[RFC 3/4] x86/signal/64: Re-add support for SS in the 64-bit signal context
From: Andy Lutomirski
Date: Mon Oct 12 2015 - 21:04:45 EST
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 load or even restore SS:ESP.
(DOSEMU has a monstrous hack to partially work around this.)
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 signal delivery due to a bogus SS reliable
without having to set any flags (64-bit signals will always be
delivered to a valid SS), and 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.
Cc: Stas Sergeev <stsp@xxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
arch/x86/include/asm/sigcontext.h | 2 +-
arch/x86/include/asm/sighandling.h | 1 -
arch/x86/include/uapi/asm/sigcontext.h | 5 ++-
arch/x86/include/uapi/asm/ucontext.h | 41 +++++++++++++++++++---
arch/x86/kernel/signal.c | 64 +++++++++++++++++++++++-----------
tools/testing/selftests/x86/Makefile | 4 +--
6 files changed, 87 insertions(+), 30 deletions(-)
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 9dfce4e0417d..9789402b99b6 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -59,7 +59,7 @@ struct sigcontext {
unsigned short cs;
unsigned short gs;
unsigned short fs;
- unsigned short __pad0;
+ unsigned short ss; /* Only restored if UC_RESTORE_SS is set. */
unsigned long err;
unsigned long trapno;
unsigned long oldmask;
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index 89db46752a8f..452c88b8ad06 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -13,7 +13,6 @@
X86_EFLAGS_CF | X86_EFLAGS_RF)
void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
-int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc);
int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
struct pt_regs *regs, unsigned long mask);
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 827c6ed0e26a..ad02ae519179 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -197,7 +197,10 @@ struct sigcontext {
*/
__u16 gs;
__u16 fs;
- __u16 __pad0;
+ union {
+ __u16 ss; /* If UC_SAVED_SS */
+ __u16 __pad0; /* If !UC_SAVED_SS */
+ };
__u64 err;
__u64 trapno;
__u64 oldmask;
diff --git a/arch/x86/include/uapi/asm/ucontext.h b/arch/x86/include/uapi/asm/ucontext.h
index b7c29c8017f2..b75b29fcd6aa 100644
--- a/arch/x86/include/uapi/asm/ucontext.h
+++ b/arch/x86/include/uapi/asm/ucontext.h
@@ -1,11 +1,42 @@
#ifndef _ASM_X86_UCONTEXT_H
#define _ASM_X86_UCONTEXT_H
-#define UC_FP_XSTATE 0x1 /* indicates the presence of extended state
- * information in the memory layout pointed
- * by the fpstate pointer in the ucontext's
- * sigcontext struct (uc_mcontext).
- */
+/*
+ * indicates the presence of extended state
+ * information in the memory layout pointed
+ * by the fpstate pointer in the ucontext's
+ * sigcontext struct (uc_mcontext).
+ */
+#define UC_FP_XSTATE 0x1
+
+#ifdef __x86_64__
+/*
+ * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on
+ * kernels that save SS in the sigcontext. All kernels that set
+ * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp
+ * regardless of SS (i.e. they implement espfix).
+ *
+ * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS
+ * when delivering a signal that came from 64-bit code.
+ *
+ * Sigreturn modifies its behavior depending on the UC_STRICT_RESTORE_SS
+ * flag. If UC_STRICT_RESTORE_SS is set, then the SS value in the
+ * signal context is restored verbatim. If UC_STRICT_RESTORE_SS is not
+ * set, the CS value in the signal context refers to a 64-bit code
+ * segment, and the signal context's SS value is invalid, it will be
+ * replaced by an flat 32-bit selector.
+
+ * This behavior serves two purposes. It ensures that older programs
+ * that are unaware of the signal context's SS slot and either construct
+ * a signal context from scratch or that catch signals from segmented
+ * contexts and change CS to a 64-bit selector won't crash due to a bad
+ * SS value. It also ensures that signal handlers that do not modify
+ * the signal context at all return back to the exact CS and SS state
+ * that they came from.
+ */
+#define UC_SIGCONTEXT_SS 0x2
+#define UC_STRICT_RESTORE_SS 0x4
+#endif
#include <asm-generic/ucontext.h>
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index ca8975096728..2fd1e901550d 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)
{
void __user *buf;
unsigned int tmpflags;
@@ -122,15 +124,18 @@ 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);
@@ -186,13 +191,13 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
put_user_ex(regs->cs, (unsigned int __user *)&sc->cs);
put_user_ex(regs->flags, &sc->flags);
put_user_ex(regs->sp, &sc->sp_at_signal);
- put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
#else /* !CONFIG_X86_32 */
put_user_ex(regs->flags, &sc->flags);
put_user_ex(regs->cs, &sc->cs);
put_user_ex(0, &sc->gs);
put_user_ex(0, &sc->fs);
#endif /* CONFIG_X86_32 */
+ put_user_ex(regs->ss, (unsigned int __user *)&sc->ss);
put_user_ex(fpstate, &sc->fpstate);
@@ -430,6 +435,21 @@ 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)
{
@@ -449,10 +469,7 @@ 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);
@@ -534,10 +551,7 @@ 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);
@@ -599,7 +613,11 @@ 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;
@@ -615,16 +633,19 @@ 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))
@@ -805,6 +826,7 @@ 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);
@@ -812,10 +834,12 @@ 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))
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 389701f59940..c2221786d835 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,8 +4,8 @@ include ../lib.mk
.PHONY: all all_32 all_64 warn_32bit_failure clean
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt ptrace_syscall
-TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt ptrace_syscall sigreturn
+TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso
TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
--
2.4.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/