public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Ben Hutchings <ben@decadent.org.uk>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: akpm@linux-foundation.org, Denis Kirjanov <kda@linux-powerpc.org>,
	"Pawan Gupta" <pawan.kumar.gupta@linux.intel.com>,
	"Borislav Petkov" <bp@suse.de>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Michal Hocko" <mhocko@suse.com>,
	"Borislav Petkov" <bpetkov@suse.de>,
	"Josh Poimboeuf" <jpoimboe@redhat.com>
Subject: [PATCH 3.16 11/25] x86/tsx: Add config options to set tsx=on|off|auto
Date: Tue, 12 Nov 2019 23:48:08 +0000	[thread overview]
Message-ID: <lsq.1573602477.219721907@decadent.org.uk> (raw)
In-Reply-To: <lsq.1573602477.548403712@decadent.org.uk>

3.16.77-rc1 review patch.  If anyone has any objections, please let me know.

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

From: Michal Hocko <mhocko@suse.com>

commit db616173d787395787ecc93eef075fa975227b10 upstream.

There is a general consensus that TSX usage is not largely spread while
the history shows there is a non trivial space for side channel attacks
possible. Therefore the tsx is disabled by default even on platforms
that might have a safe implementation of TSX according to the current
knowledge. This is a fair trade off to make.

There are, however, workloads that really do benefit from using TSX and
updating to a newer kernel with TSX disabled might introduce a
noticeable regressions. This would be especially a problem for Linux
distributions which will provide TAA mitigations.

Introduce config options X86_INTEL_TSX_MODE_OFF, X86_INTEL_TSX_MODE_ON
and X86_INTEL_TSX_MODE_AUTO to control the TSX feature. The config
setting can be overridden by the tsx cmdline options.

 [ bp: Text cleanups from Josh. ]

Suggested-by: Borislav Petkov <bpetkov@suse.de>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
[bwh: Backported to 3.16: adjust doc filename]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/Kconfig          | 45 +++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/tsx.c | 22 +++++++++++++------
 2 files changed, 61 insertions(+), 6 deletions(-)

--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1531,6 +1531,51 @@ config X86_SMAP
 
 	  If unsure, say Y.
 
+choice
+	prompt "TSX enable mode"
+	depends on CPU_SUP_INTEL
+	default X86_INTEL_TSX_MODE_OFF
+	help
+	  Intel's TSX (Transactional Synchronization Extensions) feature
+	  allows to optimize locking protocols through lock elision which
+	  can lead to a noticeable performance boost.
+
+	  On the other hand it has been shown that TSX can be exploited
+	  to form side channel attacks (e.g. TAA) and chances are there
+	  will be more of those attacks discovered in the future.
+
+	  Therefore TSX is not enabled by default (aka tsx=off). An admin
+	  might override this decision by tsx=on the command line parameter.
+	  Even with TSX enabled, the kernel will attempt to enable the best
+	  possible TAA mitigation setting depending on the microcode available
+	  for the particular machine.
+
+	  This option allows to set the default tsx mode between tsx=on, =off
+	  and =auto. See Documentation/kernel-parameters.txt for more
+	  details.
+
+	  Say off if not sure, auto if TSX is in use but it should be used on safe
+	  platforms or on if TSX is in use and the security aspect of tsx is not
+	  relevant.
+
+config X86_INTEL_TSX_MODE_OFF
+	bool "off"
+	help
+	  TSX is disabled if possible - equals to tsx=off command line parameter.
+
+config X86_INTEL_TSX_MODE_ON
+	bool "on"
+	help
+	  TSX is always enabled on TSX capable HW - equals the tsx=on command
+	  line parameter.
+
+config X86_INTEL_TSX_MODE_AUTO
+	bool "auto"
+	help
+	  TSX is enabled on TSX capable HW that is believed to be safe against
+	  side channel attacks- equals the tsx=auto command line parameter.
+endchoice
+
 config EFI
 	bool "EFI runtime service support"
 	depends on ACPI
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -73,6 +73,14 @@ static bool __init tsx_ctrl_is_supported
 	return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR);
 }
 
+static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
+{
+	if (boot_cpu_has_bug(X86_BUG_TAA))
+		return TSX_CTRL_DISABLE;
+
+	return TSX_CTRL_ENABLE;
+}
+
 void __init tsx_init(void)
 {
 	char arg[5] = {};
@@ -88,17 +96,19 @@ void __init tsx_init(void)
 		} else if (!strcmp(arg, "off")) {
 			tsx_ctrl_state = TSX_CTRL_DISABLE;
 		} else if (!strcmp(arg, "auto")) {
-			if (boot_cpu_has_bug(X86_BUG_TAA))
-				tsx_ctrl_state = TSX_CTRL_DISABLE;
-			else
-				tsx_ctrl_state = TSX_CTRL_ENABLE;
+			tsx_ctrl_state = x86_get_tsx_auto_mode();
 		} else {
 			tsx_ctrl_state = TSX_CTRL_DISABLE;
 			pr_err("tsx: invalid option, defaulting to off\n");
 		}
 	} else {
-		/* tsx= not provided, defaulting to off */
-		tsx_ctrl_state = TSX_CTRL_DISABLE;
+		/* tsx= not provided */
+		if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO))
+			tsx_ctrl_state = x86_get_tsx_auto_mode();
+		else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF))
+			tsx_ctrl_state = TSX_CTRL_DISABLE;
+		else
+			tsx_ctrl_state = TSX_CTRL_ENABLE;
 	}
 
 	if (tsx_ctrl_state == TSX_CTRL_DISABLE) {


  parent reply	other threads:[~2019-11-12 23:50 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-12 23:47 [PATCH 3.16 00/25] 3.16.77-rc1 review Ben Hutchings
2019-11-12 23:47 ` [PATCH 3.16 01/25] KVM: Introduce kvm_get_arch_capabilities() Ben Hutchings
2019-11-12 23:47 ` [PATCH 3.16 02/25] KVM: x86: use Intel speculation bugs and features as derived in generic x86 code Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 03/25] x86/msr: Add the IA32_TSX_CTRL MSR Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 04/25] x86/cpu: Add a helper function x86_read_arch_cap_msr() Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 05/25] x86/cpu: Add a "tsx=" cmdline option with TSX disabled by default Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 06/25] x86/speculation/taa: Add mitigation for TSX Async Abort Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 07/25] x86/speculation/taa: Add sysfs reporting " Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 08/25] kvm/x86: Export MDS_NO=0 to guests when TSX is enabled Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 09/25] x86/tsx: Add "auto" option to the tsx= cmdline parameter Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 10/25] x86/speculation/taa: Add documentation for TSX Async Abort Ben Hutchings
2019-11-12 23:48 ` Ben Hutchings [this message]
2019-11-12 23:48 ` [PATCH 3.16 12/25] x86/speculation/taa: Fix printing of TAA_MSG_SMT on IBRS_ALL CPUs Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 13/25] x86/bugs: Add ITLB_MULTIHIT bug infrastructure Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 14/25] drm/i915/gen8+: Add RC6 CTX corruption WA Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 15/25] net: netem: fix error path for corrupted GSO frames Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 16/25] ath6kl: fix a NULL-ptr-deref bug in ath6kl_usb_alloc_urb_from_pipe() Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 17/25] media: usb:zr364xx:Fix KASAN:null-ptr-deref Read in zr364xx_vidioc_querycap Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 18/25] media: technisat-usb2: break out of loop at end of buffer Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 19/25] ax25: enforce CAP_NET_RAW for raw sockets Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 20/25] ieee802154: " Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 21/25] appletalk: " Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 22/25] mISDN: " Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 23/25] nfc: " Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 24/25] cfg80211: wext: avoid copying malformed SSIDs Ben Hutchings
2019-11-12 23:48 ` [PATCH 3.16 25/25] rtlwifi: Fix potential overflow on P2P code Ben Hutchings
2019-11-13 18:13 ` [PATCH 3.16 00/25] 3.16.77-rc1 review Guenter Roeck
2019-11-13 18:31   ` Ben Hutchings

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=lsq.1573602477.219721907@decadent.org.uk \
    --to=ben@decadent.org.uk \
    --cc=akpm@linux-foundation.org \
    --cc=bp@suse.de \
    --cc=bpetkov@suse.de \
    --cc=jpoimboe@redhat.com \
    --cc=kda@linux-powerpc.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mhocko@suse.com \
    --cc=pawan.kumar.gupta@linux.intel.com \
    --cc=stable@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox