x86/pvops: add a paravirt_ident functions to allow special patching

Impact: Optimization

Several paravirt ops implementations simply return their arguments,
the most obvious being the make_pte/pte_val class of operations on
native.

On 32-bit, the identity function is literally a no-op, as the calling
convention uses the same registers for the first argument and return.
On 64-bit, it can be implemented with a single "mov".

This patch adds special identity functions for 32 and 64 bit argument,
and machinery to recognize them and replace them with either nops or a
mov as appropriate.

At the moment, the only users for the identity functions are the
pagetable entry conversion functions.

The result is a measureable improvement on pagetable-heavy benchmarks
(2-3%, reducing the pvops overhead from 5 to 2%).

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 1757788870908c3bc88e081368f496b47b8ea3c1..961d10c12f16c1efda86be90b20d4411e56e69b4 100644 (file)
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -388,6 +388,8 @@ extern struct pv_lock_ops pv_lock_ops;
        asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
 
 unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
 unsigned paravirt_patch_ignore(unsigned len);
 unsigned paravirt_patch_call(void *insnbuf,
                             const void *target, u16 tgt_clobbers,
@@ -1371,6 +1373,9 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 }
 
 void _paravirt_nop(void);
+u32 _paravirt_ident_32(u32);
+u64 _paravirt_ident_64(u64);
+
 #define paravirt_nop   ((void *)_paravirt_nop)
 
 void paravirt_use_bytelocks(void);

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 202514be592349b7c99f005d4524e139dab20cd6..dd25e2b1593ba1a62b4b62eea1a9e54b33b1f970 100644 (file)
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -44,6 +44,17 @@ void _paravirt_nop(void)
 {
 }
 
+/* identity function, which can be inlined */
+u32 _paravirt_ident_32(u32 x)
+{
+       return x;
+}
+
+u64 _paravirt_ident_64(u64 x)
+{
+       return x;
+}
+
 static void __init default_banner(void)
 {
        printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
@@ -138,9 +149,16 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
        if (opfunc == NULL)
                /* If there's no function, patch it with a ud2a (BUG) */
                ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a));
-       else if (opfunc == paravirt_nop)
+       else if (opfunc == _paravirt_nop)
                /* If the operation is a nop, then nop the callsite */
                ret = paravirt_patch_nop();
+
+       /* identity functions just return their single argument */
+       else if (opfunc == _paravirt_ident_32)
+               ret = paravirt_patch_ident_32(insnbuf, len);
+       else if (opfunc == _paravirt_ident_64)
+               ret = paravirt_patch_ident_64(insnbuf, len);
+
        else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
                 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
                 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
@@ -373,6 +391,45 @@ struct pv_apic_ops pv_apic_ops = {
 #endif
 };
 
+typedef pte_t make_pte_t(pteval_t);
+typedef pmd_t make_pmd_t(pmdval_t);
+typedef pud_t make_pud_t(pudval_t);
+typedef pgd_t make_pgd_t(pgdval_t);
+
+typedef pteval_t pte_val_t(pte_t);
+typedef pmdval_t pmd_val_t(pmd_t);
+typedef pudval_t pud_val_t(pud_t);
+typedef pgdval_t pgd_val_t(pgd_t);
+
+
+#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE)
+/* 32-bit pagetable entries */
+#define paravirt_native_make_pte       (make_pte_t *)_paravirt_ident_32
+#define paravirt_native_pte_val                (pte_val_t *)_paravirt_ident_32
+
+#define paravirt_native_make_pmd       (make_pmd_t *)_paravirt_ident_32
+#define paravirt_native_pmd_val                (pmd_val_t *)_paravirt_ident_32
+
+#define paravirt_native_make_pud       (make_pud_t *)_paravirt_ident_32
+#define paravirt_native_pud_val                (pud_val_t *)_paravirt_ident_32
+
+#define paravirt_native_make_pgd       (make_pgd_t *)_paravirt_ident_32
+#define paravirt_native_pgd_val                (pgd_val_t *)_paravirt_ident_32
+#else
+/* 64-bit pagetable entries */
+#define paravirt_native_make_pte       (make_pte_t *)_paravirt_ident_64
+#define paravirt_native_pte_val                (pte_val_t *)_paravirt_ident_64
+
+#define paravirt_native_make_pmd       (make_pmd_t *)_paravirt_ident_64
+#define paravirt_native_pmd_val                (pmd_val_t *)_paravirt_ident_64
+
+#define paravirt_native_make_pud       (make_pud_t *)_paravirt_ident_64
+#define paravirt_native_pud_val                (pud_val_t *)_paravirt_ident_64
+
+#define paravirt_native_make_pgd       (make_pgd_t *)_paravirt_ident_64
+#define paravirt_native_pgd_val                (pgd_val_t *)_paravirt_ident_64
+#endif
+
 struct pv_mmu_ops pv_mmu_ops = {
 #ifndef CONFIG_X86_64
        .pagetable_setup_start = native_pagetable_setup_start,
@@ -424,21 +481,21 @@ struct pv_mmu_ops pv_mmu_ops = {
        .pmd_clear = native_pmd_clear,
 #endif
        .set_pud = native_set_pud,
-       .pmd_val = native_pmd_val,
-       .make_pmd = native_make_pmd,
+       .pmd_val = paravirt_native_pmd_val,
+       .make_pmd = paravirt_native_make_pmd,
 
 #if PAGETABLE_LEVELS == 4
-       .pud_val = native_pud_val,
-       .make_pud = native_make_pud,
+       .pud_val = paravirt_native_pud_val,
+       .make_pud = paravirt_native_make_pud,
        .set_pgd = native_set_pgd,
 #endif
 #endif /* PAGETABLE_LEVELS >= 3 */
 
-       .pte_val = native_pte_val,
-       .pgd_val = native_pgd_val,
+       .pte_val = paravirt_native_pte_val,
+       .pgd_val = paravirt_native_pgd_val,
 
-       .make_pte = native_make_pte,
-       .make_pgd = native_make_pgd,
+       .make_pte = paravirt_native_make_pte,
+       .make_pgd = paravirt_native_make_pgd,
 
        .dup_mmap = paravirt_nop,
        .exit_mmap = paravirt_nop,

diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 9fe644f4861d4f675206ce16f2c8f7c799a6aae5..d9f32e6d6ab65476be60c34d06c522215b83a26b 100644 (file)
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,18 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
 
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
+{
+       /* arg in %eax, return in %eax */
+       return 0;
+}
+
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
+{
+       /* arg in %edx:%eax, return in %edx:%eax */
+       return 0;
+}
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
                      unsigned long addr, unsigned len)
 {

diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 061d01df9ae6aa0ff09ff17d43eab28e61d21b10..3f08f34f93ebc480041d0b448e3b12869450a91d 100644 (file)
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -19,6 +19,21 @@ DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
 DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl");
 DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 
+DEF_NATIVE(, mov32, "mov %edi, %eax");
+DEF_NATIVE(, mov64, "mov %rdi, %rax");
+
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
+{
+       return paravirt_patch_insns(insnbuf, len,
+                                   start__mov32, end__mov32);
+}
+
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
+{
+       return paravirt_patch_insns(insnbuf, len,
+                                   start__mov64, end__mov64);
+}
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
                      unsigned long addr, unsigned len)
 {