linux-kernel - [PATCH 4.19 054/361] arm64: cpufeature: ctr: Fix cpu capability check for late CPUs

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]

Message-Id: <20181111221627.670246412@linuxfoundation.org>
Date:   Sun, 11 Nov 2018 14:16:41 -0800
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Philip Elcan <pelcan@...eaurora.org>,
        Shanker Donthineni <shankerd@...eaurora.org>,
        Mark Rutland <mark.rutland@....com>,
        Will Deacon <will.deacon@....com>,
        Suzuki K Poulose <suzuki.poulose@....com>,
        Catalin Marinas <catalin.marinas@....com>,
        Sasha Levin <sashal@...nel.org>
Subject: [PATCH 4.19 054/361] arm64: cpufeature: ctr: Fix cpu capability check for late CPUs

4.19-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Suzuki K Poulose <suzuki.poulose@....com>

[ Upstream commit 8ab66cbe63aeaf9e5970fb4aaef1c660fca59321 ]

The matches() routine for a capability must honor the "scope"
passed to it and return the proper results.
i.e, when passed with SCOPE_LOCAL_CPU, it should check the
status of the capability on the current CPU. This is used by
verify_local_cpu_capabilities() on a late secondary CPU to make
sure that it's compliant with the established system features.
However, ARM64_HAS_CACHE_{IDC/DIC} always checks the system wide
registers and this could mean that a late secondary CPU could return
"true" (since the CPU hasn't updated the system wide registers yet)
and thus lead the system in an inconsistent state, where
the system assumes it has IDC/DIC feature, while the new CPU
doesn't.

Fixes: commit 6ae4b6e0578886eb36 ("arm64: Add support for new control bits CTR_EL0.DIC and CTR_EL0.IDC")
Cc: Philip Elcan <pelcan@...eaurora.org>
Cc: Shanker Donthineni <shankerd@...eaurora.org>
Cc: Mark Rutland <mark.rutland@....com>
Cc: Will Deacon <will.deacon@....com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@....com>
Signed-off-by: Catalin Marinas <catalin.marinas@....com>
Signed-off-by: Sasha Levin <sashal@...nel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 arch/arm64/kernel/cpufeature.c |   22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -848,15 +848,29 @@ static bool has_no_fpsimd(const struct a
 }
 
 static bool has_cache_idc(const struct arm64_cpu_capabilities *entry,
-			  int __unused)
+			  int scope)
 {
-	return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_IDC_SHIFT);
+	u64 ctr;
+
+	if (scope == SCOPE_SYSTEM)
+		ctr = arm64_ftr_reg_ctrel0.sys_val;
+	else
+		ctr = read_cpuid_cachetype();
+
+	return ctr & BIT(CTR_IDC_SHIFT);
 }
 
 static bool has_cache_dic(const struct arm64_cpu_capabilities *entry,
-			  int __unused)
+			  int scope)
 {
-	return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_DIC_SHIFT);
+	u64 ctr;
+
+	if (scope == SCOPE_SYSTEM)
+		ctr = arm64_ftr_reg_ctrel0.sys_val;
+	else
+		ctr = read_cpuid_cachetype();
+
+	return ctr & BIT(CTR_DIC_SHIFT);
 }
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0