summaryrefslogtreecommitdiff
path: root/arch/x86/mm/pageattr.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm/pageattr.c')
-rw-r--r--arch/x86/mm/pageattr.c163
1 files changed, 114 insertions, 49 deletions
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a718e0d23503..091934e1d0d9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -94,12 +94,12 @@ static inline void split_page_count(int level) { }
static inline unsigned long highmap_start_pfn(void)
{
- return __pa(_text) >> PAGE_SHIFT;
+ return __pa_symbol(_text) >> PAGE_SHIFT;
}
static inline unsigned long highmap_end_pfn(void)
{
- return __pa(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
+ return __pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
}
#endif
@@ -276,8 +276,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
* The .rodata section needs to be read-only. Using the pfn
* catches all aliases.
*/
- if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
- __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
+ if (within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT,
+ __pa_symbol(__end_rodata) >> PAGE_SHIFT))
pgprot_val(forbidden) |= _PAGE_RW;
#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
@@ -364,6 +364,37 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
EXPORT_SYMBOL_GPL(lookup_address);
/*
+ * This is necessary because __pa() does not work on some
+ * kinds of memory, like vmalloc() or the alloc_remap()
+ * areas on 32-bit NUMA systems. The percpu areas can
+ * end up in this kind of memory, for instance.
+ *
+ * This could be optimized, but it is only intended to be
+ * used at inititalization time, and keeping it
+ * unoptimized should increase the testing coverage for
+ * the more obscure platforms.
+ */
+phys_addr_t slow_virt_to_phys(void *__virt_addr)
+{
+ unsigned long virt_addr = (unsigned long)__virt_addr;
+ phys_addr_t phys_addr;
+ unsigned long offset;
+ enum pg_level level;
+ unsigned long psize;
+ unsigned long pmask;
+ pte_t *pte;
+
+ pte = lookup_address(virt_addr, &level);
+ BUG_ON(!pte);
+ psize = page_level_size(level);
+ pmask = page_level_mask(level);
+ offset = virt_addr & ~pmask;
+ phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+ return (phys_addr | offset);
+}
+EXPORT_SYMBOL_GPL(slow_virt_to_phys);
+
+/*
* Set the new pmd in all the pgds we know about:
*/
static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
@@ -396,7 +427,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
pte_t new_pte, old_pte, *tmp;
pgprot_t old_prot, new_prot, req_prot;
int i, do_split = 1;
- unsigned int level;
+ enum pg_level level;
if (cpa->force_split)
return 1;
@@ -412,15 +443,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
switch (level) {
case PG_LEVEL_2M:
- psize = PMD_PAGE_SIZE;
- pmask = PMD_PAGE_MASK;
- break;
#ifdef CONFIG_X86_64
case PG_LEVEL_1G:
- psize = PUD_PAGE_SIZE;
- pmask = PUD_PAGE_MASK;
- break;
#endif
+ psize = page_level_size(level);
+ pmask = page_level_mask(level);
+ break;
default:
do_split = -EINVAL;
goto out_unlock;
@@ -445,6 +473,19 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
/*
+ * Set the PSE and GLOBAL flags only if the PRESENT flag is
+ * set otherwise pmd_present/pmd_huge will return true even on
+ * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
+ * for the ancient hardware that doesn't support it.
+ */
+ if (pgprot_val(new_prot) & _PAGE_PRESENT)
+ pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
+ else
+ pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
+
+ new_prot = canon_pgprot(new_prot);
+
+ /*
* old_pte points to the large page base address. So we need
* to add the offset of the virtual address:
*/
@@ -489,7 +530,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
* The address is aligned and the number of pages
* covers the full page.
*/
- new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot));
+ new_pte = pfn_pte(pte_pfn(old_pte), new_prot);
__set_pmd_pte(kpte, address, new_pte);
cpa->flags |= CPA_FLUSHTLB;
do_split = 0;
@@ -501,21 +542,13 @@ out_unlock:
return do_split;
}
-static int split_large_page(pte_t *kpte, unsigned long address)
+int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
{
unsigned long pfn, pfninc = 1;
unsigned int i, level;
- pte_t *pbase, *tmp;
+ pte_t *tmp;
pgprot_t ref_prot;
- struct page *base;
-
- if (!debug_pagealloc)
- spin_unlock(&cpa_lock);
- base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
- if (!debug_pagealloc)
- spin_lock(&cpa_lock);
- if (!base)
- return -ENOMEM;
+ struct page *base = virt_to_page(pbase);
spin_lock(&pgd_lock);
/*
@@ -523,10 +556,11 @@ static int split_large_page(pte_t *kpte, unsigned long address)
* up for us already:
*/
tmp = lookup_address(address, &level);
- if (tmp != kpte)
- goto out_unlock;
+ if (tmp != kpte) {
+ spin_unlock(&pgd_lock);
+ return 1;
+ }
- pbase = (pte_t *)page_address(base);
paravirt_alloc_pte(&init_mm, page_to_pfn(base));
ref_prot = pte_pgprot(pte_clrhuge(*kpte));
/*
@@ -540,27 +574,40 @@ static int split_large_page(pte_t *kpte, unsigned long address)
#ifdef CONFIG_X86_64
if (level == PG_LEVEL_1G) {
pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
- pgprot_val(ref_prot) |= _PAGE_PSE;
+ /*
+ * Set the PSE flags only if the PRESENT flag is set
+ * otherwise pmd_present/pmd_huge will return true
+ * even on a non present pmd.
+ */
+ if (pgprot_val(ref_prot) & _PAGE_PRESENT)
+ pgprot_val(ref_prot) |= _PAGE_PSE;
+ else
+ pgprot_val(ref_prot) &= ~_PAGE_PSE;
}
#endif
/*
+ * Set the GLOBAL flags only if the PRESENT flag is set
+ * otherwise pmd/pte_present will return true even on a non
+ * present pmd/pte. The canon_pgprot will clear _PAGE_GLOBAL
+ * for the ancient hardware that doesn't support it.
+ */
+ if (pgprot_val(ref_prot) & _PAGE_PRESENT)
+ pgprot_val(ref_prot) |= _PAGE_GLOBAL;
+ else
+ pgprot_val(ref_prot) &= ~_PAGE_GLOBAL;
+
+ /*
* Get the target pfn from the original entry:
*/
pfn = pte_pfn(*kpte);
for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
- set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
+ set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot)));
- if (address >= (unsigned long)__va(0) &&
- address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT))
+ if (pfn_range_is_mapped(PFN_DOWN(__pa(address)),
+ PFN_DOWN(__pa(address)) + 1))
split_page_count(level);
-#ifdef CONFIG_X86_64
- if (address >= (unsigned long)__va(1UL<<32) &&
- address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT))
- split_page_count(level);
-#endif
-
/*
* Install the new, split up pagetable.
*
@@ -579,17 +626,27 @@ static int split_large_page(pte_t *kpte, unsigned long address)
* going on.
*/
__flush_tlb_all();
+ spin_unlock(&pgd_lock);
- base = NULL;
+ return 0;
+}
-out_unlock:
- /*
- * If we dropped out via the lookup_address check under
- * pgd_lock then stick the page back into the pool:
- */
- if (base)
+static int split_large_page(pte_t *kpte, unsigned long address)
+{
+ pte_t *pbase;
+ struct page *base;
+
+ if (!debug_pagealloc)
+ spin_unlock(&cpa_lock);
+ base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
+ if (!debug_pagealloc)
+ spin_lock(&cpa_lock);
+ if (!base)
+ return -ENOMEM;
+
+ pbase = (pte_t *)page_address(base);
+ if (__split_large_page(kpte, address, pbase))
__free_page(base);
- spin_unlock(&pgd_lock);
return 0;
}
@@ -660,6 +717,18 @@ repeat:
new_prot = static_protections(new_prot, address, pfn);
/*
+ * Set the GLOBAL flags only if the PRESENT flag is
+ * set otherwise pte_present will return true even on
+ * a non present pte. The canon_pgprot will clear
+ * _PAGE_GLOBAL for the ancient hardware that doesn't
+ * support it.
+ */
+ if (pgprot_val(new_prot) & _PAGE_PRESENT)
+ pgprot_val(new_prot) |= _PAGE_GLOBAL;
+ else
+ pgprot_val(new_prot) &= ~_PAGE_GLOBAL;
+
+ /*
* We need to keep the pfn from the existing PTE,
* after all we're only going to change it's attributes
* not the memory it points to
@@ -729,13 +798,9 @@ static int cpa_process_alias(struct cpa_data *cpa)
unsigned long vaddr;
int ret;
- if (cpa->pfn >= max_pfn_mapped)
+ if (!pfn_range_is_mapped(cpa->pfn, cpa->pfn + 1))
return 0;
-#ifdef CONFIG_X86_64
- if (cpa->pfn >= max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT)))
- return 0;
-#endif
/*
* No need to redo, when the primary call touched the direct
* mapping already: