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_*

9 files changed, 106 insertions, 185 deletions

diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 08bf95dbc911..7fec5dcf6438 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -8,18 +8,8 @@ UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
 CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_syscall_64.o	= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_syscall_32.o	= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_syscall_x32.o	= $(CC_FLAGS_FTRACE)
 
 CFLAGS_common.o			+= -fno-stack-protector
-CFLAGS_syscall_64.o		+= -fno-stack-protector
-CFLAGS_syscall_32.o		+= -fno-stack-protector
-CFLAGS_syscall_x32.o		+= -fno-stack-protector
-
-CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_syscall_x32.o		+= $(call cc-option,-Wno-override-init,)
 
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
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);
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 237da6ced61b..e38a4cf795d9 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -108,7 +108,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 
 	/* IRQs are off. */
 	movq	%rsp, %rdi
-	movq	%rax, %rsi
+	/* Sign extend the lower 32bit as syscall numbers are treated as int */
+	movslq	%eax, %rsi
 	call	do_syscall_64		/* returns with IRQs disabled */
 
 	/*
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 86eb0d89d46f..8cfc9bc73e7f 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -5,21 +5,21 @@
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <linux/syscalls.h>
-#include <asm/unistd.h>
 #include <asm/syscall.h>
 
-#define __SYSCALL_I386(nr, sym) extern long __ia32_##sym(const struct pt_regs *);
+#ifdef CONFIG_IA32_EMULATION
+#define __SYSCALL_WITH_COMPAT(nr, native, compat)	__SYSCALL(nr, compat)
+#else
+#define __SYSCALL_WITH_COMPAT(nr, native, compat)	__SYSCALL(nr, native)
+#endif
+
+#define __SYSCALL(nr, sym) extern long __ia32_##sym(const struct pt_regs *);
 
 #include <asm/syscalls_32.h>
-#undef __SYSCALL_I386
+#undef __SYSCALL
 
-#define __SYSCALL_I386(nr, sym) [nr] = __ia32_##sym,
+#define __SYSCALL(nr, sym) __ia32_##sym,
 
-__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
-	/*
-	 * Smells like a compiler bug -- it doesn't work
-	 * when the & below is removed.
-	 */
-	[0 ... __NR_ia32_syscall_max] = &__ia32_sys_ni_syscall,
+__visible const sys_call_ptr_t ia32_sys_call_table[] = {
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index 1594ec72bcbb..be120eec1fc9 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -5,23 +5,14 @@
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <linux/syscalls.h>
-#include <asm/unistd.h>
 #include <asm/syscall.h>
 
-#define __SYSCALL_X32(nr, sym)
-#define __SYSCALL_COMMON(nr, sym) __SYSCALL_64(nr, sym)
-
-#define __SYSCALL_64(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
 #include <asm/syscalls_64.h>
-#undef __SYSCALL_64
+#undef __SYSCALL
 
-#define __SYSCALL_64(nr, sym) [nr] = __x64_##sym,
+#define __SYSCALL(nr, sym) __x64_##sym,
 
-asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
-	/*
-	 * Smells like a compiler bug -- it doesn't work
-	 * when the & below is removed.
-	 */
-	[0 ... __NR_syscall_max] = &__x64_sys_ni_syscall,
+asmlinkage const sys_call_ptr_t sys_call_table[] = {
 #include <asm/syscalls_64.h>
 };
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index f2fe0a33bcfd..bdd0e03a1265 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -5,37 +5,14 @@
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <linux/syscalls.h>
-#include <asm/unistd.h>
 #include <asm/syscall.h>
 
-/*
- * Reuse the 64-bit entry points for the x32 versions that occupy different
- * slots in the syscall table.
- */
-#define __x32_sys_readv		__x64_sys_readv
-#define __x32_sys_writev	__x64_sys_writev
-#define __x32_sys_getsockopt	__x64_sys_getsockopt
-#define __x32_sys_setsockopt	__x64_sys_setsockopt
-#define __x32_sys_vmsplice	__x64_sys_vmsplice
-#define __x32_sys_process_vm_readv	__x64_sys_process_vm_readv
-#define __x32_sys_process_vm_writev	__x64_sys_process_vm_writev
+#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#include <asm/syscalls_x32.h>
+#undef __SYSCALL
 
-#define __SYSCALL_64(nr, sym)
+#define __SYSCALL(nr, sym) __x64_##sym,
 
-#define __SYSCALL_X32(nr, sym) extern long __x32_##sym(const struct pt_regs *);
-#define __SYSCALL_COMMON(nr, sym) extern long __x64_##sym(const struct pt_regs *);
-#include <asm/syscalls_64.h>
-#undef __SYSCALL_X32
-#undef __SYSCALL_COMMON
-
-#define __SYSCALL_X32(nr, sym) [nr] = __x32_##sym,
-#define __SYSCALL_COMMON(nr, sym) [nr] = __x64_##sym,
-
-asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_x32_syscall_max+1] = {
-	/*
-	 * Smells like a compiler bug -- it doesn't work
-	 * when the & below is removed.
-	 */
-	[0 ... __NR_x32_syscall_max] = &__x64_sys_ni_syscall,
-#include <asm/syscalls_64.h>
+asmlinkage const sys_call_ptr_t x32_sys_call_table[] = {
+#include <asm/syscalls_x32.h>
 };
diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile
index d8c4f6c9eadc..5b3efed0e4e8 100644
--- a/arch/x86/entry/syscalls/Makefile
+++ b/arch/x86/entry/syscalls/Makefile
@@ -9,47 +9,54 @@ _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
 syscall32 := $(src)/syscall_32.tbl
 syscall64 := $(src)/syscall_64.tbl
 
-syshdr := $(srctree)/$(src)/syscallhdr.sh
-systbl := $(srctree)/$(src)/syscalltbl.sh
+syshdr := $(srctree)/scripts/syscallhdr.sh
+systbl := $(srctree)/scripts/syscalltbl.sh
+offset :=
+prefix :=
 
 quiet_cmd_syshdr = SYSHDR  $@
-      cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \
-		   '$(syshdr_abi_$(basetarget))' \
-		   '$(syshdr_pfx_$(basetarget))' \
-		   '$(syshdr_offset_$(basetarget))'
+      cmd_syshdr = $(CONFIG_SHELL) $(syshdr) --abis $(abis) --emit-nr \
+		$(if $(offset),--offset $(offset)) \
+		$(if $(prefix),--prefix $(prefix)) \
+		$< $@
 quiet_cmd_systbl = SYSTBL  $@
-      cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
+      cmd_systbl = $(CONFIG_SHELL) $(systbl) --abis $(abis) $< $@
 
 quiet_cmd_hypercalls = HYPERCALLS $@
       cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<, $(real-prereqs))
 
-syshdr_abi_unistd_32 := i386
+$(uapi)/unistd_32.h: abis := i386
 $(uapi)/unistd_32.h: $(syscall32) $(syshdr) FORCE
 	$(call if_changed,syshdr)
 
-syshdr_abi_unistd_32_ia32 := i386
-syshdr_pfx_unistd_32_ia32 := ia32_
+$(out)/unistd_32_ia32.h: abis := i386
+$(out)/unistd_32_ia32.h: prefix := ia32_
 $(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) FORCE
 	$(call if_changed,syshdr)
 
-syshdr_abi_unistd_x32 := common,x32
-syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT
+$(uapi)/unistd_x32.h: abis := common,x32
+$(uapi)/unistd_x32.h: offset := __X32_SYSCALL_BIT
 $(uapi)/unistd_x32.h: $(syscall64) $(syshdr) FORCE
 	$(call if_changed,syshdr)
 
-syshdr_abi_unistd_64 := common,64
+$(uapi)/unistd_64.h: abis := common,64
 $(uapi)/unistd_64.h: $(syscall64) $(syshdr) FORCE
 	$(call if_changed,syshdr)
 
-syshdr_abi_unistd_64_x32 := x32
-syshdr_pfx_unistd_64_x32 := x32_
+$(out)/unistd_64_x32.h: abis := x32
+$(out)/unistd_64_x32.h: prefix := x32_
 $(out)/unistd_64_x32.h: $(syscall64) $(syshdr) FORCE
 	$(call if_changed,syshdr)
 
+$(out)/syscalls_32.h: abis := i386
 $(out)/syscalls_32.h: $(syscall32) $(systbl) FORCE
 	$(call if_changed,systbl)
+$(out)/syscalls_64.h: abis := common,64
 $(out)/syscalls_64.h: $(syscall64) $(systbl) FORCE
 	$(call if_changed,systbl)
+$(out)/syscalls_x32.h: abis := common,x32
+$(out)/syscalls_x32.h: $(syscall64) $(systbl) FORCE
+	$(call if_changed,systbl)
 
 $(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh FORCE
 	$(call if_changed,hypercalls)
@@ -60,6 +67,7 @@ uapisyshdr-y			+= unistd_32.h unistd_64.h unistd_x32.h
 syshdr-y			+= syscalls_32.h
 syshdr-$(CONFIG_X86_64)		+= unistd_32_ia32.h unistd_64_x32.h
 syshdr-$(CONFIG_X86_64)		+= syscalls_64.h
+syshdr-$(CONFIG_X86_X32)	+= syscalls_x32.h
 syshdr-$(CONFIG_XEN)		+= xen-hypercalls.h
 
 uapisyshdr-y	:= $(addprefix $(uapi)/, $(uapisyshdr-y))
diff --git a/arch/x86/entry/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh
deleted file mode 100644
index cc1e63857427..000000000000
--- a/arch/x86/entry/syscalls/syscallhdr.sh
+++ /dev/null
@@ -1,35 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-in="$1"
-out="$2"
-my_abis=`echo "($3)" | tr ',' '|'`
-prefix="$4"
-offset="$5"
-
-fileguard=_ASM_X86_`basename "$out" | sed \
-    -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
-    -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
-grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
-    echo "#ifndef ${fileguard}"
-    echo "#define ${fileguard} 1"
-    echo ""
-
-    max=0
-    while read nr abi name entry ; do
-	if [ -z "$offset" ]; then
-	    echo "#define __NR_${prefix}${name} $nr"
-	else
-	    echo "#define __NR_${prefix}${name} ($offset + $nr)"
-        fi
-
-	max=$nr
-    done
-
-    echo ""
-    echo "#ifdef __KERNEL__"
-    echo "#define __NR_${prefix}syscall_max $max"
-    echo "#endif"
-    echo ""
-    echo "#endif /* ${fileguard} */"
-) > "$out"
diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
deleted file mode 100644
index 929bde120d6b..000000000000
--- a/arch/x86/entry/syscalls/syscalltbl.sh
+++ /dev/null
@@ -1,46 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-in="$1"
-out="$2"
-
-syscall_macro() {
-    local abi="$1"
-    local nr="$2"
-    local entry="$3"
-
-    echo "__SYSCALL_${abi}($nr, $entry)"
-}
-
-emit() {
-    local abi="$1"
-    local nr="$2"
-    local entry="$3"
-    local compat="$4"
-
-    if [ "$abi" != "I386" -a -n "$compat" ]; then
-	echo "a compat entry ($abi: $compat) for a 64-bit syscall makes no sense" >&2
-	exit 1
-    fi
-
-    if [ -z "$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 "$abi" | tr '[a-z]' '[A-Z]'`
-	emit "$abi" "$nr" "$entry" "$compat"
-    done
-) > "$out"