[PATCH] i386: PARAVIRT: Allow paravirt backend to choose kernel PMD sharing

Normally when running in PAE mode, the 4th PMD maps the kernel address space,
which can be shared among all processes (since they all need the same kernel
mappings).

Xen, however, does not allow guests to have the kernel pmd shared between page
tables, so parameterize pgtable.c to allow both modes of operation.

There are several side-effects of this.  One is that vmalloc will update the
kernel address space mappings, and those updates need to be propagated into
all processes if the kernel mappings are not intrinsically shared.  In the
non-PAE case, this is done by maintaining a pgd_list of all processes; this
list is used when all process pagetables must be updated.  pgd_list is
threaded via otherwise unused entries in the page structure for the pgd, which
means that the pgd must be page-sized for this to work.

Normally the PAE pgd is only 4x64 byte entries large, but Xen requires the PAE
pgd to page aligned anyway, so this patch forces the pgd to be page
aligned+sized when the kernel pmd is unshared, to accomodate both these
requirements.

Also, since there may be several distinct kernel pmds (if the user/kernel
split is below 3G), there's no point in allocating them from a slab cache;
they're just allocated with get_free_page and initialized appropriately.  (Of
course the could be cached if there is just a single kernel pmd - which is the
default with a 3G user/kernel split - but it doesn't seem worthwhile to add
yet another case into this code).

[ Many thanks to wli for review comments. ]

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Christoph Lameter <clameter@sgi.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

6 files changed, 11 insertions, 4 deletions

diff --git a/include/asm-i386/paravirt.h b/include/asm-i386/paravirt.h
index c49b44cdd8ee..f93599dc7756 100644
--- a/include/asm-i386/paravirt.h
+++ b/include/asm-i386/paravirt.h
@@ -35,6 +35,7 @@ struct desc_struct;
 struct paravirt_ops
 {
         unsigned int kernel_rpl;
+        int shared_kernel_pmd;
         int paravirt_enabled;
         const char *name;
 
diff --git a/include/asm-i386/pgtable-2level-defs.h b/include/asm-i386/pgtable-2level-defs.h
index 02518079f816..0f71c9f13da4 100644
--- a/include/asm-i386/pgtable-2level-defs.h
+++ b/include/asm-i386/pgtable-2level-defs.h
@@ -1,6 +1,8 @@
 #ifndef _I386_PGTABLE_2LEVEL_DEFS_H
 #define _I386_PGTABLE_2LEVEL_DEFS_H
 
+#define SHARED_KERNEL_PMD       0
+
 /*
  * traditional i386 two-level paging structure:
  */
diff --git a/include/asm-i386/pgtable-2level.h b/include/asm-i386/pgtable-2level.h
index 043a2bcfa86a..781fe4bcc962 100644
--- a/include/asm-i386/pgtable-2level.h
+++ b/include/asm-i386/pgtable-2level.h
@@ -82,6 +82,4 @@ static inline int pte_exec_kernel(pte_t pte)
 #define __pte_to_swp_entry(pte)         ((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)           ((pte_t) { (x).val })
 
-void vmalloc_sync_all(void);
-
 #endif /* _I386_PGTABLE_2LEVEL_H */
diff --git a/include/asm-i386/pgtable-3level-defs.h b/include/asm-i386/pgtable-3level-defs.h
index eb3a1ea88671..c0df89f66e8b 100644
--- a/include/asm-i386/pgtable-3level-defs.h
+++ b/include/asm-i386/pgtable-3level-defs.h
@@ -1,6 +1,12 @@
 #ifndef _I386_PGTABLE_3LEVEL_DEFS_H
 #define _I386_PGTABLE_3LEVEL_DEFS_H
 
+#ifdef CONFIG_PARAVIRT
+#define SHARED_KERNEL_PMD       (paravirt_ops.shared_kernel_pmd)
+#else
+#define SHARED_KERNEL_PMD       1
+#endif
+
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
  */
diff --git a/include/asm-i386/pgtable-3level.h b/include/asm-i386/pgtable-3level.h
index be6017f37a91..664bfee5a2f2 100644
--- a/include/asm-i386/pgtable-3level.h
+++ b/include/asm-i386/pgtable-3level.h
@@ -200,6 +200,4 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 
 #define __pmd_free_tlb(tlb, x)          do { } while (0)
 
-#define vmalloc_sync_all() ((void)0)
-
 #endif /* _I386_PGTABLE_3LEVEL_H */
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index 0790ad6ed440..5b88a6a1278e 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -243,6 +243,8 @@ static inline pte_t pte_mkyoung(pte_t pte)	{ (pte).pte_low |= _PAGE_ACCESSED; re
 static inline pte_t pte_mkwrite(pte_t pte)      { (pte).pte_low |= _PAGE_RW; return pte; }
 static inline pte_t pte_mkhuge(pte_t pte)       { (pte).pte_low |= _PAGE_PSE; return pte; }
 
+extern void vmalloc_sync_all(void);
+
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>
 #else