litmus-rt.git - The LITMUS^RT kernel.

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

diff options

author	Richard Kennedy <richard@rsk.demon.co.uk>	2010-02-26 08:00:43 -0500
committer	Jens Axboe <jens.axboe@oracle.com>	2010-02-26 08:00:43 -0500
commit	58c24a61614f5da290068e47fc5ec65370eb61dd (patch)
tree	ae8f51cef37239a4ebe12379deca7042680161c1 /include/linux/spi/ad7879.h
parent	024f9066165ffe9c8284431c78adcbcddd309831 (diff)

block: remove padding from io_context on 64bit builds

On 64 bit builds when CONFIG_BLK_CGROUP=n (the default) this removes 8 bytes of padding from structure io_context and drops its size from 72 to 64 bytes, so needing one fewer cachelines and allowing more objects per slab in it's kmem_cache. Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk> ---- patch against 2.6.33 compiled & test on x86_64 AMDX2 regards Richard Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

Diffstat (limited to 'include/linux/spi/ad7879.h')

0 files changed, 0 insertions, 0 deletions

400 committer Linus Torvalds <torvalds@woody.linux-foundation.org> 2007-10-17 11:42:54 -0400 add-vmcore: cleanup the coding style according to Andrew's comments' href='/cgit/cgit.cgi/litmus-rt-ext-res.git/commit/kernel/kexec.c?id=d768281e97a403815467102bc4b677f6c425a42b'>d768281e97a4

22
23

24
25

26
27

36
37
38

47
48

64
65

117
118
119

122
123

124
125

158
159

195
196

198
199

222
223

232
233

235
236

255
256

258
259

260
261
262

264
265

266
267

317
318

320
321

330
331

333
334

335
336

338
339
340

341
342
343

344
345
346

354
355

359
360
361

363
364

403
404

441
442
443

444
445

467
468

469
470

531
532

533
534

535
536

553
554
555

561
562
563

564
565

571
572
573

574
575

607
608
609

652
653

665
666

677
678
679

682
683

729
730

741
742

762
763

787
788

802
803

804
805
806

810
811
812

813
814
815

818
819

822
823
824

826
827
828

859
860
861

879
880

895
896

897
898

930
931

932
933

935
936

937
938

980
981

984
985
986

993
994

1000
1001

1005
1006

1012
1013

1022
1023
1024

1037
1038

1039
1040
1041

1096
1097

1099
1100

1109
1110

1111
1112
1113

1114
1115

1133
1134
1135

1136
1137
1138

1145
1146

1160
1161

1218
1219

1220
1221
1222

1445
1446

1448
1449

1465
1466
1467

1479
1480

1515
1516
1517

1518
1519

1520
1521
1522

1523
1524

1526
1527
1528

1560
1561

1563
1564

1570
1571

1572
1573

1574
1575

1576
1577

1591
1592

1593
1594

1607
1608

1613
1614
1615

1617
1618
1619

1621
1622

1630
1631
1632

1656
1657

1659
1660

1703
1704

1706
1707

/*
 * kexec.c - kexec system call
 * Copyright (C) 2002-2004 Eric Biederman  <ebiederm@xmission.com>
 *
 * This source code is licensed under the GNU General Public License,
 * Version 2.  See the file COPYING for more details.
 */

#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/kexec.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <linux/reboot.h>
#include <linux/ioport.h>
#include <linux/hardirq.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/utsname.h>
#include <linux/numa.h>
#include <linux/suspend.h>
#include <linux/device.h>
#include <linux/freezer.h>
#include <linux/pm.h>
#include <linux/cpu.h>
#include <linux/console.h>
#include <linux/vmalloc.h>
#include <linux/swap.h>
#include <linux/syscore_ops.h>

#include <asm/page.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/sections.h>

/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t __percpu *crash_notes;

/* vmcoreinfo stuff */
static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
size_t vmcoreinfo_size;
size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);

/* Location of the reserved area for the crash kernel */
struct resource crashk_res = {
	.name  = "Crash kernel",
	.start = 0,
	.end   = 0,
	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
struct resource crashk_low_res = {
	.name  = "Crash kernel",
	.start = 0,
	.end   = 0,
	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};

int kexec_should_crash(struct task_struct *p)
{
	if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
		return 1;
	return 0;
}

/*
 * When kexec transitions to the new kernel there is a one-to-one
 * mapping between physical and virtual addresses.  On processors
 * where you can disable the MMU this is trivial, and easy.  For
 * others it is still a simple predictable page table to setup.
 *
 * In that environment kexec copies the new kernel to its final
 * resting place.  This means I can only support memory whose
 * physical address can fit in an unsigned long.  In particular
 * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled.
 * If the assembly stub has more restrictive requirements
 * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be
 * defined more restrictively in <asm/kexec.h>.
 *
 * The code for the transition from the current kernel to the
 * the new kernel is placed in the control_code_buffer, whose size
 * is given by KEXEC_CONTROL_PAGE_SIZE.  In the best case only a single
 * page of memory is necessary, but some architectures require more.
 * Because this memory must be identity mapped in the transition from
 * virtual to physical addresses it must live in the range
 * 0 - TASK_SIZE, as only the user space mappings are arbitrarily
 * modifiable.
 *
 * The assembly stub in the control code buffer is passed a linked list
 * of descriptor pages detailing the source pages of the new kernel,
 * and the destination addresses of those source pages.  As this data
 * structure is not used in the context of the current OS, it must
 * be self-contained.
 *
 * The code has been made to work with highmem pages and will use a
 * destination page in its final resting place (if it happens
 * to allocate it).  The end product of this is that most of the
 * physical address space, and most of RAM can be used.
 *
 * Future directions include:
 *  - allocating a page table with the control code buffer identity
 *    mapped, to simplify machine_kexec and make kexec_on_panic more
 *    reliable.
 */

/*
 * KIMAGE_NO_DEST is an impossible destination address..., for
 * allocating pages whose destination address we do not care about.
 */
#define KIMAGE_NO_DEST (-1UL)

static int kimage_is_destination_range(struct kimage *image,
				       unsigned long start, unsigned long end);
static struct page *kimage_alloc_page(struct kimage *image,
				       gfp_t gfp_mask,
				       unsigned long dest);

static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
	                    unsigned long nr_segments,
                            struct kexec_segment __user *segments)
{
	size_t segment_bytes;
	struct kimage *image;
	unsigned long i;
	int result;

	/* Allocate a controlling structure */
	result = -ENOMEM;
	image = kzalloc(sizeof(*image), GFP_KERNEL);
	if (!image)
		goto out;

	image->head = 0;
	image->entry = &image->head;
	image->last_entry = &image->head;
	image->control_page = ~0; /* By default this does not apply */
	image->start = entry;
	image->type = KEXEC_TYPE_DEFAULT;

	/* Initialize the list of control pages */
	INIT_LIST_HEAD(&image->control_pages);

	/* Initialize the list of destination pages */
	INIT_LIST_HEAD(&image->dest_pages);

	/* Initialize the list of unusable pages */
	INIT_LIST_HEAD(&image->unuseable_pages);

	/* Read in the segments */
	image->nr_segments = nr_segments;
	segment_bytes = nr_segments * sizeof(*segments);
	result = copy_from_user(image->segment, segments, segment_bytes);
	if (result) {
		result = -EFAULT;
		goto out;
	}

	/*
	 * Verify we have good destination addresses.  The caller is
	 * responsible for making certain we don't attempt to load
	 * the new image into invalid or reserved areas of RAM.  This
	 * just verifies it is an address we can use.
	 *
	 * Since the kernel does everything in page size chunks ensure
	 * the destination addresses are page aligned.  Too many
	 * special cases crop of when we don't do this.  The most
	 * insidious is getting overlapping destination addresses
	 * simply because addresses are changed to page size
	 * granularity.
	 */
	result = -EADDRNOTAVAIL;
	for (i = 0; i < nr_segments; i++) {
		unsigned long mstart, mend;

		mstart = image->segment[i].mem;
		mend   = mstart + image->segment[i].memsz;
		if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
			goto out;
		if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
			goto out;
	}

	/* Verify our destination addresses do not overlap.
	 * If we alloed overlapping destination addresses
	 * through very weird things can happen with no
	 * easy explanation as one segment stops on another.
	 */
	result = -EINVAL;
	for (i = 0; i < nr_segments; i++) {
		unsigned long mstart, mend;
		unsigned long j;

		mstart = image->segment[i].mem;
		mend   = mstart + image->segment[i].memsz;
		for (j = 0; j < i; j++) {
			unsigned long pstart, pend;
			pstart = image->segment[j].mem;
			pend   = pstart + image->segment[j].memsz;
			/* Do the segments overlap ? */
			if ((mend > pstart) && (mstart < pend))
				goto out;
		}
	}

	/* Ensure our buffer sizes are strictly less than
	 * our memory sizes.  This should always be the case,
	 * and it is easier to check up front than to be surprised
	 * later on.
	 */
	result = -EINVAL;
	for (i = 0; i < nr_segments; i++) {
		if (image->segment[i].bufsz > image->segment[i].memsz)
			goto out;
	}

	result = 0;
out:
	if (result == 0)
		*rimage = image;
	else
		kfree(image);

	return result;

}

static void kimage_free_page_list(struct list_head *list);

static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
				unsigned long nr_segments,
				struct kexec_segment __user *segments)
{
	int result;
	struct kimage *image;

	/* Allocate and initialize a controlling structure */
	image = NULL;
	result = do_kimage_alloc(&image, entry, nr_segments, segments);
	if (result)
		goto out;

	/*
	 * Find a location for the control code buffer, and add it
	 * the vector of segments so that it's pages will also be
	 * counted as destination pages.
	 */
	result = -ENOMEM;
	image->control_code_page = kimage_alloc_control_pages(image,
					   get_order(KEXEC_CONTROL_PAGE_SIZE));
	if (!image->control_code_page) {
		printk(KERN_ERR "Could not allocate control_code_buffer\n");
		goto out_free;
	}

	image->swap_page = kimage_alloc_control_pages(image, 0);
	if (!image->swap_page) {
		printk(KERN_ERR "Could not allocate swap buffer\n");
		goto out_free;
	}

	*rimage = image;
	return 0;

out_free:
	kimage_free_page_list(&image->control_pages);
	kfree(image);
out:
	return result;
}

static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
				unsigned long nr_segments,
				struct kexec_segment __user *segments)
{
	int result;
	struct kimage *image;
	unsigned long i;

	image = NULL;
	/* Verify we have a valid entry point */
	if ((entry < crashk_res.start) || (entry > crashk_res.end)) {
		result = -EADDRNOTAVAIL;
		goto out;
	}

	/* Allocate and initialize a controlling structure */
	result = do_kimage_alloc(&image, entry, nr_segments, segments);
	if (result)
		goto out;

	/* Enable the special crash kernel control page
	 * allocation policy.
	 */
	image->control_page = crashk_res.start;
	image->type = KEXEC_TYPE_CRASH;

	/*
	 * Verify we have good destination addresses.  Normally
	 * the caller is responsible for making certain we don't
	 * attempt to load the new image into invalid or reserved
	 * areas of RAM.  But crash kernels are preloaded into a
	 * reserved area of ram.  We must ensure the addresses
	 * are in the reserved area otherwise preloading the
	 * kernel could corrupt things.
	 */
	result = -EADDRNOTAVAIL;
	for (i = 0; i < nr_segments; i++) {
		unsigned long mstart, mend;

		mstart = image->segment[i].mem;
		mend = mstart + image->segment[i].memsz - 1;
		/* Ensure we are within the crash kernel limits */
		if ((mstart < crashk_res.start) || (mend > crashk_res.end))
			goto out_free;
	}

	/*
	 * Find a location for the control code buffer, and add
	 * the vector of segments so that it's pages will also be
	 * counted as destination pages.
	 */
	result = -ENOMEM;
	image->control_code_page = kimage_alloc_control_pages(image,
					   get_order(KEXEC_CONTROL_PAGE_SIZE));
	if (!image->control_code_page) {
		printk(KERN_ERR "Could not allocate control_code_buffer\n");
		goto out_free;
	}

	*rimage = image;
	return 0;

out_free:
	kfree(image);
out:
	return result;
}

static int kimage_is_destination_range(struct kimage *image,
					unsigned long start,
					unsigned long end)
{
	unsigned long i;

	for (i = 0; i < image->nr_segments; i++) {
		unsigned long mstart, mend;

		mstart = image->segment[i].mem;
		mend = mstart + image->segment[i].memsz;
		if ((end > mstart) && (start < mend))
			return 1;
	}

	return 0;
}

static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
{
	struct page *pages;

	pages = alloc_pages(gfp_mask, order);
	if (pages) {
		unsigned int count, i;
		pages->mapping = NULL;
		set_page_private(pages, order);
		count = 1 << order;
		for (i = 0; i < count; i++)
			SetPageReserved(pages + i);
	}

	return pages;
}

static void kimage_free_pages(struct page *page)
{
	unsigned int order, count, i;

	order = page_private(page);
	count = 1 << order;
	for (i = 0; i < count; i++)
		ClearPageReserved(page + i);
	__free_pages(page, order);
}

static void kimage_free_page_list(struct list_head *list)
{
	struct list_head *pos, *next;

	list_for_each_safe(pos, next, list) {
		struct page *page;

		page = list_entry(pos, struct page, lru);
		list_del(&page->lru);
		kimage_free_pages(page);
	}
}

static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
							unsigned int order)
{
	/* Control pages are special, they are the intermediaries
	 * that are needed while we copy the rest of the pages
	 * to their final resting place.  As such they must
	 * not conflict with either the destination addresses
	 * or memory the kernel is already using.
	 *
	 * The only case where we really need more than one of
	 * these are for architectures where we cannot disable
	 * the MMU and must instead generate an identity mapped
	 * page table for all of the memory.
	 *
	 * At worst this runs in O(N) of the image size.
	 */
	struct list_head extra_pages;
	struct page *pages;
	unsigned int count;

	count = 1 << order;
	INIT_LIST_HEAD(&extra_pages);

	/* Loop while I can allocate a page and the page allocated
	 * is a destination page.
	 */
	do {
		unsigned long pfn, epfn, addr, eaddr;

		pages = kimage_alloc_pages(GFP_KERNEL, order);
		if (!pages)
			break;
		pfn   = page_to_pfn(pages);
		epfn  = pfn + count;
		addr  = pfn << PAGE_SHIFT;
		eaddr = epfn << PAGE_SHIFT;
		if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
			      kimage_is_destination_range(image, addr, eaddr)) {
			list_add(&pages->lru, &extra_pages);
			pages = NULL;
		}
	} while (!pages);

	if (pages) {
		/* Remember the allocated page... */
		list_add(&pages->lru, &image->control_pages);

		/* Because the page is already in it's destination
		 * location we will never allocate another page at
		 * that address.  Therefore kimage_alloc_pages
		 * will not return it (again) and we don't need
		 * to give it an entry in image->segment[].
		 */
	}
	/* Deal with the destination pages I have inadvertently allocated.
	 *
	 * Ideally I would convert multi-page allocations into single
	 * page allocations, and add everything to image->dest_pages.
	 *
	 * For now it is simpler to just free the pages.
	 */
	kimage_free_page_list(&extra_pages);

	return pages;
}

static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
						      unsigned int order)
{
	/* Control pages are special, they are the intermediaries
	 * that are needed while we copy the rest of the pages
	 * to their final resting place.  As such they must
	 * not conflict with either the destination addresses
	 * or memory the kernel is already using.
	 *
	 * Control pages are also the only pags we must allocate
	 * when loading a crash kernel.  All of the other pages
	 * are specified by the segments and we just memcpy
	 * into them directly.
	 *
	 * The only case where we really need more than one of
	 * these are for architectures where we cannot disable
	 * the MMU and must instead generate an identity mapped
	 * page table for all of the memory.
	 *
	 * Given the low demand this implements a very simple
	 * allocator that finds the first hole of the appropriate
	 * size in the reserved memory region, and allocates all
	 * of the memory up to and including the hole.
	 */
	unsigned long hole_start, hole_end, size;
	struct page *pages;

	pages = NULL;
	size = (1 << order) << PAGE_SHIFT;
	hole_start = (image->control_page + (size - 1)) & ~(size - 1);
	hole_end   = hole_start + size - 1;
	while (hole_end <= crashk_res.end) {
		unsigned long i;

		if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT)
			break;
		/* See if I overlap any of the segments */
		for (i = 0; i < image->nr_segments; i++) {
			unsigned long mstart, mend;

			mstart = image->segment[i].mem;
			mend   = mstart + image->segment[i].memsz - 1;
			if ((hole_end >= mstart) && (hole_start <= mend)) {
				/* Advance the hole to the end of the segment */
				hole_start = (mend + (size - 1)) & ~(size - 1);
				hole_end   = hole_start + size - 1;
				break;
			}
		}
		/* If I don't overlap any segments I have found my hole! */
		if (i == image->nr_segments) {
			pages = pfn_to_page(hole_start >> PAGE_SHIFT);
			break;
		}
	}
	if (pages)
		image->control_page = hole_end;

	return pages;
}


struct page *kimage_alloc_control_pages(struct kimage *image,
					 unsigned int order)
{
	struct page *pages = NULL;

	switch (image->type) {
	case KEXEC_TYPE_DEFAULT:
		pages = kimage_alloc_normal_control_pages(image, order);
		break;
	case KEXEC_TYPE_CRASH:
		pages = kimage_alloc_crash_control_pages(image, order);
		break;
	}

	return pages;
}

static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
{
	if (*image->entry != 0)
		image->entry++;

	if (image->entry == image->last_entry) {
		kimage_entry_t *ind_page;
		struct page *page;

		page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST);
		if (!page)
			return -ENOMEM;

		ind_page = page_address(page);
		*image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
		image->entry = ind_page;
		image->last_entry = ind_page +
				      ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
	}
	*image->entry = entry;
	image->entry++;
	*image->entry = 0;

	return 0;
}

static int kimage_set_destination(struct kimage *image,
				   unsigned long destination)
{
	int result;

	destination &= PAGE_MASK;
	result = kimage_add_entry(image, destination | IND_DESTINATION);
	if (result == 0)
		image->destination = destination;

	return result;
}


static int kimage_add_page(struct kimage *image, unsigned long page)
{
	int result;

	page &= PAGE_MASK;
	result = kimage_add_entry(image, page | IND_SOURCE);
	if (result == 0)
		image->destination += PAGE_SIZE;

	return result;
}


static void kimage_free_extra_pages(struct kimage *image)
{
	/* Walk through and free any extra destination pages I may have */
	kimage_free_page_list(&image->dest_pages);

	/* Walk through and free any unusable pages I have cached */
	kimage_free_page_list(&image->unuseable_pages);

}
static void kimage_terminate(struct kimage *image)
{
	if (*image->entry != 0)
		image->entry++;

	*image->entry = IND_DONE;
}

#define for_each_kimage_entry(image, ptr, entry) \
	for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
		ptr = (entry & IND_INDIRECTION)? \
			phys_to_virt((entry & PAGE_MASK)): ptr +1)

static void kimage_free_entry(kimage_entry_t entry)
{
	struct page *page;

	page = pfn_to_page(entry >> PAGE_SHIFT);
	kimage_free_pages(page);
}

static void kimage_free(struct kimage *image)
{
	kimage_entry_t *ptr, entry;
	kimage_entry_t ind = 0;

	if (!image)
		return;

	kimage_free_extra_pages(image);
	for_each_kimage_entry(image, ptr, entry) {
		if (entry & IND_INDIRECTION) {
			/* Free the previous indirection page */
			if (ind & IND_INDIRECTION)
				kimage_free_entry(ind);
			/* Save this indirection page until we are
			 * done with it.
			 */
			ind = entry;
		}
		else if (entry & IND_SOURCE)
			kimage_free_entry(entry);
	}
	/* Free the final indirection page */
	if (ind & IND_INDIRECTION)
		kimage_free_entry(ind);

	/* Handle any machine specific cleanup */
	machine_kexec_cleanup(image);

	/* Free the kexec control pages... */
	kimage_free_page_list(&image->control_pages);
	kfree(image);
}

static kimage_entry_t *kimage_dst_used(struct kimage *image,
					unsigned long page)
{
	kimage_entry_t *ptr, entry;
	unsigned long destination = 0;

	for_each_kimage_entry(image, ptr, entry) {
		if (entry & IND_DESTINATION)
			destination = entry & PAGE_MASK;
		else if (entry & IND_SOURCE) {
			if (page == destination)
				return ptr;
			destination += PAGE_SIZE;
		}
	}

	return NULL;
}

static struct page *kimage_alloc_page(struct kimage *image,
					gfp_t gfp_mask,
					unsigned long destination)
{
	/*
	 * Here we implement safeguards to ensure that a source page
	 * is not copied to its destination page before the data on
	 * the destination page is no longer useful.
	 *
	 * To do this we maintain the invariant that a source page is
	 * either its own destination page, or it is not a
	 * destination page at all.
	 *
	 * That is slightly stronger than required, but the proof
	 * that no problems will not occur is trivial, and the
	 * implementation is simply to verify.
	 *
	 * When allocating all pages normally this algorithm will run
	 * in O(N) time, but in the worst case it will run in O(N^2)
	 * time.   If the runtime is a problem the data structures can
	 * be fixed.
	 */
	struct page *page;
	unsigned long addr;

	/*
	 * Walk through the list of destination pages, and see if I
	 * have a match.
	 */
	list_for_each_entry(page, &image->dest_pages, lru) {
		addr = page_to_pfn(page) << PAGE_SHIFT;
		if (addr == destination) {
			list_del(&page->lru);
			return page;
		}
	}
	page = NULL;
	while (1) {
		kimage_entry_t *old;

		/* Allocate a page, if we run out of memory give up */
		page = kimage_alloc_pages(gfp_mask, 0);
		if (!page)
			return NULL;
		/* If the page cannot be used file it away */


context:
space:
mode: