From 664beed0190fae687ac51295694004902ddeb18e Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 21 Nov 2005 21:32:14 -0800 Subject: [PATCH] unpaged: unifdefed PageCompound It looks like snd_xxx is not the only nopage to be using PageReserved as a way of holding a high-order page together: which no longer works, but is masked by our failure to free from VM_RESERVED areas. We cannot fix that bug without first substituting another way to hold the high-order page together, while farming out the 0-order pages from within it. That's just what PageCompound is designed for, but it's been kept under CONFIG_HUGETLB_PAGE. Remove the #ifdefs: which saves some space (out- of-line put_page), doesn't slow down what most needs to be fast (already using hugetlb), and unifies the way we handle high-order pages. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0986d19be0b7..9701210c6680 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -311,8 +311,6 @@ struct page { extern void FASTCALL(__page_cache_release(struct page *)); -#ifdef CONFIG_HUGETLB_PAGE - static inline int page_count(struct page *page) { if (PageCompound(page)) @@ -329,23 +327,6 @@ static inline void get_page(struct page *page) void put_page(struct page *page); -#else /* CONFIG_HUGETLB_PAGE */ - -#define page_count(p) (atomic_read(&(p)->_count) + 1) - -static inline void get_page(struct page *page) -{ - atomic_inc(&page->_count); -} - -static inline void put_page(struct page *page) -{ - if (put_page_testzero(page)) - __page_cache_release(page); -} - -#endif /* CONFIG_HUGETLB_PAGE */ - /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of -- cgit From 0b14c179a483e71ea41df2aa4a661760063115bd Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 21 Nov 2005 21:32:15 -0800 Subject: [PATCH] unpaged: VM_UNPAGED Although we tend to associate VM_RESERVED with remap_pfn_range, quite a few drivers set VM_RESERVED on areas which are then populated by nopage. The PageReserved removal in 2.6.15-rc1 changed VM_RESERVED not to free pages in zap_pte_range, without changing those drivers not to set it: so their pages just leak away. Let's not change miscellaneous drivers now: introduce VM_UNPAGED at the core, to flag the special areas where the ptes may have no struct page, or if they have then it's not to be touched. Replace most instances of VM_RESERVED in core mm by VM_UNPAGED. Force it on in remap_pfn_range, and the sparc and sparc64 io_remap_pfn_range. Revert addition of VM_RESERVED to powerpc vdso, it's not needed there. Is it needed anywhere? It still governs the mm->reserved_vm statistic, and special vmas not to be merged, and areas not to be core dumped; but could probably be eliminated later (the drivers are probably specifying it because in 2.4 it kept swapout off the vma, but in 2.6 we work from the LRU, which these pages don't get on). Use the VM_SHM slot for VM_UNPAGED, and define VM_SHM to 0: it serves no purpose whatsoever, and should be removed from drivers when we clean up. Signed-off-by: Hugh Dickins Acked-by: William Irwin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9701210c6680..f0cdfd18db55 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -144,7 +144,8 @@ extern unsigned int kobjsize(const void *objp); #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_GROWSUP 0x00000200 -#define VM_SHM 0x00000400 /* shared memory area, don't swap out */ +#define VM_SHM 0x00000000 /* Means nothing: delete it later */ +#define VM_UNPAGED 0x00000400 /* Pages managed without map count */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_EXECUTABLE 0x00001000 @@ -157,7 +158,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ -#define VM_RESERVED 0x00080000 /* Pages managed in a special way */ +#define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ -- cgit From 6aab341e0a28aff100a09831c5300a2994b8b986 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 28 Nov 2005 14:34:23 -0800 Subject: mm: re-architect the VM_UNPAGED logic This replaces the (in my opinion horrible) VM_UNMAPPED logic with very explicit support for a "remapped page range" aka VM_PFNMAP. It allows a VM area to contain an arbitrary range of page table entries that the VM never touches, and never considers to be normal pages. Any user of "remap_pfn_range()" automatically gets this new functionality, and doesn't even have to mark the pages reserved or indeed mark them any other way. It just works. As a side effect, doing mmap() on /dev/mem works for arbitrary ranges. Sparc update from David in the next commit. Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f0cdfd18db55..6a75a7a78bf1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -145,7 +145,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_GROWSUP 0x00000200 #define VM_SHM 0x00000000 /* Means nothing: delete it later */ -#define VM_UNPAGED 0x00000400 /* Pages managed without map count */ +#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_EXECUTABLE 0x00001000 @@ -664,6 +664,7 @@ struct zap_details { unsigned long truncate_count; /* Compare vm_truncate_count */ }; +struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t); unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); unsigned long unmap_vmas(struct mmu_gather **tlb, @@ -953,7 +954,7 @@ unsigned long vmalloc_to_pfn(void *addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); -struct page *follow_page(struct mm_struct *, unsigned long address, +struct page *follow_page(struct vm_area_struct *, unsigned long address, unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ -- cgit