From 56fb4df6da76c35dca22036174e2d1edef83ff1f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 26 Feb 2006 23:24:22 -0800 Subject: [SPARC64]: Elminate all usage of hard-coded trap globals. UltraSPARC has special sets of global registers which are switched to for certain trap types. There is one set for MMU related traps, one set of Interrupt Vector processing, and another set (called the Alternate globals) for all other trap types. For what seems like forever we've hard coded the values in some of these trap registers. Some examples include: 1) Interrupt Vector global %g6 holds current processors interrupt work struct where received interrupts are managed for IRQ handler dispatch. 2) MMU global %g7 holds the base of the page tables of the currently active address space. 3) Alternate global %g6 held the current_thread_info() value. Such hardcoding has resulted in some serious issues in many areas. There are some code sequences where having another register available would help clean up the implementation. Taking traps such as cross-calls from the OBP firmware requires some trick code sequences wherein we have to save away and restore all of the special sets of global registers when we enter/exit OBP. We were also using the IMMU TSB register on SMP to hold the per-cpu area base address, which doesn't work any longer now that we actually use the TSB facility of the cpu. The implementation is pretty straight forward. One tricky bit is getting the current processor ID as that is different on different cpu variants. We use a stub with a fancy calling convention which we patch at boot time. The calling convention is that the stub is branched to and the (PC - 4) to return to is in register %g1. The cpu number is left in %g6. This stub can be invoked by using the __GET_CPUID macro. We use an array of per-cpu trap state to store the current thread and physical address of the current address space's page tables. The TRAP_LOAD_THREAD_REG loads %g6 with the current thread from this table, it uses __GET_CPUID and also clobbers %g1. TRAP_LOAD_IRQ_WORK is used by the interrupt vector processing to load the current processor's IRQ software state into %g6. It also uses __GET_CPUID and clobbers %g1. Finally, TRAP_LOAD_PGD_PHYS loads the physical address base of the current address space's page tables into %g7, it clobbers %g1 and uses __GET_CPUID. Many refinements are possible, as well as some tuning, with this stuff in place. Signed-off-by: David S. Miller --- include/asm-sparc64/system.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/asm-sparc64/system.h') diff --git a/include/asm-sparc64/system.h b/include/asm-sparc64/system.h index af254e58183..26c0807af3e 100644 --- a/include/asm-sparc64/system.h +++ b/include/asm-sparc64/system.h @@ -209,6 +209,8 @@ do { if (test_thread_flag(TIF_PERFCTR)) { \ /* so that ASI is only written if it changes, think again. */ \ __asm__ __volatile__("wr %%g0, %0, %%asi" \ : : "r" (__thread_flag_byte_ptr(task_thread_info(next))[TI_FLAG_BYTE_CURRENT_DS]));\ + trap_block[current_thread_info()->cpu].thread = \ + task_thread_info(next); \ __asm__ __volatile__( \ "mov %%g4, %%g7\n\t" \ "wrpr %%g0, 0x95, %%pstate\n\t" \ -- cgit v1.2.3 From 314981ac7177a933319e3c071a5cf0a579205e6e Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 5 Feb 2006 21:59:03 -0800 Subject: [SPARC64]: Kill all %pstate changes in context switch code. They are totally unnecessary because: 1) Interrupts are already disabled when switch_to() runs. 2) We don't use hard-coded alternate globals any longer. This found a case in rtrap, which still assumed alternate global %g6 was current_thread_info(), and that is fixed by this changeset as well. Signed-off-by: David S. Miller --- arch/sparc64/kernel/rtrap.S | 5 ++++- include/asm-sparc64/system.h | 5 ----- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/asm-sparc64/system.h') diff --git a/arch/sparc64/kernel/rtrap.S b/arch/sparc64/kernel/rtrap.S index e6130956307..a2fa277da62 100644 --- a/arch/sparc64/kernel/rtrap.S +++ b/arch/sparc64/kernel/rtrap.S @@ -224,7 +224,8 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 ldx [%sp + PTREGS_OFF + PT_V9_G4], %g4 ldx [%sp + PTREGS_OFF + PT_V9_G5], %g5 brz,pt %l3, 1f - nop + mov %g6, %l2 + /* Must do this before thread reg is clobbered below. */ LOAD_PER_CPU_BASE(%g5, %g6, %i0, %i1, %i2) 1: @@ -238,6 +239,8 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 SET_GL(1) .previous + mov %l2, %g6 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 diff --git a/include/asm-sparc64/system.h b/include/asm-sparc64/system.h index 26c0807af3e..a18ec87a52c 100644 --- a/include/asm-sparc64/system.h +++ b/include/asm-sparc64/system.h @@ -213,7 +213,6 @@ do { if (test_thread_flag(TIF_PERFCTR)) { \ task_thread_info(next); \ __asm__ __volatile__( \ "mov %%g4, %%g7\n\t" \ - "wrpr %%g0, 0x95, %%pstate\n\t" \ "stx %%i6, [%%sp + 2047 + 0x70]\n\t" \ "stx %%i7, [%%sp + 2047 + 0x78]\n\t" \ "rdpr %%wstate, %%o5\n\t" \ @@ -227,14 +226,10 @@ do { if (test_thread_flag(TIF_PERFCTR)) { \ "ldx [%%g6 + %3], %%o6\n\t" \ "ldub [%%g6 + %2], %%o5\n\t" \ "ldub [%%g6 + %4], %%o7\n\t" \ - "mov %%g6, %%l2\n\t" \ "wrpr %%o5, 0x0, %%wstate\n\t" \ "ldx [%%sp + 2047 + 0x70], %%i6\n\t" \ "ldx [%%sp + 2047 + 0x78], %%i7\n\t" \ - "wrpr %%g0, 0x94, %%pstate\n\t" \ - "mov %%l2, %%g6\n\t" \ "ldx [%%g6 + %6], %%g4\n\t" \ - "wrpr %%g0, 0x96, %%pstate\n\t" \ "brz,pt %%o7, 1f\n\t" \ " mov %%g7, %0\n\t" \ "b,a ret_from_syscall\n\t" \ -- cgit v1.2.3