From: Tim Chen <tim.c.chen@linux.intel.com>
To: Jiri Kosina <jikos@kernel.org>, Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>,
Tom Lendacky <thomas.lendacky@amd.com>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
David Woodhouse <dwmw@amazon.co.uk>,
Andi Kleen <ak@linux.intel.com>,
Dave Hansen <dave.hansen@intel.com>,
Casey Schaufler <casey.schaufler@intel.com>,
Asit Mallick <asit.k.mallick@intel.com>,
Arjan van de Ven <arjan@linux.intel.com>,
Jon Masters <jcm@redhat.com>, Waiman Long <longman9394@gmail.com>,
linux-kernel@vger.kernel.org, x86@kernel.org
Subject: [Patch v4 15/18] x86/speculation: Add Spectre v2 app to app protection modes
Date: Tue, 30 Oct 2018 11:49:22 -0700 [thread overview]
Message-ID: <d8907b5c048e7421d992f5b31cf7006bdd9791f0.1540923609.git.tim.c.chen@linux.intel.com> (raw)
In-Reply-To: <cover.1540923609.git.tim.c.chen@linux.intel.com>
In-Reply-To: <cover.1540923609.git.tim.c.chen@linux.intel.com>
This patch adds protection modes for Spectre v2 mitigations
against attacks on user processes. There are three modes:
strict mode:
In this mode, IBPB and STIBP are deployed full
time to protect all processes.
lite mode:
In this mode, IBPB and STIBP are only deployed on
processes marked with TIF_STIBP flag.
none mode:
In this mode, no mitigations are deployed.
The protection mode can be specified by the spectre_v2_app2app
boot parameter with the following semantics:
spectre_v2_app2app=
off - Turn off mitigation
lite - Protect processes which are marked non-dumpable
strict - Protect all processes
auto - Kernel selects the mode
Not specifying this option is equivalent to
spectre_v2_app2app=auto.
Setting spectre_v2=off will also turn off this mitigation.
Setting spectre_v2=on implies unconditionally enabling
this mitigation.
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
Documentation/admin-guide/kernel-parameters.txt | 18 +++
arch/x86/include/asm/nospec-branch.h | 9 ++
arch/x86/kernel/cpu/bugs.c | 153 +++++++++++++++++++++---
arch/x86/mm/tlb.c | 23 +++-
4 files changed, 183 insertions(+), 20 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 64a3bf5..5e7028e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4186,6 +4186,24 @@
Not specifying this option is equivalent to
spectre_v2=auto.
+ spectre_v2_app2app=
+ [X86] Control mitigation of Spectre variant 2
+ application to application (indirect branch speculation)
+ vulnerability.
+
+ off - Unconditionally disable mitigations
+ lite - Protect processes which are marked non-dumpable
+ strict - Protect all processes
+ auto - Kernel selects the mode
+
+ Not specifying this option is equivalent to
+ spectre_v2_app2app=auto.
+
+ Setting spectre_v2=off will also turn off this mitigation.
+
+ Setting spectre_v2=on implies unconditionally enabling
+ this mitigation.
+
spec_store_bypass_disable=
[HW] Control Speculative Store Bypass (SSB) Disable mitigation
(Speculative Store Bypass vulnerability)
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index fd2a8c1..c59a6c4 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -3,6 +3,7 @@
#ifndef _ASM_X86_NOSPEC_BRANCH_H_
#define _ASM_X86_NOSPEC_BRANCH_H_
+#include <linux/static_key.h>
#include <asm/alternative.h>
#include <asm/alternative-asm.h>
#include <asm/cpufeatures.h>
@@ -217,6 +218,12 @@ enum spectre_v2_mitigation {
SPECTRE_V2_IBRS_ENHANCED,
};
+enum spectre_v2_app2app_mitigation {
+ SPECTRE_V2_APP2APP_NONE,
+ SPECTRE_V2_APP2APP_LITE,
+ SPECTRE_V2_APP2APP_STRICT,
+};
+
/* The Speculative Store Bypass disable variants */
enum ssb_mitigation {
SPEC_STORE_BYPASS_NONE,
@@ -228,6 +235,8 @@ enum ssb_mitigation {
extern char __indirect_thunk_start[];
extern char __indirect_thunk_end[];
+DECLARE_STATIC_KEY_FALSE(spectre_v2_app_lite);
+
/*
* On VMEXIT we must ensure that no RSB predictions learned in the guest
* can be followed in the host, by overwriting the RSB completely. Both
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 190d6eb..54f4675 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -133,6 +133,14 @@ enum spectre_v2_mitigation_cmd {
SPECTRE_V2_CMD_RETPOLINE_AMD,
};
+enum spectre_v2_app2app_mitigation_cmd {
+ SPECTRE_V2_APP2APP_CMD_NONE,
+ SPECTRE_V2_APP2APP_CMD_AUTO,
+ SPECTRE_V2_APP2APP_CMD_FORCE,
+ SPECTRE_V2_APP2APP_CMD_LITE,
+ SPECTRE_V2_APP2APP_CMD_STRICT,
+};
+
static const char *spectre_v2_strings[] = {
[SPECTRE_V2_NONE] = "Vulnerable",
[SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline",
@@ -142,12 +150,24 @@ static const char *spectre_v2_strings[] = {
[SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS",
};
+static const char *spectre_v2_app2app_strings[] = {
+ [SPECTRE_V2_APP2APP_NONE] = "App-App Vulnerable",
+ [SPECTRE_V2_APP2APP_LITE] = "App-App Mitigation: Protect non-dumpable process",
+ [SPECTRE_V2_APP2APP_STRICT] = "App-App Mitigation: Full app to app attack protection",
+};
+
+DEFINE_STATIC_KEY_FALSE(spectre_v2_app_lite);
+EXPORT_SYMBOL_GPL(spectre_v2_app_lite);
+
#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
SPECTRE_V2_NONE;
+static enum spectre_v2_app2app_mitigation
+ spectre_v2_app2app_enabled __ro_after_init = SPECTRE_V2_APP2APP_NONE;
+
void
x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
{
@@ -169,6 +189,9 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
static_cpu_has(X86_FEATURE_AMD_SSBD))
hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
+ if (static_branch_unlikely(&spectre_v2_app_lite))
+ hostval |= stibp_tif_to_spec_ctrl(ti->flags);
+
if (hostval != guestval) {
msrval = setguest ? guestval : hostval;
wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
@@ -275,6 +298,66 @@ static const struct {
{ "auto", SPECTRE_V2_CMD_AUTO, false },
};
+static const struct {
+ const char *option;
+ enum spectre_v2_app2app_mitigation_cmd cmd;
+ bool secure;
+} app2app_options[] = {
+ { "off", SPECTRE_V2_APP2APP_CMD_NONE, false },
+ { "lite", SPECTRE_V2_APP2APP_CMD_LITE, false },
+ { "strict", SPECTRE_V2_APP2APP_CMD_STRICT, false },
+ { "auto", SPECTRE_V2_APP2APP_CMD_AUTO, false },
+ /*
+ * The "on" option is kept as last entry. It is implied by
+ * spectre_v2=on boot parameter and it is not checked
+ * in spectre_v2_app2app boot parameter.
+ */
+ { "on", SPECTRE_V2_APP2APP_CMD_FORCE, true },
+};
+
+static enum spectre_v2_app2app_mitigation_cmd __init
+ spectre_v2_parse_app2app_cmdline(enum spectre_v2_mitigation_cmd v2_cmd)
+{
+ enum spectre_v2_app2app_mitigation_cmd cmd;
+ char arg[20];
+ int ret, i;
+
+ if (v2_cmd == SPECTRE_V2_CMD_FORCE) {
+ cmd = SPECTRE_V2_APP2APP_CMD_FORCE;
+ goto show_cmd;
+ }
+
+ cmd = SPECTRE_V2_APP2APP_CMD_AUTO;
+ ret = cmdline_find_option(boot_command_line, "spectre_v2_app2app",
+ arg, sizeof(arg));
+ if (ret < 0)
+ return SPECTRE_V2_APP2APP_CMD_AUTO;
+
+ /*
+ * Don't check the last entry for forced mitigation. It is infered from
+ * v2_cmd == SPECTRE_V2_CMD_FORCE
+ */
+ for (i = 0; i < ARRAY_SIZE(app2app_options)-1; i++) {
+ if (!match_option(arg, ret, app2app_options[i].option))
+ continue;
+ cmd = app2app_options[i].cmd;
+ break;
+ }
+
+ if (i >= ARRAY_SIZE(app2app_options)) {
+ pr_err("unknown app to app protection option (%s). Switching to AUTO select\n", arg);
+ return SPECTRE_V2_APP2APP_CMD_AUTO;
+ }
+
+show_cmd:
+ if (app2app_options[i].secure)
+ spec2_print_if_secure(app2app_options[i].option);
+ else
+ spec2_print_if_insecure(app2app_options[i].option);
+
+ return cmd;
+}
+
static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
{
char arg[20];
@@ -327,14 +410,19 @@ static bool stibp_needed(void)
/*
* Determine if STIBP should be always on.
* Using enhanced IBRS makes using STIBP unnecessary.
+ * For lite option, STIBP is used only for task with
+ * TIF_STIBP flag. STIBP is not always on for that case.
*/
- if (spectre_v2_enabled == SPECTRE_V2_NONE)
+ if (spectre_v2_app2app_enabled == SPECTRE_V2_APP2APP_NONE)
return false;
if (static_cpu_has(X86_FEATURE_USE_IBRS_ENHANCED))
return false;
+ if (static_branch_unlikely(&spectre_v2_app_lite))
+ return false;
+
if (!boot_cpu_has(X86_FEATURE_STIBP))
return false;
@@ -374,6 +462,8 @@ static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+ enum spectre_v2_app2app_mitigation_cmd app2app_cmd;
+ enum spectre_v2_app2app_mitigation app2app_mode;
/*
* If the CPU is not affected and the command line mode is NONE or AUTO
@@ -449,12 +539,6 @@ static void __init spectre_v2_select_mitigation(void)
setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
- /* Initialize Indirect Branch Prediction Barrier if supported */
- if (boot_cpu_has(X86_FEATURE_IBPB)) {
- setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
- pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
- }
-
/*
* Retpoline means the kernel is safe because it has no indirect
* branches. Enhanced IBRS protects firmware too, so, enable restricted
@@ -471,6 +555,43 @@ static void __init spectre_v2_select_mitigation(void)
pr_info("Enabling Restricted Speculation for firmware calls\n");
}
+ app2app_mode = SPECTRE_V2_APP2APP_NONE;
+ if (!boot_cpu_has(X86_FEATURE_IBPB) ||
+ !boot_cpu_has(X86_FEATURE_STIBP))
+ goto set_app2app_mode;
+
+ app2app_cmd = spectre_v2_parse_app2app_cmdline(cmd);
+
+ switch (app2app_cmd) {
+ case SPECTRE_V2_APP2APP_CMD_NONE:
+ break;
+
+ case SPECTRE_V2_APP2APP_CMD_LITE:
+ case SPECTRE_V2_APP2APP_CMD_AUTO:
+ app2app_mode = SPECTRE_V2_APP2APP_LITE;
+ break;
+
+ case SPECTRE_V2_APP2APP_CMD_STRICT:
+ case SPECTRE_V2_APP2APP_CMD_FORCE:
+ app2app_mode = SPECTRE_V2_APP2APP_STRICT;
+ break;
+ }
+
+ /*
+ * Initialize Indirect Branch Prediction Barrier if supported
+ * and not disabled explicitly
+ */
+ if (app2app_mode != SPECTRE_V2_APP2APP_NONE) {
+ setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+ pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
+ }
+
+set_app2app_mode:
+ spectre_v2_app2app_enabled = app2app_mode;
+ pr_info("%s\n", spectre_v2_app2app_strings[app2app_mode]);
+ if (app2app_mode == SPECTRE_V2_APP2APP_LITE)
+ static_branch_enable(&spectre_v2_app_lite);
+
/* Enable STIBP if appropriate */
arch_smt_update();
}
@@ -862,21 +983,23 @@ static ssize_t l1tf_show_state(char *buf)
static char *stibp_state(void)
{
- if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
+ if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED ||
+ spectre_v2_app2app_enabled == SPECTRE_V2_APP2APP_NONE)
return "";
-
- if (x86_spec_ctrl_base & SPEC_CTRL_STIBP)
- return ", STIBP";
+ else if (spectre_v2_app2app_enabled == SPECTRE_V2_APP2APP_LITE)
+ return ", STIBP-lite";
else
- return "";
+ return ", STIBP-strict";
}
static char *ibpb_state(void)
{
- if (boot_cpu_has(X86_FEATURE_USE_IBPB))
- return ", IBPB";
- else
+ if (spectre_v2_app2app_enabled == SPECTRE_V2_APP2APP_NONE)
return "";
+ else if (spectre_v2_app2app_enabled == SPECTRE_V2_APP2APP_LITE)
+ return ", IBPB-lite";
+ else
+ return ", IBPB-strict";
}
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 073b8df..65d8c1c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -184,14 +184,27 @@ static void sync_current_stack_to_mm(struct mm_struct *mm)
static bool ibpb_needed(struct task_struct *tsk, u64 last_ctx_id)
{
/*
- * Check if the current (previous) task has access to the memory
- * of the @tsk (next) task. If access is denied, make sure to
- * issue a IBPB to stop user->user Spectre-v2 attacks.
+ * Don't issue IBPB when switching to kernel threads or staying in the
+ * same mm context.
+ */
+ if (!tsk || !tsk->mm || tsk->mm->context.ctx_id == last_ctx_id)
+ return false;
+
+ /*
+ * If lite protection mode is enabled, check the STIBP thread flag.
+ *
+ * Otherwise check if the current (previous) task has access to the
+ * the memory of the @tsk (next) task for strict app to app protection.
+ * If access is denied, make sure to issue a IBPB to stop user->user
+ * Spectre-v2 attacks.
*
* Note: __ptrace_may_access() returns 0 or -ERRNO.
*/
- return (tsk && tsk->mm && tsk->mm->context.ctx_id != last_ctx_id &&
- ptrace_may_access_sched(tsk, PTRACE_MODE_SPEC_IBPB));
+
+ if (static_branch_unlikely(&spectre_v2_app_lite))
+ return test_tsk_thread_flag(tsk, TIF_STIBP);
+ else
+ return ptrace_may_access_sched(tsk, PTRACE_MODE_SPEC_IBPB);
}
void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
--
2.9.4
next prev parent reply other threads:[~2018-10-30 19:23 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-30 18:49 [Patch v4 00/18] Provide process property based options to enable Spectre v2 userspace-userspace protection* Tim Chen
2018-10-30 18:49 ` [Patch v4 01/18] x86/speculation: Clean up spectre_v2_parse_cmdline() Tim Chen
2018-10-30 18:49 ` [Patch v4 02/18] x86/speculation: Remove unnecessary ret variable in cpu_show_common() Tim Chen
2018-10-30 18:49 ` [Patch v4 03/18] x86/speculation: Reorganize cpu_show_common() Tim Chen
2018-11-03 18:07 ` Thomas Gleixner
2018-11-05 19:12 ` Tim Chen
2018-11-05 19:17 ` Thomas Gleixner
2018-10-30 18:49 ` [Patch v4 04/18] x86/speculation: Add X86_FEATURE_USE_IBRS_ENHANCED Tim Chen
2018-10-30 18:49 ` [Patch v4 05/18] x86/speculation: Disable STIBP when enhanced IBRS is in use Tim Chen
2018-10-30 18:49 ` [Patch v4 06/18] smt: Create cpu_smt_enabled static key for SMT specific code Tim Chen
2018-10-30 18:49 ` [Patch v4 07/18] x86/smt: Convert cpu_smt_control check to cpu_smt_enabled static key Tim Chen
2018-11-03 18:29 ` Thomas Gleixner
2018-11-08 1:43 ` Tim Chen
2018-11-08 11:18 ` Thomas Gleixner
2018-10-30 18:49 ` [Patch v4 08/18] sched: Deprecate sched_smt_present and use " Tim Chen
2018-11-03 18:20 ` Thomas Gleixner
2018-11-09 22:08 ` Tim Chen
2018-10-30 18:49 ` [Patch v4 09/18] x86/speculation: Rename SSBD update functions Tim Chen
2018-10-30 18:49 ` [Patch v4 10/18] x86/speculation: Reorganize speculation control MSRs update Tim Chen
2018-10-30 18:49 ` [Patch v4 11/18] x86/speculation: Update comment on TIF_SSBD Tim Chen
2018-10-30 18:49 ` [Patch v4 12/18] x86: Group thread info flags by functionality Tim Chen
2018-10-30 18:49 ` [Patch v4 13/18] security: Update security level of a process when modifying its dumpability Tim Chen
2018-10-30 20:57 ` Schaufler, Casey
2018-10-30 21:30 ` Tim Chen
2018-10-30 21:53 ` Schaufler, Casey
2018-10-30 18:49 ` [Patch v4 14/18] x86/speculation: Turn on or off STIBP according to a task's TIF_STIBP Tim Chen
2018-10-30 18:49 ` Tim Chen [this message]
2018-10-30 18:49 ` [Patch v4 16/18] x86/speculation: Enable STIBP to protect security sensitive tasks Tim Chen
2018-10-30 21:07 ` Schaufler, Casey
2018-10-30 21:34 ` Tim Chen
2018-10-30 22:02 ` Schaufler, Casey
2018-10-30 18:49 ` [Patch v4 17/18] x86/speculation: Update SPEC_CTRL MSRs of remote CPUs Tim Chen
2018-11-04 19:49 ` Thomas Gleixner
2018-11-05 22:02 ` Tim Chen
2018-11-05 23:04 ` Thomas Gleixner
2018-11-05 23:59 ` Tim Chen
2018-11-06 7:46 ` Thomas Gleixner
2018-11-07 0:18 ` Tim Chen
2018-11-07 18:33 ` Waiman Long
2018-11-07 23:15 ` Tim Chen
2018-11-07 23:03 ` Thomas Gleixner
2018-11-08 0:22 ` Tim Chen
2018-10-30 18:49 ` [Patch v4 18/18] x86/speculation: Create PRCTL interface to restrict indirect branch speculation Tim Chen
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=d8907b5c048e7421d992f5b31cf7006bdd9791f0.1540923609.git.tim.c.chen@linux.intel.com \
--to=tim.c.chen@linux.intel.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=arjan@linux.intel.com \
--cc=asit.k.mallick@intel.com \
--cc=casey.schaufler@intel.com \
--cc=dave.hansen@intel.com \
--cc=dwmw@amazon.co.uk \
--cc=jcm@redhat.com \
--cc=jikos@kernel.org \
--cc=jpoimboe@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=longman9394@gmail.com \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=x86@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).