Merge tag 'x86-entry-2021-06-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 entry code related updates from Thomas Gleixner:

 - Consolidate the macros for .byte ... opcode sequences

 - Deduplicate register offset defines in include files

 - Simplify the ia32,x32 compat handling of the related syscall tables
   to get rid of #ifdeffery.

 - Clear all EFLAGS which are not required for syscall handling

 - Consolidate the syscall tables and switch the generation over to the
   generic shell script and remove the CFLAGS tweaks which are not
   longer required.

 - Use 'int' type for system call numbers to match the generic code.

 - Add more selftests for syscalls

* tag 'x86-entry-2021-06-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/syscalls: Don't adjust CFLAGS for syscall tables
  x86/syscalls: Remove -Wno-override-init for syscall tables
  x86/uml/syscalls: Remove array index from syscall initializers
  x86/syscalls: Clear 'offset' and 'prefix' in case they are set in env
  x86/entry: Use int everywhere for system call numbers
  x86/entry: Treat out of range and gap system calls the same
  x86/entry/64: Sign-extend system calls on entry to int
  selftests/x86/syscall: Add tests under ptrace to syscall_numbering_64
  selftests/x86/syscall: Simplify message reporting in syscall_numbering
  selftests/x86/syscall: Update and extend syscall_numbering_64
  x86/syscalls: Switch to generic syscallhdr.sh
  x86/syscalls: Use __NR_syscalls instead of __NR_syscall_max
  x86/unistd: Define X32_NR_syscalls only for 64-bit kernel
  x86/syscalls: Stop filling syscall arrays with *_sys_ni_syscall
  x86/syscalls: Switch to generic syscalltbl.sh
  x86/entry/x32: Rename __x32_compat_sys_* to __x64_compat_sys_*

1 files changed, 61 insertions, 26 deletions

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index f79688648db1..6c2826417b33 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -36,61 +36,97 @@
 #include <asm/irq_stack.h>
 
 #ifdef CONFIG_X86_64
-__visible noinstr void do_syscall_64(struct pt_regs *regs, unsigned long nr)
+
+static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Convert negative numbers to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int unr = nr;
+
+	if (likely(unr < NR_syscalls)) {
+		unr = array_index_nospec(unr, NR_syscalls);
+		regs->ax = sys_call_table[unr](regs);
+		return true;
+	}
+	return false;
+}
+
+static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Adjust the starting offset of the table, and convert numbers
+	 * < __X32_SYSCALL_BIT to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int xnr = nr - __X32_SYSCALL_BIT;
+
+	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
+		xnr = array_index_nospec(xnr, X32_NR_syscalls);
+		regs->ax = x32_sys_call_table[xnr](regs);
+		return true;
+	}
+	return false;
+}
+
+__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
 {
 	add_random_kstack_offset();
 	nr = syscall_enter_from_user_mode(regs, nr);
 
 	instrumentation_begin();
-	if (likely(nr < NR_syscalls)) {
-		nr = array_index_nospec(nr, NR_syscalls);
-		regs->ax = sys_call_table[nr](regs);
-#ifdef CONFIG_X86_X32_ABI
-	} else if (likely((nr & __X32_SYSCALL_BIT) &&
-			  (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) {
-		nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT,
-					X32_NR_syscalls);
-		regs->ax = x32_sys_call_table[nr](regs);
-#endif
+
+	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
+		/* Invalid system call, but still a system call. */
+		regs->ax = __x64_sys_ni_syscall(regs);
 	}
+
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 }
 #endif
 
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
-static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs)
+static __always_inline int syscall_32_enter(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_IA32_EMULATION))
 		current_thread_info()->status |= TS_COMPAT;
 
-	return (unsigned int)regs->orig_ax;
+	return (int)regs->orig_ax;
 }
 
 /*
  * Invoke a 32-bit syscall.  Called with IRQs on in CONTEXT_KERNEL.
  */
-static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs,
-						  unsigned int nr)
+static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
 {
-	if (likely(nr < IA32_NR_syscalls)) {
-		nr = array_index_nospec(nr, IA32_NR_syscalls);
-		regs->ax = ia32_sys_call_table[nr](regs);
+	/*
+	 * Convert negative numbers to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int unr = nr;
+
+	if (likely(unr < IA32_NR_syscalls)) {
+		unr = array_index_nospec(unr, IA32_NR_syscalls);
+		regs->ax = ia32_sys_call_table[unr](regs);
+	} else if (nr != -1) {
+		regs->ax = __ia32_sys_ni_syscall(regs);
 	}
 }
 
 /* Handles int $0x80 */
 __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
-	unsigned int nr = syscall_32_enter(regs);
+	int nr = syscall_32_enter(regs);
 
 	add_random_kstack_offset();
 	/*
-	 * Subtlety here: if ptrace pokes something larger than 2^32-1 into
-	 * orig_ax, the unsigned int return value truncates it.  This may
-	 * or may not be necessary, but it matches the old asm behavior.
+	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
+	 * orig_ax, the int return value truncates it. This matches
+	 * the semantics of syscall_get_nr().
 	 */
-	nr = (unsigned int)syscall_enter_from_user_mode(regs, nr);
+	nr = syscall_enter_from_user_mode(regs, nr);
 	instrumentation_begin();
 
 	do_syscall_32_irqs_on(regs, nr);
@@ -101,7 +137,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
-	unsigned int nr = syscall_32_enter(regs);
+	int nr = syscall_32_enter(regs);
 	int res;
 
 	add_random_kstack_offset();
@@ -136,8 +172,7 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 		return false;
 	}
 
-	/* The case truncates any ptrace induced syscall nr > 2^32 -1 */
-	nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr);
+	nr = syscall_enter_from_user_mode_work(regs, nr);
 
 	/* Now this is just like a normal syscall. */
 	do_syscall_32_irqs_on(regs, nr);