paravirt: refactor struct paravirt_ops into smaller pv_*_ops

This patch refactors the paravirt_ops structure into groups of
functionally related ops:

pv_info - random info, rather than function entrypoints
pv_init_ops - functions used at boot time (some for module_init too)
pv_misc_ops - lazy mode, which didn't fit well anywhere else
pv_time_ops - time-related functions
pv_cpu_ops - various privileged instruction ops
pv_irq_ops - operations for managing interrupt state
pv_apic_ops - APIC operations
pv_mmu_ops - operations for managing pagetables

There are several motivations for this:

1. Some of these ops will be general to all x86, and some will be
   i386/x86-64 specific.  This makes it easier to share common stuff
   while allowing separate implementations where needed.

2. At the moment we must export all of paravirt_ops, but modules only
   need selected parts of it.  This allows us to export on a case by case
   basis (and also choose which export license we want to apply).

3. Functional groupings make things a bit more readable.

Struct paravirt_ops is now only used as a template to generate
patch-site identifiers, and to extract function pointers for inserting
into jmp/calls when patching.  It is only instantiated when needed.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Cc: Zach Amsden <zach@vmware.com>
Cc: Avi Kivity <avi@qumranet.com>
Cc: Anthony Liguory <aliguori@us.ibm.com>
Cc: "Glauber de Oliveira Costa" <glommer@gmail.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>

arch/x86/kernel/alternative.c

@@ -368,8 +368,8 @@ void apply_paravirt(struct paravirt_patch_site *start,
 		BUG_ON(p->len > MAX_PATCH_LEN);
 		/* prep the buffer with the original instructions */
 		memcpy(insnbuf, p->instr, p->len);
-		used = paravirt_ops.patch(p->instrtype, p->clobbers, insnbuf,
-					  (unsigned long)p->instr, p->len);
+		used = pv_init_ops.patch(p->instrtype, p->clobbers, insnbuf,
+					 (unsigned long)p->instr, p->len);
 
 		BUG_ON(used > p->len);
 

arch/x86/kernel/asm-offsets_32.c

@@ -116,12 +116,14 @@ void foo(void)
 
 #ifdef CONFIG_PARAVIRT
 	BLANK();
-	OFFSET(PARAVIRT_enabled, paravirt_ops, paravirt_enabled);
-	OFFSET(PARAVIRT_irq_disable, paravirt_ops, irq_disable);
-	OFFSET(PARAVIRT_irq_enable, paravirt_ops, irq_enable);
-	OFFSET(PARAVIRT_irq_enable_sysexit, paravirt_ops, irq_enable_sysexit);
-	OFFSET(PARAVIRT_iret, paravirt_ops, iret);
-	OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0);
+	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
+	OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
+	OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
+	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
+	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
+	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
 #endif
 
 #ifdef CONFIG_XEN

arch/x86/kernel/entry_32.S

@@ -434,7 +434,7 @@ ldt_ss:
 	 * is still available to implement the setting of the high
 	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
 	 */
-	cmpl $0, paravirt_ops+PARAVIRT_enabled
+	cmpl $0, pv_info+PARAVIRT_enabled
 	jne restore_nocheck
 #endif
 

arch/x86/kernel/paravirt_32.c

@@ -42,32 +42,33 @@ void _paravirt_nop(void)
 static void __init default_banner(void)
 {
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
-	       paravirt_ops.name);
+	       pv_info.name);
 }
 
 char *memory_setup(void)
 {
-	return paravirt_ops.memory_setup();
+	return pv_init_ops.memory_setup();
 }
 
 /* Simple instruction patching code. */
-#define DEF_NATIVE(name, code)					\
-	extern const char start_##name[], end_##name[];		\
-	asm("start_" #name ": " code "; end_" #name ":")
-
-DEF_NATIVE(irq_disable, "cli");
-DEF_NATIVE(irq_enable, "sti");
-DEF_NATIVE(restore_fl, "push %eax; popf");
-DEF_NATIVE(save_fl, "pushf; pop %eax");
-DEF_NATIVE(iret, "iret");
-DEF_NATIVE(irq_enable_sysexit, "sti; sysexit");
-DEF_NATIVE(read_cr2, "mov %cr2, %eax");
-DEF_NATIVE(write_cr3, "mov %eax, %cr3");
-DEF_NATIVE(read_cr3, "mov %cr3, %eax");
-DEF_NATIVE(clts, "clts");
-DEF_NATIVE(read_tsc, "rdtsc");
-
-DEF_NATIVE(ud2a, "ud2a");
+#define DEF_NATIVE(ops, name, code)					\
+	extern const char start_##ops##_##name[], end_##ops##_##name[];	\
+	asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
+
+DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
+DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
+DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf");
+DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax");
+DEF_NATIVE(pv_cpu_ops, iret, "iret");
+DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit");
+DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
+DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
+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");
+
+/* Undefined instruction for dealing with missing ops pointers. */
+static const unsigned char ud2a[] = { 0x0f, 0x0b };
 
 static unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 			     unsigned long addr, unsigned len)
@@ -76,37 +77,29 @@ static unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 	unsigned ret;
 
 	switch(type) {
-#define SITE(x)	case PARAVIRT_PATCH(x):	start = start_##x; end = end_##x; goto patch_site
-		SITE(irq_disable);
-		SITE(irq_enable);
-		SITE(restore_fl);
-		SITE(save_fl);
-		SITE(iret);
-		SITE(irq_enable_sysexit);
-		SITE(read_cr2);
-		SITE(read_cr3);
-		SITE(write_cr3);
-		SITE(clts);
-		SITE(read_tsc);
+#define SITE(ops, x)						\
+	case PARAVIRT_PATCH(ops.x):				\
+		start = start_##ops##_##x;			\
+		end = end_##ops##_##x;				\
+		goto patch_site
+
+	SITE(pv_irq_ops, irq_disable);
+	SITE(pv_irq_ops, irq_enable);
+	SITE(pv_irq_ops, restore_fl);
+	SITE(pv_irq_ops, save_fl);
+	SITE(pv_cpu_ops, iret);
+	SITE(pv_cpu_ops, irq_enable_sysexit);
+	SITE(pv_mmu_ops, read_cr2);
+	SITE(pv_mmu_ops, read_cr3);
+	SITE(pv_mmu_ops, write_cr3);
+	SITE(pv_cpu_ops, clts);
+	SITE(pv_cpu_ops, read_tsc);
 #undef SITE
 
 	patch_site:
 		ret = paravirt_patch_insns(ibuf, len, start, end);
 		break;
 
-	case PARAVIRT_PATCH(make_pgd):
-	case PARAVIRT_PATCH(make_pte):
-	case PARAVIRT_PATCH(pgd_val):
-	case PARAVIRT_PATCH(pte_val):
-#ifdef CONFIG_X86_PAE
-	case PARAVIRT_PATCH(make_pmd):
-	case PARAVIRT_PATCH(pmd_val):
-#endif
-		/* These functions end up returning exactly what
-		   they're passed, in the same registers. */
-		ret = paravirt_patch_nop();
-		break;
-
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
@@ -150,7 +143,7 @@ unsigned paravirt_patch_call(void *insnbuf,
 	return 5;
 }
 
-unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
+unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
 			    unsigned long addr, unsigned len)
 {
 	struct branch *b = insnbuf;
@@ -165,22 +158,38 @@ unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
 	return 5;
 }
 
+/* Neat trick to map patch type back to the call within the
+ * corresponding structure. */
+static void *get_call_destination(u8 type)
+{
+	struct paravirt_patch_template tmpl = {
+		.pv_init_ops = pv_init_ops,
+		.pv_misc_ops = pv_misc_ops,
+		.pv_time_ops = pv_time_ops,
+		.pv_cpu_ops = pv_cpu_ops,
+		.pv_irq_ops = pv_irq_ops,
+		.pv_apic_ops = pv_apic_ops,
+		.pv_mmu_ops = pv_mmu_ops,
+	};
+	return *((void **)&tmpl + type);
+}
+
 unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
 				unsigned long addr, unsigned len)
 {
-	void *opfunc = *((void **)&paravirt_ops + type);
+	void *opfunc = get_call_destination(type);
 	unsigned ret;
 
 	if (opfunc == NULL)
 		/* If there's no function, patch it with a ud2a (BUG) */
-		ret = paravirt_patch_insns(insnbuf, len, start_ud2a, end_ud2a);
+		ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a));
 	else if (opfunc == paravirt_nop)
 		/* If the operation is a nop, then nop the callsite */
 		ret = paravirt_patch_nop();
-	else if (type == PARAVIRT_PATCH(iret) ||
-		 type == PARAVIRT_PATCH(irq_enable_sysexit))
+	else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+		 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit))
 		/* If operation requires a jmp, then jmp */
-		ret = paravirt_patch_jmp(opfunc, insnbuf, addr, len);
+		ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
 	else
 		/* Otherwise call the function; assume target could
 		   clobber any caller-save reg */
@@ -205,7 +214,7 @@ unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
 
 void init_IRQ(void)
 {
-	paravirt_ops.init_IRQ();
+	pv_irq_ops.init_IRQ();
 }
 
 static void native_flush_tlb(void)
@@ -233,7 +242,7 @@ extern void native_irq_enable_sysexit(void);
 
 static int __init print_banner(void)
 {
-	paravirt_ops.banner();
+	pv_init_ops.banner();
 	return 0;
 }
 core_initcall(print_banner);
@@ -273,47 +282,53 @@ int paravirt_disable_iospace(void)
 	return ret;
 }
 
-struct paravirt_ops paravirt_ops = {
+struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
 	.kernel_rpl = 0,
 	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
+};
 
- 	.patch = native_patch,
+struct pv_init_ops pv_init_ops = {
+	.patch = native_patch,
 	.banner = default_banner,
 	.arch_setup = paravirt_nop,
 	.memory_setup = machine_specific_memory_setup,
+};
+
+struct pv_time_ops pv_time_ops = {
+	.time_init = hpet_time_init,
 	.get_wallclock = native_get_wallclock,
 	.set_wallclock = native_set_wallclock,
-	.time_init = hpet_time_init,
+	.sched_clock = native_sched_clock,
+	.get_cpu_khz = native_calculate_cpu_khz,
+};
+
+struct pv_irq_ops pv_irq_ops = {
 	.init_IRQ = native_init_IRQ,
+	.save_fl = native_save_fl,
+	.restore_fl = native_restore_fl,
+	.irq_disable = native_irq_disable,
+	.irq_enable = native_irq_enable,
+	.safe_halt = native_safe_halt,
+	.halt = native_halt,
+};
 
+struct pv_cpu_ops pv_cpu_ops = {
 	.cpuid = native_cpuid,
 	.get_debugreg = native_get_debugreg,
 	.set_debugreg = native_set_debugreg,
 	.clts = native_clts,
 	.read_cr0 = native_read_cr0,
 	.write_cr0 = native_write_cr0,
-	.read_cr2 = native_read_cr2,
-	.write_cr2 = native_write_cr2,
-	.read_cr3 = native_read_cr3,
-	.write_cr3 = native_write_cr3,
 	.read_cr4 = native_read_cr4,
 	.read_cr4_safe = native_read_cr4_safe,
 	.write_cr4 = native_write_cr4,
-	.save_fl = native_save_fl,
-	.restore_fl = native_restore_fl,
-	.irq_disable = native_irq_disable,
-	.irq_enable = native_irq_enable,
-	.safe_halt = native_safe_halt,
-	.halt = native_halt,
 	.wbinvd = native_wbinvd,
 	.read_msr = native_read_msr_safe,
 	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
-	.sched_clock = native_sched_clock,
-	.get_cpu_khz = native_calculate_cpu_khz,
 	.load_tr_desc = native_load_tr_desc,
 	.set_ldt = native_set_ldt,
 	.load_gdt = native_load_gdt,
@@ -327,9 +342,14 @@ struct paravirt_ops paravirt_ops = {
 	.write_idt_entry = write_dt_entry,
 	.load_esp0 = native_load_esp0,
 
+	.irq_enable_sysexit = native_irq_enable_sysexit,
+	.iret = native_iret,
+
 	.set_iopl_mask = native_set_iopl_mask,
 	.io_delay = native_io_delay,
+};
 
+struct pv_apic_ops pv_apic_ops = {
 #ifdef CONFIG_X86_LOCAL_APIC
 	.apic_write = native_apic_write,
 	.apic_write_atomic = native_apic_write_atomic,
@@ -338,11 +358,21 @@ struct paravirt_ops paravirt_ops = {
 	.setup_secondary_clock = setup_secondary_APIC_clock,
 	.startup_ipi_hook = paravirt_nop,
 #endif
+};
+
+struct pv_misc_ops pv_misc_ops = {
 	.set_lazy_mode = paravirt_nop,
+};
 
+struct pv_mmu_ops pv_mmu_ops = {
 	.pagetable_setup_start = native_pagetable_setup_start,
 	.pagetable_setup_done = native_pagetable_setup_done,
 
+	.read_cr2 = native_read_cr2,
+	.write_cr2 = native_write_cr2,
+	.read_cr3 = native_read_cr3,
+	.write_cr3 = native_write_cr3,
+
 	.flush_tlb_user = native_flush_tlb,
 	.flush_tlb_kernel = native_flush_tlb_global,
 	.flush_tlb_single = native_flush_tlb_single,
@@ -381,12 +411,14 @@ struct paravirt_ops paravirt_ops = {
 	.make_pte = native_make_pte,
 	.make_pgd = native_make_pgd,
 
-	.irq_enable_sysexit = native_irq_enable_sysexit,
-	.iret = native_iret,
-
 	.dup_mmap = paravirt_nop,
 	.exit_mmap = paravirt_nop,
 	.activate_mm = paravirt_nop,
 };
 
-EXPORT_SYMBOL(paravirt_ops);
+EXPORT_SYMBOL_GPL(pv_time_ops);
+EXPORT_SYMBOL_GPL(pv_cpu_ops);
+EXPORT_SYMBOL_GPL(pv_mmu_ops);
+EXPORT_SYMBOL_GPL(pv_apic_ops);
+EXPORT_SYMBOL_GPL(pv_info);
+EXPORT_SYMBOL    (pv_irq_ops);

arch/x86/xen/enlighten.c

@@ -124,7 +124,7 @@ static void __init xen_vcpu_setup(int cpu)
 static void __init xen_banner(void)
 {
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
-	       paravirt_ops.name);
+	       pv_info.name);
 	printk(KERN_INFO "Hypervisor signature: %s\n", xen_start_info->magic);
 }
 
@@ -738,7 +738,7 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 	pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
 
 	/* special set_pte for pagetable initialization */
-	paravirt_ops.set_pte = xen_set_pte_init;
+	pv_mmu_ops.set_pte = xen_set_pte_init;
 
 	init_mm.pgd = base;
 	/*
@@ -785,8 +785,8 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 {
 	/* This will work as long as patching hasn't happened yet
 	   (which it hasn't) */
-	paravirt_ops.alloc_pt = xen_alloc_pt;
-	paravirt_ops.set_pte = xen_set_pte;
+	pv_mmu_ops.alloc_pt = xen_alloc_pt;
+	pv_mmu_ops.set_pte = xen_set_pte;
 
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		/*
@@ -833,12 +833,12 @@ void __init xen_setup_vcpu_info_placement(void)
 	if (have_vcpu_info_placement) {
 		printk(KERN_INFO "Xen: using vcpu_info placement\n");
 
-		paravirt_ops.save_fl = xen_save_fl_direct;
-		paravirt_ops.restore_fl = xen_restore_fl_direct;
-		paravirt_ops.irq_disable = xen_irq_disable_direct;
-		paravirt_ops.irq_enable = xen_irq_enable_direct;
-		paravirt_ops.read_cr2 = xen_read_cr2_direct;
-		paravirt_ops.iret = xen_iret_direct;
+		pv_irq_ops.save_fl = xen_save_fl_direct;
+		pv_irq_ops.restore_fl = xen_restore_fl_direct;
+		pv_irq_ops.irq_disable = xen_irq_disable_direct;
+		pv_irq_ops.irq_enable = xen_irq_enable_direct;
+		pv_mmu_ops.read_cr2 = xen_read_cr2_direct;
+		pv_cpu_ops.iret = xen_iret_direct;
 	}
 }
 
@@ -850,8 +850,8 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 
 	start = end = reloc = NULL;
 
-#define SITE(x)								\
-	case PARAVIRT_PATCH(x):						\
+#define SITE(op, x)							\
+	case PARAVIRT_PATCH(op.x):					\
 	if (have_vcpu_info_placement) {					\
 		start = (char *)xen_##x##_direct;			\
 		end = xen_##x##_direct_end;				\
@@ -860,10 +860,10 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 	goto patch_site
 
 	switch (type) {
-		SITE(irq_enable);
-		SITE(irq_disable);
-		SITE(save_fl);
-		SITE(restore_fl);
+		SITE(pv_irq_ops, irq_enable);
+		SITE(pv_irq_ops, irq_disable);
+		SITE(pv_irq_ops, save_fl);
+		SITE(pv_irq_ops, restore_fl);
 #undef SITE
 
 	patch_site:
@@ -895,26 +895,32 @@ static unsigned xen_patch(u8 type, u16 clobbers, void *insnbuf,
 	return ret;
 }
 
-static const struct paravirt_ops xen_paravirt_ops __initdata = {
+static const struct pv_info xen_info __initdata = {
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
 	.name = "Xen",
-	.banner = xen_banner,
+};
 
+static const struct pv_init_ops xen_init_ops __initdata = {
 	.patch = xen_patch,
 
+	.banner = xen_banner,
 	.memory_setup = xen_memory_setup,
 	.arch_setup = xen_arch_setup,
-	.init_IRQ = xen_init_IRQ,
 	.post_allocator_init = xen_mark_init_mm_pinned,
+};
 
+static const struct pv_time_ops xen_time_ops __initdata = {
 	.time_init = xen_time_init,
+
 	.set_wallclock = xen_set_wallclock,
 	.get_wallclock = xen_get_wallclock,
 	.get_cpu_khz = xen_cpu_khz,
 	.sched_clock = xen_sched_clock,
+};
 
+static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 	.cpuid = xen_cpuid,
 
 	.set_debugreg = xen_set_debugreg,
@@ -925,22 +931,10 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
 	.read_cr0 = native_read_cr0,
 	.write_cr0 = native_write_cr0,
 
-	.read_cr2 = xen_read_cr2,
-	.write_cr2 = xen_write_cr2,
-
-	.read_cr3 = xen_read_cr3,
-	.write_cr3 = xen_write_cr3,
-
 	.read_cr4 = native_read_cr4,
 	.read_cr4_safe = native_read_cr4_safe,
 	.write_cr4 = xen_write_cr4,
 
-	.save_fl = xen_save_fl,
-	.restore_fl = xen_restore_fl,
-	.irq_disable = xen_irq_disable,
-	.irq_enable = xen_irq_enable,
-	.safe_halt = xen_safe_halt,
-	.halt = xen_halt,
 	.wbinvd = native_wbinvd,
 
 	.read_msr = native_read_msr_safe,
@@ -968,7 +962,19 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
 
 	.set_iopl_mask = xen_set_iopl_mask,
 	.io_delay = xen_io_delay,
+};
+
+static const struct pv_irq_ops xen_irq_ops __initdata = {
+	.init_IRQ = xen_init_IRQ,
+	.save_fl = xen_save_fl,
+	.restore_fl = xen_restore_fl,
+	.irq_disable = xen_irq_disable,
+	.irq_enable = xen_irq_enable,
+	.safe_halt = xen_safe_halt,
+	.halt = xen_halt,
+};
 
+static const struct pv_apic_ops xen_apic_ops __initdata = {
 #ifdef CONFIG_X86_LOCAL_APIC
 	.apic_write = xen_apic_write,
 	.apic_write_atomic = xen_apic_write,
@@ -977,6 +983,17 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
 	.setup_secondary_clock = paravirt_nop,
 	.startup_ipi_hook = paravirt_nop,
 #endif
+};
+
+static const struct pv_mmu_ops xen_mmu_ops __initdata = {
+	.pagetable_setup_start = xen_pagetable_setup_start,
+	.pagetable_setup_done = xen_pagetable_setup_done,
+
+	.read_cr2 = xen_read_cr2,
+	.write_cr2 = xen_write_cr2,
+
+	.read_cr3 = xen_read_cr3,
+	.write_cr3 = xen_write_cr3,
 
 	.flush_tlb_user = xen_flush_tlb,
 	.flush_tlb_kernel = xen_flush_tlb,
@@ -986,9 +1003,6 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
 	.pte_update = paravirt_nop,
 	.pte_update_defer = paravirt_nop,
 
-	.pagetable_setup_start = xen_pagetable_setup_start,
-	.pagetable_setup_done = xen_pagetable_setup_done,
-
 	.alloc_pt = xen_alloc_pt_init,
 	.release_pt = xen_release_pt,
 	.alloc_pd = paravirt_nop,
@@ -1023,7 +1037,9 @@ static const struct paravirt_ops xen_paravirt_ops __initdata = {
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
 	.exit_mmap = xen_exit_mmap,
+};
 
+static const struct pv_misc_ops xen_misc_ops __initdata = {
 	.set_lazy_mode = xen_set_lazy_mode,
 };
 
@@ -1091,7 +1107,15 @@ asmlinkage void __init xen_start_kernel(void)
 	BUG_ON(memcmp(xen_start_info->magic, "xen-3.0", 7) != 0);
 
 	/* Install Xen paravirt ops */
-	paravirt_ops = xen_paravirt_ops;
+	pv_info = xen_info;
+	pv_init_ops = xen_init_ops;
+	pv_time_ops = xen_time_ops;
+	pv_cpu_ops = xen_cpu_ops;
+	pv_irq_ops = xen_irq_ops;
+	pv_apic_ops = xen_apic_ops;
+	pv_mmu_ops = xen_mmu_ops;
+	pv_misc_ops = xen_misc_ops;
+
 	machine_ops = xen_machine_ops;
 
 #ifdef CONFIG_SMP
@@ -1124,9 +1148,9 @@ asmlinkage void __init xen_start_kernel(void)
 	xen_setup_vcpu_info_placement();
 #endif
 
-	paravirt_ops.kernel_rpl = 1;
+	pv_info.kernel_rpl = 1;
 	if (xen_feature(XENFEAT_supervisor_mode_kernel))
-		paravirt_ops.kernel_rpl = 0;
+		pv_info.kernel_rpl = 0;
 
 	/* set the limit of our address space */
 	reserve_top_address(-HYPERVISOR_VIRT_START + 2 * PAGE_SIZE);

drivers/char/hvc_lguest.c

@@ -115,7 +115,7 @@ static struct hv_ops lguest_cons = {
  * (0), and the struct hv_ops containing the put_chars() function. */
 static int __init cons_init(void)
 {
-	if (strcmp(paravirt_ops.name, "lguest") != 0)
+	if (strcmp(pv_info.name, "lguest") != 0)
 		return 0;
 
 	return hvc_instantiate(0, 0, &lguest_cons);

drivers/lguest/core.c

@@ -248,8 +248,8 @@ static void unmap_switcher(void)
 }
 
 /*H:130 Our Guest is usually so well behaved; it never tries to do things it
- * isn't allowed to.  Unfortunately, "struct paravirt_ops" isn't quite
- * complete, because it doesn't contain replacements for the Intel I/O
+ * isn't allowed to.  Unfortunately, Linux's paravirtual infrastructure isn't
+ * quite complete, because it doesn't contain replacements for the Intel I/O
  * instructions.  As a result, the Guest sometimes fumbles across one during
  * the boot process as it probes for various things which are usually attached
  * to a PC.
@@ -694,7 +694,7 @@ static int __init init(void)
 
 	/* Lguest can't run under Xen, VMI or itself.  It does Tricky Stuff. */
 	if (paravirt_enabled()) {
-		printk("lguest is afraid of %s\n", paravirt_ops.name);
+		printk("lguest is afraid of %s\n", pv_info.name);
 		return -EPERM;
 	}
 

drivers/lguest/lguest.c

@@ -23,7 +23,7 @@
  *
  * So how does the kernel know it's a Guest?  The Guest starts at a special
  * entry point marked with a magic string, which sets up a few things then
- * calls here.  We replace the native functions in "struct paravirt_ops"
+ * calls here.  We replace the native functions various "paravirt" structures
  * with our Guest versions, then boot like normal. :*/
 
 /*
@@ -331,7 +331,7 @@ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu)
 }
 
 /*G:038 That's enough excitement for now, back to ploughing through each of
- * the paravirt_ops (we're about 1/3 of the way through).
+ * the different pv_ops structures (we're about 1/3 of the way through).
  *
  * This is the Local Descriptor Table, another weird Intel thingy.  Linux only
  * uses this for some strange applications like Wine.  We don't do anything
@@ -558,7 +558,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval)
 		lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0);
 }
 
-/* Unfortunately for Lguest, the paravirt_ops for page tables were based on
+/* Unfortunately for Lguest, the pv_mmu_ops for page tables were based on
  * native page table operations.  On native hardware you can set a new page
  * table entry whenever you want, but if you want to remove one you have to do
  * a TLB flush (a TLB is a little cache of page table entries kept by the CPU).
@@ -782,7 +782,7 @@ static void lguest_time_init(void)
 	clocksource_register(&lguest_clock);
 
 	/* Now we've set up our clock, we can use it as the scheduler clock */
-	paravirt_ops.sched_clock = lguest_sched_clock;
+	pv_time_ops.sched_clock = lguest_sched_clock;
 
 	/* We can't set cpumask in the initializer: damn C limitations!  Set it
 	 * here and register our timer device. */
@@ -902,7 +902,7 @@ static __init char *lguest_memory_setup(void)
 /*G:050
  * Patching (Powerfully Placating Performance Pedants)
  *
- * We have already seen that "struct paravirt_ops" lets us replace simple
+ * We have already seen that pv_ops structures let us replace simple
  * native instructions with calls to the appropriate back end all throughout
  * the kernel.  This allows the same kernel to run as a Guest and as a native
  * kernel, but it's slow because of all the indirect branches.
@@ -927,10 +927,10 @@ static const struct lguest_insns
 {
 	const char *start, *end;
 } lguest_insns[] = {
-	[PARAVIRT_PATCH(irq_disable)] = { lgstart_cli, lgend_cli },
-	[PARAVIRT_PATCH(irq_enable)] = { lgstart_sti, lgend_sti },
-	[PARAVIRT_PATCH(restore_fl)] = { lgstart_popf, lgend_popf },
-	[PARAVIRT_PATCH(save_fl)] = { lgstart_pushf, lgend_pushf },
+	[PARAVIRT_PATCH(pv_irq_ops.irq_disable)] = { lgstart_cli, lgend_cli },
+	[PARAVIRT_PATCH(pv_irq_ops.irq_enable)] = { lgstart_sti, lgend_sti },
+	[PARAVIRT_PATCH(pv_irq_ops.restore_fl)] = { lgstart_popf, lgend_popf },
+	[PARAVIRT_PATCH(pv_irq_ops.save_fl)] = { lgstart_pushf, lgend_pushf },
 };
 
 /* Now our patch routine is fairly simple (based on the native one in
@@ -957,9 +957,9 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf,
 	return insn_len;
 }
 
-/*G:030 Once we get to lguest_init(), we know we're a Guest.  The paravirt_ops
- * structure in the kernel provides a single point for (almost) every routine
- * we have to override to avoid privileged instructions. */
+/*G:030 Once we get to lguest_init(), we know we're a Guest.  The pv_ops
+ * structures in the kernel provide points for (almost) every routine we have
+ * to override to avoid privileged instructions. */
 __init void lguest_init(void *boot)
 {
 	/* Copy boot parameters first: the Launcher put the physical location
@@ -974,54 +974,68 @@ __init void lguest_init(void *boot)
 
 	/* We're under lguest, paravirt is enabled, and we're running at
 	 * privilege level 1, not 0 as normal. */
-	paravirt_ops.name = "lguest";
-	paravirt_ops.paravirt_enabled = 1;
-	paravirt_ops.kernel_rpl = 1;
+	pv_info.name = "lguest";
+	pv_info.paravirt_enabled = 1;
+	pv_info.kernel_rpl = 1;
 
 	/* We set up all the lguest overrides for sensitive operations.  These
 	 * are detailed with the operations themselves. */
-	paravirt_ops.save_fl = save_fl;
-	paravirt_ops.restore_fl = restore_fl;
-	paravirt_ops.irq_disable = irq_disable;
-	paravirt_ops.irq_enable = irq_enable;
-	paravirt_ops.load_gdt = lguest_load_gdt;
-	paravirt_ops.memory_setup = lguest_memory_setup;
-	paravirt_ops.cpuid = lguest_cpuid;
-	paravirt_ops.write_cr3 = lguest_write_cr3;
-	paravirt_ops.flush_tlb_user = lguest_flush_tlb_user;
-	paravirt_ops.flush_tlb_single = lguest_flush_tlb_single;
-	paravirt_ops.flush_tlb_kernel = lguest_flush_tlb_kernel;
-	paravirt_ops.set_pte = lguest_set_pte;
-	paravirt_ops.set_pte_at = lguest_set_pte_at;
-	paravirt_ops.set_pmd = lguest_set_pmd;
+
+	/* interrupt-related operations */
+	pv_irq_ops.init_IRQ = lguest_init_IRQ;
+	pv_irq_ops.save_fl = save_fl;
+	pv_irq_ops.restore_fl = restore_fl;
+	pv_irq_ops.irq_disable = irq_disable;
+	pv_irq_ops.irq_enable = irq_enable;
+	pv_irq_ops.safe_halt = lguest_safe_halt;
+
+	/* init-time operations */
+	pv_init_ops.memory_setup = lguest_memory_setup;
+	pv_init_ops.patch = lguest_patch;
+
+	/* Intercepts of various cpu instructions */
+	pv_cpu_ops.load_gdt = lguest_load_gdt;
+	pv_cpu_ops.cpuid = lguest_cpuid;
+	pv_cpu_ops.load_idt = lguest_load_idt;
+	pv_cpu_ops.iret = lguest_iret;
+	pv_cpu_ops.load_esp0 = lguest_load_esp0;
+	pv_cpu_ops.load_tr_desc = lguest_load_tr_desc;
+	pv_cpu_ops.set_ldt = lguest_set_ldt;
+	pv_cpu_ops.load_tls = lguest_load_tls;
+	pv_cpu_ops.set_debugreg = lguest_set_debugreg;
+	pv_cpu_ops.clts = lguest_clts;
+	pv_cpu_ops.read_cr0 = lguest_read_cr0;
+	pv_cpu_ops.write_cr0 = lguest_write_cr0;
+	pv_cpu_ops.read_cr4 = lguest_read_cr4;
+	pv_cpu_ops.write_cr4 = lguest_write_cr4;
+	pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
+	pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
+	pv_cpu_ops.wbinvd = lguest_wbinvd;
+
+	/* pagetable management */
+	pv_mmu_ops.write_cr3 = lguest_write_cr3;
+	pv_mmu_ops.flush_tlb_user = lguest_flush_tlb_user;
+	pv_mmu_ops.flush_tlb_single = lguest_flush_tlb_single;
+	pv_mmu_ops.flush_tlb_kernel = lguest_flush_tlb_kernel;
+	pv_mmu_ops.set_pte = lguest_set_pte;
+	pv_mmu_ops.set_pte_at = lguest_set_pte_at;
+	pv_mmu_ops.set_pmd = lguest_set_pmd;
+	pv_mmu_ops.read_cr2 = lguest_read_cr2;
+	pv_mmu_ops.read_cr3 = lguest_read_cr3;
+
 #ifdef CONFIG_X86_LOCAL_APIC
-	paravirt_ops.apic_write = lguest_apic_write;
-	paravirt_ops.apic_write_atomic = lguest_apic_write;
-	paravirt_ops.apic_read = lguest_apic_read;
+	/* apic read/write intercepts */
+	pv_apic_ops.apic_write = lguest_apic_write;
+	pv_apic_ops.apic_write_atomic = lguest_apic_write;
+	pv_apic_ops.apic_read = lguest_apic_read;
 #endif
-	paravirt_ops.load_idt = lguest_load_idt;
-	paravirt_ops.iret = lguest_iret;
-	paravirt_ops.load_esp0 = lguest_load_esp0;
-	paravirt_ops.load_tr_desc = lguest_load_tr_desc;
-	paravirt_ops.set_ldt = lguest_set_ldt;
-	paravirt_ops.load_tls = lguest_load_tls;
-	paravirt_ops.set_debugreg = lguest_set_debugreg;
-	paravirt_ops.clts = lguest_clts;
-	paravirt_ops.read_cr0 = lguest_read_cr0;
-	paravirt_ops.write_cr0 = lguest_write_cr0;
-	paravirt_ops.init_IRQ = lguest_init_IRQ;
-	paravirt_ops.read_cr2 = lguest_read_cr2;
-	paravirt_ops.read_cr3 = lguest_read_cr3;
-	paravirt_ops.read_cr4 = lguest_read_cr4;
-	paravirt_ops.write_cr4 = lguest_write_cr4;
-	paravirt_ops.write_gdt_entry = lguest_write_gdt_entry;
-	paravirt_ops.write_idt_entry = lguest_write_idt_entry;
-	paravirt_ops.patch = lguest_patch;
-	paravirt_ops.safe_halt = lguest_safe_halt;
-	paravirt_ops.get_wallclock = lguest_get_wallclock;
-	paravirt_ops.time_init = lguest_time_init;
-	paravirt_ops.set_lazy_mode = lguest_lazy_mode;
-	paravirt_ops.wbinvd = lguest_wbinvd;
+
+	/* time operations */
+	pv_time_ops.get_wallclock = lguest_get_wallclock;
+	pv_time_ops.time_init = lguest_time_init;
+
+	pv_misc_ops.set_lazy_mode = lguest_lazy_mode;
+
 	/* Now is a good time to look at the implementations of these functions
 	 * before returning to the rest of lguest_init(). */
 

drivers/lguest/lguest_bus.c

@@ -201,7 +201,7 @@ static void scan_devices(void)
  * "struct lguest_device_desc" array. */
 static int __init lguest_bus_init(void)
 {
-	if (strcmp(paravirt_ops.name, "lguest") != 0)
+	if (strcmp(pv_info.name, "lguest") != 0)
 		return 0;
 
 	/* Devices are in a single page above top of "normal" mem */

include/asm-x86/pgtable-3level-defs.h

@@ -2,7 +2,7 @@
 #define _I386_PGTABLE_3LEVEL_DEFS_H
 
 #ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD	(paravirt_ops.shared_kernel_pmd)
+#define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
 #else
 #define SHARED_KERNEL_PMD	1
 #endif