Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Alexandre Chartre <alexandre.chartre@oracle.com>
To:     tglx@linutronix.de, mingo@redhat.com, bp@alien8.de, hpa@zytor.com,
        x86@kernel.org, dave.hansen@linux.intel.com, luto@kernel.org,
        peterz@infradead.org, linux-kernel@vger.kernel.org,
        thomas.lendacky@amd.com, jroedel@suse.de
Cc:     konrad.wilk@oracle.com, jan.setjeeilers@oracle.com,
        junaids@google.com, oweisse@google.com, rppt@linux.vnet.ibm.com,
        graf@amazon.de, mgross@linux.intel.com, kuzuno@gmail.com,
        alexandre.chartre@oracle.com
Subject: [RFC][PATCH 19/24] x86/pti: Execute page fault handler on the kernel stack
Date:   Mon,  9 Nov 2020 15:44:20 +0100
Message-Id: <20201109144425.270789-20-alexandre.chartre@oracle.com>
In-Reply-To: <20201109144425.270789-1-alexandre.chartre@oracle.com>
References: <20201109144425.270789-1-alexandre.chartre@oracle.com>
Precedence: bulk

After a page fault from 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 page fault handler, 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.

Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
 arch/x86/include/asm/idtentry.h | 17 +++++++++++++++++
 arch/x86/mm/fault.c             |  2 +-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 0c5d9f027112..a6725afaaec0 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -31,6 +31,13 @@ void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
 		(void (*)(void))(func), (void *)(arg1), (void *)(arg2)) : \
 	 func(arg1, arg2))
 
+#define CALL_ON_STACK_3(stack, func, arg1, arg2, arg3)			\
+	((stack) ?							\
+	 asm_call_on_stack_3(stack,					\
+		(void (*)(void))(func), (void *)(arg1), (void *)(arg2),	\
+					(void *)(arg3)) :		\
+	 func(arg1, arg2, arg3))
+
 /*
  * 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
@@ -66,6 +73,16 @@ void run_idt_errcode(void (*func)(struct pt_regs *, unsigned long),
 	CALL_ON_STACK_2(pti_kernel_stack(regs), func, regs, error_code);
 }
 
+static __always_inline
+void run_idt_pagefault(void (*func)(struct pt_regs *, unsigned long,
+				    unsigned long),
+		       struct pt_regs *regs, unsigned long error_code,
+		       unsigned long address)
+{
+	CALL_ON_STACK_3(pti_kernel_stack(regs),
+			func, regs, error_code, address);
+}
+
 static __always_inline
 void run_sysvec(void (*func)(struct pt_regs *regs), struct pt_regs *regs)
 {
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 82bf37a5c9ec..b9d03603d95d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1482,7 +1482,7 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 	state = irqentry_enter(regs);
 
 	instrumentation_begin();
-	handle_page_fault(regs, error_code, address);
+	run_idt_pagefault(handle_page_fault, regs, error_code, address);
 	instrumentation_end();
 
 	irqentry_exit(regs, state);
-- 
2.18.4