Revamp of the syscall path, exception and context handling. The

prime objectives are:
o  Implement a syscall path based on the epc inststruction (see
   sys/ia64/ia64/syscall.s).
o  Revisit the places were we need to save and restore registers
   and define those contexts in terms of the register sets (see
   sys/ia64/include/_regset.h).

Secundairy objectives:
o  Remove the requirement to use contigmalloc for kernel stacks.
o  Better handling of the high FP registers for SMP systems.
o  Switch to the new cpu_switch() and cpu_throw() semantics.
o  Add a good unwinder to reconstruct contexts for the rare
   cases we need to (see sys/contrib/ia64/libuwx)

Many files are affected by this change. Functionally it boils
down to:
o  The EPC syscall doesn't preserve registers it does not need
   to preserve and places the arguments differently on the stack.
   This affects libc and truss.
o  The address of the kernel page directory (kptdir) had to
   be unstaticized for use by the nested TLB fault handler.
   The name has been changed to ia64_kptdir to avoid conflicts.
   The renaming affects libkvm.
o  The trapframe only contains the special registers and the
   scratch registers. For syscalls using the EPC syscall path
   no scratch registers are saved. This affects all places where
   the trapframe is accessed. Most notably the unaligned access
   handler, the signal delivery code and the debugger.
o  Context switching only partly saves the special registers
   and the preserved registers. This affects cpu_switch() and
   triggered the move to the new semantics, which additionally
   affects cpu_throw().
o  The high FP registers are either in the PCB or on some
   CPU. context switching for them is done lazily. This affects
   trap().
o  The mcontext has room for all registers, but not all of them
   have to be defined in all cases. This mostly affects signal
   delivery code now. The *context syscalls are as of yet still
   unimplemented.

Many details went into the removal of the requirement to use
contigmalloc for kernel stacks. The details are mostly CPU
specific and limited to exception_save() and exception_restore().
The few places where we create, destroy or switch stacks were
mostly simplified by not having to construct physical addresses
and additionally saving the virtual addresses for later use.

Besides more efficient context saving and restoring, which of
course yields a noticable speedup, this also fixes the dreaded
SMP bootup problem as a side-effect. The details of which are
still not fully understood.

This change includes all the necessary backward compatibility
code to have it handle older userland binaries that use the
break instruction for syscalls. Support for break-based syscalls
has been pessimized in favor of a clean implementation. Due to
the overall better performance of the kernel, this will still
be notived as an improvement if it's noticed at all.

Approved by: re@ (jhb)

1 files changed, 23 insertions, 27 deletions

diff --git a/sys/ia64/include/cpu.h b/sys/ia64/include/cpu.h
index 324b035..c2bd78c 100644
--- a/sys/ia64/include/cpu.h
+++ b/sys/ia64/include/cpu.h
@@ -46,28 +46,25 @@
 #ifndef _MACHINE_CPU_H_
 #define _MACHINE_CPU_H_
 
-/*
- * Exported definitions unique to Alpha cpu support.
- */
-
 #include <machine/frame.h>
 
-#define	cpu_getstack(td)	((td)->td_frame->tf_r[FRAME_SP])
-
 /*
- * Arguments to hardclock and gatherstats encapsulate the previous
- * machine state in an opaque clockframe.  One the Alpha, we use
- * what we push on an interrupt (a trapframe).
+ * Arguments to hardclock and gatherstats encapsulate the previous machine
+ * state in an opaque clockframe.
  */
 struct clockframe {
-	struct trapframe	cf_tf;
+	struct trapframe cf_tf;
 };
-#define	TRAPF_USERMODE(framep)						\
-	(((framep)->tf_cr_ipsr & IA64_PSR_CPL) == IA64_PSR_CPL_USER)
-#define	TRAPF_PC(framep)	((framep)->tf_cr_iip)
+#define	CLKF_PC(cf)		((cf)->cf_tf.tf_special.iip)
+#define	CLKF_USERMODE(cf)	((CLKF_PC(cf) >> 61) < 5)
 
-#define	CLKF_USERMODE(framep)	TRAPF_USERMODE(&(framep)->cf_tf)
-#define	CLKF_PC(framep)		TRAPF_PC(&(framep)->cf_tf)
+/* Used by signaling code. */
+#define	cpu_getstack(td)	((td)->td_frame->tf_special.sp)
+
+/* XXX */
+#define	TRAPF_PC(tf)		((tf)->tf_special.iip)
+#define	TRAPF_USERMODE(framep)						\
+	(((framep)->tf_special.psr & IA64_PSR_CPL) == IA64_PSR_CPL_USER)
 
 /*
  * CTL_MACHDEP definitions.
@@ -107,34 +104,33 @@ struct trapframe;
 extern struct rpb *hwrpb;
 extern volatile int mc_expected, mc_received;
 
-int	badaddr	(void *, size_t);
+int	badaddr(void *, size_t);
 int	badaddr_read(void *, size_t, void *);
 u_int64_t console_restart(u_int64_t, u_int64_t, u_int64_t);
-void	do_sir(void);
+int	do_ast(struct trapframe *);
 void	dumpconf(void);
-void	exception_restore(void);				/* MAGIC */
 void	frametoreg(struct trapframe *, struct reg *);
 long	fswintrberr(void);				/* MAGIC */
-int	ia64_pa_access(u_long);
+int	ia64_highfp_drop(struct thread *);
+int	ia64_highfp_load(struct thread *);
+int	ia64_highfp_save(struct thread *);
 void	ia64_init(u_int64_t, u_int64_t);
-void	ia64_fpstate_check(struct thread *p);
-void	ia64_fpstate_save(struct thread *p, int write);
-void	ia64_fpstate_drop(struct thread *p);
-void	ia64_fpstate_switch(struct thread *p);
+int	ia64_pa_access(u_long);
 void	init_prom_interface(struct rpb*);
 void	interrupt(u_int64_t, struct trapframe *);
-void	machine_check
-	(unsigned long, struct trapframe *, unsigned long, unsigned long);
+void	machine_check(unsigned long, struct trapframe *, unsigned long,
+    unsigned long);
 u_int64_t hwrpb_checksum(void);
 void	hwrpb_restart_setup(void);
 void	regdump(struct trapframe *);
 void	regtoframe(struct reg *, struct trapframe *);
 void	set_iointr(void (*)(void *, unsigned long));
 void	fork_trampoline(void);				/* MAGIC */
-void	syscall(int, u_int64_t *, struct trapframe *);
-void	trap(int vector, int imm, struct trapframe *framep);
+int	syscall(struct trapframe *);
+void	trap(int vector, struct trapframe *framep);
 void	ia64_probe_sapics(void);
 int	ia64_count_cpus(void);
+void	map_gateway_page(void);
 void	map_pal_code(void);
 void	map_port_space(void);
 void	cpu_mp_add(uint, uint, uint);