linux-sg2042/fs/seq_file.c

1039 lines
23 KiB
C
Raw Normal View History

/*
* linux/fs/seq_file.c
*
* helper functions for making synthetic files from sequences of records.
* initial implementation -- AV, Oct 2001.
*/
#include <linux/fs.h>
#include <linux/export.h>
#include <linux/seq_file.h>
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/cred.h>
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
#include <linux/mm.h>
#include <linux/printk.h>
#include <linux/string_helpers.h>
#include <linux/uaccess.h>
#include <asm/page.h>
static void seq_set_overflow(struct seq_file *m)
{
m->count = m->size;
}
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
static void *seq_buf_alloc(unsigned long size)
{
mm: introduce kv[mz]alloc helpers Patch series "kvmalloc", v5. There are many open coded kmalloc with vmalloc fallback instances in the tree. Most of them are not careful enough or simply do not care about the underlying semantic of the kmalloc/page allocator which means that a) some vmalloc fallbacks are basically unreachable because the kmalloc part will keep retrying until it succeeds b) the page allocator can invoke a really disruptive steps like the OOM killer to move forward which doesn't sound appropriate when we consider that the vmalloc fallback is available. As it can be seen implementing kvmalloc requires quite an intimate knowledge if the page allocator and the memory reclaim internals which strongly suggests that a helper should be implemented in the memory subsystem proper. Most callers, I could find, have been converted to use the helper instead. This is patch 6. There are some more relying on __GFP_REPEAT in the networking stack which I have converted as well and Eric Dumazet was not opposed [2] to convert them as well. [1] http://lkml.kernel.org/r/20170130094940.13546-1-mhocko@kernel.org [2] http://lkml.kernel.org/r/1485273626.16328.301.camel@edumazet-glaptop3.roam.corp.google.com This patch (of 9): Using kmalloc with the vmalloc fallback for larger allocations is a common pattern in the kernel code. Yet we do not have any common helper for that and so users have invented their own helpers. Some of them are really creative when doing so. Let's just add kv[mz]alloc and make sure it is implemented properly. This implementation makes sure to not make a large memory pressure for > PAGE_SZE requests (__GFP_NORETRY) and also to not warn about allocation failures. This also rules out the OOM killer as the vmalloc is a more approapriate fallback than a disruptive user visible action. This patch also changes some existing users and removes helpers which are specific for them. In some cases this is not possible (e.g. ext4_kvmalloc, libcfs_kvzalloc) because those seems to be broken and require GFP_NO{FS,IO} context which is not vmalloc compatible in general (note that the page table allocation is GFP_KERNEL). Those need to be fixed separately. While we are at it, document that __vmalloc{_node} about unsupported gfp mask because there seems to be a lot of confusion out there. kvmalloc_node will warn about GFP_KERNEL incompatible (which are not superset) flags to catch new abusers. Existing ones would have to die slowly. [sfr@canb.auug.org.au: f2fs fixup] Link: http://lkml.kernel.org/r/20170320163735.332e64b7@canb.auug.org.au Link: http://lkml.kernel.org/r/20170306103032.2540-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Reviewed-by: Andreas Dilger <adilger@dilger.ca> [ext4 part] Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: John Hubbard <jhubbard@nvidia.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 06:57:09 +08:00
return kvmalloc(size, GFP_KERNEL);
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
}
/**
* seq_open - initialize sequential file
* @file: file we initialize
* @op: method table describing the sequence
*
* seq_open() sets @file, associating it with a sequence described
* by @op. @op->start() sets the iterator up and returns the first
* element of sequence. @op->stop() shuts it down. @op->next()
* returns the next element of sequence. @op->show() prints element
* into the buffer. In case of error ->start() and ->next() return
* ERR_PTR(error). In the end of sequence they return %NULL. ->show()
* returns 0 in case of success and negative number in case of error.
* Returning SEQ_SKIP means "discard this element and move on".
* Note: seq_open() will allocate a struct seq_file and store its
* pointer in @file->private_data. This pointer should not be modified.
*/
int seq_open(struct file *file, const struct seq_operations *op)
{
struct seq_file *p;
WARN_ON(file->private_data);
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return -ENOMEM;
file->private_data = p;
mutex_init(&p->lock);
p->op = op;
// No refcounting: the lifetime of 'p' is constrained
// to the lifetime of the file.
p->file = file;
/*
* Wrappers around seq_open(e.g. swaps_open) need to be
* aware of this. If they set f_version themselves, they
* should call seq_open first and then set f_version.
*/
file->f_version = 0;
/*
* seq_files support lseek() and pread(). They do not implement
* write() at all, but we clear FMODE_PWRITE here for historical
* reasons.
*
* If a client of seq_files a) implements file.write() and b) wishes to
* support pwrite() then that client will need to implement its own
* file.open() which calls seq_open() and then sets FMODE_PWRITE.
*/
file->f_mode &= ~FMODE_PWRITE;
return 0;
}
EXPORT_SYMBOL(seq_open);
static int traverse(struct seq_file *m, loff_t offset)
{
loff_t pos = 0, index;
int error = 0;
void *p;
m->version = 0;
index = 0;
m->count = m->from = 0;
if (!offset) {
m->index = index;
return 0;
}
if (!m->buf) {
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
if (!m->buf)
return -ENOMEM;
}
p = m->op->start(m, &index);
while (p) {
error = PTR_ERR(p);
if (IS_ERR(p))
break;
error = m->op->show(m, p);
if (error < 0)
break;
if (unlikely(error)) {
error = 0;
m->count = 0;
}
if (seq_has_overflowed(m))
goto Eoverflow;
if (pos + m->count > offset) {
m->from = offset - pos;
m->count -= m->from;
m->index = index;
break;
}
pos += m->count;
m->count = 0;
if (pos == offset) {
index++;
m->index = index;
break;
}
p = m->op->next(m, p, &index);
}
m->op->stop(m, p);
m->index = index;
return error;
Eoverflow:
m->op->stop(m, p);
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
kvfree(m->buf);
m->count = 0;
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
m->buf = seq_buf_alloc(m->size <<= 1);
return !m->buf ? -ENOMEM : -EAGAIN;
}
/**
* seq_read - ->read() method for sequential files.
* @file: the file to read from
* @buf: the buffer to read to
* @size: the maximum number of bytes to read
* @ppos: the current position in the file
*
* Ready-made ->f_op->read()
*/
ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
{
struct seq_file *m = file->private_data;
size_t copied = 0;
loff_t pos;
size_t n;
void *p;
int err = 0;
mutex_lock(&m->lock);
/*
* seq_file->op->..m_start/m_stop/m_next may do special actions
* or optimisations based on the file->f_version, so we want to
* pass the file->f_version to those methods.
*
* seq_file->version is just copy of f_version, and seq_file
* methods can treat it simply as file version.
* It is copied in first and copied out after all operations.
* It is convenient to have it as part of structure to avoid the
* need of passing another argument to all the seq_file methods.
*/
m->version = file->f_version;
/*
* if request is to read from zero offset, reset iterator to first
* record as it might have been already advanced by previous requests
*/
if (*ppos == 0)
m->index = 0;
/* Don't assume *ppos is where we left it */
if (unlikely(*ppos != m->read_pos)) {
while ((err = traverse(m, *ppos)) == -EAGAIN)
;
if (err) {
/* With prejudice... */
m->read_pos = 0;
m->version = 0;
m->index = 0;
m->count = 0;
goto Done;
} else {
m->read_pos = *ppos;
}
}
/* grab buffer if we didn't have one */
if (!m->buf) {
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
if (!m->buf)
goto Enomem;
}
/* if not empty - flush it first */
if (m->count) {
n = min(m->count, size);
err = copy_to_user(buf, m->buf + m->from, n);
if (err)
goto Efault;
m->count -= n;
m->from += n;
size -= n;
buf += n;
copied += n;
fs/seq_file: fix out-of-bounds read seq_read() is a nasty piece of work, not to mention buggy. It has (I think) an old bug which allows unprivileged userspace to read beyond the end of m->buf. I was getting these: BUG: KASAN: slab-out-of-bounds in seq_read+0xcd2/0x1480 at addr ffff880116889880 Read of size 2713 by task trinity-c2/1329 CPU: 2 PID: 1329 Comm: trinity-c2 Not tainted 4.8.0-rc1+ #96 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: kasan_object_err+0x1c/0x80 kasan_report_error+0x2cb/0x7e0 kasan_report+0x4e/0x80 check_memory_region+0x13e/0x1a0 kasan_check_read+0x11/0x20 seq_read+0xcd2/0x1480 proc_reg_read+0x10b/0x260 do_loop_readv_writev.part.5+0x140/0x2c0 do_readv_writev+0x589/0x860 vfs_readv+0x7b/0xd0 do_readv+0xd8/0x2c0 SyS_readv+0xb/0x10 do_syscall_64+0x1b3/0x4b0 entry_SYSCALL64_slow_path+0x25/0x25 Object at ffff880116889100, in cache kmalloc-4096 size: 4096 Allocated: PID = 1329 save_stack_trace+0x26/0x80 save_stack+0x46/0xd0 kasan_kmalloc+0xad/0xe0 __kmalloc+0x1aa/0x4a0 seq_buf_alloc+0x35/0x40 seq_read+0x7d8/0x1480 proc_reg_read+0x10b/0x260 do_loop_readv_writev.part.5+0x140/0x2c0 do_readv_writev+0x589/0x860 vfs_readv+0x7b/0xd0 do_readv+0xd8/0x2c0 SyS_readv+0xb/0x10 do_syscall_64+0x1b3/0x4b0 return_from_SYSCALL_64+0x0/0x6a Freed: PID = 0 (stack is not available) Memory state around the buggy address: ffff88011688a000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff88011688a080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff88011688a100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff88011688a180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88011688a200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint This seems to be the same thing that Dave Jones was seeing here: https://lkml.org/lkml/2016/8/12/334 There are multiple issues here: 1) If we enter the function with a non-empty buffer, there is an attempt to flush it. But it was not clearing m->from after doing so, which means that if we try to do this flush twice in a row without any call to traverse() in between, we are going to be reading from the wrong place -- the splat above, fixed by this patch. 2) If there's a short write to userspace because of page faults, the buffer may already contain multiple lines (i.e. pos has advanced by more than 1), but we don't save the progress that was made so the next call will output what we've already returned previously. Since that is a much less serious issue (and I have a headache after staring at seq_read() for the past 8 hours), I'll leave that for now. Link: http://lkml.kernel.org/r/1471447270-32093-1-git-send-email-vegard.nossum@oracle.com Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com> Reported-by: Dave Jones <davej@codemonkey.org.uk> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-26 06:17:11 +08:00
if (!m->count) {
m->from = 0;
m->index++;
fs/seq_file: fix out-of-bounds read seq_read() is a nasty piece of work, not to mention buggy. It has (I think) an old bug which allows unprivileged userspace to read beyond the end of m->buf. I was getting these: BUG: KASAN: slab-out-of-bounds in seq_read+0xcd2/0x1480 at addr ffff880116889880 Read of size 2713 by task trinity-c2/1329 CPU: 2 PID: 1329 Comm: trinity-c2 Not tainted 4.8.0-rc1+ #96 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Call Trace: kasan_object_err+0x1c/0x80 kasan_report_error+0x2cb/0x7e0 kasan_report+0x4e/0x80 check_memory_region+0x13e/0x1a0 kasan_check_read+0x11/0x20 seq_read+0xcd2/0x1480 proc_reg_read+0x10b/0x260 do_loop_readv_writev.part.5+0x140/0x2c0 do_readv_writev+0x589/0x860 vfs_readv+0x7b/0xd0 do_readv+0xd8/0x2c0 SyS_readv+0xb/0x10 do_syscall_64+0x1b3/0x4b0 entry_SYSCALL64_slow_path+0x25/0x25 Object at ffff880116889100, in cache kmalloc-4096 size: 4096 Allocated: PID = 1329 save_stack_trace+0x26/0x80 save_stack+0x46/0xd0 kasan_kmalloc+0xad/0xe0 __kmalloc+0x1aa/0x4a0 seq_buf_alloc+0x35/0x40 seq_read+0x7d8/0x1480 proc_reg_read+0x10b/0x260 do_loop_readv_writev.part.5+0x140/0x2c0 do_readv_writev+0x589/0x860 vfs_readv+0x7b/0xd0 do_readv+0xd8/0x2c0 SyS_readv+0xb/0x10 do_syscall_64+0x1b3/0x4b0 return_from_SYSCALL_64+0x0/0x6a Freed: PID = 0 (stack is not available) Memory state around the buggy address: ffff88011688a000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff88011688a080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff88011688a100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff88011688a180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88011688a200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint This seems to be the same thing that Dave Jones was seeing here: https://lkml.org/lkml/2016/8/12/334 There are multiple issues here: 1) If we enter the function with a non-empty buffer, there is an attempt to flush it. But it was not clearing m->from after doing so, which means that if we try to do this flush twice in a row without any call to traverse() in between, we are going to be reading from the wrong place -- the splat above, fixed by this patch. 2) If there's a short write to userspace because of page faults, the buffer may already contain multiple lines (i.e. pos has advanced by more than 1), but we don't save the progress that was made so the next call will output what we've already returned previously. Since that is a much less serious issue (and I have a headache after staring at seq_read() for the past 8 hours), I'll leave that for now. Link: http://lkml.kernel.org/r/1471447270-32093-1-git-send-email-vegard.nossum@oracle.com Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com> Reported-by: Dave Jones <davej@codemonkey.org.uk> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-26 06:17:11 +08:00
}
if (!size)
goto Done;
}
/* we need at least one record in buffer */
pos = m->index;
p = m->op->start(m, &pos);
while (1) {
err = PTR_ERR(p);
if (!p || IS_ERR(p))
break;
err = m->op->show(m, p);
if (err < 0)
break;
if (unlikely(err))
m->count = 0;
if (unlikely(!m->count)) {
p = m->op->next(m, p, &pos);
m->index = pos;
continue;
}
if (m->count < m->size)
goto Fill;
m->op->stop(m, p);
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
kvfree(m->buf);
m->count = 0;
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
m->buf = seq_buf_alloc(m->size <<= 1);
if (!m->buf)
goto Enomem;
m->version = 0;
pos = m->index;
p = m->op->start(m, &pos);
}
m->op->stop(m, p);
m->count = 0;
goto Done;
Fill:
/* they want more? let's try to get some more */
while (m->count < size) {
size_t offs = m->count;
loff_t next = pos;
p = m->op->next(m, p, &next);
if (!p || IS_ERR(p)) {
err = PTR_ERR(p);
break;
}
err = m->op->show(m, p);
if (seq_has_overflowed(m) || err) {
m->count = offs;
if (likely(err <= 0))
break;
}
pos = next;
}
m->op->stop(m, p);
n = min(m->count, size);
err = copy_to_user(buf, m->buf, n);
if (err)
goto Efault;
copied += n;
m->count -= n;
if (m->count)
m->from = n;
else
pos++;
m->index = pos;
Done:
if (!copied)
copied = err;
else {
*ppos += copied;
m->read_pos += copied;
}
file->f_version = m->version;
mutex_unlock(&m->lock);
return copied;
Enomem:
err = -ENOMEM;
goto Done;
Efault:
err = -EFAULT;
goto Done;
}
EXPORT_SYMBOL(seq_read);
/**
* seq_lseek - ->llseek() method for sequential files.
* @file: the file in question
* @offset: new position
* @whence: 0 for absolute, 1 for relative position
*
* Ready-made ->f_op->llseek()
*/
loff_t seq_lseek(struct file *file, loff_t offset, int whence)
{
struct seq_file *m = file->private_data;
loff_t retval = -EINVAL;
mutex_lock(&m->lock);
m->version = file->f_version;
switch (whence) {
case SEEK_CUR:
offset += file->f_pos;
case SEEK_SET:
if (offset < 0)
break;
retval = offset;
if (offset != m->read_pos) {
while ((retval = traverse(m, offset)) == -EAGAIN)
;
if (retval) {
/* with extreme prejudice... */
file->f_pos = 0;
m->read_pos = 0;
m->version = 0;
m->index = 0;
m->count = 0;
} else {
m->read_pos = offset;
retval = file->f_pos = offset;
}
} else {
file->f_pos = offset;
}
}
file->f_version = m->version;
mutex_unlock(&m->lock);
return retval;
}
EXPORT_SYMBOL(seq_lseek);
/**
* seq_release - free the structures associated with sequential file.
* @file: file in question
* @inode: its inode
*
* Frees the structures associated with sequential file; can be used
* as ->f_op->release() if you don't have private data to destroy.
*/
int seq_release(struct inode *inode, struct file *file)
{
struct seq_file *m = file->private_data;
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
kvfree(m->buf);
kfree(m);
return 0;
}
EXPORT_SYMBOL(seq_release);
/**
* seq_escape - print string into buffer, escaping some characters
* @m: target buffer
* @s: string
* @esc: set of characters that need escaping
*
* Puts string into buffer, replacing each occurrence of character from
* @esc with usual octal escape.
* Use seq_has_overflowed() to check for errors.
*/
void seq_escape(struct seq_file *m, const char *s, const char *esc)
{
char *buf;
size_t size = seq_get_buf(m, &buf);
int ret;
ret = string_escape_str(s, buf, size, ESCAPE_OCTAL, esc);
seq_commit(m, ret < size ? ret : -1);
}
EXPORT_SYMBOL(seq_escape);
void seq_vprintf(struct seq_file *m, const char *f, va_list args)
{
int len;
if (m->count < m->size) {
len = vsnprintf(m->buf + m->count, m->size - m->count, f, args);
if (m->count + len < m->size) {
m->count += len;
return;
}
}
seq_set_overflow(m);
}
EXPORT_SYMBOL(seq_vprintf);
void seq_printf(struct seq_file *m, const char *f, ...)
{
va_list args;
va_start(args, f);
seq_vprintf(m, f, args);
va_end(args);
}
EXPORT_SYMBOL(seq_printf);
/**
* mangle_path - mangle and copy path to buffer beginning
* @s: buffer start
* @p: beginning of path in above buffer
* @esc: set of characters that need escaping
*
* Copy the path from @p to @s, replacing each occurrence of character from
* @esc with usual octal escape.
* Returns pointer past last written character in @s, or NULL in case of
* failure.
*/
char *mangle_path(char *s, const char *p, const char *esc)
{
while (s <= p) {
char c = *p++;
if (!c) {
return s;
} else if (!strchr(esc, c)) {
*s++ = c;
} else if (s + 4 > p) {
break;
} else {
*s++ = '\\';
*s++ = '0' + ((c & 0300) >> 6);
*s++ = '0' + ((c & 070) >> 3);
*s++ = '0' + (c & 07);
}
}
return NULL;
}
EXPORT_SYMBOL(mangle_path);
/**
* seq_path - seq_file interface to print a pathname
* @m: the seq_file handle
* @path: the struct path to print
* @esc: set of characters to escape in the output
*
* return the absolute path of 'path', as represented by the
* dentry / mnt pair in the path parameter.
*/
int seq_path(struct seq_file *m, const struct path *path, const char *esc)
{
char *buf;
size_t size = seq_get_buf(m, &buf);
int res = -1;
if (size) {
char *p = d_path(path, buf, size);
if (!IS_ERR(p)) {
char *end = mangle_path(buf, p, esc);
if (end)
res = end - buf;
}
}
seq_commit(m, res);
return res;
}
EXPORT_SYMBOL(seq_path);
/**
* seq_file_path - seq_file interface to print a pathname of a file
* @m: the seq_file handle
* @file: the struct file to print
* @esc: set of characters to escape in the output
*
* return the absolute path to the file.
*/
int seq_file_path(struct seq_file *m, struct file *file, const char *esc)
{
return seq_path(m, &file->f_path, esc);
}
EXPORT_SYMBOL(seq_file_path);
/*
* Same as seq_path, but relative to supplied root.
*/
int seq_path_root(struct seq_file *m, const struct path *path,
const struct path *root, const char *esc)
{
char *buf;
size_t size = seq_get_buf(m, &buf);
int res = -ENAMETOOLONG;
if (size) {
char *p;
p = __d_path(path, root, buf, size);
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
if (!p)
return SEQ_SKIP;
res = PTR_ERR(p);
if (!IS_ERR(p)) {
char *end = mangle_path(buf, p, esc);
if (end)
res = end - buf;
else
res = -ENAMETOOLONG;
}
}
seq_commit(m, res);
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
return res < 0 && res != -ENAMETOOLONG ? res : 0;
}
/*
* returns the path of the 'dentry' from the root of its filesystem.
*/
int seq_dentry(struct seq_file *m, struct dentry *dentry, const char *esc)
{
char *buf;
size_t size = seq_get_buf(m, &buf);
int res = -1;
if (size) {
char *p = dentry_path(dentry, buf, size);
if (!IS_ERR(p)) {
char *end = mangle_path(buf, p, esc);
if (end)
res = end - buf;
}
}
seq_commit(m, res);
return res;
}
EXPORT_SYMBOL(seq_dentry);
static void *single_start(struct seq_file *p, loff_t *pos)
{
return NULL + (*pos == 0);
}
static void *single_next(struct seq_file *p, void *v, loff_t *pos)
{
++*pos;
return NULL;
}
static void single_stop(struct seq_file *p, void *v)
{
}
int single_open(struct file *file, int (*show)(struct seq_file *, void *),
void *data)
{
struct seq_operations *op = kmalloc(sizeof(*op), GFP_KERNEL);
int res = -ENOMEM;
if (op) {
op->start = single_start;
op->next = single_next;
op->stop = single_stop;
op->show = show;
res = seq_open(file, op);
if (!res)
((struct seq_file *)file->private_data)->private = data;
else
kfree(op);
}
return res;
}
EXPORT_SYMBOL(single_open);
int single_open_size(struct file *file, int (*show)(struct seq_file *, void *),
void *data, size_t size)
{
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
char *buf = seq_buf_alloc(size);
int ret;
if (!buf)
return -ENOMEM;
ret = single_open(file, show, data);
if (ret) {
fs/seq_file: fallback to vmalloc allocation There are a couple of seq_files which use the single_open() interface. This interface requires that the whole output must fit into a single buffer. E.g. for /proc/stat allocation failures have been observed because an order-4 memory allocation failed due to memory fragmentation. In such situations reading /proc/stat is not possible anymore. Therefore change the seq_file code to fallback to vmalloc allocations which will usually result in a couple of order-0 allocations and hence also work if memory is fragmented. For reference a call trace where reading from /proc/stat failed: sadc: page allocation failure: order:4, mode:0x1040d0 CPU: 1 PID: 192063 Comm: sadc Not tainted 3.10.0-123.el7.s390x #1 [...] Call Trace: show_stack+0x6c/0xe8 warn_alloc_failed+0xd6/0x138 __alloc_pages_nodemask+0x9da/0xb68 __get_free_pages+0x2e/0x58 kmalloc_order_trace+0x44/0xc0 stat_open+0x5a/0xd8 proc_reg_open+0x8a/0x140 do_dentry_open+0x1bc/0x2c8 finish_open+0x46/0x60 do_last+0x382/0x10d0 path_openat+0xc8/0x4f8 do_filp_open+0x46/0xa8 do_sys_open+0x114/0x1f0 sysc_tracego+0x14/0x1a Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Tested-by: David Rientjes <rientjes@google.com> Cc: Ian Kent <raven@themaw.net> Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Cc: Thorsten Diehl <thorsten.diehl@de.ibm.com> Cc: Andrea Righi <andrea@betterlinux.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stefan Bader <stefan.bader@canonical.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-07-03 06:22:37 +08:00
kvfree(buf);
return ret;
}
((struct seq_file *)file->private_data)->buf = buf;
((struct seq_file *)file->private_data)->size = size;
return 0;
}
EXPORT_SYMBOL(single_open_size);
int single_release(struct inode *inode, struct file *file)
{
const struct seq_operations *op = ((struct seq_file *)file->private_data)->op;
int res = seq_release(inode, file);
kfree(op);
return res;
}
EXPORT_SYMBOL(single_release);
int seq_release_private(struct inode *inode, struct file *file)
{
struct seq_file *seq = file->private_data;
kfree(seq->private);
seq->private = NULL;
return seq_release(inode, file);
}
EXPORT_SYMBOL(seq_release_private);
void *__seq_open_private(struct file *f, const struct seq_operations *ops,
int psize)
{
int rc;
void *private;
struct seq_file *seq;
private = kzalloc(psize, GFP_KERNEL);
if (private == NULL)
goto out;
rc = seq_open(f, ops);
if (rc < 0)
goto out_free;
seq = f->private_data;
seq->private = private;
return private;
out_free:
kfree(private);
out:
return NULL;
}
EXPORT_SYMBOL(__seq_open_private);
int seq_open_private(struct file *filp, const struct seq_operations *ops,
int psize)
{
return __seq_open_private(filp, ops, psize) ? 0 : -ENOMEM;
}
EXPORT_SYMBOL(seq_open_private);
void seq_putc(struct seq_file *m, char c)
{
if (m->count >= m->size)
return;
m->buf[m->count++] = c;
}
EXPORT_SYMBOL(seq_putc);
void seq_puts(struct seq_file *m, const char *s)
{
int len = strlen(s);
if (m->count + len >= m->size) {
seq_set_overflow(m);
return;
}
memcpy(m->buf + m->count, s, len);
m->count += len;
}
EXPORT_SYMBOL(seq_puts);
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
/*
* A helper routine for putting decimal numbers without rich format of printf().
* only 'unsigned long long' is supported.
* This routine will put strlen(delimiter) + number into seq_file.
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
* This routine is very quick when you show lots of numbers.
* In usual cases, it will be better to use seq_printf(). It's easier to read.
*/
void seq_put_decimal_ull(struct seq_file *m, const char *delimiter,
unsigned long long num)
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
{
int len;
if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */
goto overflow;
len = strlen(delimiter);
if (m->count + len >= m->size)
goto overflow;
memcpy(m->buf + m->count, delimiter, len);
m->count += len;
if (m->count + 1 >= m->size)
goto overflow;
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
if (num < 10) {
m->buf[m->count++] = num + '0';
return;
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
}
len = num_to_str(m->buf + m->count, m->size - m->count, num);
if (!len)
goto overflow;
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
m->count += len;
return;
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
overflow:
seq_set_overflow(m);
procfs: add num_to_str() to speed up /proc/stat == stat_check.py num = 0 with open("/proc/stat") as f: while num < 1000 : data = f.read() f.seek(0, 0) num = num + 1 == perf shows 20.39% stat_check.py [kernel.kallsyms] [k] format_decode 13.41% stat_check.py [kernel.kallsyms] [k] number 12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf 10.85% stat_check.py [kernel.kallsyms] [k] memcpy 4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup 4.43% stat_check.py [kernel.kallsyms] [k] seq_printf This patch removes most of calls to vsnprintf() by adding num_to_str() and seq_print_decimal_ull(), which prints decimal numbers without rich functions provided by printf(). On my 8cpu box. == Before patch == [root@bluextal test]# time ./stat_check.py real 0m0.150s user 0m0.026s sys 0m0.121s == After patch == [root@bluextal test]# time ./stat_check.py real 0m0.055s user 0m0.022s sys 0m0.030s [akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()] [andrea@betterlinux.com: avoid breaking the ABI in /proc/stat] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrea Righi <andrea@betterlinux.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Turner <pjt@google.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 06:02:54 +08:00
}
EXPORT_SYMBOL(seq_put_decimal_ull);
void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num)
{
int len;
if (m->count + 3 >= m->size) /* we'll write 2 bytes at least */
goto overflow;
len = strlen(delimiter);
if (m->count + len >= m->size)
goto overflow;
memcpy(m->buf + m->count, delimiter, len);
m->count += len;
if (m->count + 2 >= m->size)
goto overflow;
if (num < 0) {
m->buf[m->count++] = '-';
num = -num;
}
if (num < 10) {
m->buf[m->count++] = num + '0';
return;
}
len = num_to_str(m->buf + m->count, m->size - m->count, num);
if (!len)
goto overflow;
m->count += len;
return;
overflow:
seq_set_overflow(m);
}
EXPORT_SYMBOL(seq_put_decimal_ll);
/**
* seq_write - write arbitrary data to buffer
* @seq: seq_file identifying the buffer to which data should be written
* @data: data address
* @len: number of bytes
*
* Return 0 on success, non-zero otherwise.
*/
int seq_write(struct seq_file *seq, const void *data, size_t len)
{
if (seq->count + len < seq->size) {
memcpy(seq->buf + seq->count, data, len);
seq->count += len;
return 0;
}
seq_set_overflow(seq);
return -1;
}
EXPORT_SYMBOL(seq_write);
/**
* seq_pad - write padding spaces to buffer
* @m: seq_file identifying the buffer to which data should be written
* @c: the byte to append after padding if non-zero
*/
void seq_pad(struct seq_file *m, char c)
{
int size = m->pad_until - m->count;
if (size > 0)
seq_printf(m, "%*s", size, "");
if (c)
seq_putc(m, c);
}
EXPORT_SYMBOL(seq_pad);
/* A complete analogue of print_hex_dump() */
void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type,
int rowsize, int groupsize, const void *buf, size_t len,
bool ascii)
{
const u8 *ptr = buf;
int i, linelen, remaining = len;
char *buffer;
size_t size;
int ret;
if (rowsize != 16 && rowsize != 32)
rowsize = 16;
for (i = 0; i < len && !seq_has_overflowed(m); i += rowsize) {
linelen = min(remaining, rowsize);
remaining -= rowsize;
switch (prefix_type) {
case DUMP_PREFIX_ADDRESS:
seq_printf(m, "%s%p: ", prefix_str, ptr + i);
break;
case DUMP_PREFIX_OFFSET:
seq_printf(m, "%s%.8x: ", prefix_str, i);
break;
default:
seq_printf(m, "%s", prefix_str);
break;
}
size = seq_get_buf(m, &buffer);
ret = hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize,
buffer, size, ascii);
seq_commit(m, ret < size ? ret : -1);
seq_putc(m, '\n');
}
}
EXPORT_SYMBOL(seq_hex_dump);
struct list_head *seq_list_start(struct list_head *head, loff_t pos)
{
struct list_head *lh;
list_for_each(lh, head)
if (pos-- == 0)
return lh;
return NULL;
}
EXPORT_SYMBOL(seq_list_start);
struct list_head *seq_list_start_head(struct list_head *head, loff_t pos)
{
if (!pos)
return head;
return seq_list_start(head, pos - 1);
}
EXPORT_SYMBOL(seq_list_start_head);
struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos)
{
struct list_head *lh;
lh = ((struct list_head *)v)->next;
++*ppos;
return lh == head ? NULL : lh;
}
EXPORT_SYMBOL(seq_list_next);
/**
* seq_hlist_start - start an iteration of a hlist
* @head: the head of the hlist
* @pos: the start position of the sequence
*
* Called at seq_file->op->start().
*/
struct hlist_node *seq_hlist_start(struct hlist_head *head, loff_t pos)
{
struct hlist_node *node;
hlist_for_each(node, head)
if (pos-- == 0)
return node;
return NULL;
}
EXPORT_SYMBOL(seq_hlist_start);
/**
* seq_hlist_start_head - start an iteration of a hlist
* @head: the head of the hlist
* @pos: the start position of the sequence
*
* Called at seq_file->op->start(). Call this function if you want to
* print a header at the top of the output.
*/
struct hlist_node *seq_hlist_start_head(struct hlist_head *head, loff_t pos)
{
if (!pos)
return SEQ_START_TOKEN;
return seq_hlist_start(head, pos - 1);
}
EXPORT_SYMBOL(seq_hlist_start_head);
/**
* seq_hlist_next - move to the next position of the hlist
* @v: the current iterator
* @head: the head of the hlist
* @ppos: the current position
*
* Called at seq_file->op->next().
*/
struct hlist_node *seq_hlist_next(void *v, struct hlist_head *head,
loff_t *ppos)
{
struct hlist_node *node = v;
++*ppos;
if (v == SEQ_START_TOKEN)
return head->first;
else
return node->next;
}
EXPORT_SYMBOL(seq_hlist_next);
/**
* seq_hlist_start_rcu - start an iteration of a hlist protected by RCU
* @head: the head of the hlist
* @pos: the start position of the sequence
*
* Called at seq_file->op->start().
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as hlist_add_head_rcu()
* as long as the traversal is guarded by rcu_read_lock().
*/
struct hlist_node *seq_hlist_start_rcu(struct hlist_head *head,
loff_t pos)
{
struct hlist_node *node;
__hlist_for_each_rcu(node, head)
if (pos-- == 0)
return node;
return NULL;
}
EXPORT_SYMBOL(seq_hlist_start_rcu);
/**
* seq_hlist_start_head_rcu - start an iteration of a hlist protected by RCU
* @head: the head of the hlist
* @pos: the start position of the sequence
*
* Called at seq_file->op->start(). Call this function if you want to
* print a header at the top of the output.
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as hlist_add_head_rcu()
* as long as the traversal is guarded by rcu_read_lock().
*/
struct hlist_node *seq_hlist_start_head_rcu(struct hlist_head *head,
loff_t pos)
{
if (!pos)
return SEQ_START_TOKEN;
return seq_hlist_start_rcu(head, pos - 1);
}
EXPORT_SYMBOL(seq_hlist_start_head_rcu);
/**
* seq_hlist_next_rcu - move to the next position of the hlist protected by RCU
* @v: the current iterator
* @head: the head of the hlist
* @ppos: the current position
*
* Called at seq_file->op->next().
*
* This list-traversal primitive may safely run concurrently with
* the _rcu list-mutation primitives such as hlist_add_head_rcu()
* as long as the traversal is guarded by rcu_read_lock().
*/
struct hlist_node *seq_hlist_next_rcu(void *v,
struct hlist_head *head,
loff_t *ppos)
{
struct hlist_node *node = v;
++*ppos;
if (v == SEQ_START_TOKEN)
return rcu_dereference(head->first);
else
return rcu_dereference(node->next);
}
EXPORT_SYMBOL(seq_hlist_next_rcu);
/**
* seq_hlist_start_precpu - start an iteration of a percpu hlist array
* @head: pointer to percpu array of struct hlist_heads
* @cpu: pointer to cpu "cursor"
* @pos: start position of sequence
*
* Called at seq_file->op->start().
*/
struct hlist_node *
seq_hlist_start_percpu(struct hlist_head __percpu *head, int *cpu, loff_t pos)
{
struct hlist_node *node;
for_each_possible_cpu(*cpu) {
hlist_for_each(node, per_cpu_ptr(head, *cpu)) {
if (pos-- == 0)
return node;
}
}
return NULL;
}
EXPORT_SYMBOL(seq_hlist_start_percpu);
/**
* seq_hlist_next_percpu - move to the next position of the percpu hlist array
* @v: pointer to current hlist_node
* @head: pointer to percpu array of struct hlist_heads
* @cpu: pointer to cpu "cursor"
* @pos: start position of sequence
*
* Called at seq_file->op->next().
*/
struct hlist_node *
seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head,
int *cpu, loff_t *pos)
{
struct hlist_node *node = v;
++*pos;
if (node->next)
return node->next;
for (*cpu = cpumask_next(*cpu, cpu_possible_mask); *cpu < nr_cpu_ids;
*cpu = cpumask_next(*cpu, cpu_possible_mask)) {
struct hlist_head *bucket = per_cpu_ptr(head, *cpu);
if (!hlist_empty(bucket))
return bucket->first;
}
return NULL;
}
EXPORT_SYMBOL(seq_hlist_next_percpu);