Merge branches 'x86/fpu', 'x86/mm' and 'x86/asm' into x86/pkeys

Provide a stable basis for the pkeys patches, which touches various
x86 details.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/kernel-parameters.txt

@@ -666,7 +666,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	clearcpuid=BITNUM [X86]
 			Disable CPUID feature X for the kernel. See
-			arch/x86/include/asm/cpufeature.h for the valid bit
+			arch/x86/include/asm/cpufeatures.h for the valid bit
 			numbers. Note the Linux specific bits are not necessarily
 			stable over kernel options, but the vendor specific
 			ones should be.
@@ -2566,6 +2566,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nointroute	[IA-64]
 
+	noinvpcid	[X86] Disable the INVPCID cpu feature.
+
 	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver

arch/x86/Kconfig.debug

@@ -350,16 +350,6 @@ config DEBUG_IMR_SELFTEST
 
 	  If unsure say N here.
 
-config X86_DEBUG_STATIC_CPU_HAS
-	bool "Debug alternatives"
-	depends on DEBUG_KERNEL
-	---help---
-	  This option causes additional code to be generated which
-	  fails if static_cpu_has() is used before alternatives have
-	  run.
-
-	  If unsure, say N.
-
 config X86_DEBUG_FPU
 	bool "Debug the x86 FPU code"
 	depends on DEBUG_KERNEL

arch/x86/boot/cpuflags.h

 #ifndef BOOT_CPUFLAGS_H
 #define BOOT_CPUFLAGS_H
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/processor-flags.h>
 
 struct cpu_features {

arch/x86/boot/mkcpustr.c

@@ -17,7 +17,7 @@
 
 #include "../include/asm/required-features.h"
 #include "../include/asm/disabled-features.h"
-#include "../include/asm/cpufeature.h"
+#include "../include/asm/cpufeatures.h"
 #include "../kernel/cpu/capflags.c"
 
 int main(void)

arch/x86/crypto/crc32-pclmul_glue.c

@@ -33,7 +33,7 @@
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/api.h>
 

arch/x86/crypto/crc32c-intel_glue.c

@@ -30,7 +30,7 @@
 #include <linux/kernel.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/internal.h>
 

arch/x86/crypto/crct10dif-pclmul_glue.c

@@ -30,7 +30,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <asm/fpu/api.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 
 asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,

arch/x86/entry/calling.h

@@ -201,37 +201,6 @@ For 32-bit we have the following conventions - kernel is built with
 	.byte 0xf1
 	.endm
 
-#else /* CONFIG_X86_64 */
-
-/*
- * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
- * are different from the entry_32.S versions in not changing the segment
- * registers. So only suitable for in kernel use, not when transitioning
- * from or to user space. The resulting stack frame is not a standard
- * pt_regs frame. The main use case is calling C code from assembler
- * when all the registers need to be preserved.
- */
-
-	.macro SAVE_ALL
-	pushl %eax
-	pushl %ebp
-	pushl %edi
-	pushl %esi
-	pushl %edx
-	pushl %ecx
-	pushl %ebx
-	.endm
-
-	.macro RESTORE_ALL
-	popl %ebx
-	popl %ecx
-	popl %edx
-	popl %esi
-	popl %edi
-	popl %ebp
-	popl %eax
-	.endm
-
 #endif /* CONFIG_X86_64 */
 
 /*

arch/x86/entry/common.c

@@ -26,6 +26,7 @@
 #include <asm/traps.h>
 #include <asm/vdso.h>
 #include <asm/uaccess.h>
+#include <asm/cpufeature.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -344,6 +345,32 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 	prepare_exit_to_usermode(regs);
 }
 
+#ifdef CONFIG_X86_64
+__visible void do_syscall_64(struct pt_regs *regs)
+{
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	unsigned long nr = regs->orig_ax;
+
+	local_irq_enable();
+
+	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
+		nr = syscall_trace_enter(regs);
+
+	/*
+	 * NB: Native and x32 syscalls are dispatched from the same
+	 * 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)) {
+		regs->ax = sys_call_table[nr & __SYSCALL_MASK](
+			regs->di, regs->si, regs->dx,
+			regs->r10, regs->r8, regs->r9);
+	}
+
+	syscall_return_slowpath(regs);
+}
+#endif
+
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 /*
  * Does a 32-bit syscall.  Called with IRQs on and does all entry and

arch/x86/entry/entry_32.S

@@ -40,7 +40,7 @@
 #include <asm/processor-flags.h>
 #include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>

arch/x86/entry/entry_64.S

@@ -145,17 +145,11 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
+	TRACE_IRQS_OFF
+
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS			/* pt_regs->ss */
 	pushq	PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
-	/*
-	 * Re-enable interrupts.
-	 * We use 'rsp_scratch' as a scratch space, hence irq-off block above
-	 * must execute atomically in the face of possible interrupt-driven
-	 * task preemption. We must enable interrupts only after we're done
-	 * with using rsp_scratch:
-	 */
-	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq	%r11				/* pt_regs->flags */
 	pushq	$__USER_CS			/* pt_regs->cs */
 	pushq	%rcx				/* pt_regs->ip */
@@ -171,9 +165,21 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	pushq	%r11				/* pt_regs->r11 */
 	sub	$(6*8), %rsp			/* pt_regs->bp, bx, r12-15 not saved */
 
-	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	tracesys
+	/*
+	 * If we need to do entry work or if we guess we'll need to do
+	 * exit work, go straight to the slow path.
+	 */
+	testl	$_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	entry_SYSCALL64_slow_path
+
 entry_SYSCALL_64_fastpath:
+	/*
+	 * Easy case: enable interrupts and issue the syscall.  If the syscall
+	 * needs pt_regs, we'll call a stub that disables interrupts again
+	 * and jumps to the slow path.
+	 */
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
 #if __SYSCALL_MASK == ~0
 	cmpq	$__NR_syscall_max, %rax
 #else
@@ -182,103 +188,56 @@ entry_SYSCALL_64_fastpath:
 #endif
 	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
 	movq	%r10, %rcx
+
+	/*
+	 * This call instruction is handled specially in stub_ptregs_64.
+	 * It might end up jumping to the slow path.  If it jumps, RAX
+	 * and all argument registers are clobbered.
+	 */
 	call	*sys_call_table(, %rax, 8)
+.Lentry_SYSCALL_64_after_fastpath_call:
+
 	movq	%rax, RAX(%rsp)
 1:
-/*
- * Syscall return path ending with SYSRET (fast path).
- * Has incompletely filled pt_regs.
- */
-	LOCKDEP_SYS_EXIT
-	/*
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	DISABLE_INTERRUPTS(CLBR_NONE)
 
 	/*
-	 * We must check ti flags with interrupts (or at least preemption)
-	 * off because we must *never* return to userspace without
-	 * processing exit work that is enqueued if we're preempted here.
-	 * In particular, returning to userspace with any of the one-shot
-	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
-	 * very bad.
+	 * If we get here, then we know that pt_regs is clean for SYSRET64.
+	 * If we see that no exit work is required (which we are required
+	 * to check with IRQs off), then we can go straight to SYSRET64.
 	 */
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
 	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	int_ret_from_sys_call_irqs_off	/* Go to the slow path */
+	jnz	1f
 
-	RESTORE_C_REGS_EXCEPT_RCX_R11
+	LOCKDEP_SYS_EXIT
+	TRACE_IRQS_ON		/* user mode is traced as IRQs on */
 	movq	RIP(%rsp), %rcx
 	movq	EFLAGS(%rsp), %r11
+	RESTORE_C_REGS_EXCEPT_RCX_R11
 	movq	RSP(%rsp), %rsp
-	/*
-	 * 64-bit SYSRET restores rip from rcx,
-	 * rflags from r11 (but RF and VM bits are forced to 0),
-	 * cs and ss are loaded from MSRs.
-	 * Restoration of rflags re-enables interrupts.
-	 *
-	 * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
-	 * descriptor is not reinitialized.  This means that we should
-	 * avoid SYSRET with SS == NULL, which could happen if we schedule,
-	 * exit the kernel, and re-enter using an interrupt vector.  (All
-	 * interrupt entries on x86_64 set SS to NULL.)  We prevent that
-	 * from happening by reloading SS in __switch_to.  (Actually
-	 * detecting the failure in 64-bit userspace is tricky but can be
-	 * done.)
-	 */
 	USERGS_SYSRET64
 
-GLOBAL(int_ret_from_sys_call_irqs_off)
+1:
+	/*
+	 * The fast path looked good when we started, but something changed
+	 * along the way and we need to switch to the slow path.  Calling
+	 * raise(3) will trigger this, for example.  IRQs are off.
+	 */
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	jmp int_ret_from_sys_call
-
-	/* Do syscall entry tracing */
-tracesys:
-	movq	%rsp, %rdi
-	movl	$AUDIT_ARCH_X86_64, %esi
-	call	syscall_trace_enter_phase1
-	test	%rax, %rax
-	jnz	tracesys_phase2			/* if needed, run the slow path */
-	RESTORE_C_REGS_EXCEPT_RAX		/* else restore clobbered regs */
-	movq	ORIG_RAX(%rsp), %rax
-	jmp	entry_SYSCALL_64_fastpath	/* and return to the fast path */
-
-tracesys_phase2:
 	SAVE_EXTRA_REGS
 	movq	%rsp, %rdi
-	movl	$AUDIT_ARCH_X86_64, %esi
-	movq	%rax, %rdx
-	call	syscall_trace_enter_phase2
-
-	/*
-	 * Reload registers from stack in case ptrace changed them.
-	 * We don't reload %rax because syscall_trace_entry_phase2() returned
-	 * the value it wants us to use in the table lookup.
-	 */
-	RESTORE_C_REGS_EXCEPT_RAX
-	RESTORE_EXTRA_REGS
-#if __SYSCALL_MASK == ~0
-	cmpq	$__NR_syscall_max, %rax
-#else
-	andl	$__SYSCALL_MASK, %eax
-	cmpl	$__NR_syscall_max, %eax
-#endif
-	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
-	movq	%r10, %rcx			/* fixup for C */
-	call	*sys_call_table(, %rax, 8)
-	movq	%rax, RAX(%rsp)
-1:
-	/* Use IRET because user could have changed pt_regs->foo */
+	call	syscall_return_slowpath	/* returns with IRQs disabled */
+	jmp	return_from_SYSCALL_64
 
-/*
- * Syscall return path ending with IRET.
- * Has correct iret frame.
- */
-GLOBAL(int_ret_from_sys_call)
+entry_SYSCALL64_slow_path:
+	/* IRQs are off. */
 	SAVE_EXTRA_REGS
 	movq	%rsp, %rdi
-	call	syscall_return_slowpath	/* returns with IRQs disabled */
+	call	do_syscall_64		/* returns with IRQs disabled */
+
+return_from_SYSCALL_64:
 	RESTORE_EXTRA_REGS
 	TRACE_IRQS_IRETQ		/* we're about to change IF */
 
@@ -355,83 +314,45 @@ opportunistic_sysret_failed:
 	jmp	restore_c_regs_and_iret
 END(entry_SYSCALL_64)
 
-
-	.macro FORK_LIKE func
-ENTRY(stub_\func)
-	SAVE_EXTRA_REGS 8
-	jmp	sys_\func
-END(stub_\func)
-	.endm
-
-	FORK_LIKE  clone
-	FORK_LIKE  fork
-	FORK_LIKE  vfork
-
-ENTRY(stub_execve)
-	call	sys_execve
-return_from_execve:
-	testl	%eax, %eax
-	jz	1f
-	/* exec failed, can use fast SYSRET code path in this case */
-	ret
-1:
-	/* must use IRET code path (pt_regs->cs may have changed) */
-	addq	$8, %rsp
-	ZERO_EXTRA_REGS
-	movq	%rax, RAX(%rsp)
-	jmp	int_ret_from_sys_call
-END(stub_execve)
+ENTRY(stub_ptregs_64)
 	/*
- * Remaining execve stubs are only 7 bytes long.
- * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
+	 * Syscalls marked as needing ptregs land here.
+	 * If we are on the fast path, we need to save the extra regs,
+	 * which we achieve by trying again on the slow path.  If we are on
+	 * the slow path, the extra regs are already saved.
+	 *
+	 * RAX stores a pointer to the C function implementing the syscall.
+	 * IRQs are on.
 	 */
-	.align	8
-GLOBAL(stub_execveat)
-	call	sys_execveat
-	jmp	return_from_execve
-END(stub_execveat)
-
-#if defined(CONFIG_X86_X32_ABI)
-	.align	8
-GLOBAL(stub_x32_execve)
-	call	compat_sys_execve
-	jmp	return_from_execve
-END(stub_x32_execve)
-	.align	8
-GLOBAL(stub_x32_execveat)
-	call	compat_sys_execveat
-	jmp	return_from_execve
-END(stub_x32_execveat)
-#endif
+	cmpq	$.Lentry_SYSCALL_64_after_fastpath_call, (%rsp)
+	jne	1f
 
 	/*
- * sigreturn is special because it needs to restore all registers on return.
- * This cannot be done with SYSRET, so use the IRET return path instead.
- */
-ENTRY(stub_rt_sigreturn)
-	/*
-	 * SAVE_EXTRA_REGS result is not normally needed:
-	 * sigreturn overwrites all pt_regs->GPREGS.
-	 * But sigreturn can fail (!), and there is no easy way to detect that.
-	 * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
-	 * we SAVE_EXTRA_REGS here.
+	 * Called from fast path -- disable IRQs again, pop return address
+	 * and jump to slow path
 	 */
-	SAVE_EXTRA_REGS 8
-	call	sys_rt_sigreturn
-return_from_stub:
-	addq	$8, %rsp
-	RESTORE_EXTRA_REGS
-	movq	%rax, RAX(%rsp)
-	jmp	int_ret_from_sys_call
-END(stub_rt_sigreturn)
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	popq	%rax
+	jmp	entry_SYSCALL64_slow_path
 
-#ifdef CONFIG_X86_X32_ABI
-ENTRY(stub_x32_rt_sigreturn)
-	SAVE_EXTRA_REGS 8
-	call	sys32_x32_rt_sigreturn
-	jmp	return_from_stub
-END(stub_x32_rt_sigreturn)
-#endif
+1:
+	/* Called from C */
+	jmp	*%rax				/* called from C */
+END(stub_ptregs_64)
+
+.macro ptregs_stub func
+ENTRY(ptregs_\func)
+	leaq	\func(%rip), %rax
+	jmp	stub_ptregs_64
+END(ptregs_\func)
+.endm
+
+/* Instantiate ptregs_stub for each ptregs-using syscall */
+#define __SYSCALL_64_QUAL_(sym)
+#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym
+#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym)
+#include <asm/syscalls_64.h>
 
 /*
  * A newly forked process directly context switches into this address.
@@ -439,7 +360,6 @@ END(stub_x32_rt_sigreturn)
  * rdi: prev task we switched from
  */
 ENTRY(ret_from_fork)
-
 	LOCK ; btr $TIF_FORK, TI_flags(%r8)
 
 	pushq	$0x0002
@@ -447,28 +367,32 @@ ENTRY(ret_from_fork)
 
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
-	RESTORE_EXTRA_REGS
-
 	testb	$3, CS(%rsp)			/* from kernel_thread? */
+	jnz	1f
 
 	/*
-	 * By the time we get here, we have no idea whether our pt_regs,
-	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
-	 * the slow path, or one of the 32-bit compat paths.
-	 * Use IRET code path to return, since it can safely handle
-	 * all of the above.
+	 * We came from kernel_thread.  This code path is quite twisted, and
+	 * someone should clean it up.
+	 *
+	 * copy_thread_tls stashes the function pointer in RBX and the
+	 * parameter to be passed in RBP.  The called function is permitted
+	 * to call do_execve and thereby jump to user mode.
 	 */
-	jnz	int_ret_from_sys_call
+	movq	RBP(%rsp), %rdi
+	call	*RBX(%rsp)
+	movl	$0, RAX(%rsp)
 
 	/*
-	 * We came from kernel_thread
-	 * nb: we depend on RESTORE_EXTRA_REGS above
+	 * Fall through as though we're exiting a syscall.  This makes a
+	 * twisted sort of sense if we just called do_execve.
 	 */
-	movq	%rbp, %rdi
-	call	*%rbx
-	movl	$0, RAX(%rsp)
-	RESTORE_EXTRA_REGS
-	jmp	int_ret_from_sys_call
+
+1:
+	movq	%rsp, %rdi
+	call	syscall_return_slowpath	/* returns with IRQs disabled */
+	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
+	SWAPGS
+	jmp	restore_regs_and_iret
 END(ret_from_fork)
 
 /*

arch/x86/entry/syscall_32.c

@@ -6,17 +6,11 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#ifdef CONFIG_IA32_EMULATION
-#define SYM(sym, compat) compat
-#else
-#define SYM(sym, compat) sym
-#endif
-
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_32.h>
 #undef __SYSCALL_I386
 
-#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
+#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);
 

arch/x86/entry/syscall_64.c

@@ -6,19 +6,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#define __SYSCALL_64_QUAL_(sym) sym
+#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym
 
-#ifdef CONFIG_X86_X32_ABI
-# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
-#else
-# define __SYSCALL_X32(nr, sym, compat) /* nothing */
-#endif
-
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
 
-#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
+#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym),
 
 extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 

arch/x86/entry/syscalls/syscall_64.tbl

@@ -21,7 +21,7 @@
 12	common	brk			sys_brk
 13	64	rt_sigaction		sys_rt_sigaction
 14	common	rt_sigprocmask		sys_rt_sigprocmask
-15	64	rt_sigreturn		stub_rt_sigreturn
+15	64	rt_sigreturn		sys_rt_sigreturn/ptregs
 16	64	ioctl			sys_ioctl
 17	common	pread64			sys_pread64
 18	common	pwrite64		sys_pwrite64
@@ -62,10 +62,10 @@
 53	common	socketpair		sys_socketpair
 54	64	setsockopt		sys_setsockopt
 55	64	getsockopt		sys_getsockopt
-56	common	clone			stub_clone
-57	common	fork			stub_fork
-58	common	vfork			stub_vfork
-59	64	execve			stub_execve
+56	common	clone			sys_clone/ptregs
+57	common	fork			sys_fork/ptregs
+58	common	vfork			sys_vfork/ptregs
+59	64	execve			sys_execve/ptregs
 60	common	exit			sys_exit
 61	common	wait4			sys_wait4
 62	common	kill			sys_kill
@@ -178,7 +178,7 @@
 169	common	reboot			sys_reboot
 170	common	sethostname		sys_sethostname
 171	common	setdomainname		sys_setdomainname
-172	common	iopl			sys_iopl
+172	common	iopl			sys_iopl/ptregs
 173	common	ioperm			sys_ioperm
 174	64	create_module
 175	common	init_module		sys_init_module
@@ -328,7 +328,7 @@
 319	common	memfd_create		sys_memfd_create
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
-322	64	execveat		stub_execveat
+322	64	execveat		sys_execveat/ptregs
 323	common	userfaultfd		sys_userfaultfd
 324	common	membarrier		sys_membarrier
 325	common	mlock2			sys_mlock2
@@ -339,14 +339,14 @@
 # for native 64-bit operation.
 #
 512	x32	rt_sigaction		compat_sys_rt_sigaction
-513	x32	rt_sigreturn		stub_x32_rt_sigreturn
+513	x32	rt_sigreturn		sys32_x32_rt_sigreturn
 514	x32	ioctl			compat_sys_ioctl
 515	x32	readv			compat_sys_readv
 516	x32	writev			compat_sys_writev
 517	x32	recvfrom		compat_sys_recvfrom
 518	x32	sendmsg			compat_sys_sendmsg
 519	x32	recvmsg			compat_sys_recvmsg
-520	x32	execve			stub_x32_execve
+520	x32	execve			compat_sys_execve/ptregs
 521	x32	ptrace			compat_sys_ptrace
 522	x32	rt_sigpending		compat_sys_rt_sigpending
 523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait
@@ -371,4 +371,4 @@
 542	x32	getsockopt		compat_sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
-545	x32	execveat		stub_x32_execveat
+545	x32	execveat		compat_sys_execveat/ptregs

arch/x86/entry/syscalls/syscalltbl.sh

@@ -3,13 +3,63 @@
 in="$1"
 out="$2"
 
+syscall_macro() {
+    abi="$1"
+    nr="$2"
+    entry="$3"
+
+    # Entry can be either just a function name or "function/qualifier"
+    real_entry="${entry%%/*}"
+    qualifier="${entry:${#real_entry}}"		# Strip the function name
+    qualifier="${qualifier:1}"			# Strip the slash, if any
+
+    echo "__SYSCALL_${abi}($nr, $real_entry, $qualifier)"
+}
+
+emit() {
+    abi="$1"
+    nr="$2"
+    entry="$3"
+    compat="$4"
+
+    if [ "$abi" == "64" -a -n "$compat" ]; then
+	echo "a compat entry for a 64-bit syscall makes no sense" >&2
+	exit 1
+    fi
+
+    if [ -z "$compat" ]; then
+	if [ -n "$entry" ]; then
+	    syscall_macro "$abi" "$nr" "$entry"
+	fi
+    else
+	echo "#ifdef CONFIG_X86_32"
+	if [ -n "$entry" ]; then
+	    syscall_macro "$abi" "$nr" "$entry"
+	fi
+	echo "#else"
+	syscall_macro "$abi" "$nr" "$compat"
+	echo "#endif"
+    fi
+}
+
 grep '^[0-9]' "$in" | sort -n | (
     while read nr abi name entry compat; do
 	abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
-	if [ -n "$compat" ]; then
-	    echo "__SYSCALL_${abi}($nr, $entry, $compat)"
-	elif [ -n "$entry" ]; then
-	    echo "__SYSCALL_${abi}($nr, $entry, $entry)"
+	if [ "$abi" == "COMMON" -o "$abi" == "64" ]; then
+	    # COMMON is the same as 64, except that we don't expect X32
+	    # programs to use it.  Our expectation has nothing to do with
+	    # any generated code, so treat them the same.
+	    emit 64 "$nr" "$entry" "$compat"
+	elif [ "$abi" == "X32" ]; then
+	    # X32 is equivalent to 64 on an X32-compatible kernel.
+	    echo "#ifdef CONFIG_X86_X32_ABI"
+	    emit 64 "$nr" "$entry" "$compat"
+	    echo "#endif"
+	elif [ "$abi" == "I386" ]; then
+	    emit "$abi" "$nr" "$entry" "$compat"
+	else
+	    echo "Unknown abi $abi" >&2
+	    exit 1
 	fi
     done
 ) > "$out"

arch/x86/entry/vdso/vdso2c.h

@@ -150,16 +150,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "static struct page *pages[%lu];\n\n",
-		mapping_size / 4096);
-
 	fprintf(outfile, "const struct vdso_image %s = {\n", name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
-	fprintf(outfile, "\t.text_mapping = {\n");
-	fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
-	fprintf(outfile, "\t\t.pages = pages,\n");
-	fprintf(outfile, "\t},\n");
 	if (alt_sec) {
 		fprintf(outfile, "\t.alt = %lu,\n",
 			(unsigned long)GET_LE(&alt_sec->sh_offset));

arch/x86/entry/vdso/vdso32-setup.c

@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/mm_types.h>
 
-#include <asm/cpufeature.h>
 #include <asm/processor.h>
 #include <asm/vdso.h>
 

arch/x86/entry/vdso/vdso32/system_call.S

@@ -3,7 +3,7 @@
 */
 
 #include <asm/dwarf2.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*

arch/x86/entry/vdso/vma.c

@@ -20,6 +20,7 @@
 #include <asm/page.h>
 #include <asm/hpet.h>
 #include <asm/desc.h>
+#include <asm/cpufeature.h>
 
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
@@ -27,13 +28,7 @@ unsigned int __read_mostly vdso64_enabled = 1;
 
 void __init init_vdso_image(const struct vdso_image *image)
 {
-	int i;
-	int npages = (image->size) / PAGE_SIZE;
-
 	BUG_ON(image->size % PAGE_SIZE != 0);
-	for (i = 0; i < npages; i++)
-		image->text_mapping.pages[i] =
-			virt_to_page(image->data + i*PAGE_SIZE);
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
@@ -90,18 +85,87 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #endif
 }
 
+static int vdso_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+
+	if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
+	get_page(vmf->page);
+	return 0;
+}
+
+static const struct vm_special_mapping text_mapping = {
+	.name = "[vdso]",
+	.fault = vdso_fault,
+};
+
+static int vvar_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+	long sym_offset;
+	int ret = -EFAULT;
+
+	if (!image)
+		return VM_FAULT_SIGBUS;
+
+	sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
+		image->sym_vvar_start;
+
+	/*
+	 * Sanity check: a symbol offset of zero means that the page
+	 * does not exist for this vdso image, not that the page is at
+	 * offset zero relative to the text mapping.  This should be
+	 * impossible here, because sym_offset should only be zero for
+	 * the page past the end of the vvar mapping.
+	 */
+	if (sym_offset == 0)
+		return VM_FAULT_SIGBUS;
+
+	if (sym_offset == image->sym_vvar_page) {
+		ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+	} else if (sym_offset == image->sym_hpet_page) {
+#ifdef CONFIG_HPET_TIMER
+		if (hpet_address && vclock_was_used(VCLOCK_HPET)) {
+			ret = vm_insert_pfn_prot(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				hpet_address >> PAGE_SHIFT,
+				pgprot_noncached(PAGE_READONLY));
+		}
+#endif
+	} else if (sym_offset == image->sym_pvclock_page) {
+		struct pvclock_vsyscall_time_info *pvti =
+			pvclock_pvti_cpu0_va();
+		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
+			ret = vm_insert_pfn(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				__pa(pvti) >> PAGE_SHIFT);
+		}
+	}
+
+	if (ret == 0 || ret == -EBUSY)
+		return VM_FAULT_NOPAGE;
+
+	return VM_FAULT_SIGBUS;
+}
+
 static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long addr, text_start;
 	int ret = 0;
-	static struct page *no_pages[] = {NULL};
-	static struct vm_special_mapping vvar_mapping = {
+	static const struct vm_special_mapping vvar_mapping = {
 		.name = "[vvar]",
-		.pages = no_pages,
+		.fault = vvar_fault,
 	};
-	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
@@ -121,6 +185,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 
 	text_start = addr - image->sym_vvar_start;
 	current->mm->context.vdso = (void __user *)text_start;
+	current->mm->context.vdso_image = image;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -130,7 +195,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 				       image->size,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &image->text_mapping);
+				       &text_mapping);
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
@@ -140,7 +205,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	vma = _install_special_mapping(mm,
 				       addr,
 				       -image->sym_vvar_start,
-				       VM_READ|VM_MAYREAD,
+				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+				       VM_PFNMAP,
 				       &vvar_mapping);
 
 	if (IS_ERR(vma)) {
@@ -148,41 +214,6 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 		goto up_fail;
 	}
 
-	if (image->sym_vvar_page)
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_vvar_page,
-				      __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-	if (ret)
-		goto up_fail;
-
-#ifdef CONFIG_HPET_TIMER
-	if (hpet_address && image->sym_hpet_page) {
-		ret = io_remap_pfn_range(vma,
-			text_start + image->sym_hpet_page,
-			hpet_address >> PAGE_SHIFT,
-			PAGE_SIZE,
-			pgprot_noncached(PAGE_READONLY));
-
-		if (ret)
-			goto up_fail;
-	}
-#endif
-
-	pvti = pvclock_pvti_cpu0_va();
-	if (pvti && image->sym_pvclock_page) {
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_pvclock_page,
-				      __pa(pvti) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-		if (ret)
-			goto up_fail;
-	}
-
 up_fail:
 	if (ret)
 		current->mm->context.vdso = NULL;
@@ -254,7 +285,7 @@ static void vgetcpu_cpu_init(void *arg)
 #ifdef CONFIG_NUMA
 	node = cpu_to_node(cpu);
 #endif
-	if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
+	if (static_cpu_has(X86_FEATURE_RDTSCP))
 		write_rdtscp_aux((node << 12) | cpu);
 
 	/*

arch/x86/entry/vsyscall/vsyscall_gtod.c

@@ -16,6 +16,8 @@
 #include <asm/vgtod.h>
 #include <asm/vvar.h>
 
+int vclocks_used __read_mostly;
+
 DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 void update_vsyscall_tz(void)
@@ -26,12 +28,17 @@ void update_vsyscall_tz(void)
 
 void update_vsyscall(struct timekeeper *tk)
 {
+	int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
 	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
 
+	/* Mark the new vclock used. */
+	BUILD_BUG_ON(VCLOCK_MAX >= 32);
+	WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
 	gtod_write_begin(vdata);
 
 	/* copy vsyscall data */
-	vdata->vclock_mode	= tk->tkr_mono.clock->archdata.vclock_mode;
+	vdata->vclock_mode	= vclock_mode;
 	vdata->cycle_last	= tk->tkr_mono.cycle_last;
 	vdata->mask		= tk->tkr_mono.mask;
 	vdata->mult		= tk->tkr_mono.mult;