[PATCH 2/2] x86/speculation: Protect against userspace-userspace spectreRSB

[Tyler Hicks]

From: Jiri Kosina <jkosina at suse.cz>

The article "Spectre Returns! Speculation Attacks using the Return Stack
Buffer" [1] describes two new (sub-)variants of spectrev2-like attacks,
making use solely of the RSB contents even on CPUs that don't fallback to
BTB on RSB underflow (Skylake+).

Mitigate userspace-userspace attacks by always unconditionally filling RSB on
context switch when the generic spectrev2 mitigation has been enabled.

[1] https://arxiv.org/pdf/1807.07940.pdf

Signed-off-by: Jiri Kosina <jkosina at suse.cz>
Signed-off-by: Thomas Gleixner <tglx at linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe at redhat.com>
Acked-by: Tim Chen <tim.c.chen at linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk at oracle.com>
Cc: Borislav Petkov <bp at suse.de>
Cc: David Woodhouse <dwmw at amazon.co.uk>
Cc: Peter Zijlstra <peterz at infradead.org>
Cc: Linus Torvalds <torvalds at linux-foundation.org>
Cc: stable at vger.kernel.org
Link: https://lkml.kernel.org/r/nycvar.YFH.7.76.1807261308190.997@cbobk.fhfr.pm

CVE-2017-5715 (SpectreRSB sub-variant)

(backported from commit fdf82a7856b32d905c39afc85e34364491e46346)
Signed-off-by: Tyler Hicks <tyhicks at canonical.com>
---
 arch/x86/kernel/cpu/bugs.c | 38 +++++++-------------------------------
 1 file changed, 7 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ad435e671bd0..af712d8aafbc 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -324,23 +324,6 @@ 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();
@@ -405,22 +388,15 @@ retpoline_auto:
 	        ibrs_supported ? "supported" : "not-supported");
 
 	/*
-	 * 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.
+	 * If spectre v2 protection has been enabled, unconditionally fill
+	 * RSB during a context switch; this protects against two independent
+	 * issues:
 	 *
-	 * 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.
+	 *	- RSB underflow (and switch to BTB) on Skylake+
+	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
 	 */
-	if ((!boot_cpu_has(X86_FEATURE_KAISER) &&
-	     !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");
-	}
+	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
 	/*
 	 * If we have a full retpoline mode and then disable IBPB in kernel mode
-- 
2.7.4