From: Ingo Molnar <mingo@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
Thomas Gleixner <tglx@linutronix.de>,
Andrew Morton <akpm@linux-foundation.org>
Subject: [GIT PULL] x86/fpu tree changes for v3.18
Date: Mon, 13 Oct 2014 09:38:33 +0200 [thread overview]
Message-ID: <20141013073833.GA14790@gmail.com> (raw)
Linus,
Please pull the latest x86-fpu-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-fpu-for-linus
# HEAD: 6f46b3aef0031c08a7b439d63013dad2aeb093b2 x86: copy_thread: Don't nullify ->ptrace_bps twice
x86 FPU handling fixes, cleanups and enhancements from Oleg.
The signal handling race fix and the __restore_xstate_sig()
preemption fix for eager-mode is marked for -stable as well.
Thanks,
Ingo
------------------>
Oleg Nesterov (7):
x86, fpu: shift drop_init_fpu() from save_xstate_sig() to handle_signal()
x86, fpu: __restore_xstate_sig()->math_state_restore() needs preempt_disable()
x86, fpu: Change __thread_fpu_begin() to use use_eager_fpu()
x86, fpu: copy_process: Avoid fpu_alloc/copy if !used_math()
x86, fpu: copy_process: Sanitize fpu->last_cpu initialization
x86, fpu: Shift "fpu_counter = 0" from copy_thread() to arch_dup_task_struct()
x86: copy_thread: Don't nullify ->ptrace_bps twice
arch/x86/include/asm/fpu-internal.h | 2 +-
arch/x86/kernel/process.c | 16 +++++++++-------
arch/x86/kernel/process_32.c | 6 +-----
arch/x86/kernel/process_64.c | 3 ---
arch/x86/kernel/signal.c | 5 +++++
arch/x86/kernel/xsave.c | 7 ++++---
6 files changed, 20 insertions(+), 19 deletions(-)
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 412ececa00b9..e97622f57722 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -344,7 +344,7 @@ static inline void __thread_fpu_end(struct task_struct *tsk)
static inline void __thread_fpu_begin(struct task_struct *tsk)
{
- if (!static_cpu_has_safe(X86_FEATURE_EAGER_FPU))
+ if (!use_eager_fpu())
clts();
__thread_set_has_fpu(tsk);
}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f804dc935d2a..e127ddaa2d5a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -64,14 +64,16 @@ EXPORT_SYMBOL_GPL(task_xstate_cachep);
*/
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
- int ret;
-
*dst = *src;
- if (fpu_allocated(&src->thread.fpu)) {
- memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
- ret = fpu_alloc(&dst->thread.fpu);
- if (ret)
- return ret;
+
+ dst->thread.fpu_counter = 0;
+ dst->thread.fpu.has_fpu = 0;
+ dst->thread.fpu.last_cpu = ~0;
+ dst->thread.fpu.state = NULL;
+ if (tsk_used_math(src)) {
+ int err = fpu_alloc(&dst->thread.fpu);
+ if (err)
+ return err;
fpu_copy(dst, src);
}
return 0;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 7bc86bbe7485..8f3ebfe710d0 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -138,6 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
+ memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
@@ -152,9 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
childregs->orig_ax = -1;
childregs->cs = __KERNEL_CS | get_kernel_rpl();
childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
- p->thread.fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
- memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
return 0;
}
*childregs = *current_pt_regs();
@@ -165,13 +164,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.ip = (unsigned long) ret_from_fork;
task_user_gs(p) = get_user_gs(current_pt_regs());
- p->thread.fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
tsk = current;
err = -ENOMEM;
- memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
IO_BITMAP_BYTES, GFP_KERNEL);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ca5b02d405c3..3ed4a68d4013 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -163,7 +163,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.sp = (unsigned long) childregs;
p->thread.usersp = me->thread.usersp;
set_tsk_thread_flag(p, TIF_FORK);
- p->thread.fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
savesegment(gs, p->thread.gsindex);
@@ -193,8 +192,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
childregs->sp = sp;
err = -ENOMEM;
- memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr,
IO_BITMAP_BYTES, GFP_KERNEL);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 2851d63c1202..ed37a768d0fc 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -675,6 +675,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
* handler too.
*/
regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
+ /*
+ * Ensure the signal handler starts with the new fpu state.
+ */
+ if (used_math())
+ drop_init_fpu(current);
}
signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
}
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 940b142cc11f..4c540c4719d8 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -271,8 +271,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
return -1;
- drop_init_fpu(tsk); /* trigger finit */
-
return 0;
}
@@ -402,8 +400,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
set_used_math();
}
- if (use_eager_fpu())
+ if (use_eager_fpu()) {
+ preempt_disable();
math_state_restore();
+ preempt_enable();
+ }
return err;
} else {
reply other threads:[~2014-10-13 7:38 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20141013073833.GA14790@gmail.com \
--to=mingo@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.