summaryrefslogtreecommitdiff
path: root/arch/x86/entry
diff options
context:
space:
mode:
authorDominik Brodowski <linux@dominikbrodowski.net>2018-04-05 11:53:02 +0200
committerIngo Molnar <mingo@kernel.org>2018-04-05 16:59:26 +0200
commitfa697140f9a20119a9ec8fd7460cc4314fbdaff3 (patch)
treef7dbd8c7fe4b9a4db2fb4f14f5faf9f51956ef43 /arch/x86/entry
parent1bd21c6c21e848996339508d3ffb106d505256a8 (diff)
syscalls/x86: Use 'struct pt_regs' based syscall calling convention for 64-bit syscalls
Let's make use of ARCH_HAS_SYSCALL_WRAPPER=y on pure 64-bit x86-64 systems: Each syscall defines a stub which takes struct pt_regs as its only argument. It decodes just those parameters it needs, e.g: asmlinkage long sys_xyzzy(const struct pt_regs *regs) { return SyS_xyzzy(regs->di, regs->si, regs->dx); } This approach avoids leaking random user-provided register content down the call chain. For example, for sys_recv() which is a 4-parameter syscall, the assembly now is (in slightly reordered fashion): <sys_recv>: callq <__fentry__> /* decode regs->di, ->si, ->dx and ->r10 */ mov 0x70(%rdi),%rdi mov 0x68(%rdi),%rsi mov 0x60(%rdi),%rdx mov 0x38(%rdi),%rcx [ SyS_recv() is automatically inlined by the compiler, as it is not [yet] used anywhere else ] /* clear %r9 and %r8, the 5th and 6th args */ xor %r9d,%r9d xor %r8d,%r8d /* do the actual work */ callq __sys_recvfrom /* cleanup and return */ cltq retq The only valid place in an x86-64 kernel which rightfully calls a syscall function on its own -- vsyscall -- needs to be modified to pass struct pt_regs onwards as well. To keep the syscall table generation working independent of SYSCALL_PTREGS being enabled, the stubs are named the same as the "original" syscall stubs, i.e. sys_*(). This patch is based on an original proof-of-concept | From: Linus Torvalds <torvalds@linux-foundation.org> | Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> and was split up and heavily modified by me, in particular to base it on ARCH_HAS_SYSCALL_WRAPPER, to limit it to 64-bit-only for the time being, and to update the vsyscall to the new calling convention. Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20180405095307.3730-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/entry')
-rw-r--r--arch/x86/entry/common.c4
-rw-r--r--arch/x86/entry/syscall_64.c9
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c22
3 files changed, 33 insertions, 2 deletions
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index a8b066dbbf48..e1b91bffa988 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -284,9 +284,13 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
nr &= __SYSCALL_MASK;
if (likely(nr < NR_syscalls)) {
nr = array_index_nospec(nr, NR_syscalls);
+#ifdef CONFIG_SYSCALL_PTREGS
+ regs->ax = sys_call_table[nr](regs);
+#else
regs->ax = sys_call_table[nr](
regs->di, regs->si, regs->dx,
regs->r10, regs->r8, regs->r9);
+#endif
}
syscall_return_slowpath(regs);
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index c176d2fab1da..6197850adf91 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -7,14 +7,19 @@
#include <asm/asm-offsets.h>
#include <asm/syscall.h>
+#ifdef CONFIG_SYSCALL_PTREGS
+/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
+extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
+#else /* CONFIG_SYSCALL_PTREGS */
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+#endif /* CONFIG_SYSCALL_PTREGS */
#include <asm/syscalls_64.h>
#undef __SYSCALL_64
#define __SYSCALL_64(nr, sym, qual) [nr] = sym,
-extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 317be365bce3..05eebbf9b989 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -127,6 +127,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
int vsyscall_nr, syscall_nr, tmp;
int prev_sig_on_uaccess_err;
long ret;
+#ifdef CONFIG_SYSCALL_PTREGS
+ unsigned long orig_dx;
+#endif
/*
* No point in checking CS -- the only way to get here is a user mode
@@ -227,19 +230,38 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
ret = -EFAULT;
switch (vsyscall_nr) {
case 0:
+#ifdef CONFIG_SYSCALL_PTREGS
+ /* this decodes regs->di and regs->si on its own */
+ ret = sys_gettimeofday(regs);
+#else
ret = sys_gettimeofday(
(struct timeval __user *)regs->di,
(struct timezone __user *)regs->si);
+#endif /* CONFIG_SYSCALL_PTREGS */
break;
case 1:
+#ifdef CONFIG_SYSCALL_PTREGS
+ /* this decodes regs->di on its own */
+ ret = sys_time(regs);
+#else
ret = sys_time((time_t __user *)regs->di);
+#endif /* CONFIG_SYSCALL_PTREGS */
break;
case 2:
+#ifdef CONFIG_SYSCALL_PTREGS
+ /* while we could clobber regs->dx, we didn't in the past... */
+ orig_dx = regs->dx;
+ regs->dx = 0;
+ /* this decodes regs->di, regs->si and regs->dx on its own */
+ ret = sys_getcpu(regs);
+ regs->dx = orig_dx;
+#else
ret = sys_getcpu((unsigned __user *)regs->di,
(unsigned __user *)regs->si,
NULL);
+#endif /* CONFIG_SYSCALL_PTREGS */
break;
}