aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSuresh Siddha <suresh.b.siddha@intel.com>2008-10-07 13:58:46 -0700
committerIngo Molnar <mingo@elte.hu>2008-10-10 19:29:21 +0200
commitb27a43c1e90582facad44de67d02bc9e9f900289 (patch)
tree5cdf26c4043e9345cb132798a8535ccb9c20aa9a
parentad2cde16a21985cdc4302e4a4b0fc373d666fdf7 (diff)
x86, cpa: make the kernel physical mapping initialization a two pass sequence, fix
Jeremy Fitzhardinge wrote: > I'd noticed that current tip/master hasn't been booting under Xen, and I > just got around to bisecting it down to this change. > > commit 065ae73c5462d42e9761afb76f2b52965ff45bd6 > Author: Suresh Siddha <suresh.b.siddha@intel.com> > > x86, cpa: make the kernel physical mapping initialization a two pass sequence > > This patch is causing Xen to fail various pagetable updates because it > ends up remapping pagetables to RW, which Xen explicitly prohibits (as > that would allow guests to make arbitrary changes to pagetables, rather > than have them mediated by the hypervisor). Instead of making init a two pass sequence, to satisfy the Intel's TLB Application note (developer.intel.com/design/processor/applnots/317080.pdf Section 6 page 26), we preserve the original page permissions when fragmenting the large mappings and don't touch the existing memory mapping (which satisfies Xen's requirements). Only open issue is: on a native linux kernel, we will go back to mapping the first 0-1GB kernel identity mapping as executable (because of the static mapping setup in head_64.S). We can fix this in a different patch if needed. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Acked-by: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--arch/x86/mm/init_64.c149
1 files changed, 61 insertions, 88 deletions
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 6116ff0d741..8c7eae490a2 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -270,10 +270,9 @@ static __ref void unmap_low_page(void *adr)
early_iounmap(adr, PAGE_SIZE);
}
-static int physical_mapping_iter;
-
static unsigned long __meminit
-phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end)
+phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
+ pgprot_t prot)
{
unsigned pages = 0;
unsigned long last_map_addr = end;
@@ -291,35 +290,40 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end)
break;
}
+ /*
+ * We will re-use the existing mapping.
+ * Xen for example has some special requirements, like mapping
+ * pagetable pages as RO. So assume someone who pre-setup
+ * these mappings are more intelligent.
+ */
if (pte_val(*pte))
- goto repeat_set_pte;
+ continue;
if (0)
printk(" pte=%p addr=%lx pte=%016lx\n",
pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
pages++;
-repeat_set_pte:
- set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL));
+ set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot));
last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
}
- if (physical_mapping_iter == 1)
- update_page_count(PG_LEVEL_4K, pages);
+ update_page_count(PG_LEVEL_4K, pages);
return last_map_addr;
}
static unsigned long __meminit
-phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end)
+phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
+ pgprot_t prot)
{
pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
- return phys_pte_init(pte, address, end);
+ return phys_pte_init(pte, address, end, prot);
}
static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
- unsigned long page_size_mask)
+ unsigned long page_size_mask, pgprot_t prot)
{
unsigned long pages = 0;
unsigned long last_map_addr = end;
@@ -330,6 +334,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
unsigned long pte_phys;
pmd_t *pmd = pmd_page + pmd_index(address);
pte_t *pte;
+ pgprot_t new_prot = prot;
if (address >= end) {
if (!after_bootmem) {
@@ -343,45 +348,58 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
last_map_addr = phys_pte_update(pmd, address,
- end);
+ end, prot);
spin_unlock(&init_mm.page_table_lock);
continue;
}
- goto repeat_set_pte;
+ /*
+ * If we are ok with PG_LEVEL_2M mapping, then we will
+ * use the existing mapping,
+ *
+ * Otherwise, we will split the large page mapping but
+ * use the same existing protection bits except for
+ * large page, so that we don't violate Intel's TLB
+ * Application note (317080) which says, while changing
+ * the page sizes, new and old translations should
+ * not differ with respect to page frame and
+ * attributes.
+ */
+ if (page_size_mask & (1 << PG_LEVEL_2M))
+ continue;
+ new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
}
if (page_size_mask & (1<<PG_LEVEL_2M)) {
pages++;
-repeat_set_pte:
spin_lock(&init_mm.page_table_lock);
set_pte((pte_t *)pmd,
- pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+ pfn_pte(address >> PAGE_SHIFT,
+ __pgprot(pgprot_val(prot) | _PAGE_PSE)));
spin_unlock(&init_mm.page_table_lock);
last_map_addr = (address & PMD_MASK) + PMD_SIZE;
continue;
}
pte = alloc_low_page(&pte_phys);
- last_map_addr = phys_pte_init(pte, address, end);
+ last_map_addr = phys_pte_init(pte, address, end, new_prot);
unmap_low_page(pte);
spin_lock(&init_mm.page_table_lock);
pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
spin_unlock(&init_mm.page_table_lock);
}
- if (physical_mapping_iter == 1)
- update_page_count(PG_LEVEL_2M, pages);
+ update_page_count(PG_LEVEL_2M, pages);
return last_map_addr;
}
static unsigned long __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
- unsigned long page_size_mask)
+ unsigned long page_size_mask, pgprot_t prot)
{
pmd_t *pmd = pmd_offset(pud, 0);
unsigned long last_map_addr;
- last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask);
+ last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
__flush_tlb_all();
return last_map_addr;
}
@@ -398,6 +416,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
unsigned long pmd_phys;
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
+ pgprot_t prot = PAGE_KERNEL;
if (addr >= end)
break;
@@ -411,16 +430,28 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
if (pud_val(*pud)) {
if (!pud_large(*pud)) {
last_map_addr = phys_pmd_update(pud, addr, end,
- page_size_mask);
+ page_size_mask, prot);
continue;
}
-
- goto repeat_set_pte;
+ /*
+ * If we are ok with PG_LEVEL_1G mapping, then we will
+ * use the existing mapping.
+ *
+ * Otherwise, we will split the gbpage mapping but use
+ * the same existing protection bits except for large
+ * page, so that we don't violate Intel's TLB
+ * Application note (317080) which says, while changing
+ * the page sizes, new and old translations should
+ * not differ with respect to page frame and
+ * attributes.
+ */
+ if (page_size_mask & (1 << PG_LEVEL_1G))
+ continue;
+ prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
}
if (page_size_mask & (1<<PG_LEVEL_1G)) {
pages++;
-repeat_set_pte:
spin_lock(&init_mm.page_table_lock);
set_pte((pte_t *)pud,
pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
@@ -430,7 +461,8 @@ repeat_set_pte:
}
pmd = alloc_low_page(&pmd_phys);
- last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask);
+ last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
+ prot);
unmap_low_page(pmd);
spin_lock(&init_mm.page_table_lock);
@@ -439,8 +471,7 @@ repeat_set_pte:
}
__flush_tlb_all();
- if (physical_mapping_iter == 1)
- update_page_count(PG_LEVEL_1G, pages);
+ update_page_count(PG_LEVEL_1G, pages);
return last_map_addr;
}
@@ -505,54 +536,15 @@ static void __init init_gbpages(void)
direct_gbpages = 0;
}
-static int is_kernel(unsigned long pfn)
-{
- unsigned long pg_addresss = pfn << PAGE_SHIFT;
-
- if (pg_addresss >= (unsigned long) __pa(_text) &&
- pg_addresss < (unsigned long) __pa(_end))
- return 1;
-
- return 0;
-}
-
static unsigned long __init kernel_physical_mapping_init(unsigned long start,
unsigned long end,
unsigned long page_size_mask)
{
- unsigned long next, last_map_addr;
- u64 cached_supported_pte_mask = __supported_pte_mask;
- unsigned long cache_start = start;
- unsigned long cache_end = end;
-
- /*
- * First iteration will setup identity mapping using large/small pages
- * based on page_size_mask, with other attributes same as set by
- * the early code in head_64.S
- *
- * Second iteration will setup the appropriate attributes
- * as desired for the kernel identity mapping.
- *
- * This two pass mechanism conforms to the TLB app note which says:
- *
- * "Software should not write to a paging-structure entry in a way
- * that would change, for any linear address, both the page size
- * and either the page frame or attributes."
- *
- * For now, only difference between very early PTE attributes used in
- * head_64.S and here is _PAGE_NX.
- */
- BUILD_BUG_ON((__PAGE_KERNEL_LARGE & ~__PAGE_KERNEL_IDENT_LARGE_EXEC)
- != _PAGE_NX);
- __supported_pte_mask &= ~(_PAGE_NX);
- physical_mapping_iter = 1;
+ unsigned long next, last_map_addr = end;
-repeat:
- last_map_addr = cache_end;
-
- start = (unsigned long)__va(cache_start);
- end = (unsigned long)__va(cache_end);
+ start = (unsigned long)__va(start);
+ end = (unsigned long)__va(end);
for (; start < end; start = next) {
pgd_t *pgd = pgd_offset_k(start);
@@ -564,21 +556,11 @@ repeat:
next = end;
if (pgd_val(*pgd)) {
- /*
- * Static identity mappings will be overwritten
- * with run-time mappings. For example, this allows
- * the static 0-1GB identity mapping to be mapped
- * non-executable with this.
- */
- if (is_kernel(pte_pfn(*((pte_t *) pgd))))
- goto realloc;
-
last_map_addr = phys_pud_update(pgd, __pa(start),
__pa(end), page_size_mask);
continue;
}
-realloc:
pud = alloc_low_page(&pud_phys);
last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
page_size_mask);
@@ -590,15 +572,6 @@ realloc:
}
__flush_tlb_all();
- if (physical_mapping_iter == 1) {
- physical_mapping_iter = 2;
- /*
- * Second iteration will set the actual desired PTE attributes.
- */
- __supported_pte_mask = cached_supported_pte_mask;
- goto repeat;
- }
-
return last_map_addr;
}