linux-kernel - [PATCH v2] x86/fpu: Avoid writing LBR bit to IA32

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-next>] [day] [month] [year] [list]

Message-Id: <20240809-xsave-lbr-fix-v2-1-04296b387380@gmail.com>
Date: Fri, 09 Aug 2024 13:53:36 -0700
From: Mitchell Levy via B4 Relay <devnull+levymitchell0.gmail.com@...nel.org>
To: Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>, 
 Borislav Petkov <bp@...en8.de>, Dave Hansen <dave.hansen@...ux.intel.com>, 
 x86@...nel.org, "H. Peter Anvin" <hpa@...or.com>, 
 Kan Liang <kan.liang@...ux.intel.com>, 
 "Peter Zijlstra (Intel)" <peterz@...radead.org>
Cc: stable@...r.kernel.org, Borislav Petkov <bp@...e.de>, 
 linux-kernel@...r.kernel.org, Dave Hansen <dave.hansen@...el.com>, 
 Mitchell Levy <levymitchell0@...il.com>
Subject: [PATCH v2] x86/fpu: Avoid writing LBR bit to IA32_XSS unless
 supported

From: Mitchell Levy <levymitchell0@...il.com>

When computing which xfeatures are available, make sure that LBR is only
present if both LBR is supported in general, as well as by XSAVES.

There are two distinct CPU features related to the use of XSAVES as it
applies to LBR: whether LBR is itself supported (strictly speaking, I'm
not sure that this is necessary to check though it's certainly a good
sanity check), and whether XSAVES supports LBR (see sections 13.2 and
13.5.12 of the Intel 64 and IA-32 Architectures Software Developer's
Manual, Volume 1). Currently, the LBR subsystem correctly checks both
(see intel_pmu_arch_lbr_init), however the xstate initialization
subsystem does not.

When calculating what value to place in the IA32_XSS MSR,
xfeatures_mask_independent only checks whether LBR support is present,
not whether XSAVES supports LBR. If XSAVES does not support LBR, this
write causes #GP, leaving the state of IA32_XSS unchanged (i.e., set to
zero, as its not written with other values, and its default value is
zero out of RESET per section 13.3 of the arch manual).

Then, the next time XRSTORS is used to restore supervisor state, it will
fail with #GP (because the RFBM has zero for all supervisor features,
which does not match the XCOMP_BV field). In particular,
XFEATURE_MASK_FPSTATE includes supervisor features, so setting up the FPU
will cause a #GP. This results in a call to fpu_reset_from_exception_fixup,
which by the same process results in another #GP. Eventually this causes
the kernel to run out of stack space and #DF.

Fixes: f0dccc9da4c0 ("x86/fpu/xstate: Support dynamic supervisor feature for LBR")
Cc: stable@...r.kernel.org

Signed-off-by: Mitchell Levy <levymitchell0@...il.com>
---
Changes in v2:
- Corrected Fixes tag (thanks tglx)
- Properly check for XSAVES support of LBR (thanks tglx)
- Link to v1: https://lore.kernel.org/r/20240808-xsave-lbr-fix-v1-1-a223806c83e7@gmail.com
---
 arch/x86/include/asm/fpu/types.h | 7 +++++++
 arch/x86/kernel/fpu/xstate.c     | 3 +++
 arch/x86/kernel/fpu/xstate.h     | 4 ++--
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index eb17f31b06d2..de16862bf230 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -591,6 +591,13 @@ struct fpu_state_config {
 	 * even without XSAVE support, i.e. legacy features FP + SSE
 	 */
 	u64 legacy_features;
+	/*
+	 * @independent_features:
+	 *
+	 * Features that are supported by XSAVES, but not managed as part of
+	 * the FPU core, such as LBR
+	 */
+	u64 independent_features;
 };

 /* FPU state configuration information */
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c5a026fee5e0..1339f8328db5 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -788,6 +788,9 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		goto out_disable;
 	}

+	fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features &
+					      XFEATURE_MASK_INDEPENDENT;
+
 	/*
 	 * Clear XSAVE features that are disabled in the normal CPUID.
 	 */
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 2ee0b9c53dcc..afb404cd2059 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -62,9 +62,9 @@ static inline u64 xfeatures_mask_supervisor(void)
 static inline u64 xfeatures_mask_independent(void)
 {
 	if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR))
-		return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR;
+		return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR;

-	return XFEATURE_MASK_INDEPENDENT;
+	return fpu_kernel_cfg.independent_features;
 }

 /* XSAVE/XRSTOR wrapper functions */

---
base-commit: de9c2c66ad8e787abec7c9d7eff4f8c3cdd28aed
change-id: 20240807-xsave-lbr-fix-02d52f641653

Best regards,
-- 
Mitchell Levy <levymitchell0@...il.com>