Commit 9fb71c2f authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "A set of fixes and updates for x86:

   - Address a swiotlb regression which was caused by the recent DMA
     rework and made driver fail because dma_direct_supported() returned
     false

   - Fix a signedness bug in the APIC ID validation which caused invalid
     APIC IDs to be detected as valid thereby bloating the CPU possible
     space.

   - Fix inconsisten config dependcy/select magic for the MFD_CS5535
     driver.

   - Fix a corruption of the physical address space bits when encryption
     has reduced the address space and late cpuinfo updates overwrite
     the reduced bit information with the original value.

   - Dominiks syscall rework which consolidates the architecture
     specific syscall functions so all syscalls can be wrapped with the
     same macros. This allows to switch x86/64 to struct pt_regs based
     syscalls. Extend the clearing of user space controlled registers in
     the entry patch to the lower registers"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic: Fix signedness bug in APIC ID validity checks
  x86/cpu: Prevent cpuinfo_x86::x86_phys_bits adjustment corruption
  x86/olpc: Fix inconsistent MFD_CS5535 configuration
  swiotlb: Use dma_direct_supported() for swiotlb_ops
  syscalls/x86: Adapt syscall_wrapper.h to the new syscall stub naming convention
  syscalls/core, syscalls/x86: Rename struct pt_regs-based sys_*() to __x64_sys_*()
  syscalls/core, syscalls/x86: Clean up compat syscall stub naming convention
  syscalls/core, syscalls/x86: Clean up syscall stub naming convention
  syscalls/x86: Extend register clearing on syscall entry to lower registers
  syscalls/x86: Unconditionally enable 'struct pt_regs' based syscalls on x86_64
  syscalls/x86: Use 'struct pt_regs' based syscall calling for IA32_EMULATION and x32
  syscalls/core: Prepare CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y for compat syscalls
  syscalls/x86: Use 'struct pt_regs' based syscall calling convention for 64-bit syscalls
  syscalls/core: Introduce CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y
  x86/syscalls: Don't pointlessly reload the system call number
  x86/mm: Fix documentation of module mapping range with 4-level paging
  x86/cpuid: Switch to 'static const' specifier
parents 6b0a02e8 ef389b73
......@@ -360,7 +360,7 @@ First, the entry in ``arch/x86/entry/syscalls/syscall_32.tbl`` gets an extra
column to indicate that a 32-bit userspace program running on a 64-bit kernel
should hit the compat entry point::
380 i386 xyzzy sys_xyzzy compat_sys_xyzzy
380 i386 xyzzy sys_xyzzy __ia32_compat_sys_xyzzy
Second, you need to figure out what should happen for the x32 ABI version of
the new system call. There's a choice here: the layout of the arguments
......@@ -373,7 +373,7 @@ the compatibility wrapper::
333 64 xyzzy sys_xyzzy
...
555 x32 xyzzy compat_sys_xyzzy
555 x32 xyzzy __x32_compat_sys_xyzzy
If no pointers are involved, then it is preferable to re-use the 64-bit system
call for the x32 ABI (and consequently the entry in
......
......@@ -20,7 +20,7 @@ ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
... unused hole ...
ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0
ffffffffa0000000 - [fixmap start] (~1526 MB) module mapping space (variable)
ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space
[fixmap start] - ffffffffff5fffff kernel-internal fixmap range
ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
......
......@@ -29,6 +29,7 @@ config X86_64
select HAVE_ARCH_SOFT_DIRTY
select MODULES_USE_ELF_RELA
select X86_DEV_DMA_OPS
select ARCH_HAS_SYSCALL_WRAPPER
#
# Arch settings
......@@ -2763,11 +2764,9 @@ config OLPC_XO1_RTC
config OLPC_XO1_SCI
bool "OLPC XO-1 SCI extras"
depends on OLPC && OLPC_XO1_PM
depends on OLPC && OLPC_XO1_PM && GPIO_CS5535=y
depends on INPUT=y
select POWER_SUPPLY
select GPIO_CS5535
select MFD_CORE
---help---
Add support for SCI-based features of the OLPC XO-1 laptop:
- EC-driven system wakeups
......
......@@ -114,7 +114,9 @@ For 32-bit we have the following conventions - kernel is built with
pushq %rsi /* pt_regs->si */
.endif
pushq \rdx /* pt_regs->dx */
xorl %edx, %edx /* nospec dx */
pushq %rcx /* pt_regs->cx */
xorl %ecx, %ecx /* nospec cx */
pushq \rax /* pt_regs->ax */
pushq %r8 /* pt_regs->r8 */
xorl %r8d, %r8d /* nospec r8 */
......
......@@ -266,14 +266,13 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
}
#ifdef CONFIG_X86_64
__visible void do_syscall_64(struct pt_regs *regs)
__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
{
struct thread_info *ti = current_thread_info();
unsigned long nr = regs->orig_ax;
struct thread_info *ti;
enter_from_user_mode();
local_irq_enable();
ti = current_thread_info();
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
nr = syscall_trace_enter(regs);
......@@ -282,11 +281,10 @@ __visible void do_syscall_64(struct pt_regs *regs)
* table. The only functional difference is the x32 bit in
* regs->orig_ax, which changes the behavior of some syscalls.
*/
if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) {
nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls);
regs->ax = sys_call_table[nr](
regs->di, regs->si, regs->dx,
regs->r10, regs->r8, regs->r9);
nr &= __SYSCALL_MASK;
if (likely(nr < NR_syscalls)) {
nr = array_index_nospec(nr, NR_syscalls);
regs->ax = sys_call_table[nr](regs);
}
syscall_return_slowpath(regs);
......@@ -321,6 +319,9 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
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
......@@ -331,6 +332,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
(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);
......
......@@ -233,7 +233,8 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
TRACE_IRQS_OFF
/* IRQs are off. */
movq %rsp, %rdi
movq %rax, %rdi
movq %rsp, %rsi
call do_syscall_64 /* returns with IRQs disabled */
TRACE_IRQS_IRETQ /* we're about to change IF */
......
......@@ -220,8 +220,11 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
pushq %rax /* pt_regs->orig_ax */
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
xorl %esi, %esi /* nospec si */
pushq %rdx /* pt_regs->dx */
xorl %edx, %edx /* nospec dx */
pushq %rbp /* pt_regs->cx (stashed in bp) */
xorl %ecx, %ecx /* nospec cx */
pushq $-ENOSYS /* pt_regs->ax */
pushq $0 /* pt_regs->r8 = 0 */
xorl %r8d, %r8d /* nospec r8 */
......@@ -365,8 +368,11 @@ ENTRY(entry_INT80_compat)
pushq (%rdi) /* pt_regs->di */
pushq %rsi /* pt_regs->si */
xorl %esi, %esi /* nospec si */
pushq %rdx /* pt_regs->dx */
xorl %edx, %edx /* nospec dx */
pushq %rcx /* pt_regs->cx */
xorl %ecx, %ecx /* nospec cx */
pushq $-ENOSYS /* pt_regs->ax */
pushq $0 /* pt_regs->r8 = 0 */
xorl %r8d, %r8d /* nospec r8 */
......
......@@ -7,14 +7,23 @@
#include <asm/asm-offsets.h>
#include <asm/syscall.h>
#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
#ifdef CONFIG_IA32_EMULATION
/* On X86_64, we use struct pt_regs * to pass parameters to syscalls */
#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
#else /* CONFIG_IA32_EMULATION */
#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
#endif /* CONFIG_IA32_EMULATION */
#include <asm/syscalls_32.h>
#undef __SYSCALL_I386
#define __SYSCALL_I386(nr, sym, qual) [nr] = sym,
extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
......
......@@ -7,14 +7,14 @@
#include <asm/asm-offsets.h>
#include <asm/syscall.h>
#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
#include <asm/syscalls_64.h>
#undef __SYSCALL_64
#define __SYSCALL_64(nr, sym, qual) [nr] = sym,
extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
......
This diff is collapsed.
This diff is collapsed.
......@@ -25,15 +25,27 @@ emit() {
nr="$2"
entry="$3"
compat="$4"
umlentry=""
if [ "$abi" = "64" -a -n "$compat" ]; then
echo "a compat entry for a 64-bit syscall makes no sense" >&2
exit 1
fi
# For CONFIG_UML, we need to strip the __x64_sys prefix
if [ "$abi" = "64" -a "${entry}" != "${entry#__x64_sys}" ]; then
umlentry="sys${entry#__x64_sys}"
fi
if [ -z "$compat" ]; then
if [ -n "$entry" ]; then
if [ -n "$entry" -a -z "$umlentry" ]; then
syscall_macro "$abi" "$nr" "$entry"
elif [ -n "$umlentry" ]; then # implies -n "$entry"
echo "#ifdef CONFIG_X86"
syscall_macro "$abi" "$nr" "$entry"
echo "#else /* CONFIG_UML */"
syscall_macro "$abi" "$nr" "$umlentry"
echo "#endif"
fi
else
echo "#ifdef CONFIG_X86_32"
......
......@@ -127,6 +127,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
int vsyscall_nr, syscall_nr, tmp;
int prev_sig_on_uaccess_err;
long ret;
unsigned long orig_dx;
/*
* No point in checking CS -- the only way to get here is a user mode
......@@ -227,19 +228,22 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
ret = -EFAULT;
switch (vsyscall_nr) {
case 0:
ret = sys_gettimeofday(
(struct timeval __user *)regs->di,
(struct timezone __user *)regs->si);
/* this decodes regs->di and regs->si on its own */
ret = __x64_sys_gettimeofday(regs);
break;
case 1:
ret = sys_time((time_t __user *)regs->di);
/* this decodes regs->di on its own */
ret = __x64_sys_time(regs);
break;
case 2:
ret = sys_getcpu((unsigned __user *)regs->di,
(unsigned __user *)regs->si,
NULL);
/* while we could clobber regs->dx, we didn't in the past... */
orig_dx = regs->dx;
regs->dx = 0;
/* this decodes regs->di, regs->si and regs->dx on its own */
ret = __x64_sys_getcpu(regs);
regs->dx = orig_dx;
break;
}
......
......@@ -313,7 +313,7 @@ struct apic {
/* Probe, setup and smpboot functions */
int (*probe)(void);
int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
int (*apic_id_valid)(int apicid);
int (*apic_id_valid)(u32 apicid);
int (*apic_id_registered)(void);
bool (*check_apicid_used)(physid_mask_t *map, int apicid);
......@@ -486,7 +486,7 @@ static inline unsigned int read_apic_id(void)
return apic->get_apic_id(reg);
}
extern int default_apic_id_valid(int apicid);
extern int default_apic_id_valid(u32 apicid);
extern int default_acpi_madt_oem_check(char *, char *);
extern void default_setup_apic_routing(void);
......
......@@ -20,9 +20,13 @@
#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 */
extern const sys_call_ptr_t sys_call_table[];
#if defined(CONFIG_X86_32)
......
/* SPDX-License-Identifier: GPL-2.0 */
/*
* syscall_wrapper.h - x86 specific wrappers to syscall definitions
*/
#ifndef _ASM_X86_SYSCALL_WRAPPER_H
#define _ASM_X86_SYSCALL_WRAPPER_H
/* Mapping of registers to parameters for syscalls on x86-64 and x32 */
#define SC_X86_64_REGS_TO_ARGS(x, ...) \
__MAP(x,__SC_ARGS \
,,regs->di,,regs->si,,regs->dx \
,,regs->r10,,regs->r8,,regs->r9) \
/* Mapping of registers to parameters for syscalls on i386 */
#define SC_IA32_REGS_TO_ARGS(x, ...) \
__MAP(x,__SC_ARGS \
,,(unsigned int)regs->bx,,(unsigned int)regs->cx \
,,(unsigned int)regs->dx,,(unsigned int)regs->si \
,,(unsigned int)regs->di,,(unsigned int)regs->bp)
#ifdef CONFIG_IA32_EMULATION
/*
* For IA32 emulation, we need to handle "compat" syscalls *and* create
* additional wrappers (aptly named __ia32_sys_xyzzy) which decode the
* ia32 regs in the proper order for shared or "common" syscalls. As some
* syscalls may not be implemented, we need to expand COND_SYSCALL in
* kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
* case as well.
*/
#define __IA32_COMPAT_SYS_STUBx(x, name, ...) \
asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\
ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \
asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\
{ \
return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\
} \
#define __IA32_SYS_STUBx(x, name, ...) \
asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \
ALLOW_ERROR_INJECTION(__ia32_sys##name, ERRNO); \
asmlinkage long __ia32_sys##name(const struct pt_regs *regs) \
{ \
return __se_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\
}
/*
* To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias
* named __ia32_sys_*()
*/
#define SYSCALL_DEFINE0(sname) \
SYSCALL_METADATA(_##sname, 0); \
asmlinkage long __x64_sys_##sname(void); \
ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \
SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \
asmlinkage long __x64_sys_##sname(void)
#define COND_SYSCALL(name) \
cond_syscall(__x64_sys_##name); \
cond_syscall(__ia32_sys_##name)
#define SYS_NI(name) \
SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \
SYSCALL_ALIAS(__ia32_sys_##name, sys_ni_posix_timers)
#else /* CONFIG_IA32_EMULATION */
#define __IA32_COMPAT_SYS_STUBx(x, name, ...)
#define __IA32_SYS_STUBx(x, fullname, name, ...)
#endif /* CONFIG_IA32_EMULATION */
#ifdef CONFIG_X86_X32
/*
* For the x32 ABI, we need to create a stub for compat_sys_*() which is aware
* of the x86-64-style parameter ordering of x32 syscalls. The syscalls common
* with x86_64 obviously do not need such care.
*/
#define __X32_COMPAT_SYS_STUBx(x, name, ...) \
asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\
ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \
asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\
{ \
return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\
} \
#else /* CONFIG_X86_X32 */
#define __X32_COMPAT_SYS_STUBx(x, name, ...)
#endif /* CONFIG_X86_X32 */
#ifdef CONFIG_COMPAT
/*
* Compat means IA32_EMULATION and/or X86_X32. As they use a different
* mapping of registers to parameters, we need to generate stubs for each
* of them.
*/
#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
__IA32_COMPAT_SYS_STUBx(x, name, __VA_ARGS__) \
__X32_COMPAT_SYS_STUBx(x, name, __VA_ARGS__) \
static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
} \
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
/*
* As some compat syscalls may not be implemented, we need to expand
* COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
* kernel/time/posix-stubs.c to cover this case as well.
*/
#define COND_SYSCALL_COMPAT(name) \
cond_syscall(__ia32_compat_sys_##name); \
cond_syscall(__x32_compat_sys_##name)
#define COMPAT_SYS_NI(name) \
SYSCALL_ALIAS(__ia32_compat_sys_##name, sys_ni_posix_timers); \
SYSCALL_ALIAS(__x32_compat_sys_##name, sys_ni_posix_timers)
#endif /* CONFIG_COMPAT */
/*
* Instead of the generic __SYSCALL_DEFINEx() definition, this macro takes
* struct pt_regs *regs as the only argument of the syscall stub named
* __x64_sys_*(). It decodes just the registers it needs and passes them on to
* the __se_sys_*() wrapper performing sign extension and then to the
* __do_sys_*() function doing the actual job. These wrappers and functions
* are inlined (at least in very most cases), meaning that the assembly looks
* as follows (slightly re-ordered for better readability):
*
* <__x64_sys_recv>: <-- syscall with 4 parameters
* callq <__fentry__>
*
* mov 0x70(%rdi),%rdi <-- decode regs->di
* mov 0x68(%rdi),%rsi <-- decode regs->si
* mov 0x60(%rdi),%rdx <-- decode regs->dx
* mov 0x38(%rdi),%rcx <-- decode regs->r10
*
* xor %r9d,%r9d <-- clear %r9
* xor %r8d,%r8d <-- clear %r8
*
* callq __sys_recvfrom <-- do the actual work in __sys_recvfrom()
* which takes 6 arguments
*
* cltq <-- extend return value to 64-bit
* retq <-- return
*
* This approach avoids leaking random user-provided register content down
* the call chain.
*
* If IA32_EMULATION is enabled, this macro generates an additional wrapper
* named __ia32_sys_*() which decodes the struct pt_regs *regs according
* to the i386 calling convention (bx, cx, dx, si, di, bp).
*/
#define __SYSCALL_DEFINEx(x, name, ...) \
asmlinkage long __x64_sys##name(const struct pt_regs *regs); \
ALLOW_ERROR_INJECTION(__x64_sys##name, ERRNO); \
static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
asmlinkage long __x64_sys##name(const struct pt_regs *regs) \
{ \
return __se_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\
} \
__IA32_SYS_STUBx(x, name, __VA_ARGS__) \
static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\
__MAP(x,__SC_TEST,__VA_ARGS__); \
__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
return ret; \
} \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
/*
* As the generic SYSCALL_DEFINE0() macro does not decode any parameters for
* obvious reasons, and passing struct pt_regs *regs to it in %rdi does not
* hurt, we only need to re-define it here to keep the naming congruent to
* SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI()
* macros to work correctly.
*/
#ifndef SYSCALL_DEFINE0
#define SYSCALL_DEFINE0(sname) \
SYSCALL_METADATA(_##sname, 0); \
asmlinkage long __x64_sys_##sname(void); \
ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \
asmlinkage long __x64_sys_##sname(void)
#endif
#ifndef COND_SYSCALL
#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name)
#endif
#ifndef SYS_NI
#define SYS_NI(name) SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers);
#endif
/*
* For VSYSCALLS, we need to declare these three syscalls with the new
* pt_regs-based calling convention for in-kernel use.
*/
struct pt_regs;
asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs);
asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs);
asmlinkage long __x64_sys_time(const struct pt_regs *regs);
#endif /* _ASM_X86_SYSCALL_WRAPPER_H */
......@@ -18,6 +18,12 @@
/* Common in X86_32 and X86_64 */
/* kernel/ioport.c */
long ksys_ioperm(unsigned long from, unsigned long num, int turn_on);
#ifdef CONFIG_X86_32
/*
* These definitions are only valid on pure 32-bit systems; x86-64 uses a
* different syscall calling convention
*/
asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
asmlinkage long sys_iopl(unsigned int);
......@@ -32,7 +38,6 @@ asmlinkage long sys_set_thread_area(struct user_desc __user *);
asmlinkage long sys_get_thread_area(struct user_desc __user *);
/* X86_32 only */
#ifdef CONFIG_X86_32
/* kernel/signal.c */
asmlinkage long sys_sigreturn(void);
......@@ -42,15 +47,5 @@ struct vm86_struct;
asmlinkage long sys_vm86old(struct vm86_struct __user *);
asmlinkage long sys_vm86(unsigned long, unsigned long);
#else /* CONFIG_X86_32 */
/* X86_64 only */
/* kernel/process_64.c */
asmlinkage long sys_arch_prctl(int, unsigned long);
/* kernel/sys_x86_64.c */
asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
unsigned long, unsigned long, unsigned long);
#endif /* CONFIG_X86_32 */
#endif /* _ASM_X86_SYSCALLS_H */
......@@ -200,7 +200,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
{
struct acpi_madt_local_x2apic *processor = NULL;
#ifdef CONFIG_X86_X2APIC
int apic_id;
u32 apic_id;
u8 enabled;
#endif
......@@ -222,9 +222,12 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
* to not preallocating memory for all NR_CPUS
* when we use CPU hotplug.
*/
if (!apic->apic_id_valid(apic_id) && enabled)
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
else
if (!apic->apic_id_valid(apic_id)) {
if (enabled)
pr_warn(PREFIX "x2apic entry ignored\n");
return 0;
}
acpi_register_lapic(apic_id, processor->uid, enabled);
#else
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
......
......@@ -40,7 +40,7 @@ int default_check_phys_apicid_present(int phys_apicid)
return physid_isset(phys_apicid, phys_cpu_present_map);
}
int default_apic_id_valid(int apicid)
int default_apic_id_valid(u32 apicid)
{
return (apicid < 255);
}
......@@ -56,7 +56,7 @@ static u32 numachip2_set_apic_id(unsigned int id)
return id << 24;
}
static int numachip_apic_id_valid(int apicid)
static int numachip_apic_id_valid(u32 apicid)
{
/* Trust what bootloader passes in MADT */
return 1;
......
/* Common bits for X2APIC cluster/physical modes. */
int x2apic_apic_id_valid(int apicid);
int x2apic_apic_id_valid(u32 apicid);
int x2apic_apic_id_registered(void);
void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
unsigned int x2apic_get_apic_id(unsigned long id);
......
......@@ -101,7 +101,7 @@ static int x2apic_phys_probe(void)
}
/* Common x2apic functions, also used by x2apic_cluster */
int x2apic_apic_id_valid(int apicid)
int x2apic_apic_id_valid(u32 apicid)
{
return 1;
}
......
......@@ -557,7 +557,7 @@ static void uv_send_IPI_all(int vector)
uv_send_IPI_mask(cpu_online_mask, vector);
}
static int uv_apic_id_valid(int apicid)
static int uv_apic_id_valid(u32 apicid)
{
return 1;
}
......
......@@ -848,18 +848,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_power = edx;
}
if (c->extended_cpuid_level >= 0x80000008) {
cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
c->x86_capability[CPUID_8000_0008_EBX] = ebx;
}
#ifdef CONFIG_X86_32
else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
c->x86_phys_bits = 36;
#endif
if (c->extended_cpuid_level >= 0x8000000a)
c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
......@@ -874,6 +862,23 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
apply_forced_caps(c);
}
static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
if (c->extended_cpuid_level >= 0x80000008) {
cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
c->x86_capability[CPUID_8000_0008_EBX] = ebx;
}
#ifdef CONFIG_X86_32
else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
c->x86_phys_bits = 36;
#endif
}
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_32
......@@ -965,6 +970,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
get_cpu_address_sizes(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
if (this_cpu->c_early_init)
......@@ -1097,6 +1103,8 @@ static void generic_identify(struct cpuinfo_x86 *c)
get_cpu_cap(c);
get_cpu_address_sizes(c);
if (c->cpuid_level >= 0x00000001) {
c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
......
......@@ -19,7 +19,7 @@ struct cpuid_dep {
* called from cpu hotplug. It shouldn't do anything in this case,
* but it's difficult to tell that to the init reference checker.
*/
const static struct cpuid_dep cpuid_deps[] = {
static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE },
{ X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE },
{ X86_FEATURE_XSAVES, X86_FEATURE_XSAVE },
......
......@@ -112,7 +112,7 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
return xen_pv_domain();
}
static int xen_id_always_valid(int apicid)
static int xen_id_always_valid(u32 apicid)
{
return 1;
}
......
......@@ -24,6 +24,17 @@
#include <asm/siginfo.h>
#include <asm/signal.h>
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
/*
* It may be useful for an architecture to override the definitions of the
* COMPAT_SYSCALL_DEFINE0 and COMPAT_SYSCALL_DEFINEx() macros, in particular
* to use a different calling convention for syscalls. To allow for that,
+ the prototypes for the compat_sys_*() functions below will *not* be included
* if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled.
*/
#include <asm/syscall_wrapper.h>
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
#ifndef COMPAT_USE_64BIT_TIME
#define COMPAT_USE_64BIT_TIME 0
#endif
......@@ -32,10 +43,12 @@
#define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v))
#endif
#ifndef COMPAT_SYSCALL_DEFINE0
#define COMPAT_SYSCALL_DEFINE0(name) \
asmlinkage long compat_sys_##name(void); \
ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \
asmlinkage long compat_sys_##name(void)
#endif /* COMPAT_SYSCALL_DEFINE0 */
#define COMPAT_SYSCALL_DEFINE1(name, ...) \
COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
......@@ -50,18 +63,25 @@
#define COMPAT_SYSCALL_DEFINE6(name, ...) \
COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)
/*
* The asmlinkage stub is aliased to a function named __se_compat_sys_*() which
* sign-extends 32-bit ints to longs whenever needed. The actual work is
* done within __do_compat_sys_*().
*/
#ifndef COMPAT_SYSCALL_DEFINEx
#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\
__attribute__((alias(__stringify(compat_SyS##name)))); \
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
__attribute__((alias(__stringify(__se_compat_sys##name)))); \
ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \
static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\
asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \
return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
} \
static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* COMPAT_SYSCALL_DEFINEx */
#ifndef compat_user_stack_pointer
#define compat_user_stack_pointer() current_user_stack_pointer()
......@@ -519,7 +539,12 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long);
* Please note that these prototypes here are only provided for information
* purposes, for static analysis, and for linking from the syscall table.
* These functions should not be called elsewhere from kernel code.
*
* As the syscall calling convention may be different from the default
* for architectures overriding the syscall calling convention, do not
* include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled.
*/
#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p);
asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr,
u32 __user *iocb);
......@@ -957,6 +982,8 @@ asmlinkage long compat_sys_stime(compat_time_t __user *tptr);
/* obsolete: net/socket.c */
asmlinkage long compat_sys_socketcall(int call, u32 __user *args);
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
/*
* For most but not all architectures, "am I in a compat syscall?" and
......
......@@ -81,6 +81,17 @@ union bpf_attr;
#include <linux/key.h>
#include <trace/syscall.h>
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
/*
* It may be useful for an architecture to override the definitions of the
* SYSCALL_DEFINE0() and __SYSCALL_DEFINEx() macros, in particular to use a
* different calling convention for syscalls. To allow for that, the prototypes
* for the sys_*() functions below will *not* be included if
* CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled.
*/
#include <asm/syscall_wrapper.h>
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
/*
* __MAP - apply a macro to syscall arguments
* __MAP(n, m, t1, a1, t2, a2, ..., tn, an) will expand to
......@@ -91,7 +102,7 @@ union bpf_attr;
* for SYSCALL_DEFINE<n>/COMPAT_SYSCALL_DEFINE<n>
*/
#define __MAP0(m,...)
#define __MAP1(m,t,a) m(t,a)
#define __MAP1(m,t,a,...) m(t,a)
#define __MAP2(m,t,a,...) m(t,a), __MAP1(m,__VA_ARGS__)
#define __MAP3(m,t,a,...) m(t,a), __MAP2(m,__VA_ARGS__)
#define __MAP4(m,t,a,...) m(t,a), __MAP3(m,__VA_ARGS__)
......@@ -189,11 +200,13 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
}
#endif
#ifndef SYSCALL_DEFINE0
#define SYSCALL_DEFINE0(sname) \
SYSCALL_METADATA(_##sname, 0); \
asmlinkage long sys_##sname(void); \
ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \
asmlinkage long sys_##sname(void)
#endif /* SYSCALL_DEFINE0 */
#define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
#define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
......@@ -209,20 +222,28 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
#define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
/*
* The asmlinkage stub is aliased to a function named __se_sys_*() which
* sign-extends 32-bit ints to longs whenever needed. The actual work is
* done within __do_sys_*().
*/
#ifndef __SYSCALL_DEFINEx
#define __SYSCALL_DEFINEx(x, name, ...) \
asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
__attribute__((alias(__stringify(SyS##name)))); \
__attribute__((alias(__stringify(__se_sys##name)))); \
ALLOW_ERROR_INJECTION(sys##name, ERRNO); \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
{ \
long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \
long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\
__MAP(x,__SC_TEST,__VA_ARGS__); \
__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
return ret; \
} \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* __SYSCALL_DEFINEx */
/*
* Called before coming back to user-mode. Returning to user-mode with an
......@@ -252,7 +273,12 @@ static inline void addr_limit_user_check(void)
* Please note that these prototypes here are only provided for information
* purposes, for static analysis, and for linking from the syscall table.
* These functions should not be called elsewhere from kernel code.
*
* As the syscall calling convention may be different from the default
* for architectures overriding the syscall calling convention, do not
* include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled.
*/
#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx);
asmlinkage long sys_io_destroy(aio_context_t ctx);
asmlinkage long sys_io_submit(aio_context_t, long,
......@@ -1076,6 +1102,8 @@ asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
*/
asmlinkage long sys_ni_syscall(void);
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
/*
* Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly.
......
......@@ -1923,3 +1923,13 @@ source "kernel/Kconfig.locks"
config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
bool
# It may be useful for an architecture to override the definitions of the
# SYSCALL_DEFINE() and __SYSCALL_DEFINEx() macros in <linux/syscalls.h>
# and the COMPAT_ variants in <linux/compat.h>, in particular to use a
# different calling convention for syscalls. They can also override the
# macros for not-implemented syscalls in kernel/sys_ni.c and
# kernel/time/posix-stubs.c. All these overrides need to be available in
# <asm/syscall_wrapper.h>.
config ARCH_HAS_SYSCALL_WRAPPER
def_bool n
......@@ -5,6 +5,11 @@
#include <asm/unistd.h>
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
/* Architectures may override COND_SYSCALL and COND_SYSCALL_COMPAT */
#include <asm/syscall_wrapper.h>
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
/* we can't #include <linux/syscalls.h> here,
but tell gcc to not warn with -Wmissing-prototypes */
asmlinkage long sys_ni_syscall(void);
......@@ -17,8 +22,13 @@ asmlinkage long sys_ni_syscall(void)
return -ENOSYS;
}
#ifndef COND_SYSCALL
#define COND_SYSCALL(name) cond_syscall(sys_##name)
#endif /* COND_SYSCALL */
#ifndef COND_SYSCALL_COMPAT
#define COND_SYSCALL_COMPAT(name) cond_syscall(compat_sys_##name)
#endif /* COND_SYSCALL_COMPAT */
/*
* This list is kept in the same order as include/uapi/asm-generic/unistd.h.
......
......@@ -19,6 +19,11 @@
#include <linux/posix-timers.h>
#include <linux/compat.h>
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
/* Architectures may override SYS_NI and COMPAT_SYS_NI */
#include <asm/syscall_wrapper.h>
#endif
asmlinkage long sys_ni_posix_timers(void)
{
pr_err_once("process %d (%s) attempted a POSIX timer syscall "
......@@ -27,8 +32,13 @@ asmlinkage long sys_ni_posix_timers(void)
return -ENOSYS;
}
#ifndef SYS_NI
#define SYS_NI(name) SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers)
#endif
#ifndef COMPAT_SYS_NI
#define COMPAT_SYS_NI(name) SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers)
#endif
SYS_NI(timer_create);
SYS_NI(timer_gettime);
......
......@@ -1087,6 +1087,6 @@ const struct dma_map_ops swiotlb_dma_ops = {
.unmap_sg = swiotlb_unmap_sg_attrs,
.map_page = swiotlb_map_page,
.unmap_page = swiotlb_unmap_page,
.dma_supported = swiotlb_dma_supported,
.dma_supported = dma_direct_supported,
};
#endif /* CONFIG_DMA_DIRECT_OPS */
......@@ -30,8 +30,8 @@ def getsizes(file, format):
if type in format:
# strip generated symbols
if name.startswith("__mod_"): continue
if name.startswith("SyS_"): continue
if name.startswith("compat_SyS_"): continue
if name.startswith("__se_sys"): continue
if name.startswith("__se_compat_sys"): continue
if name == "linux_banner": continue
# statics and some other optimizations adds random .NUMBER
name = re_NUMBER.sub('', name)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment