lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <tip-9ed8e7d86061e7c3fb3855358d51ba4abb19ceb1@git.kernel.org>
Date:	Wed, 25 Mar 2015 02:11:01 -0700
From:	tip-bot for Denys Vlasenko <tipbot@...or.com>
To:	linux-tip-commits@...r.kernel.org
Cc:	wad@...omium.org, bp@...en8.de, luto@...nel.org,
	fweisbec@...il.com, hpa@...or.com, tglx@...utronix.de,
	luto@...capital.net, dvlasenk@...hat.com, rostedt@...dmis.org,
	keescook@...omium.org, ast@...mgrid.com,
	torvalds@...ux-foundation.org, bp@...e.de, oleg@...hat.com,
	mingo@...nel.org, linux-kernel@...r.kernel.org
Subject: [tip:x86/asm] x86/asm/entry/64:
  Use PUSH instructions to build pt_regs on stack

Commit-ID:  9ed8e7d86061e7c3fb3855358d51ba4abb19ceb1
Gitweb:     http://git.kernel.org/tip/9ed8e7d86061e7c3fb3855358d51ba4abb19ceb1
Author:     Denys Vlasenko <dvlasenk@...hat.com>
AuthorDate: Thu, 19 Mar 2015 18:17:47 +0100
Committer:  Ingo Molnar <mingo@...nel.org>
CommitDate: Tue, 24 Mar 2015 19:42:38 +0100

x86/asm/entry/64: Use PUSH instructions to build pt_regs on stack

With this change, on SYSCALL64 code path we are now populating
pt_regs->cs, pt_regs->ss and pt_regs->rcx unconditionally and
therefore don't need to do that in FIXUP_TOP_OF_STACK.

We lose a number of large instructions there:

    text    data     bss     dec     hex filename
   13298       0       0   13298    33f2 entry_64_before.o
   12978       0       0   12978    32b2 entry_64.o

What's more important, we convert two "MOVQ $imm,off(%rsp)" to
"PUSH $imm" (the ones which fill pt_regs->cs,ss).

Before this patch, placing them on fast path was slowing it down
by two cycles: this form of MOV is very large, 12 bytes, and
this probably reduces decode bandwidth to one instruction per cycle
when CPU sees them.

Therefore they were living in FIXUP_TOP_OF_STACK instead (away
from fast path).

"PUSH $imm" is a small 2-byte instruction. Moving it to fast path does
not slow it down in my measurements.

Signed-off-by: Denys Vlasenko <dvlasenk@...hat.com>
Acked-by: Borislav Petkov <bp@...e.de>
Acked-by: Andy Lutomirski <luto@...nel.org>
Cc: Alexei Starovoitov <ast@...mgrid.com>
Cc: Andy Lutomirski <luto@...capital.net>
Cc: Borislav Petkov <bp@...en8.de>
Cc: Frederic Weisbecker <fweisbec@...il.com>
Cc: H. Peter Anvin <hpa@...or.com>
Cc: Kees Cook <keescook@...omium.org>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Oleg Nesterov <oleg@...hat.com>
Cc: Steven Rostedt <rostedt@...dmis.org>
Cc: Will Drewry <wad@...omium.org>
Link: http://lkml.kernel.org/r/1426785469-15125-3-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@...nel.org>
---
 arch/x86/kernel/entry_64.S | 54 +++++++++++++++++++++++++++-------------------
 1 file changed, 32 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index eae69bb..3ea4f6d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -126,11 +126,8 @@ ENDPROC(native_usergs_sysret64)
  * manipulation.
  */
 	.macro FIXUP_TOP_OF_STACK tmp offset=0
-	movq $__USER_DS,SS+\offset(%rsp)
-	movq $__USER_CS,CS+\offset(%rsp)
-	movq RIP+\offset(%rsp),\tmp  /* get rip */
-	movq \tmp,RCX+\offset(%rsp)  /* copy it to rcx as sysret would do */
-	movq EFLAGS+\offset(%rsp),\tmp /* ditto for rflags->r11 */
+	/* copy flags to r11 as sysret would do */
+	movq EFLAGS+\offset(%rsp),\tmp
 	movq \tmp,R11+\offset(%rsp)
 	.endm
 
@@ -214,7 +211,6 @@ ENDPROC(native_usergs_sysret64)
  * r9   arg5
  * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
  *
- * Interrupts are off on entry.
  * Only called from user space.
  *
  * When user can change pt_regs->foo always force IRET. That is because
@@ -228,6 +224,12 @@ ENTRY(system_call)
 	CFI_DEF_CFA	rsp,0
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
+
+	/*
+	 * Interrupts are off on entry.
+	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+	 * it is too small to ever cause noticeable irq latency.
+	 */
 	SWAPGS_UNSAFE_STACK
 	/*
 	 * A hypervisor implementation might want to use a label
@@ -236,27 +238,35 @@ ENTRY(system_call)
 	 */
 GLOBAL(system_call_after_swapgs)
 
-	/*
-	 * We use 'rsp_scratch' as a scratch register, hence this block must execute
-	 * atomically in the face of possible interrupt-driven task preemption,
-	 * so we can enable interrupts only after we're done with using rsp_scratch:
-	 */
 	movq	%rsp,PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(kernel_stack),%rsp
-	ALLOC_PT_GPREGS_ON_STACK 6*8 /* 6*8: space for orig_ax and iret frame */
-	movq	%rcx,RIP(%rsp)
-	movq	PER_CPU_VAR(rsp_scratch),%rcx
-	movq	%r11,EFLAGS(%rsp)
-	movq	%rcx,RSP(%rsp)
+
+	/* Construct struct pt_regs on stack */
+	pushq_cfi $__USER_DS			/* pt_regs->ss */
+	pushq_cfi PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
 	/*
-	 * No need to follow this irqs off/on section - it's straight
-	 * and short:
+	 * Re-enable interrupts.
+	 * We use 'rsp_scratch' as a scratch space, hence irq-off block above
+	 * must execute atomically in the face of possible interrupt-driven
+	 * task preemption. We must enable interrupts only after we're done
+	 * with using rsp_scratch:
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	movq_cfi rax,ORIG_RAX
-	SAVE_C_REGS_EXCEPT_RAX_RCX_R11
-	movq	$-ENOSYS,RAX(%rsp)
-	CFI_REL_OFFSET rip,RIP
+	pushq_cfi	%r11			/* pt_regs->flags */
+	pushq_cfi	$__USER_CS		/* pt_regs->cs */
+	pushq_cfi	%rcx			/* pt_regs->ip */
+	CFI_REL_OFFSET rip,0
+	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
+	pushq_cfi_reg	rdi			/* pt_regs->di */
+	pushq_cfi_reg	rsi			/* pt_regs->si */
+	pushq_cfi_reg	rdx			/* pt_regs->dx */
+	pushq_cfi_reg	rcx			/* pt_regs->cx */
+	pushq_cfi	$-ENOSYS		/* pt_regs->ax */
+	pushq_cfi_reg	r8			/* pt_regs->r8 */
+	pushq_cfi_reg	r9			/* pt_regs->r9 */
+	pushq_cfi_reg	r10			/* pt_regs->r10 */
+	sub	$(7*8),%rsp /* pt_regs->r11,bp,bx,r12-15 not saved */
+
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,SIZEOF_PTREGS)
 	jnz tracesys
 system_call_fastpath:
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ