| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 05 May 2020 15:41:16 +0200
From: Thomas Gleixner <tglx@...utronix.de>
To: LKML <linux-kernel@...r.kernel.org>
Cc: x86@...nel.org, "Paul E. McKenney" <paulmck@...nel.org>,
Andy Lutomirski <luto@...nel.org>,
Alexandre Chartre <alexandre.chartre@...cle.com>,
Frederic Weisbecker <frederic@...nel.org>,
Paolo Bonzini <pbonzini@...hat.com>,
Sean Christopherson <sean.j.christopherson@...el.com>,
Masami Hiramatsu <mhiramat@...nel.org>,
Petr Mladek <pmladek@...e.com>,
Steven Rostedt <rostedt@...dmis.org>,
Joel Fernandes <joel@...lfernandes.org>,
Boris Ostrovsky <boris.ostrovsky@...cle.com>,
Juergen Gross <jgross@...e.com>,
Brian Gerst <brgerst@...il.com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Josh Poimboeuf <jpoimboe@...hat.com>,
Will Deacon <will@...nel.org>
Subject: [patch V4 part 2 04/18] x86/entry/common: Protect against instrumentation
Mark the various syscall entries with noinstr to protect them against
instrumentation and add the noinstr_begin()/end() annotations to mark the
parts of the functions which are safe to call out into instrumentable code.
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
---
arch/x86/entry/common.c | 135 ++++++++++++++++++++++++++++++++----------------
1 file changed, 90 insertions(+), 45 deletions(-)
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -41,15 +41,26 @@
#ifdef CONFIG_CONTEXT_TRACKING
/* Called on entry from user mode with IRQs off. */
-__visible inline noinstr void enter_from_user_mode(void)
+__visible noinstr void enter_from_user_mode(void)
{
- CT_WARN_ON(ct_state() != CONTEXT_USER);
+ enum ctx_state state = ct_state();
+
user_exit_irqoff();
+
+ instr_begin();
+ CT_WARN_ON(state != CONTEXT_USER);
+ instr_end();
}
#else
static inline void enter_from_user_mode(void) {}
#endif
+static noinstr void exit_to_user_mode(void)
+{
+ user_enter_irqoff();
+ mds_user_clear_cpu_buffers();
+}
+
static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
{
#ifdef CONFIG_X86_64
@@ -179,8 +190,7 @@ static void exit_to_usermode_loop(struct
}
}
-/* Called with IRQs disabled. */
-__visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
+static void __prepare_exit_to_usermode(struct pt_regs *regs)
{
struct thread_info *ti = current_thread_info();
u32 cached_flags;
@@ -219,10 +229,14 @@ static void exit_to_usermode_loop(struct
*/
ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
#endif
+}
- user_enter_irqoff();
-
- mds_user_clear_cpu_buffers();
+__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
+{
+ instr_begin();
+ __prepare_exit_to_usermode(regs);
+ instr_end();
+ exit_to_user_mode();
}
#define SYSCALL_EXIT_WORK_FLAGS \
@@ -251,11 +265,7 @@ static void syscall_slow_exit_work(struc
tracehook_report_syscall_exit(regs, step);
}
-/*
- * Called with IRQs on and fully valid regs. Returns with IRQs off in a
- * state such that we can immediately switch to user mode.
- */
-__visible inline void syscall_return_slowpath(struct pt_regs *regs)
+static void __syscall_return_slowpath(struct pt_regs *regs)
{
struct thread_info *ti = current_thread_info();
u32 cached_flags = READ_ONCE(ti->flags);
@@ -276,15 +286,29 @@ static void syscall_slow_exit_work(struc
syscall_slow_exit_work(regs, cached_flags);
local_irq_disable();
- prepare_exit_to_usermode(regs);
+ __prepare_exit_to_usermode(regs);
+}
+
+/*
+ * Called with IRQs on and fully valid regs. Returns with IRQs off in a
+ * state such that we can immediately switch to user mode.
+ */
+__visible noinstr void syscall_return_slowpath(struct pt_regs *regs)
+{
+ instr_begin();
+ __syscall_return_slowpath(regs);
+ instr_end();
+ exit_to_user_mode();
}
#ifdef CONFIG_X86_64
-__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
+__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
{
struct thread_info *ti;
enter_from_user_mode();
+ instr_begin();
+
local_irq_enable();
ti = current_thread_info();
if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
@@ -301,8 +325,10 @@ static void syscall_slow_exit_work(struc
regs->ax = x32_sys_call_table[nr](regs);
#endif
}
+ __syscall_return_slowpath(regs);
- syscall_return_slowpath(regs);
+ instr_end();
+ exit_to_user_mode();
}
#endif
@@ -310,10 +336,10 @@ static void syscall_slow_exit_work(struc
/*
* Does a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. Does
* all entry and exit work and returns with IRQs off. This function is
- * extremely hot in workloads that use it, and it's usually called from
+ * ex2tremely hot in workloads that use it, and it's usually called from
* do_fast_syscall_32, so forcibly inline it to improve performance.
*/
-static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
+static void do_syscall_32_irqs_on(struct pt_regs *regs)
{
struct thread_info *ti = current_thread_info();
unsigned int nr = (unsigned int)regs->orig_ax;
@@ -337,27 +363,62 @@ static __always_inline void do_syscall_3
regs->ax = ia32_sys_call_table[nr](regs);
}
- syscall_return_slowpath(regs);
+ __syscall_return_slowpath(regs);
}
/* Handles int $0x80 */
-__visible void do_int80_syscall_32(struct pt_regs *regs)
+__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
{
enter_from_user_mode();
+ instr_begin();
+
local_irq_enable();
do_syscall_32_irqs_on(regs);
+
+ instr_end();
+ exit_to_user_mode();
+}
+
+static bool __do_fast_syscall_32(struct pt_regs *regs)
+{
+ int res;
+
+ /* Fetch EBP from where the vDSO stashed it. */
+ if (IS_ENABLED(CONFIG_X86_64)) {
+ /*
+ * Micro-optimization: the pointer we're following is
+ * explicitly 32 bits, so it can't be out of range.
+ */
+ res = __get_user(*(u32 *)®s->bp,
+ (u32 __user __force *)(unsigned long)(u32)regs->sp);
+ } else {
+ res = get_user(*(u32 *)®s->bp,
+ (u32 __user __force *)(unsigned long)(u32)regs->sp);
+ }
+
+ if (res) {
+ /* User code screwed up. */
+ regs->ax = -EFAULT;
+ local_irq_disable();
+ __prepare_exit_to_usermode(regs);
+ return false;
+ }
+
+ /* Now this is just like a normal syscall. */
+ do_syscall_32_irqs_on(regs);
+ return true;
}
/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible long do_fast_syscall_32(struct pt_regs *regs)
+__visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
{
/*
* Called using the internal vDSO SYSENTER/SYSCALL32 calling
* convention. Adjust regs so it looks like we entered using int80.
*/
-
unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
- vdso_image_32.sym_int80_landing_pad;
+ vdso_image_32.sym_int80_landing_pad;
+ bool success;
/*
* SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
@@ -367,33 +428,17 @@ static __always_inline void do_syscall_3
regs->ip = landing_pad;
enter_from_user_mode();
+ instr_begin();
local_irq_enable();
+ success = __do_fast_syscall_32(regs);
- /* Fetch EBP from where the vDSO stashed it. */
- if (
-#ifdef CONFIG_X86_64
- /*
- * Micro-optimization: the pointer we're following is explicitly
- * 32 bits, so it can't be out of range.
- */
- __get_user(*(u32 *)®s->bp,
- (u32 __user __force *)(unsigned long)(u32)regs->sp)
-#else
- get_user(*(u32 *)®s->bp,
- (u32 __user __force *)(unsigned long)(u32)regs->sp)
-#endif
- ) {
-
- /* User code screwed up. */
- local_irq_disable();
- regs->ax = -EFAULT;
- prepare_exit_to_usermode(regs);
- return 0; /* Keep it simple: use IRET. */
- }
+ instr_end();
+ exit_to_user_mode();
- /* Now this is just like a normal syscall. */
- do_syscall_32_irqs_on(regs);
+ /* If it failed, keep it simple: use IRET. */
+ if (!success)
+ return 0;
#ifdef CONFIG_X86_64
/*
Powered by blists - more mailing lists