• T
    include cleanup: Update gfp.h and slab.h includes to prepare for breaking... · 5a0e3ad6
    Tejun Heo 提交于
    include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
    
    percpu.h is included by sched.h and module.h and thus ends up being
    included when building most .c files.  percpu.h includes slab.h which
    in turn includes gfp.h making everything defined by the two files
    universally available and complicating inclusion dependencies.
    
    percpu.h -> slab.h dependency is about to be removed.  Prepare for
    this change by updating users of gfp and slab facilities include those
    headers directly instead of assuming availability.  As this conversion
    needs to touch large number of source files, the following script is
    used as the basis of conversion.
    
      http://userweb.kernel.org/~tj/misc/slabh-sweep.py
    
    The script does the followings.
    
    * Scan files for gfp and slab usages and update includes such that
      only the necessary includes are there.  ie. if only gfp is used,
      gfp.h, if slab is used, slab.h.
    
    * When the script inserts a new include, it looks at the include
      blocks and try to put the new include such that its order conforms
      to its surrounding.  It's put in the include block which contains
      core kernel includes, in the same order that the rest are ordered -
      alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
      doesn't seem to be any matching order.
    
    * If the script can't find a place to put a new include (mostly
      because the file doesn't have fitting include block), it prints out
      an error message indicating which .h file needs to be added to the
      file.
    
    The conversion was done in the following steps.
    
    1. The initial automatic conversion of all .c files updated slightly
       over 4000 files, deleting around 700 includes and adding ~480 gfp.h
       and ~3000 slab.h inclusions.  The script emitted errors for ~400
       files.
    
    2. Each error was manually checked.  Some didn't need the inclusion,
       some needed manual addition while adding it to implementation .h or
       embedding .c file was more appropriate for others.  This step added
       inclusions to around 150 files.
    
    3. The script was run again and the output was compared to the edits
       from #2 to make sure no file was left behind.
    
    4. Several build tests were done and a couple of problems were fixed.
       e.g. lib/decompress_*.c used malloc/free() wrappers around slab
       APIs requiring slab.h to be added manually.
    
    5. The script was run on all .h files but without automatically
       editing them as sprinkling gfp.h and slab.h inclusions around .h
       files could easily lead to inclusion dependency hell.  Most gfp.h
       inclusion directives were ignored as stuff from gfp.h was usually
       wildly available and often used in preprocessor macros.  Each
       slab.h inclusion directive was examined and added manually as
       necessary.
    
    6. percpu.h was updated not to include slab.h.
    
    7. Build test were done on the following configurations and failures
       were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
       distributed build env didn't work with gcov compiles) and a few
       more options had to be turned off depending on archs to make things
       build (like ipr on powerpc/64 which failed due to missing writeq).
    
       * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
       * powerpc and powerpc64 SMP allmodconfig
       * sparc and sparc64 SMP allmodconfig
       * ia64 SMP allmodconfig
       * s390 SMP allmodconfig
       * alpha SMP allmodconfig
       * um on x86_64 SMP allmodconfig
    
    8. percpu.h modifications were reverted so that it could be applied as
       a separate patch and serve as bisection point.
    
    Given the fact that I had only a couple of failures from tests on step
    6, I'm fairly confident about the coverage of this conversion patch.
    If there is a breakage, it's likely to be something in one of the arch
    headers which should be easily discoverable easily on most builds of
    the specific arch.
    Signed-off-by: NTejun Heo <tj@kernel.org>
    Guess-its-ok-by: NChristoph Lameter <cl@linux-foundation.org>
    Cc: Ingo Molnar <mingo@redhat.com>
    Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
    5a0e3ad6
bounce.c 6.5 KB
/* bounce buffer handling for block devices
 *
 * - Split from highmem.c
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/pagemap.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
#include <asm/tlbflush.h>

#include <trace/events/block.h>

#define POOL_SIZE	64
#define ISA_POOL_SIZE	16

static mempool_t *page_pool, *isa_page_pool;

#ifdef CONFIG_HIGHMEM
static __init int init_emergency_pool(void)
{
	struct sysinfo i;
	si_meminfo(&i);
	si_swapinfo(&i);

	if (!i.totalhigh)
		return 0;

	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
	BUG_ON(!page_pool);
	printk("highmem bounce pool size: %d pages\n", POOL_SIZE);

	return 0;
}

__initcall(init_emergency_pool);

/*
 * highmem version, map in to vec
 */
static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
{
	unsigned long flags;
	unsigned char *vto;

	local_irq_save(flags);
	vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
	kunmap_atomic(vto, KM_BOUNCE_READ);
	local_irq_restore(flags);
}

#else /* CONFIG_HIGHMEM */

#define bounce_copy_vec(to, vfrom)	\
	memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)

#endif /* CONFIG_HIGHMEM */

/*
 * allocate pages in the DMA region for the ISA pool
 */
static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
{
	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
}

/*
 * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
 * as the max address, so check if the pool has already been created.
 */
int init_emergency_isa_pool(void)
{
	if (isa_page_pool)
		return 0;

	isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
				       mempool_free_pages, (void *) 0);
	BUG_ON(!isa_page_pool);

	printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
	return 0;
}

/*
 * Simple bounce buffer support for highmem pages. Depending on the
 * queue gfp mask set, *to may or may not be a highmem page. kmap it
 * always, it will do the Right Thing
 */
static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
{
	unsigned char *vfrom;
	struct bio_vec *tovec, *fromvec;
	int i;

	__bio_for_each_segment(tovec, to, i, 0) {
		fromvec = from->bi_io_vec + i;

		/*
		 * not bounced
		 */
		if (tovec->bv_page == fromvec->bv_page)
			continue;

		/*
		 * fromvec->bv_offset and fromvec->bv_len might have been
		 * modified by the block layer, so use the original copy,
		 * bounce_copy_vec already uses tovec->bv_len
		 */
		vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;

		flush_dcache_page(tovec->bv_page);
		bounce_copy_vec(tovec, vfrom);
	}
}

static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
{
	struct bio *bio_orig = bio->bi_private;
	struct bio_vec *bvec, *org_vec;
	int i;

	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);

	/*
	 * free up bounce indirect pages used
	 */
	__bio_for_each_segment(bvec, bio, i, 0) {
		org_vec = bio_orig->bi_io_vec + i;
		if (bvec->bv_page == org_vec->bv_page)
			continue;

		dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
		mempool_free(bvec->bv_page, pool);
	}

	bio_endio(bio_orig, err);
	bio_put(bio);
}

static void bounce_end_io_write(struct bio *bio, int err)
{
	bounce_end_io(bio, page_pool, err);
}

static void bounce_end_io_write_isa(struct bio *bio, int err)
{

	bounce_end_io(bio, isa_page_pool, err);
}

static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
{
	struct bio *bio_orig = bio->bi_private;

	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
		copy_to_high_bio_irq(bio_orig, bio);

	bounce_end_io(bio, pool, err);
}

static void bounce_end_io_read(struct bio *bio, int err)
{
	__bounce_end_io_read(bio, page_pool, err);
}

static void bounce_end_io_read_isa(struct bio *bio, int err)
{
	__bounce_end_io_read(bio, isa_page_pool, err);
}

static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
			       mempool_t *pool)
{
	struct page *page;
	struct bio *bio = NULL;
	int i, rw = bio_data_dir(*bio_orig);
	struct bio_vec *to, *from;

	bio_for_each_segment(from, *bio_orig, i) {
		page = from->bv_page;

		/*
		 * is destination page below bounce pfn?
		 */
		if (page_to_pfn(page) <= queue_bounce_pfn(q))
			continue;

		/*
		 * irk, bounce it
		 */
		if (!bio) {
			unsigned int cnt = (*bio_orig)->bi_vcnt;

			bio = bio_alloc(GFP_NOIO, cnt);
			memset(bio->bi_io_vec, 0, cnt * sizeof(struct bio_vec));
		}
			

		to = bio->bi_io_vec + i;

		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
		to->bv_len = from->bv_len;
		to->bv_offset = from->bv_offset;
		inc_zone_page_state(to->bv_page, NR_BOUNCE);

		if (rw == WRITE) {
			char *vto, *vfrom;

			flush_dcache_page(from->bv_page);
			vto = page_address(to->bv_page) + to->bv_offset;
			vfrom = kmap(from->bv_page) + from->bv_offset;
			memcpy(vto, vfrom, to->bv_len);
			kunmap(from->bv_page);
		}
	}

	/*
	 * no pages bounced
	 */
	if (!bio)
		return;

	trace_block_bio_bounce(q, *bio_orig);

	/*
	 * at least one page was bounced, fill in possible non-highmem
	 * pages
	 */
	__bio_for_each_segment(from, *bio_orig, i, 0) {
		to = bio_iovec_idx(bio, i);
		if (!to->bv_page) {
			to->bv_page = from->bv_page;
			to->bv_len = from->bv_len;
			to->bv_offset = from->bv_offset;
		}
	}

	bio->bi_bdev = (*bio_orig)->bi_bdev;
	bio->bi_flags |= (1 << BIO_BOUNCED);
	bio->bi_sector = (*bio_orig)->bi_sector;
	bio->bi_rw = (*bio_orig)->bi_rw;

	bio->bi_vcnt = (*bio_orig)->bi_vcnt;
	bio->bi_idx = (*bio_orig)->bi_idx;
	bio->bi_size = (*bio_orig)->bi_size;

	if (pool == page_pool) {
		bio->bi_end_io = bounce_end_io_write;
		if (rw == READ)
			bio->bi_end_io = bounce_end_io_read;
	} else {
		bio->bi_end_io = bounce_end_io_write_isa;
		if (rw == READ)
			bio->bi_end_io = bounce_end_io_read_isa;
	}

	bio->bi_private = *bio_orig;
	*bio_orig = bio;
}

void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
{
	mempool_t *pool;

	/*
	 * Data-less bio, nothing to bounce
	 */
	if (!bio_has_data(*bio_orig))
		return;

	/*
	 * for non-isa bounce case, just check if the bounce pfn is equal
	 * to or bigger than the highest pfn in the system -- in that case,
	 * don't waste time iterating over bio segments
	 */
	if (!(q->bounce_gfp & GFP_DMA)) {
		if (queue_bounce_pfn(q) >= blk_max_pfn)
			return;
		pool = page_pool;
	} else {
		BUG_ON(!isa_page_pool);
		pool = isa_page_pool;
	}

	/*
	 * slow path
	 */
	__blk_queue_bounce(q, bio_orig, pool);
}

EXPORT_SYMBOL(blk_queue_bounce);
反馈
建议
客服 返回
顶部