x86: sigcontext fixes, again

index d485232f1e9f..47dae8150520 100644
@@ -341,6 +341,25 @@ struct sigcontext {
 	__u64				rip;
 	__u64				eflags;		/* RFLAGS */
 	__u16				cs;
+
+	/*
+	 * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
+	 * Linux saved and restored fs and gs in these slots.  This
+	 * was counterproductive, as fsbase and gsbase were never
+	 * saved, so arch_prctl was presumably unreliable.
+	 *
+	 * If these slots are ever needed for any other purpose, there
+	 * is some risk that very old 64-bit binaries could get
+	 * confused.  I doubt that many such binaries still work,
+	 * though, since the same patch in 2.5.64 also removed the
+	 * 64-bit set_thread_area syscall, so it appears that there is
+	 * no TLS API beyond modify_ldt that works in both pre- and
+	 * post-2.5.64 kernels.
+	 *
+	 * There is at least one additional concern if these slots are
+	 * recycled for another purpose: some DOSEMU versions stash fs
+	 * and gs in these slots manually.
+	 */
 	__u16				gs;
 	__u16				fs;
 	__u16				__pad0;

index 278441f39856..eb5deb42484d 100644
@@ -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 */

65 lines not on this page · raw message

index 89db46752a8f..452c88b8ad06 100644
@@ -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);
 

index 47dae8150520..bb0dde737b59 100644
@@ -256,7 +256,7 @@ struct sigcontext_64 {
 	__u16				cs;
 	__u16				gs;
 	__u16				fs;
-	__u16				__pad0;
+	__u16				ss;
 	__u64				err;
 	__u64				trapno;
 	__u64				oldmask;

@@ -362,7 +362,10 @@ 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;

60 lines not on this page · raw message

137 lines not on this page · raw message

index b5aa1bab7416..92a522420a5c 100644
@@ -54,6 +54,29 @@
 #include <sys/ptrace.h>
 #include <sys/user.h>
 
+/* Pull in AR_xyz defines. */
+typedef unsigned int u32;
+typedef unsigned short u16;
+#include "../../../../arch/x86/include/asm/desc_defs.h"
+
+/*
+ * Copied from asm/ucontext.h, as asm/ucontext.h conflicts badly with the glibc
+ * headers.
+ */
+#ifdef __x86_64__
+/*
+ * UC_SAVED_SS will be set when delivering 64-bit or x32 signals on
+ * kernels that save SS in the sigcontext.  Kernels that set UC_SAVED_SS
+ * allow signal handlers to set UC_RESTORE_SS; if UC_RESTORE_SS is set,
+ * then sigreturn will restore SS.
+ *
+ * For compatibility with old programs, the kernel will *not* set
+ * UC_RESTORE_SS when delivering signals.
+ */
+#define UC_SIGCONTEXT_SS       0x2
+#define UC_STRICT_RESTORE_SS   0x4
+#endif
+
 /*
  * In principle, this test can run on Linux emulation layers (e.g.
  * Illumos "LX branded zones").  Solaris-based kernels reserve LDT

@@ -267,6 +290,9 @@ static gregset_t initial_regs, requested_regs, resulting_regs;
 /* Instructions for the SIGUSR1 handler. */
 static volatile unsigned short sig_cs, sig_ss;
 static volatile sig_atomic_t sig_trapped, sig_err, sig_trapno;
+#ifdef __x86_64__
+static volatile sig_atomic_t sig_corrupt_final_ss;
+#endif
 
 /* Abstractions for some 32-bit vs 64-bit differences. */
 #ifdef __x86_64__

@@ -305,9 +331,105 @@ static greg_t *csptr(ucontext_t *ctx)
 }
 #endif
 
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+int cs_bitness(unsigned short cs)
+{
+	uint32_t valid = 0, ar;
+	asm ("lar %[cs], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "mov $1, %[valid]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [valid] "+rm" (valid)
+	     : [cs] "r" (cs));
+
+	if (!valid)
+		return -1;
+
+	bool db = (ar & (1 << 22));
+	bool l = (ar & (1 << 21));
+
+	if (!(ar & (1<<11)))
+	    return -1;	/* Not code. */
+
+	if (l && !db)
+		return 64;
+	else if (!l && db)
+		return 32;
+	else if (!l && !db)
+		return 16;
+	else
+		return -1;	/* Unknown bitness. */
+}
+
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+bool is_valid_ss(unsigned short cs)
+{
+	uint32_t valid = 0, ar;
+	asm ("lar %[cs], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "mov $1, %[valid]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [valid] "+rm" (valid)
+	     : [cs] "r" (cs));
+
+	if (!valid)
+		return false;
+
+	if ((ar & AR_TYPE_MASK) != AR_TYPE_RWDATA &&
+	    (ar & AR_TYPE_MASK) != AR_TYPE_RWDATA_EXPDOWN)
+		return false;
+
+	return (ar & AR_P);
+}
+
 /* Number of errors in the current test case. */
 static volatile sig_atomic_t nerrs;
 
+static void validate_signal_ss(int sig, ucontext_t *ctx)
+{
+#ifdef __x86_64__
+	bool was_64bit = (cs_bitness(*csptr(ctx)) == 64);
+
+	if (!(ctx->uc_flags & UC_SIGCONTEXT_SS)) {
+		printf("[FAIL]\tUC_SIGCONTEXT_SS was not set\n");
+		nerrs++;
+
+		/*
+		 * This happens on Linux 4.1.  The rest will fail, too, so
+		 * return now to reduce the noise.
+		 */
+		return;
+	}
+
+	/* UC_STRICT_RESTORE_SS is set iff we came from 64-bit mode. */
+	if (!!(ctx->uc_flags & UC_STRICT_RESTORE_SS) != was_64bit) {
+		printf("[FAIL]\tUC_STRICT_RESTORE_SS was wrong in signal %d\n",
+		       sig);
+		nerrs++;
+	}
+
+	if (is_valid_ss(*ssptr(ctx))) {
+		/*
+		 * DOSEMU was written before 64-bit sigcontext had SS, and
+		 * it tries to figure out the signal source SS by looking at
+		 * the physical register.  Make sure that keeps working.
+		 */
+		unsigned short hw_ss;
+		asm ("mov %%ss, %0" : "=rm" (hw_ss));
+		if (hw_ss != *ssptr(ctx)) {
+			printf("[FAIL]\tHW SS didn't match saved SS\n");
+			nerrs++;
+		}
+	}
+#endif
+}
+
 /*
  * SIGUSR1 handler.  Sets CS and SS as requested and points IP to the
  * int3 trampoline.  Sets SP to a large known value so that we can see

@@ -317,6 +439,8 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+	validate_signal_ss(sig, ctx);
+
 	memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 
 	*csptr(ctx) = sig_cs;

@@ -334,13 +458,16 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 }
 
 /*
- * Called after a successful sigreturn.  Restores our state so that
- * the original raise(SIGUSR1) returns.
+ * Called after a successful sigreturn (via int3) or from a failed
+ * sigreturn (directly by kernel).  Restores our state so that the
+ * original raise(SIGUSR1) returns.
  */
 static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+	validate_signal_ss(sig, ctx);
+
 	sig_err = ctx->uc_mcontext.gregs[REG_ERR];
 	sig_trapno = ctx->uc_mcontext.gregs[REG_TRAPNO];
 

@@ -358,41 +485,62 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 	memcpy(&resulting_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 	memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t));
 
+#ifdef __x86_64__
+	if (sig_corrupt_final_ss) {
+		if (ctx->uc_flags & UC_STRICT_RESTORE_SS) {
+			printf("[FAIL]\tUC_STRICT_RESTORE_SS was set inappropriately\n");
+			nerrs++;
+		} else {
+			/*
+			 * DOSEMU transitions from 32-bit to 64-bit mode by
+			 * adjusting sigcontext, and it requires that this work
+			 * even if the saved SS is bogus.
+			 */
+			printf("\tCorrupting SS on return to 64-bit mode\n");
+			*ssptr(ctx) = 0;
+		}
+	}
+#endif
+
 	sig_trapped = sig;
 }
 
-/*
- * Checks a given selector for its code bitness or returns -1 if it's not
- * a usable code segment selector.
- */
-int cs_bitness(unsigned short cs)
+#ifdef __x86_64__
+/* Tests recovery if !UC_STRICT_RESTORE_SS */
+static void sigusr2(int sig, siginfo_t *info, void *ctx_void)
 {
-	uint32_t valid = 0, ar;
-	asm ("lar %[cs], %[ar]\n\t"
-	     "jnz 1f\n\t"
-	     "mov $1, %[valid]\n\t"
-	     "1:"
-	     : [ar] "=r" (ar), [valid] "+rm" (valid)
-	     : [cs] "r" (cs));
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
-	if (!valid)
-		return -1;
+	if (!(ctx->uc_flags & UC_STRICT_RESTORE_SS)) {
+		printf("[FAIL]\traise(2) didn't set UC_STRICT_RESTORE_SS\n");
+		nerrs++;
+		return;  /* We can't do the rest. */
+	}
 
-	bool db = (ar & (1 << 22));
-	bool l = (ar & (1 << 21));
+	ctx->uc_flags &= ~UC_STRICT_RESTORE_SS;
+	*ssptr(ctx) = 0;
 
-	if (!(ar & (1<<11)))
-	    return -1;	/* Not code. */
+	/* Return.  The kernel should recover without sending another signal. */
+}
 
-	if (l && !db)
-		return 64;
-	else if (!l && db)
-		return 32;
-	else if (!l && !db)
-		return 16;
-	else
-		return -1;	/* Unknown bitness. */
+static int test_nonstrict_ss(void)
+{
+	clearhandler(SIGUSR1);
+	clearhandler(SIGTRAP);
+	clearhandler(SIGSEGV);
+	clearhandler(SIGILL);
+	sethandler(SIGUSR2, sigusr2, 0);
+
+	nerrs = 0;
+
+	printf("[RUN]\tClear UC_STRICT_RESTORE_SS and corrupt SS\n");
+	raise(SIGUSR2);
+	if (!nerrs)
+		printf("[OK]\tIt worked\n");
+
+	return nerrs;
 }
+#endif
 
 /* Finds a usable code segment of the requested bitness. */
 int find_cs(int bitness)

@@ -576,6 +724,12 @@ static int test_bad_iret(int cs_bits, unsigned short ss, int force_cs)
 		       errdesc, strsignal(sig_trapped));
 		return 0;
 	} else {
+		/*
+		 * This also implicitly tests UC_STRICT_RESTORE_SS:
+		 * We check that these signals set UC_STRICT_RESTORE_SS and,
+		 * if UC_STRICT_RESTORE_SS doesn't cause strict behavior,
+		 * then we won't get SIGSEGV.
+		 */
 		printf("[FAIL]\tDid not get SIGSEGV\n");
 		return 1;
 	}

@@ -632,6 +786,14 @@ int main()
 						    GDT3(gdt_data16_idx));
 	}
 
+#ifdef __x86_64__
+	/* Nasty ABI case: check SS corruption handling. */
+	sig_corrupt_final_ss = 1;
+	total_nerrs += test_valid_sigreturn(32, false, -1);
+	total_nerrs += test_valid_sigreturn(32, true, -1);
+	sig_corrupt_final_ss = 0;
+#endif
+
 	/*
 	 * We're done testing valid sigreturn cases.  Now we test states
 	 * for which sigreturn itself will succeed but the subsequent

@@ -680,5 +842,9 @@ int main()
 	if (gdt_npdata32_idx)
 		test_bad_iret(32, GDT3(gdt_npdata32_idx), -1);
 
+#ifdef __x86_64__
+	total_nerrs += test_nonstrict_ss();
+#endif
+
 	return total_nerrs ? 1 : 0;
 }