linux-kernel - [RFC 06/10] x86/speculation: Add inlines to control Indirect Branch Speculation

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]

Date:   Sat, 20 Jan 2018 20:22:57 +0100
From:   KarimAllah Ahmed <karahmed@...zon.de>
To:     linux-kernel@...r.kernel.org
Cc:     KarimAllah Ahmed <karahmed@...zon.de>,
        Andi Kleen <ak@...ux.intel.com>,
        Andrea Arcangeli <aarcange@...hat.com>,
        Andy Lutomirski <luto@...nel.org>,
        Arjan van de Ven <arjan@...ux.intel.com>,
        Ashok Raj <ashok.raj@...el.com>,
        Asit Mallick <asit.k.mallick@...el.com>,
        Borislav Petkov <bp@...e.de>,
        Dan Williams <dan.j.williams@...el.com>,
        Dave Hansen <dave.hansen@...el.com>,
        David Woodhouse <dwmw@...zon.co.uk>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        "H . Peter Anvin" <hpa@...or.com>, Ingo Molnar <mingo@...hat.com>,
        Janakarajan Natarajan <Janakarajan.Natarajan@....com>,
        Joerg Roedel <joro@...tes.org>,
        Jun Nakajima <jun.nakajima@...el.com>,
        Laura Abbott <labbott@...hat.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Radim Krčmář <rkrcmar@...hat.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Tom Lendacky <thomas.lendacky@....com>, kvm@...r.kernel.org,
        x86@...nel.org
Subject: [RFC 06/10] x86/speculation: Add inlines to control Indirect Branch Speculation

From: Thomas Gleixner <tglx@...utronix.de>

XX: I am utterly unconvinced that having "friendly, self-explanatory"
    names for the IBRS-frobbing inlines is useful. There be dragons
    here for anyone who isn't intimately familiar with what's going
    on, and it's almost better to just call it IBRS, put a reference
    to the spec, and have a clear "you must be →this← tall to ride."

[karahmed: switch to using ALTERNATIVES instead of static_cpu_has]
[dwmw2: wrmsr args inside the ALTERNATIVE again, bikeshed naming]

Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Signed-off-by: KarimAllah Ahmed <karahmed@...zon.de>
Signed-off-by: David Woodhouse <dwmw@...zon.co.uk>
---
 arch/x86/include/asm/nospec-branch.h | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 8759449..5be3443 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -232,5 +232,41 @@ static inline void indirect_branch_prediction_barrier(void)
 		     : "memory");
 }
 
+/*
+ * This also performs a barrier, and setting it again when it was already
+ * set is NOT a no-op.
+ */
+static inline void restrict_branch_speculation(void)
+{
+	unsigned long ax, cx, dx;
+
+	asm volatile(ALTERNATIVE("",
+				 "movl %[msr], %%ecx\n\t"
+				 "movl %[val], %%eax\n\t"
+				 "movl $0, %%edx\n\t"
+				 "wrmsr",
+				 X86_FEATURE_IBRS)
+		     : "=a" (ax), "=c" (cx), "=d" (dx)
+		     : [msr] "i" (MSR_IA32_SPEC_CTRL),
+		       [val] "i" (SPEC_CTRL_IBRS)
+		     : "memory");
+}
+
+static inline void unrestrict_branch_speculation(void)
+{
+	unsigned long ax, cx, dx;
+
+	asm volatile(ALTERNATIVE("",
+				 "movl %[msr], %%ecx\n\t"
+				 "movl %[val], %%eax\n\t"
+				 "movl $0, %%edx\n\t"
+				 "wrmsr",
+				 X86_FEATURE_IBRS)
+		     : "=a" (ax), "=c" (cx), "=d" (dx)
+		     : [msr] "i" (MSR_IA32_SPEC_CTRL),
+		       [val] "i" (0)
+		     : "memory");
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __NOSPEC_BRANCH_H__ */
-- 
2.7.4