linux-kernel - [RFC][PATCH 16/24] x86/pti: Execute IDT handlers on the kernel stack

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20201109144425.270789-17-alexandre.chartre@oracle.com>
Date:   Mon,  9 Nov 2020 15:44:17 +0100
From:   Alexandre Chartre <alexandre.chartre@...cle.com>
To:     tglx@...utronix.de, mingo@...hat.com, bp@...en8.de, hpa@...or.com,
        x86@...nel.org, dave.hansen@...ux.intel.com, luto@...nel.org,
        peterz@...radead.org, linux-kernel@...r.kernel.org,
        thomas.lendacky@....com, jroedel@...e.de
Cc:     konrad.wilk@...cle.com, jan.setjeeilers@...cle.com,
        junaids@...gle.com, oweisse@...gle.com, rppt@...ux.vnet.ibm.com,
        graf@...zon.de, mgross@...ux.intel.com, kuzuno@...il.com,
        alexandre.chartre@...cle.com
Subject: [RFC][PATCH 16/24] x86/pti: Execute IDT handlers on the kernel stack

After an interrupt/exception in userland, the kernel is entered
and it switches the stack to the PTI stack which is mapped both in
the kernel and in the user page-table. When executing the interrupt
function, switch to the kernel stack (which is mapped only in the
kernel page-table) so that no kernel data leak to the userland
through the stack.

For now, only changes IDT handlers which have no argument other
than the pt_regs registers.

Signed-off-by: Alexandre Chartre <alexandre.chartre@...cle.com>
---
 arch/x86/include/asm/idtentry.h | 43 +++++++++++++++++++++++++++++++--
 arch/x86/kernel/cpu/mce/core.c  |  2 +-
 arch/x86/kernel/traps.c         |  4 +--
 3 files changed, 44 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 4b4aca2b1420..3595a31947b3 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -10,10 +10,49 @@
 #include <linux/hardirq.h>
 
 #include <asm/irq_stack.h>
+#include <asm/pti.h>
 
 bool idtentry_enter_nmi(struct pt_regs *regs);
 void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
 
+/*
+ * The CALL_ON_STACK_* macro call the specified function either directly
+ * if no stack is provided, or on the specified stack.
+ */
+#define CALL_ON_STACK_1(stack, func, arg1)				\
+	((stack) ?							\
+	 asm_call_on_stack_1(stack,					\
+		(void (*)(void))(func), (void *)(arg1)) :		\
+	 func(arg1))
+
+/*
+ * Functions to return the top of the kernel stack if we are using the
+ * user page-table (and thus not running with the kernel stack). If we
+ * are using the kernel page-table (and so already using the kernel
+ * stack) when it returns NULL.
+ */
+static __always_inline void *pti_kernel_stack(struct pt_regs *regs)
+{
+	unsigned long stack;
+
+	if (pti_enabled() && user_mode(regs)) {
+		stack = (unsigned long)task_top_of_kernel_stack(current);
+		return (void *)(stack - 8);
+	} else {
+		return NULL;
+	}
+}
+
+/*
+ * Wrappers to run an IDT handler on the kernel stack if we are not
+ * already using this stack.
+ */
+static __always_inline
+void run_idt(void (*func)(struct pt_regs *), struct pt_regs *regs)
+{
+	CALL_ON_STACK_1(pti_kernel_stack(regs), func, regs);
+}
+
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
  *		      No error code pushed by hardware
@@ -55,7 +94,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	irqentry_state_t state = irqentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
-	__##func (regs);						\
+	run_idt(__##func, regs);					\
 	instrumentation_end();						\
 	irqentry_exit(regs, state);					\
 }									\
@@ -271,7 +310,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	instrumentation_begin();					\
 	__irq_enter_raw();						\
 	kvm_set_cpu_l1tf_flush_l1d();					\
-	__##func (regs);						\
+	run_idt(__##func, regs);					\
 	__irq_exit_raw();						\
 	instrumentation_end();						\
 	irqentry_exit(regs, state);					\
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4102b866e7c0..9407c3cd9355 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2035,7 +2035,7 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check)
 	unsigned long dr7;
 
 	dr7 = local_db_save();
-	exc_machine_check_user(regs);
+	run_idt(exc_machine_check_user, regs);
 	local_db_restore(dr7);
 }
 #else
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 09b22a611d99..5161385b3670 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -257,7 +257,7 @@ DEFINE_IDTENTRY_RAW(exc_invalid_op)
 
 	state = irqentry_enter(regs);
 	instrumentation_begin();
-	handle_invalid_op(regs);
+	run_idt(handle_invalid_op, regs);
 	instrumentation_end();
 	irqentry_exit(regs, state);
 }
@@ -647,7 +647,7 @@ DEFINE_IDTENTRY_RAW(exc_int3)
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
 		instrumentation_begin();
-		do_int3_user(regs);
+		run_idt(do_int3_user, regs);
 		instrumentation_end();
 		irqentry_exit_to_user_mode(regs);
 	} else {
-- 
2.18.4