From 5b698be0497d8be986e2050e9b1c145b2e0603c2 Mon Sep 17 00:00:00 2001 From: Meghana Madhyastha Date: Wed, 24 Jan 2018 16:34:07 +0000 Subject: video: backlight: Add helpers to enable and disable backlight MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add helper functions backlight_enable and backlight_disable to enable/disable a backlight device. These helper functions can then be used by different drm and tinydrm drivers to avoid repetition of code and also to enforce a uniform and consistent way to enable/disable a backlight device. Acked-by: Daniel Thompson Reviewed-by: Noralf Trønnes Reviewed-by: Sean Paul Signed-off-by: Meghana Madhyastha Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/39b5bf0a02008a8072d910bdf8231c431e9ef504.1516810725.git.meghana.madhyastha@gmail.com --- include/linux/backlight.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index af7003548593..ace825e2ca2d 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -130,6 +130,38 @@ static inline int backlight_update_status(struct backlight_device *bd) return ret; } +/** + * backlight_enable - Enable backlight + * @bd: the backlight device to enable + */ +static inline int backlight_enable(struct backlight_device *bd) +{ + if (!bd) + return 0; + + bd->props.power = FB_BLANK_UNBLANK; + bd->props.fb_blank = FB_BLANK_UNBLANK; + bd->props.state &= ~BL_CORE_FBBLANK; + + return backlight_update_status(bd); +} + +/** + * backlight_disable - Disable backlight + * @bd: the backlight device to disable + */ +static inline int backlight_disable(struct backlight_device *bd) +{ + if (!bd) + return 0; + + bd->props.power = FB_BLANK_POWERDOWN; + bd->props.fb_blank = FB_BLANK_POWERDOWN; + bd->props.state |= BL_CORE_FBBLANK; + + return backlight_update_status(bd); +} + extern struct backlight_device *backlight_device_register(const char *name, struct device *dev, void *devdata, const struct backlight_ops *ops, const struct backlight_properties *props); -- cgit v1.2.3 From c2adda27d202fa8f70a5d6e8b0c12b449c8868b8 Mon Sep 17 00:00:00 2001 From: Meghana Madhyastha Date: Wed, 24 Jan 2018 16:35:30 +0000 Subject: video: backlight: Add of_find_backlight helper in backlight.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add of_find_backlight, a helper function which is a generic version of tinydrm_of_find_backlight that can be used by other drivers to avoid repetition of code and simplify things. Acked-by: Daniel Thompson Reviewed-by: Noralf Trønnes Reviewed-by: Sean Paul Reviewed-by: Thierry Reding Signed-off-by: Meghana Madhyastha Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/116d160ba78be2e6dcbdcb6855622bce67da9472.1516810725.git.meghana.madhyastha@gmail.com --- include/linux/backlight.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index ace825e2ca2d..ddc9bade4fb2 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -162,6 +162,16 @@ static inline int backlight_disable(struct backlight_device *bd) return backlight_update_status(bd); } +/** + * backlight_put - Drop backlight reference + * @bd: the backlight device to put + */ +static inline void backlight_put(struct backlight_device *bd) +{ + if (bd) + put_device(&bd->dev); +} + extern struct backlight_device *backlight_device_register(const char *name, struct device *dev, void *devdata, const struct backlight_ops *ops, const struct backlight_properties *props); @@ -205,4 +215,13 @@ of_find_backlight_by_node(struct device_node *node) } #endif +#if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE) +struct backlight_device *of_find_backlight(struct device *dev); +#else +static inline struct backlight_device *of_find_backlight(struct device *dev) +{ + return NULL; +} +#endif + #endif -- cgit v1.2.3 From 2e4ef3347b4a4eb65c4fd950d94bbd75fed4d798 Mon Sep 17 00:00:00 2001 From: Meghana Madhyastha Date: Wed, 24 Jan 2018 16:37:23 +0000 Subject: video: backlight: Add devres versions of of_find_backlight MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add devm_of_find_backlight and the corresponding release function because some drivers use devres versions of functions for acquiring device resources. Acked-by: Daniel Thompson Reviewed-by: Noralf Trønnes Reviewed-by: Sean Paul Signed-off-by: Meghana Madhyastha Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/021f8fecfa3f374dc5dcb70fb07a6f6b019bea7b.1516810725.git.meghana.madhyastha@gmail.com --- include/linux/backlight.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backlight.h b/include/linux/backlight.h index ddc9bade4fb2..2baab6f3861d 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -217,11 +217,18 @@ of_find_backlight_by_node(struct device_node *node) #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE) struct backlight_device *of_find_backlight(struct device *dev); +struct backlight_device *devm_of_find_backlight(struct device *dev); #else static inline struct backlight_device *of_find_backlight(struct device *dev) { return NULL; } + +static inline struct backlight_device * +devm_of_find_backlight(struct device *dev) +{ + return NULL; +} #endif #endif -- cgit v1.2.3 From e12f03d7031a977356e3d7b75a68c2185ff8d155 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 6 Dec 2017 14:45:15 -0800 Subject: perf/core: Implement the 'perf_kprobe' PMU A new PMU type, perf_kprobe is added. Based on attr from perf_event_open(), perf_kprobe creates a kprobe (or kretprobe) for the perf_event. This kprobe is private to this perf_event, and thus not added to global lists, and not available in tracefs. Two functions, create_local_trace_kprobe() and destroy_local_trace_kprobe() are added to created and destroy these local trace_kprobe. Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Yonghong Song Reviewed-by: Josef Bacik Cc: Cc: Cc: Cc: Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171206224518.3598254-6-songliubraving@fb.com Signed-off-by: Ingo Molnar --- include/linux/trace_events.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index af44e7c2d577..21c5d43a21af 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -533,6 +533,10 @@ extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); extern int perf_trace_add(struct perf_event *event, int flags); extern void perf_trace_del(struct perf_event *event, int flags); +#ifdef CONFIG_KPROBE_EVENTS +extern int perf_kprobe_init(struct perf_event *event, bool is_retprobe); +extern void perf_kprobe_destroy(struct perf_event *event); +#endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); -- cgit v1.2.3 From 33ea4b24277b06dbc55d7f5772a46f029600255e Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 6 Dec 2017 14:45:16 -0800 Subject: perf/core: Implement the 'perf_uprobe' PMU This patch adds perf_uprobe support with similar pattern as previous patch (for kprobe). Two functions, create_local_trace_uprobe() and destroy_local_trace_uprobe(), are created so a uprobe can be created and attached to the file descriptor created by perf_event_open(). Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Yonghong Song Reviewed-by: Josef Bacik Cc: Cc: Cc: Cc: Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20171206224518.3598254-7-songliubraving@fb.com Signed-off-by: Ingo Molnar --- include/linux/trace_events.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 21c5d43a21af..0d9d6cb454b1 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -537,6 +537,10 @@ extern void perf_trace_del(struct perf_event *event, int flags); extern int perf_kprobe_init(struct perf_event *event, bool is_retprobe); extern void perf_kprobe_destroy(struct perf_event *event); #endif +#ifdef CONFIG_UPROBE_EVENTS +extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe); +extern void perf_uprobe_destroy(struct perf_event *event); +#endif extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); -- cgit v1.2.3 From c65e774fb3f6af212641538694b9778ff9ab4300 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 14 Feb 2018 14:16:53 +0300 Subject: x86/mm: Make PGDIR_SHIFT and PTRS_PER_P4D variable For boot-time switching between 4- and 5-level paging we need to be able to fold p4d page table level at runtime. It requires variable PGDIR_SHIFT and PTRS_PER_P4D. The change doesn't affect the kernel image size much: text data bss dec hex filename 8628091 4734304 1368064 14730459 e0c4db vmlinux.before 8628393 4734340 1368064 14730797 e0c62d vmlinux.after Signed-off-by: Kirill A. Shutemov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20180214111656.88514-7-kirill.shutemov@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/kasan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index adc13474a53b..d6459bd1376d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -18,7 +18,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE]; extern pte_t kasan_zero_pte[PTRS_PER_PTE]; extern pmd_t kasan_zero_pmd[PTRS_PER_PMD]; extern pud_t kasan_zero_pud[PTRS_PER_PUD]; -extern p4d_t kasan_zero_p4d[PTRS_PER_P4D]; +extern p4d_t kasan_zero_p4d[MAX_PTRS_PER_P4D]; void kasan_populate_zero_shadow(const void *shadow_start, const void *shadow_end); -- cgit v1.2.3 From 562c45d635ecd5c0648ceb4d4aff9bdc1ad91252 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 15 Feb 2018 16:49:45 -0800 Subject: headers: Drop two #included headers from It seems that does not need nor . 8 kernels builds are successful without these 2 headers (allmodconfig, allyesconfig, allnoconfig, and tinyconfig on both i386 and x86_64). is #included 3875 times in 4.16-rc1, so this reduces #include processing of these 2 files by a total of 7750 times. Since I only tested x86 builds, this needs to be tested on other $ARCHes as well. Signed-off-by: Randy Dunlap Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Link: http://lkml.kernel.org/r/b24b9ec8-4970-65f5-759a-911d4ba2fcf0@infradead.org Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 69c238210325..5426627f9c55 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -4,9 +4,7 @@ #define _LINUX_INTERRUPT_H #include -#include #include -#include #include #include #include -- cgit v1.2.3 From 30a050defbca46f60a04f22dc4306612eeaaf04b Mon Sep 17 00:00:00 2001 From: Lihao Liang Date: Thu, 21 Dec 2017 16:16:10 +0800 Subject: doc: Fix typo in rcu_head comments Signed-off-by: Lihao Liang Signed-off-by: Paul E. McKenney --- include/linux/types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index c94d59ef96cc..ec13d02b3481 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -217,7 +217,7 @@ struct ustat { * * This guarantee is important for few reasons: * - future call_rcu_lazy() will make use of lower bits in the pointer; - * - the structure shares storage spacer in struct page with @compound_head, + * - the structure shares storage space in struct page with @compound_head, * which encode PageTail() in bit 0. The guarantee is needed to avoid * false-positive PageTail(). */ -- cgit v1.2.3 From b5482a06593c851028b5dc061f9c8882bcc20008 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 23 Jan 2018 14:48:33 -0800 Subject: rcu: Fix init_rcu_head() comment. The current (and implicit) comment header for init_rcu_head() and destroy_rcu_head() incorrectly says that they are not needed for statically allocated rcu_head structures. This commit therefore fixes this comment. Reported-by: Bart Van Assche Signed-off-by: Paul E. McKenney Reviewed-by: Bart Van Assche Reviewed-by: Leon Romanovsky --- include/linux/rcupdate.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 043d04784675..36360d07f25b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -214,10 +214,12 @@ do { \ #endif /* - * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic - * initialization and destruction of rcu_head on the stack. rcu_head structures - * allocated dynamically in the heap or defined statically don't need any - * initialization. + * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls + * are needed for dynamic initialization and destruction of rcu_head + * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for + * dynamic initialization and destruction of statically allocated rcu_head + * structures. However, rcu_head structures allocated dynamically in the + * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); -- cgit v1.2.3 From a364298359e74a414857bbbf3b725564feb22d09 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:24 +0100 Subject: nohz: Convert tick_nohz_tick_stopped() to bool It makes this function more self-explanatory about what it does and how to use it. Reported-by: Thomas Gleixner Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-3-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/tick.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 7cc35921218e..86576d9d2311 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -113,7 +113,7 @@ enum tick_dep_bits { #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; -extern int tick_nohz_tick_stopped(void); +extern bool tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); -- cgit v1.2.3 From 22ab8bc02a5f6e8ffc418759894f7a6b0b632331 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:25 +0100 Subject: nohz: Allow to check if remote CPU tick is stopped This check is racy but provides a good heuristic to determine whether a CPU may need a remote tick or not. Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-4-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/tick.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 86576d9d2311..7f8c9a127f5a 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -114,6 +114,7 @@ enum tick_dep_bits { #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; extern bool tick_nohz_tick_stopped(void); +extern bool tick_nohz_tick_stopped_cpu(int cpu); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); @@ -125,6 +126,7 @@ extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline int tick_nohz_tick_stopped(void) { return 0; } +static inline int tick_nohz_tick_stopped_cpu(int cpu) { return 0; } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } -- cgit v1.2.3 From 1bda3f8087fce9063da0b8aef87f17a3fe541aca Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:26 +0100 Subject: sched/isolation: Isolate workqueues when "nohz_full=" is set As we prepare for offloading the residual 1hz scheduler ticks to workqueue, let's affine those to housekeepers so that they don't interrupt the CPUs that don't want to be disturbed. Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-5-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index d849431c8060..4a6582c27dea 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -12,6 +12,7 @@ enum hk_flags { HK_FLAG_SCHED = (1 << 3), HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), + HK_FLAG_WQ = (1 << 6), }; #ifdef CONFIG_CPU_ISOLATION -- cgit v1.2.3 From dcdedb24159be3487e3dbbe1faa79ae7d00c92ac Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:28 +0100 Subject: sched/nohz: Remove the 1 Hz tick code Now that the 1Hz tick is offloaded to workqueues, we can safely remove the residual code that used to handle it locally. Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-7-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/nohz.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 3d3a97d9399d..094217273ff9 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -37,8 +37,4 @@ extern void wake_up_nohz_cpu(int cpu); static inline void wake_up_nohz_cpu(int cpu) { } #endif -#ifdef CONFIG_NO_HZ_FULL -extern u64 scheduler_tick_max_deferment(void); -#endif - #endif /* _LINUX_SCHED_NOHZ_H */ -- cgit v1.2.3 From 492a1abd61e4b4f78c1c5804840a304a9e32da04 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 22 Feb 2018 14:59:20 +0200 Subject: dmi: Introduce the dmi_get_bios_year() helper function The pattern to only extract the year portion of date is used in several places and more users may come. By using this helper they may create slightly cleaner code. Signed-off-by: Andy Shevchenko [ Minor stylistic cleanup. ] Cc: Bjorn Helgaas Cc: Jean Delvare Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: linux-acpi@vger.kernel.org Cc: linux-pci@vger.kernel.org Link: http://lkml.kernel.org/r/20180222125923.57385-1-andriy.shevchenko@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/dmi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 46e151172d95..0bade156e908 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -147,4 +147,13 @@ static inline const struct dmi_system_id * #endif +static inline int dmi_get_bios_year(void) +{ + int year; + + dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL); + + return year; +} + #endif /* __DMI_H__ */ -- cgit v1.2.3 From 5f171577b4f35b44795a73bde8cf2c49b4073925 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Tue, 24 Oct 2017 16:52:32 +0100 Subject: Drop a bunch of metag references Now that arch/metag/ has been removed, drop a bunch of metag references in various codes across the whole tree: - VM_GROWSUP and __VM_ARCH_SPECIFIC_1. - MT_METAG_* ELF note types. - METAG Kconfig dependencies (FRAME_POINTER) and ranges (MAX_STACK_SIZE_MB). - metag cases in tools (checkstack.pl, recordmcount.c, perf). Signed-off-by: James Hogan Acked-by: Steven Rostedt (VMware) Acked-by: Peter Zijlstra (Intel) Reviewed-by: Guenter Roeck Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: linux-mm@kvack.org Cc: linux-metag@vger.kernel.org --- include/linux/cpuhotplug.h | 1 - include/linux/mm.h | 2 -- 2 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5172ad0daa7c..c7a950681f3a 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -108,7 +108,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_STARTING, CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, - CPUHP_AP_PERF_METAG_STARTING, CPUHP_AP_MIPS_OP_LOONGSON3_STARTING, CPUHP_AP_ARM_SDEI_STARTING, CPUHP_AP_ARM_VFP_STARTING, diff --git a/include/linux/mm.h b/include/linux/mm.h index ad06d42adb1a..ccac10682ce5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -241,8 +241,6 @@ extern unsigned int kobjsize(const void *objp); # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 -#elif defined(CONFIG_METAG) -# define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) # define VM_GROWSUP VM_ARCH_1 #elif !defined(CONFIG_MMU) -- cgit v1.2.3 From df46bb1909d92eedccd4216c88e43f75cb0b2901 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 21 Feb 2018 15:31:32 +0000 Subject: irqchip: Remove metag irqchip drivers Now that arch/metag/ has been removed, remove the two metag irqchip drivers. They are of no value without the architecture code. - irq-metag: Meta internal (HWSTATMETA) interrupt code. - irq-metag-ext: Meta External interrupt code. Signed-off-by: James Hogan Cc: Thomas Gleixner Cc: Jason Cooper Cc: Marc Zyngier Cc: linux-metag@vger.kernel.org --- include/linux/irqchip/metag-ext.h | 34 ---------------------------------- include/linux/irqchip/metag.h | 25 ------------------------- 2 files changed, 59 deletions(-) delete mode 100644 include/linux/irqchip/metag-ext.h delete mode 100644 include/linux/irqchip/metag.h (limited to 'include/linux') diff --git a/include/linux/irqchip/metag-ext.h b/include/linux/irqchip/metag-ext.h deleted file mode 100644 index d120496370b9..000000000000 --- a/include/linux/irqchip/metag-ext.h +++ /dev/null @@ -1,34 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2012 Imagination Technologies - */ - -#ifndef _LINUX_IRQCHIP_METAG_EXT_H_ -#define _LINUX_IRQCHIP_METAG_EXT_H_ - -struct irq_data; -struct platform_device; - -/* called from core irq code at init */ -int init_external_IRQ(void); - -/* - * called from SoC init_irq() callback to dynamically indicate the lack of - * HWMASKEXT registers. - */ -void meta_intc_no_mask(void); - -/* - * These allow SoCs to specialise the interrupt controller from their init_irq - * callbacks. - */ - -extern struct irq_chip meta_intc_edge_chip; -extern struct irq_chip meta_intc_level_chip; - -/* this should be called in the mask callback */ -void meta_intc_mask_irq_simple(struct irq_data *data); -/* this should be called in the unmask callback */ -void meta_intc_unmask_irq_simple(struct irq_data *data); - -#endif /* _LINUX_IRQCHIP_METAG_EXT_H_ */ diff --git a/include/linux/irqchip/metag.h b/include/linux/irqchip/metag.h deleted file mode 100644 index 0adcf449e4e4..000000000000 --- a/include/linux/irqchip/metag.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2011 Imagination Technologies - */ - -#ifndef _LINUX_IRQCHIP_METAG_H_ -#define _LINUX_IRQCHIP_METAG_H_ - -#include - -#ifdef CONFIG_METAG_PERFCOUNTER_IRQS -extern int init_internal_IRQ(void); -extern int internal_irq_map(unsigned int hw); -#else -static inline int init_internal_IRQ(void) -{ - return 0; -} -static inline int internal_irq_map(unsigned int hw) -{ - return -EINVAL; -} -#endif - -#endif /* _LINUX_IRQCHIP_METAG_H_ */ -- cgit v1.2.3 From b79a732504ad2d6552458eaf72b4ed807da88340 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 21 Feb 2018 15:42:32 +0000 Subject: clocksource: Remove metag generic timer driver Now that arch/metag/ has been removed, remove the metag generic per-thread timer driver. It is of no value without the architecture code. Signed-off-by: James Hogan Acked-by: Daniel Lezcano Cc: Thomas Gleixner Cc: linux-metag@vger.kernel.org --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c7a950681f3a..5b211fe295f0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -121,7 +121,6 @@ enum cpuhp_state { CPUHP_AP_JCORE_TIMER_STARTING, CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, - CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_ARMADA_TIMER_STARTING, CPUHP_AP_MARCO_TIMER_STARTING, -- cgit v1.2.3 From 6ce5ae7977c89f2a09092954396a66c90e8213f2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 24 Feb 2018 21:22:12 -0800 Subject: mutex: Drop linkage.h from mutex.h does not use nor need , so drop that one header file from mutex.h. is currently #included in around 1250 C source files (oops, I didn't count other header files that #include it), making it the 27th most-used header file. Build tested on i386 and x86_64 * (allnoconfig, tiny.config, defconfig, allyesconfig, and allmodconfig) and x64_64 allmodconfig + SMP=disabled. Signed-off-by: Randy Dunlap Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/582b3892-4e4c-06b2-a368-5c2d439de7fc@infradead.org --- include/linux/mutex.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index f25c13423bd4..9b7fe56692bd 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From dfc9327ab7c99bc13e12106448615efba833886b Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 19 Feb 2018 11:09:04 +0100 Subject: acpi: Introduce acpi_arch_get_root_pointer() for getting rsdp address Add an architecture specific function to get the address of the RSDP table. Per default it will just return 0 indicating falling back to the current mechanism. Signed-off-by: Juergen Gross Reviewed-by: Andy Shevchenko Acked-by: Thomas Gleixner Acked-by: Rafael J. Wysocki Cc: Borislav Petkov Cc: Eric Biederman Cc: H. Peter Anvin Cc: Kees Cook Cc: Kirill A. Shutemov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: boris.ostrovsky@oracle.com Cc: lenb@kernel.org Cc: linux-acpi@vger.kernel.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/20180219100906.14265-2-jgross@suse.com Signed-off-by: Ingo Molnar --- include/linux/acpi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 968173ec2726..15bfb15c2fa5 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -623,6 +623,13 @@ bool acpi_gtdt_c3stop(int type); int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count); #endif +#ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER +static inline u64 acpi_arch_get_root_pointer(void) +{ + return 0; +} +#endif + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 -- cgit v1.2.3 From 28b0f8a6962a24ed21737578f3b1b07424635c9e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Feb 2018 07:38:08 -0800 Subject: tty: make n_tty_read() always abort if hangup is in progress A tty is hung up by __tty_hangup() setting file->f_op to hung_up_tty_fops, which is skipped on ttys whose write operation isn't tty_write(). This means that, for example, /dev/console whose write op is redirected_tty_write() is never actually marked hung up. Because n_tty_read() uses the hung up status to decide whether to abort the waiting readers, the lack of hung-up marking can lead to the following scenario. 1. A session contains two processes. The leader and its child. The child ignores SIGHUP. 2. The leader exits and starts disassociating from the controlling terminal (/dev/console). 3. __tty_hangup() skips setting f_op to hung_up_tty_fops. 4. SIGHUP is delivered and ignored. 5. tty_ldisc_hangup() is invoked. It wakes up the waits which should clear the read lockers of tty->ldisc_sem. 6. The reader wakes up but because tty_hung_up_p() is false, it doesn't abort and goes back to sleep while read-holding tty->ldisc_sem. 7. The leader progresses to tty_ldisc_lock() in tty_ldisc_hangup() and is now stuck in D sleep indefinitely waiting for tty->ldisc_sem. The following is Alan's explanation on why some ttys aren't hung up. http://lkml.kernel.org/r/20171101170908.6ad08580@alans-desktop 1. It broke the serial consoles because they would hang up and close down the hardware. With tty_port that *should* be fixable properly for any cases remaining. 2. The console layer was (and still is) completely broken and doens't refcount properly. So if you turn on console hangups it breaks (as indeed does freeing consoles and half a dozen other things). As neither can be fixed quickly, this patch works around the problem by introducing a new flag, TTY_HUPPING, which is used solely to tell n_tty_read() that hang-up is in progress for the console and the readers should be aborted regardless of the hung-up status of the device. The following is a sample hung task warning caused by this issue. INFO: task agetty:2662 blocked for more than 120 seconds. Not tainted 4.11.3-dbg-tty-lockup-02478-gfd6c7ee-dirty #28 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. 0 2662 1 0x00000086 Call Trace: __schedule+0x267/0x890 schedule+0x36/0x80 schedule_timeout+0x23c/0x2e0 ldsem_down_write+0xce/0x1f6 tty_ldisc_lock+0x16/0x30 tty_ldisc_hangup+0xb3/0x1b0 __tty_hangup+0x300/0x410 disassociate_ctty+0x6c/0x290 do_exit+0x7ef/0xb00 do_group_exit+0x3f/0xa0 get_signal+0x1b3/0x5d0 do_signal+0x28/0x660 exit_to_usermode_loop+0x46/0x86 do_syscall_64+0x9c/0xb0 entry_SYSCALL64_slow_path+0x25/0x25 The following is the repro. Run "$PROG /dev/console". The parent process hangs in D state. #include #include #include #include #include #include #include #include #include #include #include #include int main(int argc, char **argv) { struct sigaction sact = { .sa_handler = SIG_IGN }; struct timespec ts1s = { .tv_sec = 1 }; pid_t pid; int fd; if (argc < 2) { fprintf(stderr, "test-hung-tty /dev/$TTY\n"); return 1; } /* fork a child to ensure that it isn't already the session leader */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { /* top parent, wait for everyone */ while (waitpid(-1, NULL, 0) >= 0) ; if (errno != ECHILD) perror("waitpid"); return 0; } /* new session, start a new session and set the controlling tty */ if (setsid() < 0) { perror("setsid"); return 1; } fd = open(argv[1], O_RDWR); if (fd < 0) { perror("open"); return 1; } if (ioctl(fd, TIOCSCTTY, 1) < 0) { perror("ioctl"); return 1; } /* fork a child, sleep a bit and exit */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { nanosleep(&ts1s, NULL); printf("Session leader exiting\n"); exit(0); } /* * The child ignores SIGHUP and keeps reading from the controlling * tty. Because SIGHUP is ignored, the child doesn't get killed on * parent exit and the bug in n_tty makes the read(2) block the * parent's control terminal hangup attempt. The parent ends up in * D sleep until the child is explicitly killed. */ sigaction(SIGHUP, &sact, NULL); printf("Child reading tty\n"); while (1) { char buf[1024]; if (read(fd, buf, sizeof(buf)) < 0) { perror("read"); return 1; } } return 0; } Signed-off-by: Tejun Heo Cc: Alan Cox Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- 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 0a6c71e0ad01..47f8af22f216 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -364,6 +364,7 @@ struct tty_file_private { #define TTY_PTY_LOCK 16 /* pty 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_HALTED 22 /* Line discipline is halted */ /* Values for tty->flow_change */ -- cgit v1.2.3 From fde9fc766e96c494b82931b1d270a9a751be07c0 Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Mon, 19 Feb 2018 16:55:06 +0000 Subject: signals: Move put_compat_sigset to compat.h to silence hardened usercopy Since commit afcc90f8621e ("usercopy: WARN() on slab cache usercopy region violations"), MIPS systems booting with a compat root filesystem emit a warning when copying compat siginfo to userspace: WARNING: CPU: 0 PID: 953 at mm/usercopy.c:81 usercopy_warn+0x98/0xe8 Bad or missing usercopy whitelist? Kernel memory exposure attempt detected from SLAB object 'task_struct' (offset 1432, size 16)! Modules linked in: CPU: 0 PID: 953 Comm: S01logging Not tainted 4.16.0-rc2 #10 Stack : ffffffff808c0000 0000000000000000 0000000000000001 65ac85163f3bdc4a 65ac85163f3bdc4a 0000000000000000 90000000ff667ab8 ffffffff808c0000 00000000000003f8 ffffffff808d0000 00000000000000d1 0000000000000000 000000000000003c 0000000000000000 ffffffff808c8ca8 ffffffff808d0000 ffffffff808d0000 ffffffff80810000 fffffc0000000000 ffffffff80785c30 0000000000000009 0000000000000051 90000000ff667eb0 90000000ff667db0 000000007fe0d938 0000000000000018 ffffffff80449958 0000000020052798 ffffffff808c0000 90000000ff664000 90000000ff667ab0 00000000100c0000 ffffffff80698810 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 ffffffff8010d02c 65ac85163f3bdc4a ... Call Trace: [] show_stack+0x9c/0x130 [] dump_stack+0x90/0xd0 [] __warn+0x100/0x118 [] warn_slowpath_fmt+0x4c/0x70 [] usercopy_warn+0x98/0xe8 [] __check_object_size+0xfc/0x250 [] put_compat_sigset+0x30/0x88 [] setup_rt_frame_n32+0xc4/0x160 [] do_signal+0x19c/0x230 [] do_notify_resume+0x60/0x78 [] work_notifysig+0x10/0x18 ---[ end trace 88fffbf69147f48a ]--- Commit 5905429ad856 ("fork: Provide usercopy whitelisting for task_struct") noted that: "While the blocked and saved_sigmask fields of task_struct are copied to userspace (via sigmask_to_save() and setup_rt_frame()), it is always copied with a static length (i.e. sizeof(sigset_t))." However, this is not true in the case of compat signals, whose sigset is copied by put_compat_sigset and receives size as an argument. At most call sites, put_compat_sigset is copying a sigset from the current task_struct. This triggers a warning when CONFIG_HARDENED_USERCOPY is active. However, by marking this function as static inline, the warning can be avoided because in all of these cases the size is constant at compile time, which is allowed. The only site where this is not the case is handling the rt_sigpending syscall, but there the copy is being made from a stack local variable so does not trigger the warning. Move put_compat_sigset to compat.h, and mark it static inline. This fixes the WARN on MIPS. Fixes: afcc90f8621e ("usercopy: WARN() on slab cache usercopy region violations") Signed-off-by: Matt Redfearn Acked-by: Kees Cook Cc: "Dmitry V . Levin" Cc: Al Viro Cc: kernel-hardening@lists.openwall.com Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/18639/ Signed-off-by: James Hogan --- include/linux/compat.h | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8a9643857c4a..c4139c7a0de0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -17,6 +17,7 @@ #include #include #include /* for aio_context_t */ +#include #include #include @@ -550,8 +551,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); -extern int put_compat_sigset(compat_sigset_t __user *compat, - const sigset_t *set, unsigned int size); + +/* + * Defined inline such that size can be compile time constant, which avoids + * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct + */ +static inline int +put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, + unsigned int size) +{ + /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ +#ifdef __BIG_ENDIAN + compat_sigset_t v; + switch (_NSIG_WORDS) { + case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; + case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; + } + return copy_to_user(compat, &v, size) ? -EFAULT : 0; +#else + return copy_to_user(compat, set, size) ? -EFAULT : 0; +#endif +} asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, -- cgit v1.2.3 From d02f51cbcf12b09ab945873e35046045875eed9a Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Sat, 3 Mar 2018 03:03:46 +0100 Subject: bpf: fix bpf_skb_adjust_net/bpf_skb_proto_xlat to deal with gso sctp skbs SCTP GSO skbs have a gso_size of GSO_BY_FRAGS, so any sort of unconditionally mangling of that will result in nonsense value and would corrupt the skb later on. Therefore, i) add two helpers skb_increase_gso_size() and skb_decrease_gso_size() that would throw a one time warning and bail out for such skbs and ii) refuse and return early with an error in those BPF helpers that are affected. We do need to bail out as early as possible from there before any changes on the skb have been performed. Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper") Co-authored-by: Daniel Borkmann Signed-off-by: Daniel Axtens Cc: Marcelo Ricardo Leitner Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c1e66bdcf583..8c67c33f40c9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4038,6 +4038,12 @@ static inline bool skb_is_gso_v6(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } +/* Note: Should be called only if skb_is_gso(skb) is true */ +static inline bool skb_is_gso_sctp(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; +} + static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; @@ -4045,6 +4051,22 @@ static inline void skb_gso_reset(struct sk_buff *skb) skb_shinfo(skb)->gso_type = 0; } +static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, + u16 increment) +{ + if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) + return; + shinfo->gso_size += increment; +} + +static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, + u16 decrement) +{ + if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) + return; + shinfo->gso_size -= decrement; +} + void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) -- cgit v1.2.3 From 39a751a4cb7e4798f0ce1169ec92de4a1aae39e3 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Mon, 12 Feb 2018 00:19:42 -0800 Subject: of: change overlay apply input data from unflattened to FDT Move duplicating and unflattening of an overlay flattened devicetree (FDT) into the overlay application code. To accomplish this, of_overlay_apply() is replaced by of_overlay_fdt_apply(). The copy of the FDT (aka "duplicate FDT") now belongs to devicetree code, which is thus responsible for freeing the duplicate FDT. The caller of of_overlay_fdt_apply() remains responsible for freeing the original FDT. The unflattened devicetree now belongs to devicetree code, which is thus responsible for freeing the unflattened devicetree. These ownership changes prevent early freeing of the duplicated FDT or the unflattened devicetree, which could result in use after free errors. of_overlay_fdt_apply() is a private function for the anticipated overlay loader. Update unittest.c to use of_overlay_fdt_apply() instead of of_overlay_apply(). Move overlay fragments from artificial locations in drivers/of/unittest-data/tests-overlay.dtsi into one devicetree source file per overlay. This led to changes in drivers/of/unitest-data/Makefile and drivers/of/unitest.c. - Add overlay directives to the overlay devicetree source files so that dtc will compile them as true overlays into one FDT data chunk per overlay. - Set CFLAGS for drivers/of/unittest-data/testcases.dts so that symbols will be generated for overlay resolution of overlays that are no longer artificially contained in testcases.dts - Unflatten and apply each unittest overlay FDT using of_overlay_fdt_apply(). - Enable the of_resolve_phandles() check for whether the unflattened overlay is detached. This check was previously disabled because the overlays from tests-overlay.dtsi were not unflattened into detached trees. - Other changes to unittest.c infrastructure to manage multiple test FDTs built into the kernel image (access by name instead of arbitrary number). - of_unittest_overlay_high_level(): previously unused code to add properties from the overlay_base devicetree to the live tree was triggered by the restructuring of tests-overlay.dtsi and thus testcases.dts. This exposed two bugs: (1) the need to dup a property before adding it, and (2) property 'name' is auto-generated in the unflatten code and thus will be a duplicate in the __symbols__ node - do not treat this duplicate as an error. Signed-off-by: Frank Rowand --- include/linux/of.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index da1ee95241c1..ebf22dd0860c 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1359,8 +1359,8 @@ struct of_overlay_notify_data { #ifdef CONFIG_OF_OVERLAY -/* ID based overlays; the API for external users */ -int of_overlay_apply(struct device_node *tree, int *ovcs_id); +int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, + int *ovcs_id); int of_overlay_remove(int *ovcs_id); int of_overlay_remove_all(void); @@ -1369,7 +1369,7 @@ int of_overlay_notifier_unregister(struct notifier_block *nb); #else -static inline int of_overlay_apply(struct device_node *tree, int *ovcs_id) +static inline int of_overlay_fdt_apply(void *overlay_fdt, int *ovcs_id) { return -ENOTSUPP; } -- cgit v1.2.3 From 325ea10c0809406ce23f038602abbc454f3f761d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 3 Mar 2018 12:20:47 +0100 Subject: sched/headers: Simplify and clean up header usage in the scheduler Do the following cleanups and simplifications: - sched/sched.h already includes , so no need to include it in sched/core.c again. - order the headers alphabetically - add all headers to kernel/sched/sched.h - remove all unnecessary includes from the .c files that are already included in kernel/sched/sched.h. Finally, make all scheduler .c files use a single common header: #include "sched.h" ... which now contains a union of the relied upon headers. This makes the various .c files easier to read and easier to handle. Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/deadline.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index a5bc8728ead7..0cb034331cbb 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -1,8 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_SCHED_DEADLINE_H -#define _LINUX_SCHED_DEADLINE_H - -#include /* * SCHED_DEADLINE tasks has negative priorities, reflecting @@ -28,5 +24,3 @@ static inline bool dl_time_before(u64 a, u64 b) { return (s64)(a - b) < 0; } - -#endif /* _LINUX_SCHED_DEADLINE_H */ -- cgit v1.2.3 From a6f1086e29e93621a6394b94b8c0e4a4e490f38b Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 5 Mar 2018 15:22:30 -0800 Subject: PCI: Move of_irq_parse_and_map_pci() declaration under OF_IRQ Since commit 4670d610d592 ("PCI: Move OF-related PCI functions into PCI core"), sparc:allmodconfig fails to build with the following error. pcie-cadence-host.c:(.text+0x4c4): undefined reference to `of_irq_parse_and_map_pci' pcie-cadence-host.c:(.text+0x4c8): undefined reference to `of_irq_parse_and_map_pci' of_irq_parse_and_map_pci() is now only available if OF_IRQ is enabled. Make its declaration and its dummy function dependent on OF_IRQ to solve the problem. Fixes: 4670d610d592 ("PCI: Move OF-related PCI functions into PCI core") Signed-off-by: Guenter Roeck Signed-off-by: Bjorn Helgaas Acked-by: Rob Herring --- include/linux/of_pci.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 88865e0ebf4d..091033a6b836 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -13,7 +13,6 @@ struct device_node; struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); -int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); int of_pci_get_max_link_speed(struct device_node *node); @@ -33,12 +32,6 @@ static inline int of_pci_get_devfn(struct device_node *np) return -EINVAL; } -static inline int -of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) -{ - return 0; -} - static inline int of_pci_parse_bus_range(struct device_node *node, struct resource *res) { @@ -67,6 +60,16 @@ of_pci_get_max_link_speed(struct device_node *node) static inline void of_pci_check_probe_only(void) { } #endif +#if IS_ENABLED(CONFIG_OF_IRQ) +int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); +#else +static inline int +of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) +{ + return 0; +} +#endif + #if defined(CONFIG_OF_ADDRESS) int of_pci_get_host_bridge_resources(struct device_node *dev, unsigned char busno, unsigned char bus_max, -- cgit v1.2.3 From cb88a0588717ba6c756cb5972d75766b273a6817 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 6 Mar 2018 09:38:49 +0100 Subject: usb: quirks: add control message delay for 1b1c:1b20 Corsair Strafe RGB keyboard does not respond to usb control messages sometimes and hence generates timeouts. Commit de3af5bf259d ("usb: quirks: add delay init quirk for Corsair Strafe RGB keyboard") tried to fix those timeouts by adding USB_QUIRK_DELAY_INIT. Unfortunately, even with this quirk timeouts of usb_control_msg() can still be seen, but with a lower frequency (approx. 1 out of 15): [ 29.103520] usb 1-8: string descriptor 0 read error: -110 [ 34.363097] usb 1-8: can't set config #1, error -110 Adding further delays to different locations where usb control messages are issued just moves the timeouts to other locations, e.g.: [ 35.400533] usbhid 1-8:1.0: can't add hid device: -110 [ 35.401014] usbhid: probe of 1-8:1.0 failed with error -110 The only way to reliably avoid those issues is having a pause after each usb control message. In approx. 200 boot cycles no more timeouts were seen. Addionaly, keep USB_QUIRK_DELAY_INIT as it turned out to be necessary to have the delay in hub_port_connect() after hub_port_init(). The overall boot time seems not to be influenced by these additional delays, even on fast machines and lightweight distributions. Fixes: de3af5bf259d ("usb: quirks: add delay init quirk for Corsair Strafe RGB keyboard") Cc: stable@vger.kernel.org Signed-off-by: Danilo Krummrich 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 f1fcec2fd5f8..b7a99ce56bc9 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -63,4 +63,7 @@ */ #define USB_QUIRK_DISCONNECT_SUSPEND BIT(12) +/* Device needs a pause after every control message. */ +#define USB_QUIRK_DELAY_CTRL_MSG BIT(13) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From d3dcf8eb615537526bd42ff27a081d46d337816e Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Sun, 4 Mar 2018 17:29:48 +0200 Subject: rhashtable: Fix rhlist duplicates insertion When inserting duplicate objects (those with the same key), current rhlist implementation messes up the chain pointers by updating the bucket pointer instead of prev next pointer to the newly inserted node. This causes missing elements on removal and travesal. Fix that by properly updating pprev pointer to point to the correct rhash_head next pointer. Issue: 1241076 Change-Id: I86b2c140bcb4aeb10b70a72a267ff590bb2b17e7 Fixes: ca26893f05e8 ('rhashtable: Add rhlist interface') Signed-off-by: Paul Blakey Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index c9df2527e0cd..668a21f04b09 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -766,8 +766,10 @@ slow_path: if (!key || (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, head)) : - rhashtable_compare(&arg, rht_obj(ht, head)))) + rhashtable_compare(&arg, rht_obj(ht, head)))) { + pprev = &head->next; continue; + } data = rht_obj(ht, head); -- cgit v1.2.3 From 2695578b896aea472b2c0dcbe9d92daa71738484 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 5 Mar 2018 11:41:13 -0800 Subject: net: usbnet: fix potential deadlock on 32bit hosts Marek reported a LOCKDEP issue occurring on 32bit host, that we tracked down to the fact that usbnet could either run from soft or hard irqs. This patch adds u64_stats_update_begin_irqsave() and u64_stats_update_end_irqrestore() helpers to solve this case. [ 17.768040] ================================ [ 17.772239] WARNING: inconsistent lock state [ 17.776511] 4.16.0-rc3-next-20180227-00007-g876c53a7493c #453 Not tainted [ 17.783329] -------------------------------- [ 17.787580] inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. [ 17.793607] swapper/0/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 17.798751] (&syncp->seq#5){?.-.}, at: [<9b22e5f0>] asix_rx_fixup_internal+0x188/0x288 [ 17.806790] {IN-HARDIRQ-W} state was registered at: [ 17.811677] tx_complete+0x100/0x208 [ 17.815319] __usb_hcd_giveback_urb+0x60/0xf0 [ 17.819770] xhci_giveback_urb_in_irq+0xa8/0x240 [ 17.824469] xhci_td_cleanup+0xf4/0x16c [ 17.828367] xhci_irq+0xe74/0x2240 [ 17.831827] usb_hcd_irq+0x24/0x38 [ 17.835343] __handle_irq_event_percpu+0x98/0x510 [ 17.840111] handle_irq_event_percpu+0x1c/0x58 [ 17.844623] handle_irq_event+0x38/0x5c [ 17.848519] handle_fasteoi_irq+0xa4/0x138 [ 17.852681] generic_handle_irq+0x18/0x28 [ 17.856760] __handle_domain_irq+0x6c/0xe4 [ 17.860941] gic_handle_irq+0x54/0xa0 [ 17.864666] __irq_svc+0x70/0xb0 [ 17.867964] arch_cpu_idle+0x20/0x3c [ 17.871578] arch_cpu_idle+0x20/0x3c [ 17.875190] do_idle+0x144/0x218 [ 17.878468] cpu_startup_entry+0x18/0x1c [ 17.882454] start_kernel+0x394/0x400 [ 17.886177] irq event stamp: 161912 [ 17.889616] hardirqs last enabled at (161912): [<7bedfacf>] __netdev_alloc_skb+0xcc/0x140 [ 17.897893] hardirqs last disabled at (161911): [] __netdev_alloc_skb+0x94/0x140 [ 17.904903] exynos5-hsi2c 12ca0000.i2c: tx timeout [ 17.906116] softirqs last enabled at (161904): [<387102ff>] irq_enter+0x78/0x80 [ 17.906123] softirqs last disabled at (161905): [] irq_exit+0x134/0x158 [ 17.925722]. [ 17.925722] other info that might help us debug this: [ 17.933435] Possible unsafe locking scenario: [ 17.933435]. [ 17.940331] CPU0 [ 17.942488] ---- [ 17.944894] lock(&syncp->seq#5); [ 17.948274] [ 17.950847] lock(&syncp->seq#5); [ 17.954386]. [ 17.954386] *** DEADLOCK *** [ 17.954386]. [ 17.962422] no locks held by swapper/0/0. Fixes: c8b5d129ee29 ("net: usbnet: support 64bit stats") Signed-off-by: Eric Dumazet Reported-by: Marek Szyprowski Cc: Greg Ungerer Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 5bdbd9f49395..07ee0f84a46c 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -90,6 +90,28 @@ static inline void u64_stats_update_end(struct u64_stats_sync *syncp) #endif } +static inline unsigned long +u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) +{ + unsigned long flags = 0; + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + local_irq_save(flags); + write_seqcount_begin(&syncp->seq); +#endif + return flags; +} + +static inline void +u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, + unsigned long flags) +{ +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_end(&syncp->seq); + local_irq_restore(flags); +#endif +} + static inline void u64_stats_update_begin_raw(struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) -- cgit v1.2.3 From 63338a38db955cb4e0352c11b78732157c78d30b Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Wed, 7 Mar 2018 08:39:12 +0100 Subject: jailhouse: Provide detection for non-x86 systems Implement jailhouse_paravirt() via device tree probing on architectures != x86. Will be used by the PCI core. Signed-off-by: Jan Kiszka Signed-off-by: Thomas Gleixner Reviewed-by: Juergen Gross Cc: jailhouse-dev@googlegroups.com Cc: Mark Rutland Cc: linux-pci@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: Andy Shevchenko Cc: Rob Herring Cc: Bjorn Helgaas Link: https://lkml.kernel.org/r/dae9fe0c6e63141c28ca90492fa5712b4c33ffb5.1520408357.git.jan.kiszka@siemens.com --- include/linux/hypervisor.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h index b19563f9a8eb..fc08b433c856 100644 --- a/include/linux/hypervisor.h +++ b/include/linux/hypervisor.h @@ -8,15 +8,28 @@ */ #ifdef CONFIG_X86 + +#include #include + static inline void hypervisor_pin_vcpu(int cpu) { x86_platform.hyper.pin_vcpu(cpu); } -#else + +#else /* !CONFIG_X86 */ + +#include + static inline void hypervisor_pin_vcpu(int cpu) { } -#endif + +static inline bool jailhouse_paravirt(void) +{ + return of_find_compatible_node(NULL, NULL, "jailhouse,cell"); +} + +#endif /* !CONFIG_X86 */ #endif /* __LINUX_HYPEVISOR_H */ -- cgit v1.2.3 From 4042d003a0792a3b05c7c424219e4c6cf1abfe76 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Dec 2017 15:37:26 +0100 Subject: cpufreq/schedutil: Remove unused CPUFREQ_DL Bitrot... Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index 0b55834efd46..d963cfd3a0c2 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -9,8 +9,7 @@ */ #define SCHED_CPUFREQ_RT (1U << 0) -#define SCHED_CPUFREQ_DL (1U << 1) -#define SCHED_CPUFREQ_IOWAIT (1U << 2) +#define SCHED_CPUFREQ_IOWAIT (1U << 1) #ifdef CONFIG_CPU_FREQ struct update_util_data { -- cgit v1.2.3 From 8f111bc357aa811e0bb5fdfe34c4c9efdafc15b9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Dec 2017 16:26:12 +0100 Subject: cpufreq/schedutil: Rewrite CPUFREQ_RT support Instead of trying to duplicate scheduler state to track if an RT task is running, directly use the scheduler runqueue state for it. This vastly simplifies things and fixes a number of bugs related to sugov and the scheduler getting out of sync wrt this state. As a consequence we not also update the remove cfs/dl state when iterating the shared mask. Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index d963cfd3a0c2..b48f2fb3b316 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -8,8 +8,7 @@ * Interface between cpufreq drivers and the scheduler: */ -#define SCHED_CPUFREQ_RT (1U << 0) -#define SCHED_CPUFREQ_IOWAIT (1U << 1) +#define SCHED_CPUFREQ_IOWAIT (1U << 0) #ifdef CONFIG_CPU_FREQ struct update_util_data { -- cgit v1.2.3 From 00357f5ec5d67a52a175da6f29f85c2c19d59bc8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 21 Dec 2017 15:06:50 +0100 Subject: sched/nohz: Clean up nohz enter/exit The primary observation is that nohz enter/exit is always from the current CPU, therefore NOHZ_TICK_STOPPED does not in fact need to be an atomic. Secondary is that we appear to have 2 nearly identical hooks in the nohz enter code, set_cpu_sd_state_idle() and nohz_balance_enter_idle(). Fold the whole set_cpu_sd_state thing into nohz_balance_{enter,exit}_idle. Removes an atomic op from both enter and exit paths. Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/nohz.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 094217273ff9..b36f4cf38111 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -16,11 +16,9 @@ static inline void cpu_load_update_nohz_stop(void) { } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); -extern void set_cpu_sd_state_idle(void); extern int get_nohz_timer_target(void); #else static inline void nohz_balance_enter_idle(int cpu) { } -static inline void set_cpu_sd_state_idle(void) { } #endif #ifdef CONFIG_NO_HZ_COMMON -- cgit v1.2.3 From ea14b57e8a181ac0561eba7a787e088f8c89f822 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 2 Feb 2018 10:27:00 +0100 Subject: sched/cpufreq: Provide migration hint It was suggested that a migration hint might be usefull for the CPU-freq governors. Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index b48f2fb3b316..59667444669f 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -9,6 +9,7 @@ */ #define SCHED_CPUFREQ_IOWAIT (1U << 0) +#define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ struct update_util_data { -- cgit v1.2.3 From 3a4030761ea88ff439030ca98e3094b9900e96b7 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 9 Mar 2018 14:50:34 +0800 Subject: vhost_net: examine pointer types during un-producing After commit fc72d1d54dd9 ("tuntap: XDP transmission"), we can actually queueing XDP pointers in the pointer ring, so we should examine the pointer type before freeing the pointer. Fixes: fc72d1d54dd9 ("tuntap: XDP transmission") Reported-by: Michael S. Tsirkin Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/if_tun.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index c5b0a75a7812..fd00170b494f 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -25,6 +25,7 @@ struct ptr_ring *tun_get_tx_ring(struct file *file); bool tun_is_xdp_buff(void *ptr); void *tun_xdp_to_ptr(void *ptr); void *tun_ptr_to_xdp(void *ptr); +void tun_ptr_free(void *ptr); #else #include #include @@ -50,5 +51,8 @@ static inline void *tun_ptr_to_xdp(void *ptr) { return NULL; } +static inline void tun_ptr_free(void *ptr) +{ +} #endif /* CONFIG_TUN */ #endif /* __IF_TUN_H */ -- cgit v1.2.3 From 739d875dd6982618020d30f58f8acf10f6076e6d Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 8 Mar 2018 09:48:46 +0000 Subject: mn10300: Remove the architecture Remove the MN10300 arch as the hardware is defunct. Suggested-by: Arnd Bergmann Signed-off-by: David Howells cc: Masahiro Yamada cc: linux-am33-list@redhat.com Signed-off-by: Arnd Bergmann --- 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 771989d25ef8..20d42c0d9fb6 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -25,7 +25,7 @@ #include #include -#if defined(CONFIG_CRIS) || defined(CONFIG_FRV) || defined(CONFIG_MN10300) +#if defined(CONFIG_CRIS) || defined(CONFIG_FRV) # define SUPPORT_VLB_SYNC 0 #else # define SUPPORT_VLB_SYNC 1 -- cgit v1.2.3 From b1d0a5d0cba4597c0394997b2d5fced3e3841b4e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 10 Mar 2018 01:15:45 +0100 Subject: netfilter: x_tables: add and use xt_check_proc_name recent and hashlimit both create /proc files, but only check that name is 0 terminated. This can trigger WARN() from procfs when name is "" or "/". Add helper for this and then use it for both. Cc: Eric Dumazet Reported-by: Eric Dumazet Reported-by: Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 1313b35c3ab7..14529511c4b8 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -285,6 +285,8 @@ unsigned int *xt_alloc_entry_offsets(unsigned int size); bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size); +int xt_check_proc_name(const char *name, unsigned int size); + int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto, -- cgit v1.2.3 From 7e904a91bf6049071ef9d605a52f863ae774081d Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Mon, 12 Mar 2018 08:44:56 +0000 Subject: efi: Use efi_mm in x86 as well as ARM Presently, only ARM uses mm_struct to manage EFI page tables and EFI runtime region mappings. As this is the preferred approach, let's make this data structure common across architectures. Specially, for x86, using this data structure improves code maintainability and readability. Tested-by: Bhupesh Sharma [ardb: don't #include the world to get a declaration of struct mm_struct] Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Ard Biesheuvel Reviewed-by: Matt Fleming Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Lee, Chun-Yi Cc: Linus Torvalds Cc: Michael S. Tsirkin Cc: Peter Zijlstra Cc: Ravi Shankar Cc: Ricardo Neri Cc: Thomas Gleixner Cc: Tony Luck Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180312084500.10764-2-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index f5083aa72eae..f1b7d68ac460 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -966,6 +966,8 @@ extern struct efi { unsigned long flags; } efi; +extern struct mm_struct efi_mm; + static inline int efi_guidcmp (efi_guid_t left, efi_guid_t right) { -- cgit v1.2.3 From 9e49e2447c6385e45c6fddd70d6c0e917e21b669 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 27 Feb 2018 17:05:10 +0100 Subject: sched/core: Remove TASK_ALL It's unused: $ git grep "\" | wc -l 1 ... and it is also dangerous, kill the bugger. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180227160510.10829-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b161ef8a902e..21b1168da951 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -93,7 +93,6 @@ struct task_group; /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) -#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ -- cgit v1.2.3 From 8e1a2031e4b556b01ca53cd1fb2d83d811a6605b Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Fri, 8 Sep 2017 11:47:03 +0300 Subject: perf/cor: Use RB trees for pinned/flexible groups Change event groups into RB trees sorted by CPU and then by a 64bit index, so that multiplexing hrtimer interrupt handler would be able skipping to the current CPU's list and ignore groups allocated for the other CPUs. New API for manipulating event groups in the trees is implemented as well as adoption on the API in the current implementation. pinned_group_sched_in() and flexible_group_sched_in() API are introduced to consolidate code enabling the whole group from pinned and flexible groups appropriately. Signed-off-by: Alexey Budankov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: David Carrillo-Cisneros Cc: Dmitri Prokhorov Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Valery Cherepennikov Cc: Vince Weaver Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/372f9c8b-0cfe-4240-e44d-83d863d40813@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7546822a1d74..6e3f854a34d8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -558,7 +558,11 @@ struct perf_event { */ struct list_head group_entry; struct list_head sibling_list; - + /* + * Node on the pinned or flexible tree located at the event context; + */ + struct rb_node group_node; + u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the @@ -690,6 +694,12 @@ struct perf_event { #endif /* CONFIG_PERF_EVENTS */ }; + +struct perf_event_groups { + struct rb_root tree; + u64 index; +}; + /** * struct perf_event_context - event context structure * @@ -710,8 +720,8 @@ struct perf_event_context { struct mutex mutex; struct list_head active_ctx_list; - struct list_head pinned_groups; - struct list_head flexible_groups; + struct perf_event_groups pinned_groups; + struct perf_event_groups flexible_groups; struct list_head event_list; int nr_events; int nr_active; -- cgit v1.2.3 From 8343aae66167df6708128a778e750d48dbe31302 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 13 Nov 2017 14:28:33 +0100 Subject: perf/core: Remove perf_event::group_entry Now that all the grouping is done with RB trees, we no longer need group_entry and can replace the whole thing with sibling_list. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Arnaldo Carvalho de Melo Cc: David Carrillo-Cisneros Cc: Dmitri Prokhorov Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Valery Cherepennikov Cc: Vince Weaver Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6e3f854a34d8..84044ec21b31 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -549,14 +549,9 @@ struct perf_event { struct list_head event_entry; /* - * XXX: group_entry and sibling_list should be mutually exclusive; - * either you're a sibling on a group, or you're the group leader. - * Rework the code to always use the same list element. - * * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ - struct list_head group_entry; struct list_head sibling_list; /* * Node on the pinned or flexible tree located at the event context; -- cgit v1.2.3 From 6668128a9e25f7a11d25359e46df2541e6b43fc9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 13 Nov 2017 14:28:38 +0100 Subject: perf/core: Optimize ctx_sched_out() When an event group contains more events than can be scheduled on the hardware, iterating the full event group for ctx_sched_out is a waste of time. Keep track of the events that got programmed on the hardware, such that we can iterate this smaller list in order to schedule them out. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Arnaldo Carvalho de Melo Cc: David Carrillo-Cisneros Cc: Dmitri Prokhorov Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Valery Cherepennikov Cc: Vince Weaver Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 84044ec21b31..2bb200e1bbea 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -553,6 +553,7 @@ struct perf_event { * either sufficies for read. */ struct list_head sibling_list; + struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ @@ -718,6 +719,10 @@ struct perf_event_context { struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; + + struct list_head pinned_active; + struct list_head flexible_active; + int nr_events; int nr_active; int is_active; -- cgit v1.2.3 From a2c054a896b8ac794ddcfc7c92e2dc7ec4ed4ed5 Mon Sep 17 00:00:00 2001 From: Brad Mouring Date: Thu, 8 Mar 2018 16:23:03 -0600 Subject: net: phy: Tell caller result of phy_change() In 664fcf123a30e (net: phy: Threaded interrupts allow some simplification) the phy_interrupt system was changed to use a traditional threaded interrupt scheme instead of a workqueue approach. With this change, the phy status check moved into phy_change, which did not report back to the caller whether or not the interrupt was handled. This means that, in the case of a shared phy interrupt, only the first phydev's interrupt registers are checked (since phy_interrupt() would always return IRQ_HANDLED). This leads to interrupt storms when it is a secondary device that's actually the interrupt source. Signed-off-by: Brad Mouring 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 d7069539f351..b260fb336b25 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1012,7 +1012,6 @@ 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(struct phy_device *phydev); void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); -- cgit v1.2.3 From bf2ae2e4bf9360e07c0cdfa166bcdc0afd92f4ce Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 10 Mar 2018 18:57:50 +0800 Subject: sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca Acked-by: Marcelo Ricardo Leitner Acked-by: Phil Sutter Acked-by: Sabrina Dubroca Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 91216b16feb7..2a0391eea05c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -222,6 +222,7 @@ enum { int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); +bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); -- cgit v1.2.3 From 32ff77e8cc9e66cc4fb38098f64fd54cc8f54573 Mon Sep 17 00:00:00 2001 From: Milind Chabbi Date: Mon, 12 Mar 2018 14:45:47 +0100 Subject: perf/core: Implement fast breakpoint modification via _IOC_MODIFY_ATTRIBUTES Problem and motivation: Once a breakpoint perf event (PERF_TYPE_BREAKPOINT) is created, there is no flexibility to change the breakpoint type (bp_type), breakpoint address (bp_addr), or breakpoint length (bp_len). The only option is to close the perf event and configure a new breakpoint event. This inflexibility has a significant performance overhead. For example, sampling-based, lightweight performance profilers (and also concurrency bug detection tools), monitor different addresses for a short duration using PERF_TYPE_BREAKPOINT and change the address (bp_addr) to another address or change the kind of breakpoint (bp_type) from "write" to a "read" or vice-versa or change the length (bp_len) of the address being monitored. The cost of these modifications is prohibitive since it involves unmapping the circular buffer associated with the perf event, closing the perf event, opening another perf event and mmaping another circular buffer. Solution: The new ioctl flag for perf events, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, introduced in this patch takes a pointer to a struct perf_event_attr as an argument to update an old breakpoint event with new address, type, and size. This facility allows retaining a previous mmaped perf events ring buffer and avoids having to close and reopen another perf event. This patch supports only changing PERF_TYPE_BREAKPOINT event type; future implementations can extend this feature. The patch replicates some of its functionality of modify_user_hw_breakpoint() in kernel/events/hw_breakpoint.c. modify_user_hw_breakpoint cannot be called directly since perf_event_ctx_lock() is already held in _perf_ioctl(). Evidence: Experiments show that the baseline (not able to modify an already created breakpoint) costs an order of magnitude (~10x) more than the suggested optimization (having the ability to dynamically modifying a configured breakpoint via ioctl). When the breakpoints typically do not trap, the speedup due to the suggested optimization is ~10x; even when the breakpoints always trap, the speedup is ~4x due to the suggested optimization. Testing: tests posted at https://github.com/linux-contrib/perf_event_modify_bp demonstrate the performance significance of this patch. Tests also check the functional correctness of the patch. Signed-off-by: Milind Chabbi [ Using modify_user_hw_breakpoint_check function. ] [ Reformated PERF_EVENT_IOC_*, so the values are all in one column. ] Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Frederic Weisbecker Cc: Hari Bathini Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Michael Ellerman Cc: Namhyung Kim Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Sukadev Bhattiprolu Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/20180312134548.31532-8-jolsa@kernel.org Signed-off-by: Ingo Molnar --- include/linux/hw_breakpoint.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index cf045885a499..6058c3844a76 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -53,6 +53,9 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, /* FIXME: only change from the attr, and don't unregister */ extern int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr); +extern int +modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, + bool check); /* * Kernel breakpoints are not associated with any particular thread. @@ -97,6 +100,10 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, static inline int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { return -ENOSYS; } +static inline int +modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr, + bool check) { return -ENOSYS; } + static inline struct perf_event * register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr, perf_overflow_handler_t triggered, -- cgit v1.2.3 From c2b37f76485f073f020e60b5954b6dc4e55f693c Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Thu, 8 Mar 2018 15:51:41 +0200 Subject: IB/mlx5: Fix integer overflows in mlx5_ib_create_srq This patch validates user provided input to prevent integer overflow due to integer manipulation in the mlx5_ib_create_srq function. Cc: syzkaller Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Boris Pismenny Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- 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 6ed79a8a8318..9d3a03364e6e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -453,8 +453,8 @@ struct mlx5_core_srq { struct mlx5_core_rsc_common common; /* must be first */ u32 srqn; int max; - int max_gs; - int max_avail_gather; + size_t max_gs; + size_t max_avail_gather; int wqe_shift; void (*event) (struct mlx5_core_srq *, enum mlx5_event); -- cgit v1.2.3 From 6417250d3f894e66a68ba1cd93676143f2376a6f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 6 Mar 2018 19:34:42 -0800 Subject: workqueue: remove unused cancel_work() Found this by accident. There are no usages of bare cancel_work() in current kernel source. Signed-off-by: Stephen Hemminger Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bc0cda180c8b..0c3301421c57 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -456,7 +456,6 @@ extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); -extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); -- cgit v1.2.3 From 2a4d2c4240c00e7db8fb64e377bd2180cc30b146 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 3 Mar 2018 10:53:24 +0100 Subject: PCI: Make pci_wakeup_bus() & pci_bus_set_current_state() public There are PCI devices which are power-manageable by a nonstandard means, such as a custom ACPI method. One example are discrete GPUs in hybrid graphics laptops, another are Thunderbolt controllers in Macs. Such devices can't be put into D3cold with pci_set_power_state() because pci_platform_power_transition() fails with -ENODEV. Instead they're put into D3hot by pci_set_power_state() and subsequently into D3cold by invoking the nonstandard means. However as a consequence the cached current_state is incorrectly left at D3hot. What we need to do is walk the hierarchy below such a PCI device on powerdown and update the current_state to D3cold. On powerup the PCI device itself and the hierarchy below it is in D0uninitialized, so we need to walk the hierarchy again and wake all devices, causing them to be put into D0active and then letting them autosuspend as they see fit. To this end make pci_wakeup_bus() & pci_bus_set_current_state() public so PCI drivers don't have to reinvent the wheel. Cc: Rafael J. Wysocki Acked-by: Bjorn Helgaas Signed-off-by: Lukas Wunner Link: https://patchwork.freedesktop.org/patch/msgid/2962443259e7faec577274b4ef8c54aad66f9a94.1520068884.git.lukas@wunner.de --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 024a1beda008..ae42289662df 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1147,6 +1147,8 @@ void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); +void pci_wakeup_bus(struct pci_bus *bus); +void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state); /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev); -- cgit v1.2.3 From 07f4f97d7b4bf325d9f558c5b58230387e4e57e0 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 3 Mar 2018 10:53:24 +0100 Subject: vga_switcheroo: Use device link for HDA controller Back in 2013, runtime PM for GPUs with integrated HDA controller was introduced with commits 0d69704ae348 ("gpu/vga_switcheroo: add driver control power feature. (v3)") and 246efa4a072f ("snd/hda: add runtime suspend/resume on optimus support (v4)"). Briefly, the idea was that the HDA controller is forced on and off in unison with the GPU. The original code is mostly still in place even though it was never a 100% perfect solution: E.g. on access to the HDA controller, the GPU is powered up via vga_switcheroo_runtime_resume_hdmi_audio() but there are no provisions to keep it resumed until access to the HDA controller has ceased: The GPU autosuspends after 5 seconds, rendering the HDA controller inaccessible. Additionally, a kludge is required when hda_intel.c probes: It has to check whether the GPU is powered down (check_hdmi_disabled()) and defer probing if so. However in the meantime (in v4.10) the driver core has gained a feature called device links which promises to solve such issues in a clean way: It allows us to declare a dependency from the HDA controller (consumer) to the GPU (supplier). The PM core then automagically ensures that the GPU is runtime resumed as long as the HDA controller's ->probe hook is executed and whenever the HDA controller is accessed. By default, the HDA controller has a dependency on its parent, a PCIe Root Port. Adding a device link creates another dependency on its sibling: PCIe Root Port ^ ^ | | | | HDA ===> GPU The device link is not only used for runtime PM, it also guarantees that on system sleep, the HDA controller suspends before the GPU and resumes after the GPU, and on system shutdown the HDA controller's ->shutdown hook is executed before the one of the GPU. It is a complete solution. Using this functionality is as simple as calling device_link_add(), which results in a dmesg entry like this: pci 0000:01:00.1: Linked as a consumer to 0000:01:00.0 The code for the GPU-governed audio power management can thus be removed (except where it's still needed for legacy manual power control). The device link is added in a PCI quirk rather than in hda_intel.c. It is therefore legal for the GPU to runtime suspend to D3cold even if the HDA controller is not bound to a driver or if CONFIG_SND_HDA_INTEL is not enabled, for accesses to the HDA controller will cause the GPU to wake up regardless if they're occurring outside of hda_intel.c (think config space readout via sysfs). Contrary to the previous implementation, the HDA controller's power state is now self-governed, rather than GPU-governed, whereas the GPU's power state is no longer fully self-governed. (The HDA controller needs to runtime suspend before the GPU can.) It is thus crucial that runtime PM is always activated on the HDA controller even if CONFIG_SND_HDA_POWER_SAVE_DEFAULT is set to 0 (which is the default), lest the GPU stays awake. This is achieved by setting the auto_runtime_pm flag on every codec and the AZX_DCAPS_PM_RUNTIME flag on the HDA controller. A side effect is that power consumption might be reduced if the GPU is in use but the HDA controller is not, because the HDA controller is now allowed to go to D3hot. Before, it was forced to stay in D0 as long as the GPU was in use. (There is no reduction in power consumption on my Nvidia GK107, but there might be on other chips.) The code paths for legacy manual power control are adjusted such that runtime PM is disabled during power off, thereby preventing the PM core from resuming the HDA controller. Note that the device link is not only added on vga_switcheroo capable systems, but for *any* GPU with integrated HDA controller. The idea is that the HDA controller streams audio via connectors located on the GPU, so the GPU needs to be on for the HDA controller to do anything useful. This commit implicitly fixes an unbalanced runtime PM ref upon unbind of hda_intel.c: On ->probe, a runtime PM ref was previously released under the condition "azx_has_pm_runtime(chip) || hda->use_vga_switcheroo", but on ->remove a runtime PM ref was only acquired under the first of those conditions. Thus, binding and unbinding the driver twice on a vga_switcheroo capable system caused the runtime PM refcount to drop below zero. The issue is resolved because the AZX_DCAPS_PM_RUNTIME flag is now always set if use_vga_switcheroo is true. For more information on device links please refer to: https://www.kernel.org/doc/html/latest/driver-api/device_link.html Documentation/driver-api/device_link.rst Cc: Dave Airlie Cc: Ben Skeggs Cc: Alex Deucher Cc: Rafael J. Wysocki Acked-by: Bjorn Helgaas Reviewed-by: Takashi Iwai Reviewed-by: Peter Wu Tested-by: Kai Heng Feng # AMD PowerXpress Tested-by: Mike Lothian # AMD PowerXpress Tested-by: Denis Lisov # Nvidia Optimus Tested-by: Peter Wu # Nvidia Optimus Tested-by: Lukas Wunner # MacBook Pro Signed-off-by: Lukas Wunner Link: https://patchwork.freedesktop.org/patch/msgid/51bd38360ff502a8c42b1ebf4405ee1d3f27118d.1520068884.git.lukas@wunner.de --- include/linux/pci_ids.h | 1 + include/linux/vga_switcheroo.h | 6 ------ 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a6b30667a331..a637a7d8ce5b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -45,6 +45,7 @@ #define PCI_CLASS_MULTIMEDIA_VIDEO 0x0400 #define PCI_CLASS_MULTIMEDIA_AUDIO 0x0401 #define PCI_CLASS_MULTIMEDIA_PHONE 0x0402 +#define PCI_CLASS_MULTIMEDIA_HD_AUDIO 0x0403 #define PCI_CLASS_MULTIMEDIA_OTHER 0x0480 #define PCI_BASE_CLASS_MEMORY 0x05 diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index 960bedbdec87..77f0f0af3a71 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -168,11 +168,8 @@ int vga_switcheroo_process_delayed_switch(void); bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev); enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev); -void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic); - int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain); void vga_switcheroo_fini_domain_pm_ops(struct device *dev); -int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain); #else static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {} @@ -192,11 +189,8 @@ static inline int vga_switcheroo_process_delayed_switch(void) { return 0; } static inline bool vga_switcheroo_client_probe_defer(struct pci_dev *pdev) { return false; } static inline enum vga_switcheroo_state vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; } -static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {} - static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {} -static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; } #endif #endif /* _LINUX_VGA_SWITCHEROO_H_ */ -- cgit v1.2.3 From 4dcb31d4649df36297296b819437709f5407059c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 14 Mar 2018 09:04:16 -0700 Subject: net: use skb_to_full_sk() in skb_update_prio() Andrei Vagin reported a KASAN: slab-out-of-bounds error in skb_update_prio() Since SYNACK might be attached to a request socket, we need to get back to the listener socket. Since this listener is manipulated without locks, add const qualifiers to sock_cgroup_prioidx() so that the const can also be used in skb_update_prio() Also add the const qualifier to sock_cgroup_classid() for consistency. Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener") Signed-off-by: Eric Dumazet Reported-by: Andrei Vagin Signed-off-by: David S. Miller --- include/linux/cgroup-defs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 9f242b876fde..f8e76d01a5ad 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -755,13 +755,13 @@ struct sock_cgroup_data { * updaters and return part of the previous pointer as the prioidx or * classid. Such races are short-lived and the result isn't critical. */ -static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd) +static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { /* fallback to 1 which is always the ID of the root cgroup */ return (skcd->is_data & 1) ? skcd->prioidx : 1; } -static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd) +static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { /* fallback to 0 which is the unconfigured default classid */ return (skcd->is_data & 1) ? skcd->classid : 0; -- cgit v1.2.3 From 16ca6a607d84bef0129698d8d808f501afd08d43 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 6 Mar 2018 21:48:01 +0000 Subject: KVM: arm/arm64: vgic: Don't populate multiple LRs with the same vintid The vgic code is trying to be clever when injecting GICv2 SGIs, and will happily populate LRs with the same interrupt number if they come from multiple vcpus (after all, they are distinct interrupt sources). Unfortunately, this is against the letter of the architecture, and the GICv2 architecture spec says "Each valid interrupt stored in the List registers must have a unique VirtualID for that virtual CPU interface.". GICv3 has similar (although slightly ambiguous) restrictions. This results in guests locking up when using GICv2-on-GICv3, for example. The obvious fix is to stop trying so hard, and inject a single vcpu per SGI per guest entry. After all, pending SGIs with multiple source vcpus are pretty rare, and are mostly seen in scenario where the physical CPUs are severely overcomitted. But as we now only inject a single instance of a multi-source SGI per vcpu entry, we may delay those interrupts for longer than strictly necessary, and run the risk of injecting lower priority interrupts in the meantime. In order to address this, we adopt a three stage strategy: - If we encounter a multi-source SGI in the AP list while computing its depth, we force the list to be sorted - When populating the LRs, we prevent the injection of any interrupt of lower priority than that of the first multi-source SGI we've injected. - Finally, the injection of a multi-source SGI triggers the request of a maintenance interrupt when there will be no pending interrupt in the LRs (HCR_NPIE). At the point where the last pending interrupt in the LRs switches from Pending to Active, the maintenance interrupt will be delivered, allowing us to add the remaining SGIs using the same process. Cc: stable@vger.kernel.org Fixes: 0919e84c0fc1 ("KVM: arm/arm64: vgic-new: Add IRQ sync/flush framework") Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 1 + include/linux/irqchip/arm-gic.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index c00c4c33e432..b26eccc78fb1 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -503,6 +503,7 @@ #define ICH_HCR_EN (1 << 0) #define ICH_HCR_UIE (1 << 1) +#define ICH_HCR_NPIE (1 << 3) #define ICH_HCR_TC (1 << 10) #define ICH_HCR_TALL0 (1 << 11) #define ICH_HCR_TALL1 (1 << 12) diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index d3453ee072fc..68d8b1f73682 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -84,6 +84,7 @@ #define GICH_HCR_EN (1 << 0) #define GICH_HCR_UIE (1 << 1) +#define GICH_HCR_NPIE (1 << 3) #define GICH_LR_VIRTUALID (0x3ff << 0) #define GICH_LR_PHYSID_CPUID_SHIFT (10) -- cgit v1.2.3 From 95dd77580ccd66a0da96e6d4696945b8cea39431 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 14 Mar 2018 18:20:29 -0500 Subject: fs: Teach path_connected to handle nfs filesystems with multiple roots. On nfsv2 and nfsv3 the nfs server can export subsets of the same filesystem and report the same filesystem identifier, so that the nfs client can know they are the same filesystem. The subsets can be from disjoint directory trees. The nfsv2 and nfsv3 filesystems provides no way to find the common root of all directory trees exported form the server with the same filesystem identifier. The practical result is that in struct super s_root for nfs s_root is not necessarily the root of the filesystem. The nfs mount code sets s_root to the root of the first subset of the nfs filesystem that the kernel mounts. This effects the dcache invalidation code in generic_shutdown_super currently called shrunk_dcache_for_umount and that code for years has gone through an additional list of dentries that might be dentry trees that need to be freed to accomodate nfs. When I wrote path_connected I did not realize nfs was so special, and it's hueristic for avoiding calling is_subdir can fail. The practical case where this fails is when there is a move of a directory from the subtree exposed by one nfs mount to the subtree exposed by another nfs mount. This move can happen either locally or remotely. With the remote case requiring that the move directory be cached before the move and that after the move someone walks the path to where the move directory now exists and in so doing causes the already cached directory to be moved in the dcache through the magic of d_splice_alias. If someone whose working directory is in the move directory or a subdirectory and now starts calling .. from the initial mount of nfs (where s_root == mnt_root), then path_connected as a heuristic will not bother with the is_subdir check. As s_root really is not the root of the nfs filesystem this heuristic is wrong, and the path may actually not be connected and path_connected can fail. The is_subdir function might be cheap enough that we can call it unconditionally. Verifying that will take some benchmarking and the result may not be the same on all kernels this fix needs to be backported to. So I am avoiding that for now. Filesystems with snapshots such as nilfs and btrfs do something similar. But as the directory tree of the snapshots are disjoint from one another and from the main directory tree rename won't move things between them and this problem will not occur. Cc: stable@vger.kernel.org Reported-by: Al Viro Fixes: 397d425dc26d ("vfs: Test for and handle paths that are unreachable from their mnt_root") Signed-off-by: "Eric W. Biederman" Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a815560fda0..0430e03febaa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1317,6 +1317,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ +#define SB_I_MULTIROOT 0x00000008 /* Multiple roots to the dentry tree */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -- cgit v1.2.3 From 4ba66a9760722ccbb691b8f7116cad2f791cca7b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 7 Mar 2018 22:23:24 +0100 Subject: arch: remove blackfin port The Analog Devices Blackfin port was added in 2007 and was rather active for a while, but all work on it has come to a standstill over time, as Analog have changed their product line-up. Aaron Wu confirmed that the architecture port is no longer relevant, and multiple people suggested removing blackfin independently because of some of its oddities like a non-working SMP port, and the amount of duplication between the chip variants, which cause extra work when doing cross-architecture changes. Link: https://docs.blackfin.uclinux.org/ Acked-by: Aaron Wu Acked-by: Bryan Wu Cc: Steven Miao Cc: Mike Frysinger Signed-off-by: Arnd Bergmann --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5b211fe295f0..8796ba387152 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -29,7 +29,6 @@ enum cpuhp_state { CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, CPUHP_PERF_X86_AMD_UNCORE_PREP, - CPUHP_PERF_BFIN, CPUHP_PERF_POWER, CPUHP_PERF_SUPERH, CPUHP_X86_HPET_DEAD, -- cgit v1.2.3 From 79375ea3ec527f746d5beae8c8f6e8a58740d4a8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 23:14:56 +0100 Subject: mm: remove obsolete alloc_remap() Tile was the only remaining architecture to implement alloc_remap(), and since that is being removed, there is no point in keeping this function. Removing all callers simplifies the mem_map handling. Reviewed-by: Pavel Tatashin Signed-off-by: Arnd Bergmann --- include/linux/bootmem.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index a53063e9d7d8..7942a96b1a9d 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -364,15 +364,6 @@ static inline void __init memblock_free_late( } #endif /* defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) */ -#ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP -extern void *alloc_remap(int nid, unsigned long size); -#else -static inline void *alloc_remap(int nid, unsigned long size) -{ - return NULL; -} -#endif /* CONFIG_HAVE_ARCH_ALLOC_REMAP */ - extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, unsigned long numentries, -- cgit v1.2.3 From cbe7128c4b92e2004984f477fd38dfa81662f02e Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 13 Mar 2018 14:51:28 +0900 Subject: vlan: Fix out of order vlan headers with reorder header off With reorder header off, received packets are untagged in skb_vlan_untag() called from within __netif_receive_skb_core(), and later the tag will be inserted back in vlan_do_receive(). This caused out of order vlan headers when we create a vlan device on top of another vlan device, because vlan_do_receive() inserts a tag as the outermost vlan tag. E.g. the outer tag is first removed in skb_vlan_untag() and inserted back in vlan_do_receive(), then the inner tag is next removed and inserted back as the outermost tag. This patch fixes the behaviour by inserting the inner tag at the right position. Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 66 ++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 55 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 5e6a2d4dc366..c4a1cff9c768 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -300,30 +300,34 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features, } /** - * __vlan_insert_tag - regular VLAN tag inserting + * __vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert + * @mac_len: MAC header length including outer vlan headers * - * Inserts the VLAN tag into @skb as part of the payload + * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns error if skb_cow_head failes. * * Does not change skb->protocol so this function can be used during receive. */ -static inline int __vlan_insert_tag(struct sk_buff *skb, - __be16 vlan_proto, u16 vlan_tci) +static inline int __vlan_insert_inner_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci, + unsigned int mac_len) { struct vlan_ethhdr *veth; if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; - veth = skb_push(skb, VLAN_HLEN); + skb_push(skb, VLAN_HLEN); - /* Move the mac addresses to the beginning of the new header. */ - memmove(skb->data, skb->data + VLAN_HLEN, 2 * ETH_ALEN); + /* Move the mac header sans proto to the beginning of the new header. */ + memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); skb->mac_header -= VLAN_HLEN; + veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); + /* first, the ethernet type */ veth->h_vlan_proto = vlan_proto; @@ -334,12 +338,30 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, } /** - * vlan_insert_tag - regular VLAN tag inserting + * __vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload + * Returns error if skb_cow_head failes. + * + * Does not change skb->protocol so this function can be used during receive. + */ +static inline int __vlan_insert_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) +{ + return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); +} + +/** + * vlan_insert_inner_tag - inner VLAN tag inserting + * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol + * @vlan_tci: VLAN TCI to insert + * @mac_len: MAC header length including outer vlan headers + * + * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. * * Following the skb_unshare() example, in case of error, the calling function @@ -347,12 +369,14 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, * * Does not change skb->protocol so this function can be used during receive. */ -static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, - __be16 vlan_proto, u16 vlan_tci) +static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, + __be16 vlan_proto, + u16 vlan_tci, + unsigned int mac_len) { int err; - err = __vlan_insert_tag(skb, vlan_proto, vlan_tci); + err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len); if (err) { dev_kfree_skb_any(skb); return NULL; @@ -360,6 +384,26 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, return skb; } +/** + * vlan_insert_tag - regular VLAN tag inserting + * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol + * @vlan_tci: VLAN TCI to insert + * + * Inserts the VLAN tag into @skb as part of the payload + * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * + * Following the skb_unshare() example, in case of error, the calling function + * doesn't have to worry about freeing the original skb. + * + * Does not change skb->protocol so this function can be used during receive. + */ +static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) +{ + return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); +} + /** * vlan_insert_tag_set_proto - regular VLAN tag inserting * @skb: skbuff to tag -- cgit v1.2.3 From edb39592a5877bd91b2e6ee15194268f35b04892 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 15 Mar 2018 17:36:56 +0100 Subject: perf: Fix sibling iteration Mark noticed that the change to sibling_list changed some iteration semantics; because previously we used group_list as list entry, sibling events would always have an empty sibling_list. But because we now use sibling_list for both list head and list entry, siblings will report as having siblings. Fix this with a custom for_each_sibling_event() iterator. Fixes: 8343aae66167 ("perf/core: Remove perf_event::group_entry") Reported-by: Mark Rutland Suggested-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: vincent.weaver@maine.edu Cc: alexander.shishkin@linux.intel.com Cc: torvalds@linux-foundation.org Cc: alexey.budankov@linux.intel.com Cc: valery.cherepennikov@intel.com Cc: eranian@google.com Cc: acme@redhat.com Cc: linux-tip-commits@vger.kernel.org Cc: davidcc@google.com Cc: kan.liang@intel.com Cc: Dmitry.Prohorov@intel.com Cc: jolsa@redhat.com Link: https://lkml.kernel.org/r/20180315170129.GX4043@hirez.programming.kicks-ass.net --- include/linux/perf_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2bb200e1bbea..ff39ab011376 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -536,6 +536,10 @@ struct pmu_event_list { struct list_head list; }; +#define for_each_sibling_event(sibling, event) \ + if ((event)->group_leader == (event)) \ + list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) + /** * struct perf_event - performance event kernel representation: */ -- cgit v1.2.3 From b3a5d111994450909158929560906f2c1c6c1d85 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Mar 2018 12:45:12 -0700 Subject: percpu_ref: Update doc to dissuade users from depending on internal RCU grace periods percpu_ref internally uses sched-RCU to implement the percpu -> atomic mode switching and the documentation suggested that this could be depended upon. This doesn't seem like a good idea. * percpu_ref uses sched-RCU which has different grace periods regular RCU. Users may combine percpu_ref with regular RCU usage and incorrectly believe that regular RCU grace periods are performed by percpu_ref. This can lead to, for example, use-after-free due to premature freeing. * percpu_ref has a grace period when switching from percpu to atomic mode. It doesn't have one between the last put and release. This distinction is subtle and can lead to surprising bugs. * percpu_ref allows starting in and switching to atomic mode manually for debugging and other purposes. This means that there may not be any grace periods from kill to release. This patch makes it clear that the grace periods are percpu_ref's internal implementation detail and can't be depended upon by the users. Signed-off-by: Tejun Heo Cc: Kent Overstreet Cc: Linus Torvalds Signed-off-by: Tejun Heo --- include/linux/percpu-refcount.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 864d167a1073..009cdf3d65b6 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -30,10 +30,14 @@ * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it - * calls percpu_ref_kill(), then hlist_del_rcu() and synchronize_rcu() to remove - * the kioctx from the proccess's list of kioctxs - after that, there can't be - * any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop - * the initial ref with percpu_ref_put(). + * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. + * After that, there can't be any new users of the kioctx (from lookup_ioctx()) + * and it's then safe to drop the initial ref with percpu_ref_put(). + * + * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() + * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't + * imply RCU grace periods of any kind and if a user wants to combine percpu_ref + * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped @@ -113,8 +117,10 @@ void percpu_ref_reinit(struct percpu_ref *ref); * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * - * Puts @ref in non percpu mode, then does a call_rcu() before gathering up the - * percpu counters and dropping the initial ref. + * Switches @ref into atomic mode before gathering up the percpu counters + * and dropping the initial ref. + * + * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { -- cgit v1.2.3 From 7f65ea42eb00bc902f1c37a71e984e4f4064cfa9 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 9 Mar 2018 09:52:42 +0000 Subject: sched/fair: Add util_est on top of PELT The util_avg signal computed by PELT is too variable for some use-cases. For example, a big task waking up after a long sleep period will have its utilization almost completely decayed. This introduces some latency before schedutil will be able to pick the best frequency to run a task. The same issue can affect task placement. Indeed, since the task utilization is already decayed at wakeup, when the task is enqueued in a CPU, this can result in a CPU running a big task as being temporarily represented as being almost empty. This leads to a race condition where other tasks can be potentially allocated on a CPU which just started to run a big task which slept for a relatively long period. Moreover, the PELT utilization of a task can be updated every [ms], thus making it a continuously changing value for certain longer running tasks. This means that the instantaneous PELT utilization of a RUNNING task is not really meaningful to properly support scheduler decisions. For all these reasons, a more stable signal can do a better job of representing the expected/estimated utilization of a task/cfs_rq. Such a signal can be easily created on top of PELT by still using it as an estimator which produces values to be aggregated on meaningful events. This patch adds a simple implementation of util_est, a new signal built on top of PELT's util_avg where: util_est(task) = max(task::util_avg, f(task::util_avg@dequeue)) This allows to remember how big a task has been reported by PELT in its previous activations via f(task::util_avg@dequeue), which is the new _task_util_est(struct task_struct*) function added by this patch. If a task should change its behavior and it runs longer in a new activation, after a certain time its util_est will just track the original PELT signal (i.e. task::util_avg). The estimated utilization of cfs_rq is defined only for root ones. That's because the only sensible consumer of this signal are the scheduler and schedutil when looking for the overall CPU utilization due to FAIR tasks. For this reason, the estimated utilization of a root cfs_rq is simply defined as: util_est(cfs_rq) = max(cfs_rq::util_avg, cfs_rq::util_est::enqueued) where: cfs_rq::util_est::enqueued = sum(_task_util_est(task)) for each RUNNABLE task on that root cfs_rq It's worth noting that the estimated utilization is tracked only for objects of interests, specifically: - Tasks: to better support tasks placement decisions - root cfs_rqs: to better support both tasks placement decisions as well as frequencies selection Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: http://lkml.kernel.org/r/20180309095245.11071-2-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 21b1168da951..f228c6033832 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -274,6 +274,34 @@ struct load_weight { u32 inv_weight; }; +/** + * struct util_est - Estimation utilization of FAIR tasks + * @enqueued: instantaneous estimated utilization of a task/cpu + * @ewma: the Exponential Weighted Moving Average (EWMA) + * utilization of a task + * + * Support data structure to track an Exponential Weighted Moving Average + * (EWMA) of a FAIR task's utilization. New samples are added to the moving + * average each time a task completes an activation. Sample's weight is chosen + * so that the EWMA will be relatively insensitive to transient changes to the + * task's workload. + * + * The enqueued attribute has a slightly different meaning for tasks and cpus: + * - task: the task's util_avg at last task dequeue time + * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU + * Thus, the util_est.enqueued of a task represents the contribution on the + * estimated utilization of the CPU where that task is currently enqueued. + * + * Only for tasks we track a moving average of the past instantaneous + * estimated utilization. This allows to absorb sporadic drops in utilization + * of an otherwise almost periodic task. + */ +struct util_est { + unsigned int enqueued; + unsigned int ewma; +#define UTIL_EST_WEIGHT_SHIFT 2 +}; + /* * The load_avg/util_avg accumulates an infinite geometric series * (see __update_load_avg() in kernel/sched/fair.c). @@ -335,6 +363,7 @@ struct sched_avg { unsigned long load_avg; unsigned long runnable_load_avg; unsigned long util_avg; + struct util_est util_est; }; struct sched_statistics { -- cgit v1.2.3 From 6b2bb7265f0b62605e8caee3613449ed0db270b9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 15 Mar 2018 11:40:33 +0100 Subject: sched/wait: Introduce wait_var_event() As a replacement for the wait_on_atomic_t() API provide the wait_var_event() API. The wait_var_event() API is based on the very same hashed-waitqueue idea, but doesn't care about the type (atomic_t) or the specific condition (atomic_read() == 0). IOW. it's much more widely applicable/flexible. It shares all the benefits/disadvantages of a hashed-waitqueue approach with the existing wait_on_atomic_t/wait_on_bit() APIs. The API is modeled after the existing wait_event() API, but instead of taking a wait_queue_head, it takes an address. This addresses is hashed to obtain a wait_queue_head from the bit_wait_table. Similar to the wait_event() API, it takes a condition expression as second argument and will wait until this expression becomes true. The following are (mostly) identical replacements: wait_on_atomic_t(&my_atomic, atomic_t_wait, TASK_UNINTERRUPTIBLE); wake_up_atomic_t(&my_atomic); wait_var_event(&my_atomic, !atomic_read(&my_atomic)); wake_up_var(&my_atomic); The only difference is that wake_up_var() is an unconditional wakeup and doesn't check the previously hard-coded (atomic_read() == 0) condition here. This is of little concequence, since most callers are already conditional on atomic_dec_and_test() and the ones that are not, are trivial to make so. Tested-by: Dan Williams Signed-off-by: Peter Zijlstra (Intel) Cc: David Howells Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/wait_bit.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h index 61b39eaf7cad..3fcdb75d69cf 100644 --- a/include/linux/wait_bit.h +++ b/include/linux/wait_bit.h @@ -262,4 +262,74 @@ int wait_on_atomic_t(atomic_t *val, wait_atomic_t_action_f action, unsigned mode return out_of_line_wait_on_atomic_t(val, action, mode); } +extern void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int flags); +extern void wake_up_var(void *var); +extern wait_queue_head_t *__var_waitqueue(void *p); + +#define ___wait_var_event(var, condition, state, exclusive, ret, cmd) \ +({ \ + __label__ __out; \ + struct wait_queue_head *__wq_head = __var_waitqueue(var); \ + struct wait_bit_queue_entry __wbq_entry; \ + long __ret = ret; /* explicit shadow */ \ + \ + init_wait_var_entry(&__wbq_entry, var, \ + exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ + for (;;) { \ + long __int = prepare_to_wait_event(__wq_head, \ + &__wbq_entry.wq_entry, \ + state); \ + if (condition) \ + break; \ + \ + if (___wait_is_interruptible(state) && __int) { \ + __ret = __int; \ + goto __out; \ + } \ + \ + cmd; \ + } \ + finish_wait(__wq_head, &__wbq_entry.wq_entry); \ +__out: __ret; \ +}) + +#define __wait_var_event(var, condition) \ + ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + schedule()) + +#define wait_var_event(var, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __wait_var_event(var, condition); \ +} while (0) + +#define __wait_var_event_killable(var, condition) \ + ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ + schedule()) + +#define wait_var_event_killable(var, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_var_event_killable(var, condition); \ + __ret; \ +}) + +#define __wait_var_event_timeout(var, condition, timeout) \ + ___wait_var_event(var, ___wait_cond_timeout(condition), \ + TASK_UNINTERRUPTIBLE, 0, timeout, \ + __ret = schedule_timeout(__ret)) + +#define wait_var_event_timeout(var, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_var_event_timeout(var, condition, timeout); \ + __ret; \ +}) + #endif /* _LINUX_WAIT_BIT_H */ -- cgit v1.2.3 From dc5d4afbb0bf7b7746ff5e56e1a5688ad7f29b32 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 15 Mar 2018 11:43:43 +0100 Subject: sched/wait, fs/fscache: Convert wait_on_atomic_t() usage to the new wait_var_event() API The old wait_on_atomic_t() is going to get removed, use the more flexible wait_var_event() API instead. No change in functionality. Signed-off-by: Peter Zijlstra (Intel) Cc: David Howells Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/fscache-cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 4c467ef50159..3b03e29e2f1a 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -496,7 +496,7 @@ static inline bool __fscache_unuse_cookie(struct fscache_cookie *cookie) static inline void __fscache_wake_unused_cookie(struct fscache_cookie *cookie) { - wake_up_atomic_t(&cookie->n_active); + wake_up_var(&cookie->n_active); } /** -- cgit v1.2.3 From 9b8cce52c4b5c08297900bfdcafc6b08d9bc4a27 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 15 Mar 2018 11:46:30 +0100 Subject: sched/wait: Remove the wait_on_atomic_t() API There are no users left (everyone got converted to wait_var_event()), remove it. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/wait_bit.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h index 3fcdb75d69cf..9318b2166439 100644 --- a/include/linux/wait_bit.h +++ b/include/linux/wait_bit.h @@ -10,7 +10,6 @@ struct wait_bit_key { void *flags; int bit_nr; -#define WAIT_ATOMIC_T_BIT_NR -1 unsigned long timeout; }; @@ -22,21 +21,15 @@ struct wait_bit_queue_entry { #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } -#define __WAIT_ATOMIC_T_KEY_INITIALIZER(p) \ - { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, } - typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); -typedef int wait_atomic_t_action_f(atomic_t *counter, unsigned int mode); void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); void wake_up_bit(void *word, int bit); -void wake_up_atomic_t(atomic_t *p); int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); -int out_of_line_wait_on_atomic_t(atomic_t *p, wait_atomic_t_action_f action, unsigned int mode); struct wait_queue_head *bit_waitqueue(void *word, int bit); extern void __init wait_bit_init(void); @@ -57,7 +50,6 @@ extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); -extern int atomic_t_wait(atomic_t *counter, unsigned int mode); /** * wait_on_bit - wait for a bit to be cleared @@ -243,25 +235,6 @@ wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, return out_of_line_wait_on_bit_lock(word, bit, action, mode); } -/** - * wait_on_atomic_t - Wait for an atomic_t to become 0 - * @val: The atomic value being waited on, a kernel virtual address - * @action: the function used to sleep, which may take special actions - * @mode: the task state to sleep in - * - * Wait for an atomic_t to become 0. We abuse the bit-wait waitqueue table for - * the purpose of getting a waitqueue, but we set the key to a bit number - * outside of the target 'word'. - */ -static inline -int wait_on_atomic_t(atomic_t *val, wait_atomic_t_action_f action, unsigned mode) -{ - might_sleep(); - if (atomic_read(val) == 0) - return 0; - return out_of_line_wait_on_atomic_t(val, action, mode); -} - extern void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int flags); extern void wake_up_var(void *var); extern wait_queue_head_t *__var_waitqueue(void *p); -- cgit v1.2.3 From 578ae447e7e5d78c90ac40a06406c1741f79ba96 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 19 Mar 2018 13:18:57 -0500 Subject: jump_label: Disable jump labels in __exit code With the following commit: 333522447063 ("jump_label: Explicitly disable jump labels in __init code") ... we explicitly disabled jump labels in __init code, so they could be detected and not warned about in the following commit: dc1dd184c2f0 ("jump_label: Warn on failed jump_label patching attempt") In-kernel __exit code has the same issue. It's never used, so it's freed along with the rest of initmem. But jump label entries in __exit code aren't explicitly disabled, so we get the following warning when enabling pr_debug() in __exit code: can't patch jump_label at dmi_sysfs_exit+0x0/0x2d WARNING: CPU: 0 PID: 22572 at kernel/jump_label.c:376 __jump_label_update+0x9d/0xb0 Fix the warning by disabling all jump labels in initmem (which includes both __init and __exit code). Reported-and-tested-by: Li Wang Signed-off-by: Josh Poimboeuf Cc: Borislav Petkov Cc: Jason Baron Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: dc1dd184c2f0 ("jump_label: Warn on failed jump_label patching attempt") Link: http://lkml.kernel.org/r/7121e6e595374f06616c505b6e690e275c0054d1.1521483452.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- include/linux/jump_label.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 2168cc6b8b30..b46b541c67c4 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -151,7 +151,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); -extern void jump_label_invalidate_init(void); +extern void jump_label_invalidate_initmem(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -199,7 +199,7 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } -static inline void jump_label_invalidate_init(void) {} +static inline void jump_label_invalidate_initmem(void) {} static __always_inline bool static_key_false(struct static_key *key) { -- cgit v1.2.3 From b7fa07460b0f0e9fbe6d9319a0864c145bd59bcb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 19 Mar 2018 11:38:22 +0100 Subject: set_memory.h: Provide set_memory_{en,de}crypted() stubs ... to make these APIs more universally available. Tested-by: Tom Lendacky Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Gleixner Reviewed-by: Konrad Rzeszutek Wilk Reviewed-by: Tom Lendacky Cc: David Woodhouse Cc: Joerg Roedel Cc: Jon Mason Cc: Linus Torvalds Cc: Muli Ben-Yehuda Cc: Peter Zijlstra Cc: iommu@lists.linux-foundation.org Link: http://lkml.kernel.org/r/20180319103826.12853-11-hch@lst.de Signed-off-by: Ingo Molnar --- include/linux/set_memory.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index e5140648f638..da5178216da5 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -17,4 +17,16 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif +#ifndef CONFIG_ARCH_HAS_MEM_ENCRYPT +static inline int set_memory_encrypted(unsigned long addr, int numpages) +{ + return 0; +} + +static inline int set_memory_decrypted(unsigned long addr, int numpages) +{ + return 0; +} +#endif /* CONFIG_ARCH_HAS_MEM_ENCRYPT */ + #endif /* _LINUX_SET_MEMORY_H_ */ -- cgit v1.2.3 From b6e05477c10c12e36141558fc14f04b00ea634d4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 19 Mar 2018 11:38:24 +0100 Subject: dma/direct: Handle the memory encryption bit in common code Give the basic phys_to_dma() and dma_to_phys() helpers a __-prefix and add the memory encryption mask to the non-prefixed versions. Use the __-prefixed versions directly instead of clearing the mask again in various places. Tested-by: Tom Lendacky Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Gleixner Cc: David Woodhouse Cc: Joerg Roedel Cc: Jon Mason Cc: Konrad Rzeszutek Wilk Cc: Linus Torvalds Cc: Muli Ben-Yehuda Cc: Peter Zijlstra Cc: iommu@lists.linux-foundation.org Link: http://lkml.kernel.org/r/20180319103826.12853-13-hch@lst.de Signed-off-by: Ingo Molnar --- include/linux/dma-direct.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index bcdb1a3e4b1f..53ad6a47f513 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -3,18 +3,19 @@ #define _LINUX_DMA_DIRECT_H 1 #include +#include #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) { dma_addr_t dev_addr = (dma_addr_t)paddr; return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); } -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) +static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr) { phys_addr_t paddr = (phys_addr_t)dev_addr; @@ -30,6 +31,22 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ +/* + * If memory encryption is supported, phys_to_dma will set the memory encryption + * bit in the DMA address, and dma_to_phys will clear it. The raw __phys_to_dma + * and __dma_to_phys versions should only be used on non-encrypted memory for + * special occasions like DMA coherent buffers. + */ +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + return __sme_set(__phys_to_dma(dev, paddr)); +} + +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) +{ + return __sme_clr(__dma_to_phys(dev, daddr)); +} + #ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN void dma_mark_clean(void *addr, size_t size); #else -- cgit v1.2.3 From 16e73adbca76fd18733278cb688b0ddb4cad162c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 19 Mar 2018 11:38:26 +0100 Subject: dma/swiotlb: Remove swiotlb_{alloc,free}_coherent() Unused now that everyone uses swiotlb_{alloc,free}(). Tested-by: Tom Lendacky Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Gleixner Cc: David Woodhouse Cc: Joerg Roedel Cc: Jon Mason Cc: Konrad Rzeszutek Wilk Cc: Linus Torvalds Cc: Muli Ben-Yehuda Cc: Peter Zijlstra Cc: iommu@lists.linux-foundation.org Link: http://lkml.kernel.org/r/20180319103826.12853-15-hch@lst.de Signed-off-by: Ingo Molnar --- include/linux/swiotlb.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 5b1f2a00491c..965be92c33b5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -72,14 +72,6 @@ void *swiotlb_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle, void swiotlb_free(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, unsigned long attrs); -extern void -*swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags); - -extern void -swiotlb_free_coherent(struct device *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle); - extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, -- cgit v1.2.3 From 6b00c35138b404be98b85f4a703be594cbed501c Mon Sep 17 00:00:00 2001 From: Jagdish Gediya Date: Thu, 22 Mar 2018 01:08:10 +0530 Subject: mtd: nand: fsl_ifc: Read ECCSTAT0 and ECCSTAT1 registers for IFC 2.0 Due to missing information in Hardware manual, current implementation doesn't read ECCSTAT0 and ECCSTAT1 registers for IFC 2.0. Add support to read ECCSTAT0 and ECCSTAT1 registers during ecccheck for IFC 2.0. Fixes: 656441478ed5 ("mtd: nand: ifc: Fix location of eccstat registers for IFC V1.0") Cc: stable@vger.kernel.org # v3.18+ Signed-off-by: Jagdish Gediya Reviewed-by: Prabhakar Kushwaha Signed-off-by: Boris Brezillon --- include/linux/fsl_ifc.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h index c332f0a45607..3fdfede2f0f3 100644 --- a/include/linux/fsl_ifc.h +++ b/include/linux/fsl_ifc.h @@ -734,11 +734,7 @@ struct fsl_ifc_nand { u32 res19[0x10]; __be32 nand_fsr; u32 res20; - /* The V1 nand_eccstat is actually 4 words that overlaps the - * V2 nand_eccstat. - */ - __be32 v1_nand_eccstat[2]; - __be32 v2_nand_eccstat[6]; + __be32 nand_eccstat[8]; u32 res21[0x1c]; __be32 nanndcr; u32 res22[0x2]; -- cgit v1.2.3 From 5df7af85ecd88e8b5f1f31d6456c3cf38a8bbdda Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 20 Mar 2018 09:44:52 +0800 Subject: net: phy: Add general dummy stubs for MMD register access For some phy devices, even though they don't support the MMD extended register access, it does have some side effect if we are trying to read/write the MMD registers via indirect method. So introduce general dummy stubs for MMD register access which these devices can use to avoid such side effect. Fixes: b6b5e8a69118 ("gianfar: Disable EEE autoneg by default") Signed-off-by: Kevin Hao 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 b260fb336b25..7c4c2379e010 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -984,6 +984,10 @@ static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; } +int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, + u16 regnum); +int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, + u16 regnum, u16 val); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From f59f1caf72ba00d519c793c3deb32cd3be32edc2 Mon Sep 17 00:00:00 2001 From: Daniel Vacek Date: Thu, 22 Mar 2018 16:17:38 -0700 Subject: Revert "mm: page_alloc: skip over regions of invalid pfns where possible" This reverts commit b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns where possible"). The commit is meant to be a boot init speed up skipping the loop in memmap_init_zone() for invalid pfns. But given some specific memory mapping on x86_64 (or more generally theoretically anywhere but on arm with CONFIG_HAVE_ARCH_PFN_VALID) the implementation also skips valid pfns which is plain wrong and causes 'kernel BUG at mm/page_alloc.c:1389!' crash> log | grep -e BUG -e RIP -e Call.Trace -e move_freepages_block -e rmqueue -e freelist -A1 kernel BUG at mm/page_alloc.c:1389! invalid opcode: 0000 [#1] SMP -- RIP: 0010: move_freepages+0x15e/0x160 -- Call Trace: move_freepages_block+0x73/0x80 __rmqueue+0x263/0x460 get_page_from_freelist+0x7e1/0x9e0 __alloc_pages_nodemask+0x176/0x420 -- crash> page_init_bug -v | grep RAM 1000 - 9bfff System RAM (620.00 KiB) 100000 - 430bffff System RAM ( 1.05 GiB = 1071.75 MiB = 1097472.00 KiB) 4b0c8000 - 4bf9cfff System RAM ( 14.83 MiB = 15188.00 KiB) 4bfac000 - 646b1fff System RAM (391.02 MiB = 400408.00 KiB) 7b788000 - 7b7fffff System RAM (480.00 KiB) 100000000 - 67fffffff System RAM ( 22.00 GiB) crash> page_init_bug | head -6 7b788000 - 7b7fffff System RAM (480.00 KiB) 1fffff00000000 0 1 DMA32 4096 1048575 505736 505344 505855 0 0 0 DMA 1 4095 1fffff00000400 0 1 DMA32 4096 1048575 BUG, zones differ! crash> kmem -p 77fff000 78000000 7b5ff000 7b600000 7b787000 7b788000 PAGE PHYSICAL MAPPING INDEX CNT FLAGS ffffea0001e00000 78000000 0 0 0 0 ffffea0001ed7fc0 7b5ff000 0 0 0 0 ffffea0001ed8000 7b600000 0 0 0 0 <<<< ffffea0001ede1c0 7b787000 0 0 0 0 ffffea0001ede200 7b788000 0 0 1 1fffff00000000 Link: http://lkml.kernel.org/r/20180316143855.29838-1-neelx@redhat.com Fixes: b92df1de5d28 ("mm: page_alloc: skip over regions of invalid pfns where possible") Signed-off-by: Daniel Vacek Acked-by: Ard Biesheuvel Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Vlastimil Babka Cc: Mel Gorman Cc: Pavel Tatashin Cc: Paul Burton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8be5077efb5f..f92ea7783652 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -187,7 +187,6 @@ int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); -unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn); /** * for_each_mem_pfn_range - early memory pfn range iterator -- cgit v1.2.3 From 819671ff849b07b9831b91de879ddc5da4b333d4 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:25 +0100 Subject: syscalls: define and explain goal to not call syscalls in the kernel The syscall entry points to the kernel defined by SYSCALL_DEFINEx() and COMPAT_SYSCALL_DEFINEx() should only be called from userspace through kernel entry points, but not from the kernel itself. This will allow cleanups and optimizations to the entry paths *and* to the parts of the kernel code which currently need to pretend to be userspace in order to make use of syscalls. Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a78186d826d7..0526286a0314 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -941,4 +941,11 @@ asmlinkage long sys_pkey_free(int pkey); asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); + +/* + * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. + * Instead, use one of the functions which work equivalently, such as + * the ksys_xyzyyz() functions prototyped below. + */ + #endif -- cgit v1.2.3 From a687a5337063af99ebd0eebaa6f4b4cf2e07c21b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 7 Mar 2018 23:30:54 +0100 Subject: treewide: simplify Kconfig dependencies for removed archs A lot of Kconfig symbols have architecture specific dependencies. In those cases that depend on architectures we have already removed, they can be omitted. Acked-by: Kalle Valo Acked-by: Alexandre Belloni Signed-off-by: Arnd Bergmann --- include/linux/ide.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 20d42c0d9fb6..1d6f16110eae 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -25,15 +25,10 @@ #include #include -#if defined(CONFIG_CRIS) || defined(CONFIG_FRV) -# define SUPPORT_VLB_SYNC 0 -#else -# define SUPPORT_VLB_SYNC 1 -#endif - /* * Probably not wise to fiddle with these */ +#define SUPPORT_VLB_SYNC 1 #define IDE_DEFAULT_MAX_FAILURES 1 #define ERROR_MAX 8 /* Max read/write errors per sector */ #define ERROR_RESET 3 /* Reset controller every 4th retry */ -- cgit v1.2.3 From 768a032d0e73f962ec13cd05b722d9744d2cf903 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 18:21:04 +0100 Subject: net: adi: remove blackfin ethernet drivers The blackfin architecture is getting removed, so the bfin_mac driver is now obsolete. Acked-by: Dominik Brodowski Acked-by: Aaron Wu Signed-off-by: Arnd Bergmann --- include/linux/bfin_mac.h | 30 ------------------------------ 1 file changed, 30 deletions(-) delete mode 100644 include/linux/bfin_mac.h (limited to 'include/linux') diff --git a/include/linux/bfin_mac.h b/include/linux/bfin_mac.h deleted file mode 100644 index a69554ef8476..000000000000 --- a/include/linux/bfin_mac.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Blackfin On-Chip MAC Driver - * - * Copyright 2004-2010 Analog Devices Inc. - * - * Enter bugs at http://blackfin.uclinux.org/ - * - * Licensed under the GPL-2 or later. - */ - -#ifndef _LINUX_BFIN_MAC_H_ -#define _LINUX_BFIN_MAC_H_ - -#include - -struct bfin_phydev_platform_data { - unsigned short addr; - int irq; -}; - -struct bfin_mii_bus_platform_data { - int phydev_number; - struct bfin_phydev_platform_data *phydev_data; - const unsigned short *mac_peripherals; - int phy_mode; - unsigned int phy_mask; - unsigned short vlan1_mask, vlan2_mask; -}; - -#endif -- cgit v1.2.3 From 889ce12b1650b3c388634451872638a08faf6d6b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 16:05:23 +0100 Subject: raid: remove tile specific raid6 implementation The Tile architecture is getting removed, so we no longer need this either. Acked-by: Ard Biesheuvel Signed-off-by: Arnd Bergmann --- include/linux/raid/pq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 583cdd3d49ca..a366cc314479 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -105,7 +105,6 @@ extern const struct raid6_calls raid6_avx2x4; extern const struct raid6_calls raid6_avx512x1; extern const struct raid6_calls raid6_avx512x2; extern const struct raid6_calls raid6_avx512x4; -extern const struct raid6_calls raid6_tilegx8; extern const struct raid6_calls raid6_s390vx8; struct raid6_recov_calls { -- cgit v1.2.3 From 8cbfbae85085bdd0bdafc085b1ed14abe0349573 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 16:32:20 +0100 Subject: video/logo: remove obsolete logo files The blackfin and m32r architectures are getting removed, so it's time to clean up the logos as well. Acked-by: Bartlomiej Zolnierkiewicz Signed-off-by: Arnd Bergmann --- include/linux/linux_logo.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h index 5e3581d76c7f..d4d5b93efe84 100644 --- a/include/linux/linux_logo.h +++ b/include/linux/linux_logo.h @@ -36,8 +36,6 @@ struct linux_logo { extern const struct linux_logo logo_linux_mono; extern const struct linux_logo logo_linux_vga16; extern const struct linux_logo logo_linux_clut224; -extern const struct linux_logo logo_blackfin_vga16; -extern const struct linux_logo logo_blackfin_clut224; extern const struct linux_logo logo_dec_clut224; extern const struct linux_logo logo_mac_clut224; extern const struct linux_logo logo_parisc_clut224; @@ -46,7 +44,6 @@ extern const struct linux_logo logo_sun_clut224; extern const struct linux_logo logo_superh_mono; extern const struct linux_logo logo_superh_vga16; extern const struct linux_logo logo_superh_clut224; -extern const struct linux_logo logo_m32r_clut224; extern const struct linux_logo logo_spe_clut224; extern const struct linux_logo *fb_find_logo(int depth); -- cgit v1.2.3 From e3ed8b436bc32102ac2995940bc3a63c09755b63 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 17:02:41 +0100 Subject: fbdev: remove blackfin drivers The blackfin architecture is getting removed, this removes the associated fbdev drivers as well. Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Aaron Wu Signed-off-by: Arnd Bergmann --- include/linux/fb.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index f577d3c89618..aa74a228bb92 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -571,8 +571,7 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { #elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || \ defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || \ - defined(__avr32__) || defined(__bfin__) || defined(__arm__) || \ - defined(__aarch64__) + defined(__arm__) || defined(__aarch64__) #define fb_readb __raw_readb #define fb_readw __raw_readw -- cgit v1.2.3 From f59b2dc2de63652cad750efc2ad1012eb1bb342f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 18:16:31 +0100 Subject: pinctrl: remove adi2/blackfin drivers The blackfin architecture is getting removed, so these are now obsolete. Acked-by: Aaron Wu Signed-off-by: Arnd Bergmann --- include/linux/platform_data/pinctrl-adi2.h | 40 ------------------------------ 1 file changed, 40 deletions(-) delete mode 100644 include/linux/platform_data/pinctrl-adi2.h (limited to 'include/linux') diff --git a/include/linux/platform_data/pinctrl-adi2.h b/include/linux/platform_data/pinctrl-adi2.h deleted file mode 100644 index 8f91300617ec..000000000000 --- a/include/linux/platform_data/pinctrl-adi2.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * Pinctrl Driver for ADI GPIO2 controller - * - * Copyright 2007-2013 Analog Devices Inc. - * - * Licensed under the GPLv2 or later - */ - - -#ifndef PINCTRL_ADI2_H -#define PINCTRL_ADI2_H - -#include -#include - -/** - * struct adi_pinctrl_gpio_platform_data - Pinctrl gpio platform data - * for ADI GPIO2 device. - * - * @port_gpio_base: Optional global GPIO index of the GPIO bank. - * 0 means driver decides. - * @port_pin_base: Pin index of the pin controller device. - * @port_width: PIN number of the GPIO bank device - * @pint_id: GPIO PINT device id that this GPIO bank should map to. - * @pint_assign: The 32-bit GPIO PINT registers can be divided into 2 parts. A - * GPIO bank can be mapped into either low 16 bits[0] or high 16 - * bits[1] of each PINT register. - * @pint_map: GIOP bank mapping code in PINT device - */ -struct adi_pinctrl_gpio_platform_data { - unsigned int port_gpio_base; - unsigned int port_pin_base; - unsigned int port_width; - u8 pinctrl_id; - u8 pint_id; - bool pint_assign; - u8 pint_map; -}; - -#endif -- cgit v1.2.3 From c957ea5c797cfccffeee92e0af8e0e99212dd755 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 17:24:55 +0100 Subject: input: misc: remove blackfin rotary driver The blackfin architecture is getting removed, so this one is obsolete as well. Acked-by: Dmitry Torokhov Acked-by: Aaron Wu Signed-off-by: Arnd Bergmann --- include/linux/platform_data/bfin_rotary.h | 117 ------------------------------ 1 file changed, 117 deletions(-) delete mode 100644 include/linux/platform_data/bfin_rotary.h (limited to 'include/linux') diff --git a/include/linux/platform_data/bfin_rotary.h b/include/linux/platform_data/bfin_rotary.h deleted file mode 100644 index 98829370fee2..000000000000 --- a/include/linux/platform_data/bfin_rotary.h +++ /dev/null @@ -1,117 +0,0 @@ -/* - * board initialization should put one of these structures into platform_data - * and place the bfin-rotary onto platform_bus named "bfin-rotary". - * - * Copyright 2008-2010 Analog Devices Inc. - * - * Licensed under the GPL-2 or later. - */ - -#ifndef _BFIN_ROTARY_H -#define _BFIN_ROTARY_H - -/* mode bitmasks */ -#define ROT_QUAD_ENC CNTMODE_QUADENC /* quadrature/grey code encoder mode */ -#define ROT_BIN_ENC CNTMODE_BINENC /* binary encoder mode */ -#define ROT_UD_CNT CNTMODE_UDCNT /* rotary counter mode */ -#define ROT_DIR_CNT CNTMODE_DIRCNT /* direction counter mode */ - -#define ROT_DEBE DEBE /* Debounce Enable */ - -#define ROT_CDGINV CDGINV /* CDG Pin Polarity Invert */ -#define ROT_CUDINV CUDINV /* CUD Pin Polarity Invert */ -#define ROT_CZMINV CZMINV /* CZM Pin Polarity Invert */ - -struct bfin_rotary_platform_data { - /* set rotary UP KEY_### or BTN_### in case you prefer - * bfin-rotary to send EV_KEY otherwise set 0 - */ - unsigned int rotary_up_key; - /* set rotary DOWN KEY_### or BTN_### in case you prefer - * bfin-rotary to send EV_KEY otherwise set 0 - */ - unsigned int rotary_down_key; - /* set rotary BUTTON KEY_### or BTN_### */ - unsigned int rotary_button_key; - /* set rotary Relative Axis REL_### in case you prefer - * bfin-rotary to send EV_REL otherwise set 0 - */ - unsigned int rotary_rel_code; - unsigned short debounce; /* 0..17 */ - unsigned short mode; - unsigned short pm_wakeup; - unsigned short *pin_list; -}; - -/* CNT_CONFIG bitmasks */ -#define CNTE (1 << 0) /* Counter Enable */ -#define DEBE (1 << 1) /* Debounce Enable */ -#define CDGINV (1 << 4) /* CDG Pin Polarity Invert */ -#define CUDINV (1 << 5) /* CUD Pin Polarity Invert */ -#define CZMINV (1 << 6) /* CZM Pin Polarity Invert */ -#define CNTMODE_SHIFT 8 -#define CNTMODE (0x7 << CNTMODE_SHIFT) /* Counter Operating Mode */ -#define ZMZC (1 << 1) /* CZM Zeroes Counter Enable */ -#define BNDMODE_SHIFT 12 -#define BNDMODE (0x3 << BNDMODE_SHIFT) /* Boundary register Mode */ -#define INPDIS (1 << 15) /* CUG and CDG Input Disable */ - -#define CNTMODE_QUADENC (0 << CNTMODE_SHIFT) /* quadrature encoder mode */ -#define CNTMODE_BINENC (1 << CNTMODE_SHIFT) /* binary encoder mode */ -#define CNTMODE_UDCNT (2 << CNTMODE_SHIFT) /* up/down counter mode */ -#define CNTMODE_DIRCNT (4 << CNTMODE_SHIFT) /* direction counter mode */ -#define CNTMODE_DIRTMR (5 << CNTMODE_SHIFT) /* direction timer mode */ - -#define BNDMODE_COMP (0 << BNDMODE_SHIFT) /* boundary compare mode */ -#define BNDMODE_ZERO (1 << BNDMODE_SHIFT) /* boundary compare and zero mode */ -#define BNDMODE_CAPT (2 << BNDMODE_SHIFT) /* boundary capture mode */ -#define BNDMODE_AEXT (3 << BNDMODE_SHIFT) /* boundary auto-extend mode */ - -/* CNT_IMASK bitmasks */ -#define ICIE (1 << 0) /* Illegal Gray/Binary Code Interrupt Enable */ -#define UCIE (1 << 1) /* Up count Interrupt Enable */ -#define DCIE (1 << 2) /* Down count Interrupt Enable */ -#define MINCIE (1 << 3) /* Min Count Interrupt Enable */ -#define MAXCIE (1 << 4) /* Max Count Interrupt Enable */ -#define COV31IE (1 << 5) /* Bit 31 Overflow Interrupt Enable */ -#define COV15IE (1 << 6) /* Bit 15 Overflow Interrupt Enable */ -#define CZEROIE (1 << 7) /* Count to Zero Interrupt Enable */ -#define CZMIE (1 << 8) /* CZM Pin Interrupt Enable */ -#define CZMEIE (1 << 9) /* CZM Error Interrupt Enable */ -#define CZMZIE (1 << 10) /* CZM Zeroes Counter Interrupt Enable */ - -/* CNT_STATUS bitmasks */ -#define ICII (1 << 0) /* Illegal Gray/Binary Code Interrupt Identifier */ -#define UCII (1 << 1) /* Up count Interrupt Identifier */ -#define DCII (1 << 2) /* Down count Interrupt Identifier */ -#define MINCII (1 << 3) /* Min Count Interrupt Identifier */ -#define MAXCII (1 << 4) /* Max Count Interrupt Identifier */ -#define COV31II (1 << 5) /* Bit 31 Overflow Interrupt Identifier */ -#define COV15II (1 << 6) /* Bit 15 Overflow Interrupt Identifier */ -#define CZEROII (1 << 7) /* Count to Zero Interrupt Identifier */ -#define CZMII (1 << 8) /* CZM Pin Interrupt Identifier */ -#define CZMEII (1 << 9) /* CZM Error Interrupt Identifier */ -#define CZMZII (1 << 10) /* CZM Zeroes Counter Interrupt Identifier */ - -/* CNT_COMMAND bitmasks */ -#define W1LCNT 0xf /* Load Counter Register */ -#define W1LMIN 0xf0 /* Load Min Register */ -#define W1LMAX 0xf00 /* Load Max Register */ -#define W1ZMONCE (1 << 12) /* Enable CZM Clear Counter Once */ - -#define W1LCNT_ZERO (1 << 0) /* write 1 to load CNT_COUNTER with zero */ -#define W1LCNT_MIN (1 << 2) /* write 1 to load CNT_COUNTER from CNT_MIN */ -#define W1LCNT_MAX (1 << 3) /* write 1 to load CNT_COUNTER from CNT_MAX */ - -#define W1LMIN_ZERO (1 << 4) /* write 1 to load CNT_MIN with zero */ -#define W1LMIN_CNT (1 << 5) /* write 1 to load CNT_MIN from CNT_COUNTER */ -#define W1LMIN_MAX (1 << 7) /* write 1 to load CNT_MIN from CNT_MAX */ - -#define W1LMAX_ZERO (1 << 8) /* write 1 to load CNT_MAX with zero */ -#define W1LMAX_CNT (1 << 9) /* write 1 to load CNT_MAX from CNT_COUNTER */ -#define W1LMAX_MIN (1 << 10) /* write 1 to load CNT_MAX from CNT_MIN */ - -/* CNT_DEBOUNCE bitmasks */ -#define DPRESCALE 0xf /* Load Counter Register */ - -#endif -- cgit v1.2.3 From 03f4c9abd73284193f70e64da1a266d393650530 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 16:10:20 +0100 Subject: usb: host: remove tilegx platform glue The tile architecture is getting removed, so the ehci and ohci platform glue drivers are no longer needed. In case of ohci, this is the last one to define a PLATFORM_DRIVER macro, so we can remove even more. Acked-by: Greg Kroah-Hartman Acked-by: Alan Stern Signed-off-by: Arnd Bergmann --- include/linux/usb/tilegx.h | 35 ----------------------------------- 1 file changed, 35 deletions(-) delete mode 100644 include/linux/usb/tilegx.h (limited to 'include/linux') diff --git a/include/linux/usb/tilegx.h b/include/linux/usb/tilegx.h deleted file mode 100644 index 817908573fe8..000000000000 --- a/include/linux/usb/tilegx.h +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright 2012 Tilera Corporation. All Rights Reserved. - * - * 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. - * - * 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, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for - * more details. - * - * Structure to contain platform-specific data related to Tile-Gx USB - * controllers. - */ - -#ifndef _LINUX_USB_TILEGX_H -#define _LINUX_USB_TILEGX_H - -#include - -struct tilegx_usb_platform_data { - /* GXIO device index. */ - int dev_index; - - /* GXIO device context. */ - gxio_usb_host_context_t usb_ctx; - - /* Device IRQ. */ - unsigned int irq; -}; - -#endif /* _LINUX_USB_TILEGX_H */ -- cgit v1.2.3 From a9762b704f5d5e167bbc261573621782b90efbc4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Mar 2018 17:37:54 +0100 Subject: usb: musb: remove blackfin port The blackfin architecture is getting removed, so we can clean up all the special cases in the musb driver. Acked-by: Greg Kroah-Hartman Acked-by: Aaron Wu Acked-by: Bin Liu Cc: Stephen Rothwell [arnd: adding in fixups from Aaron and Stephen] Signed-off-by: Arnd Bergmann --- include/linux/usb/musb.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index 5d19e6730475..9eb908a98033 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -89,13 +89,6 @@ struct musb_hdrc_config { u8 ram_bits; /* ram address size */ struct musb_hdrc_eps_bits *eps_bits __deprecated; -#ifdef CONFIG_BLACKFIN - /* A GPIO controlling VRSEL in Blackfin */ - unsigned int gpio_vrsel; - unsigned int gpio_vrsel_active; - /* musb CLKIN in Blackfin in MHZ */ - unsigned char clkin; -#endif u32 maximum_speed; }; -- cgit v1.2.3 From fc5d1073cae299de4517755a910df4f12a6a438f Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 26 Mar 2018 23:27:21 -0700 Subject: x86/mm/32: Remove unused node_memmap_size_bytes() & CONFIG_NEED_NODE_MEMMAP_SIZE logic node_memmap_size_bytes() has been unused since the v3.9 kernel, so remove it. Signed-off-by: David Rientjes Cc: Dave Hansen Cc: Laura Abbott Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-mm@kvack.org Fixes: f03574f2d5b2 ("x86-32, mm: Rip out x86_32 NUMA remapping code") Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1803262325540.256524@chino.kir.corp.google.com Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7522a6987595..a2db4576e499 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -816,10 +816,6 @@ int local_memory_node(int node_id); static inline int local_memory_node(int node_id) { return node_id; }; #endif -#ifdef CONFIG_NEED_NODE_MEMMAP_SIZE -unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); -#endif - /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ @@ -1289,7 +1285,6 @@ struct mminit_pfnnid_cache { #endif void memory_present(int nid, unsigned long start, unsigned long end); -unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); /* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we -- cgit v1.2.3 From 3af345258617e0412059c1ab6462495947f73e89 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 20 Mar 2018 20:07:59 +0200 Subject: firmware/dmi_scan: Uninline dmi_get_bios_year() helper Uninline dmi_get_bios_year() which, in particular, allows us to optimize it in the future. While doing this, convert the function to return an error code when BIOS date is not present or not parsable, or CONFIG_DMI=n. Additionally, during the move, add a bit of documentation. Suggested-by: Bjorn Helgaas Suggested-by: Rafael J. Wysocki Signed-off-by: Andy Shevchenko Reviewed-by: Jean Delvare Reviewed-by: Rafael J. Wysocki Acked-by: Thomas Gleixner Cc: Bjorn Helgaas Cc: Linus Torvalds Cc: Lukas Wunner Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: linux-acpi@vger.kernel.org Cc: linux-pci@vger.kernel.org Fixes: 492a1abd61e4 ("dmi: Introduce the dmi_get_bios_year() helper function") Signed-off-by: Ingo Molnar --- include/linux/dmi.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 0bade156e908..6a86d8db16d9 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -106,6 +106,7 @@ extern void dmi_scan_machine(void); extern void dmi_memdev_walk(void); extern void dmi_set_dump_stack_arch_desc(void); extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp); +extern int dmi_get_bios_year(void); extern int dmi_name_in_vendors(const char *str); extern int dmi_name_in_serial(const char *str); extern int dmi_available; @@ -133,6 +134,7 @@ static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp) *dayp = 0; return false; } +static inline int dmi_get_bios_year(void) { return -ENXIO; } static inline int dmi_name_in_vendors(const char *s) { return 0; } static inline int dmi_name_in_serial(const char *s) { return 0; } #define dmi_available 0 @@ -147,13 +149,4 @@ static inline const struct dmi_system_id * #endif -static inline int dmi_get_bios_year(void) -{ - int year; - - dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL); - - return year; -} - #endif /* __DMI_H__ */ -- cgit v1.2.3 From e89f5b37015309a8bdf0b21d08007580b92f92a4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 28 Mar 2018 15:35:35 +0200 Subject: dma-mapping: Don't clear GFP_ZERO in dma_alloc_attrs Revert the clearing of __GFP_ZERO in dma_alloc_attrs and move it to dma_direct_alloc for now. While most common architectures always zero dma cohereny allocations (and x86 did so since day one) this is not documented and at least arc and s390 do not zero without the explicit __GFP_ZERO argument. Fixes: 57bf5a8963f8 ("dma-mapping: clear harmful GFP_* flags in common code") Reported-by: Evgeniy Didin Reported-by: Sebastian Ott Signed-off-by: Christoph Hellwig Signed-off-by: Thomas Gleixner Tested-by: Evgeniy Didin Cc: iommu@lists.linux-foundation.org Link: https://lkml.kernel.org/r/20180328133535.17302-2-hch@lst.de --- include/linux/dma-mapping.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index eb9eab4ecd6d..12fedcba9a9a 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -518,12 +518,8 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr)) return cpu_addr; - /* - * Let the implementation decide on the zone to allocate from, and - * decide on the way of zeroing the memory given that the memory - * returned should always be zeroed. - */ - flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM | __GFP_ZERO); + /* let the implementation decide on the zone to allocate from: */ + flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM); if (!arch_dma_alloc_attrs(&dev, &flag)) return NULL; -- cgit v1.2.3 From 6ed70cf342de03c7b11cd4eb032705faeb29d284 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Thu, 29 Mar 2018 15:06:48 +0300 Subject: perf/x86/pt, coresight: Clean up address filter structure This is a cosmetic patch that deals with the address filter structure's ambiguous fields 'filter' and 'range'. The former stands to mean that the filter's *action* should be to filter the traces to its address range if it's set or stop tracing if it's unset. This is confusing and hard on the eyes, so this patch replaces it with 'action' enum. The 'range' field is completely redundant (meaning that the filter is an address range as opposed to a single address trigger), as we can use zero size to mean the same thing. Signed-off-by: Alexander Shishkin Acked-by: Mathieu Poirier Acked-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: Will Deacon Link: http://lkml.kernel.org/r/20180329120648.11902-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ff39ab011376..e71e99eb9a4e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -449,14 +449,19 @@ struct pmu { int (*filter_match) (struct perf_event *event); /* optional */ }; +enum perf_addr_filter_action_t { + PERF_ADDR_FILTER_ACTION_STOP = 0, + PERF_ADDR_FILTER_ACTION_START, + PERF_ADDR_FILTER_ACTION_FILTER, +}; + /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @inode: object file's inode for file-based filters * @offset: filter range offset - * @size: filter range size - * @range: 1: range, 0: address - * @filter: 1: filter/start, 0: stop + * @size: filter range size (size==0 means single address trigger) + * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ @@ -465,8 +470,7 @@ struct perf_addr_filter { struct inode *inode; unsigned long offset; unsigned long size; - unsigned int range : 1, - filter : 1; + enum perf_addr_filter_action_t action; }; /** -- cgit v1.2.3 From c769accdf3d8a103940bea2979b65556718567e9 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Thu, 29 Mar 2018 19:05:30 +0900 Subject: vlan: Fix vlan insertion for packets without ethernet header In some situation vlan packets do not have ethernet headers. One example is packets from tun devices. Users can specify vlan protocol in tun_pi field instead of IP protocol. When we have a vlan device with reorder_hdr disabled on top of the tun device, such packets from tun devices are untagged in skb_vlan_untag() and vlan headers will be inserted back in vlan_insert_inner_tag(). vlan_insert_inner_tag() however did not expect packets without ethernet headers, so in such a case size argument for memmove() underflowed. We don't need to copy headers for packets which do not have preceding headers of vlan headers, so skip memmove() in that case. Also don't write vlan protocol in skb->data when it does not have enough room for it. Fixes: cbe7128c4b92 ("vlan: Fix out of order vlan headers with reorder header off") Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c4a1cff9c768..7d30892da064 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -323,13 +323,24 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, skb_push(skb, VLAN_HLEN); /* Move the mac header sans proto to the beginning of the new header. */ - memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); + if (likely(mac_len > ETH_TLEN)) + memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); /* first, the ethernet type */ - veth->h_vlan_proto = vlan_proto; + if (likely(mac_len >= ETH_TLEN)) { + /* h_vlan_encapsulated_proto should already be populated, and + * skb->data has space for h_vlan_proto + */ + veth->h_vlan_proto = vlan_proto; + } else { + /* h_vlan_encapsulated_proto should not be populated, and + * skb->data has no space for h_vlan_proto + */ + veth->h_vlan_encapsulated_proto = skb->protocol; + } /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); -- cgit v1.2.3 From f97c3dc3c0e8d23a5c4357d182afeef4c67f5c33 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Thu, 29 Mar 2018 13:53:52 +0300 Subject: net/dim: Fix int overflow When calculating difference between samples, the values are multiplied by 100. Large values may cause int overflow when multiplied (usually on first iteration). Fixed by forcing 100 to be of type unsigned long. Fixes: 4c4dbb4a7363 ("net/mlx5e: Move dynamic interrupt coalescing code to include/linux") Signed-off-by: Tal Gilboa Reviewed-by: Andy Gospodarek Signed-off-by: David S. Miller --- include/linux/net_dim.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index bebeaad897cc..29ed8fd6379a 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -231,7 +231,7 @@ static inline void net_dim_exit_parking(struct net_dim *dim) } #define IS_SIGNIFICANT_DIFF(val, ref) \ - (((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */ + (((100UL * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */ static inline int net_dim_stats_compare(struct net_dim_stats *curr, struct net_dim_stats *prev) -- cgit v1.2.3 From d53238cd51a80f6f2e5b9d64830c62e2086787bd Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:37 +0100 Subject: kernel: open-code sys_rt_sigpending() in sys_sigpending() A similar but not fully equivalent code path is already open-coded three times (in sys_rt_sigpending and in the two compat stubs), so do it a fourth time here. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- 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 0526286a0314..a63e21e7a3af 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -288,7 +288,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data); asmlinkage long sys_personality(unsigned int personality); -asmlinkage long sys_sigpending(old_sigset_t __user *set); +asmlinkage long sys_sigpending(old_sigset_t __user *uset); asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset); asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, -- cgit v1.2.3 From 2de0db992de189fccc83fed57c30875144821491 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:26 +0100 Subject: mm: use do_futex() instead of sys_futex() in mm_release() sys_futex() is a wrapper to do_futex() which does not modify any values here: - uaddr, val and val3 are kept the same - op is masked with FUTEX_CMD_MASK, but is always set to FUTEX_WAKE. Therefore, val2 is always 0. - as utime is set to NULL, *timeout is NULL This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Darren Hart Cc: Andrew Morton Reviewed-by: Thomas Gleixner Signed-off-by: Dominik Brodowski --- include/linux/futex.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index c0fb9a24bbd2..821ae502d3d8 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -9,9 +9,6 @@ struct inode; struct mm_struct; struct task_struct; -long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, - u32 __user *uaddr2, u32 val2, u32 val3); - extern int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi); @@ -55,6 +52,9 @@ union futex_key { #ifdef CONFIG_FUTEX 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 @@ -64,6 +64,13 @@ extern int futex_cmpxchg_enabled; static inline void exit_robust_list(struct task_struct *curr) { } + +static inline long do_futex(u32 __user *uaddr, int op, u32 val, + ktime_t *timeout, u32 __user *uaddr2, + u32 val2, u32 val3) +{ + return -EINVAL; +} #endif #ifdef CONFIG_FUTEX_PI -- cgit v1.2.3 From 7a09e1eb9c1e5179797e0f3341ba7315c7626a0c Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:10:06 +0100 Subject: net: socket: add __sys_recvfrom() helper; remove in-kernel call to syscall Using the net-internal helper __sys_recvfrom() allows us to avoid the internal calls to the sys_recvfrom() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 9286a5a8c60c..40cc93b91628 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -353,4 +353,10 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen unsigned int flags, struct timespec *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags); + +/* helpers which do the actual work for syscalls */ +extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, + unsigned int flags, struct sockaddr __user *addr, + int __user *addr_len); + #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 211b634b7f1ebc3436d5e8a34810a8eaa1f269d9 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:18:52 +0100 Subject: net: socket: add __sys_sendto() helper; remove in-kernel call to syscall Using the net-internal helper __sys_sendto() allows us to avoid the internal calls to the sys_sendto() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 40cc93b91628..54b85abc7265 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -358,5 +358,8 @@ extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, struct sockaddr __user *addr, int __user *addr_len); +extern int __sys_sendto(int fd, void __user *buff, size_t len, + unsigned int flags, struct sockaddr __user *addr, + int addr_len); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 4541e80560ca56d63348f40f2e34b044a5eb3dd7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:24:23 +0100 Subject: net: socket: add __sys_accept4() helper; remove in-kernel call to syscall Using the net-internal helper __sys_accept4() allows us to avoid the internal calls to the sys_accept4() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 54b85abc7265..6a9840271676 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -361,5 +361,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); +extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 9d6a15c3f23bcf0b0e6c6efd7d19f52d960a8697 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:29:43 +0100 Subject: net: socket: add __sys_socket() helper; remove in-kernel call to syscall Using the net-internal helper __sys_socket() allows us to avoid the internal calls to the sys_socket() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6a9840271676..f8d040434a13 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -363,5 +363,6 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len, int addr_len); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); +extern int __sys_socket(int family, int type, int protocol); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From a87d35d87a3e4f2a0b0968d1f06703c909138b62 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:33:09 +0100 Subject: net: socket: add __sys_bind() helper; remove in-kernel call to syscall Using the net-internal helper __sys_bind() allows us to avoid the internal calls to the sys_bind() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index f8d040434a13..e9cee272da13 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -364,5 +364,6 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 1387c2c2f988f8180c6189d5083eaeeb8f120d44 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:35:09 +0100 Subject: net: socket: add __sys_connect() helper; remove in-kernel call to syscall Using the net-internal helper __sys_connect() allows us to avoid the internal calls to the sys_connect() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index e9cee272da13..7daa344d7320 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -365,5 +365,7 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); +extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, + int addrlen); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 25e290eed9c653cc90ac675d64b30b66cffce82f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:36:54 +0100 Subject: net: socket: add __sys_listen() helper; remove in-kernel call to syscall Using the net-internal helper __sys_listen() allows us to avoid the internal calls to the sys_listen() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7daa344d7320..7e37af25509d 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -367,5 +367,6 @@ extern int __sys_socket(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); +extern int __sys_listen(int fd, int backlog); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 8882a107b3062c6222cdbeadb284ea054ae50a3f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:43:14 +0100 Subject: net: socket: add __sys_getsockname() helper; remove in-kernel call to syscall Using the net-internal helper __sys_getsockname() allows us to avoid the internal calls to the sys_getsockname() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7e37af25509d..ef0226a61b03 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -368,5 +368,7 @@ extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); +extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, + int __user *usockaddr_len); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From b21c8f838a0e5b84c0d78fd9ed6b9f2cf97afbe9 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:47:00 +0100 Subject: net: socket: add __sys_getpeername() helper; remove in-kernel call to syscall Using the net-internal helper __sys_getpeername() allows us to avoid the internal calls to the sys_getpeername() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index ef0226a61b03..9ba003e92fea 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -370,5 +370,7 @@ extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, extern int __sys_listen(int fd, int backlog); extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); +extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, + int __user *usockaddr_len); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 6debc8d834ebc73566e5255c565c8fb307be22c5 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 19:49:23 +0100 Subject: net: socket: add __sys_socketpair() helper; remove in-kernel call to syscall Using the net-internal helper __sys_socketpair() allows us to avoid the internal calls to the sys_socketpair() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 9ba003e92fea..dbdddf0d079e 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -372,5 +372,7 @@ extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); +extern int __sys_socketpair(int family, int type, int protocol, + int __user *usockvec); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From 005a1aeac46666e2805f316596893ebd2a3c12e7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 20:07:05 +0100 Subject: net: socket: add __sys_shutdown() helper; remove in-kernel call to syscall Using the net-internal helper __sys_shutdown() allows us to avoid the internal calls to the sys_shutdown() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index dbdddf0d079e..b205138b69f1 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -374,5 +374,6 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); +extern int __sys_shutdown(int fd, int how); #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From cc36dca0dffad991135d0e28938ba2b4c0b786f7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 20:10:59 +0100 Subject: net: socket: add __sys_setsockopt() helper; remove in-kernel call to syscall Using the net-internal helper __sys_setsockopt() allows us to avoid the internal calls to the sys_setsockopt() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index b205138b69f1..cad120e4ed4b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -376,4 +376,5 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown(int fd, int how); + #endif /* _LINUX_SOCKET_H */ -- cgit v1.2.3 From e1834a329d6bb5659c14e9e537bd1f750fe3b85e Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 20:35:57 +0100 Subject: net: socket: move check for forbid_cmsg_compat to __sys_...msg() The non-compat codepaths for sys_...msg() verify that MSG_CMSG_COMPAT is not set. By moving this check to the __sys_...msg() functions (and making it dependent on a static flag passed to this function), we can call the __sys...msg() functions instead of the syscall functions in all cases. __sys_recvmmsg() does not need this trickery, as the check is handled within the do_sys_recvmmsg() function internal to net/socket.c. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: David S. Miller Cc: netdev@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/socket.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index cad120e4ed4b..e2b6bd4fe977 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -346,13 +346,18 @@ extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); struct timespec; -/* The __sys_...msg variants allow MSG_CMSG_COMPAT */ -extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags); -extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags); +/* The __sys_...msg variants allow MSG_CMSG_COMPAT iff + * forbid_cmsg_compat==false + */ +extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, + unsigned int flags, bool forbid_cmsg_compat); +extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, + unsigned int flags, bool forbid_cmsg_compat); extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, - unsigned int vlen, unsigned int flags); + unsigned int vlen, unsigned int flags, + bool forbid_cmsg_compat); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, -- cgit v1.2.3 From cb0b476ab12ca3bd9dd9122047660f3a73e8d647 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sat, 17 Mar 2018 16:26:56 +0100 Subject: fs/quota: add kernel_quotactl() helper; remove in-kernel call to syscall Using the fs-internal kernel_quotactl() helper allows us to get rid of the fs-internal call to the sys_quotactl() syscall. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Acked-by: Jan Kara Signed-off-by: Dominik Brodowski --- include/linux/quotaops.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 2fb6fb11132e..dc905a4ff8d7 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -27,6 +27,9 @@ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) (ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid)); } +int kernel_quotactl(unsigned int cmd, const char __user *special, + qid_t id, void __user *addr); + #if defined(CONFIG_QUOTA) #define quota_error(sb, fmt, args...) \ -- cgit v1.2.3 From ab0d1e85bfd0c25260f02cd3708d5abdfb5b5a9c Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 4 Mar 2018 21:54:05 +0100 Subject: fs/quota: use COMPAT_SYSCALL_DEFINE for sys32_quotactl() While sys32_quotactl() is only needed on x86, it can use the recommended COMPAT_SYSCALL_DEFINEx() machinery for its setup. Acked-by: Jan Kara Cc: Christoph Hellwig Signed-off-by: Dominik Brodowski --- include/linux/compat.h | 3 +++ include/linux/syscalls.h | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 16c3027074a2..f1649a5e6716 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -461,6 +461,9 @@ asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); +asmlinkage long compat_sys_quotactl32(unsigned int cmd, + const char __user *special, qid_t id, void __user *addr); + #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, const struct compat_iovec __user *vec, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a63e21e7a3af..6ab7ed71a8b6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -241,8 +241,6 @@ static inline void addr_limit_user_check(void) #endif } -asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, - qid_t id, void __user *addr); asmlinkage long sys_time(time_t __user *tloc); asmlinkage long sys_stime(time_t __user *tptr); asmlinkage long sys_gettimeofday(struct timeval __user *tv, -- cgit v1.2.3 From 312db1aa1dc7bff133d95c92efcc5e42b57cefa6 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:39 +0100 Subject: fs: add ksys_mount() helper; remove in-kernel calls to sys_mount() Using this helper allows us to avoid the in-kernel calls to the sys_mount() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mount(). In the near future, all callers of ksys_mount() should be converted to call do_mount() directly. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 6ab7ed71a8b6..3a9f9c534624 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -946,4 +946,7 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, * the ksys_xyzyyz() functions prototyped below. */ +int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, + unsigned long flags, void __user *data); + #endif -- cgit v1.2.3 From 3a18ef5c1b3935cb05888fc37964321f7bd6231d Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:40 +0100 Subject: fs: add ksys_umount() helper; remove in-kernel call to sys_umount() Using this helper allows us to avoid the in-kernel call to the sys_umount() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as ksys_umount(). In the near future, the only fs-external caller of ksys_umount() should be converted to call do_umount() directly. Then, ksys_umount() can be moved within sys_umount() again. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3a9f9c534624..48964c408c7b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -948,5 +948,6 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, unsigned long flags, void __user *data); +int ksys_umount(char __user *name, int flags); #endif -- cgit v1.2.3 From c7248321a3d42ffba78db0dde88d1c49ca1c045f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:40 +0100 Subject: fs: add ksys_dup{,3}() helper; remove in-kernel calls to sys_dup{,3}() Using ksys_dup() and ksys_dup3() as helper functions allows us to avoid the in-kernel calls to the sys_dup() and sys_dup3() syscalls. The ksys_ prefix denotes that these functions are meant as a drop-in replacement for the syscalls. In particular, they use the same calling convention as sys_dup{,3}(). In the near future, the fs-external callers of ksys_dup{,3}() should be converted to call do_dup2() directly. Then, ksys_dup{,3}() can be moved within sys_dup{,3}() again. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 48964c408c7b..50876ae1d17b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -949,5 +949,6 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, unsigned long flags, void __user *data); int ksys_umount(char __user *name, int flags); +int ksys_dup(unsigned int fildes); #endif -- cgit v1.2.3 From a16fe33ab5572e52ef4cb9719d6eb49623b2528a Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:41 +0100 Subject: fs: add ksys_chroot() helper; remove-in kernel calls to sys_chroot() Using this helper allows us to avoid the in-kernel calls to the sys_chroot() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_chroot(). In the near future, the fs-external callers of ksys_chroot() should be converted to use kern_path()/set_fs_root() directly. Then ksys_chroot() can be moved within sys_chroot() again. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 50876ae1d17b..920a0db1871d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -950,5 +950,6 @@ int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, unsigned long flags, void __user *data); int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); +int ksys_chroot(const char __user *filename); #endif -- cgit v1.2.3 From e7a3e8b2edf544ec28f689385c3adc2903f46ec0 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:41 +0100 Subject: fs: add ksys_write() helper; remove in-kernel calls to sys_write() Using this helper allows us to avoid the in-kernel calls to the sys_write() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_write(). In the near future, the do_mounts / initramfs callers of ksys_write() should be converted to use filp_open() and vfs_write() instead. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Cc: linux-s390@vger.kernel.org Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 920a0db1871d..80524faa9664 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -951,5 +951,6 @@ int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); +ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); #endif -- cgit v1.2.3 From 447016e9681965fda8dcd9e4fd3c55308a6fd166 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:46 +0100 Subject: fs: add ksys_chdir() helper; remove in-kernel calls to sys_chdir() Using this helper allows us to avoid the in-kernel calls to the sys_chdir() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_chdir(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 80524faa9664..090645b48447 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -952,5 +952,6 @@ int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); +int ksys_chdir(const char __user *filename); #endif -- cgit v1.2.3 From 0f32ab8cfac478be053cb526ced8918ef6f4df47 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:47 +0100 Subject: fs: add ksys_unlink() wrapper; remove in-kernel calls to sys_unlink() Using this wrapper allows us to avoid the in-kernel calls to the sys_unlink() syscall. The ksys_ prefix denotes that this function is meant s a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_unlink(). In the near future, all callers of ksys_unlink() should be converted to call do_unlinkat() directly or, at least, to operate on regular kernel pointers. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 090645b48447..7cbfb41e666b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -954,4 +954,15 @@ int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); +/* + * The following kernel syscall equivalents are just wrappers to fs-internal + * functions. Therefore, provide stubs to be inlined at the callsites. + */ +extern long do_unlinkat(int dfd, struct filename *name); + +static inline long ksys_unlink(const char __user *pathname) +{ + return do_unlinkat(AT_FDCWD, getname(pathname)); +} + #endif -- cgit v1.2.3 From f459dffae1c6026928bbe8e972daecb635b7b5e9 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:48 +0100 Subject: fs: add ksys_rmdir() wrapper; remove in-kernel calls to sys_rmdir() Using this wrapper allows us to avoid the in-kernel calls to the sys_rmdir() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_rmdir(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7cbfb41e666b..746043a05884 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -965,4 +965,11 @@ static inline long ksys_unlink(const char __user *pathname) return do_unlinkat(AT_FDCWD, getname(pathname)); } +extern long do_rmdir(int dfd, const char __user *pathname); + +static inline long ksys_rmdir(const char __user *pathname) +{ + return do_rmdir(AT_FDCWD, pathname); +} + #endif -- cgit v1.2.3 From 0101db7a301981a008296d522d8c1f456b0fe837 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:49 +0100 Subject: fs: add do_mkdirat() helper and ksys_mkdir() wrapper; remove in-kernel calls to syscall Using the fs-internal do_mkdirat() helper allows us to get rid of fs-internal calls to the sys_mkdirat() syscall. Introducing the ksys_mkdir() wrapper allows us to avoid the in-kernel calls to the sys_mkdir() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mkdir(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 746043a05884..c982cb5f4e50 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -972,4 +972,11 @@ static inline long ksys_rmdir(const char __user *pathname) return do_rmdir(AT_FDCWD, pathname); } +extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); + +static inline long ksys_mkdir(const char __user *pathname, umode_t mode) +{ + return do_mkdirat(AT_FDCWD, pathname, mode); +} + #endif -- cgit v1.2.3 From b724e846b491ef8db943be8086226c9d8da31877 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:49 +0100 Subject: fs: add do_symlinkat() helper and ksys_symlink() wrapper; remove in-kernel calls to syscall Using the fs-internal do_symlinkat() helper allows us to get rid of fs-internal calls to the sys_symlinkat() syscall. Introducing the ksys_symlink() wrapper allows us to avoid the in-kernel calls to the sys_symlink() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_symlink(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c982cb5f4e50..39c5cef86a10 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -979,4 +979,13 @@ static inline long ksys_mkdir(const char __user *pathname, umode_t mode) return do_mkdirat(AT_FDCWD, pathname, mode); } +extern long do_symlinkat(const char __user *oldname, int newdfd, + const char __user *newname); + +static inline long ksys_symlink(const char __user *oldname, + const char __user *newname) +{ + return do_symlinkat(oldname, AT_FDCWD, newname); +} + #endif -- cgit v1.2.3 From 87c4e19262d81862886207be3c8795f6576d5a52 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:50 +0100 Subject: fs: add do_mknodat() helper and ksys_mknod() wrapper; remove in-kernel calls to syscall Using the fs-internal do_mknodat() helper allows us to get rid of fs-internal calls to the sys_mknodat() syscall. Introducing the ksys_mknod() wrapper allows us to avoid the in-kernel calls to sys_mknod() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mknod(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 39c5cef86a10..0b4fd684f0f1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -988,4 +988,13 @@ static inline long ksys_symlink(const char __user *oldname, return do_symlinkat(oldname, AT_FDCWD, newname); } +extern long do_mknodat(int dfd, const char __user *filename, umode_t mode, + unsigned int dev); + +static inline long ksys_mknod(const char __user *filename, umode_t mode, + unsigned int dev) +{ + return do_mknodat(AT_FDCWD, filename, mode, dev); +} + #endif -- cgit v1.2.3 From 46ea89eb652a365e10257016d09dcf1aaf23cf63 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:53 +0100 Subject: fs: add do_linkat() helper and ksys_link() wrapper; remove in-kernel calls to syscall Using the fs-internal do_linkat() helper allows us to get rid of fs-internal calls to the sys_linkat() syscall. Introducing the ksys_link() wrapper allows us to avoid the in-kernel calls to sys_link() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_link(). In the near future, the only fs-external user of ksys_link() should be converted to use vfs_link() instead. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0b4fd684f0f1..827ed917630c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -997,4 +997,13 @@ static inline long ksys_mknod(const char __user *filename, umode_t mode, return do_mknodat(AT_FDCWD, filename, mode, dev); } +extern int do_linkat(int olddfd, const char __user *oldname, int newdfd, + const char __user *newname, int flags); + +static inline long ksys_link(const char __user *oldname, + const char __user *newname) +{ + return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); +} + #endif -- cgit v1.2.3 From 03450e271a160bc07a2c48e5769e0ba338582d77 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:53 +0100 Subject: fs: add ksys_fchmod() and do_fchmodat() helpers and ksys_chmod() wrapper; remove in-kernel calls to syscall Using the fs-internal do_fchmodat() helper allows us to get rid of fs-internal calls to the sys_fchmodat() syscall. Introducing the ksys_fchmod() helper and the ksys_chmod() wrapper allows us to avoid the in-kernel calls to the sys_fchmod() and sys_chmod() syscalls. The ksys_ prefix denotes that these functions are meant as a drop-in replacement for the syscalls. In particular, they use the same calling convention as sys_fchmod() and sys_chmod(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 827ed917630c..dd6c306f4f00 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -953,6 +953,7 @@ int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); +int ksys_fchmod(unsigned int fd, umode_t mode); /* * The following kernel syscall equivalents are just wrappers to fs-internal @@ -1006,4 +1007,11 @@ static inline long ksys_link(const char __user *oldname, return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } +extern int do_fchmodat(int dfd, const char __user *filename, umode_t mode); + +static inline int ksys_chmod(const char __user *filename, umode_t mode) +{ + return do_fchmodat(AT_FDCWD, filename, mode); +} + #endif -- cgit v1.2.3 From cbfe20f565228966f0249f016752437df95df679 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:54 +0100 Subject: fs: add do_faccessat() helper and ksys_access() wrapper; remove in-kernel calls to syscall Using the fs-internal do_faccessat() helper allows us to get rid of fs-internal calls to the sys_faccessat() syscall. Introducing the ksys_access() wrapper allows us to avoid the in-kernel calls to the sys_access() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_access(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index dd6c306f4f00..33f06de090ea 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1014,4 +1014,11 @@ static inline int ksys_chmod(const char __user *filename, umode_t mode) return do_fchmodat(AT_FDCWD, filename, mode); } +extern long do_faccessat(int dfd, const char __user *filename, int mode); + +static inline long ksys_access(const char __user *filename, int mode) +{ + return do_faccessat(AT_FDCWD, filename, mode); +} + #endif -- cgit v1.2.3 From 55731b3cda3a85ee888dac3bf1f36489f275c187 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:55 +0100 Subject: fs: add do_fchownat(), ksys_fchown() helpers and ksys_{,l}chown() wrappers Using the fs-interal do_fchownat() wrapper allows us to get rid of fs-internal calls to the sys_fchownat() syscall. Introducing the ksys_fchown() helper and the ksys_{,}chown() wrappers allows us to avoid the in-kernel calls to the sys_{,l,f}chown() syscalls. The ksys_ prefix denotes that these functions are meant as a drop-in replacement for the syscalls. In particular, they use the same calling convention as sys_{,l,f}chown(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 33f06de090ea..df0d1e818a6e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -954,6 +954,7 @@ int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); int ksys_fchmod(unsigned int fd, umode_t mode); +int ksys_fchown(unsigned int fd, uid_t user, gid_t group); /* * The following kernel syscall equivalents are just wrappers to fs-internal @@ -1021,4 +1022,20 @@ static inline long ksys_access(const char __user *filename, int mode) return do_faccessat(AT_FDCWD, filename, mode); } +extern int do_fchownat(int dfd, const char __user *filename, uid_t user, + gid_t group, int flag); + +static inline long ksys_chown(const char __user *filename, uid_t user, + gid_t group) +{ + return do_fchownat(AT_FDCWD, filename, user, group, 0); +} + +static inline long ksys_lchown(const char __user *filename, uid_t user, + gid_t group) +{ + return do_fchownat(AT_FDCWD, filename, user, group, + AT_SYMLINK_NOFOLLOW); +} + #endif -- cgit v1.2.3 From 411d9475cf901b5a6d2996b46cb5726184a4fa50 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:54 +0100 Subject: fs: add ksys_ftruncate() wrapper; remove in-kernel calls to sys_ftruncate() Using the ksys_ftruncate() wrapper allows us to get rid of in-kernel calls to the sys_ftruncate() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_ftruncate(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index df0d1e818a6e..41023177c8ec 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1038,4 +1038,11 @@ static inline long ksys_lchown(const char __user *filename, uid_t user, AT_SYMLINK_NOFOLLOW); } +extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small); + +static inline long ksys_ftruncate(unsigned int fd, unsigned long length) +{ + return do_sys_ftruncate(fd, length, 1); +} + #endif -- cgit v1.2.3 From 2ca2a09d6215fd9621aa3e2db7cc9428a61f2911 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:55 +0100 Subject: fs: add ksys_close() wrapper; remove in-kernel calls to sys_close() Using the ksys_close() wrapper allows us to get rid of in-kernel calls to the sys_close() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_close(), with one subtle difference: The few places which checked the return value did not care about the return value re-writing in sys_close(), so simply use a wrapper around __close_fd(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 41023177c8ec..38805f3447ea 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1045,4 +1045,16 @@ static inline long ksys_ftruncate(unsigned int fd, unsigned long length) return do_sys_ftruncate(fd, length, 1); } +extern int __close_fd(struct files_struct *files, unsigned int fd); + +/* + * In contrast to sys_close(), this stub does not check whether the syscall + * should or should not be restarted, but returns the raw error codes from + * __close_fd(). + */ +static inline int ksys_close(unsigned int fd) +{ + return __close_fd(current->files, fd); +} + #endif -- cgit v1.2.3 From bae217ea8c7e123ed3fb1064909a262924771bbb Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:56 +0100 Subject: fs: add ksys_open() wrapper; remove in-kernel calls to sys_open() Using this wrapper allows us to avoid the in-kernel calls to the sys_open() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_open(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 38805f3447ea..f9df17dcec1c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1057,4 +1057,15 @@ static inline int ksys_close(unsigned int fd) return __close_fd(current->files, fd); } +extern long do_sys_open(int dfd, const char __user *filename, int flags, + umode_t mode); + +static inline long ksys_open(const char __user *filename, int flags, + umode_t mode) +{ + if (force_o_largefile()) + flags |= O_LARGEFILE; + return do_sys_open(AT_FDCWD, filename, flags, mode); +} + #endif -- cgit v1.2.3 From 454dab3f965ec24fda8fbe135c8dad4c5b238a86 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:34:04 +0100 Subject: fs: add ksys_getdents64() helper; remove in-kernel calls to sys_getdents64() Using this helper allows us to avoid the in-kernel calls to the sys_getdents64() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_getdents64(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9df17dcec1c..c056aff6d7ad 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -955,6 +955,8 @@ ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); int ksys_fchmod(unsigned int fd, umode_t mode); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); +int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, + unsigned int count); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From cbb60b924b9f3e4d7c67a1c9dcf981718f926e4e Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:43:59 +0100 Subject: fs: add ksys_ioctl() helper; remove in-kernel calls to sys_ioctl() Using this helper allows us to avoid the in-kernel calls to the sys_ioctl() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_ioctl(). After careful review, at least some of these calls could be converted to do_vfs_ioctl() in future. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c056aff6d7ad..5a959efd8fb7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -957,6 +957,7 @@ int ksys_fchmod(unsigned int fd, umode_t mode); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count); +int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 76847e4344350970e1c2e27c28b5abb3c588c5b3 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:51:17 +0100 Subject: fs: add ksys_lseek() helper; remove in-kernel calls to sys_lseek() Using this helper allows us to avoid the in-kernel calls to the sys_lseek() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_lseek(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5a959efd8fb7..0f24e5334569 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -958,6 +958,7 @@ int ksys_fchown(unsigned int fd, uid_t user, gid_t group); int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count); int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); +off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 3ce4a7bf66263748194b77ccefd284be963c6304 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:56:26 +0100 Subject: fs: add ksys_read() helper; remove in-kernel calls to sys_read() Using this helper allows us to avoid the in-kernel calls to the sys_read() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_read(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0f24e5334569..3a2e90842ff8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -959,6 +959,7 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count); int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); +ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 70f68ee81e2e9ad5105b8d2bd324e890e94c6ad9 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Wed, 14 Mar 2018 22:35:11 +0100 Subject: fs: add ksys_sync() helper; remove in-kernel calls to sys_sync() Using this helper allows us to avoid the in-kernel calls to the sys_sync() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_sync(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3a2e90842ff8..0a9942b3e718 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -960,6 +960,7 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); +void ksys_sync(void); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 9b32105ec6b13d32d5db6a6e7992c97ce54b5ea7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:42 +0100 Subject: kernel: add ksys_unshare() helper; remove in-kernel calls to sys_unshare() Using this helper allows us to avoid the in-kernel calls to the sys_unshare() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_unshare(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Cc: Ingo Molnar Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0a9942b3e718..e724dda509e0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -961,6 +961,7 @@ int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); +int ksys_unshare(unsigned long unshare_flags); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From e2aaa9f423367ee03755d632555c242629a08d00 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Fri, 16 Mar 2018 12:36:06 +0100 Subject: kernel: add ksys_setsid() helper; remove in-kernel call to sys_setsid() Using this helper allows us to avoid the in-kernel call to the sys_setsid() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_setsid(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e724dda509e0..4dd685ee425d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -962,6 +962,7 @@ off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); int ksys_unshare(unsigned long unshare_flags); +int ksys_setsid(void); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 806cbae1228cc1a19b978c4513f6851e9ab7f388 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:47 +0100 Subject: fs: add ksys_sync_file_range helper(); remove in-kernel calls to syscall Using this helper allows us to avoid the in-kernel calls to the sys_sync_file_range() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_sync_file_range(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4dd685ee425d..331da76f66e2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -963,6 +963,8 @@ ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); int ksys_unshare(unsigned long unshare_flags); int ksys_setsid(void); +int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, + unsigned int flags); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From df260e21e6cd5d2dfc1fe9b6a3bbf747e72b3bed Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:32:11 +0100 Subject: fs: add ksys_truncate() wrapper; remove in-kernel calls to sys_truncate() Using the ksys_truncate() wrapper allows us to get rid of in-kernel calls to the sys_truncate() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_truncate(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 331da76f66e2..78b79e3a1279 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1078,4 +1078,11 @@ static inline long ksys_open(const char __user *filename, int flags, return do_sys_open(AT_FDCWD, filename, flags, mode); } +extern long do_sys_truncate(const char __user *pathname, loff_t length); + +static inline long ksys_truncate(const char __user *pathname, loff_t length) +{ + return do_sys_truncate(pathname, length); +} + #endif -- cgit v1.2.3 From 36028d5dd71175c332ab634e089e16dbdfe3812b Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:38:31 +0100 Subject: fs: add ksys_p{read,write}64() helpers; remove in-kernel calls to syscalls Using the ksys_p{read,write}64() wrappers allows us to get rid of in-kernel calls to the sys_pread64() and sys_pwrite64() syscalls. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_p{read,write}64(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 78b79e3a1279..a30e4c2d0c27 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -965,6 +965,10 @@ int ksys_unshare(unsigned long unshare_flags); int ksys_setsid(void); int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, unsigned int flags); +ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, + loff_t pos); +ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, + size_t count, loff_t pos); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From edf292c76b884a499cc60ad5cdada2663cc39a2f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:46:32 +0100 Subject: fs: add ksys_fallocate() wrapper; remove in-kernel calls to sys_fallocate() Using the ksys_fallocate() wrapper allows us to get rid of in-kernel calls to the sys_fallocate() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_fallocate(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a30e4c2d0c27..613b8127834d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -969,6 +969,7 @@ ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos); ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); +int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 9d5b7c956b09daab955fb2a42447d5d89ff15093 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:45 +0100 Subject: mm: add ksys_fadvise64_64() helper; remove in-kernel call to sys_fadvise64_64() Using the ksys_fadvise64_64() helper allows us to avoid the in-kernel calls to the sys_fadvise64_64() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as ksys_fadvise64_64(). Some compat stubs called sys_fadvise64(), which then just passed through the arguments to sys_fadvise64_64(). Get rid of this indirection, and call ksys_fadvise64_64() directly. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 613b8127834d..466d408deefd 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -970,6 +970,15 @@ ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len); +#ifdef CONFIG_ADVISE_SYSCALLS +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice); +#else +static inline int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, + int advice) +{ + return -EINVAL; +} +#endif /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From a90f590a1bee36fc2129cfb38ceec24a555bb12d Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:46 +0100 Subject: mm: add ksys_mmap_pgoff() helper; remove in-kernel calls to sys_mmap_pgoff() Using this helper allows us to avoid the in-kernel calls to the sys_mmap_pgoff() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mmap_pgoff(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 466d408deefd..ec866c959e7d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -979,6 +979,9 @@ static inline int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, return -EINVAL; } #endif +unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From c7b95d5156a9ee70f800bd2e47a9eba677be73e1 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:51:36 +0100 Subject: mm: add ksys_readahead() helper; remove in-kernel calls to sys_readahead() Using this helper allows us to avoid the in-kernel calls to the sys_readahead() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_readahead(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index ec866c959e7d..815fbdd9cca1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -982,6 +982,7 @@ static inline int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); +ssize_t ksys_readahead(int fd, loff_t offset, size_t count); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 1bec510a9ebf00baa1aa8751e4a5d88b54efb748 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 22 Mar 2018 17:46:57 +0100 Subject: kexec: move sys_kexec_load() prototype to syscalls.h As the syscall function should only be called from the system call table but not from elsewhere in the kernel, move the prototype for sys_kexec_load() to include/syscall.h. Cc: Eric Biederman Cc: kexec@lists.infradead.org Signed-off-by: Dominik Brodowski --- include/linux/kexec.h | 4 ---- include/linux/syscalls.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index f16f6ceb3875..0ebcbeb21056 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -223,10 +223,6 @@ struct kimage { extern void machine_kexec(struct kimage *image); extern int machine_kexec_prepare(struct kimage *image); extern void machine_kexec_cleanup(struct kimage *image); -extern asmlinkage long sys_kexec_load(unsigned long entry, - unsigned long nr_segments, - struct kexec_segment __user *segments, - unsigned long flags); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 815fbdd9cca1..8330f046541e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -936,6 +936,10 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len, unsigned long prot, int pkey); asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val); asmlinkage long sys_pkey_free(int pkey); +asmlinkage long sys_kexec_load(unsigned long entry, + unsigned long nr_segments, + struct kexec_segment __user *segments, + unsigned long flags); asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); -- cgit v1.2.3 From 3c1c456f9b96c208c9dc9ad7aa3be36b8d488504 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 25 Mar 2018 21:50:11 +0200 Subject: syscalls: sort syscall prototypes in include/linux/syscalls.h Shuffle the syscall prototypes in include/linux/syscalls.h around so that they are kept in the same order as in include/uapi/asm-generic/unistd.h. The individual entries are kept the same, and neither modified to bring them in line with kernel coding style nor wrapped in proper ifdefs. Cc: Arnd Bergmann Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1226 +++++++++++++++++++++++++--------------------- 1 file changed, 678 insertions(+), 548 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 8330f046541e..1f223b7cf16d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -241,223 +241,28 @@ static inline void addr_limit_user_check(void) #endif } -asmlinkage long sys_time(time_t __user *tloc); -asmlinkage long sys_stime(time_t __user *tptr); -asmlinkage long sys_gettimeofday(struct timeval __user *tv, - struct timezone __user *tz); -asmlinkage long sys_settimeofday(struct timeval __user *tv, - struct timezone __user *tz); -asmlinkage long sys_adjtimex(struct timex __user *txc_p); - -asmlinkage long sys_times(struct tms __user *tbuf); - -asmlinkage long sys_gettid(void); -asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp); -asmlinkage long sys_alarm(unsigned int seconds); -asmlinkage long sys_getpid(void); -asmlinkage long sys_getppid(void); -asmlinkage long sys_getuid(void); -asmlinkage long sys_geteuid(void); -asmlinkage long sys_getgid(void); -asmlinkage long sys_getegid(void); -asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid); -asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid); -asmlinkage long sys_getpgid(pid_t pid); -asmlinkage long sys_getpgrp(void); -asmlinkage long sys_getsid(pid_t pid); -asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist); - -asmlinkage long sys_setregid(gid_t rgid, gid_t egid); -asmlinkage long sys_setgid(gid_t gid); -asmlinkage long sys_setreuid(uid_t ruid, uid_t euid); -asmlinkage long sys_setuid(uid_t uid); -asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid); -asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid); -asmlinkage long sys_setfsuid(uid_t uid); -asmlinkage long sys_setfsgid(gid_t gid); -asmlinkage long sys_setpgid(pid_t pid, pid_t pgid); -asmlinkage long sys_setsid(void); -asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist); - -asmlinkage long sys_acct(const char __user *name); -asmlinkage long sys_capget(cap_user_header_t header, - cap_user_data_t dataptr); -asmlinkage long sys_capset(cap_user_header_t header, - const cap_user_data_t data); -asmlinkage long sys_personality(unsigned int personality); - -asmlinkage long sys_sigpending(old_sigset_t __user *uset); -asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, - old_sigset_t __user *oset); -asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, - struct sigaltstack __user *uoss); - -asmlinkage long sys_getitimer(int which, struct itimerval __user *value); -asmlinkage long sys_setitimer(int which, - struct itimerval __user *value, - struct itimerval __user *ovalue); -asmlinkage long sys_timer_create(clockid_t which_clock, - struct sigevent __user *timer_event_spec, - timer_t __user * created_timer_id); -asmlinkage long sys_timer_gettime(timer_t timer_id, - struct itimerspec __user *setting); -asmlinkage long sys_timer_getoverrun(timer_t timer_id); -asmlinkage long sys_timer_settime(timer_t timer_id, int flags, - const struct itimerspec __user *new_setting, - struct itimerspec __user *old_setting); -asmlinkage long sys_timer_delete(timer_t timer_id); -asmlinkage long sys_clock_settime(clockid_t which_clock, - const struct timespec __user *tp); -asmlinkage long sys_clock_gettime(clockid_t which_clock, - struct timespec __user *tp); -asmlinkage long sys_clock_adjtime(clockid_t which_clock, - struct timex __user *tx); -asmlinkage long sys_clock_getres(clockid_t which_clock, - struct timespec __user *tp); -asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags, - const struct timespec __user *rqtp, - struct timespec __user *rmtp); - -asmlinkage long sys_nice(int increment); -asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, - struct sched_param __user *param); -asmlinkage long sys_sched_setparam(pid_t pid, - struct sched_param __user *param); -asmlinkage long sys_sched_setattr(pid_t pid, - struct sched_attr __user *attr, - unsigned int flags); -asmlinkage long sys_sched_getscheduler(pid_t pid); -asmlinkage long sys_sched_getparam(pid_t pid, - struct sched_param __user *param); -asmlinkage long sys_sched_getattr(pid_t pid, - struct sched_attr __user *attr, - unsigned int size, - unsigned int flags); -asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, - unsigned long __user *user_mask_ptr); -asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, - unsigned long __user *user_mask_ptr); -asmlinkage long sys_sched_yield(void); -asmlinkage long sys_sched_get_priority_max(int policy); -asmlinkage long sys_sched_get_priority_min(int policy); -asmlinkage long sys_sched_rr_get_interval(pid_t pid, - struct timespec __user *interval); -asmlinkage long sys_setpriority(int which, int who, int niceval); -asmlinkage long sys_getpriority(int which, int who); - -asmlinkage long sys_shutdown(int, int); -asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, - void __user *arg); -asmlinkage long sys_restart_syscall(void); -asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, - struct kexec_segment __user *segments, - unsigned long flags); -asmlinkage long sys_kexec_file_load(int kernel_fd, int initrd_fd, - unsigned long cmdline_len, - const char __user *cmdline_ptr, - unsigned long flags); - -asmlinkage long sys_exit(int error_code); -asmlinkage long sys_exit_group(int error_code); -asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, - int options, struct rusage __user *ru); -asmlinkage long sys_waitid(int which, pid_t pid, - struct siginfo __user *infop, - int options, struct rusage __user *ru); -asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options); -asmlinkage long sys_set_tid_address(int __user *tidptr); -asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, - struct timespec __user *utime, u32 __user *uaddr2, - u32 val3); - -asmlinkage long sys_init_module(void __user *umod, unsigned long len, - const char __user *uargs); -asmlinkage long sys_delete_module(const char __user *name_user, - unsigned int flags); - -#ifdef CONFIG_OLD_SIGSUSPEND -asmlinkage long sys_sigsuspend(old_sigset_t mask); -#endif - -#ifdef CONFIG_OLD_SIGSUSPEND3 -asmlinkage long sys_sigsuspend(int unused1, int unused2, old_sigset_t mask); -#endif - -asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); - -#ifdef CONFIG_OLD_SIGACTION -asmlinkage long sys_sigaction(int, const struct old_sigaction __user *, - struct old_sigaction __user *); -#endif - -#ifndef CONFIG_ODD_RT_SIGACTION -asmlinkage long sys_rt_sigaction(int, - const struct sigaction __user *, - struct sigaction __user *, - size_t); -#endif -asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, - sigset_t __user *oset, size_t sigsetsize); -asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); -asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, - siginfo_t __user *uinfo, - const struct timespec __user *uts, - size_t sigsetsize); -asmlinkage long sys_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, - siginfo_t __user *uinfo); -asmlinkage long sys_kill(pid_t pid, int sig); -asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig); -asmlinkage long sys_tkill(pid_t pid, int sig); -asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo); -asmlinkage long sys_sgetmask(void); -asmlinkage long sys_ssetmask(int newmask); -asmlinkage long sys_signal(int sig, __sighandler_t handler); -asmlinkage long sys_pause(void); - -asmlinkage long sys_sync(void); -asmlinkage long sys_fsync(unsigned int fd); -asmlinkage long sys_fdatasync(unsigned int fd); -asmlinkage long sys_bdflush(int func, long data); -asmlinkage long sys_mount(char __user *dev_name, char __user *dir_name, - char __user *type, unsigned long flags, - void __user *data); -asmlinkage long sys_umount(char __user *name, int flags); -asmlinkage long sys_oldumount(char __user *name); -asmlinkage long sys_truncate(const char __user *path, long length); -asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); -asmlinkage long sys_stat(const char __user *filename, - struct __old_kernel_stat __user *statbuf); -asmlinkage long sys_statfs(const char __user * path, - struct statfs __user *buf); -asmlinkage long sys_statfs64(const char __user *path, size_t sz, - struct statfs64 __user *buf); -asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf); -asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, - struct statfs64 __user *buf); -asmlinkage long sys_lstat(const char __user *filename, - struct __old_kernel_stat __user *statbuf); -asmlinkage long sys_fstat(unsigned int fd, - struct __old_kernel_stat __user *statbuf); -asmlinkage long sys_newstat(const char __user *filename, - struct stat __user *statbuf); -asmlinkage long sys_newlstat(const char __user *filename, - struct stat __user *statbuf); -asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf); -asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); -#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) -asmlinkage long sys_stat64(const char __user *filename, - struct stat64 __user *statbuf); -asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf); -asmlinkage long sys_lstat64(const char __user *filename, - struct stat64 __user *statbuf); -asmlinkage long sys_fstatat64(int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag); -#endif -#if BITS_PER_LONG == 32 -asmlinkage long sys_truncate64(const char __user *path, loff_t length); -asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); -#endif +/* + * These syscall function prototypes are kept in the same order as + * include/uapi/asm-generic/unistd.h. Architecture specific entries go below, + * followed by deprecated or obsolete system calls. + * + * Please note that these prototypes here are only provided for information + * purposes, for static analysis, and for linking from the syscall table. + * These functions should not be called elsewhere from kernel code. + */ +asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx); +asmlinkage long sys_io_destroy(aio_context_t ctx); +asmlinkage long sys_io_submit(aio_context_t, long, + struct iocb __user * __user *); +asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, + struct io_event __user *result); +asmlinkage long sys_io_getevents(aio_context_t ctx_id, + long min_nr, + long nr, + struct io_event __user *events, + struct timespec __user *timeout); +/* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, const void __user *value, size_t size, int flags); asmlinkage long sys_lsetxattr(const char __user *path, const char __user *name, @@ -481,125 +286,126 @@ asmlinkage long sys_lremovexattr(const char __user *path, const char __user *name); asmlinkage long sys_fremovexattr(int fd, const char __user *name); -asmlinkage long sys_brk(unsigned long brk); -asmlinkage long sys_mprotect(unsigned long start, size_t len, - unsigned long prot); -asmlinkage long sys_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr); -asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, - unsigned long prot, unsigned long pgoff, - unsigned long flags); -asmlinkage long sys_msync(unsigned long start, size_t len, int flags); -asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice); -asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice); -asmlinkage long sys_munmap(unsigned long addr, size_t len); -asmlinkage long sys_mlock(unsigned long start, size_t len); -asmlinkage long sys_munlock(unsigned long start, size_t len); -asmlinkage long sys_mlockall(int flags); -asmlinkage long sys_munlockall(void); -asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); -asmlinkage long sys_mincore(unsigned long start, size_t len, - unsigned char __user * vec); +/* fs/dcache.c */ +asmlinkage long sys_getcwd(char __user *buf, unsigned long size); -asmlinkage long sys_pivot_root(const char __user *new_root, - const char __user *put_old); -asmlinkage long sys_chroot(const char __user *filename); -asmlinkage long sys_mknod(const char __user *filename, umode_t mode, - unsigned dev); -asmlinkage long sys_link(const char __user *oldname, - const char __user *newname); -asmlinkage long sys_symlink(const char __user *old, const char __user *new); -asmlinkage long sys_unlink(const char __user *pathname); -asmlinkage long sys_rename(const char __user *oldname, - const char __user *newname); -asmlinkage long sys_chmod(const char __user *filename, umode_t mode); -asmlinkage long sys_fchmod(unsigned int fd, umode_t mode); +/* fs/cookies.c */ +asmlinkage long sys_lookup_dcookie(u64 cookie64, char __user *buf, size_t len); + +/* fs/eventfd.c */ +asmlinkage long sys_eventfd2(unsigned int count, int flags); +/* fs/eventpoll.c */ +asmlinkage long sys_epoll_create1(int flags); +asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, + struct epoll_event __user *event); +asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout, + const sigset_t __user *sigmask, + size_t sigsetsize); + +/* fs/fcntl.c */ +asmlinkage long sys_dup(unsigned int fildes); +asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags); asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg); #if BITS_PER_LONG == 32 asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg); #endif -asmlinkage long sys_pipe(int __user *fildes); -asmlinkage long sys_pipe2(int __user *fildes, int flags); -asmlinkage long sys_dup(unsigned int fildes); -asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd); -asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags); -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); + +/* fs/inotify_user.c */ +asmlinkage long sys_inotify_init1(int flags); +asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, + u32 mask); +asmlinkage long sys_inotify_rm_watch(int fd, __s32 wd); + +/* fs/ioctl.c */ asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); + +/* fs/ioprio.c */ +asmlinkage long sys_ioprio_set(int which, int who, int ioprio); +asmlinkage long sys_ioprio_get(int which, int who); + +/* fs/locks.c */ asmlinkage long sys_flock(unsigned int fd, unsigned int cmd); -asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx); -asmlinkage long sys_io_destroy(aio_context_t ctx); -asmlinkage long sys_io_getevents(aio_context_t ctx_id, - long min_nr, - long nr, - struct io_event __user *events, - struct timespec __user *timeout); -asmlinkage long sys_io_submit(aio_context_t, long, - struct iocb __user * __user *); -asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, - struct io_event __user *result); -asmlinkage long sys_sendfile(int out_fd, int in_fd, - off_t __user *offset, size_t count); -asmlinkage long sys_sendfile64(int out_fd, int in_fd, - loff_t __user *offset, size_t count); -asmlinkage long sys_readlink(const char __user *path, - char __user *buf, int bufsiz); -asmlinkage long sys_creat(const char __user *pathname, umode_t mode); -asmlinkage long sys_open(const char __user *filename, - int flags, umode_t mode); + +/* fs/namei.c */ +asmlinkage long sys_mknodat(int dfd, const char __user * filename, umode_t mode, + unsigned dev); +asmlinkage long sys_mkdirat(int dfd, const char __user * pathname, umode_t mode); +asmlinkage long sys_unlinkat(int dfd, const char __user * pathname, int flag); +asmlinkage long sys_symlinkat(const char __user * oldname, + int newdfd, const char __user * newname); +asmlinkage long sys_linkat(int olddfd, const char __user *oldname, + int newdfd, const char __user *newname, int flags); +asmlinkage long sys_renameat(int olddfd, const char __user * oldname, + int newdfd, const char __user * newname); + +/* fs/namespace.c */ +asmlinkage long sys_umount(char __user *name, int flags); +asmlinkage long sys_mount(char __user *dev_name, char __user *dir_name, + char __user *type, unsigned long flags, + void __user *data); +asmlinkage long sys_pivot_root(const char __user *new_root, + const char __user *put_old); + +/* fs/nfsctl.c */ + +/* fs/open.c */ +asmlinkage long sys_statfs(const char __user * path, + struct statfs __user *buf); +asmlinkage long sys_statfs64(const char __user *path, size_t sz, + struct statfs64 __user *buf); +asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf); +asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, + struct statfs64 __user *buf); +asmlinkage long sys_truncate(const char __user *path, long length); +asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); +#if BITS_PER_LONG == 32 +asmlinkage long sys_truncate64(const char __user *path, loff_t length); +asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); +#endif +asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); +asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); +asmlinkage long sys_chdir(const char __user *filename); +asmlinkage long sys_fchdir(unsigned int fd); +asmlinkage long sys_chroot(const char __user *filename); +asmlinkage long sys_fchmod(unsigned int fd, umode_t mode); +asmlinkage long sys_fchmodat(int dfd, const char __user * filename, + umode_t mode); +asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, + gid_t group, int flag); +asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); +asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, + umode_t mode); asmlinkage long sys_close(unsigned int fd); -asmlinkage long sys_access(const char __user *filename, int mode); asmlinkage long sys_vhangup(void); -asmlinkage long sys_chown(const char __user *filename, - uid_t user, gid_t group); -asmlinkage long sys_lchown(const char __user *filename, - uid_t user, gid_t group); -asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); -#ifdef CONFIG_HAVE_UID16 -asmlinkage long sys_chown16(const char __user *filename, - old_uid_t user, old_gid_t group); -asmlinkage long sys_lchown16(const char __user *filename, - old_uid_t user, old_gid_t group); -asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group); -asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid); -asmlinkage long sys_setgid16(old_gid_t gid); -asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid); -asmlinkage long sys_setuid16(old_uid_t uid); -asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid); -asmlinkage long sys_getresuid16(old_uid_t __user *ruid, - old_uid_t __user *euid, old_uid_t __user *suid); -asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid); -asmlinkage long sys_getresgid16(old_gid_t __user *rgid, - old_gid_t __user *egid, old_gid_t __user *sgid); -asmlinkage long sys_setfsuid16(old_uid_t uid); -asmlinkage long sys_setfsgid16(old_gid_t gid); -asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist); -asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist); -asmlinkage long sys_getuid16(void); -asmlinkage long sys_geteuid16(void); -asmlinkage long sys_getgid16(void); -asmlinkage long sys_getegid16(void); -#endif -asmlinkage long sys_utime(char __user *filename, - struct utimbuf __user *times); -asmlinkage long sys_utimes(char __user *filename, - struct timeval __user *utimes); -asmlinkage long sys_lseek(unsigned int fd, off_t offset, - unsigned int whence); +/* fs/pipe.c */ +asmlinkage long sys_pipe2(int __user *fildes, int flags); + +/* fs/quota.c */ +asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, + qid_t id, void __user *addr); + +/* fs/readdir.c */ +asmlinkage long sys_getdents64(unsigned int fd, + struct linux_dirent64 __user *dirent, + unsigned int count); + +/* fs/read_write.c */ asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high, unsigned long offset_low, loff_t __user *result, unsigned int whence); +asmlinkage long sys_lseek(unsigned int fd, off_t offset, + unsigned int whence); asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count); -asmlinkage long sys_readahead(int fd, loff_t offset, size_t count); +asmlinkage long sys_write(unsigned int fd, const char __user *buf, + size_t count); asmlinkage long sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen); -asmlinkage long sys_write(unsigned int fd, const char __user *buf, - size_t count); asmlinkage long sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen); @@ -609,264 +415,314 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); -asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - rwf_t flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); -asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - rwf_t flags); -asmlinkage long sys_getcwd(char __user *buf, unsigned long size); -asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); -asmlinkage long sys_chdir(const char __user *filename); -asmlinkage long sys_fchdir(unsigned int fd); -asmlinkage long sys_rmdir(const char __user *pathname); -asmlinkage long sys_lookup_dcookie(u64 cookie64, char __user *buf, size_t len); -asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, - qid_t id, void __user *addr); -asmlinkage long sys_getdents(unsigned int fd, - struct linux_dirent __user *dirent, - unsigned int count); -asmlinkage long sys_getdents64(unsigned int fd, - struct linux_dirent64 __user *dirent, - unsigned int count); -asmlinkage long sys_setsockopt(int fd, int level, int optname, - char __user *optval, int optlen); -asmlinkage long sys_getsockopt(int fd, int level, int optname, - char __user *optval, int __user *optlen); -asmlinkage long sys_bind(int, struct sockaddr __user *, int); -asmlinkage long sys_connect(int, struct sockaddr __user *, int); -asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); -asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); -asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); -asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); -asmlinkage long sys_send(int, void __user *, size_t, unsigned); -asmlinkage long sys_sendto(int, void __user *, size_t, unsigned, - struct sockaddr __user *, int); -asmlinkage long sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags); -asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, - unsigned int vlen, unsigned flags); -asmlinkage long sys_recv(int, void __user *, size_t, unsigned); -asmlinkage long sys_recvfrom(int, void __user *, size_t, unsigned, - struct sockaddr __user *, int __user *); -asmlinkage long sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags); -asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, - unsigned int vlen, unsigned flags, - struct timespec __user *timeout); -asmlinkage long sys_socket(int, int, int); -asmlinkage long sys_socketpair(int, int, int, int __user *); -asmlinkage long sys_socketcall(int call, unsigned long __user *args); -asmlinkage long sys_listen(int, int); -asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, - int timeout); -asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timeval __user *tvp); -asmlinkage long sys_old_select(struct sel_arg_struct __user *arg); -asmlinkage long sys_epoll_create(int size); -asmlinkage long sys_epoll_create1(int flags); -asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, - struct epoll_event __user *event); -asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout); -asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout, - const sigset_t __user *sigmask, +/* fs/sendfile.c */ +asmlinkage long sys_sendfile64(int out_fd, int in_fd, + loff_t __user *offset, size_t count); + +/* fs/select.c */ +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 *, + size_t); + +/* fs/signalfd.c */ +asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, int flags); + +/* fs/splice.c */ +asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, + unsigned long nr_segs, unsigned int flags); +asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, + int fd_out, loff_t __user *off_out, + size_t len, unsigned int flags); +asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags); + +/* fs/stat.c */ +asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, + int bufsiz); +asmlinkage long sys_newfstatat(int dfd, const char __user *filename, + struct stat __user *statbuf, int flag); +asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf); +#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) +asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf); +asmlinkage long sys_fstatat64(int dfd, const char __user *filename, + struct stat64 __user *statbuf, int flag); +#endif + +/* fs/sync.c */ +asmlinkage long sys_sync(void); +asmlinkage long sys_fsync(unsigned int fd); +asmlinkage long sys_fdatasync(unsigned int fd); +asmlinkage long sys_sync_file_range2(int fd, unsigned int flags, + loff_t offset, loff_t nbytes); +asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, + unsigned int flags); + +/* fs/timerfd.c */ +asmlinkage long sys_timerfd_create(int clockid, int flags); +asmlinkage long sys_timerfd_settime(int ufd, int flags, + const struct itimerspec __user *utmr, + struct itimerspec __user *otmr); +asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); + +/* fs/utimes.c */ +asmlinkage long sys_utimensat(int dfd, const char __user *filename, + struct timespec __user *utimes, int flags); + +/* kernel/acct.c */ +asmlinkage long sys_acct(const char __user *name); + +/* kernel/capability.c */ +asmlinkage long sys_capget(cap_user_header_t header, + cap_user_data_t dataptr); +asmlinkage long sys_capset(cap_user_header_t header, + const cap_user_data_t data); + +/* kernel/exec_domain.c */ +asmlinkage long sys_personality(unsigned int personality); + +/* kernel/exit.c */ +asmlinkage long sys_exit(int error_code); +asmlinkage long sys_exit_group(int error_code); +asmlinkage long sys_waitid(int which, pid_t pid, + struct siginfo __user *infop, + int options, struct rusage __user *ru); + +/* kernel/fork.c */ +asmlinkage long sys_set_tid_address(int __user *tidptr); +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, + u32 val3); +asmlinkage long sys_get_robust_list(int pid, + struct robust_list_head __user * __user *head_ptr, + size_t __user *len_ptr); +asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, + size_t len); + +/* kernel/hrtimer.c */ +asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp); + +/* kernel/itimer.c */ +asmlinkage long sys_getitimer(int which, struct itimerval __user *value); +asmlinkage long sys_setitimer(int which, + struct itimerval __user *value, + struct itimerval __user *ovalue); + +/* kernel/kexec.c */ +asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, + struct kexec_segment __user *segments, + unsigned long flags); + +/* kernel/module.c */ +asmlinkage long sys_init_module(void __user *umod, unsigned long len, + const char __user *uargs); +asmlinkage long sys_delete_module(const char __user *name_user, + unsigned int flags); + +/* kernel/posix-timers.c */ +asmlinkage long sys_timer_create(clockid_t which_clock, + struct sigevent __user *timer_event_spec, + timer_t __user * created_timer_id); +asmlinkage long sys_timer_gettime(timer_t timer_id, + struct itimerspec __user *setting); +asmlinkage long sys_timer_getoverrun(timer_t timer_id); +asmlinkage long sys_timer_settime(timer_t timer_id, int flags, + const struct itimerspec __user *new_setting, + struct itimerspec __user *old_setting); +asmlinkage long sys_timer_delete(timer_t timer_id); +asmlinkage long sys_clock_settime(clockid_t which_clock, + const struct timespec __user *tp); +asmlinkage long sys_clock_gettime(clockid_t which_clock, + struct timespec __user *tp); +asmlinkage long sys_clock_getres(clockid_t which_clock, + struct timespec __user *tp); +asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags, + const struct timespec __user *rqtp, + struct timespec __user *rmtp); + +/* kernel/printk.c */ +asmlinkage long sys_syslog(int type, char __user *buf, int len); + +/* kernel/ptrace.c */ +asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, + unsigned long data); +/* kernel/sched/core.c */ + +asmlinkage long sys_sched_setparam(pid_t pid, + struct sched_param __user *param); +asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, + struct sched_param __user *param); +asmlinkage long sys_sched_getscheduler(pid_t pid); +asmlinkage long sys_sched_getparam(pid_t pid, + struct sched_param __user *param); +asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, + unsigned long __user *user_mask_ptr); +asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, + unsigned long __user *user_mask_ptr); +asmlinkage long sys_sched_yield(void); +asmlinkage long sys_sched_get_priority_max(int policy); +asmlinkage long sys_sched_get_priority_min(int policy); +asmlinkage long sys_sched_rr_get_interval(pid_t pid, + struct timespec __user *interval); + +/* kernel/signal.c */ +asmlinkage long sys_restart_syscall(void); +asmlinkage long sys_kill(pid_t pid, int sig); +asmlinkage long sys_tkill(pid_t pid, int sig); +asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig); +asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, + struct sigaltstack __user *uoss); +asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); +#ifndef CONFIG_ODD_RT_SIGACTION +asmlinkage long sys_rt_sigaction(int, + const struct sigaction __user *, + struct sigaction __user *, + size_t); +#endif +asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, + sigset_t __user *oset, size_t sigsetsize); +asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); +asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, + siginfo_t __user *uinfo, + const struct timespec __user *uts, size_t sigsetsize); -asmlinkage long sys_gethostname(char __user *name, int len); +asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo); + +/* kernel/sys.c */ +asmlinkage long sys_setpriority(int which, int who, int niceval); +asmlinkage long sys_getpriority(int which, int who); +asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, + void __user *arg); +asmlinkage long sys_setregid(gid_t rgid, gid_t egid); +asmlinkage long sys_setgid(gid_t gid); +asmlinkage long sys_setreuid(uid_t ruid, uid_t euid); +asmlinkage long sys_setuid(uid_t uid); +asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid); +asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid); +asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid); +asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid); +asmlinkage long sys_setfsuid(uid_t uid); +asmlinkage long sys_setfsgid(gid_t gid); +asmlinkage long sys_times(struct tms __user *tbuf); +asmlinkage long sys_setpgid(pid_t pid, pid_t pgid); +asmlinkage long sys_getpgid(pid_t pid); +asmlinkage long sys_getsid(pid_t pid); +asmlinkage long sys_setsid(void); +asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist); +asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist); +asmlinkage long sys_newuname(struct new_utsname __user *name); asmlinkage long sys_sethostname(char __user *name, int len); asmlinkage long sys_setdomainname(char __user *name, int len); -asmlinkage long sys_newuname(struct new_utsname __user *name); -asmlinkage long sys_uname(struct old_utsname __user *); -asmlinkage long sys_olduname(struct oldold_utsname __user *); - asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim); -#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT -asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim); -#endif asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim); -asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource, - const struct rlimit64 __user *new_rlim, - struct rlimit64 __user *old_rlim); asmlinkage long sys_getrusage(int who, struct rusage __user *ru); asmlinkage long sys_umask(int mask); +asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5); +asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); + +/* kernel/time.c */ +asmlinkage long sys_gettimeofday(struct timeval __user *tv, + struct timezone __user *tz); +asmlinkage long sys_settimeofday(struct timeval __user *tv, + struct timezone __user *tz); +asmlinkage long sys_adjtimex(struct timex __user *txc_p); + +/* kernel/timer.c */ +asmlinkage long sys_getpid(void); +asmlinkage long sys_getppid(void); +asmlinkage long sys_getuid(void); +asmlinkage long sys_geteuid(void); +asmlinkage long sys_getgid(void); +asmlinkage long sys_getegid(void); +asmlinkage long sys_gettid(void); +asmlinkage long sys_sysinfo(struct sysinfo __user *info); + +/* ipc/mqueue.c */ +asmlinkage long sys_mq_open(const char __user *name, int oflag, umode_t mode, struct mq_attr __user *attr); +asmlinkage long sys_mq_unlink(const char __user *name); +asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout); +asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout); +asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification); +asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat); +/* ipc/msg.c */ asmlinkage long sys_msgget(key_t key, int msgflg); -asmlinkage long sys_msgsnd(int msqid, struct msgbuf __user *msgp, - size_t msgsz, int msgflg); +asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg); -asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); +asmlinkage long sys_msgsnd(int msqid, struct msgbuf __user *msgp, + size_t msgsz, int msgflg); +/* ipc/sem.c */ asmlinkage long sys_semget(key_t key, int nsems, int semflg); -asmlinkage long sys_semop(int semid, struct sembuf __user *sops, - unsigned nsops); asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg); asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops, unsigned nsops, const struct timespec __user *timeout); -asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); +asmlinkage long sys_semop(int semid, struct sembuf __user *sops, + unsigned nsops); + +/* ipc/shm.c */ asmlinkage long sys_shmget(key_t key, size_t size, int flag); -asmlinkage long sys_shmdt(char __user *shmaddr); asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); -asmlinkage long sys_ipc(unsigned int call, int first, unsigned long second, - unsigned long third, void __user *ptr, long fifth); +asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); +asmlinkage long sys_shmdt(char __user *shmaddr); -asmlinkage long sys_mq_open(const char __user *name, int oflag, umode_t mode, struct mq_attr __user *attr); -asmlinkage long sys_mq_unlink(const char __user *name); -asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout); -asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout); -asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification); -asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat); +/* net/socket.c */ +asmlinkage long sys_socket(int, int, int); +asmlinkage long sys_socketpair(int, int, int, int __user *); +asmlinkage long sys_bind(int, struct sockaddr __user *, int); +asmlinkage long sys_listen(int, int); +asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_connect(int, struct sockaddr __user *, int); +asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_sendto(int, void __user *, size_t, unsigned, + struct sockaddr __user *, int); +asmlinkage long sys_recvfrom(int, void __user *, size_t, unsigned, + struct sockaddr __user *, int __user *); +asmlinkage long sys_setsockopt(int fd, int level, int optname, + char __user *optval, int optlen); +asmlinkage long sys_getsockopt(int fd, int level, int optname, + char __user *optval, int __user *optlen); +asmlinkage long sys_shutdown(int, int); +asmlinkage long sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags); +asmlinkage long sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags); -asmlinkage long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn); -asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn, - unsigned long off, unsigned long len, - void __user *buf); -asmlinkage long sys_pciconfig_write(unsigned long bus, unsigned long dfn, - unsigned long off, unsigned long len, - void __user *buf); +/* mm/filemap.c */ +asmlinkage long sys_readahead(int fd, loff_t offset, size_t count); -asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5); -asmlinkage long sys_swapon(const char __user *specialfile, int swap_flags); -asmlinkage long sys_swapoff(const char __user *specialfile); -asmlinkage long sys_sysctl(struct __sysctl_args __user *args); -asmlinkage long sys_sysinfo(struct sysinfo __user *info); -asmlinkage long sys_sysfs(int option, - unsigned long arg1, unsigned long arg2); -asmlinkage long sys_syslog(int type, char __user *buf, int len); -asmlinkage long sys_uselib(const char __user *library); -asmlinkage long sys_ni_syscall(void); -asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, - unsigned long data); +/* mm/nommu.c, also with MMU */ +asmlinkage long sys_brk(unsigned long brk); +asmlinkage long sys_munmap(unsigned long addr, size_t len); +asmlinkage long sys_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr); +/* security/keys/keyctl.c */ asmlinkage long sys_add_key(const char __user *_type, const char __user *_description, const void __user *_payload, size_t plen, key_serial_t destringid); - asmlinkage long sys_request_key(const char __user *_type, const char __user *_description, const char __user *_callout_info, key_serial_t destringid); - asmlinkage long sys_keyctl(int cmd, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); -asmlinkage long sys_ioprio_set(int which, int who, int ioprio); -asmlinkage long sys_ioprio_get(int which, int who); -asmlinkage long sys_set_mempolicy(int mode, const unsigned long __user *nmask, - unsigned long maxnode); -asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, - const unsigned long __user *from, - const unsigned long __user *to); -asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, - const void __user * __user *pages, - const int __user *nodes, - int __user *status, - int flags); -asmlinkage long sys_mbind(unsigned long start, unsigned long len, - unsigned long mode, - const unsigned long __user *nmask, - unsigned long maxnode, - unsigned flags); -asmlinkage long sys_get_mempolicy(int __user *policy, - unsigned long __user *nmask, - unsigned long maxnode, - unsigned long addr, unsigned long flags); - -asmlinkage long sys_inotify_init(void); -asmlinkage long sys_inotify_init1(int flags); -asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, - u32 mask); -asmlinkage long sys_inotify_rm_watch(int fd, __s32 wd); - -asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, - __u32 __user *ustatus); -asmlinkage long sys_spu_create(const char __user *name, - unsigned int flags, umode_t mode, int fd); - -asmlinkage long sys_mknodat(int dfd, const char __user * filename, umode_t mode, - unsigned dev); -asmlinkage long sys_mkdirat(int dfd, const char __user * pathname, umode_t mode); -asmlinkage long sys_unlinkat(int dfd, const char __user * pathname, int flag); -asmlinkage long sys_symlinkat(const char __user * oldname, - int newdfd, const char __user * newname); -asmlinkage long sys_linkat(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname, int flags); -asmlinkage long sys_renameat(int olddfd, const char __user * oldname, - int newdfd, const char __user * newname); -asmlinkage long sys_renameat2(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname, - unsigned int flags); -asmlinkage long sys_futimesat(int dfd, const char __user *filename, - struct timeval __user *utimes); -asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); -asmlinkage long sys_fchmodat(int dfd, const char __user * filename, - umode_t mode); -asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, - gid_t group, int flag); -asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, - umode_t mode); -asmlinkage long sys_newfstatat(int dfd, const char __user *filename, - struct stat __user *statbuf, int flag); -asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, - int bufsiz); -asmlinkage long sys_utimensat(int dfd, const char __user *filename, - struct timespec __user *utimes, int flags); -asmlinkage long sys_unshare(unsigned long unshare_flags); - -asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, - int fd_out, loff_t __user *off_out, - size_t len, unsigned int flags); - -asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, - unsigned long nr_segs, unsigned int flags); - -asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags); - -asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, - unsigned int flags); -asmlinkage long sys_sync_file_range2(int fd, unsigned int flags, - loff_t offset, loff_t nbytes); -asmlinkage long sys_get_robust_list(int pid, - struct robust_list_head __user * __user *head_ptr, - size_t __user *len_ptr); -asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, - size_t len); -asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); -asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask); -asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, int flags); -asmlinkage long sys_timerfd_create(int clockid, int flags); -asmlinkage long sys_timerfd_settime(int ufd, int flags, - const struct itimerspec __user *utmr, - struct itimerspec __user *otmr); -asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); -asmlinkage long sys_eventfd(unsigned int count); -asmlinkage long sys_eventfd2(unsigned int count, int flags); -asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); -asmlinkage long sys_userfaultfd(int flags); -asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); -asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int); -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 *, - size_t); -asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags); -asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, - u64 mask, int fd, - const char __user *pathname); -asmlinkage long sys_syncfs(int fd); - -asmlinkage long sys_fork(void); -asmlinkage long sys_vfork(void); +/* arch/example/kernel/sys_example.c */ #ifdef CONFIG_CLONE_BACKWARDS asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, unsigned long, int __user *); @@ -879,26 +735,80 @@ asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int __user *, unsigned long); #endif #endif - asmlinkage long sys_execve(const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp); +/* mm/fadvise.c */ +asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice); + +/* mm/, CONFIG_MMU only */ +asmlinkage long sys_swapon(const char __user *specialfile, int swap_flags); +asmlinkage long sys_swapoff(const char __user *specialfile); +asmlinkage long sys_mprotect(unsigned long start, size_t len, + unsigned long prot); +asmlinkage long sys_msync(unsigned long start, size_t len, int flags); +asmlinkage long sys_mlock(unsigned long start, size_t len); +asmlinkage long sys_munlock(unsigned long start, size_t len); +asmlinkage long sys_mlockall(int flags); +asmlinkage long sys_munlockall(void); +asmlinkage long sys_mincore(unsigned long start, size_t len, + unsigned char __user * vec); +asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); +asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, + unsigned long prot, unsigned long pgoff, + unsigned long flags); +asmlinkage long sys_mbind(unsigned long start, unsigned long len, + unsigned long mode, + const unsigned long __user *nmask, + unsigned long maxnode, + unsigned flags); +asmlinkage long sys_get_mempolicy(int __user *policy, + unsigned long __user *nmask, + unsigned long maxnode, + unsigned long addr, unsigned long flags); +asmlinkage long sys_set_mempolicy(int mode, const unsigned long __user *nmask, + unsigned long maxnode); +asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, + const unsigned long __user *from, + const unsigned long __user *to); +asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, + const void __user * __user *pages, + const int __user *nodes, + int __user *status, + int flags); + +asmlinkage long sys_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, + siginfo_t __user *uinfo); asmlinkage long sys_perf_event_open( struct perf_event_attr __user *attr_uptr, pid_t pid, int cpu, int group_fd, unsigned long flags); +asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); +asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, + unsigned int vlen, unsigned flags, + struct timespec __user *timeout); -asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); +asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, + int options, struct rusage __user *ru); +asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource, + const struct rlimit64 __user *new_rlim, + struct rlimit64 __user *old_rlim); +asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags); +asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, + u64 mask, int fd, + const char __user *pathname); asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name, struct file_handle __user *handle, int __user *mnt_id, int flag); asmlinkage long sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); +asmlinkage long sys_clock_adjtime(clockid_t which_clock, + struct timex __user *tx); +asmlinkage long sys_syncfs(int fd); asmlinkage long sys_setns(int fd, int nstype); +asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, + unsigned int vlen, unsigned flags); asmlinkage long sys_process_vm_readv(pid_t pid, const struct iovec __user *lvec, unsigned long liovcnt, @@ -911,39 +821,259 @@ asmlinkage long sys_process_vm_writev(pid_t pid, const struct iovec __user *rvec, unsigned long riovcnt, unsigned long flags); - asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1, unsigned long idx2); asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags); +asmlinkage long sys_sched_setattr(pid_t pid, + struct sched_attr __user *attr, + unsigned int flags); +asmlinkage long sys_sched_getattr(pid_t pid, + struct sched_attr __user *attr, + unsigned int size, + unsigned int flags); +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); 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); asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); - asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); - +asmlinkage long sys_userfaultfd(int flags); asmlinkage long sys_membarrier(int cmd, int flags); +asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in, int fd_out, loff_t __user *off_out, size_t len, unsigned int flags); - -asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); - +asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + rwf_t flags); +asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + rwf_t flags); asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len, unsigned long prot, int pkey); asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val); asmlinkage long sys_pkey_free(int pkey); -asmlinkage long sys_kexec_load(unsigned long entry, - unsigned long nr_segments, - struct kexec_segment __user *segments, - unsigned long flags); asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); +/* + * Architecture-specific system calls + */ + +/* arch/x86/kernel/ioport.c */ +asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); + +/* pciconfig: alpha, arm, arm64, ia64, sparc */ +asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn, + unsigned long off, unsigned long len, + void __user *buf); +asmlinkage long sys_pciconfig_write(unsigned long bus, unsigned long dfn, + unsigned long off, unsigned long len, + void __user *buf); +asmlinkage long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn); + +/* powerpc */ +asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, + __u32 __user *ustatus); +asmlinkage long sys_spu_create(const char __user *name, + unsigned int flags, umode_t mode, int fd); + + +/* + * Deprecated system calls which are still defined in + * include/uapi/asm-generic/unistd.h and wanted by >= 1 arch + */ + +/* __ARCH_WANT_SYSCALL_NO_AT */ +asmlinkage long sys_open(const char __user *filename, + int flags, umode_t mode); +asmlinkage long sys_link(const char __user *oldname, + const char __user *newname); +asmlinkage long sys_unlink(const char __user *pathname); +asmlinkage long sys_mknod(const char __user *filename, umode_t mode, + unsigned dev); +asmlinkage long sys_chmod(const char __user *filename, umode_t mode); +asmlinkage long sys_chown(const char __user *filename, + uid_t user, gid_t group); +asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); +asmlinkage long sys_rmdir(const char __user *pathname); +asmlinkage long sys_lchown(const char __user *filename, + uid_t user, gid_t group); +asmlinkage long sys_access(const char __user *filename, int mode); +asmlinkage long sys_rename(const char __user *oldname, + const char __user *newname); +asmlinkage long sys_symlink(const char __user *old, const char __user *new); +asmlinkage long sys_utimes(char __user *filename, + struct timeval __user *utimes); +#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) +asmlinkage long sys_stat64(const char __user *filename, + struct stat64 __user *statbuf); +asmlinkage long sys_lstat64(const char __user *filename, + struct stat64 __user *statbuf); +#endif + +/* __ARCH_WANT_SYSCALL_NO_FLAGS */ +asmlinkage long sys_pipe(int __user *fildes); +asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd); +asmlinkage long sys_epoll_create(int size); +asmlinkage long sys_inotify_init(void); +asmlinkage long sys_eventfd(unsigned int count); +asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask); + +/* __ARCH_WANT_SYSCALL_OFF_T */ +asmlinkage long sys_sendfile(int out_fd, int in_fd, + off_t __user *offset, size_t count); +asmlinkage long sys_newstat(const char __user *filename, + struct stat __user *statbuf); +asmlinkage long sys_newlstat(const char __user *filename, + struct stat __user *statbuf); +asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice); + +/* __ARCH_WANT_SYSCALL_DEPRECATED */ +asmlinkage long sys_alarm(unsigned int seconds); +asmlinkage long sys_getpgrp(void); +asmlinkage long sys_pause(void); +asmlinkage long sys_time(time_t __user *tloc); +asmlinkage long sys_utime(char __user *filename, + struct utimbuf __user *times); +asmlinkage long sys_creat(const char __user *pathname, umode_t mode); +asmlinkage long sys_getdents(unsigned int fd, + struct linux_dirent __user *dirent, + unsigned int count); +asmlinkage long sys_futimesat(int dfd, const char __user *filename, + struct timeval __user *utimes); +asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, + fd_set __user *exp, struct timeval __user *tvp); +asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, + int timeout); +asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout); +asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); +asmlinkage long sys_vfork(void); +asmlinkage long sys_recv(int, void __user *, size_t, unsigned); +asmlinkage long sys_send(int, void __user *, size_t, unsigned); +asmlinkage long sys_bdflush(int func, long data); +asmlinkage long sys_oldumount(char __user *name); +asmlinkage long sys_uselib(const char __user *library); +asmlinkage long sys_sysctl(struct __sysctl_args __user *args); +asmlinkage long sys_sysfs(int option, + unsigned long arg1, unsigned long arg2); +asmlinkage long sys_fork(void); + +/* obsolete: kernel/time/time.c */ +asmlinkage long sys_stime(time_t __user *tptr); + +/* obsolete: kernel/signal.c */ +asmlinkage long sys_sigpending(old_sigset_t __user *uset); +asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, + old_sigset_t __user *oset); +#ifdef CONFIG_OLD_SIGSUSPEND +asmlinkage long sys_sigsuspend(old_sigset_t mask); +#endif + +#ifdef CONFIG_OLD_SIGSUSPEND3 +asmlinkage long sys_sigsuspend(int unused1, int unused2, old_sigset_t mask); +#endif + +#ifdef CONFIG_OLD_SIGACTION +asmlinkage long sys_sigaction(int, const struct old_sigaction __user *, + struct old_sigaction __user *); +#endif +asmlinkage long sys_sgetmask(void); +asmlinkage long sys_ssetmask(int newmask); +asmlinkage long sys_signal(int sig, __sighandler_t handler); + +/* obsolete: kernel/sched/core.c */ +asmlinkage long sys_nice(int increment); + +/* obsolete: kernel/kexec_file.c */ +asmlinkage long sys_kexec_file_load(int kernel_fd, int initrd_fd, + unsigned long cmdline_len, + const char __user *cmdline_ptr, + unsigned long flags); + +/* obsolete: kernel/exit.c */ +asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options); + +/* obsolete: kernel/uid16.c */ +#ifdef CONFIG_HAVE_UID16 +asmlinkage long sys_chown16(const char __user *filename, + old_uid_t user, old_gid_t group); +asmlinkage long sys_lchown16(const char __user *filename, + old_uid_t user, old_gid_t group); +asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group); +asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid); +asmlinkage long sys_setgid16(old_gid_t gid); +asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid); +asmlinkage long sys_setuid16(old_uid_t uid); +asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid); +asmlinkage long sys_getresuid16(old_uid_t __user *ruid, + old_uid_t __user *euid, old_uid_t __user *suid); +asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid); +asmlinkage long sys_getresgid16(old_gid_t __user *rgid, + old_gid_t __user *egid, old_gid_t __user *sgid); +asmlinkage long sys_setfsuid16(old_uid_t uid); +asmlinkage long sys_setfsgid16(old_gid_t gid); +asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist); +asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist); +asmlinkage long sys_getuid16(void); +asmlinkage long sys_geteuid16(void); +asmlinkage long sys_getgid16(void); +asmlinkage long sys_getegid16(void); +#endif + +/* obsolete: net/socket.c */ +asmlinkage long sys_socketcall(int call, unsigned long __user *args); + +/* obsolete: fs/stat.c */ +asmlinkage long sys_stat(const char __user *filename, + struct __old_kernel_stat __user *statbuf); +asmlinkage long sys_lstat(const char __user *filename, + struct __old_kernel_stat __user *statbuf); +asmlinkage long sys_fstat(unsigned int fd, + struct __old_kernel_stat __user *statbuf); +asmlinkage long sys_readlink(const char __user *path, + char __user *buf, int bufsiz); + +/* obsolete: fs/select.c */ +asmlinkage long sys_old_select(struct sel_arg_struct __user *arg); + +/* obsolete: fs/readdir.c */ +asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int); + +/* obsolete: kernel/sys.c */ +asmlinkage long sys_gethostname(char __user *name, int len); +asmlinkage long sys_uname(struct old_utsname __user *); +asmlinkage long sys_olduname(struct oldold_utsname __user *); +#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT +asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim); +#endif + +/* obsolete: ipc */ +asmlinkage long sys_ipc(unsigned int call, int first, unsigned long second, + unsigned long third, void __user *ptr, long fifth); + +/* obsolete: mm/ */ +asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); +asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); + + +/* + * Not a real system call, but a placeholder for syscalls which are + * not implemented -- see kernel/sys_ni.c + */ +asmlinkage long sys_ni_syscall(void); + + /* * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. * Instead, use one of the functions which work equivalently, such as -- cgit v1.2.3 From c679a08983db7c1eb09930570b92ff7c9fd59c1c Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 25 Mar 2018 23:04:48 +0200 Subject: syscalls: sort syscall prototypes in include/linux/compat.h Shuffle the syscall prototypes in include/linux/compat.h around so that they are kept in the same order as in include/uapi/asm-generic/unistd.h. The individual entries are kept the same, and neither modified to bring them in line with kernel coding style nor wrapped in proper ifdefs -- as an exception to this, add the prefix "asmlinkage" where it was missing. Cc: Arnd Bergmann Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/compat.h | 655 ++++++++++++++++++++++++++++--------------------- 1 file changed, 378 insertions(+), 277 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index f1649a5e6716..f881cce627f6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -305,10 +305,6 @@ extern int put_compat_rusage(const struct rusage *, struct compat_siginfo; -extern asmlinkage long compat_sys_waitid(int, compat_pid_t, - struct compat_siginfo __user *, int, - struct compat_rusage __user *); - struct compat_dirent { u32 d_ino; compat_off_t d_off; @@ -422,90 +418,6 @@ struct compat_msgbuf; extern void compat_exit_robust_list(struct task_struct *curr); -asmlinkage long -compat_sys_set_robust_list(struct compat_robust_list_head __user *head, - compat_size_t len); -asmlinkage long -compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, - compat_size_t __user *len_ptr); - -asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32); -asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); -asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); -asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, - compat_ssize_t msgsz, int msgflg); -asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp, - compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); -long compat_sys_msgctl(int first, int second, void __user *uptr); -long compat_sys_shmctl(int first, int second, void __user *uptr); -long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, - unsigned nsems, const struct compat_timespec __user *timeout); -asmlinkage long compat_sys_keyctl(u32 option, - u32 arg2, u32 arg3, u32 arg4, u32 arg5); -asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); - -asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd, - const struct compat_iovec __user *vec, compat_ulong_t vlen); -asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd, - const struct compat_iovec __user *vec, compat_ulong_t vlen); -asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, - const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high); -asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, - const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high); -asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, - const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); -asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, - const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); - -asmlinkage long compat_sys_quotactl32(unsigned int cmd, - const char __user *special, qid_t id, void __user *addr); - -#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 -asmlinkage long compat_sys_preadv64(unsigned long fd, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos); -#endif - -#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 -asmlinkage long compat_sys_pwritev64(unsigned long fd, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos); -#endif - -#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 -asmlinkage long compat_sys_readv64v2(unsigned long fd, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, rwf_t flags); -#endif - -#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 -asmlinkage long compat_sys_pwritev64v2(unsigned long fd, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, rwf_t flags); -#endif - -asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); - -asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, - const compat_uptr_t __user *envp); -asmlinkage long compat_sys_execveat(int dfd, const char __user *filename, - const compat_uptr_t __user *argv, - const compat_uptr_t __user *envp, int flags); - -asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timeval __user *tvp); - -asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg); - -asmlinkage long compat_sys_wait4(compat_pid_t pid, - compat_uint_t __user *stat_addr, int options, - struct compat_rusage __user *ru); - #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) @@ -518,13 +430,6 @@ int copy_siginfo_from_user32(siginfo_t *to, const struct compat_siginfo __user * int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from); int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig, - struct compat_siginfo __user *uinfo); -#ifdef CONFIG_COMPAT_OLD_SIGACTION -asmlinkage long compat_sys_sigaction(int sig, - const struct compat_old_sigaction __user *act, - struct compat_old_sigaction __user *oact); -#endif static inline int compat_timeval_compare(struct compat_timeval *lhs, struct compat_timeval *rhs) @@ -546,13 +451,6 @@ static inline int compat_timespec_compare(struct compat_timespec *lhs, return lhs->tv_nsec - rhs->tv_nsec; } -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz); -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz); - -asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); - extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); /* @@ -578,110 +476,132 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, #endif } -asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, - compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, - const compat_ulong_t __user *new_nodes); - extern int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); -asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, - compat_long_t addr, compat_long_t data); -asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t); +struct epoll_event; /* fortunately, this one is fixed-layout */ + +extern ssize_t compat_rw_copy_check_uvector(int type, + const struct compat_iovec __user *uvector, + unsigned long nr_segs, + unsigned long fast_segs, struct iovec *fast_pointer, + struct iovec **ret_pointer); + +extern void __user *compat_alloc_user_space(unsigned long len); + +int compat_restore_altstack(const compat_stack_t __user *uss); +int __compat_save_altstack(compat_stack_t __user *, unsigned long); +#define compat_save_altstack_ex(uss, sp) do { \ + compat_stack_t __user *__uss = uss; \ + struct task_struct *t = current; \ + put_user_ex(ptr_to_compat((void __user *)t->sas_ss_sp), &__uss->ss_sp); \ + put_user_ex(t->sas_ss_flags, &__uss->ss_flags); \ + put_user_ex(t->sas_ss_size, &__uss->ss_size); \ + if (t->sas_ss_flags & SS_AUTODISARM) \ + sas_ss_reset(t); \ +} while (0); + /* - * epoll (fs/eventpoll.c) compat bits follow ... + * These syscall function prototypes are kept in the same order as + * include/uapi/asm-generic/unistd.h. Architecture specific entries go below, + * followed by deprecated or obsolete system calls. + * + * Please note that these prototypes here are only provided for information + * purposes, for static analysis, and for linking from the syscall table. + * These functions should not be called elsewhere from kernel code. */ -struct epoll_event; /* fortunately, this one is fixed-layout */ +asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); +asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, + u32 __user *iocb); +asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id, + compat_long_t min_nr, + compat_long_t nr, + struct io_event __user *events, + struct compat_timespec __user *timeout); + +/* fs/cookies.c */ +asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t); + +/* fs/eventpoll.c */ asmlinkage long compat_sys_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, int timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); -asmlinkage long compat_sys_utime(const char __user *filename, - struct compat_utimbuf __user *t); -asmlinkage long compat_sys_utimensat(unsigned int dfd, - const char __user *filename, - struct compat_timespec __user *t, - int flags); +/* fs/fcntl.c */ +asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, + compat_ulong_t arg); +asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, + compat_ulong_t arg); -asmlinkage long compat_sys_time(compat_time_t __user *tloc); -asmlinkage long compat_sys_stime(compat_time_t __user *tptr); -asmlinkage long compat_sys_signalfd(int ufd, - const compat_sigset_t __user *sigmask, - compat_size_t sigsetsize); -asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, - const struct compat_itimerspec __user *utmr, - struct compat_itimerspec __user *otmr); -asmlinkage long compat_sys_timerfd_gettime(int ufd, - struct compat_itimerspec __user *otmr); +/* fs/ioctl.c */ +asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, + compat_ulong_t arg); -asmlinkage long compat_sys_move_pages(pid_t pid, compat_ulong_t nr_pages, - __u32 __user *pages, - const int __user *nodes, - int __user *status, - int flags); -asmlinkage long compat_sys_futimesat(unsigned int dfd, - const char __user *filename, - struct compat_timeval __user *t); -asmlinkage long compat_sys_utimes(const char __user *filename, - struct compat_timeval __user *t); -asmlinkage long compat_sys_newstat(const char __user *filename, - struct compat_stat __user *statbuf); -asmlinkage long compat_sys_newlstat(const char __user *filename, - struct compat_stat __user *statbuf); -asmlinkage long compat_sys_newfstatat(unsigned int dfd, - const char __user *filename, - struct compat_stat __user *statbuf, - int flag); -asmlinkage long compat_sys_newfstat(unsigned int fd, - struct compat_stat __user *statbuf); +/* fs/namespace.c */ +asmlinkage long compat_sys_mount(const char __user *dev_name, + const char __user *dir_name, + const char __user *type, compat_ulong_t flags, + const void __user *data); + +/* fs/open.c */ asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf); -asmlinkage long compat_sys_fstatfs(unsigned int fd, - struct compat_statfs __user *buf); asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf); +asmlinkage long compat_sys_fstatfs(unsigned int fd, + struct compat_statfs __user *buf); asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf); -asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, - compat_ulong_t arg); -asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, - compat_ulong_t arg); -asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); -asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id, - compat_long_t min_nr, - compat_long_t nr, - struct io_event __user *events, - struct compat_timespec __user *timeout); -asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, - u32 __user *iocb); -asmlinkage long compat_sys_mount(const char __user *dev_name, - const char __user *dir_name, - const char __user *type, compat_ulong_t flags, - const void __user *data); -asmlinkage long compat_sys_old_readdir(unsigned int fd, - struct compat_old_linux_dirent __user *, - unsigned int count); +asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); +asmlinkage long compat_sys_ftruncate(unsigned int, compat_ulong_t); +/* No generic prototype for truncate64, ftruncate64, fallocate */ +asmlinkage long compat_sys_openat(int dfd, const char __user *filename, + int flags, umode_t mode); + +/* fs/readdir.c */ asmlinkage long compat_sys_getdents(unsigned int fd, struct compat_linux_dirent __user *dirent, unsigned int count); -asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *, - unsigned int nr_segs, unsigned int flags); -asmlinkage long compat_sys_open(const char __user *filename, int flags, - umode_t mode); -asmlinkage long compat_sys_openat(int dfd, const char __user *filename, - int flags, umode_t mode); -asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, - struct file_handle __user *handle, - int flags); -asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); -asmlinkage long compat_sys_ftruncate(unsigned int, compat_ulong_t); + +/* fs/read_write.c */ +asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); +asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd, + const struct compat_iovec __user *vec, compat_ulong_t vlen); +asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd, + const struct compat_iovec __user *vec, compat_ulong_t vlen); +/* No generic prototype for pread64 and pwrite64 */ +asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high); +asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high); +#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 +asmlinkage long compat_sys_preadv64(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 +asmlinkage long compat_sys_pwritev64(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos); +#endif + +/* fs/sendfile.c */ +asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, + compat_off_t __user *offset, compat_size_t count); +asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, + compat_loff_t __user *offset, compat_size_t count); + +/* fs/select.c */ asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, @@ -692,110 +612,149 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, struct compat_timespec __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); + +/* fs/signalfd.c */ asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); -asmlinkage long compat_sys_get_mempolicy(int __user *policy, - compat_ulong_t __user *nmask, - compat_ulong_t maxnode, - compat_ulong_t addr, - compat_ulong_t flags); -asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, - compat_ulong_t maxnode); -asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, - compat_ulong_t mode, - compat_ulong_t __user *nmask, - compat_ulong_t maxnode, compat_ulong_t flags); -asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, - char __user *optval, unsigned int optlen); -asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, - unsigned flags); -asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, - unsigned vlen, unsigned int flags); -asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, - unsigned int flags); -asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, - unsigned flags); -asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, - unsigned flags, struct sockaddr __user *addr, - int __user *addrlen); -asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, - unsigned vlen, unsigned int flags, - struct compat_timespec __user *timeout); +/* fs/splice.c */ +asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *, + unsigned int nr_segs, unsigned int flags); + +/* fs/stat.c */ +asmlinkage long compat_sys_newfstatat(unsigned int dfd, + const char __user *filename, + struct compat_stat __user *statbuf, + int flag); +asmlinkage long compat_sys_newfstat(unsigned int fd, + struct compat_stat __user *statbuf); + +/* fs/sync.c: No generic prototype for sync_file_range and sync_file_range2 */ + +/* fs/timerfd.c */ +asmlinkage long compat_sys_timerfd_gettime(int ufd, + struct compat_itimerspec __user *otmr); +asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, + const struct compat_itimerspec __user *utmr, + struct compat_itimerspec __user *otmr); + +/* fs/utimes.c */ +asmlinkage long compat_sys_utimensat(unsigned int dfd, + const char __user *filename, + struct compat_timespec __user *t, + int flags); + +/* kernel/exit.c */ +asmlinkage long compat_sys_waitid(int, compat_pid_t, + struct compat_siginfo __user *, int, + struct compat_rusage __user *); + + + +/* kernel/futex.c */ +asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, + struct compat_timespec __user *utime, u32 __user *uaddr2, + u32 val3); +asmlinkage long +compat_sys_set_robust_list(struct compat_robust_list_head __user *head, + compat_size_t len); +asmlinkage long +compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, + compat_size_t __user *len_ptr); + +/* kernel/hrtimer.c */ asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp, struct compat_timespec __user *rmtp); + +/* kernel/itimer.c */ asmlinkage long compat_sys_getitimer(int which, struct compat_itimerval __user *it); asmlinkage long compat_sys_setitimer(int which, struct compat_itimerval __user *in, struct compat_itimerval __user *out); -asmlinkage long compat_sys_times(struct compat_tms __user *tbuf); -asmlinkage long compat_sys_setrlimit(unsigned int resource, - struct compat_rlimit __user *rlim); -asmlinkage long compat_sys_getrlimit(unsigned int resource, - struct compat_rlimit __user *rlim); -asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); -asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, - unsigned int len, - compat_ulong_t __user *user_mask_ptr); -asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, - unsigned int len, - compat_ulong_t __user *user_mask_ptr); + +/* kernel/kexec.c */ +asmlinkage long compat_sys_kexec_load(compat_ulong_t entry, + compat_ulong_t nr_segments, + struct compat_kexec_segment __user *, + compat_ulong_t flags); + +/* kernel/posix-timers.c */ asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); +asmlinkage long compat_sys_timer_gettime(timer_t timer_id, + struct compat_itimerspec __user *setting); asmlinkage long compat_sys_timer_settime(timer_t timer_id, int flags, struct compat_itimerspec __user *new, struct compat_itimerspec __user *old); -asmlinkage long compat_sys_timer_gettime(timer_t timer_id, - struct compat_itimerspec __user *setting); asmlinkage long compat_sys_clock_settime(clockid_t which_clock, struct compat_timespec __user *tp); asmlinkage long compat_sys_clock_gettime(clockid_t which_clock, struct compat_timespec __user *tp); -asmlinkage long compat_sys_clock_adjtime(clockid_t which_clock, - struct compat_timex __user *tp); asmlinkage long compat_sys_clock_getres(clockid_t which_clock, struct compat_timespec __user *tp); asmlinkage long compat_sys_clock_nanosleep(clockid_t which_clock, int flags, struct compat_timespec __user *rqtp, struct compat_timespec __user *rmtp); -asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, - struct compat_siginfo __user *uinfo, - struct compat_timespec __user *uts, compat_size_t sigsetsize); + +/* kernel/ptrace.c */ +asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, + compat_long_t addr, compat_long_t data); + +/* kernel/sched/core.c */ +asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, + unsigned int len, + compat_ulong_t __user *user_mask_ptr); +asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, + unsigned int len, + compat_ulong_t __user *user_mask_ptr); +asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, + struct compat_timespec __user *interval); + +/* kernel/signal.c */ +asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, + compat_stack_t __user *uoss_ptr); asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat_size_t sigsetsize); -asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, - compat_sigset_t __user *oset, - compat_size_t sigsetsize); -asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, - compat_size_t sigsetsize); #ifndef CONFIG_ODD_RT_SIGACTION asmlinkage long compat_sys_rt_sigaction(int, const struct compat_sigaction __user *, struct compat_sigaction __user *, compat_size_t); #endif +asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, + compat_sigset_t __user *oset, + compat_size_t sigsetsize); +asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, + compat_size_t sigsetsize); +asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, + struct compat_siginfo __user *uinfo, + struct compat_timespec __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); +/* No generic prototype for rt_sigreturn */ + +/* kernel/sys.c */ +asmlinkage long compat_sys_times(struct compat_tms __user *tbuf); +asmlinkage long compat_sys_getrlimit(unsigned int resource, + struct compat_rlimit __user *rlim); +asmlinkage long compat_sys_setrlimit(unsigned int resource, + struct compat_rlimit __user *rlim); +asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); + +/* kernel/time.c */ +asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); +asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, + struct timezone __user *tz); +asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); + +/* kernel/timer.c */ asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); -asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, - compat_ulong_t arg); -asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, - struct compat_timespec __user *utime, u32 __user *uaddr2, - u32 val3); -asmlinkage long compat_sys_getsockopt(int fd, int level, int optname, - char __user *optval, int __user *optlen); -asmlinkage long compat_sys_kexec_load(compat_ulong_t entry, - compat_ulong_t nr_segments, - struct compat_kexec_segment __user *, - compat_ulong_t flags); -asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, - const struct compat_mq_attr __user *u_mqstat, - struct compat_mq_attr __user *u_omqstat); -asmlinkage long compat_sys_mq_notify(mqd_t mqdes, - const struct compat_sigevent __user *u_notification); + +/* ipc/mqueue.c */ asmlinkage long compat_sys_mq_open(const char __user *u_name, int oflag, compat_mode_t mode, struct compat_mq_attr __user *u_attr); @@ -807,17 +766,92 @@ asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, compat_size_t msg_len, unsigned int __user *u_msg_prio, const struct compat_timespec __user *u_abs_timeout); -asmlinkage long compat_sys_socketcall(int call, u32 __user *args); -asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args); +asmlinkage long compat_sys_mq_notify(mqd_t mqdes, + const struct compat_sigevent __user *u_notification); +asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, + const struct compat_mq_attr __user *u_mqstat, + struct compat_mq_attr __user *u_omqstat); -extern ssize_t compat_rw_copy_check_uvector(int type, - const struct compat_iovec __user *uvector, - unsigned long nr_segs, - unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer); +/* ipc/msg.c */ +asmlinkage long compat_sys_msgctl(int first, int second, void __user *uptr); +asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp, + compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); +asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, + compat_ssize_t msgsz, int msgflg); -extern void __user *compat_alloc_user_space(unsigned long len); +/* ipc/sem.c */ +asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); +asmlinkage long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, + unsigned nsems, const struct compat_timespec __user *timeout); + +/* ipc/shm.c */ +asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); +asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); + +/* net/socket.c */ +asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, + unsigned flags, struct sockaddr __user *addr, + int __user *addrlen); +asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, + char __user *optval, unsigned int optlen); +asmlinkage long compat_sys_getsockopt(int fd, int level, int optname, + char __user *optval, int __user *optlen); +asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, + unsigned flags); +asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, + unsigned int flags); + +/* mm/filemap.c: No generic prototype for readahead */ +/* security/keys/keyctl.c */ +asmlinkage long compat_sys_keyctl(u32 option, + u32 arg2, u32 arg3, u32 arg4, u32 arg5); + +/* arch/example/kernel/sys_example.c */ +asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, + const compat_uptr_t __user *envp); + +/* mm/fadvise.c: No generic prototype for fadvise64_64 */ + +/* mm/, CONFIG_MMU only */ +asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, + compat_ulong_t mode, + compat_ulong_t __user *nmask, + compat_ulong_t maxnode, compat_ulong_t flags); +asmlinkage long compat_sys_get_mempolicy(int __user *policy, + compat_ulong_t __user *nmask, + compat_ulong_t maxnode, + compat_ulong_t addr, + compat_ulong_t flags); +asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask, + compat_ulong_t maxnode); +asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, + compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, + const compat_ulong_t __user *new_nodes); +asmlinkage long compat_sys_move_pages(pid_t pid, compat_ulong_t nr_pages, + __u32 __user *pages, + const int __user *nodes, + int __user *status, + int flags); + +asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, + compat_pid_t pid, int sig, + struct compat_siginfo __user *uinfo); +asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, + unsigned vlen, unsigned int flags, + struct compat_timespec __user *timeout); +asmlinkage long compat_sys_wait4(compat_pid_t pid, + compat_uint_t __user *stat_addr, int options, + struct compat_rusage __user *ru); +asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, + int, const char __user *); +asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, + struct file_handle __user *handle, + int flags); +asmlinkage long compat_sys_clock_adjtime(clockid_t which_clock, + struct compat_timex __user *tp); +asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, + unsigned vlen, unsigned int flags); asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid, const struct compat_iovec __user *lvec, compat_ulong_t liovcnt, const struct compat_iovec __user *rvec, @@ -826,14 +860,89 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, const struct compat_iovec __user *lvec, compat_ulong_t liovcnt, const struct compat_iovec __user *rvec, compat_ulong_t riovcnt, compat_ulong_t flags); +asmlinkage long compat_sys_execveat(int dfd, const char __user *filename, + const compat_uptr_t __user *argv, + const compat_uptr_t __user *envp, int flags); +asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); +asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); +#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 +asmlinkage long compat_sys_readv64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif -asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, - compat_off_t __user *offset, compat_size_t count); -asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, - compat_loff_t __user *offset, compat_size_t count); -asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, - compat_stack_t __user *uoss_ptr); +#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 +asmlinkage long compat_sys_pwritev64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + + +/* + * Architecture-specific system calls + */ + +/* fs/quota/compat.c -- x86 only */ +asmlinkage long compat_sys_quotactl32(unsigned int cmd, + const char __user *special, qid_t id, void __user *addr); + +/* arch_prctl -- x86 */ +asmlinkage long compat_sys_arch_prctl(int option, unsigned long arg2); + + +/* + * Deprecated system calls which are still defined in + * include/uapi/asm-generic/unistd.h and wanted by >= 1 arch + */ + +/* __ARCH_WANT_SYSCALL_NO_AT */ +asmlinkage long compat_sys_open(const char __user *filename, int flags, + umode_t mode); +asmlinkage long compat_sys_utimes(const char __user *filename, + struct compat_timeval __user *t); + +/* __ARCH_WANT_SYSCALL_NO_FLAGS */ +asmlinkage long compat_sys_signalfd(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize); + +/* __ARCH_WANT_SYSCALL_OFF_T */ +asmlinkage long compat_sys_newstat(const char __user *filename, + struct compat_stat __user *statbuf); +asmlinkage long compat_sys_newlstat(const char __user *filename, + struct compat_stat __user *statbuf); + +/* __ARCH_WANT_SYSCALL_DEPRECATED */ +asmlinkage long compat_sys_time(compat_time_t __user *tloc); +asmlinkage long compat_sys_utime(const char __user *filename, + struct compat_utimbuf __user *t); +asmlinkage long compat_sys_futimesat(unsigned int dfd, + const char __user *filename, + struct compat_timeval __user *t); +asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct compat_timeval __user *tvp); +asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); +asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, + unsigned flags); +asmlinkage long compat_sys_sysctl(struct compat_sysctl_args __user *args); + +/* obsolete: fs/readdir.c */ +asmlinkage long compat_sys_old_readdir(unsigned int fd, + struct compat_old_linux_dirent __user *, + unsigned int count); + +/* obsolete: fs/select.c */ +asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg); + +/* obsolete: ipc */ +asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32); +/* obsolete: kernel/signal.c */ #ifdef __ARCH_WANT_SYS_SIGPENDING asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set); #endif @@ -842,26 +951,18 @@ asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set); asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *nset, compat_old_sigset_t __user *oset); #endif +#ifdef CONFIG_COMPAT_OLD_SIGACTION +asmlinkage long compat_sys_sigaction(int sig, + const struct compat_old_sigaction __user *act, + struct compat_old_sigaction __user *oact); +#endif -int compat_restore_altstack(const compat_stack_t __user *uss); -int __compat_save_altstack(compat_stack_t __user *, unsigned long); -#define compat_save_altstack_ex(uss, sp) do { \ - compat_stack_t __user *__uss = uss; \ - struct task_struct *t = current; \ - put_user_ex(ptr_to_compat((void __user *)t->sas_ss_sp), &__uss->ss_sp); \ - put_user_ex(t->sas_ss_flags, &__uss->ss_flags); \ - put_user_ex(t->sas_ss_size, &__uss->ss_size); \ - if (t->sas_ss_flags & SS_AUTODISARM) \ - sas_ss_reset(t); \ -} while (0); - -asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, - struct compat_timespec __user *interval); +/* obsolete: kernel/time/time.c */ +asmlinkage long compat_sys_stime(compat_time_t __user *tptr); -asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, - int, const char __user *); +/* obsolete: net/socket.c */ +asmlinkage long compat_sys_socketcall(int call, u32 __user *args); -asmlinkage long compat_sys_arch_prctl(int option, unsigned long arg2); /* * For most but not all architectures, "am I in a compat syscall?" and -- cgit v1.2.3 From 3e2052e5dd4062ccc7a10e8860aa7d2e58627001 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 22 Mar 2018 14:09:17 +0100 Subject: syscalls/x86: auto-create compat_sys_*() prototypes compat_sys_*() functions are no longer called from within the kernel on x86 except from the system call table. Linking the system call does not require compat_sys_*() function prototypes at least on x86. Therefore, generate compat_sys_*() prototypes on-the-fly within the COMPAT_SYSCALL_DEFINEx() macro, and remove x86-specific prototypes from various header files. Suggested-by: Andy Lutomirski Cc: Arnd Bergmann Cc: David S. Miller Cc: netdev@vger.kernel.org Cc: Thomas Gleixner Cc: Andi Kleen Cc: Ingo Molnar Cc: Andrew Morton Cc: Al Viro Cc: x86@kernel.org Signed-off-by: Dominik Brodowski --- include/linux/compat.h | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index f881cce627f6..8cb8710db0ab 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -49,6 +49,7 @@ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ __attribute__((alias(__stringify(compat_SyS##name)))); \ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ @@ -507,8 +508,8 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); /* * These syscall function prototypes are kept in the same order as - * include/uapi/asm-generic/unistd.h. Architecture specific entries go below, - * followed by deprecated or obsolete system calls. + * include/uapi/asm-generic/unistd.h. Deprecated or obsolete system calls + * go below. * * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. @@ -882,18 +883,6 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd, #endif -/* - * Architecture-specific system calls - */ - -/* fs/quota/compat.c -- x86 only */ -asmlinkage long compat_sys_quotactl32(unsigned int cmd, - const char __user *special, qid_t id, void __user *addr); - -/* arch_prctl -- x86 */ -asmlinkage long compat_sys_arch_prctl(int option, unsigned long arg2); - - /* * Deprecated system calls which are still defined in * include/uapi/asm-generic/unistd.h and wanted by >= 1 arch -- cgit v1.2.3 From c9a211951c7c79cfb5de888d7d9550872868b086 Mon Sep 17 00:00:00 2001 From: Howard McLauchlan Date: Wed, 21 Mar 2018 18:59:08 -0700 Subject: bpf: whitelist all syscalls for error injection Error injection is a useful mechanism to fail arbitrary kernel functions. However, it is often hard to guarantee an error propagates appropriately to user space programs. By injecting into syscalls, we can return arbitrary values to user space directly; this increases flexibility and robustness in testing, allowing us to test user space error paths effectively. The following script, for example, fails calls to sys_open() from a given pid: from bcc import BPF from sys import argv pid = argv[1] prog = r""" int kprobe__SyS_open(struct pt_regs *ctx, const char *pathname, int flags) { u32 pid = bpf_get_current_pid_tgid(); if (pid == %s) bpf_override_return(ctx, -ENOMEM); return 0; } """ % pid b = BPF(text=prog) while 1: b.perf_buffer_poll() This patch whitelists all syscalls defined with SYSCALL_DEFINE and COMPAT_SYSCALL_DEFINE for error injection. These changes are not intended to be considered stable, and would normally be configured off. Signed-off-by: Howard McLauchlan Signed-off-by: Dominik Brodowski --- include/linux/compat.h | 3 +++ include/linux/syscalls.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8cb8710db0ab..9847c5a013c3 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -33,6 +33,8 @@ #endif #define COMPAT_SYSCALL_DEFINE0(name) \ + asmlinkage long compat_sys_##name(void); \ + ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \ asmlinkage long compat_sys_##name(void) #define COMPAT_SYSCALL_DEFINE1(name, ...) \ @@ -52,6 +54,7 @@ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ __attribute__((alias(__stringify(compat_SyS##name)))); \ + ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\ asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1f223b7cf16d..b961184f597a 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -191,6 +191,8 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long sys_##sname(void); \ + ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \ asmlinkage long sys_##sname(void) #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) @@ -210,6 +212,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(SyS##name)))); \ + ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ -- cgit v1.2.3 From 21035965f60b0502fc6537b232839389bb4ce664 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 2 Apr 2018 15:58:31 -0700 Subject: bitmap: fix memset optimization on big-endian systems Commit 2a98dc028f91 ("include/linux/bitmap.h: turn bitmap_set and bitmap_clear into memset when possible") introduced an optimization to bitmap_{set,clear}() which uses memset() when the start and length are constants aligned to a byte. This is wrong on big-endian systems; our bitmaps are arrays of unsigned long, so bit n is not at byte n / 8 in memory. This was caught by the Btrfs selftests, but the bitmap selftests also fail when run on a big-endian machine. We can still use memset if the start and length are aligned to an unsigned long, so do that on big-endian. The same problem applies to the memcmp in bitmap_equal(), so fix it there, too. Fixes: 2a98dc028f91 ("include/linux/bitmap.h: turn bitmap_set and bitmap_clear into memset when possible") Fixes: 2c6deb01525a ("bitmap: use memcmp optimisation in more situations") Cc: stable@kernel.org Reported-by: "Erhard F." Cc: Matthew Wilcox Cc: Rasmus Villemoes Cc: Andrew Morton Cc: Arnd Bergmann Signed-off-by: Omar Sandoval Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 5f11fbdc27f8..1ee46f492267 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -302,12 +302,20 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr __bitmap_complement(dst, src, nbits); } +#ifdef __LITTLE_ENDIAN +#define BITMAP_MEM_ALIGNMENT 8 +#else +#define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) +#endif +#define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) + static inline int bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); - if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) && + IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) return !memcmp(src1, src2, nbits / 8); return __bitmap_equal(src1, src2, nbits); } @@ -358,8 +366,10 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start, { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); - else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && - __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && + IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && + __builtin_constant_p(nbits & BITMAP_MEM_MASK) && + IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0xff, nbits / 8); else __bitmap_set(map, start, nbits); @@ -370,8 +380,10 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); - else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && - __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && + IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && + __builtin_constant_p(nbits & BITMAP_MEM_MASK) && + IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0, nbits / 8); else __bitmap_clear(map, start, nbits); -- cgit v1.2.3 From 1bd21c6c21e848996339508d3ffb106d505256a8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:01 +0200 Subject: syscalls/core: Introduce CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y It may be useful for an architecture to override the definitions of the SYSCALL_DEFINE0() and __SYSCALL_DEFINEx() macros in , in particular to use a different calling convention for syscalls. This patch provides a mechanism to do so: It introduces CONFIG_ARCH_HAS_SYSCALL_WRAPPER. If it is enabled, is included in and may be used to define the macros mentioned above. Moreover, as the syscall calling convention may be different if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is set, the syscall function prototypes in are #ifndef'd out in that case. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/syscalls.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b961184f597a..503ab245d4ce 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -81,6 +81,17 @@ union bpf_attr; #include #include +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +/* + * It may be useful for an architecture to override the definitions of the + * SYSCALL_DEFINE0() and __SYSCALL_DEFINEx() macros, in particular to use a + * different calling convention for syscalls. To allow for that, the prototypes + * for the sys_*() functions below will *not* be included if + * CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. + */ +#include +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * __MAP - apply a macro to syscall arguments * __MAP(n, m, t1, a1, t2, a2, ..., tn, an) will expand to @@ -189,11 +200,13 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) } #endif +#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ asmlinkage long sys_##sname(void); \ ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \ asmlinkage long sys_##sname(void) +#endif /* SYSCALL_DEFINE0 */ #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) @@ -209,6 +222,8 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) + +#ifndef __SYSCALL_DEFINEx #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(SyS##name)))); \ @@ -223,6 +238,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) return ret; \ } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#endif /* __SYSCALL_DEFINEx */ /* * Called before coming back to user-mode. Returning to user-mode with an @@ -252,7 +268,12 @@ static inline void addr_limit_user_check(void) * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. + * + * As the syscall calling convention may be different from the default + * for architectures overriding the syscall calling convention, do not + * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx); asmlinkage long sys_io_destroy(aio_context_t ctx); asmlinkage long sys_io_submit(aio_context_t, long, @@ -1076,6 +1097,8 @@ asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); */ asmlinkage long sys_ni_syscall(void); +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. -- cgit v1.2.3 From fa697140f9a20119a9ec8fd7460cc4314fbdaff3 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:02 +0200 Subject: syscalls/x86: Use 'struct pt_regs' based syscall calling convention for 64-bit syscalls Let's make use of ARCH_HAS_SYSCALL_WRAPPER=y on pure 64-bit x86-64 systems: Each syscall defines a stub which takes struct pt_regs as its only argument. It decodes just those parameters it needs, e.g: asmlinkage long sys_xyzzy(const struct pt_regs *regs) { return SyS_xyzzy(regs->di, regs->si, regs->dx); } This approach avoids leaking random user-provided register content down the call chain. For example, for sys_recv() which is a 4-parameter syscall, the assembly now is (in slightly reordered fashion): : callq <__fentry__> /* decode regs->di, ->si, ->dx and ->r10 */ mov 0x70(%rdi),%rdi mov 0x68(%rdi),%rsi mov 0x60(%rdi),%rdx mov 0x38(%rdi),%rcx [ SyS_recv() is automatically inlined by the compiler, as it is not [yet] used anywhere else ] /* clear %r9 and %r8, the 5th and 6th args */ xor %r9d,%r9d xor %r8d,%r8d /* do the actual work */ callq __sys_recvfrom /* cleanup and return */ cltq retq The only valid place in an x86-64 kernel which rightfully calls a syscall function on its own -- vsyscall -- needs to be modified to pass struct pt_regs onwards as well. To keep the syscall table generation working independent of SYSCALL_PTREGS being enabled, the stubs are named the same as the "original" syscall stubs, i.e. sys_*(). This patch is based on an original proof-of-concept | From: Linus Torvalds | Signed-off-by: Linus Torvalds and was split up and heavily modified by me, in particular to base it on ARCH_HAS_SYSCALL_WRAPPER, to limit it to 64-bit-only for the time being, and to update the vsyscall to the new calling convention. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- 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 503ab245d4ce..d7168b3a4b4c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -102,7 +102,7 @@ union bpf_attr; * for SYSCALL_DEFINE/COMPAT_SYSCALL_DEFINE */ #define __MAP0(m,...) -#define __MAP1(m,t,a) m(t,a) +#define __MAP1(m,t,a,...) m(t,a) #define __MAP2(m,t,a,...) m(t,a), __MAP1(m,__VA_ARGS__) #define __MAP3(m,t,a,...) m(t,a), __MAP2(m,__VA_ARGS__) #define __MAP4(m,t,a,...) m(t,a), __MAP3(m,__VA_ARGS__) -- cgit v1.2.3 From 7303e30ec1d8fb5ca1f07c92d069241c32b2ee1b Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:03 +0200 Subject: syscalls/core: Prepare CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y for compat syscalls It may be useful for an architecture to override the definitions of the COMPAT_SYSCALL_DEFINE0() and __COMPAT_SYSCALL_DEFINEx() macros in , in particular to use a different calling convention for syscalls. This patch provides a mechanism to do so, based on the previously introduced CONFIG_ARCH_HAS_SYSCALL_WRAPPER. If it is enabled, is included in and may be used to define the macros mentioned above. Moreover, as the syscall calling convention may be different if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is set, the compat syscall function prototypes in are #ifndef'd out in that case. As some of the syscalls and/or compat syscalls may not be present, the COND_SYSCALL() and COND_SYSCALL_COMPAT() macros in kernel/sys_ni.c as well as the SYS_NI() and COMPAT_SYS_NI() macros in kernel/time/posix-stubs.c can be re-defined in iff CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-5-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/compat.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 9847c5a013c3..2d85ec5cfda2 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -24,6 +24,17 @@ #include #include +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +/* + * It may be useful for an architecture to override the definitions of the + * COMPAT_SYSCALL_DEFINE0 and COMPAT_SYSCALL_DEFINEx() macros, in particular + * to use a different calling convention for syscalls. To allow for that, + + the prototypes for the compat_sys_*() functions below will *not* be included + * if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. + */ +#include +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + #ifndef COMPAT_USE_64BIT_TIME #define COMPAT_USE_64BIT_TIME 0 #endif @@ -32,10 +43,12 @@ #define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif +#ifndef COMPAT_SYSCALL_DEFINE0 #define COMPAT_SYSCALL_DEFINE0(name) \ asmlinkage long compat_sys_##name(void); \ ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \ asmlinkage long compat_sys_##name(void) +#endif /* COMPAT_SYSCALL_DEFINE0 */ #define COMPAT_SYSCALL_DEFINE1(name, ...) \ COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) @@ -50,6 +63,7 @@ #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) +#ifndef COMPAT_SYSCALL_DEFINEx #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ @@ -62,6 +76,7 @@ return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ } \ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#endif /* COMPAT_SYSCALL_DEFINEx */ #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() @@ -517,7 +532,12 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. + * + * As the syscall calling convention may be different from the default + * for architectures overriding the syscall calling convention, do not + * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, u32 __user *iocb); @@ -955,6 +975,8 @@ asmlinkage long compat_sys_stime(compat_time_t __user *tptr); /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * For most but not all architectures, "am I in a compat syscall?" and -- cgit v1.2.3 From e145242ea0df6b7d28fd7186e61d6840fa4bb06e Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 9 Apr 2018 12:51:42 +0200 Subject: syscalls/core, syscalls/x86: Clean up syscall stub naming convention Tidy the naming convention for compat syscall subs. Hints which describe the purpose of the stub go in front and receive a double underscore to denote that they are generated on-the-fly by the SYSCALL_DEFINEx() macro. For the generic case, this means (0xffffffff prefix removed): 810f08d0 t kernel_waitid # common C function (see kernel/exit.c) __do_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) 810f1aa0 T __se_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long; # casts them to the declared type) 810f1aa0 T sys_waitid # alias to __se_sys_waitid() (taking # parameters as declared), to be included # in syscall table For x86, the naming is as follows: 810efc70 t kernel_waitid # common C function (see kernel/exit.c) __do_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) 810efd60 t __se_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long; # casts them to the declared type) 810f1140 T __ia32_sys_waitid # IA32_EMULATION 32-bit-ptregs -> C stub, # calls __se_sys_waitid(); to be included # in syscall table 810f1110 T sys_waitid # x86 64-bit-ptregs -> C stub, calls # __se_sys_waitid(); to be included in # syscall table For x86, sys_waitid() will be re-named to __x64_sys_waitid in a follow-up patch. Suggested-by: Ingo Molnar Signed-off-by: Dominik Brodowski Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180409105145.5364-2-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/syscalls.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d7168b3a4b4c..70fcda1a9049 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -223,21 +223,26 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) +/* + * The asmlinkage stub is aliased to a function named __se_sys_*() which + * sign-extends 32-bit ints to longs whenever needed. The actual work is + * done within __do_sys_*(). + */ #ifndef __SYSCALL_DEFINEx #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ - __attribute__((alias(__stringify(SyS##name)))); \ + __attribute__((alias(__stringify(__se_sys##name)))); \ ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ - asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ - asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ - long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\ __MAP(x,__SC_TEST,__VA_ARGS__); \ __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ return ret; \ } \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* __SYSCALL_DEFINEx */ /* -- cgit v1.2.3 From 5ac9efa3c50d7caff9f3933bb8a3ad1139d92d92 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 9 Apr 2018 12:51:43 +0200 Subject: syscalls/core, syscalls/x86: Clean up compat syscall stub naming convention Tidy the naming convention for compat syscall subs. Hints which describe the purpose of the stub go in front and receive a double underscore to denote that they are generated on-the-fly by the COMPAT_SYSCALL_DEFINEx() macro. For the generic case, this means: t kernel_waitid # common C function (see kernel/exit.c) __do_compat_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) T __se_compat_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long, # casts them to unsigned long and then to # the declared type) T compat_sys_waitid # alias to __se_compat_sys_waitid() # (taking parameters as declared), to # be included in syscall table For x86, the naming is as follows: t kernel_waitid # common C function (see kernel/exit.c) __do_compat_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) t __se_compat_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long, # casts them to unsigned long and then to # the declared type) T __ia32_compat_sys_waitid # IA32_EMULATION 32-bit-ptregs -> C stub, # calls __se_compat_sys_waitid(); to be # included in syscall table T __x32_compat_sys_waitid # x32 64-bit-ptregs -> C stub, calls # __se_compat_sys_waitid(); to be included # in syscall table If only one of IA32_EMULATION and x32 is enabled, __se_compat_sys_waitid() may be inlined into the stub __{ia32,x32}_compat_sys_waitid(). Suggested-by: Ingo Molnar Signed-off-by: Dominik Brodowski Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180409105145.5364-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/compat.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 2d85ec5cfda2..aca050aac7b6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -63,19 +63,24 @@ #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) +/* + * The asmlinkage stub is aliased to a function named __se_compat_sys_*() which + * sign-extends 32-bit ints to longs whenever needed. The actual work is + * done within __do_compat_sys_*(). + */ #ifndef COMPAT_SYSCALL_DEFINEx -#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ - asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ - __attribute__((alias(__stringify(compat_SyS##name)))); \ - ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ - static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ - asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\ - asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\ - { \ - return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ - } \ - static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ + __attribute__((alias(__stringify(__se_compat_sys##name)))); \ + ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ + } \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ #ifndef compat_user_stack_pointer -- cgit v1.2.3