Revision 0ee7c3e25d8c28845fceb4dd1c3cb5f50b9c45a9 authored by Linus Torvalds on 31 August 2021, 18:13:35 UTC, committed by Linus Torvalds on 31 August 2021, 18:13:35 UTC
Pull iomap updates from Darrick Wong:
 "The most notable externally visible change for this cycle is the
  addition of support for reads to inline tail fragments of files, which
  was requested by the erofs developers; and a correction for a kernel
  memory corruption bug if the sysadmin tries to activate a swapfile
  with more pages than the swapfile header suggests.

  We also now report writeback completion errors to the file mapping
  correctly, instead of munging all errors into EIO.

  Internally, the bulk of the changes are Christoph's patchset to reduce
  the indirect function call count by a third to a half by converting
  iomap iteration from a loop pattern to a generator/consumer pattern.
  As an added bonus, fsdax no longer open-codes iomap apply loops.

  Summary:

   - Simplify the bio_end_page usage in the buffered IO code.

   - Support reading inline data at nonzero offsets for erofs.

   - Fix some typos and bad grammar.

   - Convert kmap_atomic usage in the inline data read path.

   - Add some extra inline data input checking.

   - Fix a memory corruption bug stemming from iomap_swapfile_activate
     trying to activate more pages than mm was expecting.

   - Pass errnos through the page writeback code so that writeback
     errors are reported correctly instead of being munged to EIO.

   - Replace iomap_apply with a open-coded iterator loops to reduce the
     number of indirect calls by a third to a half.

   - Refactor the fsdax code to use iomap iterators instead of the
     open-coded iomap_apply code that it had before.

   - Format file range iomap tracepoint data in hexadecimal and
     standardize the names used in the pretty-print string"

* tag 'iomap-5.15-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (41 commits)
  iomap: standardize tracepoint formatting and storage
  mm/swap: consider max pages in iomap_swapfile_add_extent
  iomap: move loop control code to iter.c
  iomap: constify iomap_iter_srcmap
  fsdax: switch the fault handlers to use iomap_iter
  fsdax: factor out a dax_fault_actor() helper
  fsdax: factor out helpers to simplify the dax fault code
  iomap: rework unshare flag
  iomap: pass an iomap_iter to various buffered I/O helpers
  iomap: remove iomap_apply
  fsdax: switch dax_iomap_rw to use iomap_iter
  iomap: switch iomap_swapfile_activate to use iomap_iter
  iomap: switch iomap_seek_data to use iomap_iter
  iomap: switch iomap_seek_hole to use iomap_iter
  iomap: switch iomap_bmap to use iomap_iter
  iomap: switch iomap_fiemap to use iomap_iter
  iomap: switch __iomap_dio_rw to use iomap_iter
  iomap: switch iomap_page_mkwrite to use iomap_iter
  iomap: switch iomap_zero_range to use iomap_iter
  iomap: switch iomap_file_unshare to use iomap_iter
  ...
2 parent s 916d636 + 03b8df8
Raw File
percpu-km.c
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/percpu-km.c - kernel memory based chunk allocation
 *
 * Copyright (C) 2010		SUSE Linux Products GmbH
 * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
 *
 * Chunks are allocated as a contiguous kernel memory using gfp
 * allocation.  This is to be used on nommu architectures.
 *
 * To use percpu-km,
 *
 * - define CONFIG_NEED_PER_CPU_KM from the arch Kconfig.
 *
 * - CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK must not be defined.  It's
 *   not compatible with PER_CPU_KM.  EMBED_FIRST_CHUNK should work
 *   fine.
 *
 * - NUMA is not supported.  When setting up the first chunk,
 *   @cpu_distance_fn should be NULL or report all CPUs to be nearer
 *   than or at LOCAL_DISTANCE.
 *
 * - It's best if the chunk size is power of two multiple of
 *   PAGE_SIZE.  Because each chunk is allocated as a contiguous
 *   kernel memory block using alloc_pages(), memory will be wasted if
 *   chunk size is not aligned.  percpu-km code will whine about it.
 */

#if defined(CONFIG_SMP) && defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
#error "contiguous percpu allocation is incompatible with paged first chunk"
#endif

#include <linux/log2.h>

static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
				      int page_start, int page_end)
{
	/* nothing */
}

static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
			       int page_start, int page_end, gfp_t gfp)
{
	return 0;
}

static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
				  int page_start, int page_end)
{
	/* nada */
}

static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
{
	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
	struct pcpu_chunk *chunk;
	struct page *pages;
	unsigned long flags;
	int i;

	chunk = pcpu_alloc_chunk(gfp);
	if (!chunk)
		return NULL;

	pages = alloc_pages(gfp, order_base_2(nr_pages));
	if (!pages) {
		pcpu_free_chunk(chunk);
		return NULL;
	}

	for (i = 0; i < nr_pages; i++)
		pcpu_set_page_chunk(nth_page(pages, i), chunk);

	chunk->data = pages;
	chunk->base_addr = page_address(pages);

	spin_lock_irqsave(&pcpu_lock, flags);
	pcpu_chunk_populated(chunk, 0, nr_pages);
	spin_unlock_irqrestore(&pcpu_lock, flags);

	pcpu_stats_chunk_alloc();
	trace_percpu_create_chunk(chunk->base_addr);

	return chunk;
}

static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
{
	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;

	if (!chunk)
		return;

	pcpu_stats_chunk_dealloc();
	trace_percpu_destroy_chunk(chunk->base_addr);

	if (chunk->data)
		__free_pages(chunk->data, order_base_2(nr_pages));
	pcpu_free_chunk(chunk);
}

static struct page *pcpu_addr_to_page(void *addr)
{
	return virt_to_page(addr);
}

static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
{
	size_t nr_pages, alloc_pages;

	/* all units must be in a single group */
	if (ai->nr_groups != 1) {
		pr_crit("can't handle more than one group\n");
		return -EINVAL;
	}

	nr_pages = (ai->groups[0].nr_units * ai->unit_size) >> PAGE_SHIFT;
	alloc_pages = roundup_pow_of_two(nr_pages);

	if (alloc_pages > nr_pages)
		pr_warn("wasting %zu pages per chunk\n",
			alloc_pages - nr_pages);

	return 0;
}

static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk)
{
	return false;
}
back to top