public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Blaisorblade <blaisorblade@yahoo.it>
To: user-mode-linux-devel@lists.sourceforge.net
Cc: Jeff Dike <jdike@addtoit.com>,
	LKML <linux-kernel@vger.kernel.org>,
	"Kai Tan" <mineown@hotmail.com>
Subject: Re: [uml-devel] Uml left showstopper bugs for 2.6.14
Date: Sun, 9 Oct 2005 21:42:32 +0200	[thread overview]
Message-ID: <200510092142.33332.blaisorblade@yahoo.it> (raw)
In-Reply-To: <200510092118.21032.blaisorblade@yahoo.it>

[-- Attachment #1: Type: text/plain, Size: 1428 bytes --]

Kai - go to the end, there are patches for your SKAS0 problem.

On Sunday 09 October 2005 21:18, Blaisorblade wrote:
> Here's a short and updated list of showstoppers for 2.6.14 release, from
> the UML point of view.

> 2) Someone broke endianness of COW driver macros in a header cleanup. I
> have fixes.
Just sent them.
> 3) SKAS0 is broken on amd64 hosts, when frame pointers are disabled. Jeff
> has the fix, waiting end of testing.

> 4) SKAS0 is broken with GCC 3.2.3, and potentially other GCC releases -
> look at arch/um/include/sysdep-i386/stub.h: stub_syscall*() to see how. I
> have two fixes, choosing the safer one (it's all just simply reusing code
> from <asm/unistd.h>).
Jeff, I've attached patches for this. Also found another problematic piece of 
code, in stub-segv (same bad idea).

The patch for that changes a bit more things that strictly needed - complain 
if that's a problem for merging in 2.6.14.

Kai Tan, the order of the patches is:

uml-fix-misassembling-skas0-stub
uml-fix-misassembling-skas0-stub-segv

Note that the second is a bit less tested, so if both together cause problems, 
try with only the first one.

And remember to add "skas0" to the cmd line, to force UML to run in SKAS0 
mode.
-- 
Inform me of my mistakes, so I can keep imitating Homer Simpson's "Doh!".
Paolo Giarrusso, aka Blaisorblade (Skype ID "PaoloGiarrusso", ICQ 215621894)
http://www.user-mode-linux.org/~blaisorblade

[-- Attachment #2: uml-fix-misassembling-skas0-stub --]
[-- Type: text/x-diff, Size: 6434 bytes --]

uml: fix SKAS0 assembly stubs - use proper constraints

From: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>

Jeff Dike noted that the assembly code for syscall stubs is misassembled with
GCC 3.2.3: the values copied in registers weren't preserved between one asm()
and the following one.

So I fixed the thing by rewriting the __asm__ constraints more
like unistd.h ones.

Note: in syscall6 case I had to add one more instruction (i.e. moving arg6 in
eax and shuffling things around) - it's needed for the function to be valid in
general (we can't load the value from the stack, relative to ebp, because we
change it), but could be avoided since we actually use a constant as param 6.

The only fix would be to turn stub_syscall6 to a macro and use a "i" constraint
for arg6 (i.e., specify it's a constant value).

Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Index: linux-2.6.13/arch/um/include/sysdep-i386/stub.h
===================================================================
--- linux-2.6.13.orig/arch/um/include/sysdep-i386/stub.h
+++ linux-2.6.13/arch/um/include/sysdep-i386/stub.h
@@ -16,45 +16,69 @@ extern void stub_clone_handler(void);
 #define STUB_MMAP_NR __NR_mmap2
 #define MMAP_OFFSET(o) ((o) >> PAGE_SHIFT)
 
+static inline long stub_syscall1(long syscall, long arg1)
+{
+	long ret;
+
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1));
+
+	return ret;
+}
+
 static inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
-	__asm__("movl %0, %%ecx; " : : "g" (arg2) : "%ecx");
-	__asm__("movl %0, %%ebx; " : : "g" (arg1) : "%ebx");
-	__asm__("movl %0, %%eax; " : : "g" (syscall) : "%eax");
-	__asm__("int $0x80;" : : : "%eax");
-	__asm__ __volatile__("movl %%eax, %0; " : "=g" (ret) :);
-	return(ret);
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
+			"c" (arg2));
+
+	return ret;
 }
 
 static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
 {
-	__asm__("movl %0, %%edx; " : : "g" (arg3) : "%edx");
-	return(stub_syscall2(syscall, arg1, arg2));
+	long ret;
+
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
+			"c" (arg2), "d" (arg3));
+
+	return ret;
 }
 
 static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 				 long arg4)
 {
-	__asm__("movl %0, %%esi; " : : "g" (arg4) : "%esi");
-	return(stub_syscall3(syscall, arg1, arg2, arg3));
+	long ret;
+
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
+			"c" (arg2), "d" (arg3), "S" (arg4));
+
+	return ret;
+}
+
+static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
+				 long arg4, long arg5)
+{
+	long ret;
+
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
+			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5));
+
+	return ret;
 }
 
 static inline long stub_syscall6(long syscall, long arg1, long arg2, long arg3,
 				 long arg4, long arg5, long arg6)
 {
 	long ret;
-	__asm__("movl %0, %%eax; " : : "g" (syscall) : "%eax");
-	__asm__("movl %0, %%ebx; " : : "g" (arg1) : "%ebx");
-	__asm__("movl %0, %%ecx; " : : "g" (arg2) : "%ecx");
-	__asm__("movl %0, %%edx; " : : "g" (arg3) : "%edx");
-	__asm__("movl %0, %%esi; " : : "g" (arg4) : "%esi");
-	__asm__("movl %0, %%edi; " : : "g" (arg5) : "%edi");
-	__asm__ __volatile__("pushl %%ebp ; movl %1, %%ebp; "
-		"int $0x80; popl %%ebp ; "
-		"movl %%eax, %0; " : "=g" (ret) : "g" (arg6) : "%eax");
-	return(ret);
+
+	__asm__ volatile ("push %%ebp ; movl %%eax,%%ebp ; movl %1,%%eax ; "
+			"int $0x80 ; pop %%ebp"
+			: "=a" (ret)
+			: "g" (syscall), "b" (arg1), "c" (arg2), "d" (arg3),
+			  "S" (arg4), "D" (arg5), "0" (arg6));
+
+	return ret;
 }
 
 static inline void trap_myself(void)
Index: linux-2.6.13/arch/um/include/sysdep-x86_64/stub.h
===================================================================
--- linux-2.6.13.orig/arch/um/include/sysdep-x86_64/stub.h
+++ linux-2.6.13/arch/um/include/sysdep-x86_64/stub.h
@@ -17,37 +17,72 @@ extern void stub_clone_handler(void);
 #define STUB_MMAP_NR __NR_mmap
 #define MMAP_OFFSET(o) (o)
 
+#define __syscall_clobber "r11","rcx","memory"
+#define __syscall "syscall"
+
 static inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
-	__asm__("movq %0, %%rsi; " : : "g" (arg2) : "%rsi");
-	__asm__("movq %0, %%rdi; " : : "g" (arg1) : "%rdi");
-	__asm__("movq %0, %%rax; " : : "g" (syscall) : "%rax");
-	__asm__("syscall;" : : : "%rax", "%r11", "%rcx");
-	__asm__ __volatile__("movq %%rax, %0; " : "=g" (ret) :);
-	return(ret);
+	__asm__ volatile (__syscall
+		: "=a" (ret)
+		: "0" (syscall), "D" (arg1), "S" (arg2) : __syscall_clobber );
+
+	return ret;
 }
 
 static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
 {
-	__asm__("movq %0, %%rdx; " : : "g" (arg3) : "%rdx");
-	return(stub_syscall2(syscall, arg1, arg2));
+	long ret;
+
+	__asm__ volatile (__syscall
+		: "=a" (ret)
+		: "0" (syscall), "D" (arg1), "S" (arg2), "d" (arg3)
+		: __syscall_clobber );
+
+	return ret;
 }
 
 static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 				 long arg4)
 {
-	__asm__("movq %0, %%r10; " : : "g" (arg4) : "%r10");
-	return(stub_syscall3(syscall, arg1, arg2, arg3));
+	long ret;
+
+	__asm__ volatile ("movq %5,%%r10 ; " __syscall
+		: "=a" (ret)
+		: "0" (syscall), "D" (arg1), "S" (arg2), "d" (arg3),
+		  "g" (arg4)
+		: __syscall_clobber, "r10" );
+
+	return ret;
+}
+
+static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
+				 long arg4, long arg5)
+{
+	long ret;
+
+	__asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; " __syscall
+		: "=a" (ret)
+		: "0" (syscall), "D" (arg1), "S" (arg2), "d" (arg3),
+		  "g" (arg4), "g" (arg5)
+		: __syscall_clobber, "r10", "r8" );
+
+	return ret;
 }
 
 static inline long stub_syscall6(long syscall, long arg1, long arg2, long arg3,
 				 long arg4, long arg5, long arg6)
 {
-	__asm__("movq %0, %%r9; " : : "g" (arg6) : "%r9");
-	__asm__("movq %0, %%r8; " : : "g" (arg5) : "%r8");
-	return(stub_syscall4(syscall, arg1, arg2, arg3, arg4));
+	long ret;
+
+	__asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; "
+		"movq %7, %%r9; " __syscall : "=a" (ret)
+		: "0" (syscall), "D" (arg1), "S" (arg2), "d" (arg3),
+		  "g" (arg4), "g" (arg5), "g" (arg6)
+		: __syscall_clobber, "r10", "r8", "r9" );
+
+	return ret;
 }
 
 static inline void trap_myself(void)

[-- Attachment #3: uml-fix-misassembling-skas0-stub-segv --]
[-- Type: text/x-diff, Size: 3093 bytes --]

uml: fix assembly stub for segv

From: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>

Even here, we reuse values from one asm statement to the next without telling
this to GCC - so fix this.

While at it, a bit of improvements to the generated asm code, with better use of
constraints. Still TODO: convert all this to the syscall_stub macros we already
have.

Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Index: linux-2.6.13/arch/um/sys-i386/stub_segv.c
===================================================================
--- linux-2.6.13.orig/arch/um/sys-i386/stub_segv.c
+++ linux-2.6.13/arch/um/sys-i386/stub_segv.c
@@ -14,17 +14,19 @@ void __attribute__ ((__section__ (".__sy
 stub_segv_handler(int sig)
 {
 	struct sigcontext *sc = (struct sigcontext *) (&sig + 1);
+	long pid;
 
 	GET_FAULTINFO_FROM_SC(*((struct faultinfo *) UML_CONFIG_STUB_DATA),
 			      sc);
 
-	__asm__("movl %0, %%eax ; int $0x80": : "g" (__NR_getpid));
-	__asm__("movl %%eax, %%ebx ; movl %0, %%eax ; movl %1, %%ecx ;"
-		"int $0x80": : "g" (__NR_kill), "g" (SIGUSR1));
+	__asm__("movl %1, %%eax ; int $0x80": "=&a" (pid): "i" (__NR_getpid));
+	__asm__("movl %0, %%eax ; movl %1, %%ecx ;"
+		"int $0x80": : "i" (__NR_kill), "i" (SIGUSR1), "b" (pid)
+		: "eax", "ecx");
 	/* Load pointer to sigcontext into esp, since we need to leave
 	 * the stack in its original form when we do the sigreturn here, by
 	 * hand.
 	 */
 	__asm__("mov %0,%%esp ; movl %1, %%eax ; "
-		"int $0x80" : : "a" (sc), "g" (__NR_sigreturn));
+		"int $0x80" : : "r" (sc), "i" (__NR_sigreturn));
 }
Index: linux-2.6.13/arch/um/sys-x86_64/stub_segv.c
===================================================================
--- linux-2.6.13.orig/arch/um/sys-x86_64/stub_segv.c
+++ linux-2.6.13/arch/um/sys-x86_64/stub_segv.c
@@ -30,15 +30,17 @@ void __attribute__ ((__section__ (".__sy
 stub_segv_handler(int sig)
 {
 	struct ucontext *uc;
+	long pid;
 
 	__asm__("movq %%rdx, %0" : "=g" (uc) : );
         GET_FAULTINFO_FROM_SC(*((struct faultinfo *) UML_CONFIG_STUB_DATA),
                               &uc->uc_mcontext);
 
-	__asm__("movq %0, %%rax ; syscall": : "g" (__NR_getpid) : "%rax");
-	__asm__("movq %%rax, %%rdi ; movq %0, %%rax ; movq %1, %%rsi ;"
-		"syscall": : "g" (__NR_kill), "g" (SIGUSR1) :
-		"%rdi", "%rax", "%rsi");
+	__asm__("movq %0, %%rax ; syscall": "=&a" (pid) : "g" (__NR_getpid)
+			: "rax", __syscall_clobber);
+	__asm__("movq %0, %%rax ; movq %1, %%rsi ;"
+		"syscall": : "i" (__NR_kill), "i" (SIGUSR1), "D" (pid) :
+		"rdi", "rax", "rsi", __syscall_clobber);
 	/* sys_sigreturn expects that the stack pointer will be 8 bytes into
 	 * the signal frame.  So, we use the ucontext pointer, which we know
 	 * already, to get the signal frame pointer, and add 8 to that.
@@ -46,5 +48,5 @@ stub_segv_handler(int sig)
 	__asm__("movq %0, %%rsp": :
 		"g" ((unsigned long) container_of(uc, struct rt_sigframe,
 						  uc) + 8));
-	__asm__("movq %0, %%rax ; syscall" : : "g" (__NR_rt_sigreturn) : "%rax");
+	__asm__("movq %0, %%rax ; syscall" : : "g" (__NR_rt_sigreturn) : "rax");
 }

  parent reply	other threads:[~2005-10-09 19:42 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-10-09 19:18 Uml left showstopper bugs for 2.6.14 Blaisorblade
2005-10-09 19:37 ` [PATCH 1/6] Uml: hide commands when not being verbose Paolo 'Blaisorblade' Giarrusso
2005-10-09 19:37 ` [PATCH 2/6] uml: add mode=skas0 as a synonym of skas0 Paolo 'Blaisorblade' Giarrusso
2005-10-09 19:37 ` [PATCH 3/6] uml: allow building .s/.i/.lst files from userspace files Paolo 'Blaisorblade' Giarrusso
2005-10-09 19:37 ` [PATCH 4/6] uml: restore include breakage, breaking binary format of COW driver Paolo 'Blaisorblade' Giarrusso
2005-10-09 19:37 ` [PATCH 5/6] uml: cleanup byte order macros for " Paolo 'Blaisorblade' Giarrusso
2005-10-09 19:37 ` [PATCH 6/6] uml: cleanup whitespace " Paolo 'Blaisorblade' Giarrusso
2005-10-09 19:42 ` Blaisorblade [this message]
2005-11-02 21:44   ` [uml-devel] Uml left showstopper bugs for 2.6.14 Kai Tan
2005-11-02 22:47     ` Blaisorblade
2005-10-09 22:41 ` Jeff Dike

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=200510092142.33332.blaisorblade@yahoo.it \
    --to=blaisorblade@yahoo.it \
    --cc=jdike@addtoit.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mineown@hotmail.com \
    --cc=user-mode-linux-devel@lists.sourceforge.net \
    /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