mm: memmap_init: iterate over memblock regions rather that check each PFN

When called during boot the memmap_init_zone() function checks if each PFN
is valid and actually belongs to the node being initialized using
early_pfn_valid() and early_pfn_in_nid().

Each such check may cost up to O(log(n)) where n is the number of memory
banks, so for large amount of memory overall time spent in early_pfn*()
becomes substantial.

Since the information is anyway present in memblock, we can iterate over
memblock memory regions in memmap_init() and only call memmap_init_zone()
for PFN ranges that are know to be valid and in the appropriate node.

[cai@lca.pw: fix a compilation warning from Clang]
Link: http://lkml.kernel.org/r/CF6E407F-17DC-427C-8203-21979FB882EF@lca.pw
[bhe@redhat.com: fix the incorrect hole in fast_isolate_freepages()]
Link: http://lkml.kernel.org/r/8C537EB7-85EE-4DCF-943E-3CC0ED0DF56D@lca.pw
Link: http://lkml.kernel.org/r/20200521014407.29690-1-bhe@redhat.com
Signed-off-by: Baoquan He <bhe@redhat.com>
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Hoan Tran <hoan@os.amperecomputing.com>	[arm64]
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Cc: Guo Ren <guoren@kernel.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ley Foon Tan <ley.foon.tan@intel.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Qian Cai <cai@lca.pw>
Link: http://lkml.kernel.org/r/20200412194859.12663-16-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/compaction.c b/mm/compaction.c
index c9d659e6a02c5e0e32925fc0f6983785d4600641..8c2961100840bc2665e41cf345f8777e9f4fb254 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1409,7 +1409,9 @@ fast_isolate_freepages(struct compact_control *cc)
                                cc->free_pfn = highest;
                        } else {
                                if (cc->direct_compaction && pfn_valid(min_pfn)) {
-                                       page = pfn_to_page(min_pfn);
+                                       page = pageblock_pfn_to_page(min_pfn,
+                                               pageblock_end_pfn(min_pfn),
+                                               cc->zone);
                                        cc->free_pfn = min_pfn;
                                }
                        }

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 644a59d17318a47c8ef409274721e117030630c6..40587d74cd1c6fdf522f18ea23abeb76822fd273 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5951,23 +5951,6 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
        return false;
 }
 
-#ifdef CONFIG_SPARSEMEM
-/* Skip PFNs that belong to non-present sections */
-static inline __meminit unsigned long next_pfn(unsigned long pfn)
-{
-       const unsigned long section_nr = pfn_to_section_nr(++pfn);
-
-       if (present_section_nr(section_nr))
-               return pfn;
-       return section_nr_to_pfn(next_present_section_nr(section_nr));
-}
-#else
-static inline __meminit unsigned long next_pfn(unsigned long pfn)
-{
-       return pfn++;
-}
-#endif
-
 /*
  * Initially all pages are reserved - free ones are freed
  * up by memblock_free_all() once the early boot process is
@@ -6007,14 +5990,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
                 * function.  They do not exist on hotplugged memory.
                 */
                if (context == MEMMAP_EARLY) {
-                       if (!early_pfn_valid(pfn)) {
-                               pfn = next_pfn(pfn);
-                               continue;
-                       }
-                       if (!early_pfn_in_nid(pfn, nid)) {
-                               pfn++;
-                               continue;
-                       }
                        if (overlap_memmap_init(zone, &pfn))
                                continue;
                        if (defer_init(nid, pfn, end_pfn))
@@ -6130,9 +6105,23 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 }
 
 void __meminit __weak memmap_init(unsigned long size, int nid,
-                                 unsigned long zone, unsigned long start_pfn)
+                                 unsigned long zone,
+                                 unsigned long range_start_pfn)
 {
-       memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, NULL);
+       unsigned long start_pfn, end_pfn;
+       unsigned long range_end_pfn = range_start_pfn + size;
+       int i;
+
+       for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
+               start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn);
+               end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn);
+
+               if (end_pfn > start_pfn) {
+                       size = end_pfn - start_pfn;
+                       memmap_init_zone(size, nid, zone, start_pfn,
+                                        MEMMAP_EARLY, NULL);
+               }
+       }
 }
 
 static int zone_batchsize(struct zone *zone)