From 1745cbc5d0dee0749a6bc0ea8e872c5db0074061 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 29 Dec 2015 20:12:20 -0800 Subject: [PATCH] mm: Add vm_insert_pfn_prot() The x86 vvar vma contains pages with differing cacheability flags. x86 currently implements this by manually inserting all the ptes using (io_)remap_pfn_range when the vma is set up. x86 wants to move to using .fault with VM_FAULT_NOPAGE to set up the mappings as needed. The correct API to use to insert a pfn in .fault is vm_insert_pfn(), but vm_insert_pfn() can't override the vma's cache mode, and the HPET page in particular needs to be uncached despite the fact that the rest of the VMA is cached. Add vm_insert_pfn_prot() to support varying cacheability within the same non-COW VMA in a more sane manner. x86 could alternatively use multiple VMAs, but that's messy, would break CRIU, and would create unnecessary VMAs that would waste memory. Signed-off-by: Andy Lutomirski Reviewed-by: Kees Cook Acked-by: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Quentin Casasnovas Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/d2938d1eb37be7a5e4f86182db646551f11e45aa.1451446564.git.luto@kernel.org Signed-off-by: Ingo Molnar --- include/linux/mm.h | 2 ++ mm/memory.c | 25 +++++++++++++++++++++++-- 2 files changed, 25 insertions(+), 2 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 00bad7793788..87ef1d7730ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2080,6 +2080,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); +int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); diff --git a/mm/memory.c b/mm/memory.c index c387430f06c3..a29f0b90fc56 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1563,9 +1563,30 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, */ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) +{ + return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_pfn); + +/** + * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * @pgprot: pgprot flags for the inserted page + * + * This is exactly like vm_insert_pfn, except that it allows drivers to + * to override pgprot on a per-page basis. + * + * This only makes sense for IO mappings, and it makes no sense for + * cow mappings. In general, using multiple vmas is preferable; + * vm_insert_pfn_prot should only be used if using multiple VMAs is + * impractical. + */ +int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot) { int ret; - pgprot_t pgprot = vma->vm_page_prot; /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like @@ -1587,7 +1608,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, return ret; } -EXPORT_SYMBOL(vm_insert_pfn); +EXPORT_SYMBOL(vm_insert_pfn_prot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn)