mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB

There was some desire in large applications using MAP_HUGETLB or
SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on
others.  This is useful together with NUMA policy: use 2MB interleaving
on some mappings, but 1GB on local mappings.

This patch extends the IPC/SHM syscall interfaces slightly to allow
specifying the page size.

It borrows some upper bits in the existing flag arguments and allows
encoding the log of the desired page size in addition to the *_HUGETLB
flag.  When 0 is specified the default size is used, this makes the
change fully compatible.

Extending the internal hugetlb code to handle this is straight forward.
Instead of a single mount it just keeps an array of them and selects the
right mount based on the specified page size.  When no page size is
specified it uses the mount of the default page size.

The change is not visible in /proc/mounts because internal mounts don't
appear there.  It also has very little overhead: the additional mounts
just consume a super block, but not more memory when not used.

I also exported the new flags to the user headers (they were previously
under __KERNEL__).  Right now only symbols for x86 and some other
architecture for 1GB and 2MB are defined.  The interface should already
work for all other architectures though.  Only architectures that define
multiple hugetlb sizes actually need it (that is currently x86, tile,
powerpc).  However tile and powerpc have user configurable hugetlb
sizes, so it's not easy to add defines.  A program on those
architectures would need to query sysfs and use the appropiate log2.

[akpm@linux-foundation.org: cleanups]
[rientjes@google.com: fix build]
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 47 insertions, 0 deletions

diff --git a/arch/alpha/include/asm/mman.h b/arch/alpha/include/asm/mman.h
index cbeb3616a28e..0086b472bc2b 100644
--- a/arch/alpha/include/asm/mman.h
+++ b/arch/alpha/include/asm/mman.h
@@ -63,4 +63,15 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* __ALPHA_MMAN_H__ */
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index 46d3da0d4b92..9a936ac9a942 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -87,4 +87,15 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* _ASM_MMAN_H */
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 12219ebce869..294d251ca7b2 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -70,4 +70,15 @@
 #define MAP_FILE	0
 #define MAP_VARIABLE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* __PARISC_MMAN_H__ */
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 593e51d4643f..513b05f15bb4 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -3,6 +3,9 @@
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
+#define MAP_HUGE_2MB    (21 << MAP_HUGE_SHIFT)
+#define MAP_HUGE_1GB    (30 << MAP_HUGE_SHIFT)
+
 #include <asm-generic/mman.h>
 
 #endif /* _ASM_X86_MMAN_H */
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 25bc6c1309c3..00eed6786d7e 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -93,4 +93,15 @@
 /* compatibility flags */
 #define MAP_FILE	0
 
+/*
+ * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
+ * This gives us 6 bits, which is enough until someone invents 128 bit address
+ * spaces.
+ *
+ * Assume these are all power of twos.
+ * When 0 use the default page size.
+ */
+#define MAP_HUGE_SHIFT	26
+#define MAP_HUGE_MASK	0x3f
+
 #endif /* _XTENSA_MMAN_H */