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

4 files changed, 221 insertions, 13 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 40a3d36..08acd95 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -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);
 
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 03eedc2..d653139 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -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)
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
new file mode 100644
index 0000000..e046a40
--- /dev/null
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -0,0 +1,209 @@
+/* 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 */
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index ae6e05f..9fa979d 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.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 */