x86/mm: Expand the exception table logic to allow new handling options

Huge amounts of help from  Andy Lutomirski and Borislav Petkov to
produce this. Andy provided the inspiration to add classes to the
exception table with a clever bit-squeezing trick, Boris pointed
out how much cleaner it would all be if we just had a new field.

Linus Torvalds blessed the expansion with:

  ' I'd rather not be clever in order to save just a tiny amount of space
    in the exception table, which isn't really criticial for anybody. '

The third field is another relative function pointer, this one to a
handler that executes the actions.

We start out with three handlers:

 1: Legacy - just jumps the to fixup IP
 2: Fault - provide the trap number in %ax to the fixup code
 3: Cleaned up legacy for the uaccess error hack

Signed-off-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/f6af78fcbd348cf4939875cfda9c19689b5e50b8.1455732970.git.tony.luck@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/x86/exception-tables.txt

@@ -290,3 +290,38 @@ Due to the way that the exception table is built and needs to be ordered,
 only use exceptions for code in the .text section.  Any other section
 will cause the exception table to not be sorted correctly, and the
 exceptions will fail.
+
+Things changed when 64-bit support was added to x86 Linux. Rather than
+double the size of the exception table by expanding the two entries
+from 32-bits to 64 bits, a clever trick was used to store addresses
+as relative offsets from the table itself. The assembly code changed
+from:
+	.long 1b,3b
+to:
+        .long (from) - .
+        .long (to) - .
+
+and the C-code that uses these values converts back to absolute addresses
+like this:
+
+	ex_insn_addr(const struct exception_table_entry *x)
+	{
+		return (unsigned long)&x->insn + x->insn;
+	}
+
+In v4.6 the exception table entry was expanded with a new field "handler".
+This is also 32-bits wide and contains a third relative function
+pointer which points to one of:
+
+1) int ex_handler_default(const struct exception_table_entry *fixup)
+   This is legacy case that just jumps to the fixup code
+2) int ex_handler_fault(const struct exception_table_entry *fixup)
+   This case provides the fault number of the trap that occurred at
+   entry->insn. It is used to distinguish page faults from machine
+   check.
+3) int ex_handler_ext(const struct exception_table_entry *fixup)
+   This case is used for uaccess_err ... we need to set a flag
+   in the task structure. Before the handler functions existed this
+   case was handled by adding a large offset to the fixup to tag
+   it as special.
+More functions can easily be added.

arch/x86/include/asm/asm.h

@@ -44,19 +44,22 @@
 
 /* Exception table entry */
 #ifdef __ASSEMBLY__
-# define _ASM_EXTABLE(from,to)					\
+# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
 	.pushsection "__ex_table","a" ;				\
-	.balign 8 ;						\
+	.balign 4 ;						\
 	.long (from) - . ;					\
 	.long (to) - . ;					\
+	.long (handler) - . ;					\
 	.popsection
 
-# define _ASM_EXTABLE_EX(from,to)				\
-	.pushsection "__ex_table","a" ;				\
-	.balign 8 ;						\
-	.long (from) - . ;					\
-	.long (to) - . + 0x7ffffff0 ;				\
-	.popsection
+# define _ASM_EXTABLE(from, to)					\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_FAULT(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# define _ASM_EXTABLE_EX(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
 # define _ASM_NOKPROBE(entry)					\
 	.pushsection "_kprobe_blacklist","aw" ;			\
@@ -89,19 +92,24 @@
 	.endm
 
 #else
-# define _ASM_EXTABLE(from,to)					\
+# define _EXPAND_EXTABLE_HANDLE(x) #x
+# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
-	" .balign 8\n"						\
+	" .balign 4\n"						\
 	" .long (" #from ") - .\n"				\
 	" .long (" #to ") - .\n"				\
+	" .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n"	\
 	" .popsection\n"
 
-# define _ASM_EXTABLE_EX(from,to)				\
-	" .pushsection \"__ex_table\",\"a\"\n"			\
-	" .balign 8\n"						\
-	" .long (" #from ") - .\n"				\
-	" .long (" #to ") - . + 0x7ffffff0\n"			\
-	" .popsection\n"
+# define _ASM_EXTABLE(from, to)					\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_FAULT(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# define _ASM_EXTABLE_EX(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
+
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 

arch/x86/include/asm/uaccess.h

@@ -90,12 +90,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 	likely(!__range_not_ok(addr, size, user_addr_max()))
 
 /*
- * The exception table consists of pairs of addresses relative to the
- * exception table enty itself: the first is the address of an
- * instruction that is allowed to fault, and the second is the address
- * at which the program should continue.  No registers are modified,
- * so it is entirely up to the continuation code to figure out what to
- * do.
+ * The exception table consists of triples of addresses relative to the
+ * exception table entry itself. The first address is of an instruction
+ * that is allowed to fault, the second is the target at which the program
+ * should continue. The third is a handler function to deal with the fault
+ * caused by the instruction in the first field.
  *
  * All the routines below use bits of fixup code that are out of line
  * with the main instruction path.  This means when everything is well,
@@ -104,13 +103,14 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  */
 
 struct exception_table_entry {
-	int insn, fixup;
+	int insn, fixup, handler;
 };
 /* This is not the generic standard exception_table_entry format */
 #define ARCH_HAS_SORT_EXTABLE
 #define ARCH_HAS_SEARCH_EXTABLE
 
-extern int fixup_exception(struct pt_regs *regs);
+extern int fixup_exception(struct pt_regs *regs, int trapnr);
+extern bool ex_has_fault_handler(unsigned long ip);
 extern int early_fixup_exception(unsigned long *ip);
 
 /*

arch/x86/kernel/kprobes/core.c

@@ -988,7 +988,7 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.
 		 */
-		if (fixup_exception(regs))
+		if (fixup_exception(regs, trapnr))
 			return 1;
 
 		/*

arch/x86/kernel/traps.c

@@ -199,7 +199,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 	}
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs)) {
+		if (!fixup_exception(regs, trapnr)) {
 			tsk->thread.error_code = error_code;
 			tsk->thread.trap_nr = trapnr;
 			die(str, regs, error_code);
@@ -453,7 +453,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 
 	tsk = current;
 	if (!user_mode(regs)) {
-		if (fixup_exception(regs))
+		if (fixup_exception(regs, X86_TRAP_GP))
 			return;
 
 		tsk->thread.error_code = error_code;
@@ -699,7 +699,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	conditional_sti(regs);
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs)) {
+		if (!fixup_exception(regs, trapnr)) {
 			task->thread.error_code = error_code;
 			task->thread.trap_nr = trapnr;
 			die(str, regs, error_code);

arch/x86/mm/extable.c

@@ -3,6 +3,9 @@
 #include <linux/sort.h>
 #include <asm/uaccess.h>
 
+typedef bool (*ex_handler_t)(const struct exception_table_entry *,
+			    struct pt_regs *, int);
+
 static inline unsigned long
 ex_insn_addr(const struct exception_table_entry *x)
 {
@@ -13,11 +16,56 @@ ex_fixup_addr(const struct exception_table_entry *x)
 {
 	return (unsigned long)&x->fixup + x->fixup;
 }
-
-int fixup_exception(struct pt_regs *regs)
+static inline ex_handler_t
+ex_fixup_handler(const struct exception_table_entry *x)
 {
-	const struct exception_table_entry *fixup;
-	unsigned long new_ip;
+	return (ex_handler_t)((unsigned long)&x->handler + x->handler);
+}
+
+bool ex_handler_default(const struct exception_table_entry *fixup,
+		       struct pt_regs *regs, int trapnr)
+{
+	regs->ip = ex_fixup_addr(fixup);
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_default);
+
+bool ex_handler_fault(const struct exception_table_entry *fixup,
+		     struct pt_regs *regs, int trapnr)
+{
+	regs->ip = ex_fixup_addr(fixup);
+	regs->ax = trapnr;
+	return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_fault);
+
+bool ex_handler_ext(const struct exception_table_entry *fixup,
+		   struct pt_regs *regs, int trapnr)
+{
+	/* Special hack for uaccess_err */
+	current_thread_info()->uaccess_err = 1;
+	regs->ip = ex_fixup_addr(fixup);
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_ext);
+
+bool ex_has_fault_handler(unsigned long ip)
+{
+	const struct exception_table_entry *e;
+	ex_handler_t handler;
+
+	e = search_exception_tables(ip);
+	if (!e)
+		return false;
+	handler = ex_fixup_handler(e);
+
+	return handler == ex_handler_fault;
+}
+
+int fixup_exception(struct pt_regs *regs, int trapnr)
+{
+	const struct exception_table_entry *e;
+	ex_handler_t handler;
 
 #ifdef CONFIG_PNPBIOS
 	if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
@@ -33,42 +81,34 @@ int fixup_exception(struct pt_regs *regs)
 	}
 #endif
 
-	fixup = search_exception_tables(regs->ip);
-	if (fixup) {
-		new_ip = ex_fixup_addr(fixup);
+	e = search_exception_tables(regs->ip);
+	if (!e)
+		return 0;
 
-		if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
-			/* Special hack for uaccess_err */
-			current_thread_info()->uaccess_err = 1;
-			new_ip -= 0x7ffffff0;
-		}
-		regs->ip = new_ip;
-		return 1;
-	}
-
-	return 0;
+	handler = ex_fixup_handler(e);
+	return handler(e, regs, trapnr);
 }
 
 /* Restricted version used during very early boot */
 int __init early_fixup_exception(unsigned long *ip)
 {
-	const struct exception_table_entry *fixup;
+	const struct exception_table_entry *e;
 	unsigned long new_ip;
+	ex_handler_t handler;
 
-	fixup = search_exception_tables(*ip);
-	if (fixup) {
-		new_ip = ex_fixup_addr(fixup);
+	e = search_exception_tables(*ip);
+	if (!e)
+		return 0;
 
-		if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
-			/* uaccess handling not supported during early boot */
-			return 0;
-		}
+	new_ip  = ex_fixup_addr(e);
+	handler = ex_fixup_handler(e);
 
-		*ip = new_ip;
-		return 1;
-	}
+	/* special handling not supported during early boot */
+	if (handler != ex_handler_default)
+		return 0;
 
-	return 0;
+	*ip = new_ip;
+	return 1;
 }
 
 /*
@@ -133,6 +173,8 @@ void sort_extable(struct exception_table_entry *start,
 		i += 4;
 		p->fixup += i;
 		i += 4;
+		p->handler += i;
+		i += 4;
 	}
 
 	sort(start, finish - start, sizeof(struct exception_table_entry),
@@ -145,6 +187,8 @@ void sort_extable(struct exception_table_entry *start,
 		i += 4;
 		p->fixup -= i;
 		i += 4;
+		p->handler -= i;
+		i += 4;
 	}
 }
 

arch/x86/mm/fault.c

@@ -656,7 +656,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	int sig;
 
 	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs)) {
+	if (fixup_exception(regs, X86_TRAP_PF)) {
 		/*
 		 * Any interrupt that takes a fault gets the fixup. This makes
 		 * the below recursive fault logic only apply to a faults from

scripts/sortextable.c

@@ -209,6 +209,35 @@ static int compare_relative_table(const void *a, const void *b)
 	return 0;
 }
 
+static void x86_sort_relative_table(char *extab_image, int image_size)
+{
+	int i;
+
+	i = 0;
+	while (i < image_size) {
+		uint32_t *loc = (uint32_t *)(extab_image + i);
+
+		w(r(loc) + i, loc);
+		w(r(loc + 1) + i + 4, loc + 1);
+		w(r(loc + 2) + i + 8, loc + 2);
+
+		i += sizeof(uint32_t) * 3;
+	}
+
+	qsort(extab_image, image_size / 12, 12, compare_relative_table);
+
+	i = 0;
+	while (i < image_size) {
+		uint32_t *loc = (uint32_t *)(extab_image + i);
+
+		w(r(loc) - i, loc);
+		w(r(loc + 1) - (i + 4), loc + 1);
+		w(r(loc + 2) - (i + 8), loc + 2);
+
+		i += sizeof(uint32_t) * 3;
+	}
+}
+
 static void sort_relative_table(char *extab_image, int image_size)
 {
 	int i;
@@ -281,6 +310,9 @@ do_file(char const *const fname)
 		break;
 	case EM_386:
 	case EM_X86_64:
+		custom_sort = x86_sort_relative_table;
+		break;
+
 	case EM_S390:
 		custom_sort = sort_relative_table;
 		break;