the original assembly code: > 3: movl $-14,%eax
and linked in vmlinux : > c0199ff5 <.fixup+10b5> movl $0xfffffff2,%eax
+If the fixup was able to handle the exception, control flow may be returned
+to the instruction after the one that triggered the fault, ie. local label 2b.
+
The assembly code::
> .section __ex_table,"a"
entry->insn. It is used to distinguish page faults from machine
check.
- 3) ``int ex_handler_ext(const struct exception_table_entry *fixup)``
- This case is used for uaccess_err ... we need to set a flag
- in the task structure. Before the handler functions existed this
- case was handled by adding a large offset to the fixup to tag
- it as special.
-
More functions can easily be added.
+
+CONFIG_BUILDTIME_TABLE_SORT allows the __ex_table section to be sorted post
+link of the kernel image, via a host utility scripts/sorttable. It will set the
+symbol main_extable_sort_needed to 0, avoiding sorting the __ex_table section
+at boot time. With the exception table sorted, at runtime when an exception
+occurs we can quickly lookup the __ex_table entry via binary search.
+
+This is not just a boot time optimization, some architectures require this
+table to be sorted in order to handle exceptions relatively early in the boot
+process. For example, i386 makes use of this form of exception handling before
+paging support is even enabled!
#include <asm/fpu/api.h>
#include <asm/nospec-branch.h>
#include <asm/io_bitmap.h>
+ #include <asm/syscall.h>
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
if (likely(nr < IA32_NR_syscalls)) {
nr = array_index_nospec(nr, IA32_NR_syscalls);
-#ifdef CONFIG_IA32_EMULATION
regs->ax = ia32_sys_call_table[nr](regs);
-#else
- /*
- * It's possible that a 32-bit syscall implementation
- * takes a 64-bit parameter but nonetheless assumes that
- * the high bits are zero. Make sure we zero-extend all
- * of the args.
- */
- regs->ax = ia32_sys_call_table[nr](
- (unsigned int)regs->bx, (unsigned int)regs->cx,
- (unsigned int)regs->dx, (unsigned int)regs->si,
- (unsigned int)regs->di, (unsigned int)regs->bp);
-#endif /* CONFIG_IA32_EMULATION */
}
syscall_return_slowpath(regs);
#endif
}
#endif
+
+SYSCALL_DEFINE0(ni_syscall)
+{
+ return -ENOSYS;
+}
#include <asm/fpu/types.h>
#include <asm/unwind_hints.h>
#include <asm/vmxfeatures.h>
+#include <asm/vdso/processor.h>
#include <linux/personality.h>
#include <linux/cache.h>
mm_segment_t addr_limit;
unsigned int sig_on_uaccess_err:1;
- unsigned int uaccess_err:1; /* uaccess failed */
/* Floating point and extended processor state */
struct fpu fpu;
return edx;
}
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static __always_inline void rep_nop(void)
-{
- asm volatile("rep; nop" ::: "memory");
-}
-
-static __always_inline void cpu_relax(void)
-{
- rep_nop();
-}
-
/*
* This function forces the icache and prefetched instruction stream to
* catch up with reality in two very specific cases:
X86_EFLAGS_CF | X86_EFLAGS_RF)
void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
- int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
- struct pt_regs *regs, unsigned long mask);
-#ifdef CONFIG_X86_X32_ABI
-asmlinkage long sys32_x32_rt_sigreturn(void);
-#endif
-
#endif /* _ASM_X86_SIGHANDLING_H */
#include <uapi/linux/audit.h>
#include <linux/sched.h>
#include <linux/err.h>
-#include <asm/asm-offsets.h> /* For NR_syscalls */
#include <asm/thread_info.h> /* for TS_COMPAT */
#include <asm/unistd.h>
-#ifdef CONFIG_X86_64
-typedef asmlinkage long (*sys_call_ptr_t)(const struct pt_regs *);
-#else
-typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
- unsigned long, unsigned long,
- unsigned long, unsigned long);
-#endif /* CONFIG_X86_64 */
+typedef long (*sys_call_ptr_t)(const struct pt_regs *);
extern const sys_call_ptr_t sys_call_table[];
#if defined(CONFIG_X86_32)
#define ia32_sys_call_table sys_call_table
-#define __NR_syscall_compat_max __NR_syscall_max
-#define IA32_NR_syscalls NR_syscalls
#endif
#if defined(CONFIG_IA32_EMULATION)
task->thread_info.status & TS_COMPAT)
? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
}
+
+ void do_syscall_64(unsigned long nr, struct pt_regs *regs);
+ void do_int80_syscall_32(struct pt_regs *regs);
+ long do_fast_syscall_32(struct pt_regs *regs);
+
#endif /* CONFIG_X86_32 */
#endif /* _ASM_X86_SYSCALL_H */
: : "A" (x), "r" (addr) \
: : label)
- #define __put_user_asm_ex_u64(x, addr) \
- asm volatile("\n" \
- "1: movl %%eax,0(%1)\n" \
- "2: movl %%edx,4(%1)\n" \
- "3:" \
- _ASM_EXTABLE_EX(1b, 2b) \
- _ASM_EXTABLE_EX(2b, 3b) \
- : : "A" (x), "r" (addr))
-
#define __put_user_x8(x, ptr, __ret_pu) \
asm volatile("call __put_user_8" : "=a" (__ret_pu) \
: "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
#else
#define __put_user_goto_u64(x, ptr, label) \
__put_user_goto(x, ptr, "q", "", "er", label)
- #define __put_user_asm_ex_u64(x, addr) \
- __put_user_asm_ex(x, addr, "q", "", "er")
#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
#endif
} \
} while (0)
- /*
- * This doesn't do __uaccess_begin/end - the exception handling
- * around it must do that.
- */
- #define __put_user_size_ex(x, ptr, size) \
- do { \
- __chk_user_ptr(ptr); \
- switch (size) { \
- case 1: \
- __put_user_asm_ex(x, ptr, "b", "b", "iq"); \
- break; \
- case 2: \
- __put_user_asm_ex(x, ptr, "w", "w", "ir"); \
- break; \
- case 4: \
- __put_user_asm_ex(x, ptr, "l", "k", "ir"); \
- break; \
- case 8: \
- __put_user_asm_ex_u64((__typeof__(*ptr))(x), ptr); \
- break; \
- default: \
- __put_user_bad(); \
- } \
- } while (0)
-
#ifdef CONFIG_X86_32
#define __get_user_asm_u64(x, ptr, retval, errret) \
({ \
"i" (errret), "0" (retval)); \
})
- #define __get_user_asm_ex_u64(x, ptr) (x) = __get_user_bad()
#else
#define __get_user_asm_u64(x, ptr, retval, errret) \
__get_user_asm(x, ptr, retval, "q", "", "=r", errret)
- #define __get_user_asm_ex_u64(x, ptr) \
- __get_user_asm_ex(x, ptr, "q", "", "=r")
#endif
#define __get_user_size(x, ptr, size, retval, errret) \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
- #define __get_user_asm_nozero(x, addr, err, itype, rtype, ltype, errret) \
- asm volatile("\n" \
- "1: mov"itype" %2,%"rtype"1\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: mov %3,%0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "=r" (err), ltype(x) \
- : "m" (__m(addr)), "i" (errret), "0" (err))
-
- /*
- * This doesn't do __uaccess_begin/end - the exception handling
- * around it must do that.
- */
- #define __get_user_size_ex(x, ptr, size) \
- do { \
- __chk_user_ptr(ptr); \
- switch (size) { \
- case 1: \
- __get_user_asm_ex(x, ptr, "b", "b", "=q"); \
- break; \
- case 2: \
- __get_user_asm_ex(x, ptr, "w", "w", "=r"); \
- break; \
- case 4: \
- __get_user_asm_ex(x, ptr, "l", "k", "=r"); \
- break; \
- case 8: \
- __get_user_asm_ex_u64(x, ptr); \
- break; \
- default: \
- (x) = __get_user_bad(); \
- } \
- } while (0)
-
- #define __get_user_asm_ex(x, addr, itype, rtype, ltype) \
- asm volatile("1: mov"itype" %1,%"rtype"0\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3:xor"itype" %"rtype"0,%"rtype"0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE_EX(1b, 3b) \
- : ltype(x) : "m" (__m(addr)))
-
#define __put_user_nocheck(x, ptr, size) \
({ \
__label__ __pu_label; \
retval = __put_user_failed(x, addr, itype, rtype, ltype, errret); \
} while (0)
- #define __put_user_asm_ex(x, addr, itype, rtype, ltype) \
- asm volatile("1: mov"itype" %"rtype"0,%1\n" \
- "2:\n" \
- _ASM_EXTABLE_EX(1b, 2b) \
- : : ltype(x), "m" (__m(addr)))
-
- /*
- * uaccess_try and catch
- */
- #define uaccess_try do { \
- current->thread.uaccess_err = 0; \
- __uaccess_begin(); \
- barrier();
-
- #define uaccess_try_nospec do { \
- current->thread.uaccess_err = 0; \
- __uaccess_begin_nospec(); \
-
- #define uaccess_catch(err) \
- __uaccess_end(); \
- (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \
- } while (0)
-
/**
* __get_user - Get a simple variable from user space, with less checking.
* @x: Variable to store result.
#define __put_user(x, ptr) \
__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
- /*
- * {get|put}_user_try and catch
- *
- * get_user_try {
- * get_user_ex(...);
- * } get_user_catch(err)
- */
- #define get_user_try uaccess_try_nospec
- #define get_user_catch(err) uaccess_catch(err)
-
- #define get_user_ex(x, ptr) do { \
- unsigned long __gue_val; \
- __get_user_size_ex((__gue_val), (ptr), (sizeof(*(ptr)))); \
- (x) = (__force __typeof__(*(ptr)))__gue_val; \
- } while (0)
-
- #define put_user_try uaccess_try
- #define put_user_catch(err) uaccess_catch(err)
-
- #define put_user_ex(x, ptr) \
- __put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
extern unsigned long
copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
extern __must_check long
unsigned long __must_check clear_user(void __user *mem, unsigned long len);
unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
-extern void __cmpxchg_wrong_size(void)
- __compiletime_error("Bad argument size for cmpxchg");
-
-#define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size) \
-({ \
- int __ret = 0; \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- __uaccess_begin_nospec(); \
- switch (size) { \
- case 1: \
- { \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "q" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- case 2: \
- { \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "r" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- case 4: \
- { \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "r" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- case 8: \
- { \
- if (!IS_ENABLED(CONFIG_X86_64)) \
- __cmpxchg_wrong_size(); \
- \
- asm volatile("\n" \
- "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" \
- "2:\n" \
- "\t.section .fixup, \"ax\"\n" \
- "3:\tmov %3, %0\n" \
- "\tjmp 2b\n" \
- "\t.previous\n" \
- _ASM_EXTABLE_UA(1b, 3b) \
- : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
- : "i" (-EFAULT), "r" (__new), "1" (__old) \
- : "memory" \
- ); \
- break; \
- } \
- default: \
- __cmpxchg_wrong_size(); \
- } \
- __uaccess_end(); \
- *(uval) = __old; \
- __ret; \
-})
-
-#define user_atomic_cmpxchg_inatomic(uval, ptr, old, new) \
-({ \
- access_ok((ptr), sizeof(*(ptr))) ? \
- __user_atomic_cmpxchg_inatomic((uval), (ptr), \
- (old), (new), sizeof(*(ptr))) : \
- -EFAULT; \
-})
-
/*
* movsl can be slow when source and dest are not both 8-byte aligned
*/
#endif
/*
- * We rely on the nested NMI work to allow atomic faults from the NMI path; the
- * nested NMI paths are careful to preserve CR2.
- *
- * Caller must use pagefault_enable/disable, or run in interrupt context,
- * and also do a uaccess_ok() check
- */
- #define __copy_from_user_nmi __copy_from_user_inatomic
-
- /*
* The "unsafe" user accesses aren't really "unsafe", but the naming
* is a big fat warning: you have to not only do the access_ok()
* checking before using them, but you have to surround them with the
#endif /* CONFIG_X86_64 */
#include <asm/syscall.h>
-#include <asm/syscalls.h>
-
#include <asm/sigframe.h>
#include <asm/signal.h>
- #define COPY(x) do { \
- get_user_ex(regs->x, &sc->x); \
- } while (0)
-
- #define GET_SEG(seg) ({ \
- unsigned short tmp; \
- get_user_ex(tmp, &sc->seg); \
- tmp; \
- })
-
- #define COPY_SEG(seg) do { \
- regs->seg = GET_SEG(seg); \
- } while (0)
-
- #define COPY_SEG_CPL3(seg) do { \
- regs->seg = GET_SEG(seg) | 3; \
- } while (0)
-
#ifdef CONFIG_X86_64
/*
* If regs->ss will cause an IRET fault, change it. Otherwise leave it
ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN))
regs->ss = __USER_DS;
}
+ # define CONTEXT_COPY_SIZE offsetof(struct sigcontext, reserved1)
+ #else
+ # define CONTEXT_COPY_SIZE sizeof(struct sigcontext)
#endif
static int restore_sigcontext(struct pt_regs *regs,
- struct sigcontext __user *sc,
+ struct sigcontext __user *usc,
unsigned long uc_flags)
{
- unsigned long buf_val;
- void __user *buf;
- unsigned int tmpflags;
- unsigned int err = 0;
+ struct sigcontext sc;
/* Always make any pending restarted system calls return -EINTR */
current->restart_block.fn = do_no_restart_syscall;
- get_user_try {
+ if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE))
+ return -EFAULT;
#ifdef CONFIG_X86_32
- set_user_gs(regs, GET_SEG(gs));
- COPY_SEG(fs);
- COPY_SEG(es);
- COPY_SEG(ds);
+ set_user_gs(regs, sc.gs);
+ regs->fs = sc.fs;
+ regs->es = sc.es;
+ regs->ds = sc.ds;
#endif /* CONFIG_X86_32 */
- COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
- COPY(dx); COPY(cx); COPY(ip); COPY(ax);
+ regs->bx = sc.bx;
+ regs->cx = sc.cx;
+ regs->dx = sc.dx;
+ regs->si = sc.si;
+ regs->di = sc.di;
+ regs->bp = sc.bp;
+ regs->ax = sc.ax;
+ regs->sp = sc.sp;
+ regs->ip = sc.ip;
#ifdef CONFIG_X86_64
- COPY(r8);
- COPY(r9);
- COPY(r10);
- COPY(r11);
- COPY(r12);
- COPY(r13);
- COPY(r14);
- COPY(r15);
+ regs->r8 = sc.r8;
+ regs->r9 = sc.r9;
+ regs->r10 = sc.r10;
+ regs->r11 = sc.r11;
+ regs->r12 = sc.r12;
+ regs->r13 = sc.r13;
+ regs->r14 = sc.r14;
+ regs->r15 = sc.r15;
#endif /* CONFIG_X86_64 */
- COPY_SEG_CPL3(cs);
- COPY_SEG_CPL3(ss);
-
- get_user_ex(tmpflags, &sc->flags);
- regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
- regs->orig_ax = -1; /* disable syscall checks */
+ /* Get CS/SS and force CPL3 */
+ regs->cs = sc.cs | 0x03;
+ regs->ss = sc.ss | 0x03;
- get_user_ex(buf_val, &sc->fpstate);
- buf = (void __user *)buf_val;
- } get_user_catch(err);
+ regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS);
+ /* disable syscall checks */
+ regs->orig_ax = -1;
#ifdef CONFIG_X86_64
/*
force_valid_ss(regs);
#endif
- err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32));
-
- return err;
+ return fpu__restore_sig((void __user *)sc.fpstate,
+ IS_ENABLED(CONFIG_X86_32));
}
- int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+ static __always_inline int
+ __unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
struct pt_regs *regs, unsigned long mask)
{
- int err = 0;
-
- put_user_try {
-
#ifdef CONFIG_X86_32
- put_user_ex(get_user_gs(regs), (unsigned int __user *)&sc->gs);
- put_user_ex(regs->fs, (unsigned int __user *)&sc->fs);
- put_user_ex(regs->es, (unsigned int __user *)&sc->es);
- put_user_ex(regs->ds, (unsigned int __user *)&sc->ds);
+ unsafe_put_user(get_user_gs(regs),
+ (unsigned int __user *)&sc->gs, Efault);
+ unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault);
+ unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault);
+ unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault);
#endif /* CONFIG_X86_32 */
- put_user_ex(regs->di, &sc->di);
- put_user_ex(regs->si, &sc->si);
- put_user_ex(regs->bp, &sc->bp);
- put_user_ex(regs->sp, &sc->sp);
- put_user_ex(regs->bx, &sc->bx);
- put_user_ex(regs->dx, &sc->dx);
- put_user_ex(regs->cx, &sc->cx);
- put_user_ex(regs->ax, &sc->ax);
+ unsafe_put_user(regs->di, &sc->di, Efault);
+ unsafe_put_user(regs->si, &sc->si, Efault);
+ unsafe_put_user(regs->bp, &sc->bp, Efault);
+ unsafe_put_user(regs->sp, &sc->sp, Efault);
+ unsafe_put_user(regs->bx, &sc->bx, Efault);
+ unsafe_put_user(regs->dx, &sc->dx, Efault);
+ unsafe_put_user(regs->cx, &sc->cx, Efault);
+ unsafe_put_user(regs->ax, &sc->ax, Efault);
#ifdef CONFIG_X86_64
- put_user_ex(regs->r8, &sc->r8);
- put_user_ex(regs->r9, &sc->r9);
- put_user_ex(regs->r10, &sc->r10);
- put_user_ex(regs->r11, &sc->r11);
- put_user_ex(regs->r12, &sc->r12);
- put_user_ex(regs->r13, &sc->r13);
- put_user_ex(regs->r14, &sc->r14);
- put_user_ex(regs->r15, &sc->r15);
+ unsafe_put_user(regs->r8, &sc->r8, Efault);
+ unsafe_put_user(regs->r9, &sc->r9, Efault);
+ unsafe_put_user(regs->r10, &sc->r10, Efault);
+ unsafe_put_user(regs->r11, &sc->r11, Efault);
+ unsafe_put_user(regs->r12, &sc->r12, Efault);
+ unsafe_put_user(regs->r13, &sc->r13, Efault);
+ unsafe_put_user(regs->r14, &sc->r14, Efault);
+ unsafe_put_user(regs->r15, &sc->r15, Efault);
#endif /* CONFIG_X86_64 */
- put_user_ex(current->thread.trap_nr, &sc->trapno);
- put_user_ex(current->thread.error_code, &sc->err);
- put_user_ex(regs->ip, &sc->ip);
+ unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault);
+ unsafe_put_user(current->thread.error_code, &sc->err, Efault);
+ unsafe_put_user(regs->ip, &sc->ip, Efault);
#ifdef CONFIG_X86_32
- put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
- put_user_ex(regs->flags, &sc->flags);
- put_user_ex(regs->sp, &sc->sp_at_signal);
- put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
+ unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault);
+ unsafe_put_user(regs->flags, &sc->flags, Efault);
+ unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault);
+ unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault);
#else /* !CONFIG_X86_32 */
- put_user_ex(regs->flags, &sc->flags);
- put_user_ex(regs->cs, &sc->cs);
- put_user_ex(0, &sc->gs);
- put_user_ex(0, &sc->fs);
- put_user_ex(regs->ss, &sc->ss);
+ unsafe_put_user(regs->flags, &sc->flags, Efault);
+ unsafe_put_user(regs->cs, &sc->cs, Efault);
+ unsafe_put_user(0, &sc->gs, Efault);
+ unsafe_put_user(0, &sc->fs, Efault);
+ unsafe_put_user(regs->ss, &sc->ss, Efault);
#endif /* CONFIG_X86_32 */
- put_user_ex(fpstate, (unsigned long __user *)&sc->fpstate);
+ unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault);
- /* non-iBCS2 extensions.. */
- put_user_ex(mask, &sc->oldmask);
- put_user_ex(current->thread.cr2, &sc->cr2);
- } put_user_catch(err);
-
- return err;
+ /* non-iBCS2 extensions.. */
+ unsafe_put_user(mask, &sc->oldmask, Efault);
+ unsafe_put_user(current->thread.cr2, &sc->cr2, Efault);
+ return 0;
+ Efault:
+ return -EFAULT;
}
+ #define unsafe_put_sigcontext(sc, fp, regs, set, label) \
+ do { \
+ if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \
+ goto label; \
+ } while(0);
+
+ #define unsafe_put_sigmask(set, frame, label) \
+ unsafe_put_user(*(__u64 *)(set), \
+ (__u64 __user *)&(frame)->uc.uc_sigmask, \
+ label)
+
/*
* Set up a signal frame.
*/
{
struct sigframe __user *frame;
void __user *restorer;
- int err = 0;
- void __user *fpstate = NULL;
-
- frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
+ void __user *fp = NULL;
- if (!access_ok(frame, sizeof(*frame)))
- return -EFAULT;
+ frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);
- if (__put_user(sig, &frame->sig))
+ if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
- if (setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0]))
- return -EFAULT;
-
- if (_NSIG_WORDS > 1) {
- if (__copy_to_user(&frame->extramask, &set->sig[1],
- sizeof(frame->extramask)))
- return -EFAULT;
- }
-
+ unsafe_put_user(sig, &frame->sig, Efault);
+ unsafe_put_sigcontext(&frame->sc, fp, regs, set, Efault);
+ unsafe_put_user(set->sig[1], &frame->extramask[0], Efault);
if (current->mm->context.vdso)
restorer = current->mm->context.vdso +
vdso_image_32.sym___kernel_sigreturn;
restorer = ksig->ka.sa.sa_restorer;
/* Set up to return from userspace. */
- err |= __put_user(restorer, &frame->pretcode);
+ unsafe_put_user(restorer, &frame->pretcode, Efault);
/*
* This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
- err |= __put_user(*((u64 *)&retcode), (u64 *)frame->retcode);
-
- if (err)
- return -EFAULT;
+ unsafe_put_user(*((u64 *)&retcode), (u64 *)frame->retcode, Efault);
+ user_access_end();
/* Set up registers for signal handler */
regs->sp = (unsigned long)frame;
regs->cs = __USER_CS;
return 0;
+
+ Efault:
+ user_access_end();
+ return -EFAULT;
}
static int __setup_rt_frame(int sig, struct ksignal *ksig,
{
struct rt_sigframe __user *frame;
void __user *restorer;
- int err = 0;
- void __user *fpstate = NULL;
+ void __user *fp = NULL;
- frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
+ frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);
- if (!access_ok(frame, sizeof(*frame)))
+ if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
- put_user_try {
- put_user_ex(sig, &frame->sig);
- put_user_ex(&frame->info, &frame->pinfo);
- put_user_ex(&frame->uc, &frame->puc);
+ unsafe_put_user(sig, &frame->sig, Efault);
+ unsafe_put_user(&frame->info, &frame->pinfo, Efault);
+ unsafe_put_user(&frame->uc, &frame->puc, Efault);
- /* Create the ucontext. */
- if (static_cpu_has(X86_FEATURE_XSAVE))
- put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- put_user_ex(0, &frame->uc.uc_flags);
- put_user_ex(0, &frame->uc.uc_link);
- save_altstack_ex(&frame->uc.uc_stack, regs->sp);
+ /* Create the ucontext. */
+ if (static_cpu_has(X86_FEATURE_XSAVE))
+ unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault);
+ else
+ unsafe_put_user(0, &frame->uc.uc_flags, Efault);
+ unsafe_put_user(0, &frame->uc.uc_link, Efault);
+ unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);
- /* Set up to return from userspace. */
- restorer = current->mm->context.vdso +
- vdso_image_32.sym___kernel_rt_sigreturn;
- if (ksig->ka.sa.sa_flags & SA_RESTORER)
- restorer = ksig->ka.sa.sa_restorer;
- put_user_ex(restorer, &frame->pretcode);
+ /* Set up to return from userspace. */
+ restorer = current->mm->context.vdso +
+ vdso_image_32.sym___kernel_rt_sigreturn;
+ if (ksig->ka.sa.sa_flags & SA_RESTORER)
+ restorer = ksig->ka.sa.sa_restorer;
+ unsafe_put_user(restorer, &frame->pretcode, Efault);
- /*
- * This is movl $__NR_rt_sigreturn, %ax ; int $0x80
- *
- * WE DO NOT USE IT ANY MORE! It's only left here for historical
- * reasons and because gdb uses it as a signature to notice
- * signal handler stack frames.
- */
- put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
- } put_user_catch(err);
+ /*
+ * This is movl $__NR_rt_sigreturn, %ax ; int $0x80
+ *
+ * WE DO NOT USE IT ANY MORE! It's only left here for historical
+ * reasons and because gdb uses it as a signature to notice
+ * signal handler stack frames.
+ */
+ unsafe_put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode, Efault);
+ unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
+ unsafe_put_sigmask(set, frame, Efault);
+ user_access_end();
- err |= copy_siginfo_to_user(&frame->info, &ksig->info);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
- if (err)
+ if (copy_siginfo_to_user(&frame->info, &ksig->info))
return -EFAULT;
/* Set up registers for signal handler */
regs->cs = __USER_CS;
return 0;
+ Efault:
+ user_access_end();
+ return -EFAULT;
}
#else /* !CONFIG_X86_32 */
static unsigned long frame_uc_flags(struct pt_regs *regs)
struct rt_sigframe __user *frame;
void __user *fp = NULL;
unsigned long uc_flags;
- int err = 0;
+
+ /* x86-64 should always use SA_RESTORER. */
+ if (!(ksig->ka.sa.sa_flags & SA_RESTORER))
+ return -EFAULT;
frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
+ uc_flags = frame_uc_flags(regs);
- if (!access_ok(frame, sizeof(*frame)))
+ if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
+ /* Create the ucontext. */
+ unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault);
+ unsafe_put_user(0, &frame->uc.uc_link, Efault);
+ unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);
+
+ /* Set up to return from userspace. If provided, use a stub
+ already in userspace. */
+ unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault);
+ unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
+ unsafe_put_sigmask(set, frame, Efault);
+ user_access_end();
+
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
if (copy_siginfo_to_user(&frame->info, &ksig->info))
return -EFAULT;
}
- uc_flags = frame_uc_flags(regs);
-
- put_user_try {
- /* Create the ucontext. */
- put_user_ex(uc_flags, &frame->uc.uc_flags);
- put_user_ex(0, &frame->uc.uc_link);
- save_altstack_ex(&frame->uc.uc_stack, regs->sp);
-
- /* Set up to return from userspace. If provided, use a stub
- already in userspace. */
- /* x86-64 should always use SA_RESTORER. */
- if (ksig->ka.sa.sa_flags & SA_RESTORER) {
- put_user_ex(ksig->ka.sa.sa_restorer, &frame->pretcode);
- } else {
- /* could use a vstub here */
- err |= -EFAULT;
- }
- } put_user_catch(err);
-
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
- if (err)
- return -EFAULT;
-
/* Set up registers for signal handler */
regs->di = sig;
/* In case the signal handler was declared without prototypes */
force_valid_ss(regs);
return 0;
+
+ Efault:
+ user_access_end();
+ return -EFAULT;
}
#endif /* CONFIG_X86_32 */
struct rt_sigframe_x32 __user *frame;
unsigned long uc_flags;
void __user *restorer;
- int err = 0;
- void __user *fpstate = NULL;
-
- frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fpstate);
+ void __user *fp = NULL;
- if (!access_ok(frame, sizeof(*frame)))
+ if (!(ksig->ka.sa.sa_flags & SA_RESTORER))
return -EFAULT;
- if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
- if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true))
- return -EFAULT;
- }
+ frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp);
uc_flags = frame_uc_flags(regs);
- put_user_try {
- /* Create the ucontext. */
- put_user_ex(uc_flags, &frame->uc.uc_flags);
- put_user_ex(0, &frame->uc.uc_link);
- compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
- put_user_ex(0, &frame->uc.uc__pad0);
-
- if (ksig->ka.sa.sa_flags & SA_RESTORER) {
- restorer = ksig->ka.sa.sa_restorer;
- } else {
- /* could use a vstub here */
- restorer = NULL;
- err |= -EFAULT;
- }
- put_user_ex(restorer, (unsigned long __user *)&frame->pretcode);
- } put_user_catch(err);
+ if (!user_access_begin(frame, sizeof(*frame)))
+ return -EFAULT;
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+ /* Create the ucontext. */
+ unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault);
+ unsafe_put_user(0, &frame->uc.uc_link, Efault);
+ unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault);
+ unsafe_put_user(0, &frame->uc.uc__pad0, Efault);
+ restorer = ksig->ka.sa.sa_restorer;
+ unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault);
+ unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault);
+ unsafe_put_sigmask(set, frame, Efault);
+ user_access_end();
- if (err)
- return -EFAULT;
+ if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
+ if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true))
+ return -EFAULT;
+ }
/* Set up registers for signal handler */
regs->sp = (unsigned long) frame;
#endif /* CONFIG_X86_X32_ABI */
return 0;
+ #ifdef CONFIG_X86_X32_ABI
+ Efault:
+ user_access_end();
+ return -EFAULT;
+ #endif
}
/*
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
- if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1
- && __copy_from_user(&set.sig[1], &frame->extramask,
- sizeof(frame->extramask))))
+ if (__get_user(set.sig[0], &frame->sc.oldmask) ||
+ __get_user(set.sig[1], &frame->extramask[0]))
goto badframe;
set_current_blocked(&set);
frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
- if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask))
goto badframe;
if (__get_user(uc_flags, &frame->uc.uc_flags))
goto badframe;
}
#ifdef CONFIG_X86_X32_ABI
-asmlinkage long sys32_x32_rt_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe_x32 __user *frame;
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
- if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask))
goto badframe;
if (__get_user(uc_flags, &frame->uc.uc_flags))
goto badframe;
*((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
}
+static void init_freq_invariance(void);
+
/*
* Report back to the Boot Processor during boot time or to the caller processor
* during CPU online.
*/
set_cpu_sibling_map(raw_smp_processor_id());
+ init_freq_invariance();
+
/*
* Get our bogomips.
* Update loops_per_jiffy in cpu_data. Previous call to
*/
static const struct x86_cpu_id snc_cpu[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X },
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL),
{}
};
set_sched_topology(x86_topology);
set_cpu_sibling_map(0);
-
+ init_freq_invariance();
smp_sanity_check();
switch (apic_intr_mode) {
/*
* cpu_possible_mask should be static, it cannot change as cpu's
* are onlined, or offlined. The reason is per-cpu data-structures
- * are allocated by some modules at init time, and dont expect to
+ * are allocated by some modules at init time, and don't expect to
* do this dynamically on cpu arrival/departure.
* cpu_present_mask on the other hand can change dynamically.
* In case when cpu_hotplug is not compiled, then we resort to current
}
#endif
+
+/*
+ * APERF/MPERF frequency ratio computation.
+ *
+ * The scheduler wants to do frequency invariant accounting and needs a <1
+ * ratio to account for the 'current' frequency, corresponding to
+ * freq_curr / freq_max.
+ *
+ * Since the frequency freq_curr on x86 is controlled by micro-controller and
+ * our P-state setting is little more than a request/hint, we need to observe
+ * the effective frequency 'BusyMHz', i.e. the average frequency over a time
+ * interval after discarding idle time. This is given by:
+ *
+ * BusyMHz = delta_APERF / delta_MPERF * freq_base
+ *
+ * where freq_base is the max non-turbo P-state.
+ *
+ * The freq_max term has to be set to a somewhat arbitrary value, because we
+ * can't know which turbo states will be available at a given point in time:
+ * it all depends on the thermal headroom of the entire package. We set it to
+ * the turbo level with 4 cores active.
+ *
+ * Benchmarks show that's a good compromise between the 1C turbo ratio
+ * (freq_curr/freq_max would rarely reach 1) and something close to freq_base,
+ * which would ignore the entire turbo range (a conspicuous part, making
+ * freq_curr/freq_max always maxed out).
+ *
+ * An exception to the heuristic above is the Atom uarch, where we choose the
+ * highest turbo level for freq_max since Atom's are generally oriented towards
+ * power efficiency.
+ *
+ * Setting freq_max to anything less than the 1C turbo ratio makes the ratio
+ * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1.
+ */
+
+DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key);
+
+static DEFINE_PER_CPU(u64, arch_prev_aperf);
+static DEFINE_PER_CPU(u64, arch_prev_mperf);
+static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE;
+static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE;
+
+void arch_set_max_freq_ratio(bool turbo_disabled)
+{
+ arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE :
+ arch_turbo_freq_ratio;
+}
+
+static bool turbo_disabled(void)
+{
+ u64 misc_en;
+ int err;
+
+ err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
+ if (err)
+ return false;
+
+ return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
+}
+
+static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+{
+ int err;
+
+ err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
+ if (err)
+ return false;
+
+ err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */
+ *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */
+
+ return true;
+}
+
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+
+#define ICPU(model) \
+ {X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF, 0}
+
+static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
+ ICPU(INTEL_FAM6_XEON_PHI_KNL),
+ ICPU(INTEL_FAM6_XEON_PHI_KNM),
+ {}
+};
+
+static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
+ ICPU(INTEL_FAM6_SKYLAKE_X),
+ {}
+};
+
+static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT_D),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS),
+ {}
+};
+
+static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
+ int num_delta_fratio)
+{
+ int fratio, delta_fratio, found;
+ int err, i;
+ u64 msr;
+
+ if (!x86_match_cpu(has_knl_turbo_ratio_limits))
+ return false;
+
+ err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+ if (err)
+ return false;
+
+ fratio = (msr >> 8) & 0xFF;
+ i = 16;
+ found = 0;
+ do {
+ if (found >= num_delta_fratio) {
+ *turbo_freq = fratio;
+ return true;
+ }
+
+ delta_fratio = (msr >> (i + 5)) & 0x7;
+
+ if (delta_fratio) {
+ found += 1;
+ fratio -= delta_fratio;
+ }
+
+ i += 8;
+ } while (i < 64);
+
+ return true;
+}
+
+static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
+{
+ u64 ratios, counts;
+ u32 group_size;
+ int err, i;
+
+ err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
+ if (err)
+ return false;
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
+ if (err)
+ return false;
+
+ for (i = 0; i < 64; i += 8) {
+ group_size = (counts >> i) & 0xFF;
+ if (group_size >= size) {
+ *turbo_freq = (ratios >> i) & 0xFF;
+ return true;
+ }
+ }
+
+ return false;
+}
+
+static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+{
+ int err;
+
+ err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ if (err)
+ return false;
+
+ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, turbo_freq);
+ if (err)
+ return false;
+
+ *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
+ *turbo_freq = (*turbo_freq >> 24) & 0xFF; /* 4C turbo */
+
+ return true;
+}
+
+static bool intel_set_max_freq_ratio(void)
+{
+ u64 base_freq, turbo_freq;
+
+ if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
+ goto out;
+
+ if (x86_match_cpu(has_glm_turbo_ratio_limits) &&
+ skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+ goto out;
+
+ if (knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+ goto out;
+
+ if (x86_match_cpu(has_skx_turbo_ratio_limits) &&
+ skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4))
+ goto out;
+
+ if (core_set_max_freq_ratio(&base_freq, &turbo_freq))
+ goto out;
+
+ return false;
+
+out:
+ arch_turbo_freq_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE,
+ base_freq);
+ arch_set_max_freq_ratio(turbo_disabled());
+ return true;
+}
+
+static void init_counter_refs(void *arg)
+{
+ u64 aperf, mperf;
+
+ rdmsrl(MSR_IA32_APERF, aperf);
+ rdmsrl(MSR_IA32_MPERF, mperf);
+
+ this_cpu_write(arch_prev_aperf, aperf);
+ this_cpu_write(arch_prev_mperf, mperf);
+}
+
+static void init_freq_invariance(void)
+{
+ bool ret = false;
+
+ if (smp_processor_id() != 0 || !boot_cpu_has(X86_FEATURE_APERFMPERF))
+ return;
+
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ ret = intel_set_max_freq_ratio();
+
+ if (ret) {
+ on_each_cpu(init_counter_refs, NULL, 1);
+ static_branch_enable(&arch_scale_freq_key);
+ } else {
+ pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
+ }
+}
+
+DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+
+void arch_scale_freq_tick(void)
+{
+ u64 freq_scale;
+ u64 aperf, mperf;
+ u64 acnt, mcnt;
+
+ if (!arch_scale_freq_invariant())
+ return;
+
+ rdmsrl(MSR_IA32_APERF, aperf);
+ rdmsrl(MSR_IA32_MPERF, mperf);
+
+ acnt = aperf - this_cpu_read(arch_prev_aperf);
+ mcnt = mperf - this_cpu_read(arch_prev_mperf);
+ if (!mcnt)
+ return;
+
+ this_cpu_write(arch_prev_aperf, aperf);
+ this_cpu_write(arch_prev_mperf, mperf);
+
+ acnt <<= 2*SCHED_CAPACITY_SHIFT;
+ mcnt *= arch_max_freq_ratio;
+
+ freq_scale = div64_u64(acnt, mcnt);
+
+ if (freq_scale > SCHED_CAPACITY_SCALE)
+ freq_scale = SCHED_CAPACITY_SCALE;
+
+ this_cpu_write(arch_freq_scale, freq_scale);
+}
return IRQ_HANDLED;
}
- static struct irqaction irq0 = {
- .handler = timer_interrupt,
- .flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
- .name = "timer"
- };
-
static void __init setup_default_timer_irq(void)
{
+ unsigned long flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER;
+
/*
- * Unconditionally register the legacy timer; even without legacy
- * PIC/PIT we need this for the HPET0 in legacy replacement mode.
+ * Unconditionally register the legacy timer interrupt; even
+ * without legacy PIC/PIT we need this for the HPET0 in legacy
+ * replacement mode.
*/
- if (setup_irq(0, &irq0))
+ if (request_irq(0, timer_interrupt, flags, "timer", NULL))
pr_info("Failed to register legacy timer interrupt\n");
}
*/
void clocksource_arch_init(struct clocksource *cs)
{
- if (cs->archdata.vclock_mode == VCLOCK_NONE)
+ if (cs->vdso_clock_mode == VDSO_CLOCKMODE_NONE)
return;
- if (cs->archdata.vclock_mode > VCLOCK_MAX) {
- pr_warn("clocksource %s registered with invalid vclock_mode %d. Disabling vclock.\n",
- cs->name, cs->archdata.vclock_mode);
- cs->archdata.vclock_mode = VCLOCK_NONE;
- }
-
if (cs->mask != CLOCKSOURCE_MASK(64)) {
- pr_warn("clocksource %s registered with invalid mask %016llx. Disabling vclock.\n",
+ pr_warn("clocksource %s registered with invalid mask %016llx for VDSO. Disabling VDSO support.\n",
cs->name, cs->mask);
- cs->archdata.vclock_mode = VCLOCK_NONE;
+ cs->vdso_clock_mode = VDSO_CLOCKMODE_NONE;
}
}
* transition from one expected value to another with a fairly
* high accuracy, and we didn't miss any events. We can thus
* use the TSC value at the transitions to calculate a pretty
- * good value for the TSC frequencty.
+ * good value for the TSC frequency.
*/
static inline int pit_verify_msb(unsigned char val)
{
sched_clock_tick_stable();
}
+static int tsc_cs_enable(struct clocksource *cs)
+{
+ vclocks_set_used(VDSO_CLOCKMODE_TSC);
+ return 0;
+}
+
/*
* .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
*/
static struct clocksource clocksource_tsc_early = {
- .name = "tsc-early",
- .rating = 299,
- .read = read_tsc,
- .mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS |
+ .name = "tsc-early",
+ .rating = 299,
+ .read = read_tsc,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_MUST_VERIFY,
- .archdata = { .vclock_mode = VCLOCK_TSC },
+ .vdso_clock_mode = VDSO_CLOCKMODE_TSC,
+ .enable = tsc_cs_enable,
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
* been found good.
*/
static struct clocksource clocksource_tsc = {
- .name = "tsc",
- .rating = 300,
- .read = read_tsc,
- .mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS |
+ .name = "tsc",
+ .rating = 300,
+ .read = read_tsc,
+ .mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_VALID_FOR_HRES |
CLOCK_SOURCE_MUST_VERIFY,
- .archdata = { .vclock_mode = VCLOCK_TSC },
+ .vdso_clock_mode = VDSO_CLOCKMODE_TSC,
+ .enable = tsc_cs_enable,
.resume = tsc_resume,
.mark_unstable = tsc_cs_mark_unstable,
.tick_stable = tsc_cs_tick_stable,
#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
#define PT_HAVE_ACCESSED_DIRTY(mmu) true
#ifdef CONFIG_X86_64
- #define PT_MAX_FULL_LEVELS 4
+ #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
#define CMPXCHG cmpxchg
#else
#define CMPXCHG cmpxchg64
goto error;
ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
- if (unlikely(__copy_from_user(&pte, ptep_user, sizeof(pte))))
+ if (unlikely(__get_user(pte, ptep_user)))
goto error;
walker->ptep_user[walker->level - 1] = ptep_user;
#include <asm/apic.h>
#include <asm/asm.h>
#include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/fpu/internal.h>
#include <asm/mce.h>
#include <asm/mmu_context.h>
#include <asm/mshyperv.h>
+ #include <asm/mwait.h>
#include <asm/spec-ctrl.h>
#include <asm/virtext.h>
#include <asm/vmx.h>
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+#ifdef MODULE
static const struct x86_cpu_id vmx_cpu_id[] = {
- X86_FEATURE_MATCH(X86_FEATURE_VMX),
+ X86_MATCH_FEATURE(X86_FEATURE_VMX, NULL),
{}
};
MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+#endif
bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
static bool __read_mostly fasteoi = 1;
module_param(fasteoi, bool, S_IRUGO);
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
module_param(enable_apicv, bool, S_IRUGO);
/*
vmx->guest_msrs[i].mask);
}
+
+ if (vmx->nested.need_vmcs12_to_shadow_sync)
+ nested_sync_vmcs12_to_shadow(vcpu);
+
if (vmx->guest_state_loaded)
return;
return 1;
}
+
+/*
+ * Recognizes a pending MTF VM-exit and records the nested state for later
+ * delivery.
+ */
+static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (!is_guest_mode(vcpu))
+ return;
+
+ /*
+ * Per the SDM, MTF takes priority over debug-trap exceptions besides
+ * T-bit traps. As instruction emulation is completed (i.e. at the
+ * instruction boundary), any #DB exception pending delivery must be a
+ * debug-trap. Record the pending MTF state to be delivered in
+ * vmx_check_nested_events().
+ */
+ if (nested_cpu_has_mtf(vmcs12) &&
+ (!vcpu->arch.exception.pending ||
+ vcpu->arch.exception.nr == DB_VECTOR))
+ vmx->nested.mtf_pending = true;
+ else
+ vmx->nested.mtf_pending = false;
+}
+
+static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+{
+ vmx_update_emulated_instruction(vcpu);
+ return skip_emulated_instruction(vcpu);
+}
+
static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
{
/*
kvm_cpu_vmxoff();
}
+/*
+ * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID
+ * directly instead of going through cpu_has(), to ensure KVM is trapping
+ * ENCLS whenever it's supported in hardware. It does not matter whether
+ * the host OS supports or has enabled SGX.
+ */
+static bool cpu_has_sgx(void)
+{
+ return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0));
+}
+
static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
u32 msr, u32 *result)
{
SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
SECONDARY_EXEC_PT_USE_GPA |
SECONDARY_EXEC_PT_CONCEAL_VMX |
- SECONDARY_EXEC_ENABLE_VMFUNC |
- SECONDARY_EXEC_ENCLS_EXITING;
+ SECONDARY_EXEC_ENABLE_VMFUNC;
+ if (cpu_has_sgx())
+ opt2 |= SECONDARY_EXEC_ENCLS_EXITING;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
static int get_ept_level(struct kvm_vcpu *vcpu)
{
+ /* Nested EPT currently only supports 4-level walks. */
+ if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
+ return 4;
if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
return 5;
return 4;
* 2. If target vcpu isn't running(root mode), kick it to pick up the
* interrupt from PIR in next vmentry.
*/
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int r;
r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
if (!r)
- return;
+ return 0;
+
+ if (!vcpu->arch.apicv_active)
+ return -1;
if (pi_test_and_set_pir(vector, &vmx->pi_desc))
- return;
+ return 0;
/* If a previous notification has sent the IPI, nothing to do. */
if (pi_test_and_set_on(&vmx->pi_desc))
- return;
+ return 0;
if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
kvm_vcpu_kick(vcpu);
+
+ return 0;
}
/*
vmx->msr_ia32_umwait_control = 0;
- vcpu->arch.microcode_version = 0x100000000ULL;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
vmx->hv_deadline_tsc = -1;
kvm_set_cr8(vcpu, 0);
#endif
ASM_CALL_CONSTRAINT
:
- THUNK_TARGET(entry),
+ [thunk_target]"r"(entry),
[ss]"i"(__KERNEL_DS),
[cs]"i"(__KERNEL_CS)
);
vmcs_write32(PLE_WINDOW, vmx->ple_window);
}
- if (vmx->nested.need_vmcs12_to_shadow_sync)
- nested_sync_vmcs12_to_shadow(vcpu);
+ /*
+ * We did this in prepare_switch_to_guest, because it needs to
+ * be within srcu_read_lock.
+ */
+ WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync);
if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP))
vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
if (nested)
nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
- vmx_capability.ept,
- kvm_vcpu_apicv_active(vcpu));
+ vmx_capability.ept);
else
memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
vmx->nested.posted_intr_nv = -1;
vmx->nested.current_vmptr = -1ull;
+ vcpu->arch.microcode_version = 0x100000000ULL;
vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
/*
if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
return -EIO;
if (nested)
- nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
- enable_apicv);
+ nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
smp_processor_id());
to_vmx(vcpu)->req_immediate_exit = true;
}
+static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
+ struct x86_instruction_info *info)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ unsigned short port;
+ bool intercept;
+ int size;
+
+ if (info->intercept == x86_intercept_in ||
+ info->intercept == x86_intercept_ins) {
+ port = info->src_val;
+ size = info->dst_bytes;
+ } else {
+ port = info->dst_val;
+ size = info->src_bytes;
+ }
+
+ /*
+ * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+ * VM-exits depend on the 'unconditional IO exiting' VM-execution
+ * control.
+ *
+ * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+ */
+ if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+ intercept = nested_cpu_has(vmcs12,
+ CPU_BASED_UNCOND_IO_EXITING);
+ else
+ intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+
+ /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */
+ return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+}
+
static int vmx_check_intercept(struct kvm_vcpu *vcpu,
struct x86_instruction_info *info,
enum x86_intercept_stage stage)
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+ switch (info->intercept) {
/*
* RDPID causes #UD if disabled through secondary execution controls.
* Because it is marked as EmulateOnUD, we need to intercept it here.
*/
- if (info->intercept == x86_intercept_rdtscp &&
- !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
- ctxt->exception.vector = UD_VECTOR;
- ctxt->exception.error_code_valid = false;
- return X86EMUL_PROPAGATE_FAULT;
- }
+ case x86_intercept_rdtscp:
+ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+ ctxt->exception.vector = UD_VECTOR;
+ ctxt->exception.error_code_valid = false;
+ return X86EMUL_PROPAGATE_FAULT;
+ }
+ break;
+
+ case x86_intercept_in:
+ case x86_intercept_ins:
+ case x86_intercept_out:
+ case x86_intercept_outs:
+ return vmx_check_intercept_io(vcpu, info);
+
+ case x86_intercept_lgdt:
+ case x86_intercept_lidt:
+ case x86_intercept_lldt:
+ case x86_intercept_ltr:
+ case x86_intercept_sgdt:
+ case x86_intercept_sidt:
+ case x86_intercept_sldt:
+ case x86_intercept_str:
+ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC))
+ return X86EMUL_CONTINUE;
+
+ /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */
+ break;
/* TODO: check more intercepts... */
- return X86EMUL_CONTINUE;
+ default:
+ break;
+ }
+
+ return X86EMUL_UNHANDLEABLE;
}
#ifdef CONFIG_X86_64
if (nested) {
nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
- vmx_capability.ept, enable_apicv);
+ vmx_capability.ept);
r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
if (r)
.run = vmx_vcpu_run,
.handle_exit = vmx_handle_exit,
- .skip_emulated_instruction = skip_emulated_instruction,
+ .skip_emulated_instruction = vmx_skip_emulated_instruction,
+ .update_emulated_instruction = vmx_update_emulated_instruction,
.set_interrupt_shadow = vmx_set_interrupt_shadow,
.get_interrupt_shadow = vmx_get_interrupt_shadow,
.patch_hypercall = vmx_patch_hypercall,
extern const u32 vmx_msr_index[];
extern u64 host_efer;
- extern u32 get_umwait_control_msr(void);
-
#define MSR_TYPE_R 1
#define MSR_TYPE_W 2
#define MSR_TYPE_RW 3
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
+ /* Pending MTF VM-exit into L1. */
+ bool mtf_pending;
+
struct loaded_vmcs vmcs02;
/*
} _sifields;
} compat_siginfo_t;
-/*
- * These functions operate on 32- or 64-bit specs depending on
- * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments.
- */
-extern int compat_get_timespec(struct timespec *, const void __user *);
-extern int compat_put_timespec(const struct timespec *, void __user *);
-extern int compat_get_timeval(struct timeval *, const void __user *);
-extern int compat_put_timeval(const struct timeval *, void __user *);
-
struct compat_iovec {
compat_uptr_t iov_base;
compat_size_t iov_len;
int get_compat_sigevent(struct sigevent *event,
const struct compat_sigevent __user *u_event);
-static inline int old_timeval32_compare(struct old_timeval32 *lhs,
- struct old_timeval32 *rhs)
-{
- if (lhs->tv_sec < rhs->tv_sec)
- return -1;
- if (lhs->tv_sec > rhs->tv_sec)
- return 1;
- return lhs->tv_usec - rhs->tv_usec;
-}
-
-static inline int old_timespec32_compare(struct old_timespec32 *lhs,
- struct old_timespec32 *rhs)
-{
- if (lhs->tv_sec < rhs->tv_sec)
- return -1;
- if (lhs->tv_sec > rhs->tv_sec)
- return 1;
- return lhs->tv_nsec - rhs->tv_nsec;
-}
-
extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat);
/*
int compat_restore_altstack(const compat_stack_t __user *uss);
int __compat_save_altstack(compat_stack_t __user *, unsigned long);
- #define compat_save_altstack_ex(uss, sp) do { \
+ #define unsafe_compat_save_altstack(uss, sp, label) do { \
compat_stack_t __user *__uss = uss; \
struct task_struct *t = current; \
- put_user_ex(ptr_to_compat((void __user *)t->sas_ss_sp), &__uss->ss_sp); \
- put_user_ex(t->sas_ss_flags, &__uss->ss_flags); \
- put_user_ex(t->sas_ss_size, &__uss->ss_size); \
+ unsafe_put_user(ptr_to_compat((void __user *)t->sas_ss_sp), \
+ &__uss->ss_sp, label); \
+ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \
+ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \
if (t->sas_ss_flags & SS_AUTODISARM) \
sas_ss_reset(t); \
} while (0);
#define __efiapi
#endif
-#define efi_get_handle_at(array, idx) \
- (efi_is_native() ? (array)[idx] \
- : (efi_handle_t)(unsigned long)((u32 *)(array))[idx])
-
-#define efi_get_handle_num(size) \
- ((size) / (efi_is_native() ? sizeof(efi_handle_t) : sizeof(u32)))
-
-#define for_each_efi_handle(handle, array, size, i) \
- for (i = 0; \
- i < efi_get_handle_num(size) && \
- ((handle = efi_get_handle_at((array), i)) || true); \
- i++)
-
/*
* The UEFI spec and EDK2 reference implementation both define EFI_GUID as
* struct { u32 a; u16; b; u16 c; u8 d[8]; }; and so the implied alignment
u32 imagesize;
} efi_capsule_header_t;
-struct efi_boot_memmap {
- efi_memory_desc_t **map;
- unsigned long *map_size;
- unsigned long *desc_size;
- u32 *desc_ver;
- unsigned long *key_ptr;
- unsigned long *buff_size;
-};
-
/*
* EFI capsule flags
*/
int __efi_capsule_setup_info(struct capsule_info *cap_info);
-/*
- * Allocation types for calls to boottime->allocate_pages.
- */
-#define EFI_ALLOCATE_ANY_PAGES 0
-#define EFI_ALLOCATE_MAX_ADDRESS 1
-#define EFI_ALLOCATE_ADDRESS 2
-#define EFI_MAX_ALLOCATE_TYPE 3
-
typedef int (*efi_freemem_callback_t) (u64 start, u64 end, void *arg);
/*
u8 sets_to_zero;
} efi_time_cap_t;
-typedef struct {
- efi_table_hdr_t hdr;
- u32 raise_tpl;
- u32 restore_tpl;
- u32 allocate_pages;
- u32 free_pages;
- u32 get_memory_map;
- u32 allocate_pool;
- u32 free_pool;
- u32 create_event;
- u32 set_timer;
- u32 wait_for_event;
- u32 signal_event;
- u32 close_event;
- u32 check_event;
- u32 install_protocol_interface;
- u32 reinstall_protocol_interface;
- u32 uninstall_protocol_interface;
- u32 handle_protocol;
- u32 __reserved;
- u32 register_protocol_notify;
- u32 locate_handle;
- u32 locate_device_path;
- u32 install_configuration_table;
- u32 load_image;
- u32 start_image;
- u32 exit;
- u32 unload_image;
- u32 exit_boot_services;
- u32 get_next_monotonic_count;
- u32 stall;
- u32 set_watchdog_timer;
- u32 connect_controller;
- u32 disconnect_controller;
- u32 open_protocol;
- u32 close_protocol;
- u32 open_protocol_information;
- u32 protocols_per_handle;
- u32 locate_handle_buffer;
- u32 locate_protocol;
- u32 install_multiple_protocol_interfaces;
- u32 uninstall_multiple_protocol_interfaces;
- u32 calculate_crc32;
- u32 copy_mem;
- u32 set_mem;
- u32 create_event_ex;
-} __packed efi_boot_services_32_t;
-
-/*
- * EFI Boot Services table
- */
-typedef union {
- struct {
- efi_table_hdr_t hdr;
- void *raise_tpl;
- void *restore_tpl;
- efi_status_t (__efiapi *allocate_pages)(int, int, unsigned long,
- efi_physical_addr_t *);
- efi_status_t (__efiapi *free_pages)(efi_physical_addr_t,
- unsigned long);
- efi_status_t (__efiapi *get_memory_map)(unsigned long *, void *,
- unsigned long *,
- unsigned long *, u32 *);
- efi_status_t (__efiapi *allocate_pool)(int, unsigned long,
- void **);
- efi_status_t (__efiapi *free_pool)(void *);
- void *create_event;
- void *set_timer;
- void *wait_for_event;
- void *signal_event;
- void *close_event;
- void *check_event;
- void *install_protocol_interface;
- void *reinstall_protocol_interface;
- void *uninstall_protocol_interface;
- efi_status_t (__efiapi *handle_protocol)(efi_handle_t,
- efi_guid_t *, void **);
- void *__reserved;
- void *register_protocol_notify;
- efi_status_t (__efiapi *locate_handle)(int, efi_guid_t *,
- void *, unsigned long *,
- efi_handle_t *);
- void *locate_device_path;
- efi_status_t (__efiapi *install_configuration_table)(efi_guid_t *,
- void *);
- void *load_image;
- void *start_image;
- void *exit;
- void *unload_image;
- efi_status_t (__efiapi *exit_boot_services)(efi_handle_t,
- unsigned long);
- void *get_next_monotonic_count;
- void *stall;
- void *set_watchdog_timer;
- void *connect_controller;
- efi_status_t (__efiapi *disconnect_controller)(efi_handle_t,
- efi_handle_t,
- efi_handle_t);
- void *open_protocol;
- void *close_protocol;
- void *open_protocol_information;
- void *protocols_per_handle;
- void *locate_handle_buffer;
- efi_status_t (__efiapi *locate_protocol)(efi_guid_t *, void *,
- void **);
- void *install_multiple_protocol_interfaces;
- void *uninstall_multiple_protocol_interfaces;
- void *calculate_crc32;
- void *copy_mem;
- void *set_mem;
- void *create_event_ex;
- };
- efi_boot_services_32_t mixed_mode;
-} efi_boot_services_t;
-
-typedef enum {
- EfiPciIoWidthUint8,
- EfiPciIoWidthUint16,
- EfiPciIoWidthUint32,
- EfiPciIoWidthUint64,
- EfiPciIoWidthFifoUint8,
- EfiPciIoWidthFifoUint16,
- EfiPciIoWidthFifoUint32,
- EfiPciIoWidthFifoUint64,
- EfiPciIoWidthFillUint8,
- EfiPciIoWidthFillUint16,
- EfiPciIoWidthFillUint32,
- EfiPciIoWidthFillUint64,
- EfiPciIoWidthMaximum
-} EFI_PCI_IO_PROTOCOL_WIDTH;
-
-typedef enum {
- EfiPciIoAttributeOperationGet,
- EfiPciIoAttributeOperationSet,
- EfiPciIoAttributeOperationEnable,
- EfiPciIoAttributeOperationDisable,
- EfiPciIoAttributeOperationSupported,
- EfiPciIoAttributeOperationMaximum
-} EFI_PCI_IO_PROTOCOL_ATTRIBUTE_OPERATION;
-
-typedef struct {
- u32 read;
- u32 write;
-} efi_pci_io_protocol_access_32_t;
-
-typedef union efi_pci_io_protocol efi_pci_io_protocol_t;
-
-typedef
-efi_status_t (__efiapi *efi_pci_io_protocol_cfg_t)(efi_pci_io_protocol_t *,
- EFI_PCI_IO_PROTOCOL_WIDTH,
- u32 offset,
- unsigned long count,
- void *buffer);
-
-typedef struct {
- void *read;
- void *write;
-} efi_pci_io_protocol_access_t;
-
-typedef struct {
- efi_pci_io_protocol_cfg_t read;
- efi_pci_io_protocol_cfg_t write;
-} efi_pci_io_protocol_config_access_t;
-
-union efi_pci_io_protocol {
- struct {
- void *poll_mem;
- void *poll_io;
- efi_pci_io_protocol_access_t mem;
- efi_pci_io_protocol_access_t io;
- efi_pci_io_protocol_config_access_t pci;
- void *copy_mem;
- void *map;
- void *unmap;
- void *allocate_buffer;
- void *free_buffer;
- void *flush;
- efi_status_t (__efiapi *get_location)(efi_pci_io_protocol_t *,
- unsigned long *segment_nr,
- unsigned long *bus_nr,
- unsigned long *device_nr,
- unsigned long *func_nr);
- void *attributes;
- void *get_bar_attributes;
- void *set_bar_attributes;
- uint64_t romsize;
- void *romimage;
- };
- struct {
- u32 poll_mem;
- u32 poll_io;
- efi_pci_io_protocol_access_32_t mem;
- efi_pci_io_protocol_access_32_t io;
- efi_pci_io_protocol_access_32_t pci;
- u32 copy_mem;
- u32 map;
- u32 unmap;
- u32 allocate_buffer;
- u32 free_buffer;
- u32 flush;
- u32 get_location;
- u32 attributes;
- u32 get_bar_attributes;
- u32 set_bar_attributes;
- u64 romsize;
- u32 romimage;
- } mixed_mode;
-};
-
-#define EFI_PCI_IO_ATTRIBUTE_ISA_MOTHERBOARD_IO 0x0001
-#define EFI_PCI_IO_ATTRIBUTE_ISA_IO 0x0002
-#define EFI_PCI_IO_ATTRIBUTE_VGA_PALETTE_IO 0x0004
-#define EFI_PCI_IO_ATTRIBUTE_VGA_MEMORY 0x0008
-#define EFI_PCI_IO_ATTRIBUTE_VGA_IO 0x0010
-#define EFI_PCI_IO_ATTRIBUTE_IDE_PRIMARY_IO 0x0020
-#define EFI_PCI_IO_ATTRIBUTE_IDE_SECONDARY_IO 0x0040
-#define EFI_PCI_IO_ATTRIBUTE_MEMORY_WRITE_COMBINE 0x0080
-#define EFI_PCI_IO_ATTRIBUTE_IO 0x0100
-#define EFI_PCI_IO_ATTRIBUTE_MEMORY 0x0200
-#define EFI_PCI_IO_ATTRIBUTE_BUS_MASTER 0x0400
-#define EFI_PCI_IO_ATTRIBUTE_MEMORY_CACHED 0x0800
-#define EFI_PCI_IO_ATTRIBUTE_MEMORY_DISABLE 0x1000
-#define EFI_PCI_IO_ATTRIBUTE_EMBEDDED_DEVICE 0x2000
-#define EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM 0x4000
-#define EFI_PCI_IO_ATTRIBUTE_DUAL_ADDRESS_CYCLE 0x8000
-#define EFI_PCI_IO_ATTRIBUTE_ISA_IO_16 0x10000
-#define EFI_PCI_IO_ATTRIBUTE_VGA_PALETTE_IO_16 0x20000
-#define EFI_PCI_IO_ATTRIBUTE_VGA_IO_16 0x40000
-
-struct efi_dev_path;
-
-typedef union apple_properties_protocol apple_properties_protocol_t;
-
-union apple_properties_protocol {
- struct {
- unsigned long version;
- efi_status_t (__efiapi *get)(apple_properties_protocol_t *,
- struct efi_dev_path *,
- efi_char16_t *, void *, u32 *);
- efi_status_t (__efiapi *set)(apple_properties_protocol_t *,
- struct efi_dev_path *,
- efi_char16_t *, void *, u32);
- efi_status_t (__efiapi *del)(apple_properties_protocol_t *,
- struct efi_dev_path *,
- efi_char16_t *);
- efi_status_t (__efiapi *get_all)(apple_properties_protocol_t *,
- void *buffer, u32 *);
- };
- struct {
- u32 version;
- u32 get;
- u32 set;
- u32 del;
- u32 get_all;
- } mixed_mode;
-};
-
-typedef u32 efi_tcg2_event_log_format;
-
-typedef union efi_tcg2_protocol efi_tcg2_protocol_t;
-
-union efi_tcg2_protocol {
- struct {
- void *get_capability;
- efi_status_t (__efiapi *get_event_log)(efi_handle_t,
- efi_tcg2_event_log_format,
- efi_physical_addr_t *,
- efi_physical_addr_t *,
- efi_bool_t *);
- void *hash_log_extend_event;
- void *submit_command;
- void *get_active_pcr_banks;
- void *set_active_pcr_banks;
- void *get_result_of_set_active_pcr_banks;
- };
- struct {
- u32 get_capability;
- u32 get_event_log;
- u32 hash_log_extend_event;
- u32 submit_command;
- u32 get_active_pcr_banks;
- u32 set_active_pcr_banks;
- u32 get_result_of_set_active_pcr_banks;
- } mixed_mode;
-};
+typedef union efi_boot_services efi_boot_services_t;
/*
* Types and defines for EFI ResetSystem
#define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
#define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0)
#define EFI_TCG2_PROTOCOL_GUID EFI_GUID(0x607f766c, 0x7455, 0x42be, 0x93, 0x0b, 0xe4, 0xd7, 0x6d, 0xb2, 0x72, 0x0f)
+#define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
+#define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d)
+#define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9)
#define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f)
#define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23)
#define LINUX_EFI_TPM_EVENT_LOG_GUID EFI_GUID(0xb7799cb0, 0xeca2, 0x4943, 0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa)
#define LINUX_EFI_TPM_FINAL_LOG_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25)
#define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2)
+#define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68)
/* OEM GUIDs */
#define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
u64 attribute;
};
-struct efi_fdt_params {
- u64 system_table;
- u64 mmap;
- u32 mmap_size;
- u32 desc_size;
- u32 desc_ver;
-};
-
-typedef struct {
- u32 revision;
- efi_handle_t parent_handle;
- efi_system_table_t *system_table;
- efi_handle_t device_handle;
- void *file_path;
- void *reserved;
- u32 load_options_size;
- void *load_options;
- void *image_base;
- __aligned_u64 image_size;
- unsigned int image_code_type;
- unsigned int image_data_type;
- efi_status_t ( __efiapi *unload)(efi_handle_t image_handle);
-} efi_loaded_image_t;
-
-typedef struct {
- u64 size;
- u64 file_size;
- u64 phys_size;
- efi_time_t create_time;
- efi_time_t last_access_time;
- efi_time_t modification_time;
- __aligned_u64 attribute;
- efi_char16_t filename[1];
-} efi_file_info_t;
-
-typedef struct efi_file_handle efi_file_handle_t;
-
-struct efi_file_handle {
- u64 revision;
- efi_status_t (__efiapi *open)(efi_file_handle_t *,
- efi_file_handle_t **,
- efi_char16_t *, u64, u64);
- efi_status_t (__efiapi *close)(efi_file_handle_t *);
- void *delete;
- efi_status_t (__efiapi *read)(efi_file_handle_t *,
- unsigned long *, void *);
- void *write;
- void *get_position;
- void *set_position;
- efi_status_t (__efiapi *get_info)(efi_file_handle_t *,
- efi_guid_t *, unsigned long *,
- void *);
- void *set_info;
- void *flush;
-};
-
-typedef struct efi_file_io_interface efi_file_io_interface_t;
-
-struct efi_file_io_interface {
- u64 revision;
- int (__efiapi *open_volume)(efi_file_io_interface_t *,
- efi_file_handle_t **);
-};
-
-#define EFI_FILE_MODE_READ 0x0000000000000001
-#define EFI_FILE_MODE_WRITE 0x0000000000000002
-#define EFI_FILE_MODE_CREATE 0x8000000000000000
-
typedef struct {
u32 version;
u32 length;
#define EFI_PROPERTIES_TABLE_VERSION 0x00010000
#define EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA 0x1
+typedef struct {
+ u16 version;
+ u16 length;
+ u32 runtime_services_supported;
+} efi_rt_properties_table_t;
+
+#define EFI_RT_PROPERTIES_TABLE_VERSION 0x1
+
#define EFI_INVALID_TABLE_ADDR (~0UL)
typedef struct {
efi_time_t time_of_revocation;
} efi_cert_x509_sha256_t;
+extern unsigned long __ro_after_init efi_rng_seed; /* RNG Seed table */
+
/*
* All runtime access to EFI goes through this structure:
*/
extern struct efi {
- efi_system_table_t *systab; /* EFI system table */
- unsigned int runtime_version; /* Runtime services version */
- unsigned long mps; /* MPS table */
- unsigned long acpi; /* ACPI table (IA64 ext 0.71) */
- unsigned long acpi20; /* ACPI table (ACPI 2.0) */
- unsigned long smbios; /* SMBIOS table (32 bit entry point) */
- unsigned long smbios3; /* SMBIOS table (64 bit entry point) */
- unsigned long boot_info; /* boot info table */
- unsigned long hcdp; /* HCDP table */
- unsigned long uga; /* UGA table */
- unsigned long fw_vendor; /* fw_vendor */
- unsigned long runtime; /* runtime table */
- unsigned long config_table; /* config tables */
- unsigned long esrt; /* ESRT table */
- unsigned long properties_table; /* properties table */
- unsigned long mem_attr_table; /* memory attributes table */
- unsigned long rng_seed; /* UEFI firmware random seed */
- unsigned long tpm_log; /* TPM2 Event Log table */
- unsigned long tpm_final_log; /* TPM2 Final Events Log table */
- unsigned long mem_reserve; /* Linux EFI memreserve table */
- efi_get_time_t *get_time;
- efi_set_time_t *set_time;
- efi_get_wakeup_time_t *get_wakeup_time;
- efi_set_wakeup_time_t *set_wakeup_time;
- efi_get_variable_t *get_variable;
- efi_get_next_variable_t *get_next_variable;
- efi_set_variable_t *set_variable;
- efi_set_variable_t *set_variable_nonblocking;
- efi_query_variable_info_t *query_variable_info;
- efi_query_variable_info_t *query_variable_info_nonblocking;
- efi_update_capsule_t *update_capsule;
- efi_query_capsule_caps_t *query_capsule_caps;
- efi_get_next_high_mono_count_t *get_next_high_mono_count;
- efi_reset_system_t *reset_system;
- struct efi_memory_map memmap;
- unsigned long flags;
+ const efi_runtime_services_t *runtime; /* EFI runtime services table */
+ unsigned int runtime_version; /* Runtime services version */
+ unsigned int runtime_supported_mask;
+
+ unsigned long acpi; /* ACPI table (IA64 ext 0.71) */
+ unsigned long acpi20; /* ACPI table (ACPI 2.0) */
+ unsigned long smbios; /* SMBIOS table (32 bit entry point) */
+ unsigned long smbios3; /* SMBIOS table (64 bit entry point) */
+ unsigned long esrt; /* ESRT table */
+ unsigned long tpm_log; /* TPM2 Event Log table */
+ unsigned long tpm_final_log; /* TPM2 Final Events Log table */
+
+ efi_get_time_t *get_time;
+ efi_set_time_t *set_time;
+ efi_get_wakeup_time_t *get_wakeup_time;
+ efi_set_wakeup_time_t *set_wakeup_time;
+ efi_get_variable_t *get_variable;
+ efi_get_next_variable_t *get_next_variable;
+ efi_set_variable_t *set_variable;
+ efi_set_variable_t *set_variable_nonblocking;
+ efi_query_variable_info_t *query_variable_info;
+ efi_query_variable_info_t *query_variable_info_nonblocking;
+ efi_update_capsule_t *update_capsule;
+ efi_query_capsule_caps_t *query_capsule_caps;
+ efi_get_next_high_mono_count_t *get_next_high_mono_count;
+ efi_reset_system_t *reset_system;
+
+ struct efi_memory_map memmap;
+ unsigned long flags;
} efi;
+#define EFI_RT_SUPPORTED_GET_TIME 0x0001
+#define EFI_RT_SUPPORTED_SET_TIME 0x0002
+#define EFI_RT_SUPPORTED_GET_WAKEUP_TIME 0x0004
+#define EFI_RT_SUPPORTED_SET_WAKEUP_TIME 0x0008
+#define EFI_RT_SUPPORTED_GET_VARIABLE 0x0010
+#define EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME 0x0020
+#define EFI_RT_SUPPORTED_SET_VARIABLE 0x0040
+#define EFI_RT_SUPPORTED_SET_VIRTUAL_ADDRESS_MAP 0x0080
+#define EFI_RT_SUPPORTED_CONVERT_POINTER 0x0100
+#define EFI_RT_SUPPORTED_GET_NEXT_HIGH_MONOTONIC_COUNT 0x0200
+#define EFI_RT_SUPPORTED_RESET_SYSTEM 0x0400
+#define EFI_RT_SUPPORTED_UPDATE_CAPSULE 0x0800
+#define EFI_RT_SUPPORTED_QUERY_CAPSULE_CAPABILITIES 0x1000
+#define EFI_RT_SUPPORTED_QUERY_VARIABLE_INFO 0x2000
+
+#define EFI_RT_SUPPORTED_ALL 0x3fff
+
+#define EFI_RT_SUPPORTED_TIME_SERVICES 0x000f
+#define EFI_RT_SUPPORTED_VARIABLE_SERVICES 0x0070
+
extern struct mm_struct efi_mm;
static inline int
extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap,
void *buf, struct efi_mem_range *mem);
-extern int efi_config_init(efi_config_table_type_t *arch_tables);
#ifdef CONFIG_EFI_ESRT
extern void __init efi_esrt_init(void);
#else
static inline void efi_esrt_init(void) { }
#endif
-extern int efi_config_parse_tables(void *config_tables, int count, int sz,
- efi_config_table_type_t *arch_tables);
+extern int efi_config_parse_tables(const efi_config_table_t *config_tables,
+ int count,
+ const efi_config_table_type_t *arch_tables);
+extern int efi_systab_check_header(const efi_table_hdr_t *systab_hdr,
+ int min_major_version);
+extern void efi_systab_report_header(const efi_table_hdr_t *systab_hdr,
+ unsigned long fw_vendor);
extern u64 efi_get_iobase (void);
extern int efi_mem_type(unsigned long phys_addr);
extern u64 efi_mem_attributes (unsigned long phys_addr);
extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size);
extern void efi_initialize_iomem_resources(struct resource *code_resource,
struct resource *data_resource, struct resource *bss_resource);
-extern int efi_get_fdt_params(struct efi_fdt_params *params);
+extern u64 efi_get_fdt_params(struct efi_memory_map_data *data);
extern struct kobject *efi_kobj;
extern int efi_reboot_quirk_mode;
static inline void efi_fake_memmap(void) { }
#endif
+extern unsigned long efi_mem_attr_table;
+
/*
* efi_memattr_perm_setter - arch specific callback function passed into
* efi_memattr_apply_permissions() that updates the
#define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */
#define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
#define EFI_MEM_NO_SOFT_RESERVE 11 /* Is the kernel configured to ignore soft reservations? */
+#define EFI_PRESERVE_BS_REGIONS 12 /* Are EFI boot-services memory segments available? */
#ifdef CONFIG_EFI
/*
return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE)
&& __efi_soft_reserve_enabled();
}
+
+static inline bool efi_rt_services_supported(unsigned int mask)
+{
+ return (efi.runtime_supported_mask & mask) == mask;
+}
#else
static inline bool efi_enabled(int feature)
{
{
return false;
}
+
+static inline bool efi_rt_services_supported(unsigned int mask)
+{
+ return false;
+}
#endif
extern int efi_status_to_err(efi_status_t status);
#define EFI_VARIABLE_GUID_LEN UUID_STRING_LEN
/*
- * The type of search to perform when calling boottime->locate_handle
- */
-#define EFI_LOCATE_ALL_HANDLES 0
-#define EFI_LOCATE_BY_REGISTER_NOTIFY 1
-#define EFI_LOCATE_BY_PROTOCOL 2
-
-/*
* EFI Device Path information
*/
#define EFI_DEV_HW 0x01
#define EFI_DEV_END_ENTIRE 0xFF
struct efi_generic_dev_path {
- u8 type;
- u8 sub_type;
- u16 length;
-} __attribute ((packed));
+ u8 type;
+ u8 sub_type;
+ u16 length;
+} __packed;
+
+struct efi_acpi_dev_path {
+ struct efi_generic_dev_path header;
+ u32 hid;
+ u32 uid;
+} __packed;
+
+struct efi_pci_dev_path {
+ struct efi_generic_dev_path header;
+ u8 fn;
+ u8 dev;
+} __packed;
+
+struct efi_vendor_dev_path {
+ struct efi_generic_dev_path header;
+ efi_guid_t vendorguid;
+ u8 vendordata[];
+} __packed;
struct efi_dev_path {
- u8 type; /* can be replaced with unnamed */
- u8 sub_type; /* struct efi_generic_dev_path; */
- u16 length; /* once we've moved to -std=c11 */
union {
- struct {
- u32 hid;
- u32 uid;
- } acpi;
- struct {
- u8 fn;
- u8 dev;
- } pci;
+ struct efi_generic_dev_path header;
+ struct efi_acpi_dev_path acpi;
+ struct efi_pci_dev_path pci;
+ struct efi_vendor_dev_path vendor;
};
-} __attribute ((packed));
+} __packed;
-#if IS_ENABLED(CONFIG_EFI_DEV_PATH_PARSER)
-struct device *efi_get_device_by_path(struct efi_dev_path **node, size_t *len);
-#endif
+struct device *efi_get_device_by_path(const struct efi_dev_path **node,
+ size_t *len);
static inline void memrange_efi_to_native(u64 *addr, u64 *npages)
{
bool deleting;
};
-union efi_simple_text_output_protocol {
- struct {
- void *reset;
- efi_status_t (__efiapi *output_string)(efi_simple_text_output_protocol_t *,
- efi_char16_t *);
- void *test_string;
- };
- struct {
- u32 reset;
- u32 output_string;
- u32 test_string;
- } mixed_mode;
-};
-
-#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0
-#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1
-#define PIXEL_BIT_MASK 2
-#define PIXEL_BLT_ONLY 3
-#define PIXEL_FORMAT_MAX 4
-
-typedef struct {
- u32 red_mask;
- u32 green_mask;
- u32 blue_mask;
- u32 reserved_mask;
-} efi_pixel_bitmask_t;
-
-typedef struct {
- u32 version;
- u32 horizontal_resolution;
- u32 vertical_resolution;
- int pixel_format;
- efi_pixel_bitmask_t pixel_information;
- u32 pixels_per_scan_line;
-} efi_graphics_output_mode_info_t;
-
-typedef union efi_graphics_output_protocol_mode efi_graphics_output_protocol_mode_t;
-
-union efi_graphics_output_protocol_mode {
- struct {
- u32 max_mode;
- u32 mode;
- efi_graphics_output_mode_info_t *info;
- unsigned long size_of_info;
- efi_physical_addr_t frame_buffer_base;
- unsigned long frame_buffer_size;
- };
- struct {
- u32 max_mode;
- u32 mode;
- u32 info;
- u32 size_of_info;
- u64 frame_buffer_base;
- u32 frame_buffer_size;
- } mixed_mode;
-};
-
-typedef union efi_graphics_output_protocol efi_graphics_output_protocol_t;
-
-union efi_graphics_output_protocol {
- struct {
- void *query_mode;
- void *set_mode;
- void *blt;
- efi_graphics_output_protocol_mode_t *mode;
- };
- struct {
- u32 query_mode;
- u32 set_mode;
- u32 blt;
- u32 mode;
- } mixed_mode;
-};
-
extern struct list_head efivar_sysfs_list;
static inline void
#endif
-/* prototypes shared between arch specific and generic stub code */
-
-void efi_printk(char *str);
-
-void efi_free(unsigned long size, unsigned long addr);
-
-char *efi_convert_cmdline(efi_loaded_image_t *image, int *cmd_line_len);
-
-efi_status_t efi_get_memory_map(struct efi_boot_memmap *map);
-
-efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align,
- unsigned long *addr, unsigned long min);
-
-static inline
-efi_status_t efi_low_alloc(unsigned long size, unsigned long align,
- unsigned long *addr)
-{
- /*
- * Don't allocate at 0x0. It will confuse code that
- * checks pointers against NULL. Skip the first 8
- * bytes so we start at a nice even number.
- */
- return efi_low_alloc_above(size, align, addr, 0x8);
-}
-
-efi_status_t efi_high_alloc(unsigned long size, unsigned long align,
- unsigned long *addr, unsigned long max);
-
-efi_status_t efi_relocate_kernel(unsigned long *image_addr,
- unsigned long image_size,
- unsigned long alloc_size,
- unsigned long preferred_addr,
- unsigned long alignment,
- unsigned long min_addr);
-
-efi_status_t handle_cmdline_files(efi_loaded_image_t *image,
- char *cmd_line, char *option_string,
- unsigned long max_addr,
- unsigned long *load_addr,
- unsigned long *load_size);
-
-efi_status_t efi_parse_options(char const *cmdline);
-
-efi_status_t efi_setup_gop(struct screen_info *si, efi_guid_t *proto,
- unsigned long size);
-
#ifdef CONFIG_EFI
extern bool efi_runtime_disabled(void);
#else
efi_enable_reset_attack_mitigation(void) { }
#endif
+#ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
+void efi_check_for_embedded_firmwares(void);
+#else
+static inline void efi_check_for_embedded_firmwares(void) { }
+#endif
+
efi_status_t efi_random_get_seed(void);
void efi_retrieve_tpm2_eventlog(void);
arch_efi_call_virt_teardown(); \
})
-typedef efi_status_t (*efi_exit_boot_map_processing)(
- struct efi_boot_memmap *map,
- void *priv);
-
-efi_status_t efi_exit_boot_services(void *handle,
- struct efi_boot_memmap *map,
- void *priv,
- efi_exit_boot_map_processing priv_func);
-
#define EFI_RANDOM_SEED_SIZE 64U
struct linux_efi_random_seed {
#define EFI_MEMRESERVE_COUNT(size) (((size) - sizeof(struct linux_efi_memreserve)) \
/ sizeof(((struct linux_efi_memreserve *)0)->entry[0]))
-void efi_pci_disable_bridge_busmaster(void);
-
+ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size);
+
#endif /* _LINUX_EFI_H */