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

Author: torvalds

Documentation/process/adding-syscalls.rst

@@ -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

Documentation/x86/x86_64/mm.txt

@@ -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

arch/x86/Kconfig

@@ -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

arch/x86/entry/calling.h

@@ -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 */

arch/x86/entry/common.c

@@ -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);

arch/x86/entry/entry_64.S

@@ -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 */

arch/x86/entry/entry_64_compat.S

@@ -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 */

arch/x86/entry/syscall_32.c

@@ -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

arch/x86/entry/syscall_64.c

@@ -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