From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Yu-cheng Yu <yu-cheng.yu@intel.com>,
Andy Lutomirski <luto@amacapital.net>,
Borislav Petkov <bp@alien8.de>, Borislav Petkov <bp@suse.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
Fenghua Yu <fenghua.yu@intel.com>,
"H. Peter Anvin" <hpa@zytor.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Oleg Nesterov <oleg@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Quentin Casasnovas <quentin.casasnovas@oracle.com>,
"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@kernel.org>
Subject: [PATCH 4.4 04/24] x86/fpu: Disable MPX when eagerfpu is off
Date: Thu, 14 Jun 2018 16:04:59 +0200 [thread overview]
Message-ID: <20180614132724.657637907@linuxfoundation.org> (raw)
In-Reply-To: <20180614132724.483802160@linuxfoundation.org>
4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: yu-cheng yu <yu-cheng.yu@intel.com>
commit a5fe93a549c54838063d2952dd9643b0b18aa67f upstream.
This issue is a fallout from the command-line parsing move.
When "eagerfpu=off" is given as a command-line input, the kernel
should disable MPX support. The decision for turning off MPX was
made in fpu__init_system_ctx_switch(), which is after the
selection of the XSAVE format. This patch fixes it by getting
that decision done earlier in fpu__init_system_xstate().
Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Ravi V. Shankar <ravi.v.shankar@intel.com>
Cc: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: yu-cheng yu <yu-cheng.yu@intel.com>
Link: http://lkml.kernel.org/r/1452119094-7252-4-git-send-email-yu-cheng.yu@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/x86/include/asm/fpu/internal.h | 1
arch/x86/kernel/fpu/init.c | 56 ++++++++++++++++++++++++++++--------
arch/x86/kernel/fpu/xstate.c | 3 -
3 files changed, 46 insertions(+), 14 deletions(-)
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -42,6 +42,7 @@ extern void fpu__init_cpu_xstate(void);
extern void fpu__init_system(struct cpuinfo_x86 *c);
extern void fpu__init_check_bugs(void);
extern void fpu__resume_cpu(void);
+extern u64 fpu__get_supported_xfeatures_mask(void);
/*
* Debugging facility:
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -266,7 +266,45 @@ static void __init fpu__init_system_xsta
static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
/*
+ * Find supported xfeatures based on cpu features and command-line input.
+ * This must be called after fpu__init_parse_early_param() is called and
+ * xfeatures_mask is enumerated.
+ */
+u64 __init fpu__get_supported_xfeatures_mask(void)
+{
+ /* Support all xfeatures known to us */
+ if (eagerfpu != DISABLE)
+ return XCNTXT_MASK;
+
+ /* Warning of xfeatures being disabled for no eagerfpu mode */
+ if (xfeatures_mask & XFEATURE_MASK_EAGER) {
+ pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+ xfeatures_mask & XFEATURE_MASK_EAGER);
+ }
+
+ /* Return a mask that masks out all features requiring eagerfpu mode */
+ return ~XFEATURE_MASK_EAGER;
+}
+
+/*
+ * Disable features dependent on eagerfpu.
+ */
+static void __init fpu__clear_eager_fpu_features(void)
+{
+ setup_clear_cpu_cap(X86_FEATURE_MPX);
+}
+
+/*
* Pick the FPU context switching strategy:
+ *
+ * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of
+ * the following is true:
+ *
+ * (1) the cpu has xsaveopt, as it has the optimization and doing eager
+ * FPU switching has a relatively low cost compared to a plain xsave;
+ * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU
+ * switching. Should the kernel boot with noxsaveopt, we support MPX
+ * with eager FPU switching at a higher cost.
*/
static void __init fpu__init_system_ctx_switch(void)
{
@@ -278,19 +316,11 @@ static void __init fpu__init_system_ctx_
WARN_ON_FPU(current->thread.fpu.fpstate_active);
current_thread_info()->status = 0;
- /* Auto enable eagerfpu for xsaveopt */
if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE)
eagerfpu = ENABLE;
- if (xfeatures_mask & XFEATURE_MASK_EAGER) {
- if (eagerfpu == DISABLE) {
- pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
- xfeatures_mask & XFEATURE_MASK_EAGER);
- xfeatures_mask &= ~XFEATURE_MASK_EAGER;
- } else {
- eagerfpu = ENABLE;
- }
- }
+ if (xfeatures_mask & XFEATURE_MASK_EAGER)
+ eagerfpu = ENABLE;
if (eagerfpu == ENABLE)
setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
@@ -308,10 +338,12 @@ static void __init fpu__init_parse_early
* No need to check "eagerfpu=auto" again, since it is the
* initial default.
*/
- if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off"))
+ if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) {
eagerfpu = DISABLE;
- else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on"))
+ fpu__clear_eager_fpu_features();
+ } else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) {
eagerfpu = ENABLE;
+ }
if (cmdline_find_option_bool(boot_command_line, "no387"))
setup_clear_cpu_cap(X86_FEATURE_FPU);
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -632,8 +632,7 @@ void __init fpu__init_system_xstate(void
BUG();
}
- /* Support only the state known to the OS: */
- xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+ xfeatures_mask &= fpu__get_supported_xfeatures_mask();
/* Enable xstate instructions to be able to continue with initialization: */
fpu__init_cpu_xstate();
next prev parent reply other threads:[~2018-06-14 14:14 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-06-14 14:04 [PATCH 4.4 00/24] 4.4.138-stable review Greg Kroah-Hartman
2018-06-14 14:04 ` [PATCH 4.4 01/24] x86/fpu: Fix early FPU command-line parsing Greg Kroah-Hartman
2018-06-14 14:04 ` [PATCH 4.4 02/24] x86: Remove unused function cpu_has_ht_siblings() Greg Kroah-Hartman
2018-06-14 14:04 ` [PATCH 4.4 03/24] x86/cpufeature: Remove unused and seldomly used cpu_has_xx macros Greg Kroah-Hartman
2018-06-14 14:04 ` Greg Kroah-Hartman [this message]
2018-06-14 14:05 ` [PATCH 4.4 05/24] x86/fpu: Disable AVX when eagerfpu is off Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 06/24] x86/fpu: Default eagerfpu=on on all CPUs Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 07/24] x86/fpu: Fix no387 regression Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 08/24] x86/fpu: Revert ("x86/fpu: Disable AVX when eagerfpu is off") Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 09/24] x86/fpu: Fix eager-FPU handling on legacy FPU machines Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 10/24] x86/fpu: Hard-disable lazy FPU mode Greg Kroah-Hartman
2018-06-15 4:24 ` Daniel Sangorrin
2018-06-15 4:56 ` 'Greg Kroah-Hartman'
2018-06-15 5:23 ` Daniel Sangorrin
2018-06-15 7:06 ` 'Greg Kroah-Hartman'
2018-06-15 9:49 ` Daniel Sangorrin
2018-06-19 15:02 ` Ben Hutchings
2018-06-14 14:05 ` [PATCH 4.4 11/24] x86/fpu: Fix FNSAVE usage in eagerfpu mode Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 12/24] x86/fpu: Fix math emulation in eager fpu mode Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 13/24] af_key: Always verify length of provided sadb_key Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 14/24] x86/crypto, x86/fpu: Remove X86_FEATURE_EAGER_FPU #ifdef from the crc32c code Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 15/24] gpio: No NULL owner Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 16/24] Clarify (and fix) MAX_LFS_FILESIZE macros Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 17/24] KVM: x86: introduce linear_{read,write}_system Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 18/24] KVM: x86: pass kvm_vcpu to kvm_read_guest_virt and kvm_write_guest_virt_system Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 19/24] serial: samsung: fix maxburst parameter for DMA transactions Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 20/24] vmw_balloon: fixing double free when batching mode is off Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 21/24] kvm: x86: use correct privilege level for sgdt/sidt/fxsave/fxrstor access Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 22/24] Input: goodix - add new ACPI id for GPD Win 2 touch screen Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 23/24] Input: elan_i2c - add ELAN0612 (Lenovo v330 14IKB) ACPI ID Greg Kroah-Hartman
2018-06-14 14:05 ` [PATCH 4.4 24/24] crypto: vmx - Remove overly verbose printk from AES init routines Greg Kroah-Hartman
2018-06-14 16:57 ` [PATCH 4.4 00/24] 4.4.138-stable review Nathan Chancellor
2018-06-14 18:47 ` Greg Kroah-Hartman
2018-06-14 22:43 ` Shuah Khan
2018-06-15 0:24 ` Naresh Kamboju
2018-06-15 15:18 ` Guenter Roeck
2018-06-19 14:28 ` Ben Hutchings
2018-06-28 4:09 ` Daniel Sangorrin
2018-07-05 16:08 ` Greg Kroah-Hartman
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=20180614132724.657637907@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=bp@alien8.de \
--cc=bp@suse.de \
--cc=dave.hansen@linux.intel.com \
--cc=fenghua.yu@intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=quentin.casasnovas@oracle.com \
--cc=ravi.v.shankar@intel.com \
--cc=sai.praneeth.prakhya@intel.com \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=yu-cheng.yu@intel.com \
/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).