[PATCH 0/2] x86: entry_64.S: steps towards simpler iret frame handling

[PATCH 0/2] x86: entry_64.S: steps towards simpler iret frame handling

[Denys Vlasenko]

These changes make SYSENTER64 code path save flags and user's
stack pointer in pt_regs->flags and pt_regs->sp, where they belong.

As a result, we can drop stub_iopl() and thread_struct::usersp.

Usage of PER_CPU(old_rsp) is reduced to bare minimum.

FIXUP/RESTORE_TOP_OF_STACK macros are on diet too.

(This is a resend. Previous version was on top of KERNEL_STACK_OFFSET
removal patch. This one is on top of Andy's current git. Patch is run-tested.)

CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Ingo Molnar <mingo@kernel.org>
CC: Borislav Petkov <bp@alien8.de>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: x86@kernel.org
CC: linux-kernel@vger.kernel.org

Denys Vlasenko (2):
  x86: save r11 into pt_regs->flags on SYSCALL64 fastpath
  x86: save user %rsp in pt_regs->sp on SYSCALL64 fastpath

 arch/x86/include/asm/calling.h   | 20 +++++++++-----
 arch/x86/include/asm/compat.h    |  2 +-
 arch/x86/include/asm/processor.h |  6 -----
 arch/x86/include/asm/ptrace.h    |  8 ++----
 arch/x86/kernel/entry_64.S       | 57 ++++++++++++++--------------------------
 arch/x86/kernel/perf_regs.c      |  2 +-
 arch/x86/kernel/process_64.c     |  8 +-----
 arch/x86/syscalls/syscall_64.tbl |  2 +-
 arch/x86/um/sys_call_table_64.c  |  2 +-
 9 files changed, 40 insertions(+), 67 deletions(-)

-- 
1.8.1.4

[PATCH 1/2] x86: save r11 into pt_regs->flags on SYSCALL64 fastpath

[Denys Vlasenko]

Before this patch, r11 was saved in pt_regs->r11.
Which looks natural, but requires messy shuffling to/from iret frame
whenever ptrace or e.g. iopl wants to modify flags - because
that's how this register is used by SYSCALL/SYSRET.

This patch saves r11 in pt_regs->flags,
and uses that value for SYSRET64 insn. Shuffling is eliminated.

stub_iopl is no longer needed: pt_regs->flags needs no fixing up.

Testing shows that syscall fast path is ~54.3 ns before
and after the patch (on 2.7 GHz Sandy Bridge CPU).

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Ingo Molnar <mingo@kernel.org>
CC: Borislav Petkov <bp@alien8.de>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: x86@kernel.org
CC: linux-kernel@vger.kernel.org
---
 arch/x86/include/asm/calling.h   | 20 ++++++++++++++------
 arch/x86/kernel/entry_64.S       | 37 +++++++++++--------------------------
 arch/x86/syscalls/syscall_64.tbl |  2 +-
 arch/x86/um/sys_call_table_64.c  |  2 +-
 4 files changed, 27 insertions(+), 34 deletions(-)

diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index f1a962f..4b5f7bf 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -95,9 +95,11 @@ For 32-bit we have the following conventions - kernel is built with
 	CFI_ADJUST_CFA_OFFSET 15*8+\addskip
 	.endm
 
-	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8plus=1
-	.if \r8plus
+	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
+	.if \r11
 	movq_cfi r11, 6*8+\offset
+	.endif
+	.if \r8910
 	movq_cfi r10, 7*8+\offset
 	movq_cfi r9,  8*8+\offset
 	movq_cfi r8,  9*8+\offset
@@ -113,16 +115,19 @@ For 32-bit we have the following conventions - kernel is built with
 	movq_cfi rdi, 14*8+\offset
 	.endm
 	.macro SAVE_C_REGS offset=0
-	SAVE_C_REGS_HELPER \offset, 1, 1, 1
+	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
 	.endm
 	.macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0
-	SAVE_C_REGS_HELPER \offset, 0, 0, 1
+	SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1
 	.endm
 	.macro SAVE_C_REGS_EXCEPT_R891011
-	SAVE_C_REGS_HELPER 0, 1, 1, 0
+	SAVE_C_REGS_HELPER 0, 1, 1, 0, 0
 	.endm
 	.macro SAVE_C_REGS_EXCEPT_RCX_R891011
-	SAVE_C_REGS_HELPER 0, 1, 0, 0
+	SAVE_C_REGS_HELPER 0, 1, 0, 0, 0
+	.endm
+	.macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11
+	SAVE_C_REGS_HELPER 0, 0, 0, 1, 0
 	.endm
 
 	.macro SAVE_EXTRA_REGS offset=0
@@ -179,6 +184,9 @@ For 32-bit we have the following conventions - kernel is built with
 	.macro RESTORE_C_REGS_EXCEPT_R11
 	RESTORE_C_REGS_HELPER 1,1,0,1,1
 	.endm
+	.macro RESTORE_C_REGS_EXCEPT_RCX_R11
+	RESTORE_C_REGS_HELPER 1,0,0,1,1
+	.endm
 	.macro RESTORE_RSI_RDI
 	RESTORE_C_REGS_HELPER 0,0,0,0,0
 	.endm
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c86f83e..380dde7a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -121,14 +121,12 @@ ENDPROC(native_usergs_sysret64)
 #endif
 
 /*
- * C code is not supposed to know about undefined top of stack. Every time
- * a C function with an pt_regs argument is called from the SYSCALL based
- * fast path FIXUP_TOP_OF_STACK is needed.
+ * C code is not supposed to know that the iret frame is not populated.
+ * Every time a C function with an pt_regs argument is called from
+ * the SYSCALL based fast path FIXUP_TOP_OF_STACK is needed.
  * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
  * manipulation.
  */
-
-	/* %rsp:at FRAMEEND */
 	.macro FIXUP_TOP_OF_STACK tmp offset=0
 	movq PER_CPU_VAR(old_rsp),\tmp
 	movq \tmp,RSP+\offset(%rsp)
@@ -136,15 +134,13 @@ ENDPROC(native_usergs_sysret64)
 	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 R11+\offset(%rsp),\tmp  /* get eflags */
-	movq \tmp,EFLAGS+\offset(%rsp)
+	movq EFLAGS+\offset(%rsp),\tmp /* ditto for rflags->r11 */
+	movq \tmp,R11+\offset(%rsp)
 	.endm
 
 	.macro RESTORE_TOP_OF_STACK tmp offset=0
 	movq RSP+\offset(%rsp),\tmp
 	movq \tmp,PER_CPU_VAR(old_rsp)
-	movq EFLAGS+\offset(%rsp),\tmp
-	movq \tmp,R11+\offset(%rsp)
 	.endm
 
 /*
@@ -257,9 +253,10 @@ GLOBAL(system_call_after_swapgs)
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	ALLOC_PT_GPREGS_ON_STACK 8		/* +8: space for orig_ax */
-	SAVE_C_REGS_EXCEPT_RAX_RCX
+	SAVE_C_REGS_EXCEPT_RAX_RCX_R11
 	movq	$-ENOSYS,RAX(%rsp)
 	movq_cfi rax,ORIG_RAX
+	movq	%r11,EFLAGS(%rsp)
 	movq	%rcx,RIP(%rsp)
 	CFI_REL_OFFSET rip,RIP
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP)
@@ -277,7 +274,7 @@ system_call_fastpath:
 	movq %rax,RAX(%rsp)
 /*
  * Syscall return path ending with SYSRET (fast path)
- * Has incomplete stack frame and undefined top of stack.
+ * Has incompletely filled pt_regs, iret frame is also incomplete.
  */
 ret_from_sys_call:
 	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP)
@@ -291,9 +288,10 @@ ret_from_sys_call:
 	 * sysretq will re-enable interrupts:
 	 */
 	TRACE_IRQS_ON
-	RESTORE_C_REGS_EXCEPT_RCX
-	movq RIP(%rsp),%rcx
+	RESTORE_C_REGS_EXCEPT_RCX_R11
+	movq	RIP(%rsp),%rcx
 	CFI_REGISTER	rip,rcx
+	movq	EFLAGS(%rsp),%r11
 	/*CFI_REGISTER	rflags,r11*/
 	movq	PER_CPU_VAR(old_rsp), %rsp
 	/*
@@ -423,22 +421,9 @@ ENTRY(stub_\func)
 END(stub_\func)
 	.endm
 
-	.macro FIXED_FRAME label,func
-ENTRY(\label)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8		/* offset 8: return address */
-	FIXUP_TOP_OF_STACK %r11, 8
-	call \func
-	RESTORE_TOP_OF_STACK %r11, 8
-	ret
-	CFI_ENDPROC
-END(\label)
-	.endm
-
 	FORK_LIKE  clone
 	FORK_LIKE  fork
 	FORK_LIKE  vfork
-	FIXED_FRAME stub_iopl, sys_iopl
 
 ENTRY(stub_execve)
 	CFI_STARTPROC
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 8d656fb..9ef32d5 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -178,7 +178,7 @@
 169	common	reboot			sys_reboot
 170	common	sethostname		sys_sethostname
 171	common	setdomainname		sys_setdomainname
-172	common	iopl			stub_iopl
+172	common	iopl			sys_iopl
 173	common	ioperm			sys_ioperm
 174	64	create_module
 175	common	init_module		sys_init_module
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index 5cdfa9d..a75d8700 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -16,7 +16,7 @@
  */
 
 /* Not going to be implemented by UML, since we have no hardware. */
-#define stub_iopl sys_ni_syscall
+#define sys_iopl sys_ni_syscall
 #define sys_ioperm sys_ni_syscall
 
 /*
-- 
1.8.1.4

[PATCH 2/2] x86: save user %rsp in pt_regs->sp on SYSCALL64 fastpath

[Denys Vlasenko]

PER_CPU(old_rsp) usage is simplified - now it is used only
as temp storage, and userspace stack pointer is immediately stored
in pt_regs->sp on syscall entry, instead of being used later,
on syscall exit.

All references of PER_CPU(old_rsp) in C code are gone -
pt_regs->sp is used instead.

This also allows to get rid of thread_struct::usersp,
which was needed only to set PER_CPU(old_rsp) for
correct return from fork/clone.

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Linus Torvalds <torvalds@linux-foundation.org>
CC: Steven Rostedt <rostedt@goodmis.org>
CC: Ingo Molnar <mingo@kernel.org>
CC: Borislav Petkov <bp@alien8.de>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: x86@kernel.org
CC: linux-kernel@vger.kernel.org
---
 arch/x86/include/asm/compat.h    |  2 +-
 arch/x86/include/asm/processor.h |  6 ------
 arch/x86/include/asm/ptrace.h    |  8 ++------
 arch/x86/kernel/entry_64.S       | 22 +++++++++-------------
 arch/x86/kernel/perf_regs.c      |  2 +-
 arch/x86/kernel/process_64.c     |  8 +-------
 6 files changed, 14 insertions(+), 34 deletions(-)

diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 59c6c40..acdee09 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -301,7 +301,7 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 		sp = task_pt_regs(current)->sp;
 	} else {
 		/* -128 for the x32 ABI redzone */
-		sp = this_cpu_read(old_rsp) - 128;
+		sp = task_pt_regs(current)->sp - 128;
 	}
 
 	return (void __user *)round_down(sp - len, 16);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f5e3ec6..626234c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -474,7 +474,6 @@ struct thread_struct {
 #ifdef CONFIG_X86_32
 	unsigned long		sysenter_cs;
 #else
-	unsigned long		usersp;	/* Copy from PDA */
 	unsigned short		es;
 	unsigned short		ds;
 	unsigned short		fsindex;
@@ -885,11 +884,6 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
 
-/*
- * User space RSP while inside the SYSCALL fast path
- */
-DECLARE_PER_CPU(unsigned long, old_rsp);
-
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 4077d96..74bb2e0 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -145,12 +145,8 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 #endif
 }
 
-#define current_user_stack_pointer()	this_cpu_read(old_rsp)
-/* ia32 vs. x32 difference */
-#define compat_user_stack_pointer()	\
-	(test_thread_flag(TIF_IA32) 	\
-	 ? current_pt_regs()->sp 	\
-	 : this_cpu_read(old_rsp))
+#define current_user_stack_pointer()	current_pt_regs()->sp
+#define compat_user_stack_pointer()	current_pt_regs()->sp
 #endif
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 380dde7a..e8fd9b3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -128,8 +128,6 @@ ENDPROC(native_usergs_sysret64)
  * manipulation.
  */
 	.macro FIXUP_TOP_OF_STACK tmp offset=0
-	movq PER_CPU_VAR(old_rsp),\tmp
-	movq \tmp,RSP+\offset(%rsp)
 	movq $__USER_DS,SS+\offset(%rsp)
 	movq $__USER_CS,CS+\offset(%rsp)
 	movq RIP+\offset(%rsp),\tmp  /* get rip */
@@ -139,8 +137,7 @@ ENDPROC(native_usergs_sysret64)
 	.endm
 
 	.macro RESTORE_TOP_OF_STACK tmp offset=0
-	movq RSP+\offset(%rsp),\tmp
-	movq \tmp,PER_CPU_VAR(old_rsp)
+	/* nothing to do */
 	.endm
 
 /*
@@ -222,9 +219,6 @@ ENDPROC(native_usergs_sysret64)
  * Interrupts are off on entry.
  * Only called from user space.
  *
- * XXX	if we had a free scratch register we could save the RSP into the stack frame
- *      and report it properly in ps. Unfortunately we haven't.
- *
  * When user can change the frames always force IRET. That is because
  * it deals with uncanonical addresses better. SYSRET has trouble
  * with them due to bugs in both AMD and Intel CPUs.
@@ -253,11 +247,13 @@ GLOBAL(system_call_after_swapgs)
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	ALLOC_PT_GPREGS_ON_STACK 8		/* +8: space for orig_ax */
+	movq	%rcx,RIP(%rsp)
+	movq	PER_CPU_VAR(old_rsp),%rcx
+	movq	%r11,EFLAGS(%rsp)
+	movq	%rcx,RSP(%rsp)
+	movq_cfi rax,ORIG_RAX
 	SAVE_C_REGS_EXCEPT_RAX_RCX_R11
 	movq	$-ENOSYS,RAX(%rsp)
-	movq_cfi rax,ORIG_RAX
-	movq	%r11,EFLAGS(%rsp)
-	movq	%rcx,RIP(%rsp)
 	CFI_REL_OFFSET rip,RIP
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP)
 	jnz tracesys
@@ -293,7 +289,7 @@ ret_from_sys_call:
 	CFI_REGISTER	rip,rcx
 	movq	EFLAGS(%rsp),%r11
 	/*CFI_REGISTER	rflags,r11*/
-	movq	PER_CPU_VAR(old_rsp), %rsp
+	movq	RSP(%rsp),%rsp
 	/*
 	 * 64bit SYSRET restores rip from rcx,
 	 * rflags from r11 (but RF and VM bits are forced to 0),
@@ -307,7 +303,7 @@ int_ret_from_sys_call_fixup:
 	FIXUP_TOP_OF_STACK %r11
 	jmp int_ret_from_sys_call
 
-	/* Do syscall tracing */
+	/* Do syscall entry tracing */
 tracesys:
 	movq %rsp, %rdi
 	movq $AUDIT_ARCH_X86_64, %rsi
@@ -347,7 +343,7 @@ tracesys_phase2:
 
 /*
  * Syscall return path ending with IRET.
- * Has correct top of stack, but partial stack frame.
+ * Has correct iret frame.
  */
 GLOBAL(int_ret_from_sys_call)
 	DISABLE_INTERRUPTS(CLBR_NONE)
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 781861c..02a8720 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -177,7 +177,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 		 * than just blindly copying user_regs.
 		 */
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
-		regs_user_copy->sp = this_cpu_read(old_rsp);
+		regs_user_copy->sp = user_regs->sp;
 		regs_user_copy->cs = __USER_CS;
 		regs_user_copy->ss = __USER_DS;
 		regs_user_copy->cx = -1;  /* usually contains garbage */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 2cd562f..6c29068 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -161,7 +161,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
 	childregs = task_pt_regs(p);
 	p->thread.sp = (unsigned long) childregs;
-	p->thread.usersp = me->thread.usersp;
 	set_tsk_thread_flag(p, TIF_FORK);
 	p->thread.io_bitmap_ptr = NULL;
 
@@ -235,10 +234,8 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	loadsegment(es, _ds);
 	loadsegment(ds, _ds);
 	load_gs_index(0);
-	current->thread.usersp	= new_sp;
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
-	this_cpu_write(old_rsp, new_sp);
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
@@ -401,8 +398,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	prev->usersp = this_cpu_read(old_rsp);
-	this_cpu_write(old_rsp, next->usersp);
 	this_cpu_write(current_task, next_p);
 
 	/*
@@ -602,6 +597,5 @@ long sys_arch_prctl(int code, unsigned long addr)
 
 unsigned long KSTK_ESP(struct task_struct *task)
 {
-	return (test_tsk_thread_flag(task, TIF_IA32)) ?
-			(task_pt_regs(task)->sp) : ((task)->thread.usersp);
+	return task_pt_regs(task)->sp;
 }
-- 
1.8.1.4

Re: [PATCH 1/2] x86: save r11 into pt_regs->flags on SYSCALL64 fastpath

[Ingo Molnar]

* Denys Vlasenko <dvlasenk@redhat.com> wrote:

> Before this patch, r11 was saved in pt_regs->r11.
> Which looks natural, but requires messy shuffling to/from iret frame
> whenever ptrace or e.g. iopl wants to modify flags - because
> that's how this register is used by SYSCALL/SYSRET.
> 
> This patch saves r11 in pt_regs->flags,
> and uses that value for SYSRET64 insn. Shuffling is eliminated.
> 
> stub_iopl is no longer needed: pt_regs->flags needs no fixing up.

Could you please split this into two patches: R11 saving, and 
stub_iopl removal?

For x86/asm changes we want as small changes as physically possible.

Thanks,

	Ingo

Re: [PATCH 2/2] x86: save user %rsp in pt_regs->sp on SYSCALL64 fastpath

[Ingo Molnar]

* Denys Vlasenko <dvlasenk@redhat.com> wrote:

> PER_CPU(old_rsp) usage is simplified - now it is used only
> as temp storage, and userspace stack pointer is immediately stored
> in pt_regs->sp on syscall entry, instead of being used later,
> on syscall exit.
> 
> All references of PER_CPU(old_rsp) in C code are gone -
> pt_regs->sp is used instead.
> 
> This also allows to get rid of thread_struct::usersp,
> which was needed only to set PER_CPU(old_rsp) for
> correct return from fork/clone.

Would it be possible to split this one into two parts as well:

  - Essential changes into the first one (old_rsp update 
    simplification, usersp usage conversion)

  - Removal of usersp, old_rsp extern declaration removal, comment 
    changes, in the second patch?

Thanks,

	Ingo