Revision 9e9db45649eb5d3ee5622fdad741914ecf1016a0 authored by Boaz Harrosh on 05 August 2011, 22:06:04 UTC, committed by Boaz Harrosh on 07 August 2011, 02:35:32 UTC
Exofs raid engine was saving on memory space by having a single layout-info,
single pid, and a single device-table, global to the filesystem. Then passing
a credential and object_id info at the io_state level, private for each
inode. It would also devise this contraption of rotating the device table
view for each inode->ino to spread out the device usage.

This is not compatible with the pnfs-objects standard, demanding that
each inode can have it's own layout-info, device-table, and each object
component it's own pid, oid and creds.

So: Bring exofs raid engine to be usable for generic pnfs-objects use by:

* Define an exofs_comp structure that holds obj_id and credential info.

* Break up exofs_layout struct to an exofs_components structure that holds a
  possible array of exofs_comp and the array of devices + the size of the
  arrays.

* Add a "comps" parameter to get_io_state() that specifies the ids creds
  and device array to use for each IO.

  This enables to keep the layout global, but the device-table view, creds
  and IDs at the inode level. It only adds two 64bit to each inode, since
  some of these members already existed in another form.

* ios raid engine now access layout-info and comps-info through the passed
  pointers. Everything is pre-prepared by caller for generic access of
  these structures and arrays.

At the exofs Level:

* Super block holds an exofs_components struct that holds the device
  array, previously in layout. The devices there are in device-table
  order. The device-array is twice bigger and repeats the device-table
  twice so now each inode's device array can point to a random device
  and have a round-robin view of the table, making it compatible to
  previous exofs versions.

* Each inode has an exofs_components struct that is initialized at
  load time, with it's own view of the device table IDs and creds.
  When doing IO this gets passed to the io_state together with the
  layout.

While preforming this change. Bugs where found where credentials with the
wrong IDs where used to access the different SB objects (super.c). As well
as some dead code. It was never noticed because the target we use does not
check the credentials.

Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
1 parent 85e44df
Raw File
util.c
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/module.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;
}

#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);
back to top