From e2e40f2c1ed433c5e224525c8c862fd32e5d3df2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 22 Feb 2015 08:58:50 -0800 Subject: fs: move struct kiocb to fs.h struct kiocb now is a generic I/O container, so move it to fs.h. Also do a #include diet for aio.h while we're at it. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- kernel/sysctl.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 88ea2d6e0031..83d907afb4a6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -19,6 +19,7 @@ */ #include +#include #include #include #include -- cgit v1.2.3 From 195daf665a6299de98a4da3843fed2dd9de19d3a Mon Sep 17 00:00:00 2001 From: Ulrich Obergfell Date: Tue, 14 Apr 2015 15:44:13 -0700 Subject: watchdog: enable the new user interface of the watchdog mechanism With the current user interface of the watchdog mechanism it is only possible to disable or enable both lockup detectors at the same time. This series introduces new kernel parameters and changes the semantics of some existing kernel parameters, so that the hard lockup detector and the soft lockup detector can be disabled or enabled individually. With this series applied, the user interface is as follows. - parameters in /proc/sys/kernel . soft_watchdog This is a new parameter to control and examine the run state of the soft lockup detector. . nmi_watchdog The semantics of this parameter have changed. It can now be used to control and examine the run state of the hard lockup detector. . watchdog This parameter is still available to control the run state of both lockup detectors at the same time. If this parameter is examined, it shows the logical OR of soft_watchdog and nmi_watchdog. . watchdog_thresh The semantics of this parameter are not affected by the patch. - kernel command line parameters . nosoftlockup The semantics of this parameter have changed. It can now be used to disable the soft lockup detector at boot time. . nmi_watchdog=0 or nmi_watchdog=1 Disable or enable the hard lockup detector at boot time. The patch introduces '=1' as a new option. . nowatchdog The semantics of this parameter are not affected by the patch. It is still available to disable both lockup detectors at boot time. Also, remove the proc_dowatchdog() function which is no longer needed. [dzickus@redhat.com: wrote changelog] [dzickus@redhat.com: update documentation for kernel params and sysctl] Signed-off-by: Ulrich Obergfell Signed-off-by: Don Zickus Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ce410bb9f2e1..245e7dcc3741 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -846,7 +846,7 @@ static struct ctl_table kern_table[] = { .data = &watchdog_user_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_dowatchdog, + .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, }, @@ -855,10 +855,32 @@ static struct ctl_table kern_table[] = { .data = &watchdog_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dowatchdog, + .proc_handler = proc_watchdog_thresh, .extra1 = &zero, .extra2 = &sixty, }, + { + .procname = "nmi_watchdog", + .data = &nmi_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_nmi_watchdog, + .extra1 = &zero, +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) + .extra2 = &one, +#else + .extra2 = &zero, +#endif + }, + { + .procname = "soft_watchdog", + .data = &soft_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_soft_watchdog, + .extra1 = &zero, + .extra2 = &one, + }, { .procname = "softlockup_panic", .data = &softlockup_panic, @@ -879,15 +901,6 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif /* CONFIG_SMP */ - { - .procname = "nmi_watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, - .proc_handler = proc_dowatchdog, - .extra1 = &zero, - .extra2 = &one, - }, #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { -- cgit v1.2.3 From 5bbe3547aa3ba5242366a322a28996872301b703 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Wed, 15 Apr 2015 16:13:20 -0700 Subject: mm: allow compaction of unevictable pages Currently, pages which are marked as unevictable are protected from compaction, but not from other types of migration. The POSIX real time extension explicitly states that mlock() will prevent a major page fault, but the spirit of this is that mlock() should give a process the ability to control sources of latency, including minor page faults. However, the mlock manpage only explicitly says that a locked page will not be written to swap and this can cause some confusion. The compaction code today does not give a developer who wants to avoid swap but wants to have large contiguous areas available any method to achieve this state. This patch introduces a sysctl for controlling compaction behavior with respect to the unevictable lru. Users who demand no page faults after a page is present can set compact_unevictable_allowed to 0 and users who need the large contiguous areas can enable compaction on locked memory by leaving the default value of 1. To illustrate this problem I wrote a quick test program that mmaps a large number of 1MB files filled with random data. These maps are created locked and read only. Then every other mmap is unmapped and I attempt to allocate huge pages to the static huge page pool. When the compact_unevictable_allowed sysctl is 0, I cannot allocate hugepages after fragmenting memory. When the value is set to 1, allocations succeed. Signed-off-by: Eric B Munson Acked-by: Michal Hocko Acked-by: Vlastimil Babka Acked-by: Christoph Lameter Acked-by: David Rientjes Acked-by: Rik van Riel Cc: Vlastimil Babka Cc: Thomas Gleixner Cc: Christoph Lameter Cc: Peter Zijlstra Cc: Mel Gorman Cc: David Rientjes Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8c0eabd41886..42b7fc2860c1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1335,6 +1335,15 @@ static struct ctl_table vm_table[] = { .extra1 = &min_extfrag_threshold, .extra2 = &max_extfrag_threshold, }, + { + .procname = "compact_unevictable_allowed", + .data = &sysctl_compact_unevictable_allowed, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &one, + }, #endif /* CONFIG_COMPACTION */ { -- cgit v1.2.3 From 16db3d3f1170fb0efca652c9378ce7c5f5cb4232 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Thu, 16 Apr 2015 12:47:50 -0700 Subject: kernel/sysctl.c: threads-max observe limits Users can change the maximum number of threads by writing to /proc/sys/kernel/threads-max. With the patch the value entered is checked against the same limits that apply when fork_init is called. Signed-off-by: Heinrich Schuchardt Cc: Oleg Nesterov Cc: Ingo Molnar Cc: Guenter Roeck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 42b7fc2860c1..3c0998426b57 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -93,11 +93,9 @@ #include #endif - #if defined(CONFIG_SYSCTL) /* External variables not in a header file. */ -extern int max_threads; extern int suid_dumpable; #ifdef CONFIG_COREDUMP extern int core_uses_pid; @@ -710,10 +708,10 @@ static struct ctl_table kern_table[] = { #endif { .procname = "threads-max", - .data = &max_threads, + .data = NULL, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = sysctl_max_threads, }, { .procname = "random", -- cgit v1.2.3 From 230633d109e35b0a24277498e773edeb79b4a331 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Thu, 16 Apr 2015 12:48:07 -0700 Subject: kernel/sysctl.c: detect overflows when converting to int When converting unsigned long to int overflows may occur. These currently are not detected when writing to the sysctl file system. E.g. on a system where int has 32 bits and long has 64 bits echo 0x800001234 > /proc/sys/kernel/threads-max has the same effect as echo 0x1234 > /proc/sys/kernel/threads-max The patch adds the missing check in do_proc_dointvec_conv. With the patch an overflow will result in an error EINVAL when writing to the the sysctl file system. Signed-off-by: Heinrich Schuchardt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3c0998426b57..2082b1a88fb9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1981,7 +1981,15 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, int write, void *data) { if (write) { - *valp = *negp ? -*lvalp : *lvalp; + if (*negp) { + if (*lvalp > (unsigned long) INT_MAX + 1) + return -EINVAL; + *valp = -*lvalp; + } else { + if (*lvalp > (unsigned long) INT_MAX) + return -EINVAL; + *valp = *lvalp; + } } else { int val = *valp; if (val < 0) { -- cgit v1.2.3