From 42d7395feb56f0655cd8b68e06fc6063823449f8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 11 Dec 2012 16:01:34 -0800 Subject: 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 Cc: Michael Kerrisk Acked-by: Rik van Riel Acked-by: KAMEZAWA Hiroyuki Cc: Hillf Danton Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 7 +++++-- include/linux/shm.h | 15 +++++++++++++++ 2 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 225164842ab..3e7fa1acf09 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -183,7 +183,8 @@ extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, unsigned long addr, size_t size, vm_flags_t acct, - struct user_struct **user, int creat_flags); + struct user_struct **user, int creat_flags, + int page_size_log); static inline int is_file_hugepages(struct file *file) { @@ -195,12 +196,14 @@ static inline int is_file_hugepages(struct file *file) return 0; } + #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) 0 static inline struct file * hugetlb_file_setup(const char *name, unsigned long addr, size_t size, - vm_flags_t acctflag, struct user_struct **user, int creat_flags) + vm_flags_t acctflag, struct user_struct **user, int creat_flags, + int page_size_log) { return ERR_PTR(-ENOSYS); } diff --git a/include/linux/shm.h b/include/linux/shm.h index bcf8a6a3ec0..429c1995d75 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -29,6 +29,21 @@ struct shmid_kernel /* private to the kernel */ #define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ #define SHM_NORESERVE 010000 /* don't check for reservations */ +/* Bits [26:31] are reserved */ + +/* + * When SHM_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 SHM_HUGE_SHIFT 26 +#define SHM_HUGE_MASK 0x3f +#define SHM_HUGE_2MB (21 << SHM_HUGE_SHIFT) +#define SHM_HUGE_1GB (30 << SHM_HUGE_SHIFT) + #ifdef CONFIG_SYSVIPC long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr, unsigned long shmlba); -- cgit v1.2.3-70-g09d2