x86/signal/64: Fix SS if needed when delivering a 64-bit signal

Signals are always delivered to 64-bit tasks with CS set to a long
mode segment.  In long mode, SS doesn't matter as long as it's a
present writable segment.

If SS starts out invalid (this can happen if the signal was caused
by an IRET fault or was delivered on the way out of set_thread_area
or modify_ldt), then IRET to the signal handler can fail, eventually
killing the task.

The straightforward fix would be to simply reset SS when delivering
a signal.  That breaks DOSEMU, though: 64-bit builds of DOSEMU rely
on SS being set to the faulting SS when signals are delivered.

As a compromise, this patch leaves SS alone so long as it's valid.

The net effect should be that the behavior of successfully delivered
signals is unchanged.  Some signals that would previously have
failed to be delivered will now be delivered successfully.

This has no effect for x32 or 32-bit tasks: their signal handlers
were already called with SS == __USER_DS.

(On Xen, there's a slight hole: if a task sets SS to a writable
 *kernel* data segment, then we will fail to identify it as invalid
 and we'll still kill the task.  If anyone cares, this could be fixed
 with a new paravirt hook.)

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stas Sergeev <stsp@list.ru>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/163c6e1eacde41388f3ff4d2fe6769be651d7b6e.1455664054.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index 278441f39856edf31edca4f5391479c356b19a61..eb5deb42484d5e283adeaa191c004d1566f11a7f 100644 (file)
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -98,4 +98,27 @@ struct desc_ptr {
 
 #endif /* !__ASSEMBLY__ */
 
+/* Access rights as returned by LAR */
+#define AR_TYPE_RODATA         (0 * (1 << 9))
+#define AR_TYPE_RWDATA         (1 * (1 << 9))
+#define AR_TYPE_RODATA_EXPDOWN (2 * (1 << 9))
+#define AR_TYPE_RWDATA_EXPDOWN (3 * (1 << 9))
+#define AR_TYPE_XOCODE         (4 * (1 << 9))
+#define AR_TYPE_XRCODE         (5 * (1 << 9))
+#define AR_TYPE_XOCODE_CONF    (6 * (1 << 9))
+#define AR_TYPE_XRCODE_CONF    (7 * (1 << 9))
+#define AR_TYPE_MASK           (7 * (1 << 9))
+
+#define AR_DPL0                        (0 * (1 << 13))
+#define AR_DPL3                        (3 * (1 << 13))
+#define AR_DPL_MASK            (3 * (1 << 13))
+
+#define AR_A                   (1 << 8)   /* "Accessed" */
+#define AR_S                   (1 << 12)  /* If clear, "System" segment */
+#define AR_P                   (1 << 15)  /* "Present" */
+#define AR_AVL                 (1 << 20)  /* "AVaiLable" (no HW effect) */
+#define AR_L                   (1 << 21)  /* "Long mode" for code segments */
+#define AR_DB                  (1 << 22)  /* D/B, effect depends on type */
+#define AR_G                   (1 << 23)  /* "Granularity" (limit in pages) */
+
 #endif /* _ASM_X86_DESC_DEFS_H */

diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index c07ff5ddbd477eb44edb9ea960623d17b6d43924..52f82c7ef57d4f1eaf782bc56d3993a467c0a38e 100644 (file)
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -61,6 +61,35 @@
        regs->seg = GET_SEG(seg) | 3;                   \
 } while (0)
 
+#ifdef CONFIG_X86_64
+/*
+ * If regs->ss will cause an IRET fault, change it.  Otherwise leave it
+ * alone.  Using this generally makes no sense unless
+ * user_64bit_mode(regs) would return true.
+ */
+static void force_valid_ss(struct pt_regs *regs)
+{
+       u32 ar;
+       asm volatile ("lar %[old_ss], %[ar]\n\t"
+                     "jz 1f\n\t"               /* If invalid: */
+                     "xorl %[ar], %[ar]\n\t"   /* set ar = 0 */
+                     "1:"
+                     : [ar] "=r" (ar)
+                     : [old_ss] "rm" ((u16)regs->ss));
+
+       /*
+        * For a valid 64-bit user context, we need DPL 3, type
+        * read-write data or read-write exp-down data, and S and P
+        * set.  We can't use VERW because VERW doesn't check the
+        * P bit.
+        */
+       ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK;
+       if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) &&
+           ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN))
+               regs->ss = __USER_DS;
+}
+#endif
+
 int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 {
        unsigned long buf_val;
@@ -459,10 +488,28 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
        regs->sp = (unsigned long)frame;
 
-       /* Set up the CS register to run signal handlers in 64-bit mode,
-          even if the handler happens to be interrupting 32-bit code. */
+       /*
+        * Set up the CS and SS registers to run signal handlers in
+        * 64-bit mode, even if the handler happens to be interrupting
+        * 32-bit or 16-bit code.
+        *
+        * SS is subtle.  In 64-bit mode, we don't need any particular
+        * SS descriptor, but we do need SS to be valid.  It's possible
+        * that the old SS is entirely bogus -- this can happen if the
+        * signal we're trying to deliver is #GP or #SS caused by a bad
+        * SS value.  We also have a compatbility issue here: DOSEMU
+        * relies on the contents of the SS register indicating the
+        * SS value at the time of the signal, even though that code in
+        * DOSEMU predates sigreturn's ability to restore SS.  (DOSEMU
+        * avoids relying on sigreturn to restore SS; instead it uses
+        * a trampoline.)  So we do our best: if the old SS was valid,
+        * we keep it.  Otherwise we replace it.
+        */
        regs->cs = __USER_CS;
 
+       if (unlikely(regs->ss != __USER_DS))
+               force_valid_ss(regs);
+
        return 0;
 }
 #endif /* CONFIG_X86_32 */