From 26fc40a09221330c574fa9cc06d0175273022e44 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 1 Mar 2016 09:44:17 -0800 Subject: net: pppolac/pppopns: Replace msg.msg_iov with iov_iter_kvec() Commit 1af89c1ef3b6 ("Hack: net: PPPoPNS and PPPoLAC build fixes for 4.1") fixed the build for PPPoPNS and PPPoLAC by re-introducing a field in struct msghdr which was removed upstream. Re-introducing the field doesn't get it used, so it is quite likely that the code never worked. Fix it up for good. Fixes: 1af89c1ef3b6 ("Hack: net: PPPoPNS and PPPoLAC build fixes for 4.1") Signed-off-by: Guenter Roeck --- include/linux/socket.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 18a8337c8959..5bf59c8493b7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -47,10 +47,6 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ -#if defined(CONFIG_PPPOLAC) || defined(CONFIG_PPPOPNS) - struct iovec *msg_iov; /* scatter/gather array */ - __kernel_size_t msg_iovlen; /* # elements in msg_iov */ -#endif struct iov_iter msg_iter; /* data */ void *msg_control; /* ancillary data */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ -- cgit v1.2.3 From c2c4c4ecd27d69807906cf6f0df5a176e1498e71 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 4 Mar 2016 07:22:27 -0800 Subject: power: Provide dummy log_suspend_abort_reason() if SUSPEND is disabled The API to log the suspend reason was introduced with commit 57caa2ad5ce3 ("power: Adds functionality to log the last suspend abort reason."). It is called from functions enabled with PM_SLEEP and from functions enabled with SUSPEND, but only available if SUSPEND is enabled. This can result in build failures such as the following if PM_SLEEP is enabled, but SUSPEND is not. kernel/built-in.o: In function `try_to_freeze_tasks': process.c:(.text+0x30928): undefined reference to `log_suspend_abort_reason' drivers/built-in.o: In function `syscore_suspend': (.text+0x6e250): undefined reference to `log_suspend_abort_reason' drivers/built-in.o: In function `__device_suspend': main.c:(.text+0x7a528): undefined reference to `log_suspend_abort_reason' Fixes: 57caa2ad5ce3 ("power: Adds functionality to log the last suspend abort reason.") Signed-off-by: Guenter Roeck --- include/linux/wakeup_reason.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wakeup_reason.h b/include/linux/wakeup_reason.h index ad8b76936c7f..d84d8c301546 100644 --- a/include/linux/wakeup_reason.h +++ b/include/linux/wakeup_reason.h @@ -21,7 +21,12 @@ #define MAX_SUSPEND_ABORT_LEN 256 void log_wakeup_reason(int irq); -void log_suspend_abort_reason(const char *fmt, ...); int check_wakeup_reason(int irq); +#ifdef CONFIG_SUSPEND +void log_suspend_abort_reason(const char *fmt, ...); +#else +static inline void log_suspend_abort_reason(const char *fmt, ...) { } +#endif + #endif /* _LINUX_WAKEUP_REASON_H */ -- cgit v1.2.3 From 9a3fe392e468775da2b63a813f60b923eb6476c5 Mon Sep 17 00:00:00 2001 From: dcashman Date: Wed, 24 Feb 2016 13:27:06 -0800 Subject: FROMLIST: drivers: char: random: add get_random_long() (cherry picked from commit https://lkml.org/lkml/2016/2/4/831) d07e22597d1d355 ("mm: mmap: add new /proc tunable for mmap_base ASLR") added the ability to choose from a range of values to use for entropy count in generating the random offset to the mmap_base address. The maximum value on this range was set to 32 bits for 64-bit x86 systems, but this value could be increased further, requiring more than the 32 bits of randomness provided by get_random_int(), as is already possible for arm64. Add a new function: get_random_long() which more naturally fits with the mmap usage of get_random_int() but operates exactly the same as get_random_int(). Also, fix the shifting constant in mmap_rnd() to be an unsigned long so that values greater than 31 bits generate an appropriate mask without overflow. This is especially important on x86, as its shift instruction uses a 5-bit mask for the shift operand, which meant that any value for mmap_rnd_bits over 31 acts as a no-op and effectively disables mmap_base randomization. Finally, replace calls to get_random_int() with get_random_long() where appropriate. Bug: 26963541 Signed-off-by: Daniel Cashman Signed-off-by: Daniel Cashman Change-Id: I5b45621088666d5d1dfbf43952f25ea0798b10ba --- include/linux/random.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index a75840c1aa71..9c29122037f9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops; #endif unsigned int get_random_int(void); +unsigned long get_random_long(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); u32 prandom_u32(void); -- cgit v1.2.3 From 84a1b7d3d3121e86fac74ae570311556c10b9c31 Mon Sep 17 00:00:00 2001 From: Daniel Campello Date: Mon, 20 Jul 2015 16:23:50 -0700 Subject: Included sdcardfs source code for kernel 3.0 Only included the source code as is for kernel 3.0. Following patches take care of porting this file system to version 3.10. Change-Id: I09e76db77cd98a059053ba5b6fd88572a4b75b5b Signed-off-by: Daniel Campello --- include/linux/namei.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index d8c6334cd150..ef3b4f74eaf0 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -43,6 +43,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_JUMPED 0x1000 #define LOOKUP_ROOT 0x2000 #define LOOKUP_EMPTY 0x4000 +#ifdef CONFIG_SDCARD_FS_CI_SEARCH +#define LOOKUP_CASE_INSENSITIVE 0x8000 +#endif extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -- cgit v1.2.3 From e76fbcd41aba68de594ec481a7d847982da81388 Mon Sep 17 00:00:00 2001 From: Daniel Campello Date: Mon, 20 Jul 2015 16:27:37 -0700 Subject: Port of sdcardfs to 4.4 Change-Id: I25b99ecf214e72ebf6a57ec3085972542a8d7951 Signed-off-by: Daniel Rosenberg --- include/linux/namei.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index ef3b4f74eaf0..f2b8acbdb928 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -78,6 +78,8 @@ extern struct dentry *user_path_create(int, const char __user *, struct path *, extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); +extern int vfs_path_lookup(struct dentry *, struct vfsmount *, + const char *, unsigned int, struct path *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); -- cgit v1.2.3 From 530d9c5fc268b0c90ffbca40384f9ee657076724 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Thu, 11 Feb 2016 16:44:15 -0800 Subject: vfs: add d_canonical_path for stacked filesystem support Inotify does not currently know when a filesystem is acting as a wrapper around another fs. This means that inotify watchers will miss any modifications to the base file, as well as any made in a separate stacked fs that points to the same file. d_canonical_path solves this problem by allowing the fs to map a dentry to a path in the lower fs. Inotify can use it to find the appropriate place to watch to be informed of all changes to a file. Change-Id: I09563baffad1711a045e45c1bd0bd8713c2cc0b6 Signed-off-by: Daniel Rosenberg --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d67ae119cf4e..ebad56e31a8c 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -161,6 +161,7 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); struct inode *(*d_select_inode)(struct dentry *, unsigned); + void (*d_canonical_path)(const struct dentry *, struct path *); } ____cacheline_aligned; /* -- cgit v1.2.3 From 3f3b4c799d2c9c706d68c2db31b332e5a548cf53 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 23 Mar 2016 08:32:23 -0700 Subject: fs: sdcardfs: Declare LOOKUP_CASE_INSENSITIVE unconditionally Attempts to build sdcardfs as module fail with fs/sdcardfs/lookup.c: In function '__sdcardfs_lookup': fs/sdcardfs/lookup.c:243:5: error: 'LOOKUP_CASE_INSENSITIVE' undeclared This occurs because the define is enclosed with #ifdef CONFIG_SDCARD_FS_CI_SEARCH. If SDCARD_FS_CI_SEARCH is configured to be built as module, this does not work. Alternatives would be to use #if IS_ENABLED(CONFIG_SDCARD_FS_CI_SEARCH), or to declare SDCARD_FS_CI_SEARCH as bool, but that does not work because the define is used unconditionally in the source. Note that LOOKUP_CASE_INSENSITIVE is only set but not evaluated in the current source code, so setting the flag has no real effect. Fixes: 84a1b7d3d312 ("Included sdcardfs source code for kernel 3.0") Cc: Daniel Rosenberg Signed-off-by: Guenter Roeck --- include/linux/namei.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index f2b8acbdb928..47b53673ec61 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -43,9 +43,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_JUMPED 0x1000 #define LOOKUP_ROOT 0x2000 #define LOOKUP_EMPTY 0x4000 -#ifdef CONFIG_SDCARD_FS_CI_SEARCH #define LOOKUP_CASE_INSENSITIVE 0x8000 -#endif extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -- cgit v1.2.3 From 7581abb2ceff034995e098de33282f4c7c8dd0c7 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 23 Mar 2016 16:39:30 -0700 Subject: sdcardfs: remove effectless config option CONFIG_SDCARD_FS_CI_SEARCH only guards a define for LOOKUP_CASE_INSENSITIVE, which is never used in the kernel. Remove both, along with the option matching that supports it. Change-Id: I363a8f31de8ee7a7a934d75300cc9ba8176e2edf Signed-off-by: Daniel Rosenberg --- include/linux/namei.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 47b53673ec61..d53c25453aca 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -43,7 +43,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_JUMPED 0x1000 #define LOOKUP_ROOT 0x2000 #define LOOKUP_EMPTY 0x4000 -#define LOOKUP_CASE_INSENSITIVE 0x8000 extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -- cgit v1.2.3 From 00c13787f8275d7ff3e232a0e06a3c26478811e0 Mon Sep 17 00:00:00 2001 From: Dmitry Shmidt Date: Tue, 19 Apr 2016 12:37:47 -0700 Subject: Revert "switch: switch class and GPIO drivers." Drivers should use extcon moving forward. Documentation/extcon/porting-android-switch-class describes how to port existing switch class drivers to extcon. This reverts commit e4b8e66e0ae2e78e913d7b86f2507fdb0aa731b4. Change-Id: I5b622c7ab4c0cb9670f8903f259a99888f503c1a --- include/linux/switch.h | 53 -------------------------------------------------- 1 file changed, 53 deletions(-) delete mode 100644 include/linux/switch.h (limited to 'include/linux') diff --git a/include/linux/switch.h b/include/linux/switch.h deleted file mode 100644 index 3e4c748e343a..000000000000 --- a/include/linux/switch.h +++ /dev/null @@ -1,53 +0,0 @@ -/* - * Switch class driver - * - * Copyright (C) 2008 Google, Inc. - * Author: Mike Lockwood - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * -*/ - -#ifndef __LINUX_SWITCH_H__ -#define __LINUX_SWITCH_H__ - -struct switch_dev { - const char *name; - struct device *dev; - int index; - int state; - - ssize_t (*print_name)(struct switch_dev *sdev, char *buf); - ssize_t (*print_state)(struct switch_dev *sdev, char *buf); -}; - -struct gpio_switch_platform_data { - const char *name; - unsigned gpio; - - /* if NULL, switch_dev.name will be printed */ - const char *name_on; - const char *name_off; - /* if NULL, "0" or "1" will be printed */ - const char *state_on; - const char *state_off; -}; - -extern int switch_dev_register(struct switch_dev *sdev); -extern void switch_dev_unregister(struct switch_dev *sdev); - -static inline int switch_get_state(struct switch_dev *sdev) -{ - return sdev->state; -} - -extern void switch_set_state(struct switch_dev *sdev, int state); - -#endif /* __LINUX_SWITCH_H__ */ -- cgit v1.2.3 From ece28ad441409646dc6330b06d347465d2730feb Mon Sep 17 00:00:00 2001 From: Amit Pundir Date: Mon, 25 Apr 2016 17:08:15 +0530 Subject: Revert "misc: uidstat: Adding uid stat driver to collect network statistics." This reverts commit 6b6d5fbf9ae567aefb58099a30bbb6d25fa8925b. Signed-off-by: Amit Pundir --- include/linux/uid_stat.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/uid_stat.h (limited to 'include/linux') diff --git a/include/linux/uid_stat.h b/include/linux/uid_stat.h deleted file mode 100644 index 6bd6c4e52d17..000000000000 --- a/include/linux/uid_stat.h +++ /dev/null @@ -1,29 +0,0 @@ -/* include/linux/uid_stat.h - * - * Copyright (C) 2008-2009 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef __uid_stat_h -#define __uid_stat_h - -/* Contains definitions for resource tracking per uid. */ - -#ifdef CONFIG_UID_STAT -int uid_stat_tcp_snd(uid_t uid, int size); -int uid_stat_tcp_rcv(uid_t uid, int size); -#else -#define uid_stat_tcp_snd(uid, size) do {} while (0); -#define uid_stat_tcp_rcv(uid, size) do {} while (0); -#endif - -#endif /* _LINUX_UID_STAT_H */ -- cgit v1.2.3 From 4b7de8375299c9f0e330ce521a956bc35bf1d12c Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Fri, 22 Apr 2016 00:00:14 -0700 Subject: vfs: change d_canonical_path to take two paths bug: 23904372 Change-Id: I4a686d64b6de37decf60019be1718e1d820193e6 Signed-off-by: Daniel Rosenberg --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ebad56e31a8c..5819e9b0ee22 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -161,7 +161,7 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); struct inode *(*d_select_inode)(struct dentry *, unsigned); - void (*d_canonical_path)(const struct dentry *, struct path *); + void (*d_canonical_path)(const struct path *, struct path *); } ____cacheline_aligned; /* -- cgit v1.2.3 From f24888af18176246638498325fb1ecd49e0ef00e Mon Sep 17 00:00:00 2001 From: Amit Pundir Date: Mon, 2 May 2016 15:32:15 +0530 Subject: Revert "mmc: Add status IRQ and status callback function to mmc platform data" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 91fa97e1e5c001d52f6c993d37be08d1e84f47b7. This patch is no longer valid. There are no users for this status irq and callback in android-4.x. The Qcom platform (mach-msm/qsd8x50, HTC Dream..) and SDCC controller (msm_sdcc) using this status IRQ and callback are dropped from mainline sometime back. 27842bb18b00 (mmc: Remove msm_sdcc driver) c0c89fafa289 (ARM: Remove mach-msm and associated ARM architecture code) Change-Id: Ia38e42a06dc184395f79c1ec1d306bf9775704d5 Signed-off-by: Amit Pundir --- include/linux/amba/mmci.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index 8bfd21c13d59..eff56cb0016a 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -40,10 +40,7 @@ struct mmci_platform_data { int gpio_wp; int gpio_cd; bool cd_invert; - unsigned int status_irq; struct embedded_sdio_data *embedded_sdio; - int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id); - }; #endif -- cgit v1.2.3 From d114f2c3570fc63019656b6870e4fcc506852334 Mon Sep 17 00:00:00 2001 From: Jack Pham Date: Wed, 23 Mar 2016 13:18:03 -0700 Subject: usb: dual-role: make stub functions inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If CONFIG_DUAL_ROLE_USB_INTF is disabled but the exported functions are referenced, the build will result in warnings such as: In file included from include/linux/usb/class-dual-role.h:112:13: warning: ‘dual_role_instance_changed’ defined but not used [-Wunused-function] These stub functions should be static inline. Change-Id: I5a9ef58dca32306fac5a4c7f28cdaa36fa8ae078 Signed-off-by: Jack Pham (cherry picked from commit 2d152dbb0743526b21d6bbefe097f874c027f860) (cherry picked from commit 8ad66cafaa10e6ba94ff79a8dbc2cc437c6bfe93) --- include/linux/usb/class-dual-role.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/class-dual-role.h b/include/linux/usb/class-dual-role.h index af42ed34944a..c6df2238012e 100644 --- a/include/linux/usb/class-dual-role.h +++ b/include/linux/usb/class-dual-role.h @@ -109,18 +109,19 @@ extern int dual_role_property_is_writeable(struct dual_role_phy_instance enum dual_role_property prop); extern void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role); #else /* CONFIG_DUAL_ROLE_USB_INTF */ -static void dual_role_instance_changed(struct dual_role_phy_instance +static inline void dual_role_instance_changed(struct dual_role_phy_instance *dual_role){} -static struct dual_role_phy_instance *__must_check +static inline struct dual_role_phy_instance *__must_check devm_dual_role_instance_register(struct device *parent, const struct dual_role_phy_desc *desc) { return ERR_PTR(-ENOSYS); } -static void devm_dual_role_instance_unregister(struct device *dev, +static inline void devm_dual_role_instance_unregister(struct device *dev, struct dual_role_phy_instance *dual_role){} -static void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role) +static inline void *dual_role_get_drvdata(struct dual_role_phy_instance + *dual_role) { return ERR_PTR(-ENOSYS); } -- cgit v1.2.3 From 259bd4cd8a4c5776e86ae1a86f1f8e1168e84212 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Thu, 17 Sep 2015 16:10:56 +0100 Subject: cpufreq: Frequency invariant scheduler load-tracking support Implements cpufreq_scale_freq_capacity() to provide the scheduler with a frequency scaling correction factor for more accurate load-tracking. The factor is: current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_freq(cpu) In fact, freq_scale should be a struct cpufreq_policy data member. But this would require that the scheduler hot path (__update_load_avg()) would have to grab the cpufreq lock. This can be avoided by using per-cpu data initialized to SCHED_CAPACITY_SCALE for freq_scale. Signed-off-by: Dietmar Eggemann --- include/linux/cpufreq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 177c7680c1a8..11c65f536b6c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -616,4 +616,7 @@ unsigned int cpufreq_generic_get(unsigned int cpu); int cpufreq_generic_init(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table, unsigned int transition_latency); + +struct sched_domain; +unsigned long cpufreq_scale_freq_capacity(struct sched_domain *sd, int cpu); #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3 From 0b3bda54d245ebcfeefc61f0ff763e76ca2a8784 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Fri, 14 Nov 2014 16:08:45 +0000 Subject: sched: Introduce energy data structures The struct sched_group_energy represents the per sched_group related data which is needed for energy aware scheduling. It contains: (1) number of elements of the idle state array (2) pointer to the idle state array which comprises 'power consumption' for each idle state (3) number of elements of the capacity state array (4) pointer to the capacity state array which comprises 'compute capacity and power consumption' tuples for each capacity state The struct sched_group obtains a pointer to a struct sched_group_energy. The function pointer sched_domain_energy_f is introduced into struct sched_domain_topology_level which will allow the arch to pass a particular struct sched_group_energy from the topology shim layer into the scheduler core. The function pointer sched_domain_energy_f has an 'int cpu' parameter since the folding of two adjacent sd levels via sd degenerate doesn't work for all sd levels. I.e. it is not possible for example to use this feature to provide per-cpu energy in sd level DIE on ARM's TC2 platform. It was discussed that the folding of sd levels approach is preferable over the cpu parameter approach, simply because the user (the arch specifying the sd topology table) can introduce less errors. But since it is not working, the 'int cpu' parameter is the only way out. It's possible to use the folding of sd levels approach for sched_domain_flags_f and the cpu parameter approach for the sched_domain_energy_f at the same time though. With the use of the 'int cpu' parameter, an extra check function has to be provided to make sure that all cpus spanned by a sched group are provisioned with the same energy data. cc: Ingo Molnar cc: Peter Zijlstra Signed-off-by: Dietmar Eggemann --- include/linux/sched.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index fa39434e3fdd..5bee272a86d8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1021,6 +1021,22 @@ struct sched_domain_attr { extern int sched_domain_level_max; +struct capacity_state { + unsigned long cap; /* compute capacity */ + unsigned long power; /* power consumption at this compute capacity */ +}; + +struct idle_state { + unsigned long power; /* power consumption in this idle state */ +}; + +struct sched_group_energy { + unsigned int nr_idle_states; /* number of idle states */ + struct idle_state *idle_states; /* ptr to idle state array */ + unsigned int nr_cap_states; /* number of capacity states */ + struct capacity_state *cap_states; /* ptr to capacity state array */ +}; + struct sched_group; struct sched_domain { @@ -1119,6 +1135,8 @@ bool cpus_share_cache(int this_cpu, int that_cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef int (*sched_domain_flags_f)(void); +typedef +const struct sched_group_energy * const(*sched_domain_energy_f)(int cpu); #define SDTL_OVERLAP 0x01 @@ -1131,6 +1149,7 @@ struct sd_data { struct sched_domain_topology_level { sched_domain_mask_f mask; sched_domain_flags_f sd_flags; + sched_domain_energy_f energy; int flags; int numa_level; struct sd_data data; -- cgit v1.2.3 From f0f739d887a4f144ab4937e619288d4cede2cc91 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Tue, 13 Jan 2015 13:50:46 +0000 Subject: sched: Introduce SD_SHARE_CAP_STATES sched_domain flag cpufreq is currently keeping it a secret which cpus are sharing clock source. The scheduler needs to know about clock domains as well to become more energy aware. The SD_SHARE_CAP_STATES domain flag indicates whether cpus belonging to the sched_domain share capacity states (P-states). There is no connection with cpufreq (yet). The flag must be set by the arch specific topology code. cc: Russell King cc: Ingo Molnar cc: Peter Zijlstra Signed-off-by: Morten Rasmussen --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5bee272a86d8..09e2d43406eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -989,6 +989,7 @@ extern void wake_up_q(struct wake_q_head *head); #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ #define SD_NUMA 0x4000 /* cross-node balancing */ +#define SD_SHARE_CAP_STATES 0x8000 /* Domain members share capacity state */ #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) -- cgit v1.2.3 From 19a5ebe13dded57ab2b04defd2e379579da05197 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Tue, 27 Jan 2015 13:48:07 +0000 Subject: sched, cpuidle: Track cpuidle state index in the scheduler The idle-state of each cpu is currently pointed to by rq->idle_state but there isn't any information in the struct cpuidle_state that can used to look up the idle-state energy model data stored in struct sched_group_energy. For this purpose is necessary to store the idle state index as well. Ideally, the idle-state data should be unified. cc: Ingo Molnar cc: Peter Zijlstra Signed-off-by: Morten Rasmussen --- include/linux/cpuidle.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 786ad32631a6..6eae1576499e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -204,7 +204,7 @@ static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, #endif /* kernel/sched/idle.c */ -extern void sched_idle_set_state(struct cpuidle_state *idle_state); +extern void sched_idle_set_state(struct cpuidle_state *idle_state, int index); extern void default_idle_call(void); #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED -- cgit v1.2.3 From d2b3db032e34938c970b148e71cc401fc4c541e8 Mon Sep 17 00:00:00 2001 From: Robin Randhawa Date: Mon, 29 Jun 2015 18:01:58 +0100 Subject: sched: Support for extracting EAS energy costs from DT This patch implements support for extracting energy cost data from DT. The data should conform to the DT bindings for energy cost data needed by EAS (energy aware scheduling). Signed-off-by: Robin Randhawa --- include/linux/sched_energy.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/linux/sched_energy.h (limited to 'include/linux') diff --git a/include/linux/sched_energy.h b/include/linux/sched_energy.h new file mode 100644 index 000000000000..a3f1627ac609 --- /dev/null +++ b/include/linux/sched_energy.h @@ -0,0 +1,36 @@ +#ifndef _LINUX_SCHED_ENERGY_H +#define _LINUX_SCHED_ENERGY_H + +#include +#include + +/* + * There doesn't seem to be an NR_CPUS style max number of sched domain + * levels so here's an arbitrary constant one for the moment. + * + * The levels alluded to here correspond to entries in struct + * sched_domain_topology_level that are meant to be populated by arch + * specific code (topology.c). + */ +#define NR_SD_LEVELS 8 + +#define SD_LEVEL0 0 +#define SD_LEVEL1 1 +#define SD_LEVEL2 2 +#define SD_LEVEL3 3 +#define SD_LEVEL4 4 +#define SD_LEVEL5 5 +#define SD_LEVEL6 6 +#define SD_LEVEL7 7 + +/* + * Convenience macro for iterating through said sd levels. + */ +#define for_each_possible_sd_level(level) \ + for (level = 0; level < NR_SD_LEVELS; level++) + +extern struct sched_group_energy *sge_array[NR_CPUS][NR_SD_LEVELS]; + +void init_sched_energy_costs(void); + +#endif -- cgit v1.2.3 From b03f1ba3d5bb9db0ca495c8c33ef88588daaae50 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Tue, 22 Sep 2015 16:47:48 +0100 Subject: cpufreq: Max freq invariant scheduler load-tracking and cpu capacity support Implements cpufreq_scale_max_freq_capacity() to provide the scheduler with a maximum frequency scaling correction factor for more accurate load-tracking and cpu capacity handling by being able to deal with frequency capping. This scaling factor describes the influence of running a cpu with a current maximum frequency lower than the absolute possible maximum frequency on load tracking and cpu capacity. The factor is: current_max_freq(cpu) << SCHED_CAPACITY_SHIFT / max_freq(cpu) In fact, max_freq_scale should be a struct cpufreq_policy data member. But this would require that the scheduler hot path (__update_load_avg()) would have to grab the cpufreq lock. This can be avoided by using per-cpu data initialized to SCHED_CAPACITY_SCALE for max_freq_scale. Signed-off-by: Dietmar Eggemann --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 11c65f536b6c..9b1d61e1f1d7 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -619,4 +619,5 @@ int cpufreq_generic_init(struct cpufreq_policy *policy, struct sched_domain; unsigned long cpufreq_scale_freq_capacity(struct sched_domain *sd, int cpu); +unsigned long cpufreq_scale_max_freq_capacity(int cpu); #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3 From c3b2e765af4af80ada13e5e34a26a28e3081dd0e Mon Sep 17 00:00:00 2001 From: Michael Turquette Date: Tue, 30 Jun 2015 12:45:27 +0100 Subject: cpufreq: introduce cpufreq_driver_is_slow Some architectures and platforms perform CPU frequency transitions through a non-blocking method, while some might block or sleep. Even when frequency transitions do not block or sleep they may be very slow. This distinction is important when trying to change frequency from a non-interruptible context in a scheduler hot path. Describe this distinction with a cpufreq driver flag, CPUFREQ_DRIVER_FAST. The default is to not have this flag set, thus erring on the side of caution. cpufreq_driver_is_slow() is also introduced in this patch. Setting the above flag will allow this function to return false. [smuckle@linaro.org: change flag/API to include drivers that are too slow for scheduler hot paths, in addition to those that block/sleep] Cc: Rafael J. Wysocki Cc: Viresh Kumar Signed-off-by: Michael Turquette Signed-off-by: Steve Muckle --- include/linux/cpufreq.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9b1d61e1f1d7..b5ef79aae048 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -160,6 +160,7 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); int cpufreq_update_policy(unsigned int cpu); bool have_governor_per_policy(void); +bool cpufreq_driver_is_slow(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); #else static inline unsigned int cpufreq_get(unsigned int cpu) @@ -317,6 +318,14 @@ struct cpufreq_driver { */ #define CPUFREQ_NEED_INITIAL_FREQ_CHECK (1 << 5) +/* + * Indicates that it is safe to call cpufreq_driver_target from + * non-interruptable context in scheduler hot paths. Drivers must + * opt-in to this flag, as the safe default is that they might sleep + * or be too slow for hot path use. + */ +#define CPUFREQ_DRIVER_FAST (1 << 6) + int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3 From a967a45c71ae8978b2c0d06ee0de23f47737cfd5 Mon Sep 17 00:00:00 2001 From: Michael Turquette Date: Tue, 30 Jun 2015 12:45:48 +0100 Subject: sched: scheduler-driven cpu frequency selection Scheduler-driven CPU frequency selection hopes to exploit both per-task and global information in the scheduler to improve frequency selection policy, achieving lower power consumption, improved responsiveness/performance, and less reliance on heuristics and tunables. For further discussion on the motivation of this integration see [0]. This patch implements a shim layer between the Linux scheduler and the cpufreq subsystem. The interface accepts capacity requests from the CFS, RT and deadline sched classes. The requests from each sched class are summed on each CPU with a margin applied to the CFS and RT capacity requests to provide some headroom. Deadline requests are expected to be precise enough given their nature to not require headroom. The maximum total capacity request for a CPU in a frequency domain drives the requested frequency for that domain. Policy is determined by both the sched classes and this shim layer. Note that this algorithm is event-driven. There is no polling loop to check cpu idle time nor any other method which is unsynchronized with the scheduler, aside from a throttling mechanism to ensure frequency changes are not attempted faster than the hardware can accommodate them. Thanks to Juri Lelli for contributing design ideas, code and test results, and to Ricky Liang for initialization and static key inc/dec fixes. [0] http://article.gmane.org/gmane.linux.kernel/1499836 [smuckle@linaro.org: various additions and fixes, revised commit text] CC: Ricky Liang Signed-off-by: Michael Turquette Signed-off-by: Juri Lelli Signed-off-by: Steve Muckle --- include/linux/cpufreq.h | 3 +++ include/linux/sched.h | 8 ++++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index b5ef79aae048..b5433349938a 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -496,6 +496,9 @@ extern struct cpufreq_governor cpufreq_gov_ondemand; #elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE) extern struct cpufreq_governor cpufreq_gov_conservative; #define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_conservative) +#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_SCHED) +extern struct cpufreq_governor cpufreq_gov_sched; +#define CPUFREQ_DEFAULT_GOVERNOR (&cpufreq_gov_sched) #endif /********************************************************************* diff --git a/include/linux/sched.h b/include/linux/sched.h index 09e2d43406eb..1460c6a4f65f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -927,6 +927,14 @@ enum cpu_idle_type { #define SCHED_CAPACITY_SHIFT 10 #define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) +struct sched_capacity_reqs { + unsigned long cfs; + unsigned long rt; + unsigned long dl; + + unsigned long total; +}; + /* * Wake-queues are lists of tasks with a pending wakeup, whose * callers have already marked the task as woken internally, -- cgit v1.2.3 From 344f4ec4293b75d83282eb13ede965995e5f312f Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Mon, 22 Jun 2015 18:11:44 +0100 Subject: sched/tune: add sysctl interface to define a boost value The current (CFS) scheduler implementation does not allow "to boost" tasks performance by running them at a higher OPP compared to the minimum required to meet their workload demands. To support tasks performance boosting the scheduler should provide a "knob" which allows to tune how much the system is going to be optimised for energy efficiency vs performance. This patch is the first of a series which provides a simple interface to define a tuning knob. One system-wide "boost" tunable is exposed via: /proc/sys/kernel/sched_cfs_boost which can be configured in the range [0..100], to define a percentage where: - 0% boost requires to operate in "standard" mode by scheduling tasks at the minimum capacities required by the workload demand - 100% boost requires to push at maximum the task performances, "regardless" of the incurred energy consumption A boost value in between these two boundaries is used to bias the power/performance trade-off, the higher the boost value the more the scheduler is biased toward performance boosting instead of energy efficiency. cc: Ingo Molnar cc: Peter Zijlstra Signed-off-by: Patrick Bellasi --- include/linux/sched/sysctl.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c9e4731cf10b..4479e48c7712 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -77,6 +77,22 @@ extern int sysctl_sched_rt_runtime; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif +#ifdef CONFIG_SCHED_TUNE +extern unsigned int sysctl_sched_cfs_boost; +int sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, + loff_t *ppos); +static inline unsigned int get_sysctl_sched_cfs_boost(void) +{ + return sysctl_sched_cfs_boost; +} +#else +static inline unsigned int get_sysctl_sched_cfs_boost(void) +{ + return 0; +} +#endif + #ifdef CONFIG_SCHED_AUTOGROUP extern unsigned int sysctl_sched_autogroup_enabled; #endif -- cgit v1.2.3 From 13001f47c9a610705219700af4636386b647e231 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Tue, 23 Jun 2015 09:17:54 +0100 Subject: sched/tune: add initial support for CGroups based boosting To support task performance boosting, the usage of a single knob has the advantage to be a simple solution, both from the implementation and the usability standpoint. However, on a real system it can be difficult to identify a single value for the knob which fits the needs of multiple different tasks. For example, some kernel threads and/or user-space background services should be better managed the "standard" way while we still want to be able to boost the performance of specific workloads. In order to improve the flexibility of the task boosting mechanism this patch is the first of a small series which extends the previous implementation to introduce a "per task group" support. This first patch introduces just the basic CGroups support, a new "schedtune" CGroups controller is added which allows to configure different boost value for different groups of tasks. To keep the implementation simple but still effective for a boosting strategy, the new controller: 1. allows only a two layer hierarchy 2. supports only a limited number of boost groups A two layer hierarchy allows to place each task either: a) in the root control group thus being subject to a system-wide boosting value b) in a child of the root group thus being subject to the specific boost value defined by that "boost group" The limited number of "boost groups" supported is mainly motivated by the observation that in a real system it could be useful to have only few classes of tasks which deserve different treatment. For example, background vs foreground or interactive vs low-priority. As an additional benefit, a limited number of boost groups allows also to have a simpler implementation especially for the code required to compute the boost value for CPUs which have runnable tasks belonging to different boost groups. cc: Tejun Heo cc: Li Zefan cc: Johannes Weiner cc: Ingo Molnar cc: Peter Zijlstra Signed-off-by: Patrick Bellasi --- include/linux/cgroup_subsys.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 1a96fdaa33d5..e133705d794a 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -26,6 +26,10 @@ SUBSYS(cpu) SUBSYS(cpuacct) #endif +#if IS_ENABLED(CONFIG_CGROUP_SCHEDTUNE) +SUBSYS(schedtune) +#endif + #if IS_ENABLED(CONFIG_BLK_CGROUP) SUBSYS(io) #endif -- cgit v1.2.3 From dd2460f3872f1b89839aedb21b999e802542c32b Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Thu, 30 Apr 2015 17:35:23 +0100 Subject: DEBUG: sched,cpufreq: add cpu_capacity change tracepoint This is useful when we want to compare cpu utilization and cpu curr capacity side by side. Signed-off-by: Juri Lelli --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1460c6a4f65f..b9b11b2dbabd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1046,6 +1046,8 @@ struct sched_group_energy { struct capacity_state *cap_states; /* ptr to capacity state array */ }; +unsigned long capacity_curr_of(int cpu); + struct sched_group; struct sched_domain { -- cgit v1.2.3 From 9d5f5d93461e2b6f697054c06ed26bc5fa4d629e Mon Sep 17 00:00:00 2001 From: Jeff Vander Stoep Date: Sun, 29 May 2016 14:22:32 -0700 Subject: FROMLIST: security,perf: Allow further restriction of perf_event_open When kernel.perf_event_open is set to 3 (or greater), disallow all access to performance events by users without CAP_SYS_ADMIN. Add a Kconfig symbol CONFIG_SECURITY_PERF_EVENTS_RESTRICT that makes this value the default. This is based on a similar feature in grsecurity (CONFIG_GRKERNSEC_PERF_HARDEN). This version doesn't include making the variable read-only. It also allows enabling further restriction at run-time regardless of whether the default is changed. https://lkml.org/lkml/2016/1/11/587 Signed-off-by: Ben Hutchings Bug: 29054680 Change-Id: Iff5bff4fc1042e85866df9faa01bce8d04335ab8 --- 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 f9828a48f16a..aa7294092e51 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -989,6 +989,11 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, loff_t *ppos); +static inline bool perf_paranoid_any(void) +{ + return sysctl_perf_event_paranoid > 2; +} + static inline bool perf_paranoid_tracepoint_raw(void) { return sysctl_perf_event_paranoid > -1; -- cgit v1.2.3 From ef51a2254d6579560bf7ff8ebbeb9b3848fe10bf Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Thu, 7 Jan 2016 16:46:14 +0100 Subject: BACKPORT: PM / sleep: Go direct_complete if driver has no callbacks Backport notes: This resolves clk warnings in the designware i2c driver on HiKey seen during suspend/resume. Cherrypicked from: aa8e54b559479d0cb7eb632ba443b8cacd20cd4b If a suitable prepare callback cannot be found for a given device and its driver has no PM callbacks at all, assume that it can go direct to complete when the system goes to sleep. The reason for this is that there's lots of devices in a system that do no PM at all and there's no reason for them to prevent their ancestors to do direct_complete if they can support it. Change-Id: Ia773afb4b266f012336b99fc8cf87453839e078b Signed-off-by: Tomeu Vizoso Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki [jstultz: Backported to 4.4] Signed-off-by: John Stultz --- include/linux/pm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 528be6787796..6a5d654f4447 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -573,6 +573,7 @@ struct dev_pm_info { struct wakeup_source *wakeup; bool wakeup_path:1; bool syscore:1; + bool no_pm_callbacks:1; /* Owned by the PM core */ #else unsigned int should_wakeup:1; #endif -- cgit v1.2.3 From 286d25ba46346d5b7125b2155ce92a63a73f4d7b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 17 Mar 2016 14:20:51 -0700 Subject: BACKPORT: timer: convert timer_slack_ns from unsigned long to u64 This backports da8b44d5a9f8bf26da637b7336508ca534d6b319 from upstream. This patchset introduces a /proc//timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc//timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz Cc: Arjan van de Ven Cc: Thomas Gleixner Cc: Oren Laadan Cc: Ruchi Kandoi Cc: Rom Lemarchand Cc: Kees Cook Cc: Android Kernel Team Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/freezer.h | 2 +- include/linux/hrtimer.h | 12 +++++++----- include/linux/poll.h | 2 +- include/linux/sched.h | 4 ++-- 4 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 6b7fd9cf5ea2..dd03e837ebb7 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -231,7 +231,7 @@ static inline long freezable_schedule_timeout_killable_unsafe(long timeout) * call this with locks held. */ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode) + u64 delta, const enum hrtimer_mode mode) { int __retval; freezer_do_not_count(); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 76dd4f0da5ca..90d8be19505b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -218,7 +218,7 @@ static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time timer->node.expires = ktime_add_safe(time, delta); } -static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta) +static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); @@ -355,7 +355,7 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long range_ns, const enum hrtimer_mode mode); + u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer on the current CPU @@ -376,7 +376,7 @@ extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { - unsigned long delta; + u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); @@ -449,10 +449,12 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); -extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, +extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, - unsigned long delta, const enum hrtimer_mode mode, int clock); + u64 delta, + const enum hrtimer_mode mode, + int clock); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ diff --git a/include/linux/poll.h b/include/linux/poll.h index c08386fb3e08..9fb4f40d9a26 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -96,7 +96,7 @@ extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state, ktime_t *expires, unsigned long slack); -extern long select_estimate_accuracy(struct timespec *tv); +extern u64 select_estimate_accuracy(struct timespec *tv); static inline int poll_schedule(struct poll_wqueues *pwq, int state) diff --git a/include/linux/sched.h b/include/linux/sched.h index fa39434e3fdd..a8012d691abf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1767,8 +1767,8 @@ struct task_struct { * time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ - unsigned long timer_slack_ns; - unsigned long default_timer_slack_ns; + u64 timer_slack_ns; + u64 default_timer_slack_ns; #ifdef CONFIG_KASAN unsigned int kasan_depth; -- cgit v1.2.3 From e6ec611adde326cd28f0692a263b31821f86b071 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Wed, 20 Jan 2016 15:00:04 -0800 Subject: BACKPORT: ptrace: use fsuid, fsgid, effective creds for fs access checks This patch backports 969624b (which backports caaee6234d0 upstream), from the v4.4-stable branch to the common/android-4.4 branch. This patch is needed to provide the PTRACE_MODE_ATTACH_FSCREDS definition which was used by the backported version of proc//timerslack_ns in change-id: Ie5799b9a3402a31f88cd46437dcda4a0e46415a7 commit caaee6234d05a58c5b4d05e7bf766131b810a657 upstream. By checking the effective credentials instead of the real UID / permitted capabilities, ensure that the calling process actually intended to use its credentials. To ensure that all ptrace checks use the correct caller credentials (e.g. in case out-of-tree code or newly added code omits the PTRACE_MODE_*CREDS flag), use two new flags and require one of them to be set. The problem was that when a privileged task had temporarily dropped its privileges, e.g. by calling setreuid(0, user_uid), with the intent to perform following syscalls with the credentials of a user, it still passed ptrace access checks that the user would not be able to pass. While an attacker should not be able to convince the privileged task to perform a ptrace() syscall, this is a problem because the ptrace access check is reused for things in procfs. In particular, the following somewhat interesting procfs entries only rely on ptrace access checks: /proc/$pid/stat - uses the check for determining whether pointers should be visible, useful for bypassing ASLR /proc/$pid/maps - also useful for bypassing ASLR /proc/$pid/cwd - useful for gaining access to restricted directories that contain files with lax permissions, e.g. in this scenario: lrwxrwxrwx root root /proc/13020/cwd -> /root/foobar drwx------ root root /root drwxr-xr-x root root /root/foobar -rw-r--r-- root root /root/foobar/secret Therefore, on a system where a root-owned mode 6755 binary changes its effective credentials as described and then dumps a user-specified file, this could be used by an attacker to reveal the memory layout of root's processes or reveal the contents of files he is not allowed to access (through /proc/$pid/cwd). [akpm@linux-foundation.org: fix warning] Signed-off-by: Jann Horn Acked-by: Kees Cook Cc: Casey Schaufler Cc: Oleg Nesterov Cc: Ingo Molnar Cc: James Morris Cc: "Serge E. Hallyn" Cc: Andy Shevchenko Cc: Andy Lutomirski Cc: Al Viro Cc: "Eric W. Biederman" Cc: Willy Tarreau Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman [jstultz: Cherry-picked for common/android-4.4] Signed-off-by: John Stultz --- include/linux/ptrace.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 061265f92876..504c98a278d4 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -57,7 +57,29 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -/* Returns true on success, false on denial. */ +#define PTRACE_MODE_FSCREDS 0x08 +#define PTRACE_MODE_REALCREDS 0x10 + +/* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ +#define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) +#define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) + +/** + * ptrace_may_access - check whether the caller is permitted to access + * a target task. + * @task: target task + * @mode: selects type of access and caller credentials + * + * Returns true on success, false on denial. + * + * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must + * be set in @mode to specify whether the access was requested through + * a filesystem syscall (should use effective capabilities and fsuid + * of the caller) or through an explicit syscall such as + * process_vm_writev or ptrace (and should use the real credentials). + */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) -- cgit v1.2.3 From 818aa36ea868ba8f2985f9ca0906fd9cba3e437d Mon Sep 17 00:00:00 2001 From: Amit Pundir Date: Sun, 31 Jul 2016 17:07:46 +0530 Subject: Revert "panic: Add board ID to panic output" This reverts commit 4e09c510185cb4db2277ce81cce81b7aa06bea45. I checked for the usage of this debug helper in AOSP common kernels as well as vendor kernels (e.g exynos, msm, mediatek, omap, tegra, x86, x86_64) hosted at https://android.googlesource.com/kernel/ and I found out that other than few fairly obsolete Omap trees (for tuna & Glass) and Exynos tree (for Manta), there is no active user of this debug helper. So we can safely remove this helper code. Signed-off-by: Amit Pundir --- include/linux/kernel.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 1eaf3d81f5c1..350dfb08aee3 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -830,8 +830,4 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } /* OTHER_WRITABLE? Generally considered a bad idea. */ \ BUILD_BUG_ON_ZERO((perms) & 2) + \ (perms)) - -/* To identify board information in panic logs, set this */ -extern char *mach_panic_string; - #endif -- cgit v1.2.3 From f3d9c312b89966b6d1ff9e4c503a7ae6d38e0176 Mon Sep 17 00:00:00 2001 From: James Carr Date: Fri, 29 Jul 2016 19:02:16 -0700 Subject: Implement memory_state_time, used by qcom,cpubw New driver memory_state_time tracks time spent in different DDR frequency and bandwidth states. Memory drivers such as qcom,cpubw can post updated state to the driver after registering a callback. Processed by a workqueue Bandwidth buckets are read in from device tree in the relevant qualcomm section, can be defined in any quantity and spacing. The data is exposed at /sys/kernel/memory_state_time, able to be read by the Android framework. Functionality is behind a config option CONFIG_MEMORY_STATE_TIME Change-Id: I4fee165571cb975fb9eacbc9aada5e6d7dd748f0 Signed-off-by: James Carr --- include/linux/memory-state-time.h | 42 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 include/linux/memory-state-time.h (limited to 'include/linux') diff --git a/include/linux/memory-state-time.h b/include/linux/memory-state-time.h new file mode 100644 index 000000000000..d2212b027866 --- /dev/null +++ b/include/linux/memory-state-time.h @@ -0,0 +1,42 @@ +/* include/linux/memory-state-time.h + * + * Copyright (C) 2016 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include + +#define UPDATE_MEMORY_STATE(BLOCK, VALUE) BLOCK->update_call(BLOCK, VALUE) + +struct memory_state_update_block; + +typedef void (*memory_state_update_fn_t)(struct memory_state_update_block *ub, + int value); + +/* This struct is populated when you pass it to a memory_state_register* + * function. The update_call function is used for an update and defined in the + * typedef memory_state_update_fn_t + */ +struct memory_state_update_block { + memory_state_update_fn_t update_call; + int id; +}; + +/* Register a frequency struct memory_state_update_block to provide updates to + * memory_state_time about frequency changes using its update_call function. + */ +struct memory_state_update_block *memory_state_register_frequency_source(void); + +/* Register a bandwidth struct memory_state_update_block to provide updates to + * memory_state_time about bandwidth changes using its update_call function. + */ +struct memory_state_update_block *memory_state_register_bandwidth_source(void); -- cgit v1.2.3 From 96b0434c25be8c73822a679be35b29ca5263baea Mon Sep 17 00:00:00 2001 From: Will Drewry Date: Wed, 9 Jun 2010 17:47:38 -0500 Subject: CHROMIUM: dm: boot time specification of dm= This is a wrap-up of three patches pending upstream approval. I'm bundling them because they are interdependent, and it'll be easier to drop it on rebase later. 1. dm: allow a dm-fs-style device to be shared via dm-ioctl Integrates feedback from Alisdair, Mike, and Kiyoshi. Two main changes occur here: - One function is added which allows for a programmatically created mapped device to be inserted into the dm-ioctl hash table. This binds the device to a name and, optional, uuid which is needed by udev and allows for userspace management of the mapped device. - dm_table_complete() was extended to handle all of the final functional changes required for the table to be operational once called. 2. init: boot to device-mapper targets without an initr* Add a dm= kernel parameter modeled after the md= parameter from do_mounts_md. It allows for device-mapper targets to be configured at boot time for use early in the boot process (as the root device or otherwise). It also replaces /dev/XXX calls with major:minor opportunistically. The format is dm="name uuid ro,table line 1,table line 2,...". The parser expects the comma to be safe to use as a newline substitute but, otherwise, uses the normal separator of space. Some attempt has been made to make it forgiving of additional spaces (using skip_spaces()). A mapped device created during boot will be assigned a minor of 0 and may be access via /dev/dm-0. An example dm-linear root with no uuid may look like: root=/dev/dm-0 dm="lroot none ro, 0 4096 linear /dev/ubdb 0, 4096 4096 linear /dv/ubdc 0" Once udev is started, /dev/dm-0 will become /dev/mapper/lroot. Older upstream threads: http://marc.info/?l=dm-devel&m=127429492521964&w=2 http://marc.info/?l=dm-devel&m=127429499422096&w=2 http://marc.info/?l=dm-devel&m=127429493922000&w=2 Latest upstream threads: https://patchwork.kernel.org/patch/104859/ https://patchwork.kernel.org/patch/104860/ https://patchwork.kernel.org/patch/104861/ Bug: 27175947 Signed-off-by: Will Drewry Review URL: http://codereview.chromium.org/2020011 Change-Id: I92bd53432a11241228d2e5ac89a3b20d19b05a31 --- include/linux/device-mapper.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ec1c61c87d89..87afa0552398 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -380,6 +380,12 @@ void dm_put(struct mapped_device *md); void dm_set_mdptr(struct mapped_device *md, void *ptr); void *dm_get_mdptr(struct mapped_device *md); +/* + * Export the device via the ioctl interface (uses mdptr). + */ +int dm_ioctl_export(struct mapped_device *md, const char *name, + const char *uuid); + /* * A device can still be used while suspended, but I/O is deferred. */ -- cgit v1.2.3 From 3a400abdc57e047786d0b35d39617a794e2bb97e Mon Sep 17 00:00:00 2001 From: Joseph Lo Date: Mon, 22 Apr 2013 14:39:18 +0800 Subject: CHROMIUM: sched: update the average of nr_running Doing a Exponential moving average per nr_running++/-- does not guarantee a fixed sample rate which induces errors if there are lots of threads being enqueued/dequeued from the rq (Linpack mt). Instead of keeping track of the avg, the scheduler now keeps track of the integral of nr_running and allows the readers to perform filtering on top. Original-author: Sai Charan Gurrappadi Change-Id: Id946654f32fa8be0eaf9d8fa7c9a8039b5ef9fab Signed-off-by: Joseph Lo Signed-off-by: Andrew Bresticker Reviewed-on: https://chromium-review.googlesource.com/174694 Reviewed-on: https://chromium-review.googlesource.com/272853 [jstultz: fwdported to 4.4] Signed-off-by: John Stultz --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b9b11b2dbabd..ee59abcab30d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -173,6 +173,9 @@ extern bool single_task_running(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); +#ifdef CONFIG_CPU_QUIET +extern u64 nr_running_integral(unsigned int cpu); +#endif extern void calc_global_load(unsigned long ticks); -- cgit v1.2.3 From 765c2ab363a02a71f9ef4c55a7f598e3dd401e0b Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 22 Jul 2016 11:35:59 +0100 Subject: FIXUP: sched: fix build for non-SMP target Currently the build for a single-core (e.g. user-mode) Linux is broken and this configuration is required (at least) to run some network tests. The main issues for the current code support on single-core systems are: 1. {se,rq}::sched_avg is not available nor maintained for !SMP systems This means that load and utilisation signals are NOT available in single core systems. All the EAS code depends on these signals. 2. sched_group_energy is also SMP dependant. Again this means that all the EAS setup and preparation code (energyn model initialization) has to be properly guarded/disabled for !SMP systems. 3. SchedFreq depends on utilization signal, which is not available on !SMP systems. 4. SchedTune is useless on unicore systems if SchedFreq is not available. 5. WALT machinery is not required on single-core systems. This patch addresses all these issues by enforcing some constraints for single-core systems: a) WALT, SchedTune and SchedTune are now dependant on SMP b) The default governor for !SMP systems is INTERACTIVE c) The energy model initialisation/build functions are d) Other minor code re-arrangements and CONFIG_SMP guarding to enable single core builds. Signed-off-by: Patrick Bellasi --- include/linux/sched_energy.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched_energy.h b/include/linux/sched_energy.h index a3f1627ac609..1daf3e1f98a7 100644 --- a/include/linux/sched_energy.h +++ b/include/linux/sched_energy.h @@ -29,8 +29,16 @@ #define for_each_possible_sd_level(level) \ for (level = 0; level < NR_SD_LEVELS; level++) +#ifdef CONFIG_SMP + extern struct sched_group_energy *sge_array[NR_CPUS][NR_SD_LEVELS]; void init_sched_energy_costs(void); +#else + +#define init_sched_energy_costs() do { } while (0) + +#endif /* CONFIG_SMP */ + #endif -- cgit v1.2.3 From 2e9abbc942e6211f9ac4dadb14debc39bb9d1418 Mon Sep 17 00:00:00 2001 From: Srinath Sridharan Date: Thu, 14 Jul 2016 09:57:29 +0100 Subject: sched: EAS: take cstate into account when selecting idle core Introduce a new sysctl for this option, 'sched_cstate_aware'. When this is enabled, select_idle_sibling in CFS is modified to choose the idle CPU in the sibling group which has the lowest idle state index - idle state indexes are assumed to increase as sleep depth and hence wakeup latency increase. In this way, we attempt to minimise wakeup latency when an idle CPU is required. Signed-off-by: Srinath Sridharan Includes: sched: EAS: fix select_idle_sibling when sysctl_sched_cstate_aware is enabled, best_idle cpu will not be chosen in the original flow because it will goto done directly Bug: 30107557 Change-Id: Ie09c2e3960cafbb976f8d472747faefab3b4d6ac Signed-off-by: martin_liu --- include/linux/sched/sysctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 4479e48c7712..7d021393b0da 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -39,6 +39,7 @@ extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_child_runs_first; +extern unsigned int sysctl_sched_cstate_aware; enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, -- cgit v1.2.3 From 4a5e890ec60d2e341fa560d8149997f5f0c48d67 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Fri, 29 Jul 2016 14:04:11 +0100 Subject: sched/fair: add tunable to force selection at cpu granularity EAS assumes that clusters with smaller capacity cores are more energy-efficient. This may not be true on non-big-little devices, so EAS can make incorrect cluster selections when finding a CPU to wake. The "sched_is_big_little" hint can be used to cause a cpu-based selection instead of cluster-based selection. This change incorporates the addition of the sync hint enable patch EAS did not honour synchronous wakeup hints, a new sysctl is created to ask EAS to use this information when selecting a CPU. The control is called "sched_sync_hint_enable". Also contains: EAS: sched/fair: for SMP bias toward idle core with capacity For SMP devices, on wakeup bias towards idle cores that have capacity vs busy devices that need a higher OPP eas: favor idle cpus for boosted tasks BUG: 29533997 BUG: 29512132 Change-Id: I0cc9a1b1b88fb52916f18bf2d25715bdc3634f9c Signed-off-by: Juri Lelli Signed-off-by: Srinath Sridharan eas/sched/fair: Favoring busy cpus with low OPPs BUG: 29533997 BUG: 29512132 Change-Id: I9305b3239698d64278db715a2e277ea0bb4ece79 Signed-off-by: Juri Lelli --- include/linux/sched/sysctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 7d021393b0da..4883dcf3e1a9 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -39,6 +39,8 @@ extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_child_runs_first; +extern unsigned int sysctl_sched_is_big_little; +extern unsigned int sysctl_sched_sync_hint_enable; extern unsigned int sysctl_sched_cstate_aware; enum sched_tunable_scaling { -- cgit v1.2.3 From c50cc2299cb1a9ae769c955f5dd09a9648b1600e Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Fri, 11 Mar 2016 16:44:16 -0800 Subject: sched/fair: add tunable to set initial task load The choice of initial task load upon fork has a large influence on CPU and OPP selection when scheduler-driven DVFS is in use. Make this tuneable by adding a new sysctl "sched_initial_task_util". If the sched governor is not used, the default remains at SCHED_LOAD_SCALE Otherwise, the value from the sysctl is used. This defaults to 0. Signed-off-by: "Todd Kjos " --- include/linux/sched/sysctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 4883dcf3e1a9..2834841c507e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -41,6 +41,7 @@ extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_child_runs_first; extern unsigned int sysctl_sched_is_big_little; extern unsigned int sysctl_sched_sync_hint_enable; +extern unsigned int sysctl_sched_initial_task_util; extern unsigned int sysctl_sched_cstate_aware; enum sched_tunable_scaling { -- cgit v1.2.3 From efb86bd08a2e9217d0b3c33753cf63d27e7c86da Mon Sep 17 00:00:00 2001 From: Srivatsa Vaddagiri Date: Tue, 31 May 2016 09:08:38 -0700 Subject: sched: Introduce Window Assisted Load Tracking (WALT) use a window based view of time in order to track task demand and CPU utilization in the scheduler. Window Assisted Load Tracking (WALT) implementation credits: Srivatsa Vaddagiri, Steve Muckle, Syed Rameez Mustafa, Joonwoo Park, Pavan Kumar Kondeti, Olav Haugan 2016-03-06: Integration with EAS/refactoring by Vikram Mulukutla and Todd Kjos Change-Id: I21408236836625d4e7d7de1843d20ed5ff36c708 Includes fixes for issues: eas/walt: Use walt_ktime_clock() instead of ktime_get_ns() to avoid a race resulting in watchdog resets BUG: 29353986 Change-Id: Ic1820e22a136f7c7ebd6f42e15f14d470f6bbbdb Handle walt accounting anomoly during resume During resume, there is a corner case where on wakeup, a task's prev_runnable_sum can go negative. This is a workaround that fixes the condition and warns (instead of crashing). BUG: 29464099 Change-Id: I173e7874324b31a3584435530281708145773508 Signed-off-by: Todd Kjos Signed-off-by: Srinath Sridharan Signed-off-by: Juri Lelli [jstultz: fwdported to 4.4] Signed-off-by: John Stultz --- include/linux/sched.h | 53 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched/sysctl.h | 5 +++++ 2 files changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ee59abcab30d..ce8db12f9e72 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -317,6 +317,15 @@ extern char ___assert_task_state[1 - 2*!!( /* Task command name length */ #define TASK_COMM_LEN 16 +enum task_event { + PUT_PREV_TASK = 0, + PICK_NEXT_TASK = 1, + TASK_WAKE = 2, + TASK_MIGRATE = 3, + TASK_UPDATE = 4, + IRQ_UPDATE = 5, +}; + #include /* @@ -1274,6 +1283,41 @@ struct sched_statistics { }; #endif +#ifdef CONFIG_SCHED_WALT +#define RAVG_HIST_SIZE_MAX 5 + +/* ravg represents frequency scaled cpu-demand of tasks */ +struct ravg { + /* + * 'mark_start' marks the beginning of an event (task waking up, task + * starting to execute, task being preempted) within a window + * + * 'sum' represents how runnable a task has been within current + * window. It incorporates both running time and wait time and is + * frequency scaled. + * + * 'sum_history' keeps track of history of 'sum' seen over previous + * RAVG_HIST_SIZE windows. Windows where task was entirely sleeping are + * ignored. + * + * 'demand' represents maximum sum seen over previous + * sysctl_sched_ravg_hist_size windows. 'demand' could drive frequency + * demand for tasks. + * + * 'curr_window' represents task's contribution to cpu busy time + * statistics (rq->curr_runnable_sum) in current window + * + * 'prev_window' represents task's contribution to cpu busy time + * statistics (rq->prev_runnable_sum) in previous window + */ + u64 mark_start; + u32 sum, demand; + u32 sum_history[RAVG_HIST_SIZE_MAX]; + u32 curr_window, prev_window; + u16 active_windows; +}; +#endif + struct sched_entity { struct load_weight load; /* for load-balancing */ struct rb_node run_node; @@ -1431,6 +1475,15 @@ struct task_struct { const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; +#ifdef CONFIG_SCHED_WALT + struct ravg ravg; + /* + * 'init_load_pct' represents the initial task load assigned to children + * of this task + */ + u32 init_load_pct; +#endif + #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 2834841c507e..710f58a28d63 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -43,6 +43,11 @@ extern unsigned int sysctl_sched_is_big_little; extern unsigned int sysctl_sched_sync_hint_enable; extern unsigned int sysctl_sched_initial_task_util; extern unsigned int sysctl_sched_cstate_aware; +#ifdef CONFIG_SCHED_WALT +extern unsigned int sysctl_sched_use_walt_cpu_util; +extern unsigned int sysctl_sched_use_walt_task_util; +extern unsigned int sysctl_sched_walt_init_task_load_pct; +#endif enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, -- cgit v1.2.3 From 519c62750eb6ebbb5783315272398ced72d7a036 Mon Sep 17 00:00:00 2001 From: Srinath Sridharan Date: Fri, 22 Jul 2016 13:21:15 +0100 Subject: sched/walt: Accounting for number of irqs pending on each core Schedules on a core whose irq count is less than a threshold. Improves I/O performance of EAS. Change-Id: I08ff7dd0d22502a0106fc636b1af2e6fe9e758b5 --- include/linux/sched/sysctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 710f58a28d63..d68e88c9d4d7 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -47,6 +47,7 @@ extern unsigned int sysctl_sched_cstate_aware; extern unsigned int sysctl_sched_use_walt_cpu_util; extern unsigned int sysctl_sched_use_walt_task_util; extern unsigned int sysctl_sched_walt_init_task_load_pct; +extern unsigned int sysctl_sched_walt_cpu_high_irqload; #endif enum sched_tunable_scaling { -- cgit v1.2.3 From 142b2acc79777f3cac93144d7ebf9caa53e97f9b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 14 Jan 2016 15:21:40 -0800 Subject: vmstat: make vmstat_updater deferrable again and shut down on idle Currently the vmstat updater is not deferrable as a result of commit ba4877b9ca51 ("vmstat: do not use deferrable delayed work for vmstat_update"). This in turn can cause multiple interruptions of the applications because the vmstat updater may run at Make vmstate_update deferrable again and provide a function that folds the differentials when the processor is going to idle mode thus addressing the issue of the above commit in a clean way. Note that the shepherd thread will continue scanning the differentials from another processor and will reenable the vmstat workers if it detects any changes. Change-Id: Idf256cfacb40b4dc8dbb6795cf06b34e8fec7a06 Fixes: ba4877b9ca51 ("vmstat: do not use deferrable delayed work for vmstat_update") Signed-off-by: Christoph Lameter Cc: Michal Hocko Cc: Johannes Weiner Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Git-commit: 0eb77e9880321915322d42913c3b53241739c8aa [shashim@codeaurora.org: resolve minor merge conflicts] Signed-off-by: Shiraz Hashim [jstultz: fwdport to 4.4] Signed-off-by: John Stultz --- include/linux/vmstat.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 3e5d9075960f..73fae8c4a5fb 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -189,6 +189,7 @@ extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); +void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); @@ -249,6 +250,7 @@ static inline void __dec_zone_page_state(struct page *page, static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } +static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } -- cgit v1.2.3 From 8d525c512280bb7d8218fd59c04de985b1886eca Mon Sep 17 00:00:00 2001 From: Mohan Srinivasan Date: Tue, 16 Aug 2016 15:51:34 -0700 Subject: Android: MMC/UFS IO Latency Histograms. This patch adds a new sysfs node (latency_hist) and reports IO (svc time) latency histograms. Disabled by default, can be enabled by echoing 0 into latency_hist, stats can be cleared by writing 2 into latency_hist. Bug: 30677035 Change-Id: I625938135ea33e6e87cf6af1fc7edc136d8b4b32 Signed-off-by: Mohan Srinivasan --- include/linux/blkdev.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mmc/core.h | 2 ++ include/linux/mmc/host.h | 4 +++ 3 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c70e3588a48c..faf2c0093527 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -197,6 +197,9 @@ struct request { /* for bidi */ struct request *next_rq; + + ktime_t lat_hist_io_start; + int lat_hist_enabled; }; static inline unsigned short req_get_ioprio(struct request *req) @@ -1645,6 +1648,79 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); extern long bdev_direct_access(struct block_device *, sector_t, void __pmem **addr, unsigned long *pfn, long size); + +/* + * X-axis for IO latency histogram support. + */ +static const u_int64_t latency_x_axis_us[] = { + 100, + 200, + 300, + 400, + 500, + 600, + 700, + 800, + 900, + 1000, + 1200, + 1400, + 1600, + 1800, + 2000, + 2500, + 3000, + 4000, + 5000, + 6000, + 7000, + 9000, + 10000 +}; + +#define BLK_IO_LAT_HIST_DISABLE 0 +#define BLK_IO_LAT_HIST_ENABLE 1 +#define BLK_IO_LAT_HIST_ZERO 2 + +struct io_latency_state { + u_int64_t latency_y_axis_read[ARRAY_SIZE(latency_x_axis_us) + 1]; + u_int64_t latency_reads_elems; + u_int64_t latency_y_axis_write[ARRAY_SIZE(latency_x_axis_us) + 1]; + u_int64_t latency_writes_elems; +}; + +static inline void +blk_update_latency_hist(struct io_latency_state *s, + int read, + u_int64_t delta_us) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(latency_x_axis_us); i++) { + if (delta_us < (u_int64_t)latency_x_axis_us[i]) { + if (read) + s->latency_y_axis_read[i]++; + else + s->latency_y_axis_write[i]++; + break; + } + } + if (i == ARRAY_SIZE(latency_x_axis_us)) { + /* Overflowed the histogram */ + if (read) + s->latency_y_axis_read[i]++; + else + s->latency_y_axis_write[i]++; + } + if (read) + s->latency_reads_elems++; + else + s->latency_writes_elems++; +} + +void blk_zero_latency_hist(struct io_latency_state *s); +ssize_t blk_latency_hist_show(struct io_latency_state *s, char *buf); + #else /* CONFIG_BLOCK */ struct block_device; diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 37967b6da03c..3349f0676acb 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -136,6 +136,8 @@ struct mmc_request { struct completion completion; void (*done)(struct mmc_request *);/* completion function */ struct mmc_host *host; + ktime_t io_start; + int lat_hist_enabled; }; struct mmc_card; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 40025b28c1fb..e4862f7cdede 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -379,6 +380,9 @@ struct mmc_host { } embedded_sdio_data; #endif + int latency_hist_enabled; + struct io_latency_state io_lat_s; + unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.3 From 1c6df5fdcb19a03fb6b652090b4b968a6377fb14 Mon Sep 17 00:00:00 2001 From: Mohamad Ayyash Date: Thu, 25 Aug 2016 00:59:21 +0000 Subject: Revert "Android: MMC/UFS IO Latency Histograms." This reverts commit 8d525c512280bb7d8218fd59c04de985b1886eca. Change-Id: I69350b98d9de9b1c9f591e03a90f133e328ba72a --- include/linux/blkdev.h | 76 ------------------------------------------------ include/linux/mmc/core.h | 2 -- include/linux/mmc/host.h | 4 --- 3 files changed, 82 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index faf2c0093527..c70e3588a48c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -197,9 +197,6 @@ struct request { /* for bidi */ struct request *next_rq; - - ktime_t lat_hist_io_start; - int lat_hist_enabled; }; static inline unsigned short req_get_ioprio(struct request *req) @@ -1648,79 +1645,6 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); extern long bdev_direct_access(struct block_device *, sector_t, void __pmem **addr, unsigned long *pfn, long size); - -/* - * X-axis for IO latency histogram support. - */ -static const u_int64_t latency_x_axis_us[] = { - 100, - 200, - 300, - 400, - 500, - 600, - 700, - 800, - 900, - 1000, - 1200, - 1400, - 1600, - 1800, - 2000, - 2500, - 3000, - 4000, - 5000, - 6000, - 7000, - 9000, - 10000 -}; - -#define BLK_IO_LAT_HIST_DISABLE 0 -#define BLK_IO_LAT_HIST_ENABLE 1 -#define BLK_IO_LAT_HIST_ZERO 2 - -struct io_latency_state { - u_int64_t latency_y_axis_read[ARRAY_SIZE(latency_x_axis_us) + 1]; - u_int64_t latency_reads_elems; - u_int64_t latency_y_axis_write[ARRAY_SIZE(latency_x_axis_us) + 1]; - u_int64_t latency_writes_elems; -}; - -static inline void -blk_update_latency_hist(struct io_latency_state *s, - int read, - u_int64_t delta_us) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(latency_x_axis_us); i++) { - if (delta_us < (u_int64_t)latency_x_axis_us[i]) { - if (read) - s->latency_y_axis_read[i]++; - else - s->latency_y_axis_write[i]++; - break; - } - } - if (i == ARRAY_SIZE(latency_x_axis_us)) { - /* Overflowed the histogram */ - if (read) - s->latency_y_axis_read[i]++; - else - s->latency_y_axis_write[i]++; - } - if (read) - s->latency_reads_elems++; - else - s->latency_writes_elems++; -} - -void blk_zero_latency_hist(struct io_latency_state *s); -ssize_t blk_latency_hist_show(struct io_latency_state *s, char *buf); - #else /* CONFIG_BLOCK */ struct block_device; diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 3349f0676acb..37967b6da03c 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -136,8 +136,6 @@ struct mmc_request { struct completion completion; void (*done)(struct mmc_request *);/* completion function */ struct mmc_host *host; - ktime_t io_start; - int lat_hist_enabled; }; struct mmc_card; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index e4862f7cdede..40025b28c1fb 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -16,7 +16,6 @@ #include #include #include -#include #include #include @@ -380,9 +379,6 @@ struct mmc_host { } embedded_sdio_data; #endif - int latency_hist_enabled; - struct io_latency_state io_lat_s; - unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.3 From 3228c5eb7af2b4cb981706b88ed3c3e81ab8e80a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 9 Aug 2016 08:44:12 -0700 Subject: RFC: FROMLIST: locking/percpu-rwsem: Optimize readers and reduce global impact Currently the percpu-rwsem switches to (global) atomic ops while a writer is waiting; which could be quite a while and slows down releasing the readers. This patch cures this problem by ordering the reader-state vs reader-count (see the comments in __percpu_down_read() and percpu_down_write()). This changes a global atomic op into a full memory barrier, which doesn't have the global cacheline contention. This also enables using the percpu-rwsem with rcu_sync disabled in order to bias the implementation differently, reducing the writer latency by adding some cost to readers. Mailing-list-URL: https://lkml.org/lkml/2016/8/9/181 Cc: Paul McKenney Reviewed-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) [jstultz: Backported to 4.4] Change-Id: I8ea04b4dca2ec36f1c2469eccafde1423490572f Signed-off-by: John Stultz --- include/linux/percpu-rwsem.h | 84 +++++++++++++++++++++++++++++++++++++++----- 1 file changed, 75 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index c2fa3ecb0dce..146efefde2a1 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -10,30 +10,96 @@ struct percpu_rw_semaphore { struct rcu_sync rss; - unsigned int __percpu *fast_read_ctr; + unsigned int __percpu *read_count; struct rw_semaphore rw_sem; - atomic_t slow_read_ctr; - wait_queue_head_t write_waitq; + wait_queue_head_t writer; + int readers_block; }; -extern void percpu_down_read(struct percpu_rw_semaphore *); -extern int percpu_down_read_trylock(struct percpu_rw_semaphore *); -extern void percpu_up_read(struct percpu_rw_semaphore *); +extern int __percpu_down_read(struct percpu_rw_semaphore *, int); +extern void __percpu_up_read(struct percpu_rw_semaphore *); + +static inline void percpu_down_read(struct percpu_rw_semaphore *sem) +{ + might_sleep(); + + rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 0, _RET_IP_); + + preempt_disable(); + /* + * We are in an RCU-sched read-side critical section, so the writer + * cannot both change sem->state from readers_fast and start checking + * counters while we are here. So if we see !sem->state, we know that + * the writer won't be checking until we're past the preempt_enable() + * and that one the synchronize_sched() is done, the writer will see + * anything we did within this RCU-sched read-size critical section. + */ + __this_cpu_inc(*sem->read_count); + if (unlikely(!rcu_sync_is_idle(&sem->rss))) + __percpu_down_read(sem, false); /* Unconditional memory barrier */ + preempt_enable(); + /* + * The barrier() from preempt_enable() prevents the compiler from + * bleeding the critical section out. + */ +} + +static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem) +{ + int ret = 1; + + preempt_disable(); + /* + * Same as in percpu_down_read(). + */ + __this_cpu_inc(*sem->read_count); + if (unlikely(!rcu_sync_is_idle(&sem->rss))) + ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ + preempt_enable(); + /* + * The barrier() from preempt_enable() prevents the compiler from + * bleeding the critical section out. + */ + + if (ret) + rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 1, _RET_IP_); + + return ret; +} + +static inline void percpu_up_read(struct percpu_rw_semaphore *sem) +{ + /* + * The barrier() in preempt_disable() prevents the compiler from + * bleeding the critical section out. + */ + preempt_disable(); + /* + * Same as in percpu_down_read(). + */ + if (likely(rcu_sync_is_idle(&sem->rss))) + __this_cpu_dec(*sem->read_count); + else + __percpu_up_read(sem); /* Unconditional memory barrier */ + preempt_enable(); + + rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); +} extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); + extern void percpu_free_rwsem(struct percpu_rw_semaphore *); -#define percpu_init_rwsem(brw) \ +#define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ - __percpu_init_rwsem(brw, #brw, &rwsem_key); \ + __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) - #define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, -- cgit v1.2.3 From 0c3240a1ef2e840aaa17f593326e3642bc857aa7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Aug 2016 18:54:13 +0200 Subject: RFC: FROMLIST: cgroup: avoid synchronize_sched() in __cgroup_procs_write() The current percpu-rwsem read side is entirely free of serializing insns at the cost of having a synchronize_sched() in the write path. The latency of the synchronize_sched() is too high for cgroups. The commit 1ed1328792ff talks about the write path being a fairly cold path but this is not the case for Android which moves task to the foreground cgroup and back around binder IPC calls from foreground processes to background processes, so it is significantly hotter than human initiated operations. Switch cgroup_threadgroup_rwsem into the slow mode for now to avoid the problem, hopefully it should not be that slow after another commit 80127a39681b ("locking/percpu-rwsem: Optimize readers and reduce global impact"). We could just add rcu_sync_enter() into cgroup_init() but we do not want another synchronize_sched() at boot time, so this patch adds the new helper which doesn't block but currently can only be called before the first use. Cc: Tejun Heo Cc: Paul McKenney Reported-by: John Stultz Reported-by: Dmitry Shmidt Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Oleg Nesterov [jstultz: backported to 4.4] Change-Id: I34aa9c394d3052779b56976693e96d861bd255f2 Mailing-list-URL: https://lkml.org/lkml/2016/8/11/557 Signed-off-by: John Stultz --- include/linux/rcu_sync.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h index a63a33e6196e..ece7ed9a4a70 100644 --- a/include/linux/rcu_sync.h +++ b/include/linux/rcu_sync.h @@ -59,6 +59,7 @@ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) } extern void rcu_sync_init(struct rcu_sync *, enum rcu_sync_type); +extern void rcu_sync_enter_start(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); -- cgit v1.2.3 From 8ac959cc06c8715cdc64aa88993b3a8b1ef61eaa Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 17 Dec 2015 09:57:27 -0800 Subject: UPSTREAM: Add 'unsafe' user access functions for batched accesses The naming is meant to discourage random use: the helper functions are not really any more "unsafe" than the traditional double-underscore functions (which need the address range checking), but they do need even more infrastructure around them, and should not be used willy-nilly. In addition to checking the access range, these user access functions require that you wrap the user access with a "user_acess_{begin,end}()" around it. That allows architectures that implement kernel user access control (x86: SMAP, arm64: PAN) to do the user access control in the wrapping user_access_begin/end part, and then batch up the actual user space accesses using the new interfaces. The main (and hopefully only) use for these are for core generic access helpers, initially just the generic user string functions (strnlen_user() and strncpy_from_user()). Signed-off-by: Linus Torvalds Change-Id: Ic64efea41f97171bdbdabe3e531489aebd9b6fac (cherry picked from commit 5b24a7a2aa2040c8c50c3b71122901d01661ff78) Signed-off-by: Sami Tolvanen --- include/linux/uaccess.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 558129af828a..349557825428 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -111,4 +111,11 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #define probe_kernel_address(addr, retval) \ probe_kernel_read(&retval, addr, sizeof(retval)) +#ifndef user_access_begin +#define user_access_begin() do { } while (0) +#define user_access_end() do { } while (0) +#define unsafe_get_user(x, ptr) __get_user(x, ptr) +#define unsafe_put_user(x, ptr) __put_user(x, ptr) +#endif + #endif /* __LINUX_UACCESS_H__ */ -- cgit v1.2.3 From 5f1b3400f0ccc2368dc444b5d9a7c93be2e700da Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 8 Aug 2016 13:02:01 -0700 Subject: UPSTREAM: unsafe_[get|put]_user: change interface to use a error target label When I initially added the unsafe_[get|put]_user() helpers in commit 5b24a7a2aa20 ("Add 'unsafe' user access functions for batched accesses"), I made the mistake of modeling the interface on our traditional __[get|put]_user() functions, which return zero on success, or -EFAULT on failure. That interface is fairly easy to use, but it's actually fairly nasty for good code generation, since it essentially forces the caller to check the error value for each access. In particular, since the error handling is already internally implemented with an exception handler, and we already use "asm goto" for various other things, we could fairly easily make the error cases just jump directly to an error label instead, and avoid the need for explicit checking after each operation. So switch the interface to pass in an error label, rather than checking the error value in the caller. Best do it now before we start growing more users (the signal handling code in particular would be a good place to use the new interface). So rather than if (unsafe_get_user(x, ptr)) ... handle error .. the interface is now unsafe_get_user(x, ptr, label); where an error during the user mode fetch will now just cause a jump to 'label' in the caller. Right now the actual _implementation_ of this all still ends up being a "if (err) goto label", and does not take advantage of any exception label tricks, but for "unsafe_put_user()" in particular it should be fairly straightforward to convert to using the exception table model. Note that "unsafe_get_user()" is much harder to convert to a clever exception table model, because current versions of gcc do not allow the use of "asm goto" (for the exception) with output values (for the actual value to be fetched). But that is hopefully not a limitation in the long term. [ Also note that it might be a good idea to switch unsafe_get_user() to actually _return_ the value it fetches from user space, but this commit only changes the error handling semantics ] Signed-off-by: Linus Torvalds Change-Id: Ib905a84a04d46984320f6fd1056da4d72f3d6b53 (cherry picked from commit 1bd4403d86a1c06cb6cc9ac87664a0c9d3413d51) Signed-off-by: Sami Tolvanen --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 349557825428..f30c187ed785 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -114,8 +114,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #ifndef user_access_begin #define user_access_begin() do { } while (0) #define user_access_end() do { } while (0) -#define unsafe_get_user(x, ptr) __get_user(x, ptr) -#define unsafe_put_user(x, ptr) __put_user(x, ptr) +#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) +#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) #endif #endif /* __LINUX_UACCESS_H__ */ -- cgit v1.2.3 From 1e701cdc5bbce1f5561ee25ff8709a18dc0b2282 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 19 Jul 2016 15:00:04 -0700 Subject: UPSTREAM: mm: Add is_migrate_cma_page Code such as hardened user copy[1] needs a way to tell if a page is CMA or not. Add is_migrate_cma_page in a similar way to is_migrate_isolate_page. [1]http://article.gmane.org/gmane.linux.kernel.mm/155238 Signed-off-by: Laura Abbott Signed-off-by: Kees Cook Change-Id: I1f9aa13d8d063038fa70b93282a836648fbb4f6d (cherry picked from commit 7c15d9bb8231f998ae7dc0b72415f5215459f7fb) Signed-off-by: Sami Tolvanen --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e23a9e704536..bab4053fb795 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -65,8 +65,10 @@ enum { #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false +# define is_migrate_cma_page(_page) false #endif #define for_each_migratetype_order(order, type) \ -- cgit v1.2.3 From c30d7340ee0b167a45cd8d6d5c48add8f62db9a5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 12 Jul 2016 16:19:48 -0700 Subject: BACKPORT: mm: Implement stack frame object validation This creates per-architecture function arch_within_stack_frames() that should validate if a given object is contained by a kernel stack frame. Initial implementation is on x86. This is based on code from PaX. Signed-off-by: Kees Cook Change-Id: I1f3b299bb8991d65dcdac6af85d633d4b7776df1 (cherry picked from commit 0f60a8efe4005ab5e65ce000724b04d4ca04a199) Signed-off-by: Sami Tolvanen --- include/linux/thread_info.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index ff307b548ed3..5ecb68e86968 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -145,6 +145,15 @@ static inline bool test_and_clear_restore_sigmask(void) #error "no set_restore_sigmask() provided and default one won't work" #endif +#ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ + return 0; +} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ -- cgit v1.2.3 From d677b3104d3c8e927211f20083a6c2e97e003b87 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 7 Jun 2016 11:05:33 -0700 Subject: BACKPORT: mm: Hardened usercopy This is the start of porting PAX_USERCOPY into the mainline kernel. This is the first set of features, controlled by CONFIG_HARDENED_USERCOPY. The work is based on code by PaX Team and Brad Spengler, and an earlier port from Casey Schaufler. Additional non-slab page tests are from Rik van Riel. This patch contains the logic for validating several conditions when performing copy_to_user() and copy_from_user() on the kernel object being copied to/from: - address range doesn't wrap around - address range isn't NULL or zero-allocated (with a non-zero copy size) - if on the slab allocator: - object size must be less than or equal to copy size (when check is implemented in the allocator, which appear in subsequent patches) - otherwise, object must not span page allocations (excepting Reserved and CMA ranges) - if on the stack - object must not extend before/after the current process stack - object must be contained by a valid stack frame (when there is arch/build support for identifying stack frames) - object must not overlap with kernel text Signed-off-by: Kees Cook Tested-by: Valdis Kletnieks Tested-by: Michael Ellerman Change-Id: Iff3b5f1ddb04acd99ccf9a9046c7797363962b2a (cherry picked from commit f5509cc18daa7f82bcc553be70df2117c8eedc16) Signed-off-by: Sami Tolvanen --- include/linux/slab.h | 12 ++++++++++++ include/linux/thread_info.h | 15 +++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2037a861e367..4ef384b172e0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -144,6 +144,18 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR +const char *__check_heap_object(const void *ptr, unsigned long n, + struct page *page); +#else +static inline const char *__check_heap_object(const void *ptr, + unsigned long n, + struct page *page) +{ + return NULL; +} +#endif + /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 5ecb68e86968..0ae29ff9ccfd 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -154,6 +154,21 @@ static inline int arch_within_stack_frames(const void * const stack, } #endif +#ifdef CONFIG_HARDENED_USERCOPY +extern void __check_object_size(const void *ptr, unsigned long n, + bool to_user); + +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ + __check_object_size(ptr, n, to_user); +} +#else +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ } +#endif /* CONFIG_HARDENED_USERCOPY */ + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ -- cgit v1.2.3 From 65733da1dd5c3643e310d371bdb2420a6f3d8e97 Mon Sep 17 00:00:00 2001 From: Mohan Srinivasan Date: Thu, 25 Aug 2016 18:31:01 -0700 Subject: Android: MMC/UFS IO Latency Histograms. This patch adds a new sysfs node (latency_hist) and reports IO (svc time) latency histograms. Disabled by default, can be enabled by echoing 0 into latency_hist, stats can be cleared by writing 2 into latency_hist. This commit fixes the 32 bit build breakage in the previous commit. Tested on both 32 bit and 64 bit arm devices. Bug: 30677035 Change-Id: I9a615a16616d80f87e75676ac4d078a5c429dcf9 Signed-off-by: Mohan Srinivasan --- include/linux/blkdev.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mmc/core.h | 2 ++ include/linux/mmc/host.h | 4 +++ 3 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c70e3588a48c..faf2c0093527 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -197,6 +197,9 @@ struct request { /* for bidi */ struct request *next_rq; + + ktime_t lat_hist_io_start; + int lat_hist_enabled; }; static inline unsigned short req_get_ioprio(struct request *req) @@ -1645,6 +1648,79 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); extern long bdev_direct_access(struct block_device *, sector_t, void __pmem **addr, unsigned long *pfn, long size); + +/* + * X-axis for IO latency histogram support. + */ +static const u_int64_t latency_x_axis_us[] = { + 100, + 200, + 300, + 400, + 500, + 600, + 700, + 800, + 900, + 1000, + 1200, + 1400, + 1600, + 1800, + 2000, + 2500, + 3000, + 4000, + 5000, + 6000, + 7000, + 9000, + 10000 +}; + +#define BLK_IO_LAT_HIST_DISABLE 0 +#define BLK_IO_LAT_HIST_ENABLE 1 +#define BLK_IO_LAT_HIST_ZERO 2 + +struct io_latency_state { + u_int64_t latency_y_axis_read[ARRAY_SIZE(latency_x_axis_us) + 1]; + u_int64_t latency_reads_elems; + u_int64_t latency_y_axis_write[ARRAY_SIZE(latency_x_axis_us) + 1]; + u_int64_t latency_writes_elems; +}; + +static inline void +blk_update_latency_hist(struct io_latency_state *s, + int read, + u_int64_t delta_us) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(latency_x_axis_us); i++) { + if (delta_us < (u_int64_t)latency_x_axis_us[i]) { + if (read) + s->latency_y_axis_read[i]++; + else + s->latency_y_axis_write[i]++; + break; + } + } + if (i == ARRAY_SIZE(latency_x_axis_us)) { + /* Overflowed the histogram */ + if (read) + s->latency_y_axis_read[i]++; + else + s->latency_y_axis_write[i]++; + } + if (read) + s->latency_reads_elems++; + else + s->latency_writes_elems++; +} + +void blk_zero_latency_hist(struct io_latency_state *s); +ssize_t blk_latency_hist_show(struct io_latency_state *s, char *buf); + #else /* CONFIG_BLOCK */ struct block_device; diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 37967b6da03c..3349f0676acb 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -136,6 +136,8 @@ struct mmc_request { struct completion completion; void (*done)(struct mmc_request *);/* completion function */ struct mmc_host *host; + ktime_t io_start; + int lat_hist_enabled; }; struct mmc_card; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 40025b28c1fb..e4862f7cdede 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -379,6 +380,9 @@ struct mmc_host { } embedded_sdio_data; #endif + int latency_hist_enabled; + struct io_latency_state io_lat_s; + unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.3 From a5eeb9b4123eee6aa88bb7a43dba919641abeeb6 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 15 Mar 2016 14:55:12 -0700 Subject: UPSTREAM: mm/slub: support left redzone SLUB already has a redzone debugging feature. But it is only positioned at the end of object (aka right redzone) so it cannot catch left oob. Although current object's right redzone acts as left redzone of next object, first object in a slab cannot take advantage of this effect. This patch explicitly adds a left red zone to each object to detect left oob more precisely. Background: Someone complained to me that left OOB doesn't catch even if KASAN is enabled which does page allocation debugging. That page is out of our control so it would be allocated when left OOB happens and, in this case, we can't find OOB. Moreover, SLUB debugging feature can be enabled without page allocator debugging and, in this case, we will miss that OOB. Before trying to implement, I expected that changes would be too complex, but, it doesn't look that complex to me now. Almost changes are applied to debug specific functions so I feel okay. Signed-off-by: Joonsoo Kim Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Change-Id: Ib893a17ecabd692e6c402e864196bf89cd6781a5 (cherry picked from commit d86bd1bece6fc41d59253002db5441fe960a37f6) Signed-off-by: Sami Tolvanen --- include/linux/slub_def.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 33885118523c..f4e857e920cd 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -81,6 +81,7 @@ struct kmem_cache { int reserved; /* Reserved bytes at the end of slabs */ const char *name; /* Name (only for display!) */ struct list_head list; /* List of slab caches */ + int red_left_pad; /* Left redzone padding size */ #ifdef CONFIG_SYSFS struct kobject kobj; /* For sysfs */ #endif -- cgit v1.2.3 From 65a2cd6d500d2620e5a5aa156b518d5fd25d492a Mon Sep 17 00:00:00 2001 From: Mohan Srinivasan Date: Wed, 7 Sep 2016 17:39:42 -0700 Subject: Android: Fix build breakages. The IO latency histogram change broke allmodconfig and allnoconfig builds. This fixes those breakages. Change-Id: I9cdae655b40ed155468f3cef25cdb74bb56c4d3e Signed-off-by: Mohan Srinivasan --- include/linux/mmc/host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index e4862f7cdede..97b2b0b1f99d 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -380,8 +380,10 @@ struct mmc_host { } embedded_sdio_data; #endif +#ifdef CONFIG_BLOCK int latency_hist_enabled; struct io_latency_state io_lat_s; +#endif unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.3 From 1fd70f71e8f428f0c191a6b86e72e700dbe34bed Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 31 Aug 2016 16:04:21 -0700 Subject: BACKPORT: usercopy: fold builtin_const check into inline function Instead of having each caller of check_object_size() need to remember to check for a const size parameter, move the check into check_object_size() itself. This actually matches the original implementation in PaX, though this commit cleans up the now-redundant builtin_const() calls in the various architectures. Signed-off-by: Kees Cook Change-Id: I348809399c10ffa051251866063be674d064b9ff (cherry picked from 81409e9e28058811c9ea865345e1753f8f677e44) Signed-off-by: Sami Tolvanen --- include/linux/thread_info.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 0ae29ff9ccfd..eded095fe81e 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -161,7 +161,8 @@ extern void __check_object_size(const void *ptr, unsigned long n, static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { - __check_object_size(ptr, n, to_user); + if (!__builtin_constant_p(n)) + __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, -- cgit v1.2.3 From 93584e7e1b4ea543ed04cff643186946196eaebb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 7 Sep 2016 09:39:32 -0700 Subject: UPSTREAM: usercopy: force check_object_size() inline Just for good measure, make sure that check_object_size() is always inlined too, as already done for copy_*_user() and __copy_*_user(). Suggested-by: Linus Torvalds Signed-off-by: Kees Cook Change-Id: Ibfdf4790d03fe426e68d9a864c55a0d1bbfb7d61 (cherry picked from commit a85d6b8242dc78ef3f4542a0f979aebcbe77fc4e) Signed-off-by: Sami Tolvanen --- include/linux/thread_info.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index eded095fe81e..4cf89517783a 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -158,8 +158,8 @@ static inline int arch_within_stack_frames(const void * const stack, extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); -static inline void check_object_size(const void *ptr, unsigned long n, - bool to_user) +static __always_inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); -- cgit v1.2.3 From a38338f1cd595f6a66870ba46cc6a4ae7378c084 Mon Sep 17 00:00:00 2001 From: Mark Salyzyn Date: Wed, 31 Aug 2016 08:09:04 -0700 Subject: FROMLIST: pstore: drop pmsg bounce buffer (from https://lkml.org/lkml/2016/9/1/428) (cherry pick from android-3.10 commit b58133100b38f2bf83cad2d7097417a3a196ed0b) Removing a bounce buffer copy operation in the pmsg driver path is always better. We also gain in overall performance by not requesting a vmalloc on every write as this can cause precious RT tasks, such as user facing media operation, to stall while memory is being reclaimed. Added a write_buf_user to the pstore functions, a backup platform write_buf_user that uses the small buffer that is part of the instance, and implemented a ramoops write_buf_user that only supports PSTORE_TYPE_PMSG. Signed-off-by: Mark Salyzyn Bug: 31057326 Change-Id: I4cdee1cd31467aa3e6c605bce2fbd4de5b0f8caa --- include/linux/pstore.h | 11 ++++++++--- include/linux/pstore_ram.h | 7 +++++-- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 831479f8df8f..5cae2c6c90ad 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -22,12 +22,13 @@ #ifndef _LINUX_PSTORE_H #define _LINUX_PSTORE_H -#include +#include +#include #include #include -#include #include -#include +#include +#include /* types */ enum pstore_type_id { @@ -67,6 +68,10 @@ struct pstore_info { enum kmsg_dump_reason reason, u64 *id, unsigned int part, const char *buf, bool compressed, size_t size, struct pstore_info *psi); + int (*write_buf_user)(enum pstore_type_id type, + enum kmsg_dump_reason reason, u64 *id, + unsigned int part, const char __user *buf, + bool compressed, size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, int count, struct timespec time, struct pstore_info *psi); diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 712757f320a4..45ac5a0d29ee 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -17,11 +17,12 @@ #ifndef __LINUX_PSTORE_RAM_H__ #define __LINUX_PSTORE_RAM_H__ +#include #include +#include #include #include #include -#include struct persistent_ram_buffer; struct rs_control; @@ -59,7 +60,9 @@ void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); int persistent_ram_write(struct persistent_ram_zone *prz, const void *s, - unsigned int count); + unsigned int count); +int persistent_ram_write_user(struct persistent_ram_zone *prz, + const void __user *s, unsigned int count); void persistent_ram_save_old(struct persistent_ram_zone *prz); size_t persistent_ram_old_size(struct persistent_ram_zone *prz); -- cgit v1.2.3 From 662afd95b354bcf78a301838f345c59d9e164ad4 Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Thu, 8 Sep 2016 00:42:25 +0900 Subject: net: inet: diag: expose the socket mark to privileged processes. This adds the capability for a process that has CAP_NET_ADMIN on a socket to see the socket mark in socket dumps. Commit a52e95abf772 ("net: diag: allow socket bytecode filters to match socket marks") recently gave privileged processes the ability to filter socket dumps based on mark. This patch is complementary: it ensures that the mark is also passed to userspace in the socket's netlink attributes. It is useful for tools like ss which display information about sockets. [backport of net-next d545caca827b65aab557a9e9dcdcf1e5a3823c2d] Change-Id: I33336ed9c3ee3fb78fe05c4c47b7fd18c6e33ef1 Tested: https://android-review.googlesource.com/270210 Signed-off-by: Lorenzo Colitti Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 7c27fa1030e8..795852dc3434 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -37,7 +37,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, const struct inet_diag_req_v2 *req, struct user_namespace *user_ns, u32 pid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh); + const struct nlmsghdr *unlh, bool net_admin); void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, -- cgit v1.2.3 From 357838314d69e67ff89db49a7170fa1968638b88 Mon Sep 17 00:00:00 2001 From: David Woods Date: Thu, 17 Dec 2015 14:31:26 -0500 Subject: UPSTREAM: arm64: hugetlb: add support for PTE contiguous bit The arm64 MMU supports a Contiguous bit which is a hint that the TTE is one of a set of contiguous entries which can be cached in a single TLB entry. Supporting this bit adds new intermediate huge page sizes. The set of huge page sizes available depends on the base page size. Without using contiguous pages the huge page sizes are as follows. 4KB: 2MB 1GB 64KB: 512MB With a 4KB granule, the contiguous bit groups together sets of 16 pages and with a 64KB granule it groups sets of 32 pages. This enables two new huge page sizes in each case, so that the full set of available sizes is as follows. 4KB: 64KB 2MB 32MB 1GB 64KB: 2MB 512MB 16GB If a 16KB granule is used then the contiguous bit groups 128 pages at the PTE level and 32 pages at the PMD level. If the base page size is set to 64KB then 2MB pages are enabled by default. It is possible in the future to make 2MB the default huge page size for both 4KB and 64KB granules. Reviewed-by: Chris Metcalf Reviewed-by: Steve Capper Signed-off-by: David Woods Signed-off-by: Will Deacon Bug: 30369029 Patchset: rework-pagetable (cherry picked from commit 66b3923a1a0f77a563b43f43f6ad091354abbfe9) Signed-off-by: Jeff Vander Stoep Change-Id: I5e99c5165bc5eb966adf4d4523632fd9eedd9602 --- include/linux/hugetlb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 685c262e0be8..b0eb06423d5e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -96,9 +96,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, struct address_space *mapping, pgoff_t idx, unsigned long address); -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); -#endif extern int hugepages_treat_as_movable; extern int sysctl_hugetlb_shm_group; -- cgit v1.2.3 From 39b0815e4872fe6eb20a7d1b42b551e341cb7167 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sun, 10 Jan 2016 11:29:07 +0100 Subject: BACKPORT: efi: stub: implement efi_get_random_bytes() based on EFI_RNG_PROTOCOL This exposes the firmware's implementation of EFI_RNG_PROTOCOL via a new function efi_get_random_bytes(). Reviewed-by: Matt Fleming Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas Bug: 30369029 Patchset: kaslr-arm64-4.4 (cherry picked from commit e4fbf4767440472f9d23b0f25a2b905e1c63b6a8) Signed-off-by: Jeff Vander Stoep Change-Id: Id46036b78c2efd223b6cd5488e512fd93e8f597d --- include/linux/efi.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 569b5a866bb1..e747eb08b2be 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -299,7 +299,7 @@ typedef struct { void *open_protocol_information; void *protocols_per_handle; void *locate_handle_buffer; - void *locate_protocol; + efi_status_t (*locate_protocol)(efi_guid_t *, void *, void **); void *install_multiple_protocol_interfaces; void *uninstall_multiple_protocol_interfaces; void *calculate_crc32; @@ -599,6 +599,10 @@ void efi_native_runtime_setup(void); #define EFI_PROPERTIES_TABLE_GUID \ EFI_GUID( 0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5 ) +#define EFI_RNG_PROTOCOL_GUID \ + EFI_GUID(0x3152bca5, 0xeade, 0x433d, \ + 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) + typedef struct { efi_guid_t guid; u64 table; -- cgit v1.2.3 From 8ab85055db1054611473cfd1d72512e45b37e251 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Feb 2016 14:41:12 -0800 Subject: UPSTREAM: asm-generic: Consolidate mark_rodata_ro() Instead of defining mark_rodata_ro() in each architecture, consolidate it. Signed-off-by: Kees Cook Acked-by: Will Deacon Cc: Andrew Morton Cc: Andy Gross Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Ashok Kumar Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Catalin Marinas Cc: Dan Williams Cc: David Brown Cc: David Hildenbrand Cc: Denys Vlasenko Cc: Emese Revfy Cc: H. Peter Anvin Cc: Helge Deller Cc: James E.J. Bottomley Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Marc Zyngier Cc: Mark Rutland Cc: Mathias Krause Cc: Michael Ellerman Cc: Nicolas Pitre Cc: PaX Team Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Ross Zwisler Cc: Russell King Cc: Rusty Russell Cc: Stephen Boyd Cc: Thomas Gleixner Cc: Toshi Kani Cc: kernel-hardening@lists.openwall.com Cc: linux-arch Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-parisc@vger.kernel.org Link: http://lkml.kernel.org/r/1455748879-21872-2-git-send-email-keescook@chromium.org Signed-off-by: Ingo Molnar Bug: 31660652 Change-Id: Iec0c44b3f5d7948954da93fba6cb57888a2709de (cherry picked from commit e267d97b83d9cecc16c54825f9f3ac7f72dc1e1e) Signed-off-by: Sami Tolvanen --- include/linux/init.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index b449f378f995..aedb254abc37 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -142,6 +142,10 @@ void prepare_namespace(void); void __init load_default_modules(void); int __init init_rootfs(void); +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void); +#endif + extern void (*late_time_init)(void); extern bool initcall_debug; -- cgit v1.2.3 From bfd3de058f94daa2a2751e7660bb9561fa23d7cd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Feb 2016 14:41:15 -0800 Subject: UPSTREAM: arch: Introduce post-init read-only memory One of the easiest ways to protect the kernel from attack is to reduce the internal attack surface exposed when a "write" flaw is available. By making as much of the kernel read-only as possible, we reduce the attack surface. Many things are written to only during __init, and never changed again. These cannot be made "const" since the compiler will do the wrong thing (we do actually need to write to them). Instead, move these items into a memory region that will be made read-only during mark_rodata_ro() which happens after all kernel __init code has finished. This introduces __ro_after_init as a way to mark such memory, and adds some documentation about the existing __read_mostly marking. This improves the security of the Linux kernel by marking formerly read-write memory regions as read-only on a fully booted up system. Based on work by PaX Team and Brad Spengler. Signed-off-by: Kees Cook Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brad Spengler Cc: Brian Gerst Cc: David Brown Cc: Denys Vlasenko Cc: Emese Revfy Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Mathias Krause Cc: Michael Ellerman Cc: PaX Team Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-hardening@lists.openwall.com Cc: linux-arch Link: http://lkml.kernel.org/r/1455748879-21872-5-git-send-email-keescook@chromium.org Signed-off-by: Ingo Molnar Bug: 31660652 Change-Id: I640f6d858d9770a5e480d12a1c716adf8842feb0 (cherry picked from commit c74ba8b3480da6ddaea17df2263ec09b869ac496) Signed-off-by: Sami Tolvanen --- include/linux/cache.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cache.h b/include/linux/cache.h index 17e7e82d2aa7..1be04f8c563a 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -12,10 +12,24 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif +/* + * __read_mostly is used to keep rarely changing variables out of frequently + * updated cachelines. If an architecture doesn't support it, ignore the + * hint. + */ #ifndef __read_mostly #define __read_mostly #endif +/* + * __ro_after_init is used to mark things that are read-only after init (i.e. + * after mark_rodata_ro() has been called). These are effectively read-only, + * but may get written to during init, so can't live in .rodata (via "const"). + */ +#ifndef __ro_after_init +#define __ro_after_init __attribute__((__section__(".data..ro_after_init"))) +#endif + #ifndef ____cacheline_aligned #define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) #endif -- cgit v1.2.3 From bb849676d5a9351c7d263c20b5ef9e67ec463412 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 30 Nov 2015 13:28:15 +0100 Subject: UPSTREAM: mm/memblock: add MEMBLOCK_NOMAP attribute to memblock memory table This introduces the MEMBLOCK_NOMAP attribute and the required plumbing to make it usable as an indicator that some parts of normal memory should not be covered by the kernel direct mapping. It is up to the arch to actually honor the attribute when laying out this mapping, but the memblock code itself is modified to disregard these regions for allocations and other general use. Cc: linux-mm@kvack.org Cc: Alexander Kuleshov Cc: Andrew Morton Reviewed-by: Matt Fleming Signed-off-by: Ard Biesheuvel Signed-off-by: Will Deacon Change-Id: I55cd3abdf514ac54c071fa0037d8dac73bda798d (cherry picked from commit bf3d3cc580f9960883ebf9ea05868f336d9491c2) Signed-off-by: Sami Tolvanen --- include/linux/memblock.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 24daf8fc4d7c..fec66f86eeff 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -25,6 +25,7 @@ enum { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ + MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ }; struct memblock_region { @@ -82,6 +83,7 @@ bool memblock_overlaps_region(struct memblock_type *type, int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); +int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); ulong choose_memblock_flags(void); /* Low level functions */ @@ -184,6 +186,11 @@ static inline bool memblock_is_mirror(struct memblock_region *m) return m->flags & MEMBLOCK_MIRROR; } +static inline bool memblock_is_nomap(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_NOMAP; +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); @@ -319,6 +326,7 @@ phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); int memblock_is_memory(phys_addr_t addr); +int memblock_is_map_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); int memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); -- cgit v1.2.3 From 8fd31d5a2c06726a6060ea355bb5c90d44b132c4 Mon Sep 17 00:00:00 2001 From: Mohan Srinivasan Date: Mon, 3 Oct 2016 16:17:34 -0700 Subject: Fix a build breakage in IO latency hist code. Fix a build breakage where MMC is enabled, but BLOCK is not. Change-Id: I0eb422d12264f0371f3368ae7c37342ef9efabaa Signed-off-by: Mohan Srinivasan --- include/linux/mmc/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 3349f0676acb..0860efd6e1be 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -137,7 +137,9 @@ struct mmc_request { void (*done)(struct mmc_request *);/* completion function */ struct mmc_host *host; ktime_t io_start; +#ifdef CONFIG_BLOCK int lat_hist_enabled; +#endif }; struct mmc_card; -- cgit v1.2.3 From e78f134a78a0ae95b83ac0cac47ab0bb584ebaa7 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 6 Oct 2016 15:53:38 -0700 Subject: CHROMIUM: remove Android's cgroup generic permissions checks The implementation is utterly broken, resulting in all processes being allows to move tasks between sets (as long as they have access to the "tasks" attribute), and upstream is heading towards checking only capability anyway, so let's get rid of this code. BUG=b:31790445,chromium:647994 TEST=Boot android container, examine logcat Change-Id: I2f780a5992c34e52a8f2d0b3557fc9d490da2779 Signed-off-by: Dmitry Torokhov Reviewed-on: https://chromium-review.googlesource.com/394967 Reviewed-by: Ricky Zhou Reviewed-by: John Stultz --- include/linux/cgroup-defs.h | 1 - include/linux/cgroup.h | 14 -------------- 2 files changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4a4eea01956c..06b77f9dd3f2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -422,7 +422,6 @@ struct cgroup_subsys { void (*css_reset)(struct cgroup_subsys_state *css); void (*css_e_css_changed)(struct cgroup_subsys_state *css); - int (*allow_attach)(struct cgroup_taskset *tset); int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 70358b9f5a7a..cb91b44f5f78 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -528,16 +528,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -/* - * Default Android check for whether the current process is allowed to move a - * task across cgroups, either because CAP_SYS_NICE is set or because the uid - * of the calling process is the same as the moved task or because we are - * running as root. - * Returns 0 if this is allowed, or -EACCES otherwise. - */ -int subsys_cgroup_allow_attach(struct cgroup_taskset *tset); - - #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -562,10 +552,6 @@ static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } -static inline int subsys_cgroup_allow_attach(void *tset) -{ - return -EINVAL; -} #endif /* !CONFIG_CGROUPS */ #endif /* _LINUX_CGROUP_H */ -- cgit v1.2.3 From af80d7c3e91450fbcad01c497b394bf8ab01d37c Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Mon, 28 Nov 2016 14:35:22 -0800 Subject: UPSTREAM: timekeeping: Add a fast and NMI safe boot clock This boot clock can be used as a tracing clock and will account for suspend time. To keep it NMI safe since we're accessing from tracing, we're not using a separate timekeeper with updates to monotonic clock and boot offset protected with seqlocks. This has the following minor side effects: (1) Its possible that a timestamp be taken after the boot offset is updated but before the timekeeper is updated. If this happens, the new boot offset is added to the old timekeeping making the clock appear to update slightly earlier: CPU 0 CPU 1 timekeeping_inject_sleeptime64() __timekeeping_inject_sleeptime(tk, delta); timestamp(); timekeeping_update(tk, TK_CLEAR_NTP...); (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be partially updated. Since the tk->offs_boot update is a rare event, this should be a rare occurrence which postprocessing should be able to handle. Bug: b/33184060 Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Richard Cochran Cc: Prarit Bhargava Reviewed-by: Thomas Gleixner Signed-off-by: Joel Fernandes Signed-off-by: John Stultz --- include/linux/timekeeping.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index ec89d846324c..b7246d2ed7c9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -233,6 +233,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); +extern u64 ktime_get_boot_fast_ns(void); /* * Timespec interfaces utilizing the ktime based ones -- cgit v1.2.3 From 6b42d02561d335017cd6066f506514f32962fa2d Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 26 Oct 2016 15:29:51 -0700 Subject: ANDROID: mnt: Add filesystem private data to mount points This starts to add private data associated directly to mount points. The intent is to give filesystems a sense of where they have come from, as a means of letting a filesystem take different actions based on this information. Change-Id: Ie769d7b3bb2f5972afe05c1bf16cf88c91647ab2 Signed-off-by: Daniel Rosenberg --- include/linux/fs.h | 3 +++ include/linux/mount.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..3996b8ec0b84 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1697,6 +1697,8 @@ struct super_operations { int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); + void *(*clone_mnt_data) (void *); + void (*copy_mnt_data) (void *, void *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); @@ -1931,6 +1933,7 @@ struct file_system_type { #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); + void *(*alloc_mnt_data) (void); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; diff --git a/include/linux/mount.h b/include/linux/mount.h index f822c3c11377..0e9b0977237a 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,6 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; + void *data; }; struct file; /* forward dec */ -- cgit v1.2.3 From 0ad2dd493c2fb614cb0b7f2355990ce035224590 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 26 Oct 2016 15:58:22 -0700 Subject: ANDROID: vfs: Allow filesystems to access their private mount data Now we pass the vfsmount when mounting and remounting. This allows the filesystem to actually set up the mount specific data, although we can't quite do anything with it yet. show_options is expanded to include data that lives with the mount. To avoid changing existing filesystems, these have been added as new vfs functions. Change-Id: If80670bfad9f287abb8ac22457e1b034c9697097 Signed-off-by: Daniel Rosenberg --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3996b8ec0b84..31382e732e9e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1697,11 +1697,13 @@ struct super_operations { int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); + int (*remount_fs2) (struct vfsmount *, struct super_block *, int *, char *); void *(*clone_mnt_data) (void *); void (*copy_mnt_data) (void *, void *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); + int (*show_options2)(struct vfsmount *,struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); @@ -1933,6 +1935,8 @@ struct file_system_type { #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); + struct dentry *(*mount2) (struct vfsmount *, struct file_system_type *, int, + const char *, void *); void *(*alloc_mnt_data) (void); void (*kill_sb) (struct super_block *); struct module *owner; -- cgit v1.2.3 From 21fc44e40ae3c574c288159846ab5a4762bd0e3f Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 26 Oct 2016 16:27:45 -0700 Subject: ANDROID: vfs: Add permission2 for filesystems with per mount permissions This allows filesystems to use their mount private data to influence the permssions they return in permission2. It has been separated into a new call to avoid disrupting current permission users. Change-Id: I9d416e3b8b6eca84ef3e336bd2af89ddd51df6ca Signed-off-by: Daniel Rosenberg --- include/linux/fs.h | 11 +++++++++++ include/linux/namei.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 31382e732e9e..b5a863580120 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1503,13 +1503,21 @@ extern bool inode_owner_or_capable(const struct inode *inode); * VFS helper functions.. */ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); +extern int vfs_create2(struct vfsmount *, struct inode *, struct dentry *, umode_t, bool); extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); +extern int vfs_mkdir2(struct vfsmount *, struct inode *, struct dentry *, umode_t); extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); +extern int vfs_mknod2(struct vfsmount *, struct inode *, struct dentry *, umode_t, dev_t); extern int vfs_symlink(struct inode *, struct dentry *, const char *); +extern int vfs_symlink2(struct vfsmount *, struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); +extern int vfs_link2(struct vfsmount *, struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); +extern int vfs_rmdir2(struct vfsmount *, struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); +extern int vfs_unlink2(struct vfsmount *, struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); +extern int vfs_rename2(struct vfsmount *, struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); extern int vfs_whiteout(struct inode *, struct dentry *); /* @@ -1635,6 +1643,7 @@ struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*follow_link) (struct dentry *, void **); int (*permission) (struct inode *, int); + int (*permission2) (struct vfsmount *, struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); @@ -2442,7 +2451,9 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); +extern int inode_permission2(struct vfsmount *, struct inode *, int); extern int __inode_permission(struct inode *, int); +extern int __inode_permission2(struct vfsmount *, struct inode *, int); extern int generic_permission(struct inode *, int); extern int __check_sticky(struct inode *dir, struct inode *inode); diff --git a/include/linux/namei.h b/include/linux/namei.h index d53c25453aca..023359f18567 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -79,6 +79,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); +extern struct dentry *lookup_one_len2(const char *, struct vfsmount *mnt, struct dentry *, int); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3 From 1cbf8e31e3a7440a3ada22ba06f62d6359c27c0e Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Wed, 26 Oct 2016 16:33:11 -0700 Subject: ANDROID: vfs: Add setattr2 for filesystems with per mount permissions This allows filesystems to use their mount private data to influence the permssions they use in setattr2. It has been separated into a new call to avoid disrupting current setattr users. Change-Id: I19959038309284448f1b7f232d579674ef546385 Signed-off-by: Daniel Rosenberg --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b5a863580120..31bf8e1e58ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1661,6 +1661,7 @@ struct inode_operations { int (*rename2) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); + int (*setattr2) (struct vfsmount *, struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); @@ -2226,6 +2227,8 @@ struct filename { extern long vfs_truncate(struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); +extern int do_truncate2(struct vfsmount *, struct dentry *, loff_t start, + unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, @@ -2450,6 +2453,7 @@ extern void emergency_remount(void); extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); +extern int notify_change2(struct vfsmount *, struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); extern int inode_permission2(struct vfsmount *, struct inode *, int); extern int __inode_permission(struct inode *, int); -- cgit v1.2.3 From 49b60d4aa95aa0519238a06fde5c838146742796 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 19 Sep 2016 17:39:09 +0200 Subject: BACKPORT: posix_acl: Clear SGID bit when setting file permissions (cherry pick from commit 073931017b49d9458aa351605b43a7e34598caef) When file permissions are modified via chmod(2) and the user is not in the owning group or capable of CAP_FSETID, the setgid bit is cleared in inode_change_ok(). Setting a POSIX ACL via setxattr(2) sets the file permissions as well as the new ACL, but doesn't clear the setgid bit in a similar way; this allows to bypass the check in chmod(2). Fix that. NB: We did not resolve the ACL leak in this CL, require additional upstream fix. References: CVE-2016-7097 Reviewed-by: Christoph Hellwig Reviewed-by: Jeff Layton Signed-off-by: Jan Kara Signed-off-by: Andreas Gruenbacher Bug: 32458736 Change-Id: I19591ad452cc825ac282b3cfd2daaa72aa9a1ac1 --- include/linux/posix_acl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 3e96a6a76103..d1a8ad7e5ae4 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -95,6 +95,7 @@ extern int set_posix_acl(struct inode *, int, struct posix_acl *); extern int posix_acl_chmod(struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); +extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); -- cgit v1.2.3 From a4f5f251e951d2e6f454f82c58e7044f7de87a0d Mon Sep 17 00:00:00 2001 From: Jin Qian Date: Thu, 2 Mar 2017 13:32:59 -0800 Subject: ANDROID: sched: add a counter to track fsync Change-Id: I6c138de5b2332eea70f57e098134d1d141247b3f Signed-off-by: Jin Qian --- include/linux/sched.h | 8 ++++++++ include/linux/task_io_accounting.h | 2 ++ include/linux/task_io_accounting_ops.h | 1 + 3 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8be9f0dbdd0c..5b250c9f7718 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3227,6 +3227,11 @@ static inline void inc_syscw(struct task_struct *tsk) { tsk->ioac.syscw++; } + +static inline void inc_syscfs(struct task_struct *tsk) +{ + tsk->ioac.syscfs++; +} #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { @@ -3243,6 +3248,9 @@ static inline void inc_syscr(struct task_struct *tsk) static inline void inc_syscw(struct task_struct *tsk) { } +static inline void inc_syscfs(struct task_struct *tsk) +{ +} #endif #ifndef TASK_SIZE_OF diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h index bdf855c2856f..2dd338fdf881 100644 --- a/include/linux/task_io_accounting.h +++ b/include/linux/task_io_accounting.h @@ -18,6 +18,8 @@ struct task_io_accounting { u64 syscr; /* # of write syscalls */ u64 syscw; + /* # of fsync syscalls */ + u64 syscfs; #endif /* CONFIG_TASK_XACCT */ #ifdef CONFIG_TASK_IO_ACCOUNTING diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h index 4d090f9ee608..1b505c804af3 100644 --- a/include/linux/task_io_accounting_ops.h +++ b/include/linux/task_io_accounting_ops.h @@ -96,6 +96,7 @@ static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, dst->wchar += src->wchar; dst->syscr += src->syscr; dst->syscw += src->syscw; + dst->syscfs += src->syscfs; } #else static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, -- cgit v1.2.3 From 741ee549472cb814d9ffaa0e679b9ddc02eca192 Mon Sep 17 00:00:00 2001 From: Manu Gautam Date: Mon, 20 Mar 2017 17:00:52 +0530 Subject: usb: gadget: ccid: Fix data types of header structures Replace unsigned long with __u32 as 4 bytes is the length of field where as unsigned long could be 8 bytes on 64 bit machine. Also, replace short and char with u16 and u8 respectively for better readability. Change-Id: I8637f6b32d56d90c01b4453b4677f40d5b865bf6 Signed-off-by: Manu Gautam --- include/linux/usb/ccid_desc.h | 44 +++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/ccid_desc.h b/include/linux/usb/ccid_desc.h index 9a0c72650cd2..2e6dbb5afe71 100644 --- a/include/linux/usb/ccid_desc.h +++ b/include/linux/usb/ccid_desc.h @@ -86,27 +86,27 @@ * Table 5.1-1 Smart Card Device Class descriptors */ struct usb_ccid_class_descriptor { - unsigned char bLength; - unsigned char bDescriptorType; - unsigned short bcdCCID; - unsigned char bMaxSlotIndex; - unsigned char bVoltageSupport; - unsigned long dwProtocols; - unsigned long dwDefaultClock; - unsigned long dwMaximumClock; - unsigned char bNumClockSupported; - unsigned long dwDataRate; - unsigned long dwMaxDataRate; - unsigned char bNumDataRatesSupported; - unsigned long dwMaxIFSD; - unsigned long dwSynchProtocols; - unsigned long dwMechanical; - unsigned long dwFeatures; - unsigned long dwMaxCCIDMessageLength; - unsigned char bClassGetResponse; - unsigned char bClassEnvelope; - unsigned short wLcdLayout; - unsigned char bPINSupport; - unsigned char bMaxCCIDBusySlots; + __u8 bLength; + __u8 bDescriptorType; + __u16 bcdCCID; + __u8 bMaxSlotIndex; + __u8 bVoltageSupport; + __u32 dwProtocols; + __u32 dwDefaultClock; + __u32 dwMaximumClock; + __u8 bNumClockSupported; + __u32 dwDataRate; + __u32 dwMaxDataRate; + __u8 bNumDataRatesSupported; + __u32 dwMaxIFSD; + __u32 dwSynchProtocols; + __u32 dwMechanical; + __u32 dwFeatures; + __u32 dwMaxCCIDMessageLength; + __u8 bClassGetResponse; + __u8 bClassEnvelope; + __u16 wLcdLayout; + __u8 bPINSupport; + __u8 bMaxCCIDBusySlots; } __packed; #endif -- cgit v1.2.3 From bc5b6dd5dfd838f7338e8d1ae42f670adc1a4d03 Mon Sep 17 00:00:00 2001 From: Jungseung Lee Date: Thu, 22 Dec 2016 12:37:34 +0900 Subject: BACKPORT: mmc: core: Export device lifetime information through sysfs In the eMMC 5.0 version of the spec, several EXT_CSD fields about device lifetime are added. - Two types of estimated indications reflected by averaged wear out of memory - An indication reflected by average reserved blocks Export the information through sysfs. Signed-off-by: Jungseung Lee Reviewed-by: Jaehoon Chung Reviewed-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 3 +++ include/linux/mmc/mmc.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index eb0151bac50c..8f23fb2c5ed2 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -118,6 +118,9 @@ struct mmc_ext_csd { u8 raw_pwr_cl_ddr_200_360; /* 253 */ u8 raw_bkops_status; /* 246 */ u8 raw_sectors[4]; /* 212 - 4 bytes */ + u8 pre_eol_info; /* 267 */ + u8 device_life_time_est_typ_a; /* 268 */ + u8 device_life_time_est_typ_b; /* 269 */ unsigned int feature_support; #define MMC_DISCARD_FEATURE BIT(0) /* CMD38 feature */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 15f2c4a0a62c..2c6b1d45626e 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -330,6 +330,9 @@ struct _mmc_csd { #define EXT_CSD_CACHE_SIZE 249 /* RO, 4 bytes */ #define EXT_CSD_PWR_CL_DDR_200_360 253 /* RO */ #define EXT_CSD_FIRMWARE_VERSION 254 /* RO, 8 bytes */ +#define EXT_CSD_PRE_EOL_INFO 267 /* RO */ +#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A 268 /* RO */ +#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B 269 /* RO */ #define EXT_CSD_SUPPORTED_MODE 493 /* RO */ #define EXT_CSD_TAG_UNIT_SIZE 498 /* RO */ #define EXT_CSD_DATA_TAG_SUPPORT 499 /* RO */ -- cgit v1.2.3 From d0ebde92fbeb98eedbfce15cef3c86b652846d25 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Mar 2017 10:52:16 -0800 Subject: dccp: fix use-after-free in dccp_feat_activate_values [ Upstream commit 62f8f4d9066c1c6f2474845d1ca7e2891f2ae3fd ] Dmitry reported crashes in DCCP stack [1] Problem here is that when I got rid of listener spinlock, I missed the fact that DCCP stores a complex state in struct dccp_request_sock, while TCP does not. Since multiple cpus could access it at the same time, we need to add protection. [1] BUG: KASAN: use-after-free in dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541 at addr ffff88003713be68 Read of size 8 by task syz-executor2/8457 CPU: 2 PID: 8457 Comm: syz-executor2 Not tainted 4.10.0-rc7+ #127 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:15 [inline] dump_stack+0x292/0x398 lib/dump_stack.c:51 kasan_object_err+0x1c/0x70 mm/kasan/report.c:162 print_address_description mm/kasan/report.c:200 [inline] kasan_report_error mm/kasan/report.c:289 [inline] kasan_report.part.1+0x20e/0x4e0 mm/kasan/report.c:311 kasan_report mm/kasan/report.c:332 [inline] __asan_report_load8_noabort+0x29/0x30 mm/kasan/report.c:332 dccp_feat_activate_values+0x967/0xab0 net/dccp/feat.c:1541 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279 NF_HOOK include/linux/netfilter.h:257 [inline] ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322 dst_input include/net/dst.h:507 [inline] ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69 NF_HOOK include/linux/netfilter.h:257 [inline] ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228 process_backlog+0xe5/0x6c0 net/core/dev.c:4839 napi_poll net/core/dev.c:5202 [inline] net_rx_action+0xe70/0x1900 net/core/dev.c:5267 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902 do_softirq.part.17+0x1e8/0x230 kernel/softirq.c:328 do_softirq kernel/softirq.c:176 [inline] __local_bh_enable_ip+0x1f2/0x200 kernel/softirq.c:181 local_bh_enable include/linux/bottom_half.h:31 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:971 [inline] ip6_finish_output2+0xbb0/0x23d0 net/ipv6/ip6_output.c:123 ip6_finish_output+0x302/0x960 net/ipv6/ip6_output.c:148 NF_HOOK_COND include/linux/netfilter.h:246 [inline] ip6_output+0x1cb/0x8d0 net/ipv6/ip6_output.c:162 ip6_xmit+0xcdf/0x20d0 include/net/dst.h:501 inet6_csk_xmit+0x320/0x5f0 net/ipv6/inet6_connection_sock.c:179 dccp_transmit_skb+0xb09/0x1120 net/dccp/output.c:141 dccp_xmit_packet+0x215/0x760 net/dccp/output.c:280 dccp_write_xmit+0x168/0x1d0 net/dccp/output.c:362 dccp_sendmsg+0x79c/0xb10 net/dccp/proto.c:796 inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744 sock_sendmsg_nosec net/socket.c:635 [inline] sock_sendmsg+0xca/0x110 net/socket.c:645 SYSC_sendto+0x660/0x810 net/socket.c:1687 SyS_sendto+0x40/0x50 net/socket.c:1655 entry_SYSCALL_64_fastpath+0x1f/0xc2 RIP: 0033:0x4458b9 RSP: 002b:00007f8ceb77bb58 EFLAGS: 00000282 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000017 RCX: 00000000004458b9 RDX: 0000000000000023 RSI: 0000000020e60000 RDI: 0000000000000017 RBP: 00000000006e1b90 R08: 00000000200f9fe1 R09: 0000000000000020 R10: 0000000000008010 R11: 0000000000000282 R12: 00000000007080a8 R13: 0000000000000000 R14: 00007f8ceb77c9c0 R15: 00007f8ceb77c700 Object at ffff88003713be50, in cache kmalloc-64 size: 64 Allocated: PID = 8446 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57 save_stack+0x43/0xd0 mm/kasan/kasan.c:502 set_track mm/kasan/kasan.c:514 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605 kmem_cache_alloc_trace+0x82/0x270 mm/slub.c:2738 kmalloc include/linux/slab.h:490 [inline] dccp_feat_entry_new+0x214/0x410 net/dccp/feat.c:467 dccp_feat_push_change+0x38/0x220 net/dccp/feat.c:487 __feat_register_sp+0x223/0x2f0 net/dccp/feat.c:741 dccp_feat_propagate_ccid+0x22b/0x2b0 net/dccp/feat.c:949 dccp_feat_server_ccid_dependencies+0x1b3/0x250 net/dccp/feat.c:1012 dccp_make_response+0x1f1/0xc90 net/dccp/output.c:423 dccp_v6_send_response+0x4ec/0xc20 net/dccp/ipv6.c:217 dccp_v6_conn_request+0xaba/0x11b0 net/dccp/ipv6.c:377 dccp_rcv_state_process+0x51e/0x1650 net/dccp/input.c:606 dccp_v6_do_rcv+0x213/0x350 net/dccp/ipv6.c:632 sk_backlog_rcv include/net/sock.h:893 [inline] __sk_receive_skb+0x36f/0xcc0 net/core/sock.c:479 dccp_v6_rcv+0xba5/0x1d00 net/dccp/ipv6.c:742 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279 NF_HOOK include/linux/netfilter.h:257 [inline] ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322 dst_input include/net/dst.h:507 [inline] ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69 NF_HOOK include/linux/netfilter.h:257 [inline] ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228 process_backlog+0xe5/0x6c0 net/core/dev.c:4839 napi_poll net/core/dev.c:5202 [inline] net_rx_action+0xe70/0x1900 net/core/dev.c:5267 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284 Freed: PID = 15 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57 save_stack+0x43/0xd0 mm/kasan/kasan.c:502 set_track mm/kasan/kasan.c:514 [inline] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578 slab_free_hook mm/slub.c:1355 [inline] slab_free_freelist_hook mm/slub.c:1377 [inline] slab_free mm/slub.c:2954 [inline] kfree+0xe8/0x2b0 mm/slub.c:3874 dccp_feat_entry_destructor.part.4+0x48/0x60 net/dccp/feat.c:418 dccp_feat_entry_destructor net/dccp/feat.c:416 [inline] dccp_feat_list_pop net/dccp/feat.c:541 [inline] dccp_feat_activate_values+0x57f/0xab0 net/dccp/feat.c:1543 dccp_create_openreq_child+0x464/0x610 net/dccp/minisocks.c:121 dccp_v6_request_recv_sock+0x1f6/0x1960 net/dccp/ipv6.c:457 dccp_check_req+0x335/0x5a0 net/dccp/minisocks.c:186 dccp_v6_rcv+0x69e/0x1d00 net/dccp/ipv6.c:711 ip6_input_finish+0x46d/0x17a0 net/ipv6/ip6_input.c:279 NF_HOOK include/linux/netfilter.h:257 [inline] ip6_input+0xdb/0x590 net/ipv6/ip6_input.c:322 dst_input include/net/dst.h:507 [inline] ip6_rcv_finish+0x289/0x890 net/ipv6/ip6_input.c:69 NF_HOOK include/linux/netfilter.h:257 [inline] ipv6_rcv+0x12ec/0x23d0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x1ae5/0x3400 net/core/dev.c:4190 __netif_receive_skb+0x2a/0x170 net/core/dev.c:4228 process_backlog+0xe5/0x6c0 net/core/dev.c:4839 napi_poll net/core/dev.c:5202 [inline] net_rx_action+0xe70/0x1900 net/core/dev.c:5267 __do_softirq+0x2fb/0xb7d kernel/softirq.c:284 Memory state around the buggy address: ffff88003713bd00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88003713bd80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88003713be00: fc fc fc fc fc fc fc fc fc fc fb fb fb fb fb fb ^ Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/dccp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 61d042bbbf60..68449293c4b6 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -163,6 +163,7 @@ struct dccp_request_sock { __u64 dreq_isr; __u64 dreq_gsr; __be32 dreq_service; + spinlock_t dreq_lock; struct list_head dreq_featneg; __u32 dreq_timestamp_echo; __u32 dreq_timestamp_time; -- cgit v1.2.3 From e953f89b8563efe0b92f70033d237874c43d4a3d Mon Sep 17 00:00:00 2001 From: Joel Scherpelz Date: Wed, 22 Mar 2017 18:19:04 +0900 Subject: net: ipv6: Add sysctl for minimum prefix len acceptable in RIOs. This commit adds a new sysctl accept_ra_rt_info_min_plen that defines the minimum acceptable prefix length of Route Information Options. The new sysctl is intended to be used together with accept_ra_rt_info_max_plen to configure a range of acceptable prefix lengths. It is useful to prevent misconfigurations from unintentionally blackholing too much of the IPv6 address space (e.g., home routers announcing RIOs for fc00::/7, which is incorrect). [backport of net-next bbea124bc99df968011e76eba105fe964a4eceab] Bug: 33333670 Test: net_test passes Signed-off-by: Joel Scherpelz Acked-by: Lorenzo Colitti Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ce777260e9ea..1182f0e21697 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -36,6 +36,7 @@ struct ipv6_devconf { __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; #ifdef CONFIG_IPV6_ROUTE_INFO + __s32 accept_ra_rt_info_min_plen; __s32 accept_ra_rt_info_max_plen; #endif #endif -- cgit v1.2.3 From ac1a97d8a562161e42edd23e5d0f1740a3d93c85 Mon Sep 17 00:00:00 2001 From: Chris Bainbridge Date: Mon, 25 Apr 2016 13:48:38 +0100 Subject: usb: core: hub: hub_port_init lock controller instead of bus commit feb26ac31a2a5cb88d86680d9a94916a6343e9e6 upstream. The XHCI controller presents two USB buses to the system - one for USB2 and one for USB3. The hub init code (hub_port_init) is reentrant but only locks one bus per thread, leading to a race condition failure when two threads attempt to simultaneously initialise a USB2 and USB3 device: [ 8.034843] xhci_hcd 0000:00:14.0: Timeout while waiting for setup device command [ 13.183701] usb 3-3: device descriptor read/all, error -110 On a test system this failure occurred on 6% of all boots. The call traces at the point of failure are: Call Trace: [] schedule+0x37/0x90 [] usb_kill_urb+0x8d/0xd0 [] ? wake_up_atomic_t+0x30/0x30 [] usb_start_wait_urb+0xbe/0x150 [] usb_control_msg+0xbc/0xf0 [] hub_port_init+0x51e/0xb70 [] hub_event+0x817/0x1570 [] process_one_work+0x1ff/0x620 [] ? process_one_work+0x15f/0x620 [] worker_thread+0x64/0x4b0 [] ? rescuer_thread+0x390/0x390 [] kthread+0x105/0x120 [] ? kthread_create_on_node+0x200/0x200 [] ret_from_fork+0x3f/0x70 [] ? kthread_create_on_node+0x200/0x200 Call Trace: [] xhci_setup_device+0x53d/0xa40 [] xhci_address_device+0xe/0x10 [] hub_port_init+0x1bf/0xb70 [] ? trace_hardirqs_on+0xd/0x10 [] hub_event+0x817/0x1570 [] process_one_work+0x1ff/0x620 [] ? process_one_work+0x15f/0x620 [] worker_thread+0x64/0x4b0 [] ? rescuer_thread+0x390/0x390 [] kthread+0x105/0x120 [] ? kthread_create_on_node+0x200/0x200 [] ret_from_fork+0x3f/0x70 [] ? kthread_create_on_node+0x200/0x200 Which results from the two call chains: hub_port_init usb_get_device_descriptor usb_get_descriptor usb_control_msg usb_internal_control_msg usb_start_wait_urb usb_submit_urb / wait_for_completion_timeout / usb_kill_urb hub_port_init hub_set_address xhci_address_device xhci_setup_device Mathias Nyman explains the current behaviour violates the XHCI spec: hub_port_reset() will end up moving the corresponding xhci device slot to default state. As hub_port_reset() is called several times in hub_port_init() it sounds reasonable that we could end up with two threads having their xhci device slots in default state at the same time, which according to xhci 4.5.3 specs still is a big no no: "Note: Software shall not transition more than one Device Slot to the Default State at a time" So both threads fail at their next task after this. One fails to read the descriptor, and the other fails addressing the device. Fix this in hub_port_init by locking the USB controller (instead of an individual bus) to prevent simultaneous initialisation of both buses. Fixes: 638139eb95d2 ("usb: hub: allow to process more usb hub events in parallel") Link: https://lkml.org/lkml/2016/2/8/312 Link: https://lkml.org/lkml/2016/2/4/748 Signed-off-by: Chris Bainbridge Cc: stable Acked-by: Mathias Nyman Signed-off-by: Sumit Semwal [sumits: minor merge conflict resolution for linux-4.4.y] Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +-- include/linux/usb/hcd.h | 1 + 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 12891ffd4bf0..8c75af6b7d5b 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -371,14 +371,13 @@ struct usb_bus { int devnum_next; /* Next open device number in * round-robin allocation */ + struct mutex devnum_next_mutex; /* devnum_next mutex */ struct usb_devmap devmap; /* device address allocation map */ struct usb_device *root_hub; /* Root hub */ struct usb_bus *hs_companion; /* Companion EHCI bus, if any */ struct list_head bus_list; /* list of busses */ - struct mutex usb_address0_mutex; /* unaddressed device mutex */ - int bandwidth_allocated; /* on this bus: how much of the time * reserved for periodic (intr/iso) * requests is used, on average? diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index f89c24bd53a4..3993b21f3d11 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -180,6 +180,7 @@ struct usb_hcd { * bandwidth_mutex should be dropped after a successful control message * to the device, or resetting the bandwidth after a failed attempt. */ + struct mutex *address0_mutex; struct mutex *bandwidth_mutex; struct usb_hcd *shared_hcd; struct usb_hcd *primary_hcd; -- cgit v1.2.3 From 4cb0c0b73d1c79a8ce260836b3f27650aa1c57f1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 2 Mar 2017 12:17:22 -0800 Subject: give up on gcc ilog2() constant optimizations commit 474c90156c8dcc2fa815e6716cc9394d7930cb9c upstream. gcc-7 has an "optimization" pass that completely screws up, and generates the code expansion for the (impossible) case of calling ilog2() with a zero constant, even when the code gcc compiles does not actually have a zero constant. And we try to generate a compile-time error for anybody doing ilog2() on a constant where that doesn't make sense (be it zero or negative). So now gcc7 will fail the build due to our sanity checking, because it created that constant-zero case that didn't actually exist in the source code. There's a whole long discussion on the kernel mailing about how to work around this gcc bug. The gcc people themselevs have discussed their "feature" in https://gcc.gnu.org/bugzilla/show_bug.cgi?id=72785 but it's all water under the bridge, because while it looked at one point like it would be solved by the time gcc7 was released, that was not to be. So now we have to deal with this compiler braindamage. And the only simple approach seems to be to just delete the code that tries to warn about bad uses of ilog2(). So now "ilog2()" will just return 0 not just for the value 1, but for any non-positive value too. It's not like I can recall anybody having ever actually tried to use this function on any invalid value, but maybe the sanity check just meant that such code never made it out in public. Reported-by: Laura Abbott Cc: John Stultz , Cc: Thomas Gleixner Cc: Ard Biesheuvel Signed-off-by: Linus Torvalds Cc: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- include/linux/log2.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/log2.h b/include/linux/log2.h index fd7ff3d91e6a..f38fae23bdac 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -15,12 +15,6 @@ #include #include -/* - * deal with unrepresentable constant logarithms - */ -extern __attribute__((const, noreturn)) -int ____ilog2_NaN(void); - /* * non-constant log of base 2 calculators * - the arch may override these in asm/bitops.h if they can be implemented @@ -85,7 +79,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n) < 1 ? ____ilog2_NaN() : \ + (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ @@ -148,10 +142,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - (n) & (1ULL << 1) ? 1 : \ - (n) & (1ULL << 0) ? 0 : \ - ____ilog2_NaN() \ - ) : \ + 1 ) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ -- cgit v1.2.3 From 2c929ea720f968da2f1ad90db995cc49a937955f Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Mon, 13 Mar 2017 20:50:08 +0100 Subject: usb-core: Add LINEAR_FRAME_INTR_BINTERVAL USB quirk commit 3243367b209faed5c320a4e5f9a565ee2a2ba958 upstream. Some USB 2.0 devices erroneously report millisecond values in bInterval. The generic config code manages to catch most of them, but in some cases it's not completely enough. The case at stake here is a USB 2.0 braille device, which wants to announce 10ms and thus sets bInterval to 10, but with the USB 2.0 computation that yields to 64ms. It happens that one can type fast enough to reach this interval and get the device buffers overflown, leading to problematic latencies. The generic config code does not catch this case because the 64ms is considered a sane enough value. This change thus adds a USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL quirk to mark devices which actually report milliseconds in bInterval, and marks Vario Ultra devices as needing it. Signed-off-by: Samuel Thibault Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 1d0043dc34e4..de2a722fe3cf 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -50,4 +50,10 @@ /* device can't handle Link Power Management */ #define USB_QUIRK_NO_LPM BIT(10) +/* + * Device reports its bInterval as linear frames instead of the + * USB 2.0 calculation. + */ +#define USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL BIT(11) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 4748cf2bdee373fba9cec3f1f7e95928ae21c100 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Sat, 23 Jul 2016 09:46:39 +0200 Subject: sched/debug: Make the "Preemption disabled at ..." message more useful This message is currently really useless since it always prints a value that comes from the printk() we just did, e.g.: BUG: sleeping function called from invalid context at mm/slab.h:388 in_atomic(): 0, irqs_disabled(): 0, pid: 31996, name: trinity-c1 Preemption disabled at:[] down_trylock+0x13/0x80 BUG: sleeping function called from invalid context at include/linux/freezer.h:56 in_atomic(): 0, irqs_disabled(): 0, pid: 31996, name: trinity-c1 Preemption disabled at:[] console_unlock+0x2f7/0x930 Here, both down_trylock() and console_unlock() is somewhere in the printk() path. We should save the value before calling printk() and use the saved value instead. That immediately reveals the offending callsite: BUG: sleeping function called from invalid context at mm/slab.h:388 in_atomic(): 0, irqs_disabled(): 0, pid: 14971, name: trinity-c2 Preemption disabled at:[] rhashtable_walk_start+0x46/0x150 Bug report: http://marc.info/?l=linux-netdev&m=146925979821849&w=2 Change-Id: I5b08294385a2ac625dbf28d1f18ffd164aedabe0 Signed-off-by: Vegard Nossum Cc: Andrew Morton Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rusty Russel Cc: Thomas Gleixner Signed-off-by: Ingo Molnar [mkhaja@codeaurora.org: Fix trivial merge conflict] Git-commit: d1c6d149cf04d6c7c3c3ebf4b66c82500cbcf6e1 Git-repo: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Signed-off-by: Mohammed Khajapasha --- include/linux/sched.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3a7521064fe3..e32cab9fe290 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3246,6 +3246,15 @@ static inline void cond_resched_rcu(void) #endif } +static inline unsigned long get_preempt_disable_ip(struct task_struct *p) +{ +#ifdef CONFIG_DEBUG_PREEMPT + return p->preempt_disable_ip; +#else + return 0; +#endif +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPT, -- cgit v1.2.3 From 510b819279cb6d4b803059ef66ec1bc05e187a04 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Thu, 14 Jan 2016 15:18:33 -0800 Subject: UPSTREAM: mm: add PHYS_PFN, use it in __phys_to_pfn() (cherry pick from commit 8f235d1a3eb7198affe7cadf676a10afb8a46a1a) __phys_to_pfn and __pfn_to_phys are symmetric, PHYS_PFN and PFN_PHYS are semmetric: - y = (phys_addr_t)x << PAGE_SHIFT - y >> PAGE_SHIFT = (phys_add_t)x - (unsigned long)(y >> PAGE_SHIFT) = x [akpm@linux-foundation.org: use macro arg name `x'] [arnd@arndb.de: include linux/pfn.h for PHYS_PFN definition] Signed-off-by: Chen Gang Cc: Oleg Nesterov Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Bug: 20045882 Bug: 19198045 Change-Id: If968d2246b381b9e5d6446e9d6d9fa45bb718e91 --- include/linux/pfn.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pfn.h b/include/linux/pfn.h index 7646637221f3..97f3e88aead4 100644 --- a/include/linux/pfn.h +++ b/include/linux/pfn.h @@ -9,5 +9,6 @@ #define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) #define PFN_DOWN(x) ((x) >> PAGE_SHIFT) #define PFN_PHYS(x) ((phys_addr_t)(x) << PAGE_SHIFT) +#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT)) #endif -- cgit v1.2.3 From 6d9f602c728b3f41f24a965ef60db0f273f51cbe Mon Sep 17 00:00:00 2001 From: Abhijit Kulkarni Date: Thu, 16 Feb 2017 19:02:17 -0800 Subject: msm: dsi: Turn off supplies in low power state This change allows certain phy supplies to be turned off when display transtions to low power state. This change adds funtionality to check each supplies setting and accordingly turns off the the regulator if it is allowed in low power state. CRs-Fixed: 2009863 Change-Id: I764a8e65246b5de733f27e4f73d966b19039895d Signed-off-by: Abhijit Kulkarni --- include/linux/mdss_io_util.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mdss_io_util.h b/include/linux/mdss_io_util.h index 5b2587b28737..3cca007e618c 100644 --- a/include/linux/mdss_io_util.h +++ b/include/linux/mdss_io_util.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2012, 2016, The Linux Foundation. All rights reserved. +/* Copyright (c) 2012, 2016-2017, The Linux Foundation. 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 version 2 and @@ -58,6 +58,8 @@ struct dss_vreg { int post_on_sleep; int pre_off_sleep; int post_off_sleep; + bool lp_disable_allowed; + bool disabled; }; struct dss_gpio { -- cgit v1.2.3 From 240cf80a7e4e8ab80da5b1f3920c18a6a5295627 Mon Sep 17 00:00:00 2001 From: Prasad Malisetty Date: Fri, 31 Mar 2017 12:40:48 +0530 Subject: mhi: core: Enable mhi_dev_net interface channels Enable 46, 47 channels for mhi_dev_net interface. mhi_dev_net client uses read and write channels to communicate mhi host rmnet interface over PCIe link. CRs-Fixed: 2029099 Change-Id: Ifdda4b1a139751bd2b36143d9125068f34fec9e5 Signed-off-by: Prasad Malisetty --- include/linux/msm_mhi.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msm_mhi.h b/include/linux/msm_mhi.h index b9fd610f92da..029d2ba69cce 100644 --- a/include/linux/msm_mhi.h +++ b/include/linux/msm_mhi.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2014-2016, The Linux Foundation. All rights reserved. +/* Copyright (c) 2014-2017, The Linux Foundation. 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 version 2 and @@ -61,7 +61,9 @@ enum MHI_CLIENT_CHANNEL { MHI_CLIENT_CSVT_IN = 43, MHI_CLIENT_SMCT_OUT = 44, MHI_CLIENT_SMCT_IN = 45, - MHI_CLIENT_RESERVED_1_LOWER = 46, + MHI_CLIENT_IP_SW_4_OUT = 46, + MHI_CLIENT_IP_SW_4_IN = 47, + MHI_CLIENT_RESERVED_1_LOWER = 48, MHI_CLIENT_RESERVED_1_UPPER = 99, MHI_CLIENT_IP_HW_0_OUT = 100, MHI_CLIENT_IP_HW_0_IN = 101, -- cgit v1.2.3 From e246a2f11fcca7702dbf526da235d37c828742ea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Tue, 27 Sep 2016 23:57:58 -0700 Subject: UPSTREAM: ipv6 addrconf: implement RFC7559 router solicitation backoff MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This implements: https://tools.ietf.org/html/rfc7559 Backoff is performed according to RFC3315 section 14: https://tools.ietf.org/html/rfc3315#section-14 We allow setting /proc/sys/net/ipv6/conf/*/router_solicitations to a negative value meaning an unlimited number of retransmits, and we make this the new default (inline with the RFC). We also add a new setting: /proc/sys/net/ipv6/conf/*/router_solicitation_max_interval defaulting to 1 hour (per RFC recommendation). Signed-off-by: Maciej Żenczykowski Acked-by: Erik Kline Signed-off-by: David S. Miller (cherry picked from commit bd11f0741fa5a2c296629898ad07759dd12b35bb in DaveM's net-next/master, should make Linus' tree in 4.9-rc1) Change-Id: Ia32cdc5c61481893ef8040734e014bf2229fc39e --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 1182f0e21697..a0fc3cf932af 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -18,6 +18,7 @@ struct ipv6_devconf { __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; + __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; -- cgit v1.2.3 From 80ded5dd4b5e9d5d6c60701f8664013a4a77de78 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 10 Aug 2016 16:29:21 +0100 Subject: drm: edid: HDMI 2.0 HF-VSDB block parsing Adds parsing for HDMI 2.0 'HDMI Forum Vendor Specific Data Block'. This block is present in some HDMI 2.0 EDID's and gives information about scrambling support, SCDC, 3D Views, and others. Parsed parameters are stored in drm_connector structure. Change-Id: I018cfefea2fd3827d5f83c8e5717ebd95e497519 Signed-off-by: Jose Abreu Cc: Carlos Palminha Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Patch-mainline: dri-devel @ 10 Aug 2016 16:29 Signed-off-by: Jin Li Signed-off-by: Abhinav Kumar --- include/linux/hdmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index e9744202fa29..6e234093d435 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -35,6 +35,7 @@ enum hdmi_infoframe_type { }; #define HDMI_IEEE_OUI 0x000c03 +#define HDMI_IEEE_OUI_HF 0xc45dd8 #define HDMI_INFOFRAME_HEADER_SIZE 4 #define HDMI_AVI_INFOFRAME_SIZE 13 #define HDMI_SPD_INFOFRAME_SIZE 25 -- cgit v1.2.3 From c3e9d3d01d5643e7fafbe33e333c1f6fd18254a9 Mon Sep 17 00:00:00 2001 From: Abhijeet Dharmapurikar Date: Tue, 4 Apr 2017 19:37:09 -0700 Subject: qpnp-revid: add smb1355 definitions Add revision definitions for smb1355 i2c charger chip. Change-Id: I60429c6462a2faa70df71d3440afe696a13fcab0 Signed-off-by: Abhijeet Dharmapurikar --- include/linux/qpnp/qpnp-revid.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qpnp/qpnp-revid.h b/include/linux/qpnp/qpnp-revid.h index 7254f4d16176..7fca674b6230 100644 --- a/include/linux/qpnp/qpnp-revid.h +++ b/include/linux/qpnp/qpnp-revid.h @@ -235,6 +235,9 @@ /* SMB1381 */ #define SMB1381_SUBTYPE 0x17 +/* SMB1355 */ +#define SMB1355_SUBTYPE 0x1C + struct pmic_revid_data { u8 rev1; u8 rev2; -- cgit v1.2.3 From 42462d23e60b89a3c2f7d8d63f5f4e464ba77727 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 23 Mar 2017 18:24:19 +0100 Subject: KVM: kvm_io_bus_unregister_dev() should never fail commit 90db10434b163e46da413d34db8d0e77404cc645 upstream. No caller currently checks the return value of kvm_io_bus_unregister_dev(). This is evil, as all callers silently go on freeing their device. A stale reference will remain in the io_bus, getting at least used again, when the iobus gets teared down on kvm_destroy_vm() - leading to use after free errors. There is nothing the callers could do, except retrying over and over again. So let's simply remove the bus altogether, print an error and make sure no one can access this broken bus again (returning -ENOMEM on any attempt to access it). Fixes: e93f8a0f821e ("KVM: convert io_bus to SRCU") Reported-by: Dmitry Vyukov Reviewed-by: Cornelia Huck Signed-off-by: David Hildenbrand Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c923350ca20a..d7ce4e3280db 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -182,8 +182,8 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); -int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, - struct kvm_io_device *dev); +void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev); #ifdef CONFIG_KVM_ASYNC_PF struct kvm_async_pf { -- cgit v1.2.3 From 2ecedf5dc75bc770ec09bd2238e798063aeafc4b Mon Sep 17 00:00:00 2001 From: Ajay Agarwal Date: Tue, 7 Feb 2017 16:40:09 +0530 Subject: sound: usb: Add support for parsing AudioStreaming intf for BADD devices BADD(Basic Audio Device Definition) is a subset of UAC3 specifications. It defines standard profiles which provide specific attributes of class descriptors. BADD audio device provides profile id and BADD supporting host will infer attributes from profile-id. Currently USB Audio Host driver has support for UAC1 and UAC2 devices. To handle BADD 3.0 devices, AudioControl and AudioStreaming Interfaces have to be properly parsed. The Host has to derive all class-specific information based on the profile ID that the device exposes. Add support for parsing the AudioStreaming interfaces exposed by the device. Change-Id: I726bbb735708fe8e395011c7228a73d5f65c092d Signed-off-by: Ajay Agarwal --- include/linux/usb/audio-v3.h | 72 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100644 include/linux/usb/audio-v3.h (limited to 'include/linux') diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h new file mode 100644 index 000000000000..04adabf5648d --- /dev/null +++ b/include/linux/usb/audio-v3.h @@ -0,0 +1,72 @@ +/* + * Copyright (c) 2017, The Linux Foundation. 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 version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This file holds USB constants and structures defined + * by the USB Device Class Definition for Audio Devices in version 3.0. + * Comments below reference relevant sections of the documents contained + * in http://www.usb.org/developers/docs/devclass_docs/USB_Audio_v3.0.zip + */ + +#ifndef __LINUX_USB_AUDIO_V3_H +#define __LINUX_USB_AUDIO_V3_H + +#include + +#define BADD_MAXPSIZE_SYNC_MONO_16 0x0060 +#define BADD_MAXPSIZE_SYNC_MONO_24 0x0090 +#define BADD_MAXPSIZE_SYNC_STEREO_16 0x00c0 +#define BADD_MAXPSIZE_SYNC_STEREO_24 0x0120 + +#define BADD_MAXPSIZE_ASYNC_MONO_16 0x0062 +#define BADD_MAXPSIZE_ASYNC_MONO_24 0x0093 +#define BADD_MAXPSIZE_ASYNC_STEREO_16 0x00c4 +#define BADD_MAXPSIZE_ASYNC_STEREO_24 0x0126 + +#define BIT_RES_16_BIT 0x10 +#define BIT_RES_24_BIT 0x18 + +#define SUBSLOTSIZE_16_BIT 0x02 +#define SUBSLOTSIZE_24_BIT 0x03 + +#define BADD_SAMPLING_RATE 48000 + +#define NUM_CHANNELS_MONO 1 +#define NUM_CHANNELS_STEREO 2 +#define BADD_CH_CONFIG_MONO 0 +#define BADD_CH_CONFIG_STEREO 3 + +#define FULL_ADC_PROFILE 0x01 + +/* BADD Profile IDs */ +#define PROF_GENERIC_IO 0x20 +#define PROF_HEADPHONE 0x21 +#define PROF_SPEAKER 0x22 +#define PROF_MICROPHONE 0x23 +#define PROF_HEADSET 0x24 +#define PROF_HEADSET_ADAPTER 0x25 +#define PROF_SPEAKERPHONE 0x26 + +/* BADD Entity IDs */ +#define BADD_OUT_TERM_ID_BAOF 0x03 +#define BADD_OUT_TERM_ID_BAIF 0x06 +#define BADD_IN_TERM_ID_BAOF 0x01 +#define BADD_IN_TERM_ID_BAIF 0x04 +#define BADD_FU_ID_BAOF 0x02 +#define BADD_FU_ID_BAIF 0x05 +#define BADD_CLOCK_SOURCE 0x09 +#define BADD_FU_ID_BAIOF 0x07 +#define BADD_MU_ID_BAIOF 0x08 + +#define UAC_BIDIR_TERMINAL_HEADSET 0x0402 +#define UAC_BIDIR_TERMINAL_SPEAKERPHONE 0x0403 + +#endif /* __LINUX_USB_AUDIO_V3_H */ -- cgit v1.2.3 From 2b7792c59846628ea08d683858ecb1849f899888 Mon Sep 17 00:00:00 2001 From: Ajay Agarwal Date: Tue, 7 Feb 2017 18:41:34 +0530 Subject: sound: usb: Add support for parsing AudioControl intf for BADD devices BADD 3.0 devices support three types of topologies; Basic I/P, Basic O/P, and BASIC I/P. Accordingly, various units and terminals have to be parsed which are not exposed by the device and host must be able to figure out various class-specific descriptors based on the profile ID of the device. This patch adds this logic to build various units and terminals of the AudioControl interface of a BADD device. Change-Id: Ib52f884133cdf6e0ec95f49095c14f7d005a5356 Signed-off-by: Ajay Agarwal --- include/linux/usb/audio-v3.h | 108 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 104 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h index 04adabf5648d..f2322f3c74f7 100644 --- a/include/linux/usb/audio-v3.h +++ b/include/linux/usb/audio-v3.h @@ -21,6 +21,10 @@ #include +#define UAC3_MIXER_UNIT_V3 0x05 +#define UAC3_FEATURE_UNIT_V3 0x07 +#define UAC3_CLOCK_SOURCE 0x0b + #define BADD_MAXPSIZE_SYNC_MONO_16 0x0060 #define BADD_MAXPSIZE_SYNC_MONO_24 0x0090 #define BADD_MAXPSIZE_SYNC_STEREO_16 0x00c0 @@ -39,10 +43,12 @@ #define BADD_SAMPLING_RATE 48000 -#define NUM_CHANNELS_MONO 1 -#define NUM_CHANNELS_STEREO 2 -#define BADD_CH_CONFIG_MONO 0 -#define BADD_CH_CONFIG_STEREO 3 +#define NUM_CHANNELS_MONO 1 +#define NUM_CHANNELS_STEREO 2 +#define BADD_CH_CONFIG_MONO 0 +#define BADD_CH_CONFIG_STEREO 3 +#define CLUSTER_ID_MONO 0x0001 +#define CLUSTER_ID_STEREO 0x0002 #define FULL_ADC_PROFILE 0x01 @@ -69,4 +75,98 @@ #define UAC_BIDIR_TERMINAL_HEADSET 0x0402 #define UAC_BIDIR_TERMINAL_SPEAKERPHONE 0x0403 +#define NUM_BADD_DESCS 7 + +struct uac3_input_terminal_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDescriptorSubtype; + __u8 bTerminalID; + __u16 wTerminalType; + __u8 bAssocTerminal; + __u8 bCSourceID; + __u32 bmControls; + __u16 wClusterDescrID; + __u16 wExTerminalDescrID; + __u16 wConnectorsDescrID; + __u16 wTerminalDescrStr; +} __packed; + +#define UAC3_DT_INPUT_TERMINAL_SIZE 0x14 + +extern struct uac3_input_terminal_descriptor badd_baif_in_term_desc; +extern struct uac3_input_terminal_descriptor badd_baof_in_term_desc; + +struct uac3_output_terminal_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDescriptorSubtype; + __u8 bTerminalID; + __u16 wTerminalType; + __u8 bAssocTerminal; + __u8 bSourceID; + __u8 bCSourceID; + __u32 bmControls; + __u16 wExTerminalDescrID; + __u16 wConnectorsDescrID; + __u16 wTerminalDescrStr; +} __packed; + +#define UAC3_DT_OUTPUT_TERMINAL_SIZE 0x13 + +extern struct uac3_output_terminal_descriptor badd_baif_out_term_desc; +extern struct uac3_output_terminal_descriptor badd_baof_out_term_desc; + +extern __u8 monoControls[]; +extern __u8 stereoControls[]; +extern __u8 badd_mu_src_ids[]; + +struct uac3_mixer_unit_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDescriptorSubtype; + __u8 bUnitID; + __u8 bNrInPins; + __u8 *baSourceID; + __u16 wClusterDescrID; + __u8 bmMixerControls; + __u32 bmControls; + __u16 wMixerDescrStr; +} __packed; + +#define UAC3_DT_MIXER_UNIT_SIZE 0x10 + +extern struct uac3_mixer_unit_descriptor badd_baiof_mu_desc; + +struct uac3_feature_unit_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDescriptorSubtype; + __u8 bUnitID; + __u8 bSourceID; + __u8 *bmaControls; + __u16 wFeatureDescrStr; +} __packed; + +extern struct uac3_feature_unit_descriptor badd_baif_fu_desc; +extern struct uac3_feature_unit_descriptor badd_baof_fu_desc; +extern struct uac3_feature_unit_descriptor badd_baiof_fu_desc; + +struct uac3_clock_source_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDescriptorSubtype; + __u8 bClockID; + __u8 bmAttributes; + __u32 bmControls; + __u8 bReferenceTerminal; + __u16 wClockSourceStr; +} __packed; + +#define UAC3_DT_CLOCK_SRC_SIZE 0x0c + +extern struct uac3_clock_source_descriptor badd_clock_desc; + +extern void *badd_desc_list[]; + #endif /* __LINUX_USB_AUDIO_V3_H */ -- cgit v1.2.3 From 073d867c01294d04f6ca9c1c163f4d05ad4d3878 Mon Sep 17 00:00:00 2001 From: Shashank Sharma Date: Mon, 17 Oct 2016 17:34:39 +0530 Subject: drivers/video: Add new aspect ratios for HDMI 2.0 HDMI 2.0/CEA-861-F introduces two new aspect ratios: - 64:27 - 256:135 This patch adds enumeration for the new aspect ratios in the existing aspect ratio list. V2: rebase V3: rebase V4: Added r-b from Jose, Ack by Tomi Change-Id: Ie90d43e4088a7c19274fe2aa25aa40d38683f584 Signed-off-by: Shashank Sharma Reviewed-by: Sean Paul Reviewed-by: Jose Abreu Acked-by: Tomi Valkeinen Cc: Daniel Vetter Cc: Emil Velikov Signed-off-by: Daniel Vetter Git-commit: a6e78b3e1406575323b30b65890ee3c29930fb27 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Signed-off-by: Abhinav Kumar --- include/linux/hdmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 6e234093d435..bc38b99a9fc9 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -79,6 +79,8 @@ enum hdmi_picture_aspect { HDMI_PICTURE_ASPECT_NONE, HDMI_PICTURE_ASPECT_4_3, HDMI_PICTURE_ASPECT_16_9, + HDMI_PICTURE_ASPECT_64_27, + HDMI_PICTURE_ASPECT_256_135, HDMI_PICTURE_ASPECT_RESERVED, }; -- cgit v1.2.3 From 16793068c2a21bd4173d80615106f74f10aed7af Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:02 +0300 Subject: cfg80211: Add Fast Initial Link Setup (FILS) auth algs This defines authentication algorithms for FILS (IEEE 802.11ai). Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg Git-commit: 631810603a20874554b2f17adf42b72d0f15eda5 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git CRs-Fixed: 2028536 Change-Id: I530913c84f2c3e678e83144ac474195184f4dd3b Signed-off-by: Vidyullatha Kanchanapally --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 452c0b0d2f32..d8f4316167d8 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1535,6 +1535,9 @@ struct ieee80211_vht_operation { #define WLAN_AUTH_SHARED_KEY 1 #define WLAN_AUTH_FT 2 #define WLAN_AUTH_SAE 3 +#define WLAN_AUTH_FILS_SK 4 +#define WLAN_AUTH_FILS_SK_PFS 5 +#define WLAN_AUTH_FILS_PK 6 #define WLAN_AUTH_LEAP 128 #define WLAN_AUTH_CHALLENGE_LEN 128 -- cgit v1.2.3 From deb005f7956bedcdb116681e8a41f93944df1584 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:03 +0300 Subject: cfg80211: Add KEK/nonces for FILS association frames The new nl80211 attributes can be used to provide KEK and nonces to allow the driver to encrypt and decrypt FILS (Re)Association Request/Response frames in station mode. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg Git-commit: 348bd456699801920a309c66e382380809fbdf41 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git CRs-Fixed: 2028536 Change-Id: I60ed3727279029e72b9dea18b3e5683a16d2cc04 Signed-off-by: Vidyullatha Kanchanapally --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d8f4316167d8..ddba92d46eba 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2035,6 +2035,9 @@ enum ieee80211_key_len { #define IEEE80211_GCMP_MIC_LEN 16 #define IEEE80211_GCMP_PN_LEN 6 +#define FILS_NONCE_LEN 16 +#define FILS_MAX_KEK_LEN 64 + /* Public action codes */ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, -- cgit v1.2.3 From 839e05b97ae9fd27b2c7e58df5ac8e6ce7aba513 Mon Sep 17 00:00:00 2001 From: Ray Zhang Date: Tue, 28 Mar 2017 23:43:44 +0800 Subject: msm: ext_disp: add audio ops to notify codec status In some cases the audio codec is not ready when display is up, while the interface driver doesn't know how to respond without knowing audio codec's status. So add an audio ops to support this case. CRs-Fixed: 2010135 Change-Id: I4a19f57858a5ed2999daefc0192d62bef332453b Signed-off-by: Ray Zhang --- include/linux/msm_ext_display.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msm_ext_display.h b/include/linux/msm_ext_display.h index fc53e861eba4..9a03b79e09d7 100644 --- a/include/linux/msm_ext_display.h +++ b/include/linux/msm_ext_display.h @@ -114,6 +114,7 @@ struct msm_ext_disp_intf_ops { * @cable_status: cable connected/disconnected * @get_intf_id: id of connected interface * @acknowledge: acknowledge audio status + * @codec_ready: notify when codec is ready */ struct msm_ext_disp_audio_codec_ops { int (*audio_info_setup)(struct platform_device *pdev, @@ -124,6 +125,7 @@ struct msm_ext_disp_audio_codec_ops { int (*get_intf_id)(struct platform_device *pdev); void (*teardown_done)(struct platform_device *pdev); int (*acknowledge)(struct platform_device *pdev, u32 ack); + void (*codec_ready)(struct platform_device *pdev); }; /* -- cgit v1.2.3 From c079e157fd833cf3650705dc5caea5dd867e55f8 Mon Sep 17 00:00:00 2001 From: Patrick Fay Date: Fri, 14 Apr 2017 10:14:02 -0700 Subject: Perf: arm64: disable irq for hotplug offline Currently the hotplug notifier calls cpu_pmu_enable_percpu_irq when a CPU comes online. The notifier doesn't have a corresponding call to cpu_pmu_disable_percpu_irq when the CPU goes offline. Change the code to follow what was done in 3.18 including tracking whether the PMU is active and the IRQ number in use. Change-Id: I1835fb543eb483713a30eb6c0ccd4e4a4b9908be Signed-off-by: Patrick Fay --- include/linux/perf/arm_pmu.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 654bb97a3188..5bc4836af286 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -77,6 +77,12 @@ struct pmu_hw_events { struct arm_pmu *percpu_pmu; }; +enum armpmu_pmu_states { + ARM_PMU_STATE_OFF, + ARM_PMU_STATE_RUNNING, + ARM_PMU_STATE_GOING_DOWN, +}; + struct arm_pmu { struct pmu pmu; cpumask_t active_irqs; @@ -101,6 +107,8 @@ struct arm_pmu { void (*free_irq)(struct arm_pmu *); int (*map_event)(struct perf_event *event); int num_events; + int pmu_state; + int percpu_irq; atomic_t active_events; struct mutex reserve_mutex; u64 max_period; -- cgit v1.2.3 From 5c69adad61e27f467fa8e1671633e455741e3fae Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 15 Mar 2016 14:56:27 -0700 Subject: mm/page_poison.c: enable PAGE_POISONING as a separate option Page poisoning is currently set up as a feature if architectures don't have architecture debug page_alloc to allow unmapping of pages. It has uses apart from that though. Clearing of the pages on free provides an increase in security as it helps to limit the risk of information leaks. Allow page poisoning to be enabled as a separate option independent of kernel_map pages since the two features do separate work. Because of how hiberanation is implemented, the checks on alloc cannot occur if hibernation is enabled. The runtime alloc checks can also be enabled with an option when !HIBERNATION. Credit to Grsecurity/PaX team for inspiring this work Change-Id: I77a36f844ddae54695089c98a97bf0a6e226a025 Signed-off-by: Laura Abbott Cc: Rafael J. Wysocki Cc: "Kirill A. Shutemov" Cc: Vlastimil Babka Cc: Michal Hocko Cc: Kees Cook Cc: Mathias Krause Cc: Dave Hansen Cc: Jianyu Zhan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Git-commit: 8823b1dbc05fab1a8bec275eeae4709257c2661d Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Signed-off-by: Vinayak Menon --- include/linux/mm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 186d2ab9cd13..8e4e3debce84 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2146,6 +2146,15 @@ static inline void vm_stat_account(struct mm_struct *mm, } #endif /* CONFIG_PROC_FS */ +#ifdef CONFIG_PAGE_POISONING +extern bool page_poisoning_enabled(void); +extern void kernel_poison_pages(struct page *page, int numpages, int enable); +#else +static inline bool page_poisoning_enabled(void) { return false; } +static inline void kernel_poison_pages(struct page *page, int numpages, + int enable) { } +#endif + #ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; extern void __kernel_map_pages(struct page *page, int numpages, int enable); -- cgit v1.2.3 From 2c00b603db67af40aa0b02c834cc58fec98d3023 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 15 Mar 2016 14:56:30 -0700 Subject: mm/page_poisoning.c: allow for zero poisoning By default, page poisoning uses a poison value (0xaa) on free. If this is changed to 0, the page is not only sanitized but zeroing on alloc with __GFP_ZERO can be skipped as well. The tradeoff is that detecting corruption from the poisoning is harder to detect. This feature also cannot be used with hibernation since pages are not guaranteed to be zeroed after hibernation. Credit to Grsecurity/PaX team for inspiring this work Change-Id: If7116e6bff246abbafc38bdfeb3601d3ea063ad2 Signed-off-by: Laura Abbott Acked-by: Rafael J. Wysocki Cc: "Kirill A. Shutemov" Cc: Vlastimil Babka Cc: Michal Hocko Cc: Kees Cook Cc: Mathias Krause Cc: Dave Hansen Cc: Jianyu Zhan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Git-commit: 1414c7f4f7d72d138fff35f00151d15749b5beda Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Signed-off-by: Vinayak Menon --- include/linux/mm.h | 2 ++ include/linux/poison.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e4e3debce84..d9fe27c8a57e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2149,10 +2149,12 @@ static inline void vm_stat_account(struct mm_struct *mm, #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); +extern bool page_is_poisoned(struct page *page); #else static inline bool page_poisoning_enabled(void) { return false; } static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } +static inline bool page_is_poisoned(struct page *page) { return false; } #endif #ifdef CONFIG_DEBUG_PAGEALLOC diff --git a/include/linux/poison.h b/include/linux/poison.h index 317e16de09e5..199ffec4bdf3 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -30,7 +30,11 @@ #define TIMER_ENTRY_STATIC ((void *) 0x74737461) /********** mm/debug-pagealloc.c **********/ +#ifdef CONFIG_PAGE_POISONING_ZERO +#define PAGE_POISON 0x00 +#else #define PAGE_POISON 0xaa +#endif /********** mm/slab.c **********/ /* -- cgit v1.2.3 From 49118fe6a32a49d198128a6dd1d6bfd0e3b189f8 Mon Sep 17 00:00:00 2001 From: Vinayak Menon Date: Fri, 31 Mar 2017 11:13:06 +1100 Subject: mm: enable page poisoning early at boot On SPARSEMEM systems page poisoning is enabled after buddy is up, because of the dependency on page extension init. This causes the pages released by free_all_bootmem not to be poisoned. This either delays or misses the identification of some issues because the pages have to undergo another cycle of alloc-free-alloc for any corruption to be detected. Enable page poisoning early by getting rid of the PAGE_EXT_DEBUG_POISON flag. Since all the free pages will now be poisoned, the flag need not be verified before checking the poison during an alloc. Link: http://lkml.kernel.org/r/1490358246-11001-1-git-send-email-vinmenon@codeaurora.org Acked-by: Laura Abbott Tested-by: Laura Abbott Cc: Joonsoo Kim Cc: Michal Hocko Cc: Akinobu Mita Signed-off-by: Andrew Morton [vinmenon@codeaurora.org: resolve trivial merge conflicts. Remove the redundant free pages RO feature from the page_poison.c file which is the reason for conflicts + squash the addendum commit 40961ef8d65f51093bc94de110b97b590b6b9275 ('mm-enable-page-poisoning-early-at-boot-v2')] Git-commit: c5b7cd344fd6341e6db79e55c0f1f4d1d9c67a7e Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git Change-Id: I1bb1f99d3a2e1135131911905e0916c837ba9d8a Signed-off-by: Vinayak Menon --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d9fe27c8a57e..3c10d4638646 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2306,7 +2306,6 @@ extern void copy_user_huge_page(struct page *dst, struct page *src, #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ extern struct page_ext_operations debug_guardpage_ops; -extern struct page_ext_operations page_poisoning_ops; #ifdef CONFIG_DEBUG_PAGEALLOC extern unsigned int _debug_guardpage_minorder; -- cgit v1.2.3 From d8c98bb6aee804c47b6462d3012aae38d0b043e0 Mon Sep 17 00:00:00 2001 From: Vinayak Menon Date: Fri, 14 Apr 2017 12:15:18 +0530 Subject: mm: separate out the invocation of lowmemorykiller shrinker The commit '6b4f77 (mm: vmscan: invoke slab shrinkers from shrink_zone())' fixed the invocation of shrinkers but resulted in lowmemorykiller shrinker being called more. Reduce the number of lowmemorykiller shrinker invocations by separating out the lowmemorykiller shrinker from shrink_slab. This will make lowmemorykiller invoked only once for all zones reclaimed in the direct reclaim path, and once for each zone in the kswap path. As a consequence the eligible pages passed to shrink_slab_lmk is now the reclaimable pages of all zones. Reducing the number of lowmemorykiller invocations reduces the unnecessary time spent in lowmemorykiller and thus contention or failures on lowmemorykiller's scan_mutex. Change-Id: Iaabb9e441711f1dc804980b5853b64b3f214698d Signed-off-by: Vinayak Menon --- include/linux/shrinker.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 4fcacd915d45..e77f648f9662 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -66,6 +66,7 @@ struct shrinker { /* Flags */ #define SHRINKER_NUMA_AWARE (1 << 0) #define SHRINKER_MEMCG_AWARE (1 << 1) +#define SHRINKER_LMK (1 << 2) extern int register_shrinker(struct shrinker *); extern void unregister_shrinker(struct shrinker *); -- cgit v1.2.3 From e5316ea0f17e88eda0b2931f6e53cdfcca066173 Mon Sep 17 00:00:00 2001 From: Ankit Sharma Date: Wed, 22 Mar 2017 19:04:52 +0530 Subject: leds: qpnp-flash-v2: Enable charger mitigation When the charger mitigation is configured based on SW, enable it locally when the total brightness (or current level) of all torch/flash LED devices is greater than 1 A. CRs-Fixed: 2011199 Change-Id: I8336b3201f0780855c3dc3633179c398b9f62162 Signed-off-by: Ankit Sharma --- include/linux/leds-qpnp-flash.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds-qpnp-flash.h b/include/linux/leds-qpnp-flash.h index 4b5a339970fa..1fe6e1709fa6 100644 --- a/include/linux/leds-qpnp-flash.h +++ b/include/linux/leds-qpnp-flash.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2016, The Linux Foundation. All rights reserved. +/* Copyright (c) 2016-2017, The Linux Foundation. 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 version 2 and @@ -18,7 +18,6 @@ #define ENABLE_REGULATOR BIT(0) #define DISABLE_REGULATOR BIT(1) #define QUERY_MAX_CURRENT BIT(2) -#define PRE_FLASH BIT(3) #define FLASH_LED_PREPARE_OPTIONS_MASK GENMASK(3, 0) -- cgit v1.2.3 From 4f8307107888499c15838aa83c5656c7cd3beaf4 Mon Sep 17 00:00:00 2001 From: Liam Mark Date: Mon, 3 Apr 2017 16:43:53 -0700 Subject: iommu/arm-smmu: add support to configure IOVA range Allow clients to specify the IOVA range for fastmap clients via the DOMAIN_ATTR_GEOMETRY domain attribute. Presently fastmap only allocates page tables for the IOVA range specified during the create mapping call. However clients may want to use IOVA addresses outside this range, such as for their calls to iommu_map. So allow clients to extend the available IOVA space by setting the DOMAIN_ATTR_GEOMETRY domain attribute's iommu_domain_geometry.aperture_start to the new start address of the IOVA space and by setting iommu_domain_geometry.aperture_end to the new end address of the IOVA space. The new IOVA space created by iommu_domain_geometry.aperture_start and iommu_domain_geometry.aperture_end will be a superset of the IOVA range which was created through the create mapping call. The DOMAIN_ATTR_GEOMETRY domain attribute can only be set before attaching. Calls to set the DOMAIN_ATTR_GEOMETRY domain attribute can only be used to extend the IOVA space, it cannot shrink the range. Note that extending the IOVA range will not change the range of IOVA addresses which will be available to the DMA APIs. Change-Id: Ib389e019a022d98417884002de08115fb0fc9384 Signed-off-by: Liam Mark --- include/linux/io-pgtable-fast.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable-fast.h b/include/linux/io-pgtable-fast.h index 029e11f9919b..6a56f0039f15 100644 --- a/include/linux/io-pgtable-fast.h +++ b/include/linux/io-pgtable-fast.h @@ -37,7 +37,7 @@ void av8l_fast_unmap_public(av8l_fast_iopte *ptep, size_t size); #define AV8L_FAST_PTE_UNMAPPED_NEED_TLBI 0xa void av8l_fast_clear_stale_ptes(av8l_fast_iopte *puds, u64 base, - u64 end, bool skip_sync); + u64 start, u64 end, bool skip_sync); void av8l_register_notify(struct notifier_block *nb); #else /* !CONFIG_IOMMU_IO_PGTABLE_FAST_PROVE_TLB */ @@ -46,6 +46,7 @@ void av8l_register_notify(struct notifier_block *nb); static inline void av8l_fast_clear_stale_ptes(av8l_fast_iopte *puds, u64 base, + u64 start, u64 end, bool skip_sync) { -- cgit v1.2.3 From 9e242ec92f951165b52de630ca8ecc6a2748f655 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2016 11:49:09 -0500 Subject: BACKPORT: [UPSTREAM] mbcache2: reimplement mbcache (Cherry-pick from commit f9a61eb4e2471c56a63cd804c7474128138c38ac) Original mbcache was designed to have more features than what ext? filesystems ended up using. It supported entry being in more hashes, it had a home-grown rwlocking of each entry, and one cache could cache entries from multiple filesystems. This genericity also resulted in more complex locking, larger cache entries, and generally more code complexity. This is reimplementation of the mbcache functionality to exactly fit the purpose ext? filesystems use it for. Cache entries are now considerably smaller (7 instead of 13 longs), the code is considerably smaller as well (414 vs 913 lines of code), and IMO also simpler. The new code is also much more lightweight. I have measured the speed using artificial xattr-bench benchmark, which spawns P processes, each process sets xattr for F different files, and the value of xattr is randomly chosen from a pool of V values. Averages of runtimes for 5 runs for various combinations of parameters are below. The first value in each cell is old mbache, the second value is the new mbcache. V=10 F\P 1 2 4 8 16 32 64 10 0.158,0.157 0.208,0.196 0.500,0.277 0.798,0.400 3.258,0.584 13.807,1.047 61.339,2.803 100 0.172,0.167 0.279,0.222 0.520,0.275 0.825,0.341 2.981,0.505 12.022,1.202 44.641,2.943 1000 0.185,0.174 0.297,0.239 0.445,0.283 0.767,0.340 2.329,0.480 6.342,1.198 16.440,3.888 V=100 F\P 1 2 4 8 16 32 64 10 0.162,0.153 0.200,0.186 0.362,0.257 0.671,0.496 1.433,0.943 3.801,1.345 7.938,2.501 100 0.153,0.160 0.221,0.199 0.404,0.264 0.945,0.379 1.556,0.485 3.761,1.156 7.901,2.484 1000 0.215,0.191 0.303,0.246 0.471,0.288 0.960,0.347 1.647,0.479 3.916,1.176 8.058,3.160 V=1000 F\P 1 2 4 8 16 32 64 10 0.151,0.129 0.210,0.163 0.326,0.245 0.685,0.521 1.284,0.859 3.087,2.251 6.451,4.801 100 0.154,0.153 0.211,0.191 0.276,0.282 0.687,0.506 1.202,0.877 3.259,1.954 8.738,2.887 1000 0.145,0.179 0.202,0.222 0.449,0.319 0.899,0.333 1.577,0.524 4.221,1.240 9.782,3.579 V=10000 F\P 1 2 4 8 16 32 64 10 0.161,0.154 0.198,0.190 0.296,0.256 0.662,0.480 1.192,0.818 2.989,2.200 6.362,4.746 100 0.176,0.174 0.236,0.203 0.326,0.255 0.696,0.511 1.183,0.855 4.205,3.444 19.510,17.760 1000 0.199,0.183 0.240,0.227 1.159,1.014 2.286,2.154 6.023,6.039 ---,10.933 ---,36.620 V=100000 F\P 1 2 4 8 16 32 64 10 0.171,0.162 0.204,0.198 0.285,0.230 0.692,0.500 1.225,0.881 2.990,2.243 6.379,4.771 100 0.151,0.171 0.220,0.210 0.295,0.255 0.720,0.518 1.226,0.844 3.423,2.831 19.234,17.544 1000 0.192,0.189 0.249,0.225 1.162,1.043 2.257,2.093 5.853,4.997 ---,10.399 ---,32.198 We see that the new code is faster in pretty much all the cases and starting from 4 processes there are significant gains with the new code resulting in upto 20-times shorter runtimes. Also for large numbers of cached entries all values for the old code could not be measured as the kernel started hitting softlockups and died before the test completed. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Bug: 32461228 --- include/linux/mbcache2.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 include/linux/mbcache2.h (limited to 'include/linux') diff --git a/include/linux/mbcache2.h b/include/linux/mbcache2.h new file mode 100644 index 000000000000..b6f160ff2533 --- /dev/null +++ b/include/linux/mbcache2.h @@ -0,0 +1,50 @@ +#ifndef _LINUX_MB2CACHE_H +#define _LINUX_MB2CACHE_H + +#include +#include +#include +#include +#include + +struct mb2_cache; + +struct mb2_cache_entry { + /* LRU list - protected by cache->c_lru_list_lock */ + struct list_head e_lru_list; + /* Hash table list - protected by bitlock in e_hash_list_head */ + struct hlist_bl_node e_hash_list; + atomic_t e_refcnt; + /* Key in hash - stable during lifetime of the entry */ + u32 e_key; + /* Block number of hashed block - stable during lifetime of the entry */ + sector_t e_block; + /* Head of hash list (for list bit lock) - stable */ + struct hlist_bl_head *e_hash_list_head; +}; + +struct mb2_cache *mb2_cache_create(int bucket_bits); +void mb2_cache_destroy(struct mb2_cache *cache); + +int mb2_cache_entry_create(struct mb2_cache *cache, gfp_t mask, u32 key, + sector_t block); +void __mb2_cache_entry_free(struct mb2_cache_entry *entry); +static inline int mb2_cache_entry_put(struct mb2_cache *cache, + struct mb2_cache_entry *entry) +{ + if (!atomic_dec_and_test(&entry->e_refcnt)) + return 0; + __mb2_cache_entry_free(entry); + return 1; +} + +void mb2_cache_entry_delete_block(struct mb2_cache *cache, u32 key, + sector_t block); +struct mb2_cache_entry *mb2_cache_entry_find_first(struct mb2_cache *cache, + u32 key); +struct mb2_cache_entry *mb2_cache_entry_find_next(struct mb2_cache *cache, + struct mb2_cache_entry *entry); +void mb2_cache_entry_touch(struct mb2_cache *cache, + struct mb2_cache_entry *entry); + +#endif /* _LINUX_MB2CACHE_H */ -- cgit v1.2.3 From 929dac49005a6a137ef39a1de4af440d3c8ac106 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Mar 2016 14:08:15 -0800 Subject: kasan: add functions to clear stack poison Functions which the compiler has instrumented for ASAN place poison on the stack shadow upon entry and remove this poison prior to returning. In some cases (e.g. hotplug and idle), CPUs may exit the kernel a number of levels deep in C code. If there are any instrumented functions on this critical path, these will leave portions of the idle thread stack shadow poisoned. If a CPU returns to the kernel via a different path (e.g. a cold entry), then depending on stack frame layout subsequent calls to instrumented functions may use regions of the stack with stale poison, resulting in (spurious) KASAN splats to the console. Contemporary GCCs always add stack shadow poisoning when ASAN is enabled, even when asked to not instrument a function [1], so we can't simply annotate functions on the critical path to avoid poisoning. Instead, this series explicitly removes any stale poison before it can be hit. In the common hotplug case we clear the entire stack shadow in common code, before a CPU is brought online. On architectures which perform a cold return as part of cpu idle may retain an architecture-specific amount of stack contents. To retain the poison for this retained context, the arch code must call the core KASAN code, passing a "watermark" stack pointer value beyond which shadow will be cleared. Architectures which don't perform a cold return as part of idle do not need any additional code. This patch (of 3): Functions which the compiler has instrumented for KASAN place poison on the stack shadow upon entry and remove this poision prior to returning. In some cases (e.g. hotplug and idle), CPUs may exit the kernel a number of levels deep in C code. If there are any instrumented functions on this critical path, these will leave portions of the stack shadow poisoned. If a CPU returns to the kernel via a different path (e.g. a cold entry), then depending on stack frame layout subsequent calls to instrumented functions may use regions of the stack with stale poison, resulting in (spurious) KASAN splats to the console. To avoid this, we must clear stale poison from the stack prior to instrumented functions being called. This patch adds functions to the KASAN core for removing poison from (portions of) a task's stack. These will be used by subsequent patches to avoid problems with hotplug and idle. Change-Id: I5813ed6901ad27b168e54dfc6186ffc31aba8d84 Signed-off-by: Mark Rutland Acked-by: Catalin Marinas Reviewed-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Lorenzo Pieralisi Cc: Will Deacon Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Git-commit: e3ae116339f9a0c77523abc95e338fa405946e07 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git Signed-off-by: Mohammed Khajapasha --- include/linux/kasan.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 4b9f85c963d0..0fdc798e3ff7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -1,6 +1,7 @@ #ifndef _LINUX_KASAN_H #define _LINUX_KASAN_H +#include #include struct kmem_cache; @@ -13,7 +14,6 @@ struct vm_struct; #include #include -#include extern unsigned char kasan_zero_page[PAGE_SIZE]; extern pte_t kasan_zero_pte[PTRS_PER_PTE]; @@ -43,6 +43,8 @@ static inline void kasan_disable_current(void) void kasan_unpoison_shadow(const void *address, size_t size); +void kasan_unpoison_task_stack(struct task_struct *task); + void kasan_alloc_pages(struct page *page, unsigned int order); void kasan_free_pages(struct page *page, unsigned int order); @@ -66,6 +68,8 @@ void kasan_free_shadow(const struct vm_struct *vm); static inline void kasan_unpoison_shadow(const void *address, size_t size) {} +static inline void kasan_unpoison_task_stack(struct task_struct *task) {} + static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} -- cgit v1.2.3 From 91a6162f195c0b79799cabc9d34b8785fc8df120 Mon Sep 17 00:00:00 2001 From: Kiran Gunda Date: Fri, 24 Mar 2017 12:29:39 +0530 Subject: regulator: qpnp-labibb: Handle LAB short circuit(SC) detection On certain PMICs, there is no short circuit (SC) detection available in LAB module. Add support to detect it manually and disable LAB/IBB module upon SC detection. In addition, notify it to OLEDB driver to disable OLEDB module. Change-Id: I2a9dc5b1ae8ece45c85b3992026c7f389fd4d135 Signed-off-by: Kiran Gunda --- include/linux/regulator/qpnp-labibb-regulator.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/qpnp-labibb-regulator.h b/include/linux/regulator/qpnp-labibb-regulator.h index 247069507fd9..33985afeb6e9 100644 --- a/include/linux/regulator/qpnp-labibb-regulator.h +++ b/include/linux/regulator/qpnp-labibb-regulator.h @@ -15,6 +15,7 @@ enum labibb_notify_event { LAB_VREG_OK = 1, + LAB_VREG_NOT_OK, }; int qpnp_labibb_notifier_register(struct notifier_block *nb); -- cgit v1.2.3 From 35b84c47a59fae5755fd21532b2fee48ef1cf540 Mon Sep 17 00:00:00 2001 From: Kiran Gunda Date: Fri, 14 Apr 2017 12:25:20 +0530 Subject: regulator: qpnp-oledb: Clear SPARE_CTL register during disable OLEDB_SPARE_CTL register bit is set by the PBS during the display enable and is used during the display suspend to trigger the PBS event. Hence, move clearing of the OLEDB_SPARE_CTL register to regulator disable. Also enable the force_pd_ctl only for DRAX-A revisions <=2.0. Change-Id: I339cefc91f94f772bc4f84e85f2471e1a73e4aed Signed-off-by: Kiran Gunda --- include/linux/qpnp/qpnp-revid.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qpnp/qpnp-revid.h b/include/linux/qpnp/qpnp-revid.h index 7fca674b6230..b025df568259 100644 --- a/include/linux/qpnp/qpnp-revid.h +++ b/include/linux/qpnp/qpnp-revid.h @@ -214,6 +214,11 @@ #define PM660L_V1P1_REV3 0x01 #define PM660L_V1P1_REV4 0x01 +#define PM660L_V2P0_REV1 0x00 +#define PM660L_V2P0_REV2 0x00 +#define PM660L_V2P0_REV3 0x00 +#define PM660L_V2P0_REV4 0x02 + /* PMI8998 FAB_ID */ #define PMI8998_FAB_ID_SMIC 0x11 #define PMI8998_FAB_ID_GF 0x30 -- cgit v1.2.3 From 87d20dd4d339a4ac0229861f26e9e5974d1cc419 Mon Sep 17 00:00:00 2001 From: Dhoat Harpal Date: Wed, 12 Apr 2017 19:48:14 +0530 Subject: char: msm_smd_pkt: Add snapshot of SMD packet driver This snapshot is taken as of msm-3.18 'commit 7e1165aac628 ("Merge drivers: iio: bmi160: Enabled the buffering support for BMI160 Sensor")' CRs-Fixed: 2035593 Change-Id: I2951e77f226062d82e84a26fce6ab932b9685223 Signed-off-by: Dhoat Harpal --- include/linux/msm_smd_pkt.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/msm_smd_pkt.h (limited to 'include/linux') diff --git a/include/linux/msm_smd_pkt.h b/include/linux/msm_smd_pkt.h new file mode 100644 index 000000000000..c79933d27d4a --- /dev/null +++ b/include/linux/msm_smd_pkt.h @@ -0,0 +1,23 @@ +/* Copyright (c) 2010,2017 The Linux Foundation. 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 version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#ifndef __LINUX_MSM_SMD_PKT_H +#define __LINUX_MSM_SMD_PKT_H + +#include + +#define SMD_PKT_IOCTL_MAGIC (0xC2) + +#define SMD_PKT_IOCTL_BLOCKING_WRITE \ + _IOR(SMD_PKT_IOCTL_MAGIC, 0, unsigned int) + +#endif /* __LINUX_MSM_SMD_PKT_H */ -- cgit v1.2.3 From 3144d81a77352a3934ff0f60dccb38dbf462da39 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Mar 2017 16:54:24 -0400 Subject: cgroup, kthread: close race window where new kthreads can be migrated to non-root cgroups commit 77f88796cee819b9c4562b0b6b44691b3b7755b1 upstream. Creation of a kthread goes through a couple interlocked stages between the kthread itself and its creator. Once the new kthread starts running, it initializes itself and wakes up the creator. The creator then can further configure the kthread and then let it start doing its job by waking it up. In this configuration-by-creator stage, the creator is the only one that can wake it up but the kthread is visible to userland. When altering the kthread's attributes from userland is allowed, this is fine; however, for cases where CPU affinity is critical, kthread_bind() is used to first disable affinity changes from userland and then set the affinity. This also prevents the kthread from being migrated into non-root cgroups as that can affect the CPU affinity and many other things. Unfortunately, the cgroup side of protection is racy. While the PF_NO_SETAFFINITY flag prevents further migrations, userland can win the race before the creator sets the flag with kthread_bind() and put the kthread in a non-root cgroup, which can lead to all sorts of problems including incorrect CPU affinity and starvation. This bug got triggered by userland which periodically tries to migrate all processes in the root cpuset cgroup to a non-root one. Per-cpu workqueue workers got caught while being created and ended up with incorrected CPU affinity breaking concurrency management and sometimes stalling workqueue execution. This patch adds task->no_cgroup_migration which disallows the task to be migrated by userland. kthreadd starts with the flag set making every child kthread start in the root cgroup with migration disallowed. The flag is cleared after the kthread finishes initialization by which time PF_NO_SETAFFINITY is set if the kthread should stay in the root cgroup. It'd be better to wait for the initialization instead of failing but I couldn't think of a way of implementing that without adding either a new PF flag, or sleeping and retrying from waiting side. Even if userland depends on changing cgroup membership of a kthread, it either has to be synchronized with kthread_create() or periodically repeat, so it's unlikely that this would break anything. v2: Switch to a simpler implementation using a new task_struct bit field suggested by Oleg. Signed-off-by: Tejun Heo Suggested-by: Oleg Nesterov Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra (Intel) Cc: Thomas Gleixner Reported-and-debugged-by: Chris Mason Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/cgroup.h | 21 +++++++++++++++++++++ include/linux/sched.h | 4 ++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cb91b44f5f78..ad2bcf647b9a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -528,6 +528,25 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline void cgroup_init_kthreadd(void) +{ + /* + * kthreadd is inherited by all kthreads, keep it in the root so + * that the new kthreads are guaranteed to stay in the root until + * initialization is finished. + */ + current->no_cgroup_migration = 1; +} + +static inline void cgroup_kthread_ready(void) +{ + /* + * This kthread finished initialization. The creator should have + * set PF_NO_SETAFFINITY if this kthread should stay in the root. + */ + current->no_cgroup_migration = 0; +} + #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -551,6 +570,8 @@ static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } +static inline void cgroup_init_kthreadd(void) {} +static inline void cgroup_kthread_ready(void) {} #endif /* !CONFIG_CGROUPS */ diff --git a/include/linux/sched.h b/include/linux/sched.h index ce0f61dcd887..352213b360d7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1475,6 +1475,10 @@ struct task_struct { #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif +#ifdef CONFIG_CGROUPS + /* disallow userland-initiated cgroup migration */ + unsigned no_cgroup_migration:1; +#endif unsigned long atomic_flags; /* Flags needing atomic access. */ -- cgit v1.2.3 From 883e3ea07e3b725c90e57bbf1200856d07b389ff Mon Sep 17 00:00:00 2001 From: Prasad Sodagudi Date: Wed, 5 Apr 2017 10:17:19 -0700 Subject: sched: Add a check for cpu unbound deferrable timers Add a check for cpu unbound deferrable timer expiry and raise softirq for handling the expired timers so that the CPU can process the cpu unbound deferrable times as early as possible when a cpu tries to enter/exit idle loop. Change-Id: Ieffa74fa22a4d25493f5590b5ac1e0d784fcbbad Signed-off-by: Prasad Sodagudi --- include/linux/timer.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index b1617e8932b2..1239c6ef949e 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -173,6 +173,9 @@ extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); extern int mod_timer_pinned(struct timer_list *timer, unsigned long expires); extern void set_timer_slack(struct timer_list *time, int slack_hz); +#ifdef CONFIG_SMP +extern bool check_pending_deferrable_timers(int cpu); +#endif #define TIMER_NOT_PINNED 0 #define TIMER_PINNED 1 -- cgit v1.2.3 From ad3b1dcc9393ae156f3714110070cf0afb1ef1c4 Mon Sep 17 00:00:00 2001 From: Charan Teja Reddy Date: Thu, 20 Apr 2017 19:11:20 +0530 Subject: iommu: disable smmu stalls on faulty transactions Disable the SMMU stalls on faulty transactions by terminating it using the CB.SCTLR register. Faulty transaction on a CB causes the back pressure on the QSMMU transaction pipe which inturn affect the other masters using the same SMMU. Pass the DOMAIN_ATTR_CB_STALL_DISABLE flag to iommu_domain_set_attr api in order to use this feature. Change-Id: Ib8fa35854ff24e0295d330c5fb79375f58c3e841 Signed-off-by: Charan Teja Reddy --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c4c25651ff21..55ae8b928411 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -137,6 +137,7 @@ enum iommu_attr { DOMAIN_ATTR_PAGE_TABLE_IS_COHERENT, DOMAIN_ATTR_PAGE_TABLE_FORCE_COHERENT, DOMAIN_ATTR_ENABLE_TTBR1, + DOMAIN_ATTR_CB_STALL_DISABLE, DOMAIN_ATTR_MAX, }; -- cgit v1.2.3 From 6a6a7657c231e947233c43ae0522bbd4edf0139e Mon Sep 17 00:00:00 2001 From: David Zeuthen Date: Tue, 24 Jan 2017 13:02:35 -0500 Subject: ANDROID: Update init/do_mounts_dm.c to the latest ChromiumOS version. This is needed for AVB integration work. Bug: 31796270 Test: Manually tested (other arch). Change-Id: I32fd37c1578c6414e3e6ff277d16ad94df7886b8 Signed-off-by: David Zeuthen --- include/linux/device-mapper.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index b874d5b61ffc..f3f87db34429 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -415,6 +415,13 @@ union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); +void dm_lock_md_type(struct mapped_device *md); +void dm_unlock_md_type(struct mapped_device *md); +void dm_set_md_type(struct mapped_device *md, unsigned type); +unsigned dm_get_md_type(struct mapped_device *md); +int dm_setup_md_queue(struct mapped_device *md); +unsigned dm_table_get_type(struct dm_table *t); + /* * Geometry functions. */ -- cgit v1.2.3 From 330da40c2175e796e94fa93cc86b6d2fad712bf7 Mon Sep 17 00:00:00 2001 From: David Zeuthen Date: Tue, 24 Jan 2017 13:02:35 -0500 Subject: ANDROID: Update init/do_mounts_dm.c to the latest ChromiumOS version. This is needed for AVB integration work. Bug: 31796270 Test: Manually tested (other arch). Change-Id: I32fd37c1578c6414e3e6ff277d16ad94df7886b8 Signed-off-by: David Zeuthen Git-commit: 6a6a7657c231e947233c43ae0522bbd4edf0139e Git-repo: https://android.googlesource.com/kernel/common/ Signed-off-by: Runmin Wang --- include/linux/device-mapper.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 5c720864db89..403a239b7aa1 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -415,6 +415,13 @@ union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); +void dm_lock_md_type(struct mapped_device *md); +void dm_unlock_md_type(struct mapped_device *md); +void dm_set_md_type(struct mapped_device *md, unsigned type); +unsigned dm_get_md_type(struct mapped_device *md); +int dm_setup_md_queue(struct mapped_device *md); +unsigned dm_table_get_type(struct dm_table *t); + /* * Geometry functions. */ -- cgit v1.2.3 From c50fd34e10897114a7be2120133bd7e0b4184024 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 28 Sep 2016 00:27:17 -0500 Subject: mnt: Add a per mount namespace limit on the number of mounts commit d29216842a85c7970c536108e093963f02714498 upstream. CAI Qian pointed out that the semantics of shared subtrees make it possible to create an exponentially increasing number of mounts in a mount namespace. mkdir /tmp/1 /tmp/2 mount --make-rshared / for i in $(seq 1 20) ; do mount --bind /tmp/1 /tmp/2 ; done Will create create 2^20 or 1048576 mounts, which is a practical problem as some people have managed to hit this by accident. As such CVE-2016-6213 was assigned. Ian Kent described the situation for autofs users as follows: > The number of mounts for direct mount maps is usually not very large because of > the way they are implemented, large direct mount maps can have performance > problems. There can be anywhere from a few (likely case a few hundred) to less > than 10000, plus mounts that have been triggered and not yet expired. > > Indirect mounts have one autofs mount at the root plus the number of mounts that > have been triggered and not yet expired. > > The number of autofs indirect map entries can range from a few to the common > case of several thousand and in rare cases up to between 30000 and 50000. I've > not heard of people with maps larger than 50000 entries. > > The larger the number of map entries the greater the possibility for a large > number of active mounts so it's not hard to expect cases of a 1000 or somewhat > more active mounts. So I am setting the default number of mounts allowed per mount namespace at 100,000. This is more than enough for any use case I know of, but small enough to quickly stop an exponential increase in mounts. Which should be perfect to catch misconfigurations and malfunctioning programs. For anyone who needs a higher limit this can be changed by writing to the new /proc/sys/fs/mount-max sysctl. Tested-by: CAI Qian Signed-off-by: "Eric W. Biederman" [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- include/linux/mount.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index f822c3c11377..dc6cd800cd5d 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -95,4 +95,6 @@ extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); +extern unsigned int sysctl_mount_max; + #endif /* _LINUX_MOUNT_H */ -- cgit v1.2.3 From 6ea5a099d64ae0369755ec950ec27ecfeb5a5d4e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 26 Jan 2017 17:15:44 +0100 Subject: wireless: define cipher/AKM suites using a macro The spec writes cipher/AKM suites as something like 00-0F-AC:9, but the part after the colon isn't hex, it's decimal, so that we've already had a few mistakes (in other code, or unmerged patches) to e.g. write 0x000FAC10 instead of 0x000FAC0A. Use a macro to avoid that problem. Reviewed-by: Luca Coelho Signed-off-by: Johannes Berg Git-commit: 228c8c6b1f4376788e9d5ab00d50b10228eb40d3 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git CRs-Fixed: 2028536 Change-Id: I1507de1ee316182d429186ff33a932675013ba7d Signed-off-by: Vidyullatha Kanchanapally --- include/linux/ieee80211.h | 46 ++++++++++++++++++++++++---------------------- 1 file changed, 24 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ddba92d46eba..97204b0d2fca 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2251,31 +2251,33 @@ enum ieee80211_sa_query_action { }; +#define SUITE(oui, id) (((oui) << 8) | (id)) + /* cipher suite selectors */ -#define WLAN_CIPHER_SUITE_USE_GROUP 0x000FAC00 -#define WLAN_CIPHER_SUITE_WEP40 0x000FAC01 -#define WLAN_CIPHER_SUITE_TKIP 0x000FAC02 -/* reserved: 0x000FAC03 */ -#define WLAN_CIPHER_SUITE_CCMP 0x000FAC04 -#define WLAN_CIPHER_SUITE_WEP104 0x000FAC05 -#define WLAN_CIPHER_SUITE_AES_CMAC 0x000FAC06 -#define WLAN_CIPHER_SUITE_GCMP 0x000FAC08 -#define WLAN_CIPHER_SUITE_GCMP_256 0x000FAC09 -#define WLAN_CIPHER_SUITE_CCMP_256 0x000FAC0A -#define WLAN_CIPHER_SUITE_BIP_GMAC_128 0x000FAC0B -#define WLAN_CIPHER_SUITE_BIP_GMAC_256 0x000FAC0C -#define WLAN_CIPHER_SUITE_BIP_CMAC_256 0x000FAC0D - -#define WLAN_CIPHER_SUITE_SMS4 0x00147201 +#define WLAN_CIPHER_SUITE_USE_GROUP SUITE(0x000FAC, 0) +#define WLAN_CIPHER_SUITE_WEP40 SUITE(0x000FAC, 1) +#define WLAN_CIPHER_SUITE_TKIP SUITE(0x000FAC, 2) +/* reserved: SUITE(0x000FAC, 3) */ +#define WLAN_CIPHER_SUITE_CCMP SUITE(0x000FAC, 4) +#define WLAN_CIPHER_SUITE_WEP104 SUITE(0x000FAC, 5) +#define WLAN_CIPHER_SUITE_AES_CMAC SUITE(0x000FAC, 6) +#define WLAN_CIPHER_SUITE_GCMP SUITE(0x000FAC, 8) +#define WLAN_CIPHER_SUITE_GCMP_256 SUITE(0x000FAC, 9) +#define WLAN_CIPHER_SUITE_CCMP_256 SUITE(0x000FAC, 10) +#define WLAN_CIPHER_SUITE_BIP_GMAC_128 SUITE(0x000FAC, 11) +#define WLAN_CIPHER_SUITE_BIP_GMAC_256 SUITE(0x000FAC, 12) +#define WLAN_CIPHER_SUITE_BIP_CMAC_256 SUITE(0x000FAC, 13) + +#define WLAN_CIPHER_SUITE_SMS4 SUITE(0x001472, 1) /* AKM suite selectors */ -#define WLAN_AKM_SUITE_8021X 0x000FAC01 -#define WLAN_AKM_SUITE_PSK 0x000FAC02 -#define WLAN_AKM_SUITE_8021X_SHA256 0x000FAC05 -#define WLAN_AKM_SUITE_PSK_SHA256 0x000FAC06 -#define WLAN_AKM_SUITE_TDLS 0x000FAC07 -#define WLAN_AKM_SUITE_SAE 0x000FAC08 -#define WLAN_AKM_SUITE_FT_OVER_SAE 0x000FAC09 +#define WLAN_AKM_SUITE_8021X SUITE(0x000FAC, 1) +#define WLAN_AKM_SUITE_PSK SUITE(0x000FAC, 2) +#define WLAN_AKM_SUITE_8021X_SHA256 SUITE(0x000FAC, 5) +#define WLAN_AKM_SUITE_PSK_SHA256 SUITE(0x000FAC, 6) +#define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7) +#define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8) +#define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9) #define WLAN_MAX_KEY_LEN 32 -- cgit v1.2.3 From 6ee553ab2e91311fc50d50dbd0319457c525b37f Mon Sep 17 00:00:00 2001 From: Vidyullatha Kanchanapally Date: Fri, 31 Mar 2017 00:22:34 +0300 Subject: cfg80211: Add support for FILS shared key authentication offload Enhance nl80211 and cfg80211 connect request and response APIs to support FILS shared key authentication offload. The new nl80211 attributes can be used to provide additional information to the driver to establish a FILS connection. Also enhance the set/del PMKSA to allow support for adding and deleting PMKSA based on FILS cache identifier. Add a new feature flag that drivers can use to advertize support for FILS shared key authentication and association in station mode when using their own SME. Change-Id: I75d47301b767e691d6240fd6c20c28b9bfaaa571 Signed-off-by: Vidyullatha Kanchanapally Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg Git-commit: a3caf7440dedd2399f90f27ff11ac390bf03e6c4 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git CRs-Fixed: 2028536 [vidyullatha@codeaurora.org: backport to kernel 4.4 - This commit includes the changes from following commits in include/uapi/linux/nl80211.h to compile for msm-4.4 - 4a4b8169501b18c3450ac735a7e277b24886a651 : cfg80211: Accept multiple RSSI thresholds for CQM] Signed-off-by: Vidyullatha Kanchanapally --- include/linux/ieee80211.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 97204b0d2fca..6cfef2760e09 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1677,6 +1677,9 @@ enum ieee80211_statuscode { WLAN_STATUS_REJECT_DSE_BAND = 96, WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99, WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103, + /* 802.11ai */ + WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108, + WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109, }; @@ -2038,6 +2041,12 @@ enum ieee80211_key_len { #define FILS_NONCE_LEN 16 #define FILS_MAX_KEK_LEN 64 +#define FILS_ERP_MAX_USERNAME_LEN 16 +#define FILS_ERP_MAX_REALM_LEN 253 +#define FILS_ERP_MAX_RRK_LEN 64 + +#define PMK_MAX_LEN 48 + /* Public action codes */ enum ieee80211_pub_actioncode { WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, @@ -2278,6 +2287,10 @@ enum ieee80211_sa_query_action { #define WLAN_AKM_SUITE_TDLS SUITE(0x000FAC, 7) #define WLAN_AKM_SUITE_SAE SUITE(0x000FAC, 8) #define WLAN_AKM_SUITE_FT_OVER_SAE SUITE(0x000FAC, 9) +#define WLAN_AKM_SUITE_FILS_SHA256 SUITE(0x000FAC, 14) +#define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) +#define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) +#define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) #define WLAN_MAX_KEY_LEN 32 -- cgit v1.2.3 From 2fc978c8b7b8cbd66a578b02a43e365d1ad3746c Mon Sep 17 00:00:00 2001 From: Fenglin Wu Date: Tue, 25 Apr 2017 20:51:06 +0800 Subject: power_supply: Add REAL_TYPE power_supply_property Add REAL_TYPE power_supply property to record the real time charger type. Change-Id: I5fb2e3e3e782bcac0f8dd6071a830bcf370ebbd4 Signed-off-by: Fenglin Wu --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 7488bb993d7a..aa8edf9928eb 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -247,6 +247,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_CONNECTOR_HEALTH, POWER_SUPPLY_PROP_CTM_CURRENT_MAX, POWER_SUPPLY_PROP_HW_CURRENT_MAX, + POWER_SUPPLY_PROP_REAL_TYPE, /* Local extensions of type int64_t */ POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT, /* Properties of type `const char *' */ -- cgit v1.2.3 From 058ccb29334351370324ca45d753708718714827 Mon Sep 17 00:00:00 2001 From: Sudarshan Rajagopalan Date: Tue, 4 Apr 2017 19:10:06 -0700 Subject: iommu/iommu-debug: Add validation support for per-buffer coherent mappings Added new debugfs files/nodes to perform basic validation of the per-buffer IO coherent dma-mapping that was recently implemented. Also, added a node to print out the PTE for a given IOVA. Nodes added: dma_attach dma_map dma_unmap dma_atos virt_addr pte Change-Id: I041ab5f4e37e50dd3f58e2def3fdd3125a60629c Signed-off-by: Sudarshan Rajagopalan --- include/linux/iommu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 55ae8b928411..2767fcdec5a1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -235,6 +235,8 @@ struct iommu_ops { void (*tlbi_domain)(struct iommu_domain *domain); int (*enable_config_clocks)(struct iommu_domain *domain); void (*disable_config_clocks)(struct iommu_domain *domain); + uint64_t (*iova_to_pte)(struct iommu_domain *domain, + dma_addr_t iova); #ifdef CONFIG_OF_IOMMU int (*of_xlate)(struct device *dev, struct of_phandle_args *args); @@ -334,6 +336,9 @@ extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t offset, u64 size, int prot); extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr); + +extern uint64_t iommu_iova_to_pte(struct iommu_domain *domain, + dma_addr_t iova); /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened -- cgit v1.2.3 From 660dbf1cf4d78f3c77dab65d0a62a58bd838fb3d Mon Sep 17 00:00:00 2001 From: Anirudh Ghayal Date: Tue, 2 May 2017 16:15:27 +0530 Subject: drivers: regulator: Add snapshot of OnSemi NCP6335D regulator This is snapshot of the OnSemi NCP6335D driver as of msm-3.10 'commit 156ba1726643 ("regulator: onsemi-ncp6335d: Add i2c retry logic")'. Change-Id: I4cf0acd272fcf498462d4397385cd62f144eadf8 Signed-off-by: Kiran Gunda --- include/linux/regulator/onsemi-ncp6335d.h | 35 +++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/regulator/onsemi-ncp6335d.h (limited to 'include/linux') diff --git a/include/linux/regulator/onsemi-ncp6335d.h b/include/linux/regulator/onsemi-ncp6335d.h new file mode 100644 index 000000000000..399742f7e2ac --- /dev/null +++ b/include/linux/regulator/onsemi-ncp6335d.h @@ -0,0 +1,35 @@ +/* Copyright (c) 2012-2014, The Linux Foundation. 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 version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __NCP6335D_H__ +#define __NCP6335D_H__ + +enum { + NCP6335D_VSEL0, + NCP6335D_VSEL1, +}; + +struct ncp6335d_platform_data { + struct regulator_init_data *init_data; + int default_vsel; + int slew_rate_ns; + int discharge_enable; + bool sleep_enable; +}; + +#ifdef CONFIG_REGULATOR_ONSEMI_NCP6335D +int __init ncp6335d_regulator_init(void); +#else +static inline int __init ncp6335d_regulator_init(void) { return 0; } +#endif + +#endif -- cgit v1.2.3 From fd79e436325841863d070f8e72246b437c0f5a15 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 29 Feb 2016 13:20:28 +0100 Subject: mtd: avoid stack overflow in MTD CFI code commit fddcca5107051adf9e4481d2a79ae0616577fd2c upstream. When map_word gets too large, we use a lot of kernel stack, and for MTD_MAP_BANK_WIDTH_32, this means we use more than the recommended 1024 bytes in a number of functions: drivers/mtd/chips/cfi_cmdset_0020.c: In function 'cfi_staa_write_buffers': drivers/mtd/chips/cfi_cmdset_0020.c:651:1: warning: the frame size of 1336 bytes is larger than 1024 bytes [-Wframe-larger-than=] drivers/mtd/chips/cfi_cmdset_0020.c: In function 'cfi_staa_erase_varsize': drivers/mtd/chips/cfi_cmdset_0020.c:972:1: warning: the frame size of 1208 bytes is larger than 1024 bytes [-Wframe-larger-than=] drivers/mtd/chips/cfi_cmdset_0001.c: In function 'do_write_buffer': drivers/mtd/chips/cfi_cmdset_0001.c:1835:1: warning: the frame size of 1240 bytes is larger than 1024 bytes [-Wframe-larger-than=] This can be avoided if all operations on the map word are done indirectly and the stack gets reused between the calls. We can mostly achieve this by selecting MTD_COMPLEX_MAPPINGS whenever MTD_MAP_BANK_WIDTH_32 is set, but for the case that no other bank width is enabled, we also need to use a non-constant map_bankwidth() to convince the compiler to use less stack. Signed-off-by: Arnd Bergmann [Brian: this patch mostly achieves its goal by forcing MTD_COMPLEX_MAPPINGS (and the accompanying indirection) for 256-bit mappings; the rest of the change is mostly a wash, though it helps reduce stack size slightly. If we really care about supporting 256-bit mappings though, we should consider rewriting some of this code to avoid keeping and assigning so many 256-bit objects on the stack.] Signed-off-by: Brian Norris Signed-off-by: Greg Kroah-Hartman --- include/linux/mtd/map.h | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 366cf77953b5..806d0ab845e0 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -122,18 +122,13 @@ #endif #ifdef CONFIG_MTD_MAP_BANK_WIDTH_32 -# ifdef map_bankwidth -# undef map_bankwidth -# define map_bankwidth(map) ((map)->bankwidth) -# undef map_bankwidth_is_large -# define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8) -# undef map_words -# define map_words(map) map_calc_words(map) -# else -# define map_bankwidth(map) 32 -# define map_bankwidth_is_large(map) (1) -# define map_words(map) map_calc_words(map) -# endif +/* always use indirect access for 256-bit to preserve kernel stack */ +# undef map_bankwidth +# define map_bankwidth(map) ((map)->bankwidth) +# undef map_bankwidth_is_large +# define map_bankwidth_is_large(map) (map_bankwidth(map) > BITS_PER_LONG/8) +# undef map_words +# define map_words(map) map_calc_words(map) #define map_bankwidth_is_32(map) (map_bankwidth(map) == 32) #undef MAX_MAP_BANKWIDTH #define MAX_MAP_BANKWIDTH 32 -- cgit v1.2.3 From b5428181f94bd0d1ff5d321bd58413bdb61f8df4 Mon Sep 17 00:00:00 2001 From: Chenbo Feng Date: Wed, 19 Apr 2017 14:22:47 -0700 Subject: ANDROID: Add untag hacks to inet_release function To prevent protential risk of memory leak caused by closing socket with out untag it from qtaguid module, the qtaguid module now do not hold any socket file reference count. Instead, it will increase the sk_refcnt of the sk struct to prevent a reuse of the socket pointer. And when a socket is released. It will delete the tag if the socket is previously tagged so no more resources is held by xt_qtaguid moudle. A flag is added to the untag process to prevent possible kernel crash caused by fail to delete corresponding socket_tag_entry list. Bug: 36374484 Test: compile and run test under system/extra/test/iptables, run cts -m CtsNetTestCases -t android.net.cts.SocketRefCntTest Signed-off-by: Chenbo Feng Change-Id: Iea7c3bf0c59b9774a5114af905b2405f6bc9ee52 --- include/linux/netfilter/xt_qtaguid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_qtaguid.h b/include/linux/netfilter/xt_qtaguid.h index ca60fbdec2f3..1c671552ec37 100644 --- a/include/linux/netfilter/xt_qtaguid.h +++ b/include/linux/netfilter/xt_qtaguid.h @@ -10,4 +10,5 @@ #define XT_QTAGUID_SOCKET XT_OWNER_SOCKET #define xt_qtaguid_match_info xt_owner_match_info +int qtaguid_untag(struct socket *sock, bool kernel); #endif /* _XT_QTAGUID_MATCH_H */ -- cgit v1.2.3 From 2428776eb1e60acf636a48a76acd8a27ccf92aa8 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 28 Dec 2016 14:56:51 -0800 Subject: usb: chipidea: Handle extcon events properly commit a89b94b53371bbfa582787c2fa3378000ea4263d upstream. We're currently emulating the vbus and id interrupts in the OTGSC read API, but we also need to make sure that if we're handling the events with extcon that we don't enable the interrupts for those events in the hardware. Therefore, properly emulate this register if we're using extcon, but don't enable the interrupts. This allows me to get my cable connect/disconnect working properly without getting spurious interrupts on my device that uses an extcon for these two events. Acked-by: Peter Chen Cc: Greg Kroah-Hartman Cc: "Ivan T. Ivanov" Fixes: 3ecb3e09b042 ("usb: chipidea: Use extcon framework for VBUS and ID detect") Signed-off-by: Stephen Boyd Signed-off-by: Peter Chen Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 5dd75fa47dd8..f9be467d6695 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -14,6 +14,7 @@ struct ci_hdrc; * struct ci_hdrc_cable - structure for external connector cable state tracking * @state: current state of the line * @changed: set to true when extcon event happen + * @enabled: set to true if we've enabled the vbus or id interrupt * @edev: device which generate events * @ci: driver state of the chipidea device * @nb: hold event notification callback @@ -22,6 +23,7 @@ struct ci_hdrc; struct ci_hdrc_cable { bool state; bool changed; + bool enabled; struct extcon_dev *edev; struct ci_hdrc *ci; struct notifier_block nb; -- cgit v1.2.3 From 4edbdf57bc26a126aa3cbafd63fae4b00e002e2d Mon Sep 17 00:00:00 2001 From: Jin Qian Date: Tue, 25 Apr 2017 16:28:48 -0700 Subject: f2fs: sanity check segment count commit b9dd46188edc2f0d1f37328637860bb65a771124 upstream. F2FS uses 4 bytes to represent block address. As a result, supported size of disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments. Signed-off-by: Jin Qian Signed-off-by: Jaegeuk Kim Signed-off-by: Greg Kroah-Hartman --- include/linux/f2fs_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 25c6324a0dd0..3d6e6ce44c5c 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -283,6 +283,12 @@ struct f2fs_nat_block { #define SIT_VBLOCK_MAP_SIZE 64 #define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry)) +/* + * F2FS uses 4 bytes to represent block address. As a result, supported size of + * disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments. + */ +#define F2FS_MAX_SEGMENT ((16 * 1024 * 1024) / 2) + /* * Note that f2fs_sit_entry->vblocks has the following bit-field information. * [15:10] : allocation type such as CURSEG_XXXX_TYPE -- cgit v1.2.3 From 4a4c6a08906f8c8df19ee2b3514fa76be64ddc83 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 18 Apr 2017 18:43:20 +0200 Subject: block: get rid of blk_integrity_revalidate() commit 19b7ccf8651df09d274671b53039c672a52ad84d upstream. Commit 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk") introduced blk_integrity_revalidate(), which seems to assume ownership of the stable pages flag and unilaterally clears it if no blk_integrity profile is registered: if (bi->profile) disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; else disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; It's called from revalidate_disk() and rescan_partitions(), making it impossible to enable stable pages for drivers that support partitions and don't use blk_integrity: while the call in revalidate_disk() can be trivially worked around (see zram, which doesn't support partitions and hence gets away with zram_revalidate_disk()), rescan_partitions() can be triggered from userspace at any time. This breaks rbd, where the ceph messenger is responsible for generating/verifying CRCs. Since blk_integrity_{un,}register() "must" be used for (un)registering the integrity profile with the block layer, move BDI_CAP_STABLE_WRITES setting there. This way drivers that call blk_integrity_register() and use integrity infrastructure won't interfere with drivers that don't but still want stable pages. Fixes: 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk") Cc: "Martin K. Petersen" Cc: Christoph Hellwig Cc: Mike Snitzer Tested-by: Dan Williams Signed-off-by: Ilya Dryomov [idryomov@gmail.com: backport to < 4.11: bdi is embedded in queue] Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/genhd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 847cc1d91634..5012fcdb4c9e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -742,11 +742,9 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) #if defined(CONFIG_BLK_DEV_INTEGRITY) extern void blk_integrity_add(struct gendisk *); extern void blk_integrity_del(struct gendisk *); -extern void blk_integrity_revalidate(struct gendisk *); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void blk_integrity_add(struct gendisk *disk) { } static inline void blk_integrity_del(struct gendisk *disk) { } -static inline void blk_integrity_revalidate(struct gendisk *disk) { } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #else /* CONFIG_BLOCK */ -- cgit v1.2.3 From be814112fda176cf81899253b151a88f8b65df98 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 8 Feb 2017 11:26:59 -0800 Subject: time: Remove CONFIG_TIMER_STATS Currently CONFIG_TIMER_STATS exposes process information across namespaces: kernel/time/timer_list.c print_timer(): SEQ_printf(m, ", %s/%d", tmp, timer->start_pid); /proc/timer_list: #11: <0000000000000000>, hrtimer_wakeup, S:01, do_nanosleep, cron/2570 Given that the tracer can give the same information, this patch entirely removes CONFIG_TIMER_STATS. Change-Id: I66e06ae2d6e32c309824310d3d9bf54d1047eab1 Suggested-by: Thomas Gleixner Signed-off-by: Kees Cook Acked-by: John Stultz Cc: Nicolas Pitre Cc: linux-doc@vger.kernel.org Cc: Lai Jiangshan Cc: Shuah Khan Cc: Xing Gao Cc: Jonathan Corbet Cc: Jessica Frazelle Cc: kernel-hardening@lists.openwall.com Cc: Nicolas Iooss Cc: "Paul E. McKenney" Cc: Petr Mladek Cc: Richard Cochran Cc: Tejun Heo Cc: Michal Marek Cc: Josh Poimboeuf Cc: Dmitry Vyukov Cc: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Olof Johansson Cc: Andrew Morton Cc: linux-api@vger.kernel.org Cc: Arjan van de Ven Link: http://lkml.kernel.org/r/20170208192659.GA32582@beast Signed-off-by: Thomas Gleixner Git-commit: dfb4357da6ddbdf57d583ba64361c9d792b0e0b1 Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git [ohaugan@codeaurora.org: Fixed merge conflicts] Signed-off-by: Olav Haugan --- include/linux/hrtimer.h | 11 ----------- include/linux/timer.h | 45 --------------------------------------------- 2 files changed, 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 74921a39edee..a72ce396bb7d 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -91,12 +91,6 @@ enum hrtimer_restart { * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) * @is_rel: Set if the timer was armed relative - * @start_pid: timer statistics field to store the pid of the task which - * started the timer - * @start_site: timer statistics field to store the site where the timer - * was started - * @start_comm: timer statistics field to store the name of the process which - * started the timer * * The hrtimer structure must be initialized by hrtimer_init() */ @@ -107,11 +101,6 @@ struct hrtimer { struct hrtimer_clock_base *base; u8 state; u8 is_rel; -#ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; -#endif }; /** diff --git a/include/linux/timer.h b/include/linux/timer.h index 1239c6ef949e..5ea2c58406de 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -21,11 +21,6 @@ struct timer_list { u32 flags; int slack; -#ifdef CONFIG_TIMER_STATS - int start_pid; - void *start_site; - char start_comm[16]; -#endif #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -188,46 +183,6 @@ extern bool check_pending_deferrable_timers(int cpu); /* To be used from cpusets, only */ extern void timer_quiesce_cpu(void *cpup); -/* - * Timer-statistics info: - */ -#ifdef CONFIG_TIMER_STATS - -extern int timer_stats_active; - -extern void init_timer_stats(void); - -extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf, - void *timerf, char *comm, u32 flags); - -extern void __timer_stats_timer_set_start_info(struct timer_list *timer, - void *addr); - -static inline void timer_stats_timer_set_start_info(struct timer_list *timer) -{ - if (likely(!timer_stats_active)) - return; - __timer_stats_timer_set_start_info(timer, __builtin_return_address(0)); -} - -static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) -{ - timer->start_site = NULL; -} -#else -static inline void init_timer_stats(void) -{ -} - -static inline void timer_stats_timer_set_start_info(struct timer_list *timer) -{ -} - -static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) -{ -} -#endif - extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); -- cgit v1.2.3 From b8189b170793ca0bce98a1b49a673d63d028b805 Mon Sep 17 00:00:00 2001 From: Sahitya Tummala Date: Tue, 9 May 2017 11:04:01 +0530 Subject: mmc: core: extend SDR104 workaround for other paths UHS-I SD cards support SDR104 mode which runs the SD card interface clock upto 208 MHz. But we may see repeated CRC errors in SDR104 with some SDCC controllers. If this happens, commit ("mmc: sd: reduce the bus speed in case of multiple CRC errors") would reinit the card to lower speed (SDR50) hoping that CRC error rate would reduce at lower clock speed (100MHz for SDR50). As the error may happen for any cmd, this change tries to fix several other paths - clock scaling, mmc_rescan, non-data commands error path. Change-Id: I8ccbbf7e330cde3862d9660d3be4d67fb00d97ca Signed-off-by: Sahitya Tummala Signed-off-by: Subhash Jadavani Signed-off-by: Veerabhadrarao Badiganti --- include/linux/mmc/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 2a1a6fec179f..0065ffc9322b 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -223,6 +223,7 @@ extern void mmc_cmdq_clk_scaling_start_busy(struct mmc_host *host, bool lock_needed); extern void mmc_cmdq_clk_scaling_stop_busy(struct mmc_host *host, bool lock_needed, bool is_cmdq_dcmd); +extern void mmc_recovery_fallback_lower_speed(struct mmc_host *host); /** * mmc_claim_host - exclusively claim a host -- cgit v1.2.3 From 6384f782a69cf93a8a59322e1b6cf29f27fa0c8f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 17 May 2017 10:19:49 +0200 Subject: tracing/kprobes: Enforce kprobes teardown after testing commit 30e7d894c1478c88d50ce94ddcdbd7f9763d9cdd upstream. Enabling the tracer selftest triggers occasionally the warning in text_poke(), which warns when the to be modified page is not marked reserved. The reason is that the tracer selftest installs kprobes on functions marked __init for testing. These probes are removed after the tests, but that removal schedules the delayed kprobes_optimizer work, which will do the actual text poke. If the work is executed after the init text is freed, then the warning triggers. The bug can be reproduced reliably when the work delay is increased. Flush the optimizer work and wait for the optimizing/unoptimizing lists to become empty before returning from the kprobes tracer selftest. That ensures that all operations which were queued due to the probes removal have completed. Link: http://lkml.kernel.org/r/20170516094802.76a468bb@gandalf.local.home Signed-off-by: Thomas Gleixner Acked-by: Masami Hiramatsu Fixes: 6274de498 ("kprobes: Support delayed unoptimizing") Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- include/linux/kprobes.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8f6849084248..e23392517db9 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -330,7 +330,9 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif - +extern void wait_for_kprobe_optimizer(void); +#else +static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, -- cgit v1.2.3 From e91e2202ec0b63f9e272ce2e075f58cfd90d7082 Mon Sep 17 00:00:00 2001 From: Abhijeet Dharmapurikar Date: Wed, 24 May 2017 17:11:24 -0700 Subject: power_supply: introduce PR_SWAP property Introduce POWER_SUPPLY_PROP_PR_SWAP to notify if the device is in power role swap. Change-Id: I8d0cb3a71ec1a646b7ec37405e66cb00ddc40e0d Signed-off-by: Abhijeet Dharmapurikar --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index aa8edf9928eb..5cc13e9fbd8f 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -248,6 +248,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_CTM_CURRENT_MAX, POWER_SUPPLY_PROP_HW_CURRENT_MAX, POWER_SUPPLY_PROP_REAL_TYPE, + POWER_SUPPLY_PROP_PR_SWAP, /* Local extensions of type int64_t */ POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT, /* Properties of type `const char *' */ -- cgit v1.2.3 From 57fd979fc92aac87bc6745883940d32fbdeb4ac4 Mon Sep 17 00:00:00 2001 From: Pavankumar Kondeti Date: Wed, 10 May 2017 15:43:29 +0530 Subject: core_ctl: un-isolate BIG CPUs more aggressively The current algorithm to bring additional BIG CPUs is very conservative. It works when BIG tasks alone run on BIG cluster. When co-location and scheduler boost features are activated, small/medium tasks also run on BIG cluster. We don't want these tasks to downmigrate, when BIG CPUs are available but isolated. The following changes are done to un-isolate CPUs more aggressively. (1) Round up the big_avg. When the big_avg indicates that there are 1.5 tasks on an average in the last window, it indicates that we need 2 BIG CPUs not 1 BIG CPU. (2) Track the maximum number of running tasks in the last window on all CPUs. If any of the CPU in a cluster has more than 4 runnable tasks in the last window, bring an additional CPU to help out. Change-Id: Id05d9983af290760cec6d93d1bdc45bc5e924cce Signed-off-by: Pavankumar Kondeti --- include/linux/sched.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c71978453864..138fcf72508a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -178,7 +178,9 @@ extern u64 nr_running_integral(unsigned int cpu); #endif extern void sched_update_nr_prod(int cpu, long delta, bool inc); -extern void sched_get_nr_running_avg(int *avg, int *iowait_avg, int *big_avg); +extern void sched_get_nr_running_avg(int *avg, int *iowait_avg, int *big_avg, + unsigned int *max_nr, + unsigned int *big_max_nr); extern void calc_global_load(unsigned long ticks); -- cgit v1.2.3 From 05d7bcef3fc4a17722eb3d6a61eae0b5c8bcf846 Mon Sep 17 00:00:00 2001 From: Ray Zhang Date: Wed, 17 May 2017 14:34:23 +0800 Subject: clk: mdss: fix bugs when parsing mdss regulators There are two definitions of struct dss_vreg in mdss driver. One is used during parsing regulators from device tree file, the other is used when operating regulators. This introduces different understanding of dss_vreg data in these two places. Future plan is to have only one definition for these shared data structure. Currently only make dss_vreg in sync to fix this issue. CRs-Fixed: 2054371 Change-Id: I4f16e1409c832432fa1df73b0ae030176b664e58 Signed-off-by: Ray Zhang --- include/linux/sde_io_util.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sde_io_util.h b/include/linux/sde_io_util.h index 6bd5c168ecd8..da4a50722984 100644 --- a/include/linux/sde_io_util.h +++ b/include/linux/sde_io_util.h @@ -58,6 +58,8 @@ struct dss_vreg { int post_on_sleep; int pre_off_sleep; int post_off_sleep; + bool lp_disable_allowed; + bool disabled; }; struct dss_gpio { -- cgit v1.2.3 From fb7523d08fa68f75aa15d509967598d2c95b4631 Mon Sep 17 00:00:00 2001 From: Sujeev Dias Date: Fri, 26 May 2017 12:26:46 -0700 Subject: mhi: core: Create dummy MHI APIs to fix compile errors MHI is not supported by all targets, however many MHI client drivers have a common driver that include MHI APIs. Create dummy APIs such that even if MHI not present, does not cause any compile errors. CRs-Fixed: 2053159 Change-Id: I427d925a658518d230a1d14df0cf27a7b19f207e Signed-off-by: Sujeev Dias --- include/linux/msm_mhi.h | 137 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 116 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msm_mhi.h b/include/linux/msm_mhi.h index c01cb1af4231..e655f7397527 100644 --- a/include/linux/msm_mhi.h +++ b/include/linux/msm_mhi.h @@ -168,6 +168,7 @@ enum mhi_rddm_segment { MHI_RDDM_RD_SEGMENT, }; +#if defined(CONFIG_MSM_MHI) /** * mhi_is_device_ready - Check if MHI is ready to register clients * @@ -187,10 +188,22 @@ bool mhi_is_device_ready(const struct device * const dev, * @userdata: cb data for client * @Return 0 on success */ -int mhi_register_device(struct mhi_device *mhi_device, - const char *node_name, +int mhi_register_device(struct mhi_device *mhi_device, const char *node_name, void *user_data); +/** + * mhi_register_channel - Client must call this function to obtain a handle for + * any MHI operations + * + * @client_handle: Handle populated by MHI, opaque to client + * @client_info: Channel\device information provided by client to + * which the handle maps to. + * + * @Return errno + */ +int mhi_register_channel(struct mhi_client_handle **client_handle, + struct mhi_client_info_t *client_info); + /** * mhi_pm_control_device - power management control api * @mhi_device: registered device structure @@ -218,19 +231,6 @@ int mhi_xfer_rddm(struct mhi_device *mhi_device, enum mhi_rddm_segment seg, */ int mhi_deregister_channel(struct mhi_client_handle *client_handle); -/** - * mhi_register_channel - Client must call this function to obtain a handle for - * any MHI operations - * - * @client_handle: Handle populated by MHI, opaque to client - * @client_info: Channel\device information provided by client to - * which the handle maps to. - * - * @Return errno - */ -int mhi_register_channel(struct mhi_client_handle **client_handle, - struct mhi_client_info_t *client_info); - /** * mhi_open_channel - Client must call this function to open a channel * @@ -258,8 +258,8 @@ int mhi_open_channel(struct mhi_client_handle *client_handle); * * @Return errno */ -int mhi_queue_xfer(struct mhi_client_handle *client_handle, - void *buf, size_t buf_len, enum MHI_FLAGS mhi_flags); +int mhi_queue_xfer(struct mhi_client_handle *client_handle, void *buf, + size_t buf_len, enum MHI_FLAGS mhi_flags); /** * mhi_close_channel - Client can request channel to be closed and handle freed @@ -300,7 +300,7 @@ int mhi_get_free_desc(struct mhi_client_handle *client_handle); * @Return non negative on success */ int mhi_poll_inbound(struct mhi_client_handle *client_handle, - struct mhi_result *result); + struct mhi_result *result); /** * mhi_get_max_desc - Get the maximum number of descriptors @@ -311,12 +311,107 @@ int mhi_poll_inbound(struct mhi_client_handle *client_handle, */ int mhi_get_max_desc(struct mhi_client_handle *client_handle); -/* RmNET Reserved APIs, This APIs are reserved for use by the linux network -* stack only. Use by other clients will introduce system wide issues -*/ +/* following APIs meant to be used by rmnet interface only */ int mhi_set_lpm(struct mhi_client_handle *client_handle, bool enable_lpm); int mhi_get_epid(struct mhi_client_handle *mhi_handle); struct mhi_result *mhi_poll(struct mhi_client_handle *client_handle); void mhi_mask_irq(struct mhi_client_handle *client_handle); void mhi_unmask_irq(struct mhi_client_handle *client_handle); + +#else +static inline bool mhi_is_device_ready(const struct device * const dev, + const char *node_name) +{ + return false; +}; + +static inline int mhi_register_device(struct mhi_device *mhi_device, + const char *node_name, void *user_data) +{ + return -EINVAL; +}; + +static inline int mhi_register_channel(struct mhi_client_handle **client_handle, + struct mhi_client_info_t *client_info) +{ + return -EINVAL; +}; + +static inline int mhi_pm_control_device(struct mhi_device *mhi_device, + enum mhi_dev_ctrl ctrl) +{ + return -EINVAL; +}; + +static inline int mhi_xfer_rddm(struct mhi_device *mhi_device, + enum mhi_rddm_segment seg, + struct scatterlist **sg_list) +{ + return -EINVAL; +}; + +static inline int mhi_deregister_channel(struct mhi_client_handle + *client_handle) +{ + return -EINVAL; +}; + +static inline int mhi_open_channel(struct mhi_client_handle *client_handle) +{ + return -EINVAL; +}; + +static inline int mhi_queue_xfer(struct mhi_client_handle *client_handle, + void *buf, size_t buf_len, + enum MHI_FLAGS mhi_flags) +{ + return -EINVAL; +}; + +static inline void mhi_close_channel(struct mhi_client_handle *client_handle) +{ +}; + +static inline int mhi_get_free_desc(struct mhi_client_handle *client_handle) +{ + return -EINVAL; +}; + +static inline int mhi_poll_inbound(struct mhi_client_handle *client_handle, + struct mhi_result *result) +{ + return -EINVAL; +}; + +static inline int mhi_get_max_desc(struct mhi_client_handle *client_handle) +{ + return -EINVAL; +}; + +static inline int mhi_set_lpm(struct mhi_client_handle *client_handle, + bool enable_lpm) +{ + return -EINVAL; +}; + +static inline int mhi_get_epid(struct mhi_client_handle *mhi_handle) +{ + return -EINVAL; +}; + +static inline struct mhi_result *mhi_poll(struct mhi_client_handle + *client_handle) +{ + return NULL; +}; + +static inline void mhi_mask_irq(struct mhi_client_handle *client_handle) +{ +}; + +static inline void mhi_unmask_irq(struct mhi_client_handle *client_handle) +{ +}; + +#endif #endif -- cgit v1.2.3 From 422f64451504c8683b8024732f4a94fbd063b345 Mon Sep 17 00:00:00 2001 From: Sujeev Dias Date: Tue, 9 May 2017 18:46:42 -0700 Subject: mhi: core: Bind devices with variable PCIe device IDs with same device node In order to bind devices with variable PCIe device IDs with same device tree node, make PCIe device ID optional parameter in device tree node. If PCIe device ID not specified in device tree, any device can be bind with the node. CRs-Fixed: 2040899 Change-Id: Iaedcb40db15fa0e8c5c30eb147c904a10cd7569d Signed-off-by: Sujeev Dias --- include/linux/msm_mhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msm_mhi.h b/include/linux/msm_mhi.h index e655f7397527..01fe2e78b9d5 100644 --- a/include/linux/msm_mhi.h +++ b/include/linux/msm_mhi.h @@ -81,6 +81,7 @@ enum MHI_CB_REASON { MHI_CB_MHI_SHUTDOWN, MHI_CB_SYS_ERROR, MHI_CB_RDDM, + MHI_CB_MHI_PROBED, }; enum MHI_FLAGS { @@ -119,6 +120,7 @@ struct mhi_client_handle { u32 domain; u32 bus; u32 slot; + bool enabled; struct mhi_client_config *client_config; }; -- cgit v1.2.3 From 70bc2b791f1b2f801331b6764fd9566c61588f1b Mon Sep 17 00:00:00 2001 From: Veerabhadrarao Badiganti Date: Tue, 30 May 2017 20:34:46 +0530 Subject: mmc: sdhci-msm: Store clock scaling frequencies in a dedicated table Use a separate table to store the platform specific clock-scaling frequencies. The generic table where these frequencies used to be stored, would get updated (in some cases) during clock scaling initialization. But when a new card is inserted (In the case of a removable card), the frequencies supported by the card should be compared against the platform specific frequencies. By storing these values in a separate table, these values would remain intact and this table can be used for initializing the generic table during clock-scaling initialization. Change-Id: I5729f18a975f849bc2965a946473a9cdbd81e94a Signed-off-by: Veerabhadrarao Badiganti --- include/linux/mmc/host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index d9e12c1b1748..279411c42ded 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -330,7 +330,9 @@ struct mmc_devfeq_clk_scaling { atomic_t devfreq_abort; bool skip_clk_scale_freq_update; int freq_table_sz; + int pltfm_freq_table_sz; u32 *freq_table; + u32 *pltfm_freq_table; unsigned long total_busy_time_us; unsigned long target_freq; unsigned long curr_freq; -- cgit v1.2.3 From 90bf661847845b2e3e9c52cdbb257ff3f707ca1c Mon Sep 17 00:00:00 2001 From: Sujeev Dias Date: Tue, 16 May 2017 15:19:16 -0700 Subject: mhi: core: Add support for host triggered device ram dump Add support for bus master to trigger PCIe device into ram dump mode to collect device ram dump. RDDM capabilities are extended to support under kernel panic as well. CRs-Fixed: 2055981 Change-Id: I18f7d5784992df70aafc6e41d248ced3fac37181 Signed-off-by: Sujeev Dias --- include/linux/msm_mhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msm_mhi.h b/include/linux/msm_mhi.h index 01fe2e78b9d5..1704cb93e6a3 100644 --- a/include/linux/msm_mhi.h +++ b/include/linux/msm_mhi.h @@ -160,9 +160,11 @@ enum mhi_dev_ctrl { MHI_DEV_CTRL_RESUME, MHI_DEV_CTRL_POWER_OFF, MHI_DEV_CTRL_POWER_ON, + MHI_DEV_CTRL_TRIGGER_RDDM, MHI_DEV_CTRL_RDDM, MHI_DEV_CTRL_RDDM_KERNEL_PANIC, MHI_DEV_CTRL_NOTIFY_LINK_ERROR, + MHI_DEV_CTRL_MAXCMD, }; enum mhi_rddm_segment { -- cgit v1.2.3 From 10ed66867a47e843a14393017b8d40204311557e Mon Sep 17 00:00:00 2001 From: Arun Kumar Neelakantam Date: Fri, 26 May 2017 17:57:52 +0530 Subject: net: ipc_router: Add dynamic enable/disable wakeup source feature By default IPC Router core uses edge and port specific wakeup sources which are blocking system suspend in special use cases like streaming non wakeup sensors data at high speed. Add dynamic wakeup source enable/disable functionality to acquire the wakeup source only during the APPS suspend stage. CRs-Fixed: 2057391 Change-Id: I2a5ea4e2c31432a9dd195c702ef7001b26eed33d Signed-off-by: Arun Kumar Neelakantam --- include/linux/ipc_router.h | 12 +++++++++++- include/linux/ipc_router_xprt.h | 6 +++++- 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_router.h b/include/linux/ipc_router.h index b17f684a9895..04a06df66d4b 100644 --- a/include/linux/ipc_router.h +++ b/include/linux/ipc_router.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. +/* Copyright (c) 2012-2015,2017 The Linux Foundation. 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 version 2 and @@ -269,6 +269,14 @@ int register_ipcrtr_af_init_notifier(struct notifier_block *nb); */ int unregister_ipcrtr_af_init_notifier(struct notifier_block *nb); +/** + * msm_ipc_router_set_ws_allowed() - To Enable/disable the wakeup source allowed + * flag + * @flag: Flag to set/clear the wakeup soruce allowed + * + */ +void msm_ipc_router_set_ws_allowed(bool flag); + #else struct msm_ipc_port *msm_ipc_router_create_port( @@ -341,6 +349,8 @@ int unregister_ipcrtr_af_init_notifier(struct notifier_block *nb) return -ENODEV; } +void msm_ipc_router_set_ws_allowed(bool flag) { } + #endif #endif diff --git a/include/linux/ipc_router_xprt.h b/include/linux/ipc_router_xprt.h index 276c79ff1591..ac6c1e4db8a4 100644 --- a/include/linux/ipc_router_xprt.h +++ b/include/linux/ipc_router_xprt.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2011-2015, The Linux Foundation. All rights reserved. +/* Copyright (c) 2011-2015,2017 The Linux Foundation. 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 version 2 and @@ -100,6 +100,7 @@ struct rr_opt_hdr { * @pkt_fragment_q: Queue of SKBs containing payload. * @length: Length of data in the chain of SKBs * @ref: Reference count for the packet. + * @ws_need: Flag to check wakeup soruce need */ struct rr_packet { struct list_head list; @@ -108,6 +109,7 @@ struct rr_packet { struct sk_buff_head *pkt_fragment_q; uint32_t length; struct kref ref; + bool ws_need; }; /** @@ -125,6 +127,7 @@ struct rr_packet { * @close: Method to close the XPRT. * @sft_close_done: Method to indicate to the XPRT that handling of reset * event is complete. + * @get_ws_info: Method to get the wakeup soruce inforamtion of the XPRT */ struct msm_ipc_router_xprt { char *name; @@ -143,6 +146,7 @@ struct msm_ipc_router_xprt { struct msm_ipc_router_xprt *xprt); int (*close)(struct msm_ipc_router_xprt *xprt); void (*sft_close_done)(struct msm_ipc_router_xprt *xprt); + bool (*get_ws_info)(struct msm_ipc_router_xprt *xprt); }; void msm_ipc_router_xprt_notify(struct msm_ipc_router_xprt *xprt, -- cgit v1.2.3