x86/retpoline: Fill RSB on context switch for affected CPUs

On context switch from a shallow call stack to a deeper one, as the CPU
does 'ret' up the deeper side it may encounter RSB entries (predictions for
where the 'ret' goes to) which were populated in userspace.

This is problematic if neither SMEP nor KPTI (the latter of which marks
userspace pages as NX for the kernel) are active, as malicious code in
userspace may then be executed speculatively.

Overwrite the CPU's return prediction stack with calls which are predicted
to return to an infinite loop, to "capture" speculation if this
happens. This is required both for retpoline, and also in conjunction with
IBRS for !SMEP && !KPTI.

On Skylake+ the problem is slightly different, and an *underflow* of the
RSB may cause errant branch predictions to occur. So there it's not so much
overwrite, as *filling* the RSB to attempt to prevent it getting
empty. This is only a partial solution for Skylake+ since there are many
other conditions which may result in the RSB becoming empty. The full
solution on Skylake+ is to use IBRS, which will prevent the problem even
when the RSB becomes empty. With IBRS, the RSB-stuffing will not be
required on context switch.

[ tglx: Added missing vendor check and slighty massaged comments and
  	changelog ]

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: thomas.lendacky@amd.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kees Cook <keescook@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linux-foundation.org>
Cc: Paul Turner <pjt@google.com>
Link: https://lkml.kernel.org/r/1515779365-9032-1-git-send-email-dwmw@amazon.co.uk

arch/x86/entry/entry_32.S

@@ -244,6 +244,17 @@ ENTRY(__switch_to_asm)
 	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popl	%esi
 	popl	%edi

arch/x86/entry/entry_64.S

@@ -487,6 +487,17 @@ ENTRY(__switch_to_asm)
 	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
 #endif
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * When switching from a shallower to a deeper call stack
+	 * the RSB may either underflow or use entries populated
+	 * with userspace addresses. On CPUs where those concerns
+	 * exist, overwrite the RSB with entries which capture
+	 * speculative execution to prevent attack.
+	 */
+	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
 	/* restore callee-saved registers */
 	popq	%r15
 	popq	%r14

arch/x86/include/asm/cpufeatures.h

@@ -211,6 +211,7 @@
 #define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* Fill RSB on context switches */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */

arch/x86/kernel/cpu/bugs.c

@@ -23,6 +23,7 @@
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
+#include <asm/intel-family.h>
 
 static void __init spectre_v2_select_mitigation(void);
 
@@ -155,6 +156,23 @@ disable:
 	return SPECTRE_V2_CMD_NONE;
 }
 
+/* Check for Skylake-like CPUs (for RSB handling) */
+static bool __init is_skylake_era(void)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6) {
+		switch (boot_cpu_data.x86_model) {
+		case INTEL_FAM6_SKYLAKE_MOBILE:
+		case INTEL_FAM6_SKYLAKE_DESKTOP:
+		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_KABYLAKE_MOBILE:
+		case INTEL_FAM6_KABYLAKE_DESKTOP:
+			return true;
+		}
+	}
+	return false;
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -213,6 +231,24 @@ retpoline_auto:
 
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
+
+	/*
+	 * If neither SMEP or KPTI are available, there is a risk of
+	 * hitting userspace addresses in the RSB after a context switch
+	 * from a shallow call stack to a deeper one. To prevent this fill
+	 * the entire RSB, even when using IBRS.
+	 *
+	 * Skylake era CPUs have a separate issue with *underflow* of the
+	 * RSB, when they will predict 'ret' targets from the generic BTB.
+	 * The proper mitigation for this is IBRS. If IBRS is not supported
+	 * or deactivated in favour of retpolines the RSB fill on context
+	 * switch is required.
+	 */
+	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
+	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
+		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+		pr_info("Filling RSB on context switch\n");
+	}
 }
 
 #undef pr_fmt