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
kmemcheck.c
#include <linux/gfp.h>
#include <linux/mm_types.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/kmemcheck.h>
void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
{
struct page *shadow;
int pages;
int i;
pages = 1 << order;
/*
* With kmemcheck enabled, we need to allocate a memory area for the
* shadow bits as well.
*/
shadow = alloc_pages_node(node, flags | __GFP_NOTRACK, order);
if (!shadow) {
if (printk_ratelimit())
printk(KERN_ERR "kmemcheck: failed to allocate "
"shadow bitmap\n");
return;
}
for(i = 0; i < pages; ++i)
page[i].shadow = page_address(&shadow[i]);
/*
* Mark it as non-present for the MMU so that our accesses to
* this memory will trigger a page fault and let us analyze
* the memory accesses.
*/
kmemcheck_hide_pages(page, pages);
}
void kmemcheck_free_shadow(struct page *page, int order)
{
struct page *shadow;
int pages;
int i;
if (!kmemcheck_page_is_tracked(page))
return;
pages = 1 << order;
kmemcheck_show_pages(page, pages);
shadow = virt_to_page(page[0].shadow);
for(i = 0; i < pages; ++i)
page[i].shadow = NULL;
__free_pages(shadow, order);
}
void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
size_t size)
{
/*
* Has already been memset(), which initializes the shadow for us
* as well.
*/
if (gfpflags & __GFP_ZERO)
return;
/* No need to initialize the shadow of a non-tracked slab. */
if (s->flags & SLAB_NOTRACK)
return;
if (!kmemcheck_enabled || gfpflags & __GFP_NOTRACK) {
/*
* Allow notracked objects to be allocated from
* tracked caches. Note however that these objects
* will still get page faults on access, they just
* won't ever be flagged as uninitialized. If page
* faults are not acceptable, the slab cache itself
* should be marked NOTRACK.
*/
kmemcheck_mark_initialized(object, size);
} else if (!s->ctor) {
/*
* New objects should be marked uninitialized before
* they're returned to the called.
*/
kmemcheck_mark_uninitialized(object, size);
}
}
void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size)
{
/* TODO: RCU freeing is unsupported for now; hide false positives. */
if (!s->ctor && !(s->flags & SLAB_DESTROY_BY_RCU))
kmemcheck_mark_freed(object, size);
}
void kmemcheck_pagealloc_alloc(struct page *page, unsigned int order,
gfp_t gfpflags)
{
int pages;
if (gfpflags & (__GFP_HIGHMEM | __GFP_NOTRACK))
return;
pages = 1 << order;
/*
* NOTE: We choose to track GFP_ZERO pages too; in fact, they
* can become uninitialized by copying uninitialized memory
* into them.
*/
/* XXX: Can use zone->node for node? */
kmemcheck_alloc_shadow(page, order, gfpflags, -1);
if (gfpflags & __GFP_ZERO)
kmemcheck_mark_initialized_pages(page, pages);
else
kmemcheck_mark_uninitialized_pages(page, pages);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...