summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAmmar Faizi <ammarfaizi2@gnuweeb.org>2022-04-15 05:41:40 +0700
committerJens Axboe <axboe@kernel.dk>2022-04-18 09:24:08 -0600
commitb7d8dd8bbf5b8550c8a0c1ed70431cd8050709f0 (patch)
treebc0f113387787286aff1ecffd9cf2bb4530591c2
parent48342e4c482349718eeecd34b3026d3d6aa78794 (diff)
downloadliburing-b7d8dd8bbf5b8550c8a0c1ed70431cd8050709f0.tar.gz
liburing-b7d8dd8bbf5b8550c8a0c1ed70431cd8050709f0.tar.bz2
arch/x86/syscall: Add x86 32-bit native syscall support
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/2e335ac54db44f1d8496583d97f9dab0@AcuMS.aculab.com Suggested-by: David Laight <David.Laight@ACULAB.COM> Co-authored-by: Alviro Iskandar Setiawan <alviro.iskandar@gnuweeb.org> Signed-off-by: Alviro Iskandar Setiawan <alviro.iskandar@gnuweeb.org> Signed-off-by: Ammar Faizi <ammarfaizi2@gnuweeb.org> Link: https://lore.kernel.org/r/20220414224001.187778-4-ammar.faizi@intel.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--src/arch/x86/syscall.h150
1 files 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 */