +32,18 @@ extern void ima_add_kexec_buffer(struct kimage *image); #ifdef CONFIG_X86 extern bool arch_ima_get_secureboot(void); +extern const char * const *arch_get_ima_policy(void); #else static inline bool arch_ima_get_secureboot(void) { return false; } -#endif static inline const char * const *arch_get_ima_policy(void) { return NULL; } +#endif #else static inline int ima_bprm_check(struct linux_binprm *bprm) -- cgit v1.2.3 From 399574c64eaf94e82b7cf056978d7e68748c0f1d Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Sun, 18 Nov 2018 04:08:12 -0500 Subject: x86/ima: retry detecting secure boot mode The secure boot mode may not be detected on boot for some reason (eg. buggy firmware). This patch attempts one more time to detect the secure boot mode. Signed-off-by: Mimi Zohar --- include/linux/ima.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 5ab9134d4fd7..b5e16b8c50b7 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -30,7 +30,7 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern void ima_add_kexec_buffer(struct kimage *image); #endif -#ifdef CONFIG_X86 +#if defined(CONFIG_X86) && defined(CONFIG_EFI) extern bool arch_ima_get_secureboot(void); extern const char * const *arch_get_ima_policy(void); #else -- cgit v1.2.3 From 0cb0e25e421436a83ee39857923e4213b983e463 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 10 Dec 2018 14:00:32 +0000 Subject: dma/debug: Remove dma_debug_resize_entries() With the only caller now gone, we can clean up this part of dma-debug's exposed internals and make way to tweak the allocation behaviour. Signed-off-by: Robin Murphy Tested-by: Qian Cai Signed-off-by: Christoph Hellwig --- include/linux/dma-debug.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 30213adbb6b9..46e6131a72b6 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -30,8 +30,6 @@ struct bus_type; extern void dma_debug_add_bus(struct bus_type *bus); -extern int dma_debug_resize_entries(u32 num_entries); - extern void debug_dma_map_single(struct device *dev, const void *addr, unsigned long len); @@ -101,11 +99,6 @@ static inline void dma_debug_add_bus(struct bus_type *bus) { } -static inline int dma_debug_resize_entries(u32 num_entries) -{ - return 0; -} - static inline void debug_dma_map_single(struct device *dev, const void *addr, unsigned long len) { -- cgit v1.2.3 From 2421b7f3573babfe1673a5ffee1677a5013e6df1 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 19 Nov 2018 13:55:10 -0500 Subject: locking/lockdep: Remove ::version from lock_class structure It turns out the version field in the lock_class structure isn't used anywhere. Just remove it. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Andrey Ryabinin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Petr Mladek Cc: Sasha Levin Cc: Sergey Senozhatsky Cc: Tejun Heo Cc: Thomas Gleixner Cc: Will Deacon Cc: iommu@lists.linux-foundation.org Cc: kasan-dev@googlegroups.com Link: https://lkml.kernel.org/r/1542653726-5655-2-git-send-email-longman@redhat.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1fd82ff99c65..c5335df2372f 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -97,8 +97,6 @@ struct lock_class { * Generation counter, when doing certain classes of graph walking, * to ensure that we check one node only once: */ - unsigned int version; - int name_version; const char *name; -- cgit v1.2.3 From 43b9e4febc66b98d83cc1560196d56ac7fef3c32 Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Tue, 27 Nov 2018 14:43:32 +0530 Subject: perf/core: Declare the __percpu attribute on non-deref types Sparse reports the current declaration of two perf percpu variables with this warning: warning: incorrect type in initializer (different address spaces) expected void const [noderef] *__vpp_verify got struct perf_cpu_context * While it's normally perfectly fine to place GCC attributes anywhere in the definition, this particular attribute is for a checking compiler's such as Sparse's benefit, which doesn't want __percpu on pointers. So reorder the attribute to come after the structure type, not after the pointer type. [ mingo: Rewrote the changelog. ] Signed-off-by: Mukesh Ojha Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/1543310012-7967-1-git-send-email-mojha@codeaurora.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 53c500f0ca79..1d5c551a5add 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -262,8 +262,8 @@ struct pmu { */ int capabilities; - int * __percpu pmu_disable_count; - struct perf_cpu_context * __percpu pmu_cpu_context; + int __percpu *pmu_disable_count; + struct perf_cpu_context __percpu *pmu_cpu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; -- cgit v1.2.3 From 765d0af19f5f388a34bf4533378f8398b72ded46 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 29 Aug 2018 15:19:11 +0200 Subject: sched/topology: Remove the ::smt_gain field from 'struct sched_domain' ::smt_gain is used to compute the capacity of CPUs of a SMT core with the constraint 1 < ::smt_gain < 2 in order to be able to compute number of CPUs per core. The field has_free_capacity of struct numa_stat, which was the last user of this computation of number of CPUs per core, has been removed by: 2d4056fafa19 ("sched/numa: Remove numa_has_capacity()") We can now remove this constraint on core capacity and use the defautl value SCHED_CAPACITY_SCALE for SMT CPUs. With this remove, SCHED_CAPACITY_SCALE becomes the maximum compute capacity of CPUs on every systems. This should help to simplify some code and remove fields like rd->max_cpu_capacity Furthermore, arch_scale_cpu_capacity() is used with a NULL sd in several other places in the code when it wants the capacity of a CPUs to scale some metrics like in pelt, deadline or schedutil. In case on SMT, the value returned is not the capacity of SMT CPUs but default SCHED_CAPACITY_SCALE. So remove it. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1535548752-4434-4-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 6b9976180c1e..7fa0bc17cd8c 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -89,7 +89,6 @@ struct sched_domain { unsigned int newidle_idx; unsigned int wake_idx; unsigned int forkexec_idx; - unsigned int smt_gain; int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ -- cgit v1.2.3 From 5bd0988be12733a42a1a3d50e3e2ddfd79e57518 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:14 +0000 Subject: sched/topology: Relocate arch_scale_cpu_capacity() to the internal header By default, arch_scale_cpu_capacity() is only visible from within the kernel/sched folder. Relocate it to include/linux/sched/topology.h to make it visible to other clients needing to know about the capacity of CPUs, such as the Energy Model framework. This also shrinks the public header. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-2-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7fa0bc17cd8c..c31d3a47a47c 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -201,6 +201,14 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl); # define SD_INIT_NAME(type) #endif +#ifndef arch_scale_cpu_capacity +static __always_inline +unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -216,6 +224,14 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) return true; } +#ifndef arch_scale_cpu_capacity +static __always_inline +unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + #endif /* !CONFIG_SMP */ static inline int task_node(const struct task_struct *p) -- cgit v1.2.3 From 938e5e4b0d1502a93e787985cb95b136b40717b7 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:15 +0000 Subject: sched/cpufreq: Prepare schedutil for Energy Aware Scheduling Schedutil requests frequency by aggregating utilization signals from the scheduler (CFS, RT, DL, IRQ) and applying a 25% margin on top of them. Since Energy Aware Scheduling (EAS) needs to be able to predict the frequency requests, it needs to forecast the decisions made by the governor. In order to prepare the introduction of EAS, introduce schedutil_freq_util() to centralize the aforementioned signal aggregation and make it available to both schedutil and EAS. Since frequency selection and energy estimation still need to deal with RT and DL signals slightly differently, schedutil_freq_util() is called with a different 'type' parameter in those two contexts, and returns an aggregated utilization signal accordingly. While at it, introduce the map_util_freq() function which is designed to make schedutil's 25% margin usable easily for both sugov and EAS. As EAS will be able to predict schedutil's frequency requests more accurately than any other governor by design, it'd be sensible to make sure EAS cannot be used without schedutil. This will be done later, once EAS has actually been introduced. Suggested-by: Peter Zijlstra Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: rjw@rjwysocki.net Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-3-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index 59667444669f..afa940cd50dc 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -20,6 +20,12 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, void (*func)(struct update_util_data *data, u64 time, unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); + +static inline unsigned long map_util_freq(unsigned long util, + unsigned long freq, unsigned long cap) +{ + return (freq + (freq >> 2)) * util / cap; +} #endif /* CONFIG_CPU_FREQ */ #endif /* _LINUX_SCHED_CPUFREQ_H */ -- cgit v1.2.3 From 27871f7a8a341ef5c636a337856369acf8013e4e Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:16 +0000 Subject: PM: Introduce an Energy Model management framework Several subsystems in the kernel (task scheduler and/or thermal at the time of writing) can benefit from knowing about the energy consumed by CPUs. Yet, this information can come from different sources (DT or firmware for example), in different formats, hence making it hard to exploit without a standard API. As an attempt to address this, introduce a centralized Energy Model (EM) management framework which aggregates the power values provided by drivers into a table for each performance domain in the system. The power cost tables are made available to interested clients (e.g. task scheduler or thermal) via platform-agnostic APIs. The overall design is represented by the diagram below (focused on Arm-related drivers as an example, but applicable to any architecture): +---------------+ +-----------------+ +-------------+ | Thermal (IPA) | | Scheduler (EAS) | | Other | +---------------+ +-----------------+ +-------------+ | | em_pd_energy() | | | em_cpu_get() | +-----------+ | +--------+ | | | v v v +---------------------+ | | | Energy Model | | | | Framework | | | +---------------------+ ^ ^ ^ | | | em_register_perf_domain() +----------+ | +---------+ | | | +---------------+ +---------------+ +--------------+ | cpufreq-dt | | arm_scmi | | Other | +---------------+ +---------------+ +--------------+ ^ ^ ^ | | | +--------------+ +---------------+ +--------------+ | Device Tree | | Firmware | | ? | +--------------+ +---------------+ +--------------+ Drivers (typically, but not limited to, CPUFreq drivers) can register data in the EM framework using the em_register_perf_domain() API. The calling driver must provide a callback function with a standardized signature that will be used by the EM framework to build the power cost tables of the performance domain. This design should offer a lot of flexibility to calling drivers which are free of reading information from any location and to use any technique to compute power costs. Moreover, the capacity states registered by drivers in the EM framework are not required to match real performance states of the target. This is particularly important on targets where the performance states are not known by the OS. The power cost coefficients managed by the EM framework are specified in milli-watts. Although the two potential users of those coefficients (IPA and EAS) only need relative correctness, IPA specifically needs to compare the power of CPUs with the power of other components (GPUs, for example), which are still expressed in absolute terms in their respective subsystems. Hence, specifying the power of CPUs in milli-watts should help transitioning IPA to using the EM framework without introducing new problems by keeping units comparable across sub-systems. On the longer term, the EM of other devices than CPUs could also be managed by the EM framework, which would enable to remove the absolute unit. However, this is not absolutely required as a first step, so this extension of the EM framework is left for later. On the client side, the EM framework offers APIs to access the power cost tables of a CPU (em_cpu_get()), and to estimate the energy consumed by the CPUs of a performance domain (em_pd_energy()). Clients such as the task scheduler can then use these APIs to access the shared data structures holding the Energy Model of CPUs. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-4-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- include/linux/energy_model.h | 187 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 187 insertions(+) create mode 100644 include/linux/energy_model.h (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h new file mode 100644 index 000000000000..aa027f7bcb3e --- /dev/null +++ b/include/linux/energy_model.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ENERGY_MODEL_H +#define _LINUX_ENERGY_MODEL_H +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_ENERGY_MODEL +/** + * em_cap_state - Capacity state of a performance domain + * @frequency: The CPU frequency in KHz, for consistency with CPUFreq + * @power: The power consumed by 1 CPU at this level, in milli-watts + * @cost: The cost coefficient associated with this level, used during + * energy calculation. Equal to: power * max_frequency / frequency + */ +struct em_cap_state { + unsigned long frequency; + unsigned long power; + unsigned long cost; +}; + +/** + * em_perf_domain - Performance domain + * @table: List of capacity states, in ascending order + * @nr_cap_states: Number of capacity states + * @cpus: Cpumask covering the CPUs of the domain + * + * A "performance domain" represents a group of CPUs whose performance is + * scaled together. All CPUs of a performance domain must have the same + * micro-architecture. Performance domains often have a 1-to-1 mapping with + * CPUFreq policies. + */ +struct em_perf_domain { + struct em_cap_state *table; + int nr_cap_states; + unsigned long cpus[0]; +}; + +#define EM_CPU_MAX_POWER 0xFFFF + +struct em_data_callback { + /** + * active_power() - Provide power at the next capacity state of a CPU + * @power : Active power at the capacity state in mW (modified) + * @freq : Frequency at the capacity state in kHz (modified) + * @cpu : CPU for which we do this operation + * + * active_power() must find the lowest capacity state of 'cpu' above + * 'freq' and update 'power' and 'freq' to the matching active power + * and frequency. + * + * The power is the one of a single CPU in the domain, expressed in + * milli-watts. It is expected to fit in the [0, EM_CPU_MAX_POWER] + * range. + * + * Return 0 on success. + */ + int (*active_power)(unsigned long *power, unsigned long *freq, int cpu); +}; +#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } + +struct em_perf_domain *em_cpu_get(int cpu); +int em_register_perf_domain(cpumask_t *span, unsigned int nr_states, + struct em_data_callback *cb); + +/** + * em_pd_energy() - Estimates the energy consumed by the CPUs of a perf. domain + * @pd : performance domain for which energy has to be estimated + * @max_util : highest utilization among CPUs of the domain + * @sum_util : sum of the utilization of all CPUs in the domain + * + * Return: the sum of the energy consumed by the CPUs of the domain assuming + * a capacity state satisfying the max utilization of the domain. + */ +static inline unsigned long em_pd_energy(struct em_perf_domain *pd, + unsigned long max_util, unsigned long sum_util) +{ + unsigned long freq, scale_cpu; + struct em_cap_state *cs; + int i, cpu; + + /* + * In order to predict the capacity state, map the utilization of the + * most utilized CPU of the performance domain to a requested frequency, + * like schedutil. + */ + cpu = cpumask_first(to_cpumask(pd->cpus)); + scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + cs = &pd->table[pd->nr_cap_states - 1]; + freq = map_util_freq(max_util, cs->frequency, scale_cpu); + + /* + * Find the lowest capacity state of the Energy Model above the + * requested frequency. + */ + for (i = 0; i < pd->nr_cap_states; i++) { + cs = &pd->table[i]; + if (cs->frequency >= freq) + break; + } + + /* + * The capacity of a CPU in the domain at that capacity state (cs) + * can be computed as: + * + * cs->freq * scale_cpu + * cs->cap = -------------------- (1) + * cpu_max_freq + * + * So, ignoring the costs of idle states (which are not available in + * the EM), the energy consumed by this CPU at that capacity state is + * estimated as: + * + * cs->power * cpu_util + * cpu_nrg = -------------------- (2) + * cs->cap + * + * since 'cpu_util / cs->cap' represents its percentage of busy time. + * + * NOTE: Although the result of this computation actually is in + * units of power, it can be manipulated as an energy value + * over a scheduling period, since it is assumed to be + * constant during that interval. + * + * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product + * of two terms: + * + * cs->power * cpu_max_freq cpu_util + * cpu_nrg = ------------------------ * --------- (3) + * cs->freq scale_cpu + * + * The first term is static, and is stored in the em_cap_state struct + * as 'cs->cost'. + * + * Since all CPUs of the domain have the same micro-architecture, they + * share the same 'cs->cost', and the same CPU capacity. Hence, the + * total energy of the domain (which is the simple sum of the energy of + * all of its CPUs) can be factorized as: + * + * cs->cost * \Sum cpu_util + * pd_nrg = ------------------------ (4) + * scale_cpu + */ + return cs->cost * sum_util / scale_cpu; +} + +/** + * em_pd_nr_cap_states() - Get the number of capacity states of a perf. domain + * @pd : performance domain for which this must be done + * + * Return: the number of capacity states in the performance domain table + */ +static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +{ + return pd->nr_cap_states; +} + +#else +struct em_perf_domain {}; +struct em_data_callback {}; +#define EM_DATA_CB(_active_power_cb) { } + +static inline int em_register_perf_domain(cpumask_t *span, + unsigned int nr_states, struct em_data_callback *cb) +{ + return -EINVAL; +} +static inline struct em_perf_domain *em_cpu_get(int cpu) +{ + return NULL; +} +static inline unsigned long em_pd_energy(struct em_perf_domain *pd, + unsigned long max_util, unsigned long sum_util) +{ + return 0; +} +static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) +{ + return 0; +} +#endif + +#endif -- cgit v1.2.3 From 531b5c9f5cd05ead53324f419b32685a22eebe8b Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 3 Dec 2018 09:56:21 +0000 Subject: sched/topology: Make Energy Aware Scheduling depend on schedutil Energy Aware Scheduling (EAS) is designed with the assumption that frequencies of CPUs follow their utilization value. When using a CPUFreq governor other than schedutil, the chances of this assumption being true are small, if any. When schedutil is being used, EAS' predictions are at least consistent with the frequency requests. Although those requests have no guarantees to be honored by the hardware, they should at least guide DVFS in the right direction and provide some hope in regards to the EAS model being accurate. To make sure EAS is only used in a sane configuration, create a strong dependency on schedutil being used. Since having sugov compiled-in does not provide that guarantee, make CPUFreq call a scheduler function on governor changes hence letting it rebuild the scheduling domains, check the governors of the online CPUs, and enable/disable EAS accordingly. Signed-off-by: Quentin Perret Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: adharmap@codeaurora.org Cc: chris.redpath@arm.com Cc: currojerez@riseup.net Cc: dietmar.eggemann@arm.com Cc: edubezval@gmail.com Cc: gregkh@linuxfoundation.org Cc: javi.merino@kernel.org Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: patrick.bellasi@arm.com Cc: pkondeti@codeaurora.org Cc: skannan@codeaurora.org Cc: smuckle@google.com Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Cc: viresh.kumar@linaro.org Link: https://lkml.kernel.org/r/20181203095628.11858-9-quentin.perret@arm.com Signed-off-by: Ingo Molnar --- include/linux/cpufreq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 882a9b9e34bc..c86d6d8bdfed 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -950,6 +950,14 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) } #endif +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) +void sched_cpufreq_governor_change(struct cpufreq_policy *policy, + struct cpufreq_governor *old_gov); +#else +static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, + struct cpufreq_governor *old_gov) { } +#endif + extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); -- cgit v1.2.3 From ebafb63dc7759c4cc54065b5aa675080b5f453ce Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 11 Dec 2018 09:43:03 -0800 Subject: clk: Tag clk core files with SPDX These are all GPL-2.0 files per the existing license text. Replace the boiler plate with the tag. Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 7 +------ include/linux/clk/clk-conf.h | 5 +---- 2 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 60c51871b04b..a2daf4572b05 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1,12 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * linux/include/linux/clk-provider.h - * * Copyright (c) 2010-2011 Jeremy Kerr * Copyright (C) 2011-2012 Linaro Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_CLK_PROVIDER_H #define __LINUX_CLK_PROVIDER_H diff --git a/include/linux/clk/clk-conf.h b/include/linux/clk/clk-conf.h index e0c362363c38..85f8cf9d1226 100644 --- a/include/linux/clk/clk-conf.h +++ b/include/linux/clk/clk-conf.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2014 Samsung Electronics Co., Ltd. * Sylwester Nawrocki - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include -- cgit v1.2.3 From 24828d0536bbedc9b265f2b01ffca99de3f6a7c7 Mon Sep 17 00:00:00 2001 From: Igor Konopko Date: Tue, 11 Dec 2018 20:16:24 +0100 Subject: lightnvm: dynamic DMA pool entry size MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently lightnvm and pblk uses single DMA pool, for which the entry size always is equal to PAGE_SIZE. The contents of each entry allocated from the DMA pool consists of a PPA list (8bytes * 64), leaving 56bytes * 64 space for metadata. Since the metadata field can be bigger, such as 128 bytes, the static size does not cover this use-case. This patch adds support for I/O metadata above 56 bytes by changing DMA pool size based on device meta size and allows pblk to use OOB metadata >=16B. Reviewed-by: Javier González Signed-off-by: Igor Konopko Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 2fdeac1a420d..7afedaddbd15 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -90,7 +90,7 @@ typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, sector_t, int, struct nvm_chk_meta *); typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *); -typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); +typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *, int); typedef void (nvm_destroy_dma_pool_fn)(void *); typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, dma_addr_t *); -- cgit v1.2.3 From a16816b9e462e8ee86a908606bde54b53cfeca80 Mon Sep 17 00:00:00 2001 From: Igor Konopko Date: Tue, 11 Dec 2018 20:16:25 +0100 Subject: lightnvm: disable interleaved metadata MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently pblk only check the size of I/O metadata and does not take into account if this metadata is in a separate buffer or interleaved in a single metadata buffer. In reality only the first scenario is supported, where second mode will break pblk functionality during any IO operation. This patch prevents pblk to be instantiated in case device only supports interleaved metadata. Reviewed-by: Javier González Signed-off-by: Igor Konopko Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 7afedaddbd15..5d865a5d5cdc 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -357,6 +357,7 @@ struct nvm_geo { u32 clba; /* sectors per chunk */ u16 csecs; /* sector size */ u16 sos; /* out-of-band area size */ + bool ext; /* metadata in extended data buffer */ /* device write constrains */ u32 ws_min; /* minimum write size */ -- cgit v1.2.3 From 4106a758f791de11502cc6be89c971735cab360f Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Sun, 9 Dec 2018 11:49:51 +0200 Subject: IB/mlx5: Report CapabilityMask2 in ib_query_port CapabilityMask2 exists when IB_PORT_CAP_MASK2_SUP is set in the original capability mask. In such cases, query its value and report it in query port. Signed-off-by: Michael Guralnik Reviewed-by: Majd Dibbiny Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/driver.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 584d8a5df7eb..b090a96f87df 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -749,8 +749,8 @@ struct mlx5_hca_vport_context { u64 node_guid; u32 cap_mask1; u32 cap_mask1_perm; - u32 cap_mask2; - u32 cap_mask2_perm; + u16 cap_mask2; + u16 cap_mask2_perm; u16 lid; u8 init_type_reply; /* bitmask: see ib spec 14.2.5.6 InitTypeReply */ u8 lmc; -- cgit v1.2.3 From 939de57d30344ce728b0de61be87984e75af420e Mon Sep 17 00:00:00 2001 From: Daniel Jurgens Date: Mon, 5 Nov 2018 16:05:37 -0600 Subject: net/mlx5e: Use CQE padding for Ethernet CQs Writing 64B CQEs to 128B cache lines results in a RMW operation. Padding the CQEs to 128B if possible improves performance on 128B cache line systems like PPC. Testing on PPC showed up to a 24% improvement in small packet throughput vs the default behavior, depending on the workload and system topology. Signed-off-by: Daniel Jurgens Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/cq.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 28b757a64029..612c8c2f2466 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -125,9 +125,9 @@ struct mlx5_cq_modify_params { }; enum { - CQE_SIZE_64 = 0, - CQE_SIZE_128 = 1, - CQE_SIZE_128_PAD = 2, + CQE_STRIDE_64 = 0, + CQE_STRIDE_128 = 1, + CQE_STRIDE_128_PAD = 2, }; #define MLX5_MAX_CQ_PERIOD (BIT(__mlx5_bit_sz(cqc, cq_period)) - 1) @@ -135,8 +135,8 @@ enum { static inline int cqe_sz_to_mlx_sz(u8 size, int padding_128_en) { - return padding_128_en ? CQE_SIZE_128_PAD : - size == 64 ? CQE_SIZE_64 : CQE_SIZE_128; + return padding_128_en ? CQE_STRIDE_128_PAD : + size == 64 ? CQE_STRIDE_64 : CQE_STRIDE_128; } static inline void mlx5_cq_set_ci(struct mlx5_core_cq *cq) -- cgit v1.2.3 From 75370eb0d3b802f54600f2fc3ae5255fe9270112 Mon Sep 17 00:00:00 2001 From: Eyal Davidovich Date: Sun, 7 Oct 2018 15:18:37 +0300 Subject: net/mlx5e: Avoid query PPCNT register if not supported by the device PPCNT is not supported if PCAM access reg is supported and ppcnt bit is clear. Signed-off-by: Eyal Davidovich Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 60c1d49eb40c..c12b0dec2889 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8283,7 +8283,9 @@ struct mlx5_ifc_pcam_regs_5000_to_507f_bits { u8 port_access_reg_cap_mask_31_to_13[0x13]; u8 pbmc[0x1]; u8 pptb[0x1]; - u8 port_access_reg_cap_mask_10_to_0[0xb]; + u8 port_access_reg_cap_mask_10_to_09[0x2]; + u8 ppcnt[0x1]; + u8 port_access_reg_cap_mask_07_to_00[0x8]; }; struct mlx5_ifc_pcam_reg_bits { -- cgit v1.2.3 From a5662e4d81c4d4b08140c625d0f3c50b15786252 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Sun, 9 Dec 2018 11:24:12 -0700 Subject: seccomp: switch system call argument type to void * The const qualifier causes problems for any code that wants to write to the third argument of the seccomp syscall, as we will do in a future patch in this series. The third argument to the seccomp syscall is documented as void *, so rather than just dropping the const, let's switch everything to use void * as well. I believe this is safe because of 1. the documentation above, 2. there's no real type information exported about syscalls anywhere besides the man pages. Signed-off-by: Tycho Andersen CC: Kees Cook CC: Andy Lutomirski CC: Oleg Nesterov CC: Eric W. Biederman CC: "Serge E. Hallyn" Acked-by: Serge Hallyn CC: Christian Brauner CC: Tyler Hicks CC: Akihiro Suda Signed-off-by: Kees Cook --- include/linux/seccomp.h | 2 +- include/linux/syscalls.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index e5320f6c8654..b5103c019cf4 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -43,7 +43,7 @@ extern void secure_computing_strict(int this_syscall); #endif extern long prctl_get_seccomp(void); -extern long prctl_set_seccomp(unsigned long, char __user *); +extern long prctl_set_seccomp(unsigned long, void __user *); static inline int seccomp_mode(struct seccomp *s) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2ac3d13a915b..a60694fb0f58 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -879,7 +879,7 @@ asmlinkage long sys_renameat2(int olddfd, const char __user *oldname, int newdfd, const char __user *newname, unsigned int flags); asmlinkage long sys_seccomp(unsigned int op, unsigned int flags, - const char __user *uargs); + void __user *uargs); asmlinkage long sys_getrandom(char __user *buf, size_t count, unsigned int flags); asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); -- cgit v1.2.3 From 6a21cc50f0c7f87dae5259f6cfefe024412313f6 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Sun, 9 Dec 2018 11:24:13 -0700 Subject: seccomp: add a return code to trap to userspace This patch introduces a means for syscalls matched in seccomp to notify some other task that a particular filter has been triggered. The motivation for this is primarily for use with containers. For example, if a container does an init_module(), we obviously don't want to load this untrusted code, which may be compiled for the wrong version of the kernel anyway. Instead, we could parse the module image, figure out which module the container is trying to load and load it on the host. As another example, containers cannot mount() in general since various filesystems assume a trusted image. However, if an orchestrator knows that e.g. a particular block device has not been exposed to a container for writing, it want to allow the container to mount that block device (that is, handle the mount for it). This patch adds functionality that is already possible via at least two other means that I know about, both of which involve ptrace(): first, one could ptrace attach, and then iterate through syscalls via PTRACE_SYSCALL. Unfortunately this is slow, so a faster version would be to install a filter that does SECCOMP_RET_TRACE, which triggers a PTRACE_EVENT_SECCOMP. Since ptrace allows only one tracer, if the container runtime is that tracer, users inside the container (or outside) trying to debug it will not be able to use ptrace, which is annoying. It also means that older distributions based on Upstart cannot boot inside containers using ptrace, since upstart itself uses ptrace to monitor services while starting. The actual implementation of this is fairly small, although getting the synchronization right was/is slightly complex. Finally, it's worth noting that the classic seccomp TOCTOU of reading memory data from the task still applies here, but can be avoided with careful design of the userspace handler: if the userspace handler reads all of the task memory that is necessary before applying its security policy, the tracee's subsequent memory edits will not be read by the tracer. Signed-off-by: Tycho Andersen CC: Kees Cook CC: Andy Lutomirski CC: Oleg Nesterov CC: Eric W. Biederman CC: "Serge E. Hallyn" Acked-by: Serge Hallyn CC: Christian Brauner CC: Tyler Hicks CC: Akihiro Suda Signed-off-by: Kees Cook --- include/linux/seccomp.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index b5103c019cf4..84868d37b35d 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -4,9 +4,10 @@ #include -#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ - SECCOMP_FILTER_FLAG_LOG | \ - SECCOMP_FILTER_FLAG_SPEC_ALLOW) +#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ + SECCOMP_FILTER_FLAG_LOG | \ + SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ + SECCOMP_FILTER_FLAG_NEW_LISTENER) #ifdef CONFIG_SECCOMP -- cgit v1.2.3 From fdadd04931c2d7cd294dc5b2b342863f94be53a3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 11 Dec 2018 12:14:12 +0100 Subject: bpf: fix bpf_jit_limit knob for PAGE_SIZE >= 64K Michael and Sandipan report: Commit ede95a63b5 introduced a bpf_jit_limit tuneable to limit BPF JIT allocations. At compile time it defaults to PAGE_SIZE * 40000, and is adjusted again at init time if MODULES_VADDR is defined. For ppc64 kernels, MODULES_VADDR isn't defined, so we're stuck with the compile-time default at boot-time, which is 0x9c400000 when using 64K page size. This overflows the signed 32-bit bpf_jit_limit value: root@ubuntu:/tmp# cat /proc/sys/net/core/bpf_jit_limit -1673527296 and can cause various unexpected failures throughout the network stack. In one case `strace dhclient eth0` reported: setsockopt(5, SOL_SOCKET, SO_ATTACH_FILTER, {len=11, filter=0x105dd27f8}, 16) = -1 ENOTSUPP (Unknown error 524) and similar failures can be seen with tools like tcpdump. This doesn't always reproduce however, and I'm not sure why. The more consistent failure I've seen is an Ubuntu 18.04 KVM guest booted on a POWER9 host would time out on systemd/netplan configuring a virtio-net NIC with no noticeable errors in the logs. Given this and also given that in near future some architectures like arm64 will have a custom area for BPF JIT image allocations we should get rid of the BPF_JIT_LIMIT_DEFAULT fallback / default entirely. For 4.21, we have an overridable bpf_jit_alloc_exec(), bpf_jit_free_exec() so therefore add another overridable bpf_jit_alloc_exec_limit() helper function which returns the possible size of the memory area for deriving the default heuristic in bpf_jit_charge_init(). Like bpf_jit_alloc_exec() and bpf_jit_free_exec(), the new bpf_jit_alloc_exec_limit() assumes that module_alloc() is the default JIT memory provider, and therefore in case archs implement their custom module_alloc() we use MODULES_{END,_VADDR} for limits and otherwise for vmalloc_exec() cases like on ppc64 we use VMALLOC_{END,_START}. Additionally, for archs supporting large page sizes, we should change the sysctl to be handled as long to not run into sysctl restrictions in future. Fixes: ede95a63b5e8 ("bpf: add bpf_jit_limit knob to restrict unpriv allocations") Reported-by: Sandipan Das Reported-by: Michael Roth Signed-off-by: Daniel Borkmann Tested-by: Michael Roth Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 795ff0b869bb..a8b9d90a8042 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -861,7 +861,7 @@ bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; -extern int bpf_jit_limit; +extern long bpf_jit_limit; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); -- cgit v1.2.3 From 79a5a18aa9d1062205cdcfa183d4cd5241d1b8da Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Mon, 19 Nov 2018 19:24:20 -0600 Subject: phy: core: rework phy_set_mode to accept phy mode and submode Currently the attempt to add support for Ethernet interface mode PHY (MII/GMII/RGMII) will lead to the necessity of extending enum phy_mode and duplicate there values from phy_interface_t enum (or introduce more PHY callbacks) [1]. Both approaches are ineffective and would lead to fast bloating of enum phy_mode or struct phy_ops in the process of adding more PHYs for different subsystems which will make them unmaintainable. As discussed in [1] the solution could be to introduce dual level PHYs mode configuration - PHY mode and PHY submode. The PHY mode will define generic PHY type (subsystem - PCIE/ETHERNET/USB_) while the PHY submode - subsystem specific interface mode. The last is usually already defined in corresponding subsystem headers (phy_interface_t for Ethernet, enum usb_device_speed for USB). This patch is cumulative change which refactors PHY framework code to support dual level PHYs mode configuration - PHY mode and PHY submode. It extends .set_mode() callback to support additional parameter "int submode" and converts all corresponding PHY drivers to support new .set_mode() callback declaration. The new extended PHY API int phy_set_mode_ext(struct phy *phy, enum phy_mode mode, int submode) is introduced to support dual level PHYs mode configuration and existing phy_set_mode() API is converted to macros, so PHY framework consumers do not need to be changed (~21 matches). [1] http://lkml.kernel.org/r/d63588f6-9ab0-848a-5ad4-8073143bd95d@ti.com Signed-off-by: Grygorii Strashko Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 03b319f89a34..b17e7709c5dc 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -60,7 +60,7 @@ struct phy_ops { int (*exit)(struct phy *phy); int (*power_on)(struct phy *phy); int (*power_off)(struct phy *phy); - int (*set_mode)(struct phy *phy, enum phy_mode mode); + int (*set_mode)(struct phy *phy, enum phy_mode mode, int submode); int (*reset)(struct phy *phy); int (*calibrate)(struct phy *phy); struct module *owner; @@ -164,7 +164,10 @@ int phy_init(struct phy *phy); int phy_exit(struct phy *phy); int phy_power_on(struct phy *phy); int phy_power_off(struct phy *phy); -int phy_set_mode(struct phy *phy, enum phy_mode mode); +int phy_set_mode_ext(struct phy *phy, enum phy_mode mode, int submode); +#define phy_set_mode(phy, mode) \ + phy_set_mode_ext(phy, mode, 0) + static inline enum phy_mode phy_get_mode(struct phy *phy) { return phy->attrs.mode; @@ -278,13 +281,17 @@ static inline int phy_power_off(struct phy *phy) return -ENOSYS; } -static inline int phy_set_mode(struct phy *phy, enum phy_mode mode) +static inline int phy_set_mode_ext(struct phy *phy, enum phy_mode mode, + int submode) { if (!phy) return 0; return -ENOSYS; } +#define phy_set_mode(phy, mode) \ + phy_set_mode_ext(phy, mode, 0) + static inline enum phy_mode phy_get_mode(struct phy *phy) { return PHY_MODE_INVALID; -- cgit v1.2.3 From 2af8caeee47846a84bc96abc3a72f7c991153040 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Mon, 19 Nov 2018 19:24:21 -0600 Subject: phy: core: add PHY_MODE_ETHERNET Add new PHY's mode to be used by Ethernet PHY interface drivers or multipurpose PHYs like serdes. It will be reused in further changes. Signed-off-by: Grygorii Strashko Signed-off-by: Kishon Vijay Abraham I --- 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 b17e7709c5dc..02c9ef0c8fff 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -42,6 +42,7 @@ enum phy_mode { PHY_MODE_UFS_HS_A, PHY_MODE_UFS_HS_B, PHY_MODE_PCIE, + PHY_MODE_ETHERNET, }; /** -- cgit v1.2.3 From b3af06451bf859a45a306678e02b12bb676a9687 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Mon, 19 Nov 2018 19:24:24 -0600 Subject: phy: core: clean up unused ethernet specific phy modes After recent changes PHY_MODE_SGMII, PHY_MODE_2500SGMII, PHY_MODE_QSGMII, PHY_MODE_10GKR are not used any more and can be removed. Hence - remove them. Signed-off-by: Grygorii Strashko Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 02c9ef0c8fff..79da05a3e28d 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -35,10 +35,6 @@ enum phy_mode { PHY_MODE_USB_DEVICE_HS, PHY_MODE_USB_DEVICE_SS, PHY_MODE_USB_OTG, - PHY_MODE_SGMII, - PHY_MODE_2500SGMII, - PHY_MODE_QSGMII, - PHY_MODE_10GKR, PHY_MODE_UFS_HS_A, PHY_MODE_UFS_HS_B, PHY_MODE_PCIE, -- cgit v1.2.3 From c8457828ff481411dca4cdea944c1a0980c862e1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 7 Dec 2018 14:55:28 +0100 Subject: phy: Add MIPI D-PHY mode MIPI D-PHY is a MIPI standard meant mostly for display and cameras in embedded systems. Add a mode for it. Reviewed-by: Laurent Pinchart Reviewed-by: Sakari Ailus Signed-off-by: Maxime Ripard Signed-off-by: Kishon Vijay Abraham I --- 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 79da05a3e28d..453f21834685 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -39,6 +39,7 @@ enum phy_mode { PHY_MODE_UFS_HS_B, PHY_MODE_PCIE, PHY_MODE_ETHERNET, + PHY_MODE_MIPI_DPHY, }; /** -- cgit v1.2.3 From aeaac93ddb28eeacc0dff9c12cb338eb1de7481d Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 7 Dec 2018 14:55:29 +0100 Subject: phy: Add configuration interface The phy framework is only allowing to configure the power state of the PHY using the init and power_on hooks, and their power_off and exit counterparts. While it works for most, simple, PHYs supported so far, some more advanced PHYs need some configuration depending on runtime parameters. These PHYs have been supported by a number of means already, often by using ad-hoc drivers in their consumer drivers. That doesn't work too well however, when a consumer device needs to deal with multiple PHYs, or when multiple consumers need to deal with the same PHY (a DSI driver and a CSI driver for example). So we'll add a new interface, through two funtions, phy_validate and phy_configure. The first one will allow to check that a current configuration, for a given mode, is applicable. It will also allow the PHY driver to tune the settings given as parameters as it sees fit. phy_configure will actually apply that configuration in the phy itself. Signed-off-by: Maxime Ripard Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy.h | 58 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 453f21834685..04476c026b5a 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -42,6 +42,12 @@ enum phy_mode { PHY_MODE_MIPI_DPHY, }; +/** + * union phy_configure_opts - Opaque generic phy configuration + */ +union phy_configure_opts { +}; + /** * struct phy_ops - set of function pointers for performing phy operations * @init: operation to be performed for initializing phy @@ -59,6 +65,37 @@ struct phy_ops { int (*power_on)(struct phy *phy); int (*power_off)(struct phy *phy); int (*set_mode)(struct phy *phy, enum phy_mode mode, int submode); + + /** + * @configure: + * + * Optional. + * + * Used to change the PHY parameters. phy_init() must have + * been called on the phy. + * + * Returns: 0 if successful, an negative error code otherwise + */ + int (*configure)(struct phy *phy, union phy_configure_opts *opts); + + /** + * @validate: + * + * Optional. + * + * Used to check that the current set of parameters can be + * handled by the phy. Implementations are free to tune the + * parameters passed as arguments if needed by some + * implementation detail or constraints. It must not change + * any actual configuration of the PHY, so calling it as many + * times as deemed fit by the consumer must have no side + * effect. + * + * Returns: 0 if the configuration can be applied, an negative + * error code otherwise + */ + int (*validate)(struct phy *phy, enum phy_mode mode, int submode, + union phy_configure_opts *opts); int (*reset)(struct phy *phy); int (*calibrate)(struct phy *phy); struct module *owner; @@ -165,6 +202,9 @@ int phy_power_off(struct phy *phy); int phy_set_mode_ext(struct phy *phy, enum phy_mode mode, int submode); #define phy_set_mode(phy, mode) \ phy_set_mode_ext(phy, mode, 0) +int phy_configure(struct phy *phy, union phy_configure_opts *opts); +int phy_validate(struct phy *phy, enum phy_mode mode, int submode, + union phy_configure_opts *opts); static inline enum phy_mode phy_get_mode(struct phy *phy) { @@ -309,6 +349,24 @@ static inline int phy_calibrate(struct phy *phy) return -ENOSYS; } +static inline int phy_configure(struct phy *phy, + union phy_configure_opts *opts) +{ + if (!phy) + return 0; + + return -ENOSYS; +} + +static inline int phy_validate(struct phy *phy, enum phy_mode mode, int submode, + union phy_configure_opts *opts) +{ + if (!phy) + return 0; + + return -ENOSYS; +} + static inline int phy_get_bus_width(struct phy *phy) { return -ENOSYS; -- cgit v1.2.3 From 2ed869990e14bc5528aeb00c45e42793c5406637 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 7 Dec 2018 14:55:30 +0100 Subject: phy: Add MIPI D-PHY configuration options Now that we have some infrastructure for it, allow the MIPI D-PHY phy's to be configured through the generic functions through a custom structure added to the generic union. The parameters added here are the ones defined in the MIPI D-PHY spec, plus the number of lanes in use. The current set of parameters should cover all the potential users. Signed-off-by: Maxime Ripard Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy-mipi-dphy.h | 279 ++++++++++++++++++++++++++++++++++++++ include/linux/phy/phy.h | 6 + 2 files changed, 285 insertions(+) create mode 100644 include/linux/phy/phy-mipi-dphy.h (limited to 'include/linux') diff --git a/include/linux/phy/phy-mipi-dphy.h b/include/linux/phy/phy-mipi-dphy.h new file mode 100644 index 000000000000..29bf94db88ad --- /dev/null +++ b/include/linux/phy/phy-mipi-dphy.h @@ -0,0 +1,279 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 Cadence Design Systems Inc. + */ + +#ifndef __PHY_MIPI_DPHY_H_ +#define __PHY_MIPI_DPHY_H_ + +#include