From 6bfde05bf5c9682e255c6a2c669dc80f91af6296 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Mon, 21 Sep 2009 17:03:43 -0700 Subject: hugetlbfs: allow the creation of files suitable for MAP_PRIVATE on the vfs internal mount This patchset adds a flag to mmap that allows the user to request that an anonymous mapping be backed with huge pages. This mapping will borrow functionality from the huge page shm code to create a file on the kernel internal mount and use it to approximate an anonymous mapping. The MAP_HUGETLB flag is a modifier to MAP_ANONYMOUS and will not work without both flags being preset. A new flag is necessary because there is no other way to hook into huge pages without creating a file on a hugetlbfs mount which wouldn't be MAP_ANONYMOUS. To userspace, this mapping will behave just like an anonymous mapping because the file is not accessible outside of the kernel. This patchset is meant to simplify the programming model. Presently there is a large chunk of boiler platecode, contained in libhugetlbfs, required to create private, hugepage backed mappings. This patch set would allow use of hugepages without linking to libhugetlbfs or having hugetblfs mounted. Unification of the VM code would provide these same benefits, but it has been resisted each time that it has been suggested for several reasons: it would break PAGE_SIZE assumptions across the kernel, it makes page-table abstractions really expensive, and it does not provide any benefit on architectures that do not support huge pages, incurring fast path penalties without providing any benefit on these architectures. This patch: There are two means of creating mappings backed by huge pages: 1. mmap() a file created on hugetlbfs 2. Use shm which creates a file on an internal mount which essentially maps it MAP_SHARED The internal mount is only used for shared mappings but there is very little that stops it being used for private mappings. This patch extends hugetlbfs_file_setup() to deal with the creation of files that will be mapped MAP_PRIVATE on the internal hugetlbfs mount. This extended API is used in a subsequent patch to implement the MAP_HUGETLB mmap() flag. Signed-off-by: Eric Munson Acked-by: David Rientjes Cc: Mel Gorman Cc: Adam Litke Cc: David Gibson Cc: Lee Schermerhorn Cc: Nick Piggin Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'ipc/shm.c') diff --git a/ipc/shm.c b/ipc/shm.c index 30162a59621..9eb1488b543 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -370,7 +370,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; file = hugetlb_file_setup(name, size, acctflag, - &shp->mlock_user); + &shp->mlock_user, HUGETLB_SHMFS_INODE); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even -- cgit From f0f37e2f77731b3473fa6bd5ee53255d9a9cdb40 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 27 Sep 2009 22:29:37 +0400 Subject: const: mark struct vm_struct_operations * mark struct vm_area_struct::vm_ops as const * mark vm_ops in AGP code But leave TTM code alone, something is fishy there with global vm_ops being used. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- ipc/shm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'ipc/shm.c') diff --git a/ipc/shm.c b/ipc/shm.c index 9eb1488b543..464694e0aa4 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -55,7 +55,7 @@ struct shm_file_data { #define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) static const struct file_operations shm_file_operations; -static struct vm_operations_struct shm_vm_ops; +static const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) @@ -312,7 +312,7 @@ static const struct file_operations shm_file_operations = { .get_unmapped_area = shm_get_unmapped_area, }; -static struct vm_operations_struct shm_vm_ops = { +static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, -- cgit