From: "Chang S. Bae" <chang.seok.bae@intel.com>
To: linux-kernel@vger.kernel.org
Cc: ravi.v.shankar@intel.com, chang.seok.bae@intel.com,
Andy Lutomirski <luto@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
Borislav Petkov <bp@alien8.de>, "H . Peter Anvin" <hpa@zytor.com>,
Dave Hansen <dave.hansen@intel.com>,
Tony Luck <tony.luck@intel.com>, Andi Kleen <ak@linux.intel.com>
Subject: [PATCH v8 06/17] x86/fsgsbase/64: Use FSGSBASE in switch_to() if available
Date: Thu, 12 Sep 2019 13:06:47 -0700 [thread overview]
Message-ID: <1568318818-4091-7-git-send-email-chang.seok.bae@intel.com> (raw)
In-Reply-To: <1568318818-4091-1-git-send-email-chang.seok.bae@intel.com>
From: Andy Lutomirski <luto@kernel.org>
With the new FSGSBASE instructions, FS/GS base can be efficiently read
and written in __switch_to(). Use that capability to preserve the full
state.
This will enable user code to do whatever it wants with the new
instructions without any kernel-induced gotchas. (There can still be
architectural gotchas: movl %gs,%eax; movl %eax,%gs may change GS base
if WRGSBASE was used, but users are expected to read the CPU manual
before doing things like that.)
This is a considerable speedup. It seems to save about 100 cycles per
context switch compared to the baseline 4.6-rc1 behavior on a Skylake
laptop.
[ chang: 5~10% performance improvements were seen by a context switch
benchmark that ran threads with different FS/GS base values (to the
baseline 4.16). ]
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
---
Changes from v7:
* Used appropriate GS base read/write functions depending on interrupt
conditions. This fixes the bug in v7.
* Massaged changelog by Thomas
* Used '[FS|GS] base' consistently, instead of '[FS|GS]BASE'
---
arch/x86/kernel/process_64.c | 40 ++++++++++++++++++++++++++++++++++------
1 file changed, 34 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c8a67bf..4c388817 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -234,8 +234,21 @@ static __always_inline void save_fsgs(struct task_struct *task)
{
savesegment(fs, task->thread.fsindex);
savesegment(gs, task->thread.gsindex);
- save_base_legacy(task, task->thread.fsindex, FS);
- save_base_legacy(task, task->thread.gsindex, GS);
+ if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+ /*
+ * If FSGSBASE is enabled, we can't make any useful guesses
+ * about the base, and user code expects us to save the current
+ * value. Fortunately, reading the base directly is efficient.
+ */
+ task->thread.fsbase = rdfsbase();
+ if (irqs_disabled())
+ task->thread.gsbase = __rdgsbase_inactive();
+ else
+ task->thread.gsbase = x86_gsbase_read_cpu_inactive();
+ } else {
+ save_base_legacy(task, task->thread.fsindex, FS);
+ save_base_legacy(task, task->thread.gsindex, GS);
+ }
}
#if IS_ENABLED(CONFIG_KVM)
@@ -314,10 +327,25 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
static __always_inline void x86_fsgsbase_load(struct thread_struct *prev,
struct thread_struct *next)
{
- load_seg_legacy(prev->fsindex, prev->fsbase,
- next->fsindex, next->fsbase, FS);
- load_seg_legacy(prev->gsindex, prev->gsbase,
- next->gsindex, next->gsbase, GS);
+ if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+ /* Update the FS and GS selectors if they could have changed. */
+ if (unlikely(prev->fsindex || next->fsindex))
+ loadseg(FS, next->fsindex);
+ if (unlikely(prev->gsindex || next->gsindex))
+ loadseg(GS, next->gsindex);
+
+ /* Update the bases. */
+ wrfsbase(next->fsbase);
+ if (irqs_disabled())
+ __wrgsbase_inactive(next->gsbase);
+ else
+ x86_gsbase_write_cpu_inactive(next->gsbase);
+ } else {
+ load_seg_legacy(prev->fsindex, prev->fsbase,
+ next->fsindex, next->fsbase, FS);
+ load_seg_legacy(prev->gsindex, prev->gsbase,
+ next->gsindex, next->gsbase, GS);
+ }
}
static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
--
2.7.4
next prev parent reply other threads:[~2019-09-12 20:08 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-12 20:06 [PATCH v8 00/17] Enable FSGSBASE instructions Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 01/17] x86/ptrace: Prevent ptrace from clearing the FS/GS selector Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 02/17] selftests/x86/fsgsbase: Test GS selector on ptracer-induced GS base write Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 03/17] x86/cpu: Add 'unsafe_fsgsbase' to enable CR4.FSGSBASE Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 04/17] x86/fsgsbase/64: Add intrinsics for FSGSBASE instructions Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 05/17] x86/fsgsbase/64: Enable FSGSBASE instructions in helper functions Chang S. Bae
2019-09-12 20:06 ` Chang S. Bae [this message]
2019-09-12 20:06 ` [PATCH v8 07/17] x86/fsgsbase/64: Use FSGSBASE instructions on thread copy and ptrace Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 08/17] x86/entry/64: Clean up paranoid exit Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 09/17] x86/entry/64: Switch CR3 before SWAPGS in paranoid entry Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 10/17] x86/entry/64: Introduce the FIND_PERCPU_BASE macro Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 11/17] x86/entry/64: Handle FSGSBASE enabled paranoid entry/exit Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 12/17] x86/entry/64: Document GSBASE handling in the paranoid path Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 13/17] x86/speculation/swapgs: Check FSGSBASE in enabling SWAPGS mitigation Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 14/17] selftests/x86/fsgsbase: Test ptracer-induced GS base write with FSGSBASE Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 15/17] x86/fsgsbase/64: Enable FSGSBASE on 64bit by default and add a chicken bit Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 16/17] x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2 Chang S. Bae
2019-09-12 20:06 ` [PATCH v8 17/17] Documentation/x86/64: Add documentation for GS/FS addressing mode Chang S. Bae
2019-09-27 21:25 ` Randy Dunlap
2019-09-27 21:50 ` Bae, Chang Seok
2019-09-13 4:10 ` [PATCH v8 00/17] Enable FSGSBASE instructions Andy Lutomirski
2019-09-16 9:21 ` Thomas Gleixner
2019-09-18 21:02 ` Bae, Chang Seok
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=1568318818-4091-7-git-send-email-chang.seok.bae@intel.com \
--to=chang.seok.bae@intel.com \
--cc=ak@linux.intel.com \
--cc=bp@alien8.de \
--cc=dave.hansen@intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=ravi.v.shankar@intel.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@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).