[PATCH] paravirt: Add MMU virtualization to paravirt_ops

Add the three bare TLB accessor functions to paravirt-ops.  Most amusingly,
flush_tlb is redefined on SMP, so I can't call the paravirt op flush_tlb.
Instead, I chose to indicate the actual flush type, kernel (global) vs. user
(non-global).  Global in this sense means using the global bit in the page
table entry, which makes TLB entries persistent across CR3 reloads, not
global as in the SMP sense of invoking remote shootdowns, so the term is
confusingly overloaded.

AK: folded in fix from Zach for PAE compilation

Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>

5 files changed, 116 insertions, 26 deletions

diff --git a/include/asm-i386/paravirt.h b/include/asm-i386/paravirt.h
index e2c803fadb1..9f06265065f 100644
--- a/include/asm-i386/paravirt.h
+++ b/include/asm-i386/paravirt.h
@@ -4,6 +4,7 @@
  * para-virtualization: those hooks are defined here. */
 #include <linux/linkage.h>
 #include <linux/stringify.h>
+#include <asm/page.h>
 
 #ifdef CONFIG_PARAVIRT
 /* These are the most performance critical ops, so we want to be able to patch
@@ -27,6 +28,7 @@
 struct thread_struct;
 struct Xgt_desc_struct;
 struct tss_struct;
+struct mm_struct;
 struct paravirt_ops
 {
 	unsigned int kernel_rpl;
@@ -121,6 +123,23 @@ struct paravirt_ops
 	unsigned long (fastcall *apic_read)(unsigned long reg);
 #endif
 
+	void (fastcall *flush_tlb_user)(void);
+	void (fastcall *flush_tlb_kernel)(void);
+	void (fastcall *flush_tlb_single)(u32 addr);
+
+	void (fastcall *set_pte)(pte_t *ptep, pte_t pteval);
+	void (fastcall *set_pte_at)(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval);
+	void (fastcall *set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+	void (fastcall *pte_update)(struct mm_struct *mm, u32 addr, pte_t *ptep);
+	void (fastcall *pte_update_defer)(struct mm_struct *mm, u32 addr, pte_t *ptep);
+#ifdef CONFIG_X86_PAE
+	void (fastcall *set_pte_atomic)(pte_t *ptep, pte_t pteval);
+	void (fastcall *set_pte_present)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+	void (fastcall *set_pud)(pud_t *pudp, pud_t pudval);
+	void (fastcall *pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+	void (fastcall *pmd_clear)(pmd_t *pmdp);
+#endif
+
 	/* These two are jmp to, not actually called. */
 	void (fastcall *irq_enable_sysexit)(void);
 	void (fastcall *iret)(void);
@@ -297,6 +316,62 @@ static inline unsigned long apic_read(unsigned long reg)
 #endif
 
 
+#define __flush_tlb() paravirt_ops.flush_tlb_user()
+#define __flush_tlb_global() paravirt_ops.flush_tlb_kernel()
+#define __flush_tlb_single(addr) paravirt_ops.flush_tlb_single(addr)
+
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+	paravirt_ops.set_pte(ptep, pteval);
+}
+
+static inline void set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval)
+{
+	paravirt_ops.set_pte_at(mm, addr, ptep, pteval);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
+{
+	paravirt_ops.set_pmd(pmdp, pmdval);
+}
+
+static inline void pte_update(struct mm_struct *mm, u32 addr, pte_t *ptep)
+{
+	paravirt_ops.pte_update(mm, addr, ptep);
+}
+
+static inline void pte_update_defer(struct mm_struct *mm, u32 addr, pte_t *ptep)
+{
+	paravirt_ops.pte_update_defer(mm, addr, ptep);
+}
+
+#ifdef CONFIG_X86_PAE
+static inline void set_pte_atomic(pte_t *ptep, pte_t pteval)
+{
+	paravirt_ops.set_pte_atomic(ptep, pteval);
+}
+
+static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+{
+	paravirt_ops.set_pte_present(mm, addr, ptep, pte);
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pudval)
+{
+	paravirt_ops.set_pud(pudp, pudval);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	paravirt_ops.pte_clear(mm, addr, ptep);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	paravirt_ops.pmd_clear(pmdp);
+}
+#endif
+
 /* These all sit in the .parainstructions section to tell us what to patch. */
 struct paravirt_patch {
 	u8 *instr; 		/* original instructions */
diff --git a/include/asm-i386/pgtable-2level.h b/include/asm-i386/pgtable-2level.h
index 8d8d3b9ecdb..04d6186abc2 100644
--- a/include/asm-i386/pgtable-2level.h
+++ b/include/asm-i386/pgtable-2level.h
@@ -13,11 +13,14 @@
  * within a page table are directly modified.  Thus, the following
  * hook is made available.
  */
+#ifndef CONFIG_PARAVIRT
 #define set_pte(pteptr, pteval) (*(pteptr) = pteval)
 #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
+#endif
+
 #define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval)
 #define set_pte_present(mm,addr,ptep,pteval) set_pte_at(mm,addr,ptep,pteval)
-#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
 
 #define pte_clear(mm,addr,xp)	do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
 #define pmd_clear(xp)	do { set_pmd(xp, __pmd(0)); } while (0)
diff --git a/include/asm-i386/pgtable-3level.h b/include/asm-i386/pgtable-3level.h
index c2d701ea35b..2a6e67db8bc 100644
--- a/include/asm-i386/pgtable-3level.h
+++ b/include/asm-i386/pgtable-3level.h
@@ -44,6 +44,7 @@ static inline int pte_exec_kernel(pte_t pte)
 	return pte_x(pte);
 }
 
+#ifndef CONFIG_PARAVIRT
 /* Rules for using set_pte: the pte being assigned *must* be
  * either not present or in a state where the hardware will
  * not attempt to update the pte.  In places where this is
@@ -81,25 +82,6 @@ static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, pte
 		(*(pudptr) = (pudval))
 
 /*
- * Pentium-II erratum A13: in PAE mode we explicitly have to flush
- * the TLB via cr3 if the top-level pgd is changed...
- * We do not let the generic code free and clear pgd entries due to
- * this erratum.
- */
-static inline void pud_clear (pud_t * pud) { }
-
-#define pud_page(pud) \
-((struct page *) __va(pud_val(pud) & PAGE_MASK))
-
-#define pud_page_vaddr(pud) \
-((unsigned long) __va(pud_val(pud) & PAGE_MASK))
-
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \
-			pmd_index(address))
-
-/*
  * For PTEs and PDEs, we must clear the P-bit first when clearing a page table
  * entry, so clear the bottom half first and enforce ordering with a compiler
  * barrier.
@@ -118,6 +100,26 @@ static inline void pmd_clear(pmd_t *pmd)
 	smp_wmb();
 	*(tmp + 1) = 0;
 }
+#endif
+
+/*
+ * Pentium-II erratum A13: in PAE mode we explicitly have to flush
+ * the TLB via cr3 if the top-level pgd is changed...
+ * We do not let the generic code free and clear pgd entries due to
+ * this erratum.
+ */
+static inline void pud_clear (pud_t * pud) { }
+
+#define pud_page(pud) \
+((struct page *) __va(pud_val(pud) & PAGE_MASK))
+
+#define pud_page_vaddr(pud) \
+((unsigned long) __va(pud_val(pud) & PAGE_MASK))
+
+
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \
+			pmd_index(address))
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index 7d398f493dd..efd7d90789d 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -15,6 +15,7 @@
 #include <asm/processor.h>
 #include <asm/fixmap.h>
 #include <linux/threads.h>
+#include <asm/paravirt.h>
 
 #ifndef _I386_BITOPS_H
 #include <asm/bitops.h>
@@ -246,6 +247,7 @@ static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= _PAGE_PSE; return p
 # include <asm/pgtable-2level.h>
 #endif
 
+#ifndef CONFIG_PARAVIRT
 /*
  * Rules for using pte_update - it must be called after any PTE update which
  * has not been done using the set_pte / clear_pte interfaces.  It is used by
@@ -261,7 +263,7 @@ static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= _PAGE_PSE; return p
  */
 #define pte_update(mm, addr, ptep)		do { } while (0)
 #define pte_update_defer(mm, addr, ptep)	do { } while (0)
-
+#endif
 
 /*
  * We only update the dirty/accessed state if we set
diff --git a/include/asm-i386/tlbflush.h b/include/asm-i386/tlbflush.h
index 360648b0f2b..4dd82840d53 100644
--- a/include/asm-i386/tlbflush.h
+++ b/include/asm-i386/tlbflush.h
@@ -4,7 +4,15 @@
 #include <linux/mm.h>
 #include <asm/processor.h>
 
-#define __flush_tlb()							\
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define __flush_tlb() __native_flush_tlb()
+#define __flush_tlb_global() __native_flush_tlb_global()
+#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
+#endif
+
+#define __native_flush_tlb()						\
 	do {								\
 		unsigned int tmpreg;					\
 									\
@@ -19,7 +27,7 @@
  * Global pages have to be flushed a bit differently. Not a real
  * performance problem because this does not happen often.
  */
-#define __flush_tlb_global()						\
+#define __native_flush_tlb_global()					\
 	do {								\
 		unsigned int tmpreg, cr4, cr4_orig;			\
 									\
@@ -36,6 +44,9 @@
 			: "memory");					\
 	} while (0)
 
+#define __native_flush_tlb_single(addr) 				\
+	__asm__ __volatile__("invlpg (%0)" ::"r" (addr) : "memory")
+
 # define __flush_tlb_all()						\
 	do {								\
 		if (cpu_has_pge)					\
@@ -46,9 +57,6 @@
 
 #define cpu_has_invlpg	(boot_cpu_data.x86 > 3)
 
-#define __flush_tlb_single(addr) \
-	__asm__ __volatile__("invlpg (%0)" ::"r" (addr) : "memory")
-
 #ifdef CONFIG_X86_INVLPG
 # define __flush_tlb_one(addr) __flush_tlb_single(addr)
 #else