Merge tag 'x86_bugs_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu mitigation updates from Borislav Petkov:

 - Add a spectre_bhi=vmexit mitigation option aimed at cloud
   environments

 - Remove duplicated Spectre cmdline option documentation

 - Add separate macro definitions for syscall handlers which do not
   return in order to address objtool warnings

* tag 'x86_bugs_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/bugs: Add 'spectre_bhi=vmexit' cmdline option
  x86/bugs: Remove duplicate Spectre cmdline option descriptions
  x86/syscall: Mark exit[_group] syscall handlers __noreturn

8 files changed, 47 insertions, 28 deletions

diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index c2235bae17ef..8cc9950d7104 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -14,9 +14,12 @@
 #endif
 
 #define __SYSCALL(nr, sym) extern long __ia32_##sym(const struct pt_regs *);
-
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __ia32_##sym(const struct pt_regs *);
 #include <asm/syscalls_32.h>
-#undef __SYSCALL
+#undef  __SYSCALL
+
+#undef  __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
 
 /*
  * The sys_call_table[] is no longer used for system calls, but
@@ -28,11 +31,10 @@
 const sys_call_ptr_t sys_call_table[] = {
 #include <asm/syscalls_32.h>
 };
-#undef __SYSCALL
+#undef  __SYSCALL
 #endif
 
 #define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
-
 long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
 {
 	switch (nr) {
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index 33b3f09e6f15..ba8354424860 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -8,8 +8,12 @@
 #include <asm/syscall.h>
 
 #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
 #include <asm/syscalls_64.h>
-#undef __SYSCALL
+#undef  __SYSCALL
+
+#undef  __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
 
 /*
  * The sys_call_table[] is no longer used for system calls, but
@@ -20,10 +24,9 @@
 const sys_call_ptr_t sys_call_table[] = {
 #include <asm/syscalls_64.h>
 };
-#undef __SYSCALL
+#undef  __SYSCALL
 
 #define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-
 long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
 {
 	switch (nr) {
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index 03de4a932131..fb77908f44f3 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -8,11 +8,14 @@
 #include <asm/syscall.h>
 
 #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
 #include <asm/syscalls_x32.h>
-#undef __SYSCALL
+#undef  __SYSCALL
 
-#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+#undef  __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
 
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
 long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
 {
 	switch (nr) {
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ecf5f146783f..534c74b14fab 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -3,7 +3,7 @@
 # 32-bit system call numbers and entry vectors
 #
 # The format is:
-# <number> <abi> <name> <entry point> <compat entry point>
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
 #
 # The __ia32_sys and __ia32_compat_sys stubs are created on-the-fly for
 # sys_*() system calls and compat_sys_*() compat system calls if
@@ -13,7 +13,7 @@
 # The abi is always "i386" for this file.
 #
 0	i386	restart_syscall		sys_restart_syscall
-1	i386	exit			sys_exit
+1	i386	exit			sys_exit			-			noreturn
 2	i386	fork			sys_fork
 3	i386	read			sys_read
 4	i386	write			sys_write
@@ -264,7 +264,7 @@
 249	i386	io_cancel		sys_io_cancel
 250	i386	fadvise64		sys_ia32_fadvise64
 # 251 is available for reuse (was briefly sys_set_zone_reclaim)
-252	i386	exit_group		sys_exit_group
+252	i386	exit_group		sys_exit_group			-			noreturn
 253	i386	lookup_dcookie
 254	i386	epoll_create		sys_epoll_create
 255	i386	epoll_ctl		sys_epoll_ctl
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 129bdd475cf0..097e5a18db52 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -3,7 +3,7 @@
 # 64-bit system call numbers and entry vectors
 #
 # The format is:
-# <number> <abi> <name> <entry point>
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
 #
 # The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
 #
@@ -69,7 +69,7 @@
 57	common	fork			sys_fork
 58	common	vfork			sys_vfork
 59	64	execve			sys_execve
-60	common	exit			sys_exit
+60	common	exit			sys_exit			-			noreturn
 61	common	wait4			sys_wait4
 62	common	kill			sys_kill
 63	common	uname			sys_newuname
@@ -240,7 +240,7 @@
 228	common	clock_gettime		sys_clock_gettime
 229	common	clock_getres		sys_clock_getres
 230	common	clock_nanosleep		sys_clock_nanosleep
-231	common	exit_group		sys_exit_group
+231	common	exit_group		sys_exit_group			-			noreturn
 232	common	epoll_wait		sys_epoll_wait
 233	common	epoll_ctl		sys_epoll_ctl
 234	common	tgkill			sys_tgkill
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b6f927f6c567..45675da354f3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1625,6 +1625,7 @@ static bool __init spec_ctrl_bhi_dis(void)
 enum bhi_mitigations {
 	BHI_MITIGATION_OFF,
 	BHI_MITIGATION_ON,
+	BHI_MITIGATION_VMEXIT_ONLY,
 };
 
 static enum bhi_mitigations bhi_mitigation __ro_after_init =
@@ -1639,6 +1640,8 @@ static int __init spectre_bhi_parse_cmdline(char *str)
 		bhi_mitigation = BHI_MITIGATION_OFF;
 	else if (!strcmp(str, "on"))
 		bhi_mitigation = BHI_MITIGATION_ON;
+	else if (!strcmp(str, "vmexit"))
+		bhi_mitigation = BHI_MITIGATION_VMEXIT_ONLY;
 	else
 		pr_err("Ignoring unknown spectre_bhi option (%s)", str);
 
@@ -1659,19 +1662,22 @@ static void __init bhi_select_mitigation(void)
 			return;
 	}
 
+	/* Mitigate in hardware if supported */
 	if (spec_ctrl_bhi_dis())
 		return;
 
 	if (!IS_ENABLED(CONFIG_X86_64))
 		return;
 
-	/* Mitigate KVM by default */
-	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
-	pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
+	if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
+		pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n");
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+		return;
+	}
 
-	/* Mitigate syscalls when the mitigation is forced =on */
+	pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n");
 	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
-	pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
+	setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
 }
 
 static void __init spectre_v2_select_mitigation(void)
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 89df5d89d664..51655133eee3 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -9,6 +9,10 @@
 #include <linux/cache.h>
 #include <asm/syscall.h>
 
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
+				      unsigned long, unsigned long,
+				      unsigned long, unsigned long);
+
 /*
  * Below you can see, in terms of #define's, the differences between the x86-64
  * and the UML syscall table.
@@ -22,15 +26,13 @@
 #define sys_vm86 sys_ni_syscall
 
 #define __SYSCALL_WITH_COMPAT(nr, native, compat)	__SYSCALL(nr, native)
+#define __SYSCALL_NORETURN __SYSCALL
 
 #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 #include <asm/syscalls_32.h>
+#undef  __SYSCALL
 
-#undef __SYSCALL
 #define __SYSCALL(nr, sym) sym,
-
-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
 const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index b0b4cfd2308c..943d414f2109 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -9,6 +9,10 @@
 #include <linux/cache.h>
 #include <asm/syscall.h>
 
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
+				      unsigned long, unsigned long,
+				      unsigned long, unsigned long);
+
 /*
  * Below you can see, in terms of #define's, the differences between the x86-64
  * and the UML syscall table.
@@ -18,14 +22,13 @@
 #define sys_iopl sys_ni_syscall
 #define sys_ioperm sys_ni_syscall
 
+#define __SYSCALL_NORETURN __SYSCALL
+
 #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 #include <asm/syscalls_64.h>
+#undef  __SYSCALL
 
-#undef __SYSCALL
 #define __SYSCALL(nr, sym) sym,
-
-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
 const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 #include <asm/syscalls_64.h>
 };