x86/paravirt: add a pgd_alloc/free hooks

Add hooks which are called at pgd_alloc/free time.  The pgd_alloc hook
may return an error code, which if non-zero, causes the pgd allocation
to be failed.  The hooks may be used to allocate/free auxillary
per-pgd information.

also fix:

> * Ingo Molnar <mingo@elte.hu> wrote:
>
>  include/asm/pgalloc.h: In function ‘paravirt_pgd_free':
>  include/asm/pgalloc.h:14: error: parameter name omitted
>  arch/x86/kernel/entry_64.S: In file included from
>  arch/x86/kernel/traps_64.c:51:include/asm/pgalloc.h: In function ‘paravirt_pgd_free':
>  include/asm/pgalloc.h:14: error: parameter name omitted

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: xen-devel <xen-devel@lists.xensource.com>
Cc: Stephen Tweedie <sct@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/paravirt.c

@@ -30,6 +30,7 @@
 #include <asm/setup.h>
 #include <asm/arch_hooks.h>
 #include <asm/time.h>
+#include <asm/pgalloc.h>
 #include <asm/irq.h>
 #include <asm/delay.h>
 #include <asm/fixmap.h>
@@ -366,6 +367,9 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.flush_tlb_single = native_flush_tlb_single,
 	.flush_tlb_others = native_flush_tlb_others,
 
+	.pgd_alloc = __paravirt_pgd_alloc,
+	.pgd_free = paravirt_nop,
+
 	.alloc_pte = paravirt_nop,
 	.alloc_pmd = paravirt_nop,
 	.alloc_pmd_clone = paravirt_nop,

arch/x86/mm/pgtable.c

@@ -215,13 +215,15 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	/* so that alloc_pmd can use it */
 	mm->pgd = pgd;
-	if (pgd)
+	if (pgd) {
 		pgd_ctor(pgd);
 
-	if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
-		pgd_dtor(pgd);
-		free_page((unsigned long)pgd);
-		pgd = NULL;
+		if (paravirt_pgd_alloc(mm) != 0 ||
+		    !pgd_prepopulate_pmd(mm, pgd)) {
+			pgd_dtor(pgd);
+			free_page((unsigned long)pgd);
+			pgd = NULL;
+		}
 	}
 
 	return pgd;
@@ -231,6 +233,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	pgd_mop_up_pmds(mm, pgd);
 	pgd_dtor(pgd);
+	paravirt_pgd_free(mm, pgd);
 	free_page((unsigned long)pgd);
 }
 

arch/x86/xen/enlighten.c

@@ -45,6 +45,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/reboot.h>
+#include <asm/pgalloc.h>
 
 #include "xen-ops.h"
 #include "mmu.h"
@@ -1153,6 +1154,9 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.pte_update = paravirt_nop,
 	.pte_update_defer = paravirt_nop,
 
+	.pgd_alloc = __paravirt_pgd_alloc,
+	.pgd_free = paravirt_nop,
+
 	.alloc_pte = xen_alloc_pte_init,
 	.release_pte = xen_release_pte_init,
 	.alloc_pmd = xen_alloc_pte_init,

include/asm-x86/paravirt.h

@@ -219,7 +219,14 @@ struct pv_mmu_ops {
 	void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
 				 unsigned long va);
 
-	/* Hooks for allocating/releasing pagetable pages */
+	/* Hooks for allocating and freeing a pagetable top-level */
+	int  (*pgd_alloc)(struct mm_struct *mm);
+	void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
+
+	/*
+	 * Hooks for allocating/releasing pagetable pages when they're
+	 * attached to a pagetable
+	 */
 	void (*alloc_pte)(struct mm_struct *mm, u32 pfn);
 	void (*alloc_pmd)(struct mm_struct *mm, u32 pfn);
 	void (*alloc_pmd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
@@ -925,6 +932,16 @@ static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
 }
 
+static inline int paravirt_pgd_alloc(struct mm_struct *mm)
+{
+	return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
+}
+
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
+}
+
 static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned pfn)
 {
 	PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);

include/asm-x86/pgalloc.h

@@ -5,9 +5,13 @@
 #include <linux/mm.h>		/* for struct page */
 #include <linux/pagemap.h>
 
+static inline int  __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
+#define paravirt_pgd_alloc(mm)	__paravirt_pgd_alloc(mm)
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {}
 static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)	{}
 static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)	{}
 static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,