mm/sparsemem: introduce a SECTION_IS_EARLY flag

In preparation for sub-section hotplug, track whether a given section
was created during early memory initialization, or later via memory
hotplug.  This distinction is needed to maintain the coarse expectation
that pfn_valid() returns true for any pfn within a given section even if
that section has pages that are reserved from the page allocator.

For example one of the of goals of subsection hotplug is to support
cases where the system physical memory layout collides System RAM and
PMEM within a section.  Several pfn_valid() users expect to just check
if a section is valid, but they are not careful to check if the given
pfn is within a "System RAM" boundary and instead expect pgdat
information to further validate the pfn.

Rather than unwind those paths to make their pfn_valid() queries more
precise a follow on patch uses the SECTION_IS_EARLY flag to maintain the
traditional expectation that pfn_valid() returns true for all early
sections.

Link: https://lore.kernel.org/lkml/1560366952-10660-1-git-send-email-cai@lca.pw/
Link: http://lkml.kernel.org/r/156092350358.979959.5817209875548072819.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: Qian Cai <cai@lca.pw>
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: Logan Gunthorpe <logang@deltatee.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.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: Vlastimil Babka <vbabka@suse.cz>
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>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2520336bdfd1894abf9aa2ef93847aab0cc442b0..4be40634238b380b451b67ac94cf58a1b3b14fac 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1260,7 +1260,8 @@ extern size_t mem_section_usage_size(void);
 #define        SECTION_MARKED_PRESENT  (1UL<<0)
 #define SECTION_HAS_MEM_MAP    (1UL<<1)
 #define SECTION_IS_ONLINE      (1UL<<2)
-#define SECTION_MAP_LAST_BIT   (1UL<<3)
+#define SECTION_IS_EARLY       (1UL<<3)
+#define SECTION_MAP_LAST_BIT   (1UL<<4)
 #define SECTION_MAP_MASK       (~(SECTION_MAP_LAST_BIT-1))
 #define SECTION_NID_SHIFT      3
 
@@ -1286,6 +1287,11 @@ static inline int valid_section(struct mem_section *section)
        return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
 }
 
+static inline int early_section(struct mem_section *section)
+{
+       return (section && (section->section_mem_map & SECTION_IS_EARLY));
+}
+
 static inline int valid_section_nr(unsigned long nr)
 {
        return valid_section(__nr_to_section(nr));

diff --git a/mm/sparse.c b/mm/sparse.c
index 41bef8e1f65c192427f19265fb864727fa7992fd..6d23a526279a7029ce1c473055c34fc9b8f30313 100644 (file)
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -288,11 +288,11 @@ struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pn
 
 static void __meminit sparse_init_one_section(struct mem_section *ms,
                unsigned long pnum, struct page *mem_map,
-               struct mem_section_usage *usage)
+               struct mem_section_usage *usage, unsigned long flags)
 {
        ms->section_mem_map &= ~SECTION_MAP_MASK;
-       ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
-                                                       SECTION_HAS_MEM_MAP;
+       ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum)
+               | SECTION_HAS_MEM_MAP | flags;
        ms->usage = usage;
 }
 
@@ -497,7 +497,8 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
                        goto failed;
                }
                check_usemap_section_nr(nid, usage);
-               sparse_init_one_section(__nr_to_section(pnum), pnum, map, usage);
+               sparse_init_one_section(__nr_to_section(pnum), pnum, map, usage,
+                               SECTION_IS_EARLY);
                usage = (void *) usage + mem_section_usage_size();
        }
        sparse_buffer_fini();
@@ -732,7 +733,7 @@ int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
 
        set_section_nid(section_nr, nid);
        section_mark_present(ms);
-       sparse_init_one_section(ms, section_nr, memmap, usage);
+       sparse_init_one_section(ms, section_nr, memmap, usage, 0);
 
 out:
        if (ret < 0) {
@@ -772,19 +773,16 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 }
 #endif
 
-static void free_section_usage(struct page *memmap,
+static void free_section_usage(struct mem_section *ms, struct page *memmap,
                struct mem_section_usage *usage, struct vmem_altmap *altmap)
 {
-       struct page *usage_page;
-
        if (!usage)
                return;
 
-       usage_page = virt_to_page(usage);
        /*
         * Check to see if allocation came from hot-plug-add
         */
-       if (PageSlab(usage_page) || PageCompound(usage_page)) {
+       if (!early_section(ms)) {
                kfree(usage);
                if (memmap)
                        __kfree_section_memmap(memmap, altmap);
@@ -816,6 +814,6 @@ void sparse_remove_one_section(struct mem_section *ms, unsigned long map_offset,
 
        clear_hwpoisoned_pages(memmap + map_offset,
                        PAGES_PER_SECTION - map_offset);
-       free_section_usage(memmap, usage, altmap);
+       free_section_usage(ms, memmap, usage, altmap);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */