All of lore.kernel.org
 help / color / mirror / Atom feed
From: Youquan Song <youquan.song@intel.com>
To: stable@vger.kernel.org, gregkh@linuxfoundation.org
Cc: tim.c.chen@linux.intel.com, ashok.raj@intel.com,
	dave.hansen@intel.com, yi.y.sun@linux.intel.com,
	youquan.song@intel.com, youquan.song@linux.intel.com,
	David Woodhouse <dwmw@amazon.co.uk>,
	ak@linux.intel.com, karahmed@amazon.de, arjan@linux.intel.com,
	torvalds@linux-foundation.org, peterz@infradead.org,
	bp@alien8.de, pbonzini@redhat.com, gregkh@linux-foundation.org
Subject: [PATCH 08/24] x86/cpufeatures: Clean up Spectre v2 related CPUID flags
Date: Tue, 17 Apr 2018 00:27:04 -0400	[thread overview]
Message-ID: <1523939240-16508-8-git-send-email-youquan.song@intel.com> (raw)
In-Reply-To: <1523939240-16508-1-git-send-email-youquan.song@intel.com>

From: David Woodhouse <dwmw@amazon.co.uk>

(cherry picked from commit 2961298efe1ea1b6fc0d7ee8b76018fa6c0bcef2)

We want to expose the hardware features simply in /proc/cpuinfo as "ibrs",
"ibpb" and "stibp". Since AMD has separate CPUID bits for those, use them
as the user-visible bits.

When the Intel SPEC_CTRL bit is set which indicates both IBRS and IBPB
capability, set those (AMD) bits accordingly. Likewise if the Intel STIBP
bit is set, set the AMD STIBP that's used for the generic hardware
capability.

Hide the rest from /proc/cpuinfo by putting "" in the comments. Including
RETPOLINE and RETPOLINE_AMD which shouldn't be visible there. There are
patches to make the sysfs vulnerabilities information non-readable by
non-root, and the same should apply to all information about which
mitigations are actually in use. Those *shouldn't* appear in /proc/cpuinfo.

The feature bit for whether IBPB is actually used, which is needed for
ALTERNATIVEs, is renamed to X86_FEATURE_USE_IBPB.

Originally-by: Borislav Petkov <bp@suse.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: ak@linux.intel.com
Cc: dave.hansen@intel.com
Cc: karahmed@amazon.de
Cc: arjan@linux.intel.com
Cc: torvalds@linux-foundation.org
Cc: peterz@infradead.org
Cc: bp@alien8.de
Cc: pbonzini@redhat.com
Cc: tim.c.chen@linux.intel.com
Cc: gregkh@linux-foundation.org
Link: https://lkml.kernel.org/r/1517070274-12128-2-git-send-email-dwmw@amazon.co.uk
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Youquan Song <youquan.song@linux.intel.com> [v4.4 backport]
---
 arch/x86/include/asm/cpufeature.h    | 13 +++++++------
 arch/x86/include/asm/nospec-branch.h |  2 +-
 arch/x86/kernel/cpu/bugs.c           |  7 +++----
 arch/x86/kernel/cpu/intel.c          | 31 +++++++++++++++++++++----------
 4 files changed, 32 insertions(+), 21 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index fe318a5..13a53a6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -206,7 +206,7 @@
 /* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
 #define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */
 
-#define X86_FEATURE_IBPB		( 7*32+21) /* Indirect Branch Prediction Barrier enabled*/
+#define X86_FEATURE_USE_IBPB	( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
@@ -267,13 +267,14 @@
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
 #define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_AMD_PRED_CMD (13*32+12) /* Prediction Command MSR (AMD) */
-#define X86_FEATURE_AMD_SPEC_CTRL (13*32+14) /* Speculation Control MSR only (AMD) */
-#define X86_FEATURE_AMD_STIBP  (13*32+15) /* Single Thread Indirect Branch Predictors (AMD) */
+#define X86_FEATURE_IBPB	(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS	(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP	(13*32+15) /* Single Thread Indirect Branch Predictors */
+
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 14 */
-#define X86_FEATURE_SPEC_CTRL          (14*32+26) /* Speculation Control (IBRS + IBPB) */
-#define X86_FEATURE_STIBP              (14*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_SPEC_CTRL		(14*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP		(14*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES  (14*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 
 /*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index a884fd3..9a00eaa 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -201,7 +201,7 @@ static inline void indirect_branch_prediction_barrier(void)
 				 "movl %[val], %%eax\n\t"
 				 "movl $0, %%edx\n\t"
 				 "wrmsr",
-				 X86_FEATURE_IBPB)
+				 X86_FEATURE_USE_IBPB)
 		     : : [msr] "i" (MSR_IA32_PRED_CMD),
 			 [val] "i" (PRED_CMD_IBPB)
 		     : "eax", "ecx", "edx", "memory");
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 719712e..478ac10 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -298,9 +298,8 @@ retpoline_auto:
 	}
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
-	if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) ||
-	    boot_cpu_has(X86_FEATURE_AMD_PRED_CMD)) {
-		setup_force_cpu_cap(X86_FEATURE_IBPB);
+	if (boot_cpu_has(X86_FEATURE_IBPB)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 		pr_info("Enabling Indirect Branch Prediction Barrier\n");
 	}
 }
@@ -333,7 +332,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 		return sprintf(buf, "Not affected\n");
 
 	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-			boot_cpu_has(X86_FEATURE_IBPB) ? ", IPBP" : "",
+			boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
 			spectre_v2_module_string());
 }
 #endif
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f6e71a4..000aff7 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -105,17 +105,28 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
 	}
 
-	if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) ||
-	     cpu_has(c, X86_FEATURE_STIBP) ||
-	     cpu_has(c, X86_FEATURE_AMD_SPEC_CTRL) ||
-	     cpu_has(c, X86_FEATURE_AMD_PRED_CMD) ||
-	     cpu_has(c, X86_FEATURE_AMD_STIBP)) && bad_spectre_microcode(c)) {
-		pr_warn("Intel Spectre v2 broken microcode detected; disabling SPEC_CTRL\n");
-		clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+	/*
+	 * The Intel SPEC_CTRL CPUID bit implies IBRS and IBPB support,
+	 * and they also have a different bit for STIBP support. Also,
+	 * a hypervisor might have set the individual AMD bits even on
+	 * Intel CPUs, for finer-grained selection of what's available.
+	 */
+	if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) {
+		set_cpu_cap(c, X86_FEATURE_IBRS);
+		set_cpu_cap(c, X86_FEATURE_IBPB);
+	}
+	if (cpu_has(c, X86_FEATURE_INTEL_STIBP))
+		set_cpu_cap(c, X86_FEATURE_STIBP);
+
+	/* Now if any of them are set, check the blacklist and clear the lot */
+	if ((cpu_has(c, X86_FEATURE_IBRS) || cpu_has(c, X86_FEATURE_IBPB) ||
+	     cpu_has(c, X86_FEATURE_STIBP)) && bad_spectre_microcode(c)) {
+		pr_warn("Intel Spectre v2 broken microcode detected; disabling Speculation Control\n");
+		clear_cpu_cap(c, X86_FEATURE_IBRS);
+		clear_cpu_cap(c, X86_FEATURE_IBPB);
 		clear_cpu_cap(c, X86_FEATURE_STIBP);
-		clear_cpu_cap(c, X86_FEATURE_AMD_SPEC_CTRL);
-		clear_cpu_cap(c, X86_FEATURE_AMD_PRED_CMD);
-		clear_cpu_cap(c, X86_FEATURE_AMD_STIBP);
+		clear_cpu_cap(c, X86_FEATURE_SPEC_CTRL);
+		clear_cpu_cap(c, X86_FEATURE_INTEL_STIBP);
 	}
 
 	/*
-- 
1.8.3.1

  parent reply	other threads:[~2018-04-16 16:58 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-17  4:26 [PATCH 01/24] x86/cpufeatures: Add CPUID_7_EDX CPUID leaf Youquan Song
2018-04-16 18:27 ` Greg KH
2018-04-17  4:26 ` [PATCH 02/24] x86/cpufeatures: Add Intel feature bits for Speculation Control Youquan Song
2018-04-17  4:26 ` [PATCH 03/24] x86/cpufeatures: Add AMD " Youquan Song
2018-04-17  4:27 ` [PATCH 04/24] x86/msr: Add definitions for new speculation control MSRs Youquan Song
2018-04-17  4:27 ` [PATCH 05/24] x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown Youquan Song
2018-04-17  4:27 ` [PATCH 06/24] x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes Youquan Song
2018-04-17  4:27 ` [PATCH 07/24] x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support Youquan Song
2018-04-17  4:27 ` Youquan Song [this message]
2018-04-17  4:27 ` [PATCH 09/24] x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel Youquan Song
2018-04-17  4:27 ` [PATCH 10/24] x86/speculation: Add <asm/msr-index.h> dependency Youquan Song
2018-04-17  4:27 ` [PATCH 11/24] x86/mm: Give each mm TLB flush generation a unique ID Youquan Song
2018-04-17  4:27 ` [PATCH 12/24] x86/speculation: Use Indirect Branch Prediction Barrier in context switch Youquan Song
2018-04-17  4:27 ` [PATCH 13/24] x86/speculation: Use IBRS if available before calling into firmware Youquan Song
2018-04-17  4:27 ` [PATCH 14/24] x86/speculation: Move firmware_restrict_branch_speculation_*() from C to CPP Youquan Song
2018-04-17  4:27 ` [PATCH 15/24] KVM: nVMX: Eliminate vmcs02 pool Youquan Song
2018-04-17  4:27 ` [PATCH 16/24] KVM: VMX: introduce alloc_loaded_vmcs Youquan Song
2018-04-17  4:27 ` [PATCH 17/24] KVM: VMX: make MSR bitmaps per-VCPU Youquan Song
2018-04-17  4:27 ` [PATCH 18/24] KVM/x86: Add IBPB support Youquan Song
2018-04-17  4:27 ` [PATCH 19/24] KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES Youquan Song
2018-04-17  4:27 ` [PATCH 20/24] KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL Youquan Song
2018-04-17  4:27 ` [PATCH 21/24] KVM/SVM: " Youquan Song
2018-04-17  4:27 ` [PATCH 22/24] KVM/x86: Remove indirect MSR op calls from SPEC_CTRL Youquan Song
2018-04-17  4:27 ` [PATCH 23/24] KVM/VMX: Optimize vmx_vcpu_run() and svm_vcpu_run() by marking the RDMSR path as unlikely() Youquan Song
2018-04-17  4:27 ` [PATCH 24/24] x86/spectre_v2: Don't check microcode versions when running under hypervisors Youquan Song
2018-04-18  3:18 [PATCH 00/24] Backport Speculation Control support for 4.4 Youquan Song
2018-04-18  3:18 ` [PATCH 08/24] x86/cpufeatures: Clean up Spectre v2 related CPUID flags Youquan Song

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1523939240-16508-8-git-send-email-youquan.song@intel.com \
    --to=youquan.song@intel.com \
    --cc=ak@linux.intel.com \
    --cc=arjan@linux.intel.com \
    --cc=ashok.raj@intel.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@intel.com \
    --cc=dwmw@amazon.co.uk \
    --cc=gregkh@linux-foundation.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=karahmed@amazon.de \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=stable@vger.kernel.org \
    --cc=tim.c.chen@linux.intel.com \
    --cc=torvalds@linux-foundation.org \
    --cc=yi.y.sun@linux.intel.com \
    --cc=youquan.song@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.