um: rework userspace stubs to not hard-code stub location

The userspace stacks mostly have a stack (and in the case of the
syscall stub we can just set their stack pointer) that points to
the location of the stub data page already.

Rework the stubs to use the stack pointer to derive the start of
the data page, rather than requiring it to be hard-coded.

In the clone stub, also integrate the int3 into the stack remap,
since we really must not use the stack while we remap it.

This prepares for putting the stub at a variable location that's
not part of the normal address space of the userspace processes
running inside the UML machine.

Signed-off-by: Johannes Berg <[e-mail]>
Signed-off-by: Richard Weinberger <[e-mail]>

arch/um/include/shared/as-layout.h

···
  * 'UL' and other type specifiers unilaterally.  We
  * use the following macros to deal with this.
  */
-
-#ifdef __ASSEMBLY__
-#define _UML_AC(X, Y)	(Y)
-#else
-#define __UML_AC(X, Y)	(X(Y))
-#define _UML_AC(X, Y)	__UML_AC(X, Y)
-#endif
-
-#define STUB_START _UML_AC(, 0x100000)
-#define STUB_CODE _UML_AC((unsigned long), STUB_START)
-#define STUB_DATA _UML_AC((unsigned long), STUB_CODE + UM_KERN_PAGE_SIZE)
-#define STUB_END _UML_AC((unsigned long), STUB_DATA + UM_KERN_PAGE_SIZE)
+#define STUB_START 0x100000UL
+#define STUB_CODE STUB_START
+#define STUB_DATA (STUB_CODE + UM_KERN_PAGE_SIZE)
+#define STUB_END (STUB_DATA + UM_KERN_PAGE_SIZE)
 
 #ifndef __ASSEMBLY__
 

arch/um/include/shared/common-offsets.h

···
 /* SPDX-License-Identifier: GPL-2.0 */
 /* for use by sys-$SUBARCH/kernel-offsets.c */
+#include <stub-data.h>
 
 DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
 
···
 #ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
 DEFINE(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT, CONFIG_UML_TIME_TRAVEL_SUPPORT);
 #endif
+
+/* for stub */
+DEFINE(UML_STUB_FIELD_OFFSET, offsetof(struct stub_data, offset));
+DEFINE(UML_STUB_FIELD_CHILD_ERR, offsetof(struct stub_data, child_err));
+DEFINE(UML_STUB_FIELD_FD, offsetof(struct stub_data, fd));

arch/um/kernel/skas/clone.c

···
 		goto done;
 	}
 
-	remap_stack(data->fd, data->offset);
-	goto done;
+	remap_stack_and_trap();
 
  done:
 	trap_myself();

arch/um/os-Linux/skas/mem.c

···
 	syscall_regs[REGS_IP_INDEX] = STUB_CODE +
 		((unsigned long) batch_syscall_stub -
 		 (unsigned long) __syscall_stub_start);
+	syscall_regs[REGS_SP_INDEX] = STUB_DATA;
+
 	return 0;
 }
 

arch/x86/um/shared/sysdep/stub_32.h

···
 #define __SYSDEP_STUB_H
 
 #include <asm/ptrace.h>
+#include <generated/asm-offsets.h>
 
-#define STUB_SYSCALL_RET EAX
 #define STUB_MMAP_NR __NR_mmap2
 #define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT)
 
···
 	__asm("int3");
 }
 
-static inline void remap_stack(int fd, unsigned long offset)
+static void inline remap_stack_and_trap(void)
 {
-	__asm__ volatile ("movl %%eax,%%ebp ; movl %0,%%eax ; int $0x80 ;"
-			  "movl %7, %%ebx ; movl %%eax, (%%ebx)"
-			  : : "g" (STUB_MMAP_NR), "b" (STUB_DATA),
-			    "c" (UM_KERN_PAGE_SIZE),
-			    "d" (PROT_READ | PROT_WRITE),
-			    "S" (MAP_FIXED | MAP_SHARED), "D" (fd),
-			    "a" (offset),
-			    "i" (&((struct stub_data *) STUB_DATA)->child_err)
-			  : "memory");
+	__asm__ volatile (
+		"movl %%esp,%%ebx ;"
+		"andl %0,%%ebx ;"
+		"movl %1,%%eax ;"
+		"movl %%ebx,%%edi ; addl %2,%%edi ; movl (%%edi),%%edi ;"
+		"movl %%ebx,%%ebp ; addl %3,%%ebp ; movl (%%ebp),%%ebp ;"
+		"int $0x80 ;"
+		"addl %4,%%ebx ; movl %%eax, (%%ebx) ;"
+		"int $3"
+		: :
+		"g" (~(UM_KERN_PAGE_SIZE - 1)),
+		"g" (STUB_MMAP_NR),
+		"g" (UML_STUB_FIELD_FD),
+		"g" (UML_STUB_FIELD_OFFSET),
+		"g" (UML_STUB_FIELD_CHILD_ERR),
+		"c" (UM_KERN_PAGE_SIZE),
+		"d" (PROT_READ | PROT_WRITE),
+		"S" (MAP_FIXED | MAP_SHARED)
+		:
+		"memory");
 }
 
 #endif

arch/x86/um/shared/sysdep/stub_64.h

···
 #define __SYSDEP_STUB_H
 
 #include <sysdep/ptrace_user.h>
+#include <generated/asm-offsets.h>
 
-#define STUB_SYSCALL_RET PT_INDEX(RAX)
 #define STUB_MMAP_NR __NR_mmap
 #define MMAP_OFFSET(o) (o)
 
···
 	__asm("int3");
 }
 
-static inline void remap_stack(long fd, unsigned long offset)
+static inline void remap_stack_and_trap(void)
 {
-	__asm__ volatile ("movq %4,%%r10 ; movq %5,%%r8 ; "
-			  "movq %6, %%r9; " __syscall "; movq %7, %%rbx ; "
-			  "movq %%rax, (%%rbx)":
-			  : "a" (STUB_MMAP_NR), "D" (STUB_DATA),
-			    "S" (UM_KERN_PAGE_SIZE),
-			    "d" (PROT_READ | PROT_WRITE),
-                            "g" (MAP_FIXED | MAP_SHARED), "g" (fd),
-			    "g" (offset),
-			    "i" (&((struct stub_data *) STUB_DATA)->child_err)
-			  : __syscall_clobber, "r10", "r8", "r9" );
+	__asm__ volatile (
+		"movq %0,%%rax ;"
+		"movq %%rsp,%%rdi ;"
+		"andq %1,%%rdi ;"
+		"movq %2,%%r10 ;"
+		"movq %%rdi,%%r8 ; addq %3,%%r8 ; movq (%%r8),%%r8 ;"
+		"movq %%rdi,%%r9 ; addq %4,%%r9 ; movq (%%r9),%%r9 ;"
+		__syscall ";"
+		"movq %%rsp,%%rdi ; andq %1,%%rdi ;"
+		"addq %5,%%rdi ; movq %%rax, (%%rdi) ;"
+		"int3"
+		: :
+		"g" (STUB_MMAP_NR),
+		"g" (~(UM_KERN_PAGE_SIZE - 1)),
+		"g" (MAP_FIXED | MAP_SHARED),
+		"g" (UML_STUB_FIELD_FD),
+		"g" (UML_STUB_FIELD_OFFSET),
+		"g" (UML_STUB_FIELD_CHILD_ERR),
+		"S" (UM_KERN_PAGE_SIZE),
+		"d" (PROT_READ | PROT_WRITE)
+		:
+		__syscall_clobber, "r10", "r8", "r9");
 }
 
 #endif

arch/x86/um/stub_32.S

···
 
 	.globl batch_syscall_stub
 batch_syscall_stub:
-	/* load pointer to first operation */
-	mov	$(STUB_DATA+8), %esp
-
+	/* %esp comes in as "top of page" */
+	mov %esp, %ecx
+	/* %esp has pointer to first operation */
+	add $8, %esp
 again:
 	/* load length of additional data */
 	mov	0x0(%esp), %eax
 
 	/* if(length == 0) : end of list */
 	/* write possible 0 to header */
-	mov	%eax, STUB_DATA+4
+	mov	%eax, 0x4(%ecx)
 	cmpl	$0, %eax
 	jz	done
 
 	/* save current pointer */
-	mov	%esp, STUB_DATA+4
+	mov	%esp, 0x4(%ecx)
 
 	/* skip additional data */
 	add	%eax, %esp
···
 	/* execute syscall */
 	int	$0x80
 
+	/* restore top of page pointer in %ecx */
+	mov	%esp, %ecx
+	andl	$(~UM_KERN_PAGE_SIZE) + 1, %ecx
+
 	/* check return value */
 	pop	%ebx
 	cmp	%ebx, %eax
···
 
 done:
 	/* save return value */
-	mov	%eax, STUB_DATA
+	mov	%eax, (%ecx)
 
 	/* stop */
 	int3

arch/x86/um/stub_64.S

···
 .section .__syscall_stub, "ax"
 	.globl batch_syscall_stub
 batch_syscall_stub:
-	mov	$(STUB_DATA), %rbx
-	/* load pointer to first operation */
-	mov	%rbx, %rsp
+	/* %rsp has the pointer to first operation */
+	mov	%rsp, %rbx
 	add	$0x10, %rsp
 again:
 	/* load length of additional data */

arch/x86/um/stub_segv.c

···
 void __attribute__ ((__section__ (".__syscall_stub")))
 stub_segv_handler(int sig, siginfo_t *info, void *p)
 {
+	int stack;
 	ucontext_t *uc = p;
+	struct faultinfo *f = (void *)(((unsigned long)&stack) & ~(UM_KERN_PAGE_SIZE - 1));
 
-	GET_FAULTINFO_FROM_MC(*((struct faultinfo *) STUB_DATA),
-			      &uc->uc_mcontext);
+	GET_FAULTINFO_FROM_MC(*f, &uc->uc_mcontext);
 	trap_myself();
 }