x86/paravirt: Use a single ops structure
Instead of using six globally visible paravirt ops structures combine
them in a single structure, keeping the original structures as
sub-structures.
This avoids the need to assemble struct paravirt_patch_template at
runtime on the stack each time apply_paravirt() is being called (i.e.
when loading a module).
[ tglx: Made the struct and the initializer tabular for readability sake ]
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: xen-devel@lists.xenproject.org
Cc: virtualization@lists.linux-foundation.org
Cc: akataria@vmware.com
Cc: rusty@rustcorp.com.au
Cc: boris.ostrovsky@oracle.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/20180828074026.820-9-jgross@suse.com
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 287d345..0ca0576 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -128,29 +128,14 @@ void __init native_pv_lock_init(void)
static_branch_disable(&virt_spin_lock_key);
}
-/*
- * 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_time_ops = pv_time_ops,
- .pv_cpu_ops = pv_cpu_ops,
- .pv_irq_ops = pv_irq_ops,
- .pv_mmu_ops = pv_mmu_ops,
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
- .pv_lock_ops = pv_lock_ops,
-#endif
- };
- return *((void **)&tmpl + type);
-}
-
unsigned paravirt_patch_default(u8 type, void *insnbuf,
unsigned long addr, unsigned len)
{
- void *opfunc = get_call_destination(type);
+ /*
+ * Neat trick to map patch type back to the call within the
+ * corresponding structure.
+ */
+ void *opfunc = *((void **)&pv_ops + type);
unsigned ret;
if (opfunc == NULL)
@@ -165,8 +150,8 @@ unsigned paravirt_patch_default(u8 type, void *insnbuf,
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.usergs_sysret64))
+ else if (type == PARAVIRT_PATCH(cpu.iret) ||
+ type == PARAVIRT_PATCH(cpu.usergs_sysret64))
/* If operation requires a jmp, then jmp */
ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
else
@@ -316,77 +301,6 @@ struct pv_info pv_info = {
#endif
};
-struct pv_init_ops pv_init_ops = {
- .patch = native_patch,
-};
-
-struct pv_time_ops pv_time_ops = {
- .sched_clock = native_sched_clock,
- .steal_clock = native_steal_clock,
-};
-
-__visible struct pv_irq_ops pv_irq_ops = {
- .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
- .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
- .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
- .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
- .safe_halt = native_safe_halt,
- .halt = native_halt,
-};
-
-__visible struct pv_cpu_ops pv_cpu_ops = {
- .cpuid = native_cpuid,
- .get_debugreg = native_get_debugreg,
- .set_debugreg = native_set_debugreg,
- .read_cr0 = native_read_cr0,
- .write_cr0 = native_write_cr0,
- .write_cr4 = native_write_cr4,
-#ifdef CONFIG_X86_64
- .read_cr8 = native_read_cr8,
- .write_cr8 = native_write_cr8,
-#endif
- .wbinvd = native_wbinvd,
- .read_msr = native_read_msr,
- .write_msr = native_write_msr,
- .read_msr_safe = native_read_msr_safe,
- .write_msr_safe = native_write_msr_safe,
- .read_pmc = native_read_pmc,
- .load_tr_desc = native_load_tr_desc,
- .set_ldt = native_set_ldt,
- .load_gdt = native_load_gdt,
- .load_idt = native_load_idt,
- .store_tr = native_store_tr,
- .load_tls = native_load_tls,
-#ifdef CONFIG_X86_64
- .load_gs_index = native_load_gs_index,
-#endif
- .write_ldt_entry = native_write_ldt_entry,
- .write_gdt_entry = native_write_gdt_entry,
- .write_idt_entry = native_write_idt_entry,
-
- .alloc_ldt = paravirt_nop,
- .free_ldt = paravirt_nop,
-
- .load_sp0 = native_load_sp0,
-
-#ifdef CONFIG_X86_64
- .usergs_sysret64 = native_usergs_sysret64,
-#endif
- .iret = native_iret,
- .swapgs = native_swapgs,
-
- .set_iopl_mask = native_set_iopl_mask,
- .io_delay = native_io_delay,
-
- .start_context_switch = paravirt_nop,
- .end_context_switch = paravirt_nop,
-};
-
-/* At this point, native_get/set_debugreg has real function entries */
-NOKPROBE_SYMBOL(native_get_debugreg);
-NOKPROBE_SYMBOL(native_set_debugreg);
-NOKPROBE_SYMBOL(native_load_idt);
-
#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE)
/* 32-bit pagetable entries */
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32)
@@ -395,85 +309,163 @@ NOKPROBE_SYMBOL(native_load_idt);
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
#endif
-struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
+struct paravirt_patch_template pv_ops = {
+ /* Init ops. */
+ .init.patch = native_patch,
- .read_cr2 = native_read_cr2,
- .write_cr2 = native_write_cr2,
- .read_cr3 = __native_read_cr3,
- .write_cr3 = native_write_cr3,
+ /* Time ops. */
+ .time.sched_clock = native_sched_clock,
+ .time.steal_clock = native_steal_clock,
- .flush_tlb_user = native_flush_tlb,
- .flush_tlb_kernel = native_flush_tlb_global,
- .flush_tlb_one_user = native_flush_tlb_one_user,
- .flush_tlb_others = native_flush_tlb_others,
- .tlb_remove_table = (void (*)(struct mmu_gather *, void *))tlb_remove_page,
+ /* Cpu ops. */
+ .cpu.cpuid = native_cpuid,
+ .cpu.get_debugreg = native_get_debugreg,
+ .cpu.set_debugreg = native_set_debugreg,
+ .cpu.read_cr0 = native_read_cr0,
+ .cpu.write_cr0 = native_write_cr0,
+ .cpu.write_cr4 = native_write_cr4,
+#ifdef CONFIG_X86_64
+ .cpu.read_cr8 = native_read_cr8,
+ .cpu.write_cr8 = native_write_cr8,
+#endif
+ .cpu.wbinvd = native_wbinvd,
+ .cpu.read_msr = native_read_msr,
+ .cpu.write_msr = native_write_msr,
+ .cpu.read_msr_safe = native_read_msr_safe,
+ .cpu.write_msr_safe = native_write_msr_safe,
+ .cpu.read_pmc = native_read_pmc,
+ .cpu.load_tr_desc = native_load_tr_desc,
+ .cpu.set_ldt = native_set_ldt,
+ .cpu.load_gdt = native_load_gdt,
+ .cpu.load_idt = native_load_idt,
+ .cpu.store_tr = native_store_tr,
+ .cpu.load_tls = native_load_tls,
+#ifdef CONFIG_X86_64
+ .cpu.load_gs_index = native_load_gs_index,
+#endif
+ .cpu.write_ldt_entry = native_write_ldt_entry,
+ .cpu.write_gdt_entry = native_write_gdt_entry,
+ .cpu.write_idt_entry = native_write_idt_entry,
- .pgd_alloc = __paravirt_pgd_alloc,
- .pgd_free = paravirt_nop,
+ .cpu.alloc_ldt = paravirt_nop,
+ .cpu.free_ldt = paravirt_nop,
- .alloc_pte = paravirt_nop,
- .alloc_pmd = paravirt_nop,
- .alloc_pud = paravirt_nop,
- .alloc_p4d = paravirt_nop,
- .release_pte = paravirt_nop,
- .release_pmd = paravirt_nop,
- .release_pud = paravirt_nop,
- .release_p4d = paravirt_nop,
+ .cpu.load_sp0 = native_load_sp0,
- .set_pte = native_set_pte,
- .set_pte_at = native_set_pte_at,
- .set_pmd = native_set_pmd,
+#ifdef CONFIG_X86_64
+ .cpu.usergs_sysret64 = native_usergs_sysret64,
+#endif
+ .cpu.iret = native_iret,
+ .cpu.swapgs = native_swapgs,
- .ptep_modify_prot_start = __ptep_modify_prot_start,
- .ptep_modify_prot_commit = __ptep_modify_prot_commit,
+ .cpu.set_iopl_mask = native_set_iopl_mask,
+ .cpu.io_delay = native_io_delay,
+
+ .cpu.start_context_switch = paravirt_nop,
+ .cpu.end_context_switch = paravirt_nop,
+
+ /* Irq ops. */
+ .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
+ .irq.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
+ .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
+ .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable),
+ .irq.safe_halt = native_safe_halt,
+ .irq.halt = native_halt,
+
+ /* Mmu ops. */
+ .mmu.read_cr2 = native_read_cr2,
+ .mmu.write_cr2 = native_write_cr2,
+ .mmu.read_cr3 = __native_read_cr3,
+ .mmu.write_cr3 = native_write_cr3,
+
+ .mmu.flush_tlb_user = native_flush_tlb,
+ .mmu.flush_tlb_kernel = native_flush_tlb_global,
+ .mmu.flush_tlb_one_user = native_flush_tlb_one_user,
+ .mmu.flush_tlb_others = native_flush_tlb_others,
+ .mmu.tlb_remove_table =
+ (void (*)(struct mmu_gather *, void *))tlb_remove_page,
+
+ .mmu.pgd_alloc = __paravirt_pgd_alloc,
+ .mmu.pgd_free = paravirt_nop,
+
+ .mmu.alloc_pte = paravirt_nop,
+ .mmu.alloc_pmd = paravirt_nop,
+ .mmu.alloc_pud = paravirt_nop,
+ .mmu.alloc_p4d = paravirt_nop,
+ .mmu.release_pte = paravirt_nop,
+ .mmu.release_pmd = paravirt_nop,
+ .mmu.release_pud = paravirt_nop,
+ .mmu.release_p4d = paravirt_nop,
+
+ .mmu.set_pte = native_set_pte,
+ .mmu.set_pte_at = native_set_pte_at,
+ .mmu.set_pmd = native_set_pmd,
+
+ .mmu.ptep_modify_prot_start = __ptep_modify_prot_start,
+ .mmu.ptep_modify_prot_commit = __ptep_modify_prot_commit,
#if CONFIG_PGTABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
- .set_pte_atomic = native_set_pte_atomic,
- .pte_clear = native_pte_clear,
- .pmd_clear = native_pmd_clear,
+ .mmu.set_pte_atomic = native_set_pte_atomic,
+ .mmu.pte_clear = native_pte_clear,
+ .mmu.pmd_clear = native_pmd_clear,
#endif
- .set_pud = native_set_pud,
+ .mmu.set_pud = native_set_pud,
- .pmd_val = PTE_IDENT,
- .make_pmd = PTE_IDENT,
+ .mmu.pmd_val = PTE_IDENT,
+ .mmu.make_pmd = PTE_IDENT,
#if CONFIG_PGTABLE_LEVELS >= 4
- .pud_val = PTE_IDENT,
- .make_pud = PTE_IDENT,
+ .mmu.pud_val = PTE_IDENT,
+ .mmu.make_pud = PTE_IDENT,
- .set_p4d = native_set_p4d,
+ .mmu.set_p4d = native_set_p4d,
#if CONFIG_PGTABLE_LEVELS >= 5
- .p4d_val = PTE_IDENT,
- .make_p4d = PTE_IDENT,
+ .mmu.p4d_val = PTE_IDENT,
+ .mmu.make_p4d = PTE_IDENT,
- .set_pgd = native_set_pgd,
+ .mmu.set_pgd = native_set_pgd,
#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
#endif /* CONFIG_PGTABLE_LEVELS >= 4 */
#endif /* CONFIG_PGTABLE_LEVELS >= 3 */
- .pte_val = PTE_IDENT,
- .pgd_val = PTE_IDENT,
+ .mmu.pte_val = PTE_IDENT,
+ .mmu.pgd_val = PTE_IDENT,
- .make_pte = PTE_IDENT,
- .make_pgd = PTE_IDENT,
+ .mmu.make_pte = PTE_IDENT,
+ .mmu.make_pgd = PTE_IDENT,
- .dup_mmap = paravirt_nop,
- .exit_mmap = paravirt_nop,
- .activate_mm = paravirt_nop,
+ .mmu.dup_mmap = paravirt_nop,
+ .mmu.exit_mmap = paravirt_nop,
+ .mmu.activate_mm = paravirt_nop,
- .lazy_mode = {
- .enter = paravirt_nop,
- .leave = paravirt_nop,
- .flush = paravirt_nop,
+ .mmu.lazy_mode = {
+ .enter = paravirt_nop,
+ .leave = paravirt_nop,
+ .flush = paravirt_nop,
},
- .set_fixmap = native_set_fixmap,
+ .mmu.set_fixmap = native_set_fixmap,
+
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
+ /* Lock ops. */
+#ifdef CONFIG_SMP
+ .lock.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+ .lock.queued_spin_unlock =
+ PV_CALLEE_SAVE(__native_queued_spin_unlock),
+ .lock.wait = paravirt_nop,
+ .lock.kick = paravirt_nop,
+ .lock.vcpu_is_preempted =
+ PV_CALLEE_SAVE(__native_vcpu_is_preempted),
+#endif /* SMP */
+#endif
};
-EXPORT_SYMBOL_GPL(pv_time_ops);
-EXPORT_SYMBOL (pv_cpu_ops);
-EXPORT_SYMBOL (pv_mmu_ops);
+/* At this point, native_get/set_debugreg has real function entries */
+NOKPROBE_SYMBOL(native_get_debugreg);
+NOKPROBE_SYMBOL(native_set_debugreg);
+NOKPROBE_SYMBOL(native_load_idt);
+
+EXPORT_SYMBOL_GPL(pv_ops);
EXPORT_SYMBOL_GPL(pv_info);
-EXPORT_SYMBOL (pv_irq_ops);