#ifndef __ASSEMBLY__
#include <linux/types.h>
+#include <linux/cpumask.h>
+#include <asm/kmap_types.h>
+struct page;
struct thread_struct;
struct Xgt_desc_struct;
struct tss_struct;
struct mm_struct;
struct desc_struct;
+
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+ PARAVIRT_LAZY_NONE = 0,
+ PARAVIRT_LAZY_MMU = 1,
+ PARAVIRT_LAZY_CPU = 2,
+ PARAVIRT_LAZY_FLUSH = 3,
+};
+
struct paravirt_ops
{
unsigned int kernel_rpl;
*/
unsigned (*patch)(u8 type, u16 clobber, void *firstinsn, unsigned len);
+ /* Basic arch-specific setup */
void (*arch_setup)(void);
char *(*memory_setup)(void);
void (*init_IRQ)(void);
+ void (*time_init)(void);
+ /*
+ * Called before/after init_mm pagetable setup. setup_start
+ * may reset %cr3, and may pre-install parts of the pagetable;
+ * pagetable setup is expected to preserve any existing
+ * mapping.
+ */
void (*pagetable_setup_start)(pgd_t *pgd_base);
void (*pagetable_setup_done)(pgd_t *pgd_base);
+ /* Print a banner to identify the environment */
void (*banner)(void);
+ /* Set and set time of day */
unsigned long (*get_wallclock)(void);
int (*set_wallclock)(unsigned long);
- void (*time_init)(void);
+ /* cpuid emulation, mostly so that caps bits can be disabled */
void (*cpuid)(unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx);
+ /* hooks for various privileged instructions */
unsigned long (*get_debugreg)(int regno);
void (*set_debugreg)(int regno, unsigned long value);
unsigned long (*read_cr4)(void);
void (*write_cr4)(unsigned long);
+ /*
+ * Get/set interrupt state. save_fl and restore_fl are only
+ * expected to use X86_EFLAGS_IF; all other bits
+ * returned from save_fl are undefined, and may be ignored by
+ * restore_fl.
+ */
unsigned long (*save_fl)(void);
void (*restore_fl)(unsigned long);
void (*irq_disable)(void);
void (*irq_enable)(void);
void (*safe_halt)(void);
void (*halt)(void);
+
void (*wbinvd)(void);
- /* err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */
+ /* MSR, PMC and TSR operations.
+ err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */
u64 (*read_msr)(unsigned int msr, int *err);
int (*write_msr)(unsigned int msr, u64 val);
u64 (*get_scheduled_cycles)(void);
unsigned long (*get_cpu_khz)(void);
+ /* Segment descriptor handling */
void (*load_tr_desc)(void);
void (*load_gdt)(const struct Xgt_desc_struct *);
void (*load_idt)(const struct Xgt_desc_struct *);
void (*load_esp0)(struct tss_struct *tss, struct thread_struct *t);
void (*set_iopl_mask)(unsigned mask);
-
void (*io_delay)(void);
+ /*
+ * Hooks for intercepting the creation/use/destruction of an
+ * mm_struct.
+ */
void (*activate_mm)(struct mm_struct *prev,
struct mm_struct *next);
void (*dup_mmap)(struct mm_struct *oldmm,
void (*exit_mmap)(struct mm_struct *mm);
#ifdef CONFIG_X86_LOCAL_APIC
+ /*
+ * Direct APIC operations, principally for VMI. Ideally
+ * these shouldn't be in this interface.
+ */
void (*apic_write)(unsigned long reg, unsigned long v);
void (*apic_write_atomic)(unsigned long reg, unsigned long v);
unsigned long (*apic_read)(unsigned long reg);
void (*setup_boot_clock)(void);
void (*setup_secondary_clock)(void);
+
+ void (*startup_ipi_hook)(int phys_apicid,
+ unsigned long start_eip,
+ unsigned long start_esp);
#endif
+ /* TLB operations */
void (*flush_tlb_user)(void);
void (*flush_tlb_kernel)(void);
void (*flush_tlb_single)(unsigned long addr);
+ void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
+ unsigned long va);
- void (*map_pt_hook)(int type, pte_t *va, u32 pfn);
-
+ /* Hooks for allocating/releasing pagetable pages */
void (*alloc_pt)(u32 pfn);
void (*alloc_pd)(u32 pfn);
void (*alloc_pd_clone)(u32 pfn, u32 clonepfn, u32 start, u32 count);
void (*release_pt)(u32 pfn);
void (*release_pd)(u32 pfn);
+ /* Pagetable manipulation functions */
void (*set_pte)(pte_t *ptep, pte_t pteval);
- void (*set_pte_at)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval);
+ void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pteval);
void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
- void (*pte_update_defer)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+ void (*pte_update_defer)(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep);
- pte_t (*ptep_get_and_clear)(pte_t *ptep);
+#ifdef CONFIG_HIGHPTE
+ void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
+#endif
#ifdef CONFIG_X86_PAE
void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
pgd_t (*make_pgd)(unsigned long pgd);
#endif
- void (*set_lazy_mode)(int mode);
+ /* Set deferred update mode, used for batching operations. */
+ void (*set_lazy_mode)(enum paravirt_lazy_mode mode);
/* These two are jmp to, not actually called. */
void (*irq_enable_sysexit)(void);
void (*iret)(void);
-
- void (*startup_ipi_hook)(int phys_apicid, unsigned long start_eip, unsigned long start_esp);
};
/* Mark a paravirt probe function. */
#define paravirt_clobber(clobber) \
[paravirt_clobber] "i" (clobber)
-#define PARAVIRT_CALL "call *(paravirt_ops+%c[paravirt_typenum]*4);"
-
+/*
+ * Generate some code, and mark it as patchable by the
+ * apply_paravirt() alternate instruction patcher.
+ */
#define _paravirt_alt(insn_string, type, clobber) \
"771:\n\t" insn_string "\n" "772:\n" \
".pushsection .parainstructions,\"a\"\n" \
" .short " clobber "\n" \
".popsection\n"
+/* Generate patchable code, with the default asm parameters. */
#define paravirt_alt(insn_string) \
_paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
-#define PVOP_CALL0(__rettype, __op) \
- ({ \
- __rettype __ret; \
- if (sizeof(__rettype) > sizeof(unsigned long)) { \
- unsigned long long __tmp; \
- unsigned long __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=A" (__tmp), "=c" (__ecx) \
- : paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } else { \
- unsigned long __tmp, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__tmp), "=d" (__edx), \
- "=c" (__ecx) \
- : paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } \
- __ret; \
- })
-#define PVOP_VCALL0(__op) \
- ({ \
- unsigned long __eax, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__eax), "=d" (__edx), "=c" (__ecx) \
- : paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- })
+unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ignore(unsigned len);
+unsigned paravirt_patch_call(void *target, u16 tgt_clobbers,
+ void *site, u16 site_clobbers,
+ unsigned len);
+unsigned paravirt_patch_jmp(void *target, void *site, unsigned len);
+unsigned paravirt_patch_default(u8 type, u16 clobbers, void *site, unsigned len);
-#define PVOP_CALL1(__rettype, __op, arg1) \
- ({ \
- __rettype __ret; \
- if (sizeof(__rettype) > sizeof(unsigned long)) { \
- unsigned long long __tmp; \
- unsigned long __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=A" (__tmp), "=c" (__ecx) \
- : "a" ((u32)(arg1)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } else { \
- unsigned long __tmp, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__tmp), "=d" (__edx), \
- "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } \
- __ret; \
- })
-#define PVOP_VCALL1(__op, arg1) \
- ({ \
- unsigned long __eax, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__eax), "=d" (__edx), "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- })
+unsigned paravirt_patch_insns(void *site, unsigned len,
+ const char *start, const char *end);
-#define PVOP_CALL2(__rettype, __op, arg1, arg2) \
- ({ \
- __rettype __ret; \
- if (sizeof(__rettype) > sizeof(unsigned long)) { \
- unsigned long long __tmp; \
- unsigned long __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=A" (__tmp), "=c" (__ecx) \
- : "a" ((u32)(arg1)), \
- "d" ((u32)(arg2)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } else { \
- unsigned long __tmp, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__tmp), "=d" (__edx), \
- "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- "1" ((u32)(arg2)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } \
- __ret; \
- })
-#define PVOP_VCALL2(__op, arg1, arg2) \
- ({ \
- unsigned long __eax, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__eax), "=d" (__edx), "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- "1" ((u32)(arg2)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- })
-#define PVOP_CALL3(__rettype, __op, arg1, arg2, arg3) \
- ({ \
- __rettype __ret; \
- if (sizeof(__rettype) > sizeof(unsigned long)) { \
- unsigned long long __tmp; \
- unsigned long __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=A" (__tmp), "=c" (__ecx) \
- : "a" ((u32)(arg1)), \
- "d" ((u32)(arg2)), \
- "1" ((u32)(arg3)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } else { \
- unsigned long __tmp, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__tmp), "=d" (__edx), \
- "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- __ret = (__rettype)__tmp; \
- } \
- __ret; \
- })
-#define PVOP_VCALL3(__op, arg1, arg2, arg3) \
- ({ \
- unsigned long __eax, __edx, __ecx; \
- asm volatile(paravirt_alt(PARAVIRT_CALL) \
- : "=a" (__eax), "=d" (__edx), "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc"); \
- })
+/*
+ * This generates an indirect call based on the operation type number.
+ * The type number, computed in PARAVIRT_PATCH, is derived from the
+ * offset into the paravirt_ops structure, and can therefore be freely
+ * converted back into a structure offset.
+ */
+#define PARAVIRT_CALL "call *(paravirt_ops+%c[paravirt_typenum]*4);"
-#define PVOP_CALL4(__rettype, __op, arg1, arg2, arg3, arg4) \
+/*
+ * These macros are intended to wrap calls into a paravirt_ops
+ * operation, so that they can be later identified and patched at
+ * runtime.
+ *
+ * Normally, a call to a pv_op function is a simple indirect call:
+ * (paravirt_ops.operations)(args...).
+ *
+ * Unfortunately, this is a relatively slow operation for modern CPUs,
+ * because it cannot necessarily determine what the destination
+ * address is. In this case, the address is a runtime constant, so at
+ * the very least we can patch the call to e a simple direct call, or
+ * ideally, patch an inline implementation into the callsite. (Direct
+ * calls are essentially free, because the call and return addresses
+ * are completely predictable.)
+ *
+ * These macros rely on the standard gcc "regparm(3)" calling
+ * convention, in which the first three arguments are placed in %eax,
+ * %edx, %ecx (in that order), and the remaining arguments are placed
+ * on the stack. All caller-save registers (eax,edx,ecx) are expected
+ * to be modified (either clobbered or used for return values).
+ *
+ * The call instruction itself is marked by placing its start address
+ * and size into the .parainstructions section, so that
+ * apply_paravirt() in arch/i386/kernel/alternative.c can do the
+ * appropriate patching under the control of the backend paravirt_ops
+ * implementation.
+ *
+ * Unfortunately there's no way to get gcc to generate the args setup
+ * for the call, and then allow the call itself to be generated by an
+ * inline asm. Because of this, we must do the complete arg setup and
+ * return value handling from within these macros. This is fairly
+ * cumbersome.
+ *
+ * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
+ * It could be extended to more arguments, but there would be little
+ * to be gained from that. For each number of arguments, there are
+ * the two VCALL and CALL variants for void and non-void functions.
+ *
+ * When there is a return value, the invoker of the macro must specify
+ * the return type. The macro then uses sizeof() on that type to
+ * determine whether its a 32 or 64 bit value, and places the return
+ * in the right register(s) (just %eax for 32-bit, and %edx:%eax for
+ * 64-bit).
+ *
+ * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
+ * in low,high order.
+ *
+ * Small structures are passed and returned in registers. The macro
+ * calling convention can't directly deal with this, so the wrapper
+ * functions must do this.
+ *
+ * These PVOP_* macros are only defined within this header. This
+ * means that all uses must be wrapped in inline functions. This also
+ * makes sure the incoming and outgoing types are always correct.
+ */
+#define __PVOP_CALL(rettype, op, pre, post, ...) \
({ \
- __rettype __ret; \
- if (sizeof(__rettype) > sizeof(unsigned long)) { \
- unsigned long long __tmp; \
- unsigned long __ecx; \
- asm volatile("push %[_arg4]; " \
+ rettype __ret; \
+ unsigned long __eax, __edx, __ecx; \
+ if (sizeof(rettype) > sizeof(unsigned long)) { \
+ asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
- "lea 4(%%esp),%%esp" \
- : "=A" (__tmp), "=c" (__ecx) \
- : "a" ((u32)(arg1)), \
- "d" ((u32)(arg2)), \
- "1" ((u32)(arg3)), \
- [_arg4] "mr" ((u32)(arg4)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
- : "memory", "cc",); \
- __ret = (__rettype)__tmp; \
+ post \
+ : "=a" (__eax), "=d" (__edx), \
+ "=c" (__ecx) \
+ : paravirt_type(op), \
+ paravirt_clobber(CLBR_ANY), \
+ ##__VA_ARGS__ \
+ : "memory", "cc"); \
+ __ret = (rettype)((((u64)__edx) << 32) | __eax); \
} else { \
- unsigned long __tmp, __edx, __ecx; \
- asm volatile("push %[_arg4]; " \
+ asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
- "lea 4(%%esp),%%esp" \
- : "=a" (__tmp), "=d" (__edx), "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), \
- [_arg4]"mr" ((u32)(arg4)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
+ post \
+ : "=a" (__eax), "=d" (__edx), \
+ "=c" (__ecx) \
+ : paravirt_type(op), \
+ paravirt_clobber(CLBR_ANY), \
+ ##__VA_ARGS__ \
: "memory", "cc"); \
- __ret = (__rettype)__tmp; \
+ __ret = (rettype)__eax; \
} \
__ret; \
})
-#define PVOP_VCALL4(__op, arg1, arg2, arg3, arg4) \
+#define __PVOP_VCALL(op, pre, post, ...) \
({ \
unsigned long __eax, __edx, __ecx; \
- asm volatile("push %[_arg4]; " \
+ asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
- "lea 4(%%esp),%%esp" \
+ post \
: "=a" (__eax), "=d" (__edx), "=c" (__ecx) \
- : "0" ((u32)(arg1)), \
- "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), \
- [_arg4]"mr" ((u32)(arg4)), \
- paravirt_type(__op), \
- paravirt_clobber(CLBR_ANY) \
+ : paravirt_type(op), \
+ paravirt_clobber(CLBR_ANY), \
+ ##__VA_ARGS__ \
: "memory", "cc"); \
})
+#define PVOP_CALL0(rettype, op) \
+ __PVOP_CALL(rettype, op, "", "")
+#define PVOP_VCALL0(op) \
+ __PVOP_VCALL(op, "", "")
+
+#define PVOP_CALL1(rettype, op, arg1) \
+ __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)))
+#define PVOP_VCALL1(op, arg1) \
+ __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)))
+
+#define PVOP_CALL2(rettype, op, arg1, arg2) \
+ __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)), "1" ((u32)(arg2)))
+#define PVOP_VCALL2(op, arg1, arg2) \
+ __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)), "1" ((u32)(arg2)))
+
+#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \
+ __PVOP_CALL(rettype, op, "", "", "0" ((u32)(arg1)), \
+ "1"((u32)(arg2)), "2"((u32)(arg3)))
+#define PVOP_VCALL3(op, arg1, arg2, arg3) \
+ __PVOP_VCALL(op, "", "", "0" ((u32)(arg1)), "1"((u32)(arg2)), \
+ "2"((u32)(arg3)))
+
+#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
+ __PVOP_CALL(rettype, op, \
+ "push %[_arg4];", "lea 4(%%esp),%%esp;", \
+ "0" ((u32)(arg1)), "1" ((u32)(arg2)), \
+ "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
+ __PVOP_VCALL(op, \
+ "push %[_arg4];", "lea 4(%%esp),%%esp;", \
+ "0" ((u32)(arg1)), "1" ((u32)(arg2)), \
+ "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+
static inline int paravirt_enabled(void)
{
return paravirt_ops.paravirt_enabled;
PVOP_VCALL1(flush_tlb_single, addr);
}
-static inline void paravirt_map_pt_hook(int type, pte_t *va, u32 pfn)
+static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+ unsigned long va)
{
- PVOP_VCALL3(map_pt_hook, type, va, pfn);
+ PVOP_VCALL3(flush_tlb_others, &cpumask, mm, va);
}
static inline void paravirt_alloc_pt(unsigned pfn)
PVOP_VCALL1(release_pd, pfn);
}
+#ifdef CONFIG_HIGHPTE
+static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
+{
+ unsigned long ret;
+ ret = PVOP_CALL2(unsigned long, kmap_atomic_pte, page, type);
+ return (void *)ret;
+}
+#endif
+
static inline void pte_update(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
PVOP_VCALL1(pmd_clear, pmdp);
}
-static inline pte_t raw_ptep_get_and_clear(pte_t *p)
-{
- unsigned long long val = PVOP_CALL1(unsigned long long, ptep_get_and_clear, p);
- return (pte_t) { val, val >> 32 };
-}
#else /* !CONFIG_X86_PAE */
+
static inline pte_t __pte(unsigned long val)
{
return (pte_t) { PVOP_CALL1(unsigned long, make_pte, val) };
{
PVOP_VCALL2(set_pmd, pmdp, pmdval.pud.pgd.pgd);
}
-
-static inline pte_t raw_ptep_get_and_clear(pte_t *p)
-{
- return (pte_t) { PVOP_CALL1(unsigned long, ptep_get_and_clear, p) };
-}
#endif /* CONFIG_X86_PAE */
-/* Lazy mode for batching updates / context switch */
-#define PARAVIRT_LAZY_NONE 0
-#define PARAVIRT_LAZY_MMU 1
-#define PARAVIRT_LAZY_CPU 2
-#define PARAVIRT_LAZY_FLUSH 3
-
#define __HAVE_ARCH_ENTER_LAZY_CPU_MODE
static inline void arch_enter_lazy_cpu_mode(void)
{
[paravirt_sti_type] "i" (PARAVIRT_PATCH(irq_enable)), \
paravirt_clobber(CLBR_EAX)
+/* Make sure as little as possible of this mess escapes. */
#undef PARAVIRT_CALL
+#undef __PVOP_CALL
+#undef __PVOP_VCALL
#undef PVOP_VCALL0
#undef PVOP_CALL0
#undef PVOP_VCALL1
projects / powerpc.git / blobdiff