mm/sparsemem: prepare for sub-section ranges

Prepare the memory hot-{add,remove} paths for handling sub-section
ranges by plumbing the starting page frame and number of pages being
handled through arch_{add,remove}_memory() to
sparse_{add,remove}_one_section().

This is simply plumbing, small cleanups, and some identifier renames.
No intended functional changes.

Link: http://lkml.kernel.org/r/156092353780.979959.9713046515562743194.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>	[ppc64]
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 78 insertions, 52 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 11220044b01a..3fbb2cfab126 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -252,51 +252,84 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
 }
 #endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
 
-static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
-                                   struct vmem_altmap *altmap)
+static int __meminit __add_section(int nid, unsigned long pfn,
+                unsigned long nr_pages, struct vmem_altmap *altmap)
 {
         int ret;
 
-        if (pfn_valid(phys_start_pfn))
+        if (pfn_valid(pfn))
                 return -EEXIST;
 
-        ret = sparse_add_one_section(nid, phys_start_pfn, altmap);
+        ret = sparse_add_section(nid, pfn, nr_pages, altmap);
         return ret < 0 ? ret : 0;
 }
 
+static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
+                const char *reason)
+{
+        /*
+         * Disallow all operations smaller than a sub-section and only
+         * allow operations smaller than a section for
+         * SPARSEMEM_VMEMMAP. Note that check_hotplug_memory_range()
+         * enforces a larger memory_block_size_bytes() granularity for
+         * memory that will be marked online, so this check should only
+         * fire for direct arch_{add,remove}_memory() users outside of
+         * add_memory_resource().
+         */
+        unsigned long min_align;
+
+        if (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
+                min_align = PAGES_PER_SUBSECTION;
+        else
+                min_align = PAGES_PER_SECTION;
+        if (!IS_ALIGNED(pfn, min_align)
+                        || !IS_ALIGNED(nr_pages, min_align)) {
+                WARN(1, "Misaligned __%s_pages start: %#lx end: #%lx\n",
+                                reason, pfn, pfn + nr_pages - 1);
+                return -EINVAL;
+        }
+        return 0;
+}
+
 /*
  * Reasonably generic function for adding memory.  It is
  * expected that archs that support memory hotplug will
  * call this function after deciding the zone to which to
  * add the new pages.
  */
-int __ref __add_pages(int nid, unsigned long phys_start_pfn,
-                unsigned long nr_pages, struct mhp_restrictions *restrictions)
+int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
+                struct mhp_restrictions *restrictions)
 {
         unsigned long i;
-        int err = 0;
-        int start_sec, end_sec;
+        int start_sec, end_sec, err;
         struct vmem_altmap *altmap = restrictions->altmap;
 
-        /* during initialize mem_map, align hot-added range to section */
-        start_sec = pfn_to_section_nr(phys_start_pfn);
-        end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
-
         if (altmap) {
                 /*
                  * Validate altmap is within bounds of the total request
                  */
-                if (altmap->base_pfn != phys_start_pfn
+                if (altmap->base_pfn != pfn
                                 || vmem_altmap_offset(altmap) > nr_pages) {
                         pr_warn_once("memory add fail, invalid altmap\n");
-                        err = -EINVAL;
-                        goto out;
+                        return -EINVAL;
                 }
                 altmap->alloc = 0;
         }
 
+        err = check_pfn_span(pfn, nr_pages, "add");
+        if (err)
+                return err;
+
+        start_sec = pfn_to_section_nr(pfn);
+        end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
         for (i = start_sec; i <= end_sec; i++) {
-                err = __add_section(nid, section_nr_to_pfn(i), altmap);
+                unsigned long pfns;
+
+                pfns = min(nr_pages, PAGES_PER_SECTION
+                                - (pfn & ~PAGE_SECTION_MASK));
+                err = __add_section(nid, pfn, pfns, altmap);
+                pfn += pfns;
+                nr_pages -= pfns;
 
                 /*
                  * EEXIST is finally dealt with by ioresource collision
@@ -309,7 +342,6 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn,
                 cond_resched();
         }
         vmemmap_populate_print_last();
-out:
         return err;
 }
 
@@ -487,10 +519,10 @@ static void shrink_pgdat_span(struct pglist_data *pgdat,
         pgdat->node_spanned_pages = 0;
 }
 
-static void __remove_zone(struct zone *zone, unsigned long start_pfn)
+static void __remove_zone(struct zone *zone, unsigned long start_pfn,
+                unsigned long nr_pages)
 {
         struct pglist_data *pgdat = zone->zone_pgdat;
-        int nr_pages = PAGES_PER_SECTION;
         unsigned long flags;
 
         pgdat_resize_lock(zone->zone_pgdat, &flags);
@@ -499,27 +531,23 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn)
         pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
-static void __remove_section(struct zone *zone, struct mem_section *ms,
-                             unsigned long map_offset,
-                             struct vmem_altmap *altmap)
+static void __remove_section(struct zone *zone, unsigned long pfn,
+                unsigned long nr_pages, unsigned long map_offset,
+                struct vmem_altmap *altmap)
 {
-        unsigned long start_pfn;
-        int scn_nr;
+        struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
 
         if (WARN_ON_ONCE(!valid_section(ms)))
                 return;
 
-        scn_nr = __section_nr(ms);
-        start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
-        __remove_zone(zone, start_pfn);
-
-        sparse_remove_one_section(ms, map_offset, altmap);
+        __remove_zone(zone, pfn, nr_pages);
+        sparse_remove_one_section(ms, pfn, nr_pages, map_offset, altmap);
 }
 
 /**
  * __remove_pages() - remove sections of pages from a zone
  * @zone: zone from which pages need to be removed
- * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
+ * @pfn: starting pageframe (must be aligned to start of a section)
  * @nr_pages: number of pages to remove (must be multiple of section size)
  * @altmap: alternative device page map or %NULL if default memmap is used
  *
@@ -528,30 +556,30 @@ static void __remove_section(struct zone *zone, struct mem_section *ms,
  * sure that pages are marked reserved and zones are adjust properly by
  * calling offline_pages().
  */
-void __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
+void __remove_pages(struct zone *zone, unsigned long pfn,
                     unsigned long nr_pages, struct vmem_altmap *altmap)
 {
-        unsigned long i;
         unsigned long map_offset = 0;
-        int sections_to_remove;
+        int i, start_sec, end_sec;
 
         map_offset = vmem_altmap_offset(altmap);
 
         clear_zone_contiguous(zone);
 
-        /*
-         * We can only remove entire sections
-         */
-        BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
-        BUG_ON(nr_pages % PAGES_PER_SECTION);
+        if (check_pfn_span(pfn, nr_pages, "remove"))
+                return;
 
-        sections_to_remove = nr_pages / PAGES_PER_SECTION;
-        for (i = 0; i < sections_to_remove; i++) {
-                unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+        start_sec = pfn_to_section_nr(pfn);
+        end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+        for (i = start_sec; i <= end_sec; i++) {
+                unsigned long pfns;
 
                 cond_resched();
-                __remove_section(zone, __pfn_to_section(pfn), map_offset,
-                                 altmap);
+                pfns = min(nr_pages, PAGES_PER_SECTION
+                                - (pfn & ~PAGE_SECTION_MASK));
+                __remove_section(zone, pfn, pfns, map_offset, altmap);
+                pfn += pfns;
+                nr_pages -= pfns;
                 map_offset = 0;
         }
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 6b01022e23a9..41579b66fff1 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -728,8 +728,8 @@ static void free_map_bootmem(struct page *memmap)
  * * -EEXIST    - Section has been present.
  * * -ENOMEM    - Out of memory.
  */
-int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
-                                     struct vmem_altmap *altmap)
+int __meminit sparse_add_section(int nid, unsigned long start_pfn,
+                unsigned long nr_pages, struct vmem_altmap *altmap)
 {
         unsigned long section_nr = pfn_to_section_nr(start_pfn);
         struct mem_section_usage *usage;
@@ -835,8 +835,9 @@ static void free_section_usage(struct mem_section *ms, struct page *memmap,
                 free_map_bootmem(memmap);
 }
 
-void sparse_remove_one_section(struct mem_section *ms, unsigned long map_offset,
-                               struct vmem_altmap *altmap)
+void sparse_remove_one_section(struct mem_section *ms, unsigned long pfn,
+                unsigned long nr_pages, unsigned long map_offset,
+                struct vmem_altmap *altmap)
 {
         struct page *memmap = NULL;
         struct mem_section_usage *usage = NULL;
@@ -849,10 +850,7 @@ void sparse_remove_one_section(struct mem_section *ms, unsigned long map_offset,
                 ms->usage = NULL;
         }
 
-        clear_hwpoisoned_pages(memmap + map_offset,
-                        PAGES_PER_SECTION - map_offset);
-        free_section_usage(ms, memmap, usage,
-                        section_nr_to_pfn(__section_nr(ms)),
-                        PAGES_PER_SECTION, altmap);
+        clear_hwpoisoned_pages(memmap + map_offset, nr_pages - map_offset);
+        free_section_usage(ms, memmap, usage, pfn, nr_pages, altmap);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */