1
0
Fork 0
alistair23-linux/include/linux/mman.h

134 lines
3.1 KiB
C
Raw Normal View History

#ifndef _LINUX_MMAN_H
#define _LINUX_MMAN_H
#include <linux/mm.h>
mm: fix Committed_AS underflow on large NR_CPUS environment The Committed_AS field can underflow in certain situations: > # while true; do cat /proc/meminfo | grep _AS; sleep 1; done | uniq -c > 1 Committed_AS: 18446744073709323392 kB > 11 Committed_AS: 18446744073709455488 kB > 6 Committed_AS: 35136 kB > 5 Committed_AS: 18446744073709454400 kB > 7 Committed_AS: 35904 kB > 3 Committed_AS: 18446744073709453248 kB > 2 Committed_AS: 34752 kB > 9 Committed_AS: 18446744073709453248 kB > 8 Committed_AS: 34752 kB > 3 Committed_AS: 18446744073709320960 kB > 7 Committed_AS: 18446744073709454080 kB > 3 Committed_AS: 18446744073709320960 kB > 5 Committed_AS: 18446744073709454080 kB > 6 Committed_AS: 18446744073709320960 kB Because NR_CPUS can be greater than 1000 and meminfo_proc_show() does not check for underflow. But NR_CPUS proportional isn't good calculation. In general, possibility of lock contention is proportional to the number of online cpus, not theorical maximum cpus (NR_CPUS). The current kernel has generic percpu-counter stuff. using it is right way. it makes code simplify and percpu_counter_read_positive() don't make underflow issue. Reported-by: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> [All kernel versions] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-30 16:08:51 -06:00
#include <linux/percpu_counter.h>
#include <linux/atomic.h>
#include <uapi/linux/mman.h>
mm: introduce MAP_SHARED_VALIDATE, a mechanism to safely define new mmap flags The mmap(2) syscall suffers from the ABI anti-pattern of not validating unknown flags. However, proposals like MAP_SYNC need a mechanism to define new behavior that is known to fail on older kernels without the support. Define a new MAP_SHARED_VALIDATE flag pattern that is guaranteed to fail on all legacy mmap implementations. It is worth noting that the original proposal was for a standalone MAP_VALIDATE flag. However, when that could not be supported by all archs Linus observed: I see why you *think* you want a bitmap. You think you want a bitmap because you want to make MAP_VALIDATE be part of MAP_SYNC etc, so that people can do ret = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_SYNC, fd, 0); and "know" that MAP_SYNC actually takes. And I'm saying that whole wish is bogus. You're fundamentally depending on special semantics, just make it explicit. It's already not portable, so don't try to make it so. Rename that MAP_VALIDATE as MAP_SHARED_VALIDATE, make it have a value of 0x3, and make people do ret = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED_VALIDATE | MAP_SYNC, fd, 0); and then the kernel side is easier too (none of that random garbage playing games with looking at the "MAP_VALIDATE bit", but just another case statement in that map type thing. Boom. Done. Similar to ->fallocate() we also want the ability to validate the support for new flags on a per ->mmap() 'struct file_operations' instance basis. Towards that end arrange for flags to be generically validated against a mmap_supported_flags exported by 'struct file_operations'. By default all existing flags are implicitly supported, but new flags require MAP_SHARED_VALIDATE and per-instance-opt-in. Cc: Jan Kara <jack@suse.cz> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Andy Lutomirski <luto@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Suggested-by: Christoph Hellwig <hch@lst.de> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-11-01 09:36:30 -06:00
/*
* Arrange for legacy / undefined architecture specific flags to be
* ignored by default in LEGACY_MAP_MASK.
*/
#ifndef MAP_32BIT
#define MAP_32BIT 0
#endif
#ifndef MAP_HUGE_2MB
#define MAP_HUGE_2MB 0
#endif
#ifndef MAP_HUGE_1GB
#define MAP_HUGE_1GB 0
#endif
#ifndef MAP_UNINITIALIZED
#define MAP_UNINITIALIZED 0
#endif
/*
* The historical set of flags that all mmap implementations implicitly
* support when a ->mmap_validate() op is not provided in file_operations.
*/
#define LEGACY_MAP_MASK (MAP_SHARED \
| MAP_PRIVATE \
| MAP_FIXED \
| MAP_ANONYMOUS \
| MAP_DENYWRITE \
| MAP_EXECUTABLE \
| MAP_UNINITIALIZED \
| MAP_GROWSDOWN \
| MAP_LOCKED \
| MAP_NORESERVE \
| MAP_POPULATE \
| MAP_NONBLOCK \
| MAP_STACK \
| MAP_HUGETLB \
| MAP_32BIT \
| MAP_HUGE_2MB \
| MAP_HUGE_1GB)
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern unsigned long sysctl_overcommit_kbytes;
mm: fix Committed_AS underflow on large NR_CPUS environment The Committed_AS field can underflow in certain situations: > # while true; do cat /proc/meminfo | grep _AS; sleep 1; done | uniq -c > 1 Committed_AS: 18446744073709323392 kB > 11 Committed_AS: 18446744073709455488 kB > 6 Committed_AS: 35136 kB > 5 Committed_AS: 18446744073709454400 kB > 7 Committed_AS: 35904 kB > 3 Committed_AS: 18446744073709453248 kB > 2 Committed_AS: 34752 kB > 9 Committed_AS: 18446744073709453248 kB > 8 Committed_AS: 34752 kB > 3 Committed_AS: 18446744073709320960 kB > 7 Committed_AS: 18446744073709454080 kB > 3 Committed_AS: 18446744073709320960 kB > 5 Committed_AS: 18446744073709454080 kB > 6 Committed_AS: 18446744073709320960 kB Because NR_CPUS can be greater than 1000 and meminfo_proc_show() does not check for underflow. But NR_CPUS proportional isn't good calculation. In general, possibility of lock contention is proportional to the number of online cpus, not theorical maximum cpus (NR_CPUS). The current kernel has generic percpu-counter stuff. using it is right way. it makes code simplify and percpu_counter_read_positive() don't make underflow issue. Reported-by: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> [All kernel versions] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-30 16:08:51 -06:00
extern struct percpu_counter vm_committed_as;
#ifdef CONFIG_SMP
extern s32 vm_committed_as_batch;
#else
#define vm_committed_as_batch 0
#endif
unsigned long vm_memory_committed(void);
static inline void vm_acct_memory(long pages)
{
percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch);
}
static inline void vm_unacct_memory(long pages)
{
vm_acct_memory(-pages);
}
/*
* Allow architectures to handle additional protection bits
*/
#ifndef arch_calc_vm_prot_bits
mm/core, arch, powerpc: Pass a protection key in to calc_vm_flag_bits() This plumbs a protection key through calc_vm_flag_bits(). We could have done this in calc_vm_prot_bits(), but I did not feel super strongly which way to go. It was pretty arbitrary which one to use. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arve Hjønnevåg <arve@android.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Chen Gang <gang.chen.5i5j@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave@sr71.net> Cc: David Airlie <airlied@linux.ie> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Geliang Tang <geliangtang@163.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Leon Romanovsky <leon@leon.nu> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Riley Andrews <riandrews@android.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Cc: devel@driverdev.osuosl.org Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20160212210231.E6F1F0D6@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 14:02:31 -07:00
#define arch_calc_vm_prot_bits(prot, pkey) 0
#endif
#ifndef arch_vm_get_page_prot
#define arch_vm_get_page_prot(vm_flags) __pgprot(0)
#endif
#ifndef arch_validate_prot
/*
* This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have
* already been masked out.
*
* Returns true if the prot flags are valid
*/
static inline bool arch_validate_prot(unsigned long prot)
{
return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0;
}
#define arch_validate_prot arch_validate_prot
#endif
/*
* Optimisation macro. It is equivalent to:
* (x & bit1) ? bit2 : 0
* but this version is faster.
* ("bit1" and "bit2" must be single bits)
*/
#define _calc_vm_trans(x, bit1, bit2) \
((!(bit1) || !(bit2)) ? 0 : \
((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \
: ((x) & (bit1)) / ((bit1) / (bit2))))
/*
* Combine the mmap "prot" argument into "vm_flags" used internally.
*/
static inline unsigned long
mm/core, arch, powerpc: Pass a protection key in to calc_vm_flag_bits() This plumbs a protection key through calc_vm_flag_bits(). We could have done this in calc_vm_prot_bits(), but I did not feel super strongly which way to go. It was pretty arbitrary which one to use. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arve Hjønnevåg <arve@android.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Chen Gang <gang.chen.5i5j@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave@sr71.net> Cc: David Airlie <airlied@linux.ie> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Geliang Tang <geliangtang@163.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Leon Romanovsky <leon@leon.nu> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Riley Andrews <riandrews@android.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Cc: devel@driverdev.osuosl.org Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20160212210231.E6F1F0D6@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 14:02:31 -07:00
calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
{
return _calc_vm_trans(prot, PROT_READ, VM_READ ) |
_calc_vm_trans(prot, PROT_WRITE, VM_WRITE) |
_calc_vm_trans(prot, PROT_EXEC, VM_EXEC) |
mm/core, arch, powerpc: Pass a protection key in to calc_vm_flag_bits() This plumbs a protection key through calc_vm_flag_bits(). We could have done this in calc_vm_prot_bits(), but I did not feel super strongly which way to go. It was pretty arbitrary which one to use. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arve Hjønnevåg <arve@android.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Chen Gang <gang.chen.5i5j@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave@sr71.net> Cc: David Airlie <airlied@linux.ie> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Geliang Tang <geliangtang@163.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Leon Romanovsky <leon@leon.nu> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Riley Andrews <riandrews@android.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Cc: devel@driverdev.osuosl.org Cc: linux-api@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20160212210231.E6F1F0D6@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 14:02:31 -07:00
arch_calc_vm_prot_bits(prot, pkey);
}
/*
* Combine the mmap "flags" argument into "vm_flags" used internally.
*/
static inline unsigned long
calc_vm_flag_bits(unsigned long flags)
{
return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) |
_calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) |
_calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED );
}
unsigned long vm_commit_limit(void);
#endif /* _LINUX_MMAN_H */