From 5180da410db6369d1f95c9014da1c9bc33fb043e Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 8 Oct 2012 16:28:29 -0700 Subject: x86, pat: separate the pfn attribute tracking for remap_pfn_range and vm_insert_pfn With PAT enabled, vm_insert_pfn() looks up the existing pfn memory attribute and uses it. Expectation is that the driver reserves the memory attributes for the pfn before calling vm_insert_pfn(). remap_pfn_range() (when called for the whole vma) will setup a new attribute (based on the prot argument) for the specified pfn range. This addresses the legacy usage which typically calls remap_pfn_range() with a desired memory attribute. For ranges smaller than the vma size (which is typically not the case), remap_pfn_range() will use the existing memory attribute for the pfn range. Expose two different API's for these different behaviors. track_pfn_insert() for tracking the pfn attribute set by vm_insert_pfn() and track_pfn_remap() for the remap_pfn_range(). This cleanup also prepares the ground for the track/untrack pfn vma routines to take over the ownership of setting PAT specific vm_flag in the 'vma'. [khlebnikov@openvz.org: Clear checks in track_pfn_remap()] [akpm@linux-foundation.org: tweak a few comments] Signed-off-by: Suresh Siddha Signed-off-by: Konstantin Khlebnikov Cc: Venkatesh Pallipadi Cc: H. Peter Anvin Cc: Nick Piggin Cc: Ingo Molnar Cc: Alexander Viro Cc: Carsten Otte Cc: Chris Metcalf Cc: Cyrill Gorcunov Cc: Eric Paris Cc: Hugh Dickins Cc: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Konstantin Khlebnikov Cc: Matt Helsley Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Tetsuo Handa Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/pat.c | 47 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 36 insertions(+), 11 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index de36c886cd38..74a702674e86 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -664,13 +664,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) } /* - * track_pfn_vma_copy is called when vma that is covering the pfnmap gets + * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). * * If the vma has a linear pfn mapping for the entire range, we get the prot * from pte and reserve the entire vma range with single reserve_pfn_range call. */ -int track_pfn_vma_copy(struct vm_area_struct *vma) +int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; unsigned long prot; @@ -694,15 +694,12 @@ int track_pfn_vma_copy(struct vm_area_struct *vma) } /* - * track_pfn_vma_new is called when a _new_ pfn mapping is being established - * for physical range indicated by pfn and size. - * * prot is passed in as a parameter for the new mapping. If the vma has a * linear pfn mapping for the entire range reserve the entire vma range with * single reserve_pfn_range call. */ -int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn, unsigned long size) +int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn, unsigned long size) { resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT; unsigned long flags; @@ -714,8 +711,36 @@ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot, if (!pat_enabled) return 0; - /* for vm_insert_pfn and friends, we set prot based on lookup */ + /* + * For anything smaller than the vma size we set prot based on the + * lookup. + */ flags = lookup_memtype(paddr); + + /* Check memtype for the remaining pages */ + while (size > PAGE_SIZE) { + size -= PAGE_SIZE; + paddr += PAGE_SIZE; + if (flags != lookup_memtype(paddr)) + return -EINVAL; + } + + *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | + flags); + + return 0; +} + +int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, + unsigned long pfn) +{ + unsigned long flags; + + if (!pat_enabled) + return 0; + + /* Set prot based on lookup */ + flags = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | flags); @@ -723,12 +748,12 @@ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot, } /* - * untrack_pfn_vma is called while unmapping a pfnmap for a region. + * untrack_pfn is called while unmapping a pfnmap for a region. * untrack can be called for a specific region indicated by pfn and size or * can be for the entire vma (in which case pfn, size are zero). */ -void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size) +void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, + unsigned long size) { resource_size_t paddr; unsigned long prot; -- cgit v1.2.3-59-g8ed1b