summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/paravirt.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--arch/x86/kernel/paravirt.c483
1 files changed, 483 insertions, 0 deletions
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
new file mode 100644
index 000000000..8dc69d825
--- /dev/null
+++ b/arch/x86/kernel/paravirt.c
@@ -0,0 +1,483 @@
+/* Paravirtualization interfaces
+ Copyright (C) 2006 Rusty Russell IBM Corporation
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
+ 2007 - x86_64 support added by Glauber de Oliveira Costa, Red Hat Inc
+*/
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/efi.h>
+#include <linux/bcd.h>
+#include <linux/highmem.h>
+#include <linux/kprobes.h>
+
+#include <asm/bug.h>
+#include <asm/paravirt.h>
+#include <asm/debugreg.h>
+#include <asm/desc.h>
+#include <asm/setup.h>
+#include <asm/pgtable.h>
+#include <asm/time.h>
+#include <asm/pgalloc.h>
+#include <asm/irq.h>
+#include <asm/delay.h>
+#include <asm/fixmap.h>
+#include <asm/apic.h>
+#include <asm/tlbflush.h>
+#include <asm/timer.h>
+#include <asm/special_insns.h>
+#include <asm/tlb.h>
+
+/*
+ * nop stub, which must not clobber anything *including the stack* to
+ * avoid confusing the entry prologues.
+ */
+extern void _paravirt_nop(void);
+asm (".pushsection .entry.text, \"ax\"\n"
+ ".global _paravirt_nop\n"
+ "_paravirt_nop:\n\t"
+ "ret\n\t"
+ ".size _paravirt_nop, . - _paravirt_nop\n\t"
+ ".type _paravirt_nop, @function\n\t"
+ ".popsection");
+
+/* identity function, which can be inlined */
+u32 notrace _paravirt_ident_32(u32 x)
+{
+ return x;
+}
+
+u64 notrace _paravirt_ident_64(u64 x)
+{
+ return x;
+}
+
+void __init default_banner(void)
+{
+ printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
+ pv_info.name);
+}
+
+/* Undefined instruction for dealing with missing ops pointers. */
+static const unsigned char ud2a[] = { 0x0f, 0x0b };
+
+struct branch {
+ unsigned char opcode;
+ u32 delta;
+} __attribute__((packed));
+
+unsigned paravirt_patch_call(void *insnbuf,
+ const void *target, u16 tgt_clobbers,
+ unsigned long addr, u16 site_clobbers,
+ unsigned len)
+{
+ struct branch *b = insnbuf;
+ unsigned long delta = (unsigned long)target - (addr+5);
+
+ if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+ WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr);
+#endif
+ return len; /* call too long for patch site */
+ }
+
+ b->opcode = 0xe8; /* call */
+ b->delta = delta;
+ BUILD_BUG_ON(sizeof(*b) != 5);
+
+ return 5;
+}
+
+unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
+ unsigned long addr, unsigned len)
+{
+ struct branch *b = insnbuf;
+ unsigned long delta = (unsigned long)target - (addr+5);
+
+ if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+ WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
+#endif
+ return len; /* call too long for patch site */
+ }
+
+ b->opcode = 0xe9; /* jmp */
+ b->delta = delta;
+
+ return 5;
+}
+
+DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
+
+void __init native_pv_lock_init(void)
+{
+ if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ 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, u16 clobbers, void *insnbuf,
+ unsigned long addr, unsigned len)
+{
+ 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, ud2a, ud2a+sizeof(ud2a));
+ else if (opfunc == _paravirt_nop)
+ ret = 0;
+
+ /* 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.usergs_sysret64))
+ /* If operation requires a jmp, then jmp */
+ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
+ else
+ /* Otherwise call the function; assume target could
+ clobber any caller-save reg */
+ ret = paravirt_patch_call(insnbuf, opfunc, CLBR_ANY,
+ addr, clobbers, len);
+
+ return ret;
+}
+
+unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
+ const char *start, const char *end)
+{
+ unsigned insn_len = end - start;
+
+ if (insn_len > len || start == NULL)
+ insn_len = len;
+ else
+ memcpy(insnbuf, start, insn_len);
+
+ return insn_len;
+}
+
+static void native_flush_tlb(void)
+{
+ __native_flush_tlb();
+}
+
+/*
+ * Global pages have to be flushed a bit differently. Not a real
+ * performance problem because this does not happen often.
+ */
+static void native_flush_tlb_global(void)
+{
+ __native_flush_tlb_global();
+}
+
+static void native_flush_tlb_one_user(unsigned long addr)
+{
+ __native_flush_tlb_one_user(addr);
+}
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+ return 0;
+}
+
+/* These are in entry.S */
+extern void native_iret(void);
+extern void native_usergs_sysret64(void);
+
+static struct resource reserve_ioports = {
+ .start = 0,
+ .end = IO_SPACE_LIMIT,
+ .name = "paravirt-ioport",
+ .flags = IORESOURCE_IO | IORESOURCE_BUSY,
+};
+
+/*
+ * Reserve the whole legacy IO space to prevent any legacy drivers
+ * from wasting time probing for their hardware. This is a fairly
+ * brute-force approach to disabling all non-virtual drivers.
+ *
+ * Note that this must be called very early to have any effect.
+ */
+int paravirt_disable_iospace(void)
+{
+ return request_resource(&ioport_resource, &reserve_ioports);
+}
+
+static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+
+static inline void enter_lazy(enum paravirt_lazy_mode mode)
+{
+ BUG_ON(this_cpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
+
+ this_cpu_write(paravirt_lazy_mode, mode);
+}
+
+static void leave_lazy(enum paravirt_lazy_mode mode)
+{
+ BUG_ON(this_cpu_read(paravirt_lazy_mode) != mode);
+
+ this_cpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
+}
+
+void paravirt_enter_lazy_mmu(void)
+{
+ enter_lazy(PARAVIRT_LAZY_MMU);
+}
+
+void paravirt_leave_lazy_mmu(void)
+{
+ leave_lazy(PARAVIRT_LAZY_MMU);
+}
+
+void paravirt_flush_lazy_mmu(void)
+{
+ preempt_disable();
+
+ if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+ arch_leave_lazy_mmu_mode();
+ arch_enter_lazy_mmu_mode();
+ }
+
+ preempt_enable();
+}
+
+void paravirt_start_context_switch(struct task_struct *prev)
+{
+ BUG_ON(preemptible());
+
+ if (this_cpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+ arch_leave_lazy_mmu_mode();
+ set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+ }
+ enter_lazy(PARAVIRT_LAZY_CPU);
+}
+
+void paravirt_end_context_switch(struct task_struct *next)
+{
+ BUG_ON(preemptible());
+
+ leave_lazy(PARAVIRT_LAZY_CPU);
+
+ if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+ arch_enter_lazy_mmu_mode();
+}
+
+enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
+{
+ if (in_interrupt())
+ return PARAVIRT_LAZY_NONE;
+
+ return this_cpu_read(paravirt_lazy_mode);
+}
+
+struct pv_info pv_info = {
+ .name = "bare hardware",
+ .kernel_rpl = 0,
+ .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
+
+#ifdef CONFIG_X86_64
+ .extra_user_64bit_cs = __USER_CS,
+#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)
+#else
+/* 64-bit pagetable entries */
+#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
+#endif
+
+struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
+
+ .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_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,
+
+ .pgd_alloc = __paravirt_pgd_alloc,
+ .pgd_free = 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,
+
+ .set_pte = native_set_pte,
+ .set_pte_at = native_set_pte_at,
+ .set_pmd = native_set_pmd,
+
+ .ptep_modify_prot_start = __ptep_modify_prot_start,
+ .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,
+#endif
+ .set_pud = native_set_pud,
+
+ .pmd_val = PTE_IDENT,
+ .make_pmd = PTE_IDENT,
+
+#if CONFIG_PGTABLE_LEVELS >= 4
+ .pud_val = PTE_IDENT,
+ .make_pud = PTE_IDENT,
+
+ .set_p4d = native_set_p4d,
+
+#if CONFIG_PGTABLE_LEVELS >= 5
+ .p4d_val = PTE_IDENT,
+ .make_p4d = PTE_IDENT,
+
+ .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,
+
+ .make_pte = PTE_IDENT,
+ .make_pgd = PTE_IDENT,
+
+ .dup_mmap = paravirt_nop,
+ .exit_mmap = paravirt_nop,
+ .activate_mm = paravirt_nop,
+
+ .lazy_mode = {
+ .enter = paravirt_nop,
+ .leave = paravirt_nop,
+ .flush = paravirt_nop,
+ },
+
+ .set_fixmap = native_set_fixmap,
+};
+
+EXPORT_SYMBOL_GPL(pv_time_ops);
+EXPORT_SYMBOL (pv_cpu_ops);
+EXPORT_SYMBOL (pv_mmu_ops);
+EXPORT_SYMBOL_GPL(pv_info);
+EXPORT_SYMBOL (pv_irq_ops);