From d6cb41cc44c63492702281b1d329955ca767d399 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 31 Jan 2018 16:17:10 -0800 Subject: mm, hugetlb: remove hugepages_treat_as_movable sysctl hugepages_treat_as_movable has been introduced by 396faf0303d2 ("Allow huge page allocations to use GFP_HIGH_MOVABLE") to allow hugetlb allocations from ZONE_MOVABLE even when hugetlb pages were not migrateable. The purpose of the movable zone was different at the time. It aimed at reducing memory fragmentation and hugetlb pages being long lived and large werre not contributing to the fragmentation so it was acceptable to use the zone back then. Things have changed though and the primary purpose of the zone became migratability guarantee. If we allow non migrateable hugetlb pages to be in ZONE_MOVABLE memory hotplug might fail to offline the memory. Remove the knob and only rely on hugepage_migration_supported to allow movable zones. Mel said: : Primarily it was aimed at allowing the hugetlb pool to safely shrink with : the ability to grow it again. The use case was for batched jobs, some of : which needed huge pages and others that did not but didn't want the memory : useless pinned in the huge pages pool. : : I suspect that more users rely on THP than hugetlbfs for flexible use of : huge pages with fallback options so I think that removing the option : should be ok. Link: http://lkml.kernel.org/r/20171003072619.8654-1-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Alexandru Moise <00moses.alexander00@gmail.com> Acked-by: Mel Gorman Cc: Alexandru Moise <00moses.alexander00@gmail.com> Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 557d46728577..2fb4e27c636a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1374,13 +1374,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "hugepages_treat_as_movable", - .data = &hugepages_treat_as_movable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "nr_overcommit_hugepages", .data = NULL, -- cgit v1.3-14-g43fede From 4c2e4befb3cc9ce42d506aa537c9ab504723e98c Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 6 Feb 2018 15:41:45 -0800 Subject: pipe, sysctl: drop 'min' parameter from pipe-max-size converter Patch series "pipe: buffer limits fixes and cleanups", v2. This series simplifies the sysctl handler for pipe-max-size and fixes another set of bugs related to the pipe buffer limits: - The root user wasn't allowed to exceed the limits when creating new pipes. - There was an off-by-one error when checking the limits, so a limit of N was actually treated as N - 1. - F_SETPIPE_SZ accepted values over UINT_MAX. - Reading the pipe buffer limits could be racy. This patch (of 7): Before validating the given value against pipe_min_size, do_proc_dopipe_max_size_conv() calls round_pipe_size(), which rounds the value up to pipe_min_size. Therefore, the second check against pipe_min_size is redundant. Remove it. Link: http://lkml.kernel.org/r/20180111052902.14409-2-ebiggers3@gmail.com Signed-off-by: Eric Biggers Acked-by: Kees Cook Acked-by: Joe Lawrence Cc: Alexander Viro Cc: "Luis R . Rodriguez" Cc: Michael Kerrisk Cc: Mikulas Patocka Cc: Willy Tarreau Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 10 +++------- include/linux/pipe_fs_i.h | 2 +- kernel/sysctl.c | 15 +-------------- 3 files changed, 5 insertions(+), 22 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/fs/pipe.c b/fs/pipe.c index a449ca0ec0c6..1f6ec1051e59 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -35,11 +35,6 @@ */ unsigned int pipe_max_size = 1048576; -/* - * Minimum pipe size, as required by POSIX - */ -unsigned int pipe_min_size = PAGE_SIZE; - /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ @@ -1024,8 +1019,9 @@ unsigned int round_pipe_size(unsigned int size) { unsigned long nr_pages; - if (size < pipe_min_size) - size = pipe_min_size; + /* Minimum pipe size, as required by POSIX */ + if (size < PAGE_SIZE) + size = PAGE_SIZE; nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; if (nr_pages == 0) diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 2dc5e9870fcd..7d9beda14584 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -167,7 +167,7 @@ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); -extern unsigned int pipe_max_size, pipe_min_size; +extern unsigned int pipe_max_size; extern unsigned long pipe_user_pages_hard; extern unsigned long pipe_user_pages_soft; int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2fb4e27c636a..f21375aa6cf6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1813,7 +1813,6 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = &pipe_proc_fn, - .extra1 = &pipe_min_size, }, { .procname = "pipe-user-pages-hard", @@ -2615,16 +2614,10 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, do_proc_douintvec_minmax_conv, ¶m); } -struct do_proc_dopipe_max_size_conv_param { - unsigned int *min; -}; - static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { - struct do_proc_dopipe_max_size_conv_param *param = data; - if (write) { unsigned int val; @@ -2635,9 +2628,6 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, if (val == 0) return -EINVAL; - if (param->min && *param->min > val) - return -ERANGE; - *valp = val; } else { unsigned int val = *valp; @@ -2650,11 +2640,8 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, int proc_dopipe_max_size(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - struct do_proc_dopipe_max_size_conv_param param = { - .min = (unsigned int *) table->extra1, - }; return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_dopipe_max_size_conv, ¶m); + do_proc_dopipe_max_size_conv, NULL); } static void validate_coredump_safety(void) -- cgit v1.3-14-g43fede From 319e0a21bb7823abbb4818fe2724e572bbac77a2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 6 Feb 2018 15:41:49 -0800 Subject: pipe, sysctl: remove pipe_proc_fn() pipe_proc_fn() is no longer needed, as it only calls through to proc_dopipe_max_size(). Just put proc_dopipe_max_size() in the ctl_table entry directly, and remove the unneeded EXPORT_SYMBOL() and the ENOSYS stub for it. (The reason the ENOSYS stub isn't needed is that the pipe-max-size ctl_table entry is located directly in 'kern_table' rather than being registered separately. Therefore, the entry is already only defined when the kernel is built with sysctl support.) Link: http://lkml.kernel.org/r/20180111052902.14409-3-ebiggers3@gmail.com Signed-off-by: Eric Biggers Acked-by: Kees Cook Acked-by: Joe Lawrence Cc: Alexander Viro Cc: "Luis R . Rodriguez" Cc: Michael Kerrisk Cc: Mikulas Patocka Cc: Willy Tarreau Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 10 ---------- include/linux/pipe_fs_i.h | 1 - include/linux/sysctl.h | 3 --- kernel/sysctl.c | 15 +++++---------- 4 files changed, 5 insertions(+), 24 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/fs/pipe.c b/fs/pipe.c index 1f6ec1051e59..61adbf0f5b53 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1120,16 +1120,6 @@ out_revert_acct: return ret; } -/* - * This should work even if CONFIG_PROC_FS isn't set, as proc_dopipe_max_size - * will return an error. - */ -int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, - size_t *lenp, loff_t *ppos) -{ - return proc_dopipe_max_size(table, write, buf, lenp, ppos); -} - /* * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same * location, so checking ->i_pipe is not enough to verify that this is a diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 7d9beda14584..5028bd4b2c96 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -170,7 +170,6 @@ void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); extern unsigned int pipe_max_size; extern unsigned long pipe_user_pages_hard; extern unsigned long pipe_user_pages_soft; -int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *); /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 992bc9948232..b769ecfcc3bd 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -51,9 +51,6 @@ extern int proc_dointvec_minmax(struct ctl_table *, int, extern int proc_douintvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -extern int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f21375aa6cf6..59f09ea3ca3e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -218,6 +218,8 @@ static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, static int proc_dostring_coredump(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_MAGIC_SYSRQ /* Note: sysrq code uses it's own private copy */ @@ -1812,7 +1814,7 @@ static struct ctl_table fs_table[] = { .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, - .proc_handler = &pipe_proc_fn, + .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", @@ -2637,8 +2639,8 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, return 0; } -int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); @@ -3147,12 +3149,6 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } -int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -3196,7 +3192,6 @@ EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL_GPL(proc_douintvec_minmax); -EXPORT_SYMBOL_GPL(proc_dopipe_max_size); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); -- cgit v1.3-14-g43fede From 96e99be40e4cff870a83233731121ec0f7f95075 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 6 Feb 2018 15:42:00 -0800 Subject: pipe: reject F_SETPIPE_SZ with size over UINT_MAX A pipe's size is represented as an 'unsigned int'. As expected, writing a value greater than UINT_MAX to /proc/sys/fs/pipe-max-size fails with EINVAL. However, the F_SETPIPE_SZ fcntl silently truncates such values to 32 bits, rather than failing with EINVAL as expected. (It *does* fail with EINVAL for values above (1 << 31) but <= UINT_MAX.) Fix this by moving the check against UINT_MAX into round_pipe_size() which is called in both cases. Link: http://lkml.kernel.org/r/20180111052902.14409-6-ebiggers3@gmail.com Signed-off-by: Eric Biggers Acked-by: Kees Cook Acked-by: Joe Lawrence Cc: Alexander Viro Cc: "Luis R . Rodriguez" Cc: Michael Kerrisk Cc: Mikulas Patocka Cc: Willy Tarreau Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 5 ++++- include/linux/pipe_fs_i.h | 2 +- kernel/sysctl.c | 3 --- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/fs/pipe.c b/fs/pipe.c index 46c30ac777da..817393d36244 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1020,10 +1020,13 @@ const struct file_operations pipefifo_fops = { * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ -unsigned int round_pipe_size(unsigned int size) +unsigned int round_pipe_size(unsigned long size) { unsigned long nr_pages; + if (size > UINT_MAX) + return 0; + /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) size = PAGE_SIZE; diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5028bd4b2c96..5a3bb3b7c9ad 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -190,6 +190,6 @@ long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file); int create_pipe_files(struct file **, int); -unsigned int round_pipe_size(unsigned int size); +unsigned int round_pipe_size(unsigned long size); #endif diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 59f09ea3ca3e..f98f28c12020 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2623,9 +2623,6 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, if (write) { unsigned int val; - if (*lvalp > UINT_MAX) - return -EINVAL; - val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; -- cgit v1.3-14-g43fede