linux/fs/proc/proc_misc.c

904 lines
23 KiB
C
Raw Normal View History

/*
* linux/fs/proc/proc_misc.c
*
* linux/fs/proc/array.c
* Copyright (C) 1992 by Linus Torvalds
* based on ideas by Darren Senn
*
* This used to be the part of array.c. See the rest of history and credits
* there. I took this into a separate file and switched the thing to generic
* proc_file_inode_operations, leaving in array.c only per-process stuff.
* Inumbers allocation made dynamic (via create_proc_entry()). AV, May 1999.
*
* Changes:
* Fulton Green : Encapsulated position metric calculations.
* <kernel@FultonGreen.com>
*/
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/fs.h>
#include <linux/tty.h>
#include <linux/string.h>
#include <linux/mman.h>
#include <linux/proc_fs.h>
#include <linux/ioport.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/signal.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/times.h>
#include <linux/profile.h>
#include <linux/utsname.h>
#include <linux/blkdev.h>
#include <linux/hugetlb.h>
#include <linux/jiffies.h>
#include <linux/sysrq.h>
#include <linux/vmalloc.h>
#include <linux/crash_dump.h>
#include <linux/pid_namespace.h>
#include <linux/bootmem.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/io.h>
#include <asm/tlb.h>
#include <asm/div64.h>
#include "internal.h"
#define LOAD_INT(x) ((x) >> FSHIFT)
#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
/*
* Warning: stuff below (imported functions) assumes that its output will fit
* into one page. For some of those functions it may be wrong. Moreover, we
* have a way to deal with that gracefully. Right now I used straightforward
* wrappers, but this needs further analysis wrt potential overflows.
*/
extern int get_hardware_list(char *);
extern int get_stram_list(char *);
extern int get_filesystem_list(char *);
extern int get_exec_domain_list(char *);
extern int get_dma_list(char *);
static int proc_calc_metrics(char *page, char **start, off_t off,
int count, int *eof, int len)
{
if (len <= off+count) *eof = 1;
*start = page + off;
len -= off;
if (len>count) len = count;
if (len<0) len = 0;
return len;
}
static int loadavg_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int a, b, c;
int len;
a = avenrun[0] + (FIXED_1/200);
b = avenrun[1] + (FIXED_1/200);
c = avenrun[2] + (FIXED_1/200);
len = sprintf(page,"%d.%02d %d.%02d %d.%02d %ld/%d %d\n",
LOAD_INT(a), LOAD_FRAC(a),
LOAD_INT(b), LOAD_FRAC(b),
LOAD_INT(c), LOAD_FRAC(c),
pid namespaces: define and use task_active_pid_ns() wrapper With multiple pid namespaces, a process is known by some pid_t in every ancestor pid namespace. Every time the process forks, the child process also gets a pid_t in every ancestor pid namespace. While a process is visible in >=1 pid namespaces, it can see pid_t's in only one pid namespace. We call this pid namespace it's "active pid namespace", and it is always the youngest pid namespace in which the process is known. This patch defines and uses a wrapper to find the active pid namespace of a process. The implementation of the wrapper will be changed in when support for multiple pid namespaces are added. Changelog: 2.6.22-rc4-mm2-pidns1: - [Pavel Emelianov, Alexey Dobriyan] Back out the change to use task_active_pid_ns() in child_reaper() since task->nsproxy can be NULL during task exit (so child_reaper() continues to use init_pid_ns). to implement child_reaper() since init_pid_ns.child_reaper to implement child_reaper() since tsk->nsproxy can be NULL during exit. 2.6.21-rc6-mm1: - Rename task_pid_ns() to task_active_pid_ns() to reflect that a process can have multiple pid namespaces. Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Serge Hallyn <serue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:49 +08:00
nr_running(), nr_threads,
task_active_pid_ns(current)->last_pid);
return proc_calc_metrics(page, start, off, count, eof, len);
}
static int uptime_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
struct timespec uptime;
struct timespec idle;
int len;
cputime_t idletime = cputime_add(init_task.utime, init_task.stime);
do_posix_clock_monotonic_gettime(&uptime);
monotonic_to_bootbased(&uptime);
cputime_to_timespec(idletime, &idle);
len = sprintf(page,"%lu.%02lu %lu.%02lu\n",
(unsigned long) uptime.tv_sec,
(uptime.tv_nsec / (NSEC_PER_SEC / 100)),
(unsigned long) idle.tv_sec,
(idle.tv_nsec / (NSEC_PER_SEC / 100)));
return proc_calc_metrics(page, start, off, count, eof, len);
}
static int meminfo_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
struct sysinfo i;
int len;
unsigned long committed;
unsigned long allowed;
struct vmalloc_info vmi;
long cached;
/*
* display in kilobytes.
*/
#define K(x) ((x) << (PAGE_SHIFT - 10))
si_meminfo(&i);
si_swapinfo(&i);
committed = atomic_read(&vm_committed_space);
allowed = ((totalram_pages - hugetlb_total_pages())
* sysctl_overcommit_ratio / 100) + total_swap_pages;
cached = global_page_state(NR_FILE_PAGES) -
total_swapcache_pages - i.bufferram;
if (cached < 0)
cached = 0;
get_vmalloc_info(&vmi);
/*
* Tagged format, for easy grepping and expansion.
*/
len = sprintf(page,
"MemTotal: %8lu kB\n"
"MemFree: %8lu kB\n"
"Buffers: %8lu kB\n"
"Cached: %8lu kB\n"
"SwapCached: %8lu kB\n"
"Active: %8lu kB\n"
"Inactive: %8lu kB\n"
#ifdef CONFIG_HIGHMEM
"HighTotal: %8lu kB\n"
"HighFree: %8lu kB\n"
"LowTotal: %8lu kB\n"
"LowFree: %8lu kB\n"
#endif
"SwapTotal: %8lu kB\n"
"SwapFree: %8lu kB\n"
"Dirty: %8lu kB\n"
"Writeback: %8lu kB\n"
"AnonPages: %8lu kB\n"
"Mapped: %8lu kB\n"
"Slab: %8lu kB\n"
"SReclaimable: %8lu kB\n"
"SUnreclaim: %8lu kB\n"
"PageTables: %8lu kB\n"
"NFS_Unstable: %8lu kB\n"
"Bounce: %8lu kB\n"
"CommitLimit: %8lu kB\n"
"Committed_AS: %8lu kB\n"
"VmallocTotal: %8lu kB\n"
"VmallocUsed: %8lu kB\n"
"VmallocChunk: %8lu kB\n",
K(i.totalram),
K(i.freeram),
K(i.bufferram),
K(cached),
K(total_swapcache_pages),
K(global_page_state(NR_ACTIVE)),
K(global_page_state(NR_INACTIVE)),
#ifdef CONFIG_HIGHMEM
K(i.totalhigh),
K(i.freehigh),
K(i.totalram-i.totalhigh),
K(i.freeram-i.freehigh),
#endif
K(i.totalswap),
K(i.freeswap),
K(global_page_state(NR_FILE_DIRTY)),
K(global_page_state(NR_WRITEBACK)),
K(global_page_state(NR_ANON_PAGES)),
K(global_page_state(NR_FILE_MAPPED)),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
K(global_page_state(NR_SLAB_RECLAIMABLE)),
K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
K(global_page_state(NR_PAGETABLE)),
K(global_page_state(NR_UNSTABLE_NFS)),
K(global_page_state(NR_BOUNCE)),
K(allowed),
K(committed),
(unsigned long)VMALLOC_TOTAL >> 10,
vmi.used >> 10,
vmi.largest_chunk >> 10
);
len += hugetlb_report_meminfo(page + len);
return proc_calc_metrics(page, start, off, count, eof, len);
#undef K
}
extern struct seq_operations fragmentation_op;
static int fragmentation_open(struct inode *inode, struct file *file)
{
(void)inode;
return seq_open(file, &fragmentation_op);
}
static const struct file_operations fragmentation_file_operations = {
.open = fragmentation_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo This patch provides fragmentation avoidance statistics via /proc/pagetypeinfo. The information is collected only on request so there is no runtime overhead. The statistics are in three parts: The first part prints information on the size of blocks that pages are being grouped on and looks like Page block order: 10 Pages per block: 1024 The second part is a more detailed version of /proc/buddyinfo and looks like Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 Node 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0 Node 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0 Node 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0 Node 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0 Node 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4 The third part looks like Number of blocks type Unmovable Reclaimable Movable Reserve Node 0, zone DMA 0 1 2 1 Node 0, zone Normal 3 17 94 4 To walk the zones within a node with interrupts disabled, walk_zones_in_node() is introduced and shared between /proc/buddyinfo, /proc/zoneinfo and /proc/pagetypeinfo to reduce code duplication. It seems specific to what vmstat.c requires but could be broken out as a general utility function in mmzone.c if there were other other potential users. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:02 +08:00
extern struct seq_operations pagetypeinfo_op;
static int pagetypeinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &pagetypeinfo_op);
}
static const struct file_operations pagetypeinfo_file_ops = {
.open = pagetypeinfo_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
extern struct seq_operations zoneinfo_op;
static int zoneinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &zoneinfo_op);
}
static const struct file_operations proc_zoneinfo_file_operations = {
.open = zoneinfo_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int version_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len;
len = snprintf(page, PAGE_SIZE, linux_proc_banner,
utsname()->sysname,
utsname()->release,
utsname()->version);
return proc_calc_metrics(page, start, off, count, eof, len);
}
extern struct seq_operations cpuinfo_op;
static int cpuinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &cpuinfo_op);
}
static const struct file_operations proc_cpuinfo_operations = {
.open = cpuinfo_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int devinfo_show(struct seq_file *f, void *v)
{
int i = *(loff_t *) v;
if (i < CHRDEV_MAJOR_HASH_SIZE) {
if (i == 0)
seq_printf(f, "Character devices:\n");
chrdev_show(f, i);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
}
#ifdef CONFIG_BLOCK
else {
i -= CHRDEV_MAJOR_HASH_SIZE;
if (i == 0)
seq_printf(f, "\nBlock devices:\n");
blkdev_show(f, i);
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
return 0;
}
static void *devinfo_start(struct seq_file *f, loff_t *pos)
{
if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE))
return pos;
return NULL;
}
static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos)
{
(*pos)++;
if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE))
return NULL;
return pos;
}
static void devinfo_stop(struct seq_file *f, void *v)
{
/* Nothing to do */
}
static struct seq_operations devinfo_ops = {
.start = devinfo_start,
.next = devinfo_next,
.stop = devinfo_stop,
.show = devinfo_show
};
static int devinfo_open(struct inode *inode, struct file *filp)
{
return seq_open(filp, &devinfo_ops);
}
static const struct file_operations proc_devinfo_operations = {
.open = devinfo_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
extern struct seq_operations vmstat_op;
static int vmstat_open(struct inode *inode, struct file *file)
{
return seq_open(file, &vmstat_op);
}
static const struct file_operations proc_vmstat_file_operations = {
.open = vmstat_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
#ifdef CONFIG_PROC_HARDWARE
static int hardware_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len = get_hardware_list(page);
return proc_calc_metrics(page, start, off, count, eof, len);
}
#endif
#ifdef CONFIG_STRAM_PROC
static int stram_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len = get_stram_list(page);
return proc_calc_metrics(page, start, off, count, eof, len);
}
#endif
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
extern struct seq_operations partitions_op;
static int partitions_open(struct inode *inode, struct file *file)
{
return seq_open(file, &partitions_op);
}
static const struct file_operations proc_partitions_operations = {
.open = partitions_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
extern struct seq_operations diskstats_op;
static int diskstats_open(struct inode *inode, struct file *file)
{
return seq_open(file, &diskstats_op);
}
static const struct file_operations proc_diskstats_operations = {
.open = diskstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
#ifdef CONFIG_MODULES
extern struct seq_operations modules_op;
static int modules_open(struct inode *inode, struct file *file)
{
return seq_open(file, &modules_op);
}
static const struct file_operations proc_modules_operations = {
.open = modules_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
#endif
#ifdef CONFIG_SLABINFO
static int slabinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &slabinfo_op);
}
static const struct file_operations proc_slabinfo_operations = {
.open = slabinfo_open,
.read = seq_read,
.write = slabinfo_write,
.llseek = seq_lseek,
.release = seq_release,
};
[PATCH] slab: implement /proc/slab_allocators Implement /proc/slab_allocators. It produces output like: idr_layer_cache: 80 idr_pre_get+0x33/0x4e buffer_head: 2555 alloc_buffer_head+0x20/0x75 mm_struct: 9 mm_alloc+0x1e/0x42 mm_struct: 20 dup_mm+0x36/0x370 vm_area_struct: 384 dup_mm+0x18f/0x370 vm_area_struct: 151 do_mmap_pgoff+0x2e0/0x7c3 vm_area_struct: 1 split_vma+0x5a/0x10e vm_area_struct: 11 do_brk+0x206/0x2e2 vm_area_struct: 2 copy_vma+0xda/0x142 vm_area_struct: 9 setup_arg_pages+0x99/0x214 fs_cache: 8 copy_fs_struct+0x21/0x133 fs_cache: 29 copy_process+0xf38/0x10e3 files_cache: 30 alloc_files+0x1b/0xcf signal_cache: 81 copy_process+0xbaa/0x10e3 sighand_cache: 77 copy_process+0xe65/0x10e3 sighand_cache: 1 de_thread+0x4d/0x5f8 anon_vma: 241 anon_vma_prepare+0xd9/0xf3 size-2048: 1 add_sect_attrs+0x5f/0x145 size-2048: 2 journal_init_revoke+0x99/0x302 size-2048: 2 journal_init_revoke+0x137/0x302 size-2048: 2 journal_init_inode+0xf9/0x1c4 Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> DESC slab-leaks3-locking-fix EDESC From: Andrew Morton <akpm@osdl.org> Update for slab-remove-cachep-spinlock.patch Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-25 19:06:39 +08:00
#ifdef CONFIG_DEBUG_SLAB_LEAK
extern struct seq_operations slabstats_op;
static int slabstats_open(struct inode *inode, struct file *file)
{
unsigned long *n = kzalloc(PAGE_SIZE, GFP_KERNEL);
int ret = -ENOMEM;
if (n) {
ret = seq_open(file, &slabstats_op);
if (!ret) {
struct seq_file *m = file->private_data;
*n = PAGE_SIZE / (2 * sizeof(unsigned long));
m->private = n;
n = NULL;
}
kfree(n);
}
return ret;
}
static const struct file_operations proc_slabstats_operations = {
[PATCH] slab: implement /proc/slab_allocators Implement /proc/slab_allocators. It produces output like: idr_layer_cache: 80 idr_pre_get+0x33/0x4e buffer_head: 2555 alloc_buffer_head+0x20/0x75 mm_struct: 9 mm_alloc+0x1e/0x42 mm_struct: 20 dup_mm+0x36/0x370 vm_area_struct: 384 dup_mm+0x18f/0x370 vm_area_struct: 151 do_mmap_pgoff+0x2e0/0x7c3 vm_area_struct: 1 split_vma+0x5a/0x10e vm_area_struct: 11 do_brk+0x206/0x2e2 vm_area_struct: 2 copy_vma+0xda/0x142 vm_area_struct: 9 setup_arg_pages+0x99/0x214 fs_cache: 8 copy_fs_struct+0x21/0x133 fs_cache: 29 copy_process+0xf38/0x10e3 files_cache: 30 alloc_files+0x1b/0xcf signal_cache: 81 copy_process+0xbaa/0x10e3 sighand_cache: 77 copy_process+0xe65/0x10e3 sighand_cache: 1 de_thread+0x4d/0x5f8 anon_vma: 241 anon_vma_prepare+0xd9/0xf3 size-2048: 1 add_sect_attrs+0x5f/0x145 size-2048: 2 journal_init_revoke+0x99/0x302 size-2048: 2 journal_init_revoke+0x137/0x302 size-2048: 2 journal_init_inode+0xf9/0x1c4 Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> DESC slab-leaks3-locking-fix EDESC From: Andrew Morton <akpm@osdl.org> Update for slab-remove-cachep-spinlock.patch Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-25 19:06:39 +08:00
.open = slabstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
[PATCH] slab: implement /proc/slab_allocators Implement /proc/slab_allocators. It produces output like: idr_layer_cache: 80 idr_pre_get+0x33/0x4e buffer_head: 2555 alloc_buffer_head+0x20/0x75 mm_struct: 9 mm_alloc+0x1e/0x42 mm_struct: 20 dup_mm+0x36/0x370 vm_area_struct: 384 dup_mm+0x18f/0x370 vm_area_struct: 151 do_mmap_pgoff+0x2e0/0x7c3 vm_area_struct: 1 split_vma+0x5a/0x10e vm_area_struct: 11 do_brk+0x206/0x2e2 vm_area_struct: 2 copy_vma+0xda/0x142 vm_area_struct: 9 setup_arg_pages+0x99/0x214 fs_cache: 8 copy_fs_struct+0x21/0x133 fs_cache: 29 copy_process+0xf38/0x10e3 files_cache: 30 alloc_files+0x1b/0xcf signal_cache: 81 copy_process+0xbaa/0x10e3 sighand_cache: 77 copy_process+0xe65/0x10e3 sighand_cache: 1 de_thread+0x4d/0x5f8 anon_vma: 241 anon_vma_prepare+0xd9/0xf3 size-2048: 1 add_sect_attrs+0x5f/0x145 size-2048: 2 journal_init_revoke+0x99/0x302 size-2048: 2 journal_init_revoke+0x137/0x302 size-2048: 2 journal_init_inode+0xf9/0x1c4 Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> DESC slab-leaks3-locking-fix EDESC From: Andrew Morton <akpm@osdl.org> Update for slab-remove-cachep-spinlock.patch Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-25 19:06:39 +08:00
};
#endif
[PATCH] slob: introduce the SLOB allocator configurable replacement for slab allocator This adds a CONFIG_SLAB option under CONFIG_EMBEDDED. When CONFIG_SLAB is disabled, the kernel falls back to using the 'SLOB' allocator. SLOB is a traditional K&R/UNIX allocator with a SLAB emulation layer, similar to the original Linux kmalloc allocator that SLAB replaced. It's signicantly smaller code and is more memory efficient. But like all similar allocators, it scales poorly and suffers from fragmentation more than SLAB, so it's only appropriate for small systems. It's been tested extensively in the Linux-tiny tree. I've also stress-tested it with make -j 8 compiles on a 3G SMP+PREEMPT box (not recommended). Here's a comparison for otherwise identical builds, showing SLOB saving nearly half a megabyte of RAM: $ size vmlinux* text data bss dec hex filename 3336372 529360 190812 4056544 3de5e0 vmlinux-slab 3323208 527948 190684 4041840 3dac70 vmlinux-slob $ size mm/{slab,slob}.o text data bss dec hex filename 13221 752 48 14021 36c5 mm/slab.o 1896 52 8 1956 7a4 mm/slob.o /proc/meminfo: SLAB SLOB delta MemTotal: 27964 kB 27980 kB +16 kB MemFree: 24596 kB 25092 kB +496 kB Buffers: 36 kB 36 kB 0 kB Cached: 1188 kB 1188 kB 0 kB SwapCached: 0 kB 0 kB 0 kB Active: 608 kB 600 kB -8 kB Inactive: 808 kB 812 kB +4 kB HighTotal: 0 kB 0 kB 0 kB HighFree: 0 kB 0 kB 0 kB LowTotal: 27964 kB 27980 kB +16 kB LowFree: 24596 kB 25092 kB +496 kB SwapTotal: 0 kB 0 kB 0 kB SwapFree: 0 kB 0 kB 0 kB Dirty: 4 kB 12 kB +8 kB Writeback: 0 kB 0 kB 0 kB Mapped: 560 kB 556 kB -4 kB Slab: 1756 kB 0 kB -1756 kB CommitLimit: 13980 kB 13988 kB +8 kB Committed_AS: 4208 kB 4208 kB 0 kB PageTables: 28 kB 28 kB 0 kB VmallocTotal: 1007312 kB 1007312 kB 0 kB VmallocUsed: 48 kB 48 kB 0 kB VmallocChunk: 1007264 kB 1007264 kB 0 kB (this work has been sponsored in part by CELF) From: Ingo Molnar <mingo@elte.hu> Fix 32-bitness bugs in mm/slob.c. Signed-off-by: Matt Mackall <mpm@selenic.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:45 +08:00
#endif
static int show_stat(struct seq_file *p, void *v)
{
int i;
unsigned long jif;
cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
cputime64_t guest;
u64 sum = 0;
struct timespec boottime;
unsigned int *per_irq_sum;
per_irq_sum = kzalloc(sizeof(unsigned int)*NR_IRQS, GFP_KERNEL);
if (!per_irq_sum)
return -ENOMEM;
user = nice = system = idle = iowait =
irq = softirq = steal = cputime64_zero;
guest = cputime64_zero;
getboottime(&boottime);
jif = boottime.tv_sec;
for_each_possible_cpu(i) {
int j;
user = cputime64_add(user, kstat_cpu(i).cpustat.user);
nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
system = cputime64_add(system, kstat_cpu(i).cpustat.system);
idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle);
iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait);
irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq);
softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
for (j = 0; j < NR_IRQS; j++) {
unsigned int temp = kstat_cpu(i).irqs[j];
sum += temp;
per_irq_sum[j] += temp;
}
}
seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
(unsigned long long)cputime64_to_clock_t(user),
(unsigned long long)cputime64_to_clock_t(nice),
(unsigned long long)cputime64_to_clock_t(system),
(unsigned long long)cputime64_to_clock_t(idle),
(unsigned long long)cputime64_to_clock_t(iowait),
(unsigned long long)cputime64_to_clock_t(irq),
(unsigned long long)cputime64_to_clock_t(softirq),
(unsigned long long)cputime64_to_clock_t(steal),
(unsigned long long)cputime64_to_clock_t(guest));
for_each_online_cpu(i) {
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = kstat_cpu(i).cpustat.user;
nice = kstat_cpu(i).cpustat.nice;
system = kstat_cpu(i).cpustat.system;
idle = kstat_cpu(i).cpustat.idle;
iowait = kstat_cpu(i).cpustat.iowait;
irq = kstat_cpu(i).cpustat.irq;
softirq = kstat_cpu(i).cpustat.softirq;
steal = kstat_cpu(i).cpustat.steal;
guest = kstat_cpu(i).cpustat.guest;
seq_printf(p,
"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
i,
(unsigned long long)cputime64_to_clock_t(user),
(unsigned long long)cputime64_to_clock_t(nice),
(unsigned long long)cputime64_to_clock_t(system),
(unsigned long long)cputime64_to_clock_t(idle),
(unsigned long long)cputime64_to_clock_t(iowait),
(unsigned long long)cputime64_to_clock_t(irq),
(unsigned long long)cputime64_to_clock_t(softirq),
(unsigned long long)cputime64_to_clock_t(steal),
(unsigned long long)cputime64_to_clock_t(guest));
}
seq_printf(p, "intr %llu", (unsigned long long)sum);
for (i = 0; i < NR_IRQS; i++)
seq_printf(p, " %u", per_irq_sum[i]);
seq_printf(p,
"\nctxt %llu\n"
"btime %lu\n"
"processes %lu\n"
"procs_running %lu\n"
"procs_blocked %lu\n",
nr_context_switches(),
(unsigned long)jif,
total_forks,
nr_running(),
nr_iowait());
kfree(per_irq_sum);
return 0;
}
static int stat_open(struct inode *inode, struct file *file)
{
unsigned size = 4096 * (1 + num_possible_cpus() / 32);
char *buf;
struct seq_file *m;
int res;
/* don't ask for more than the kmalloc() max size, currently 128 KB */
if (size > 128 * 1024)
size = 128 * 1024;
buf = kmalloc(size, GFP_KERNEL);
if (!buf)
return -ENOMEM;
res = single_open(file, show_stat, NULL);
if (!res) {
m = file->private_data;
m->buf = buf;
m->size = size;
} else
kfree(buf);
return res;
}
static const struct file_operations proc_stat_operations = {
.open = stat_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
/*
* /proc/interrupts
*/
static void *int_seq_start(struct seq_file *f, loff_t *pos)
{
return (*pos <= NR_IRQS) ? pos : NULL;
}
static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
{
(*pos)++;
if (*pos > NR_IRQS)
return NULL;
return pos;
}
static void int_seq_stop(struct seq_file *f, void *v)
{
/* Nothing to do */
}
extern int show_interrupts(struct seq_file *f, void *v); /* In arch code */
static struct seq_operations int_seq_ops = {
.start = int_seq_start,
.next = int_seq_next,
.stop = int_seq_stop,
.show = show_interrupts
};
static int interrupts_open(struct inode *inode, struct file *filp)
{
return seq_open(filp, &int_seq_ops);
}
static const struct file_operations proc_interrupts_operations = {
.open = interrupts_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int filesystems_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len = get_filesystem_list(page);
return proc_calc_metrics(page, start, off, count, eof, len);
}
static int cmdline_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len;
len = sprintf(page, "%s\n", saved_command_line);
return proc_calc_metrics(page, start, off, count, eof, len);
}
static int locks_open(struct inode *inode, struct file *filp)
{
return seq_open(filp, &locks_seq_operations);
}
static const struct file_operations proc_locks_operations = {
.open = locks_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int execdomains_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len = get_exec_domain_list(page);
return proc_calc_metrics(page, start, off, count, eof, len);
}
#ifdef CONFIG_MAGIC_SYSRQ
/*
* writing 'C' to /proc/sysrq-trigger is like sysrq-C
*/
static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
if (count) {
char c;
if (get_user(c, buf))
return -EFAULT;
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
__handle_sysrq(c, NULL, 0);
}
return count;
}
static const struct file_operations proc_sysrq_trigger_operations = {
.write = write_sysrq_trigger,
};
#endif
#define KPMSIZE sizeof(u64)
#define KPMMASK (KPMSIZE - 1)
/* /proc/kpagecount - an array exposing page counts
*
* Each entry is a u64 representing the corresponding
* physical page count.
*/
static ssize_t kpagecount_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
u64 __user *out = (u64 __user *)buf;
struct page *ppage;
unsigned long src = *ppos;
unsigned long pfn;
ssize_t ret = 0;
u64 pcount;
pfn = src / KPMSIZE;
count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
if (src & KPMMASK || count & KPMMASK)
return -EIO;
while (count > 0) {
ppage = NULL;
if (pfn_valid(pfn))
ppage = pfn_to_page(pfn);
pfn++;
if (!ppage)
pcount = 0;
else
pcount = atomic_read(&ppage->_count);
if (put_user(pcount, out++)) {
ret = -EFAULT;
break;
}
count -= KPMSIZE;
}
*ppos += (char __user *)out - buf;
if (!ret)
ret = (char __user *)out - buf;
return ret;
}
static struct file_operations proc_kpagecount_operations = {
.llseek = mem_lseek,
.read = kpagecount_read,
};
/* /proc/kpageflags - an array exposing page flags
*
* Each entry is a u64 representing the corresponding
* physical page flags.
*/
/* These macros are used to decouple internal flags from exported ones */
#define KPF_LOCKED 0
#define KPF_ERROR 1
#define KPF_REFERENCED 2
#define KPF_UPTODATE 3
#define KPF_DIRTY 4
#define KPF_LRU 5
#define KPF_ACTIVE 6
#define KPF_SLAB 7
#define KPF_WRITEBACK 8
#define KPF_RECLAIM 9
#define KPF_BUDDY 10
#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos)
static ssize_t kpageflags_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
u64 __user *out = (u64 __user *)buf;
struct page *ppage;
unsigned long src = *ppos;
unsigned long pfn;
ssize_t ret = 0;
u64 kflags, uflags;
pfn = src / KPMSIZE;
count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
if (src & KPMMASK || count & KPMMASK)
return -EIO;
while (count > 0) {
ppage = NULL;
if (pfn_valid(pfn))
ppage = pfn_to_page(pfn);
pfn++;
if (!ppage)
kflags = 0;
else
kflags = ppage->flags;
uflags = kpf_copy_bit(KPF_LOCKED, PG_locked, kflags) |
kpf_copy_bit(kflags, KPF_ERROR, PG_error) |
kpf_copy_bit(kflags, KPF_REFERENCED, PG_referenced) |
kpf_copy_bit(kflags, KPF_UPTODATE, PG_uptodate) |
kpf_copy_bit(kflags, KPF_DIRTY, PG_dirty) |
kpf_copy_bit(kflags, KPF_LRU, PG_lru) |
kpf_copy_bit(kflags, KPF_ACTIVE, PG_active) |
kpf_copy_bit(kflags, KPF_SLAB, PG_slab) |
kpf_copy_bit(kflags, KPF_WRITEBACK, PG_writeback) |
kpf_copy_bit(kflags, KPF_RECLAIM, PG_reclaim) |
kpf_copy_bit(kflags, KPF_BUDDY, PG_buddy);
if (put_user(uflags, out++)) {
ret = -EFAULT;
break;
}
count -= KPMSIZE;
}
*ppos += (char __user *)out - buf;
if (!ret)
ret = (char __user *)out - buf;
return ret;
}
static struct file_operations proc_kpageflags_operations = {
.llseek = mem_lseek,
.read = kpageflags_read,
};
struct proc_dir_entry *proc_root_kcore;
void create_seq_entry(char *name, mode_t mode, const struct file_operations *f)
{
struct proc_dir_entry *entry;
entry = create_proc_entry(name, mode, NULL);
if (entry)
entry->proc_fops = f;
}
void __init proc_misc_init(void)
{
static struct {
char *name;
int (*read_proc)(char*,char**,off_t,int,int*,void*);
} *p, simple_ones[] = {
{"loadavg", loadavg_read_proc},
{"uptime", uptime_read_proc},
{"meminfo", meminfo_read_proc},
{"version", version_read_proc},
#ifdef CONFIG_PROC_HARDWARE
{"hardware", hardware_read_proc},
#endif
#ifdef CONFIG_STRAM_PROC
{"stram", stram_read_proc},
#endif
{"filesystems", filesystems_read_proc},
{"cmdline", cmdline_read_proc},
{"execdomains", execdomains_read_proc},
{NULL,}
};
for (p = simple_ones; p->name; p++)
create_proc_read_entry(p->name, 0, NULL, p->read_proc, NULL);
proc_symlink("mounts", NULL, "self/mounts");
/* And now for trickier ones */
#ifdef CONFIG_PRINTK
{
struct proc_dir_entry *entry;
entry = create_proc_entry("kmsg", S_IRUSR, &proc_root);
if (entry)
entry->proc_fops = &proc_kmsg_operations;
}
#endif
create_seq_entry("locks", 0, &proc_locks_operations);
create_seq_entry("devices", 0, &proc_devinfo_operations);
create_seq_entry("cpuinfo", 0, &proc_cpuinfo_operations);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
create_seq_entry("partitions", 0, &proc_partitions_operations);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
create_seq_entry("stat", 0, &proc_stat_operations);
create_seq_entry("interrupts", 0, &proc_interrupts_operations);
#ifdef CONFIG_SLABINFO
create_seq_entry("slabinfo",S_IWUSR|S_IRUGO,&proc_slabinfo_operations);
[PATCH] slab: implement /proc/slab_allocators Implement /proc/slab_allocators. It produces output like: idr_layer_cache: 80 idr_pre_get+0x33/0x4e buffer_head: 2555 alloc_buffer_head+0x20/0x75 mm_struct: 9 mm_alloc+0x1e/0x42 mm_struct: 20 dup_mm+0x36/0x370 vm_area_struct: 384 dup_mm+0x18f/0x370 vm_area_struct: 151 do_mmap_pgoff+0x2e0/0x7c3 vm_area_struct: 1 split_vma+0x5a/0x10e vm_area_struct: 11 do_brk+0x206/0x2e2 vm_area_struct: 2 copy_vma+0xda/0x142 vm_area_struct: 9 setup_arg_pages+0x99/0x214 fs_cache: 8 copy_fs_struct+0x21/0x133 fs_cache: 29 copy_process+0xf38/0x10e3 files_cache: 30 alloc_files+0x1b/0xcf signal_cache: 81 copy_process+0xbaa/0x10e3 sighand_cache: 77 copy_process+0xe65/0x10e3 sighand_cache: 1 de_thread+0x4d/0x5f8 anon_vma: 241 anon_vma_prepare+0xd9/0xf3 size-2048: 1 add_sect_attrs+0x5f/0x145 size-2048: 2 journal_init_revoke+0x99/0x302 size-2048: 2 journal_init_revoke+0x137/0x302 size-2048: 2 journal_init_inode+0xf9/0x1c4 Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> DESC slab-leaks3-locking-fix EDESC From: Andrew Morton <akpm@osdl.org> Update for slab-remove-cachep-spinlock.patch Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Alexander Nyberg <alexn@telia.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: Ravikiran Thirumalai <kiran@scalex86.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-25 19:06:39 +08:00
#ifdef CONFIG_DEBUG_SLAB_LEAK
create_seq_entry("slab_allocators", 0 ,&proc_slabstats_operations);
#endif
[PATCH] slob: introduce the SLOB allocator configurable replacement for slab allocator This adds a CONFIG_SLAB option under CONFIG_EMBEDDED. When CONFIG_SLAB is disabled, the kernel falls back to using the 'SLOB' allocator. SLOB is a traditional K&R/UNIX allocator with a SLAB emulation layer, similar to the original Linux kmalloc allocator that SLAB replaced. It's signicantly smaller code and is more memory efficient. But like all similar allocators, it scales poorly and suffers from fragmentation more than SLAB, so it's only appropriate for small systems. It's been tested extensively in the Linux-tiny tree. I've also stress-tested it with make -j 8 compiles on a 3G SMP+PREEMPT box (not recommended). Here's a comparison for otherwise identical builds, showing SLOB saving nearly half a megabyte of RAM: $ size vmlinux* text data bss dec hex filename 3336372 529360 190812 4056544 3de5e0 vmlinux-slab 3323208 527948 190684 4041840 3dac70 vmlinux-slob $ size mm/{slab,slob}.o text data bss dec hex filename 13221 752 48 14021 36c5 mm/slab.o 1896 52 8 1956 7a4 mm/slob.o /proc/meminfo: SLAB SLOB delta MemTotal: 27964 kB 27980 kB +16 kB MemFree: 24596 kB 25092 kB +496 kB Buffers: 36 kB 36 kB 0 kB Cached: 1188 kB 1188 kB 0 kB SwapCached: 0 kB 0 kB 0 kB Active: 608 kB 600 kB -8 kB Inactive: 808 kB 812 kB +4 kB HighTotal: 0 kB 0 kB 0 kB HighFree: 0 kB 0 kB 0 kB LowTotal: 27964 kB 27980 kB +16 kB LowFree: 24596 kB 25092 kB +496 kB SwapTotal: 0 kB 0 kB 0 kB SwapFree: 0 kB 0 kB 0 kB Dirty: 4 kB 12 kB +8 kB Writeback: 0 kB 0 kB 0 kB Mapped: 560 kB 556 kB -4 kB Slab: 1756 kB 0 kB -1756 kB CommitLimit: 13980 kB 13988 kB +8 kB Committed_AS: 4208 kB 4208 kB 0 kB PageTables: 28 kB 28 kB 0 kB VmallocTotal: 1007312 kB 1007312 kB 0 kB VmallocUsed: 48 kB 48 kB 0 kB VmallocChunk: 1007264 kB 1007264 kB 0 kB (this work has been sponsored in part by CELF) From: Ingo Molnar <mingo@elte.hu> Fix 32-bitness bugs in mm/slob.c. Signed-off-by: Matt Mackall <mpm@selenic.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:45 +08:00
#endif
create_seq_entry("buddyinfo",S_IRUGO, &fragmentation_file_operations);
Print out statistics in relation to fragmentation avoidance to /proc/pagetypeinfo This patch provides fragmentation avoidance statistics via /proc/pagetypeinfo. The information is collected only on request so there is no runtime overhead. The statistics are in three parts: The first part prints information on the size of blocks that pages are being grouped on and looks like Page block order: 10 Pages per block: 1024 The second part is a more detailed version of /proc/buddyinfo and looks like Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 Node 0, zone DMA, type Unmovable 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Reclaimable 1 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Movable 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Reserve 0 4 4 0 0 0 0 1 0 1 0 Node 0, zone Normal, type Unmovable 111 8 4 4 2 3 1 0 0 0 0 Node 0, zone Normal, type Reclaimable 293 89 8 0 0 0 0 0 0 0 0 Node 0, zone Normal, type Movable 1 6 13 9 7 6 3 0 0 0 0 Node 0, zone Normal, type Reserve 0 0 0 0 0 0 0 0 0 0 4 The third part looks like Number of blocks type Unmovable Reclaimable Movable Reserve Node 0, zone DMA 0 1 2 1 Node 0, zone Normal 3 17 94 4 To walk the zones within a node with interrupts disabled, walk_zones_in_node() is introduced and shared between /proc/buddyinfo, /proc/zoneinfo and /proc/pagetypeinfo to reduce code duplication. It seems specific to what vmstat.c requires but could be broken out as a general utility function in mmzone.c if there were other other potential users. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:26:02 +08:00
create_seq_entry("pagetypeinfo", S_IRUGO, &pagetypeinfo_file_ops);
create_seq_entry("vmstat",S_IRUGO, &proc_vmstat_file_operations);
create_seq_entry("zoneinfo",S_IRUGO, &proc_zoneinfo_file_operations);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
create_seq_entry("diskstats", 0, &proc_diskstats_operations);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
#ifdef CONFIG_MODULES
create_seq_entry("modules", 0, &proc_modules_operations);
#endif
#ifdef CONFIG_SCHEDSTATS
create_seq_entry("schedstat", 0, &proc_schedstat_operations);
#endif
#ifdef CONFIG_PROC_KCORE
proc_root_kcore = create_proc_entry("kcore", S_IRUSR, NULL);
if (proc_root_kcore) {
proc_root_kcore->proc_fops = &proc_kcore_operations;
proc_root_kcore->size =
(size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
}
#endif
create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations);
create_seq_entry("kpageflags", S_IRUSR, &proc_kpageflags_operations);
#ifdef CONFIG_PROC_VMCORE
proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
if (proc_vmcore)
proc_vmcore->proc_fops = &proc_vmcore_operations;
#endif
#ifdef CONFIG_MAGIC_SYSRQ
{
struct proc_dir_entry *entry;
entry = create_proc_entry("sysrq-trigger", S_IWUSR, NULL);
if (entry)
entry->proc_fops = &proc_sysrq_trigger_operations;
}
#endif
}