![David Howells](/assets/img/avatar_default.png)
Make VMAs per mm_struct as for MMU-mode linux. This solves two problems: (1) In SYSV SHM where nattch for a segment does not reflect the number of shmat's (and forks) done. (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an exec'ing process when VM_EXECUTABLE is specified, regardless of the fact that a VMA might be shared and already have its vm_mm assigned to another process or a dead process. A new struct (vm_region) is introduced to track a mapped region and to remember the circumstances under which it may be shared and the vm_list_struct structure is discarded as it's no longer required. This patch makes the following additional changes: (1) Regions are now allocated with alloc_pages() rather than kmalloc() and with no recourse to __GFP_COMP, so the pages are not composite. Instead, each page has a reference on it held by the region. Anything else that is interested in such a page will have to get a reference on it to retain it. When the pages are released due to unmapping, each page is passed to put_page() and will be freed when the page usage count reaches zero. (2) Excess pages are trimmed after an allocation as the allocation must be made as a power-of-2 quantity of pages. (3) VMAs are added to the parent MM's R/B tree and mmap lists. As an MM may end up with overlapping VMAs within the tree, the VMA struct address is appended to the sort key. (4) Non-anonymous VMAs are now added to the backing inode's prio list. (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of the backing region. The VMA and region structs will be split if necessary. (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory segment instead of all the attachments at that addresss. Multiple shmat()'s return the same address under NOMMU-mode instead of different virtual addresses as under MMU-mode. (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode. (8) /proc/maps is now the global list of mapped regions, and may list bits that aren't actually mapped anywhere. (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount of RAM currently allocated by mmap to hold mappable regions that can't be mapped directly. These are copies of the backing device or file if not anonymous. These changes make NOMMU mode more similar to MMU mode. The downside is that NOMMU mode requires some extra memory to track things over NOMMU without this patch (VMAs are no longer shared, and there are now region structs). Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Mike Frysinger <vapier.adi@gmail.com> Acked-by: Paul Mundt <lethal@linux-sh.org>
94 lines
2.8 KiB
C
94 lines
2.8 KiB
C
/* internal.h: internal procfs definitions
|
|
*
|
|
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/proc_fs.h>
|
|
|
|
extern struct proc_dir_entry proc_root;
|
|
#ifdef CONFIG_PROC_SYSCTL
|
|
extern int proc_sys_init(void);
|
|
#else
|
|
static inline void proc_sys_init(void) { }
|
|
#endif
|
|
#ifdef CONFIG_NET
|
|
extern int proc_net_init(void);
|
|
#else
|
|
static inline int proc_net_init(void) { return 0; }
|
|
#endif
|
|
|
|
struct vmalloc_info {
|
|
unsigned long used;
|
|
unsigned long largest_chunk;
|
|
};
|
|
|
|
extern struct mm_struct *mm_for_maps(struct task_struct *);
|
|
|
|
#ifdef CONFIG_MMU
|
|
#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
|
|
extern void get_vmalloc_info(struct vmalloc_info *vmi);
|
|
#else
|
|
|
|
#define VMALLOC_TOTAL 0UL
|
|
#define get_vmalloc_info(vmi) \
|
|
do { \
|
|
(vmi)->used = 0; \
|
|
(vmi)->largest_chunk = 0; \
|
|
} while(0)
|
|
#endif
|
|
|
|
extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
|
|
struct pid *pid, struct task_struct *task);
|
|
extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
|
|
struct pid *pid, struct task_struct *task);
|
|
extern int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
|
|
struct pid *pid, struct task_struct *task);
|
|
extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
|
|
struct pid *pid, struct task_struct *task);
|
|
extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
|
|
|
|
extern const struct file_operations proc_maps_operations;
|
|
extern const struct file_operations proc_numa_maps_operations;
|
|
extern const struct file_operations proc_smaps_operations;
|
|
extern const struct file_operations proc_clear_refs_operations;
|
|
extern const struct file_operations proc_pagemap_operations;
|
|
extern const struct file_operations proc_net_operations;
|
|
extern const struct inode_operations proc_net_inode_operations;
|
|
|
|
void free_proc_entry(struct proc_dir_entry *de);
|
|
|
|
void proc_init_inodecache(void);
|
|
|
|
static inline struct pid *proc_pid(struct inode *inode)
|
|
{
|
|
return PROC_I(inode)->pid;
|
|
}
|
|
|
|
static inline struct task_struct *get_proc_task(struct inode *inode)
|
|
{
|
|
return get_pid_task(proc_pid(inode), PIDTYPE_PID);
|
|
}
|
|
|
|
static inline int proc_fd(struct inode *inode)
|
|
{
|
|
return PROC_I(inode)->fd;
|
|
}
|
|
|
|
struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino,
|
|
struct dentry *dentry);
|
|
int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
|
|
filldir_t filldir);
|
|
|
|
struct pde_opener {
|
|
struct inode *inode;
|
|
struct file *file;
|
|
int (*release)(struct inode *, struct file *);
|
|
struct list_head lh;
|
|
};
|