mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 23:26:45 +07:00
b76437579d
Stack for a new thread is mapped by userspace code and passed via sys_clone. This memory is currently seen as anonymous in /proc/<pid>/maps, which makes it difficult to ascertain which mappings are being used for thread stacks. This patch uses the individual task stack pointers to determine which vmas are actually thread stacks. For a multithreaded program like the following: #include <pthread.h> void *thread_main(void *foo) { while(1); } int main() { pthread_t t; pthread_create(&t, NULL, thread_main, NULL); pthread_join(t, NULL); } proc/PID/maps looks like the following: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:002097482
/lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:002097482
/lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:002097482
/lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:002097482
/lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Here, one could guess that 7f8a44492000-7f8a44c92000 is a stack since the earlier vma that has no permissions (7f8a44e3d000-7f8a4503d000) but that is not always a reliable way to find out which vma is a thread stack. Also, /proc/PID/maps and /proc/PID/task/TID/maps has the same content. With this patch in place, /proc/PID/task/TID/maps are treated as 'maps as the task would see it' and hence, only the vma that that task uses as stack is marked as [stack]. All other 'stack' vmas are marked as anonymous memory. /proc/PID/maps acts as a thread group level view, where all thread stack vmas are marked as [stack:TID] where TID is the process ID of the task that uses that vma as stack, while the process stack is marked as [stack]. So /proc/PID/maps will look like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:002097482
/lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:002097482
/lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:002097482
/lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:002097482
/lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Thus marking all vmas that are used as stacks by the threads in the thread group along with the process stack. The task level maps will however like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:002097482
/lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:002097482
/lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:002097482
/lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:002097482
/lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] where only the vma that is being used as a stack by *that* task is marked as [stack]. Analogous changes have been made to /proc/PID/smaps, /proc/PID/numa_maps, /proc/PID/task/TID/smaps and /proc/PID/task/TID/numa_maps. Relevant snippets from smaps and numa_maps: [siddhesh@localhost ~ ]$ pgrep a.out 1441 [siddhesh@localhost ~ ]$ cat /proc/1441/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/smaps | grep "\[stack" 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/numa_maps | grep "stack" 7f8a44492000 default stack:1442 anon=2 dirty=2 N0=2 7fff6273a000 default stack anon=3 dirty=3 N0=3 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/numa_maps | grep "stack" 7f8a44492000 default stack anon=2 dirty=2 N0=2 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/numa_maps | grep "stack" 7fff6273a000 default stack anon=3 dirty=3 N0=3 [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix build] Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Jamie Lokier <jamie@shareable.org> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
351 lines
8.1 KiB
C
351 lines
8.1 KiB
C
#include <linux/mm.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/string.h>
|
|
#include <linux/export.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sched.h>
|
|
#include <asm/uaccess.h>
|
|
|
|
#include "internal.h"
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/kmem.h>
|
|
|
|
/**
|
|
* kstrdup - allocate space for and copy an existing string
|
|
* @s: the string to duplicate
|
|
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
|
|
*/
|
|
char *kstrdup(const char *s, gfp_t gfp)
|
|
{
|
|
size_t len;
|
|
char *buf;
|
|
|
|
if (!s)
|
|
return NULL;
|
|
|
|
len = strlen(s) + 1;
|
|
buf = kmalloc_track_caller(len, gfp);
|
|
if (buf)
|
|
memcpy(buf, s, len);
|
|
return buf;
|
|
}
|
|
EXPORT_SYMBOL(kstrdup);
|
|
|
|
/**
|
|
* kstrndup - allocate space for and copy an existing string
|
|
* @s: the string to duplicate
|
|
* @max: read at most @max chars from @s
|
|
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
|
|
*/
|
|
char *kstrndup(const char *s, size_t max, gfp_t gfp)
|
|
{
|
|
size_t len;
|
|
char *buf;
|
|
|
|
if (!s)
|
|
return NULL;
|
|
|
|
len = strnlen(s, max);
|
|
buf = kmalloc_track_caller(len+1, gfp);
|
|
if (buf) {
|
|
memcpy(buf, s, len);
|
|
buf[len] = '\0';
|
|
}
|
|
return buf;
|
|
}
|
|
EXPORT_SYMBOL(kstrndup);
|
|
|
|
/**
|
|
* kmemdup - duplicate region of memory
|
|
*
|
|
* @src: memory region to duplicate
|
|
* @len: memory region length
|
|
* @gfp: GFP mask to use
|
|
*/
|
|
void *kmemdup(const void *src, size_t len, gfp_t gfp)
|
|
{
|
|
void *p;
|
|
|
|
p = kmalloc_track_caller(len, gfp);
|
|
if (p)
|
|
memcpy(p, src, len);
|
|
return p;
|
|
}
|
|
EXPORT_SYMBOL(kmemdup);
|
|
|
|
/**
|
|
* memdup_user - duplicate memory region from user space
|
|
*
|
|
* @src: source address in user space
|
|
* @len: number of bytes to copy
|
|
*
|
|
* Returns an ERR_PTR() on failure.
|
|
*/
|
|
void *memdup_user(const void __user *src, size_t len)
|
|
{
|
|
void *p;
|
|
|
|
/*
|
|
* Always use GFP_KERNEL, since copy_from_user() can sleep and
|
|
* cause pagefault, which makes it pointless to use GFP_NOFS
|
|
* or GFP_ATOMIC.
|
|
*/
|
|
p = kmalloc_track_caller(len, GFP_KERNEL);
|
|
if (!p)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
if (copy_from_user(p, src, len)) {
|
|
kfree(p);
|
|
return ERR_PTR(-EFAULT);
|
|
}
|
|
|
|
return p;
|
|
}
|
|
EXPORT_SYMBOL(memdup_user);
|
|
|
|
/**
|
|
* __krealloc - like krealloc() but don't free @p.
|
|
* @p: object to reallocate memory for.
|
|
* @new_size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate.
|
|
*
|
|
* This function is like krealloc() except it never frees the originally
|
|
* allocated buffer. Use this if you don't want to free the buffer immediately
|
|
* like, for example, with RCU.
|
|
*/
|
|
void *__krealloc(const void *p, size_t new_size, gfp_t flags)
|
|
{
|
|
void *ret;
|
|
size_t ks = 0;
|
|
|
|
if (unlikely(!new_size))
|
|
return ZERO_SIZE_PTR;
|
|
|
|
if (p)
|
|
ks = ksize(p);
|
|
|
|
if (ks >= new_size)
|
|
return (void *)p;
|
|
|
|
ret = kmalloc_track_caller(new_size, flags);
|
|
if (ret && p)
|
|
memcpy(ret, p, ks);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__krealloc);
|
|
|
|
/**
|
|
* krealloc - reallocate memory. The contents will remain unchanged.
|
|
* @p: object to reallocate memory for.
|
|
* @new_size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate.
|
|
*
|
|
* The contents of the object pointed to are preserved up to the
|
|
* lesser of the new and old sizes. If @p is %NULL, krealloc()
|
|
* behaves exactly like kmalloc(). If @size is 0 and @p is not a
|
|
* %NULL pointer, the object pointed to is freed.
|
|
*/
|
|
void *krealloc(const void *p, size_t new_size, gfp_t flags)
|
|
{
|
|
void *ret;
|
|
|
|
if (unlikely(!new_size)) {
|
|
kfree(p);
|
|
return ZERO_SIZE_PTR;
|
|
}
|
|
|
|
ret = __krealloc(p, new_size, flags);
|
|
if (ret && p != ret)
|
|
kfree(p);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(krealloc);
|
|
|
|
/**
|
|
* kzfree - like kfree but zero memory
|
|
* @p: object to free memory of
|
|
*
|
|
* The memory of the object @p points to is zeroed before freed.
|
|
* If @p is %NULL, kzfree() does nothing.
|
|
*
|
|
* Note: this function zeroes the whole allocated buffer which can be a good
|
|
* deal bigger than the requested buffer size passed to kmalloc(). So be
|
|
* careful when using this function in performance sensitive code.
|
|
*/
|
|
void kzfree(const void *p)
|
|
{
|
|
size_t ks;
|
|
void *mem = (void *)p;
|
|
|
|
if (unlikely(ZERO_OR_NULL_PTR(mem)))
|
|
return;
|
|
ks = ksize(mem);
|
|
memset(mem, 0, ks);
|
|
kfree(mem);
|
|
}
|
|
EXPORT_SYMBOL(kzfree);
|
|
|
|
/*
|
|
* strndup_user - duplicate an existing string from user space
|
|
* @s: The string to duplicate
|
|
* @n: Maximum number of bytes to copy, including the trailing NUL.
|
|
*/
|
|
char *strndup_user(const char __user *s, long n)
|
|
{
|
|
char *p;
|
|
long length;
|
|
|
|
length = strnlen_user(s, n);
|
|
|
|
if (!length)
|
|
return ERR_PTR(-EFAULT);
|
|
|
|
if (length > n)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
p = memdup_user(s, length);
|
|
|
|
if (IS_ERR(p))
|
|
return p;
|
|
|
|
p[length - 1] = '\0';
|
|
|
|
return p;
|
|
}
|
|
EXPORT_SYMBOL(strndup_user);
|
|
|
|
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
struct vm_area_struct *prev, struct rb_node *rb_parent)
|
|
{
|
|
struct vm_area_struct *next;
|
|
|
|
vma->vm_prev = prev;
|
|
if (prev) {
|
|
next = prev->vm_next;
|
|
prev->vm_next = vma;
|
|
} else {
|
|
mm->mmap = vma;
|
|
if (rb_parent)
|
|
next = rb_entry(rb_parent,
|
|
struct vm_area_struct, vm_rb);
|
|
else
|
|
next = NULL;
|
|
}
|
|
vma->vm_next = next;
|
|
if (next)
|
|
next->vm_prev = vma;
|
|
}
|
|
|
|
/* Check if the vma is being used as a stack by this task */
|
|
static int vm_is_stack_for_task(struct task_struct *t,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
|
|
}
|
|
|
|
/*
|
|
* Check if the vma is being used as a stack.
|
|
* If is_group is non-zero, check in the entire thread group or else
|
|
* just check in the current task. Returns the pid of the task that
|
|
* the vma is stack for.
|
|
*/
|
|
pid_t vm_is_stack(struct task_struct *task,
|
|
struct vm_area_struct *vma, int in_group)
|
|
{
|
|
pid_t ret = 0;
|
|
|
|
if (vm_is_stack_for_task(task, vma))
|
|
return task->pid;
|
|
|
|
if (in_group) {
|
|
struct task_struct *t;
|
|
rcu_read_lock();
|
|
if (!pid_alive(task))
|
|
goto done;
|
|
|
|
t = task;
|
|
do {
|
|
if (vm_is_stack_for_task(t, vma)) {
|
|
ret = t->pid;
|
|
goto done;
|
|
}
|
|
} while_each_thread(task, t);
|
|
done:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
|
|
void arch_pick_mmap_layout(struct mm_struct *mm)
|
|
{
|
|
mm->mmap_base = TASK_UNMAPPED_BASE;
|
|
mm->get_unmapped_area = arch_get_unmapped_area;
|
|
mm->unmap_area = arch_unmap_area;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Like get_user_pages_fast() except its IRQ-safe in that it won't fall
|
|
* back to the regular GUP.
|
|
* If the architecture not support this function, simply return with no
|
|
* page pinned
|
|
*/
|
|
int __attribute__((weak)) __get_user_pages_fast(unsigned long start,
|
|
int nr_pages, int write, struct page **pages)
|
|
{
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__get_user_pages_fast);
|
|
|
|
/**
|
|
* get_user_pages_fast() - pin user pages in memory
|
|
* @start: starting user address
|
|
* @nr_pages: number of pages from start to pin
|
|
* @write: whether pages will be written to
|
|
* @pages: array that receives pointers to the pages pinned.
|
|
* Should be at least nr_pages long.
|
|
*
|
|
* Returns number of pages pinned. This may be fewer than the number
|
|
* requested. If nr_pages is 0 or negative, returns 0. If no pages
|
|
* were pinned, returns -errno.
|
|
*
|
|
* get_user_pages_fast provides equivalent functionality to get_user_pages,
|
|
* operating on current and current->mm, with force=0 and vma=NULL. However
|
|
* unlike get_user_pages, it must be called without mmap_sem held.
|
|
*
|
|
* get_user_pages_fast may take mmap_sem and page table locks, so no
|
|
* assumptions can be made about lack of locking. get_user_pages_fast is to be
|
|
* implemented in a way that is advantageous (vs get_user_pages()) when the
|
|
* user memory area is already faulted in and present in ptes. However if the
|
|
* pages have to be faulted in, it may turn out to be slightly slower so
|
|
* callers need to carefully consider what to use. On many architectures,
|
|
* get_user_pages_fast simply falls back to get_user_pages.
|
|
*/
|
|
int __attribute__((weak)) get_user_pages_fast(unsigned long start,
|
|
int nr_pages, int write, struct page **pages)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
int ret;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
ret = get_user_pages(current, mm, start, nr_pages,
|
|
write, 0, pages, NULL);
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_user_pages_fast);
|
|
|
|
/* Tracepoints definitions. */
|
|
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
|
|
EXPORT_TRACEPOINT_SYMBOL(kfree);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
|