| 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
| ||
|
Message-ID: <99a54b96cee85275692ca01fe4a0ef0d83996f0f.1758171893.git.thehajime@gmail.com>
Date: Thu, 18 Sep 2025 14:15:57 +0900
From: Hajime Tazaki <thehajime@...il.com>
To: linux-um@...ts.infradead.org
Cc: thehajime@...il.com,
ricarkol@...gle.com,
Liam.Howlett@...cle.com,
linux-kernel@...r.kernel.org
Subject: [PATCH v11 04/14] x86/um: nommu: syscall handling
This commit introduces an entry point of syscall interface for !MMU
mode. It uses an entry function, __kernel_vsyscall, a kernel-wide global
symbol accessible from any locations.
Although it isn't in the scope of this commit, it can be also exposed
via vdso image which is directly accessible from userspace. A standard
library (i.e., libc) can utilize this entry point to implement syscall
wrapper; we can also use this by hooking syscall for unmodified userspace
applications/libraries, which will be implemented in the subsequent
commit.
This only supports 64-bit mode of x86 architecture.
Signed-off-by: Hajime Tazaki <thehajime@...il.com>
Signed-off-by: Ricardo Koller <ricarkol@...gle.com>
---
arch/x86/um/Makefile | 4 ++
arch/x86/um/asm/syscall.h | 6 ++
arch/x86/um/nommu/Makefile | 8 +++
arch/x86/um/nommu/do_syscall_64.c | 32 +++++++++
arch/x86/um/nommu/entry_64.S | 112 ++++++++++++++++++++++++++++++
arch/x86/um/nommu/syscalls.h | 16 +++++
6 files changed, 178 insertions(+)
create mode 100644 arch/x86/um/nommu/Makefile
create mode 100644 arch/x86/um/nommu/do_syscall_64.c
create mode 100644 arch/x86/um/nommu/entry_64.S
create mode 100644 arch/x86/um/nommu/syscalls.h
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index b42c31cd2390..227af2a987e2 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -32,6 +32,10 @@ obj-y += syscalls_64.o vdso/
subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o \
../lib/memmove_64.o ../lib/memset_64.o
+ifneq ($(CONFIG_MMU),y)
+obj-y += nommu/
+endif
+
endif
subarch-$(CONFIG_MODULES) += ../kernel/module.o
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
index d6208d0fad51..bb4f6f011667 100644
--- a/arch/x86/um/asm/syscall.h
+++ b/arch/x86/um/asm/syscall.h
@@ -20,4 +20,10 @@ static inline int syscall_get_arch(struct task_struct *task)
#endif
}
+#ifndef CONFIG_MMU
+extern void do_syscall_64(struct pt_regs *regs);
+extern long __kernel_vsyscall(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
+ int64_t a4, int64_t a5, int64_t a6);
+#endif
+
#endif /* __UM_ASM_SYSCALL_H */
diff --git a/arch/x86/um/nommu/Makefile b/arch/x86/um/nommu/Makefile
new file mode 100644
index 000000000000..d72c63afffa5
--- /dev/null
+++ b/arch/x86/um/nommu/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+ifeq ($(CONFIG_X86_32),y)
+ BITS := 32
+else
+ BITS := 64
+endif
+
+obj-y = do_syscall_$(BITS).o entry_$(BITS).o
diff --git a/arch/x86/um/nommu/do_syscall_64.c b/arch/x86/um/nommu/do_syscall_64.c
new file mode 100644
index 000000000000..292d7c578622
--- /dev/null
+++ b/arch/x86/um/nommu/do_syscall_64.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+#include <kern_util.h>
+#include <asm/syscall.h>
+#include <os.h>
+
+__visible void do_syscall_64(struct pt_regs *regs)
+{
+ int syscall;
+
+ syscall = PT_SYSCALL_NR(regs->regs.gp);
+ UPT_SYSCALL_NR(®s->regs) = syscall;
+
+ if (likely(syscall < NR_syscalls)) {
+ unsigned long ret;
+
+ ret = (*sys_call_table[syscall])(UPT_SYSCALL_ARG1(®s->regs),
+ UPT_SYSCALL_ARG2(®s->regs),
+ UPT_SYSCALL_ARG3(®s->regs),
+ UPT_SYSCALL_ARG4(®s->regs),
+ UPT_SYSCALL_ARG5(®s->regs),
+ UPT_SYSCALL_ARG6(®s->regs));
+ PT_REGS_SET_SYSCALL_RETURN(regs, ret);
+ }
+
+ PT_REGS_SYSCALL_RET(regs) = regs->regs.gp[HOST_AX];
+
+ /* handle tasks and signals at the end */
+ interrupt_end();
+}
diff --git a/arch/x86/um/nommu/entry_64.S b/arch/x86/um/nommu/entry_64.S
new file mode 100644
index 000000000000..485c578aae64
--- /dev/null
+++ b/arch/x86/um/nommu/entry_64.S
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/errno.h>
+
+#include <linux/linkage.h>
+#include <asm/percpu.h>
+#include <asm/desc.h>
+
+#include "../entry/calling.h"
+
+#ifdef CONFIG_SMP
+#error need to stash these variables somewhere else
+#endif
+
+#define UM_GLOBAL_VAR(x) .data; .align 8; .globl x; x:; .long 0
+
+UM_GLOBAL_VAR(current_top_of_stack)
+UM_GLOBAL_VAR(current_ptregs)
+
+.code64
+.section .entry.text, "ax"
+
+.align 8
+#undef ENTRY
+#define ENTRY(x) .text; .globl x; .type x,%function; x:
+#undef END
+#define END(x) .size x, . - x
+
+/*
+ * %rcx has the return address (we set it before entering __kernel_vsyscall).
+ *
+ * Registers on entry:
+ * rax system call number
+ * rcx return address
+ * rdi arg0
+ * rsi arg1
+ * rdx arg2
+ * r10 arg3
+ * r8 arg4
+ * r9 arg5
+ *
+ * (note: we are allowed to mess with r11: r11 is callee-clobbered
+ * register in C ABI)
+ */
+ENTRY(__kernel_vsyscall)
+
+ movq %rsp, %r11
+
+ /* Point rsp to the top of the ptregs array, so we can
+ just fill it with a bunch of push'es. */
+ movq current_ptregs, %rsp
+
+ /* 8 bytes * 20 registers (plus 8 for the push) */
+ addq $168, %rsp
+
+ /* Construct struct pt_regs on stack */
+ pushq $0 /* pt_regs->ss (index 20) */
+ pushq %r11 /* pt_regs->sp */
+ pushfq /* pt_regs->flags */
+ pushq $0 /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+ pushq %rax /* pt_regs->orig_ax */
+
+ PUSH_AND_CLEAR_REGS rax=$-ENOSYS
+
+ mov %rsp, %rdi
+
+ /*
+ * Switch to current top of stack, so "current->" points
+ * to the right task.
+ */
+ movq current_top_of_stack, %rsp
+
+ call do_syscall_64
+
+ jmp userspace
+
+END(__kernel_vsyscall)
+
+/*
+ * common userspace returning routine
+ *
+ * all procedures like syscalls, signal handlers, umh processes, will gate
+ * this routine to properly configure registers/stacks.
+ *
+ * void userspace(struct uml_pt_regs *regs)
+ */
+ENTRY(userspace)
+
+ /* clear direction flag to meet ABI */
+ cld
+ /* align the stack for x86_64 ABI */
+ and $-0x10, %rsp
+ /* Handle any immediate reschedules or signals */
+ call interrupt_end
+
+ movq current_ptregs, %rsp
+
+ POP_REGS
+
+ addq $8, %rsp /* skip orig_ax */
+ popq %rcx /* pt_regs->ip */
+ addq $8, %rsp /* skip cs */
+ addq $8, %rsp /* skip flags */
+ popq %rsp
+
+ /*
+ * not return w/ ret but w/ jmp as the stack is already popped before
+ * entering __kernel_vsyscall
+ */
+ jmp *%rcx
+
+END(userspace)
diff --git a/arch/x86/um/nommu/syscalls.h b/arch/x86/um/nommu/syscalls.h
new file mode 100644
index 000000000000..a2433756b1fc
--- /dev/null
+++ b/arch/x86/um/nommu/syscalls.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_NOMMU_SYSCALLS_H
+#define __UM_NOMMU_SYSCALLS_H
+
+
+#define task_top_of_stack(task) \
+({ \
+ unsigned long __ptr = (unsigned long)task->stack; \
+ __ptr += THREAD_SIZE; \
+ __ptr; \
+})
+
+extern long current_top_of_stack;
+extern long current_ptregs;
+
+#endif
--
2.43.0
Powered by blists - more mailing lists