This is a note to let you know that I've just added the patch titled
x86/syscall: Don't force use of indirect calls for system calls
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
x86-syscall-don-t-force-use-of-indirect-calls-for-system-calls.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 287a6036dd9b15bdb5ec7b3f89f21f2c1d5861ea Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Wed, 3 Apr 2024 16:36:44 -0700
Subject: x86/syscall: Don't force use of indirect calls for system calls
From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
commit 1e3ad78334a69b36e107232e337f9d693dcc9df2 upstream.
Make <asm/syscall.h> build a switch statement instead, and the compiler can
either decide to generate an indirect jump, or - more likely these days due
to mitigations - just a series of conditional branches.
Yes, the conditional branches also have branch prediction, but the branch
prediction is much more controlled, in that it just causes speculatively
running the wrong system call (harmless), rather than speculatively running
possibly wrong random less controlled code gadgets.
This doesn't mitigate other indirect calls, but the system call indirection
is the first and most easily triggered case.
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Daniel Sneddon <daniel.sneddon@xxxxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Signed-off-by: Daniel Sneddon <daniel.sneddon@xxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/entry/common.c | 6 +++---
arch/x86/entry/syscall_32.c | 21 +++++++++++++++++++--
arch/x86/entry/syscall_64.c | 19 +++++++++++++++++--
arch/x86/entry/syscall_x32.c | 10 +++++++---
arch/x86/include/asm/syscall.h | 10 ++++------
5 files changed, 50 insertions(+), 16 deletions(-)
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -47,7 +47,7 @@ static __always_inline bool do_syscall_x
if (likely(unr < NR_syscalls)) {
unr = array_index_nospec(unr, NR_syscalls);
- regs->ax = sys_call_table[unr](regs);
+ regs->ax = x64_sys_call(regs, unr);
return true;
}
return false;
@@ -64,7 +64,7 @@ static __always_inline bool do_syscall_x
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);
+ regs->ax = x32_sys_call(regs, xnr);
return true;
}
return false;
@@ -109,7 +109,7 @@ static __always_inline void do_syscall_3
if (likely(unr < IA32_NR_syscalls)) {
unr = array_index_nospec(unr, IA32_NR_syscalls);
- regs->ax = ia32_sys_call_table[unr](regs);
+ regs->ax = ia32_sys_call(regs, unr);
} else if (nr != -1) {
regs->ax = __ia32_sys_ni_syscall(regs);
}
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -18,8 +18,25 @@
#include <asm/syscalls_32.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
+#ifdef CONFIG_X86_32
#define __SYSCALL(nr, sym) __ia32_##sym,
-
-__visible const sys_call_ptr_t ia32_sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_32.h>
};
+#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) {
+ #include <asm/syscalls_32.h>
+ default: return __ia32_sys_ni_syscall(regs);
+ }
+};
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -11,8 +11,23 @@
#include <asm/syscalls_64.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
#define __SYSCALL(nr, sym) __x64_##sym,
-
-asmlinkage const sys_call_ptr_t sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_64.h>
};
+#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) {
+ #include <asm/syscalls_64.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
+};
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -11,8 +11,12 @@
#include <asm/syscalls_x32.h>
#undef __SYSCALL
-#define __SYSCALL(nr, sym) __x64_##sym,
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-asmlinkage const sys_call_ptr_t x32_sys_call_table[] = {
-#include <asm/syscalls_x32.h>
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_x32.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
};
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,19 +16,17 @@
#include <asm/thread_info.h> /* for TS_COMPAT */
#include <asm/unistd.h>
+/* This is used purely for kernel/trace/trace_syscalls.c */
typedef long (*sys_call_ptr_t)(const struct pt_regs *);
extern const sys_call_ptr_t sys_call_table[];
-#if defined(CONFIG_X86_32)
-#define ia32_sys_call_table sys_call_table
-#else
/*
* These may not exist, but still put the prototypes in so we
* can use IS_ENABLED().
*/
-extern const sys_call_ptr_t ia32_sys_call_table[];
-extern const sys_call_ptr_t x32_sys_call_table[];
-#endif
+extern long ia32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x64_sys_call(const struct pt_regs *, unsigned int nr);
/*
* Only the low 32 bits of orig_ax are meaningful, so we return int.
Patches currently in stable-queue which might be from torvalds@xxxxxxxxxxxxxxxxxxxx are
queue-5.15/x86-cpu-amd-update-the-zenbleed-microcode-revisions.patch
queue-5.15/ring-buffer-fix-resetting-of-shortest_full.patch
queue-5.15/x86-cpufeatures-add-cpuid_lnx_5-to-track-recently-added-linux-defined-word.patch
queue-5.15/ring-buffer-use-wait_event_interruptible-in-ring_buf.patch
queue-5.15/x86-bugs-fix-the-srso-mitigation-on-zen3-4.patch
queue-5.15/x86-retpoline-do-the-necessary-fixup-to-the-zen3-4-srso-return-thunk-for-srso.patch
queue-5.15/x86-syscall-don-t-force-use-of-indirect-calls-for-system-calls.patch
queue-5.15/minmax-add-umin-a-b-and-umax-a-b.patch
queue-5.15/kasan-test-add-memcpy-test-that-avoids-out-of-bounds.patch
queue-5.15/ring-buffer-fix-waking-up-ring-buffer-readers.patch
queue-5.15/tracing-use-.flush-call-to-wake-up-readers.patch
queue-5.15/arch-introduce-config_function_alignment.patch
queue-5.15/x86-pm-work-around-false-positive-kmemleak-report-in.patch
