public inbox for [email protected]
 help / color / mirror / Atom feed
From: Ammar Faizi <[email protected]>
To: Jens Axboe <[email protected]>
Cc: Ammar Faizi <[email protected]>,
	io-uring Mailing List <[email protected]>,
	GNU/Weeb Mailing List <[email protected]>,
	Pavel Begunkov <[email protected]>,
	David Laight <[email protected]>,
	Alviro Iskandar Setiawan <[email protected]>
Subject: [PATCH liburing 3/3] arch/x86/syscall: Add x86 32-bit native syscall support
Date: Fri, 15 Apr 2022 05:41:40 +0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

Create __do_syscall{0..6} macros for x86 32-bit. Unlike x86-64, only
use these macros when CONFIG_NOLIBC is enabled for a 32-bit build. The
reason is that the libc syscall wrapper can do better in 32-bit.

libc syscall wrapper can dispatch the best syscall instruction that the
environment is supported, there are at least two variants of syscall
instruction for x86 32-bit, they are: `int $0x80` and `sysenter`. The
`int $0x80` instruction is always available, but `sysenter` is not, it
relies on VDSO. liburing always uses `int $0x80` for syscall if it's
compiled with CONFIG_NOLIBC, otherwise, it uses whatever the libc
provides.

Extra notes for __do_syscall6() macro:
On i386, the 6th argument of syscall goes in %ebp. However, both Clang
and GCC cannot use %ebp in the clobber list and the "r" constraint
without using -fomit-frame-pointer. To make it always available for any
kind of compilation, the below workaround is implemented:

  1) Push the 6-th argument.
  2) Push %ebp.
  3) Load the 6-th argument from 4(%esp) to %ebp.
  4) Do the syscall (int $0x80).
  5) Pop %ebp (restore the old value of %ebp).
  6) Add %esp by 4 (undo the stack pointer).

WARNING:
  Don't use register variables for __do_syscall6(), there is a known
  GCC bug that results in an endless loop.

BugLink: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105032

Link: https://lore.kernel.org/lkml/[email protected]
Suggested-by: David Laight <[email protected]>
Co-authored-by: Alviro Iskandar Setiawan <[email protected]>
Signed-off-by: Alviro Iskandar Setiawan <[email protected]>
Signed-off-by: Ammar Faizi <[email protected]>
---
 src/arch/x86/syscall.h | 150 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 148 insertions(+), 2 deletions(-)

diff --git a/src/arch/x86/syscall.h b/src/arch/x86/syscall.h
index 89a68f6..8cd24dd 100644
--- a/src/arch/x86/syscall.h
+++ b/src/arch/x86/syscall.h
@@ -151,10 +151,156 @@
  * TODO: Add x86 (32-bit) nolibc support.
  */
 #ifdef CONFIG_NOLIBC
-	#error "x86 (32-bit) is currently not supported for nolibc builds"
-#endif
+/**
+ * Note for syscall registers usage (x86, 32-bit):
+ *   - %eax is the syscall number.
+ *   - %eax is also the return value.
+ *   - %ebx is the 1st argument.
+ *   - %ecx is the 2nd argument.
+ *   - %edx is the 3rd argument.
+ *   - %esi is the 4th argument.
+ *   - %edi is the 5th argument.
+ *   - %ebp is the 6th argument.
+ */
+
+#define __do_syscall0(NUM) ({			\
+	intptr_t eax;				\
+						\
+	__asm__ volatile(			\
+		"int	$0x80"			\
+		: "=a"(eax)	/* %eax */	\
+		: "a"(NUM)	/* %eax */	\
+		: "memory"			\
+	);					\
+	eax;					\
+})
+
+#define __do_syscall1(NUM, ARG1) ({		\
+	intptr_t eax;				\
+						\
+	__asm__ volatile(			\
+		"int	$0x80"			\
+		: "=a"(eax)	/* %eax */	\
+		: "a"(NUM),	/* %eax */	\
+		  "b"((ARG1))	/* %ebx */	\
+		: "memory"			\
+	);					\
+	eax;					\
+})
+
+#define __do_syscall2(NUM, ARG1, ARG2) ({	\
+	intptr_t eax;				\
+						\
+	__asm__ volatile(			\
+		"int	$0x80"			\
+		: "=a" (eax)	/* %eax */	\
+		: "a"(NUM),	/* %eax */	\
+		  "b"((ARG1)),	/* %ebx */	\
+		  "c"((ARG2))	/* %ecx */	\
+		: "memory"			\
+	);					\
+	eax;					\
+})
+
+#define __do_syscall3(NUM, ARG1, ARG2, ARG3) ({	\
+	intptr_t eax;				\
+						\
+	__asm__ volatile(			\
+		"int	$0x80"			\
+		: "=a" (eax)	/* %eax */	\
+		: "a"(NUM),	/* %eax */	\
+		  "b"((ARG1)),	/* %ebx */	\
+		  "c"((ARG2)),	/* %ecx */	\
+		  "d"((ARG3))	/* %edx */	\
+		: "memory"			\
+	);					\
+	eax;					\
+})
+
+#define __do_syscall4(NUM, ARG1, ARG2, ARG3, ARG4) ({	\
+	intptr_t eax;					\
+							\
+	__asm__ volatile(				\
+		"int	$0x80"				\
+		: "=a" (eax)	/* %eax */		\
+		: "a"(NUM),	/* %eax */		\
+		  "b"((ARG1)),	/* %ebx */		\
+		  "c"((ARG2)),	/* %ecx */		\
+		  "d"((ARG3)),	/* %edx */		\
+		  "S"((ARG4))	/* %esi */		\
+		: "memory"				\
+	);						\
+	eax;						\
+})
+
+#define __do_syscall5(NUM, ARG1, ARG2, ARG3, ARG4, ARG5) ({	\
+	intptr_t eax;						\
+								\
+	__asm__ volatile(					\
+		"int	$0x80"					\
+		: "=a" (eax)	/* %eax */			\
+		: "a"(NUM),	/* %eax */			\
+		  "b"((ARG1)),	/* %ebx */			\
+		  "c"((ARG2)),	/* %ecx */			\
+		  "d"((ARG3)),	/* %edx */			\
+		  "S"((ARG4)),	/* %esi */			\
+		  "D"((ARG5))	/* %edi */			\
+		: "memory"					\
+	);							\
+	eax;							\
+})
+
+
+/*
+ * On i386, the 6th argument of syscall goes in %ebp. However, both Clang
+ * and GCC cannot use %ebp in the clobber list and in the "r" constraint
+ * without using -fomit-frame-pointer. To make it always available for
+ * any kind of compilation, the below workaround is implemented:
+ *
+ *  1) Push the 6-th argument.
+ *  2) Push %ebp.
+ *  3) Load the 6-th argument from 4(%esp) to %ebp.
+ *  4) Do the syscall (int $0x80).
+ *  5) Pop %ebp (restore the old value of %ebp).
+ *  6) Add %esp by 4 (undo the stack pointer).
+ *
+ * WARNING:
+ *   Don't use register variables for __do_syscall6(), there is a known
+ *   GCC bug that results in an endless loop.
+ *
+ * BugLink: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105032
+ *
+ */
+#define __do_syscall6(NUM, ARG1, ARG2, ARG3, ARG4, ARG5, ARG6) ({	\
+	intptr_t eax  = (intptr_t)(NUM);				\
+	intptr_t arg6 = (intptr_t)(ARG6); /* Always in memory */	\
+	__asm__ volatile (						\
+		"pushl	%[_arg6]\n\t"					\
+		"pushl	%%ebp\n\t"					\
+		"movl	4(%%esp),%%ebp\n\t"				\
+		"int	$0x80\n\t"					\
+		"popl	%%ebp\n\t"					\
+		"addl	$4,%%esp"					\
+		: "+a"(eax)		/* %eax */			\
+		: "b"(ARG1),		/* %ebx */			\
+		  "c"(ARG2),		/* %ecx */			\
+		  "d"(ARG3),		/* %edx */			\
+		  "S"(ARG4),		/* %esi */			\
+		  "D"(ARG5),		/* %edi */			\
+		  [_arg6]"m"(arg6)	/* memory */			\
+		: "memory", "cc"					\
+	);								\
+	eax;								\
+})
+
+#include "../syscall-defs.h"
+
+#else /* #ifdef CONFIG_NOLIBC */
+
 #include "../generic/syscall.h"
 
+#endif /* #ifdef CONFIG_NOLIBC */
+
 #endif /* #if defined(__x86_64__) */
 
 #endif /* #ifndef LIBURING_ARCH_X86_SYSCALL_H */
-- 
Ammar Faizi


  parent reply	other threads:[~2022-04-14 22:42 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-14 22:41 [PATCH liburing 0/3] Add x86 32-bit support for the nolibc build Ammar Faizi
2022-04-14 22:41 ` [PATCH liburing 1/3] arch/syscall-defs: Use `__NR_mmap2` instead of `__NR_mmap` for x86 32-bit Ammar Faizi
2022-04-14 22:41 ` [PATCH liburing 2/3] arch/x86/lib: Provide `get_page_size()` function " Ammar Faizi
2022-04-14 22:41 ` Ammar Faizi [this message]
2022-04-18  2:01 ` [PATCH liburing 0/3] Add x86 32-bit support for the nolibc build Jens Axboe
2022-04-18 14:14   ` Ammar Faizi
2022-04-18 15:23     ` Jens Axboe
2022-04-18 15:24 ` Jens Axboe

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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