x86/signal/64: Re-add support for SS in the 64-bit signal context

This is a second attempt to make the improvements from c6f2062935c8
("x86/signal/64: Fix SS handling for signals delivered to 64-bit
programs"), which was reverted by 51adbfbba5c6 ("x86/signal/64: Add
support for SS in the 64-bit signal context").

This adds two new uc_flags flags.  UC_SIGCONTEXT_SS will be set for
all 64-bit signals (including x32).  It indicates that the saved SS
field is valid and that the kernel supports the new behavior.

The goal is to fix a problems with signal handling in 64-bit tasks:
SS wasn't saved in the 64-bit signal context, making it awkward to
determine what SS was at the time of signal delivery and making it
impossible to return to a non-flat SS (as calling sigreturn clobbers
SS).

This also made it extremely difficult for 64-bit tasks to return to
fully-defined 16-bit contexts, because only the kernel can easily do
espfix64, but sigreturn was unable to set a non-flag SS:ESP.
(DOSEMU has a monstrous hack to partially work around this
limitation.)

If we could go back in time, the correct fix would be to make 64-bit
signals work just like 32-bit signals with respect to SS: save it
in signal context, reset it when delivering a signal, and restore
it in sigreturn.

Unfortunately, doing that (as I tried originally) breaks DOSEMU:
DOSEMU wouldn't reset the signal context's SS when clearing the LDT
and changing the saved CS to 64-bit mode, since it predates the SS
context field existing in the first place.

This patch is a bit more complicated, and it tries to balance a
bunch of goals.  It makes most cases of changing ucontext->ss during
signal handling work as expected.

I do this by special-casing the interesting case.  On sigreturn,
ucontext->ss will be honored by default, unless the ucontext was
created from scratch by an old program and had a 64-bit CS
(unfortunately, CRIU can do this) or was the result of changing a
32-bit signal context to 64-bit without resetting SS (as DOSEMU
does).

For the benefit of new 64-bit software that uses segmentation (new
versions of DOSEMU might), the new behavior can be detected with a
new ucontext flag UC_SIGCONTEXT_SS.

To avoid compilation issues, __pad0 is left as an alias for ss in
ucontext.

The nitty-gritty details are documented in the header file.

This patch also re-enables the sigreturn_64 and ldt_gdt_64 selftests,
as the kernel change allows both of them to pass.

Tested-by: Stas Sergeev <stsp@list.ru>
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: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/749149cbfc3e75cd7fcdad69a854b399d792cc6f.1455664054.git.luto@kernel.org
[ Small readability edit. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 44 insertions, 19 deletions

diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 52f82c7ef57d..548ddf7d6fd2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -90,7 +90,9 @@ static void force_valid_ss(struct pt_regs *regs)
 }
 #endif
 
-int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
+static int restore_sigcontext(struct pt_regs *regs,
+                              struct sigcontext __user *sc,
+                              unsigned long uc_flags)
 {
         unsigned long buf_val;
         void __user *buf;
@@ -123,15 +125,18 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
                 COPY(r15);
 #endif /* CONFIG_X86_64 */
 
-#ifdef CONFIG_X86_32
                 COPY_SEG_CPL3(cs);
                 COPY_SEG_CPL3(ss);
-#else /* !CONFIG_X86_32 */
-                /* Kernel saves and restores only the CS segment register on signals,
-                 * which is the bare minimum needed to allow mixed 32/64-bit code.
-                 * App's signal handler can save/restore other segments if needed. */
-                COPY_SEG_CPL3(cs);
-#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_X86_64
+                /*
+                 * Fix up SS if needed for the benefit of old DOSEMU and
+                 * CRIU.
+                 */
+                if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
+                             user_64bit_mode(regs)))
+                        force_valid_ss(regs);
+#endif
 
                 get_user_ex(tmpflags, &sc->flags);
                 regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -194,6 +199,7 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
                 put_user_ex(regs->cs, &sc->cs);
                 put_user_ex(0, &sc->gs);
                 put_user_ex(0, &sc->fs);
+                put_user_ex(regs->ss, &sc->ss);
 #endif /* CONFIG_X86_32 */
 
                 put_user_ex(fpstate, &sc->fpstate);
@@ -432,6 +438,21 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
         return 0;
 }
 #else /* !CONFIG_X86_32 */
+static unsigned long frame_uc_flags(struct pt_regs *regs)
+{
+        unsigned long flags;
+
+        if (cpu_has_xsave)
+                flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS;
+        else
+                flags = UC_SIGCONTEXT_SS;
+
+        if (likely(user_64bit_mode(regs)))
+                flags |= UC_STRICT_RESTORE_SS;
+
+        return flags;
+}
+
 static int __setup_rt_frame(int sig, struct ksignal *ksig,
                             sigset_t *set, struct pt_regs *regs)
 {
@@ -451,10 +472,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
         put_user_try {
                 /* Create the ucontext.  */
-                if (cpu_has_xsave)
-                        put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
-                else
-                        put_user_ex(0, &frame->uc.uc_flags);
+                put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
                 put_user_ex(0, &frame->uc.uc_link);
                 save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
@@ -536,10 +554,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 
         put_user_try {
                 /* Create the ucontext.  */
-                if (cpu_has_xsave)
-                        put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
-                else
-                        put_user_ex(0, &frame->uc.uc_flags);
+                put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
                 put_user_ex(0, &frame->uc.uc_link);
                 compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
                 put_user_ex(0, &frame->uc.uc__pad0);
@@ -601,7 +616,11 @@ asmlinkage unsigned long sys_sigreturn(void)
 
         set_current_blocked(&set);
 
-        if (restore_sigcontext(regs, &frame->sc))
+        /*
+         * x86_32 has no uc_flags bits relevant to restore_sigcontext.
+         * Save a few cycles by skipping the __get_user.
+         */
+        if (restore_sigcontext(regs, &frame->sc, 0))
                 goto badframe;
         return regs->ax;
 
@@ -617,16 +636,19 @@ asmlinkage long sys_rt_sigreturn(void)
         struct pt_regs *regs = current_pt_regs();
         struct rt_sigframe __user *frame;
         sigset_t set;
+        unsigned long uc_flags;
 
         frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
         if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
                 goto badframe;
         if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
                 goto badframe;
+        if (__get_user(uc_flags, &frame->uc.uc_flags))
+                goto badframe;
 
         set_current_blocked(&set);
 
-        if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+        if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
                 goto badframe;
 
         if (restore_altstack(&frame->uc.uc_stack))
@@ -813,6 +835,7 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
         struct pt_regs *regs = current_pt_regs();
         struct rt_sigframe_x32 __user *frame;
         sigset_t set;
+        unsigned long uc_flags;
 
         frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 
@@ -820,10 +843,12 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
                 goto badframe;
         if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
                 goto badframe;
+        if (__get_user(uc_flags, &frame->uc.uc_flags))
+                goto badframe;
 
         set_current_blocked(&set);
 
-        if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+        if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
                 goto badframe;
 
         if (compat_restore_altstack(&frame->uc.uc_stack))