percpu: move vmalloc based chunk management into percpu-vm.c

Separate out and move chunk management (creation/desctruction and
[de]population) code into percpu-vm.c which is included by percpu.c
and compiled together.  The interface for chunk management is defined
as follows.

 * pcpu_populate_chunk		- populate the specified range of a chunk
 * pcpu_depopulate_chunk	- depopulate the specified range of a chunk
 * pcpu_create_chunk		- create a new chunk
 * pcpu_destroy_chunk		- destroy a chunk, always preceded by full depop
 * pcpu_addr_to_page		- translate address to physical address
 * pcpu_verify_alloc_info	- check alloc_info is acceptable during init

Other than wrapping vmalloc_to_page() inside pcpu_addr_to_page() and
dummy pcpu_verify_alloc_info() implementation, this patch only moves
code around.  This separation is to allow alternate chunk management
implementation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: Graff Yang <graff.yang@gmail.com>
Cc: Sonic Zhang <sonic.adi@gmail.com>

1 files changed, 24 insertions, 428 deletions

diff --git a/mm/percpu.c b/mm/percpu.c
index b403d7c02c67..15f680430671 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -236,15 +236,6 @@ static unsigned long __maybe_unused pcpu_chunk_addr(struct pcpu_chunk *chunk,
                 (page_idx << PAGE_SHIFT);
 }
 
-static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
-                                    unsigned int cpu, int page_idx)
-{
-        /* must not be used on pre-mapped chunk */
-        WARN_ON(chunk->immutable);
-
-        return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx));
-}
-
 static void __maybe_unused pcpu_next_unpop(struct pcpu_chunk *chunk,
                                            int *rs, int *re, int end)
 {
@@ -641,425 +632,29 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
         kfree(chunk);
 }
 
-/**
- * pcpu_get_pages_and_bitmap - get temp pages array and bitmap
- * @chunk: chunk of interest
- * @bitmapp: output parameter for bitmap
- * @may_alloc: may allocate the array
- *
- * Returns pointer to array of pointers to struct page and bitmap,
- * both of which can be indexed with pcpu_page_idx().  The returned
- * array is cleared to zero and *@bitmapp is copied from
- * @chunk->populated.  Note that there is only one array and bitmap
- * and access exclusion is the caller's responsibility.
- *
- * CONTEXT:
- * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc.
- * Otherwise, don't care.
- *
- * RETURNS:
- * Pointer to temp pages array on success, NULL on failure.
- */
-static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
-                                               unsigned long **bitmapp,
-                                               bool may_alloc)
-{
-        static struct page **pages;
-        static unsigned long *bitmap;
-        size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
-        size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) *
-                             sizeof(unsigned long);
-
-        if (!pages || !bitmap) {
-                if (may_alloc && !pages)
-                        pages = pcpu_mem_alloc(pages_size);
-                if (may_alloc && !bitmap)
-                        bitmap = pcpu_mem_alloc(bitmap_size);
-                if (!pages || !bitmap)
-                        return NULL;
-        }
-
-        memset(pages, 0, pages_size);
-        bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
-
-        *bitmapp = bitmap;
-        return pages;
-}
-
-/**
- * pcpu_free_pages - free pages which were allocated for @chunk
- * @chunk: chunk pages were allocated for
- * @pages: array of pages to be freed, indexed by pcpu_page_idx()
- * @populated: populated bitmap
- * @page_start: page index of the first page to be freed
- * @page_end: page index of the last page to be freed + 1
- *
- * Free pages [@page_start and @page_end) in @pages for all units.
- * The pages were allocated for @chunk.
- */
-static void pcpu_free_pages(struct pcpu_chunk *chunk,
-                            struct page **pages, unsigned long *populated,
-                            int page_start, int page_end)
-{
-        unsigned int cpu;
-        int i;
-
-        for_each_possible_cpu(cpu) {
-                for (i = page_start; i < page_end; i++) {
-                        struct page *page = pages[pcpu_page_idx(cpu, i)];
-
-                        if (page)
-                                __free_page(page);
-                }
-        }
-}
-
-/**
- * pcpu_alloc_pages - allocates pages for @chunk
- * @chunk: target chunk
- * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
- * @populated: populated bitmap
- * @page_start: page index of the first page to be allocated
- * @page_end: page index of the last page to be allocated + 1
- *
- * Allocate pages [@page_start,@page_end) into @pages for all units.
- * The allocation is for @chunk.  Percpu core doesn't care about the
- * content of @pages and will pass it verbatim to pcpu_map_pages().
- */
-static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
-                            struct page **pages, unsigned long *populated,
-                            int page_start, int page_end)
-{
-        const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
-        unsigned int cpu;
-        int i;
-
-        for_each_possible_cpu(cpu) {
-                for (i = page_start; i < page_end; i++) {
-                        struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
-
-                        *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
-                        if (!*pagep) {
-                                pcpu_free_pages(chunk, pages, populated,
-                                                page_start, page_end);
-                                return -ENOMEM;
-                        }
-                }
-        }
-        return 0;
-}
-
-/**
- * pcpu_pre_unmap_flush - flush cache prior to unmapping
- * @chunk: chunk the regions to be flushed belongs to
- * @page_start: page index of the first page to be flushed
- * @page_end: page index of the last page to be flushed + 1
- *
- * Pages in [@page_start,@page_end) of @chunk are about to be
- * unmapped.  Flush cache.  As each flushing trial can be very
- * expensive, issue flush on the whole region at once rather than
- * doing it for each cpu.  This could be an overkill but is more
- * scalable.
- */
-static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
-                                 int page_start, int page_end)
-{
-        flush_cache_vunmap(
-                pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-                pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
-}
-
-static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
-{
-        unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
-}
-
-/**
- * pcpu_unmap_pages - unmap pages out of a pcpu_chunk
- * @chunk: chunk of interest
- * @pages: pages array which can be used to pass information to free
- * @populated: populated bitmap
- * @page_start: page index of the first page to unmap
- * @page_end: page index of the last page to unmap + 1
- *
- * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
- * Corresponding elements in @pages were cleared by the caller and can
- * be used to carry information to pcpu_free_pages() which will be
- * called after all unmaps are finished.  The caller should call
- * proper pre/post flush functions.
- */
-static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
-                             struct page **pages, unsigned long *populated,
-                             int page_start, int page_end)
-{
-        unsigned int cpu;
-        int i;
-
-        for_each_possible_cpu(cpu) {
-                for (i = page_start; i < page_end; i++) {
-                        struct page *page;
-
-                        page = pcpu_chunk_page(chunk, cpu, i);
-                        WARN_ON(!page);
-                        pages[pcpu_page_idx(cpu, i)] = page;
-                }
-                __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
-                                   page_end - page_start);
-        }
-
-        for (i = page_start; i < page_end; i++)
-                __clear_bit(i, populated);
-}
-
-/**
- * pcpu_post_unmap_tlb_flush - flush TLB after unmapping
- * @chunk: pcpu_chunk the regions to be flushed belong to
- * @page_start: page index of the first page to be flushed
- * @page_end: page index of the last page to be flushed + 1
- *
- * Pages [@page_start,@page_end) of @chunk have been unmapped.  Flush
- * TLB for the regions.  This can be skipped if the area is to be
- * returned to vmalloc as vmalloc will handle TLB flushing lazily.
- *
- * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
- * for the whole region.
- */
-static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
-                                      int page_start, int page_end)
-{
-        flush_tlb_kernel_range(
-                pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-                pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
-}
-
-static int __pcpu_map_pages(unsigned long addr, struct page **pages,
-                            int nr_pages)
-{
-        return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT,
-                                        PAGE_KERNEL, pages);
-}
-
-/**
- * pcpu_map_pages - map pages into a pcpu_chunk
- * @chunk: chunk of interest
- * @pages: pages array containing pages to be mapped
- * @populated: populated bitmap
- * @page_start: page index of the first page to map
- * @page_end: page index of the last page to map + 1
- *
- * For each cpu, map pages [@page_start,@page_end) into @chunk.  The
- * caller is responsible for calling pcpu_post_map_flush() after all
- * mappings are complete.
- *
- * This function is responsible for setting corresponding bits in
- * @chunk->populated bitmap and whatever is necessary for reverse
- * lookup (addr -> chunk).
- */
-static int pcpu_map_pages(struct pcpu_chunk *chunk,
-                          struct page **pages, unsigned long *populated,
-                          int page_start, int page_end)
-{
-        unsigned int cpu, tcpu;
-        int i, err;
-
-        for_each_possible_cpu(cpu) {
-                err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),
-                                       &pages[pcpu_page_idx(cpu, page_start)],
-                                       page_end - page_start);
-                if (err < 0)
-                        goto err;
-        }
-
-        /* mapping successful, link chunk and mark populated */
-        for (i = page_start; i < page_end; i++) {
-                for_each_possible_cpu(cpu)
-                        pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
-                                            chunk);
-                __set_bit(i, populated);
-        }
-
-        return 0;
-
-err:
-        for_each_possible_cpu(tcpu) {
-                if (tcpu == cpu)
-                        break;
-                __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
-                                   page_end - page_start);
-        }
-        return err;
-}
-
-/**
- * pcpu_post_map_flush - flush cache after mapping
- * @chunk: pcpu_chunk the regions to be flushed belong to
- * @page_start: page index of the first page to be flushed
- * @page_end: page index of the last page to be flushed + 1
- *
- * Pages [@page_start,@page_end) of @chunk have been mapped.  Flush
- * cache.
- *
- * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
- * for the whole region.
- */
-static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
-                                int page_start, int page_end)
-{
-        flush_cache_vmap(
-                pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-                pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
-}
-
-/**
- * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
- * @chunk: chunk to depopulate
- * @off: offset to the area to depopulate
- * @size: size of the area to depopulate in bytes
- * @flush: whether to flush cache and tlb or not
- *
- * For each cpu, depopulate and unmap pages [@page_start,@page_end)
- * from @chunk.  If @flush is true, vcache is flushed before unmapping
- * and tlb after.
- *
- * CONTEXT:
- * pcpu_alloc_mutex.
- */
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
-{
-        int page_start = PFN_DOWN(off);
-        int page_end = PFN_UP(off + size);
-        struct page **pages;
-        unsigned long *populated;
-        int rs, re;
-
-        /* quick path, check whether it's empty already */
-        rs = page_start;
-        pcpu_next_unpop(chunk, &rs, &re, page_end);
-        if (rs == page_start && re == page_end)
-                return;
-
-        /* immutable chunks can't be depopulated */
-        WARN_ON(chunk->immutable);
-
-        /*
-         * If control reaches here, there must have been at least one
-         * successful population attempt so the temp pages array must
-         * be available now.
-         */
-        pages = pcpu_get_pages_and_bitmap(chunk, &populated, false);
-        BUG_ON(!pages);
-
-        /* unmap and free */
-        pcpu_pre_unmap_flush(chunk, page_start, page_end);
-
-        pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
-                pcpu_unmap_pages(chunk, pages, populated, rs, re);
-
-        /* no need to flush tlb, vmalloc will handle it lazily */
-
-        pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
-                pcpu_free_pages(chunk, pages, populated, rs, re);
-
-        /* commit new bitmap */
-        bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
-}
-
-/**
- * pcpu_populate_chunk - populate and map an area of a pcpu_chunk
- * @chunk: chunk of interest
- * @off: offset to the area to populate
- * @size: size of the area to populate in bytes
- *
- * For each cpu, populate and map pages [@page_start,@page_end) into
- * @chunk.  The area is cleared on return.
- *
- * CONTEXT:
- * pcpu_alloc_mutex, does GFP_KERNEL allocation.
+/*
+ * Chunk management implementation.
+ *
+ * To allow different implementations, chunk alloc/free and
+ * [de]population are implemented in a separate file which is pulled
+ * into this file and compiled together.  The following functions
+ * should be implemented.
+ *
+ * pcpu_populate_chunk          - populate the specified range of a chunk
+ * pcpu_depopulate_chunk        - depopulate the specified range of a chunk
+ * pcpu_create_chunk            - create a new chunk
+ * pcpu_destroy_chunk           - destroy a chunk, always preceded by full depop
+ * pcpu_addr_to_page            - translate address to physical address
+ * pcpu_verify_alloc_info       - check alloc_info is acceptable during init
  */
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
-{
-        int page_start = PFN_DOWN(off);
-        int page_end = PFN_UP(off + size);
-        int free_end = page_start, unmap_end = page_start;
-        struct page **pages;
-        unsigned long *populated;
-        unsigned int cpu;
-        int rs, re, rc;
-
-        /* quick path, check whether all pages are already there */
-        rs = page_start;
-        pcpu_next_pop(chunk, &rs, &re, page_end);
-        if (rs == page_start && re == page_end)
-                goto clear;
-
-        /* need to allocate and map pages, this chunk can't be immutable */
-        WARN_ON(chunk->immutable);
-
-        pages = pcpu_get_pages_and_bitmap(chunk, &populated, true);
-        if (!pages)
-                return -ENOMEM;
-
-        /* alloc and map */
-        pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
-                rc = pcpu_alloc_pages(chunk, pages, populated, rs, re);
-                if (rc)
-                        goto err_free;
-                free_end = re;
-        }
-
-        pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
-                rc = pcpu_map_pages(chunk, pages, populated, rs, re);
-                if (rc)
-                        goto err_unmap;
-                unmap_end = re;
-        }
-        pcpu_post_map_flush(chunk, page_start, page_end);
-
-        /* commit new bitmap */
-        bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
-clear:
-        for_each_possible_cpu(cpu)
-                memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
-        return 0;
-
-err_unmap:
-        pcpu_pre_unmap_flush(chunk, page_start, unmap_end);
-        pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end)
-                pcpu_unmap_pages(chunk, pages, populated, rs, re);
-        pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end);
-err_free:
-        pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end)
-                pcpu_free_pages(chunk, pages, populated, rs, re);
-        return rc;
-}
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size);
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size);
+static struct pcpu_chunk *pcpu_create_chunk(void);
+static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
+static struct page *pcpu_addr_to_page(void *addr);
+static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);
 
-static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
-{
-        if (chunk && chunk->data)
-                pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
-        pcpu_free_chunk(chunk);
-}
-
-static struct pcpu_chunk *pcpu_create_chunk(void)
-{
-        struct pcpu_chunk *chunk;
-        struct vm_struct **vms;
-
-        chunk = pcpu_alloc_chunk();
-        if (!chunk)
-                return NULL;
-
-        vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
-                                pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL);
-        if (!vms) {
-                pcpu_free_chunk(chunk);
-                return NULL;
-        }
-
-        chunk->data = vms;
-        chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
-        return chunk;
-}
+#include "percpu-vm.c"
 
 /**
  * pcpu_chunk_addr_search - determine chunk containing specified address
@@ -1086,7 +681,7 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
          * there's no need to worry about preemption or cpu hotplug.
          */
         addr += pcpu_unit_offsets[raw_smp_processor_id()];
-        return pcpu_get_page_chunk(vmalloc_to_page(addr));
+        return pcpu_get_page_chunk(pcpu_addr_to_page(addr));
 }
 
 /**
@@ -1386,7 +981,7 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
                 else
                         return page_to_phys(vmalloc_to_page(addr));
         } else
-                return page_to_phys(vmalloc_to_page(addr));
+                return page_to_phys(pcpu_addr_to_page(addr));
 }
 
 static inline size_t pcpu_calc_fc_sizes(size_t static_size,
@@ -1758,6 +1353,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
         PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
         PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
         PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
+        PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
 
         /* process group information and build config tables accordingly */
         group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));