From 16e53dbf10a2d7e228709a7286310e629ede5e45 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Wed, 12 Jun 2013 14:04:36 -0700 Subject: CPU hotplug: provide a generic helper to disable/enable CPU hotplug There are instances in the kernel where we would like to disable CPU hotplug (from sysfs) during some important operation. Today the freezer code depends on this and the code to do it was kinda tailor-made for that. Restructure the code and make it generic enough to be useful for other usecases too. Signed-off-by: Srivatsa S. Bhat Signed-off-by: Robin Holt Cc: H. Peter Anvin Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Russ Anderson Cc: Robin Holt Cc: Russell King Cc: Guan Xuetao Cc: Shawn Guo Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c6f6e0839b61..9f3c7e81270a 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -175,6 +175,8 @@ extern struct bus_type cpu_subsys; extern void get_online_cpus(void); extern void put_online_cpus(void); +extern void cpu_hotplug_disable(void); +extern void cpu_hotplug_enable(void); #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) #define register_hotcpu_notifier(nb) register_cpu_notifier(nb) #define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb) @@ -198,6 +200,8 @@ static inline void cpu_hotplug_driver_unlock(void) #define get_online_cpus() do { } while (0) #define put_online_cpus() do { } while (0) +#define cpu_hotplug_disable() do { } while (0) +#define cpu_hotplug_enable() do { } while (0) #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) /* These aren't inline functions due to a GCC bug. */ #define register_hotcpu_notifier(nb) ({ (void)(nb); 0; }) -- cgit v1.2.3 From 637241a900cbd982f744d44646b48a273d609b34 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jun 2013 14:04:39 -0700 Subject: kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook Reported-by: Christian Kujau Tested-by: Josh Boyer Cc: Kay Sievers Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/kmsg.c | 10 +++--- include/linux/syslog.h | 4 +-- kernel/printk.c | 91 +++++++++++++++++++++++++++----------------------- 3 files changed, 57 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index bd4b5a740ff1..bdfabdaefdce 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -21,12 +21,12 @@ extern wait_queue_head_t log_wait; static int kmsg_open(struct inode * inode, struct file * file) { - return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_FILE); + return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC); } static int kmsg_release(struct inode * inode, struct file * file) { - (void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_FILE); + (void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_PROC); return 0; } @@ -34,15 +34,15 @@ static ssize_t kmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { if ((file->f_flags & O_NONBLOCK) && - !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE)) + !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC)) return -EAGAIN; - return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_FILE); + return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_PROC); } static unsigned int kmsg_poll(struct file *file, poll_table *wait) { poll_wait(file, &log_wait, wait); - if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE)) + if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC)) return POLLIN | POLLRDNORM; return 0; } diff --git a/include/linux/syslog.h b/include/linux/syslog.h index 38911391a139..98a3153c0f96 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -44,8 +44,8 @@ /* Return size of the log buffer */ #define SYSLOG_ACTION_SIZE_BUFFER 10 -#define SYSLOG_FROM_CALL 0 -#define SYSLOG_FROM_FILE 1 +#define SYSLOG_FROM_READER 0 +#define SYSLOG_FROM_PROC 1 int do_syslog(int type, char __user *buf, int count, bool from_file); diff --git a/kernel/printk.c b/kernel/printk.c index fa36e1494420..8212c1aef125 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -363,6 +363,53 @@ static void log_store(int facility, int level, log_next_seq++; } +#ifdef CONFIG_SECURITY_DMESG_RESTRICT +int dmesg_restrict = 1; +#else +int dmesg_restrict; +#endif + +static int syslog_action_restricted(int type) +{ + if (dmesg_restrict) + return 1; + /* + * Unless restricted, we allow "read all" and "get buffer size" + * for everybody. + */ + return type != SYSLOG_ACTION_READ_ALL && + type != SYSLOG_ACTION_SIZE_BUFFER; +} + +static int check_syslog_permissions(int type, bool from_file) +{ + /* + * If this is from /proc/kmsg and we've already opened it, then we've + * already done the capabilities checks at open time. + */ + if (from_file && type != SYSLOG_ACTION_OPEN) + return 0; + + if (syslog_action_restricted(type)) { + if (capable(CAP_SYSLOG)) + return 0; + /* + * For historical reasons, accept CAP_SYS_ADMIN too, with + * a warning. + */ + if (capable(CAP_SYS_ADMIN)) { + pr_warn_once("%s (%d): Attempt to access syslog with " + "CAP_SYS_ADMIN but no CAP_SYSLOG " + "(deprecated).\n", + current->comm, task_pid_nr(current)); + return 0; + } + return -EPERM; + } + return security_syslog(type); +} + + /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { u64 seq; @@ -620,7 +667,8 @@ static int devkmsg_open(struct inode *inode, struct file *file) if ((file->f_flags & O_ACCMODE) == O_WRONLY) return 0; - err = security_syslog(SYSLOG_ACTION_READ_ALL); + err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); if (err) return err; @@ -813,45 +861,6 @@ static inline void boot_delay_msec(int level) } #endif -#ifdef CONFIG_SECURITY_DMESG_RESTRICT -int dmesg_restrict = 1; -#else -int dmesg_restrict; -#endif - -static int syslog_action_restricted(int type) -{ - if (dmesg_restrict) - return 1; - /* Unless restricted, we allow "read all" and "get buffer size" for everybody */ - return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; -} - -static int check_syslog_permissions(int type, bool from_file) -{ - /* - * If this is from /proc/kmsg and we've already opened it, then we've - * already done the capabilities checks at open time. - */ - if (from_file && type != SYSLOG_ACTION_OPEN) - return 0; - - if (syslog_action_restricted(type)) { - if (capable(CAP_SYSLOG)) - return 0; - /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */ - if (capable(CAP_SYS_ADMIN)) { - printk_once(KERN_WARNING "%s (%d): " - "Attempt to access syslog with CAP_SYS_ADMIN " - "but no CAP_SYSLOG (deprecated).\n", - current->comm, task_pid_nr(current)); - return 0; - } - return -EPERM; - } - return 0; -} - #if defined(CONFIG_PRINTK_TIME) static bool printk_time = 1; #else @@ -1249,7 +1258,7 @@ out: SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { - return do_syslog(type, buf, len, SYSLOG_FROM_CALL); + return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* -- cgit v1.2.3 From 30dad30922ccc733cfdbfe232090cf674dc374dc Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 12 Jun 2013 14:05:04 -0700 Subject: mm: migration: add migrate_entry_wait_huge() When we have a page fault for the address which is backed by a hugepage under migration, the kernel can't wait correctly and do busy looping on hugepage fault until the migration finishes. As a result, users who try to kick hugepage migration (via soft offlining, for example) occasionally experience long delay or soft lockup. This is because pte_offset_map_lock() can't get a correct migration entry or a correct page table lock for hugepage. This patch introduces migration_entry_wait_huge() to solve this. Signed-off-by: Naoya Horiguchi Reviewed-by: Rik van Riel Reviewed-by: Wanpeng Li Reviewed-by: Michal Hocko Cc: Mel Gorman Cc: Andi Kleen Cc: KOSAKI Motohiro Cc: [2.6.35+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 3 +++ mm/hugetlb.c | 2 +- mm/migrate.c | 23 ++++++++++++++++++----- 3 files changed, 22 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 47ead515c811..c5fd30d2a415 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -137,6 +137,7 @@ static inline void make_migration_entry_read(swp_entry_t *entry) extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); +extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte); #else #define make_migration_entry(page, write) swp_entry(0, 0) @@ -148,6 +149,8 @@ static inline int is_migration_entry(swp_entry_t swp) static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } +static inline void migration_entry_wait_huge(struct mm_struct *mm, + pte_t *pte) { } static inline int is_write_migration_entry(swp_entry_t entry) { return 0; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeeca6686..e2bfbf73a551 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2839,7 +2839,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ptep) { entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait(mm, (pmd_t *)ptep, address); + migration_entry_wait_huge(mm, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | diff --git a/mm/migrate.c b/mm/migrate.c index b1f57501de9c..6f0c24438bba 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -200,15 +200,14 @@ static void remove_migration_ptes(struct page *old, struct page *new) * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ -void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) +static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { - pte_t *ptep, pte; - spinlock_t *ptl; + pte_t pte; swp_entry_t entry; struct page *page; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + spin_lock(ptl); pte = *ptep; if (!is_swap_pte(pte)) goto out; @@ -236,6 +235,20 @@ out: pte_unmap_unlock(ptep, ptl); } +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl = pte_lockptr(mm, pmd); + pte_t *ptep = pte_offset_map(pmd, address); + __migration_entry_wait(mm, ptep, ptl); +} + +void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte) +{ + spinlock_t *ptl = &(mm)->page_table_lock; + __migration_entry_wait(mm, pte, ptl); +} + #ifdef CONFIG_BLOCK /* Returns true if all buffers are successfully locked */ static bool buffer_migrate_lock_buffers(struct buffer_head *head, -- cgit v1.2.3 From c2853c8df57f49620d26f317d7d43347c29bfc2e Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Wed, 12 Jun 2013 14:05:10 -0700 Subject: include/linux/math64.h: add div64_ul() There is div64_long() to handle the s64/long division, but no mocro do u64/ul division. It is necessary in some scenarios, so add this function. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alex Shi Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/math64.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index b8ba85544721..2913b86eb12a 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -6,7 +6,8 @@ #if BITS_PER_LONG == 64 -#define div64_long(x,y) div64_s64((x),(y)) +#define div64_long(x, y) div64_s64((x), (y)) +#define div64_ul(x, y) div64_u64((x), (y)) /** * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder @@ -47,7 +48,8 @@ static inline s64 div64_s64(s64 dividend, s64 divisor) #elif BITS_PER_LONG == 32 -#define div64_long(x,y) div_s64((x),(y)) +#define div64_long(x, y) div_s64((x), (y)) +#define div64_ul(x, y) div_u64((x), (y)) #ifndef div_u64_rem static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) -- cgit v1.2.3