summaryrefslogtreecommitdiff
path: root/arch/ppc/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/ppc/kernel')
-rw-r--r--arch/ppc/kernel/Makefile33
-rw-r--r--arch/ppc/kernel/align.c398
-rw-r--r--arch/ppc/kernel/asm-offsets.c146
-rw-r--r--arch/ppc/kernel/bitops.c126
-rw-r--r--arch/ppc/kernel/cpu_setup_6xx.S440
-rw-r--r--arch/ppc/kernel/cpu_setup_power4.S201
-rw-r--r--arch/ppc/kernel/cputable.c922
-rw-r--r--arch/ppc/kernel/dma-mapping.c447
-rw-r--r--arch/ppc/kernel/entry.S969
-rw-r--r--arch/ppc/kernel/find_name.c48
-rw-r--r--arch/ppc/kernel/head.S1710
-rw-r--r--arch/ppc/kernel/head_44x.S753
-rw-r--r--arch/ppc/kernel/head_4xx.S1010
-rw-r--r--arch/ppc/kernel/head_8xx.S862
-rw-r--r--arch/ppc/kernel/head_booke.h340
-rw-r--r--arch/ppc/kernel/head_fsl_booke.S952
-rw-r--r--arch/ppc/kernel/idle.c100
-rw-r--r--arch/ppc/kernel/idle_6xx.S233
-rw-r--r--arch/ppc/kernel/idle_power4.S91
-rw-r--r--arch/ppc/kernel/irq.c164
-rw-r--r--arch/ppc/kernel/l2cr.S442
-rw-r--r--arch/ppc/kernel/misc.S1453
-rw-r--r--arch/ppc/kernel/module.c320
-rw-r--r--arch/ppc/kernel/pci.c1849
-rw-r--r--arch/ppc/kernel/perfmon.c93
-rw-r--r--arch/ppc/kernel/perfmon_fsl_booke.c222
-rw-r--r--arch/ppc/kernel/ppc-stub.c867
-rw-r--r--arch/ppc/kernel/ppc_htab.c467
-rw-r--r--arch/ppc/kernel/ppc_ksyms.c350
-rw-r--r--arch/ppc/kernel/process.c781
-rw-r--r--arch/ppc/kernel/ptrace.c474
-rw-r--r--arch/ppc/kernel/semaphore.c131
-rw-r--r--arch/ppc/kernel/setup.c778
-rw-r--r--arch/ppc/kernel/signal.c775
-rw-r--r--arch/ppc/kernel/smp-tbsync.c181
-rw-r--r--arch/ppc/kernel/smp.c399
-rw-r--r--arch/ppc/kernel/softemu8xx.c147
-rw-r--r--arch/ppc/kernel/swsusp.S349
-rw-r--r--arch/ppc/kernel/syscalls.c272
-rw-r--r--arch/ppc/kernel/temp.c272
-rw-r--r--arch/ppc/kernel/time.c447
-rw-r--r--arch/ppc/kernel/traps.c886
-rw-r--r--arch/ppc/kernel/vecemu.c345
-rw-r--r--arch/ppc/kernel/vector.S217
-rw-r--r--arch/ppc/kernel/vmlinux.lds.S192
45 files changed, 22654 insertions, 0 deletions
diff --git a/arch/ppc/kernel/Makefile b/arch/ppc/kernel/Makefile
new file mode 100644
index 000000000000..86bc878cb3ee
--- /dev/null
+++ b/arch/ppc/kernel/Makefile
@@ -0,0 +1,33 @@
+#
+# Makefile for the linux kernel.
+#
+
+extra-$(CONFIG_PPC_STD_MMU) := head.o
+extra-$(CONFIG_40x) := head_4xx.o
+extra-$(CONFIG_44x) := head_44x.o
+extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o
+extra-$(CONFIG_8xx) := head_8xx.o
+extra-$(CONFIG_6xx) += idle_6xx.o
+extra-$(CONFIG_POWER4) += idle_power4.o
+extra-y += vmlinux.lds
+
+obj-y := entry.o traps.o irq.o idle.o time.o misc.o \
+ process.o signal.o ptrace.o align.o \
+ semaphore.o syscalls.o setup.o \
+ cputable.o ppc_htab.o perfmon.o
+obj-$(CONFIG_6xx) += l2cr.o cpu_setup_6xx.o
+obj-$(CONFIG_SOFTWARE_SUSPEND) += swsusp.o
+obj-$(CONFIG_POWER4) += cpu_setup_power4.o
+obj-$(CONFIG_MODULES) += module.o ppc_ksyms.o
+obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-mapping.o
+obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_KGDB) += ppc-stub.o
+obj-$(CONFIG_SMP) += smp.o smp-tbsync.o
+obj-$(CONFIG_TAU) += temp.o
+obj-$(CONFIG_ALTIVEC) += vecemu.o vector.o
+obj-$(CONFIG_FSL_BOOKE) += perfmon_fsl_booke.o
+
+ifndef CONFIG_MATH_EMULATION
+obj-$(CONFIG_8xx) += softemu8xx.o
+endif
+
diff --git a/arch/ppc/kernel/align.c b/arch/ppc/kernel/align.c
new file mode 100644
index 000000000000..79c929475037
--- /dev/null
+++ b/arch/ppc/kernel/align.c
@@ -0,0 +1,398 @@
+/*
+ * align.c - handle alignment exceptions for the Power PC.
+ *
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ */
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/cache.h>
+
+struct aligninfo {
+ unsigned char len;
+ unsigned char flags;
+};
+
+#if defined(CONFIG_4xx) || defined(CONFIG_POWER4) || defined(CONFIG_BOOKE)
+#define OPCD(inst) (((inst) & 0xFC000000) >> 26)
+#define RS(inst) (((inst) & 0x03E00000) >> 21)
+#define RA(inst) (((inst) & 0x001F0000) >> 16)
+#define IS_XFORM(code) ((code) == 31)
+#endif
+
+#define INVALID { 0, 0 }
+
+#define LD 1 /* load */
+#define ST 2 /* store */
+#define SE 4 /* sign-extend value */
+#define F 8 /* to/from fp regs */
+#define U 0x10 /* update index register */
+#define M 0x20 /* multiple load/store */
+#define S 0x40 /* single-precision fp, or byte-swap value */
+#define SX 0x40 /* byte count in XER */
+#define HARD 0x80 /* string, stwcx. */
+
+#define DCBZ 0x5f /* 8xx/82xx dcbz faults when cache not enabled */
+
+/*
+ * The PowerPC stores certain bits of the instruction that caused the
+ * alignment exception in the DSISR register. This array maps those
+ * bits to information about the operand length and what the
+ * instruction would do.
+ */
+static struct aligninfo aligninfo[128] = {
+ { 4, LD }, /* 00 0 0000: lwz / lwarx */
+ INVALID, /* 00 0 0001 */
+ { 4, ST }, /* 00 0 0010: stw */
+ INVALID, /* 00 0 0011 */
+ { 2, LD }, /* 00 0 0100: lhz */
+ { 2, LD+SE }, /* 00 0 0101: lha */
+ { 2, ST }, /* 00 0 0110: sth */
+ { 4, LD+M }, /* 00 0 0111: lmw */
+ { 4, LD+F+S }, /* 00 0 1000: lfs */
+ { 8, LD+F }, /* 00 0 1001: lfd */
+ { 4, ST+F+S }, /* 00 0 1010: stfs */
+ { 8, ST+F }, /* 00 0 1011: stfd */
+ INVALID, /* 00 0 1100 */
+ INVALID, /* 00 0 1101: ld/ldu/lwa */
+ INVALID, /* 00 0 1110 */
+ INVALID, /* 00 0 1111: std/stdu */
+ { 4, LD+U }, /* 00 1 0000: lwzu */
+ INVALID, /* 00 1 0001 */
+ { 4, ST+U }, /* 00 1 0010: stwu */
+ INVALID, /* 00 1 0011 */
+ { 2, LD+U }, /* 00 1 0100: lhzu */
+ { 2, LD+SE+U }, /* 00 1 0101: lhau */
+ { 2, ST+U }, /* 00 1 0110: sthu */
+ { 4, ST+M }, /* 00 1 0111: stmw */
+ { 4, LD+F+S+U }, /* 00 1 1000: lfsu */
+ { 8, LD+F+U }, /* 00 1 1001: lfdu */
+ { 4, ST+F+S+U }, /* 00 1 1010: stfsu */
+ { 8, ST+F+U }, /* 00 1 1011: stfdu */
+ INVALID, /* 00 1 1100 */
+ INVALID, /* 00 1 1101 */
+ INVALID, /* 00 1 1110 */
+ INVALID, /* 00 1 1111 */
+ INVALID, /* 01 0 0000: ldx */
+ INVALID, /* 01 0 0001 */
+ INVALID, /* 01 0 0010: stdx */
+ INVALID, /* 01 0 0011 */
+ INVALID, /* 01 0 0100 */
+ INVALID, /* 01 0 0101: lwax */
+ INVALID, /* 01 0 0110 */
+ INVALID, /* 01 0 0111 */
+ { 4, LD+M+HARD+SX }, /* 01 0 1000: lswx */
+ { 4, LD+M+HARD }, /* 01 0 1001: lswi */
+ { 4, ST+M+HARD+SX }, /* 01 0 1010: stswx */
+ { 4, ST+M+HARD }, /* 01 0 1011: stswi */
+ INVALID, /* 01 0 1100 */
+ INVALID, /* 01 0 1101 */
+ INVALID, /* 01 0 1110 */
+ INVALID, /* 01 0 1111 */
+ INVALID, /* 01 1 0000: ldux */
+ INVALID, /* 01 1 0001 */
+ INVALID, /* 01 1 0010: stdux */
+ INVALID, /* 01 1 0011 */
+ INVALID, /* 01 1 0100 */
+ INVALID, /* 01 1 0101: lwaux */
+ INVALID, /* 01 1 0110 */
+ INVALID, /* 01 1 0111 */
+ INVALID, /* 01 1 1000 */
+ INVALID, /* 01 1 1001 */
+ INVALID, /* 01 1 1010 */
+ INVALID, /* 01 1 1011 */
+ INVALID, /* 01 1 1100 */
+ INVALID, /* 01 1 1101 */
+ INVALID, /* 01 1 1110 */
+ INVALID, /* 01 1 1111 */
+ INVALID, /* 10 0 0000 */
+ INVALID, /* 10 0 0001 */
+ { 0, ST+HARD }, /* 10 0 0010: stwcx. */
+ INVALID, /* 10 0 0011 */
+ INVALID, /* 10 0 0100 */
+ INVALID, /* 10 0 0101 */
+ INVALID, /* 10 0 0110 */
+ INVALID, /* 10 0 0111 */
+ { 4, LD+S }, /* 10 0 1000: lwbrx */
+ INVALID, /* 10 0 1001 */
+ { 4, ST+S }, /* 10 0 1010: stwbrx */
+ INVALID, /* 10 0 1011 */
+ { 2, LD+S }, /* 10 0 1100: lhbrx */
+ INVALID, /* 10 0 1101 */
+ { 2, ST+S }, /* 10 0 1110: sthbrx */
+ INVALID, /* 10 0 1111 */
+ INVALID, /* 10 1 0000 */
+ INVALID, /* 10 1 0001 */
+ INVALID, /* 10 1 0010 */
+ INVALID, /* 10 1 0011 */
+ INVALID, /* 10 1 0100 */
+ INVALID, /* 10 1 0101 */
+ INVALID, /* 10 1 0110 */
+ INVALID, /* 10 1 0111 */
+ INVALID, /* 10 1 1000 */
+ INVALID, /* 10 1 1001 */
+ INVALID, /* 10 1 1010 */
+ INVALID, /* 10 1 1011 */
+ INVALID, /* 10 1 1100 */
+ INVALID, /* 10 1 1101 */
+ INVALID, /* 10 1 1110 */
+ { 0, ST+HARD }, /* 10 1 1111: dcbz */
+ { 4, LD }, /* 11 0 0000: lwzx */
+ INVALID, /* 11 0 0001 */
+ { 4, ST }, /* 11 0 0010: stwx */
+ INVALID, /* 11 0 0011 */
+ { 2, LD }, /* 11 0 0100: lhzx */
+ { 2, LD+SE }, /* 11 0 0101: lhax */
+ { 2, ST }, /* 11 0 0110: sthx */
+ INVALID, /* 11 0 0111 */
+ { 4, LD+F+S }, /* 11 0 1000: lfsx */
+ { 8, LD+F }, /* 11 0 1001: lfdx */
+ { 4, ST+F+S }, /* 11 0 1010: stfsx */
+ { 8, ST+F }, /* 11 0 1011: stfdx */
+ INVALID, /* 11 0 1100 */
+ INVALID, /* 11 0 1101: lmd */
+ INVALID, /* 11 0 1110 */
+ INVALID, /* 11 0 1111: stmd */
+ { 4, LD+U }, /* 11 1 0000: lwzux */
+ INVALID, /* 11 1 0001 */
+ { 4, ST+U }, /* 11 1 0010: stwux */
+ INVALID, /* 11 1 0011 */
+ { 2, LD+U }, /* 11 1 0100: lhzux */
+ { 2, LD+SE+U }, /* 11 1 0101: lhaux */
+ { 2, ST+U }, /* 11 1 0110: sthux */
+ INVALID, /* 11 1 0111 */
+ { 4, LD+F+S+U }, /* 11 1 1000: lfsux */
+ { 8, LD+F+U }, /* 11 1 1001: lfdux */
+ { 4, ST+F+S+U }, /* 11 1 1010: stfsux */
+ { 8, ST+F+U }, /* 11 1 1011: stfdux */
+ INVALID, /* 11 1 1100 */
+ INVALID, /* 11 1 1101 */
+ INVALID, /* 11 1 1110 */
+ INVALID, /* 11 1 1111 */
+};
+
+#define SWAP(a, b) (t = (a), (a) = (b), (b) = t)
+
+int
+fix_alignment(struct pt_regs *regs)
+{
+ int instr, nb, flags;
+#if defined(CONFIG_4xx) || defined(CONFIG_POWER4) || defined(CONFIG_BOOKE)
+ int opcode, f1, f2, f3;
+#endif
+ int i, t;
+ int reg, areg;
+ int offset, nb0;
+ unsigned char __user *addr;
+ unsigned char *rptr;
+ union {
+ long l;
+ float f;
+ double d;
+ unsigned char v[8];
+ } data;
+
+ CHECK_FULL_REGS(regs);
+
+#if defined(CONFIG_4xx) || defined(CONFIG_POWER4) || defined(CONFIG_BOOKE)
+ /* The 4xx-family & Book-E processors have no DSISR register,
+ * so we emulate it.
+ * The POWER4 has a DSISR register but doesn't set it on
+ * an alignment fault. -- paulus
+ */
+
+ if (__get_user(instr, (unsigned int __user *) regs->nip))
+ return 0;
+ opcode = OPCD(instr);
+ reg = RS(instr);
+ areg = RA(instr);
+
+ if (!IS_XFORM(opcode)) {
+ f1 = 0;
+ f2 = (instr & 0x04000000) >> 26;
+ f3 = (instr & 0x78000000) >> 27;
+ } else {
+ f1 = (instr & 0x00000006) >> 1;
+ f2 = (instr & 0x00000040) >> 6;
+ f3 = (instr & 0x00000780) >> 7;
+ }
+
+ instr = ((f1 << 5) | (f2 << 4) | f3);
+#else
+ reg = (regs->dsisr >> 5) & 0x1f; /* source/dest register */
+ areg = regs->dsisr & 0x1f; /* register to update */
+ instr = (regs->dsisr >> 10) & 0x7f;
+#endif
+
+ nb = aligninfo[instr].len;
+ if (nb == 0) {
+ long __user *p;
+ int i;
+
+ if (instr != DCBZ)
+ return 0; /* too hard or invalid instruction */
+ /*
+ * The dcbz (data cache block zero) instruction
+ * gives an alignment fault if used on non-cacheable
+ * memory. We handle the fault mainly for the
+ * case when we are running with the cache disabled
+ * for debugging.
+ */
+ p = (long __user *) (regs->dar & -L1_CACHE_BYTES);
+ if (user_mode(regs)
+ && !access_ok(VERIFY_WRITE, p, L1_CACHE_BYTES))
+ return -EFAULT;
+ for (i = 0; i < L1_CACHE_BYTES / sizeof(long); ++i)
+ if (__put_user(0, p+i))
+ return -EFAULT;
+ return 1;
+ }
+
+ flags = aligninfo[instr].flags;
+ if ((flags & (LD|ST)) == 0)
+ return 0;
+
+ /* For the 4xx-family & Book-E processors, the 'dar' field of the
+ * pt_regs structure is overloaded and is really from the DEAR.
+ */
+
+ addr = (unsigned char __user *)regs->dar;
+
+ if (flags & M) {
+ /* lmw, stmw, lswi/x, stswi/x */
+ nb0 = 0;
+ if (flags & HARD) {
+ if (flags & SX) {
+ nb = regs->xer & 127;
+ if (nb == 0)
+ return 1;
+ } else {
+ if (__get_user(instr,
+ (unsigned int __user *)regs->nip))
+ return 0;
+ nb = (instr >> 11) & 0x1f;
+ if (nb == 0)
+ nb = 32;
+ }
+ if (nb + reg * 4 > 128) {
+ nb0 = nb + reg * 4 - 128;
+ nb = 128 - reg * 4;
+ }
+ } else {
+ /* lwm, stmw */
+ nb = (32 - reg) * 4;
+ }
+ rptr = (unsigned char *) &regs->gpr[reg];
+ if (flags & LD) {
+ for (i = 0; i < nb; ++i)
+ if (__get_user(rptr[i], addr+i))
+ return -EFAULT;
+ if (nb0 > 0) {
+ rptr = (unsigned char *) &regs->gpr[0];
+ addr += nb;
+ for (i = 0; i < nb0; ++i)
+ if (__get_user(rptr[i], addr+i))
+ return -EFAULT;
+ }
+ for (; (i & 3) != 0; ++i)
+ rptr[i] = 0;
+ } else {
+ for (i = 0; i < nb; ++i)
+ if (__put_user(rptr[i], addr+i))
+ return -EFAULT;
+ if (nb0 > 0) {
+ rptr = (unsigned char *) &regs->gpr[0];
+ addr += nb;
+ for (i = 0; i < nb0; ++i)
+ if (__put_user(rptr[i], addr+i))
+ return -EFAULT;
+ }
+ }
+ return 1;
+ }
+
+ offset = 0;
+ if (nb < 4) {
+ /* read/write the least significant bits */
+ data.l = 0;
+ offset = 4 - nb;
+ }
+
+ /* Verify the address of the operand */
+ if (user_mode(regs)) {
+ if (!access_ok((flags & ST? VERIFY_WRITE: VERIFY_READ), addr, nb))
+ return -EFAULT; /* bad address */
+ }
+
+ if (flags & F) {
+ preempt_disable();
+ if (regs->msr & MSR_FP)
+ giveup_fpu(current);
+ preempt_enable();
+ }
+
+ /* If we read the operand, copy it in, else get register values */
+ if (flags & LD) {
+ for (i = 0; i < nb; ++i)
+ if (__get_user(data.v[offset+i], addr+i))
+ return -EFAULT;
+ } else if (flags & F) {
+ data.d = current->thread.fpr[reg];
+ } else {
+ data.l = regs->gpr[reg];
+ }
+
+ switch (flags & ~U) {
+ case LD+SE: /* sign extend */
+ if (data.v[2] >= 0x80)
+ data.v[0] = data.v[1] = -1;
+ break;
+
+ case LD+S: /* byte-swap */
+ case ST+S:
+ if (nb == 2) {
+ SWAP(data.v[2], data.v[3]);
+ } else {
+ SWAP(data.v[0], data.v[3]);
+ SWAP(data.v[1], data.v[2]);
+ }
+ break;
+
+ /* Single-precision FP load and store require conversions... */
+ case LD+F+S:
+ preempt_disable();
+ enable_kernel_fp();
+ cvt_fd(&data.f, &data.d, &current->thread.fpscr);
+ preempt_enable();
+ break;
+ case ST+F+S:
+ preempt_disable();
+ enable_kernel_fp();
+ cvt_df(&data.d, &data.f, &current->thread.fpscr);
+ preempt_enable();
+ break;
+ }
+
+ if (flags & ST) {
+ for (i = 0; i < nb; ++i)
+ if (__put_user(data.v[offset+i], addr+i))
+ return -EFAULT;
+ } else if (flags & F) {
+ current->thread.fpr[reg] = data.d;
+ } else {
+ regs->gpr[reg] = data.l;
+ }
+
+ if (flags & U)
+ regs->gpr[areg] = regs->dar;
+
+ return 1;
+}
diff --git a/arch/ppc/kernel/asm-offsets.c b/arch/ppc/kernel/asm-offsets.c
new file mode 100644
index 000000000000..d9ad1d776d0e
--- /dev/null
+++ b/arch/ppc/kernel/asm-offsets.c
@@ -0,0 +1,146 @@
+/*
+ * This program is used to generate definitions needed by
+ * assembly language modules.
+ *
+ * We use the technique used in the OSF Mach kernel code:
+ * generate asm statements containing #defines,
+ * compile this file to assembler, and then extract the
+ * #defines from the assembly-language output.
+ */
+
+#include <linux/config.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/suspend.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <asm/io.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+
+#define DEFINE(sym, val) \
+ asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+
+#define BLANK() asm volatile("\n->" : : )
+
+int
+main(void)
+{
+ DEFINE(THREAD, offsetof(struct task_struct, thread));
+ DEFINE(THREAD_INFO, offsetof(struct task_struct, thread_info));
+ DEFINE(MM, offsetof(struct task_struct, mm));
+ DEFINE(PTRACE, offsetof(struct task_struct, ptrace));
+ DEFINE(KSP, offsetof(struct thread_struct, ksp));
+ DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));
+ DEFINE(LAST_SYSCALL, offsetof(struct thread_struct, last_syscall));
+ DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
+ DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
+ DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
+ DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr));
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
+ DEFINE(PT_PTRACED, PT_PTRACED);
+#endif
+#ifdef CONFIG_ALTIVEC
+ DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0]));
+ DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave));
+ DEFINE(THREAD_VSCR, offsetof(struct thread_struct, vscr));
+ DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr));
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ DEFINE(THREAD_EVR0, offsetof(struct thread_struct, evr[0]));
+ DEFINE(THREAD_ACC, offsetof(struct thread_struct, acc));
+ DEFINE(THREAD_SPEFSCR, offsetof(struct thread_struct, spefscr));
+ DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
+#endif /* CONFIG_SPE */
+ /* Interrupt register frame */
+ DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD);
+ DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
+ /* in fact we only use gpr0 - gpr9 and gpr20 - gpr23 */
+ DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0]));
+ DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1]));
+ DEFINE(GPR2, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[2]));
+ DEFINE(GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[3]));
+ DEFINE(GPR4, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[4]));
+ DEFINE(GPR5, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[5]));
+ DEFINE(GPR6, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[6]));
+ DEFINE(GPR7, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[7]));
+ DEFINE(GPR8, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[8]));
+ DEFINE(GPR9, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[9]));
+ DEFINE(GPR10, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[10]));
+ DEFINE(GPR11, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[11]));
+ DEFINE(GPR12, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[12]));
+ DEFINE(GPR13, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[13]));
+ DEFINE(GPR14, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[14]));
+ DEFINE(GPR15, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[15]));
+ DEFINE(GPR16, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[16]));
+ DEFINE(GPR17, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[17]));
+ DEFINE(GPR18, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[18]));
+ DEFINE(GPR19, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[19]));
+ DEFINE(GPR20, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[20]));
+ DEFINE(GPR21, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[21]));
+ DEFINE(GPR22, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[22]));
+ DEFINE(GPR23, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[23]));
+ DEFINE(GPR24, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[24]));
+ DEFINE(GPR25, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[25]));
+ DEFINE(GPR26, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[26]));
+ DEFINE(GPR27, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[27]));
+ DEFINE(GPR28, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[28]));
+ DEFINE(GPR29, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[29]));
+ DEFINE(GPR30, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[30]));
+ DEFINE(GPR31, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[31]));
+ /* Note: these symbols include _ because they overlap with special
+ * register names
+ */
+ DEFINE(_NIP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, nip));
+ DEFINE(_MSR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, msr));
+ DEFINE(_CTR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ctr));
+ DEFINE(_LINK, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, link));
+ DEFINE(_CCR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ccr));
+ DEFINE(_MQ, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, mq));
+ DEFINE(_XER, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, xer));
+ DEFINE(_DAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar));
+ DEFINE(_DSISR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr));
+ /* The PowerPC 400-class & Book-E processors have neither the DAR nor the DSISR
+ * SPRs. Hence, we overload them to hold the similar DEAR and ESR SPRs
+ * for such processors. For critical interrupts we use them to
+ * hold SRR0 and SRR1.
+ */
+ DEFINE(_DEAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar));
+ DEFINE(_ESR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr));
+ DEFINE(ORIG_GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, orig_gpr3));
+ DEFINE(RESULT, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, result));
+ DEFINE(TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap));
+ DEFINE(CLONE_VM, CLONE_VM);
+ DEFINE(CLONE_UNTRACED, CLONE_UNTRACED);
+ DEFINE(MM_PGD, offsetof(struct mm_struct, pgd));
+
+ /* About the CPU features table */
+ DEFINE(CPU_SPEC_ENTRY_SIZE, sizeof(struct cpu_spec));
+ DEFINE(CPU_SPEC_PVR_MASK, offsetof(struct cpu_spec, pvr_mask));
+ DEFINE(CPU_SPEC_PVR_VALUE, offsetof(struct cpu_spec, pvr_value));
+ DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features));
+ DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup));
+
+ DEFINE(TI_TASK, offsetof(struct thread_info, task));
+ DEFINE(TI_EXECDOMAIN, offsetof(struct thread_info, exec_domain));
+ DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
+ DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
+ DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
+ DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
+
+ DEFINE(pbe_address, offsetof(struct pbe, address));
+ DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
+ DEFINE(pbe_next, offsetof(struct pbe, next));
+
+ DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28);
+ return 0;
+}
diff --git a/arch/ppc/kernel/bitops.c b/arch/ppc/kernel/bitops.c
new file mode 100644
index 000000000000..7f53d193968b
--- /dev/null
+++ b/arch/ppc/kernel/bitops.c
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 1996 Paul Mackerras.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+/*
+ * If the bitops are not inlined in bitops.h, they are defined here.
+ * -- paulus
+ */
+#if !__INLINE_BITOPS
+void set_bit(int nr, volatile void * addr)
+{
+ unsigned long old;
+ unsigned long mask = 1 << (nr & 0x1f);
+ unsigned long *p = ((unsigned long *)addr) + (nr >> 5);
+
+ __asm__ __volatile__(SMP_WMB "\n\
+1: lwarx %0,0,%3 \n\
+ or %0,%0,%2 \n"
+ PPC405_ERR77(0,%3)
+" stwcx. %0,0,%3 \n\
+ bne 1b"
+ SMP_MB
+ : "=&r" (old), "=m" (*p)
+ : "r" (mask), "r" (p), "m" (*p)
+ : "cc" );
+}
+
+void clear_bit(int nr, volatile void *addr)
+{
+ unsigned long old;
+ unsigned long mask = 1 << (nr & 0x1f);
+ unsigned long *p = ((unsigned long *)addr) + (nr >> 5);
+
+ __asm__ __volatile__(SMP_WMB "\n\
+1: lwarx %0,0,%3 \n\
+ andc %0,%0,%2 \n"
+ PPC405_ERR77(0,%3)
+" stwcx. %0,0,%3 \n\
+ bne 1b"
+ SMP_MB
+ : "=&r" (old), "=m" (*p)
+ : "r" (mask), "r" (p), "m" (*p)
+ : "cc");
+}
+
+void change_bit(int nr, volatile void *addr)
+{
+ unsigned long old;
+ unsigned long mask = 1 << (nr & 0x1f);
+ unsigned long *p = ((unsigned long *)addr) + (nr >> 5);
+
+ __asm__ __volatile__(SMP_WMB "\n\
+1: lwarx %0,0,%3 \n\
+ xor %0,%0,%2 \n"
+ PPC405_ERR77(0,%3)
+" stwcx. %0,0,%3 \n\
+ bne 1b"
+ SMP_MB
+ : "=&r" (old), "=m" (*p)
+ : "r" (mask), "r" (p), "m" (*p)
+ : "cc");
+}
+
+int test_and_set_bit(int nr, volatile void *addr)
+{
+ unsigned int old, t;
+ unsigned int mask = 1 << (nr & 0x1f);
+ volatile unsigned int *p = ((volatile unsigned int *)addr) + (nr >> 5);
+
+ __asm__ __volatile__(SMP_WMB "\n\
+1: lwarx %0,0,%4 \n\
+ or %1,%0,%3 \n"
+ PPC405_ERR77(0,%4)
+" stwcx. %1,0,%4 \n\
+ bne 1b"
+ SMP_MB
+ : "=&r" (old), "=&r" (t), "=m" (*p)
+ : "r" (mask), "r" (p), "m" (*p)
+ : "cc");
+
+ return (old & mask) != 0;
+}
+
+int test_and_clear_bit(int nr, volatile void *addr)
+{
+ unsigned int old, t;
+ unsigned int mask = 1 << (nr & 0x1f);
+ volatile unsigned int *p = ((volatile unsigned int *)addr) + (nr >> 5);
+
+ __asm__ __volatile__(SMP_WMB "\n\
+1: lwarx %0,0,%4 \n\
+ andc %1,%0,%3 \n"
+ PPC405_ERR77(0,%4)
+" stwcx. %1,0,%4 \n\
+ bne 1b"
+ SMP_MB
+ : "=&r" (old), "=&r" (t), "=m" (*p)
+ : "r" (mask), "r" (p), "m" (*p)
+ : "cc");
+
+ return (old & mask) != 0;
+}
+
+int test_and_change_bit(int nr, volatile void *addr)
+{
+ unsigned int old, t;
+ unsigned int mask = 1 << (nr & 0x1f);
+ volatile unsigned int *p = ((volatile unsigned int *)addr) + (nr >> 5);
+
+ __asm__ __volatile__(SMP_WMB "\n\
+1: lwarx %0,0,%4 \n\
+ xor %1,%0,%3 \n"
+ PPC405_ERR77(0,%4)
+" stwcx. %1,0,%4 \n\
+ bne 1b"
+ SMP_MB
+ : "=&r" (old), "=&r" (t), "=m" (*p)
+ : "r" (mask), "r" (p), "m" (*p)
+ : "cc");
+
+ return (old & mask) != 0;
+}
+#endif /* !__INLINE_BITOPS */
diff --git a/arch/ppc/kernel/cpu_setup_6xx.S b/arch/ppc/kernel/cpu_setup_6xx.S
new file mode 100644
index 000000000000..74f781b486a3
--- /dev/null
+++ b/arch/ppc/kernel/cpu_setup_6xx.S
@@ -0,0 +1,440 @@
+/*
+ * This file contains low level CPU setup functions.
+ * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+#include <asm/cache.h>
+
+_GLOBAL(__setup_cpu_601)
+ blr
+_GLOBAL(__setup_cpu_603)
+ b setup_common_caches
+_GLOBAL(__setup_cpu_604)
+ mflr r4
+ bl setup_common_caches
+ bl setup_604_hid0
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_750)
+ mflr r4
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_750cx)
+ mflr r4
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ bl setup_750cx
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_750fx)
+ mflr r4
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ bl setup_750fx
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_7400)
+ mflr r4
+ bl setup_7400_workarounds
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_7410)
+ mflr r4
+ bl setup_7410_workarounds
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ li r3,0
+ mtspr SPRN_L2CR2,r3
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_745x)
+ mflr r4
+ bl setup_common_caches
+ bl setup_745x_specifics
+ mtlr r4
+ blr
+
+/* Enable caches for 603's, 604, 750 & 7400 */
+setup_common_caches:
+ mfspr r11,SPRN_HID0
+ andi. r0,r11,HID0_DCE
+ ori r11,r11,HID0_ICE|HID0_DCE
+ ori r8,r11,HID0_ICFI
+ bne 1f /* don't invalidate the D-cache */
+ ori r8,r8,HID0_DCI /* unless it wasn't enabled */
+1: sync
+ mtspr SPRN_HID0,r8 /* enable and invalidate caches */
+ sync
+ mtspr SPRN_HID0,r11 /* enable caches */
+ sync
+ isync
+ blr
+
+/* 604, 604e, 604ev, ...
+ * Enable superscalar execution & branch history table
+ */
+setup_604_hid0:
+ mfspr r11,SPRN_HID0
+ ori r11,r11,HID0_SIED|HID0_BHTE
+ ori r8,r11,HID0_BTCD
+ sync
+ mtspr SPRN_HID0,r8 /* flush branch target address cache */
+ sync /* on 604e/604r */
+ mtspr SPRN_HID0,r11
+ sync
+ isync
+ blr
+
+/* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
+ * erratas we work around here.
+ * Moto MPC710CE.pdf describes them, those are errata
+ * #3, #4 and #5
+ * Note that we assume the firmware didn't choose to
+ * apply other workarounds (there are other ones documented
+ * in the .pdf). It appear that Apple firmware only works
+ * around #3 and with the same fix we use. We may want to
+ * check if the CPU is using 60x bus mode in which case
+ * the workaround for errata #4 is useless. Also, we may
+ * want to explicitely clear HID0_NOPDST as this is not
+ * needed once we have applied workaround #5 (though it's
+ * not set by Apple's firmware at least).
+ */
+setup_7400_workarounds:
+ mfpvr r3
+ rlwinm r3,r3,0,20,31
+ cmpwi 0,r3,0x0207
+ ble 1f
+ blr
+setup_7410_workarounds:
+ mfpvr r3
+ rlwinm r3,r3,0,20,31
+ cmpwi 0,r3,0x0100
+ bnelr
+1:
+ mfspr r11,SPRN_MSSSR0
+ /* Errata #3: Set L1OPQ_SIZE to 0x10 */
+ rlwinm r11,r11,0,9,6
+ oris r11,r11,0x0100
+ /* Errata #4: Set L2MQ_SIZE to 1 (check for MPX mode first ?) */
+ oris r11,r11,0x0002
+ /* Errata #5: Set DRLT_SIZE to 0x01 */
+ rlwinm r11,r11,0,5,2
+ oris r11,r11,0x0800
+ sync
+ mtspr SPRN_MSSSR0,r11
+ sync
+ isync
+ blr
+
+/* 740/750/7400/7410
+ * Enable Store Gathering (SGE), Address Brodcast (ABE),
+ * Branch History Table (BHTE), Branch Target ICache (BTIC)
+ * Dynamic Power Management (DPM), Speculative (SPD)
+ * Clear Instruction cache throttling (ICTC)
+ */
+setup_750_7400_hid0:
+ mfspr r11,SPRN_HID0
+ ori r11,r11,HID0_SGE | HID0_ABE | HID0_BHTE | HID0_BTIC
+BEGIN_FTR_SECTION
+ oris r11,r11,HID0_DPM@h /* enable dynamic power mgmt */
+END_FTR_SECTION_IFCLR(CPU_FTR_NO_DPM)
+ li r3,HID0_SPD
+ andc r11,r11,r3 /* clear SPD: enable speculative */
+ li r3,0
+ mtspr SPRN_ICTC,r3 /* Instruction Cache Throttling off */
+ isync
+ mtspr SPRN_HID0,r11
+ sync
+ isync
+ blr
+
+/* 750cx specific
+ * Looks like we have to disable NAP feature for some PLL settings...
+ * (waiting for confirmation)
+ */
+setup_750cx:
+ mfspr r10, SPRN_HID1
+ rlwinm r10,r10,4,28,31
+ cmpwi cr0,r10,7
+ cmpwi cr1,r10,9
+ cmpwi cr2,r10,11
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr2+eq
+ bnelr
+ lwz r6,CPU_SPEC_FEATURES(r5)
+ li r7,CPU_FTR_CAN_NAP
+ andc r6,r6,r7
+ stw r6,CPU_SPEC_FEATURES(r5)
+ blr
+
+/* 750fx specific
+ */
+setup_750fx:
+ blr
+
+/* MPC 745x
+ * Enable Store Gathering (SGE), Branch Folding (FOLD)
+ * Branch History Table (BHTE), Branch Target ICache (BTIC)
+ * Dynamic Power Management (DPM), Speculative (SPD)
+ * Ensure our data cache instructions really operate.
+ * Timebase has to be running or we wouldn't have made it here,
+ * just ensure we don't disable it.
+ * Clear Instruction cache throttling (ICTC)
+ * Enable L2 HW prefetch
+ */
+setup_745x_specifics:
+ /* We check for the presence of an L3 cache setup by
+ * the firmware. If any, we disable NAP capability as
+ * it's known to be bogus on rev 2.1 and earlier
+ */
+ mfspr r11,SPRN_L3CR
+ andis. r11,r11,L3CR_L3E@h
+ beq 1f
+ lwz r6,CPU_SPEC_FEATURES(r5)
+ andi. r0,r6,CPU_FTR_L3_DISABLE_NAP
+ beq 1f
+ li r7,CPU_FTR_CAN_NAP
+ andc r6,r6,r7
+ stw r6,CPU_SPEC_FEATURES(r5)
+1:
+ mfspr r11,SPRN_HID0
+
+ /* All of the bits we have to set.....
+ */
+ ori r11,r11,HID0_SGE | HID0_FOLD | HID0_BHTE | HID0_LRSTK | HID0_BTIC
+BEGIN_FTR_SECTION
+ xori r11,r11,HID0_BTIC
+END_FTR_SECTION_IFSET(CPU_FTR_NO_BTIC)
+BEGIN_FTR_SECTION
+ oris r11,r11,HID0_DPM@h /* enable dynamic power mgmt */
+END_FTR_SECTION_IFCLR(CPU_FTR_NO_DPM)
+
+ /* All of the bits we have to clear....
+ */
+ li r3,HID0_SPD | HID0_NOPDST | HID0_NOPTI
+ andc r11,r11,r3 /* clear SPD: enable speculative */
+ li r3,0
+
+ mtspr SPRN_ICTC,r3 /* Instruction Cache Throttling off */
+ isync
+ mtspr SPRN_HID0,r11
+ sync
+ isync
+
+ /* Enable L2 HW prefetch
+ */
+ mfspr r3,SPRN_MSSCR0
+ ori r3,r3,3
+ sync
+ mtspr SPRN_MSSCR0,r3
+ sync
+ isync
+ blr
+
+/* Definitions for the table use to save CPU states */
+#define CS_HID0 0
+#define CS_HID1 4
+#define CS_HID2 8
+#define CS_MSSCR0 12
+#define CS_MSSSR0 16
+#define CS_ICTRL 20
+#define CS_LDSTCR 24
+#define CS_LDSTDB 28
+#define CS_SIZE 32
+
+ .data
+ .balign L1_CACHE_LINE_SIZE
+cpu_state_storage:
+ .space CS_SIZE
+ .balign L1_CACHE_LINE_SIZE,0
+ .text
+
+/* Called in normal context to backup CPU 0 state. This
+ * does not include cache settings. This function is also
+ * called for machine sleep. This does not include the MMU
+ * setup, BATs, etc... but rather the "special" registers
+ * like HID0, HID1, MSSCR0, etc...
+ */
+_GLOBAL(__save_cpu_setup)
+ /* Some CR fields are volatile, we back it up all */
+ mfcr r7
+
+ /* Get storage ptr */
+ lis r5,cpu_state_storage@h
+ ori r5,r5,cpu_state_storage@l
+
+ /* Save HID0 (common to all CONFIG_6xx cpus) */
+ mfspr r3,SPRN_HID0
+ stw r3,CS_HID0(r5)
+
+ /* Now deal with CPU type dependent registers */
+ mfspr r3,SPRN_PVR
+ srwi r3,r3,16
+ cmplwi cr0,r3,0x8000 /* 7450 */
+ cmplwi cr1,r3,0x000c /* 7400 */
+ cmplwi cr2,r3,0x800c /* 7410 */
+ cmplwi cr3,r3,0x8001 /* 7455 */
+ cmplwi cr4,r3,0x8002 /* 7457 */
+ cmplwi cr5,r3,0x8003 /* 7447A */
+ cmplwi cr6,r3,0x7000 /* 750FX */
+ /* cr1 is 7400 || 7410 */
+ cror 4*cr1+eq,4*cr1+eq,4*cr2+eq
+ /* cr0 is 74xx */
+ cror 4*cr0+eq,4*cr0+eq,4*cr3+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr4+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr5+eq
+ bne 1f
+ /* Backup 74xx specific regs */
+ mfspr r4,SPRN_MSSCR0
+ stw r4,CS_MSSCR0(r5)
+ mfspr r4,SPRN_MSSSR0
+ stw r4,CS_MSSSR0(r5)
+ beq cr1,1f
+ /* Backup 745x specific registers */
+ mfspr r4,SPRN_HID1
+ stw r4,CS_HID1(r5)
+ mfspr r4,SPRN_ICTRL
+ stw r4,CS_ICTRL(r5)
+ mfspr r4,SPRN_LDSTCR
+ stw r4,CS_LDSTCR(r5)
+ mfspr r4,SPRN_LDSTDB
+ stw r4,CS_LDSTDB(r5)
+1:
+ bne cr6,1f
+ /* Backup 750FX specific registers */
+ mfspr r4,SPRN_HID1
+ stw r4,CS_HID1(r5)
+ /* If rev 2.x, backup HID2 */
+ mfspr r3,SPRN_PVR
+ andi. r3,r3,0xff00
+ cmpwi cr0,r3,0x0200
+ bne 1f
+ mfspr r4,SPRN_HID2
+ stw r4,CS_HID2(r5)
+1:
+ mtcr r7
+ blr
+
+/* Called with no MMU context (typically MSR:IR/DR off) to
+ * restore CPU state as backed up by the previous
+ * function. This does not include cache setting
+ */
+_GLOBAL(__restore_cpu_setup)
+ /* Some CR fields are volatile, we back it up all */
+ mfcr r7
+
+ /* Get storage ptr */
+ lis r5,(cpu_state_storage-KERNELBASE)@h
+ ori r5,r5,cpu_state_storage@l
+
+ /* Restore HID0 */
+ lwz r3,CS_HID0(r5)
+ sync
+ isync
+ mtspr SPRN_HID0,r3
+ sync
+ isync
+
+ /* Now deal with CPU type dependent registers */
+ mfspr r3,SPRN_PVR
+ srwi r3,r3,16
+ cmplwi cr0,r3,0x8000 /* 7450 */
+ cmplwi cr1,r3,0x000c /* 7400 */
+ cmplwi cr2,r3,0x800c /* 7410 */
+ cmplwi cr3,r3,0x8001 /* 7455 */
+ cmplwi cr4,r3,0x8002 /* 7457 */
+ cmplwi cr5,r3,0x8003 /* 7447A */
+ cmplwi cr6,r3,0x7000 /* 750FX */
+ /* cr1 is 7400 || 7410 */
+ cror 4*cr1+eq,4*cr1+eq,4*cr2+eq
+ /* cr0 is 74xx */
+ cror 4*cr0+eq,4*cr0+eq,4*cr3+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr4+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr5+eq
+ bne 2f
+ /* Restore 74xx specific regs */
+ lwz r4,CS_MSSCR0(r5)
+ sync
+ mtspr SPRN_MSSCR0,r4
+ sync
+ isync
+ lwz r4,CS_MSSSR0(r5)
+ sync
+ mtspr SPRN_MSSSR0,r4
+ sync
+ isync
+ bne cr2,1f
+ /* Clear 7410 L2CR2 */
+ li r4,0
+ mtspr SPRN_L2CR2,r4
+1: beq cr1,2f
+ /* Restore 745x specific registers */
+ lwz r4,CS_HID1(r5)
+ sync
+ mtspr SPRN_HID1,r4
+ isync
+ sync
+ lwz r4,CS_ICTRL(r5)
+ sync
+ mtspr SPRN_ICTRL,r4
+ isync
+ sync
+ lwz r4,CS_LDSTCR(r5)
+ sync
+ mtspr SPRN_LDSTCR,r4
+ isync
+ sync
+ lwz r4,CS_LDSTDB(r5)
+ sync
+ mtspr SPRN_LDSTDB,r4
+ isync
+ sync
+2: bne cr6,1f
+ /* Restore 750FX specific registers
+ * that is restore HID2 on rev 2.x and PLL config & switch
+ * to PLL 0 on all
+ */
+ /* If rev 2.x, restore HID2 with low voltage bit cleared */
+ mfspr r3,SPRN_PVR
+ andi. r3,r3,0xff00
+ cmpwi cr0,r3,0x0200
+ bne 4f
+ lwz r4,CS_HID2(r5)
+ rlwinm r4,r4,0,19,17
+ mtspr SPRN_HID2,r4
+ sync
+4:
+ lwz r4,CS_HID1(r5)
+ rlwinm r5,r4,0,16,14
+ mtspr SPRN_HID1,r5
+ /* Wait for PLL to stabilize */
+ mftbl r5
+3: mftbl r6
+ sub r6,r6,r5
+ cmplwi cr0,r6,10000
+ ble 3b
+ /* Setup final PLL */
+ mtspr SPRN_HID1,r4
+1:
+ mtcr r7
+ blr
+
diff --git a/arch/ppc/kernel/cpu_setup_power4.S b/arch/ppc/kernel/cpu_setup_power4.S
new file mode 100644
index 000000000000..f2ea1a990f17
--- /dev/null
+++ b/arch/ppc/kernel/cpu_setup_power4.S
@@ -0,0 +1,201 @@
+/*
+ * This file contains low level CPU setup functions.
+ * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+#include <asm/cache.h>
+
+_GLOBAL(__970_cpu_preinit)
+ /*
+ * Deal only with PPC970 and PPC970FX.
+ */
+ mfspr r0,SPRN_PVR
+ srwi r0,r0,16
+ cmpwi cr0,r0,0x39
+ cmpwi cr1,r0,0x3c
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ bnelr
+
+ /* Make sure HID4:rm_ci is off before MMU is turned off, that large
+ * pages are enabled with HID4:61 and clear HID5:DCBZ_size and
+ * HID5:DCBZ32_ill
+ */
+ li r0,0
+ mfspr r11,SPRN_HID4
+ rldimi r11,r0,40,23 /* clear bit 23 (rm_ci) */
+ rldimi r11,r0,2,61 /* clear bit 61 (lg_pg_en) */
+ sync
+ mtspr SPRN_HID4,r11
+ isync
+ sync
+ mfspr r11,SPRN_HID5
+ rldimi r11,r0,6,56 /* clear bits 56 & 57 (DCBZ*) */
+ sync
+ mtspr SPRN_HID5,r11
+ isync
+ sync
+
+ /* Setup some basic HID1 features */
+ mfspr r0,SPRN_HID1
+ li r11,0x1200 /* enable i-fetch cacheability */
+ sldi r11,r11,44 /* and prefetch */
+ or r0,r0,r11
+ mtspr SPRN_HID1,r0
+ mtspr SPRN_HID1,r0
+ isync
+
+ /* Clear HIOR */
+ li r0,0
+ sync
+ mtspr SPRN_HIOR,0 /* Clear interrupt prefix */
+ isync
+ blr
+
+_GLOBAL(__setup_cpu_power4)
+ blr
+_GLOBAL(__setup_cpu_ppc970)
+ mfspr r0,SPRN_HID0
+ li r11,5 /* clear DOZE and SLEEP */
+ rldimi r0,r11,52,8 /* set NAP and DPM */
+ mtspr SPRN_HID0,r0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ sync
+ isync
+ blr
+
+/* Definitions for the table use to save CPU states */
+#define CS_HID0 0
+#define CS_HID1 8
+#define CS_HID4 16
+#define CS_HID5 24
+#define CS_SIZE 32
+
+ .data
+ .balign L1_CACHE_LINE_SIZE
+cpu_state_storage:
+ .space CS_SIZE
+ .balign L1_CACHE_LINE_SIZE,0
+ .text
+
+/* Called in normal context to backup CPU 0 state. This
+ * does not include cache settings. This function is also
+ * called for machine sleep. This does not include the MMU
+ * setup, BATs, etc... but rather the "special" registers
+ * like HID0, HID1, HID4, etc...
+ */
+_GLOBAL(__save_cpu_setup)
+ /* Some CR fields are volatile, we back it up all */
+ mfcr r7
+
+ /* Get storage ptr */
+ lis r5,cpu_state_storage@h
+ ori r5,r5,cpu_state_storage@l
+
+ /* We only deal with 970 for now */
+ mfspr r0,SPRN_PVR
+ srwi r0,r0,16
+ cmpwi cr0,r0,0x39
+ cmpwi cr1,r0,0x3c
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ bne 1f
+
+ /* Save HID0,1,4 and 5 */
+ mfspr r3,SPRN_HID0
+ std r3,CS_HID0(r5)
+ mfspr r3,SPRN_HID1
+ std r3,CS_HID1(r5)
+ mfspr r3,SPRN_HID4
+ std r3,CS_HID4(r5)
+ mfspr r3,SPRN_HID5
+ std r3,CS_HID5(r5)
+
+1:
+ mtcr r7
+ blr
+
+/* Called with no MMU context (typically MSR:IR/DR off) to
+ * restore CPU state as backed up by the previous
+ * function. This does not include cache setting
+ */
+_GLOBAL(__restore_cpu_setup)
+ /* Some CR fields are volatile, we back it up all */
+ mfcr r7
+
+ /* Get storage ptr */
+ lis r5,(cpu_state_storage-KERNELBASE)@h
+ ori r5,r5,cpu_state_storage@l
+
+ /* We only deal with 970 for now */
+ mfspr r0,SPRN_PVR
+ srwi r0,r0,16
+ cmpwi cr0,r0,0x39
+ cmpwi cr1,r0,0x3c
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ bne 1f
+
+ /* Clear interrupt prefix */
+ li r0,0
+ sync
+ mtspr SPRN_HIOR,0
+ isync
+
+ /* Restore HID0 */
+ ld r3,CS_HID0(r5)
+ sync
+ isync
+ mtspr SPRN_HID0,r3
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ sync
+ isync
+
+ /* Restore HID1 */
+ ld r3,CS_HID1(r5)
+ sync
+ isync
+ mtspr SPRN_HID1,r3
+ mtspr SPRN_HID1,r3
+ sync
+ isync
+
+ /* Restore HID4 */
+ ld r3,CS_HID4(r5)
+ sync
+ isync
+ mtspr SPRN_HID4,r3
+ sync
+ isync
+
+ /* Restore HID5 */
+ ld r3,CS_HID5(r5)
+ sync
+ isync
+ mtspr SPRN_HID5,r3
+ sync
+ isync
+1:
+ mtcr r7
+ blr
+
diff --git a/arch/ppc/kernel/cputable.c b/arch/ppc/kernel/cputable.c
new file mode 100644
index 000000000000..8aa5e8c69009
--- /dev/null
+++ b/arch/ppc/kernel/cputable.c
@@ -0,0 +1,922 @@
+/*
+ * arch/ppc/kernel/cputable.c
+ *
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <linux/init.h>
+#include <asm/cputable.h>
+
+struct cpu_spec* cur_cpu_spec[NR_CPUS];
+
+extern void __setup_cpu_601(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_603(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_604(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_750(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_750cx(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_750fx(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_7400(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_7410(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_745x(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_power3(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_power4(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_ppc970(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+extern void __setup_cpu_generic(unsigned long offset, int cpu_nr, struct cpu_spec* spec);
+
+#define CLASSIC_PPC (!defined(CONFIG_8xx) && !defined(CONFIG_4xx) && \
+ !defined(CONFIG_POWER3) && !defined(CONFIG_POWER4) && \
+ !defined(CONFIG_BOOKE))
+
+/* This table only contains "desktop" CPUs, it need to be filled with embedded
+ * ones as well...
+ */
+#define COMMON_PPC (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \
+ PPC_FEATURE_HAS_MMU)
+
+/* We only set the altivec features if the kernel was compiled with altivec
+ * support
+ */
+#ifdef CONFIG_ALTIVEC
+#define CPU_FTR_ALTIVEC_COMP CPU_FTR_ALTIVEC
+#define PPC_FEATURE_ALTIVEC_COMP PPC_FEATURE_HAS_ALTIVEC
+#else
+#define CPU_FTR_ALTIVEC_COMP 0
+#define PPC_FEATURE_ALTIVEC_COMP 0
+#endif
+
+/* We only set the spe features if the kernel was compiled with
+ * spe support
+ */
+#ifdef CONFIG_SPE
+#define PPC_FEATURE_SPE_COMP PPC_FEATURE_HAS_SPE
+#else
+#define PPC_FEATURE_SPE_COMP 0
+#endif
+
+/* We need to mark all pages as being coherent if we're SMP or we
+ * have a 74[45]x and an MPC107 host bridge.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_MPC10X_BRIDGE)
+#define CPU_FTR_COMMON CPU_FTR_NEED_COHERENT
+#else
+#define CPU_FTR_COMMON 0
+#endif
+
+/* The powersave features NAP & DOZE seems to confuse BDI when
+ debugging. So if a BDI is used, disable theses
+ */
+#ifndef CONFIG_BDI_SWITCH
+#define CPU_FTR_MAYBE_CAN_DOZE CPU_FTR_CAN_DOZE
+#define CPU_FTR_MAYBE_CAN_NAP CPU_FTR_CAN_NAP
+#else
+#define CPU_FTR_MAYBE_CAN_DOZE 0
+#define CPU_FTR_MAYBE_CAN_NAP 0
+#endif
+
+struct cpu_spec cpu_specs[] = {
+#if CLASSIC_PPC
+ { /* 601 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00010000,
+ .cpu_name = "601",
+ .cpu_features = CPU_FTR_COMMON | CPU_FTR_601 |
+ CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_601_INSTR |
+ PPC_FEATURE_UNIFIED_CACHE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_601
+ },
+ { /* 603 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00030000,
+ .cpu_name = "603",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603
+ },
+ { /* 603e */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00060000,
+ .cpu_name = "603e",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603
+ },
+ { /* 603ev */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00070000,
+ .cpu_name = "603ev",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603
+ },
+ { /* 604 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00040000,
+ .cpu_name = "604",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_604_PERF_MON | CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 2,
+ .cpu_setup = __setup_cpu_604
+ },
+ { /* 604e */
+ .pvr_mask = 0xfffff000,
+ .pvr_value = 0x00090000,
+ .cpu_name = "604e",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_604_PERF_MON | CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604
+ },
+ { /* 604r */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00090000,
+ .cpu_name = "604r",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_604_PERF_MON | CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604
+ },
+ { /* 604ev */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x000a0000,
+ .cpu_name = "604ev",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_604_PERF_MON | CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604
+ },
+ { /* 740/750 (0x4202, don't support TAU ?) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x00084202,
+ .cpu_name = "740/750",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_HPTE_TABLE |
+ CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750
+ },
+ { /* 745/755 */
+ .pvr_mask = 0xfffff000,
+ .pvr_value = 0x00083000,
+ .cpu_name = "745/755",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750
+ },
+ { /* 750CX (80100 and 8010x?) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00080100,
+ .cpu_name = "750CX",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750cx
+ },
+ { /* 750CX (82201 and 82202) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00082200,
+ .cpu_name = "750CX",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750cx
+ },
+ { /* 750CXe (82214) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00082210,
+ .cpu_name = "750CXe",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750cx
+ },
+ { /* 750FX rev 1.x */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x70000100,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP |
+ CPU_FTR_DUAL_PLL_750FX | CPU_FTR_NO_DPM,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750
+ },
+ { /* 750FX rev 2.0 must disable HID0[DPM] */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x70000200,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP |
+ CPU_FTR_NO_DPM,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750
+ },
+ { /* 750FX (All revs except 2.0) */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x70000000,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP |
+ CPU_FTR_DUAL_PLL_750FX | CPU_FTR_HAS_HIGH_BATS,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750fx
+ },
+ { /* 750GX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x70020000,
+ .cpu_name = "750GX",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB |
+ CPU_FTR_L2CR | CPU_FTR_TAU | CPU_FTR_HPTE_TABLE |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_DUAL_PLL_750FX |
+ CPU_FTR_HAS_HIGH_BATS,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750fx
+ },
+ { /* 740/750 (L2CR bit need fixup for 740) */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00080000,
+ .cpu_name = "740/750",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750
+ },
+ { /* 7400 rev 1.1 ? (no TAU) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x000c1101,
+ .cpu_name = "7400 (1.1)",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_7400
+ },
+ { /* 7400 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x000c0000,
+ .cpu_name = "7400",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE |
+ CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_7400
+ },
+ { /* 7410 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x800c0000,
+ .cpu_name = "7410",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB | CPU_FTR_L2CR | CPU_FTR_TAU |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE |
+ CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_7410
+ },
+ { /* 7450 2.0 - no doze/nap */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80000200,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NEED_COHERENT,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7450 2.1 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80000201,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP |
+ CPU_FTR_NEED_COHERENT,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7450 2.3 and newer */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80000000,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_NEED_COHERENT,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7455 rev 1.x */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x80010100,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_HAS_HIGH_BATS | CPU_FTR_NEED_COHERENT,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7455 rev 2.0 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80010200,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP |
+ CPU_FTR_NEED_COHERENT | CPU_FTR_HAS_HIGH_BATS,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7455 others */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80010000,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS |
+ CPU_FTR_NEED_COHERENT,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7447/7457 Rev 1.0 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80020100,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS |
+ CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7447/7457 Rev 1.1 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80020101,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS |
+ CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7447/7457 Rev 1.2 and later */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80020000,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR |
+ CPU_FTR_HPTE_TABLE | CPU_FTR_SPEC7450 |
+ CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_HAS_HIGH_BATS |
+ CPU_FTR_NEED_COHERENT,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 7447A */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80030000,
+ .cpu_name = "7447A",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_HPTE_TABLE |
+ CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR |
+ CPU_FTR_HAS_HIGH_BATS | CPU_FTR_NEED_COHERENT,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_745x
+ },
+ { /* 82xx (8240, 8245, 8260 are all 603e cores) */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00810000,
+ .cpu_name = "82xx",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_MAYBE_CAN_DOZE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603
+ },
+ { /* All G2_LE (603e core, plus some) have the same pvr */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00820000,
+ .cpu_name = "G2_LE",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603
+ },
+ { /* e300 (a 603e core, plus some) on 83xx */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00830000,
+ .cpu_name = "e300",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB |
+ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_HAS_HIGH_BATS,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603
+ },
+ { /* default match, we assume split I/D cache & TB (non-601)... */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic PPC)",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_generic
+ },
+#endif /* CLASSIC_PPC */
+#ifdef CONFIG_PPC64BRIDGE
+ { /* Power3 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00400000,
+ .cpu_name = "Power3 (630)",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_64,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .cpu_setup = __setup_cpu_power3
+ },
+ { /* Power3+ */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00410000,
+ .cpu_name = "Power3 (630+)",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_64,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .cpu_setup = __setup_cpu_power3
+ },
+ { /* I-star */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00360000,
+ .cpu_name = "I-star",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_64,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .cpu_setup = __setup_cpu_power3
+ },
+ { /* S-star */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00370000,
+ .cpu_name = "S-star",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_64,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .cpu_setup = __setup_cpu_power3
+ },
+#endif /* CONFIG_PPC64BRIDGE */
+#ifdef CONFIG_POWER4
+ { /* Power4 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00350000,
+ .cpu_name = "Power4",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_64,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .cpu_setup = __setup_cpu_power4
+ },
+ { /* PPC970 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00390000,
+ .cpu_name = "PPC970",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_64 |
+ PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .cpu_setup = __setup_cpu_ppc970
+ },
+ { /* PPC970FX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003c0000,
+ .cpu_name = "PPC970FX",
+ .cpu_features = CPU_FTR_COMMON |
+ CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB |
+ CPU_FTR_HPTE_TABLE |
+ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MAYBE_CAN_NAP,
+ .cpu_user_features = COMMON_PPC | PPC_FEATURE_64 |
+ PPC_FEATURE_ALTIVEC_COMP,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .cpu_setup = __setup_cpu_ppc970
+ },
+#endif /* CONFIG_POWER4 */
+#ifdef CONFIG_8xx
+ { /* 8xx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00500000,
+ .cpu_name = "8xx",
+ /* CPU_FTR_MAYBE_CAN_DOZE is possible,
+ * if the 8xx code is there.... */
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 16,
+ .dcache_bsize = 16,
+ },
+#endif /* CONFIG_8xx */
+#ifdef CONFIG_40x
+ { /* 403GC */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x00200200,
+ .cpu_name = "403GC",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 16,
+ .dcache_bsize = 16,
+ },
+ { /* 403GCX */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x00201400,
+ .cpu_name = "403GCX",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 16,
+ .dcache_bsize = 16,
+ },
+ { /* 403G ?? */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00200000,
+ .cpu_name = "403G ??",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 16,
+ .dcache_bsize = 16,
+ },
+ { /* 405GP */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x40110000,
+ .cpu_name = "405GP",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* STB 03xxx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x40130000,
+ .cpu_name = "STB03xxx",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* STB 04xxx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41810000,
+ .cpu_name = "STB04xxx",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* NP405L */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41610000,
+ .cpu_name = "NP405L",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* NP4GS3 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x40B10000,
+ .cpu_name = "NP4GS3",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* NP405H */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41410000,
+ .cpu_name = "NP405H",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* 405GPr */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x50910000,
+ .cpu_name = "405GPr",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* STBx25xx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x51510000,
+ .cpu_name = "STBx25xx",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* 405LP */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41F10000,
+ .cpu_name = "405LP",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* Xilinx Virtex-II Pro */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x20010000,
+ .cpu_name = "Virtex-II Pro",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+
+#endif /* CONFIG_40x */
+#ifdef CONFIG_44x
+ { /* 440GP Rev. B */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000440,
+ .cpu_name = "440GP Rev. B",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* 440GP Rev. C */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000481,
+ .cpu_name = "440GP Rev. C",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* 440GX Rev. A */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000850,
+ .cpu_name = "440GX Rev. A",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* 440GX Rev. B */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000851,
+ .cpu_name = "440GX Rev. B",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+ { /* 440GX Rev. C */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000892,
+ .cpu_name = "440GX Rev. C",
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ },
+#endif /* CONFIG_44x */
+#ifdef CONFIG_E500
+ { /* e500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80200000,
+ .cpu_name = "e500",
+ /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */
+ .cpu_features = CPU_FTR_SPLIT_ID_CACHE |
+ CPU_FTR_USE_TB,
+ .cpu_user_features = PPC_FEATURE_32 |
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_SPE_COMP |
+ PPC_FEATURE_HAS_EFP_SINGLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ },
+#endif
+#if !CLASSIC_PPC
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic PPC)",
+ .cpu_features = CPU_FTR_COMMON,
+ .cpu_user_features = PPC_FEATURE_32,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ }
+#endif /* !CLASSIC_PPC */
+};
diff --git a/arch/ppc/kernel/dma-mapping.c b/arch/ppc/kernel/dma-mapping.c
new file mode 100644
index 000000000000..e0c631cf96b0
--- /dev/null
+++ b/arch/ppc/kernel/dma-mapping.c
@@ -0,0 +1,447 @@
+/*
+ * PowerPC version derived from arch/arm/mm/consistent.c
+ * Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
+ *
+ * Copyright (C) 2000 Russell King
+ *
+ * Consistent memory allocators. Used for DMA devices that want to
+ * share uncached memory with the processor core. The function return
+ * is the virtual address and 'dma_handle' is the physical address.
+ * Mostly stolen from the ARM port, with some changes for PowerPC.
+ * -- Dan
+ *
+ * Reorganized to get rid of the arch-specific consistent_* functions
+ * and provide non-coherent implementations for the DMA API. -Matt
+ *
+ * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
+ * implementation. This is pulled straight from ARM and barely
+ * modified. -Matt
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/stddef.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/bootmem.h>
+#include <linux/highmem.h>
+#include <linux/dma-mapping.h>
+#include <linux/hardirq.h>
+
+#include <asm/pgalloc.h>
+#include <asm/prom.h>
+#include <asm/io.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+#include <asm/mmu.h>
+#include <asm/uaccess.h>
+#include <asm/smp.h>
+#include <asm/machdep.h>
+
+int map_page(unsigned long va, phys_addr_t pa, int flags);
+
+#include <asm/tlbflush.h>
+
+/*
+ * This address range defaults to a value that is safe for all
+ * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It
+ * can be further configured for specific applications under
+ * the "Advanced Setup" menu. -Matt
+ */
+#define CONSISTENT_BASE (CONFIG_CONSISTENT_START)
+#define CONSISTENT_END (CONFIG_CONSISTENT_START + CONFIG_CONSISTENT_SIZE)
+#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
+
+/*
+ * This is the page table (2MB) covering uncached, DMA consistent allocations
+ */
+static pte_t *consistent_pte;
+static DEFINE_SPINLOCK(consistent_lock);
+
+/*
+ * VM region handling support.
+ *
+ * This should become something generic, handling VM region allocations for
+ * vmalloc and similar (ioremap, module space, etc).
+ *
+ * I envisage vmalloc()'s supporting vm_struct becoming:
+ *
+ * struct vm_struct {
+ * struct vm_region region;
+ * unsigned long flags;
+ * struct page **pages;
+ * unsigned int nr_pages;
+ * unsigned long phys_addr;
+ * };
+ *
+ * get_vm_area() would then call vm_region_alloc with an appropriate
+ * struct vm_region head (eg):
+ *
+ * struct vm_region vmalloc_head = {
+ * .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list),
+ * .vm_start = VMALLOC_START,
+ * .vm_end = VMALLOC_END,
+ * };
+ *
+ * However, vmalloc_head.vm_start is variable (typically, it is dependent on
+ * the amount of RAM found at boot time.) I would imagine that get_vm_area()
+ * would have to initialise this each time prior to calling vm_region_alloc().
+ */
+struct vm_region {
+ struct list_head vm_list;
+ unsigned long vm_start;
+ unsigned long vm_end;
+};
+
+static struct vm_region consistent_head = {
+ .vm_list = LIST_HEAD_INIT(consistent_head.vm_list),
+ .vm_start = CONSISTENT_BASE,
+ .vm_end = CONSISTENT_END,
+};
+
+static struct vm_region *
+vm_region_alloc(struct vm_region *head, size_t size, int gfp)
+{
+ unsigned long addr = head->vm_start, end = head->vm_end - size;
+ unsigned long flags;
+ struct vm_region *c, *new;
+
+ new = kmalloc(sizeof(struct vm_region), gfp);
+ if (!new)
+ goto out;
+
+ spin_lock_irqsave(&consistent_lock, flags);
+
+ list_for_each_entry(c, &head->vm_list, vm_list) {
+ if ((addr + size) < addr)
+ goto nospc;
+ if ((addr + size) <= c->vm_start)
+ goto found;
+ addr = c->vm_end;
+ if (addr > end)
+ goto nospc;
+ }
+
+ found:
+ /*
+ * Insert this entry _before_ the one we found.
+ */
+ list_add_tail(&new->vm_list, &c->vm_list);
+ new->vm_start = addr;
+ new->vm_end = addr + size;
+
+ spin_unlock_irqrestore(&consistent_lock, flags);
+ return new;
+
+ nospc:
+ spin_unlock_irqrestore(&consistent_lock, flags);
+ kfree(new);
+ out:
+ return NULL;
+}
+
+static struct vm_region *vm_region_find(struct vm_region *head, unsigned long addr)
+{
+ struct vm_region *c;
+
+ list_for_each_entry(c, &head->vm_list, vm_list) {
+ if (c->vm_start == addr)
+ goto out;
+ }
+ c = NULL;
+ out:
+ return c;
+}
+
+/*
+ * Allocate DMA-coherent memory space and return both the kernel remapped
+ * virtual and bus address for that space.
+ */
+void *
+__dma_alloc_coherent(size_t size, dma_addr_t *handle, int gfp)
+{
+ struct page *page;
+ struct vm_region *c;
+ unsigned long order;
+ u64 mask = 0x00ffffff, limit; /* ISA default */
+
+ if (!consistent_pte) {
+ printk(KERN_ERR "%s: not initialised\n", __func__);
+ dump_stack();
+ return NULL;
+ }
+
+ size = PAGE_ALIGN(size);
+ limit = (mask + 1) & ~mask;
+ if ((limit && size >= limit) || size >= (CONSISTENT_END - CONSISTENT_BASE)) {
+ printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
+ size, mask);
+ return NULL;
+ }
+
+ order = get_order(size);
+
+ if (mask != 0xffffffff)
+ gfp |= GFP_DMA;
+
+ page = alloc_pages(gfp, order);
+ if (!page)
+ goto no_page;
+
+ /*
+ * Invalidate any data that might be lurking in the
+ * kernel direct-mapped region for device DMA.
+ */
+ {
+ unsigned long kaddr = (unsigned long)page_address(page);
+ memset(page_address(page), 0, size);
+ flush_dcache_range(kaddr, kaddr + size);
+ }
+
+ /*
+ * Allocate a virtual address in the consistent mapping region.
+ */
+ c = vm_region_alloc(&consistent_head, size,
+ gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
+ if (c) {
+ unsigned long vaddr = c->vm_start;
+ pte_t *pte = consistent_pte + CONSISTENT_OFFSET(vaddr);
+ struct page *end = page + (1 << order);
+
+ /*
+ * Set the "dma handle"
+ */
+ *handle = page_to_bus(page);
+
+ do {
+ BUG_ON(!pte_none(*pte));
+
+ set_page_count(page, 1);
+ SetPageReserved(page);
+ set_pte_at(&init_mm, vaddr,
+ pte, mk_pte(page, pgprot_noncached(PAGE_KERNEL)));
+ page++;
+ pte++;
+ vaddr += PAGE_SIZE;
+ } while (size -= PAGE_SIZE);
+
+ /*
+ * Free the otherwise unused pages.
+ */
+ while (page < end) {
+ set_page_count(page, 1);
+ __free_page(page);
+ page++;
+ }
+
+ return (void *)c->vm_start;
+ }
+
+ if (page)
+ __free_pages(page, order);
+ no_page:
+ return NULL;
+}
+EXPORT_SYMBOL(__dma_alloc_coherent);
+
+/*
+ * free a page as defined by the above mapping.
+ */
+void __dma_free_coherent(size_t size, void *vaddr)
+{
+ struct vm_region *c;
+ unsigned long flags, addr;
+ pte_t *ptep;
+
+ size = PAGE_ALIGN(size);
+
+ spin_lock_irqsave(&consistent_lock, flags);
+
+ c = vm_region_find(&consistent_head, (unsigned long)vaddr);
+ if (!c)
+ goto no_area;
+
+ if ((c->vm_end - c->vm_start) != size) {
+ printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
+ __func__, c->vm_end - c->vm_start, size);
+ dump_stack();
+ size = c->vm_end - c->vm_start;
+ }
+
+ ptep = consistent_pte + CONSISTENT_OFFSET(c->vm_start);
+ addr = c->vm_start;
+ do {
+ pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
+ unsigned long pfn;
+
+ ptep++;
+ addr += PAGE_SIZE;
+
+ if (!pte_none(pte) && pte_present(pte)) {
+ pfn = pte_pfn(pte);
+
+ if (pfn_valid(pfn)) {
+ struct page *page = pfn_to_page(pfn);
+ ClearPageReserved(page);
+
+ __free_page(page);
+ continue;
+ }
+ }
+
+ printk(KERN_CRIT "%s: bad page in kernel page table\n",
+ __func__);
+ } while (size -= PAGE_SIZE);
+
+ flush_tlb_kernel_range(c->vm_start, c->vm_end);
+
+ list_del(&c->vm_list);
+
+ spin_unlock_irqrestore(&consistent_lock, flags);
+
+ kfree(c);
+ return;
+
+ no_area:
+ spin_unlock_irqrestore(&consistent_lock, flags);
+ printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
+ __func__, vaddr);
+ dump_stack();
+}
+EXPORT_SYMBOL(__dma_free_coherent);
+
+/*
+ * Initialise the consistent memory allocation.
+ */
+static int __init dma_alloc_init(void)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+ int ret = 0;
+
+ spin_lock(&init_mm.page_table_lock);
+
+ do {
+ pgd = pgd_offset(&init_mm, CONSISTENT_BASE);
+ pmd = pmd_alloc(&init_mm, pgd, CONSISTENT_BASE);
+ if (!pmd) {
+ printk(KERN_ERR "%s: no pmd tables\n", __func__);
+ ret = -ENOMEM;
+ break;
+ }
+ WARN_ON(!pmd_none(*pmd));
+
+ pte = pte_alloc_kernel(&init_mm, pmd, CONSISTENT_BASE);
+ if (!pte) {
+ printk(KERN_ERR "%s: no pte tables\n", __func__);
+ ret = -ENOMEM;
+ break;
+ }
+
+ consistent_pte = pte;
+ } while (0);
+
+ spin_unlock(&init_mm.page_table_lock);
+
+ return ret;
+}
+
+core_initcall(dma_alloc_init);
+
+/*
+ * make an area consistent.
+ */
+void __dma_sync(void *vaddr, size_t size, int direction)
+{
+ unsigned long start = (unsigned long)vaddr;
+ unsigned long end = start + size;
+
+ switch (direction) {
+ case DMA_NONE:
+ BUG();
+ case DMA_FROM_DEVICE: /* invalidate only */
+ invalidate_dcache_range(start, end);
+ break;
+ case DMA_TO_DEVICE: /* writeback only */
+ clean_dcache_range(start, end);
+ break;
+ case DMA_BIDIRECTIONAL: /* writeback and invalidate */
+ flush_dcache_range(start, end);
+ break;
+ }
+}
+EXPORT_SYMBOL(__dma_sync);
+
+#ifdef CONFIG_HIGHMEM
+/*
+ * __dma_sync_page() implementation for systems using highmem.
+ * In this case, each page of a buffer must be kmapped/kunmapped
+ * in order to have a virtual address for __dma_sync(). This must
+ * not sleep so kmap_atmomic()/kunmap_atomic() are used.
+ *
+ * Note: yes, it is possible and correct to have a buffer extend
+ * beyond the first page.
+ */
+static inline void __dma_sync_page_highmem(struct page *page,
+ unsigned long offset, size_t size, int direction)
+{
+ size_t seg_size = min((size_t)PAGE_SIZE, size) - offset;
+ size_t cur_size = seg_size;
+ unsigned long flags, start, seg_offset = offset;
+ int nr_segs = PAGE_ALIGN(size + (PAGE_SIZE - offset))/PAGE_SIZE;
+ int seg_nr = 0;
+
+ local_irq_save(flags);
+
+ do {
+ start = (unsigned long)kmap_atomic(page + seg_nr,
+ KM_PPC_SYNC_PAGE) + seg_offset;
+
+ /* Sync this buffer segment */
+ __dma_sync((void *)start, seg_size, direction);
+ kunmap_atomic((void *)start, KM_PPC_SYNC_PAGE);
+ seg_nr++;
+
+ /* Calculate next buffer segment size */
+ seg_size = min((size_t)PAGE_SIZE, size - cur_size);
+
+ /* Add the segment size to our running total */
+ cur_size += seg_size;
+ seg_offset = 0;
+ } while (seg_nr < nr_segs);
+
+ local_irq_restore(flags);
+}
+#endif /* CONFIG_HIGHMEM */
+
+/*
+ * __dma_sync_page makes memory consistent. identical to __dma_sync, but
+ * takes a struct page instead of a virtual address
+ */
+void __dma_sync_page(struct page *page, unsigned long offset,
+ size_t size, int direction)
+{
+#ifdef CONFIG_HIGHMEM
+ __dma_sync_page_highmem(page, offset, size, direction);
+#else
+ unsigned long start = (unsigned long)page_address(page) + offset;
+ __dma_sync((void *)start, size, direction);
+#endif
+}
+EXPORT_SYMBOL(__dma_sync_page);
diff --git a/arch/ppc/kernel/entry.S b/arch/ppc/kernel/entry.S
new file mode 100644
index 000000000000..035217d6c0f1
--- /dev/null
+++ b/arch/ppc/kernel/entry.S
@@ -0,0 +1,969 @@
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Rewritten by Cort Dougan (cort@fsmlabs.com) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@fsmlabs.com>
+ * Adapted for Power Macintosh by Paul Mackerras.
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ * This file contains the system call entry code, context switch
+ * code, and exception/interrupt return code for PowerPC.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/sys.h>
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+#include <asm/unistd.h>
+
+#undef SHOW_SYSCALLS
+#undef SHOW_SYSCALLS_TASK
+
+/*
+ * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE.
+ */
+#if MSR_KERNEL >= 0x10000
+#define LOAD_MSR_KERNEL(r, x) lis r,(x)@h; ori r,r,(x)@l
+#else
+#define LOAD_MSR_KERNEL(r, x) li r,(x)
+#endif
+
+#ifdef CONFIG_BOOKE
+#include "head_booke.h"
+ .globl mcheck_transfer_to_handler
+mcheck_transfer_to_handler:
+ mtspr MCHECK_SPRG,r8
+ BOOKE_LOAD_MCHECK_STACK
+ lwz r0,GPR10-INT_FRAME_SIZE(r8)
+ stw r0,GPR10(r11)
+ lwz r0,GPR11-INT_FRAME_SIZE(r8)
+ stw r0,GPR11(r11)
+ mfspr r8,MCHECK_SPRG
+ b transfer_to_handler_full
+
+ .globl crit_transfer_to_handler
+crit_transfer_to_handler:
+ mtspr CRIT_SPRG,r8
+ BOOKE_LOAD_CRIT_STACK
+ lwz r0,GPR10-INT_FRAME_SIZE(r8)
+ stw r0,GPR10(r11)
+ lwz r0,GPR11-INT_FRAME_SIZE(r8)
+ stw r0,GPR11(r11)
+ mfspr r8,CRIT_SPRG
+ /* fall through */
+#endif
+
+#ifdef CONFIG_40x
+ .globl crit_transfer_to_handler
+crit_transfer_to_handler:
+ lwz r0,crit_r10@l(0)
+ stw r0,GPR10(r11)
+ lwz r0,crit_r11@l(0)
+ stw r0,GPR11(r11)
+ /* fall through */
+#endif
+
+/*
+ * This code finishes saving the registers to the exception frame
+ * and jumps to the appropriate handler for the exception, turning
+ * on address translation.
+ * Note that we rely on the caller having set cr0.eq iff the exception
+ * occurred in kernel mode (i.e. MSR:PR = 0).
+ */
+ .globl transfer_to_handler_full
+transfer_to_handler_full:
+ SAVE_NVGPRS(r11)
+ /* fall through */
+
+ .globl transfer_to_handler
+transfer_to_handler:
+ stw r2,GPR2(r11)
+ stw r12,_NIP(r11)
+ stw r9,_MSR(r11)
+ andi. r2,r9,MSR_PR
+ mfctr r12
+ mfspr r2,SPRN_XER
+ stw r12,_CTR(r11)
+ stw r2,_XER(r11)
+ mfspr r12,SPRN_SPRG3
+ addi r2,r12,-THREAD
+ tovirt(r2,r2) /* set r2 to current */
+ beq 2f /* if from user, fix up THREAD.regs */
+ addi r11,r1,STACK_FRAME_OVERHEAD
+ stw r11,PT_REGS(r12)
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+ /* Check to see if the dbcr0 register is set up to debug. Use the
+ single-step bit to do this. */
+ lwz r12,THREAD_DBCR0(r12)
+ andis. r12,r12,DBCR0_IC@h
+ beq+ 3f
+ /* From user and task is ptraced - load up global dbcr0 */
+ li r12,-1 /* clear all pending debug events */
+ mtspr SPRN_DBSR,r12
+ lis r11,global_dbcr0@ha
+ tophys(r11,r11)
+ addi r11,r11,global_dbcr0@l
+ lwz r12,0(r11)
+ mtspr SPRN_DBCR0,r12
+ lwz r12,4(r11)
+ addi r12,r12,-1
+ stw r12,4(r11)
+#endif
+ b 3f
+2: /* if from kernel, check interrupted DOZE/NAP mode and
+ * check for stack overflow
+ */
+#ifdef CONFIG_6xx
+ mfspr r11,SPRN_HID0
+ mtcr r11
+BEGIN_FTR_SECTION
+ bt- 8,power_save_6xx_restore /* Check DOZE */
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+BEGIN_FTR_SECTION
+ bt- 9,power_save_6xx_restore /* Check NAP */
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+#endif /* CONFIG_6xx */
+ .globl transfer_to_handler_cont
+transfer_to_handler_cont:
+ lwz r11,THREAD_INFO-THREAD(r12)
+ cmplw r1,r11 /* if r1 <= current->thread_info */
+ ble- stack_ovf /* then the kernel stack overflowed */
+3:
+ mflr r9
+ lwz r11,0(r9) /* virtual address of handler */
+ lwz r9,4(r9) /* where to go when done */
+ FIX_SRR1(r10,r12)
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r10
+ mtlr r9
+ SYNC
+ RFI /* jump to handler, enable MMU */
+
+/*
+ * On kernel stack overflow, load up an initial stack pointer
+ * and call StackOverflow(regs), which should not return.
+ */
+stack_ovf:
+ /* sometimes we use a statically-allocated stack, which is OK. */
+ lis r11,_end@h
+ ori r11,r11,_end@l
+ cmplw r1,r11
+ ble 3b /* r1 <= &_end is OK */
+ SAVE_NVGPRS(r11)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ lis r1,init_thread_union@ha
+ addi r1,r1,init_thread_union@l
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+ lis r9,StackOverflow@ha
+ addi r9,r9,StackOverflow@l
+ LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ FIX_SRR1(r10,r12)
+ mtspr SPRN_SRR0,r9
+ mtspr SPRN_SRR1,r10
+ SYNC
+ RFI
+
+/*
+ * Handle a system call.
+ */
+ .stabs "arch/ppc/kernel/",N_SO,0,0,0f
+ .stabs "entry.S",N_SO,0,0,0f
+0:
+
+_GLOBAL(DoSyscall)
+ stw r0,THREAD+LAST_SYSCALL(r2)
+ stw r3,ORIG_GPR3(r1)
+ li r12,0
+ stw r12,RESULT(r1)
+ lwz r11,_CCR(r1) /* Clear SO bit in CR */
+ rlwinm r11,r11,0,4,2
+ stw r11,_CCR(r1)
+#ifdef SHOW_SYSCALLS
+ bl do_show_syscall
+#endif /* SHOW_SYSCALLS */
+ rlwinm r10,r1,0,0,18 /* current_thread_info() */
+ lwz r11,TI_LOCAL_FLAGS(r10)
+ rlwinm r11,r11,0,~_TIFL_FORCE_NOERROR
+ stw r11,TI_LOCAL_FLAGS(r10)
+ lwz r11,TI_FLAGS(r10)
+ andi. r11,r11,_TIF_SYSCALL_TRACE
+ bne- syscall_dotrace
+syscall_dotrace_cont:
+ cmplwi 0,r0,NR_syscalls
+ lis r10,sys_call_table@h
+ ori r10,r10,sys_call_table@l
+ slwi r0,r0,2
+ bge- 66f
+ lwzx r10,r10,r0 /* Fetch system call handler [ptr] */
+ mtlr r10
+ addi r9,r1,STACK_FRAME_OVERHEAD
+ blrl /* Call handler */
+ .globl ret_from_syscall
+ret_from_syscall:
+#ifdef SHOW_SYSCALLS
+ bl do_show_syscall_exit
+#endif
+ mr r6,r3
+ li r11,-_LAST_ERRNO
+ cmplw 0,r3,r11
+ rlwinm r12,r1,0,0,18 /* current_thread_info() */
+ blt+ 30f
+ lwz r11,TI_LOCAL_FLAGS(r12)
+ andi. r11,r11,_TIFL_FORCE_NOERROR
+ bne 30f
+ neg r3,r3
+ lwz r10,_CCR(r1) /* Set SO bit in CR */
+ oris r10,r10,0x1000
+ stw r10,_CCR(r1)
+
+ /* disable interrupts so current_thread_info()->flags can't change */
+30: LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
+ SYNC
+ MTMSRD(r10)
+ lwz r9,TI_FLAGS(r12)
+ andi. r0,r9,(_TIF_SYSCALL_TRACE|_TIF_SIGPENDING|_TIF_NEED_RESCHED)
+ bne- syscall_exit_work
+syscall_exit_cont:
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ /* If the process has its own DBCR0 value, load it up. The single
+ step bit tells us that dbcr0 should be loaded. */
+ lwz r0,THREAD+THREAD_DBCR0(r2)
+ andis. r10,r0,DBCR0_IC@h
+ bnel- load_dbcr0
+#endif
+ stwcx. r0,0,r1 /* to clear the reservation */
+ lwz r4,_LINK(r1)
+ lwz r5,_CCR(r1)
+ mtlr r4
+ mtcr r5
+ lwz r7,_NIP(r1)
+ lwz r8,_MSR(r1)
+ FIX_SRR1(r8, r0)
+ lwz r2,GPR2(r1)
+ lwz r1,GPR1(r1)
+ mtspr SPRN_SRR0,r7
+ mtspr SPRN_SRR1,r8
+ SYNC
+ RFI
+
+66: li r3,-ENOSYS
+ b ret_from_syscall
+
+ .globl ret_from_fork
+ret_from_fork:
+ REST_NVGPRS(r1)
+ bl schedule_tail
+ li r3,0
+ b ret_from_syscall
+
+/* Traced system call support */
+syscall_dotrace:
+ SAVE_NVGPRS(r1)
+ li r0,0xc00
+ stw r0,TRAP(r1)
+ bl do_syscall_trace
+ lwz r0,GPR0(r1) /* Restore original registers */
+ lwz r3,GPR3(r1)
+ lwz r4,GPR4(r1)
+ lwz r5,GPR5(r1)
+ lwz r6,GPR6(r1)
+ lwz r7,GPR7(r1)
+ lwz r8,GPR8(r1)
+ REST_NVGPRS(r1)
+ b syscall_dotrace_cont
+
+syscall_exit_work:
+ stw r6,RESULT(r1) /* Save result */
+ stw r3,GPR3(r1) /* Update return value */
+ andi. r0,r9,_TIF_SYSCALL_TRACE
+ beq 5f
+ ori r10,r10,MSR_EE
+ SYNC
+ MTMSRD(r10) /* re-enable interrupts */
+ lwz r4,TRAP(r1)
+ andi. r4,r4,1
+ beq 4f
+ SAVE_NVGPRS(r1)
+ li r4,0xc00
+ stw r4,TRAP(r1)
+4:
+ bl do_syscall_trace
+ REST_NVGPRS(r1)
+2:
+ lwz r3,GPR3(r1)
+ LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
+ SYNC
+ MTMSRD(r10) /* disable interrupts again */
+ rlwinm r12,r1,0,0,18 /* current_thread_info() */
+ lwz r9,TI_FLAGS(r12)
+5:
+ andi. r0,r9,_TIF_NEED_RESCHED
+ bne 1f
+ lwz r5,_MSR(r1)
+ andi. r5,r5,MSR_PR
+ beq syscall_exit_cont
+ andi. r0,r9,_TIF_SIGPENDING
+ beq syscall_exit_cont
+ b do_user_signal
+1:
+ ori r10,r10,MSR_EE
+ SYNC
+ MTMSRD(r10) /* re-enable interrupts */
+ bl schedule
+ b 2b
+
+#ifdef SHOW_SYSCALLS
+do_show_syscall:
+#ifdef SHOW_SYSCALLS_TASK
+ lis r11,show_syscalls_task@ha
+ lwz r11,show_syscalls_task@l(r11)
+ cmp 0,r2,r11
+ bnelr
+#endif
+ stw r31,GPR31(r1)
+ mflr r31
+ lis r3,7f@ha
+ addi r3,r3,7f@l
+ lwz r4,GPR0(r1)
+ lwz r5,GPR3(r1)
+ lwz r6,GPR4(r1)
+ lwz r7,GPR5(r1)
+ lwz r8,GPR6(r1)
+ lwz r9,GPR7(r1)
+ bl printk
+ lis r3,77f@ha
+ addi r3,r3,77f@l
+ lwz r4,GPR8(r1)
+ mr r5,r2
+ bl printk
+ lwz r0,GPR0(r1)
+ lwz r3,GPR3(r1)
+ lwz r4,GPR4(r1)
+ lwz r5,GPR5(r1)
+ lwz r6,GPR6(r1)
+ lwz r7,GPR7(r1)
+ lwz r8,GPR8(r1)
+ mtlr r31
+ lwz r31,GPR31(r1)
+ blr
+
+do_show_syscall_exit:
+#ifdef SHOW_SYSCALLS_TASK
+ lis r11,show_syscalls_task@ha
+ lwz r11,show_syscalls_task@l(r11)
+ cmp 0,r2,r11
+ bnelr
+#endif
+ stw r31,GPR31(r1)
+ mflr r31
+ stw r3,RESULT(r1) /* Save result */
+ mr r4,r3
+ lis r3,79f@ha
+ addi r3,r3,79f@l
+ bl printk
+ lwz r3,RESULT(r1)
+ mtlr r31
+ lwz r31,GPR31(r1)
+ blr
+
+7: .string "syscall %d(%x, %x, %x, %x, %x, "
+77: .string "%x), current=%p\n"
+79: .string " -> %x\n"
+ .align 2,0
+
+#ifdef SHOW_SYSCALLS_TASK
+ .data
+ .globl show_syscalls_task
+show_syscalls_task:
+ .long -1
+ .text
+#endif
+#endif /* SHOW_SYSCALLS */
+
+/*
+ * The sigsuspend and rt_sigsuspend system calls can call do_signal
+ * and thus put the process into the stopped state where we might
+ * want to examine its user state with ptrace. Therefore we need
+ * to save all the nonvolatile registers (r13 - r31) before calling
+ * the C code.
+ */
+ .globl ppc_sigsuspend
+ppc_sigsuspend:
+ SAVE_NVGPRS(r1)
+ lwz r0,TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,TRAP(r1) /* register set saved */
+ b sys_sigsuspend
+
+ .globl ppc_rt_sigsuspend
+ppc_rt_sigsuspend:
+ SAVE_NVGPRS(r1)
+ lwz r0,TRAP(r1)
+ rlwinm r0,r0,0,0,30
+ stw r0,TRAP(r1)
+ b sys_rt_sigsuspend
+
+ .globl ppc_fork
+ppc_fork:
+ SAVE_NVGPRS(r1)
+ lwz r0,TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,TRAP(r1) /* register set saved */
+ b sys_fork
+
+ .globl ppc_vfork
+ppc_vfork:
+ SAVE_NVGPRS(r1)
+ lwz r0,TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,TRAP(r1) /* register set saved */
+ b sys_vfork
+
+ .globl ppc_clone
+ppc_clone:
+ SAVE_NVGPRS(r1)
+ lwz r0,TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,TRAP(r1) /* register set saved */
+ b sys_clone
+
+ .globl ppc_swapcontext
+ppc_swapcontext:
+ SAVE_NVGPRS(r1)
+ lwz r0,TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,TRAP(r1) /* register set saved */
+ b sys_swapcontext
+
+/*
+ * Top-level page fault handling.
+ * This is in assembler because if do_page_fault tells us that
+ * it is a bad kernel page fault, we want to save the non-volatile
+ * registers before calling bad_page_fault.
+ */
+ .globl handle_page_fault
+handle_page_fault:
+ stw r4,_DAR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_page_fault
+ cmpwi r3,0
+ beq+ ret_from_except
+ SAVE_NVGPRS(r1)
+ lwz r0,TRAP(r1)
+ clrrwi r0,r0,1
+ stw r0,TRAP(r1)
+ mr r5,r3
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ lwz r4,_DAR(r1)
+ bl bad_page_fault
+ b ret_from_except_full
+
+/*
+ * This routine switches between two different tasks. The process
+ * state of one is saved on its kernel stack. Then the state
+ * of the other is restored from its kernel stack. The memory
+ * management hardware is updated to the second process's state.
+ * Finally, we can return to the second process.
+ * On entry, r3 points to the THREAD for the current task, r4
+ * points to the THREAD for the new task.
+ *
+ * This routine is always called with interrupts disabled.
+ *
+ * Note: there are two ways to get to the "going out" portion
+ * of this code; either by coming in via the entry (_switch)
+ * or via "fork" which must set up an environment equivalent
+ * to the "_switch" path. If you change this , you'll have to
+ * change the fork code also.
+ *
+ * The code which creates the new task context is in 'copy_thread'
+ * in arch/ppc/kernel/process.c
+ */
+_GLOBAL(_switch)
+ stwu r1,-INT_FRAME_SIZE(r1)
+ mflr r0
+ stw r0,INT_FRAME_SIZE+4(r1)
+ /* r3-r12 are caller saved -- Cort */
+ SAVE_NVGPRS(r1)
+ stw r0,_NIP(r1) /* Return to switch caller */
+ mfmsr r11
+ li r0,MSR_FP /* Disable floating-point */
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ oris r0,r0,MSR_VEC@h /* Disable altivec */
+ mfspr r12,SPRN_VRSAVE /* save vrsave register value */
+ stw r12,THREAD+THREAD_VRSAVE(r2)
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ oris r0,r0,MSR_SPE@h /* Disable SPE */
+ mfspr r12,SPRN_SPEFSCR /* save spefscr register value */
+ stw r12,THREAD+THREAD_SPEFSCR(r2)
+#endif /* CONFIG_SPE */
+ and. r0,r0,r11 /* FP or altivec or SPE enabled? */
+ beq+ 1f
+ andc r11,r11,r0
+ MTMSRD(r11)
+ isync
+1: stw r11,_MSR(r1)
+ mfcr r10
+ stw r10,_CCR(r1)
+ stw r1,KSP(r3) /* Set old stack pointer */
+
+#ifdef CONFIG_SMP
+ /* We need a sync somewhere here to make sure that if the
+ * previous task gets rescheduled on another CPU, it sees all
+ * stores it has performed on this one.
+ */
+ sync
+#endif /* CONFIG_SMP */
+
+ tophys(r0,r4)
+ CLR_TOP32(r0)
+ mtspr SPRN_SPRG3,r0 /* Update current THREAD phys addr */
+ lwz r1,KSP(r4) /* Load new stack pointer */
+
+ /* save the old current 'last' for return value */
+ mr r3,r2
+ addi r2,r4,-THREAD /* Update current */
+
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ lwz r0,THREAD+THREAD_VRSAVE(r2)
+ mtspr SPRN_VRSAVE,r0 /* if G4, restore VRSAVE reg */
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ lwz r0,THREAD+THREAD_SPEFSCR(r2)
+ mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */
+#endif /* CONFIG_SPE */
+
+ lwz r0,_CCR(r1)
+ mtcrf 0xFF,r0
+ /* r3-r12 are destroyed -- Cort */
+ REST_NVGPRS(r1)
+
+ lwz r4,_NIP(r1) /* Return to _switch caller in new task */
+ mtlr r4
+ addi r1,r1,INT_FRAME_SIZE
+ blr
+
+ .globl sigreturn_exit
+sigreturn_exit:
+ subi r1,r3,STACK_FRAME_OVERHEAD
+ rlwinm r12,r1,0,0,18 /* current_thread_info() */
+ lwz r9,TI_FLAGS(r12)
+ andi. r0,r9,_TIF_SYSCALL_TRACE
+ bnel- do_syscall_trace
+ /* fall through */
+
+ .globl ret_from_except_full
+ret_from_except_full:
+ REST_NVGPRS(r1)
+ /* fall through */
+
+ .globl ret_from_except
+ret_from_except:
+ /* Hard-disable interrupts so that current_thread_info()->flags
+ * can't change between when we test it and when we return
+ * from the interrupt. */
+ LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ SYNC /* Some chip revs have problems here... */
+ MTMSRD(r10) /* disable interrupts */
+
+ lwz r3,_MSR(r1) /* Returning to user mode? */
+ andi. r0,r3,MSR_PR
+ beq resume_kernel
+
+user_exc_return: /* r10 contains MSR_KERNEL here */
+ /* Check current_thread_info()->flags */
+ rlwinm r9,r1,0,0,18
+ lwz r9,TI_FLAGS(r9)
+ andi. r0,r9,(_TIF_SIGPENDING|_TIF_NEED_RESCHED)
+ bne do_work
+
+restore_user:
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ /* Check whether this process has its own DBCR0 value. The single
+ step bit tells us that dbcr0 should be loaded. */
+ lwz r0,THREAD+THREAD_DBCR0(r2)
+ andis. r10,r0,DBCR0_IC@h
+ bnel- load_dbcr0
+#endif
+
+#ifdef CONFIG_PREEMPT
+ b restore
+
+/* N.B. the only way to get here is from the beq following ret_from_except. */
+resume_kernel:
+ /* check current_thread_info->preempt_count */
+ rlwinm r9,r1,0,0,18
+ lwz r0,TI_PREEMPT(r9)
+ cmpwi 0,r0,0 /* if non-zero, just restore regs and return */
+ bne restore
+ lwz r0,TI_FLAGS(r9)
+ andi. r0,r0,_TIF_NEED_RESCHED
+ beq+ restore
+ andi. r0,r3,MSR_EE /* interrupts off? */
+ beq restore /* don't schedule if so */
+1: bl preempt_schedule_irq
+ rlwinm r9,r1,0,0,18
+ lwz r3,TI_FLAGS(r9)
+ andi. r0,r3,_TIF_NEED_RESCHED
+ bne- 1b
+#else
+resume_kernel:
+#endif /* CONFIG_PREEMPT */
+
+ /* interrupts are hard-disabled at this point */
+restore:
+ lwz r0,GPR0(r1)
+ lwz r2,GPR2(r1)
+ REST_4GPRS(3, r1)
+ REST_2GPRS(7, r1)
+
+ lwz r10,_XER(r1)
+ lwz r11,_CTR(r1)
+ mtspr SPRN_XER,r10
+ mtctr r11
+
+ PPC405_ERR77(0,r1)
+ stwcx. r0,0,r1 /* to clear the reservation */
+
+#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+ lwz r9,_MSR(r1)
+ andi. r10,r9,MSR_RI /* check if this exception occurred */
+ beql nonrecoverable /* at a bad place (MSR:RI = 0) */
+
+ lwz r10,_CCR(r1)
+ lwz r11,_LINK(r1)
+ mtcrf 0xFF,r10
+ mtlr r11
+
+ /*
+ * Once we put values in SRR0 and SRR1, we are in a state
+ * where exceptions are not recoverable, since taking an
+ * exception will trash SRR0 and SRR1. Therefore we clear the
+ * MSR:RI bit to indicate this. If we do take an exception,
+ * we can't return to the point of the exception but we
+ * can restart the exception exit path at the label
+ * exc_exit_restart below. -- paulus
+ */
+ LOAD_MSR_KERNEL(r10,MSR_KERNEL & ~MSR_RI)
+ SYNC
+ MTMSRD(r10) /* clear the RI bit */
+ .globl exc_exit_restart
+exc_exit_restart:
+ lwz r9,_MSR(r1)
+ lwz r12,_NIP(r1)
+ FIX_SRR1(r9,r10)
+ mtspr SPRN_SRR0,r12
+ mtspr SPRN_SRR1,r9
+ REST_4GPRS(9, r1)
+ lwz r1,GPR1(r1)
+ .globl exc_exit_restart_end
+exc_exit_restart_end:
+ SYNC
+ RFI
+
+#else /* !(CONFIG_4xx || CONFIG_BOOKE) */
+ /*
+ * This is a bit different on 4xx/Book-E because it doesn't have
+ * the RI bit in the MSR.
+ * The TLB miss handler checks if we have interrupted
+ * the exception exit path and restarts it if so
+ * (well maybe one day it will... :).
+ */
+ lwz r11,_LINK(r1)
+ mtlr r11
+ lwz r10,_CCR(r1)
+ mtcrf 0xff,r10
+ REST_2GPRS(9, r1)
+ .globl exc_exit_restart
+exc_exit_restart:
+ lwz r11,_NIP(r1)
+ lwz r12,_MSR(r1)
+exc_exit_start:
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r12
+ REST_2GPRS(11, r1)
+ lwz r1,GPR1(r1)
+ .globl exc_exit_restart_end
+exc_exit_restart_end:
+ PPC405_ERR77_SYNC
+ rfi
+ b . /* prevent prefetch past rfi */
+
+/*
+ * Returning from a critical interrupt in user mode doesn't need
+ * to be any different from a normal exception. For a critical
+ * interrupt in the kernel, we just return (without checking for
+ * preemption) since the interrupt may have happened at some crucial
+ * place (e.g. inside the TLB miss handler), and because we will be
+ * running with r1 pointing into critical_stack, not the current
+ * process's kernel stack (and therefore current_thread_info() will
+ * give the wrong answer).
+ * We have to restore various SPRs that may have been in use at the
+ * time of the critical interrupt.
+ *
+ */
+ .globl ret_from_crit_exc
+ret_from_crit_exc:
+ REST_NVGPRS(r1)
+ lwz r3,_MSR(r1)
+ andi. r3,r3,MSR_PR
+ LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ bne user_exc_return
+
+ lwz r0,GPR0(r1)
+ lwz r2,GPR2(r1)
+ REST_4GPRS(3, r1)
+ REST_2GPRS(7, r1)
+
+ lwz r10,_XER(r1)
+ lwz r11,_CTR(r1)
+ mtspr SPRN_XER,r10
+ mtctr r11
+
+ PPC405_ERR77(0,r1)
+ stwcx. r0,0,r1 /* to clear the reservation */
+
+ lwz r11,_LINK(r1)
+ mtlr r11
+ lwz r10,_CCR(r1)
+ mtcrf 0xff,r10
+#ifdef CONFIG_40x
+ /* avoid any possible TLB misses here by turning off MSR.DR, we
+ * assume the instructions here are mapped by a pinned TLB entry */
+ li r10,MSR_IR
+ mtmsr r10
+ isync
+ tophys(r1, r1)
+#endif
+ lwz r9,_DEAR(r1)
+ lwz r10,_ESR(r1)
+ mtspr SPRN_DEAR,r9
+ mtspr SPRN_ESR,r10
+ lwz r11,_NIP(r1)
+ lwz r12,_MSR(r1)
+ mtspr SPRN_CSRR0,r11
+ mtspr SPRN_CSRR1,r12
+ lwz r9,GPR9(r1)
+ lwz r12,GPR12(r1)
+ lwz r10,GPR10(r1)
+ lwz r11,GPR11(r1)
+ lwz r1,GPR1(r1)
+ PPC405_ERR77_SYNC
+ rfci
+ b . /* prevent prefetch past rfci */
+
+#ifdef CONFIG_BOOKE
+/*
+ * Return from a machine check interrupt, similar to a critical
+ * interrupt.
+ */
+ .globl ret_from_mcheck_exc
+ret_from_mcheck_exc:
+ REST_NVGPRS(r1)
+ lwz r3,_MSR(r1)
+ andi. r3,r3,MSR_PR
+ LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ bne user_exc_return
+
+ lwz r0,GPR0(r1)
+ lwz r2,GPR2(r1)
+ REST_4GPRS(3, r1)
+ REST_2GPRS(7, r1)
+
+ lwz r10,_XER(r1)
+ lwz r11,_CTR(r1)
+ mtspr SPRN_XER,r10
+ mtctr r11
+
+ stwcx. r0,0,r1 /* to clear the reservation */
+
+ lwz r11,_LINK(r1)
+ mtlr r11
+ lwz r10,_CCR(r1)
+ mtcrf 0xff,r10
+ lwz r9,_DEAR(r1)
+ lwz r10,_ESR(r1)
+ mtspr SPRN_DEAR,r9
+ mtspr SPRN_ESR,r10
+ lwz r11,_NIP(r1)
+ lwz r12,_MSR(r1)
+ mtspr SPRN_MCSRR0,r11
+ mtspr SPRN_MCSRR1,r12
+ lwz r9,GPR9(r1)
+ lwz r12,GPR12(r1)
+ lwz r10,GPR10(r1)
+ lwz r11,GPR11(r1)
+ lwz r1,GPR1(r1)
+ RFMCI
+#endif /* CONFIG_BOOKE */
+
+/*
+ * Load the DBCR0 value for a task that is being ptraced,
+ * having first saved away the global DBCR0. Note that r0
+ * has the dbcr0 value to set upon entry to this.
+ */
+load_dbcr0:
+ mfmsr r10 /* first disable debug exceptions */
+ rlwinm r10,r10,0,~MSR_DE
+ mtmsr r10
+ isync
+ mfspr r10,SPRN_DBCR0
+ lis r11,global_dbcr0@ha
+ addi r11,r11,global_dbcr0@l
+ stw r10,0(r11)
+ mtspr SPRN_DBCR0,r0
+ lwz r10,4(r11)
+ addi r10,r10,1
+ stw r10,4(r11)
+ li r11,-1
+ mtspr SPRN_DBSR,r11 /* clear all pending debug events */
+ blr
+
+ .comm global_dbcr0,8
+#endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
+
+do_work: /* r10 contains MSR_KERNEL here */
+ andi. r0,r9,_TIF_NEED_RESCHED
+ beq do_user_signal
+
+do_resched: /* r10 contains MSR_KERNEL here */
+ ori r10,r10,MSR_EE
+ SYNC
+ MTMSRD(r10) /* hard-enable interrupts */
+ bl schedule
+recheck:
+ LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ SYNC
+ MTMSRD(r10) /* disable interrupts */
+ rlwinm r9,r1,0,0,18
+ lwz r9,TI_FLAGS(r9)
+ andi. r0,r9,_TIF_NEED_RESCHED
+ bne- do_resched
+ andi. r0,r9,_TIF_SIGPENDING
+ beq restore_user
+do_user_signal: /* r10 contains MSR_KERNEL here */
+ ori r10,r10,MSR_EE
+ SYNC
+ MTMSRD(r10) /* hard-enable interrupts */
+ /* save r13-r31 in the exception frame, if not already done */
+ lwz r3,TRAP(r1)
+ andi. r0,r3,1
+ beq 2f
+ SAVE_NVGPRS(r1)
+ rlwinm r3,r3,0,0,30
+ stw r3,TRAP(r1)
+2: li r3,0
+ addi r4,r1,STACK_FRAME_OVERHEAD
+ bl do_signal
+ REST_NVGPRS(r1)
+ b recheck
+
+/*
+ * We come here when we are at the end of handling an exception
+ * that occurred at a place where taking an exception will lose
+ * state information, such as the contents of SRR0 and SRR1.
+ */
+nonrecoverable:
+ lis r10,exc_exit_restart_end@ha
+ addi r10,r10,exc_exit_restart_end@l
+ cmplw r12,r10
+ bge 3f
+ lis r11,exc_exit_restart@ha
+ addi r11,r11,exc_exit_restart@l
+ cmplw r12,r11
+ blt 3f
+ lis r10,ee_restarts@ha
+ lwz r12,ee_restarts@l(r10)
+ addi r12,r12,1
+ stw r12,ee_restarts@l(r10)
+ mr r12,r11 /* restart at exc_exit_restart */
+ blr
+3: /* OK, we can't recover, kill this process */
+ /* but the 601 doesn't implement the RI bit, so assume it's OK */
+BEGIN_FTR_SECTION
+ blr
+END_FTR_SECTION_IFSET(CPU_FTR_601)
+ lwz r3,TRAP(r1)
+ andi. r0,r3,1
+ beq 4f
+ SAVE_NVGPRS(r1)
+ rlwinm r3,r3,0,0,30
+ stw r3,TRAP(r1)
+4: addi r3,r1,STACK_FRAME_OVERHEAD
+ bl nonrecoverable_exception
+ /* shouldn't return */
+ b 4b
+
+ .comm ee_restarts,4
+
+/*
+ * PROM code for specific machines follows. Put it
+ * here so it's easy to add arch-specific sections later.
+ * -- Cort
+ */
+#ifdef CONFIG_PPC_OF
+/*
+ * On CHRP, the Run-Time Abstraction Services (RTAS) have to be
+ * called with the MMU off.
+ */
+_GLOBAL(enter_rtas)
+ stwu r1,-INT_FRAME_SIZE(r1)
+ mflr r0
+ stw r0,INT_FRAME_SIZE+4(r1)
+ lis r4,rtas_data@ha
+ lwz r4,rtas_data@l(r4)
+ lis r6,1f@ha /* physical return address for rtas */
+ addi r6,r6,1f@l
+ tophys(r6,r6)
+ tophys(r7,r1)
+ lis r8,rtas_entry@ha
+ lwz r8,rtas_entry@l(r8)
+ mfmsr r9
+ stw r9,8(r1)
+ LOAD_MSR_KERNEL(r0,MSR_KERNEL)
+ SYNC /* disable interrupts so SRR0/1 */
+ MTMSRD(r0) /* don't get trashed */
+ li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+ mtlr r6
+ CLR_TOP32(r7)
+ mtspr SPRN_SPRG2,r7
+ mtspr SPRN_SRR0,r8
+ mtspr SPRN_SRR1,r9
+ RFI
+1: tophys(r9,r1)
+ lwz r8,INT_FRAME_SIZE+4(r9) /* get return address */
+ lwz r9,8(r9) /* original msr value */
+ FIX_SRR1(r9,r0)
+ addi r1,r1,INT_FRAME_SIZE
+ li r0,0
+ mtspr SPRN_SPRG2,r0
+ mtspr SPRN_SRR0,r8
+ mtspr SPRN_SRR1,r9
+ RFI /* return to caller */
+
+ .globl machine_check_in_rtas
+machine_check_in_rtas:
+ twi 31,0,0
+ /* XXX load up BATs and panic */
+
+#endif /* CONFIG_PPC_OF */
diff --git a/arch/ppc/kernel/find_name.c b/arch/ppc/kernel/find_name.c
new file mode 100644
index 000000000000..3c0fa8e0c077
--- /dev/null
+++ b/arch/ppc/kernel/find_name.c
@@ -0,0 +1,48 @@
+#include <stdio.h>
+#include <asm/page.h>
+#include <sys/mman.h>
+#include <strings.h>
+/*
+ * Finds a given address in the System.map and prints it out
+ * with its neighbors. -- Cort
+ */
+
+int main(int argc, char **argv)
+{
+ unsigned long addr, cmp, i;
+ FILE *f;
+ char s[256], last[256];
+
+ if ( argc < 2 )
+ {
+ fprintf(stderr, "Usage: %s <address>\n", argv[0]);
+ return -1;
+ }
+
+ for ( i = 1 ; argv[i] ; i++ )
+ {
+ sscanf( argv[i], "%0lx", &addr );
+ /* adjust if addr is relative to kernelbase */
+ if ( addr < PAGE_OFFSET )
+ addr += PAGE_OFFSET;
+
+ if ( (f = fopen( "System.map", "r" )) == NULL )
+ {
+ perror("fopen()\n");
+ exit(-1);
+ }
+
+ while ( !feof(f) )
+ {
+ fgets(s, 255 , f);
+ sscanf( s, "%0lx", &cmp );
+ if ( addr < cmp )
+ break;
+ strcpy( last, s);
+ }
+
+ printf( "%s%s", last, s );
+ }
+ fclose(f);
+ return 0;
+}
diff --git a/arch/ppc/kernel/head.S b/arch/ppc/kernel/head.S
new file mode 100644
index 000000000000..1a89a71e0acc
--- /dev/null
+++ b/arch/ppc/kernel/head.S
@@ -0,0 +1,1710 @@
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Adapted for Power Macintosh by Paul Mackerras.
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk).
+ *
+ * This file contains the low-level support and setup for the
+ * PowerPC platform, including trap and interrupt dispatch.
+ * (The PPC 8xx embedded CPUs use head_8xx.S instead.)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+
+#ifdef CONFIG_APUS
+#include <asm/amigappc.h>
+#endif
+
+#ifdef CONFIG_PPC64BRIDGE
+#define LOAD_BAT(n, reg, RA, RB) \
+ ld RA,(n*32)+0(reg); \
+ ld RB,(n*32)+8(reg); \
+ mtspr SPRN_IBAT##n##U,RA; \
+ mtspr SPRN_IBAT##n##L,RB; \
+ ld RA,(n*32)+16(reg); \
+ ld RB,(n*32)+24(reg); \
+ mtspr SPRN_DBAT##n##U,RA; \
+ mtspr SPRN_DBAT##n##L,RB; \
+
+#else /* CONFIG_PPC64BRIDGE */
+
+/* 601 only have IBAT; cr0.eq is set on 601 when using this macro */
+#define LOAD_BAT(n, reg, RA, RB) \
+ /* see the comment for clear_bats() -- Cort */ \
+ li RA,0; \
+ mtspr SPRN_IBAT##n##U,RA; \
+ mtspr SPRN_DBAT##n##U,RA; \
+ lwz RA,(n*16)+0(reg); \
+ lwz RB,(n*16)+4(reg); \
+ mtspr SPRN_IBAT##n##U,RA; \
+ mtspr SPRN_IBAT##n##L,RB; \
+ beq 1f; \
+ lwz RA,(n*16)+8(reg); \
+ lwz RB,(n*16)+12(reg); \
+ mtspr SPRN_DBAT##n##U,RA; \
+ mtspr SPRN_DBAT##n##L,RB; \
+1:
+#endif /* CONFIG_PPC64BRIDGE */
+
+ .text
+ .stabs "arch/ppc/kernel/",N_SO,0,0,0f
+ .stabs "head.S",N_SO,0,0,0f
+0:
+ .globl _stext
+_stext:
+
+/*
+ * _start is defined this way because the XCOFF loader in the OpenFirmware
+ * on the powermac expects the entry point to be a procedure descriptor.
+ */
+ .text
+ .globl _start
+_start:
+ /*
+ * These are here for legacy reasons, the kernel used to
+ * need to look like a coff function entry for the pmac
+ * but we're always started by some kind of bootloader now.
+ * -- Cort
+ */
+ nop /* used by __secondary_hold on prep (mtx) and chrp smp */
+ nop /* used by __secondary_hold on prep (mtx) and chrp smp */
+ nop
+
+/* PMAC
+ * Enter here with the kernel text, data and bss loaded starting at
+ * 0, running with virtual == physical mapping.
+ * r5 points to the prom entry point (the client interface handler
+ * address). Address translation is turned on, with the prom
+ * managing the hash table. Interrupts are disabled. The stack
+ * pointer (r1) points to just below the end of the half-meg region
+ * from 0x380000 - 0x400000, which is mapped in already.
+ *
+ * If we are booted from MacOS via BootX, we enter with the kernel
+ * image loaded somewhere, and the following values in registers:
+ * r3: 'BooX' (0x426f6f58)
+ * r4: virtual address of boot_infos_t
+ * r5: 0
+ *
+ * APUS
+ * r3: 'APUS'
+ * r4: physical address of memory base
+ * Linux/m68k style BootInfo structure at &_end.
+ *
+ * PREP
+ * This is jumped to on prep systems right after the kernel is relocated
+ * to its proper place in memory by the boot loader. The expected layout
+ * of the regs is:
+ * r3: ptr to residual data
+ * r4: initrd_start or if no initrd then 0
+ * r5: initrd_end - unused if r4 is 0
+ * r6: Start of command line string
+ * r7: End of command line string
+ *
+ * This just gets a minimal mmu environment setup so we can call
+ * start_here() to do the real work.
+ * -- Cort
+ */
+
+ .globl __start
+__start:
+/*
+ * We have to do any OF calls before we map ourselves to KERNELBASE,
+ * because OF may have I/O devices mapped into that area
+ * (particularly on CHRP).
+ */
+ mr r31,r3 /* save parameters */
+ mr r30,r4
+ mr r29,r5
+ mr r28,r6
+ mr r27,r7
+ li r24,0 /* cpu # */
+
+/*
+ * early_init() does the early machine identification and does
+ * the necessary low-level setup and clears the BSS
+ * -- Cort <cort@fsmlabs.com>
+ */
+ bl early_init
+
+/*
+ * On POWER4, we first need to tweak some CPU configuration registers
+ * like real mode cache inhibit or exception base
+ */
+#ifdef CONFIG_POWER4
+ bl __970_cpu_preinit
+#endif /* CONFIG_POWER4 */
+
+#ifdef CONFIG_APUS
+/* On APUS the __va/__pa constants need to be set to the correct
+ * values before continuing.
+ */
+ mr r4,r30
+ bl fix_mem_constants
+#endif /* CONFIG_APUS */
+
+/* Switch MMU off, clear BATs and flush TLB. At this point, r3 contains
+ * the physical address we are running at, returned by early_init()
+ */
+ bl mmu_off
+__after_mmu_off:
+#ifndef CONFIG_POWER4
+ bl clear_bats
+ bl flush_tlbs
+
+ bl initial_bats
+#if !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT)
+ bl setup_disp_bat
+#endif
+#else /* CONFIG_POWER4 */
+ bl reloc_offset
+ bl initial_mm_power4
+#endif /* CONFIG_POWER4 */
+
+/*
+ * Call setup_cpu for CPU 0 and initialize 6xx Idle
+ */
+ bl reloc_offset
+ li r24,0 /* cpu# */
+ bl call_setup_cpu /* Call setup_cpu for this CPU */
+#ifdef CONFIG_6xx
+ bl reloc_offset
+ bl init_idle_6xx
+#endif /* CONFIG_6xx */
+#ifdef CONFIG_POWER4
+ bl reloc_offset
+ bl init_idle_power4
+#endif /* CONFIG_POWER4 */
+
+
+#ifndef CONFIG_APUS
+/*
+ * We need to run with _start at physical address 0.
+ * On CHRP, we are loaded at 0x10000 since OF on CHRP uses
+ * the exception vectors at 0 (and therefore this copy
+ * overwrites OF's exception vectors with our own).
+ * If the MMU is already turned on, we copy stuff to KERNELBASE,
+ * otherwise we copy it to 0.
+ */
+ bl reloc_offset
+ mr r26,r3
+ addis r4,r3,KERNELBASE@h /* current address of _start */
+ cmpwi 0,r4,0 /* are we already running at 0? */
+ bne relocate_kernel
+#endif /* CONFIG_APUS */
+/*
+ * we now have the 1st 16M of ram mapped with the bats.
+ * prep needs the mmu to be turned on here, but pmac already has it on.
+ * this shouldn't bother the pmac since it just gets turned on again
+ * as we jump to our code at KERNELBASE. -- Cort
+ * Actually no, pmac doesn't have it on any more. BootX enters with MMU
+ * off, and in other cases, we now turn it off before changing BATs above.
+ */
+turn_on_mmu:
+ mfmsr r0
+ ori r0,r0,MSR_DR|MSR_IR
+ mtspr SPRN_SRR1,r0
+ lis r0,start_here@h
+ ori r0,r0,start_here@l
+ mtspr SPRN_SRR0,r0
+ SYNC
+ RFI /* enables MMU */
+
+/*
+ * We need __secondary_hold as a place to hold the other cpus on
+ * an SMP machine, even when we are running a UP kernel.
+ */
+ . = 0xc0 /* for prep bootloader */
+ li r3,1 /* MTX only has 1 cpu */
+ .globl __secondary_hold
+__secondary_hold:
+ /* tell the master we're here */
+ stw r3,4(0)
+#ifdef CONFIG_SMP
+100: lwz r4,0(0)
+ /* wait until we're told to start */
+ cmpw 0,r4,r3
+ bne 100b
+ /* our cpu # was at addr 0 - go */
+ mr r24,r3 /* cpu # */
+ b __secondary_start
+#else
+ b .
+#endif /* CONFIG_SMP */
+
+/*
+ * Exception entry code. This code runs with address translation
+ * turned off, i.e. using physical addresses.
+ * We assume sprg3 has the physical address of the current
+ * task's thread_struct.
+ */
+#define EXCEPTION_PROLOG \
+ mtspr SPRN_SPRG0,r10; \
+ mtspr SPRN_SPRG1,r11; \
+ mfcr r10; \
+ EXCEPTION_PROLOG_1; \
+ EXCEPTION_PROLOG_2
+
+#define EXCEPTION_PROLOG_1 \
+ mfspr r11,SPRN_SRR1; /* check whether user or kernel */ \
+ andi. r11,r11,MSR_PR; \
+ tophys(r11,r1); /* use tophys(r1) if kernel */ \
+ beq 1f; \
+ mfspr r11,SPRN_SPRG3; \
+ lwz r11,THREAD_INFO-THREAD(r11); \
+ addi r11,r11,THREAD_SIZE; \
+ tophys(r11,r11); \
+1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
+
+
+#define EXCEPTION_PROLOG_2 \
+ CLR_TOP32(r11); \
+ stw r10,_CCR(r11); /* save registers */ \
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mfspr r10,SPRN_SPRG0; \
+ stw r10,GPR10(r11); \
+ mfspr r12,SPRN_SPRG1; \
+ stw r12,GPR11(r11); \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r12,SPRN_SRR0; \
+ mfspr r9,SPRN_SRR1; \
+ stw r1,GPR1(r11); \
+ stw r1,0(r11); \
+ tovirt(r1,r11); /* set new kernel sp */ \
+ li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \
+ MTMSRD(r10); /* (except for mach check in rtas) */ \
+ stw r0,GPR0(r11); \
+ SAVE_4GPRS(3, r11); \
+ SAVE_2GPRS(7, r11)
+
+/*
+ * Note: code which follows this uses cr0.eq (set if from kernel),
+ * r11, r12 (SRR0), and r9 (SRR1).
+ *
+ * Note2: once we have set r1 we are in a position to take exceptions
+ * again, and we could thus set MSR:RI at that point.
+ */
+
+/*
+ * Exception vectors.
+ */
+#define EXCEPTION(n, label, hdlr, xfer) \
+ . = n; \
+label: \
+ EXCEPTION_PROLOG; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ xfer(n, hdlr)
+
+#define EXC_XFER_TEMPLATE(n, hdlr, trap, copyee, tfer, ret) \
+ li r10,trap; \
+ stw r10,TRAP(r11); \
+ li r10,MSR_KERNEL; \
+ copyee(r10, r9); \
+ bl tfer; \
+i##n: \
+ .long hdlr; \
+ .long ret
+
+#define COPY_EE(d, s) rlwimi d,s,0,16,16
+#define NOCOPY(d, s)
+
+#define EXC_XFER_STD(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n, NOCOPY, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n+1, NOCOPY, transfer_to_handler, \
+ ret_from_except)
+
+#define EXC_XFER_EE(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n, COPY_EE, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_EE_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n+1, COPY_EE, transfer_to_handler, \
+ ret_from_except)
+
+/* System reset */
+/* core99 pmac starts the seconary here by changing the vector, and
+ putting it back to what it was (UnknownException) when done. */
+#if defined(CONFIG_GEMINI) && defined(CONFIG_SMP)
+ . = 0x100
+ b __secondary_start_gemini
+#else
+ EXCEPTION(0x100, Reset, UnknownException, EXC_XFER_STD)
+#endif
+
+/* Machine check */
+/*
+ * On CHRP, this is complicated by the fact that we could get a
+ * machine check inside RTAS, and we have no guarantee that certain
+ * critical registers will have the values we expect. The set of
+ * registers that might have bad values includes all the GPRs
+ * and all the BATs. We indicate that we are in RTAS by putting
+ * a non-zero value, the address of the exception frame to use,
+ * in SPRG2. The machine check handler checks SPRG2 and uses its
+ * value if it is non-zero. If we ever needed to free up SPRG2,
+ * we could use a field in the thread_info or thread_struct instead.
+ * (Other exception handlers assume that r1 is a valid kernel stack
+ * pointer when we take an exception from supervisor mode.)
+ * -- paulus.
+ */
+ . = 0x200
+ mtspr SPRN_SPRG0,r10
+ mtspr SPRN_SPRG1,r11
+ mfcr r10
+#ifdef CONFIG_PPC_CHRP
+ mfspr r11,SPRN_SPRG2
+ cmpwi 0,r11,0
+ bne 7f
+#endif /* CONFIG_PPC_CHRP */
+ EXCEPTION_PROLOG_1
+7: EXCEPTION_PROLOG_2
+ addi r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_PPC_CHRP
+ mfspr r4,SPRN_SPRG2
+ cmpwi cr1,r4,0
+ bne cr1,1f
+#endif
+ EXC_XFER_STD(0x200, MachineCheckException)
+#ifdef CONFIG_PPC_CHRP
+1: b machine_check_in_rtas
+#endif
+
+/* Data access exception. */
+ . = 0x300
+#ifdef CONFIG_PPC64BRIDGE
+ b DataAccess
+DataAccessCont:
+#else
+DataAccess:
+ EXCEPTION_PROLOG
+#endif /* CONFIG_PPC64BRIDGE */
+ mfspr r10,SPRN_DSISR
+ andis. r0,r10,0xa470 /* weird error? */
+ bne 1f /* if not, try to put a PTE */
+ mfspr r4,SPRN_DAR /* into the hash table */
+ rlwinm r3,r10,32-15,21,21 /* DSISR_STORE -> _PAGE_RW */
+ bl hash_page
+1: stw r10,_DSISR(r11)
+ mr r5,r10
+ mfspr r4,SPRN_DAR
+ EXC_XFER_EE_LITE(0x300, handle_page_fault)
+
+#ifdef CONFIG_PPC64BRIDGE
+/* SLB fault on data access. */
+ . = 0x380
+ b DataSegment
+#endif /* CONFIG_PPC64BRIDGE */
+
+/* Instruction access exception. */
+ . = 0x400
+#ifdef CONFIG_PPC64BRIDGE
+ b InstructionAccess
+InstructionAccessCont:
+#else
+InstructionAccess:
+ EXCEPTION_PROLOG
+#endif /* CONFIG_PPC64BRIDGE */
+ andis. r0,r9,0x4000 /* no pte found? */
+ beq 1f /* if so, try to put a PTE */
+ li r3,0 /* into the hash table */
+ mr r4,r12 /* SRR0 is fault address */
+ bl hash_page
+1: mr r4,r12
+ mr r5,r9
+ EXC_XFER_EE_LITE(0x400, handle_page_fault)
+
+#ifdef CONFIG_PPC64BRIDGE
+/* SLB fault on instruction access. */
+ . = 0x480
+ b InstructionSegment
+#endif /* CONFIG_PPC64BRIDGE */
+
+/* External interrupt */
+ EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
+
+/* Alignment exception */
+ . = 0x600
+Alignment:
+ EXCEPTION_PROLOG
+ mfspr r4,SPRN_DAR
+ stw r4,_DAR(r11)
+ mfspr r5,SPRN_DSISR
+ stw r5,_DSISR(r11)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_EE(0x600, AlignmentException)
+
+/* Program check exception */
+ EXCEPTION(0x700, ProgramCheck, ProgramCheckException, EXC_XFER_STD)
+
+/* Floating-point unavailable */
+ . = 0x800
+FPUnavailable:
+ EXCEPTION_PROLOG
+ bne load_up_fpu /* if from user, just load it up */
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_EE_LITE(0x800, KernelFP)
+
+/* Decrementer */
+ EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
+
+ EXCEPTION(0xa00, Trap_0a, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0xb00, Trap_0b, UnknownException, EXC_XFER_EE)
+
+/* System call */
+ . = 0xc00
+SystemCall:
+ EXCEPTION_PROLOG
+ EXC_XFER_EE_LITE(0xc00, DoSyscall)
+
+/* Single step - not used on 601 */
+ EXCEPTION(0xd00, SingleStep, SingleStepException, EXC_XFER_STD)
+ EXCEPTION(0xe00, Trap_0e, UnknownException, EXC_XFER_EE)
+
+/*
+ * The Altivec unavailable trap is at 0x0f20. Foo.
+ * We effectively remap it to 0x3000.
+ * We include an altivec unavailable exception vector even if
+ * not configured for Altivec, so that you can't panic a
+ * non-altivec kernel running on a machine with altivec just
+ * by executing an altivec instruction.
+ */
+ . = 0xf00
+ b Trap_0f
+
+ . = 0xf20
+ b AltiVecUnavailable
+
+Trap_0f:
+ EXCEPTION_PROLOG
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_EE(0xf00, UnknownException)
+
+/*
+ * Handle TLB miss for instruction on 603/603e.
+ * Note: we get an alternate set of r0 - r3 to use automatically.
+ */
+ . = 0x1000
+InstructionTLBMiss:
+/*
+ * r0: stored ctr
+ * r1: linux style pte ( later becomes ppc hardware pte )
+ * r2: ptr to linux-style pte
+ * r3: scratch
+ */
+ mfctr r0
+ /* Get PTE (linux-style) and check access */
+ mfspr r3,SPRN_IMISS
+ lis r1,KERNELBASE@h /* check if kernel address */
+ cmplw 0,r3,r1
+ mfspr r2,SPRN_SPRG3
+ li r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */
+ lwz r2,PGDIR(r2)
+ blt+ 112f
+ lis r2,swapper_pg_dir@ha /* if kernel address, use */
+ addi r2,r2,swapper_pg_dir@l /* kernel page table */
+ mfspr r1,SPRN_SRR1 /* and MSR_PR bit from SRR1 */
+ rlwinm r1,r1,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */
+112: tophys(r2,r2)
+ rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ rlwinm. r2,r2,0,0,19 /* extract address of pte page */
+ beq- InstructionAddressInvalid /* return if no mapping */
+ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
+ lwz r3,0(r2) /* get linux-style pte */
+ andc. r1,r1,r3 /* check access & ~permission */
+ bne- InstructionAddressInvalid /* return if access not permitted */
+ ori r3,r3,_PAGE_ACCESSED /* set _PAGE_ACCESSED in pte */
+ /*
+ * NOTE! We are assuming this is not an SMP system, otherwise
+ * we would need to update the pte atomically with lwarx/stwcx.
+ */
+ stw r3,0(r2) /* update PTE (accessed bit) */
+ /* Convert linux-style PTE to low word of PPC-style PTE */
+ rlwinm r1,r3,32-10,31,31 /* _PAGE_RW -> PP lsb */
+ rlwinm r2,r3,32-7,31,31 /* _PAGE_DIRTY -> PP lsb */
+ and r1,r1,r2 /* writable if _RW and _DIRTY */
+ rlwimi r3,r3,32-1,30,30 /* _PAGE_USER -> PP msb */
+ rlwimi r3,r3,32-1,31,31 /* _PAGE_USER -> PP lsb */
+ ori r1,r1,0xe14 /* clear out reserved bits and M */
+ andc r1,r3,r1 /* PP = user? (rw&dirty? 2: 3): 0 */
+ mtspr SPRN_RPA,r1
+ mfspr r3,SPRN_IMISS
+ tlbli r3
+ mfspr r3,SPRN_SRR1 /* Need to restore CR0 */
+ mtcrf 0x80,r3
+ rfi
+InstructionAddressInvalid:
+ mfspr r3,SPRN_SRR1
+ rlwinm r1,r3,9,6,6 /* Get load/store bit */
+
+ addis r1,r1,0x2000
+ mtspr SPRN_DSISR,r1 /* (shouldn't be needed) */
+ mtctr r0 /* Restore CTR */
+ andi. r2,r3,0xFFFF /* Clear upper bits of SRR1 */
+ or r2,r2,r1
+ mtspr SPRN_SRR1,r2
+ mfspr r1,SPRN_IMISS /* Get failing address */
+ rlwinm. r2,r2,0,31,31 /* Check for little endian access */
+ rlwimi r2,r2,1,30,30 /* change 1 -> 3 */
+ xor r1,r1,r2
+ mtspr SPRN_DAR,r1 /* Set fault address */
+ mfmsr r0 /* Restore "normal" registers */
+ xoris r0,r0,MSR_TGPR>>16
+ mtcrf 0x80,r3 /* Restore CR0 */
+ mtmsr r0
+ b InstructionAccess
+
+/*
+ * Handle TLB miss for DATA Load operation on 603/603e
+ */
+ . = 0x1100
+DataLoadTLBMiss:
+/*
+ * r0: stored ctr
+ * r1: linux style pte ( later becomes ppc hardware pte )
+ * r2: ptr to linux-style pte
+ * r3: scratch
+ */
+ mfctr r0
+ /* Get PTE (linux-style) and check access */
+ mfspr r3,SPRN_DMISS
+ lis r1,KERNELBASE@h /* check if kernel address */
+ cmplw 0,r3,r1
+ mfspr r2,SPRN_SPRG3
+ li r1,_PAGE_USER|_PAGE_PRESENT /* low addresses tested as user */
+ lwz r2,PGDIR(r2)
+ blt+ 112f
+ lis r2,swapper_pg_dir@ha /* if kernel address, use */
+ addi r2,r2,swapper_pg_dir@l /* kernel page table */
+ mfspr r1,SPRN_SRR1 /* and MSR_PR bit from SRR1 */
+ rlwinm r1,r1,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */
+112: tophys(r2,r2)
+ rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ rlwinm. r2,r2,0,0,19 /* extract address of pte page */
+ beq- DataAddressInvalid /* return if no mapping */
+ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
+ lwz r3,0(r2) /* get linux-style pte */
+ andc. r1,r1,r3 /* check access & ~permission */
+ bne- DataAddressInvalid /* return if access not permitted */
+ ori r3,r3,_PAGE_ACCESSED /* set _PAGE_ACCESSED in pte */
+ /*
+ * NOTE! We are assuming this is not an SMP system, otherwise
+ * we would need to update the pte atomically with lwarx/stwcx.
+ */
+ stw r3,0(r2) /* update PTE (accessed bit) */
+ /* Convert linux-style PTE to low word of PPC-style PTE */
+ rlwinm r1,r3,32-10,31,31 /* _PAGE_RW -> PP lsb */
+ rlwinm r2,r3,32-7,31,31 /* _PAGE_DIRTY -> PP lsb */
+ and r1,r1,r2 /* writable if _RW and _DIRTY */
+ rlwimi r3,r3,32-1,30,30 /* _PAGE_USER -> PP msb */
+ rlwimi r3,r3,32-1,31,31 /* _PAGE_USER -> PP lsb */
+ ori r1,r1,0xe14 /* clear out reserved bits and M */
+ andc r1,r3,r1 /* PP = user? (rw&dirty? 2: 3): 0 */
+ mtspr SPRN_RPA,r1
+ mfspr r3,SPRN_DMISS
+ tlbld r3
+ mfspr r3,SPRN_SRR1 /* Need to restore CR0 */
+ mtcrf 0x80,r3
+ rfi
+DataAddressInvalid:
+ mfspr r3,SPRN_SRR1
+ rlwinm r1,r3,9,6,6 /* Get load/store bit */
+ addis r1,r1,0x2000
+ mtspr SPRN_DSISR,r1
+ mtctr r0 /* Restore CTR */
+ andi. r2,r3,0xFFFF /* Clear upper bits of SRR1 */
+ mtspr SPRN_SRR1,r2
+ mfspr r1,SPRN_DMISS /* Get failing address */
+ rlwinm. r2,r2,0,31,31 /* Check for little endian access */
+ beq 20f /* Jump if big endian */
+ xori r1,r1,3
+20: mtspr SPRN_DAR,r1 /* Set fault address */
+ mfmsr r0 /* Restore "normal" registers */
+ xoris r0,r0,MSR_TGPR>>16
+ mtcrf 0x80,r3 /* Restore CR0 */
+ mtmsr r0
+ b DataAccess
+
+/*
+ * Handle TLB miss for DATA Store on 603/603e
+ */
+ . = 0x1200
+DataStoreTLBMiss:
+/*
+ * r0: stored ctr
+ * r1: linux style pte ( later becomes ppc hardware pte )
+ * r2: ptr to linux-style pte
+ * r3: scratch
+ */
+ mfctr r0
+ /* Get PTE (linux-style) and check access */
+ mfspr r3,SPRN_DMISS
+ lis r1,KERNELBASE@h /* check if kernel address */
+ cmplw 0,r3,r1
+ mfspr r2,SPRN_SPRG3
+ li r1,_PAGE_RW|_PAGE_USER|_PAGE_PRESENT /* access flags */
+ lwz r2,PGDIR(r2)
+ blt+ 112f
+ lis r2,swapper_pg_dir@ha /* if kernel address, use */
+ addi r2,r2,swapper_pg_dir@l /* kernel page table */
+ mfspr r1,SPRN_SRR1 /* and MSR_PR bit from SRR1 */
+ rlwinm r1,r1,32-12,29,29 /* shift MSR_PR to _PAGE_USER posn */
+112: tophys(r2,r2)
+ rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ rlwinm. r2,r2,0,0,19 /* extract address of pte page */
+ beq- DataAddressInvalid /* return if no mapping */
+ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
+ lwz r3,0(r2) /* get linux-style pte */
+ andc. r1,r1,r3 /* check access & ~permission */
+ bne- DataAddressInvalid /* return if access not permitted */
+ ori r3,r3,_PAGE_ACCESSED|_PAGE_DIRTY
+ /*
+ * NOTE! We are assuming this is not an SMP system, otherwise
+ * we would need to update the pte atomically with lwarx/stwcx.
+ */
+ stw r3,0(r2) /* update PTE (accessed/dirty bits) */
+ /* Convert linux-style PTE to low word of PPC-style PTE */
+ rlwimi r3,r3,32-1,30,30 /* _PAGE_USER -> PP msb */
+ li r1,0xe15 /* clear out reserved bits and M */
+ andc r1,r3,r1 /* PP = user? 2: 0 */
+ mtspr SPRN_RPA,r1
+ mfspr r3,SPRN_DMISS
+ tlbld r3
+ mfspr r3,SPRN_SRR1 /* Need to restore CR0 */
+ mtcrf 0x80,r3
+ rfi
+
+#ifndef CONFIG_ALTIVEC
+#define AltivecAssistException UnknownException
+#endif
+
+ EXCEPTION(0x1300, Trap_13, InstructionBreakpoint, EXC_XFER_EE)
+ EXCEPTION(0x1400, SMI, SMIException, EXC_XFER_EE)
+ EXCEPTION(0x1500, Trap_15, UnknownException, EXC_XFER_EE)
+#ifdef CONFIG_POWER4
+ EXCEPTION(0x1600, Trap_16, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1700, Trap_17, AltivecAssistException, EXC_XFER_EE)
+ EXCEPTION(0x1800, Trap_18, TAUException, EXC_XFER_STD)
+#else /* !CONFIG_POWER4 */
+ EXCEPTION(0x1600, Trap_16, AltivecAssistException, EXC_XFER_EE)
+ EXCEPTION(0x1700, Trap_17, TAUException, EXC_XFER_STD)
+ EXCEPTION(0x1800, Trap_18, UnknownException, EXC_XFER_EE)
+#endif /* CONFIG_POWER4 */
+ EXCEPTION(0x1900, Trap_19, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1a00, Trap_1a, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1b00, Trap_1b, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1c00, Trap_1c, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1d00, Trap_1d, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1e00, Trap_1e, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1f00, Trap_1f, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2000, RunMode, RunModeException, EXC_XFER_EE)
+ EXCEPTION(0x2100, Trap_21, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2200, Trap_22, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2300, Trap_23, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2400, Trap_24, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2500, Trap_25, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2600, Trap_26, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2700, Trap_27, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2800, Trap_28, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2900, Trap_29, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2a00, Trap_2a, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2b00, Trap_2b, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2c00, Trap_2c, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2d00, Trap_2d, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2e00, Trap_2e, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x2f00, MOLTrampoline, UnknownException, EXC_XFER_EE_LITE)
+
+ .globl mol_trampoline
+ .set mol_trampoline, i0x2f00
+
+ . = 0x3000
+
+AltiVecUnavailable:
+ EXCEPTION_PROLOG
+#ifdef CONFIG_ALTIVEC
+ bne load_up_altivec /* if from user, just load it up */
+#endif /* CONFIG_ALTIVEC */
+ EXC_XFER_EE_LITE(0xf20, AltivecUnavailException)
+
+#ifdef CONFIG_PPC64BRIDGE
+DataAccess:
+ EXCEPTION_PROLOG
+ b DataAccessCont
+
+InstructionAccess:
+ EXCEPTION_PROLOG
+ b InstructionAccessCont
+
+DataSegment:
+ EXCEPTION_PROLOG
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ mfspr r4,SPRN_DAR
+ stw r4,_DAR(r11)
+ EXC_XFER_STD(0x380, UnknownException)
+
+InstructionSegment:
+ EXCEPTION_PROLOG
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_STD(0x480, UnknownException)
+#endif /* CONFIG_PPC64BRIDGE */
+
+/*
+ * This task wants to use the FPU now.
+ * On UP, disable FP for the task which had the FPU previously,
+ * and save its floating-point registers in its thread_struct.
+ * Load up this task's FP registers from its thread_struct,
+ * enable the FPU for the current task and return to the task.
+ */
+load_up_fpu:
+ mfmsr r5
+ ori r5,r5,MSR_FP
+#ifdef CONFIG_PPC64BRIDGE
+ clrldi r5,r5,1 /* turn off 64-bit mode */
+#endif /* CONFIG_PPC64BRIDGE */
+ SYNC
+ MTMSRD(r5) /* enable use of fpu now */
+ isync
+/*
+ * For SMP, we don't do lazy FPU switching because it just gets too
+ * horrendously complex, especially when a task switches from one CPU
+ * to another. Instead we call giveup_fpu in switch_to.
+ */
+#ifndef CONFIG_SMP
+ tophys(r6,0) /* get __pa constant */
+ addis r3,r6,last_task_used_math@ha
+ lwz r4,last_task_used_math@l(r3)
+ cmpwi 0,r4,0
+ beq 1f
+ add r4,r4,r6
+ addi r4,r4,THREAD /* want last_task_used_math->thread */
+ SAVE_32FPRS(0, r4)
+ mffs fr0
+ stfd fr0,THREAD_FPSCR-4(r4)
+ lwz r5,PT_REGS(r4)
+ add r5,r5,r6
+ lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ li r10,MSR_FP|MSR_FE0|MSR_FE1
+ andc r4,r4,r10 /* disable FP for previous task */
+ stw r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+ /* enable use of FP after return */
+ mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */
+ lwz r4,THREAD_FPEXC_MODE(r5)
+ ori r9,r9,MSR_FP /* enable FP for current */
+ or r9,r9,r4
+ lfd fr0,THREAD_FPSCR-4(r5)
+ mtfsf 0xff,fr0
+ REST_32FPRS(0, r5)
+#ifndef CONFIG_SMP
+ subi r4,r5,THREAD
+ sub r4,r4,r6
+ stw r4,last_task_used_math@l(r3)
+#endif /* CONFIG_SMP */
+ /* restore registers and return */
+ /* we haven't used ctr or xer or lr */
+ /* fall through to fast_exception_return */
+
+ .globl fast_exception_return
+fast_exception_return:
+ andi. r10,r9,MSR_RI /* check for recoverable interrupt */
+ beq 1f /* if not, we've got problems */
+2: REST_4GPRS(3, r11)
+ lwz r10,_CCR(r11)
+ REST_GPR(1, r11)
+ mtcr r10
+ lwz r10,_LINK(r11)
+ mtlr r10
+ REST_GPR(10, r11)
+ mtspr SPRN_SRR1,r9
+ mtspr SPRN_SRR0,r12
+ REST_GPR(9, r11)
+ REST_GPR(12, r11)
+ lwz r11,GPR11(r11)
+ SYNC
+ RFI
+
+/* check if the exception happened in a restartable section */
+1: lis r3,exc_exit_restart_end@ha
+ addi r3,r3,exc_exit_restart_end@l
+ cmplw r12,r3
+ bge 3f
+ lis r4,exc_exit_restart@ha
+ addi r4,r4,exc_exit_restart@l
+ cmplw r12,r4
+ blt 3f
+ lis r3,fee_restarts@ha
+ tophys(r3,r3)
+ lwz r5,fee_restarts@l(r3)
+ addi r5,r5,1
+ stw r5,fee_restarts@l(r3)
+ mr r12,r4 /* restart at exc_exit_restart */
+ b 2b
+
+ .comm fee_restarts,4
+
+/* aargh, a nonrecoverable interrupt, panic */
+/* aargh, we don't know which trap this is */
+/* but the 601 doesn't implement the RI bit, so assume it's OK */
+3:
+BEGIN_FTR_SECTION
+ b 2b
+END_FTR_SECTION_IFSET(CPU_FTR_601)
+ li r10,-1
+ stw r10,TRAP(r11)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ li r10,MSR_KERNEL
+ bl transfer_to_handler_full
+ .long nonrecoverable_exception
+ .long ret_from_except
+
+/*
+ * FP unavailable trap from kernel - print a message, but let
+ * the task use FP in the kernel until it returns to user mode.
+ */
+KernelFP:
+ lwz r3,_MSR(r1)
+ ori r3,r3,MSR_FP
+ stw r3,_MSR(r1) /* enable use of FP after return */
+ lis r3,86f@h
+ ori r3,r3,86f@l
+ mr r4,r2 /* current */
+ lwz r5,_NIP(r1)
+ bl printk
+ b ret_from_except
+86: .string "floating point used in kernel (task=%p, pc=%x)\n"
+ .align 4,0
+
+#ifdef CONFIG_ALTIVEC
+/* Note that the AltiVec support is closely modeled after the FP
+ * support. Changes to one are likely to be applicable to the
+ * other! */
+load_up_altivec:
+/*
+ * Disable AltiVec for the task which had AltiVec previously,
+ * and save its AltiVec registers in its thread_struct.
+ * Enables AltiVec for use in the kernel on return.
+ * On SMP we know the AltiVec units are free, since we give it up every
+ * switch. -- Kumar
+ */
+ mfmsr r5
+ oris r5,r5,MSR_VEC@h
+ MTMSRD(r5) /* enable use of AltiVec now */
+ isync
+/*
+ * For SMP, we don't do lazy AltiVec switching because it just gets too
+ * horrendously complex, especially when a task switches from one CPU
+ * to another. Instead we call giveup_altivec in switch_to.
+ */
+#ifndef CONFIG_SMP
+ tophys(r6,0)
+ addis r3,r6,last_task_used_altivec@ha
+ lwz r4,last_task_used_altivec@l(r3)
+ cmpwi 0,r4,0
+ beq 1f
+ add r4,r4,r6
+ addi r4,r4,THREAD /* want THREAD of last_task_used_altivec */
+ SAVE_32VR(0,r10,r4)
+ mfvscr vr0
+ li r10,THREAD_VSCR
+ stvx vr0,r10,r4
+ lwz r5,PT_REGS(r4)
+ add r5,r5,r6
+ lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ lis r10,MSR_VEC@h
+ andc r4,r4,r10 /* disable altivec for previous task */
+ stw r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+ /* enable use of AltiVec after return */
+ oris r9,r9,MSR_VEC@h
+ mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */
+ li r4,1
+ li r10,THREAD_VSCR
+ stw r4,THREAD_USED_VR(r5)
+ lvx vr0,r10,r5
+ mtvscr vr0
+ REST_32VR(0,r10,r5)
+#ifndef CONFIG_SMP
+ subi r4,r5,THREAD
+ sub r4,r4,r6
+ stw r4,last_task_used_altivec@l(r3)
+#endif /* CONFIG_SMP */
+ /* restore registers and return */
+ /* we haven't used ctr or xer or lr */
+ b fast_exception_return
+
+/*
+ * AltiVec unavailable trap from kernel - print a message, but let
+ * the task use AltiVec in the kernel until it returns to user mode.
+ */
+KernelAltiVec:
+ lwz r3,_MSR(r1)
+ oris r3,r3,MSR_VEC@h
+ stw r3,_MSR(r1) /* enable use of AltiVec after return */
+ lis r3,87f@h
+ ori r3,r3,87f@l
+ mr r4,r2 /* current */
+ lwz r5,_NIP(r1)
+ bl printk
+ b ret_from_except
+87: .string "AltiVec used in kernel (task=%p, pc=%x) \n"
+ .align 4,0
+
+/*
+ * giveup_altivec(tsk)
+ * Disable AltiVec for the task given as the argument,
+ * and save the AltiVec registers in its thread_struct.
+ * Enables AltiVec for use in the kernel on return.
+ */
+
+ .globl giveup_altivec
+giveup_altivec:
+ mfmsr r5
+ oris r5,r5,MSR_VEC@h
+ SYNC
+ MTMSRD(r5) /* enable use of AltiVec now */
+ isync
+ cmpwi 0,r3,0
+ beqlr- /* if no previous owner, done */
+ addi r3,r3,THREAD /* want THREAD of task */
+ lwz r5,PT_REGS(r3)
+ cmpwi 0,r5,0
+ SAVE_32VR(0, r4, r3)
+ mfvscr vr0
+ li r4,THREAD_VSCR
+ stvx vr0,r4,r3
+ beq 1f
+ lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ lis r3,MSR_VEC@h
+ andc r4,r4,r3 /* disable AltiVec for previous task */
+ stw r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#ifndef CONFIG_SMP
+ li r5,0
+ lis r4,last_task_used_altivec@ha
+ stw r5,last_task_used_altivec@l(r4)
+#endif /* CONFIG_SMP */
+ blr
+#endif /* CONFIG_ALTIVEC */
+
+/*
+ * giveup_fpu(tsk)
+ * Disable FP for the task given as the argument,
+ * and save the floating-point registers in its thread_struct.
+ * Enables the FPU for use in the kernel on return.
+ */
+ .globl giveup_fpu
+giveup_fpu:
+ mfmsr r5
+ ori r5,r5,MSR_FP
+ SYNC_601
+ ISYNC_601
+ MTMSRD(r5) /* enable use of fpu now */
+ SYNC_601
+ isync
+ cmpwi 0,r3,0
+ beqlr- /* if no previous owner, done */
+ addi r3,r3,THREAD /* want THREAD of task */
+ lwz r5,PT_REGS(r3)
+ cmpwi 0,r5,0
+ SAVE_32FPRS(0, r3)
+ mffs fr0
+ stfd fr0,THREAD_FPSCR-4(r3)
+ beq 1f
+ lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ li r3,MSR_FP|MSR_FE0|MSR_FE1
+ andc r4,r4,r3 /* disable FP for previous task */
+ stw r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#ifndef CONFIG_SMP
+ li r5,0
+ lis r4,last_task_used_math@ha
+ stw r5,last_task_used_math@l(r4)
+#endif /* CONFIG_SMP */
+ blr
+
+/*
+ * This code is jumped to from the startup code to copy
+ * the kernel image to physical address 0.
+ */
+relocate_kernel:
+ addis r9,r26,klimit@ha /* fetch klimit */
+ lwz r25,klimit@l(r9)
+ addis r25,r25,-KERNELBASE@h
+ li r3,0 /* Destination base address */
+ li r6,0 /* Destination offset */
+ li r5,0x4000 /* # bytes of memory to copy */
+ bl copy_and_flush /* copy the first 0x4000 bytes */
+ addi r0,r3,4f@l /* jump to the address of 4f */
+ mtctr r0 /* in copy and do the rest. */
+ bctr /* jump to the copy */
+4: mr r5,r25
+ bl copy_and_flush /* copy the rest */
+ b turn_on_mmu
+
+/*
+ * Copy routine used to copy the kernel to start at physical address 0
+ * and flush and invalidate the caches as needed.
+ * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset
+ * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5.
+ */
+copy_and_flush:
+ addi r5,r5,-4
+ addi r6,r6,-4
+4: li r0,L1_CACHE_LINE_SIZE/4
+ mtctr r0
+3: addi r6,r6,4 /* copy a cache line */
+ lwzx r0,r6,r4
+ stwx r0,r6,r3
+ bdnz 3b
+ dcbst r6,r3 /* write it to memory */
+ sync
+ icbi r6,r3 /* flush the icache line */
+ cmplw 0,r6,r5
+ blt 4b
+ sync /* additional sync needed on g4 */
+ isync
+ addi r5,r5,4
+ addi r6,r6,4
+ blr
+
+#ifdef CONFIG_APUS
+/*
+ * On APUS the physical base address of the kernel is not known at compile
+ * time, which means the __pa/__va constants used are incorrect. In the
+ * __init section is recorded the virtual addresses of instructions using
+ * these constants, so all that has to be done is fix these before
+ * continuing the kernel boot.
+ *
+ * r4 = The physical address of the kernel base.
+ */
+fix_mem_constants:
+ mr r10,r4
+ addis r10,r10,-KERNELBASE@h /* virt_to_phys constant */
+ neg r11,r10 /* phys_to_virt constant */
+
+ lis r12,__vtop_table_begin@h
+ ori r12,r12,__vtop_table_begin@l
+ add r12,r12,r10 /* table begin phys address */
+ lis r13,__vtop_table_end@h
+ ori r13,r13,__vtop_table_end@l
+ add r13,r13,r10 /* table end phys address */
+ subi r12,r12,4
+ subi r13,r13,4
+1: lwzu r14,4(r12) /* virt address of instruction */
+ add r14,r14,r10 /* phys address of instruction */
+ lwz r15,0(r14) /* instruction, now insert top */
+ rlwimi r15,r10,16,16,31 /* half of vp const in low half */
+ stw r15,0(r14) /* of instruction and restore. */
+ dcbst r0,r14 /* write it to memory */
+ sync
+ icbi r0,r14 /* flush the icache line */
+ cmpw r12,r13
+ bne 1b
+ sync /* additional sync needed on g4 */
+ isync
+
+/*
+ * Map the memory where the exception handlers will
+ * be copied to when hash constants have been patched.
+ */
+#ifdef CONFIG_APUS_FAST_EXCEPT
+ lis r8,0xfff0
+#else
+ lis r8,0
+#endif
+ ori r8,r8,0x2 /* 128KB, supervisor */
+ mtspr SPRN_DBAT3U,r8
+ mtspr SPRN_DBAT3L,r8
+
+ lis r12,__ptov_table_begin@h
+ ori r12,r12,__ptov_table_begin@l
+ add r12,r12,r10 /* table begin phys address */
+ lis r13,__ptov_table_end@h
+ ori r13,r13,__ptov_table_end@l
+ add r13,r13,r10 /* table end phys address */
+ subi r12,r12,4
+ subi r13,r13,4
+1: lwzu r14,4(r12) /* virt address of instruction */
+ add r14,r14,r10 /* phys address of instruction */
+ lwz r15,0(r14) /* instruction, now insert top */
+ rlwimi r15,r11,16,16,31 /* half of pv const in low half*/
+ stw r15,0(r14) /* of instruction and restore. */
+ dcbst r0,r14 /* write it to memory */
+ sync
+ icbi r0,r14 /* flush the icache line */
+ cmpw r12,r13
+ bne 1b
+
+ sync /* additional sync needed on g4 */
+ isync /* No speculative loading until now */
+ blr
+
+/***********************************************************************
+ * Please note that on APUS the exception handlers are located at the
+ * physical address 0xfff0000. For this reason, the exception handlers
+ * cannot use relative branches to access the code below.
+ ***********************************************************************/
+#endif /* CONFIG_APUS */
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_GEMINI
+ .globl __secondary_start_gemini
+__secondary_start_gemini:
+ mfspr r4,SPRN_HID0
+ ori r4,r4,HID0_ICFI
+ li r3,0
+ ori r3,r3,HID0_ICE
+ andc r4,r4,r3
+ mtspr SPRN_HID0,r4
+ sync
+ bl gemini_prom_init
+ b __secondary_start
+#endif /* CONFIG_GEMINI */
+ .globl __secondary_start_psurge
+__secondary_start_psurge:
+ li r24,1 /* cpu # */
+ b __secondary_start_psurge99
+ .globl __secondary_start_psurge2
+__secondary_start_psurge2:
+ li r24,2 /* cpu # */
+ b __secondary_start_psurge99
+ .globl __secondary_start_psurge3
+__secondary_start_psurge3:
+ li r24,3 /* cpu # */
+ b __secondary_start_psurge99
+__secondary_start_psurge99:
+ /* we come in here with IR=0 and DR=1, and DBAT 0
+ set to map the 0xf0000000 - 0xffffffff region */
+ mfmsr r0
+ rlwinm r0,r0,0,28,26 /* clear DR (0x10) */
+ SYNC
+ mtmsr r0
+ isync
+
+ .globl __secondary_start
+__secondary_start:
+#ifdef CONFIG_PPC64BRIDGE
+ mfmsr r0
+ clrldi r0,r0,1 /* make sure it's in 32-bit mode */
+ SYNC
+ MTMSRD(r0)
+ isync
+#endif
+ /* Copy some CPU settings from CPU 0 */
+ bl __restore_cpu_setup
+
+ lis r3,-KERNELBASE@h
+ mr r4,r24
+ bl identify_cpu
+ bl call_setup_cpu /* Call setup_cpu for this CPU */
+#ifdef CONFIG_6xx
+ lis r3,-KERNELBASE@h
+ bl init_idle_6xx
+#endif /* CONFIG_6xx */
+#ifdef CONFIG_POWER4
+ lis r3,-KERNELBASE@h
+ bl init_idle_power4
+#endif /* CONFIG_POWER4 */
+
+ /* get current_thread_info and current */
+ lis r1,secondary_ti@ha
+ tophys(r1,r1)
+ lwz r1,secondary_ti@l(r1)
+ tophys(r2,r1)
+ lwz r2,TI_TASK(r2)
+
+ /* stack */
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+ li r0,0
+ tophys(r3,r1)
+ stw r0,0(r3)
+
+ /* load up the MMU */
+ bl load_up_mmu
+
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* phys address of our thread_struct */
+ CLR_TOP32(r4)
+ mtspr SPRN_SPRG3,r4
+ li r3,0
+ mtspr SPRN_SPRG2,r3 /* 0 => not in RTAS */
+
+ /* enable MMU and jump to start_secondary */
+ li r4,MSR_KERNEL
+ FIX_SRR1(r4,r5)
+ lis r3,start_secondary@h
+ ori r3,r3,start_secondary@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ SYNC
+ RFI
+#endif /* CONFIG_SMP */
+
+/*
+ * Those generic dummy functions are kept for CPUs not
+ * included in CONFIG_6xx
+ */
+_GLOBAL(__setup_cpu_power3)
+ blr
+_GLOBAL(__setup_cpu_generic)
+ blr
+
+#if !defined(CONFIG_6xx) && !defined(CONFIG_POWER4)
+_GLOBAL(__save_cpu_setup)
+ blr
+_GLOBAL(__restore_cpu_setup)
+ blr
+#endif /* !defined(CONFIG_6xx) && !defined(CONFIG_POWER4) */
+
+
+/*
+ * Load stuff into the MMU. Intended to be called with
+ * IR=0 and DR=0.
+ */
+load_up_mmu:
+ sync /* Force all PTE updates to finish */
+ isync
+ tlbia /* Clear all TLB entries */
+ sync /* wait for tlbia/tlbie to finish */
+ TLBSYNC /* ... on all CPUs */
+ /* Load the SDR1 register (hash table base & size) */
+ lis r6,_SDR1@ha
+ tophys(r6,r6)
+ lwz r6,_SDR1@l(r6)
+ mtspr SPRN_SDR1,r6
+#ifdef CONFIG_PPC64BRIDGE
+ /* clear the ASR so we only use the pseudo-segment registers. */
+ li r6,0
+ mtasr r6
+#endif /* CONFIG_PPC64BRIDGE */
+ li r0,16 /* load up segment register values */
+ mtctr r0 /* for context 0 */
+ lis r3,0x2000 /* Ku = 1, VSID = 0 */
+ li r4,0
+3: mtsrin r3,r4
+ addi r3,r3,0x111 /* increment VSID */
+ addis r4,r4,0x1000 /* address of next segment */
+ bdnz 3b
+#ifndef CONFIG_POWER4
+/* Load the BAT registers with the values set up by MMU_init.
+ MMU_init takes care of whether we're on a 601 or not. */
+ mfpvr r3
+ srwi r3,r3,16
+ cmpwi r3,1
+ lis r3,BATS@ha
+ addi r3,r3,BATS@l
+ tophys(r3,r3)
+ LOAD_BAT(0,r3,r4,r5)
+ LOAD_BAT(1,r3,r4,r5)
+ LOAD_BAT(2,r3,r4,r5)
+ LOAD_BAT(3,r3,r4,r5)
+#endif /* CONFIG_POWER4 */
+ blr
+
+/*
+ * This is where the main kernel code starts.
+ */
+start_here:
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+ /* Set up for using our exception vectors */
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* init task's THREAD */
+ CLR_TOP32(r4)
+ mtspr SPRN_SPRG3,r4
+ li r3,0
+ mtspr SPRN_SPRG2,r3 /* 0 => not in RTAS */
+
+ /* stack */
+ lis r1,init_thread_union@ha
+ addi r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+/*
+ * Do early bootinfo parsing, platform-specific initialization,
+ * and set up the MMU.
+ */
+ mr r3,r31
+ mr r4,r30
+ mr r5,r29
+ mr r6,r28
+ mr r7,r27
+ bl machine_init
+ bl MMU_init
+
+#ifdef CONFIG_APUS
+ /* Copy exception code to exception vector base on APUS. */
+ lis r4,KERNELBASE@h
+#ifdef CONFIG_APUS_FAST_EXCEPT
+ lis r3,0xfff0 /* Copy to 0xfff00000 */
+#else
+ lis r3,0 /* Copy to 0x00000000 */
+#endif
+ li r5,0x4000 /* # bytes of memory to copy */
+ li r6,0
+ bl copy_and_flush /* copy the first 0x4000 bytes */
+#endif /* CONFIG_APUS */
+
+/*
+ * Go back to running unmapped so we can load up new values
+ * for SDR1 (hash table pointer) and the segment registers
+ * and change to using our exception vectors.
+ */
+ lis r4,2f@h
+ ori r4,r4,2f@l
+ tophys(r4,r4)
+ li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+ FIX_SRR1(r3,r5)
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ SYNC
+ RFI
+/* Load up the kernel context */
+2: bl load_up_mmu
+
+#ifdef CONFIG_BDI_SWITCH
+ /* Add helper information for the Abatron bdiGDB debugger.
+ * We do this here because we know the mmu is disabled, and
+ * will be enabled for real in just a few instructions.
+ */
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r5, 0xf0(r0) /* This much match your Abatron config */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ tophys(r5, r5)
+ stw r6, 0(r5)
+#endif /* CONFIG_BDI_SWITCH */
+
+/* Now turn on the MMU for real! */
+ li r4,MSR_KERNEL
+ FIX_SRR1(r4,r5)
+ lis r3,start_kernel@h
+ ori r3,r3,start_kernel@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ SYNC
+ RFI
+
+/*
+ * Set up the segment registers for a new context.
+ */
+_GLOBAL(set_context)
+ mulli r3,r3,897 /* multiply context by skew factor */
+ rlwinm r3,r3,4,8,27 /* VSID = (context & 0xfffff) << 4 */
+ addis r3,r3,0x6000 /* Set Ks, Ku bits */
+ li r0,NUM_USER_SEGMENTS
+ mtctr r0
+
+#ifdef CONFIG_BDI_SWITCH
+ /* Context switch the PTE pointer for the Abatron BDI2000.
+ * The PGDIR is passed as second argument.
+ */
+ lis r5, KERNELBASE@h
+ lwz r5, 0xf0(r5)
+ stw r4, 0x4(r5)
+#endif
+ li r4,0
+ isync
+3:
+#ifdef CONFIG_PPC64BRIDGE
+ slbie r4
+#endif /* CONFIG_PPC64BRIDGE */
+ mtsrin r3,r4
+ addi r3,r3,0x111 /* next VSID */
+ rlwinm r3,r3,0,8,3 /* clear out any overflow from VSID field */
+ addis r4,r4,0x1000 /* address of next segment */
+ bdnz 3b
+ sync
+ isync
+ blr
+
+/*
+ * An undocumented "feature" of 604e requires that the v bit
+ * be cleared before changing BAT values.
+ *
+ * Also, newer IBM firmware does not clear bat3 and 4 so
+ * this makes sure it's done.
+ * -- Cort
+ */
+clear_bats:
+ li r10,0
+ mfspr r9,SPRN_PVR
+ rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */
+ cmpwi r9, 1
+ beq 1f
+
+ mtspr SPRN_DBAT0U,r10
+ mtspr SPRN_DBAT0L,r10
+ mtspr SPRN_DBAT1U,r10
+ mtspr SPRN_DBAT1L,r10
+ mtspr SPRN_DBAT2U,r10
+ mtspr SPRN_DBAT2L,r10
+ mtspr SPRN_DBAT3U,r10
+ mtspr SPRN_DBAT3L,r10
+1:
+ mtspr SPRN_IBAT0U,r10
+ mtspr SPRN_IBAT0L,r10
+ mtspr SPRN_IBAT1U,r10
+ mtspr SPRN_IBAT1L,r10
+ mtspr SPRN_IBAT2U,r10
+ mtspr SPRN_IBAT2L,r10
+ mtspr SPRN_IBAT3U,r10
+ mtspr SPRN_IBAT3L,r10
+BEGIN_FTR_SECTION
+ /* Here's a tweak: at this point, CPU setup have
+ * not been called yet, so HIGH_BAT_EN may not be
+ * set in HID0 for the 745x processors. However, it
+ * seems that doesn't affect our ability to actually
+ * write to these SPRs.
+ */
+ mtspr SPRN_DBAT4U,r10
+ mtspr SPRN_DBAT4L,r10
+ mtspr SPRN_DBAT5U,r10
+ mtspr SPRN_DBAT5L,r10
+ mtspr SPRN_DBAT6U,r10
+ mtspr SPRN_DBAT6L,r10
+ mtspr SPRN_DBAT7U,r10
+ mtspr SPRN_DBAT7L,r10
+ mtspr SPRN_IBAT4U,r10
+ mtspr SPRN_IBAT4L,r10
+ mtspr SPRN_IBAT5U,r10
+ mtspr SPRN_IBAT5L,r10
+ mtspr SPRN_IBAT6U,r10
+ mtspr SPRN_IBAT6L,r10
+ mtspr SPRN_IBAT7U,r10
+ mtspr SPRN_IBAT7L,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+ blr
+
+flush_tlbs:
+ lis r10, 0x40
+1: addic. r10, r10, -0x1000
+ tlbie r10
+ blt 1b
+ sync
+ blr
+
+mmu_off:
+ addi r4, r3, __after_mmu_off - _start
+ mfmsr r3
+ andi. r0,r3,MSR_DR|MSR_IR /* MMU enabled? */
+ beqlr
+ andc r3,r3,r0
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ sync
+ RFI
+
+#ifndef CONFIG_POWER4
+/*
+ * Use the first pair of BAT registers to map the 1st 16MB
+ * of RAM to KERNELBASE. From this point on we can't safely
+ * call OF any more.
+ */
+initial_bats:
+ lis r11,KERNELBASE@h
+#ifndef CONFIG_PPC64BRIDGE
+ mfspr r9,SPRN_PVR
+ rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */
+ cmpwi 0,r9,1
+ bne 4f
+ ori r11,r11,4 /* set up BAT registers for 601 */
+ li r8,0x7f /* valid, block length = 8MB */
+ oris r9,r11,0x800000@h /* set up BAT reg for 2nd 8M */
+ oris r10,r8,0x800000@h /* set up BAT reg for 2nd 8M */
+ mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */
+ mtspr SPRN_IBAT0L,r8 /* lower BAT register */
+ mtspr SPRN_IBAT1U,r9
+ mtspr SPRN_IBAT1L,r10
+ isync
+ blr
+#endif /* CONFIG_PPC64BRIDGE */
+
+4: tophys(r8,r11)
+#ifdef CONFIG_SMP
+ ori r8,r8,0x12 /* R/W access, M=1 */
+#else
+ ori r8,r8,2 /* R/W access */
+#endif /* CONFIG_SMP */
+#ifdef CONFIG_APUS
+ ori r11,r11,BL_8M<<2|0x2 /* set up 8MB BAT registers for 604 */
+#else
+ ori r11,r11,BL_256M<<2|0x2 /* set up BAT registers for 604 */
+#endif /* CONFIG_APUS */
+
+#ifdef CONFIG_PPC64BRIDGE
+ /* clear out the high 32 bits in the BAT */
+ clrldi r11,r11,32
+ clrldi r8,r8,32
+#endif /* CONFIG_PPC64BRIDGE */
+ mtspr SPRN_DBAT0L,r8 /* N.B. 6xx (not 601) have valid */
+ mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */
+ mtspr SPRN_IBAT0L,r8
+ mtspr SPRN_IBAT0U,r11
+ isync
+ blr
+
+#if !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT)
+setup_disp_bat:
+ /*
+ * setup the display bat prepared for us in prom.c
+ */
+ mflr r8
+ bl reloc_offset
+ mtlr r8
+ addis r8,r3,disp_BAT@ha
+ addi r8,r8,disp_BAT@l
+ lwz r11,0(r8)
+ lwz r8,4(r8)
+ mfspr r9,SPRN_PVR
+ rlwinm r9,r9,16,16,31 /* r9 = 1 for 601, 4 for 604 */
+ cmpwi 0,r9,1
+ beq 1f
+ mtspr SPRN_DBAT3L,r8
+ mtspr SPRN_DBAT3U,r11
+ blr
+1: mtspr SPRN_IBAT3L,r8
+ mtspr SPRN_IBAT3U,r11
+ blr
+
+#endif /* !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT) */
+
+#else /* CONFIG_POWER4 */
+/*
+ * Load up the SDR1 and segment register values now
+ * since we don't have the BATs.
+ * Also make sure we are running in 32-bit mode.
+ */
+
+initial_mm_power4:
+ addis r14,r3,_SDR1@ha /* get the value from _SDR1 */
+ lwz r14,_SDR1@l(r14) /* assume hash table below 4GB */
+ mtspr SPRN_SDR1,r14
+ slbia
+ lis r4,0x2000 /* set pseudo-segment reg 12 */
+ ori r5,r4,0x0ccc
+ mtsr 12,r5
+#if 0
+ ori r5,r4,0x0888 /* set pseudo-segment reg 8 */
+ mtsr 8,r5 /* (for access to serial port) */
+#endif
+#ifdef CONFIG_BOOTX_TEXT
+ ori r5,r4,0x0999 /* set pseudo-segment reg 9 */
+ mtsr 9,r5 /* (for access to screen) */
+#endif
+ mfmsr r0
+ clrldi r0,r0,1
+ sync
+ mtmsr r0
+ isync
+ blr
+
+#endif /* CONFIG_POWER4 */
+
+#ifdef CONFIG_8260
+/* Jump into the system reset for the rom.
+ * We first disable the MMU, and then jump to the ROM reset address.
+ *
+ * r3 is the board info structure, r4 is the location for starting.
+ * I use this for building a small kernel that can load other kernels,
+ * rather than trying to write or rely on a rom monitor that can tftp load.
+ */
+ .globl m8260_gorom
+m8260_gorom:
+ mfmsr r0
+ rlwinm r0,r0,0,17,15 /* clear MSR_EE in r0 */
+ sync
+ mtmsr r0
+ sync
+ mfspr r11, SPRN_HID0
+ lis r10, 0
+ ori r10,r10,HID0_ICE|HID0_DCE
+ andc r11, r11, r10
+ mtspr SPRN_HID0, r11
+ isync
+ li r5, MSR_ME|MSR_RI
+ lis r6,2f@h
+ addis r6,r6,-KERNELBASE@h
+ ori r6,r6,2f@l
+ mtspr SPRN_SRR0,r6
+ mtspr SPRN_SRR1,r5
+ isync
+ sync
+ rfi
+2:
+ mtlr r4
+ blr
+#endif
+
+
+/*
+ * We put a few things here that have to be page-aligned.
+ * This stuff goes at the beginning of the data segment,
+ * which is page-aligned.
+ */
+ .data
+ .globl sdata
+sdata:
+ .globl empty_zero_page
+empty_zero_page:
+ .space 4096
+
+ .globl swapper_pg_dir
+swapper_pg_dir:
+ .space 4096
+
+/*
+ * This space gets a copy of optional info passed to us by the bootstrap
+ * Used to pass parameters into the kernel like root=/dev/sda1, etc.
+ */
+ .globl cmd_line
+cmd_line:
+ .space 512
+
+ .globl intercept_table
+intercept_table:
+ .long 0, 0, i0x200, i0x300, i0x400, 0, i0x600, i0x700
+ .long i0x800, 0, 0, 0, 0, i0xd00, 0, 0
+ .long 0, 0, 0, i0x1300, 0, 0, 0, 0
+ .long 0, 0, 0, 0, 0, 0, 0, 0
+ .long 0, 0, 0, 0, 0, 0, 0, 0
+ .long 0, 0, 0, 0, 0, 0, 0, 0
+
+/* Room for two PTE pointers, usually the kernel and current user pointers
+ * to their respective root page table.
+ */
+abatron_pteptrs:
+ .space 8
diff --git a/arch/ppc/kernel/head_44x.S b/arch/ppc/kernel/head_44x.S
new file mode 100644
index 000000000000..9ed8165a3d6c
--- /dev/null
+++ b/arch/ppc/kernel/head_44x.S
@@ -0,0 +1,753 @@
+/*
+ * arch/ppc/kernel/head_44x.S
+ *
+ * Kernel execution entry point code.
+ *
+ * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
+ * Initial PowerPC version.
+ * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Rewritten for PReP
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Low-level exception handers, MMU support, and rewrite.
+ * Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
+ * PowerPC 8xx modifications.
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ * Copyright 2000 MontaVista Software Inc.
+ * PPC405 modifications
+ * PowerPC 403GCX/405GP modifications.
+ * Author: MontaVista Software, Inc.
+ * frank_rowand@mvista.com or source@mvista.com
+ * debbie_chu@mvista.com
+ * Copyright 2002-2005 MontaVista Software, Inc.
+ * PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/ibm4xx.h>
+#include <asm/ibm44x.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+#include "head_booke.h"
+
+
+/* As with the other PowerPC ports, it is expected that when code
+ * execution begins here, the following registers contain valid, yet
+ * optional, information:
+ *
+ * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
+ * r4 - Starting address of the init RAM disk
+ * r5 - Ending address of the init RAM disk
+ * r6 - Start of kernel command line string (e.g. "mem=128")
+ * r7 - End of kernel command line string
+ *
+ */
+ .text
+_GLOBAL(_stext)
+_GLOBAL(_start)
+ /*
+ * Reserve a word at a fixed location to store the address
+ * of abatron_pteptrs
+ */
+ nop
+/*
+ * Save parameters we are passed
+ */
+ mr r31,r3
+ mr r30,r4
+ mr r29,r5
+ mr r28,r6
+ mr r27,r7
+ li r24,0 /* CPU number */
+
+/*
+ * Set up the initial MMU state
+ *
+ * We are still executing code at the virtual address
+ * mappings set by the firmware for the base of RAM.
+ *
+ * We first invalidate all TLB entries but the one
+ * we are running from. We then load the KERNELBASE
+ * mappings so we can begin to use kernel addresses
+ * natively and so the interrupt vector locations are
+ * permanently pinned (necessary since Book E
+ * implementations always have translation enabled).
+ *
+ * TODO: Use the known TLB entry we are running from to
+ * determine which physical region we are located
+ * in. This can be used to determine where in RAM
+ * (on a shared CPU system) or PCI memory space
+ * (on a DRAMless system) we are located.
+ * For now, we assume a perfect world which means
+ * we are located at the base of DRAM (physical 0).
+ */
+
+/*
+ * Search TLB for entry that we are currently using.
+ * Invalidate all entries but the one we are using.
+ */
+ /* Load our current PID->MMUCR TID and MSR IS->MMUCR STS */
+ mfspr r3,SPRN_PID /* Get PID */
+ mfmsr r4 /* Get MSR */
+ andi. r4,r4,MSR_IS@l /* TS=1? */
+ beq wmmucr /* If not, leave STS=0 */
+ oris r3,r3,PPC44x_MMUCR_STS@h /* Set STS=1 */
+wmmucr: mtspr SPRN_MMUCR,r3 /* Put MMUCR */
+ sync
+
+ bl invstr /* Find our address */
+invstr: mflr r5 /* Make it accessible */
+ tlbsx r23,0,r5 /* Find entry we are in */
+ li r4,0 /* Start at TLB entry 0 */
+ li r3,0 /* Set PAGEID inval value */
+1: cmpw r23,r4 /* Is this our entry? */
+ beq skpinv /* If so, skip the inval */
+ tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */
+skpinv: addi r4,r4,1 /* Increment */
+ cmpwi r4,64 /* Are we done? */
+ bne 1b /* If not, repeat */
+ isync /* If so, context change */
+
+/*
+ * Configure and load pinned entry into TLB slot 63.
+ */
+
+ lis r3,KERNELBASE@h /* Load the kernel virtual address */
+ ori r3,r3,KERNELBASE@l
+
+ /* Kernel is at the base of RAM */
+ li r4, 0 /* Load the kernel physical address */
+
+ /* Load the kernel PID = 0 */
+ li r0,0
+ mtspr SPRN_PID,r0
+ sync
+
+ /* Initialize MMUCR */
+ li r5,0
+ mtspr SPRN_MMUCR,r5
+ sync
+
+ /* pageid fields */
+ clrrwi r3,r3,10 /* Mask off the effective page number */
+ ori r3,r3,PPC44x_TLB_VALID | PPC44x_TLB_256M
+
+ /* xlat fields */
+ clrrwi r4,r4,10 /* Mask off the real page number */
+ /* ERPN is 0 for first 4GB page */
+
+ /* attrib fields */
+ /* Added guarded bit to protect against speculative loads/stores */
+ li r5,0
+ ori r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G)
+
+ li r0,63 /* TLB slot 63 */
+
+ tlbwe r3,r0,PPC44x_TLB_PAGEID /* Load the pageid fields */
+ tlbwe r4,r0,PPC44x_TLB_XLAT /* Load the translation fields */
+ tlbwe r5,r0,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */
+
+ /* Force context change */
+ mfmsr r0
+ mtspr SPRN_SRR1, r0
+ lis r0,3f@h
+ ori r0,r0,3f@l
+ mtspr SPRN_SRR0,r0
+ sync
+ rfi
+
+ /* If necessary, invalidate original entry we used */
+3: cmpwi r23,63
+ beq 4f
+ li r6,0
+ tlbwe r6,r23,PPC44x_TLB_PAGEID
+ isync
+
+4:
+#ifdef CONFIG_SERIAL_TEXT_DEBUG
+ /*
+ * Add temporary UART mapping for early debug. This
+ * mapping must be identical to that used by the early
+ * bootloader code since the same asm/serial.h parameters
+ * are used for polled operation.
+ */
+ /* pageid fields */
+ lis r3,UART0_IO_BASE@h
+ ori r3,r3,PPC44x_TLB_VALID | PPC44x_TLB_256M
+
+ /* xlat fields */
+ lis r4,UART0_PHYS_IO_BASE@h /* RPN depends on SoC */
+ ori r4,r4,0x0001 /* ERPN is 1 for second 4GB page */
+
+ /* attrib fields */
+ li r5,0
+ ori r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_I | PPC44x_TLB_G)
+
+ li r0,1 /* TLB slot 1 */
+
+ tlbwe r3,r0,PPC44x_TLB_PAGEID /* Load the pageid fields */
+ tlbwe r4,r0,PPC44x_TLB_XLAT /* Load the translation fields */
+ tlbwe r5,r0,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */
+
+ /* Force context change */
+ isync
+#endif /* CONFIG_SERIAL_TEXT_DEBUG */
+
+ /* Establish the interrupt vector offsets */
+ SET_IVOR(0, CriticalInput);
+ SET_IVOR(1, MachineCheck);
+ SET_IVOR(2, DataStorage);
+ SET_IVOR(3, InstructionStorage);
+ SET_IVOR(4, ExternalInput);
+ SET_IVOR(5, Alignment);
+ SET_IVOR(6, Program);
+ SET_IVOR(7, FloatingPointUnavailable);
+ SET_IVOR(8, SystemCall);
+ SET_IVOR(9, AuxillaryProcessorUnavailable);
+ SET_IVOR(10, Decrementer);
+ SET_IVOR(11, FixedIntervalTimer);
+ SET_IVOR(12, WatchdogTimer);
+ SET_IVOR(13, DataTLBError);
+ SET_IVOR(14, InstructionTLBError);
+ SET_IVOR(15, Debug);
+
+ /* Establish the interrupt vector base */
+ lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */
+ mtspr SPRN_IVPR,r4
+
+ /*
+ * This is where the main kernel code starts.
+ */
+
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to current thread */
+ addi r4,r2,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG3,r4
+
+ /* stack */
+ lis r1,init_thread_union@h
+ ori r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+
+ bl early_init
+
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+ mr r3,r31
+ mr r4,r30
+ mr r5,r29
+ mr r6,r28
+ mr r7,r27
+ bl machine_init
+ bl MMU_init
+
+ /* Setup PTE pointers for the Abatron bdiGDB */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ lis r4, KERNELBASE@h
+ ori r4, r4, KERNELBASE@l
+ stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */
+ stw r6, 0(r5)
+
+ /* Let's move on */
+ lis r4,start_kernel@h
+ ori r4,r4,start_kernel@l
+ lis r3,MSR_KERNEL@h
+ ori r3,r3,MSR_KERNEL@l
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi /* change context and jump to start_kernel */
+
+/*
+ * Interrupt vector entry code
+ *
+ * The Book E MMUs are always on so we don't need to handle
+ * interrupts in real mode as with previous PPC processors. In
+ * this case we handle interrupts in the kernel virtual address
+ * space.
+ *
+ * Interrupt vectors are dynamically placed relative to the
+ * interrupt prefix as determined by the address of interrupt_base.
+ * The interrupt vectors offsets are programmed using the labels
+ * for each interrupt vector entry.
+ *
+ * Interrupt vectors must be aligned on a 16 byte boundary.
+ * We align on a 32 byte cache line boundary for good measure.
+ */
+
+interrupt_base:
+ /* Critical Input Interrupt */
+ CRITICAL_EXCEPTION(0x0100, CriticalInput, UnknownException)
+
+ /* Machine Check Interrupt */
+#ifdef CONFIG_440A
+ MCHECK_EXCEPTION(0x0200, MachineCheck, MachineCheckException)
+#else
+ CRITICAL_EXCEPTION(0x0200, MachineCheck, MachineCheckException)
+#endif
+
+ /* Data Storage Interrupt */
+ START_EXCEPTION(DataStorage)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+ mtspr SPRN_SPRG4W, r12
+ mtspr SPRN_SPRG5W, r13
+ mfcr r11
+ mtspr SPRN_SPRG7W, r11
+
+ /*
+ * Check if it was a store fault, if not then bail
+ * because a user tried to access a kernel or
+ * read-protected page. Otherwise, get the
+ * offending address and handle it.
+ */
+ mfspr r10, SPRN_ESR
+ andis. r10, r10, ESR_ST@h
+ beq 2f
+
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andis. r11, r10, 0x8000
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MMUCR
+ rlwinm r12,r12,0,0,23 /* Clear TID */
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+
+ /* Load PID into MMUCR TID */
+ mfspr r12,SPRN_MMUCR /* Get MMUCR */
+ mfspr r13,SPRN_PID /* Get PID */
+ rlwimi r12,r13,0,24,31 /* Set TID */
+
+4:
+ mtspr SPRN_MMUCR,r12
+
+ rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */
+ lwzx r11, r12, r11 /* Get pgd/pmd entry */
+ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 23, 20, 28 /* Compute pte address */
+ lwz r11, 4(r12) /* Get pte entry */
+
+ andi. r13, r11, _PAGE_RW /* Is it writeable? */
+ beq 2f /* Bail if not */
+
+ /* Update 'changed'.
+ */
+ ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
+ stw r11, 4(r12) /* Update Linux page table */
+
+ li r13, PPC44x_TLB_SR@l /* Set SR */
+ rlwimi r13, r11, 29, 29, 29 /* SX = _PAGE_HWEXEC */
+ rlwimi r13, r11, 0, 30, 30 /* SW = _PAGE_RW */
+ rlwimi r13, r11, 29, 28, 28 /* UR = _PAGE_USER */
+ rlwimi r12, r11, 31, 26, 26 /* (_PAGE_USER>>1)->r12 */
+ rlwimi r12, r11, 29, 30, 30 /* (_PAGE_USER>>3)->r12 */
+ and r12, r12, r11 /* HWEXEC/RW & USER */
+ rlwimi r13, r12, 0, 26, 26 /* UX = HWEXEC & USER */
+ rlwimi r13, r12, 3, 27, 27 /* UW = RW & USER */
+
+ rlwimi r11,r13,0,26,31 /* Insert static perms */
+
+ rlwinm r11,r11,0,20,15 /* Clear U0-U3 */
+
+ /* find the TLB index that caused the fault. It has to be here. */
+ tlbsx r10, 0, r10
+
+ tlbwe r11, r10, PPC44x_TLB_ATTRIB /* Write ATTRIB */
+
+ /* Done...restore registers and get out of here.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ rfi /* Force context change */
+
+2:
+ /*
+ * The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b data_access
+
+ /* Instruction Storage Interrupt */
+ INSTRUCTION_STORAGE_EXCEPTION
+
+ /* External Input Interrupt */
+ EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+
+ /* Alignment Interrupt */
+ ALIGNMENT_EXCEPTION
+
+ /* Program Interrupt */
+ PROGRAM_EXCEPTION
+
+ /* Floating Point Unavailable Interrupt */
+ EXCEPTION(0x2010, FloatingPointUnavailable, UnknownException, EXC_XFER_EE)
+
+ /* System Call Interrupt */
+ START_EXCEPTION(SystemCall)
+ NORMAL_EXCEPTION_PROLOG
+ EXC_XFER_EE_LITE(0x0c00, DoSyscall)
+
+ /* Auxillary Processor Unavailable Interrupt */
+ EXCEPTION(0x2020, AuxillaryProcessorUnavailable, UnknownException, EXC_XFER_EE)
+
+ /* Decrementer Interrupt */
+ DECREMENTER_EXCEPTION
+
+ /* Fixed Internal Timer Interrupt */
+ /* TODO: Add FIT support */
+ EXCEPTION(0x1010, FixedIntervalTimer, UnknownException, EXC_XFER_EE)
+
+ /* Watchdog Timer Interrupt */
+ /* TODO: Add watchdog support */
+ CRITICAL_EXCEPTION(0x1020, WatchdogTimer, UnknownException)
+
+ /* Data TLB Error Interrupt */
+ START_EXCEPTION(DataTLBError)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+ mtspr SPRN_SPRG4W, r12
+ mtspr SPRN_SPRG5W, r13
+ mfcr r11
+ mtspr SPRN_SPRG7W, r11
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andis. r11, r10, 0x8000
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MMUCR
+ rlwinm r12,r12,0,0,23 /* Clear TID */
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+
+ /* Load PID into MMUCR TID */
+ mfspr r12,SPRN_MMUCR
+ mfspr r13,SPRN_PID /* Get PID */
+ rlwimi r12,r13,0,24,31 /* Set TID */
+
+4:
+ mtspr SPRN_MMUCR,r12
+
+ rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */
+ lwzx r11, r12, r11 /* Get pgd/pmd entry */
+ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 23, 20, 28 /* Compute pte address */
+ lwz r11, 4(r12) /* Get pte entry */
+ andi. r13, r11, _PAGE_PRESENT /* Is the page present? */
+ beq 2f /* Bail if not present */
+
+ ori r11, r11, _PAGE_ACCESSED
+ stw r11, 4(r12)
+
+ /* Jump to common tlb load */
+ b finish_tlb_load
+
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b data_access
+
+ /* Instruction TLB Error Interrupt */
+ /*
+ * Nearly the same as above, except we get our
+ * information from different registers and bailout
+ * to a different point.
+ */
+ START_EXCEPTION(InstructionTLBError)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+ mtspr SPRN_SPRG4W, r12
+ mtspr SPRN_SPRG5W, r13
+ mfcr r11
+ mtspr SPRN_SPRG7W, r11
+ mfspr r10, SPRN_SRR0 /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andis. r11, r10, 0x8000
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MMUCR
+ rlwinm r12,r12,0,0,23 /* Clear TID */
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+
+ /* Load PID into MMUCR TID */
+ mfspr r12,SPRN_MMUCR
+ mfspr r13,SPRN_PID /* Get PID */
+ rlwimi r12,r13,0,24,31 /* Set TID */
+
+4:
+ mtspr SPRN_MMUCR,r12
+
+ rlwinm r12, r10, 13, 19, 29 /* Compute pgdir/pmd offset */
+ lwzx r11, r12, r11 /* Get pgd/pmd entry */
+ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 23, 20, 28 /* Compute pte address */
+ lwz r11, 4(r12) /* Get pte entry */
+ andi. r13, r11, _PAGE_PRESENT /* Is the page present? */
+ beq 2f /* Bail if not present */
+
+ ori r11, r11, _PAGE_ACCESSED
+ stw r11, 4(r12)
+
+ /* Jump to common TLB load point */
+ b finish_tlb_load
+
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b InstructionStorage
+
+ /* Debug Interrupt */
+ DEBUG_EXCEPTION
+
+/*
+ * Local functions
+ */
+ /*
+ * Data TLB exceptions will bail out to this point
+ * if they can't resolve the lightweight TLB fault.
+ */
+data_access:
+ NORMAL_EXCEPTION_PROLOG
+ mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
+ stw r5,_ESR(r11)
+ mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
+ EXC_XFER_EE_LITE(0x0300, handle_page_fault)
+
+/*
+
+ * Both the instruction and data TLB miss get to this
+ * point to load the TLB.
+ * r10 - EA of fault
+ * r11 - available to use
+ * r12 - Pointer to the 64-bit PTE
+ * r13 - available to use
+ * MMUCR - loaded with proper value when we get here
+ * Upon exit, we reload everything and RFI.
+ */
+finish_tlb_load:
+ /*
+ * We set execute, because we don't have the granularity to
+ * properly set this at the page level (Linux problem).
+ * If shared is set, we cause a zero PID->TID load.
+ * Many of these bits are software only. Bits we don't set
+ * here we (properly should) assume have the appropriate value.
+ */
+
+ /* Load the next available TLB index */
+ lis r13, tlb_44x_index@ha
+ lwz r13, tlb_44x_index@l(r13)
+ /* Load the TLB high watermark */
+ lis r11, tlb_44x_hwater@ha
+ lwz r11, tlb_44x_hwater@l(r11)
+
+ /* Increment, rollover, and store TLB index */
+ addi r13, r13, 1
+ cmpw 0, r13, r11 /* reserve entries */
+ ble 7f
+ li r13, 0
+7:
+ /* Store the next available TLB index */
+ lis r11, tlb_44x_index@ha
+ stw r13, tlb_44x_index@l(r11)
+
+ lwz r11, 0(r12) /* Get MS word of PTE */
+ lwz r12, 4(r12) /* Get LS word of PTE */
+ rlwimi r11, r12, 0, 0 , 19 /* Insert RPN */
+ tlbwe r11, r13, PPC44x_TLB_XLAT /* Write XLAT */
+
+ /*
+ * Create PAGEID. This is the faulting address,
+ * page size, and valid flag.
+ */
+ li r11, PPC44x_TLB_VALID | PPC44x_TLB_4K
+ rlwimi r10, r11, 0, 20, 31 /* Insert valid and page size */
+ tlbwe r10, r13, PPC44x_TLB_PAGEID /* Write PAGEID */
+
+ li r10, PPC44x_TLB_SR@l /* Set SR */
+ rlwimi r10, r12, 0, 30, 30 /* Set SW = _PAGE_RW */
+ rlwimi r10, r12, 29, 29, 29 /* SX = _PAGE_HWEXEC */
+ rlwimi r10, r12, 29, 28, 28 /* UR = _PAGE_USER */
+ rlwimi r11, r12, 31, 26, 26 /* (_PAGE_USER>>1)->r12 */
+ and r11, r12, r11 /* HWEXEC & USER */
+ rlwimi r10, r11, 0, 26, 26 /* UX = HWEXEC & USER */
+
+ rlwimi r12, r10, 0, 26, 31 /* Insert static perms */
+ rlwinm r12, r12, 0, 20, 15 /* Clear U0-U3 */
+ tlbwe r12, r13, PPC44x_TLB_ATTRIB /* Write ATTRIB */
+
+ /* Done...restore registers and get out of here.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ rfi /* Force context change */
+
+/*
+ * Global functions
+ */
+
+/*
+ * extern void giveup_altivec(struct task_struct *prev)
+ *
+ * The 44x core does not have an AltiVec unit.
+ */
+_GLOBAL(giveup_altivec)
+ blr
+
+/*
+ * extern void giveup_fpu(struct task_struct *prev)
+ *
+ * The 44x core does not have an FPU.
+ */
+_GLOBAL(giveup_fpu)
+ blr
+
+/*
+ * extern void abort(void)
+ *
+ * At present, this routine just applies a system reset.
+ */
+_GLOBAL(abort)
+ mfspr r13,SPRN_DBCR0
+ oris r13,r13,DBCR0_RST_SYSTEM@h
+ mtspr SPRN_DBCR0,r13
+
+_GLOBAL(set_context)
+
+#ifdef CONFIG_BDI_SWITCH
+ /* Context switch the PTE pointer for the Abatron BDI2000.
+ * The PGDIR is the second parameter.
+ */
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r4, 0x4(r5)
+#endif
+ mtspr SPRN_PID,r3
+ isync /* Force context change */
+ blr
+
+/*
+ * We put a few things here that have to be page-aligned. This stuff
+ * goes at the beginning of the data segment, which is page-aligned.
+ */
+ .data
+_GLOBAL(sdata)
+_GLOBAL(empty_zero_page)
+ .space 4096
+
+/*
+ * To support >32-bit physical addresses, we use an 8KB pgdir.
+ */
+_GLOBAL(swapper_pg_dir)
+ .space 8192
+
+/* Reserved 4k for the critical exception stack & 4k for the machine
+ * check stack per CPU for kernel mode exceptions */
+ .section .bss
+ .align 12
+exception_stack_bottom:
+ .space BOOKE_EXCEPTION_STACK_SIZE
+_GLOBAL(exception_stack_top)
+
+/*
+ * This space gets a copy of optional info passed to us by the bootstrap
+ * which is used to pass parameters into the kernel like root=/dev/sda1, etc.
+ */
+_GLOBAL(cmd_line)
+ .space 512
+
+/*
+ * Room for two PTE pointers, usually the kernel and current user pointers
+ * to their respective root page table.
+ */
+abatron_pteptrs:
+ .space 8
+
+
diff --git a/arch/ppc/kernel/head_4xx.S b/arch/ppc/kernel/head_4xx.S
new file mode 100644
index 000000000000..6f5d380e2345
--- /dev/null
+++ b/arch/ppc/kernel/head_4xx.S
@@ -0,0 +1,1010 @@
+/*
+ * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
+ * Initial PowerPC version.
+ * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Rewritten for PReP
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Low-level exception handers, MMU support, and rewrite.
+ * Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
+ * PowerPC 8xx modifications.
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ * Copyright 2000 MontaVista Software Inc.
+ * PPC405 modifications
+ * PowerPC 403GCX/405GP modifications.
+ * Author: MontaVista Software, Inc.
+ * frank_rowand@mvista.com or source@mvista.com
+ * debbie_chu@mvista.com
+ *
+ *
+ * Module name: head_4xx.S
+ *
+ * Description:
+ * Kernel execution entry point code.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/ibm4xx.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+
+/* As with the other PowerPC ports, it is expected that when code
+ * execution begins here, the following registers contain valid, yet
+ * optional, information:
+ *
+ * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
+ * r4 - Starting address of the init RAM disk
+ * r5 - Ending address of the init RAM disk
+ * r6 - Start of kernel command line string (e.g. "mem=96m")
+ * r7 - End of kernel command line string
+ *
+ * This is all going to change RSN when we add bi_recs....... -- Dan
+ */
+ .text
+_GLOBAL(_stext)
+_GLOBAL(_start)
+
+ /* Save parameters we are passed.
+ */
+ mr r31,r3
+ mr r30,r4
+ mr r29,r5
+ mr r28,r6
+ mr r27,r7
+
+ /* We have to turn on the MMU right away so we get cache modes
+ * set correctly.
+ */
+ bl initial_mmu
+
+/* We now have the lower 16 Meg mapped into TLB entries, and the caches
+ * ready to work.
+ */
+turn_on_mmu:
+ lis r0,MSR_KERNEL@h
+ ori r0,r0,MSR_KERNEL@l
+ mtspr SPRN_SRR1,r0
+ lis r0,start_here@h
+ ori r0,r0,start_here@l
+ mtspr SPRN_SRR0,r0
+ SYNC
+ rfi /* enables MMU */
+ b . /* prevent prefetch past rfi */
+
+/*
+ * This area is used for temporarily saving registers during the
+ * critical exception prolog.
+ */
+ . = 0xc0
+crit_save:
+_GLOBAL(crit_r10)
+ .space 4
+_GLOBAL(crit_r11)
+ .space 4
+
+/*
+ * Exception vector entry code. This code runs with address translation
+ * turned off (i.e. using physical addresses). We assume SPRG3 has the
+ * physical address of the current task thread_struct.
+ * Note that we have to have decremented r1 before we write to any fields
+ * of the exception frame, since a critical interrupt could occur at any
+ * time, and it will write to the area immediately below the current r1.
+ */
+#define NORMAL_EXCEPTION_PROLOG \
+ mtspr SPRN_SPRG0,r10; /* save two registers to work with */\
+ mtspr SPRN_SPRG1,r11; \
+ mtspr SPRN_SPRG2,r1; \
+ mfcr r10; /* save CR in r10 for now */\
+ mfspr r11,SPRN_SRR1; /* check whether user or kernel */\
+ andi. r11,r11,MSR_PR; \
+ beq 1f; \
+ mfspr r1,SPRN_SPRG3; /* if from user, start at top of */\
+ lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\
+ addi r1,r1,THREAD_SIZE; \
+1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\
+ tophys(r11,r1); \
+ stw r10,_CCR(r11); /* save various registers */\
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mfspr r10,SPRN_SPRG0; \
+ stw r10,GPR10(r11); \
+ mfspr r12,SPRN_SPRG1; \
+ stw r12,GPR11(r11); \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r10,SPRN_SPRG2; \
+ mfspr r12,SPRN_SRR0; \
+ stw r10,GPR1(r11); \
+ mfspr r9,SPRN_SRR1; \
+ stw r10,0(r11); \
+ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\
+ stw r0,GPR0(r11); \
+ SAVE_4GPRS(3, r11); \
+ SAVE_2GPRS(7, r11)
+
+/*
+ * Exception prolog for critical exceptions. This is a little different
+ * from the normal exception prolog above since a critical exception
+ * can potentially occur at any point during normal exception processing.
+ * Thus we cannot use the same SPRG registers as the normal prolog above.
+ * Instead we use a couple of words of memory at low physical addresses.
+ * This is OK since we don't support SMP on these processors.
+ */
+#define CRITICAL_EXCEPTION_PROLOG \
+ stw r10,crit_r10@l(0); /* save two registers to work with */\
+ stw r11,crit_r11@l(0); \
+ mfcr r10; /* save CR in r10 for now */\
+ mfspr r11,SPRN_SRR3; /* check whether user or kernel */\
+ andi. r11,r11,MSR_PR; \
+ lis r11,critical_stack_top@h; \
+ ori r11,r11,critical_stack_top@l; \
+ beq 1f; \
+ /* COMING FROM USER MODE */ \
+ mfspr r11,SPRN_SPRG3; /* if from user, start at top of */\
+ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ addi r11,r11,THREAD_SIZE; \
+1: subi r11,r11,INT_FRAME_SIZE; /* Allocate an exception frame */\
+ tophys(r11,r11); \
+ stw r10,_CCR(r11); /* save various registers */\
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r12,SPRN_DEAR; /* save DEAR and ESR in the frame */\
+ stw r12,_DEAR(r11); /* since they may have had stuff */\
+ mfspr r9,SPRN_ESR; /* in them at the point where the */\
+ stw r9,_ESR(r11); /* exception was taken */\
+ mfspr r12,SPRN_SRR2; \
+ stw r1,GPR1(r11); \
+ mfspr r9,SPRN_SRR3; \
+ stw r1,0(r11); \
+ tovirt(r1,r11); \
+ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\
+ stw r0,GPR0(r11); \
+ SAVE_4GPRS(3, r11); \
+ SAVE_2GPRS(7, r11)
+
+ /*
+ * State at this point:
+ * r9 saved in stack frame, now saved SRR3 & ~MSR_WE
+ * r10 saved in crit_r10 and in stack frame, trashed
+ * r11 saved in crit_r11 and in stack frame,
+ * now phys stack/exception frame pointer
+ * r12 saved in stack frame, now saved SRR2
+ * CR saved in stack frame, CR0.EQ = !SRR3.PR
+ * LR, DEAR, ESR in stack frame
+ * r1 saved in stack frame, now virt stack/excframe pointer
+ * r0, r3-r8 saved in stack frame
+ */
+
+/*
+ * Exception vectors.
+ */
+#define START_EXCEPTION(n, label) \
+ . = n; \
+label:
+
+#define EXCEPTION(n, label, hdlr, xfer) \
+ START_EXCEPTION(n, label); \
+ NORMAL_EXCEPTION_PROLOG; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ xfer(n, hdlr)
+
+#define CRITICAL_EXCEPTION(n, label, hdlr) \
+ START_EXCEPTION(n, label); \
+ CRITICAL_EXCEPTION_PROLOG; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
+ NOCOPY, crit_transfer_to_handler, \
+ ret_from_crit_exc)
+
+#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret) \
+ li r10,trap; \
+ stw r10,TRAP(r11); \
+ lis r10,msr@h; \
+ ori r10,r10,msr@l; \
+ copyee(r10, r9); \
+ bl tfer; \
+ .long hdlr; \
+ .long ret
+
+#define COPY_EE(d, s) rlwimi d,s,0,16,16
+#define NOCOPY(d, s)
+
+#define EXC_XFER_STD(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \
+ ret_from_except)
+
+#define EXC_XFER_EE(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_EE_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \
+ ret_from_except)
+
+
+/*
+ * 0x0100 - Critical Interrupt Exception
+ */
+ CRITICAL_EXCEPTION(0x0100, CriticalInterrupt, UnknownException)
+
+/*
+ * 0x0200 - Machine Check Exception
+ */
+ CRITICAL_EXCEPTION(0x0200, MachineCheck, MachineCheckException)
+
+/*
+ * 0x0300 - Data Storage Exception
+ * This happens for just a few reasons. U0 set (but we don't do that),
+ * or zone protection fault (user violation, write to protected page).
+ * If this is just an update of modified status, we do that quickly
+ * and exit. Otherwise, we call heavywight functions to do the work.
+ */
+ START_EXCEPTION(0x0300, DataStorage)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+#ifdef CONFIG_403GCX
+ stw r12, 0(r0)
+ stw r9, 4(r0)
+ mfcr r11
+ mfspr r12, SPRN_PID
+ stw r11, 8(r0)
+ stw r12, 12(r0)
+#else
+ mtspr SPRN_SPRG4, r12
+ mtspr SPRN_SPRG5, r9
+ mfcr r11
+ mfspr r12, SPRN_PID
+ mtspr SPRN_SPRG7, r11
+ mtspr SPRN_SPRG6, r12
+#endif
+
+ /* First, check if it was a zone fault (which means a user
+ * tried to access a kernel or read-protected page - always
+ * a SEGV). All other faults here must be stores, so no
+ * need to check ESR_DST as well. */
+ mfspr r10, SPRN_ESR
+ andis. r10, r10, ESR_DIZ@h
+ bne 2f
+
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andis. r11, r10, 0x8000
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ li r9, 0
+ mtspr SPRN_PID, r9 /* TLB will have 0 TID */
+ b 4f
+
+ /* Get the PGD for the current thread.
+ */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+4:
+ tophys(r11, r11)
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r11, 0(r11) /* Get L1 entry */
+ rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r12) /* Get Linux PTE */
+
+ andi. r9, r11, _PAGE_RW /* Is it writeable? */
+ beq 2f /* Bail if not */
+
+ /* Update 'changed'.
+ */
+ ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
+ stw r11, 0(r12) /* Update Linux page table */
+
+ /* Most of the Linux PTE is ready to load into the TLB LO.
+ * We set ZSEL, where only the LS-bit determines user access.
+ * We set execute, because we don't have the granularity to
+ * properly set this at the page level (Linux problem).
+ * If shared is set, we cause a zero PID->TID load.
+ * Many of these bits are software only. Bits we don't set
+ * here we (properly should) assume have the appropriate value.
+ */
+ li r12, 0x0ce2
+ andc r11, r11, r12 /* Make sure 20, 21 are zero */
+
+ /* find the TLB index that caused the fault. It has to be here.
+ */
+ tlbsx r9, 0, r10
+
+ tlbwe r11, r9, TLB_DATA /* Load TLB LO */
+
+ /* Done...restore registers and get out of here.
+ */
+#ifdef CONFIG_403GCX
+ lwz r12, 12(r0)
+ lwz r11, 8(r0)
+ mtspr SPRN_PID, r12
+ mtcr r11
+ lwz r9, 4(r0)
+ lwz r12, 0(r0)
+#else
+ mfspr r12, SPRN_SPRG6
+ mfspr r11, SPRN_SPRG7
+ mtspr SPRN_PID, r12
+ mtcr r11
+ mfspr r9, SPRN_SPRG5
+ mfspr r12, SPRN_SPRG4
+#endif
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ PPC405_ERR77_SYNC
+ rfi /* Should sync shadow TLBs */
+ b . /* prevent prefetch past rfi */
+
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+#ifdef CONFIG_403GCX
+ lwz r12, 12(r0)
+ lwz r11, 8(r0)
+ mtspr SPRN_PID, r12
+ mtcr r11
+ lwz r9, 4(r0)
+ lwz r12, 0(r0)
+#else
+ mfspr r12, SPRN_SPRG6
+ mfspr r11, SPRN_SPRG7
+ mtspr SPRN_PID, r12
+ mtcr r11
+ mfspr r9, SPRN_SPRG5
+ mfspr r12, SPRN_SPRG4
+#endif
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b DataAccess
+
+/*
+ * 0x0400 - Instruction Storage Exception
+ * This is caused by a fetch from non-execute or guarded pages.
+ */
+ START_EXCEPTION(0x0400, InstructionAccess)
+ NORMAL_EXCEPTION_PROLOG
+ mr r4,r12 /* Pass SRR0 as arg2 */
+ li r5,0 /* Pass zero as arg3 */
+ EXC_XFER_EE_LITE(0x400, handle_page_fault)
+
+/* 0x0500 - External Interrupt Exception */
+ EXCEPTION(0x0500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
+
+/* 0x0600 - Alignment Exception */
+ START_EXCEPTION(0x0600, Alignment)
+ NORMAL_EXCEPTION_PROLOG
+ mfspr r4,SPRN_DEAR /* Grab the DEAR and save it */
+ stw r4,_DEAR(r11)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_EE(0x600, AlignmentException)
+
+/* 0x0700 - Program Exception */
+ START_EXCEPTION(0x0700, ProgramCheck)
+ NORMAL_EXCEPTION_PROLOG
+ mfspr r4,SPRN_ESR /* Grab the ESR and save it */
+ stw r4,_ESR(r11)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_STD(0x700, ProgramCheckException)
+
+ EXCEPTION(0x0800, Trap_08, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x0900, Trap_09, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x0A00, Trap_0A, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x0B00, Trap_0B, UnknownException, EXC_XFER_EE)
+
+/* 0x0C00 - System Call Exception */
+ START_EXCEPTION(0x0C00, SystemCall)
+ NORMAL_EXCEPTION_PROLOG
+ EXC_XFER_EE_LITE(0xc00, DoSyscall)
+
+ EXCEPTION(0x0D00, Trap_0D, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x0E00, Trap_0E, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x0F00, Trap_0F, UnknownException, EXC_XFER_EE)
+
+/* 0x1000 - Programmable Interval Timer (PIT) Exception */
+ START_EXCEPTION(0x1000, Decrementer)
+ NORMAL_EXCEPTION_PROLOG
+ lis r0,TSR_PIS@h
+ mtspr SPRN_TSR,r0 /* Clear the PIT exception */
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_LITE(0x1000, timer_interrupt)
+
+#if 0
+/* NOTE:
+ * FIT and WDT handlers are not implemented yet.
+ */
+
+/* 0x1010 - Fixed Interval Timer (FIT) Exception
+*/
+ STND_EXCEPTION(0x1010, FITException, UnknownException)
+
+/* 0x1020 - Watchdog Timer (WDT) Exception
+*/
+
+ CRITICAL_EXCEPTION(0x1020, WDTException, UnknownException)
+#endif
+
+/* 0x1100 - Data TLB Miss Exception
+ * As the name implies, translation is not in the MMU, so search the
+ * page tables and fix it. The only purpose of this function is to
+ * load TLB entries from the page table if they exist.
+ */
+ START_EXCEPTION(0x1100, DTLBMiss)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+#ifdef CONFIG_403GCX
+ stw r12, 0(r0)
+ stw r9, 4(r0)
+ mfcr r11
+ mfspr r12, SPRN_PID
+ stw r11, 8(r0)
+ stw r12, 12(r0)
+#else
+ mtspr SPRN_SPRG4, r12
+ mtspr SPRN_SPRG5, r9
+ mfcr r11
+ mfspr r12, SPRN_PID
+ mtspr SPRN_SPRG7, r11
+ mtspr SPRN_SPRG6, r12
+#endif
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andis. r11, r10, 0x8000
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ li r9, 0
+ mtspr SPRN_PID, r9 /* TLB will have 0 TID */
+ b 4f
+
+ /* Get the PGD for the current thread.
+ */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+4:
+ tophys(r11, r11)
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r12, 0(r11) /* Get L1 entry */
+ andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r12) /* Get Linux PTE */
+ andi. r9, r11, _PAGE_PRESENT
+ beq 5f
+
+ ori r11, r11, _PAGE_ACCESSED
+ stw r11, 0(r12)
+
+ /* Create TLB tag. This is the faulting address plus a static
+ * set of bits. These are size, valid, E, U0.
+ */
+ li r12, 0x00c0
+ rlwimi r10, r12, 0, 20, 31
+
+ b finish_tlb_load
+
+2: /* Check for possible large-page pmd entry */
+ rlwinm. r9, r12, 2, 22, 24
+ beq 5f
+
+ /* Create TLB tag. This is the faulting address, plus a static
+ * set of bits (valid, E, U0) plus the size from the PMD.
+ */
+ ori r9, r9, 0x40
+ rlwimi r10, r9, 0, 20, 31
+ mr r11, r12
+
+ b finish_tlb_load
+
+5:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+#ifdef CONFIG_403GCX
+ lwz r12, 12(r0)
+ lwz r11, 8(r0)
+ mtspr SPRN_PID, r12
+ mtcr r11
+ lwz r9, 4(r0)
+ lwz r12, 0(r0)
+#else
+ mfspr r12, SPRN_SPRG6
+ mfspr r11, SPRN_SPRG7
+ mtspr SPRN_PID, r12
+ mtcr r11
+ mfspr r9, SPRN_SPRG5
+ mfspr r12, SPRN_SPRG4
+#endif
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b DataAccess
+
+/* 0x1200 - Instruction TLB Miss Exception
+ * Nearly the same as above, except we get our information from different
+ * registers and bailout to a different point.
+ */
+ START_EXCEPTION(0x1200, ITLBMiss)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+#ifdef CONFIG_403GCX
+ stw r12, 0(r0)
+ stw r9, 4(r0)
+ mfcr r11
+ mfspr r12, SPRN_PID
+ stw r11, 8(r0)
+ stw r12, 12(r0)
+#else
+ mtspr SPRN_SPRG4, r12
+ mtspr SPRN_SPRG5, r9
+ mfcr r11
+ mfspr r12, SPRN_PID
+ mtspr SPRN_SPRG7, r11
+ mtspr SPRN_SPRG6, r12
+#endif
+ mfspr r10, SPRN_SRR0 /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andis. r11, r10, 0x8000
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ li r9, 0
+ mtspr SPRN_PID, r9 /* TLB will have 0 TID */
+ b 4f
+
+ /* Get the PGD for the current thread.
+ */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+4:
+ tophys(r11, r11)
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r12, 0(r11) /* Get L1 entry */
+ andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r12) /* Get Linux PTE */
+ andi. r9, r11, _PAGE_PRESENT
+ beq 5f
+
+ ori r11, r11, _PAGE_ACCESSED
+ stw r11, 0(r12)
+
+ /* Create TLB tag. This is the faulting address plus a static
+ * set of bits. These are size, valid, E, U0.
+ */
+ li r12, 0x00c0
+ rlwimi r10, r12, 0, 20, 31
+
+ b finish_tlb_load
+
+2: /* Check for possible large-page pmd entry */
+ rlwinm. r9, r12, 2, 22, 24
+ beq 5f
+
+ /* Create TLB tag. This is the faulting address, plus a static
+ * set of bits (valid, E, U0) plus the size from the PMD.
+ */
+ ori r9, r9, 0x40
+ rlwimi r10, r9, 0, 20, 31
+ mr r11, r12
+
+ b finish_tlb_load
+
+5:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+#ifdef CONFIG_403GCX
+ lwz r12, 12(r0)
+ lwz r11, 8(r0)
+ mtspr SPRN_PID, r12
+ mtcr r11
+ lwz r9, 4(r0)
+ lwz r12, 0(r0)
+#else
+ mfspr r12, SPRN_SPRG6
+ mfspr r11, SPRN_SPRG7
+ mtspr SPRN_PID, r12
+ mtcr r11
+ mfspr r9, SPRN_SPRG5
+ mfspr r12, SPRN_SPRG4
+#endif
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b InstructionAccess
+
+ EXCEPTION(0x1300, Trap_13, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1400, Trap_14, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1500, Trap_15, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1600, Trap_16, UnknownException, EXC_XFER_EE)
+#ifdef CONFIG_IBM405_ERR51
+ /* 405GP errata 51 */
+ START_EXCEPTION(0x1700, Trap_17)
+ b DTLBMiss
+#else
+ EXCEPTION(0x1700, Trap_17, UnknownException, EXC_XFER_EE)
+#endif
+ EXCEPTION(0x1800, Trap_18, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1900, Trap_19, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1A00, Trap_1A, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1B00, Trap_1B, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1C00, Trap_1C, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1D00, Trap_1D, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1E00, Trap_1E, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1F00, Trap_1F, UnknownException, EXC_XFER_EE)
+
+/* Check for a single step debug exception while in an exception
+ * handler before state has been saved. This is to catch the case
+ * where an instruction that we are trying to single step causes
+ * an exception (eg ITLB/DTLB miss) and thus the first instruction of
+ * the exception handler generates a single step debug exception.
+ *
+ * If we get a debug trap on the first instruction of an exception handler,
+ * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is
+ * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR).
+ * The exception handler was handling a non-critical interrupt, so it will
+ * save (and later restore) the MSR via SPRN_SRR1, which will still have
+ * the MSR_DE bit set.
+ */
+ /* 0x2000 - Debug Exception */
+ START_EXCEPTION(0x2000, DebugTrap)
+ CRITICAL_EXCEPTION_PROLOG
+
+ /*
+ * If this is a single step or branch-taken exception in an
+ * exception entry sequence, it was probably meant to apply to
+ * the code where the exception occurred (since exception entry
+ * doesn't turn off DE automatically). We simulate the effect
+ * of turning off DE on entry to an exception handler by turning
+ * off DE in the SRR3 value and clearing the debug status.
+ */
+ mfspr r10,SPRN_DBSR /* check single-step/branch taken */
+ andis. r10,r10,DBSR_IC@h
+ beq+ 2f
+
+ andi. r10,r9,MSR_IR|MSR_PR /* check supervisor + MMU off */
+ beq 1f /* branch and fix it up */
+
+ mfspr r10,SPRN_SRR2 /* Faulting instruction address */
+ cmplwi r10,0x2100
+ bgt+ 2f /* address above exception vectors */
+
+ /* here it looks like we got an inappropriate debug exception. */
+1: rlwinm r9,r9,0,~MSR_DE /* clear DE in the SRR3 value */
+ lis r10,DBSR_IC@h /* clear the IC event */
+ mtspr SPRN_DBSR,r10
+ /* restore state and get out */
+ lwz r10,_CCR(r11)
+ lwz r0,GPR0(r11)
+ lwz r1,GPR1(r11)
+ mtcrf 0x80,r10
+ mtspr SPRN_SRR2,r12
+ mtspr SPRN_SRR3,r9
+ lwz r9,GPR9(r11)
+ lwz r12,GPR12(r11)
+ lwz r10,crit_r10@l(0)
+ lwz r11,crit_r11@l(0)
+ PPC405_ERR77_SYNC
+ rfci
+ b .
+
+ /* continue normal handling for a critical exception... */
+2: mfspr r4,SPRN_DBSR
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_TEMPLATE(DebugException, 0x2002, \
+ (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
+ NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
+
+/*
+ * The other Data TLB exceptions bail out to this point
+ * if they can't resolve the lightweight TLB fault.
+ */
+DataAccess:
+ NORMAL_EXCEPTION_PROLOG
+ mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
+ stw r5,_ESR(r11)
+ mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
+ EXC_XFER_EE_LITE(0x300, handle_page_fault)
+
+/* Other PowerPC processors, namely those derived from the 6xx-series
+ * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved.
+ * However, for the 4xx-series processors these are neither defined nor
+ * reserved.
+ */
+
+ /* Damn, I came up one instruction too many to fit into the
+ * exception space :-). Both the instruction and data TLB
+ * miss get to this point to load the TLB.
+ * r10 - TLB_TAG value
+ * r11 - Linux PTE
+ * r12, r9 - avilable to use
+ * PID - loaded with proper value when we get here
+ * Upon exit, we reload everything and RFI.
+ * Actually, it will fit now, but oh well.....a common place
+ * to load the TLB.
+ */
+tlb_4xx_index:
+ .long 0
+finish_tlb_load:
+ /* load the next available TLB index.
+ */
+ lwz r9, tlb_4xx_index@l(0)
+ addi r9, r9, 1
+ andi. r9, r9, (PPC4XX_TLB_SIZE-1)
+ stw r9, tlb_4xx_index@l(0)
+
+6:
+ /*
+ * Clear out the software-only bits in the PTE to generate the
+ * TLB_DATA value. These are the bottom 2 bits of the RPM, the
+ * top 3 bits of the zone field, and M.
+ */
+ li r12, 0x0ce2
+ andc r11, r11, r12
+
+ tlbwe r11, r9, TLB_DATA /* Load TLB LO */
+ tlbwe r10, r9, TLB_TAG /* Load TLB HI */
+
+ /* Done...restore registers and get out of here.
+ */
+#ifdef CONFIG_403GCX
+ lwz r12, 12(r0)
+ lwz r11, 8(r0)
+ mtspr SPRN_PID, r12
+ mtcr r11
+ lwz r9, 4(r0)
+ lwz r12, 0(r0)
+#else
+ mfspr r12, SPRN_SPRG6
+ mfspr r11, SPRN_SPRG7
+ mtspr SPRN_PID, r12
+ mtcr r11
+ mfspr r9, SPRN_SPRG5
+ mfspr r12, SPRN_SPRG4
+#endif
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ PPC405_ERR77_SYNC
+ rfi /* Should sync shadow TLBs */
+ b . /* prevent prefetch past rfi */
+
+/* extern void giveup_fpu(struct task_struct *prev)
+ *
+ * The PowerPC 4xx family of processors do not have an FPU, so this just
+ * returns.
+ */
+_GLOBAL(giveup_fpu)
+ blr
+
+/* This is where the main kernel code starts.
+ */
+start_here:
+
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG3,r4
+
+ /* stack */
+ lis r1,init_thread_union@ha
+ addi r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+
+ bl early_init /* We have to do this with MMU on */
+
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+ mr r3,r31
+ mr r4,r30
+ mr r5,r29
+ mr r6,r28
+ mr r7,r27
+ bl machine_init
+ bl MMU_init
+
+/* Go back to running unmapped so we can load up new values
+ * and change to using our exception vectors.
+ * On the 4xx, all we have to do is invalidate the TLB to clear
+ * the old 16M byte TLB mappings.
+ */
+ lis r4,2f@h
+ ori r4,r4,2f@l
+ tophys(r4,r4)
+ lis r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@h
+ ori r3,r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@l
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi
+ b . /* prevent prefetch past rfi */
+
+/* Load up the kernel context */
+2:
+ sync /* Flush to memory before changing TLB */
+ tlbia
+ isync /* Flush shadow TLBs */
+
+ /* set up the PTE pointers for the Abatron bdiGDB.
+ */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r5, 0xf0(r0) /* Must match your Abatron config file */
+ tophys(r5,r5)
+ stw r6, 0(r5)
+
+/* Now turn on the MMU for real! */
+ lis r4,MSR_KERNEL@h
+ ori r4,r4,MSR_KERNEL@l
+ lis r3,start_kernel@h
+ ori r3,r3,start_kernel@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ rfi /* enable MMU and jump to start_kernel */
+ b . /* prevent prefetch past rfi */
+
+/* Set up the initial MMU state so we can do the first level of
+ * kernel initialization. This maps the first 16 MBytes of memory 1:1
+ * virtual to physical and more importantly sets the cache mode.
+ */
+initial_mmu:
+ tlbia /* Invalidate all TLB entries */
+ isync
+
+ /* We should still be executing code at physical address 0x0000xxxx
+ * at this point. However, start_here is at virtual address
+ * 0xC000xxxx. So, set up a TLB mapping to cover this once
+ * translation is enabled.
+ */
+
+ lis r3,KERNELBASE@h /* Load the kernel virtual address */
+ ori r3,r3,KERNELBASE@l
+ tophys(r4,r3) /* Load the kernel physical address */
+
+ iccci r0,r3 /* Invalidate the i-cache before use */
+
+ /* Load the kernel PID.
+ */
+ li r0,0
+ mtspr SPRN_PID,r0
+ sync
+
+ /* Configure and load two entries into TLB slots 62 and 63.
+ * In case we are pinning TLBs, these are reserved in by the
+ * other TLB functions. If not reserving, then it doesn't
+ * matter where they are loaded.
+ */
+ clrrwi r4,r4,10 /* Mask off the real page number */
+ ori r4,r4,(TLB_WR | TLB_EX) /* Set the write and execute bits */
+
+ clrrwi r3,r3,10 /* Mask off the effective page number */
+ ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M))
+
+ li r0,63 /* TLB slot 63 */
+
+ tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
+ tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
+
+#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE)
+
+ /* Load a TLB entry for the UART, so that ppc4xx_progress() can use
+ * the UARTs nice and early. We use a 4k real==virtual mapping. */
+
+ lis r3,SERIAL_DEBUG_IO_BASE@h
+ ori r3,r3,SERIAL_DEBUG_IO_BASE@l
+ mr r4,r3
+ clrrwi r4,r4,12
+ ori r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G)
+
+ clrrwi r3,r3,12
+ ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K))
+
+ li r0,0 /* TLB slot 0 */
+ tlbwe r4,r0,TLB_DATA
+ tlbwe r3,r0,TLB_TAG
+#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */
+
+ isync
+
+ /* Establish the exception vector base
+ */
+ lis r4,KERNELBASE@h /* EVPR only uses the high 16-bits */
+ tophys(r0,r4) /* Use the physical address */
+ mtspr SPRN_EVPR,r0
+
+ blr
+
+_GLOBAL(abort)
+ mfspr r13,SPRN_DBCR0
+ oris r13,r13,DBCR0_RST_SYSTEM@h
+ mtspr SPRN_DBCR0,r13
+
+_GLOBAL(set_context)
+
+#ifdef CONFIG_BDI_SWITCH
+ /* Context switch the PTE pointer for the Abatron BDI2000.
+ * The PGDIR is the second parameter.
+ */
+ lis r5, KERNELBASE@h
+ lwz r5, 0xf0(r5)
+ stw r4, 0x4(r5)
+#endif
+ sync
+ mtspr SPRN_PID,r3
+ isync /* Need an isync to flush shadow */
+ /* TLBs after changing PID */
+ blr
+
+/* We put a few things here that have to be page-aligned. This stuff
+ * goes at the beginning of the data segment, which is page-aligned.
+ */
+ .data
+_GLOBAL(sdata)
+_GLOBAL(empty_zero_page)
+ .space 4096
+_GLOBAL(swapper_pg_dir)
+ .space 4096
+
+
+/* Stack for handling critical exceptions from kernel mode */
+ .section .bss
+ .align 12
+exception_stack_bottom:
+ .space 4096
+critical_stack_top:
+_GLOBAL(exception_stack_top)
+
+/* This space gets a copy of optional info passed to us by the bootstrap
+ * which is used to pass parameters into the kernel like root=/dev/sda1, etc.
+ */
+_GLOBAL(cmd_line)
+ .space 512
+
+/* Room for two PTE pointers, usually the kernel and current user pointers
+ * to their respective root page table.
+ */
+abatron_pteptrs:
+ .space 8
diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S
new file mode 100644
index 000000000000..5a7a64e91fc5
--- /dev/null
+++ b/arch/ppc/kernel/head_8xx.S
@@ -0,0 +1,862 @@
+/*
+ * arch/ppc/kernel/except_8xx.S
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications by Dan Malek
+ * Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ * This file contains low-level support and setup for PowerPC 8xx
+ * embedded processors, including trap and interrupt dispatch.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cache.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+
+/* Macro to make the code more readable. */
+#ifdef CONFIG_8xx_CPU6
+#define DO_8xx_CPU6(val, reg) \
+ li reg, val; \
+ stw reg, 12(r0); \
+ lwz reg, 12(r0);
+#else
+#define DO_8xx_CPU6(val, reg)
+#endif
+ .text
+ .globl _stext
+_stext:
+ .text
+ .globl _start
+_start:
+
+/* MPC8xx
+ * This port was done on an MBX board with an 860. Right now I only
+ * support an ELF compressed (zImage) boot from EPPC-Bug because the
+ * code there loads up some registers before calling us:
+ * r3: ptr to board info data
+ * r4: initrd_start or if no initrd then 0
+ * r5: initrd_end - unused if r4 is 0
+ * r6: Start of command line string
+ * r7: End of command line string
+ *
+ * I decided to use conditional compilation instead of checking PVR and
+ * adding more processor specific branches around code I don't need.
+ * Since this is an embedded processor, I also appreciate any memory
+ * savings I can get.
+ *
+ * The MPC8xx does not have any BATs, but it supports large page sizes.
+ * We first initialize the MMU to support 8M byte pages, then load one
+ * entry into each of the instruction and data TLBs to map the first
+ * 8M 1:1. I also mapped an additional I/O space 1:1 so we can get to
+ * the "internal" processor registers before MMU_init is called.
+ *
+ * The TLB code currently contains a major hack. Since I use the condition
+ * code register, I have to save and restore it. I am out of registers, so
+ * I just store it in memory location 0 (the TLB handlers are not reentrant).
+ * To avoid making any decisions, I need to use the "segment" valid bit
+ * in the first level table, but that would require many changes to the
+ * Linux page directory/table functions that I don't want to do right now.
+ *
+ * I used to use SPRG2 for a temporary register in the TLB handler, but it
+ * has since been put to other uses. I now use a hack to save a register
+ * and the CCR at memory location 0.....Someday I'll fix this.....
+ * -- Dan
+ */
+ .globl __start
+__start:
+ mr r31,r3 /* save parameters */
+ mr r30,r4
+ mr r29,r5
+ mr r28,r6
+ mr r27,r7
+
+ /* We have to turn on the MMU right away so we get cache modes
+ * set correctly.
+ */
+ bl initial_mmu
+
+/* We now have the lower 8 Meg mapped into TLB entries, and the caches
+ * ready to work.
+ */
+
+turn_on_mmu:
+ mfmsr r0
+ ori r0,r0,MSR_DR|MSR_IR
+ mtspr SPRN_SRR1,r0
+ lis r0,start_here@h
+ ori r0,r0,start_here@l
+ mtspr SPRN_SRR0,r0
+ SYNC
+ rfi /* enables MMU */
+
+/*
+ * Exception entry code. This code runs with address translation
+ * turned off, i.e. using physical addresses.
+ * We assume sprg3 has the physical address of the current
+ * task's thread_struct.
+ */
+#define EXCEPTION_PROLOG \
+ mtspr SPRN_SPRG0,r10; \
+ mtspr SPRN_SPRG1,r11; \
+ mfcr r10; \
+ EXCEPTION_PROLOG_1; \
+ EXCEPTION_PROLOG_2
+
+#define EXCEPTION_PROLOG_1 \
+ mfspr r11,SPRN_SRR1; /* check whether user or kernel */ \
+ andi. r11,r11,MSR_PR; \
+ tophys(r11,r1); /* use tophys(r1) if kernel */ \
+ beq 1f; \
+ mfspr r11,SPRN_SPRG3; \
+ lwz r11,THREAD_INFO-THREAD(r11); \
+ addi r11,r11,THREAD_SIZE; \
+ tophys(r11,r11); \
+1: subi r11,r11,INT_FRAME_SIZE /* alloc exc. frame */
+
+
+#define EXCEPTION_PROLOG_2 \
+ CLR_TOP32(r11); \
+ stw r10,_CCR(r11); /* save registers */ \
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mfspr r10,SPRN_SPRG0; \
+ stw r10,GPR10(r11); \
+ mfspr r12,SPRN_SPRG1; \
+ stw r12,GPR11(r11); \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r12,SPRN_SRR0; \
+ mfspr r9,SPRN_SRR1; \
+ stw r1,GPR1(r11); \
+ stw r1,0(r11); \
+ tovirt(r1,r11); /* set new kernel sp */ \
+ li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \
+ MTMSRD(r10); /* (except for mach check in rtas) */ \
+ stw r0,GPR0(r11); \
+ SAVE_4GPRS(3, r11); \
+ SAVE_2GPRS(7, r11)
+
+/*
+ * Note: code which follows this uses cr0.eq (set if from kernel),
+ * r11, r12 (SRR0), and r9 (SRR1).
+ *
+ * Note2: once we have set r1 we are in a position to take exceptions
+ * again, and we could thus set MSR:RI at that point.
+ */
+
+/*
+ * Exception vectors.
+ */
+#define EXCEPTION(n, label, hdlr, xfer) \
+ . = n; \
+label: \
+ EXCEPTION_PROLOG; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ xfer(n, hdlr)
+
+#define EXC_XFER_TEMPLATE(n, hdlr, trap, copyee, tfer, ret) \
+ li r10,trap; \
+ stw r10,TRAP(r11); \
+ li r10,MSR_KERNEL; \
+ copyee(r10, r9); \
+ bl tfer; \
+i##n: \
+ .long hdlr; \
+ .long ret
+
+#define COPY_EE(d, s) rlwimi d,s,0,16,16
+#define NOCOPY(d, s)
+
+#define EXC_XFER_STD(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n, NOCOPY, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n+1, NOCOPY, transfer_to_handler, \
+ ret_from_except)
+
+#define EXC_XFER_EE(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n, COPY_EE, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_EE_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(n, hdlr, n+1, COPY_EE, transfer_to_handler, \
+ ret_from_except)
+
+/* System reset */
+ EXCEPTION(0x100, Reset, UnknownException, EXC_XFER_STD)
+
+/* Machine check */
+ . = 0x200
+MachineCheck:
+ EXCEPTION_PROLOG
+ mfspr r4,SPRN_DAR
+ stw r4,_DAR(r11)
+ mfspr r5,SPRN_DSISR
+ stw r5,_DSISR(r11)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_STD(0x200, MachineCheckException)
+
+/* Data access exception.
+ * This is "never generated" by the MPC8xx. We jump to it for other
+ * translation errors.
+ */
+ . = 0x300
+DataAccess:
+ EXCEPTION_PROLOG
+ mfspr r10,SPRN_DSISR
+ stw r10,_DSISR(r11)
+ mr r5,r10
+ mfspr r4,SPRN_DAR
+ EXC_XFER_EE_LITE(0x300, handle_page_fault)
+
+/* Instruction access exception.
+ * This is "never generated" by the MPC8xx. We jump to it for other
+ * translation errors.
+ */
+ . = 0x400
+InstructionAccess:
+ EXCEPTION_PROLOG
+ mr r4,r12
+ mr r5,r9
+ EXC_XFER_EE_LITE(0x400, handle_page_fault)
+
+/* External interrupt */
+ EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
+
+/* Alignment exception */
+ . = 0x600
+Alignment:
+ EXCEPTION_PROLOG
+ mfspr r4,SPRN_DAR
+ stw r4,_DAR(r11)
+ mfspr r5,SPRN_DSISR
+ stw r5,_DSISR(r11)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_EE(0x600, AlignmentException)
+
+/* Program check exception */
+ EXCEPTION(0x700, ProgramCheck, ProgramCheckException, EXC_XFER_STD)
+
+/* No FPU on MPC8xx. This exception is not supposed to happen.
+*/
+ EXCEPTION(0x800, FPUnavailable, UnknownException, EXC_XFER_STD)
+
+/* Decrementer */
+ EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
+
+ EXCEPTION(0xa00, Trap_0a, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0xb00, Trap_0b, UnknownException, EXC_XFER_EE)
+
+/* System call */
+ . = 0xc00
+SystemCall:
+ EXCEPTION_PROLOG
+ EXC_XFER_EE_LITE(0xc00, DoSyscall)
+
+/* Single step - not used on 601 */
+ EXCEPTION(0xd00, SingleStep, SingleStepException, EXC_XFER_STD)
+ EXCEPTION(0xe00, Trap_0e, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0xf00, Trap_0f, UnknownException, EXC_XFER_EE)
+
+/* On the MPC8xx, this is a software emulation interrupt. It occurs
+ * for all unimplemented and illegal instructions.
+ */
+ EXCEPTION(0x1000, SoftEmu, SoftwareEmulation, EXC_XFER_STD)
+
+ . = 0x1100
+/*
+ * For the MPC8xx, this is a software tablewalk to load the instruction
+ * TLB. It is modelled after the example in the Motorola manual. The task
+ * switch loads the M_TWB register with the pointer to the first level table.
+ * If we discover there is no second level table (the value is zero), the
+ * plan was to load that into the TLB, which causes another fault into the
+ * TLB Error interrupt where we can handle such problems. However, that did
+ * not work, so if we discover there is no second level table, we restore
+ * registers and branch to the error exception. We have to use the MD_xxx
+ * registers for the tablewalk because the equivalent MI_xxx registers
+ * only perform the attribute functions.
+ */
+InstructionTLBMiss:
+#ifdef CONFIG_8xx_CPU6
+ stw r3, 8(r0)
+#endif
+ DO_8xx_CPU6(0x3f80, r3)
+ mtspr SPRN_M_TW, r10 /* Save a couple of working registers */
+ mfcr r10
+ stw r10, 0(r0)
+ stw r11, 4(r0)
+ mfspr r10, SPRN_SRR0 /* Get effective address of fault */
+ DO_8xx_CPU6(0x3780, r3)
+ mtspr SPRN_MD_EPN, r10 /* Have to use MD_EPN for walk, MI_EPN can't */
+ mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andi. r11, r10, 0x0800 /* Address >= 0x80000000 */
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ rlwimi r10, r11, 0, 2, 19
+3:
+ lwz r11, 0(r10) /* Get the level 1 entry */
+ rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */
+ beq 2f /* If zero, don't try to find a pte */
+
+ /* We have a pte table, so load the MI_TWC with the attributes
+ * for this "segment."
+ */
+ ori r11,r11,1 /* Set valid bit */
+ DO_8xx_CPU6(0x2b80, r3)
+ mtspr SPRN_MI_TWC, r11 /* Set segment attributes */
+ DO_8xx_CPU6(0x3b80, r3)
+ mtspr SPRN_MD_TWC, r11 /* Load pte table base address */
+ mfspr r11, SPRN_MD_TWC /* ....and get the pte address */
+ lwz r10, 0(r11) /* Get the pte */
+
+ ori r10, r10, _PAGE_ACCESSED
+ stw r10, 0(r11)
+
+ /* The Linux PTE won't go exactly into the MMU TLB.
+ * Software indicator bits 21, 22 and 28 must be clear.
+ * Software indicator bits 24, 25, 26, and 27 must be
+ * set. All other Linux PTE bits control the behavior
+ * of the MMU.
+ */
+2: li r11, 0x00f0
+ rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */
+ DO_8xx_CPU6(0x2d80, r3)
+ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
+
+ mfspr r10, SPRN_M_TW /* Restore registers */
+ lwz r11, 0(r0)
+ mtcr r11
+ lwz r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+ lwz r3, 8(r0)
+#endif
+ rfi
+
+ . = 0x1200
+DataStoreTLBMiss:
+#ifdef CONFIG_8xx_CPU6
+ stw r3, 8(r0)
+#endif
+ DO_8xx_CPU6(0x3f80, r3)
+ mtspr SPRN_M_TW, r10 /* Save a couple of working registers */
+ mfcr r10
+ stw r10, 0(r0)
+ stw r11, 4(r0)
+ mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andi. r11, r10, 0x0800
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ rlwimi r10, r11, 0, 2, 19
+3:
+ lwz r11, 0(r10) /* Get the level 1 entry */
+ rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */
+ beq 2f /* If zero, don't try to find a pte */
+
+ /* We have a pte table, so load fetch the pte from the table.
+ */
+ ori r11, r11, 1 /* Set valid bit in physical L2 page */
+ DO_8xx_CPU6(0x3b80, r3)
+ mtspr SPRN_MD_TWC, r11 /* Load pte table base address */
+ mfspr r10, SPRN_MD_TWC /* ....and get the pte address */
+ lwz r10, 0(r10) /* Get the pte */
+
+ /* Insert the Guarded flag into the TWC from the Linux PTE.
+ * It is bit 27 of both the Linux PTE and the TWC (at least
+ * I got that right :-). It will be better when we can put
+ * this into the Linux pgd/pmd and load it in the operation
+ * above.
+ */
+ rlwimi r11, r10, 0, 27, 27
+ DO_8xx_CPU6(0x3b80, r3)
+ mtspr SPRN_MD_TWC, r11
+
+ mfspr r11, SPRN_MD_TWC /* get the pte address again */
+ ori r10, r10, _PAGE_ACCESSED
+ stw r10, 0(r11)
+
+ /* The Linux PTE won't go exactly into the MMU TLB.
+ * Software indicator bits 21, 22 and 28 must be clear.
+ * Software indicator bits 24, 25, 26, and 27 must be
+ * set. All other Linux PTE bits control the behavior
+ * of the MMU.
+ */
+2: li r11, 0x00f0
+ rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */
+ DO_8xx_CPU6(0x3d80, r3)
+ mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
+
+ mfspr r10, SPRN_M_TW /* Restore registers */
+ lwz r11, 0(r0)
+ mtcr r11
+ lwz r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+ lwz r3, 8(r0)
+#endif
+ rfi
+
+/* This is an instruction TLB error on the MPC8xx. This could be due
+ * to many reasons, such as executing guarded memory or illegal instruction
+ * addresses. There is nothing to do but handle a big time error fault.
+ */
+ . = 0x1300
+InstructionTLBError:
+ b InstructionAccess
+
+/* This is the data TLB error on the MPC8xx. This could be due to
+ * many reasons, including a dirty update to a pte. We can catch that
+ * one here, but anything else is an error. First, we track down the
+ * Linux pte. If it is valid, write access is allowed, but the
+ * page dirty bit is not set, we will set it and reload the TLB. For
+ * any other case, we bail out to a higher level function that can
+ * handle it.
+ */
+ . = 0x1400
+DataTLBError:
+#ifdef CONFIG_8xx_CPU6
+ stw r3, 8(r0)
+#endif
+ DO_8xx_CPU6(0x3f80, r3)
+ mtspr SPRN_M_TW, r10 /* Save a couple of working registers */
+ mfcr r10
+ stw r10, 0(r0)
+ stw r11, 4(r0)
+
+ /* First, make sure this was a store operation.
+ */
+ mfspr r10, SPRN_DSISR
+ andis. r11, r10, 0x0200 /* If set, indicates store op */
+ beq 2f
+
+ /* The EA of a data TLB miss is automatically stored in the MD_EPN
+ * register. The EA of a data TLB error is automatically stored in
+ * the DAR, but not the MD_EPN register. We must copy the 20 most
+ * significant bits of the EA from the DAR to MD_EPN before we
+ * start walking the page tables. We also need to copy the CASID
+ * value from the M_CASID register.
+ * Addendum: The EA of a data TLB error is _supposed_ to be stored
+ * in DAR, but it seems that this doesn't happen in some cases, such
+ * as when the error is due to a dcbi instruction to a page with a
+ * TLB that doesn't have the changed bit set. In such cases, there
+ * does not appear to be any way to recover the EA of the error
+ * since it is neither in DAR nor MD_EPN. As a workaround, the
+ * _PAGE_HWWRITE bit is set for all kernel data pages when the PTEs
+ * are initialized in mapin_ram(). This will avoid the problem,
+ * assuming we only use the dcbi instruction on kernel addresses.
+ */
+ mfspr r10, SPRN_DAR
+ rlwinm r11, r10, 0, 0, 19
+ ori r11, r11, MD_EVALID
+ mfspr r10, SPRN_M_CASID
+ rlwimi r11, r10, 0, 28, 31
+ DO_8xx_CPU6(0x3780, r3)
+ mtspr SPRN_MD_EPN, r11
+
+ mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ andi. r11, r10, 0x0800
+ beq 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ rlwimi r10, r11, 0, 2, 19
+3:
+ lwz r11, 0(r10) /* Get the level 1 entry */
+ rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */
+ beq 2f /* If zero, bail */
+
+ /* We have a pte table, so fetch the pte from the table.
+ */
+ ori r11, r11, 1 /* Set valid bit in physical L2 page */
+ DO_8xx_CPU6(0x3b80, r3)
+ mtspr SPRN_MD_TWC, r11 /* Load pte table base address */
+ mfspr r11, SPRN_MD_TWC /* ....and get the pte address */
+ lwz r10, 0(r11) /* Get the pte */
+
+ andi. r11, r10, _PAGE_RW /* Is it writeable? */
+ beq 2f /* Bail out if not */
+
+ /* Update 'changed', among others.
+ */
+ ori r10, r10, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
+ mfspr r11, SPRN_MD_TWC /* Get pte address again */
+ stw r10, 0(r11) /* and update pte in table */
+
+ /* The Linux PTE won't go exactly into the MMU TLB.
+ * Software indicator bits 21, 22 and 28 must be clear.
+ * Software indicator bits 24, 25, 26, and 27 must be
+ * set. All other Linux PTE bits control the behavior
+ * of the MMU.
+ */
+ li r11, 0x00f0
+ rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */
+ DO_8xx_CPU6(0x3d80, r3)
+ mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
+
+ mfspr r10, SPRN_M_TW /* Restore registers */
+ lwz r11, 0(r0)
+ mtcr r11
+ lwz r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+ lwz r3, 8(r0)
+#endif
+ rfi
+2:
+ mfspr r10, SPRN_M_TW /* Restore registers */
+ lwz r11, 0(r0)
+ mtcr r11
+ lwz r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+ lwz r3, 8(r0)
+#endif
+ b DataAccess
+
+ EXCEPTION(0x1500, Trap_15, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1600, Trap_16, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1700, Trap_17, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1800, Trap_18, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1900, Trap_19, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1a00, Trap_1a, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1b00, Trap_1b, UnknownException, EXC_XFER_EE)
+
+/* On the MPC8xx, these next four traps are used for development
+ * support of breakpoints and such. Someday I will get around to
+ * using them.
+ */
+ EXCEPTION(0x1c00, Trap_1c, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1d00, Trap_1d, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1e00, Trap_1e, UnknownException, EXC_XFER_EE)
+ EXCEPTION(0x1f00, Trap_1f, UnknownException, EXC_XFER_EE)
+
+ . = 0x2000
+
+ .globl giveup_fpu
+giveup_fpu:
+ blr
+
+/*
+ * This is where the main kernel code starts.
+ */
+start_here:
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG3,r4
+ li r3,0
+ mtspr SPRN_SPRG2,r3 /* 0 => r1 has kernel sp */
+
+ /* stack */
+ lis r1,init_thread_union@ha
+ addi r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+
+ bl early_init /* We have to do this with MMU on */
+
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+ mr r3,r31
+ mr r4,r30
+ mr r5,r29
+ mr r6,r28
+ mr r7,r27
+ bl machine_init
+ bl MMU_init
+
+/*
+ * Go back to running unmapped so we can load up new values
+ * and change to using our exception vectors.
+ * On the 8xx, all we have to do is invalidate the TLB to clear
+ * the old 8M byte TLB mappings and load the page table base register.
+ */
+ /* The right way to do this would be to track it down through
+ * init's THREAD like the context switch code does, but this is
+ * easier......until someone changes init's static structures.
+ */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ tophys(r6,r6)
+#ifdef CONFIG_8xx_CPU6
+ lis r4, cpu6_errata_word@h
+ ori r4, r4, cpu6_errata_word@l
+ li r3, 0x3980
+ stw r3, 12(r4)
+ lwz r3, 12(r4)
+#endif
+ mtspr SPRN_M_TWB, r6
+ lis r4,2f@h
+ ori r4,r4,2f@l
+ tophys(r4,r4)
+ li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi
+/* Load up the kernel context */
+2:
+ SYNC /* Force all PTE updates to finish */
+ tlbia /* Clear all TLB entries */
+ sync /* wait for tlbia/tlbie to finish */
+ TLBSYNC /* ... on all CPUs */
+
+ /* set up the PTE pointers for the Abatron bdiGDB.
+ */
+ tovirt(r6,r6)
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r5, 0xf0(r0) /* Must match your Abatron config file */
+ tophys(r5,r5)
+ stw r6, 0(r5)
+
+/* Now turn on the MMU for real! */
+ li r4,MSR_KERNEL
+ lis r3,start_kernel@h
+ ori r3,r3,start_kernel@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ rfi /* enable MMU and jump to start_kernel */
+
+/* Set up the initial MMU state so we can do the first level of
+ * kernel initialization. This maps the first 8 MBytes of memory 1:1
+ * virtual to physical. Also, set the cache mode since that is defined
+ * by TLB entries and perform any additional mapping (like of the IMMR).
+ * If configured to pin some TLBs, we pin the first 8 Mbytes of kernel,
+ * 24 Mbytes of data, and the 8M IMMR space. Anything not covered by
+ * these mappings is mapped by page tables.
+ */
+initial_mmu:
+ tlbia /* Invalidate all TLB entries */
+#ifdef CONFIG_PIN_TLB
+ lis r8, MI_RSV4I@h
+ ori r8, r8, 0x1c00
+#else
+ li r8, 0
+#endif
+ mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */
+
+#ifdef CONFIG_PIN_TLB
+ lis r10, (MD_RSV4I | MD_RESETVAL)@h
+ ori r10, r10, 0x1c00
+ mr r8, r10
+#else
+ lis r10, MD_RESETVAL@h
+#endif
+#ifndef CONFIG_8xx_COPYBACK
+ oris r10, r10, MD_WTDEF@h
+#endif
+ mtspr SPRN_MD_CTR, r10 /* Set data TLB control */
+
+ /* Now map the lower 8 Meg into the TLBs. For this quick hack,
+ * we can load the instruction and data TLB registers with the
+ * same values.
+ */
+ lis r8, KERNELBASE@h /* Create vaddr for TLB */
+ ori r8, r8, MI_EVALID /* Mark it valid */
+ mtspr SPRN_MI_EPN, r8
+ mtspr SPRN_MD_EPN, r8
+ li r8, MI_PS8MEG /* Set 8M byte page */
+ ori r8, r8, MI_SVALID /* Make it valid */
+ mtspr SPRN_MI_TWC, r8
+ mtspr SPRN_MD_TWC, r8
+ li r8, MI_BOOTINIT /* Create RPN for address 0 */
+ mtspr SPRN_MI_RPN, r8 /* Store TLB entry */
+ mtspr SPRN_MD_RPN, r8
+ lis r8, MI_Kp@h /* Set the protection mode */
+ mtspr SPRN_MI_AP, r8
+ mtspr SPRN_MD_AP, r8
+
+ /* Map another 8 MByte at the IMMR to get the processor
+ * internal registers (among other things).
+ */
+#ifdef CONFIG_PIN_TLB
+ addi r10, r10, 0x0100
+ mtspr SPRN_MD_CTR, r10
+#endif
+ mfspr r9, 638 /* Get current IMMR */
+ andis. r9, r9, 0xff80 /* Get 8Mbyte boundary */
+
+ mr r8, r9 /* Create vaddr for TLB */
+ ori r8, r8, MD_EVALID /* Mark it valid */
+ mtspr SPRN_MD_EPN, r8
+ li r8, MD_PS8MEG /* Set 8M byte page */
+ ori r8, r8, MD_SVALID /* Make it valid */
+ mtspr SPRN_MD_TWC, r8
+ mr r8, r9 /* Create paddr for TLB */
+ ori r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */
+ mtspr SPRN_MD_RPN, r8
+
+#ifdef CONFIG_PIN_TLB
+ /* Map two more 8M kernel data pages.
+ */
+ addi r10, r10, 0x0100
+ mtspr SPRN_MD_CTR, r10
+
+ lis r8, KERNELBASE@h /* Create vaddr for TLB */
+ addis r8, r8, 0x0080 /* Add 8M */
+ ori r8, r8, MI_EVALID /* Mark it valid */
+ mtspr SPRN_MD_EPN, r8
+ li r9, MI_PS8MEG /* Set 8M byte page */
+ ori r9, r9, MI_SVALID /* Make it valid */
+ mtspr SPRN_MD_TWC, r9
+ li r11, MI_BOOTINIT /* Create RPN for address 0 */
+ addis r11, r11, 0x0080 /* Add 8M */
+ mtspr SPRN_MD_RPN, r8
+
+ addis r8, r8, 0x0080 /* Add 8M */
+ mtspr SPRN_MD_EPN, r8
+ mtspr SPRN_MD_TWC, r9
+ addis r11, r11, 0x0080 /* Add 8M */
+ mtspr SPRN_MD_RPN, r8
+#endif
+
+ /* Since the cache is enabled according to the information we
+ * just loaded into the TLB, invalidate and enable the caches here.
+ * We should probably check/set other modes....later.
+ */
+ lis r8, IDC_INVALL@h
+ mtspr SPRN_IC_CST, r8
+ mtspr SPRN_DC_CST, r8
+ lis r8, IDC_ENABLE@h
+ mtspr SPRN_IC_CST, r8
+#ifdef CONFIG_8xx_COPYBACK
+ mtspr SPRN_DC_CST, r8
+#else
+ /* For a debug option, I left this here to easily enable
+ * the write through cache mode
+ */
+ lis r8, DC_SFWT@h
+ mtspr SPRN_DC_CST, r8
+ lis r8, IDC_ENABLE@h
+ mtspr SPRN_DC_CST, r8
+#endif
+ blr
+
+
+/*
+ * Set up to use a given MMU context.
+ * r3 is context number, r4 is PGD pointer.
+ *
+ * We place the physical address of the new task page directory loaded
+ * into the MMU base register, and set the ASID compare register with
+ * the new "context."
+ */
+_GLOBAL(set_context)
+
+#ifdef CONFIG_BDI_SWITCH
+ /* Context switch the PTE pointer for the Abatron BDI2000.
+ * The PGDIR is passed as second argument.
+ */
+ lis r5, KERNELBASE@h
+ lwz r5, 0xf0(r5)
+ stw r4, 0x4(r5)
+#endif
+
+#ifdef CONFIG_8xx_CPU6
+ lis r6, cpu6_errata_word@h
+ ori r6, r6, cpu6_errata_word@l
+ tophys (r4, r4)
+ li r7, 0x3980
+ stw r7, 12(r6)
+ lwz r7, 12(r6)
+ mtspr SPRN_M_TWB, r4 /* Update MMU base address */
+ li r7, 0x3380
+ stw r7, 12(r6)
+ lwz r7, 12(r6)
+ mtspr SPRN_M_CASID, r3 /* Update context */
+#else
+ mtspr SPRN_M_CASID,r3 /* Update context */
+ tophys (r4, r4)
+ mtspr SPRN_M_TWB, r4 /* and pgd */
+#endif
+ SYNC
+ blr
+
+#ifdef CONFIG_8xx_CPU6
+/* It's here because it is unique to the 8xx.
+ * It is important we get called with interrupts disabled. I used to
+ * do that, but it appears that all code that calls this already had
+ * interrupt disabled.
+ */
+ .globl set_dec_cpu6
+set_dec_cpu6:
+ lis r7, cpu6_errata_word@h
+ ori r7, r7, cpu6_errata_word@l
+ li r4, 0x2c00
+ stw r4, 8(r7)
+ lwz r4, 8(r7)
+ mtspr 22, r3 /* Update Decrementer */
+ SYNC
+ blr
+#endif
+
+/*
+ * We put a few things here that have to be page-aligned.
+ * This stuff goes at the beginning of the data segment,
+ * which is page-aligned.
+ */
+ .data
+ .globl sdata
+sdata:
+ .globl empty_zero_page
+empty_zero_page:
+ .space 4096
+
+ .globl swapper_pg_dir
+swapper_pg_dir:
+ .space 4096
+
+/*
+ * This space gets a copy of optional info passed to us by the bootstrap
+ * Used to pass parameters into the kernel like root=/dev/sda1, etc.
+ */
+ .globl cmd_line
+cmd_line:
+ .space 512
+
+/* Room for two PTE table poiners, usually the kernel and current user
+ * pointer to their respective root page table (pgdir).
+ */
+abatron_pteptrs:
+ .space 8
+
+#ifdef CONFIG_8xx_CPU6
+ .globl cpu6_errata_word
+cpu6_errata_word:
+ .space 16
+#endif
+
diff --git a/arch/ppc/kernel/head_booke.h b/arch/ppc/kernel/head_booke.h
new file mode 100644
index 000000000000..884dac916bce
--- /dev/null
+++ b/arch/ppc/kernel/head_booke.h
@@ -0,0 +1,340 @@
+#ifndef __HEAD_BOOKE_H__
+#define __HEAD_BOOKE_H__
+
+/*
+ * Macros used for common Book-e exception handling
+ */
+
+#define SET_IVOR(vector_number, vector_label) \
+ li r26,vector_label@l; \
+ mtspr SPRN_IVOR##vector_number,r26; \
+ sync
+
+#define NORMAL_EXCEPTION_PROLOG \
+ mtspr SPRN_SPRG0,r10; /* save two registers to work with */\
+ mtspr SPRN_SPRG1,r11; \
+ mtspr SPRN_SPRG4W,r1; \
+ mfcr r10; /* save CR in r10 for now */\
+ mfspr r11,SPRN_SRR1; /* check whether user or kernel */\
+ andi. r11,r11,MSR_PR; \
+ beq 1f; \
+ mfspr r1,SPRN_SPRG3; /* if from user, start at top of */\
+ lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\
+ addi r1,r1,THREAD_SIZE; \
+1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\
+ mr r11,r1; \
+ stw r10,_CCR(r11); /* save various registers */\
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mfspr r10,SPRN_SPRG0; \
+ stw r10,GPR10(r11); \
+ mfspr r12,SPRN_SPRG1; \
+ stw r12,GPR11(r11); \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r10,SPRN_SPRG4R; \
+ mfspr r12,SPRN_SRR0; \
+ stw r10,GPR1(r11); \
+ mfspr r9,SPRN_SRR1; \
+ stw r10,0(r11); \
+ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\
+ stw r0,GPR0(r11); \
+ SAVE_4GPRS(3, r11); \
+ SAVE_2GPRS(7, r11)
+
+/* To handle the additional exception priority levels on 40x and Book-E
+ * processors we allocate a 4k stack per additional priority level. The various
+ * head_xxx.S files allocate space (exception_stack_top) for each priority's
+ * stack times the number of CPUs
+ *
+ * On 40x critical is the only additional level
+ * On 44x/e500 we have critical and machine check
+ *
+ * Additionally we reserve a SPRG for each priority level so we can free up a
+ * GPR to use as the base for indirect access to the exception stacks. This
+ * is necessary since the MMU is always on, for Book-E parts, and the stacks
+ * are offset from KERNELBASE.
+ *
+ */
+#define BOOKE_EXCEPTION_STACK_SIZE (8192)
+
+/* CRIT_SPRG only used in critical exception handling */
+#define CRIT_SPRG SPRN_SPRG2
+/* MCHECK_SPRG only used in critical exception handling */
+#define MCHECK_SPRG SPRN_SPRG6W
+
+#define MCHECK_STACK_TOP (exception_stack_top - 4096)
+#define CRIT_STACK_TOP (exception_stack_top)
+
+#ifdef CONFIG_SMP
+#define BOOKE_LOAD_CRIT_STACK \
+ mfspr r8,SPRN_PIR; \
+ mulli r8,r8,BOOKE_EXCEPTION_STACK_SIZE; \
+ neg r8,r8; \
+ addis r8,r8,CRIT_STACK_TOP@ha; \
+ addi r8,r8,CRIT_STACK_TOP@l
+#define BOOKE_LOAD_MCHECK_STACK \
+ mfspr r8,SPRN_PIR; \
+ mulli r8,r8,BOOKE_EXCEPTION_STACK_SIZE; \
+ neg r8,r8; \
+ addis r8,r8,MCHECK_STACK_TOP@ha; \
+ addi r8,r8,MCHECK_STACK_TOP@l
+#else
+#define BOOKE_LOAD_CRIT_STACK \
+ lis r8,CRIT_STACK_TOP@h; \
+ ori r8,r8,CRIT_STACK_TOP@l
+#define BOOKE_LOAD_MCHECK_STACK \
+ lis r8,MCHECK_STACK_TOP@h; \
+ ori r8,r8,MCHECK_STACK_TOP@l
+#endif
+
+/*
+ * Exception prolog for critical exceptions. This is a little different
+ * from the normal exception prolog above since a critical exception
+ * can potentially occur at any point during normal exception processing.
+ * Thus we cannot use the same SPRG registers as the normal prolog above.
+ * Instead we use a portion of the critical exception stack at low physical
+ * addresses.
+ */
+
+#define CRITICAL_EXCEPTION_PROLOG \
+ mtspr CRIT_SPRG,r8; \
+ BOOKE_LOAD_CRIT_STACK; /* r8 points to the crit stack */ \
+ stw r10,GPR10-INT_FRAME_SIZE(r8); \
+ stw r11,GPR11-INT_FRAME_SIZE(r8); \
+ mfcr r10; /* save CR in r10 for now */\
+ mfspr r11,SPRN_CSRR1; /* check whether user or kernel */\
+ andi. r11,r11,MSR_PR; \
+ mr r11,r8; \
+ mfspr r8,CRIT_SPRG; \
+ beq 1f; \
+ /* COMING FROM USER MODE */ \
+ mfspr r11,SPRN_SPRG3; /* if from user, start at top of */\
+ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ addi r11,r11,THREAD_SIZE; \
+1: subi r11,r11,INT_FRAME_SIZE; /* Allocate an exception frame */\
+ stw r10,_CCR(r11); /* save various registers */\
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r12,SPRN_DEAR; /* save DEAR and ESR in the frame */\
+ stw r12,_DEAR(r11); /* since they may have had stuff */\
+ mfspr r9,SPRN_ESR; /* in them at the point where the */\
+ stw r9,_ESR(r11); /* exception was taken */\
+ mfspr r12,SPRN_CSRR0; \
+ stw r1,GPR1(r11); \
+ mfspr r9,SPRN_CSRR1; \
+ stw r1,0(r11); \
+ mr r1,r11; \
+ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\
+ stw r0,GPR0(r11); \
+ SAVE_4GPRS(3, r11); \
+ SAVE_2GPRS(7, r11)
+
+/*
+ * Exception prolog for machine check exceptions. This is similar to
+ * the critical exception prolog, except that machine check exceptions
+ * have their stack.
+ */
+#define MCHECK_EXCEPTION_PROLOG \
+ mtspr MCHECK_SPRG,r8; \
+ BOOKE_LOAD_MCHECK_STACK; /* r8 points to the mcheck stack */\
+ stw r10,GPR10-INT_FRAME_SIZE(r8); \
+ stw r11,GPR11-INT_FRAME_SIZE(r8); \
+ mfcr r10; /* save CR in r10 for now */\
+ mfspr r11,SPRN_MCSRR1; /* check whether user or kernel */\
+ andi. r11,r11,MSR_PR; \
+ mr r11,r8; \
+ mfspr r8,MCHECK_SPRG; \
+ beq 1f; \
+ /* COMING FROM USER MODE */ \
+ mfspr r11,SPRN_SPRG3; /* if from user, start at top of */\
+ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+ addi r11,r11,THREAD_SIZE; \
+1: subi r11,r11,INT_FRAME_SIZE; /* Allocate an exception frame */\
+ stw r10,_CCR(r11); /* save various registers */\
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r12,SPRN_DEAR; /* save DEAR and ESR in the frame */\
+ stw r12,_DEAR(r11); /* since they may have had stuff */\
+ mfspr r9,SPRN_ESR; /* in them at the point where the */\
+ stw r9,_ESR(r11); /* exception was taken */\
+ mfspr r12,SPRN_MCSRR0; \
+ stw r1,GPR1(r11); \
+ mfspr r9,SPRN_MCSRR1; \
+ stw r1,0(r11); \
+ mr r1,r11; \
+ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\
+ stw r0,GPR0(r11); \
+ SAVE_4GPRS(3, r11); \
+ SAVE_2GPRS(7, r11)
+
+/*
+ * Exception vectors.
+ */
+#define START_EXCEPTION(label) \
+ .align 5; \
+label:
+
+#define FINISH_EXCEPTION(func) \
+ bl transfer_to_handler_full; \
+ .long func; \
+ .long ret_from_except_full
+
+#define EXCEPTION(n, label, hdlr, xfer) \
+ START_EXCEPTION(label); \
+ NORMAL_EXCEPTION_PROLOG; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ xfer(n, hdlr)
+
+#define CRITICAL_EXCEPTION(n, label, hdlr) \
+ START_EXCEPTION(label); \
+ CRITICAL_EXCEPTION_PROLOG; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
+ NOCOPY, crit_transfer_to_handler, \
+ ret_from_crit_exc)
+
+#define MCHECK_EXCEPTION(n, label, hdlr) \
+ START_EXCEPTION(label); \
+ MCHECK_EXCEPTION_PROLOG; \
+ mfspr r5,SPRN_ESR; \
+ stw r5,_ESR(r11); \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
+ NOCOPY, mcheck_transfer_to_handler, \
+ ret_from_mcheck_exc)
+
+#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret) \
+ li r10,trap; \
+ stw r10,TRAP(r11); \
+ lis r10,msr@h; \
+ ori r10,r10,msr@l; \
+ copyee(r10, r9); \
+ bl tfer; \
+ .long hdlr; \
+ .long ret
+
+#define COPY_EE(d, s) rlwimi d,s,0,16,16
+#define NOCOPY(d, s)
+
+#define EXC_XFER_STD(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \
+ ret_from_except)
+
+#define EXC_XFER_EE(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \
+ ret_from_except_full)
+
+#define EXC_XFER_EE_LITE(n, hdlr) \
+ EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \
+ ret_from_except)
+
+
+/* Check for a single step debug exception while in an exception
+ * handler before state has been saved. This is to catch the case
+ * where an instruction that we are trying to single step causes
+ * an exception (eg ITLB/DTLB miss) and thus the first instruction of
+ * the exception handler generates a single step debug exception.
+ *
+ * If we get a debug trap on the first instruction of an exception handler,
+ * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is
+ * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR).
+ * The exception handler was handling a non-critical interrupt, so it will
+ * save (and later restore) the MSR via SPRN_CSRR1, which will still have
+ * the MSR_DE bit set.
+ */
+#define DEBUG_EXCEPTION \
+ START_EXCEPTION(Debug); \
+ CRITICAL_EXCEPTION_PROLOG; \
+ \
+ /* \
+ * If there is a single step or branch-taken exception in an \
+ * exception entry sequence, it was probably meant to apply to \
+ * the code where the exception occurred (since exception entry \
+ * doesn't turn off DE automatically). We simulate the effect \
+ * of turning off DE on entry to an exception handler by turning \
+ * off DE in the CSRR1 value and clearing the debug status. \
+ */ \
+ mfspr r10,SPRN_DBSR; /* check single-step/branch taken */ \
+ andis. r10,r10,DBSR_IC@h; \
+ beq+ 2f; \
+ \
+ lis r10,KERNELBASE@h; /* check if exception in vectors */ \
+ ori r10,r10,KERNELBASE@l; \
+ cmplw r12,r10; \
+ blt+ 2f; /* addr below exception vectors */ \
+ \
+ lis r10,Debug@h; \
+ ori r10,r10,Debug@l; \
+ cmplw r12,r10; \
+ bgt+ 2f; /* addr above exception vectors */ \
+ \
+ /* here it looks like we got an inappropriate debug exception. */ \
+1: rlwinm r9,r9,0,~MSR_DE; /* clear DE in the CSRR1 value */ \
+ lis r10,DBSR_IC@h; /* clear the IC event */ \
+ mtspr SPRN_DBSR,r10; \
+ /* restore state and get out */ \
+ lwz r10,_CCR(r11); \
+ lwz r0,GPR0(r11); \
+ lwz r1,GPR1(r11); \
+ mtcrf 0x80,r10; \
+ mtspr SPRN_CSRR0,r12; \
+ mtspr SPRN_CSRR1,r9; \
+ lwz r9,GPR9(r11); \
+ lwz r12,GPR12(r11); \
+ mtspr CRIT_SPRG,r8; \
+ BOOKE_LOAD_CRIT_STACK; /* r8 points to the crit stack */ \
+ lwz r10,GPR10-INT_FRAME_SIZE(r8); \
+ lwz r11,GPR11-INT_FRAME_SIZE(r8); \
+ mfspr r8,CRIT_SPRG; \
+ \
+ rfci; \
+ b .; \
+ \
+ /* continue normal handling for a critical exception... */ \
+2: mfspr r4,SPRN_DBSR; \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
+
+#define INSTRUCTION_STORAGE_EXCEPTION \
+ START_EXCEPTION(InstructionStorage) \
+ NORMAL_EXCEPTION_PROLOG; \
+ mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
+ stw r5,_ESR(r11); \
+ mr r4,r12; /* Pass SRR0 as arg2 */ \
+ li r5,0; /* Pass zero as arg3 */ \
+ EXC_XFER_EE_LITE(0x0400, handle_page_fault)
+
+#define ALIGNMENT_EXCEPTION \
+ START_EXCEPTION(Alignment) \
+ NORMAL_EXCEPTION_PROLOG; \
+ mfspr r4,SPRN_DEAR; /* Grab the DEAR and save it */ \
+ stw r4,_DEAR(r11); \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ EXC_XFER_EE(0x0600, AlignmentException)
+
+#define PROGRAM_EXCEPTION \
+ START_EXCEPTION(Program) \
+ NORMAL_EXCEPTION_PROLOG; \
+ mfspr r4,SPRN_ESR; /* Grab the ESR and save it */ \
+ stw r4,_ESR(r11); \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ EXC_XFER_STD(0x0700, ProgramCheckException)
+
+#define DECREMENTER_EXCEPTION \
+ START_EXCEPTION(Decrementer) \
+ NORMAL_EXCEPTION_PROLOG; \
+ lis r0,TSR_DIS@h; /* Setup the DEC interrupt mask */ \
+ mtspr SPRN_TSR,r0; /* Clear the DEC interrupt */ \
+ addi r3,r1,STACK_FRAME_OVERHEAD; \
+ EXC_XFER_LITE(0x0900, timer_interrupt)
+
+#endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/ppc/kernel/head_fsl_booke.S b/arch/ppc/kernel/head_fsl_booke.S
new file mode 100644
index 000000000000..dea19c216fc3
--- /dev/null
+++ b/arch/ppc/kernel/head_fsl_booke.S
@@ -0,0 +1,952 @@
+/*
+ * arch/ppc/kernel/head_fsl_booke.S
+ *
+ * Kernel execution entry point code.
+ *
+ * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
+ * Initial PowerPC version.
+ * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Rewritten for PReP
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Low-level exception handers, MMU support, and rewrite.
+ * Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
+ * PowerPC 8xx modifications.
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ * Copyright 2000 MontaVista Software Inc.
+ * PPC405 modifications
+ * PowerPC 403GCX/405GP modifications.
+ * Author: MontaVista Software, Inc.
+ * frank_rowand@mvista.com or source@mvista.com
+ * debbie_chu@mvista.com
+ * Copyright 2002-2004 MontaVista Software, Inc.
+ * PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org>
+ * Copyright 2004 Freescale Semiconductor, Inc
+ * PowerPC e500 modifications, Kumar Gala <kumar.gala@freescale.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+#include "head_booke.h"
+
+/* As with the other PowerPC ports, it is expected that when code
+ * execution begins here, the following registers contain valid, yet
+ * optional, information:
+ *
+ * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
+ * r4 - Starting address of the init RAM disk
+ * r5 - Ending address of the init RAM disk
+ * r6 - Start of kernel command line string (e.g. "mem=128")
+ * r7 - End of kernel command line string
+ *
+ */
+ .text
+_GLOBAL(_stext)
+_GLOBAL(_start)
+ /*
+ * Reserve a word at a fixed location to store the address
+ * of abatron_pteptrs
+ */
+ nop
+/*
+ * Save parameters we are passed
+ */
+ mr r31,r3
+ mr r30,r4
+ mr r29,r5
+ mr r28,r6
+ mr r27,r7
+ li r24,0 /* CPU number */
+
+/* We try to not make any assumptions about how the boot loader
+ * setup or used the TLBs. We invalidate all mappings from the
+ * boot loader and load a single entry in TLB1[0] to map the
+ * first 16M of kernel memory. Any boot info passed from the
+ * bootloader needs to live in this first 16M.
+ *
+ * Requirement on bootloader:
+ * - The page we're executing in needs to reside in TLB1 and
+ * have IPROT=1. If not an invalidate broadcast could
+ * evict the entry we're currently executing in.
+ *
+ * r3 = Index of TLB1 were executing in
+ * r4 = Current MSR[IS]
+ * r5 = Index of TLB1 temp mapping
+ *
+ * Later in mapin_ram we will correctly map lowmem, and resize TLB1[0]
+ * if needed
+ */
+
+/* 1. Find the index of the entry we're executing in */
+ bl invstr /* Find our address */
+invstr: mflr r6 /* Make it accessible */
+ mfmsr r7
+ rlwinm r4,r7,27,31,31 /* extract MSR[IS] */
+ mfspr r7, SPRN_PID0
+ slwi r7,r7,16
+ or r7,r7,r4
+ mtspr SPRN_MAS6,r7
+ tlbsx 0,r6 /* search MSR[IS], SPID=PID0 */
+ mfspr r7,SPRN_MAS1
+ andis. r7,r7,MAS1_VALID@h
+ bne match_TLB
+ mfspr r7,SPRN_PID1
+ slwi r7,r7,16
+ or r7,r7,r4
+ mtspr SPRN_MAS6,r7
+ tlbsx 0,r6 /* search MSR[IS], SPID=PID1 */
+ mfspr r7,SPRN_MAS1
+ andis. r7,r7,MAS1_VALID@h
+ bne match_TLB
+ mfspr r7, SPRN_PID2
+ slwi r7,r7,16
+ or r7,r7,r4
+ mtspr SPRN_MAS6,r7
+ tlbsx 0,r6 /* Fall through, we had to match */
+match_TLB:
+ mfspr r7,SPRN_MAS0
+ rlwinm r3,r7,16,20,31 /* Extract MAS0(Entry) */
+
+ mfspr r7,SPRN_MAS1 /* Insure IPROT set */
+ oris r7,r7,MAS1_IPROT@h
+ mtspr SPRN_MAS1,r7
+ tlbwe
+
+/* 2. Invalidate all entries except the entry we're executing in */
+ mfspr r9,SPRN_TLB1CFG
+ andi. r9,r9,0xfff
+ li r6,0 /* Set Entry counter to 0 */
+1: lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r6,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+ mfspr r7,SPRN_MAS1
+ rlwinm r7,r7,0,2,31 /* Clear MAS1 Valid and IPROT */
+ cmpw r3,r6
+ beq skpinv /* Dont update the current execution TLB */
+ mtspr SPRN_MAS1,r7
+ tlbwe
+ isync
+skpinv: addi r6,r6,1 /* Increment */
+ cmpw r6,r9 /* Are we done? */
+ bne 1b /* If not, repeat */
+
+ /* Invalidate TLB0 */
+ li r6,0x04
+ tlbivax 0,r6
+#ifdef CONFIG_SMP
+ tlbsync
+#endif
+ /* Invalidate TLB1 */
+ li r6,0x0c
+ tlbivax 0,r6
+#ifdef CONFIG_SMP
+ tlbsync
+#endif
+ msync
+
+/* 3. Setup a temp mapping and jump to it */
+ andi. r5, r3, 0x1 /* Find an entry not used and is non-zero */
+ addi r5, r5, 0x1
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+
+ /* Just modify the entry ID and EPN for the temp mapping */
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */
+ mtspr SPRN_MAS0,r7
+ xori r6,r4,1 /* Setup TMP mapping in the other Address space */
+ slwi r6,r6,12
+ oris r6,r6,(MAS1_VALID|MAS1_IPROT)@h
+ ori r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_4K))@l
+ mtspr SPRN_MAS1,r6
+ mfspr r6,SPRN_MAS2
+ li r7,0 /* temp EPN = 0 */
+ rlwimi r7,r6,0,20,31
+ mtspr SPRN_MAS2,r7
+ tlbwe
+
+ xori r6,r4,1
+ slwi r6,r6,5 /* setup new context with other address space */
+ bl 1f /* Find our address */
+1: mflr r9
+ rlwimi r7,r9,0,20,31
+ addi r7,r7,24
+ mtspr SPRN_SRR0,r7
+ mtspr SPRN_SRR1,r6
+ rfi
+
+/* 4. Clear out PIDs & Search info */
+ li r6,0
+ mtspr SPRN_PID0,r6
+ mtspr SPRN_PID1,r6
+ mtspr SPRN_PID2,r6
+ mtspr SPRN_MAS6,r6
+
+/* 5. Invalidate mapping we started in */
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+ li r6,0
+ mtspr SPRN_MAS1,r6
+ tlbwe
+ /* Invalidate TLB1 */
+ li r9,0x0c
+ tlbivax 0,r9
+#ifdef CONFIG_SMP
+ tlbsync
+#endif
+ msync
+
+/* 6. Setup KERNELBASE mapping in TLB1[0] */
+ lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
+ mtspr SPRN_MAS0,r6
+ lis r6,(MAS1_VALID|MAS1_IPROT)@h
+ ori r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_16M))@l
+ mtspr SPRN_MAS1,r6
+ li r7,0
+ lis r6,KERNELBASE@h
+ ori r6,r6,KERNELBASE@l
+ rlwimi r6,r7,0,20,31
+ mtspr SPRN_MAS2,r6
+ li r7,(MAS3_SX|MAS3_SW|MAS3_SR)
+ mtspr SPRN_MAS3,r7
+ tlbwe
+
+/* 7. Jump to KERNELBASE mapping */
+ li r7,0
+ bl 1f /* Find our address */
+1: mflr r9
+ rlwimi r6,r9,0,20,31
+ addi r6,r6,24
+ mtspr SPRN_SRR0,r6
+ mtspr SPRN_SRR1,r7
+ rfi /* start execution out of TLB1[0] entry */
+
+/* 8. Clear out the temp mapping */
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+ mtspr SPRN_MAS1,r8
+ tlbwe
+ /* Invalidate TLB1 */
+ li r9,0x0c
+ tlbivax 0,r9
+#ifdef CONFIG_SMP
+ tlbsync
+#endif
+ msync
+
+ /* Establish the interrupt vector offsets */
+ SET_IVOR(0, CriticalInput);
+ SET_IVOR(1, MachineCheck);
+ SET_IVOR(2, DataStorage);
+ SET_IVOR(3, InstructionStorage);
+ SET_IVOR(4, ExternalInput);
+ SET_IVOR(5, Alignment);
+ SET_IVOR(6, Program);
+ SET_IVOR(7, FloatingPointUnavailable);
+ SET_IVOR(8, SystemCall);
+ SET_IVOR(9, AuxillaryProcessorUnavailable);
+ SET_IVOR(10, Decrementer);
+ SET_IVOR(11, FixedIntervalTimer);
+ SET_IVOR(12, WatchdogTimer);
+ SET_IVOR(13, DataTLBError);
+ SET_IVOR(14, InstructionTLBError);
+ SET_IVOR(15, Debug);
+ SET_IVOR(32, SPEUnavailable);
+ SET_IVOR(33, SPEFloatingPointData);
+ SET_IVOR(34, SPEFloatingPointRound);
+ SET_IVOR(35, PerformanceMonitor);
+
+ /* Establish the interrupt vector base */
+ lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */
+ mtspr SPRN_IVPR,r4
+
+ /* Setup the defaults for TLB entries */
+ li r2,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l
+ mtspr SPRN_MAS4, r2
+
+#if 0
+ /* Enable DOZE */
+ mfspr r2,SPRN_HID0
+ oris r2,r2,HID0_DOZE@h
+ mtspr SPRN_HID0, r2
+#endif
+
+ /*
+ * This is where the main kernel code starts.
+ */
+
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to current thread */
+ addi r4,r2,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG3,r4
+
+ /* stack */
+ lis r1,init_thread_union@h
+ ori r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
+
+ bl early_init
+
+ mfspr r3,SPRN_TLB1CFG
+ andi. r3,r3,0xfff
+ lis r4,num_tlbcam_entries@ha
+ stw r3,num_tlbcam_entries@l(r4)
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+ mr r3,r31
+ mr r4,r30
+ mr r5,r29
+ mr r6,r28
+ mr r7,r27
+ bl machine_init
+ bl MMU_init
+
+ /* Setup PTE pointers for the Abatron bdiGDB */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ lis r4, KERNELBASE@h
+ ori r4, r4, KERNELBASE@l
+ stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */
+ stw r6, 0(r5)
+
+ /* Let's move on */
+ lis r4,start_kernel@h
+ ori r4,r4,start_kernel@l
+ lis r3,MSR_KERNEL@h
+ ori r3,r3,MSR_KERNEL@l
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi /* change context and jump to start_kernel */
+
+/*
+ * Interrupt vector entry code
+ *
+ * The Book E MMUs are always on so we don't need to handle
+ * interrupts in real mode as with previous PPC processors. In
+ * this case we handle interrupts in the kernel virtual address
+ * space.
+ *
+ * Interrupt vectors are dynamically placed relative to the
+ * interrupt prefix as determined by the address of interrupt_base.
+ * The interrupt vectors offsets are programmed using the labels
+ * for each interrupt vector entry.
+ *
+ * Interrupt vectors must be aligned on a 16 byte boundary.
+ * We align on a 32 byte cache line boundary for good measure.
+ */
+
+interrupt_base:
+ /* Critical Input Interrupt */
+ CRITICAL_EXCEPTION(0x0100, CriticalInput, UnknownException)
+
+ /* Machine Check Interrupt */
+ MCHECK_EXCEPTION(0x0200, MachineCheck, MachineCheckException)
+
+ /* Data Storage Interrupt */
+ START_EXCEPTION(DataStorage)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+ mtspr SPRN_SPRG4W, r12
+ mtspr SPRN_SPRG5W, r13
+ mfcr r11
+ mtspr SPRN_SPRG7W, r11
+
+ /*
+ * Check if it was a store fault, if not then bail
+ * because a user tried to access a kernel or
+ * read-protected page. Otherwise, get the
+ * offending address and handle it.
+ */
+ mfspr r10, SPRN_ESR
+ andis. r10, r10, ESR_ST@h
+ beq 2f
+
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, TASK_SIZE@h
+ ori r11, r11, TASK_SIZE@l
+ cmplw 0, r10, r11
+ bge 2f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+4:
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r11, 0(r11) /* Get L1 entry */
+ rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r12) /* Get Linux PTE */
+
+ /* Are _PAGE_USER & _PAGE_RW set & _PAGE_HWWRITE not? */
+ andi. r13, r11, _PAGE_RW|_PAGE_USER|_PAGE_HWWRITE
+ cmpwi 0, r13, _PAGE_RW|_PAGE_USER
+ bne 2f /* Bail if not */
+
+ /* Update 'changed'. */
+ ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
+ stw r11, 0(r12) /* Update Linux page table */
+
+ /* MAS2 not updated as the entry does exist in the tlb, this
+ fault taken to detect state transition (eg: COW -> DIRTY)
+ */
+ lis r12, MAS3_RPN@h
+ ori r12, r12, _PAGE_HWEXEC | MAS3_RPN@l
+ and r11, r11, r12
+ rlwimi r11, r11, 31, 27, 27 /* SX <- _PAGE_HWEXEC */
+ ori r11, r11, (MAS3_UW|MAS3_SW|MAS3_UR|MAS3_SR)@l /* set static perms */
+
+ /* update search PID in MAS6, AS = 0 */
+ mfspr r12, SPRN_PID0
+ slwi r12, r12, 16
+ mtspr SPRN_MAS6, r12
+
+ /* find the TLB index that caused the fault. It has to be here. */
+ tlbsx 0, r10
+
+ mtspr SPRN_MAS3,r11
+ tlbwe
+
+ /* Done...restore registers and get out of here. */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ rfi /* Force context change */
+
+2:
+ /*
+ * The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b data_access
+
+ /* Instruction Storage Interrupt */
+ INSTRUCTION_STORAGE_EXCEPTION
+
+ /* External Input Interrupt */
+ EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+
+ /* Alignment Interrupt */
+ ALIGNMENT_EXCEPTION
+
+ /* Program Interrupt */
+ PROGRAM_EXCEPTION
+
+ /* Floating Point Unavailable Interrupt */
+ EXCEPTION(0x0800, FloatingPointUnavailable, UnknownException, EXC_XFER_EE)
+
+ /* System Call Interrupt */
+ START_EXCEPTION(SystemCall)
+ NORMAL_EXCEPTION_PROLOG
+ EXC_XFER_EE_LITE(0x0c00, DoSyscall)
+
+ /* Auxillary Processor Unavailable Interrupt */
+ EXCEPTION(0x2900, AuxillaryProcessorUnavailable, UnknownException, EXC_XFER_EE)
+
+ /* Decrementer Interrupt */
+ DECREMENTER_EXCEPTION
+
+ /* Fixed Internal Timer Interrupt */
+ /* TODO: Add FIT support */
+ EXCEPTION(0x3100, FixedIntervalTimer, UnknownException, EXC_XFER_EE)
+
+ /* Watchdog Timer Interrupt */
+ /* TODO: Add watchdog support */
+ CRITICAL_EXCEPTION(0x3200, WatchdogTimer, UnknownException)
+
+ /* Data TLB Error Interrupt */
+ START_EXCEPTION(DataTLBError)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+ mtspr SPRN_SPRG4W, r12
+ mtspr SPRN_SPRG5W, r13
+ mfcr r11
+ mtspr SPRN_SPRG7W, r11
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, TASK_SIZE@h
+ ori r11, r11, TASK_SIZE@l
+ cmplw 5, r10, r11
+ blt 5, 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MAS1 /* Set TID to 0 */
+ rlwinm r12,r12,0,16,1
+ mtspr SPRN_MAS1,r12
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+
+4:
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r11, 0(r11) /* Get L1 entry */
+ rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r12) /* Get Linux PTE */
+ andi. r13, r11, _PAGE_PRESENT
+ beq 2f
+
+ ori r11, r11, _PAGE_ACCESSED
+ stw r11, 0(r12)
+
+ /* Jump to common tlb load */
+ b finish_tlb_load
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b data_access
+
+ /* Instruction TLB Error Interrupt */
+ /*
+ * Nearly the same as above, except we get our
+ * information from different registers and bailout
+ * to a different point.
+ */
+ START_EXCEPTION(InstructionTLBError)
+ mtspr SPRN_SPRG0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG1, r11
+ mtspr SPRN_SPRG4W, r12
+ mtspr SPRN_SPRG5W, r13
+ mfcr r11
+ mtspr SPRN_SPRG7W, r11
+ mfspr r10, SPRN_SRR0 /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, TASK_SIZE@h
+ ori r11, r11, TASK_SIZE@l
+ cmplw 5, r10, r11
+ blt 5, 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MAS1 /* Set TID to 0 */
+ rlwinm r12,r12,0,16,1
+ mtspr SPRN_MAS1,r12
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+
+4:
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r11, 0(r11) /* Get L1 entry */
+ rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */
+ beq 2f /* Bail if no table */
+
+ rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r12) /* Get Linux PTE */
+ andi. r13, r11, _PAGE_PRESENT
+ beq 2f
+
+ ori r11, r11, _PAGE_ACCESSED
+ stw r11, 0(r12)
+
+ /* Jump to common TLB load point */
+ b finish_tlb_load
+
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ b InstructionStorage
+
+#ifdef CONFIG_SPE
+ /* SPE Unavailable */
+ START_EXCEPTION(SPEUnavailable)
+ NORMAL_EXCEPTION_PROLOG
+ bne load_up_spe
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_EE_LITE(0x2010, KernelSPE)
+#else
+ EXCEPTION(0x2020, SPEUnavailable, UnknownException, EXC_XFER_EE)
+#endif /* CONFIG_SPE */
+
+ /* SPE Floating Point Data */
+#ifdef CONFIG_SPE
+ EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE);
+#else
+ EXCEPTION(0x2040, SPEFloatingPointData, UnknownException, EXC_XFER_EE)
+#endif /* CONFIG_SPE */
+
+ /* SPE Floating Point Round */
+ EXCEPTION(0x2050, SPEFloatingPointRound, UnknownException, EXC_XFER_EE)
+
+ /* Performance Monitor */
+ EXCEPTION(0x2060, PerformanceMonitor, PerformanceMonitorException, EXC_XFER_STD)
+
+
+ /* Debug Interrupt */
+ DEBUG_EXCEPTION
+
+/*
+ * Local functions
+ */
+ /*
+ * Data TLB exceptions will bail out to this point
+ * if they can't resolve the lightweight TLB fault.
+ */
+data_access:
+ NORMAL_EXCEPTION_PROLOG
+ mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */
+ stw r5,_ESR(r11)
+ mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */
+ andis. r10,r5,(ESR_ILK|ESR_DLK)@h
+ bne 1f
+ EXC_XFER_EE_LITE(0x0300, handle_page_fault)
+1:
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ EXC_XFER_EE_LITE(0x0300, CacheLockingException)
+
+/*
+
+ * Both the instruction and data TLB miss get to this
+ * point to load the TLB.
+ * r10 - EA of fault
+ * r11 - TLB (info from Linux PTE)
+ * r12, r13 - available to use
+ * CR5 - results of addr < TASK_SIZE
+ * MAS0, MAS1 - loaded with proper value when we get here
+ * MAS2, MAS3 - will need additional info from Linux PTE
+ * Upon exit, we reload everything and RFI.
+ */
+finish_tlb_load:
+ /*
+ * We set execute, because we don't have the granularity to
+ * properly set this at the page level (Linux problem).
+ * Many of these bits are software only. Bits we don't set
+ * here we (properly should) assume have the appropriate value.
+ */
+
+ mfspr r12, SPRN_MAS2
+ rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */
+ mtspr SPRN_MAS2, r12
+
+ bge 5, 1f
+
+ /* addr > TASK_SIZE */
+ li r10, (MAS3_UX | MAS3_UW | MAS3_UR)
+ andi. r13, r11, (_PAGE_USER | _PAGE_HWWRITE | _PAGE_HWEXEC)
+ andi. r12, r11, _PAGE_USER /* Test for _PAGE_USER */
+ iseleq r12, 0, r10
+ and r10, r12, r13
+ srwi r12, r10, 1
+ or r12, r12, r10 /* Copy user perms into supervisor */
+ b 2f
+
+ /* addr <= TASK_SIZE */
+1: rlwinm r12, r11, 31, 29, 29 /* Extract _PAGE_HWWRITE into SW */
+ ori r12, r12, (MAS3_SX | MAS3_SR)
+
+2: rlwimi r11, r12, 0, 20, 31 /* Extract RPN from PTE and merge with perms */
+ mtspr SPRN_MAS3, r11
+ tlbwe
+
+ /* Done...restore registers and get out of here. */
+ mfspr r11, SPRN_SPRG7R
+ mtcr r11
+ mfspr r13, SPRN_SPRG5R
+ mfspr r12, SPRN_SPRG4R
+ mfspr r11, SPRN_SPRG1
+ mfspr r10, SPRN_SPRG0
+ rfi /* Force context change */
+
+#ifdef CONFIG_SPE
+/* Note that the SPE support is closely modeled after the AltiVec
+ * support. Changes to one are likely to be applicable to the
+ * other! */
+load_up_spe:
+/*
+ * Disable SPE for the task which had SPE previously,
+ * and save its SPE registers in its thread_struct.
+ * Enables SPE for use in the kernel on return.
+ * On SMP we know the SPE units are free, since we give it up every
+ * switch. -- Kumar
+ */
+ mfmsr r5
+ oris r5,r5,MSR_SPE@h
+ mtmsr r5 /* enable use of SPE now */
+ isync
+/*
+ * For SMP, we don't do lazy SPE switching because it just gets too
+ * horrendously complex, especially when a task switches from one CPU
+ * to another. Instead we call giveup_spe in switch_to.
+ */
+#ifndef CONFIG_SMP
+ lis r3,last_task_used_spe@ha
+ lwz r4,last_task_used_spe@l(r3)
+ cmpi 0,r4,0
+ beq 1f
+ addi r4,r4,THREAD /* want THREAD of last_task_used_spe */
+ SAVE_32EVR(0,r10,r4)
+ evxor evr10, evr10, evr10 /* clear out evr10 */
+ evmwumiaa evr10, evr10, evr10 /* evr10 <- ACC = 0 * 0 + ACC */
+ li r5,THREAD_ACC
+ evstddx evr10, r4, r5 /* save off accumulator */
+ lwz r5,PT_REGS(r4)
+ lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ lis r10,MSR_SPE@h
+ andc r4,r4,r10 /* disable SPE for previous task */
+ stw r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+ /* enable use of SPE after return */
+ oris r9,r9,MSR_SPE@h
+ mfspr r5,SPRN_SPRG3 /* current task's THREAD (phys) */
+ li r4,1
+ li r10,THREAD_ACC
+ stw r4,THREAD_USED_SPE(r5)
+ evlddx evr4,r10,r5
+ evmra evr4,evr4
+ REST_32EVR(0,r10,r5)
+#ifndef CONFIG_SMP
+ subi r4,r5,THREAD
+ stw r4,last_task_used_spe@l(r3)
+#endif /* CONFIG_SMP */
+ /* restore registers and return */
+2: REST_4GPRS(3, r11)
+ lwz r10,_CCR(r11)
+ REST_GPR(1, r11)
+ mtcr r10
+ lwz r10,_LINK(r11)
+ mtlr r10
+ REST_GPR(10, r11)
+ mtspr SPRN_SRR1,r9
+ mtspr SPRN_SRR0,r12
+ REST_GPR(9, r11)
+ REST_GPR(12, r11)
+ lwz r11,GPR11(r11)
+ SYNC
+ rfi
+
+/*
+ * SPE unavailable trap from kernel - print a message, but let
+ * the task use SPE in the kernel until it returns to user mode.
+ */
+KernelSPE:
+ lwz r3,_MSR(r1)
+ oris r3,r3,MSR_SPE@h
+ stw r3,_MSR(r1) /* enable use of SPE after return */
+ lis r3,87f@h
+ ori r3,r3,87f@l
+ mr r4,r2 /* current */
+ lwz r5,_NIP(r1)
+ bl printk
+ b ret_from_except
+87: .string "SPE used in kernel (task=%p, pc=%x) \n"
+ .align 4,0
+
+#endif /* CONFIG_SPE */
+
+/*
+ * Global functions
+ */
+
+/*
+ * extern void loadcam_entry(unsigned int index)
+ *
+ * Load TLBCAM[index] entry in to the L2 CAM MMU
+ */
+_GLOBAL(loadcam_entry)
+ lis r4,TLBCAM@ha
+ addi r4,r4,TLBCAM@l
+ mulli r5,r3,20
+ add r3,r5,r4
+ lwz r4,0(r3)
+ mtspr SPRN_MAS0,r4
+ lwz r4,4(r3)
+ mtspr SPRN_MAS1,r4
+ lwz r4,8(r3)
+ mtspr SPRN_MAS2,r4
+ lwz r4,12(r3)
+ mtspr SPRN_MAS3,r4
+ tlbwe
+ isync
+ blr
+
+/*
+ * extern void giveup_altivec(struct task_struct *prev)
+ *
+ * The e500 core does not have an AltiVec unit.
+ */
+_GLOBAL(giveup_altivec)
+ blr
+
+#ifdef CONFIG_SPE
+/*
+ * extern void giveup_spe(struct task_struct *prev)
+ *
+ */
+_GLOBAL(giveup_spe)
+ mfmsr r5
+ oris r5,r5,MSR_SPE@h
+ SYNC
+ mtmsr r5 /* enable use of SPE now */
+ isync
+ cmpi 0,r3,0
+ beqlr- /* if no previous owner, done */
+ addi r3,r3,THREAD /* want THREAD of task */
+ lwz r5,PT_REGS(r3)
+ cmpi 0,r5,0
+ SAVE_32EVR(0, r4, r3)
+ evxor evr6, evr6, evr6 /* clear out evr6 */
+ evmwumiaa evr6, evr6, evr6 /* evr6 <- ACC = 0 * 0 + ACC */
+ li r4,THREAD_ACC
+ evstddx evr6, r4, r3 /* save off accumulator */
+ mfspr r6,SPRN_SPEFSCR
+ stw r6,THREAD_SPEFSCR(r3) /* save spefscr register value */
+ beq 1f
+ lwz r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+ lis r3,MSR_SPE@h
+ andc r4,r4,r3 /* disable SPE for previous task */
+ stw r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#ifndef CONFIG_SMP
+ li r5,0
+ lis r4,last_task_used_spe@ha
+ stw r5,last_task_used_spe@l(r4)
+#endif /* CONFIG_SMP */
+ blr
+#endif /* CONFIG_SPE */
+
+/*
+ * extern void giveup_fpu(struct task_struct *prev)
+ *
+ * The e500 core does not have an FPU.
+ */
+_GLOBAL(giveup_fpu)
+ blr
+
+/*
+ * extern void abort(void)
+ *
+ * At present, this routine just applies a system reset.
+ */
+_GLOBAL(abort)
+ li r13,0
+ mtspr SPRN_DBCR0,r13 /* disable all debug events */
+ mfmsr r13
+ ori r13,r13,MSR_DE@l /* Enable Debug Events */
+ mtmsr r13
+ mfspr r13,SPRN_DBCR0
+ lis r13,(DBCR0_IDM|DBCR0_RST_CHIP)@h
+ mtspr SPRN_DBCR0,r13
+
+_GLOBAL(set_context)
+
+#ifdef CONFIG_BDI_SWITCH
+ /* Context switch the PTE pointer for the Abatron BDI2000.
+ * The PGDIR is the second parameter.
+ */
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r4, 0x4(r5)
+#endif
+ mtspr SPRN_PID,r3
+ isync /* Force context change */
+ blr
+
+/*
+ * We put a few things here that have to be page-aligned. This stuff
+ * goes at the beginning of the data segment, which is page-aligned.
+ */
+ .data
+_GLOBAL(sdata)
+_GLOBAL(empty_zero_page)
+ .space 4096
+_GLOBAL(swapper_pg_dir)
+ .space 4096
+
+/* Reserved 4k for the critical exception stack & 4k for the machine
+ * check stack per CPU for kernel mode exceptions */
+ .section .bss
+ .align 12
+exception_stack_bottom:
+ .space BOOKE_EXCEPTION_STACK_SIZE * NR_CPUS
+_GLOBAL(exception_stack_top)
+
+/*
+ * This space gets a copy of optional info passed to us by the bootstrap
+ * which is used to pass parameters into the kernel like root=/dev/sda1, etc.
+ */
+_GLOBAL(cmd_line)
+ .space 512
+
+/*
+ * Room for two PTE pointers, usually the kernel and current user pointers
+ * to their respective root page table.
+ */
+abatron_pteptrs:
+ .space 8
+
diff --git a/arch/ppc/kernel/idle.c b/arch/ppc/kernel/idle.c
new file mode 100644
index 000000000000..53547b6de45b
--- /dev/null
+++ b/arch/ppc/kernel/idle.c
@@ -0,0 +1,100 @@
+/*
+ * Idle daemon for PowerPC. Idle daemon will handle any action
+ * that needs to be taken when the system becomes idle.
+ *
+ * Written by Cort Dougan (cort@cs.nmt.edu). Subsequently hacked
+ * on by Tom Rini, Armin Kuster, Paul Mackerras and others.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/mmu.h>
+#include <asm/cache.h>
+#include <asm/cputable.h>
+#include <asm/machdep.h>
+
+void default_idle(void)
+{
+ void (*powersave)(void);
+
+ powersave = ppc_md.power_save;
+
+ if (!need_resched()) {
+ if (powersave != NULL)
+ powersave();
+#ifdef CONFIG_SMP
+ else {
+ set_thread_flag(TIF_POLLING_NRFLAG);
+ while (!need_resched())
+ barrier();
+ clear_thread_flag(TIF_POLLING_NRFLAG);
+ }
+#endif
+ }
+ if (need_resched())
+ schedule();
+}
+
+/*
+ * The body of the idle task.
+ */
+void cpu_idle(void)
+{
+ for (;;)
+ if (ppc_md.idle != NULL)
+ ppc_md.idle();
+ else
+ default_idle();
+}
+
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_6xx)
+/*
+ * Register the sysctl to set/clear powersave_nap.
+ */
+extern unsigned long powersave_nap;
+
+static ctl_table powersave_nap_ctl_table[]={
+ {
+ .ctl_name = KERN_PPC_POWERSAVE_NAP,
+ .procname = "powersave-nap",
+ .data = &powersave_nap,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ { 0, },
+};
+static ctl_table powersave_nap_sysctl_root[] = {
+ { 1, "kernel", NULL, 0, 0755, powersave_nap_ctl_table, },
+ { 0,},
+};
+
+static int __init
+register_powersave_nap_sysctl(void)
+{
+ register_sysctl_table(powersave_nap_sysctl_root, 0);
+
+ return 0;
+}
+
+__initcall(register_powersave_nap_sysctl);
+#endif
diff --git a/arch/ppc/kernel/idle_6xx.S b/arch/ppc/kernel/idle_6xx.S
new file mode 100644
index 000000000000..25d009c75f7b
--- /dev/null
+++ b/arch/ppc/kernel/idle_6xx.S
@@ -0,0 +1,233 @@
+/*
+ * This file contains the power_save function for 6xx & 7xxx CPUs
+ * rewritten in assembler
+ *
+ * Warning ! This code assumes that if your machine has a 750fx
+ * it will have PLL 1 set to low speed mode (used during NAP/DOZE).
+ * if this is not the case some additional changes will have to
+ * be done to check a runtime var (a bit like powersave-nap)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+
+#undef DEBUG
+
+ .text
+
+/*
+ * Init idle, called at early CPU setup time from head.S for each CPU
+ * Make sure no rest of NAP mode remains in HID0, save default
+ * values for some CPU specific registers. Called with r24
+ * containing CPU number and r3 reloc offset
+ */
+_GLOBAL(init_idle_6xx)
+BEGIN_FTR_SECTION
+ mfspr r4,SPRN_HID0
+ rlwinm r4,r4,0,10,8 /* Clear NAP */
+ mtspr SPRN_HID0, r4
+ b 1f
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+ blr
+1:
+ slwi r5,r24,2
+ add r5,r5,r3
+BEGIN_FTR_SECTION
+ mfspr r4,SPRN_MSSCR0
+ addis r6,r5, nap_save_msscr0@ha
+ stw r4,nap_save_msscr0@l(r6)
+END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
+BEGIN_FTR_SECTION
+ mfspr r4,SPRN_HID1
+ addis r6,r5,nap_save_hid1@ha
+ stw r4,nap_save_hid1@l(r6)
+END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
+ blr
+
+/*
+ * Here is the power_save_6xx function. This could eventually be
+ * split into several functions & changing the function pointer
+ * depending on the various features.
+ */
+_GLOBAL(ppc6xx_idle)
+ /* Check if we can nap or doze, put HID0 mask in r3
+ */
+ lis r3, 0
+BEGIN_FTR_SECTION
+ lis r3,HID0_DOZE@h
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+BEGIN_FTR_SECTION
+ /* We must dynamically check for the NAP feature as it
+ * can be cleared by CPU init after the fixups are done
+ */
+ lis r4,cur_cpu_spec@ha
+ lwz r4,cur_cpu_spec@l(r4)
+ lwz r4,CPU_SPEC_FEATURES(r4)
+ andi. r0,r4,CPU_FTR_CAN_NAP
+ beq 1f
+ /* Now check if user or arch enabled NAP mode */
+ lis r4,powersave_nap@ha
+ lwz r4,powersave_nap@l(r4)
+ cmpwi 0,r4,0
+ beq 1f
+ lis r3,HID0_NAP@h
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+ cmpwi 0,r3,0
+ beqlr
+
+ /* Clear MSR:EE */
+ mfmsr r7
+ rlwinm r0,r7,0,17,15
+ mtmsr r0
+
+ /* Check current_thread_info()->flags */
+ rlwinm r4,r1,0,0,18
+ lwz r4,TI_FLAGS(r4)
+ andi. r0,r4,_TIF_NEED_RESCHED
+ beq 1f
+ mtmsr r7 /* out of line this ? */
+ blr
+1:
+ /* Some pre-nap cleanups needed on some CPUs */
+ andis. r0,r3,HID0_NAP@h
+ beq 2f
+BEGIN_FTR_SECTION
+ /* Disable L2 prefetch on some 745x and try to ensure
+ * L2 prefetch engines are idle. As explained by errata
+ * text, we can't be sure they are, we just hope very hard
+ * that well be enough (sic !). At least I noticed Apple
+ * doesn't even bother doing the dcbf's here...
+ */
+ mfspr r4,SPRN_MSSCR0
+ rlwinm r4,r4,0,0,29
+ sync
+ mtspr SPRN_MSSCR0,r4
+ sync
+ isync
+ lis r4,KERNELBASE@h
+ dcbf 0,r4
+ dcbf 0,r4
+ dcbf 0,r4
+ dcbf 0,r4
+END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
+#ifdef DEBUG
+ lis r6,nap_enter_count@ha
+ lwz r4,nap_enter_count@l(r6)
+ addi r4,r4,1
+ stw r4,nap_enter_count@l(r6)
+#endif
+2:
+BEGIN_FTR_SECTION
+ /* Go to low speed mode on some 750FX */
+ lis r4,powersave_lowspeed@ha
+ lwz r4,powersave_lowspeed@l(r4)
+ cmpwi 0,r4,0
+ beq 1f
+ mfspr r4,SPRN_HID1
+ oris r4,r4,0x0001
+ mtspr SPRN_HID1,r4
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
+
+ /* Go to NAP or DOZE now */
+ mfspr r4,SPRN_HID0
+ lis r5,(HID0_NAP|HID0_SLEEP)@h
+BEGIN_FTR_SECTION
+ oris r5,r5,HID0_DOZE@h
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+ andc r4,r4,r5
+ or r4,r4,r3
+BEGIN_FTR_SECTION
+ oris r4,r4,HID0_DPM@h /* that should be done once for all */
+END_FTR_SECTION_IFCLR(CPU_FTR_NO_DPM)
+ mtspr SPRN_HID0,r4
+BEGIN_FTR_SECTION
+ DSSALL
+ sync
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ ori r7,r7,MSR_EE /* Could be ommited (already set) */
+ oris r7,r7,MSR_POW@h
+ sync
+ isync
+ mtmsr r7
+ isync
+ sync
+ blr
+
+/*
+ * Return from NAP/DOZE mode, restore some CPU specific registers,
+ * we are called with DR/IR still off and r2 containing physical
+ * address of current.
+ */
+_GLOBAL(power_save_6xx_restore)
+ mfspr r11,SPRN_HID0
+ rlwinm. r11,r11,0,10,8 /* Clear NAP & copy NAP bit !state to cr1 EQ */
+ cror 4*cr1+eq,4*cr0+eq,4*cr0+eq
+BEGIN_FTR_SECTION
+ rlwinm r11,r11,0,9,7 /* Clear DOZE */
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+ mtspr SPRN_HID0, r11
+
+#ifdef DEBUG
+ beq cr1,1f
+ lis r11,(nap_return_count-KERNELBASE)@ha
+ lwz r9,nap_return_count@l(r11)
+ addi r9,r9,1
+ stw r9,nap_return_count@l(r11)
+1:
+#endif
+
+ rlwinm r9,r1,0,0,18
+ tophys(r9,r9)
+ lwz r11,TI_CPU(r9)
+ slwi r11,r11,2
+ /* Todo make sure all these are in the same page
+ * and load r22 (@ha part + CPU offset) only once
+ */
+BEGIN_FTR_SECTION
+ beq cr1,1f
+ addis r9,r11,(nap_save_msscr0-KERNELBASE)@ha
+ lwz r9,nap_save_msscr0@l(r9)
+ mtspr SPRN_MSSCR0, r9
+ sync
+ isync
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
+BEGIN_FTR_SECTION
+ addis r9,r11,(nap_save_hid1-KERNELBASE)@ha
+ lwz r9,nap_save_hid1@l(r9)
+ mtspr SPRN_HID1, r9
+END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
+ b transfer_to_handler_cont
+
+ .data
+
+_GLOBAL(nap_save_msscr0)
+ .space 4*NR_CPUS
+
+_GLOBAL(nap_save_hid1)
+ .space 4*NR_CPUS
+
+_GLOBAL(powersave_nap)
+ .long 0
+_GLOBAL(powersave_lowspeed)
+ .long 0
+
+#ifdef DEBUG
+_GLOBAL(nap_enter_count)
+ .space 4
+_GLOBAL(nap_return_count)
+ .space 4
+#endif
diff --git a/arch/ppc/kernel/idle_power4.S b/arch/ppc/kernel/idle_power4.S
new file mode 100644
index 000000000000..73a58ff03900
--- /dev/null
+++ b/arch/ppc/kernel/idle_power4.S
@@ -0,0 +1,91 @@
+/*
+ * This file contains the power_save function for 6xx & 7xxx CPUs
+ * rewritten in assembler
+ *
+ * Warning ! This code assumes that if your machine has a 750fx
+ * it will have PLL 1 set to low speed mode (used during NAP/DOZE).
+ * if this is not the case some additional changes will have to
+ * be done to check a runtime var (a bit like powersave-nap)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+
+#undef DEBUG
+
+ .text
+
+/*
+ * Init idle, called at early CPU setup time from head.S for each CPU
+ * So nothing for now. Called with r24 containing CPU number and r3
+ * reloc offset
+ */
+ .globl init_idle_power4
+init_idle_power4:
+ blr
+
+/*
+ * Here is the power_save_6xx function. This could eventually be
+ * split into several functions & changing the function pointer
+ * depending on the various features.
+ */
+ .globl power4_idle
+power4_idle:
+BEGIN_FTR_SECTION
+ blr
+END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
+ /* We must dynamically check for the NAP feature as it
+ * can be cleared by CPU init after the fixups are done
+ */
+ lis r4,cur_cpu_spec@ha
+ lwz r4,cur_cpu_spec@l(r4)
+ lwz r4,CPU_SPEC_FEATURES(r4)
+ andi. r0,r4,CPU_FTR_CAN_NAP
+ beqlr
+ /* Now check if user or arch enabled NAP mode */
+ lis r4,powersave_nap@ha
+ lwz r4,powersave_nap@l(r4)
+ cmpwi 0,r4,0
+ beqlr
+
+ /* Clear MSR:EE */
+ mfmsr r7
+ rlwinm r0,r7,0,17,15
+ mtmsr r0
+
+ /* Check current_thread_info()->flags */
+ rlwinm r4,r1,0,0,18
+ lwz r4,TI_FLAGS(r4)
+ andi. r0,r4,_TIF_NEED_RESCHED
+ beq 1f
+ mtmsr r7 /* out of line this ? */
+ blr
+1:
+ /* Go to NAP now */
+BEGIN_FTR_SECTION
+ DSSALL
+ sync
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ ori r7,r7,MSR_EE /* Could be ommited (already set) */
+ oris r7,r7,MSR_POW@h
+ sync
+ isync
+ mtmsr r7
+ isync
+ sync
+ blr
+
+ .globl powersave_nap
+powersave_nap:
+ .long 0
diff --git a/arch/ppc/kernel/irq.c b/arch/ppc/kernel/irq.c
new file mode 100644
index 000000000000..8843f3af230f
--- /dev/null
+++ b/arch/ppc/kernel/irq.c
@@ -0,0 +1,164 @@
+/*
+ * arch/ppc/kernel/irq.c
+ *
+ * Derived from arch/i386/kernel/irq.c
+ * Copyright (C) 1992 Linus Torvalds
+ * Adapted from arch/i386 by Gary Thomas
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Updated and modified by Cort Dougan <cort@fsmlabs.com>
+ * Copyright (C) 1996-2001 Cort Dougan
+ * Adapted for Power Macintosh by Paul Mackerras
+ * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
+ * Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk).
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ *
+ * The MPC8xx has an interrupt mask in the SIU. If a bit is set, the
+ * interrupt is _enabled_. As expected, IRQ0 is bit 0 in the 32-bit
+ * mask register (of which only 16 are defined), hence the weird shifting
+ * and complement of the cached_irq_mask. I want to be able to stuff
+ * this right into the SIU SMASK register.
+ * Many of the prep/chrp functions are conditional compiled on CONFIG_8xx
+ * to reduce code space and undefined function references.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/threads.h>
+#include <linux/kernel_stat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/proc_fs.h>
+#include <linux/random.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/profile.h>
+#include <linux/bitops.h>
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/pgtable.h>
+#include <asm/irq.h>
+#include <asm/cache.h>
+#include <asm/prom.h>
+#include <asm/ptrace.h>
+
+#define NR_MASK_WORDS ((NR_IRQS + 31) / 32)
+
+extern atomic_t ipi_recv;
+extern atomic_t ipi_sent;
+
+#define MAXCOUNT 10000000
+
+int ppc_spurious_interrupts = 0;
+struct irqaction *ppc_irq_action[NR_IRQS];
+unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
+unsigned long ppc_lost_interrupts[NR_MASK_WORDS];
+atomic_t ppc_n_lost_interrupts;
+
+#ifdef CONFIG_TAU_INT
+extern int tau_initialized;
+extern int tau_interrupts(int);
+#endif
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+ int i = *(loff_t *) v, j;
+ struct irqaction * action;
+ unsigned long flags;
+
+ if (i == 0) {
+ seq_puts(p, " ");
+ for (j=0; j<NR_CPUS; j++)
+ if (cpu_online(j))
+ seq_printf(p, "CPU%d ", j);
+ seq_putc(p, '\n');
+ }
+
+ if (i < NR_IRQS) {
+ spin_lock_irqsave(&irq_desc[i].lock, flags);
+ action = irq_desc[i].action;
+ if ( !action || !action->handler )
+ goto skip;
+ seq_printf(p, "%3d: ", i);
+#ifdef CONFIG_SMP
+ for (j = 0; j < NR_CPUS; j++)
+ if (cpu_online(j))
+ seq_printf(p, "%10u ",
+ kstat_cpu(j).irqs[i]);
+#else
+ seq_printf(p, "%10u ", kstat_irqs(i));
+#endif /* CONFIG_SMP */
+ if (irq_desc[i].handler)
+ seq_printf(p, " %s ", irq_desc[i].handler->typename);
+ else
+ seq_puts(p, " None ");
+ seq_printf(p, "%s", (irq_desc[i].status & IRQ_LEVEL) ? "Level " : "Edge ");
+ seq_printf(p, " %s", action->name);
+ for (action = action->next; action; action = action->next)
+ seq_printf(p, ", %s", action->name);
+ seq_putc(p, '\n');
+skip:
+ spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+ } else if (i == NR_IRQS) {
+#ifdef CONFIG_TAU_INT
+ if (tau_initialized){
+ seq_puts(p, "TAU: ");
+ for (j = 0; j < NR_CPUS; j++)
+ if (cpu_online(j))
+ seq_printf(p, "%10u ", tau_interrupts(j));
+ seq_puts(p, " PowerPC Thermal Assist (cpu temp)\n");
+ }
+#endif
+#ifdef CONFIG_SMP
+ /* should this be per processor send/receive? */
+ seq_printf(p, "IPI (recv/sent): %10u/%u\n",
+ atomic_read(&ipi_recv), atomic_read(&ipi_sent));
+#endif
+ seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts);
+ }
+ return 0;
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+ int irq, first = 1;
+ irq_enter();
+
+ /*
+ * Every platform is required to implement ppc_md.get_irq.
+ * This function will either return an irq number or -1 to
+ * indicate there are no more pending. But the first time
+ * through the loop this means there wasn't and IRQ pending.
+ * The value -2 is for buggy hardware and means that this IRQ
+ * has already been handled. -- Tom
+ */
+ while ((irq = ppc_md.get_irq(regs)) >= 0) {
+ __do_IRQ(irq, regs);
+ first = 0;
+ }
+ if (irq != -2 && first)
+ /* That's not SMP safe ... but who cares ? */
+ ppc_spurious_interrupts++;
+ irq_exit();
+}
+
+void __init init_IRQ(void)
+{
+ ppc_md.init_IRQ();
+}
diff --git a/arch/ppc/kernel/l2cr.S b/arch/ppc/kernel/l2cr.S
new file mode 100644
index 000000000000..c39441048266
--- /dev/null
+++ b/arch/ppc/kernel/l2cr.S
@@ -0,0 +1,442 @@
+/*
+ L2CR functions
+ Copyright © 1997-1998 by PowerLogix R & D, Inc.
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+*/
+/*
+ Thur, Dec. 12, 1998.
+ - First public release, contributed by PowerLogix.
+ ***********
+ Sat, Aug. 7, 1999.
+ - Terry: Made sure code disabled interrupts before running. (Previously
+ it was assumed interrupts were already disabled).
+ - Terry: Updated for tentative G4 support. 4MB of memory is now flushed
+ instead of 2MB. (Prob. only 3 is necessary).
+ - Terry: Updated for workaround to HID0[DPM] processor bug
+ during global invalidates.
+ ***********
+ Thu, July 13, 2000.
+ - Terry: Added isync to correct for an errata.
+
+ 22 August 2001.
+ - DanM: Finally added the 7450 patch I've had for the past
+ several months. The L2CR is similar, but I'm going
+ to assume the user of this functions knows what they
+ are doing.
+
+ Author: Terry Greeniaus (tgree@phys.ualberta.ca)
+ Please e-mail updates to this file to me, thanks!
+*/
+#include <linux/config.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/cache.h>
+#include <asm/page.h>
+
+/* Usage:
+
+ When setting the L2CR register, you must do a few special
+ things. If you are enabling the cache, you must perform a
+ global invalidate. If you are disabling the cache, you must
+ flush the cache contents first. This routine takes care of
+ doing these things. When first enabling the cache, make sure
+ you pass in the L2CR you want, as well as passing in the
+ global invalidate bit set. A global invalidate will only be
+ performed if the L2I bit is set in applyThis. When enabling
+ the cache, you should also set the L2E bit in applyThis. If
+ you want to modify the L2CR contents after the cache has been
+ enabled, the recommended procedure is to first call
+ __setL2CR(0) to disable the cache and then call it again with
+ the new values for L2CR. Examples:
+
+ _setL2CR(0) - disables the cache
+ _setL2CR(0xB3A04000) - enables my G3 upgrade card:
+ - L2E set to turn on the cache
+ - L2SIZ set to 1MB
+ - L2CLK set to 1:1
+ - L2RAM set to pipelined synchronous late-write
+ - L2I set to perform a global invalidation
+ - L2OH set to 0.5 nS
+ - L2DF set because this upgrade card
+ requires it
+
+ A similar call should work for your card. You need to know
+ the correct setting for your card and then place them in the
+ fields I have outlined above. Other fields support optional
+ features, such as L2DO which caches only data, or L2TS which
+ causes cache pushes from the L1 cache to go to the L2 cache
+ instead of to main memory.
+
+IMPORTANT:
+ Starting with the 7450, the bits in this register have moved
+ or behave differently. The Enable, Parity Enable, Size,
+ and L2 Invalidate are the only bits that have not moved.
+ The size is read-only for these processors with internal L2
+ cache, and the invalidate is a control as well as status.
+ -- Dan
+
+*/
+/*
+ * Summary: this procedure ignores the L2I bit in the value passed in,
+ * flushes the cache if it was already enabled, always invalidates the
+ * cache, then enables the cache if the L2E bit is set in the value
+ * passed in.
+ * -- paulus.
+ */
+_GLOBAL(_set_L2CR)
+ /* Make sure this is a 750 or 7400 chip */
+BEGIN_FTR_SECTION
+ li r3,-1
+ blr
+END_FTR_SECTION_IFCLR(CPU_FTR_L2CR)
+
+ mflr r9
+
+ /* Stop DST streams */
+BEGIN_FTR_SECTION
+ DSSALL
+ sync
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+
+ /* Turn off interrupts and data relocation. */
+ mfmsr r7 /* Save MSR in r7 */
+ rlwinm r4,r7,0,17,15
+ rlwinm r4,r4,0,28,26 /* Turn off DR bit */
+ sync
+ mtmsr r4
+ isync
+
+ /* Before we perform the global invalidation, we must disable dynamic
+ * power management via HID0[DPM] to work around a processor bug where
+ * DPM can possibly interfere with the state machine in the processor
+ * that invalidates the L2 cache tags.
+ */
+ mfspr r8,SPRN_HID0 /* Save HID0 in r8 */
+ rlwinm r4,r8,0,12,10 /* Turn off HID0[DPM] */
+ sync
+ mtspr SPRN_HID0,r4 /* Disable DPM */
+ sync
+
+ /* Get the current enable bit of the L2CR into r4 */
+ mfspr r4,SPRN_L2CR
+
+ /* Tweak some bits */
+ rlwinm r5,r3,0,0,0 /* r5 contains the new enable bit */
+ rlwinm r3,r3,0,11,9 /* Turn off the invalidate bit */
+ rlwinm r3,r3,0,1,31 /* Turn off the enable bit */
+
+ /* Check to see if we need to flush */
+ rlwinm. r4,r4,0,0,0
+ beq 2f
+
+ /* Flush the cache. First, read the first 4MB of memory (physical) to
+ * put new data in the cache. (Actually we only need
+ * the size of the L2 cache plus the size of the L1 cache, but 4MB will
+ * cover everything just to be safe).
+ */
+
+ /**** Might be a good idea to set L2DO here - to prevent instructions
+ from getting into the cache. But since we invalidate
+ the next time we enable the cache it doesn't really matter.
+ Don't do this unless you accomodate all processor variations.
+ The bit moved on the 7450.....
+ ****/
+
+ /* TODO: use HW flush assist when available */
+
+ lis r4,0x0002
+ mtctr r4
+ li r4,0
+1:
+ lwzx r0,r0,r4
+ addi r4,r4,32 /* Go to start of next cache line */
+ bdnz 1b
+ isync
+
+ /* Now, flush the first 4MB of memory */
+ lis r4,0x0002
+ mtctr r4
+ li r4,0
+ sync
+1:
+ dcbf 0,r4
+ addi r4,r4,32 /* Go to start of next cache line */
+ bdnz 1b
+
+2:
+ /* Set up the L2CR configuration bits (and switch L2 off) */
+ /* CPU errata: Make sure the mtspr below is already in the
+ * L1 icache
+ */
+ b 20f
+ .balign L1_CACHE_LINE_SIZE
+22:
+ sync
+ mtspr SPRN_L2CR,r3
+ sync
+ b 23f
+20:
+ b 21f
+21: sync
+ isync
+ b 22b
+
+23:
+ /* Perform a global invalidation */
+ oris r3,r3,0x0020
+ sync
+ mtspr SPRN_L2CR,r3
+ sync
+ isync /* For errata */
+
+BEGIN_FTR_SECTION
+ /* On the 7450, we wait for the L2I bit to clear......
+ */
+10: mfspr r3,SPRN_L2CR
+ andis. r4,r3,0x0020
+ bne 10b
+ b 11f
+END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450)
+
+ /* Wait for the invalidation to complete */
+3: mfspr r3,SPRN_L2CR
+ rlwinm. r4,r3,0,31,31
+ bne 3b
+
+11: rlwinm r3,r3,0,11,9 /* Turn off the L2I bit */
+ sync
+ mtspr SPRN_L2CR,r3
+ sync
+
+ /* See if we need to enable the cache */
+ cmplwi r5,0
+ beq 4f
+
+ /* Enable the cache */
+ oris r3,r3,0x8000
+ mtspr SPRN_L2CR,r3
+ sync
+
+4:
+
+ /* Restore HID0[DPM] to whatever it was before */
+ sync
+ mtspr 1008,r8
+ sync
+
+ /* Restore MSR (restores EE and DR bits to original state) */
+ SYNC
+ mtmsr r7
+ isync
+
+ mtlr r9
+ blr
+
+_GLOBAL(_get_L2CR)
+ /* Return the L2CR contents */
+ li r3,0
+BEGIN_FTR_SECTION
+ mfspr r3,SPRN_L2CR
+END_FTR_SECTION_IFSET(CPU_FTR_L2CR)
+ blr
+
+
+/*
+ * Here is a similar routine for dealing with the L3 cache
+ * on the 745x family of chips
+ */
+
+_GLOBAL(_set_L3CR)
+ /* Make sure this is a 745x chip */
+BEGIN_FTR_SECTION
+ li r3,-1
+ blr
+END_FTR_SECTION_IFCLR(CPU_FTR_L3CR)
+
+ /* Turn off interrupts and data relocation. */
+ mfmsr r7 /* Save MSR in r7 */
+ rlwinm r4,r7,0,17,15
+ rlwinm r4,r4,0,28,26 /* Turn off DR bit */
+ sync
+ mtmsr r4
+ isync
+
+ /* Stop DST streams */
+ DSSALL
+ sync
+
+ /* Get the current enable bit of the L3CR into r4 */
+ mfspr r4,SPRN_L3CR
+
+ /* Tweak some bits */
+ rlwinm r5,r3,0,0,0 /* r5 contains the new enable bit */
+ rlwinm r3,r3,0,22,20 /* Turn off the invalidate bit */
+ rlwinm r3,r3,0,2,31 /* Turn off the enable & PE bits */
+ rlwinm r3,r3,0,5,3 /* Turn off the clken bit */
+ /* Check to see if we need to flush */
+ rlwinm. r4,r4,0,0,0
+ beq 2f
+
+ /* Flush the cache.
+ */
+
+ /* TODO: use HW flush assist */
+
+ lis r4,0x0008
+ mtctr r4
+ li r4,0
+1:
+ lwzx r0,r0,r4
+ dcbf 0,r4
+ addi r4,r4,32 /* Go to start of next cache line */
+ bdnz 1b
+
+2:
+ /* Set up the L3CR configuration bits (and switch L3 off) */
+ sync
+ mtspr SPRN_L3CR,r3
+ sync
+
+ oris r3,r3,L3CR_L3RES@h /* Set reserved bit 5 */
+ mtspr SPRN_L3CR,r3
+ sync
+ oris r3,r3,L3CR_L3CLKEN@h /* Set clken */
+ mtspr SPRN_L3CR,r3
+ sync
+
+ /* Wait for stabilize */
+ li r0,256
+ mtctr r0
+1: bdnz 1b
+
+ /* Perform a global invalidation */
+ ori r3,r3,0x0400
+ sync
+ mtspr SPRN_L3CR,r3
+ sync
+ isync
+
+ /* We wait for the L3I bit to clear...... */
+10: mfspr r3,SPRN_L3CR
+ andi. r4,r3,0x0400
+ bne 10b
+
+ /* Clear CLKEN */
+ rlwinm r3,r3,0,5,3 /* Turn off the clken bit */
+ mtspr SPRN_L3CR,r3
+ sync
+
+ /* Wait for stabilize */
+ li r0,256
+ mtctr r0
+1: bdnz 1b
+
+ /* See if we need to enable the cache */
+ cmplwi r5,0
+ beq 4f
+
+ /* Enable the cache */
+ oris r3,r3,(L3CR_L3E | L3CR_L3CLKEN)@h
+ mtspr SPRN_L3CR,r3
+ sync
+
+ /* Wait for stabilize */
+ li r0,256
+ mtctr r0
+1: bdnz 1b
+
+ /* Restore MSR (restores EE and DR bits to original state) */
+4: SYNC
+ mtmsr r7
+ isync
+ blr
+
+_GLOBAL(_get_L3CR)
+ /* Return the L3CR contents */
+ li r3,0
+BEGIN_FTR_SECTION
+ mfspr r3,SPRN_L3CR
+END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
+ blr
+
+/* --- End of PowerLogix code ---
+ */
+
+
+/* flush_disable_L1() - Flush and disable L1 cache
+ *
+ * clobbers r0, r3, ctr, cr0
+ * Must be called with interrupts disabled and MMU enabled.
+ */
+_GLOBAL(__flush_disable_L1)
+ /* Stop pending alitvec streams and memory accesses */
+BEGIN_FTR_SECTION
+ DSSALL
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ sync
+
+ /* Load counter to 0x4000 cache lines (512k) and
+ * load cache with datas
+ */
+ li r3,0x4000 /* 512kB / 32B */
+ mtctr r3
+ lis r3,KERNELBASE@h
+1:
+ lwz r0,0(r3)
+ addi r3,r3,0x0020 /* Go to start of next cache line */
+ bdnz 1b
+ isync
+ sync
+
+ /* Now flush those cache lines */
+ li r3,0x4000 /* 512kB / 32B */
+ mtctr r3
+ lis r3,KERNELBASE@h
+1:
+ dcbf 0,r3
+ addi r3,r3,0x0020 /* Go to start of next cache line */
+ bdnz 1b
+ sync
+
+ /* We can now disable the L1 cache (HID0:DCE, HID0:ICE) */
+ mfspr r3,SPRN_HID0
+ rlwinm r3,r3,0,18,15
+ mtspr SPRN_HID0,r3
+ sync
+ isync
+ blr
+
+/* inval_enable_L1 - Invalidate and enable L1 cache
+ *
+ * Assumes L1 is already disabled and MSR:EE is off
+ *
+ * clobbers r3
+ */
+_GLOBAL(__inval_enable_L1)
+ /* Enable and then Flash inval the instruction & data cache */
+ mfspr r3,SPRN_HID0
+ ori r3,r3, HID0_ICE|HID0_ICFI|HID0_DCE|HID0_DCI
+ sync
+ isync
+ mtspr SPRN_HID0,r3
+ xori r3,r3, HID0_ICFI|HID0_DCI
+ mtspr SPRN_HID0,r3
+ sync
+
+ blr
+
+
diff --git a/arch/ppc/kernel/misc.S b/arch/ppc/kernel/misc.S
new file mode 100644
index 000000000000..73f7c23b0dd4
--- /dev/null
+++ b/arch/ppc/kernel/misc.S
@@ -0,0 +1,1453 @@
+/*
+ * This file contains miscellaneous low-level functions.
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/sys.h>
+#include <asm/unistd.h>
+#include <asm/errno.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/cputable.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/thread_info.h>
+#include <asm/offsets.h>
+
+ .text
+
+ .align 5
+_GLOBAL(__delay)
+ cmpwi 0,r3,0
+ mtctr r3
+ beqlr
+1: bdnz 1b
+ blr
+
+/*
+ * Returns (address we're running at) - (address we were linked at)
+ * for use before the text and data are mapped to KERNELBASE.
+ */
+_GLOBAL(reloc_offset)
+ mflr r0
+ bl 1f
+1: mflr r3
+ lis r4,1b@ha
+ addi r4,r4,1b@l
+ subf r3,r4,r3
+ mtlr r0
+ blr
+
+/*
+ * add_reloc_offset(x) returns x + reloc_offset().
+ */
+_GLOBAL(add_reloc_offset)
+ mflr r0
+ bl 1f
+1: mflr r5
+ lis r4,1b@ha
+ addi r4,r4,1b@l
+ subf r5,r4,r5
+ add r3,r3,r5
+ mtlr r0
+ blr
+
+/*
+ * sub_reloc_offset(x) returns x - reloc_offset().
+ */
+_GLOBAL(sub_reloc_offset)
+ mflr r0
+ bl 1f
+1: mflr r5
+ lis r4,1b@ha
+ addi r4,r4,1b@l
+ subf r5,r4,r5
+ subf r3,r5,r3
+ mtlr r0
+ blr
+
+/*
+ * reloc_got2 runs through the .got2 section adding an offset
+ * to each entry.
+ */
+_GLOBAL(reloc_got2)
+ mflr r11
+ lis r7,__got2_start@ha
+ addi r7,r7,__got2_start@l
+ lis r8,__got2_end@ha
+ addi r8,r8,__got2_end@l
+ subf r8,r7,r8
+ srwi. r8,r8,2
+ beqlr
+ mtctr r8
+ bl 1f
+1: mflr r0
+ lis r4,1b@ha
+ addi r4,r4,1b@l
+ subf r0,r4,r0
+ add r7,r0,r7
+2: lwz r0,0(r7)
+ add r0,r0,r3
+ stw r0,0(r7)
+ addi r7,r7,4
+ bdnz 2b
+ mtlr r11
+ blr
+
+/*
+ * identify_cpu,
+ * called with r3 = data offset and r4 = CPU number
+ * doesn't change r3
+ */
+_GLOBAL(identify_cpu)
+ addis r8,r3,cpu_specs@ha
+ addi r8,r8,cpu_specs@l
+ mfpvr r7
+1:
+ lwz r5,CPU_SPEC_PVR_MASK(r8)
+ and r5,r5,r7
+ lwz r6,CPU_SPEC_PVR_VALUE(r8)
+ cmplw 0,r6,r5
+ beq 1f
+ addi r8,r8,CPU_SPEC_ENTRY_SIZE
+ b 1b
+1:
+ addis r6,r3,cur_cpu_spec@ha
+ addi r6,r6,cur_cpu_spec@l
+ slwi r4,r4,2
+ sub r8,r8,r3
+ stwx r8,r4,r6
+ blr
+
+/*
+ * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
+ * and writes nop's over sections of code that don't apply for this cpu.
+ * r3 = data offset (not changed)
+ */
+_GLOBAL(do_cpu_ftr_fixups)
+ /* Get CPU 0 features */
+ addis r6,r3,cur_cpu_spec@ha
+ addi r6,r6,cur_cpu_spec@l
+ lwz r4,0(r6)
+ add r4,r4,r3
+ lwz r4,CPU_SPEC_FEATURES(r4)
+
+ /* Get the fixup table */
+ addis r6,r3,__start___ftr_fixup@ha
+ addi r6,r6,__start___ftr_fixup@l
+ addis r7,r3,__stop___ftr_fixup@ha
+ addi r7,r7,__stop___ftr_fixup@l
+
+ /* Do the fixup */
+1: cmplw 0,r6,r7
+ bgelr
+ addi r6,r6,16
+ lwz r8,-16(r6) /* mask */
+ and r8,r8,r4
+ lwz r9,-12(r6) /* value */
+ cmplw 0,r8,r9
+ beq 1b
+ lwz r8,-8(r6) /* section begin */
+ lwz r9,-4(r6) /* section end */
+ subf. r9,r8,r9
+ beq 1b
+ /* write nops over the section of code */
+ /* todo: if large section, add a branch at the start of it */
+ srwi r9,r9,2
+ mtctr r9
+ add r8,r8,r3
+ lis r0,0x60000000@h /* nop */
+3: stw r0,0(r8)
+ andi. r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
+ beq 2f
+ dcbst 0,r8 /* suboptimal, but simpler */
+ sync
+ icbi 0,r8
+2: addi r8,r8,4
+ bdnz 3b
+ sync /* additional sync needed on g4 */
+ isync
+ b 1b
+
+/*
+ * call_setup_cpu - call the setup_cpu function for this cpu
+ * r3 = data offset, r24 = cpu number
+ *
+ * Setup function is called with:
+ * r3 = data offset
+ * r4 = CPU number
+ * r5 = ptr to CPU spec (relocated)
+ */
+_GLOBAL(call_setup_cpu)
+ addis r5,r3,cur_cpu_spec@ha
+ addi r5,r5,cur_cpu_spec@l
+ slwi r4,r24,2
+ lwzx r5,r4,r5
+ add r5,r5,r3
+ lwz r6,CPU_SPEC_SETUP(r5)
+ add r6,r6,r3
+ mtctr r6
+ mr r4,r24
+ bctr
+
+#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_6xx)
+
+/* This gets called by via-pmu.c to switch the PLL selection
+ * on 750fx CPU. This function should really be moved to some
+ * other place (as most of the cpufreq code in via-pmu
+ */
+_GLOBAL(low_choose_750fx_pll)
+ /* Clear MSR:EE */
+ mfmsr r7
+ rlwinm r0,r7,0,17,15
+ mtmsr r0
+
+ /* If switching to PLL1, disable HID0:BTIC */
+ cmplwi cr0,r3,0
+ beq 1f
+ mfspr r5,SPRN_HID0
+ rlwinm r5,r5,0,27,25
+ sync
+ mtspr SPRN_HID0,r5
+ isync
+ sync
+
+1:
+ /* Calc new HID1 value */
+ mfspr r4,SPRN_HID1 /* Build a HID1:PS bit from parameter */
+ rlwinm r5,r3,16,15,15 /* Clear out HID1:PS from value read */
+ rlwinm r4,r4,0,16,14 /* Could have I used rlwimi here ? */
+ or r4,r4,r5
+ mtspr SPRN_HID1,r4
+
+ /* Store new HID1 image */
+ rlwinm r6,r1,0,0,18
+ lwz r6,TI_CPU(r6)
+ slwi r6,r6,2
+ addis r6,r6,nap_save_hid1@ha
+ stw r4,nap_save_hid1@l(r6)
+
+ /* If switching to PLL0, enable HID0:BTIC */
+ cmplwi cr0,r3,0
+ bne 1f
+ mfspr r5,SPRN_HID0
+ ori r5,r5,HID0_BTIC
+ sync
+ mtspr SPRN_HID0,r5
+ isync
+ sync
+
+1:
+ /* Return */
+ mtmsr r7
+ blr
+
+_GLOBAL(low_choose_7447a_dfs)
+ /* Clear MSR:EE */
+ mfmsr r7
+ rlwinm r0,r7,0,17,15
+ mtmsr r0
+
+ /* Calc new HID1 value */
+ mfspr r4,SPRN_HID1
+ insrwi r4,r3,1,9 /* insert parameter into bit 9 */
+ sync
+ mtspr SPRN_HID1,r4
+ sync
+ isync
+
+ /* Return */
+ mtmsr r7
+ blr
+
+#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_6xx */
+
+/* void local_save_flags_ptr(unsigned long *flags) */
+_GLOBAL(local_save_flags_ptr)
+ mfmsr r4
+ stw r4,0(r3)
+ blr
+ /*
+ * Need these nops here for taking over save/restore to
+ * handle lost intrs
+ * -- Cort
+ */
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+_GLOBAL(local_save_flags_ptr_end)
+
+/* void local_irq_restore(unsigned long flags) */
+_GLOBAL(local_irq_restore)
+/*
+ * Just set/clear the MSR_EE bit through restore/flags but do not
+ * change anything else. This is needed by the RT system and makes
+ * sense anyway.
+ * -- Cort
+ */
+ mfmsr r4
+ /* Copy all except the MSR_EE bit from r4 (current MSR value)
+ to r3. This is the sort of thing the rlwimi instruction is
+ designed for. -- paulus. */
+ rlwimi r3,r4,0,17,15
+ /* Check if things are setup the way we want _already_. */
+ cmpw 0,r3,r4
+ beqlr
+1: SYNC
+ mtmsr r3
+ SYNC
+ blr
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+_GLOBAL(local_irq_restore_end)
+
+_GLOBAL(local_irq_disable)
+ mfmsr r0 /* Get current interrupt state */
+ rlwinm r3,r0,16+1,32-1,31 /* Extract old value of 'EE' */
+ rlwinm r0,r0,0,17,15 /* clear MSR_EE in r0 */
+ SYNC /* Some chip revs have problems here... */
+ mtmsr r0 /* Update machine state */
+ blr /* Done */
+ /*
+ * Need these nops here for taking over save/restore to
+ * handle lost intrs
+ * -- Cort
+ */
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+_GLOBAL(local_irq_disable_end)
+
+_GLOBAL(local_irq_enable)
+ mfmsr r3 /* Get current state */
+ ori r3,r3,MSR_EE /* Turn on 'EE' bit */
+ SYNC /* Some chip revs have problems here... */
+ mtmsr r3 /* Update machine state */
+ blr
+ /*
+ * Need these nops here for taking over save/restore to
+ * handle lost intrs
+ * -- Cort
+ */
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+_GLOBAL(local_irq_enable_end)
+
+/*
+ * complement mask on the msr then "or" some values on.
+ * _nmask_and_or_msr(nmask, value_to_or)
+ */
+_GLOBAL(_nmask_and_or_msr)
+ mfmsr r0 /* Get current msr */
+ andc r0,r0,r3 /* And off the bits set in r3 (first parm) */
+ or r0,r0,r4 /* Or on the bits in r4 (second parm) */
+ SYNC /* Some chip revs have problems here... */
+ mtmsr r0 /* Update machine state */
+ isync
+ blr /* Done */
+
+
+/*
+ * Flush MMU TLB
+ */
+_GLOBAL(_tlbia)
+#if defined(CONFIG_40x)
+ sync /* Flush to memory before changing mapping */
+ tlbia
+ isync /* Flush shadow TLB */
+#elif defined(CONFIG_44x)
+ li r3,0
+ sync
+
+ /* Load high watermark */
+ lis r4,tlb_44x_hwater@ha
+ lwz r5,tlb_44x_hwater@l(r4)
+
+1: tlbwe r3,r3,PPC44x_TLB_PAGEID
+ addi r3,r3,1
+ cmpw 0,r3,r5
+ ble 1b
+
+ isync
+#elif defined(CONFIG_FSL_BOOKE)
+ /* Invalidate all entries in TLB0 */
+ li r3, 0x04
+ tlbivax 0,3
+ /* Invalidate all entries in TLB1 */
+ li r3, 0x0c
+ tlbivax 0,3
+ /* Invalidate all entries in TLB2 */
+ li r3, 0x14
+ tlbivax 0,3
+ /* Invalidate all entries in TLB3 */
+ li r3, 0x1c
+ tlbivax 0,3
+ msync
+#ifdef CONFIG_SMP
+ tlbsync
+#endif /* CONFIG_SMP */
+#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
+#if defined(CONFIG_SMP)
+ rlwinm r8,r1,0,0,18
+ lwz r8,TI_CPU(r8)
+ oris r8,r8,10
+ mfmsr r10
+ SYNC
+ rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */
+ rlwinm r0,r0,0,28,26 /* clear DR */
+ mtmsr r0
+ SYNC_601
+ isync
+ lis r9,mmu_hash_lock@h
+ ori r9,r9,mmu_hash_lock@l
+ tophys(r9,r9)
+10: lwarx r7,0,r9
+ cmpwi 0,r7,0
+ bne- 10b
+ stwcx. r8,0,r9
+ bne- 10b
+ sync
+ tlbia
+ sync
+ TLBSYNC
+ li r0,0
+ stw r0,0(r9) /* clear mmu_hash_lock */
+ mtmsr r10
+ SYNC_601
+ isync
+#else /* CONFIG_SMP */
+ sync
+ tlbia
+ sync
+#endif /* CONFIG_SMP */
+#endif /* ! defined(CONFIG_40x) */
+ blr
+
+/*
+ * Flush MMU TLB for a particular address
+ */
+_GLOBAL(_tlbie)
+#if defined(CONFIG_40x)
+ tlbsx. r3, 0, r3
+ bne 10f
+ sync
+ /* There are only 64 TLB entries, so r3 < 64, which means bit 25 is clear.
+ * Since 25 is the V bit in the TLB_TAG, loading this value will invalidate
+ * the TLB entry. */
+ tlbwe r3, r3, TLB_TAG
+ isync
+10:
+#elif defined(CONFIG_44x)
+ mfspr r4,SPRN_MMUCR
+ mfspr r5,SPRN_PID /* Get PID */
+ rlwimi r4,r5,0,24,31 /* Set TID */
+ mtspr SPRN_MMUCR,r4
+
+ tlbsx. r3, 0, r3
+ bne 10f
+ sync
+ /* There are only 64 TLB entries, so r3 < 64,
+ * which means bit 22, is clear. Since 22 is
+ * the V bit in the TLB_PAGEID, loading this
+ * value will invalidate the TLB entry.
+ */
+ tlbwe r3, r3, PPC44x_TLB_PAGEID
+ isync
+10:
+#elif defined(CONFIG_FSL_BOOKE)
+ rlwinm r4, r3, 0, 0, 19
+ ori r5, r4, 0x08 /* TLBSEL = 1 */
+ ori r6, r4, 0x10 /* TLBSEL = 2 */
+ ori r7, r4, 0x18 /* TLBSEL = 3 */
+ tlbivax 0, r4
+ tlbivax 0, r5
+ tlbivax 0, r6
+ tlbivax 0, r7
+ msync
+#if defined(CONFIG_SMP)
+ tlbsync
+#endif /* CONFIG_SMP */
+#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
+#if defined(CONFIG_SMP)
+ rlwinm r8,r1,0,0,18
+ lwz r8,TI_CPU(r8)
+ oris r8,r8,11
+ mfmsr r10
+ SYNC
+ rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */
+ rlwinm r0,r0,0,28,26 /* clear DR */
+ mtmsr r0
+ SYNC_601
+ isync
+ lis r9,mmu_hash_lock@h
+ ori r9,r9,mmu_hash_lock@l
+ tophys(r9,r9)
+10: lwarx r7,0,r9
+ cmpwi 0,r7,0
+ bne- 10b
+ stwcx. r8,0,r9
+ bne- 10b
+ eieio
+ tlbie r3
+ sync
+ TLBSYNC
+ li r0,0
+ stw r0,0(r9) /* clear mmu_hash_lock */
+ mtmsr r10
+ SYNC_601
+ isync
+#else /* CONFIG_SMP */
+ tlbie r3
+ sync
+#endif /* CONFIG_SMP */
+#endif /* ! CONFIG_40x */
+ blr
+
+/*
+ * Flush instruction cache.
+ * This is a no-op on the 601.
+ */
+_GLOBAL(flush_instruction_cache)
+#if defined(CONFIG_8xx)
+ isync
+ lis r5, IDC_INVALL@h
+ mtspr SPRN_IC_CST, r5
+#elif defined(CONFIG_4xx)
+#ifdef CONFIG_403GCX
+ li r3, 512
+ mtctr r3
+ lis r4, KERNELBASE@h
+1: iccci 0, r4
+ addi r4, r4, 16
+ bdnz 1b
+#else
+ lis r3, KERNELBASE@h
+ iccci 0,r3
+#endif
+#elif CONFIG_FSL_BOOKE
+ mfspr r3,SPRN_L1CSR1
+ ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR
+ mtspr SPRN_L1CSR1,r3
+#else
+ mfspr r3,SPRN_PVR
+ rlwinm r3,r3,16,16,31
+ cmpwi 0,r3,1
+ beqlr /* for 601, do nothing */
+ /* 603/604 processor - use invalidate-all bit in HID0 */
+ mfspr r3,SPRN_HID0
+ ori r3,r3,HID0_ICFI
+ mtspr SPRN_HID0,r3
+#endif /* CONFIG_8xx/4xx */
+ isync
+ blr
+
+/*
+ * Write any modified data cache blocks out to memory
+ * and invalidate the corresponding instruction cache blocks.
+ * This is a no-op on the 601.
+ *
+ * flush_icache_range(unsigned long start, unsigned long stop)
+ */
+_GLOBAL(flush_icache_range)
+BEGIN_FTR_SECTION
+ blr /* for 601, do nothing */
+END_FTR_SECTION_IFSET(PPC_FEATURE_UNIFIED_CACHE)
+ li r5,L1_CACHE_LINE_SIZE-1
+ andc r3,r3,r5
+ subf r4,r3,r4
+ add r4,r4,r5
+ srwi. r4,r4,LG_L1_CACHE_LINE_SIZE
+ beqlr
+ mtctr r4
+ mr r6,r3
+1: dcbst 0,r3
+ addi r3,r3,L1_CACHE_LINE_SIZE
+ bdnz 1b
+ sync /* wait for dcbst's to get to ram */
+ mtctr r4
+2: icbi 0,r6
+ addi r6,r6,L1_CACHE_LINE_SIZE
+ bdnz 2b
+ sync /* additional sync needed on g4 */
+ isync
+ blr
+/*
+ * Write any modified data cache blocks out to memory.
+ * Does not invalidate the corresponding cache lines (especially for
+ * any corresponding instruction cache).
+ *
+ * clean_dcache_range(unsigned long start, unsigned long stop)
+ */
+_GLOBAL(clean_dcache_range)
+ li r5,L1_CACHE_LINE_SIZE-1
+ andc r3,r3,r5
+ subf r4,r3,r4
+ add r4,r4,r5
+ srwi. r4,r4,LG_L1_CACHE_LINE_SIZE
+ beqlr
+ mtctr r4
+
+1: dcbst 0,r3
+ addi r3,r3,L1_CACHE_LINE_SIZE
+ bdnz 1b
+ sync /* wait for dcbst's to get to ram */
+ blr
+
+/*
+ * Write any modified data cache blocks out to memory and invalidate them.
+ * Does not invalidate the corresponding instruction cache blocks.
+ *
+ * flush_dcache_range(unsigned long start, unsigned long stop)
+ */
+_GLOBAL(flush_dcache_range)
+ li r5,L1_CACHE_LINE_SIZE-1
+ andc r3,r3,r5
+ subf r4,r3,r4
+ add r4,r4,r5
+ srwi. r4,r4,LG_L1_CACHE_LINE_SIZE
+ beqlr
+ mtctr r4
+
+1: dcbf 0,r3
+ addi r3,r3,L1_CACHE_LINE_SIZE
+ bdnz 1b
+ sync /* wait for dcbst's to get to ram */
+ blr
+
+/*
+ * Like above, but invalidate the D-cache. This is used by the 8xx
+ * to invalidate the cache so the PPC core doesn't get stale data
+ * from the CPM (no cache snooping here :-).
+ *
+ * invalidate_dcache_range(unsigned long start, unsigned long stop)
+ */
+_GLOBAL(invalidate_dcache_range)
+ li r5,L1_CACHE_LINE_SIZE-1
+ andc r3,r3,r5
+ subf r4,r3,r4
+ add r4,r4,r5
+ srwi. r4,r4,LG_L1_CACHE_LINE_SIZE
+ beqlr
+ mtctr r4
+
+1: dcbi 0,r3
+ addi r3,r3,L1_CACHE_LINE_SIZE
+ bdnz 1b
+ sync /* wait for dcbi's to get to ram */
+ blr
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+/*
+ * 40x cores have 8K or 16K dcache and 32 byte line size.
+ * 44x has a 32K dcache and 32 byte line size.
+ * 8xx has 1, 2, 4, 8K variants.
+ * For now, cover the worst case of the 44x.
+ * Must be called with external interrupts disabled.
+ */
+#define CACHE_NWAYS 64
+#define CACHE_NLINES 16
+
+_GLOBAL(flush_dcache_all)
+ li r4, (2 * CACHE_NWAYS * CACHE_NLINES)
+ mtctr r4
+ lis r5, KERNELBASE@h
+1: lwz r3, 0(r5) /* Load one word from every line */
+ addi r5, r5, L1_CACHE_LINE_SIZE
+ bdnz 1b
+ blr
+#endif /* CONFIG_NOT_COHERENT_CACHE */
+
+/*
+ * Flush a particular page from the data cache to RAM.
+ * Note: this is necessary because the instruction cache does *not*
+ * snoop from the data cache.
+ * This is a no-op on the 601 which has a unified cache.
+ *
+ * void __flush_dcache_icache(void *page)
+ */
+_GLOBAL(__flush_dcache_icache)
+BEGIN_FTR_SECTION
+ blr /* for 601, do nothing */
+END_FTR_SECTION_IFSET(PPC_FEATURE_UNIFIED_CACHE)
+ rlwinm r3,r3,0,0,19 /* Get page base address */
+ li r4,4096/L1_CACHE_LINE_SIZE /* Number of lines in a page */
+ mtctr r4
+ mr r6,r3
+0: dcbst 0,r3 /* Write line to ram */
+ addi r3,r3,L1_CACHE_LINE_SIZE
+ bdnz 0b
+ sync
+ mtctr r4
+1: icbi 0,r6
+ addi r6,r6,L1_CACHE_LINE_SIZE
+ bdnz 1b
+ sync
+ isync
+ blr
+
+/*
+ * Flush a particular page from the data cache to RAM, identified
+ * by its physical address. We turn off the MMU so we can just use
+ * the physical address (this may be a highmem page without a kernel
+ * mapping).
+ *
+ * void __flush_dcache_icache_phys(unsigned long physaddr)
+ */
+_GLOBAL(__flush_dcache_icache_phys)
+BEGIN_FTR_SECTION
+ blr /* for 601, do nothing */
+END_FTR_SECTION_IFSET(PPC_FEATURE_UNIFIED_CACHE)
+ mfmsr r10
+ rlwinm r0,r10,0,28,26 /* clear DR */
+ mtmsr r0
+ isync
+ rlwinm r3,r3,0,0,19 /* Get page base address */
+ li r4,4096/L1_CACHE_LINE_SIZE /* Number of lines in a page */
+ mtctr r4
+ mr r6,r3
+0: dcbst 0,r3 /* Write line to ram */
+ addi r3,r3,L1_CACHE_LINE_SIZE
+ bdnz 0b
+ sync
+ mtctr r4
+1: icbi 0,r6
+ addi r6,r6,L1_CACHE_LINE_SIZE
+ bdnz 1b
+ sync
+ mtmsr r10 /* restore DR */
+ isync
+ blr
+
+/*
+ * Clear pages using the dcbz instruction, which doesn't cause any
+ * memory traffic (except to write out any cache lines which get
+ * displaced). This only works on cacheable memory.
+ *
+ * void clear_pages(void *page, int order) ;
+ */
+_GLOBAL(clear_pages)
+ li r0,4096/L1_CACHE_LINE_SIZE
+ slw r0,r0,r4
+ mtctr r0
+#ifdef CONFIG_8xx
+ li r4, 0
+1: stw r4, 0(r3)
+ stw r4, 4(r3)
+ stw r4, 8(r3)
+ stw r4, 12(r3)
+#else
+1: dcbz 0,r3
+#endif
+ addi r3,r3,L1_CACHE_LINE_SIZE
+ bdnz 1b
+ blr
+
+/*
+ * Copy a whole page. We use the dcbz instruction on the destination
+ * to reduce memory traffic (it eliminates the unnecessary reads of
+ * the destination into cache). This requires that the destination
+ * is cacheable.
+ */
+#define COPY_16_BYTES \
+ lwz r6,4(r4); \
+ lwz r7,8(r4); \
+ lwz r8,12(r4); \
+ lwzu r9,16(r4); \
+ stw r6,4(r3); \
+ stw r7,8(r3); \
+ stw r8,12(r3); \
+ stwu r9,16(r3)
+
+_GLOBAL(copy_page)
+ addi r3,r3,-4
+ addi r4,r4,-4
+
+#ifdef CONFIG_8xx
+ /* don't use prefetch on 8xx */
+ li r0,4096/L1_CACHE_LINE_SIZE
+ mtctr r0
+1: COPY_16_BYTES
+ bdnz 1b
+ blr
+
+#else /* not 8xx, we can prefetch */
+ li r5,4
+
+#if MAX_COPY_PREFETCH > 1
+ li r0,MAX_COPY_PREFETCH
+ li r11,4
+ mtctr r0
+11: dcbt r11,r4
+ addi r11,r11,L1_CACHE_LINE_SIZE
+ bdnz 11b
+#else /* MAX_COPY_PREFETCH == 1 */
+ dcbt r5,r4
+ li r11,L1_CACHE_LINE_SIZE+4
+#endif /* MAX_COPY_PREFETCH */
+ li r0,4096/L1_CACHE_LINE_SIZE - MAX_COPY_PREFETCH
+ crclr 4*cr0+eq
+2:
+ mtctr r0
+1:
+ dcbt r11,r4
+ dcbz r5,r3
+ COPY_16_BYTES
+#if L1_CACHE_LINE_SIZE >= 32
+ COPY_16_BYTES
+#if L1_CACHE_LINE_SIZE >= 64
+ COPY_16_BYTES
+ COPY_16_BYTES
+#if L1_CACHE_LINE_SIZE >= 128
+ COPY_16_BYTES
+ COPY_16_BYTES
+ COPY_16_BYTES
+ COPY_16_BYTES
+#endif
+#endif
+#endif
+ bdnz 1b
+ beqlr
+ crnot 4*cr0+eq,4*cr0+eq
+ li r0,MAX_COPY_PREFETCH
+ li r11,4
+ b 2b
+#endif /* CONFIG_8xx */
+
+/*
+ * void atomic_clear_mask(atomic_t mask, atomic_t *addr)
+ * void atomic_set_mask(atomic_t mask, atomic_t *addr);
+ */
+_GLOBAL(atomic_clear_mask)
+10: lwarx r5,0,r4
+ andc r5,r5,r3
+ PPC405_ERR77(0,r4)
+ stwcx. r5,0,r4
+ bne- 10b
+ blr
+_GLOBAL(atomic_set_mask)
+10: lwarx r5,0,r4
+ or r5,r5,r3
+ PPC405_ERR77(0,r4)
+ stwcx. r5,0,r4
+ bne- 10b
+ blr
+
+/*
+ * I/O string operations
+ *
+ * insb(port, buf, len)
+ * outsb(port, buf, len)
+ * insw(port, buf, len)
+ * outsw(port, buf, len)
+ * insl(port, buf, len)
+ * outsl(port, buf, len)
+ * insw_ns(port, buf, len)
+ * outsw_ns(port, buf, len)
+ * insl_ns(port, buf, len)
+ * outsl_ns(port, buf, len)
+ *
+ * The *_ns versions don't do byte-swapping.
+ */
+_GLOBAL(_insb)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,1
+ blelr-
+00: lbz r5,0(r3)
+ eieio
+ stbu r5,1(r4)
+ bdnz 00b
+ blr
+
+_GLOBAL(_outsb)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,1
+ blelr-
+00: lbzu r5,1(r4)
+ stb r5,0(r3)
+ eieio
+ bdnz 00b
+ blr
+
+_GLOBAL(_insw)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,2
+ blelr-
+00: lhbrx r5,0,r3
+ eieio
+ sthu r5,2(r4)
+ bdnz 00b
+ blr
+
+_GLOBAL(_outsw)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,2
+ blelr-
+00: lhzu r5,2(r4)
+ eieio
+ sthbrx r5,0,r3
+ bdnz 00b
+ blr
+
+_GLOBAL(_insl)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,4
+ blelr-
+00: lwbrx r5,0,r3
+ eieio
+ stwu r5,4(r4)
+ bdnz 00b
+ blr
+
+_GLOBAL(_outsl)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,4
+ blelr-
+00: lwzu r5,4(r4)
+ stwbrx r5,0,r3
+ eieio
+ bdnz 00b
+ blr
+
+_GLOBAL(__ide_mm_insw)
+_GLOBAL(_insw_ns)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,2
+ blelr-
+00: lhz r5,0(r3)
+ eieio
+ sthu r5,2(r4)
+ bdnz 00b
+ blr
+
+_GLOBAL(__ide_mm_outsw)
+_GLOBAL(_outsw_ns)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,2
+ blelr-
+00: lhzu r5,2(r4)
+ sth r5,0(r3)
+ eieio
+ bdnz 00b
+ blr
+
+_GLOBAL(__ide_mm_insl)
+_GLOBAL(_insl_ns)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,4
+ blelr-
+00: lwz r5,0(r3)
+ eieio
+ stwu r5,4(r4)
+ bdnz 00b
+ blr
+
+_GLOBAL(__ide_mm_outsl)
+_GLOBAL(_outsl_ns)
+ cmpwi 0,r5,0
+ mtctr r5
+ subi r4,r4,4
+ blelr-
+00: lwzu r5,4(r4)
+ stw r5,0(r3)
+ eieio
+ bdnz 00b
+ blr
+
+/*
+ * Extended precision shifts.
+ *
+ * Updated to be valid for shift counts from 0 to 63 inclusive.
+ * -- Gabriel
+ *
+ * R3/R4 has 64 bit value
+ * R5 has shift count
+ * result in R3/R4
+ *
+ * ashrdi3: arithmetic right shift (sign propagation)
+ * lshrdi3: logical right shift
+ * ashldi3: left shift
+ */
+_GLOBAL(__ashrdi3)
+ subfic r6,r5,32
+ srw r4,r4,r5 # LSW = count > 31 ? 0 : LSW >> count
+ addi r7,r5,32 # could be xori, or addi with -32
+ slw r6,r3,r6 # t1 = count > 31 ? 0 : MSW << (32-count)
+ rlwinm r8,r7,0,32 # t3 = (count < 32) ? 32 : 0
+ sraw r7,r3,r7 # t2 = MSW >> (count-32)
+ or r4,r4,r6 # LSW |= t1
+ slw r7,r7,r8 # t2 = (count < 32) ? 0 : t2
+ sraw r3,r3,r5 # MSW = MSW >> count
+ or r4,r4,r7 # LSW |= t2
+ blr
+
+_GLOBAL(__ashldi3)
+ subfic r6,r5,32
+ slw r3,r3,r5 # MSW = count > 31 ? 0 : MSW << count
+ addi r7,r5,32 # could be xori, or addi with -32
+ srw r6,r4,r6 # t1 = count > 31 ? 0 : LSW >> (32-count)
+ slw r7,r4,r7 # t2 = count < 32 ? 0 : LSW << (count-32)
+ or r3,r3,r6 # MSW |= t1
+ slw r4,r4,r5 # LSW = LSW << count
+ or r3,r3,r7 # MSW |= t2
+ blr
+
+_GLOBAL(__lshrdi3)
+ subfic r6,r5,32
+ srw r4,r4,r5 # LSW = count > 31 ? 0 : LSW >> count
+ addi r7,r5,32 # could be xori, or addi with -32
+ slw r6,r3,r6 # t1 = count > 31 ? 0 : MSW << (32-count)
+ srw r7,r3,r7 # t2 = count < 32 ? 0 : MSW >> (count-32)
+ or r4,r4,r6 # LSW |= t1
+ srw r3,r3,r5 # MSW = MSW >> count
+ or r4,r4,r7 # LSW |= t2
+ blr
+
+_GLOBAL(abs)
+ srawi r4,r3,31
+ xor r3,r3,r4
+ sub r3,r3,r4
+ blr
+
+_GLOBAL(_get_SP)
+ mr r3,r1 /* Close enough */
+ blr
+
+/*
+ * These are used in the alignment trap handler when emulating
+ * single-precision loads and stores.
+ * We restore and save the fpscr so the task gets the same result
+ * and exceptions as if the cpu had performed the load or store.
+ */
+
+#if defined(CONFIG_4xx) || defined(CONFIG_E500)
+_GLOBAL(cvt_fd)
+ lfs 0,0(r3)
+ stfd 0,0(r4)
+ blr
+
+_GLOBAL(cvt_df)
+ lfd 0,0(r3)
+ stfs 0,0(r4)
+ blr
+#else
+_GLOBAL(cvt_fd)
+ lfd 0,-4(r5) /* load up fpscr value */
+ mtfsf 0xff,0
+ lfs 0,0(r3)
+ stfd 0,0(r4)
+ mffs 0 /* save new fpscr value */
+ stfd 0,-4(r5)
+ blr
+
+_GLOBAL(cvt_df)
+ lfd 0,-4(r5) /* load up fpscr value */
+ mtfsf 0xff,0
+ lfd 0,0(r3)
+ stfs 0,0(r4)
+ mffs 0 /* save new fpscr value */
+ stfd 0,-4(r5)
+ blr
+#endif
+
+/*
+ * Create a kernel thread
+ * kernel_thread(fn, arg, flags)
+ */
+_GLOBAL(kernel_thread)
+ stwu r1,-16(r1)
+ stw r30,8(r1)
+ stw r31,12(r1)
+ mr r30,r3 /* function */
+ mr r31,r4 /* argument */
+ ori r3,r5,CLONE_VM /* flags */
+ oris r3,r3,CLONE_UNTRACED>>16
+ li r4,0 /* new sp (unused) */
+ li r0,__NR_clone
+ sc
+ cmpwi 0,r3,0 /* parent or child? */
+ bne 1f /* return if parent */
+ li r0,0 /* make top-level stack frame */
+ stwu r0,-16(r1)
+ mtlr r30 /* fn addr in lr */
+ mr r3,r31 /* load arg and call fn */
+ blrl
+ li r0,__NR_exit /* exit if function returns */
+ li r3,0
+ sc
+1: lwz r30,8(r1)
+ lwz r31,12(r1)
+ addi r1,r1,16
+ blr
+
+/*
+ * This routine is just here to keep GCC happy - sigh...
+ */
+_GLOBAL(__main)
+ blr
+
+#define SYSCALL(name) \
+_GLOBAL(name) \
+ li r0,__NR_##name; \
+ sc; \
+ bnslr; \
+ lis r4,errno@ha; \
+ stw r3,errno@l(r4); \
+ li r3,-1; \
+ blr
+
+SYSCALL(execve)
+
+/* Why isn't this a) automatic, b) written in 'C'? */
+ .data
+ .align 4
+_GLOBAL(sys_call_table)
+ .long sys_restart_syscall /* 0 */
+ .long sys_exit
+ .long ppc_fork
+ .long sys_read
+ .long sys_write
+ .long sys_open /* 5 */
+ .long sys_close
+ .long sys_waitpid
+ .long sys_creat
+ .long sys_link
+ .long sys_unlink /* 10 */
+ .long sys_execve
+ .long sys_chdir
+ .long sys_time
+ .long sys_mknod
+ .long sys_chmod /* 15 */
+ .long sys_lchown
+ .long sys_ni_syscall /* old break syscall holder */
+ .long sys_stat
+ .long sys_lseek
+ .long sys_getpid /* 20 */
+ .long sys_mount
+ .long sys_oldumount
+ .long sys_setuid
+ .long sys_getuid
+ .long sys_stime /* 25 */
+ .long sys_ptrace
+ .long sys_alarm
+ .long sys_fstat
+ .long sys_pause
+ .long sys_utime /* 30 */
+ .long sys_ni_syscall /* old stty syscall holder */
+ .long sys_ni_syscall /* old gtty syscall holder */
+ .long sys_access
+ .long sys_nice
+ .long sys_ni_syscall /* 35 */ /* old ftime syscall holder */
+ .long sys_sync
+ .long sys_kill
+ .long sys_rename
+ .long sys_mkdir
+ .long sys_rmdir /* 40 */
+ .long sys_dup
+ .long sys_pipe
+ .long sys_times
+ .long sys_ni_syscall /* old prof syscall holder */
+ .long sys_brk /* 45 */
+ .long sys_setgid
+ .long sys_getgid
+ .long sys_signal
+ .long sys_geteuid
+ .long sys_getegid /* 50 */
+ .long sys_acct
+ .long sys_umount /* recycled never used phys() */
+ .long sys_ni_syscall /* old lock syscall holder */
+ .long sys_ioctl
+ .long sys_fcntl /* 55 */
+ .long sys_ni_syscall /* old mpx syscall holder */
+ .long sys_setpgid
+ .long sys_ni_syscall /* old ulimit syscall holder */
+ .long sys_olduname
+ .long sys_umask /* 60 */
+ .long sys_chroot
+ .long sys_ustat
+ .long sys_dup2
+ .long sys_getppid
+ .long sys_getpgrp /* 65 */
+ .long sys_setsid
+ .long sys_sigaction
+ .long sys_sgetmask
+ .long sys_ssetmask
+ .long sys_setreuid /* 70 */
+ .long sys_setregid
+ .long ppc_sigsuspend
+ .long sys_sigpending
+ .long sys_sethostname
+ .long sys_setrlimit /* 75 */
+ .long sys_old_getrlimit
+ .long sys_getrusage
+ .long sys_gettimeofday
+ .long sys_settimeofday
+ .long sys_getgroups /* 80 */
+ .long sys_setgroups
+ .long ppc_select
+ .long sys_symlink
+ .long sys_lstat
+ .long sys_readlink /* 85 */
+ .long sys_uselib
+ .long sys_swapon
+ .long sys_reboot
+ .long old_readdir
+ .long sys_mmap /* 90 */
+ .long sys_munmap
+ .long sys_truncate
+ .long sys_ftruncate
+ .long sys_fchmod
+ .long sys_fchown /* 95 */
+ .long sys_getpriority
+ .long sys_setpriority
+ .long sys_ni_syscall /* old profil syscall holder */
+ .long sys_statfs
+ .long sys_fstatfs /* 100 */
+ .long sys_ni_syscall
+ .long sys_socketcall
+ .long sys_syslog
+ .long sys_setitimer
+ .long sys_getitimer /* 105 */
+ .long sys_newstat
+ .long sys_newlstat
+ .long sys_newfstat
+ .long sys_uname
+ .long sys_ni_syscall /* 110 */
+ .long sys_vhangup
+ .long sys_ni_syscall /* old 'idle' syscall */
+ .long sys_ni_syscall
+ .long sys_wait4
+ .long sys_swapoff /* 115 */
+ .long sys_sysinfo
+ .long sys_ipc
+ .long sys_fsync
+ .long sys_sigreturn
+ .long ppc_clone /* 120 */
+ .long sys_setdomainname
+ .long sys_newuname
+ .long sys_ni_syscall
+ .long sys_adjtimex
+ .long sys_mprotect /* 125 */
+ .long sys_sigprocmask
+ .long sys_ni_syscall /* old sys_create_module */
+ .long sys_init_module
+ .long sys_delete_module
+ .long sys_ni_syscall /* old sys_get_kernel_syms */ /* 130 */
+ .long sys_quotactl
+ .long sys_getpgid
+ .long sys_fchdir
+ .long sys_bdflush
+ .long sys_sysfs /* 135 */
+ .long sys_personality
+ .long sys_ni_syscall /* for afs_syscall */
+ .long sys_setfsuid
+ .long sys_setfsgid
+ .long sys_llseek /* 140 */
+ .long sys_getdents
+ .long ppc_select
+ .long sys_flock
+ .long sys_msync
+ .long sys_readv /* 145 */
+ .long sys_writev
+ .long sys_getsid
+ .long sys_fdatasync
+ .long sys_sysctl
+ .long sys_mlock /* 150 */
+ .long sys_munlock
+ .long sys_mlockall
+ .long sys_munlockall
+ .long sys_sched_setparam
+ .long sys_sched_getparam /* 155 */
+ .long sys_sched_setscheduler
+ .long sys_sched_getscheduler
+ .long sys_sched_yield
+ .long sys_sched_get_priority_max
+ .long sys_sched_get_priority_min /* 160 */
+ .long sys_sched_rr_get_interval
+ .long sys_nanosleep
+ .long sys_mremap
+ .long sys_setresuid
+ .long sys_getresuid /* 165 */
+ .long sys_ni_syscall /* old sys_query_module */
+ .long sys_poll
+ .long sys_nfsservctl
+ .long sys_setresgid
+ .long sys_getresgid /* 170 */
+ .long sys_prctl
+ .long sys_rt_sigreturn
+ .long sys_rt_sigaction
+ .long sys_rt_sigprocmask
+ .long sys_rt_sigpending /* 175 */
+ .long sys_rt_sigtimedwait
+ .long sys_rt_sigqueueinfo
+ .long ppc_rt_sigsuspend
+ .long sys_pread64
+ .long sys_pwrite64 /* 180 */
+ .long sys_chown
+ .long sys_getcwd
+ .long sys_capget
+ .long sys_capset
+ .long sys_sigaltstack /* 185 */
+ .long sys_sendfile
+ .long sys_ni_syscall /* streams1 */
+ .long sys_ni_syscall /* streams2 */
+ .long ppc_vfork
+ .long sys_getrlimit /* 190 */
+ .long sys_readahead
+ .long sys_mmap2
+ .long sys_truncate64
+ .long sys_ftruncate64
+ .long sys_stat64 /* 195 */
+ .long sys_lstat64
+ .long sys_fstat64
+ .long sys_pciconfig_read
+ .long sys_pciconfig_write
+ .long sys_pciconfig_iobase /* 200 */
+ .long sys_ni_syscall /* 201 - reserved - MacOnLinux - new */
+ .long sys_getdents64
+ .long sys_pivot_root
+ .long sys_fcntl64
+ .long sys_madvise /* 205 */
+ .long sys_mincore
+ .long sys_gettid
+ .long sys_tkill
+ .long sys_setxattr
+ .long sys_lsetxattr /* 210 */
+ .long sys_fsetxattr
+ .long sys_getxattr
+ .long sys_lgetxattr
+ .long sys_fgetxattr
+ .long sys_listxattr /* 215 */
+ .long sys_llistxattr
+ .long sys_flistxattr
+ .long sys_removexattr
+ .long sys_lremovexattr
+ .long sys_fremovexattr /* 220 */
+ .long sys_futex
+ .long sys_sched_setaffinity
+ .long sys_sched_getaffinity
+ .long sys_ni_syscall
+ .long sys_ni_syscall /* 225 - reserved for Tux */
+ .long sys_sendfile64
+ .long sys_io_setup
+ .long sys_io_destroy
+ .long sys_io_getevents
+ .long sys_io_submit /* 230 */
+ .long sys_io_cancel
+ .long sys_set_tid_address
+ .long sys_fadvise64
+ .long sys_exit_group
+ .long sys_lookup_dcookie /* 235 */
+ .long sys_epoll_create
+ .long sys_epoll_ctl
+ .long sys_epoll_wait
+ .long sys_remap_file_pages
+ .long sys_timer_create /* 240 */
+ .long sys_timer_settime
+ .long sys_timer_gettime
+ .long sys_timer_getoverrun
+ .long sys_timer_delete
+ .long sys_clock_settime /* 245 */
+ .long sys_clock_gettime
+ .long sys_clock_getres
+ .long sys_clock_nanosleep
+ .long ppc_swapcontext
+ .long sys_tgkill /* 250 */
+ .long sys_utimes
+ .long sys_statfs64
+ .long sys_fstatfs64
+ .long ppc_fadvise64_64
+ .long sys_ni_syscall /* 255 - rtas (used on ppc64) */
+ .long sys_debug_setcontext
+ .long sys_ni_syscall /* 257 reserved for vserver */
+ .long sys_ni_syscall /* 258 reserved for new sys_remap_file_pages */
+ .long sys_ni_syscall /* 259 reserved for new sys_mbind */
+ .long sys_ni_syscall /* 260 reserved for new sys_get_mempolicy */
+ .long sys_ni_syscall /* 261 reserved for new sys_set_mempolicy */
+ .long sys_mq_open
+ .long sys_mq_unlink
+ .long sys_mq_timedsend
+ .long sys_mq_timedreceive /* 265 */
+ .long sys_mq_notify
+ .long sys_mq_getsetattr
+ .long sys_ni_syscall /* 268 reserved for sys_kexec_load */
+ .long sys_add_key
+ .long sys_request_key /* 270 */
+ .long sys_keyctl
+ .long sys_waitid
diff --git a/arch/ppc/kernel/module.c b/arch/ppc/kernel/module.c
new file mode 100644
index 000000000000..92f4e5f64f02
--- /dev/null
+++ b/arch/ppc/kernel/module.c
@@ -0,0 +1,320 @@
+/* Kernel module help for PPC.
+ Copyright (C) 2001 Rusty Russell.
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+*/
+#include <linux/module.h>
+#include <linux/moduleloader.h>
+#include <linux/elf.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/cache.h>
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(fmt , ...)
+#endif
+
+LIST_HEAD(module_bug_list);
+
+void *module_alloc(unsigned long size)
+{
+ if (size == 0)
+ return NULL;
+ return vmalloc(size);
+}
+
+/* Free memory returned from module_alloc */
+void module_free(struct module *mod, void *module_region)
+{
+ vfree(module_region);
+ /* FIXME: If module_region == mod->init_region, trim exception
+ table entries. */
+}
+
+/* Count how many different relocations (different symbol, different
+ addend) */
+static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
+{
+ unsigned int i, j, ret = 0;
+
+ /* Sure, this is order(n^2), but it's usually short, and not
+ time critical */
+ for (i = 0; i < num; i++) {
+ for (j = 0; j < i; j++) {
+ /* If this addend appeared before, it's
+ already been counted */
+ if (ELF32_R_SYM(rela[i].r_info)
+ == ELF32_R_SYM(rela[j].r_info)
+ && rela[i].r_addend == rela[j].r_addend)
+ break;
+ }
+ if (j == i) ret++;
+ }
+ return ret;
+}
+
+/* Get the potential trampolines size required of the init and
+ non-init sections */
+static unsigned long get_plt_size(const Elf32_Ehdr *hdr,
+ const Elf32_Shdr *sechdrs,
+ const char *secstrings,
+ int is_init)
+{
+ unsigned long ret = 0;
+ unsigned i;
+
+ /* Everything marked ALLOC (this includes the exported
+ symbols) */
+ for (i = 1; i < hdr->e_shnum; i++) {
+ /* If it's called *.init*, and we're not init, we're
+ not interested */
+ if ((strstr(secstrings + sechdrs[i].sh_name, ".init") != 0)
+ != is_init)
+ continue;
+
+ /* We don't want to look at debug sections. */
+ if (strstr(secstrings + sechdrs[i].sh_name, ".debug") != 0)
+ continue;
+
+ if (sechdrs[i].sh_type == SHT_RELA) {
+ DEBUGP("Found relocations in section %u\n", i);
+ DEBUGP("Ptr: %p. Number: %u\n",
+ (void *)hdr + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size / sizeof(Elf32_Rela));
+ ret += count_relocs((void *)hdr
+ + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size
+ / sizeof(Elf32_Rela))
+ * sizeof(struct ppc_plt_entry);
+ }
+ }
+
+ return ret;
+}
+
+int module_frob_arch_sections(Elf32_Ehdr *hdr,
+ Elf32_Shdr *sechdrs,
+ char *secstrings,
+ struct module *me)
+{
+ unsigned int i;
+
+ /* Find .plt and .init.plt sections */
+ for (i = 0; i < hdr->e_shnum; i++) {
+ if (strcmp(secstrings + sechdrs[i].sh_name, ".init.plt") == 0)
+ me->arch.init_plt_section = i;
+ else if (strcmp(secstrings + sechdrs[i].sh_name, ".plt") == 0)
+ me->arch.core_plt_section = i;
+ }
+ if (!me->arch.core_plt_section || !me->arch.init_plt_section) {
+ printk("Module doesn't contain .plt or .init.plt sections.\n");
+ return -ENOEXEC;
+ }
+
+ /* Override their sizes */
+ sechdrs[me->arch.core_plt_section].sh_size
+ = get_plt_size(hdr, sechdrs, secstrings, 0);
+ sechdrs[me->arch.init_plt_section].sh_size
+ = get_plt_size(hdr, sechdrs, secstrings, 1);
+ return 0;
+}
+
+int apply_relocate(Elf32_Shdr *sechdrs,
+ const char *strtab,
+ unsigned int symindex,
+ unsigned int relsec,
+ struct module *module)
+{
+ printk(KERN_ERR "%s: Non-ADD RELOCATION unsupported\n",
+ module->name);
+ return -ENOEXEC;
+}
+
+static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
+{
+ if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16)
+ && entry->jump[1] == 0x396b0000 + (val & 0xffff))
+ return 1;
+ return 0;
+}
+
+/* Set up a trampoline in the PLT to bounce us to the distant function */
+static uint32_t do_plt_call(void *location,
+ Elf32_Addr val,
+ Elf32_Shdr *sechdrs,
+ struct module *mod)
+{
+ struct ppc_plt_entry *entry;
+
+ DEBUGP("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location);
+ /* Init, or core PLT? */
+ if (location >= mod->module_core
+ && location < mod->module_core + mod->core_size)
+ entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr;
+ else
+ entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr;
+
+ /* Find this entry, or if that fails, the next avail. entry */
+ while (entry->jump[0]) {
+ if (entry_matches(entry, val)) return (uint32_t)entry;
+ entry++;
+ }
+
+ /* Stolen from Paul Mackerras as well... */
+ entry->jump[0] = 0x3d600000+((val+0x8000)>>16); /* lis r11,sym@ha */
+ entry->jump[1] = 0x396b0000 + (val&0xffff); /* addi r11,r11,sym@l*/
+ entry->jump[2] = 0x7d6903a6; /* mtctr r11 */
+ entry->jump[3] = 0x4e800420; /* bctr */
+
+ DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);
+ return (uint32_t)entry;
+}
+
+int apply_relocate_add(Elf32_Shdr *sechdrs,
+ const char *strtab,
+ unsigned int symindex,
+ unsigned int relsec,
+ struct module *module)
+{
+ unsigned int i;
+ Elf32_Rela *rela = (void *)sechdrs[relsec].sh_addr;
+ Elf32_Sym *sym;
+ uint32_t *location;
+ uint32_t value;
+
+ DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
+ sechdrs[relsec].sh_info);
+ for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
+ /* This is where to make the change */
+ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rela[i].r_offset;
+ /* This is the symbol it is referring to. Note that all
+ undefined symbols have been resolved. */
+ sym = (Elf32_Sym *)sechdrs[symindex].sh_addr
+ + ELF32_R_SYM(rela[i].r_info);
+ /* `Everything is relative'. */
+ value = sym->st_value + rela[i].r_addend;
+
+ switch (ELF32_R_TYPE(rela[i].r_info)) {
+ case R_PPC_ADDR32:
+ /* Simply set it */
+ *(uint32_t *)location = value;
+ break;
+
+ case R_PPC_ADDR16_LO:
+ /* Low half of the symbol */
+ *(uint16_t *)location = value;
+ break;
+
+ case R_PPC_ADDR16_HA:
+ /* Sign-adjusted lower 16 bits: PPC ELF ABI says:
+ (((x >> 16) + ((x & 0x8000) ? 1 : 0))) & 0xFFFF.
+ This is the same, only sane.
+ */
+ *(uint16_t *)location = (value + 0x8000) >> 16;
+ break;
+
+ case R_PPC_REL24:
+ if ((int)(value - (uint32_t)location) < -0x02000000
+ || (int)(value - (uint32_t)location) >= 0x02000000)
+ value = do_plt_call(location, value,
+ sechdrs, module);
+
+ /* Only replace bits 2 through 26 */
+ DEBUGP("REL24 value = %08X. location = %08X\n",
+ value, (uint32_t)location);
+ DEBUGP("Location before: %08X.\n",
+ *(uint32_t *)location);
+ *(uint32_t *)location
+ = (*(uint32_t *)location & ~0x03fffffc)
+ | ((value - (uint32_t)location)
+ & 0x03fffffc);
+ DEBUGP("Location after: %08X.\n",
+ *(uint32_t *)location);
+ DEBUGP("ie. jump to %08X+%08X = %08X\n",
+ *(uint32_t *)location & 0x03fffffc,
+ (uint32_t)location,
+ (*(uint32_t *)location & 0x03fffffc)
+ + (uint32_t)location);
+ break;
+
+ case R_PPC_REL32:
+ /* 32-bit relative jump. */
+ *(uint32_t *)location = value - (uint32_t)location;
+ break;
+
+ default:
+ printk("%s: unknown ADD relocation: %u\n",
+ module->name,
+ ELF32_R_TYPE(rela[i].r_info));
+ return -ENOEXEC;
+ }
+ }
+ return 0;
+}
+
+int module_finalize(const Elf_Ehdr *hdr,
+ const Elf_Shdr *sechdrs,
+ struct module *me)
+{
+ char *secstrings;
+ unsigned int i;
+
+ me->arch.bug_table = NULL;
+ me->arch.num_bugs = 0;
+
+ /* Find the __bug_table section, if present */
+ secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table"))
+ continue;
+ me->arch.bug_table = (void *) sechdrs[i].sh_addr;
+ me->arch.num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry);
+ break;
+ }
+
+ /*
+ * Strictly speaking this should have a spinlock to protect against
+ * traversals, but since we only traverse on BUG()s, a spinlock
+ * could potentially lead to deadlock and thus be counter-productive.
+ */
+ list_add(&me->arch.bug_list, &module_bug_list);
+
+ return 0;
+}
+
+void module_arch_cleanup(struct module *mod)
+{
+ list_del(&mod->arch.bug_list);
+}
+
+struct bug_entry *module_find_bug(unsigned long bugaddr)
+{
+ struct mod_arch_specific *mod;
+ unsigned int i;
+ struct bug_entry *bug;
+
+ list_for_each_entry(mod, &module_bug_list, bug_list) {
+ bug = mod->bug_table;
+ for (i = 0; i < mod->num_bugs; ++i, ++bug)
+ if (bugaddr == bug->bug_addr)
+ return bug;
+ }
+ return NULL;
+}
diff --git a/arch/ppc/kernel/pci.c b/arch/ppc/kernel/pci.c
new file mode 100644
index 000000000000..98f94b60204c
--- /dev/null
+++ b/arch/ppc/kernel/pci.c
@@ -0,0 +1,1849 @@
+/*
+ * Common pmac/prep/chrp pci routines. -- Cort
+ */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/capability.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/bootmem.h>
+
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/sections.h>
+#include <asm/pci-bridge.h>
+#include <asm/byteorder.h>
+#include <asm/irq.h>
+#include <asm/uaccess.h>
+
+#undef DEBUG
+
+#ifdef DEBUG
+#define DBG(x...) printk(x)
+#else
+#define DBG(x...)
+#endif
+
+unsigned long isa_io_base = 0;
+unsigned long isa_mem_base = 0;
+unsigned long pci_dram_offset = 0;
+int pcibios_assign_bus_offset = 1;
+
+void pcibios_make_OF_bus_map(void);
+
+static int pci_relocate_bridge_resource(struct pci_bus *bus, int i);
+static int probe_resource(struct pci_bus *parent, struct resource *pr,
+ struct resource *res, struct resource **conflict);
+static void update_bridge_base(struct pci_bus *bus, int i);
+static void pcibios_fixup_resources(struct pci_dev* dev);
+static void fixup_broken_pcnet32(struct pci_dev* dev);
+static int reparent_resources(struct resource *parent, struct resource *res);
+static void fixup_rev1_53c810(struct pci_dev* dev);
+static void fixup_cpc710_pci64(struct pci_dev* dev);
+#ifdef CONFIG_PPC_OF
+static u8* pci_to_OF_bus_map;
+#endif
+
+/* By default, we don't re-assign bus numbers. We do this only on
+ * some pmacs
+ */
+int pci_assign_all_busses;
+
+struct pci_controller* hose_head;
+struct pci_controller** hose_tail = &hose_head;
+
+static int pci_bus_count;
+
+static void
+fixup_rev1_53c810(struct pci_dev* dev)
+{
+ /* rev 1 ncr53c810 chips don't set the class at all which means
+ * they don't get their resources remapped. Fix that here.
+ */
+
+ if ((dev->class == PCI_CLASS_NOT_DEFINED)) {
+ printk("NCR 53c810 rev 1 detected, setting PCI class.\n");
+ dev->class = PCI_CLASS_STORAGE_SCSI;
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, fixup_rev1_53c810);
+
+static void
+fixup_broken_pcnet32(struct pci_dev* dev)
+{
+ if ((dev->class>>8 == PCI_CLASS_NETWORK_ETHERNET)) {
+ dev->vendor = PCI_VENDOR_ID_AMD;
+ pci_write_config_word(dev, PCI_VENDOR_ID, PCI_VENDOR_ID_AMD);
+ pci_name_device(dev);
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TRIDENT, PCI_ANY_ID, fixup_broken_pcnet32);
+
+static void
+fixup_cpc710_pci64(struct pci_dev* dev)
+{
+ /* Hide the PCI64 BARs from the kernel as their content doesn't
+ * fit well in the resource management
+ */
+ dev->resource[0].start = dev->resource[0].end = 0;
+ dev->resource[0].flags = 0;
+ dev->resource[1].start = dev->resource[1].end = 0;
+ dev->resource[1].flags = 0;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CPC710_PCI64, fixup_cpc710_pci64);
+
+static void
+pcibios_fixup_resources(struct pci_dev *dev)
+{
+ struct pci_controller* hose = (struct pci_controller *)dev->sysdata;
+ int i;
+ unsigned long offset;
+
+ if (!hose) {
+ printk(KERN_ERR "No hose for PCI dev %s!\n", pci_name(dev));
+ return;
+ }
+ for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+ struct resource *res = dev->resource + i;
+ if (!res->flags)
+ continue;
+ if (res->end == 0xffffffff) {
+ DBG("PCI:%s Resource %d [%08lx-%08lx] is unassigned\n",
+ pci_name(dev), i, res->start, res->end);
+ res->end -= res->start;
+ res->start = 0;
+ res->flags |= IORESOURCE_UNSET;
+ continue;
+ }
+ offset = 0;
+ if (res->flags & IORESOURCE_MEM) {
+ offset = hose->pci_mem_offset;
+ } else if (res->flags & IORESOURCE_IO) {
+ offset = (unsigned long) hose->io_base_virt
+ - isa_io_base;
+ }
+ if (offset != 0) {
+ res->start += offset;
+ res->end += offset;
+#ifdef DEBUG
+ printk("Fixup res %d (%lx) of dev %s: %lx -> %lx\n",
+ i, res->flags, pci_name(dev),
+ res->start - offset, res->start);
+#endif
+ }
+ }
+
+ /* Call machine specific resource fixup */
+ if (ppc_md.pcibios_fixup_resources)
+ ppc_md.pcibios_fixup_resources(dev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_resources);
+
+void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
+ struct resource *res)
+{
+ unsigned long offset = 0;
+ struct pci_controller *hose = dev->sysdata;
+
+ if (hose && res->flags & IORESOURCE_IO)
+ offset = (unsigned long)hose->io_base_virt - isa_io_base;
+ else if (hose && res->flags & IORESOURCE_MEM)
+ offset = hose->pci_mem_offset;
+ region->start = res->start - offset;
+ region->end = res->end - offset;
+}
+EXPORT_SYMBOL(pcibios_resource_to_bus);
+
+/*
+ * We need to avoid collisions with `mirrored' VGA ports
+ * and other strange ISA hardware, so we always want the
+ * addresses to be allocated in the 0x000-0x0ff region
+ * modulo 0x400.
+ *
+ * Why? Because some silly external IO cards only decode
+ * the low 10 bits of the IO address. The 0x00-0xff region
+ * is reserved for motherboard devices that decode all 16
+ * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
+ * but we want to try to avoid allocating at 0x2900-0x2bff
+ * which might have be mirrored at 0x0100-0x03ff..
+ */
+void pcibios_align_resource(void *data, struct resource *res, unsigned long size,
+ unsigned long align)
+{
+ struct pci_dev *dev = data;
+
+ if (res->flags & IORESOURCE_IO) {
+ unsigned long start = res->start;
+
+ if (size > 0x100) {
+ printk(KERN_ERR "PCI: I/O Region %s/%d too large"
+ " (%ld bytes)\n", pci_name(dev),
+ dev->resource - res, size);
+ }
+
+ if (start & 0x300) {
+ start = (start + 0x3ff) & ~0x3ff;
+ res->start = start;
+ }
+ }
+}
+EXPORT_SYMBOL(pcibios_align_resource);
+
+/*
+ * Handle resources of PCI devices. If the world were perfect, we could
+ * just allocate all the resource regions and do nothing more. It isn't.
+ * On the other hand, we cannot just re-allocate all devices, as it would
+ * require us to know lots of host bridge internals. So we attempt to
+ * keep as much of the original configuration as possible, but tweak it
+ * when it's found to be wrong.
+ *
+ * Known BIOS problems we have to work around:
+ * - I/O or memory regions not configured
+ * - regions configured, but not enabled in the command register
+ * - bogus I/O addresses above 64K used
+ * - expansion ROMs left enabled (this may sound harmless, but given
+ * the fact the PCI specs explicitly allow address decoders to be
+ * shared between expansion ROMs and other resource regions, it's
+ * at least dangerous)
+ *
+ * Our solution:
+ * (1) Allocate resources for all buses behind PCI-to-PCI bridges.
+ * This gives us fixed barriers on where we can allocate.
+ * (2) Allocate resources for all enabled devices. If there is
+ * a collision, just mark the resource as unallocated. Also
+ * disable expansion ROMs during this step.
+ * (3) Try to allocate resources for disabled devices. If the
+ * resources were assigned correctly, everything goes well,
+ * if they weren't, they won't disturb allocation of other
+ * resources.
+ * (4) Assign new addresses to resources which were either
+ * not configured at all or misconfigured. If explicitly
+ * requested by the user, configure expansion ROM address
+ * as well.
+ */
+
+static void __init
+pcibios_allocate_bus_resources(struct list_head *bus_list)
+{
+ struct pci_bus *bus;
+ int i;
+ struct resource *res, *pr;
+
+ /* Depth-First Search on bus tree */
+ list_for_each_entry(bus, bus_list, node) {
+ for (i = 0; i < 4; ++i) {
+ if ((res = bus->resource[i]) == NULL || !res->flags
+ || res->start > res->end)
+ continue;
+ if (bus->parent == NULL)
+ pr = (res->flags & IORESOURCE_IO)?
+ &ioport_resource: &iomem_resource;
+ else {
+ pr = pci_find_parent_resource(bus->self, res);
+ if (pr == res) {
+ /* this happens when the generic PCI
+ * code (wrongly) decides that this
+ * bridge is transparent -- paulus
+ */
+ continue;
+ }
+ }
+
+ DBG("PCI: bridge rsrc %lx..%lx (%lx), parent %p\n",
+ res->start, res->end, res->flags, pr);
+ if (pr) {
+ if (request_resource(pr, res) == 0)
+ continue;
+ /*
+ * Must be a conflict with an existing entry.
+ * Move that entry (or entries) under the
+ * bridge resource and try again.
+ */
+ if (reparent_resources(pr, res) == 0)
+ continue;
+ }
+ printk(KERN_ERR "PCI: Cannot allocate resource region "
+ "%d of PCI bridge %d\n", i, bus->number);
+ if (pci_relocate_bridge_resource(bus, i))
+ bus->resource[i] = NULL;
+ }
+ pcibios_allocate_bus_resources(&bus->children);
+ }
+}
+
+/*
+ * Reparent resource children of pr that conflict with res
+ * under res, and make res replace those children.
+ */
+static int __init
+reparent_resources(struct resource *parent, struct resource *res)
+{
+ struct resource *p, **pp;
+ struct resource **firstpp = NULL;
+
+ for (pp = &parent->child; (p = *pp) != NULL; pp = &p->sibling) {
+ if (p->end < res->start)
+ continue;
+ if (res->end < p->start)
+ break;
+ if (p->start < res->start || p->end > res->end)
+ return -1; /* not completely contained */
+ if (firstpp == NULL)
+ firstpp = pp;
+ }
+ if (firstpp == NULL)
+ return -1; /* didn't find any conflicting entries? */
+ res->parent = parent;
+ res->child = *firstpp;
+ res->sibling = *pp;
+ *firstpp = res;
+ *pp = NULL;
+ for (p = res->child; p != NULL; p = p->sibling) {
+ p->parent = res;
+ DBG(KERN_INFO "PCI: reparented %s [%lx..%lx] under %s\n",
+ p->name, p->start, p->end, res->name);
+ }
+ return 0;
+}
+
+/*
+ * A bridge has been allocated a range which is outside the range
+ * of its parent bridge, so it needs to be moved.
+ */
+static int __init
+pci_relocate_bridge_resource(struct pci_bus *bus, int i)
+{
+ struct resource *res, *pr, *conflict;
+ unsigned long try, size;
+ int j;
+ struct pci_bus *parent = bus->parent;
+
+ if (parent == NULL) {
+ /* shouldn't ever happen */
+ printk(KERN_ERR "PCI: can't move host bridge resource\n");
+ return -1;
+ }
+ res = bus->resource[i];
+ if (res == NULL)
+ return -1;
+ pr = NULL;
+ for (j = 0; j < 4; j++) {
+ struct resource *r = parent->resource[j];
+ if (!r)
+ continue;
+ if ((res->flags ^ r->flags) & (IORESOURCE_IO | IORESOURCE_MEM))
+ continue;
+ if (!((res->flags ^ r->flags) & IORESOURCE_PREFETCH)) {
+ pr = r;
+ break;
+ }
+ if (res->flags & IORESOURCE_PREFETCH)
+ pr = r;
+ }
+ if (pr == NULL)
+ return -1;
+ size = res->end - res->start;
+ if (pr->start > pr->end || size > pr->end - pr->start)
+ return -1;
+ try = pr->end;
+ for (;;) {
+ res->start = try - size;
+ res->end = try;
+ if (probe_resource(bus->parent, pr, res, &conflict) == 0)
+ break;
+ if (conflict->start <= pr->start + size)
+ return -1;
+ try = conflict->start - 1;
+ }
+ if (request_resource(pr, res)) {
+ DBG(KERN_ERR "PCI: huh? couldn't move to %lx..%lx\n",
+ res->start, res->end);
+ return -1; /* "can't happen" */
+ }
+ update_bridge_base(bus, i);
+ printk(KERN_INFO "PCI: bridge %d resource %d moved to %lx..%lx\n",
+ bus->number, i, res->start, res->end);
+ return 0;
+}
+
+static int __init
+probe_resource(struct pci_bus *parent, struct resource *pr,
+ struct resource *res, struct resource **conflict)
+{
+ struct pci_bus *bus;
+ struct pci_dev *dev;
+ struct resource *r;
+ int i;
+
+ for (r = pr->child; r != NULL; r = r->sibling) {
+ if (r->end >= res->start && res->end >= r->start) {
+ *conflict = r;
+ return 1;
+ }
+ }
+ list_for_each_entry(bus, &parent->children, node) {
+ for (i = 0; i < 4; ++i) {
+ if ((r = bus->resource[i]) == NULL)
+ continue;
+ if (!r->flags || r->start > r->end || r == res)
+ continue;
+ if (pci_find_parent_resource(bus->self, r) != pr)
+ continue;
+ if (r->end >= res->start && res->end >= r->start) {
+ *conflict = r;
+ return 1;
+ }
+ }
+ }
+ list_for_each_entry(dev, &parent->devices, bus_list) {
+ for (i = 0; i < 6; ++i) {
+ r = &dev->resource[i];
+ if (!r->flags || (r->flags & IORESOURCE_UNSET))
+ continue;
+ if (pci_find_parent_resource(dev, r) != pr)
+ continue;
+ if (r->end >= res->start && res->end >= r->start) {
+ *conflict = r;
+ return 1;
+ }
+ }
+ }
+ return 0;
+}
+
+static void __init
+update_bridge_base(struct pci_bus *bus, int i)
+{
+ struct resource *res = bus->resource[i];
+ u8 io_base_lo, io_limit_lo;
+ u16 mem_base, mem_limit;
+ u16 cmd;
+ unsigned long start, end, off;
+ struct pci_dev *dev = bus->self;
+ struct pci_controller *hose = dev->sysdata;
+
+ if (!hose) {
+ printk("update_bridge_base: no hose?\n");
+ return;
+ }
+ pci_read_config_word(dev, PCI_COMMAND, &cmd);
+ pci_write_config_word(dev, PCI_COMMAND,
+ cmd & ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY));
+ if (res->flags & IORESOURCE_IO) {
+ off = (unsigned long) hose->io_base_virt - isa_io_base;
+ start = res->start - off;
+ end = res->end - off;
+ io_base_lo = (start >> 8) & PCI_IO_RANGE_MASK;
+ io_limit_lo = (end >> 8) & PCI_IO_RANGE_MASK;
+ if (end > 0xffff) {
+ pci_write_config_word(dev, PCI_IO_BASE_UPPER16,
+ start >> 16);
+ pci_write_config_word(dev, PCI_IO_LIMIT_UPPER16,
+ end >> 16);
+ io_base_lo |= PCI_IO_RANGE_TYPE_32;
+ } else
+ io_base_lo |= PCI_IO_RANGE_TYPE_16;
+ pci_write_config_byte(dev, PCI_IO_BASE, io_base_lo);
+ pci_write_config_byte(dev, PCI_IO_LIMIT, io_limit_lo);
+
+ } else if ((res->flags & (IORESOURCE_MEM | IORESOURCE_PREFETCH))
+ == IORESOURCE_MEM) {
+ off = hose->pci_mem_offset;
+ mem_base = ((res->start - off) >> 16) & PCI_MEMORY_RANGE_MASK;
+ mem_limit = ((res->end - off) >> 16) & PCI_MEMORY_RANGE_MASK;
+ pci_write_config_word(dev, PCI_MEMORY_BASE, mem_base);
+ pci_write_config_word(dev, PCI_MEMORY_LIMIT, mem_limit);
+
+ } else if ((res->flags & (IORESOURCE_MEM | IORESOURCE_PREFETCH))
+ == (IORESOURCE_MEM | IORESOURCE_PREFETCH)) {
+ off = hose->pci_mem_offset;
+ mem_base = ((res->start - off) >> 16) & PCI_PREF_RANGE_MASK;
+ mem_limit = ((res->end - off) >> 16) & PCI_PREF_RANGE_MASK;
+ pci_write_config_word(dev, PCI_PREF_MEMORY_BASE, mem_base);
+ pci_write_config_word(dev, PCI_PREF_MEMORY_LIMIT, mem_limit);
+
+ } else {
+ DBG(KERN_ERR "PCI: ugh, bridge %s res %d has flags=%lx\n",
+ pci_name(dev), i, res->flags);
+ }
+ pci_write_config_word(dev, PCI_COMMAND, cmd);
+}
+
+static inline void alloc_resource(struct pci_dev *dev, int idx)
+{
+ struct resource *pr, *r = &dev->resource[idx];
+
+ DBG("PCI:%s: Resource %d: %08lx-%08lx (f=%lx)\n",
+ pci_name(dev), idx, r->start, r->end, r->flags);
+ pr = pci_find_parent_resource(dev, r);
+ if (!pr || request_resource(pr, r) < 0) {
+ printk(KERN_ERR "PCI: Cannot allocate resource region %d"
+ " of device %s\n", idx, pci_name(dev));
+ if (pr)
+ DBG("PCI: parent is %p: %08lx-%08lx (f=%lx)\n",
+ pr, pr->start, pr->end, pr->flags);
+ /* We'll assign a new address later */
+ r->flags |= IORESOURCE_UNSET;
+ r->end -= r->start;
+ r->start = 0;
+ }
+}
+
+static void __init
+pcibios_allocate_resources(int pass)
+{
+ struct pci_dev *dev = NULL;
+ int idx, disabled;
+ u16 command;
+ struct resource *r;
+
+ while ((dev = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+ pci_read_config_word(dev, PCI_COMMAND, &command);
+ for (idx = 0; idx < 6; idx++) {
+ r = &dev->resource[idx];
+ if (r->parent) /* Already allocated */
+ continue;
+ if (!r->flags || (r->flags & IORESOURCE_UNSET))
+ continue; /* Not assigned at all */
+ if (r->flags & IORESOURCE_IO)
+ disabled = !(command & PCI_COMMAND_IO);
+ else
+ disabled = !(command & PCI_COMMAND_MEMORY);
+ if (pass == disabled)
+ alloc_resource(dev, idx);
+ }
+ if (pass)
+ continue;
+ r = &dev->resource[PCI_ROM_RESOURCE];
+ if (r->flags & IORESOURCE_ROM_ENABLE) {
+ /* Turn the ROM off, leave the resource region, but keep it unregistered. */
+ u32 reg;
+ DBG("PCI: Switching off ROM of %s\n", pci_name(dev));
+ r->flags &= ~IORESOURCE_ROM_ENABLE;
+ pci_read_config_dword(dev, dev->rom_base_reg, &reg);
+ pci_write_config_dword(dev, dev->rom_base_reg,
+ reg & ~PCI_ROM_ADDRESS_ENABLE);
+ }
+ }
+}
+
+static void __init
+pcibios_assign_resources(void)
+{
+ struct pci_dev *dev = NULL;
+ int idx;
+ struct resource *r;
+
+ while ((dev = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+ int class = dev->class >> 8;
+
+ /* Don't touch classless devices and host bridges */
+ if (!class || class == PCI_CLASS_BRIDGE_HOST)
+ continue;
+
+ for (idx = 0; idx < 6; idx++) {
+ r = &dev->resource[idx];
+
+ /*
+ * We shall assign a new address to this resource,
+ * either because the BIOS (sic) forgot to do so
+ * or because we have decided the old address was
+ * unusable for some reason.
+ */
+ if ((r->flags & IORESOURCE_UNSET) && r->end &&
+ (!ppc_md.pcibios_enable_device_hook ||
+ !ppc_md.pcibios_enable_device_hook(dev, 1))) {
+ r->flags &= ~IORESOURCE_UNSET;
+ pci_assign_resource(dev, idx);
+ }
+ }
+
+#if 0 /* don't assign ROMs */
+ r = &dev->resource[PCI_ROM_RESOURCE];
+ r->end -= r->start;
+ r->start = 0;
+ if (r->end)
+ pci_assign_resource(dev, PCI_ROM_RESOURCE);
+#endif
+ }
+}
+
+
+int
+pcibios_enable_resources(struct pci_dev *dev, int mask)
+{
+ u16 cmd, old_cmd;
+ int idx;
+ struct resource *r;
+
+ pci_read_config_word(dev, PCI_COMMAND, &cmd);
+ old_cmd = cmd;
+ for (idx=0; idx<6; idx++) {
+ /* Only set up the requested stuff */
+ if (!(mask & (1<<idx)))
+ continue;
+
+ r = &dev->resource[idx];
+ if (r->flags & IORESOURCE_UNSET) {
+ printk(KERN_ERR "PCI: Device %s not available because of resource collisions\n", pci_name(dev));
+ return -EINVAL;
+ }
+ if (r->flags & IORESOURCE_IO)
+ cmd |= PCI_COMMAND_IO;
+ if (r->flags & IORESOURCE_MEM)
+ cmd |= PCI_COMMAND_MEMORY;
+ }
+ if (dev->resource[PCI_ROM_RESOURCE].start)
+ cmd |= PCI_COMMAND_MEMORY;
+ if (cmd != old_cmd) {
+ printk("PCI: Enabling device %s (%04x -> %04x)\n", pci_name(dev), old_cmd, cmd);
+ pci_write_config_word(dev, PCI_COMMAND, cmd);
+ }
+ return 0;
+}
+
+static int next_controller_index;
+
+struct pci_controller * __init
+pcibios_alloc_controller(void)
+{
+ struct pci_controller *hose;
+
+ hose = (struct pci_controller *)alloc_bootmem(sizeof(*hose));
+ memset(hose, 0, sizeof(struct pci_controller));
+
+ *hose_tail = hose;
+ hose_tail = &hose->next;
+
+ hose->index = next_controller_index++;
+
+ return hose;
+}
+
+#ifdef CONFIG_PPC_OF
+/*
+ * Functions below are used on OpenFirmware machines.
+ */
+static void __openfirmware
+make_one_node_map(struct device_node* node, u8 pci_bus)
+{
+ int *bus_range;
+ int len;
+
+ if (pci_bus >= pci_bus_count)
+ return;
+ bus_range = (int *) get_property(node, "bus-range", &len);
+ if (bus_range == NULL || len < 2 * sizeof(int)) {
+ printk(KERN_WARNING "Can't get bus-range for %s, "
+ "assuming it starts at 0\n", node->full_name);
+ pci_to_OF_bus_map[pci_bus] = 0;
+ } else
+ pci_to_OF_bus_map[pci_bus] = bus_range[0];
+
+ for (node=node->child; node != 0;node = node->sibling) {
+ struct pci_dev* dev;
+ unsigned int *class_code, *reg;
+
+ class_code = (unsigned int *) get_property(node, "class-code", NULL);
+ if (!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI &&
+ (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS))
+ continue;
+ reg = (unsigned int *)get_property(node, "reg", NULL);
+ if (!reg)
+ continue;
+ dev = pci_find_slot(pci_bus, ((reg[0] >> 8) & 0xff));
+ if (!dev || !dev->subordinate)
+ continue;
+ make_one_node_map(node, dev->subordinate->number);
+ }
+}
+
+void __openfirmware
+pcibios_make_OF_bus_map(void)
+{
+ int i;
+ struct pci_controller* hose;
+ u8* of_prop_map;
+
+ pci_to_OF_bus_map = (u8*)kmalloc(pci_bus_count, GFP_KERNEL);
+ if (!pci_to_OF_bus_map) {
+ printk(KERN_ERR "Can't allocate OF bus map !\n");
+ return;
+ }
+
+ /* We fill the bus map with invalid values, that helps
+ * debugging.
+ */
+ for (i=0; i<pci_bus_count; i++)
+ pci_to_OF_bus_map[i] = 0xff;
+
+ /* For each hose, we begin searching bridges */
+ for(hose=hose_head; hose; hose=hose->next) {
+ struct device_node* node;
+ node = (struct device_node *)hose->arch_data;
+ if (!node)
+ continue;
+ make_one_node_map(node, hose->first_busno);
+ }
+ of_prop_map = get_property(find_path_device("/"), "pci-OF-bus-map", NULL);
+ if (of_prop_map)
+ memcpy(of_prop_map, pci_to_OF_bus_map, pci_bus_count);
+#ifdef DEBUG
+ printk("PCI->OF bus map:\n");
+ for (i=0; i<pci_bus_count; i++) {
+ if (pci_to_OF_bus_map[i] == 0xff)
+ continue;
+ printk("%d -> %d\n", i, pci_to_OF_bus_map[i]);
+ }
+#endif
+}
+
+typedef int (*pci_OF_scan_iterator)(struct device_node* node, void* data);
+
+static struct device_node* __openfirmware
+scan_OF_pci_childs(struct device_node* node, pci_OF_scan_iterator filter, void* data)
+{
+ struct device_node* sub_node;
+
+ for (; node != 0;node = node->sibling) {
+ unsigned int *class_code;
+
+ if (filter(node, data))
+ return node;
+
+ /* For PCI<->PCI bridges or CardBus bridges, we go down
+ * Note: some OFs create a parent node "multifunc-device" as
+ * a fake root for all functions of a multi-function device,
+ * we go down them as well.
+ */
+ class_code = (unsigned int *) get_property(node, "class-code", NULL);
+ if ((!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI &&
+ (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS)) &&
+ strcmp(node->name, "multifunc-device"))
+ continue;
+ sub_node = scan_OF_pci_childs(node->child, filter, data);
+ if (sub_node)
+ return sub_node;
+ }
+ return NULL;
+}
+
+static int
+scan_OF_pci_childs_iterator(struct device_node* node, void* data)
+{
+ unsigned int *reg;
+ u8* fdata = (u8*)data;
+
+ reg = (unsigned int *) get_property(node, "reg", NULL);
+ if (reg && ((reg[0] >> 8) & 0xff) == fdata[1]
+ && ((reg[0] >> 16) & 0xff) == fdata[0])
+ return 1;
+ return 0;
+}
+
+static struct device_node* __openfirmware
+scan_OF_childs_for_device(struct device_node* node, u8 bus, u8 dev_fn)
+{
+ u8 filter_data[2] = {bus, dev_fn};
+
+ return scan_OF_pci_childs(node, scan_OF_pci_childs_iterator, filter_data);
+}
+
+/*
+ * Scans the OF tree for a device node matching a PCI device
+ */
+struct device_node *
+pci_busdev_to_OF_node(struct pci_bus *bus, int devfn)
+{
+ struct pci_controller *hose;
+ struct device_node *node;
+ int busnr;
+
+ if (!have_of)
+ return NULL;
+
+ /* Lookup the hose */
+ busnr = bus->number;
+ hose = pci_bus_to_hose(busnr);
+ if (!hose)
+ return NULL;
+
+ /* Check it has an OF node associated */
+ node = (struct device_node *) hose->arch_data;
+ if (!node)
+ return NULL;
+
+ /* Fixup bus number according to what OF think it is. */
+#ifdef CONFIG_PPC_PMAC
+ /* The G5 need a special case here. Basically, we don't remap all
+ * busses on it so we don't create the pci-OF-map. However, we do
+ * remap the AGP bus and so have to deal with it. A future better
+ * fix has to be done by making the remapping per-host and always
+ * filling the pci_to_OF map. --BenH
+ */
+ if (_machine == _MACH_Pmac && busnr >= 0xf0)
+ busnr -= 0xf0;
+ else
+#endif
+ if (pci_to_OF_bus_map)
+ busnr = pci_to_OF_bus_map[busnr];
+ if (busnr == 0xff)
+ return NULL;
+
+ /* Now, lookup childs of the hose */
+ return scan_OF_childs_for_device(node->child, busnr, devfn);
+}
+
+struct device_node*
+pci_device_to_OF_node(struct pci_dev *dev)
+{
+ return pci_busdev_to_OF_node(dev->bus, dev->devfn);
+}
+
+/* This routine is meant to be used early during boot, when the
+ * PCI bus numbers have not yet been assigned, and you need to
+ * issue PCI config cycles to an OF device.
+ * It could also be used to "fix" RTAS config cycles if you want
+ * to set pci_assign_all_busses to 1 and still use RTAS for PCI
+ * config cycles.
+ */
+struct pci_controller*
+pci_find_hose_for_OF_device(struct device_node* node)
+{
+ if (!have_of)
+ return NULL;
+ while(node) {
+ struct pci_controller* hose;
+ for (hose=hose_head;hose;hose=hose->next)
+ if (hose->arch_data == node)
+ return hose;
+ node=node->parent;
+ }
+ return NULL;
+}
+
+static int __openfirmware
+find_OF_pci_device_filter(struct device_node* node, void* data)
+{
+ return ((void *)node == data);
+}
+
+/*
+ * Returns the PCI device matching a given OF node
+ */
+int
+pci_device_from_OF_node(struct device_node* node, u8* bus, u8* devfn)
+{
+ unsigned int *reg;
+ struct pci_controller* hose;
+ struct pci_dev* dev = NULL;
+
+ if (!have_of)
+ return -ENODEV;
+ /* Make sure it's really a PCI device */
+ hose = pci_find_hose_for_OF_device(node);
+ if (!hose || !hose->arch_data)
+ return -ENODEV;
+ if (!scan_OF_pci_childs(((struct device_node*)hose->arch_data)->child,
+ find_OF_pci_device_filter, (void *)node))
+ return -ENODEV;
+ reg = (unsigned int *) get_property(node, "reg", NULL);
+ if (!reg)
+ return -ENODEV;
+ *bus = (reg[0] >> 16) & 0xff;
+ *devfn = ((reg[0] >> 8) & 0xff);
+
+ /* Ok, here we need some tweak. If we have already renumbered
+ * all busses, we can't rely on the OF bus number any more.
+ * the pci_to_OF_bus_map is not enough as several PCI busses
+ * may match the same OF bus number.
+ */
+ if (!pci_to_OF_bus_map)
+ return 0;
+ while ((dev = pci_find_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+ if (pci_to_OF_bus_map[dev->bus->number] != *bus)
+ continue;
+ if (dev->devfn != *devfn)
+ continue;
+ *bus = dev->bus->number;
+ return 0;
+ }
+ return -ENODEV;
+}
+
+void __init
+pci_process_bridge_OF_ranges(struct pci_controller *hose,
+ struct device_node *dev, int primary)
+{
+ static unsigned int static_lc_ranges[256] __initdata;
+ unsigned int *dt_ranges, *lc_ranges, *ranges, *prev;
+ unsigned int size;
+ int rlen = 0, orig_rlen;
+ int memno = 0;
+ struct resource *res;
+ int np, na = prom_n_addr_cells(dev);
+ np = na + 5;
+
+ /* First we try to merge ranges to fix a problem with some pmacs
+ * that can have more than 3 ranges, fortunately using contiguous
+ * addresses -- BenH
+ */
+ dt_ranges = (unsigned int *) get_property(dev, "ranges", &rlen);
+ if (!dt_ranges)
+ return;
+ /* Sanity check, though hopefully that never happens */
+ if (rlen > sizeof(static_lc_ranges)) {
+ printk(KERN_WARNING "OF ranges property too large !\n");
+ rlen = sizeof(static_lc_ranges);
+ }
+ lc_ranges = static_lc_ranges;
+ memcpy(lc_ranges, dt_ranges, rlen);
+ orig_rlen = rlen;
+
+ /* Let's work on a copy of the "ranges" property instead of damaging
+ * the device-tree image in memory
+ */
+ ranges = lc_ranges;
+ prev = NULL;
+ while ((rlen -= np * sizeof(unsigned int)) >= 0) {
+ if (prev) {
+ if (prev[0] == ranges[0] && prev[1] == ranges[1] &&
+ (prev[2] + prev[na+4]) == ranges[2] &&
+ (prev[na+2] + prev[na+4]) == ranges[na+2]) {
+ prev[na+4] += ranges[na+4];
+ ranges[0] = 0;
+ ranges += np;
+ continue;
+ }
+ }
+ prev = ranges;
+ ranges += np;
+ }
+
+ /*
+ * The ranges property is laid out as an array of elements,
+ * each of which comprises:
+ * cells 0 - 2: a PCI address
+ * cells 3 or 3+4: a CPU physical address
+ * (size depending on dev->n_addr_cells)
+ * cells 4+5 or 5+6: the size of the range
+ */
+ ranges = lc_ranges;
+ rlen = orig_rlen;
+ while (ranges && (rlen -= np * sizeof(unsigned int)) >= 0) {
+ res = NULL;
+ size = ranges[na+4];
+ switch (ranges[0] >> 24) {
+ case 1: /* I/O space */
+ if (ranges[2] != 0)
+ break;
+ hose->io_base_phys = ranges[na+2];
+ /* limit I/O space to 16MB */
+ if (size > 0x01000000)
+ size = 0x01000000;
+ hose->io_base_virt = ioremap(ranges[na+2], size);
+ if (primary)
+ isa_io_base = (unsigned long) hose->io_base_virt;
+ res = &hose->io_resource;
+ res->flags = IORESOURCE_IO;
+ res->start = ranges[2];
+ break;
+ case 2: /* memory space */
+ memno = 0;
+ if (ranges[1] == 0 && ranges[2] == 0
+ && ranges[na+4] <= (16 << 20)) {
+ /* 1st 16MB, i.e. ISA memory area */
+ if (primary)
+ isa_mem_base = ranges[na+2];
+ memno = 1;
+ }
+ while (memno < 3 && hose->mem_resources[memno].flags)
+ ++memno;
+ if (memno == 0)
+ hose->pci_mem_offset = ranges[na+2] - ranges[2];
+ if (memno < 3) {
+ res = &hose->mem_resources[memno];
+ res->flags = IORESOURCE_MEM;
+ res->start = ranges[na+2];
+ }
+ break;
+ }
+ if (res != NULL) {
+ res->name = dev->full_name;
+ res->end = res->start + size - 1;
+ res->parent = NULL;
+ res->sibling = NULL;
+ res->child = NULL;
+ }
+ ranges += np;
+ }
+}
+
+/* We create the "pci-OF-bus-map" property now so it appears in the
+ * /proc device tree
+ */
+void __init
+pci_create_OF_bus_map(void)
+{
+ struct property* of_prop;
+
+ of_prop = (struct property*) alloc_bootmem(sizeof(struct property) + 256);
+ if (of_prop && find_path_device("/")) {
+ memset(of_prop, -1, sizeof(struct property) + 256);
+ of_prop->name = "pci-OF-bus-map";
+ of_prop->length = 256;
+ of_prop->value = (unsigned char *)&of_prop[1];
+ prom_add_property(find_path_device("/"), of_prop);
+ }
+}
+
+static ssize_t pci_show_devspec(struct device *dev, char *buf)
+{
+ struct pci_dev *pdev;
+ struct device_node *np;
+
+ pdev = to_pci_dev (dev);
+ np = pci_device_to_OF_node(pdev);
+ if (np == NULL || np->full_name == NULL)
+ return 0;
+ return sprintf(buf, "%s", np->full_name);
+}
+static DEVICE_ATTR(devspec, S_IRUGO, pci_show_devspec, NULL);
+
+#endif /* CONFIG_PPC_OF */
+
+/* Add sysfs properties */
+void pcibios_add_platform_entries(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PPC_OF
+ device_create_file(&pdev->dev, &dev_attr_devspec);
+#endif /* CONFIG_PPC_OF */
+}
+
+
+#ifdef CONFIG_PPC_PMAC
+/*
+ * This set of routines checks for PCI<->PCI bridges that have closed
+ * IO resources and have child devices. It tries to re-open an IO
+ * window on them.
+ *
+ * This is a _temporary_ fix to workaround a problem with Apple's OF
+ * closing IO windows on P2P bridges when the OF drivers of cards
+ * below this bridge don't claim any IO range (typically ATI or
+ * Adaptec).
+ *
+ * A more complete fix would be to use drivers/pci/setup-bus.c, which
+ * involves a working pcibios_fixup_pbus_ranges(), some more care about
+ * ordering when creating the host bus resources, and maybe a few more
+ * minor tweaks
+ */
+
+/* Initialize bridges with base/limit values we have collected */
+static void __init
+do_update_p2p_io_resource(struct pci_bus *bus, int enable_vga)
+{
+ struct pci_dev *bridge = bus->self;
+ struct pci_controller* hose = (struct pci_controller *)bridge->sysdata;
+ u32 l;
+ u16 w;
+ struct resource res;
+
+ if (bus->resource[0] == NULL)
+ return;
+ res = *(bus->resource[0]);
+
+ DBG("Remapping Bus %d, bridge: %s\n", bus->number, pci_name(bridge));
+ res.start -= ((unsigned long) hose->io_base_virt - isa_io_base);
+ res.end -= ((unsigned long) hose->io_base_virt - isa_io_base);
+ DBG(" IO window: %08lx-%08lx\n", res.start, res.end);
+
+ /* Set up the top and bottom of the PCI I/O segment for this bus. */
+ pci_read_config_dword(bridge, PCI_IO_BASE, &l);
+ l &= 0xffff000f;
+ l |= (res.start >> 8) & 0x00f0;
+ l |= res.end & 0xf000;
+ pci_write_config_dword(bridge, PCI_IO_BASE, l);
+
+ if ((l & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32) {
+ l = (res.start >> 16) | (res.end & 0xffff0000);
+ pci_write_config_dword(bridge, PCI_IO_BASE_UPPER16, l);
+ }
+
+ pci_read_config_word(bridge, PCI_COMMAND, &w);
+ w |= PCI_COMMAND_IO;
+ pci_write_config_word(bridge, PCI_COMMAND, w);
+
+#if 0 /* Enabling this causes XFree 4.2.0 to hang during PCI probe */
+ if (enable_vga) {
+ pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, &w);
+ w |= PCI_BRIDGE_CTL_VGA;
+ pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, w);
+ }
+#endif
+}
+
+/* This function is pretty basic and actually quite broken for the
+ * general case, it's enough for us right now though. It's supposed
+ * to tell us if we need to open an IO range at all or not and what
+ * size.
+ */
+static int __init
+check_for_io_childs(struct pci_bus *bus, struct resource* res, int *found_vga)
+{
+ struct pci_dev *dev;
+ int i;
+ int rc = 0;
+
+#define push_end(res, size) do { unsigned long __sz = (size) ; \
+ res->end = ((res->end + __sz) / (__sz + 1)) * (__sz + 1) + __sz; \
+ } while (0)
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ u16 class = dev->class >> 8;
+
+ if (class == PCI_CLASS_DISPLAY_VGA ||
+ class == PCI_CLASS_NOT_DEFINED_VGA)
+ *found_vga = 1;
+ if (class >> 8 == PCI_BASE_CLASS_BRIDGE && dev->subordinate)
+ rc |= check_for_io_childs(dev->subordinate, res, found_vga);
+ if (class == PCI_CLASS_BRIDGE_CARDBUS)
+ push_end(res, 0xfff);
+
+ for (i=0; i<PCI_NUM_RESOURCES; i++) {
+ struct resource *r;
+ unsigned long r_size;
+
+ if (dev->class >> 8 == PCI_CLASS_BRIDGE_PCI
+ && i >= PCI_BRIDGE_RESOURCES)
+ continue;
+ r = &dev->resource[i];
+ r_size = r->end - r->start;
+ if (r_size < 0xfff)
+ r_size = 0xfff;
+ if (r->flags & IORESOURCE_IO && (r_size) != 0) {
+ rc = 1;
+ push_end(res, r_size);
+ }
+ }
+ }
+
+ return rc;
+}
+
+/* Here we scan all P2P bridges of a given level that have a closed
+ * IO window. Note that the test for the presence of a VGA card should
+ * be improved to take into account already configured P2P bridges,
+ * currently, we don't see them and might end up configuring 2 bridges
+ * with VGA pass through enabled
+ */
+static void __init
+do_fixup_p2p_level(struct pci_bus *bus)
+{
+ struct pci_bus *b;
+ int i, parent_io;
+ int has_vga = 0;
+
+ for (parent_io=0; parent_io<4; parent_io++)
+ if (bus->resource[parent_io]
+ && bus->resource[parent_io]->flags & IORESOURCE_IO)
+ break;
+ if (parent_io >= 4)
+ return;
+
+ list_for_each_entry(b, &bus->children, node) {
+ struct pci_dev *d = b->self;
+ struct pci_controller* hose = (struct pci_controller *)d->sysdata;
+ struct resource *res = b->resource[0];
+ struct resource tmp_res;
+ unsigned long max;
+ int found_vga = 0;
+
+ memset(&tmp_res, 0, sizeof(tmp_res));
+ tmp_res.start = bus->resource[parent_io]->start;
+
+ /* We don't let low addresses go through that closed P2P bridge, well,
+ * that may not be necessary but I feel safer that way
+ */
+ if (tmp_res.start == 0)
+ tmp_res.start = 0x1000;
+
+ if (!list_empty(&b->devices) && res && res->flags == 0 &&
+ res != bus->resource[parent_io] &&
+ (d->class >> 8) == PCI_CLASS_BRIDGE_PCI &&
+ check_for_io_childs(b, &tmp_res, &found_vga)) {
+ u8 io_base_lo;
+
+ printk(KERN_INFO "Fixing up IO bus %s\n", b->name);
+
+ if (found_vga) {
+ if (has_vga) {
+ printk(KERN_WARNING "Skipping VGA, already active"
+ " on bus segment\n");
+ found_vga = 0;
+ } else
+ has_vga = 1;
+ }
+ pci_read_config_byte(d, PCI_IO_BASE, &io_base_lo);
+
+ if ((io_base_lo & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32)
+ max = ((unsigned long) hose->io_base_virt
+ - isa_io_base) + 0xffffffff;
+ else
+ max = ((unsigned long) hose->io_base_virt
+ - isa_io_base) + 0xffff;
+
+ *res = tmp_res;
+ res->flags = IORESOURCE_IO;
+ res->name = b->name;
+
+ /* Find a resource in the parent where we can allocate */
+ for (i = 0 ; i < 4; i++) {
+ struct resource *r = bus->resource[i];
+ if (!r)
+ continue;
+ if ((r->flags & IORESOURCE_IO) == 0)
+ continue;
+ DBG("Trying to allocate from %08lx, size %08lx from parent"
+ " res %d: %08lx -> %08lx\n",
+ res->start, res->end, i, r->start, r->end);
+
+ if (allocate_resource(r, res, res->end + 1, res->start, max,
+ res->end + 1, NULL, NULL) < 0) {
+ DBG("Failed !\n");
+ continue;
+ }
+ do_update_p2p_io_resource(b, found_vga);
+ break;
+ }
+ }
+ do_fixup_p2p_level(b);
+ }
+}
+
+static void
+pcibios_fixup_p2p_bridges(void)
+{
+ struct pci_bus *b;
+
+ list_for_each_entry(b, &pci_root_buses, node)
+ do_fixup_p2p_level(b);
+}
+
+#endif /* CONFIG_PPC_PMAC */
+
+static int __init
+pcibios_init(void)
+{
+ struct pci_controller *hose;
+ struct pci_bus *bus;
+ int next_busno;
+
+ printk(KERN_INFO "PCI: Probing PCI hardware\n");
+
+ /* Scan all of the recorded PCI controllers. */
+ for (next_busno = 0, hose = hose_head; hose; hose = hose->next) {
+ if (pci_assign_all_busses)
+ hose->first_busno = next_busno;
+ hose->last_busno = 0xff;
+ bus = pci_scan_bus(hose->first_busno, hose->ops, hose);
+ hose->last_busno = bus->subordinate;
+ if (pci_assign_all_busses || next_busno <= hose->last_busno)
+ next_busno = hose->last_busno + pcibios_assign_bus_offset;
+ }
+ pci_bus_count = next_busno;
+
+ /* OpenFirmware based machines need a map of OF bus
+ * numbers vs. kernel bus numbers since we may have to
+ * remap them.
+ */
+ if (pci_assign_all_busses && have_of)
+ pcibios_make_OF_bus_map();
+
+ /* Do machine dependent PCI interrupt routing */
+ if (ppc_md.pci_swizzle && ppc_md.pci_map_irq)
+ pci_fixup_irqs(ppc_md.pci_swizzle, ppc_md.pci_map_irq);
+
+ /* Call machine dependent fixup */
+ if (ppc_md.pcibios_fixup)
+ ppc_md.pcibios_fixup();
+
+ /* Allocate and assign resources */
+ pcibios_allocate_bus_resources(&pci_root_buses);
+ pcibios_allocate_resources(0);
+ pcibios_allocate_resources(1);
+#ifdef CONFIG_PPC_PMAC
+ pcibios_fixup_p2p_bridges();
+#endif /* CONFIG_PPC_PMAC */
+ pcibios_assign_resources();
+
+ /* Call machine dependent post-init code */
+ if (ppc_md.pcibios_after_init)
+ ppc_md.pcibios_after_init();
+
+ return 0;
+}
+
+subsys_initcall(pcibios_init);
+
+unsigned char __init
+common_swizzle(struct pci_dev *dev, unsigned char *pinp)
+{
+ struct pci_controller *hose = dev->sysdata;
+
+ if (dev->bus->number != hose->first_busno) {
+ u8 pin = *pinp;
+ do {
+ pin = bridge_swizzle(pin, PCI_SLOT(dev->devfn));
+ /* Move up the chain of bridges. */
+ dev = dev->bus->self;
+ } while (dev->bus->self);
+ *pinp = pin;
+
+ /* The slot is the idsel of the last bridge. */
+ }
+ return PCI_SLOT(dev->devfn);
+}
+
+unsigned long resource_fixup(struct pci_dev * dev, struct resource * res,
+ unsigned long start, unsigned long size)
+{
+ return start;
+}
+
+void __init pcibios_fixup_bus(struct pci_bus *bus)
+{
+ struct pci_controller *hose = (struct pci_controller *) bus->sysdata;
+ unsigned long io_offset;
+ struct resource *res;
+ int i;
+
+ io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
+ if (bus->parent == NULL) {
+ /* This is a host bridge - fill in its resources */
+ hose->bus = bus;
+
+ bus->resource[0] = res = &hose->io_resource;
+ if (!res->flags) {
+ if (io_offset)
+ printk(KERN_ERR "I/O resource not set for host"
+ " bridge %d\n", hose->index);
+ res->start = 0;
+ res->end = IO_SPACE_LIMIT;
+ res->flags = IORESOURCE_IO;
+ }
+ res->start += io_offset;
+ res->end += io_offset;
+
+ for (i = 0; i < 3; ++i) {
+ res = &hose->mem_resources[i];
+ if (!res->flags) {
+ if (i > 0)
+ continue;
+ printk(KERN_ERR "Memory resource not set for "
+ "host bridge %d\n", hose->index);
+ res->start = hose->pci_mem_offset;
+ res->end = ~0U;
+ res->flags = IORESOURCE_MEM;
+ }
+ bus->resource[i+1] = res;
+ }
+ } else {
+ /* This is a subordinate bridge */
+ pci_read_bridge_bases(bus);
+
+ for (i = 0; i < 4; ++i) {
+ if ((res = bus->resource[i]) == NULL)
+ continue;
+ if (!res->flags)
+ continue;
+ if (io_offset && (res->flags & IORESOURCE_IO)) {
+ res->start += io_offset;
+ res->end += io_offset;
+ } else if (hose->pci_mem_offset
+ && (res->flags & IORESOURCE_MEM)) {
+ res->start += hose->pci_mem_offset;
+ res->end += hose->pci_mem_offset;
+ }
+ }
+ }
+
+ if (ppc_md.pcibios_fixup_bus)
+ ppc_md.pcibios_fixup_bus(bus);
+}
+
+char __init *pcibios_setup(char *str)
+{
+ return str;
+}
+
+/* the next one is stolen from the alpha port... */
+void __init
+pcibios_update_irq(struct pci_dev *dev, int irq)
+{
+ pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
+ /* XXX FIXME - update OF device tree node interrupt property */
+}
+
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+ u16 cmd, old_cmd;
+ int idx;
+ struct resource *r;
+
+ if (ppc_md.pcibios_enable_device_hook)
+ if (ppc_md.pcibios_enable_device_hook(dev, 0))
+ return -EINVAL;
+
+ pci_read_config_word(dev, PCI_COMMAND, &cmd);
+ old_cmd = cmd;
+ for (idx=0; idx<6; idx++) {
+ r = &dev->resource[idx];
+ if (r->flags & IORESOURCE_UNSET) {
+ printk(KERN_ERR "PCI: Device %s not available because of resource collisions\n", pci_name(dev));
+ return -EINVAL;
+ }
+ if (r->flags & IORESOURCE_IO)
+ cmd |= PCI_COMMAND_IO;
+ if (r->flags & IORESOURCE_MEM)
+ cmd |= PCI_COMMAND_MEMORY;
+ }
+ if (cmd != old_cmd) {
+ printk("PCI: Enabling device %s (%04x -> %04x)\n",
+ pci_name(dev), old_cmd, cmd);
+ pci_write_config_word(dev, PCI_COMMAND, cmd);
+ }
+ return 0;
+}
+
+struct pci_controller*
+pci_bus_to_hose(int bus)
+{
+ struct pci_controller* hose = hose_head;
+
+ for (; hose; hose = hose->next)
+ if (bus >= hose->first_busno && bus <= hose->last_busno)
+ return hose;
+ return NULL;
+}
+
+void*
+pci_bus_io_base(unsigned int bus)
+{
+ struct pci_controller *hose;
+
+ hose = pci_bus_to_hose(bus);
+ if (!hose)
+ return NULL;
+ return hose->io_base_virt;
+}
+
+unsigned long
+pci_bus_io_base_phys(unsigned int bus)
+{
+ struct pci_controller *hose;
+
+ hose = pci_bus_to_hose(bus);
+ if (!hose)
+ return 0;
+ return hose->io_base_phys;
+}
+
+unsigned long
+pci_bus_mem_base_phys(unsigned int bus)
+{
+ struct pci_controller *hose;
+
+ hose = pci_bus_to_hose(bus);
+ if (!hose)
+ return 0;
+ return hose->pci_mem_offset;
+}
+
+unsigned long
+pci_resource_to_bus(struct pci_dev *pdev, struct resource *res)
+{
+ /* Hack alert again ! See comments in chrp_pci.c
+ */
+ struct pci_controller* hose =
+ (struct pci_controller *)pdev->sysdata;
+ if (hose && res->flags & IORESOURCE_MEM)
+ return res->start - hose->pci_mem_offset;
+ /* We may want to do something with IOs here... */
+ return res->start;
+}
+
+
+static struct resource *__pci_mmap_make_offset(struct pci_dev *dev,
+ unsigned long *offset,
+ enum pci_mmap_state mmap_state)
+{
+ struct pci_controller *hose = pci_bus_to_hose(dev->bus->number);
+ unsigned long io_offset = 0;
+ int i, res_bit;
+
+ if (hose == 0)
+ return NULL; /* should never happen */
+
+ /* If memory, add on the PCI bridge address offset */
+ if (mmap_state == pci_mmap_mem) {
+ *offset += hose->pci_mem_offset;
+ res_bit = IORESOURCE_MEM;
+ } else {
+ io_offset = (unsigned long)hose->io_base_virt;
+ *offset += io_offset;
+ res_bit = IORESOURCE_IO;
+ }
+
+ /*
+ * Check that the offset requested corresponds to one of the
+ * resources of the device.
+ */
+ for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+ struct resource *rp = &dev->resource[i];
+ int flags = rp->flags;
+
+ /* treat ROM as memory (should be already) */
+ if (i == PCI_ROM_RESOURCE)
+ flags |= IORESOURCE_MEM;
+
+ /* Active and same type? */
+ if ((flags & res_bit) == 0)
+ continue;
+
+ /* In the range of this resource? */
+ if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end)
+ continue;
+
+ /* found it! construct the final physical address */
+ if (mmap_state == pci_mmap_io)
+ *offset += hose->io_base_phys - _IO_BASE;
+ return rp;
+ }
+
+ return NULL;
+}
+
+/*
+ * Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
+ * device mapping.
+ */
+static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
+ pgprot_t protection,
+ enum pci_mmap_state mmap_state,
+ int write_combine)
+{
+ unsigned long prot = pgprot_val(protection);
+
+ /* Write combine is always 0 on non-memory space mappings. On
+ * memory space, if the user didn't pass 1, we check for a
+ * "prefetchable" resource. This is a bit hackish, but we use
+ * this to workaround the inability of /sysfs to provide a write
+ * combine bit
+ */
+ if (mmap_state != pci_mmap_mem)
+ write_combine = 0;
+ else if (write_combine == 0) {
+ if (rp->flags & IORESOURCE_PREFETCH)
+ write_combine = 1;
+ }
+
+ /* XXX would be nice to have a way to ask for write-through */
+ prot |= _PAGE_NO_CACHE;
+ if (write_combine)
+ prot &= ~_PAGE_GUARDED;
+ else
+ prot |= _PAGE_GUARDED;
+
+ printk("PCI map for %s:%lx, prot: %lx\n", pci_name(dev), rp->start,
+ prot);
+
+ return __pgprot(prot);
+}
+
+/*
+ * This one is used by /dev/mem and fbdev who have no clue about the
+ * PCI device, it tries to find the PCI device first and calls the
+ * above routine
+ */
+pgprot_t pci_phys_mem_access_prot(struct file *file,
+ unsigned long offset,
+ unsigned long size,
+ pgprot_t protection)
+{
+ struct pci_dev *pdev = NULL;
+ struct resource *found = NULL;
+ unsigned long prot = pgprot_val(protection);
+ int i;
+
+ if (page_is_ram(offset >> PAGE_SHIFT))
+ return prot;
+
+ prot |= _PAGE_NO_CACHE | _PAGE_GUARDED;
+
+ for_each_pci_dev(pdev) {
+ for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+ struct resource *rp = &pdev->resource[i];
+ int flags = rp->flags;
+
+ /* Active and same type? */
+ if ((flags & IORESOURCE_MEM) == 0)
+ continue;
+ /* In the range of this resource? */
+ if (offset < (rp->start & PAGE_MASK) ||
+ offset > rp->end)
+ continue;
+ found = rp;
+ break;
+ }
+ if (found)
+ break;
+ }
+ if (found) {
+ if (found->flags & IORESOURCE_PREFETCH)
+ prot &= ~_PAGE_GUARDED;
+ pci_dev_put(pdev);
+ }
+
+ DBG("non-PCI map for %lx, prot: %lx\n", offset, prot);
+
+ return __pgprot(prot);
+}
+
+
+/*
+ * Perform the actual remap of the pages for a PCI device mapping, as
+ * appropriate for this architecture. The region in the process to map
+ * is described by vm_start and vm_end members of VMA, the base physical
+ * address is found in vm_pgoff.
+ * The pci device structure is provided so that architectures may make mapping
+ * decisions on a per-device or per-bus basis.
+ *
+ * Returns a negative error code on failure, zero on success.
+ */
+int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+ enum pci_mmap_state mmap_state,
+ int write_combine)
+{
+ unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+ struct resource *rp;
+ int ret;
+
+ rp = __pci_mmap_make_offset(dev, &offset, mmap_state);
+ if (rp == NULL)
+ return -EINVAL;
+
+ vma->vm_pgoff = offset >> PAGE_SHIFT;
+ vma->vm_flags |= VM_SHM | VM_LOCKED | VM_IO;
+ vma->vm_page_prot = __pci_mmap_set_pgprot(dev, rp,
+ vma->vm_page_prot,
+ mmap_state, write_combine);
+
+ ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+ vma->vm_end - vma->vm_start, vma->vm_page_prot);
+
+ return ret;
+}
+
+/* Obsolete functions. Should be removed once the symbios driver
+ * is fixed
+ */
+unsigned long
+phys_to_bus(unsigned long pa)
+{
+ struct pci_controller *hose;
+ int i;
+
+ for (hose = hose_head; hose; hose = hose->next) {
+ for (i = 0; i < 3; ++i) {
+ if (pa >= hose->mem_resources[i].start
+ && pa <= hose->mem_resources[i].end) {
+ /*
+ * XXX the hose->pci_mem_offset really
+ * only applies to mem_resources[0].
+ * We need a way to store an offset for
+ * the others. -- paulus
+ */
+ if (i == 0)
+ pa -= hose->pci_mem_offset;
+ return pa;
+ }
+ }
+ }
+ /* hmmm, didn't find it */
+ return 0;
+}
+
+unsigned long
+pci_phys_to_bus(unsigned long pa, int busnr)
+{
+ struct pci_controller* hose = pci_bus_to_hose(busnr);
+ if (!hose)
+ return pa;
+ return pa - hose->pci_mem_offset;
+}
+
+unsigned long
+pci_bus_to_phys(unsigned int ba, int busnr)
+{
+ struct pci_controller* hose = pci_bus_to_hose(busnr);
+ if (!hose)
+ return ba;
+ return ba + hose->pci_mem_offset;
+}
+
+/* Provide information on locations of various I/O regions in physical
+ * memory. Do this on a per-card basis so that we choose the right
+ * root bridge.
+ * Note that the returned IO or memory base is a physical address
+ */
+
+long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn)
+{
+ struct pci_controller* hose;
+ long result = -EOPNOTSUPP;
+
+ /* Argh ! Please forgive me for that hack, but that's the
+ * simplest way to get existing XFree to not lockup on some
+ * G5 machines... So when something asks for bus 0 io base
+ * (bus 0 is HT root), we return the AGP one instead.
+ */
+#ifdef CONFIG_PPC_PMAC
+ if (_machine == _MACH_Pmac && machine_is_compatible("MacRISC4"))
+ if (bus == 0)
+ bus = 0xf0;
+#endif /* CONFIG_PPC_PMAC */
+
+ hose = pci_bus_to_hose(bus);
+ if (!hose)
+ return -ENODEV;
+
+ switch (which) {
+ case IOBASE_BRIDGE_NUMBER:
+ return (long)hose->first_busno;
+ case IOBASE_MEMORY:
+ return (long)hose->pci_mem_offset;
+ case IOBASE_IO:
+ return (long)hose->io_base_phys;
+ case IOBASE_ISA_IO:
+ return (long)isa_io_base;
+ case IOBASE_ISA_MEM:
+ return (long)isa_mem_base;
+ }
+
+ return result;
+}
+
+void __init
+pci_init_resource(struct resource *res, unsigned long start, unsigned long end,
+ int flags, char *name)
+{
+ res->start = start;
+ res->end = end;
+ res->flags = flags;
+ res->name = name;
+ res->parent = NULL;
+ res->sibling = NULL;
+ res->child = NULL;
+}
+
+void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max)
+{
+ unsigned long start = pci_resource_start(dev, bar);
+ unsigned long len = pci_resource_len(dev, bar);
+ unsigned long flags = pci_resource_flags(dev, bar);
+
+ if (!len)
+ return NULL;
+ if (max && len > max)
+ len = max;
+ if (flags & IORESOURCE_IO)
+ return ioport_map(start, len);
+ if (flags & IORESOURCE_MEM)
+ /* Not checking IORESOURCE_CACHEABLE because PPC does
+ * not currently distinguish between ioremap and
+ * ioremap_nocache.
+ */
+ return ioremap(start, len);
+ /* What? */
+ return NULL;
+}
+
+void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
+{
+ /* Nothing to do */
+}
+EXPORT_SYMBOL(pci_iomap);
+EXPORT_SYMBOL(pci_iounmap);
+
+
+/*
+ * Null PCI config access functions, for the case when we can't
+ * find a hose.
+ */
+#define NULL_PCI_OP(rw, size, type) \
+static int \
+null_##rw##_config_##size(struct pci_dev *dev, int offset, type val) \
+{ \
+ return PCIBIOS_DEVICE_NOT_FOUND; \
+}
+
+static int
+null_read_config(struct pci_bus *bus, unsigned int devfn, int offset,
+ int len, u32 *val)
+{
+ return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
+static int
+null_write_config(struct pci_bus *bus, unsigned int devfn, int offset,
+ int len, u32 val)
+{
+ return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
+static struct pci_ops null_pci_ops =
+{
+ null_read_config,
+ null_write_config
+};
+
+/*
+ * These functions are used early on before PCI scanning is done
+ * and all of the pci_dev and pci_bus structures have been created.
+ */
+static struct pci_bus *
+fake_pci_bus(struct pci_controller *hose, int busnr)
+{
+ static struct pci_bus bus;
+
+ if (hose == 0) {
+ hose = pci_bus_to_hose(busnr);
+ if (hose == 0)
+ printk(KERN_ERR "Can't find hose for PCI bus %d!\n", busnr);
+ }
+ bus.number = busnr;
+ bus.sysdata = hose;
+ bus.ops = hose? hose->ops: &null_pci_ops;
+ return &bus;
+}
+
+#define EARLY_PCI_OP(rw, size, type) \
+int early_##rw##_config_##size(struct pci_controller *hose, int bus, \
+ int devfn, int offset, type value) \
+{ \
+ return pci_bus_##rw##_config_##size(fake_pci_bus(hose, bus), \
+ devfn, offset, value); \
+}
+
+EARLY_PCI_OP(read, byte, u8 *)
+EARLY_PCI_OP(read, word, u16 *)
+EARLY_PCI_OP(read, dword, u32 *)
+EARLY_PCI_OP(write, byte, u8)
+EARLY_PCI_OP(write, word, u16)
+EARLY_PCI_OP(write, dword, u32)
diff --git a/arch/ppc/kernel/perfmon.c b/arch/ppc/kernel/perfmon.c
new file mode 100644
index 000000000000..918f6b252e45
--- /dev/null
+++ b/arch/ppc/kernel/perfmon.c
@@ -0,0 +1,93 @@
+/* kernel/perfmon.c
+ * PPC 32 Performance Monitor Infrastructure
+ *
+ * Author: Andy Fleming
+ * Copyright (c) 2004 Freescale Semiconductor, Inc
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/prctl.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/reg.h>
+#include <asm/xmon.h>
+
+/* A lock to regulate grabbing the interrupt */
+DEFINE_SPINLOCK(perfmon_lock);
+
+#ifdef CONFIG_FSL_BOOKE
+static void dummy_perf(struct pt_regs *regs)
+{
+ unsigned int pmgc0 = mfpmr(PMRN_PMGC0);
+
+ pmgc0 &= ~PMGC0_PMIE;
+ mtpmr(PMRN_PMGC0, pmgc0);
+}
+
+#else
+/* Ensure exceptions are disabled */
+
+static void dummy_perf(struct pt_regs *regs)
+{
+ unsigned int mmcr0 = mfspr(SPRN_MMCR0);
+
+ mmcr0 &= ~MMCR0_PMXE;
+ mtspr(SPRN_MMCR0, mmcr0);
+}
+#endif
+
+void (*perf_irq)(struct pt_regs *) = dummy_perf;
+
+/* Grab the interrupt, if it's free.
+ * Returns 0 on success, -1 if the interrupt is taken already */
+int request_perfmon_irq(void (*handler)(struct pt_regs *))
+{
+ int err = 0;
+
+ spin_lock(&perfmon_lock);
+
+ if (perf_irq == dummy_perf)
+ perf_irq = handler;
+ else {
+ pr_info("perfmon irq already handled by %p\n", perf_irq);
+ err = -1;
+ }
+
+ spin_unlock(&perfmon_lock);
+
+ return err;
+}
+
+void free_perfmon_irq(void)
+{
+ spin_lock(&perfmon_lock);
+
+ perf_irq = dummy_perf;
+
+ spin_unlock(&perfmon_lock);
+}
+
+EXPORT_SYMBOL(perf_irq);
+EXPORT_SYMBOL(request_perfmon_irq);
+EXPORT_SYMBOL(free_perfmon_irq);
diff --git a/arch/ppc/kernel/perfmon_fsl_booke.c b/arch/ppc/kernel/perfmon_fsl_booke.c
new file mode 100644
index 000000000000..03526bfb0840
--- /dev/null
+++ b/arch/ppc/kernel/perfmon_fsl_booke.c
@@ -0,0 +1,222 @@
+/* kernel/perfmon_fsl_booke.c
+ * Freescale Book-E Performance Monitor code
+ *
+ * Author: Andy Fleming
+ * Copyright (c) 2004 Freescale Semiconductor, Inc
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/prctl.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/reg.h>
+#include <asm/xmon.h>
+#include <asm/perfmon.h>
+
+static inline u32 get_pmlca(int ctr);
+static inline void set_pmlca(int ctr, u32 pmlca);
+
+static inline u32 get_pmlca(int ctr)
+{
+ u32 pmlca;
+
+ switch (ctr) {
+ case 0:
+ pmlca = mfpmr(PMRN_PMLCA0);
+ break;
+ case 1:
+ pmlca = mfpmr(PMRN_PMLCA1);
+ break;
+ case 2:
+ pmlca = mfpmr(PMRN_PMLCA2);
+ break;
+ case 3:
+ pmlca = mfpmr(PMRN_PMLCA3);
+ break;
+ default:
+ panic("Bad ctr number\n");
+ }
+
+ return pmlca;
+}
+
+static inline void set_pmlca(int ctr, u32 pmlca)
+{
+ switch (ctr) {
+ case 0:
+ mtpmr(PMRN_PMLCA0, pmlca);
+ break;
+ case 1:
+ mtpmr(PMRN_PMLCA1, pmlca);
+ break;
+ case 2:
+ mtpmr(PMRN_PMLCA2, pmlca);
+ break;
+ case 3:
+ mtpmr(PMRN_PMLCA3, pmlca);
+ break;
+ default:
+ panic("Bad ctr number\n");
+ }
+}
+
+void init_pmc_stop(int ctr)
+{
+ u32 pmlca = (PMLCA_FC | PMLCA_FCS | PMLCA_FCU |
+ PMLCA_FCM1 | PMLCA_FCM0);
+ u32 pmlcb = 0;
+
+ switch (ctr) {
+ case 0:
+ mtpmr(PMRN_PMLCA0, pmlca);
+ mtpmr(PMRN_PMLCB0, pmlcb);
+ break;
+ case 1:
+ mtpmr(PMRN_PMLCA1, pmlca);
+ mtpmr(PMRN_PMLCB1, pmlcb);
+ break;
+ case 2:
+ mtpmr(PMRN_PMLCA2, pmlca);
+ mtpmr(PMRN_PMLCB2, pmlcb);
+ break;
+ case 3:
+ mtpmr(PMRN_PMLCA3, pmlca);
+ mtpmr(PMRN_PMLCB3, pmlcb);
+ break;
+ default:
+ panic("Bad ctr number!\n");
+ }
+}
+
+void set_pmc_event(int ctr, int event)
+{
+ u32 pmlca;
+
+ pmlca = get_pmlca(ctr);
+
+ pmlca = (pmlca & ~PMLCA_EVENT_MASK) |
+ ((event << PMLCA_EVENT_SHIFT) &
+ PMLCA_EVENT_MASK);
+
+ set_pmlca(ctr, pmlca);
+}
+
+void set_pmc_user_kernel(int ctr, int user, int kernel)
+{
+ u32 pmlca;
+
+ pmlca = get_pmlca(ctr);
+
+ if(user)
+ pmlca &= ~PMLCA_FCU;
+ else
+ pmlca |= PMLCA_FCU;
+
+ if(kernel)
+ pmlca &= ~PMLCA_FCS;
+ else
+ pmlca |= PMLCA_FCS;
+
+ set_pmlca(ctr, pmlca);
+}
+
+void set_pmc_marked(int ctr, int mark0, int mark1)
+{
+ u32 pmlca = get_pmlca(ctr);
+
+ if(mark0)
+ pmlca &= ~PMLCA_FCM0;
+ else
+ pmlca |= PMLCA_FCM0;
+
+ if(mark1)
+ pmlca &= ~PMLCA_FCM1;
+ else
+ pmlca |= PMLCA_FCM1;
+
+ set_pmlca(ctr, pmlca);
+}
+
+void pmc_start_ctr(int ctr, int enable)
+{
+ u32 pmlca = get_pmlca(ctr);
+
+ pmlca &= ~PMLCA_FC;
+
+ if (enable)
+ pmlca |= PMLCA_CE;
+ else
+ pmlca &= ~PMLCA_CE;
+
+ set_pmlca(ctr, pmlca);
+}
+
+void pmc_start_ctrs(int enable)
+{
+ u32 pmgc0 = mfpmr(PMRN_PMGC0);
+
+ pmgc0 &= ~PMGC0_FAC;
+ pmgc0 |= PMGC0_FCECE;
+
+ if (enable)
+ pmgc0 |= PMGC0_PMIE;
+ else
+ pmgc0 &= ~PMGC0_PMIE;
+
+ mtpmr(PMRN_PMGC0, pmgc0);
+}
+
+void pmc_stop_ctrs(void)
+{
+ u32 pmgc0 = mfpmr(PMRN_PMGC0);
+
+ pmgc0 |= PMGC0_FAC;
+
+ pmgc0 &= ~(PMGC0_PMIE | PMGC0_FCECE);
+
+ mtpmr(PMRN_PMGC0, pmgc0);
+}
+
+void dump_pmcs(void)
+{
+ printk("pmgc0: %x\n", mfpmr(PMRN_PMGC0));
+ printk("pmc\t\tpmlca\t\tpmlcb\n");
+ printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC0),
+ mfpmr(PMRN_PMLCA0), mfpmr(PMRN_PMLCB0));
+ printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC1),
+ mfpmr(PMRN_PMLCA1), mfpmr(PMRN_PMLCB1));
+ printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC2),
+ mfpmr(PMRN_PMLCA2), mfpmr(PMRN_PMLCB2));
+ printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC3),
+ mfpmr(PMRN_PMLCA3), mfpmr(PMRN_PMLCB3));
+}
+
+EXPORT_SYMBOL(init_pmc_stop);
+EXPORT_SYMBOL(set_pmc_event);
+EXPORT_SYMBOL(set_pmc_user_kernel);
+EXPORT_SYMBOL(set_pmc_marked);
+EXPORT_SYMBOL(pmc_start_ctr);
+EXPORT_SYMBOL(pmc_start_ctrs);
+EXPORT_SYMBOL(pmc_stop_ctrs);
+EXPORT_SYMBOL(dump_pmcs);
diff --git a/arch/ppc/kernel/ppc-stub.c b/arch/ppc/kernel/ppc-stub.c
new file mode 100644
index 000000000000..d61889c24046
--- /dev/null
+++ b/arch/ppc/kernel/ppc-stub.c
@@ -0,0 +1,867 @@
+/*
+ * ppc-stub.c: KGDB support for the Linux kernel.
+ *
+ * adapted from arch/sparc/kernel/sparc-stub.c for the PowerPC
+ * some stuff borrowed from Paul Mackerras' xmon
+ * Copyright (C) 1998 Michael AK Tesch (tesch@cs.wisc.edu)
+ *
+ * Modifications to run under Linux
+ * Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
+ *
+ * This file originally came from the gdb sources, and the
+ * copyright notices have been retained below.
+ */
+
+/****************************************************************************
+
+ THIS SOFTWARE IS NOT COPYRIGHTED
+
+ HP offers the following for use in the public domain. HP makes no
+ warranty with regard to the software or its performance and the
+ user accepts the software "AS IS" with all faults.
+
+ HP DISCLAIMS ANY WARRANTIES, EXPRESS OR IMPLIED, WITH REGARD
+ TO THIS SOFTWARE INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+
+****************************************************************************/
+
+/****************************************************************************
+ * Header: remcom.c,v 1.34 91/03/09 12:29:49 glenne Exp $
+ *
+ * Module name: remcom.c $
+ * Revision: 1.34 $
+ * Date: 91/03/09 12:29:49 $
+ * Contributor: Lake Stevens Instrument Division$
+ *
+ * Description: low level support for gdb debugger. $
+ *
+ * Considerations: only works on target hardware $
+ *
+ * Written by: Glenn Engel $
+ * ModuleState: Experimental $
+ *
+ * NOTES: See Below $
+ *
+ * Modified for SPARC by Stu Grossman, Cygnus Support.
+ *
+ * This code has been extensively tested on the Fujitsu SPARClite demo board.
+ *
+ * To enable debugger support, two things need to happen. One, a
+ * call to set_debug_traps() is necessary in order to allow any breakpoints
+ * or error conditions to be properly intercepted and reported to gdb.
+ * Two, a breakpoint needs to be generated to begin communication. This
+ * is most easily accomplished by a call to breakpoint(). Breakpoint()
+ * simulates a breakpoint by executing a trap #1.
+ *
+ *************
+ *
+ * The following gdb commands are supported:
+ *
+ * command function Return value
+ *
+ * g return the value of the CPU registers hex data or ENN
+ * G set the value of the CPU registers OK or ENN
+ * qOffsets Get section offsets. Reply is Text=xxx;Data=yyy;Bss=zzz
+ *
+ * mAA..AA,LLLL Read LLLL bytes at address AA..AA hex data or ENN
+ * MAA..AA,LLLL: Write LLLL bytes at address AA.AA OK or ENN
+ *
+ * c Resume at current address SNN ( signal NN)
+ * cAA..AA Continue at address AA..AA SNN
+ *
+ * s Step one instruction SNN
+ * sAA..AA Step one instruction from AA..AA SNN
+ *
+ * k kill
+ *
+ * ? What was the last sigval ? SNN (signal NN)
+ *
+ * bBB..BB Set baud rate to BB..BB OK or BNN, then sets
+ * baud rate
+ *
+ * All commands and responses are sent with a packet which includes a
+ * checksum. A packet consists of
+ *
+ * $<packet info>#<checksum>.
+ *
+ * where
+ * <packet info> :: <characters representing the command or response>
+ * <checksum> :: <two hex digits computed as modulo 256 sum of <packetinfo>>
+ *
+ * When a packet is received, it is first acknowledged with either '+' or '-'.
+ * '+' indicates a successful transfer. '-' indicates a failed transfer.
+ *
+ * Example:
+ *
+ * Host: Reply:
+ * $m0,10#2a +$00010203040506070809101112131415#42
+ *
+ ****************************************************************************/
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/sysrq.h>
+
+#include <asm/cacheflush.h>
+#include <asm/system.h>
+#include <asm/signal.h>
+#include <asm/kgdb.h>
+#include <asm/pgtable.h>
+#include <asm/ptrace.h>
+
+void breakinst(void);
+
+/*
+ * BUFMAX defines the maximum number of characters in inbound/outbound buffers
+ * at least NUMREGBYTES*2 are needed for register packets
+ */
+#define BUFMAX 2048
+static char remcomInBuffer[BUFMAX];
+static char remcomOutBuffer[BUFMAX];
+
+static int initialized;
+static int kgdb_active;
+static int kgdb_started;
+static u_int fault_jmp_buf[100];
+static int kdebug;
+
+
+static const char hexchars[]="0123456789abcdef";
+
+/* Place where we save old trap entries for restoration - sparc*/
+/* struct tt_entry kgdb_savettable[256]; */
+/* typedef void (*trapfunc_t)(void); */
+
+static void kgdb_fault_handler(struct pt_regs *regs);
+static int handle_exception (struct pt_regs *regs);
+
+#if 0
+/* Install an exception handler for kgdb */
+static void exceptionHandler(int tnum, unsigned int *tfunc)
+{
+ /* We are dorking with a live trap table, all irqs off */
+}
+#endif
+
+int
+kgdb_setjmp(long *buf)
+{
+ asm ("mflr 0; stw 0,0(%0);"
+ "stw 1,4(%0); stw 2,8(%0);"
+ "mfcr 0; stw 0,12(%0);"
+ "stmw 13,16(%0)"
+ : : "r" (buf));
+ /* XXX should save fp regs as well */
+ return 0;
+}
+void
+kgdb_longjmp(long *buf, int val)
+{
+ if (val == 0)
+ val = 1;
+ asm ("lmw 13,16(%0);"
+ "lwz 0,12(%0); mtcrf 0x38,0;"
+ "lwz 0,0(%0); lwz 1,4(%0); lwz 2,8(%0);"
+ "mtlr 0; mr 3,%1"
+ : : "r" (buf), "r" (val));
+}
+/* Convert ch from a hex digit to an int */
+static int
+hex(unsigned char ch)
+{
+ if (ch >= 'a' && ch <= 'f')
+ return ch-'a'+10;
+ if (ch >= '0' && ch <= '9')
+ return ch-'0';
+ if (ch >= 'A' && ch <= 'F')
+ return ch-'A'+10;
+ return -1;
+}
+
+/* Convert the memory pointed to by mem into hex, placing result in buf.
+ * Return a pointer to the last char put in buf (null), in case of mem fault,
+ * return 0.
+ */
+static unsigned char *
+mem2hex(const char *mem, char *buf, int count)
+{
+ unsigned char ch;
+ unsigned short tmp_s;
+ unsigned long tmp_l;
+
+ if (kgdb_setjmp((long*)fault_jmp_buf) == 0) {
+ debugger_fault_handler = kgdb_fault_handler;
+
+ /* Accessing 16 bit and 32 bit objects in a single
+ ** load instruction is required to avoid bad side
+ ** effects for some IO registers.
+ */
+
+ if ((count == 2) && (((long)mem & 1) == 0)) {
+ tmp_s = *(unsigned short *)mem;
+ mem += 2;
+ *buf++ = hexchars[(tmp_s >> 12) & 0xf];
+ *buf++ = hexchars[(tmp_s >> 8) & 0xf];
+ *buf++ = hexchars[(tmp_s >> 4) & 0xf];
+ *buf++ = hexchars[tmp_s & 0xf];
+
+ } else if ((count == 4) && (((long)mem & 3) == 0)) {
+ tmp_l = *(unsigned int *)mem;
+ mem += 4;
+ *buf++ = hexchars[(tmp_l >> 28) & 0xf];
+ *buf++ = hexchars[(tmp_l >> 24) & 0xf];
+ *buf++ = hexchars[(tmp_l >> 20) & 0xf];
+ *buf++ = hexchars[(tmp_l >> 16) & 0xf];
+ *buf++ = hexchars[(tmp_l >> 12) & 0xf];
+ *buf++ = hexchars[(tmp_l >> 8) & 0xf];
+ *buf++ = hexchars[(tmp_l >> 4) & 0xf];
+ *buf++ = hexchars[tmp_l & 0xf];
+
+ } else {
+ while (count-- > 0) {
+ ch = *mem++;
+ *buf++ = hexchars[ch >> 4];
+ *buf++ = hexchars[ch & 0xf];
+ }
+ }
+
+ } else {
+ /* error condition */
+ }
+ debugger_fault_handler = NULL;
+ *buf = 0;
+ return buf;
+}
+
+/* convert the hex array pointed to by buf into binary to be placed in mem
+ * return a pointer to the character AFTER the last byte written.
+*/
+static char *
+hex2mem(char *buf, char *mem, int count)
+{
+ unsigned char ch;
+ int i;
+ char *orig_mem;
+ unsigned short tmp_s;
+ unsigned long tmp_l;
+
+ orig_mem = mem;
+
+ if (kgdb_setjmp((long*)fault_jmp_buf) == 0) {
+ debugger_fault_handler = kgdb_fault_handler;
+
+ /* Accessing 16 bit and 32 bit objects in a single
+ ** store instruction is required to avoid bad side
+ ** effects for some IO registers.
+ */
+
+ if ((count == 2) && (((long)mem & 1) == 0)) {
+ tmp_s = hex(*buf++) << 12;
+ tmp_s |= hex(*buf++) << 8;
+ tmp_s |= hex(*buf++) << 4;
+ tmp_s |= hex(*buf++);
+
+ *(unsigned short *)mem = tmp_s;
+ mem += 2;
+
+ } else if ((count == 4) && (((long)mem & 3) == 0)) {
+ tmp_l = hex(*buf++) << 28;
+ tmp_l |= hex(*buf++) << 24;
+ tmp_l |= hex(*buf++) << 20;
+ tmp_l |= hex(*buf++) << 16;
+ tmp_l |= hex(*buf++) << 12;
+ tmp_l |= hex(*buf++) << 8;
+ tmp_l |= hex(*buf++) << 4;
+ tmp_l |= hex(*buf++);
+
+ *(unsigned long *)mem = tmp_l;
+ mem += 4;
+
+ } else {
+ for (i=0; i<count; i++) {
+ ch = hex(*buf++) << 4;
+ ch |= hex(*buf++);
+ *mem++ = ch;
+ }
+ }
+
+
+ /*
+ ** Flush the data cache, invalidate the instruction cache.
+ */
+ flush_icache_range((int)orig_mem, (int)orig_mem + count - 1);
+
+ } else {
+ /* error condition */
+ }
+ debugger_fault_handler = NULL;
+ return mem;
+}
+
+/*
+ * While we find nice hex chars, build an int.
+ * Return number of chars processed.
+ */
+static int
+hexToInt(char **ptr, int *intValue)
+{
+ int numChars = 0;
+ int hexValue;
+
+ *intValue = 0;
+
+ if (kgdb_setjmp((long*)fault_jmp_buf) == 0) {
+ debugger_fault_handler = kgdb_fault_handler;
+ while (**ptr) {
+ hexValue = hex(**ptr);
+ if (hexValue < 0)
+ break;
+
+ *intValue = (*intValue << 4) | hexValue;
+ numChars ++;
+
+ (*ptr)++;
+ }
+ } else {
+ /* error condition */
+ }
+ debugger_fault_handler = NULL;
+
+ return (numChars);
+}
+
+/* scan for the sequence $<data>#<checksum> */
+static void
+getpacket(char *buffer)
+{
+ unsigned char checksum;
+ unsigned char xmitcsum;
+ int i;
+ int count;
+ unsigned char ch;
+
+ do {
+ /* wait around for the start character, ignore all other
+ * characters */
+ while ((ch = (getDebugChar() & 0x7f)) != '$') ;
+
+ checksum = 0;
+ xmitcsum = -1;
+
+ count = 0;
+
+ /* now, read until a # or end of buffer is found */
+ while (count < BUFMAX) {
+ ch = getDebugChar() & 0x7f;
+ if (ch == '#')
+ break;
+ checksum = checksum + ch;
+ buffer[count] = ch;
+ count = count + 1;
+ }
+
+ if (count >= BUFMAX)
+ continue;
+
+ buffer[count] = 0;
+
+ if (ch == '#') {
+ xmitcsum = hex(getDebugChar() & 0x7f) << 4;
+ xmitcsum |= hex(getDebugChar() & 0x7f);
+ if (checksum != xmitcsum)
+ putDebugChar('-'); /* failed checksum */
+ else {
+ putDebugChar('+'); /* successful transfer */
+ /* if a sequence char is present, reply the ID */
+ if (buffer[2] == ':') {
+ putDebugChar(buffer[0]);
+ putDebugChar(buffer[1]);
+ /* remove sequence chars from buffer */
+ count = strlen(buffer);
+ for (i=3; i <= count; i++)
+ buffer[i-3] = buffer[i];
+ }
+ }
+ }
+ } while (checksum != xmitcsum);
+}
+
+/* send the packet in buffer. */
+static void putpacket(unsigned char *buffer)
+{
+ unsigned char checksum;
+ int count;
+ unsigned char ch, recv;
+
+ /* $<packet info>#<checksum>. */
+ do {
+ putDebugChar('$');
+ checksum = 0;
+ count = 0;
+
+ while ((ch = buffer[count])) {
+ putDebugChar(ch);
+ checksum += ch;
+ count += 1;
+ }
+
+ putDebugChar('#');
+ putDebugChar(hexchars[checksum >> 4]);
+ putDebugChar(hexchars[checksum & 0xf]);
+ recv = getDebugChar();
+ } while ((recv & 0x7f) != '+');
+}
+
+static void kgdb_flush_cache_all(void)
+{
+ flush_instruction_cache();
+}
+
+/* Set up exception handlers for tracing and breakpoints
+ * [could be called kgdb_init()]
+ */
+void set_debug_traps(void)
+{
+#if 0
+ unsigned char c;
+
+ save_and_cli(flags);
+
+ /* In case GDB is started before us, ack any packets (presumably
+ * "$?#xx") sitting there.
+ *
+ * I've found this code causes more problems than it solves,
+ * so that's why it's commented out. GDB seems to work fine
+ * now starting either before or after the kernel -bwb
+ */
+
+ while((c = getDebugChar()) != '$');
+ while((c = getDebugChar()) != '#');
+ c = getDebugChar(); /* eat first csum byte */
+ c = getDebugChar(); /* eat second csum byte */
+ putDebugChar('+'); /* ack it */
+#endif
+ debugger = kgdb;
+ debugger_bpt = kgdb_bpt;
+ debugger_sstep = kgdb_sstep;
+ debugger_iabr_match = kgdb_iabr_match;
+ debugger_dabr_match = kgdb_dabr_match;
+
+ initialized = 1;
+}
+
+static void kgdb_fault_handler(struct pt_regs *regs)
+{
+ kgdb_longjmp((long*)fault_jmp_buf, 1);
+}
+
+int kgdb_bpt(struct pt_regs *regs)
+{
+ return handle_exception(regs);
+}
+
+int kgdb_sstep(struct pt_regs *regs)
+{
+ return handle_exception(regs);
+}
+
+void kgdb(struct pt_regs *regs)
+{
+ handle_exception(regs);
+}
+
+int kgdb_iabr_match(struct pt_regs *regs)
+{
+ printk(KERN_ERR "kgdb doesn't support iabr, what?!?\n");
+ return handle_exception(regs);
+}
+
+int kgdb_dabr_match(struct pt_regs *regs)
+{
+ printk(KERN_ERR "kgdb doesn't support dabr, what?!?\n");
+ return handle_exception(regs);
+}
+
+/* Convert the hardware trap type code to a unix signal number. */
+/*
+ * This table contains the mapping between PowerPC hardware trap types, and
+ * signals, which are primarily what GDB understands.
+ */
+static struct hard_trap_info
+{
+ unsigned int tt; /* Trap type code for powerpc */
+ unsigned char signo; /* Signal that we map this trap into */
+} hard_trap_info[] = {
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+ { 0x100, SIGINT }, /* critical input interrupt */
+ { 0x200, SIGSEGV }, /* machine check */
+ { 0x300, SIGSEGV }, /* data storage */
+ { 0x400, SIGBUS }, /* instruction storage */
+ { 0x500, SIGINT }, /* interrupt */
+ { 0x600, SIGBUS }, /* alignment */
+ { 0x700, SIGILL }, /* program */
+ { 0x800, SIGILL }, /* reserved */
+ { 0x900, SIGILL }, /* reserved */
+ { 0xa00, SIGILL }, /* reserved */
+ { 0xb00, SIGILL }, /* reserved */
+ { 0xc00, SIGCHLD }, /* syscall */
+ { 0xd00, SIGILL }, /* reserved */
+ { 0xe00, SIGILL }, /* reserved */
+ { 0xf00, SIGILL }, /* reserved */
+ /*
+ ** 0x1000 PIT
+ ** 0x1010 FIT
+ ** 0x1020 watchdog
+ ** 0x1100 data TLB miss
+ ** 0x1200 instruction TLB miss
+ */
+ { 0x2002, SIGTRAP}, /* debug */
+#else
+ { 0x200, SIGSEGV }, /* machine check */
+ { 0x300, SIGSEGV }, /* address error (store) */
+ { 0x400, SIGBUS }, /* instruction bus error */
+ { 0x500, SIGINT }, /* interrupt */
+ { 0x600, SIGBUS }, /* alingment */
+ { 0x700, SIGTRAP }, /* breakpoint trap */
+ { 0x800, SIGFPE }, /* fpu unavail */
+ { 0x900, SIGALRM }, /* decrementer */
+ { 0xa00, SIGILL }, /* reserved */
+ { 0xb00, SIGILL }, /* reserved */
+ { 0xc00, SIGCHLD }, /* syscall */
+ { 0xd00, SIGTRAP }, /* single-step/watch */
+ { 0xe00, SIGFPE }, /* fp assist */
+#endif
+ { 0, 0} /* Must be last */
+
+};
+
+static int computeSignal(unsigned int tt)
+{
+ struct hard_trap_info *ht;
+
+ for (ht = hard_trap_info; ht->tt && ht->signo; ht++)
+ if (ht->tt == tt)
+ return ht->signo;
+
+ return SIGHUP; /* default for things we don't know about */
+}
+
+#define PC_REGNUM 64
+#define SP_REGNUM 1
+
+/*
+ * This function does all command processing for interfacing to gdb.
+ */
+static int
+handle_exception (struct pt_regs *regs)
+{
+ int sigval;
+ int addr;
+ int length;
+ char *ptr;
+ unsigned int msr;
+
+ /* We don't handle user-mode breakpoints. */
+ if (user_mode(regs))
+ return 0;
+
+ if (debugger_fault_handler) {
+ debugger_fault_handler(regs);
+ panic("kgdb longjump failed!\n");
+ }
+ if (kgdb_active) {
+ printk(KERN_ERR "interrupt while in kgdb, returning\n");
+ return 0;
+ }
+
+ kgdb_active = 1;
+ kgdb_started = 1;
+
+#ifdef KGDB_DEBUG
+ printk("kgdb: entering handle_exception; trap [0x%x]\n",
+ (unsigned int)regs->trap);
+#endif
+
+ kgdb_interruptible(0);
+ lock_kernel();
+ msr = mfmsr();
+ mtmsr(msr & ~MSR_EE); /* disable interrupts */
+
+ if (regs->nip == (unsigned long)breakinst) {
+ /* Skip over breakpoint trap insn */
+ regs->nip += 4;
+ }
+
+ /* reply to host that an exception has occurred */
+ sigval = computeSignal(regs->trap);
+ ptr = remcomOutBuffer;
+
+ *ptr++ = 'T';
+ *ptr++ = hexchars[sigval >> 4];
+ *ptr++ = hexchars[sigval & 0xf];
+ *ptr++ = hexchars[PC_REGNUM >> 4];
+ *ptr++ = hexchars[PC_REGNUM & 0xf];
+ *ptr++ = ':';
+ ptr = mem2hex((char *)&regs->nip, ptr, 4);
+ *ptr++ = ';';
+ *ptr++ = hexchars[SP_REGNUM >> 4];
+ *ptr++ = hexchars[SP_REGNUM & 0xf];
+ *ptr++ = ':';
+ ptr = mem2hex(((char *)regs) + SP_REGNUM*4, ptr, 4);
+ *ptr++ = ';';
+ *ptr++ = 0;
+
+ putpacket(remcomOutBuffer);
+ if (kdebug)
+ printk("remcomOutBuffer: %s\n", remcomOutBuffer);
+
+ /* XXX We may want to add some features dealing with poking the
+ * XXX page tables, ... (look at sparc-stub.c for more info)
+ * XXX also required hacking to the gdb sources directly...
+ */
+
+ while (1) {
+ remcomOutBuffer[0] = 0;
+
+ getpacket(remcomInBuffer);
+ switch (remcomInBuffer[0]) {
+ case '?': /* report most recent signal */
+ remcomOutBuffer[0] = 'S';
+ remcomOutBuffer[1] = hexchars[sigval >> 4];
+ remcomOutBuffer[2] = hexchars[sigval & 0xf];
+ remcomOutBuffer[3] = 0;
+ break;
+#if 0
+ case 'q': /* this screws up gdb for some reason...*/
+ {
+ extern long _start, sdata, __bss_start;
+
+ ptr = &remcomInBuffer[1];
+ if (strncmp(ptr, "Offsets", 7) != 0)
+ break;
+
+ ptr = remcomOutBuffer;
+ sprintf(ptr, "Text=%8.8x;Data=%8.8x;Bss=%8.8x",
+ &_start, &sdata, &__bss_start);
+ break;
+ }
+#endif
+ case 'd':
+ /* toggle debug flag */
+ kdebug ^= 1;
+ break;
+
+ case 'g': /* return the value of the CPU registers.
+ * some of them are non-PowerPC names :(
+ * they are stored in gdb like:
+ * struct {
+ * u32 gpr[32];
+ * f64 fpr[32];
+ * u32 pc, ps, cnd, lr; (ps=msr)
+ * u32 cnt, xer, mq;
+ * }
+ */
+ {
+ int i;
+ ptr = remcomOutBuffer;
+ /* General Purpose Regs */
+ ptr = mem2hex((char *)regs, ptr, 32 * 4);
+ /* Floating Point Regs - FIXME */
+ /*ptr = mem2hex((char *), ptr, 32 * 8);*/
+ for(i=0; i<(32*8*2); i++) { /* 2chars/byte */
+ ptr[i] = '0';
+ }
+ ptr += 32*8*2;
+ /* pc, msr, cr, lr, ctr, xer, (mq is unused) */
+ ptr = mem2hex((char *)&regs->nip, ptr, 4);
+ ptr = mem2hex((char *)&regs->msr, ptr, 4);
+ ptr = mem2hex((char *)&regs->ccr, ptr, 4);
+ ptr = mem2hex((char *)&regs->link, ptr, 4);
+ ptr = mem2hex((char *)&regs->ctr, ptr, 4);
+ ptr = mem2hex((char *)&regs->xer, ptr, 4);
+ }
+ break;
+
+ case 'G': /* set the value of the CPU registers */
+ {
+ ptr = &remcomInBuffer[1];
+
+ /*
+ * If the stack pointer has moved, you should pray.
+ * (cause only god can help you).
+ */
+
+ /* General Purpose Regs */
+ hex2mem(ptr, (char *)regs, 32 * 4);
+
+ /* Floating Point Regs - FIXME?? */
+ /*ptr = hex2mem(ptr, ??, 32 * 8);*/
+ ptr += 32*8*2;
+
+ /* pc, msr, cr, lr, ctr, xer, (mq is unused) */
+ ptr = hex2mem(ptr, (char *)&regs->nip, 4);
+ ptr = hex2mem(ptr, (char *)&regs->msr, 4);
+ ptr = hex2mem(ptr, (char *)&regs->ccr, 4);
+ ptr = hex2mem(ptr, (char *)&regs->link, 4);
+ ptr = hex2mem(ptr, (char *)&regs->ctr, 4);
+ ptr = hex2mem(ptr, (char *)&regs->xer, 4);
+
+ strcpy(remcomOutBuffer,"OK");
+ }
+ break;
+ case 'H':
+ /* don't do anything, yet, just acknowledge */
+ hexToInt(&ptr, &addr);
+ strcpy(remcomOutBuffer,"OK");
+ break;
+
+ case 'm': /* mAA..AA,LLLL Read LLLL bytes at address AA..AA */
+ /* Try to read %x,%x. */
+
+ ptr = &remcomInBuffer[1];
+
+ if (hexToInt(&ptr, &addr) && *ptr++ == ','
+ && hexToInt(&ptr, &length)) {
+ if (mem2hex((char *)addr, remcomOutBuffer,
+ length))
+ break;
+ strcpy(remcomOutBuffer, "E03");
+ } else
+ strcpy(remcomOutBuffer, "E01");
+ break;
+
+ case 'M': /* MAA..AA,LLLL: Write LLLL bytes at address AA.AA return OK */
+ /* Try to read '%x,%x:'. */
+
+ ptr = &remcomInBuffer[1];
+
+ if (hexToInt(&ptr, &addr) && *ptr++ == ','
+ && hexToInt(&ptr, &length)
+ && *ptr++ == ':') {
+ if (hex2mem(ptr, (char *)addr, length))
+ strcpy(remcomOutBuffer, "OK");
+ else
+ strcpy(remcomOutBuffer, "E03");
+ flush_icache_range(addr, addr+length);
+ } else
+ strcpy(remcomOutBuffer, "E02");
+ break;
+
+
+ case 'k': /* kill the program, actually just continue */
+ case 'c': /* cAA..AA Continue; address AA..AA optional */
+ /* try to read optional parameter, pc unchanged if no parm */
+
+ ptr = &remcomInBuffer[1];
+ if (hexToInt(&ptr, &addr))
+ regs->nip = addr;
+
+/* Need to flush the instruction cache here, as we may have deposited a
+ * breakpoint, and the icache probably has no way of knowing that a data ref to
+ * some location may have changed something that is in the instruction cache.
+ */
+ kgdb_flush_cache_all();
+ mtmsr(msr);
+
+ kgdb_interruptible(1);
+ unlock_kernel();
+ kgdb_active = 0;
+ if (kdebug) {
+ printk("remcomInBuffer: %s\n", remcomInBuffer);
+ printk("remcomOutBuffer: %s\n", remcomOutBuffer);
+ }
+ return 1;
+
+ case 's':
+ kgdb_flush_cache_all();
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+ mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC);
+ regs->msr |= MSR_DE;
+#else
+ regs->msr |= MSR_SE;
+#endif
+ unlock_kernel();
+ kgdb_active = 0;
+ if (kdebug) {
+ printk("remcomInBuffer: %s\n", remcomInBuffer);
+ printk("remcomOutBuffer: %s\n", remcomOutBuffer);
+ }
+ return 1;
+
+ case 'r': /* Reset (if user process..exit ???)*/
+ panic("kgdb reset.");
+ break;
+ } /* switch */
+ if (remcomOutBuffer[0] && kdebug) {
+ printk("remcomInBuffer: %s\n", remcomInBuffer);
+ printk("remcomOutBuffer: %s\n", remcomOutBuffer);
+ }
+ /* reply to the request */
+ putpacket(remcomOutBuffer);
+ } /* while(1) */
+}
+
+/* This function will generate a breakpoint exception. It is used at the
+ beginning of a program to sync up with a debugger and can be used
+ otherwise as a quick means to stop program execution and "break" into
+ the debugger. */
+
+void
+breakpoint(void)
+{
+ if (!initialized) {
+ printk("breakpoint() called b4 kgdb init\n");
+ return;
+ }
+
+ asm(" .globl breakinst \n\
+ breakinst: .long 0x7d821008");
+}
+
+#ifdef CONFIG_KGDB_CONSOLE
+/* Output string in GDB O-packet format if GDB has connected. If nothing
+ output, returns 0 (caller must then handle output). */
+int
+kgdb_output_string (const char* s, unsigned int count)
+{
+ char buffer[512];
+
+ if (!kgdb_started)
+ return 0;
+
+ count = (count <= (sizeof(buffer) / 2 - 2))
+ ? count : (sizeof(buffer) / 2 - 2);
+
+ buffer[0] = 'O';
+ mem2hex (s, &buffer[1], count);
+ putpacket(buffer);
+
+ return 1;
+}
+#endif
+
+static void sysrq_handle_gdb(int key, struct pt_regs *pt_regs,
+ struct tty_struct *tty)
+{
+ printk("Entering GDB stub\n");
+ breakpoint();
+}
+static struct sysrq_key_op sysrq_gdb_op = {
+ .handler = sysrq_handle_gdb,
+ .help_msg = "Gdb",
+ .action_msg = "GDB",
+};
+
+static int gdb_register_sysrq(void)
+{
+ printk("Registering GDB sysrq handler\n");
+ register_sysrq_key('g', &sysrq_gdb_op);
+ return 0;
+}
+module_init(gdb_register_sysrq);
diff --git a/arch/ppc/kernel/ppc_htab.c b/arch/ppc/kernel/ppc_htab.c
new file mode 100644
index 000000000000..ca810025993f
--- /dev/null
+++ b/arch/ppc/kernel/ppc_htab.c
@@ -0,0 +1,467 @@
+/*
+ * PowerPC hash table management proc entry. Will show information
+ * about the current hash table and will allow changes to it.
+ *
+ * Written by Cort Dougan (cort@cs.nmt.edu)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/sysctl.h>
+#include <linux/ctype.h>
+#include <linux/threads.h>
+#include <linux/smp_lock.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+
+#include <asm/uaccess.h>
+#include <asm/mmu.h>
+#include <asm/residual.h>
+#include <asm/io.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/system.h>
+#include <asm/reg.h>
+
+static int ppc_htab_show(struct seq_file *m, void *v);
+static ssize_t ppc_htab_write(struct file * file, const char __user * buffer,
+ size_t count, loff_t *ppos);
+extern PTE *Hash, *Hash_end;
+extern unsigned long Hash_size, Hash_mask;
+extern unsigned long _SDR1;
+extern unsigned long htab_reloads;
+extern unsigned long htab_preloads;
+extern unsigned long htab_evicts;
+extern unsigned long pte_misses;
+extern unsigned long pte_errors;
+extern unsigned int primary_pteg_full;
+extern unsigned int htab_hash_searches;
+
+static int ppc_htab_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ppc_htab_show, NULL);
+}
+
+struct file_operations ppc_htab_operations = {
+ .open = ppc_htab_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .write = ppc_htab_write,
+ .release = single_release,
+};
+
+static char *pmc1_lookup(unsigned long mmcr0)
+{
+ switch ( mmcr0 & (0x7f<<7) )
+ {
+ case 0x0:
+ return "none";
+ case MMCR0_PMC1_CYCLES:
+ return "cycles";
+ case MMCR0_PMC1_ICACHEMISS:
+ return "ic miss";
+ case MMCR0_PMC1_DTLB:
+ return "dtlb miss";
+ default:
+ return "unknown";
+ }
+}
+
+static char *pmc2_lookup(unsigned long mmcr0)
+{
+ switch ( mmcr0 & 0x3f )
+ {
+ case 0x0:
+ return "none";
+ case MMCR0_PMC2_CYCLES:
+ return "cycles";
+ case MMCR0_PMC2_DCACHEMISS:
+ return "dc miss";
+ case MMCR0_PMC2_ITLB:
+ return "itlb miss";
+ case MMCR0_PMC2_LOADMISSTIME:
+ return "load miss time";
+ default:
+ return "unknown";
+ }
+}
+
+/*
+ * print some useful info about the hash table. This function
+ * is _REALLY_ slow (see the nested for loops below) but nothing
+ * in here should be really timing critical. -- Cort
+ */
+static int ppc_htab_show(struct seq_file *m, void *v)
+{
+ unsigned long mmcr0 = 0, pmc1 = 0, pmc2 = 0;
+#if defined(CONFIG_PPC_STD_MMU) && !defined(CONFIG_PPC64BRIDGE)
+ unsigned int kptes = 0, uptes = 0;
+ PTE *ptr;
+#endif /* CONFIG_PPC_STD_MMU */
+
+ if (cpu_has_feature(CPU_FTR_604_PERF_MON)) {
+ mmcr0 = mfspr(SPRN_MMCR0);
+ pmc1 = mfspr(SPRN_PMC1);
+ pmc2 = mfspr(SPRN_PMC2);
+ seq_printf(m,
+ "604 Performance Monitoring\n"
+ "MMCR0\t\t: %08lx %s%s ",
+ mmcr0,
+ ( mmcr0>>28 & 0x2 ) ? "(user mode counted)" : "",
+ ( mmcr0>>28 & 0x4 ) ? "(kernel mode counted)" : "");
+ seq_printf(m,
+ "\nPMC1\t\t: %08lx (%s)\n"
+ "PMC2\t\t: %08lx (%s)\n",
+ pmc1, pmc1_lookup(mmcr0),
+ pmc2, pmc2_lookup(mmcr0));
+ }
+
+#ifdef CONFIG_PPC_STD_MMU
+ /* if we don't have a htab */
+ if ( Hash_size == 0 ) {
+ seq_printf(m, "No Hash Table used\n");
+ return 0;
+ }
+
+#ifndef CONFIG_PPC64BRIDGE
+ for (ptr = Hash; ptr < Hash_end; ptr++) {
+ unsigned int mctx, vsid;
+
+ if (!ptr->v)
+ continue;
+ /* undo the esid skew */
+ vsid = ptr->vsid;
+ mctx = ((vsid - (vsid & 0xf) * 0x111) >> 4) & 0xfffff;
+ if (mctx == 0)
+ kptes++;
+ else
+ uptes++;
+ }
+#endif
+
+ seq_printf(m,
+ "PTE Hash Table Information\n"
+ "Size\t\t: %luKb\n"
+ "Buckets\t\t: %lu\n"
+ "Address\t\t: %08lx\n"
+ "Entries\t\t: %lu\n"
+#ifndef CONFIG_PPC64BRIDGE
+ "User ptes\t: %u\n"
+ "Kernel ptes\t: %u\n"
+ "Percent full\t: %lu%%\n"
+#endif
+ , (unsigned long)(Hash_size>>10),
+ (Hash_size/(sizeof(PTE)*8)),
+ (unsigned long)Hash,
+ Hash_size/sizeof(PTE)
+#ifndef CONFIG_PPC64BRIDGE
+ , uptes,
+ kptes,
+ ((kptes+uptes)*100) / (Hash_size/sizeof(PTE))
+#endif
+ );
+
+ seq_printf(m,
+ "Reloads\t\t: %lu\n"
+ "Preloads\t: %lu\n"
+ "Searches\t: %u\n"
+ "Overflows\t: %u\n"
+ "Evicts\t\t: %lu\n",
+ htab_reloads, htab_preloads, htab_hash_searches,
+ primary_pteg_full, htab_evicts);
+#endif /* CONFIG_PPC_STD_MMU */
+
+ seq_printf(m,
+ "Non-error misses: %lu\n"
+ "Error misses\t: %lu\n",
+ pte_misses, pte_errors);
+ return 0;
+}
+
+/*
+ * Allow user to define performance counters and resize the hash table
+ */
+static ssize_t ppc_htab_write(struct file * file, const char __user * ubuffer,
+ size_t count, loff_t *ppos)
+{
+#ifdef CONFIG_PPC_STD_MMU
+ unsigned long tmp;
+ char buffer[16];
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (strncpy_from_user(buffer, ubuffer, 15))
+ return -EFAULT;
+ buffer[15] = 0;
+
+ /* don't set the htab size for now */
+ if ( !strncmp( buffer, "size ", 5) )
+ return -EBUSY;
+
+ if ( !strncmp( buffer, "reset", 5) )
+ {
+ if (cpu_has_feature(CPU_FTR_604_PERF_MON)) {
+ /* reset PMC1 and PMC2 */
+ mtspr(SPRN_PMC1, 0);
+ mtspr(SPRN_PMC2, 0);
+ }
+ htab_reloads = 0;
+ htab_evicts = 0;
+ pte_misses = 0;
+ pte_errors = 0;
+ }
+
+ /* Everything below here requires the performance monitor feature. */
+ if (!cpu_has_feature(CPU_FTR_604_PERF_MON))
+ return count;
+
+ /* turn off performance monitoring */
+ if ( !strncmp( buffer, "off", 3) )
+ {
+ mtspr(SPRN_MMCR0, 0);
+ mtspr(SPRN_PMC1, 0);
+ mtspr(SPRN_PMC2, 0);
+ }
+
+ if ( !strncmp( buffer, "user", 4) )
+ {
+ /* setup mmcr0 and clear the correct pmc */
+ tmp = (mfspr(SPRN_MMCR0) & ~(0x60000000)) | 0x20000000;
+ mtspr(SPRN_MMCR0, tmp);
+ mtspr(SPRN_PMC1, 0);
+ mtspr(SPRN_PMC2, 0);
+ }
+
+ if ( !strncmp( buffer, "kernel", 6) )
+ {
+ /* setup mmcr0 and clear the correct pmc */
+ tmp = (mfspr(SPRN_MMCR0) & ~(0x60000000)) | 0x40000000;
+ mtspr(SPRN_MMCR0, tmp);
+ mtspr(SPRN_PMC1, 0);
+ mtspr(SPRN_PMC2, 0);
+ }
+
+ /* PMC1 values */
+ if ( !strncmp( buffer, "dtlb", 4) )
+ {
+ /* setup mmcr0 and clear the correct pmc */
+ tmp = (mfspr(SPRN_MMCR0) & ~(0x7F << 7)) | MMCR0_PMC1_DTLB;
+ mtspr(SPRN_MMCR0, tmp);
+ mtspr(SPRN_PMC1, 0);
+ }
+
+ if ( !strncmp( buffer, "ic miss", 7) )
+ {
+ /* setup mmcr0 and clear the correct pmc */
+ tmp = (mfspr(SPRN_MMCR0) & ~(0x7F<<7)) | MMCR0_PMC1_ICACHEMISS;
+ mtspr(SPRN_MMCR0, tmp);
+ mtspr(SPRN_PMC1, 0);
+ }
+
+ /* PMC2 values */
+ if ( !strncmp( buffer, "load miss time", 14) )
+ {
+ /* setup mmcr0 and clear the correct pmc */
+ asm volatile(
+ "mfspr %0,%1\n\t" /* get current mccr0 */
+ "rlwinm %0,%0,0,0,31-6\n\t" /* clear bits [26-31] */
+ "ori %0,%0,%2 \n\t" /* or in mmcr0 settings */
+ "mtspr %1,%0 \n\t" /* set new mccr0 */
+ "mtspr %3,%4 \n\t" /* reset the pmc */
+ : "=r" (tmp)
+ : "i" (SPRN_MMCR0),
+ "i" (MMCR0_PMC2_LOADMISSTIME),
+ "i" (SPRN_PMC2), "r" (0) );
+ }
+
+ if ( !strncmp( buffer, "itlb", 4) )
+ {
+ /* setup mmcr0 and clear the correct pmc */
+ asm volatile(
+ "mfspr %0,%1\n\t" /* get current mccr0 */
+ "rlwinm %0,%0,0,0,31-6\n\t" /* clear bits [26-31] */
+ "ori %0,%0,%2 \n\t" /* or in mmcr0 settings */
+ "mtspr %1,%0 \n\t" /* set new mccr0 */
+ "mtspr %3,%4 \n\t" /* reset the pmc */
+ : "=r" (tmp)
+ : "i" (SPRN_MMCR0), "i" (MMCR0_PMC2_ITLB),
+ "i" (SPRN_PMC2), "r" (0) );
+ }
+
+ if ( !strncmp( buffer, "dc miss", 7) )
+ {
+ /* setup mmcr0 and clear the correct pmc */
+ asm volatile(
+ "mfspr %0,%1\n\t" /* get current mccr0 */
+ "rlwinm %0,%0,0,0,31-6\n\t" /* clear bits [26-31] */
+ "ori %0,%0,%2 \n\t" /* or in mmcr0 settings */
+ "mtspr %1,%0 \n\t" /* set new mccr0 */
+ "mtspr %3,%4 \n\t" /* reset the pmc */
+ : "=r" (tmp)
+ : "i" (SPRN_MMCR0), "i" (MMCR0_PMC2_DCACHEMISS),
+ "i" (SPRN_PMC2), "r" (0) );
+ }
+
+ return count;
+#else /* CONFIG_PPC_STD_MMU */
+ return 0;
+#endif /* CONFIG_PPC_STD_MMU */
+}
+
+int proc_dol2crvec(ctl_table *table, int write, struct file *filp,
+ void __user *buffer_arg, size_t *lenp, loff_t *ppos)
+{
+ int vleft, first=1, len, left, val;
+ char __user *buffer = (char __user *) buffer_arg;
+ #define TMPBUFLEN 256
+ char buf[TMPBUFLEN], *p;
+ static const char *sizestrings[4] = {
+ "2MB", "256KB", "512KB", "1MB"
+ };
+ static const char *clockstrings[8] = {
+ "clock disabled", "+1 clock", "+1.5 clock", "reserved(3)",
+ "+2 clock", "+2.5 clock", "+3 clock", "reserved(7)"
+ };
+ static const char *typestrings[4] = {
+ "flow-through burst SRAM", "reserved SRAM",
+ "pipelined burst SRAM", "pipelined late-write SRAM"
+ };
+ static const char *holdstrings[4] = {
+ "0.5", "1.0", "(reserved2)", "(reserved3)"
+ };
+
+ if (!cpu_has_feature(CPU_FTR_L2CR))
+ return -EFAULT;
+
+ if ( /*!table->maxlen ||*/ (*ppos && !write)) {
+ *lenp = 0;
+ return 0;
+ }
+
+ vleft = table->maxlen / sizeof(int);
+ left = *lenp;
+
+ for (; left /*&& vleft--*/; first=0) {
+ if (write) {
+ while (left) {
+ char c;
+ if(get_user(c, buffer))
+ return -EFAULT;
+ if (!isspace(c))
+ break;
+ left--;
+ buffer++;
+ }
+ if (!left)
+ break;
+ len = left;
+ if (len > TMPBUFLEN-1)
+ len = TMPBUFLEN-1;
+ if(copy_from_user(buf, buffer, len))
+ return -EFAULT;
+ buf[len] = 0;
+ p = buf;
+ if (*p < '0' || *p > '9')
+ break;
+ val = simple_strtoul(p, &p, 0);
+ len = p-buf;
+ if ((len < left) && *p && !isspace(*p))
+ break;
+ buffer += len;
+ left -= len;
+ _set_L2CR(val);
+ } else {
+ p = buf;
+ if (!first)
+ *p++ = '\t';
+ val = _get_L2CR();
+ p += sprintf(p, "0x%08x: ", val);
+ p += sprintf(p, " %s", (val >> 31) & 1 ? "enabled" :
+ "disabled");
+ p += sprintf(p, ", %sparity", (val>>30)&1 ? "" : "no ");
+ p += sprintf(p, ", %s", sizestrings[(val >> 28) & 3]);
+ p += sprintf(p, ", %s", clockstrings[(val >> 25) & 7]);
+ p += sprintf(p, ", %s", typestrings[(val >> 23) & 2]);
+ p += sprintf(p, "%s", (val>>22)&1 ? ", data only" : "");
+ p += sprintf(p, "%s", (val>>20)&1 ? ", ZZ enabled": "");
+ p += sprintf(p, ", %s", (val>>19)&1 ? "write-through" :
+ "copy-back");
+ p += sprintf(p, "%s", (val>>18)&1 ? ", testing" : "");
+ p += sprintf(p, ", %sns hold",holdstrings[(val>>16)&3]);
+ p += sprintf(p, "%s", (val>>15)&1 ? ", DLL slow" : "");
+ p += sprintf(p, "%s", (val>>14)&1 ? ", diff clock" :"");
+ p += sprintf(p, "%s", (val>>13)&1 ? ", DLL bypass" :"");
+
+ p += sprintf(p,"\n");
+
+ len = strlen(buf);
+ if (len > left)
+ len = left;
+ if (copy_to_user(buffer, buf, len))
+ return -EFAULT;
+ left -= len;
+ buffer += len;
+ break;
+ }
+ }
+
+ if (!write && !first && left) {
+ if(put_user('\n', (char __user *) buffer))
+ return -EFAULT;
+ left--, buffer++;
+ }
+ if (write) {
+ char __user *s = (char __user *) buffer;
+ while (left) {
+ char c;
+ if(get_user(c, s++))
+ return -EFAULT;
+ if (!isspace(c))
+ break;
+ left--;
+ }
+ }
+ if (write && first)
+ return -EINVAL;
+ *lenp -= left;
+ *ppos += *lenp;
+ return 0;
+}
+
+#ifdef CONFIG_SYSCTL
+/*
+ * Register our sysctl.
+ */
+static ctl_table htab_ctl_table[]={
+ {
+ .ctl_name = KERN_PPC_L2CR,
+ .procname = "l2cr",
+ .mode = 0644,
+ .proc_handler = &proc_dol2crvec,
+ },
+ { 0, },
+};
+static ctl_table htab_sysctl_root[] = {
+ { 1, "kernel", NULL, 0, 0755, htab_ctl_table, },
+ { 0,},
+};
+
+static int __init
+register_ppc_htab_sysctl(void)
+{
+ register_sysctl_table(htab_sysctl_root, 0);
+
+ return 0;
+}
+
+__initcall(register_ppc_htab_sysctl);
+#endif
diff --git a/arch/ppc/kernel/ppc_ksyms.c b/arch/ppc/kernel/ppc_ksyms.c
new file mode 100644
index 000000000000..2ccb58fe4fc3
--- /dev/null
+++ b/arch/ppc/kernel/ppc_ksyms.c
@@ -0,0 +1,350 @@
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/threads.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <linux/elfcore.h>
+#include <linux/string.h>
+#include <linux/interrupt.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h>
+#include <linux/nvram.h>
+#include <linux/console.h>
+#include <linux/irq.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/ide.h>
+#include <linux/pm.h>
+#include <linux/bitops.h>
+
+#include <asm/page.h>
+#include <asm/semaphore.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/ide.h>
+#include <asm/atomic.h>
+#include <asm/checksum.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <linux/adb.h>
+#include <linux/cuda.h>
+#include <linux/pmu.h>
+#include <asm/prom.h>
+#include <asm/system.h>
+#include <asm/pci-bridge.h>
+#include <asm/irq.h>
+#include <asm/pmac_feature.h>
+#include <asm/dma.h>
+#include <asm/machdep.h>
+#include <asm/hw_irq.h>
+#include <asm/nvram.h>
+#include <asm/mmu_context.h>
+#include <asm/backlight.h>
+#include <asm/time.h>
+#include <asm/cputable.h>
+#include <asm/btext.h>
+#include <asm/div64.h>
+#include <asm/xmon.h>
+
+#ifdef CONFIG_8xx
+#include <asm/commproc.h>
+#endif
+
+/* Tell string.h we don't want memcpy etc. as cpp defines */
+#define EXPORT_SYMTAB_STROPS
+
+extern void transfer_to_handler(void);
+extern void do_syscall_trace(void);
+extern void do_IRQ(struct pt_regs *regs);
+extern void MachineCheckException(struct pt_regs *regs);
+extern void AlignmentException(struct pt_regs *regs);
+extern void ProgramCheckException(struct pt_regs *regs);
+extern void SingleStepException(struct pt_regs *regs);
+extern int do_signal(sigset_t *, struct pt_regs *);
+extern int pmac_newworld;
+extern int sys_sigreturn(struct pt_regs *regs);
+
+long long __ashrdi3(long long, int);
+long long __ashldi3(long long, int);
+long long __lshrdi3(long long, int);
+
+extern unsigned long mm_ptov (unsigned long paddr);
+
+EXPORT_SYMBOL(clear_pages);
+EXPORT_SYMBOL(clear_user_page);
+EXPORT_SYMBOL(do_signal);
+EXPORT_SYMBOL(do_syscall_trace);
+EXPORT_SYMBOL(transfer_to_handler);
+EXPORT_SYMBOL(do_IRQ);
+EXPORT_SYMBOL(MachineCheckException);
+EXPORT_SYMBOL(AlignmentException);
+EXPORT_SYMBOL(ProgramCheckException);
+EXPORT_SYMBOL(SingleStepException);
+EXPORT_SYMBOL(sys_sigreturn);
+EXPORT_SYMBOL(ppc_n_lost_interrupts);
+EXPORT_SYMBOL(ppc_lost_interrupts);
+
+EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
+EXPORT_SYMBOL(DMA_MODE_READ);
+EXPORT_SYMBOL(DMA_MODE_WRITE);
+#if defined(CONFIG_PPC_PREP)
+EXPORT_SYMBOL(_prep_type);
+EXPORT_SYMBOL(ucSystemType);
+#endif
+
+#if !defined(__INLINE_BITOPS)
+EXPORT_SYMBOL(set_bit);
+EXPORT_SYMBOL(clear_bit);
+EXPORT_SYMBOL(change_bit);
+EXPORT_SYMBOL(test_and_set_bit);
+EXPORT_SYMBOL(test_and_clear_bit);
+EXPORT_SYMBOL(test_and_change_bit);
+#endif /* __INLINE_BITOPS */
+
+EXPORT_SYMBOL(strcpy);
+EXPORT_SYMBOL(strncpy);
+EXPORT_SYMBOL(strcat);
+EXPORT_SYMBOL(strncat);
+EXPORT_SYMBOL(strchr);
+EXPORT_SYMBOL(strrchr);
+EXPORT_SYMBOL(strpbrk);
+EXPORT_SYMBOL(strstr);
+EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(strnlen);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strncmp);
+EXPORT_SYMBOL(strcasecmp);
+EXPORT_SYMBOL(__div64_32);
+
+EXPORT_SYMBOL(csum_partial);
+EXPORT_SYMBOL(csum_partial_copy_generic);
+EXPORT_SYMBOL(ip_fast_csum);
+EXPORT_SYMBOL(csum_tcpudp_magic);
+
+EXPORT_SYMBOL(__copy_tofrom_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__strncpy_from_user);
+EXPORT_SYMBOL(__strnlen_user);
+
+/*
+EXPORT_SYMBOL(inb);
+EXPORT_SYMBOL(inw);
+EXPORT_SYMBOL(inl);
+EXPORT_SYMBOL(outb);
+EXPORT_SYMBOL(outw);
+EXPORT_SYMBOL(outl);
+EXPORT_SYMBOL(outsl);*/
+
+EXPORT_SYMBOL(_insb);
+EXPORT_SYMBOL(_outsb);
+EXPORT_SYMBOL(_insw);
+EXPORT_SYMBOL(_outsw);
+EXPORT_SYMBOL(_insl);
+EXPORT_SYMBOL(_outsl);
+EXPORT_SYMBOL(_insw_ns);
+EXPORT_SYMBOL(_outsw_ns);
+EXPORT_SYMBOL(_insl_ns);
+EXPORT_SYMBOL(_outsl_ns);
+EXPORT_SYMBOL(iopa);
+EXPORT_SYMBOL(mm_ptov);
+EXPORT_SYMBOL(ioremap);
+#ifdef CONFIG_44x
+EXPORT_SYMBOL(ioremap64);
+#endif
+EXPORT_SYMBOL(__ioremap);
+EXPORT_SYMBOL(iounmap);
+EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */
+
+#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_IDE_MODULE)
+EXPORT_SYMBOL(ppc_ide_md);
+#endif
+
+#ifdef CONFIG_PCI
+EXPORT_SYMBOL(isa_io_base);
+EXPORT_SYMBOL(isa_mem_base);
+EXPORT_SYMBOL(pci_dram_offset);
+EXPORT_SYMBOL(pci_alloc_consistent);
+EXPORT_SYMBOL(pci_free_consistent);
+EXPORT_SYMBOL(pci_bus_io_base);
+EXPORT_SYMBOL(pci_bus_io_base_phys);
+EXPORT_SYMBOL(pci_bus_mem_base_phys);
+EXPORT_SYMBOL(pci_bus_to_hose);
+EXPORT_SYMBOL(pci_resource_to_bus);
+EXPORT_SYMBOL(pci_phys_to_bus);
+EXPORT_SYMBOL(pci_bus_to_phys);
+#endif /* CONFIG_PCI */
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+EXPORT_SYMBOL(flush_dcache_all);
+#endif
+
+EXPORT_SYMBOL(start_thread);
+EXPORT_SYMBOL(kernel_thread);
+
+EXPORT_SYMBOL(flush_instruction_cache);
+EXPORT_SYMBOL(giveup_fpu);
+EXPORT_SYMBOL(flush_icache_range);
+EXPORT_SYMBOL(flush_dcache_range);
+EXPORT_SYMBOL(flush_icache_user_range);
+EXPORT_SYMBOL(flush_dcache_page);
+EXPORT_SYMBOL(flush_tlb_kernel_range);
+EXPORT_SYMBOL(flush_tlb_page);
+EXPORT_SYMBOL(_tlbie);
+#ifdef CONFIG_ALTIVEC
+EXPORT_SYMBOL(last_task_used_altivec);
+EXPORT_SYMBOL(giveup_altivec);
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+EXPORT_SYMBOL(last_task_used_spe);
+EXPORT_SYMBOL(giveup_spe);
+#endif /* CONFIG_SPE */
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(smp_call_function);
+EXPORT_SYMBOL(smp_hw_index);
+#endif
+
+EXPORT_SYMBOL(ppc_md);
+
+#ifdef CONFIG_ADB
+EXPORT_SYMBOL(adb_request);
+EXPORT_SYMBOL(adb_register);
+EXPORT_SYMBOL(adb_unregister);
+EXPORT_SYMBOL(adb_poll);
+EXPORT_SYMBOL(adb_try_handler_change);
+#endif /* CONFIG_ADB */
+#ifdef CONFIG_ADB_CUDA
+EXPORT_SYMBOL(cuda_request);
+EXPORT_SYMBOL(cuda_poll);
+#endif /* CONFIG_ADB_CUDA */
+#ifdef CONFIG_PPC_MULTIPLATFORM
+EXPORT_SYMBOL(_machine);
+#endif
+#ifdef CONFIG_PPC_PMAC
+EXPORT_SYMBOL(sys_ctrler);
+EXPORT_SYMBOL(pmac_newworld);
+#endif
+#ifdef CONFIG_PPC_OF
+EXPORT_SYMBOL(find_devices);
+EXPORT_SYMBOL(find_type_devices);
+EXPORT_SYMBOL(find_compatible_devices);
+EXPORT_SYMBOL(find_path_device);
+EXPORT_SYMBOL(device_is_compatible);
+EXPORT_SYMBOL(machine_is_compatible);
+EXPORT_SYMBOL(find_all_nodes);
+EXPORT_SYMBOL(get_property);
+EXPORT_SYMBOL(request_OF_resource);
+EXPORT_SYMBOL(release_OF_resource);
+EXPORT_SYMBOL(pci_busdev_to_OF_node);
+EXPORT_SYMBOL(pci_device_to_OF_node);
+EXPORT_SYMBOL(pci_device_from_OF_node);
+EXPORT_SYMBOL(of_find_node_by_name);
+EXPORT_SYMBOL(of_find_node_by_type);
+EXPORT_SYMBOL(of_find_compatible_node);
+EXPORT_SYMBOL(of_find_node_by_path);
+EXPORT_SYMBOL(of_find_all_nodes);
+EXPORT_SYMBOL(of_get_parent);
+EXPORT_SYMBOL(of_get_next_child);
+EXPORT_SYMBOL(of_node_get);
+EXPORT_SYMBOL(of_node_put);
+#endif /* CONFIG_PPC_OF */
+#if defined(CONFIG_BOOTX_TEXT)
+EXPORT_SYMBOL(btext_update_display);
+#endif
+#if defined(CONFIG_SCSI) && defined(CONFIG_PPC_PMAC)
+EXPORT_SYMBOL(note_scsi_host);
+#endif
+#ifdef CONFIG_VT
+EXPORT_SYMBOL(kd_mksound);
+#endif
+EXPORT_SYMBOL(to_tm);
+
+EXPORT_SYMBOL(pm_power_off);
+
+EXPORT_SYMBOL(__ashrdi3);
+EXPORT_SYMBOL(__ashldi3);
+EXPORT_SYMBOL(__lshrdi3);
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(memscan);
+EXPORT_SYMBOL(memcmp);
+EXPORT_SYMBOL(memchr);
+
+#if defined(CONFIG_FB_VGA16_MODULE)
+EXPORT_SYMBOL(screen_info);
+#endif
+
+EXPORT_SYMBOL(__delay);
+#ifndef INLINE_IRQS
+EXPORT_SYMBOL(local_irq_enable);
+EXPORT_SYMBOL(local_irq_enable_end);
+EXPORT_SYMBOL(local_irq_disable);
+EXPORT_SYMBOL(local_irq_disable_end);
+EXPORT_SYMBOL(local_save_flags_ptr);
+EXPORT_SYMBOL(local_save_flags_ptr_end);
+EXPORT_SYMBOL(local_irq_restore);
+EXPORT_SYMBOL(local_irq_restore_end);
+#endif
+EXPORT_SYMBOL(timer_interrupt);
+EXPORT_SYMBOL(irq_desc);
+EXPORT_SYMBOL(tb_ticks_per_jiffy);
+EXPORT_SYMBOL(get_wchan);
+EXPORT_SYMBOL(console_drivers);
+#ifdef CONFIG_XMON
+EXPORT_SYMBOL(xmon);
+EXPORT_SYMBOL(xmon_printf);
+#endif
+EXPORT_SYMBOL(__up);
+EXPORT_SYMBOL(__down);
+EXPORT_SYMBOL(__down_interruptible);
+
+#if defined(CONFIG_KGDB) || defined(CONFIG_XMON)
+extern void (*debugger)(struct pt_regs *regs);
+extern int (*debugger_bpt)(struct pt_regs *regs);
+extern int (*debugger_sstep)(struct pt_regs *regs);
+extern int (*debugger_iabr_match)(struct pt_regs *regs);
+extern int (*debugger_dabr_match)(struct pt_regs *regs);
+extern void (*debugger_fault_handler)(struct pt_regs *regs);
+
+EXPORT_SYMBOL(debugger);
+EXPORT_SYMBOL(debugger_bpt);
+EXPORT_SYMBOL(debugger_sstep);
+EXPORT_SYMBOL(debugger_iabr_match);
+EXPORT_SYMBOL(debugger_dabr_match);
+EXPORT_SYMBOL(debugger_fault_handler);
+#endif
+
+#ifdef CONFIG_8xx
+EXPORT_SYMBOL(cpm_install_handler);
+EXPORT_SYMBOL(cpm_free_handler);
+#endif /* CONFIG_8xx */
+#if defined(CONFIG_8xx) || defined(CONFIG_40x) || defined(CONFIG_85xx) ||\
+ defined(CONFIG_83xx)
+EXPORT_SYMBOL(__res);
+#endif
+
+EXPORT_SYMBOL(next_mmu_context);
+EXPORT_SYMBOL(set_context);
+EXPORT_SYMBOL(handle_mm_fault); /* For MOL */
+EXPORT_SYMBOL(disarm_decr);
+#ifdef CONFIG_PPC_STD_MMU
+extern long mol_trampoline;
+EXPORT_SYMBOL(mol_trampoline); /* For MOL */
+EXPORT_SYMBOL(flush_hash_pages); /* For MOL */
+#ifdef CONFIG_SMP
+extern int mmu_hash_lock;
+EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */
+#endif /* CONFIG_SMP */
+extern long *intercept_table;
+EXPORT_SYMBOL(intercept_table);
+#endif /* CONFIG_PPC_STD_MMU */
+EXPORT_SYMBOL(cur_cpu_spec);
+#ifdef CONFIG_PPC_PMAC
+extern unsigned long agp_special_page;
+EXPORT_SYMBOL(agp_special_page);
+#endif
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+EXPORT_SYMBOL(__mtdcr);
+EXPORT_SYMBOL(__mfdcr);
+#endif
diff --git a/arch/ppc/kernel/process.c b/arch/ppc/kernel/process.c
new file mode 100644
index 000000000000..82de66e4db6d
--- /dev/null
+++ b/arch/ppc/kernel/process.c
@@ -0,0 +1,781 @@
+/*
+ * arch/ppc/kernel/process.c
+ *
+ * Derived from "arch/i386/kernel/process.c"
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Updated and modified by Cort Dougan (cort@cs.nmt.edu) and
+ * Paul Mackerras (paulus@cs.anu.edu.au)
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/init.h>
+#include <linux/prctl.h>
+#include <linux/init_task.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/mqueue.h>
+#include <linux/hardirq.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/mmu.h>
+#include <asm/prom.h>
+
+extern unsigned long _get_SP(void);
+
+struct task_struct *last_task_used_math = NULL;
+struct task_struct *last_task_used_altivec = NULL;
+struct task_struct *last_task_used_spe = NULL;
+
+static struct fs_struct init_fs = INIT_FS;
+static struct files_struct init_files = INIT_FILES;
+static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
+static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
+struct mm_struct init_mm = INIT_MM(init_mm);
+EXPORT_SYMBOL(init_mm);
+
+/* this is 8kB-aligned so we can get to the thread_info struct
+ at the base of it from the stack pointer with 1 integer instruction. */
+union thread_union init_thread_union
+ __attribute__((__section__(".data.init_task"))) =
+{ INIT_THREAD_INFO(init_task) };
+
+/* initial task structure */
+struct task_struct init_task = INIT_TASK(init_task);
+EXPORT_SYMBOL(init_task);
+
+/* only used to get secondary processor up */
+struct task_struct *current_set[NR_CPUS] = {&init_task, };
+
+#undef SHOW_TASK_SWITCHES
+#undef CHECK_STACK
+
+#if defined(CHECK_STACK)
+unsigned long
+kernel_stack_top(struct task_struct *tsk)
+{
+ return ((unsigned long)tsk) + sizeof(union task_union);
+}
+
+unsigned long
+task_top(struct task_struct *tsk)
+{
+ return ((unsigned long)tsk) + sizeof(struct thread_info);
+}
+
+/* check to make sure the kernel stack is healthy */
+int check_stack(struct task_struct *tsk)
+{
+ unsigned long stack_top = kernel_stack_top(tsk);
+ unsigned long tsk_top = task_top(tsk);
+ int ret = 0;
+
+#if 0
+ /* check thread magic */
+ if ( tsk->thread.magic != THREAD_MAGIC )
+ {
+ ret |= 1;
+ printk("thread.magic bad: %08x\n", tsk->thread.magic);
+ }
+#endif
+
+ if ( !tsk )
+ printk("check_stack(): tsk bad tsk %p\n",tsk);
+
+ /* check if stored ksp is bad */
+ if ( (tsk->thread.ksp > stack_top) || (tsk->thread.ksp < tsk_top) )
+ {
+ printk("stack out of bounds: %s/%d\n"
+ " tsk_top %08lx ksp %08lx stack_top %08lx\n",
+ tsk->comm,tsk->pid,
+ tsk_top, tsk->thread.ksp, stack_top);
+ ret |= 2;
+ }
+
+ /* check if stack ptr RIGHT NOW is bad */
+ if ( (tsk == current) && ((_get_SP() > stack_top ) || (_get_SP() < tsk_top)) )
+ {
+ printk("current stack ptr out of bounds: %s/%d\n"
+ " tsk_top %08lx sp %08lx stack_top %08lx\n",
+ current->comm,current->pid,
+ tsk_top, _get_SP(), stack_top);
+ ret |= 4;
+ }
+
+#if 0
+ /* check amount of free stack */
+ for ( i = (unsigned long *)task_top(tsk) ; i < kernel_stack_top(tsk) ; i++ )
+ {
+ if ( !i )
+ printk("check_stack(): i = %p\n", i);
+ if ( *i != 0 )
+ {
+ /* only notify if it's less than 900 bytes */
+ if ( (i - (unsigned long *)task_top(tsk)) < 900 )
+ printk("%d bytes free on stack\n",
+ i - task_top(tsk));
+ break;
+ }
+ }
+#endif
+
+ if (ret)
+ {
+ panic("bad kernel stack");
+ }
+ return(ret);
+}
+#endif /* defined(CHECK_STACK) */
+
+#ifdef CONFIG_ALTIVEC
+int
+dump_altivec(struct pt_regs *regs, elf_vrregset_t *vrregs)
+{
+ if (regs->msr & MSR_VEC)
+ giveup_altivec(current);
+ memcpy(vrregs, &current->thread.vr[0], sizeof(*vrregs));
+ return 1;
+}
+
+void
+enable_kernel_altivec(void)
+{
+ WARN_ON(preemptible());
+
+#ifdef CONFIG_SMP
+ if (current->thread.regs && (current->thread.regs->msr & MSR_VEC))
+ giveup_altivec(current);
+ else
+ giveup_altivec(NULL); /* just enable AltiVec for kernel - force */
+#else
+ giveup_altivec(last_task_used_altivec);
+#endif /* __SMP __ */
+}
+EXPORT_SYMBOL(enable_kernel_altivec);
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_SPE
+int
+dump_spe(struct pt_regs *regs, elf_vrregset_t *evrregs)
+{
+ if (regs->msr & MSR_SPE)
+ giveup_spe(current);
+ /* We copy u32 evr[32] + u64 acc + u32 spefscr -> 35 */
+ memcpy(evrregs, &current->thread.evr[0], sizeof(u32) * 35);
+ return 1;
+}
+
+void
+enable_kernel_spe(void)
+{
+ WARN_ON(preemptible());
+
+#ifdef CONFIG_SMP
+ if (current->thread.regs && (current->thread.regs->msr & MSR_SPE))
+ giveup_spe(current);
+ else
+ giveup_spe(NULL); /* just enable SPE for kernel - force */
+#else
+ giveup_spe(last_task_used_spe);
+#endif /* __SMP __ */
+}
+EXPORT_SYMBOL(enable_kernel_spe);
+#endif /* CONFIG_SPE */
+
+void
+enable_kernel_fp(void)
+{
+ WARN_ON(preemptible());
+
+#ifdef CONFIG_SMP
+ if (current->thread.regs && (current->thread.regs->msr & MSR_FP))
+ giveup_fpu(current);
+ else
+ giveup_fpu(NULL); /* just enables FP for kernel */
+#else
+ giveup_fpu(last_task_used_math);
+#endif /* CONFIG_SMP */
+}
+EXPORT_SYMBOL(enable_kernel_fp);
+
+int
+dump_task_fpu(struct task_struct *tsk, elf_fpregset_t *fpregs)
+{
+ preempt_disable();
+ if (tsk->thread.regs && (tsk->thread.regs->msr & MSR_FP))
+ giveup_fpu(tsk);
+ preempt_enable();
+ memcpy(fpregs, &tsk->thread.fpr[0], sizeof(*fpregs));
+ return 1;
+}
+
+struct task_struct *__switch_to(struct task_struct *prev,
+ struct task_struct *new)
+{
+ struct thread_struct *new_thread, *old_thread;
+ unsigned long s;
+ struct task_struct *last;
+
+ local_irq_save(s);
+#ifdef CHECK_STACK
+ check_stack(prev);
+ check_stack(new);
+#endif
+
+#ifdef CONFIG_SMP
+ /* avoid complexity of lazy save/restore of fpu
+ * by just saving it every time we switch out if
+ * this task used the fpu during the last quantum.
+ *
+ * If it tries to use the fpu again, it'll trap and
+ * reload its fp regs. So we don't have to do a restore
+ * every switch, just a save.
+ * -- Cort
+ */
+ if (prev->thread.regs && (prev->thread.regs->msr & MSR_FP))
+ giveup_fpu(prev);
+#ifdef CONFIG_ALTIVEC
+ /*
+ * If the previous thread used altivec in the last quantum
+ * (thus changing altivec regs) then save them.
+ * We used to check the VRSAVE register but not all apps
+ * set it, so we don't rely on it now (and in fact we need
+ * to save & restore VSCR even if VRSAVE == 0). -- paulus
+ *
+ * On SMP we always save/restore altivec regs just to avoid the
+ * complexity of changing processors.
+ * -- Cort
+ */
+ if ((prev->thread.regs && (prev->thread.regs->msr & MSR_VEC)))
+ giveup_altivec(prev);
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ /*
+ * If the previous thread used spe in the last quantum
+ * (thus changing spe regs) then save them.
+ *
+ * On SMP we always save/restore spe regs just to avoid the
+ * complexity of changing processors.
+ */
+ if ((prev->thread.regs && (prev->thread.regs->msr & MSR_SPE)))
+ giveup_spe(prev);
+#endif /* CONFIG_SPE */
+#endif /* CONFIG_SMP */
+
+ /* Avoid the trap. On smp this this never happens since
+ * we don't set last_task_used_altivec -- Cort
+ */
+ if (new->thread.regs && last_task_used_altivec == new)
+ new->thread.regs->msr |= MSR_VEC;
+#ifdef CONFIG_SPE
+ /* Avoid the trap. On smp this this never happens since
+ * we don't set last_task_used_spe
+ */
+ if (new->thread.regs && last_task_used_spe == new)
+ new->thread.regs->msr |= MSR_SPE;
+#endif /* CONFIG_SPE */
+ new_thread = &new->thread;
+ old_thread = &current->thread;
+ last = _switch(old_thread, new_thread);
+ local_irq_restore(s);
+ return last;
+}
+
+void show_regs(struct pt_regs * regs)
+{
+ int i, trap;
+
+ printk("NIP: %08lX LR: %08lX SP: %08lX REGS: %p TRAP: %04lx %s\n",
+ regs->nip, regs->link, regs->gpr[1], regs, regs->trap,
+ print_tainted());
+ printk("MSR: %08lx EE: %01x PR: %01x FP: %01x ME: %01x IR/DR: %01x%01x\n",
+ regs->msr, regs->msr&MSR_EE ? 1 : 0, regs->msr&MSR_PR ? 1 : 0,
+ regs->msr & MSR_FP ? 1 : 0,regs->msr&MSR_ME ? 1 : 0,
+ regs->msr&MSR_IR ? 1 : 0,
+ regs->msr&MSR_DR ? 1 : 0);
+ trap = TRAP(regs);
+ if (trap == 0x300 || trap == 0x600)
+ printk("DAR: %08lX, DSISR: %08lX\n", regs->dar, regs->dsisr);
+ printk("TASK = %p[%d] '%s' THREAD: %p\n",
+ current, current->pid, current->comm, current->thread_info);
+ printk("Last syscall: %ld ", current->thread.last_syscall);
+
+#ifdef CONFIG_SMP
+ printk(" CPU: %d", smp_processor_id());
+#endif /* CONFIG_SMP */
+
+ for (i = 0; i < 32; i++) {
+ long r;
+ if ((i % 8) == 0)
+ printk("\n" KERN_INFO "GPR%02d: ", i);
+ if (__get_user(r, &regs->gpr[i]))
+ break;
+ printk("%08lX ", r);
+ if (i == 12 && !FULL_REGS(regs))
+ break;
+ }
+ printk("\n");
+#ifdef CONFIG_KALLSYMS
+ /*
+ * Lookup NIP late so we have the best change of getting the
+ * above info out without failing
+ */
+ printk("NIP [%08lx] ", regs->nip);
+ print_symbol("%s\n", regs->nip);
+ printk("LR [%08lx] ", regs->link);
+ print_symbol("%s\n", regs->link);
+#endif
+ show_stack(current, (unsigned long *) regs->gpr[1]);
+}
+
+void exit_thread(void)
+{
+ if (last_task_used_math == current)
+ last_task_used_math = NULL;
+ if (last_task_used_altivec == current)
+ last_task_used_altivec = NULL;
+#ifdef CONFIG_SPE
+ if (last_task_used_spe == current)
+ last_task_used_spe = NULL;
+#endif
+}
+
+void flush_thread(void)
+{
+ if (last_task_used_math == current)
+ last_task_used_math = NULL;
+ if (last_task_used_altivec == current)
+ last_task_used_altivec = NULL;
+#ifdef CONFIG_SPE
+ if (last_task_used_spe == current)
+ last_task_used_spe = NULL;
+#endif
+}
+
+void
+release_thread(struct task_struct *t)
+{
+}
+
+/*
+ * This gets called before we allocate a new thread and copy
+ * the current task into it.
+ */
+void prepare_to_copy(struct task_struct *tsk)
+{
+ struct pt_regs *regs = tsk->thread.regs;
+
+ if (regs == NULL)
+ return;
+ preempt_disable();
+ if (regs->msr & MSR_FP)
+ giveup_fpu(current);
+#ifdef CONFIG_ALTIVEC
+ if (regs->msr & MSR_VEC)
+ giveup_altivec(current);
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ if (regs->msr & MSR_SPE)
+ giveup_spe(current);
+#endif /* CONFIG_SPE */
+ preempt_enable();
+}
+
+/*
+ * Copy a thread..
+ */
+int
+copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+ unsigned long unused,
+ struct task_struct *p, struct pt_regs *regs)
+{
+ struct pt_regs *childregs, *kregs;
+ extern void ret_from_fork(void);
+ unsigned long sp = (unsigned long)p->thread_info + THREAD_SIZE;
+ unsigned long childframe;
+
+ CHECK_FULL_REGS(regs);
+ /* Copy registers */
+ sp -= sizeof(struct pt_regs);
+ childregs = (struct pt_regs *) sp;
+ *childregs = *regs;
+ if ((childregs->msr & MSR_PR) == 0) {
+ /* for kernel thread, set `current' and stackptr in new task */
+ childregs->gpr[1] = sp + sizeof(struct pt_regs);
+ childregs->gpr[2] = (unsigned long) p;
+ p->thread.regs = NULL; /* no user register state */
+ } else {
+ childregs->gpr[1] = usp;
+ p->thread.regs = childregs;
+ if (clone_flags & CLONE_SETTLS)
+ childregs->gpr[2] = childregs->gpr[6];
+ }
+ childregs->gpr[3] = 0; /* Result from fork() */
+ sp -= STACK_FRAME_OVERHEAD;
+ childframe = sp;
+
+ /*
+ * The way this works is that at some point in the future
+ * some task will call _switch to switch to the new task.
+ * That will pop off the stack frame created below and start
+ * the new task running at ret_from_fork. The new task will
+ * do some house keeping and then return from the fork or clone
+ * system call, using the stack frame created above.
+ */
+ sp -= sizeof(struct pt_regs);
+ kregs = (struct pt_regs *) sp;
+ sp -= STACK_FRAME_OVERHEAD;
+ p->thread.ksp = sp;
+ kregs->nip = (unsigned long)ret_from_fork;
+
+ p->thread.last_syscall = -1;
+
+ return 0;
+}
+
+/*
+ * Set up a thread for executing a new program
+ */
+void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp)
+{
+ set_fs(USER_DS);
+ memset(regs->gpr, 0, sizeof(regs->gpr));
+ regs->ctr = 0;
+ regs->link = 0;
+ regs->xer = 0;
+ regs->ccr = 0;
+ regs->mq = 0;
+ regs->nip = nip;
+ regs->gpr[1] = sp;
+ regs->msr = MSR_USER;
+ if (last_task_used_math == current)
+ last_task_used_math = NULL;
+ if (last_task_used_altivec == current)
+ last_task_used_altivec = NULL;
+#ifdef CONFIG_SPE
+ if (last_task_used_spe == current)
+ last_task_used_spe = NULL;
+#endif
+ memset(current->thread.fpr, 0, sizeof(current->thread.fpr));
+ current->thread.fpscr = 0;
+#ifdef CONFIG_ALTIVEC
+ memset(current->thread.vr, 0, sizeof(current->thread.vr));
+ memset(&current->thread.vscr, 0, sizeof(current->thread.vscr));
+ current->thread.vrsave = 0;
+ current->thread.used_vr = 0;
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ memset(current->thread.evr, 0, sizeof(current->thread.evr));
+ current->thread.acc = 0;
+ current->thread.spefscr = 0;
+ current->thread.used_spe = 0;
+#endif /* CONFIG_SPE */
+}
+
+#define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \
+ | PR_FP_EXC_RES | PR_FP_EXC_INV)
+
+int set_fpexc_mode(struct task_struct *tsk, unsigned int val)
+{
+ struct pt_regs *regs = tsk->thread.regs;
+
+ /* This is a bit hairy. If we are an SPE enabled processor
+ * (have embedded fp) we store the IEEE exception enable flags in
+ * fpexc_mode. fpexc_mode is also used for setting FP exception
+ * mode (asyn, precise, disabled) for 'Classic' FP. */
+ if (val & PR_FP_EXC_SW_ENABLE) {
+#ifdef CONFIG_SPE
+ tsk->thread.fpexc_mode = val &
+ (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT);
+#else
+ return -EINVAL;
+#endif
+ } else {
+ /* on a CONFIG_SPE this does not hurt us. The bits that
+ * __pack_fe01 use do not overlap with bits used for
+ * PR_FP_EXC_SW_ENABLE. Additionally, the MSR[FE0,FE1] bits
+ * on CONFIG_SPE implementations are reserved so writing to
+ * them does not change anything */
+ if (val > PR_FP_EXC_PRECISE)
+ return -EINVAL;
+ tsk->thread.fpexc_mode = __pack_fe01(val);
+ if (regs != NULL && (regs->msr & MSR_FP) != 0)
+ regs->msr = (regs->msr & ~(MSR_FE0|MSR_FE1))
+ | tsk->thread.fpexc_mode;
+ }
+ return 0;
+}
+
+int get_fpexc_mode(struct task_struct *tsk, unsigned long adr)
+{
+ unsigned int val;
+
+ if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE)
+#ifdef CONFIG_SPE
+ val = tsk->thread.fpexc_mode;
+#else
+ return -EINVAL;
+#endif
+ else
+ val = __unpack_fe01(tsk->thread.fpexc_mode);
+ return put_user(val, (unsigned int __user *) adr);
+}
+
+int sys_clone(unsigned long clone_flags, unsigned long usp,
+ int __user *parent_tidp, void __user *child_threadptr,
+ int __user *child_tidp, int p6,
+ struct pt_regs *regs)
+{
+ CHECK_FULL_REGS(regs);
+ if (usp == 0)
+ usp = regs->gpr[1]; /* stack pointer for child */
+ return do_fork(clone_flags, usp, regs, 0, parent_tidp, child_tidp);
+}
+
+int sys_fork(int p1, int p2, int p3, int p4, int p5, int p6,
+ struct pt_regs *regs)
+{
+ CHECK_FULL_REGS(regs);
+ return do_fork(SIGCHLD, regs->gpr[1], regs, 0, NULL, NULL);
+}
+
+int sys_vfork(int p1, int p2, int p3, int p4, int p5, int p6,
+ struct pt_regs *regs)
+{
+ CHECK_FULL_REGS(regs);
+ return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->gpr[1],
+ regs, 0, NULL, NULL);
+}
+
+int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2,
+ unsigned long a3, unsigned long a4, unsigned long a5,
+ struct pt_regs *regs)
+{
+ int error;
+ char * filename;
+
+ filename = getname((char __user *) a0);
+ error = PTR_ERR(filename);
+ if (IS_ERR(filename))
+ goto out;
+ preempt_disable();
+ if (regs->msr & MSR_FP)
+ giveup_fpu(current);
+#ifdef CONFIG_ALTIVEC
+ if (regs->msr & MSR_VEC)
+ giveup_altivec(current);
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ if (regs->msr & MSR_SPE)
+ giveup_spe(current);
+#endif /* CONFIG_SPE */
+ preempt_enable();
+ error = do_execve(filename, (char __user *__user *) a1,
+ (char __user *__user *) a2, regs);
+ if (error == 0) {
+ task_lock(current);
+ current->ptrace &= ~PT_DTRACE;
+ task_unlock(current);
+ }
+ putname(filename);
+out:
+ return error;
+}
+
+void dump_stack(void)
+{
+ show_stack(current, NULL);
+}
+
+EXPORT_SYMBOL(dump_stack);
+
+void show_stack(struct task_struct *tsk, unsigned long *stack)
+{
+ unsigned long sp, stack_top, prev_sp, ret;
+ int count = 0;
+ unsigned long next_exc = 0;
+ struct pt_regs *regs;
+ extern char ret_from_except, ret_from_except_full, ret_from_syscall;
+
+ sp = (unsigned long) stack;
+ if (tsk == NULL)
+ tsk = current;
+ if (sp == 0) {
+ if (tsk == current)
+ asm("mr %0,1" : "=r" (sp));
+ else
+ sp = tsk->thread.ksp;
+ }
+
+ prev_sp = (unsigned long) (tsk->thread_info + 1);
+ stack_top = (unsigned long) tsk->thread_info + THREAD_SIZE;
+ while (count < 16 && sp > prev_sp && sp < stack_top && (sp & 3) == 0) {
+ if (count == 0) {
+ printk("Call trace:");
+#ifdef CONFIG_KALLSYMS
+ printk("\n");
+#endif
+ } else {
+ if (next_exc) {
+ ret = next_exc;
+ next_exc = 0;
+ } else
+ ret = *(unsigned long *)(sp + 4);
+ printk(" [%08lx] ", ret);
+#ifdef CONFIG_KALLSYMS
+ print_symbol("%s", ret);
+ printk("\n");
+#endif
+ if (ret == (unsigned long) &ret_from_except
+ || ret == (unsigned long) &ret_from_except_full
+ || ret == (unsigned long) &ret_from_syscall) {
+ /* sp + 16 points to an exception frame */
+ regs = (struct pt_regs *) (sp + 16);
+ if (sp + 16 + sizeof(*regs) <= stack_top)
+ next_exc = regs->nip;
+ }
+ }
+ ++count;
+ sp = *(unsigned long *)sp;
+ }
+#ifndef CONFIG_KALLSYMS
+ if (count > 0)
+ printk("\n");
+#endif
+}
+
+#if 0
+/*
+ * Low level print for debugging - Cort
+ */
+int __init ll_printk(const char *fmt, ...)
+{
+ va_list args;
+ char buf[256];
+ int i;
+
+ va_start(args, fmt);
+ i=vsprintf(buf,fmt,args);
+ ll_puts(buf);
+ va_end(args);
+ return i;
+}
+
+int lines = 24, cols = 80;
+int orig_x = 0, orig_y = 0;
+
+void puthex(unsigned long val)
+{
+ unsigned char buf[10];
+ int i;
+ for (i = 7; i >= 0; i--)
+ {
+ buf[i] = "0123456789ABCDEF"[val & 0x0F];
+ val >>= 4;
+ }
+ buf[8] = '\0';
+ prom_print(buf);
+}
+
+void __init ll_puts(const char *s)
+{
+ int x,y;
+ char *vidmem = (char *)/*(_ISA_MEM_BASE + 0xB8000) */0xD00B8000;
+ char c;
+ extern int mem_init_done;
+
+ if ( mem_init_done ) /* assume this means we can printk */
+ {
+ printk(s);
+ return;
+ }
+
+#if 0
+ if ( have_of )
+ {
+ prom_print(s);
+ return;
+ }
+#endif
+
+ /*
+ * can't ll_puts on chrp without openfirmware yet.
+ * vidmem just needs to be setup for it.
+ * -- Cort
+ */
+ if ( _machine != _MACH_prep )
+ return;
+ x = orig_x;
+ y = orig_y;
+
+ while ( ( c = *s++ ) != '\0' ) {
+ if ( c == '\n' ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ /*scroll();*/
+ /*y--;*/
+ y = 0;
+ }
+ } else {
+ vidmem [ ( x + cols * y ) * 2 ] = c;
+ if ( ++x >= cols ) {
+ x = 0;
+ if ( ++y >= lines ) {
+ /*scroll();*/
+ /*y--;*/
+ y = 0;
+ }
+ }
+ }
+ }
+
+ orig_x = x;
+ orig_y = y;
+}
+#endif
+
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long ip, sp;
+ unsigned long stack_page = (unsigned long) p->thread_info;
+ int count = 0;
+ if (!p || p == current || p->state == TASK_RUNNING)
+ return 0;
+ sp = p->thread.ksp;
+ do {
+ sp = *(unsigned long *)sp;
+ if (sp < stack_page || sp >= stack_page + 8188)
+ return 0;
+ if (count > 0) {
+ ip = *(unsigned long *)(sp + 4);
+ if (!in_sched_functions(ip))
+ return ip;
+ }
+ } while (count++ < 16);
+ return 0;
+}
diff --git a/arch/ppc/kernel/ptrace.c b/arch/ppc/kernel/ptrace.c
new file mode 100644
index 000000000000..426b6f7d9de3
--- /dev/null
+++ b/arch/ppc/kernel/ptrace.c
@@ -0,0 +1,474 @@
+/*
+ * arch/ppc/kernel/ptrace.c
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/m68k/kernel/ptrace.c"
+ * Copyright (C) 1994 by Hamish Macdonald
+ * Taken from linux/kernel/ptrace.c and modified for M680x0.
+ * linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
+ *
+ * Modified by Cort Dougan (cort@hq.fsmlabs.com)
+ * and Paul Mackerras (paulus@linuxcare.com.au).
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file README.legal in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+#include <linux/security.h>
+
+#include <asm/uaccess.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+
+/*
+ * Set of msr bits that gdb can change on behalf of a process.
+ */
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#define MSR_DEBUGCHANGE 0
+#else
+#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE)
+#endif
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+/*
+ * Get contents of register REGNO in task TASK.
+ */
+static inline unsigned long get_reg(struct task_struct *task, int regno)
+{
+ if (regno < sizeof(struct pt_regs) / sizeof(unsigned long)
+ && task->thread.regs != NULL)
+ return ((unsigned long *)task->thread.regs)[regno];
+ return (0);
+}
+
+/*
+ * Write contents of register REGNO in task TASK.
+ */
+static inline int put_reg(struct task_struct *task, int regno,
+ unsigned long data)
+{
+ if (regno <= PT_MQ && task->thread.regs != NULL) {
+ if (regno == PT_MSR)
+ data = (data & MSR_DEBUGCHANGE)
+ | (task->thread.regs->msr & ~MSR_DEBUGCHANGE);
+ ((unsigned long *)task->thread.regs)[regno] = data;
+ return 0;
+ }
+ return -EIO;
+}
+
+#ifdef CONFIG_ALTIVEC
+/*
+ * Get contents of AltiVec register state in task TASK
+ */
+static inline int get_vrregs(unsigned long __user *data, struct task_struct *task)
+{
+ int i, j;
+
+ if (!access_ok(VERIFY_WRITE, data, 133 * sizeof(unsigned long)))
+ return -EFAULT;
+
+ /* copy AltiVec registers VR[0] .. VR[31] */
+ for (i = 0; i < 32; i++)
+ for (j = 0; j < 4; j++, data++)
+ if (__put_user(task->thread.vr[i].u[j], data))
+ return -EFAULT;
+
+ /* copy VSCR */
+ for (i = 0; i < 4; i++, data++)
+ if (__put_user(task->thread.vscr.u[i], data))
+ return -EFAULT;
+
+ /* copy VRSAVE */
+ if (__put_user(task->thread.vrsave, data))
+ return -EFAULT;
+
+ return 0;
+}
+
+/*
+ * Write contents of AltiVec register state into task TASK.
+ */
+static inline int set_vrregs(struct task_struct *task, unsigned long __user *data)
+{
+ int i, j;
+
+ if (!access_ok(VERIFY_READ, data, 133 * sizeof(unsigned long)))
+ return -EFAULT;
+
+ /* copy AltiVec registers VR[0] .. VR[31] */
+ for (i = 0; i < 32; i++)
+ for (j = 0; j < 4; j++, data++)
+ if (__get_user(task->thread.vr[i].u[j], data))
+ return -EFAULT;
+
+ /* copy VSCR */
+ for (i = 0; i < 4; i++, data++)
+ if (__get_user(task->thread.vscr.u[i], data))
+ return -EFAULT;
+
+ /* copy VRSAVE */
+ if (__get_user(task->thread.vrsave, data))
+ return -EFAULT;
+
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_SPE
+
+/*
+ * For get_evrregs/set_evrregs functions 'data' has the following layout:
+ *
+ * struct {
+ * u32 evr[32];
+ * u64 acc;
+ * u32 spefscr;
+ * }
+ */
+
+/*
+ * Get contents of SPE register state in task TASK.
+ */
+static inline int get_evrregs(unsigned long *data, struct task_struct *task)
+{
+ int i;
+
+ if (!access_ok(VERIFY_WRITE, data, 35 * sizeof(unsigned long)))
+ return -EFAULT;
+
+ /* copy SPEFSCR */
+ if (__put_user(task->thread.spefscr, &data[34]))
+ return -EFAULT;
+
+ /* copy SPE registers EVR[0] .. EVR[31] */
+ for (i = 0; i < 32; i++, data++)
+ if (__put_user(task->thread.evr[i], data))
+ return -EFAULT;
+
+ /* copy ACC */
+ if (__put_user64(task->thread.acc, (unsigned long long *)data))
+ return -EFAULT;
+
+ return 0;
+}
+
+/*
+ * Write contents of SPE register state into task TASK.
+ */
+static inline int set_evrregs(struct task_struct *task, unsigned long *data)
+{
+ int i;
+
+ if (!access_ok(VERIFY_READ, data, 35 * sizeof(unsigned long)))
+ return -EFAULT;
+
+ /* copy SPEFSCR */
+ if (__get_user(task->thread.spefscr, &data[34]))
+ return -EFAULT;
+
+ /* copy SPE registers EVR[0] .. EVR[31] */
+ for (i = 0; i < 32; i++, data++)
+ if (__get_user(task->thread.evr[i], data))
+ return -EFAULT;
+ /* copy ACC */
+ if (__get_user64(task->thread.acc, (unsigned long long*)data))
+ return -EFAULT;
+
+ return 0;
+}
+#endif /* CONFIG_SPE */
+
+static inline void
+set_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+ task->thread.dbcr0 = DBCR0_IDM | DBCR0_IC;
+ regs->msr |= MSR_DE;
+#else
+ regs->msr |= MSR_SE;
+#endif
+ }
+}
+
+static inline void
+clear_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+ task->thread.dbcr0 = 0;
+ regs->msr &= ~MSR_DE;
+#else
+ regs->msr &= ~MSR_SE;
+#endif
+ }
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure single step bits etc are not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+ /* make sure the single step bit is not set. */
+ clear_single_step(child);
+}
+
+int sys_ptrace(long request, long pid, long addr, long data)
+{
+ struct task_struct *child;
+ int ret = -EPERM;
+
+ lock_kernel();
+ if (request == PTRACE_TRACEME) {
+ /* are we already being traced? */
+ if (current->ptrace & PT_PTRACED)
+ goto out;
+ ret = security_ptrace(current->parent, current);
+ if (ret)
+ goto out;
+ /* set the ptrace bit in the process flags. */
+ current->ptrace |= PT_PTRACED;
+ ret = 0;
+ goto out;
+ }
+ ret = -ESRCH;
+ read_lock(&tasklist_lock);
+ child = find_task_by_pid(pid);
+ if (child)
+ get_task_struct(child);
+ read_unlock(&tasklist_lock);
+ if (!child)
+ goto out;
+
+ ret = -EPERM;
+ if (pid == 1) /* you may not mess with init */
+ goto out_tsk;
+
+ if (request == PTRACE_ATTACH) {
+ ret = ptrace_attach(child);
+ goto out_tsk;
+ }
+
+ ret = ptrace_check_attach(child, request == PTRACE_KILL);
+ if (ret < 0)
+ goto out_tsk;
+
+ switch (request) {
+ /* when I and D space are separate, these will need to be fixed. */
+ case PTRACE_PEEKTEXT: /* read word at location addr. */
+ case PTRACE_PEEKDATA: {
+ unsigned long tmp;
+ int copied;
+
+ copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+ ret = -EIO;
+ if (copied != sizeof(tmp))
+ break;
+ ret = put_user(tmp,(unsigned long __user *) data);
+ break;
+ }
+
+ /* read the word at location addr in the USER area. */
+ /* XXX this will need fixing for 64-bit */
+ case PTRACE_PEEKUSR: {
+ unsigned long index, tmp;
+
+ ret = -EIO;
+ /* convert to index and check */
+ index = (unsigned long) addr >> 2;
+ if ((addr & 3) || index > PT_FPSCR
+ || child->thread.regs == NULL)
+ break;
+
+ CHECK_FULL_REGS(child->thread.regs);
+ if (index < PT_FPR0) {
+ tmp = get_reg(child, (int) index);
+ } else {
+ preempt_disable();
+ if (child->thread.regs->msr & MSR_FP)
+ giveup_fpu(child);
+ preempt_enable();
+ tmp = ((unsigned long *)child->thread.fpr)[index - PT_FPR0];
+ }
+ ret = put_user(tmp,(unsigned long __user *) data);
+ break;
+ }
+
+ /* If I and D space are separate, this will have to be fixed. */
+ case PTRACE_POKETEXT: /* write the word at location addr. */
+ case PTRACE_POKEDATA:
+ ret = 0;
+ if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
+ break;
+ ret = -EIO;
+ break;
+
+ /* write the word at location addr in the USER area */
+ case PTRACE_POKEUSR: {
+ unsigned long index;
+
+ ret = -EIO;
+ /* convert to index and check */
+ index = (unsigned long) addr >> 2;
+ if ((addr & 3) || index > PT_FPSCR
+ || child->thread.regs == NULL)
+ break;
+
+ CHECK_FULL_REGS(child->thread.regs);
+ if (index == PT_ORIG_R3)
+ break;
+ if (index < PT_FPR0) {
+ ret = put_reg(child, index, data);
+ } else {
+ preempt_disable();
+ if (child->thread.regs->msr & MSR_FP)
+ giveup_fpu(child);
+ preempt_enable();
+ ((unsigned long *)child->thread.fpr)[index - PT_FPR0] = data;
+ ret = 0;
+ }
+ break;
+ }
+
+ case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
+ case PTRACE_CONT: { /* restart after signal. */
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ if (request == PTRACE_SYSCALL) {
+ set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ } else {
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ }
+ child->exit_code = data;
+ /* make sure the single step bit is not set. */
+ clear_single_step(child);
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+/*
+ * make the child exit. Best I can do is send it a sigkill.
+ * perhaps it should be put in the status that it wants to
+ * exit.
+ */
+ case PTRACE_KILL: {
+ ret = 0;
+ if (child->exit_state == EXIT_ZOMBIE) /* already dead */
+ break;
+ child->exit_code = SIGKILL;
+ /* make sure the single step bit is not set. */
+ clear_single_step(child);
+ wake_up_process(child);
+ break;
+ }
+
+ case PTRACE_SINGLESTEP: { /* set the trap flag. */
+ ret = -EIO;
+ if ((unsigned long) data > _NSIG)
+ break;
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ set_single_step(child);
+ child->exit_code = data;
+ /* give it a chance to run. */
+ wake_up_process(child);
+ ret = 0;
+ break;
+ }
+
+ case PTRACE_DETACH:
+ ret = ptrace_detach(child, data);
+ break;
+
+#ifdef CONFIG_ALTIVEC
+ case PTRACE_GETVRREGS:
+ /* Get the child altivec register state. */
+ preempt_disable();
+ if (child->thread.regs->msr & MSR_VEC)
+ giveup_altivec(child);
+ preempt_enable();
+ ret = get_vrregs((unsigned long __user *)data, child);
+ break;
+
+ case PTRACE_SETVRREGS:
+ /* Set the child altivec register state. */
+ /* this is to clear the MSR_VEC bit to force a reload
+ * of register state from memory */
+ preempt_disable();
+ if (child->thread.regs->msr & MSR_VEC)
+ giveup_altivec(child);
+ preempt_enable();
+ ret = set_vrregs(child, (unsigned long __user *)data);
+ break;
+#endif
+#ifdef CONFIG_SPE
+ case PTRACE_GETEVRREGS:
+ /* Get the child spe register state. */
+ if (child->thread.regs->msr & MSR_SPE)
+ giveup_spe(child);
+ ret = get_evrregs((unsigned long __user *)data, child);
+ break;
+
+ case PTRACE_SETEVRREGS:
+ /* Set the child spe register state. */
+ /* this is to clear the MSR_SPE bit to force a reload
+ * of register state from memory */
+ if (child->thread.regs->msr & MSR_SPE)
+ giveup_spe(child);
+ ret = set_evrregs(child, (unsigned long __user *)data);
+ break;
+#endif
+
+ default:
+ ret = ptrace_request(child, request, addr, data);
+ break;
+ }
+out_tsk:
+ put_task_struct(child);
+out:
+ unlock_kernel();
+ return ret;
+}
+
+void do_syscall_trace(void)
+{
+ if (!test_thread_flag(TIF_SYSCALL_TRACE)
+ || !(current->ptrace & PT_PTRACED))
+ return;
+ ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
+ ? 0x80 : 0));
+
+ /*
+ * this isn't the same as continuing with a signal, but it will do
+ * for normal use. strace only continues with a signal if the
+ * stopping signal is not SIGTRAP. -brl
+ */
+ if (current->exit_code) {
+ send_sig(current->exit_code, current, 1);
+ current->exit_code = 0;
+ }
+}
diff --git a/arch/ppc/kernel/semaphore.c b/arch/ppc/kernel/semaphore.c
new file mode 100644
index 000000000000..2fe429b27c14
--- /dev/null
+++ b/arch/ppc/kernel/semaphore.c
@@ -0,0 +1,131 @@
+/*
+ * PowerPC-specific semaphore code.
+ *
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * April 2001 - Reworked by Paul Mackerras <paulus@samba.org>
+ * to eliminate the SMP races in the old version between the updates
+ * of `count' and `waking'. Now we use negative `count' values to
+ * indicate that some process(es) are waiting for the semaphore.
+ */
+
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <asm/atomic.h>
+#include <asm/semaphore.h>
+#include <asm/errno.h>
+
+/*
+ * Atomically update sem->count.
+ * This does the equivalent of the following:
+ *
+ * old_count = sem->count;
+ * tmp = MAX(old_count, 0) + incr;
+ * sem->count = tmp;
+ * return old_count;
+ */
+static inline int __sem_update_count(struct semaphore *sem, int incr)
+{
+ int old_count, tmp;
+
+ __asm__ __volatile__("\n"
+"1: lwarx %0,0,%3\n"
+" srawi %1,%0,31\n"
+" andc %1,%0,%1\n"
+" add %1,%1,%4\n"
+ PPC405_ERR77(0,%3)
+" stwcx. %1,0,%3\n"
+" bne 1b"
+ : "=&r" (old_count), "=&r" (tmp), "=m" (sem->count)
+ : "r" (&sem->count), "r" (incr), "m" (sem->count)
+ : "cc");
+
+ return old_count;
+}
+
+void __up(struct semaphore *sem)
+{
+ /*
+ * Note that we incremented count in up() before we came here,
+ * but that was ineffective since the result was <= 0, and
+ * any negative value of count is equivalent to 0.
+ * This ends up setting count to 1, unless count is now > 0
+ * (i.e. because some other cpu has called up() in the meantime),
+ * in which case we just increment count.
+ */
+ __sem_update_count(sem, 1);
+ wake_up(&sem->wait);
+}
+
+/*
+ * Note that when we come in to __down or __down_interruptible,
+ * we have already decremented count, but that decrement was
+ * ineffective since the result was < 0, and any negative value
+ * of count is equivalent to 0.
+ * Thus it is only when we decrement count from some value > 0
+ * that we have actually got the semaphore.
+ */
+void __sched __down(struct semaphore *sem)
+{
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+ smp_wmb();
+
+ /*
+ * Try to get the semaphore. If the count is > 0, then we've
+ * got the semaphore; we decrement count and exit the loop.
+ * If the count is 0 or negative, we set it to -1, indicating
+ * that we are asleep, and then sleep.
+ */
+ while (__sem_update_count(sem, -1) <= 0) {
+ schedule();
+ tsk->state = TASK_UNINTERRUPTIBLE;
+ }
+ remove_wait_queue(&sem->wait, &wait);
+ tsk->state = TASK_RUNNING;
+
+ /*
+ * If there are any more sleepers, wake one of them up so
+ * that it can either get the semaphore, or set count to -1
+ * indicating that there are still processes sleeping.
+ */
+ wake_up(&sem->wait);
+}
+
+int __sched __down_interruptible(struct semaphore * sem)
+{
+ int retval = 0;
+ struct task_struct *tsk = current;
+ DECLARE_WAITQUEUE(wait, tsk);
+
+ tsk->state = TASK_INTERRUPTIBLE;
+ add_wait_queue_exclusive(&sem->wait, &wait);
+ smp_wmb();
+
+ while (__sem_update_count(sem, -1) <= 0) {
+ if (signal_pending(current)) {
+ /*
+ * A signal is pending - give up trying.
+ * Set sem->count to 0 if it is negative,
+ * since we are no longer sleeping.
+ */
+ __sem_update_count(sem, 0);
+ retval = -EINTR;
+ break;
+ }
+ schedule();
+ tsk->state = TASK_INTERRUPTIBLE;
+ }
+ tsk->state = TASK_RUNNING;
+ remove_wait_queue(&sem->wait, &wait);
+ wake_up(&sem->wait);
+ return retval;
+}
diff --git a/arch/ppc/kernel/setup.c b/arch/ppc/kernel/setup.c
new file mode 100644
index 000000000000..e97ce635b99e
--- /dev/null
+++ b/arch/ppc/kernel/setup.c
@@ -0,0 +1,778 @@
+/*
+ * Common prep/pmac/chrp boot and setup code.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/delay.h>
+#include <linux/initrd.h>
+#include <linux/ide.h>
+#include <linux/tty.h>
+#include <linux/bootmem.h>
+#include <linux/seq_file.h>
+#include <linux/root_dev.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
+
+#include <asm/residual.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/processor.h>
+#include <asm/pgtable.h>
+#include <asm/bootinfo.h>
+#include <asm/setup.h>
+#include <asm/amigappc.h>
+#include <asm/smp.h>
+#include <asm/elf.h>
+#include <asm/cputable.h>
+#include <asm/bootx.h>
+#include <asm/btext.h>
+#include <asm/machdep.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/pmac_feature.h>
+#include <asm/sections.h>
+#include <asm/nvram.h>
+#include <asm/xmon.h>
+#include <asm/ocp.h>
+
+#if defined(CONFIG_85xx) || defined(CONFIG_83xx)
+#include <asm/ppc_sys.h>
+#endif
+
+#if defined CONFIG_KGDB
+#include <asm/kgdb.h>
+#endif
+
+extern void platform_init(unsigned long r3, unsigned long r4,
+ unsigned long r5, unsigned long r6, unsigned long r7);
+extern void bootx_init(unsigned long r4, unsigned long phys);
+extern void identify_cpu(unsigned long offset, unsigned long cpu);
+extern void do_cpu_ftr_fixups(unsigned long offset);
+extern void reloc_got2(unsigned long offset);
+
+extern void ppc6xx_idle(void);
+extern void power4_idle(void);
+
+extern boot_infos_t *boot_infos;
+struct ide_machdep_calls ppc_ide_md;
+char *sysmap;
+unsigned long sysmap_size;
+
+/* Used with the BI_MEMSIZE bootinfo parameter to store the memory
+ size value reported by the boot loader. */
+unsigned long boot_mem_size;
+
+unsigned long ISA_DMA_THRESHOLD;
+unsigned long DMA_MODE_READ, DMA_MODE_WRITE;
+
+#ifdef CONFIG_PPC_MULTIPLATFORM
+int _machine = 0;
+
+extern void prep_init(unsigned long r3, unsigned long r4,
+ unsigned long r5, unsigned long r6, unsigned long r7);
+extern void pmac_init(unsigned long r3, unsigned long r4,
+ unsigned long r5, unsigned long r6, unsigned long r7);
+extern void chrp_init(unsigned long r3, unsigned long r4,
+ unsigned long r5, unsigned long r6, unsigned long r7);
+#endif /* CONFIG_PPC_MULTIPLATFORM */
+
+#ifdef CONFIG_MAGIC_SYSRQ
+unsigned long SYSRQ_KEY = 0x54;
+#endif /* CONFIG_MAGIC_SYSRQ */
+
+#ifdef CONFIG_VGA_CONSOLE
+unsigned long vgacon_remap_base;
+#endif
+
+struct machdep_calls ppc_md;
+
+/*
+ * These are used in binfmt_elf.c to put aux entries on the stack
+ * for each elf executable being started.
+ */
+int dcache_bsize;
+int icache_bsize;
+int ucache_bsize;
+
+#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_FB_VGA16) || \
+ defined(CONFIG_FB_VGA16_MODULE) || defined(CONFIG_FB_VESA)
+struct screen_info screen_info = {
+ 0, 25, /* orig-x, orig-y */
+ 0, /* unused */
+ 0, /* orig-video-page */
+ 0, /* orig-video-mode */
+ 80, /* orig-video-cols */
+ 0,0,0, /* ega_ax, ega_bx, ega_cx */
+ 25, /* orig-video-lines */
+ 1, /* orig-video-isVGA */
+ 16 /* orig-video-points */
+};
+#endif /* CONFIG_VGA_CONSOLE || CONFIG_FB_VGA16 || CONFIG_FB_VESA */
+
+void machine_restart(char *cmd)
+{
+#ifdef CONFIG_NVRAM
+ nvram_sync();
+#endif
+ ppc_md.restart(cmd);
+}
+
+EXPORT_SYMBOL(machine_restart);
+
+void machine_power_off(void)
+{
+#ifdef CONFIG_NVRAM
+ nvram_sync();
+#endif
+ ppc_md.power_off();
+}
+
+EXPORT_SYMBOL(machine_power_off);
+
+void machine_halt(void)
+{
+#ifdef CONFIG_NVRAM
+ nvram_sync();
+#endif
+ ppc_md.halt();
+}
+
+EXPORT_SYMBOL(machine_halt);
+
+void (*pm_power_off)(void) = machine_power_off;
+
+#ifdef CONFIG_TAU
+extern u32 cpu_temp(unsigned long cpu);
+extern u32 cpu_temp_both(unsigned long cpu);
+#endif /* CONFIG_TAU */
+
+int show_cpuinfo(struct seq_file *m, void *v)
+{
+ int i = (int) v - 1;
+ int err = 0;
+ unsigned int pvr;
+ unsigned short maj, min;
+ unsigned long lpj;
+
+ if (i >= NR_CPUS) {
+ /* Show summary information */
+#ifdef CONFIG_SMP
+ unsigned long bogosum = 0;
+ for (i = 0; i < NR_CPUS; ++i)
+ if (cpu_online(i))
+ bogosum += cpu_data[i].loops_per_jiffy;
+ seq_printf(m, "total bogomips\t: %lu.%02lu\n",
+ bogosum/(500000/HZ), bogosum/(5000/HZ) % 100);
+#endif /* CONFIG_SMP */
+
+ if (ppc_md.show_cpuinfo != NULL)
+ err = ppc_md.show_cpuinfo(m);
+ return err;
+ }
+
+#ifdef CONFIG_SMP
+ if (!cpu_online(i))
+ return 0;
+ pvr = cpu_data[i].pvr;
+ lpj = cpu_data[i].loops_per_jiffy;
+#else
+ pvr = mfspr(SPRN_PVR);
+ lpj = loops_per_jiffy;
+#endif
+
+ seq_printf(m, "processor\t: %d\n", i);
+ seq_printf(m, "cpu\t\t: ");
+
+ if (cur_cpu_spec[i]->pvr_mask)
+ seq_printf(m, "%s", cur_cpu_spec[i]->cpu_name);
+ else
+ seq_printf(m, "unknown (%08x)", pvr);
+#ifdef CONFIG_ALTIVEC
+ if (cur_cpu_spec[i]->cpu_features & CPU_FTR_ALTIVEC)
+ seq_printf(m, ", altivec supported");
+#endif
+ seq_printf(m, "\n");
+
+#ifdef CONFIG_TAU
+ if (cur_cpu_spec[i]->cpu_features & CPU_FTR_TAU) {
+#ifdef CONFIG_TAU_AVERAGE
+ /* more straightforward, but potentially misleading */
+ seq_printf(m, "temperature \t: %u C (uncalibrated)\n",
+ cpu_temp(i));
+#else
+ /* show the actual temp sensor range */
+ u32 temp;
+ temp = cpu_temp_both(i);
+ seq_printf(m, "temperature \t: %u-%u C (uncalibrated)\n",
+ temp & 0xff, temp >> 16);
+#endif
+ }
+#endif /* CONFIG_TAU */
+
+ if (ppc_md.show_percpuinfo != NULL) {
+ err = ppc_md.show_percpuinfo(m, i);
+ if (err)
+ return err;
+ }
+
+ switch (PVR_VER(pvr)) {
+ case 0x0020: /* 403 family */
+ maj = PVR_MAJ(pvr) + 1;
+ min = PVR_MIN(pvr);
+ break;
+ case 0x1008: /* 740P/750P ?? */
+ maj = ((pvr >> 8) & 0xFF) - 1;
+ min = pvr & 0xFF;
+ break;
+ case 0x8083: /* e300 */
+ maj = PVR_MAJ(pvr);
+ min = PVR_MIN(pvr);
+ break;
+ case 0x8020: /* e500 */
+ maj = PVR_MAJ(pvr);
+ min = PVR_MIN(pvr);
+ break;
+ default:
+ maj = (pvr >> 8) & 0xFF;
+ min = pvr & 0xFF;
+ break;
+ }
+
+ seq_printf(m, "revision\t: %hd.%hd (pvr %04x %04x)\n",
+ maj, min, PVR_VER(pvr), PVR_REV(pvr));
+
+ seq_printf(m, "bogomips\t: %lu.%02lu\n",
+ lpj / (500000/HZ), (lpj / (5000/HZ)) % 100);
+
+#if defined(CONFIG_85xx) || defined(CONFIG_83xx)
+ if (cur_ppc_sys_spec->ppc_sys_name)
+ seq_printf(m, "chipset\t\t: %s\n",
+ cur_ppc_sys_spec->ppc_sys_name);
+#endif
+
+#ifdef CONFIG_SMP
+ seq_printf(m, "\n");
+#endif
+
+ return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ int i = *pos;
+
+ return i <= NR_CPUS? (void *) (i + 1): NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ ++*pos;
+ return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+struct seq_operations cpuinfo_op = {
+ .start =c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = show_cpuinfo,
+};
+
+/*
+ * We're called here very early in the boot. We determine the machine
+ * type and call the appropriate low-level setup functions.
+ * -- Cort <cort@fsmlabs.com>
+ *
+ * Note that the kernel may be running at an address which is different
+ * from the address that it was linked at, so we must use RELOC/PTRRELOC
+ * to access static data (including strings). -- paulus
+ */
+__init
+unsigned long
+early_init(int r3, int r4, int r5)
+{
+ unsigned long phys;
+ unsigned long offset = reloc_offset();
+
+ /* Default */
+ phys = offset + KERNELBASE;
+
+ /* First zero the BSS -- use memset, some arches don't have
+ * caches on yet */
+ memset_io(PTRRELOC(&__bss_start), 0, _end - __bss_start);
+
+ /*
+ * Identify the CPU type and fix up code sections
+ * that depend on which cpu we have.
+ */
+ identify_cpu(offset, 0);
+ do_cpu_ftr_fixups(offset);
+
+#if defined(CONFIG_PPC_MULTIPLATFORM)
+ reloc_got2(offset);
+
+ /* If we came here from BootX, clear the screen,
+ * set up some pointers and return. */
+ if ((r3 == 0x426f6f58) && (r5 == 0))
+ bootx_init(r4, phys);
+
+ /*
+ * don't do anything on prep
+ * for now, don't use bootinfo because it breaks yaboot 0.5
+ * and assume that if we didn't find a magic number, we have OF
+ */
+ else if (*(unsigned long *)(0) != 0xdeadc0de)
+ phys = prom_init(r3, r4, (prom_entry)r5);
+
+ reloc_got2(-offset);
+#endif
+
+ return phys;
+}
+
+#ifdef CONFIG_PPC_OF
+/*
+ * Assume here that all clock rates are the same in a
+ * smp system. -- Cort
+ */
+int __openfirmware
+of_show_percpuinfo(struct seq_file *m, int i)
+{
+ struct device_node *cpu_node;
+ u32 *fp;
+ int s;
+
+ cpu_node = find_type_devices("cpu");
+ if (!cpu_node)
+ return 0;
+ for (s = 0; s < i && cpu_node->next; s++)
+ cpu_node = cpu_node->next;
+ fp = (u32 *)get_property(cpu_node, "clock-frequency", NULL);
+ if (fp)
+ seq_printf(m, "clock\t\t: %dMHz\n", *fp / 1000000);
+ return 0;
+}
+
+void __init
+intuit_machine_type(void)
+{
+ char *model;
+ struct device_node *root;
+
+ /* ask the OF info if we're a chrp or pmac */
+ root = find_path_device("/");
+ if (root != 0) {
+ /* assume pmac unless proven to be chrp -- Cort */
+ _machine = _MACH_Pmac;
+ model = get_property(root, "device_type", NULL);
+ if (model && !strncmp("chrp", model, 4))
+ _machine = _MACH_chrp;
+ else {
+ model = get_property(root, "model", NULL);
+ if (model && !strncmp(model, "IBM", 3))
+ _machine = _MACH_chrp;
+ }
+ }
+}
+#endif
+
+#ifdef CONFIG_PPC_MULTIPLATFORM
+/*
+ * The PPC_MULTIPLATFORM version of platform_init...
+ */
+void __init
+platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+ unsigned long r6, unsigned long r7)
+{
+#ifdef CONFIG_BOOTX_TEXT
+ if (boot_text_mapped) {
+ btext_clearscreen();
+ btext_welcome();
+ }
+#endif
+
+ parse_bootinfo(find_bootinfo());
+
+ /* if we didn't get any bootinfo telling us what we are... */
+ if (_machine == 0) {
+ /* prep boot loader tells us if we're prep or not */
+ if ( *(unsigned long *)(KERNELBASE) == (0xdeadc0de) )
+ _machine = _MACH_prep;
+ }
+
+ /* not much more to do here, if prep */
+ if (_machine == _MACH_prep) {
+ prep_init(r3, r4, r5, r6, r7);
+ return;
+ }
+
+ /* prom_init has already been called from __start */
+ if (boot_infos)
+ relocate_nodes();
+
+ /* If we aren't PReP, we can find out if we're Pmac
+ * or CHRP with this. */
+ if (_machine == 0)
+ intuit_machine_type();
+
+ /* finish_device_tree may need _machine defined. */
+ finish_device_tree();
+
+ /*
+ * If we were booted via quik, r3 points to the physical
+ * address of the command-line parameters.
+ * If we were booted from an xcoff image (i.e. netbooted or
+ * booted from floppy), we get the command line from the
+ * bootargs property of the /chosen node.
+ * If an initial ramdisk is present, r3 and r4
+ * are used for initrd_start and initrd_size,
+ * otherwise they contain 0xdeadbeef.
+ */
+ if (r3 >= 0x4000 && r3 < 0x800000 && r4 == 0) {
+ strlcpy(cmd_line, (char *)r3 + KERNELBASE,
+ sizeof(cmd_line));
+ } else if (boot_infos != 0) {
+ /* booted by BootX - check for ramdisk */
+ if (boot_infos->kernelParamsOffset != 0)
+ strlcpy(cmd_line, (char *) boot_infos
+ + boot_infos->kernelParamsOffset,
+ sizeof(cmd_line));
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (boot_infos->ramDisk) {
+ initrd_start = (unsigned long) boot_infos
+ + boot_infos->ramDisk;
+ initrd_end = initrd_start + boot_infos->ramDiskSize;
+ initrd_below_start_ok = 1;
+ }
+#endif
+ } else {
+ struct device_node *chosen;
+ char *p;
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (r3 && r4 && r4 != 0xdeadbeef) {
+ if (r3 < KERNELBASE)
+ r3 += KERNELBASE;
+ initrd_start = r3;
+ initrd_end = r3 + r4;
+ ROOT_DEV = Root_RAM0;
+ initrd_below_start_ok = 1;
+ }
+#endif
+ chosen = find_devices("chosen");
+ if (chosen != NULL) {
+ p = get_property(chosen, "bootargs", NULL);
+ if (p && *p) {
+ strlcpy(cmd_line, p, sizeof(cmd_line));
+ }
+ }
+ }
+#ifdef CONFIG_ADB
+ if (strstr(cmd_line, "adb_sync")) {
+ extern int __adb_probe_sync;
+ __adb_probe_sync = 1;
+ }
+#endif /* CONFIG_ADB */
+
+ switch (_machine) {
+ case _MACH_Pmac:
+ pmac_init(r3, r4, r5, r6, r7);
+ break;
+ case _MACH_chrp:
+ chrp_init(r3, r4, r5, r6, r7);
+ break;
+ }
+}
+
+#ifdef CONFIG_SERIAL_CORE_CONSOLE
+extern char *of_stdout_device;
+
+static int __init set_preferred_console(void)
+{
+ struct device_node *prom_stdout;
+ char *name;
+ int offset;
+
+ if (of_stdout_device == NULL)
+ return -ENODEV;
+
+ /* The user has requested a console so this is already set up. */
+ if (strstr(saved_command_line, "console="))
+ return -EBUSY;
+
+ prom_stdout = find_path_device(of_stdout_device);
+ if (!prom_stdout)
+ return -ENODEV;
+
+ name = (char *)get_property(prom_stdout, "name", NULL);
+ if (!name)
+ return -ENODEV;
+
+ if (strcmp(name, "serial") == 0) {
+ int i;
+ u32 *reg = (u32 *)get_property(prom_stdout, "reg", &i);
+ if (i > 8) {
+ switch (reg[1]) {
+ case 0x3f8:
+ offset = 0;
+ break;
+ case 0x2f8:
+ offset = 1;
+ break;
+ case 0x898:
+ offset = 2;
+ break;
+ case 0x890:
+ offset = 3;
+ break;
+ default:
+ /* We dont recognise the serial port */
+ return -ENODEV;
+ }
+ }
+ } else if (strcmp(name, "ch-a") == 0)
+ offset = 0;
+ else if (strcmp(name, "ch-b") == 0)
+ offset = 1;
+ else
+ return -ENODEV;
+ return add_preferred_console("ttyS", offset, NULL);
+}
+console_initcall(set_preferred_console);
+#endif /* CONFIG_SERIAL_CORE_CONSOLE */
+#endif /* CONFIG_PPC_MULTIPLATFORM */
+
+struct bi_record *find_bootinfo(void)
+{
+ struct bi_record *rec;
+
+ rec = (struct bi_record *)_ALIGN((ulong)__bss_start+(1<<20)-1,(1<<20));
+ if ( rec->tag != BI_FIRST ) {
+ /*
+ * This 0x10000 offset is a terrible hack but it will go away when
+ * we have the bootloader handle all the relocation and
+ * prom calls -- Cort
+ */
+ rec = (struct bi_record *)_ALIGN((ulong)__bss_start+0x10000+(1<<20)-1,(1<<20));
+ if ( rec->tag != BI_FIRST )
+ return NULL;
+ }
+ return rec;
+}
+
+void parse_bootinfo(struct bi_record *rec)
+{
+ if (rec == NULL || rec->tag != BI_FIRST)
+ return;
+ while (rec->tag != BI_LAST) {
+ ulong *data = rec->data;
+ switch (rec->tag) {
+ case BI_CMD_LINE:
+ strlcpy(cmd_line, (void *)data, sizeof(cmd_line));
+ break;
+ case BI_SYSMAP:
+ sysmap = (char *)((data[0] >= (KERNELBASE)) ? data[0] :
+ (data[0]+KERNELBASE));
+ sysmap_size = data[1];
+ break;
+#ifdef CONFIG_BLK_DEV_INITRD
+ case BI_INITRD:
+ initrd_start = data[0] + KERNELBASE;
+ initrd_end = data[0] + data[1] + KERNELBASE;
+ break;
+#endif /* CONFIG_BLK_DEV_INITRD */
+#ifdef CONFIG_PPC_MULTIPLATFORM
+ case BI_MACHTYPE:
+ _machine = data[0];
+ break;
+#endif
+ case BI_MEMSIZE:
+ boot_mem_size = data[0];
+ break;
+ }
+ rec = (struct bi_record *)((ulong)rec + rec->size);
+ }
+}
+
+/*
+ * Find out what kind of machine we're on and save any data we need
+ * from the early boot process (devtree is copied on pmac by prom_init()).
+ * This is called very early on the boot process, after a minimal
+ * MMU environment has been set up but before MMU_init is called.
+ */
+void __init
+machine_init(unsigned long r3, unsigned long r4, unsigned long r5,
+ unsigned long r6, unsigned long r7)
+{
+#ifdef CONFIG_CMDLINE
+ strlcpy(cmd_line, CONFIG_CMDLINE, sizeof(cmd_line));
+#endif /* CONFIG_CMDLINE */
+
+#ifdef CONFIG_6xx
+ ppc_md.power_save = ppc6xx_idle;
+#endif
+#ifdef CONFIG_POWER4
+ ppc_md.power_save = power4_idle;
+#endif
+
+ platform_init(r3, r4, r5, r6, r7);
+
+ if (ppc_md.progress)
+ ppc_md.progress("id mach(): done", 0x200);
+}
+
+/* Checks "l2cr=xxxx" command-line option */
+int __init ppc_setup_l2cr(char *str)
+{
+ if (cpu_has_feature(CPU_FTR_L2CR)) {
+ unsigned long val = simple_strtoul(str, NULL, 0);
+ printk(KERN_INFO "l2cr set to %lx\n", val);
+ _set_L2CR(0); /* force invalidate by disable cache */
+ _set_L2CR(val); /* and enable it */
+ }
+ return 1;
+}
+__setup("l2cr=", ppc_setup_l2cr);
+
+#ifdef CONFIG_GENERIC_NVRAM
+
+/* Generic nvram hooks used by drivers/char/gen_nvram.c */
+unsigned char nvram_read_byte(int addr)
+{
+ if (ppc_md.nvram_read_val)
+ return ppc_md.nvram_read_val(addr);
+ return 0xff;
+}
+EXPORT_SYMBOL(nvram_read_byte);
+
+void nvram_write_byte(unsigned char val, int addr)
+{
+ if (ppc_md.nvram_write_val)
+ ppc_md.nvram_write_val(addr, val);
+}
+EXPORT_SYMBOL(nvram_write_byte);
+
+void nvram_sync(void)
+{
+ if (ppc_md.nvram_sync)
+ ppc_md.nvram_sync();
+}
+EXPORT_SYMBOL(nvram_sync);
+
+#endif /* CONFIG_NVRAM */
+
+static struct cpu cpu_devices[NR_CPUS];
+
+int __init ppc_init(void)
+{
+ int i;
+
+ /* clear the progress line */
+ if ( ppc_md.progress ) ppc_md.progress(" ", 0xffff);
+
+ /* register CPU devices */
+ for (i = 0; i < NR_CPUS; i++)
+ if (cpu_possible(i))
+ register_cpu(&cpu_devices[i], i, NULL);
+
+ /* call platform init */
+ if (ppc_md.init != NULL) {
+ ppc_md.init();
+ }
+ return 0;
+}
+
+arch_initcall(ppc_init);
+
+/* Warning, IO base is not yet inited */
+void __init setup_arch(char **cmdline_p)
+{
+ extern char *klimit;
+ extern void do_init_bootmem(void);
+
+ /* so udelay does something sensible, assume <= 1000 bogomips */
+ loops_per_jiffy = 500000000 / HZ;
+
+#ifdef CONFIG_PPC_MULTIPLATFORM
+ /* This could be called "early setup arch", it must be done
+ * now because xmon need it
+ */
+ if (_machine == _MACH_Pmac)
+ pmac_feature_init(); /* New cool way */
+#endif
+
+#ifdef CONFIG_XMON
+ xmon_map_scc();
+ if (strstr(cmd_line, "xmon"))
+ xmon(NULL);
+#endif /* CONFIG_XMON */
+ if ( ppc_md.progress ) ppc_md.progress("setup_arch: enter", 0x3eab);
+
+#if defined(CONFIG_KGDB)
+ if (ppc_md.kgdb_map_scc)
+ ppc_md.kgdb_map_scc();
+ set_debug_traps();
+ if (strstr(cmd_line, "gdb")) {
+ if (ppc_md.progress)
+ ppc_md.progress("setup_arch: kgdb breakpoint", 0x4000);
+ printk("kgdb breakpoint activated\n");
+ breakpoint();
+ }
+#endif
+
+ /*
+ * Set cache line size based on type of cpu as a default.
+ * Systems with OF can look in the properties on the cpu node(s)
+ * for a possibly more accurate value.
+ */
+ if (cpu_has_feature(CPU_FTR_SPLIT_ID_CACHE)) {
+ dcache_bsize = cur_cpu_spec[0]->dcache_bsize;
+ icache_bsize = cur_cpu_spec[0]->icache_bsize;
+ ucache_bsize = 0;
+ } else
+ ucache_bsize = dcache_bsize = icache_bsize
+ = cur_cpu_spec[0]->dcache_bsize;
+
+ /* reboot on panic */
+ panic_timeout = 180;
+
+ init_mm.start_code = PAGE_OFFSET;
+ init_mm.end_code = (unsigned long) _etext;
+ init_mm.end_data = (unsigned long) _edata;
+ init_mm.brk = (unsigned long) klimit;
+
+ /* Save unparsed command line copy for /proc/cmdline */
+ strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE);
+ *cmdline_p = cmd_line;
+
+ /* set up the bootmem stuff with available memory */
+ do_init_bootmem();
+ if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab);
+
+#ifdef CONFIG_PPC_OCP
+ /* Initialize OCP device list */
+ ocp_early_init();
+ if ( ppc_md.progress ) ppc_md.progress("ocp: exit", 0x3eab);
+#endif
+
+#ifdef CONFIG_DUMMY_CONSOLE
+ conswitchp = &dummy_con;
+#endif
+
+ ppc_md.setup_arch();
+ if ( ppc_md.progress ) ppc_md.progress("arch: exit", 0x3eab);
+
+ paging_init();
+
+ /* this is for modules since _machine can be a define -- Cort */
+ ppc_md.ppc_machine = _machine;
+}
diff --git a/arch/ppc/kernel/signal.c b/arch/ppc/kernel/signal.c
new file mode 100644
index 000000000000..9567d3041ea7
--- /dev/null
+++ b/arch/ppc/kernel/signal.c
@@ -0,0 +1,775 @@
+/*
+ * arch/ppc/kernel/signal.c
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/i386/kernel/signal.c"
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/elf.h>
+#include <linux/tty.h>
+#include <linux/binfmts.h>
+#include <linux/suspend.h>
+#include <asm/ucontext.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+#undef DEBUG_SIG
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+extern void sigreturn_exit(struct pt_regs *);
+
+#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
+
+int do_signal(sigset_t *oldset, struct pt_regs *regs);
+
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+int
+sys_sigsuspend(old_sigset_t mask, int p2, int p3, int p4, int p6, int p7,
+ struct pt_regs *regs)
+{
+ sigset_t saveset;
+
+ mask &= _BLOCKABLE;
+ spin_lock_irq(&current->sighand->siglock);
+ saveset = current->blocked;
+ siginitset(&current->blocked, mask);
+ recalc_sigpending();
+ spin_unlock_irq(&current->sighand->siglock);
+
+ regs->result = -EINTR;
+ regs->gpr[3] = EINTR;
+ regs->ccr |= 0x10000000;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(&saveset, regs))
+ sigreturn_exit(regs);
+ }
+}
+
+int
+sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, int p3, int p4,
+ int p6, int p7, struct pt_regs *regs)
+{
+ sigset_t saveset, newset;
+
+ /* XXX: Don't preclude handling different sized sigset_t's. */
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+
+ if (copy_from_user(&newset, unewset, sizeof(newset)))
+ return -EFAULT;
+ sigdelsetmask(&newset, ~_BLOCKABLE);
+
+ spin_lock_irq(&current->sighand->siglock);
+ saveset = current->blocked;
+ current->blocked = newset;
+ recalc_sigpending();
+ spin_unlock_irq(&current->sighand->siglock);
+
+ regs->result = -EINTR;
+ regs->gpr[3] = EINTR;
+ regs->ccr |= 0x10000000;
+ while (1) {
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ if (do_signal(&saveset, regs))
+ sigreturn_exit(regs);
+ }
+}
+
+
+int
+sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, int r5,
+ int r6, int r7, int r8, struct pt_regs *regs)
+{
+ return do_sigaltstack(uss, uoss, regs->gpr[1]);
+}
+
+int
+sys_sigaction(int sig, const struct old_sigaction __user *act,
+ struct old_sigaction __user *oact)
+{
+ struct k_sigaction new_ka, old_ka;
+ int ret;
+
+ if (act) {
+ old_sigset_t mask;
+ if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
+ __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
+ __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+ return -EFAULT;
+ __get_user(new_ka.sa.sa_flags, &act->sa_flags);
+ __get_user(mask, &act->sa_mask);
+ siginitset(&new_ka.sa.sa_mask, mask);
+ }
+
+ ret = do_sigaction(sig, (act? &new_ka: NULL), (oact? &old_ka: NULL));
+
+ if (!ret && oact) {
+ if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
+ __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
+ __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+ return -EFAULT;
+ __put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+ __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+ }
+
+ return ret;
+}
+
+/*
+ * When we have signals to deliver, we set up on the
+ * user stack, going down from the original stack pointer:
+ * a sigregs struct
+ * a sigcontext struct
+ * a gap of __SIGNAL_FRAMESIZE bytes
+ *
+ * Each of these things must be a multiple of 16 bytes in size.
+ *
+ */
+struct sigregs {
+ struct mcontext mctx; /* all the register values */
+ /* Programs using the rs6000/xcoff abi can save up to 19 gp regs
+ and 18 fp regs below sp before decrementing it. */
+ int abigap[56];
+};
+
+/* We use the mc_pad field for the signal return trampoline. */
+#define tramp mc_pad
+
+/*
+ * When we have rt signals to deliver, we set up on the
+ * user stack, going down from the original stack pointer:
+ * one rt_sigframe struct (siginfo + ucontext + ABI gap)
+ * a gap of __SIGNAL_FRAMESIZE+16 bytes
+ * (the +16 is to get the siginfo and ucontext in the same
+ * positions as in older kernels).
+ *
+ * Each of these things must be a multiple of 16 bytes in size.
+ *
+ */
+struct rt_sigframe
+{
+ struct siginfo info;
+ struct ucontext uc;
+ /* Programs using the rs6000/xcoff abi can save up to 19 gp regs
+ and 18 fp regs below sp before decrementing it. */
+ int abigap[56];
+};
+
+/*
+ * Save the current user registers on the user stack.
+ * We only save the altivec/spe registers if the process has used
+ * altivec/spe instructions at some point.
+ */
+static int
+save_user_regs(struct pt_regs *regs, struct mcontext __user *frame, int sigret)
+{
+ /* save general and floating-point registers */
+ CHECK_FULL_REGS(regs);
+ preempt_disable();
+ if (regs->msr & MSR_FP)
+ giveup_fpu(current);
+#ifdef CONFIG_ALTIVEC
+ if (current->thread.used_vr && (regs->msr & MSR_VEC))
+ giveup_altivec(current);
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ if (current->thread.used_spe && (regs->msr & MSR_SPE))
+ giveup_spe(current);
+#endif /* CONFIG_ALTIVEC */
+ preempt_enable();
+
+ if (__copy_to_user(&frame->mc_gregs, regs, GP_REGS_SIZE)
+ || __copy_to_user(&frame->mc_fregs, current->thread.fpr,
+ ELF_NFPREG * sizeof(double)))
+ return 1;
+
+ current->thread.fpscr = 0; /* turn off all fp exceptions */
+
+#ifdef CONFIG_ALTIVEC
+ /* save altivec registers */
+ if (current->thread.used_vr) {
+ if (__copy_to_user(&frame->mc_vregs, current->thread.vr,
+ ELF_NVRREG * sizeof(vector128)))
+ return 1;
+ /* set MSR_VEC in the saved MSR value to indicate that
+ frame->mc_vregs contains valid data */
+ if (__put_user(regs->msr | MSR_VEC, &frame->mc_gregs[PT_MSR]))
+ return 1;
+ }
+ /* else assert((regs->msr & MSR_VEC) == 0) */
+
+ /* We always copy to/from vrsave, it's 0 if we don't have or don't
+ * use altivec. Since VSCR only contains 32 bits saved in the least
+ * significant bits of a vector, we "cheat" and stuff VRSAVE in the
+ * most significant bits of that same vector. --BenH
+ */
+ if (__put_user(current->thread.vrsave, (u32 __user *)&frame->mc_vregs[32]))
+ return 1;
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_SPE
+ /* save spe registers */
+ if (current->thread.used_spe) {
+ if (__copy_to_user(&frame->mc_vregs, current->thread.evr,
+ ELF_NEVRREG * sizeof(u32)))
+ return 1;
+ /* set MSR_SPE in the saved MSR value to indicate that
+ frame->mc_vregs contains valid data */
+ if (__put_user(regs->msr | MSR_SPE, &frame->mc_gregs[PT_MSR]))
+ return 1;
+ }
+ /* else assert((regs->msr & MSR_SPE) == 0) */
+
+ /* We always copy to/from spefscr */
+ if (__put_user(current->thread.spefscr, (u32 *)&frame->mc_vregs + ELF_NEVRREG))
+ return 1;
+#endif /* CONFIG_SPE */
+
+ if (sigret) {
+ /* Set up the sigreturn trampoline: li r0,sigret; sc */
+ if (__put_user(0x38000000UL + sigret, &frame->tramp[0])
+ || __put_user(0x44000002UL, &frame->tramp[1]))
+ return 1;
+ flush_icache_range((unsigned long) &frame->tramp[0],
+ (unsigned long) &frame->tramp[2]);
+ }
+
+ return 0;
+}
+
+/*
+ * Restore the current user register values from the user stack,
+ * (except for MSR).
+ */
+static int
+restore_user_regs(struct pt_regs *regs, struct mcontext __user *sr, int sig)
+{
+ unsigned long save_r2 = 0;
+#if defined(CONFIG_ALTIVEC) || defined(CONFIG_SPE)
+ unsigned long msr;
+#endif
+
+ /* backup/restore the TLS as we don't want it to be modified */
+ if (!sig)
+ save_r2 = regs->gpr[2];
+ /* copy up to but not including MSR */
+ if (__copy_from_user(regs, &sr->mc_gregs, PT_MSR * sizeof(elf_greg_t)))
+ return 1;
+ /* copy from orig_r3 (the word after the MSR) up to the end */
+ if (__copy_from_user(&regs->orig_gpr3, &sr->mc_gregs[PT_ORIG_R3],
+ GP_REGS_SIZE - PT_ORIG_R3 * sizeof(elf_greg_t)))
+ return 1;
+ if (!sig)
+ regs->gpr[2] = save_r2;
+
+ /* force the process to reload the FP registers from
+ current->thread when it next does FP instructions */
+ regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1);
+ if (__copy_from_user(current->thread.fpr, &sr->mc_fregs,
+ sizeof(sr->mc_fregs)))
+ return 1;
+
+#ifdef CONFIG_ALTIVEC
+ /* force the process to reload the altivec registers from
+ current->thread when it next does altivec instructions */
+ regs->msr &= ~MSR_VEC;
+ if (!__get_user(msr, &sr->mc_gregs[PT_MSR]) && (msr & MSR_VEC) != 0) {
+ /* restore altivec registers from the stack */
+ if (__copy_from_user(current->thread.vr, &sr->mc_vregs,
+ sizeof(sr->mc_vregs)))
+ return 1;
+ } else if (current->thread.used_vr)
+ memset(&current->thread.vr, 0, ELF_NVRREG * sizeof(vector128));
+
+ /* Always get VRSAVE back */
+ if (__get_user(current->thread.vrsave, (u32 __user *)&sr->mc_vregs[32]))
+ return 1;
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_SPE
+ /* force the process to reload the spe registers from
+ current->thread when it next does spe instructions */
+ regs->msr &= ~MSR_SPE;
+ if (!__get_user(msr, &sr->mc_gregs[PT_MSR]) && (msr & MSR_SPE) != 0) {
+ /* restore spe registers from the stack */
+ if (__copy_from_user(current->thread.evr, &sr->mc_vregs,
+ ELF_NEVRREG * sizeof(u32)))
+ return 1;
+ } else if (current->thread.used_spe)
+ memset(&current->thread.evr, 0, ELF_NEVRREG * sizeof(u32));
+
+ /* Always get SPEFSCR back */
+ if (__get_user(current->thread.spefscr, (u32 *)&sr->mc_vregs + ELF_NEVRREG))
+ return 1;
+#endif /* CONFIG_SPE */
+
+#ifndef CONFIG_SMP
+ preempt_disable();
+ if (last_task_used_math == current)
+ last_task_used_math = NULL;
+ if (last_task_used_altivec == current)
+ last_task_used_altivec = NULL;
+ if (last_task_used_spe == current)
+ last_task_used_spe = NULL;
+ preempt_enable();
+#endif
+ return 0;
+}
+
+/*
+ * Restore the user process's signal mask
+ */
+static void
+restore_sigmask(sigset_t *set)
+{
+ sigdelsetmask(set, ~_BLOCKABLE);
+ spin_lock_irq(&current->sighand->siglock);
+ current->blocked = *set;
+ recalc_sigpending();
+ spin_unlock_irq(&current->sighand->siglock);
+}
+
+/*
+ * Set up a signal frame for a "real-time" signal handler
+ * (one which gets siginfo).
+ */
+static void
+handle_rt_signal(unsigned long sig, struct k_sigaction *ka,
+ siginfo_t *info, sigset_t *oldset, struct pt_regs * regs,
+ unsigned long newsp)
+{
+ struct rt_sigframe __user *rt_sf;
+ struct mcontext __user *frame;
+ unsigned long origsp = newsp;
+
+ /* Set up Signal Frame */
+ /* Put a Real Time Context onto stack */
+ newsp -= sizeof(*rt_sf);
+ rt_sf = (struct rt_sigframe __user *) newsp;
+
+ /* create a stack frame for the caller of the handler */
+ newsp -= __SIGNAL_FRAMESIZE + 16;
+
+ if (!access_ok(VERIFY_WRITE, (void __user *) newsp, origsp - newsp))
+ goto badframe;
+
+ /* Put the siginfo & fill in most of the ucontext */
+ if (copy_siginfo_to_user(&rt_sf->info, info)
+ || __put_user(0, &rt_sf->uc.uc_flags)
+ || __put_user(0, &rt_sf->uc.uc_link)
+ || __put_user(current->sas_ss_sp, &rt_sf->uc.uc_stack.ss_sp)
+ || __put_user(sas_ss_flags(regs->gpr[1]),
+ &rt_sf->uc.uc_stack.ss_flags)
+ || __put_user(current->sas_ss_size, &rt_sf->uc.uc_stack.ss_size)
+ || __put_user(&rt_sf->uc.uc_mcontext, &rt_sf->uc.uc_regs)
+ || __copy_to_user(&rt_sf->uc.uc_sigmask, oldset, sizeof(*oldset)))
+ goto badframe;
+
+ /* Save user registers on the stack */
+ frame = &rt_sf->uc.uc_mcontext;
+ if (save_user_regs(regs, frame, __NR_rt_sigreturn))
+ goto badframe;
+
+ if (put_user(regs->gpr[1], (unsigned long __user *)newsp))
+ goto badframe;
+ regs->gpr[1] = newsp;
+ regs->gpr[3] = sig;
+ regs->gpr[4] = (unsigned long) &rt_sf->info;
+ regs->gpr[5] = (unsigned long) &rt_sf->uc;
+ regs->gpr[6] = (unsigned long) rt_sf;
+ regs->nip = (unsigned long) ka->sa.sa_handler;
+ regs->link = (unsigned long) frame->tramp;
+ regs->trap = 0;
+
+ return;
+
+badframe:
+#ifdef DEBUG_SIG
+ printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n",
+ regs, frame, newsp);
+#endif
+ force_sigsegv(sig, current);
+}
+
+static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int sig)
+{
+ sigset_t set;
+ struct mcontext __user *mcp;
+
+ if (__copy_from_user(&set, &ucp->uc_sigmask, sizeof(set))
+ || __get_user(mcp, &ucp->uc_regs))
+ return -EFAULT;
+ restore_sigmask(&set);
+ if (restore_user_regs(regs, mcp, sig))
+ return -EFAULT;
+
+ return 0;
+}
+
+int sys_swapcontext(struct ucontext __user *old_ctx,
+ struct ucontext __user *new_ctx,
+ int ctx_size, int r6, int r7, int r8, struct pt_regs *regs)
+{
+ unsigned char tmp;
+
+ /* Context size is for future use. Right now, we only make sure
+ * we are passed something we understand
+ */
+ if (ctx_size < sizeof(struct ucontext))
+ return -EINVAL;
+
+ if (old_ctx != NULL) {
+ if (!access_ok(VERIFY_WRITE, old_ctx, sizeof(*old_ctx))
+ || save_user_regs(regs, &old_ctx->uc_mcontext, 0)
+ || __copy_to_user(&old_ctx->uc_sigmask,
+ &current->blocked, sizeof(sigset_t))
+ || __put_user(&old_ctx->uc_mcontext, &old_ctx->uc_regs))
+ return -EFAULT;
+ }
+ if (new_ctx == NULL)
+ return 0;
+ if (!access_ok(VERIFY_READ, new_ctx, sizeof(*new_ctx))
+ || __get_user(tmp, (u8 __user *) new_ctx)
+ || __get_user(tmp, (u8 __user *) (new_ctx + 1) - 1))
+ return -EFAULT;
+
+ /*
+ * If we get a fault copying the context into the kernel's
+ * image of the user's registers, we can't just return -EFAULT
+ * because the user's registers will be corrupted. For instance
+ * the NIP value may have been updated but not some of the
+ * other registers. Given that we have done the access_ok
+ * and successfully read the first and last bytes of the region
+ * above, this should only happen in an out-of-memory situation
+ * or if another thread unmaps the region containing the context.
+ * We kill the task with a SIGSEGV in this situation.
+ */
+ if (do_setcontext(new_ctx, regs, 0))
+ do_exit(SIGSEGV);
+ sigreturn_exit(regs);
+ /* doesn't actually return back to here */
+ return 0;
+}
+
+int sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
+ struct pt_regs *regs)
+{
+ struct rt_sigframe __user *rt_sf;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+ rt_sf = (struct rt_sigframe __user *)
+ (regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
+ if (!access_ok(VERIFY_READ, rt_sf, sizeof(struct rt_sigframe)))
+ goto bad;
+ if (do_setcontext(&rt_sf->uc, regs, 1))
+ goto bad;
+
+ /*
+ * It's not clear whether or why it is desirable to save the
+ * sigaltstack setting on signal delivery and restore it on
+ * signal return. But other architectures do this and we have
+ * always done it up until now so it is probably better not to
+ * change it. -- paulus
+ */
+ do_sigaltstack(&rt_sf->uc.uc_stack, NULL, regs->gpr[1]);
+
+ sigreturn_exit(regs); /* doesn't return here */
+ return 0;
+
+ bad:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+int sys_debug_setcontext(struct ucontext __user *ctx,
+ int ndbg, struct sig_dbg_op *dbg,
+ int r6, int r7, int r8,
+ struct pt_regs *regs)
+{
+ struct sig_dbg_op op;
+ int i;
+ unsigned long new_msr = regs->msr;
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ unsigned long new_dbcr0 = current->thread.dbcr0;
+#endif
+
+ for (i=0; i<ndbg; i++) {
+ if (__copy_from_user(&op, dbg, sizeof(op)))
+ return -EFAULT;
+ switch (op.dbg_type) {
+ case SIG_DBG_SINGLE_STEPPING:
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ if (op.dbg_value) {
+ new_msr |= MSR_DE;
+ new_dbcr0 |= (DBCR0_IDM | DBCR0_IC);
+ } else {
+ new_msr &= ~MSR_DE;
+ new_dbcr0 &= ~(DBCR0_IDM | DBCR0_IC);
+ }
+#else
+ if (op.dbg_value)
+ new_msr |= MSR_SE;
+ else
+ new_msr &= ~MSR_SE;
+#endif
+ break;
+ case SIG_DBG_BRANCH_TRACING:
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ return -EINVAL;
+#else
+ if (op.dbg_value)
+ new_msr |= MSR_BE;
+ else
+ new_msr &= ~MSR_BE;
+#endif
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ }
+
+ /* We wait until here to actually install the values in the
+ registers so if we fail in the above loop, it will not
+ affect the contents of these registers. After this point,
+ failure is a problem, anyway, and it's very unlikely unless
+ the user is really doing something wrong. */
+ regs->msr = new_msr;
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+ current->thread.dbcr0 = new_dbcr0;
+#endif
+
+ /*
+ * If we get a fault copying the context into the kernel's
+ * image of the user's registers, we can't just return -EFAULT
+ * because the user's registers will be corrupted. For instance
+ * the NIP value may have been updated but not some of the
+ * other registers. Given that we have done the access_ok
+ * and successfully read the first and last bytes of the region
+ * above, this should only happen in an out-of-memory situation
+ * or if another thread unmaps the region containing the context.
+ * We kill the task with a SIGSEGV in this situation.
+ */
+ if (do_setcontext(ctx, regs, 1)) {
+ force_sig(SIGSEGV, current);
+ goto out;
+ }
+
+ /*
+ * It's not clear whether or why it is desirable to save the
+ * sigaltstack setting on signal delivery and restore it on
+ * signal return. But other architectures do this and we have
+ * always done it up until now so it is probably better not to
+ * change it. -- paulus
+ */
+ do_sigaltstack(&ctx->uc_stack, NULL, regs->gpr[1]);
+
+ sigreturn_exit(regs);
+ /* doesn't actually return back to here */
+
+ out:
+ return 0;
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+static void
+handle_signal(unsigned long sig, struct k_sigaction *ka,
+ siginfo_t *info, sigset_t *oldset, struct pt_regs * regs,
+ unsigned long newsp)
+{
+ struct sigcontext __user *sc;
+ struct sigregs __user *frame;
+ unsigned long origsp = newsp;
+
+ /* Set up Signal Frame */
+ newsp -= sizeof(struct sigregs);
+ frame = (struct sigregs __user *) newsp;
+
+ /* Put a sigcontext on the stack */
+ newsp -= sizeof(*sc);
+ sc = (struct sigcontext __user *) newsp;
+
+ /* create a stack frame for the caller of the handler */
+ newsp -= __SIGNAL_FRAMESIZE;
+
+ if (!access_ok(VERIFY_WRITE, (void __user *) newsp, origsp - newsp))
+ goto badframe;
+
+#if _NSIG != 64
+#error "Please adjust handle_signal()"
+#endif
+ if (__put_user((unsigned long) ka->sa.sa_handler, &sc->handler)
+ || __put_user(oldset->sig[0], &sc->oldmask)
+ || __put_user(oldset->sig[1], &sc->_unused[3])
+ || __put_user((struct pt_regs *)frame, &sc->regs)
+ || __put_user(sig, &sc->signal))
+ goto badframe;
+
+ if (save_user_regs(regs, &frame->mctx, __NR_sigreturn))
+ goto badframe;
+
+ if (put_user(regs->gpr[1], (unsigned long __user *)newsp))
+ goto badframe;
+ regs->gpr[1] = newsp;
+ regs->gpr[3] = sig;
+ regs->gpr[4] = (unsigned long) sc;
+ regs->nip = (unsigned long) ka->sa.sa_handler;
+ regs->link = (unsigned long) frame->mctx.tramp;
+ regs->trap = 0;
+
+ return;
+
+badframe:
+#ifdef DEBUG_SIG
+ printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n",
+ regs, frame, newsp);
+#endif
+ force_sigsegv(sig, current);
+}
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+int sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
+ struct pt_regs *regs)
+{
+ struct sigcontext __user *sc;
+ struct sigcontext sigctx;
+ struct mcontext __user *sr;
+ sigset_t set;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+ sc = (struct sigcontext __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+ if (copy_from_user(&sigctx, sc, sizeof(sigctx)))
+ goto badframe;
+
+ set.sig[0] = sigctx.oldmask;
+ set.sig[1] = sigctx._unused[3];
+ restore_sigmask(&set);
+
+ sr = (struct mcontext __user *) sigctx.regs;
+ if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
+ || restore_user_regs(regs, sr, 1))
+ goto badframe;
+
+ sigreturn_exit(regs); /* doesn't return */
+ return 0;
+
+badframe:
+ force_sig(SIGSEGV, current);
+ return 0;
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+int do_signal(sigset_t *oldset, struct pt_regs *regs)
+{
+ siginfo_t info;
+ struct k_sigaction ka;
+ unsigned long frame, newsp;
+ int signr, ret;
+
+ if (current->flags & PF_FREEZE) {
+ refrigerator(PF_FREEZE);
+ signr = 0;
+ ret = regs->gpr[3];
+ if (!signal_pending(current))
+ goto no_signal;
+ }
+
+ if (!oldset)
+ oldset = &current->blocked;
+
+ newsp = frame = 0;
+
+ signr = get_signal_to_deliver(&info, &ka, regs, NULL);
+
+ if (TRAP(regs) == 0x0C00 /* System Call! */
+ && regs->ccr & 0x10000000 /* error signalled */
+ && ((ret = regs->gpr[3]) == ERESTARTSYS
+ || ret == ERESTARTNOHAND || ret == ERESTARTNOINTR
+ || ret == ERESTART_RESTARTBLOCK)) {
+
+ if (signr > 0
+ && (ret == ERESTARTNOHAND || ret == ERESTART_RESTARTBLOCK
+ || (ret == ERESTARTSYS
+ && !(ka.sa.sa_flags & SA_RESTART)))) {
+ /* make the system call return an EINTR error */
+ regs->result = -EINTR;
+ regs->gpr[3] = EINTR;
+ /* note that the cr0.SO bit is already set */
+ } else {
+no_signal:
+ regs->nip -= 4; /* Back up & retry system call */
+ regs->result = 0;
+ regs->trap = 0;
+ if (ret == ERESTART_RESTARTBLOCK)
+ regs->gpr[0] = __NR_restart_syscall;
+ else
+ regs->gpr[3] = regs->orig_gpr3;
+ }
+ }
+
+ if (signr == 0)
+ return 0; /* no signals delivered */
+
+ if ((ka.sa.sa_flags & SA_ONSTACK) && current->sas_ss_size
+ && !on_sig_stack(regs->gpr[1]))
+ newsp = current->sas_ss_sp + current->sas_ss_size;
+ else
+ newsp = regs->gpr[1];
+ newsp &= ~0xfUL;
+
+ /* Whee! Actually deliver the signal. */
+ if (ka.sa.sa_flags & SA_SIGINFO)
+ handle_rt_signal(signr, &ka, &info, oldset, regs, newsp);
+ else
+ handle_signal(signr, &ka, &info, oldset, regs, newsp);
+
+ if (!(ka.sa.sa_flags & SA_NODEFER)) {
+ spin_lock_irq(&current->sighand->siglock);
+ sigorsets(&current->blocked,&current->blocked,&ka.sa.sa_mask);
+ sigaddset(&current->blocked, signr);
+ recalc_sigpending();
+ spin_unlock_irq(&current->sighand->siglock);
+ }
+
+ return 1;
+}
+
diff --git a/arch/ppc/kernel/smp-tbsync.c b/arch/ppc/kernel/smp-tbsync.c
new file mode 100644
index 000000000000..2c9cd95bcea6
--- /dev/null
+++ b/arch/ppc/kernel/smp-tbsync.c
@@ -0,0 +1,181 @@
+/*
+ * Smp timebase synchronization for ppc.
+ *
+ * Copyright (C) 2003 Samuel Rydh (samuel@ibrium.se)
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/unistd.h>
+#include <linux/init.h>
+#include <asm/atomic.h>
+#include <asm/smp.h>
+#include <asm/time.h>
+
+#define NUM_ITER 300
+
+enum {
+ kExit=0, kSetAndTest, kTest
+};
+
+static struct {
+ volatile int tbu;
+ volatile int tbl;
+ volatile int mark;
+ volatile int cmd;
+ volatile int handshake;
+ int filler[3];
+
+ volatile int ack;
+ int filler2[7];
+
+ volatile int race_result;
+} *tbsync;
+
+static volatile int running;
+
+static void __devinit
+enter_contest( int mark, int add )
+{
+ while( (int)(get_tbl() - mark) < 0 )
+ tbsync->race_result = add;
+}
+
+void __devinit
+smp_generic_take_timebase( void )
+{
+ int cmd, tbl, tbu;
+
+ local_irq_disable();
+ while( !running )
+ ;
+ rmb();
+
+ for( ;; ) {
+ tbsync->ack = 1;
+ while( !tbsync->handshake )
+ ;
+ rmb();
+
+ cmd = tbsync->cmd;
+ tbl = tbsync->tbl;
+ tbu = tbsync->tbu;
+ tbsync->ack = 0;
+ if( cmd == kExit )
+ return;
+
+ if( cmd == kSetAndTest ) {
+ while( tbsync->handshake )
+ ;
+ asm volatile ("mttbl %0" :: "r" (tbl) );
+ asm volatile ("mttbu %0" :: "r" (tbu) );
+ } else {
+ while( tbsync->handshake )
+ ;
+ }
+ enter_contest( tbsync->mark, -1 );
+ }
+ local_irq_enable();
+}
+
+static int __devinit
+start_contest( int cmd, int offset, int num )
+{
+ int i, tbu, tbl, mark, score=0;
+
+ tbsync->cmd = cmd;
+
+ local_irq_disable();
+ for( i=-3; i<num; ) {
+ tbl = get_tbl() + 400;
+ tbsync->tbu = tbu = get_tbu();
+ tbsync->tbl = tbl + offset;
+ tbsync->mark = mark = tbl + 400;
+
+ wmb();
+
+ tbsync->handshake = 1;
+ while( tbsync->ack )
+ ;
+
+ while( (int)(get_tbl() - tbl) <= 0 )
+ ;
+ tbsync->handshake = 0;
+ enter_contest( mark, 1 );
+
+ while( !tbsync->ack )
+ ;
+
+ if( tbsync->tbu != get_tbu() || ((tbsync->tbl ^ get_tbl()) & 0x80000000) )
+ continue;
+ if( i++ > 0 )
+ score += tbsync->race_result;
+ }
+ local_irq_enable();
+ return score;
+}
+
+void __devinit
+smp_generic_give_timebase( void )
+{
+ int i, score, score2, old, min=0, max=5000, offset=1000;
+
+ printk("Synchronizing timebase\n");
+
+ /* if this fails then this kernel won't work anyway... */
+ tbsync = kmalloc( sizeof(*tbsync), GFP_KERNEL );
+ memset( tbsync, 0, sizeof(*tbsync) );
+ mb();
+ running = 1;
+
+ while( !tbsync->ack )
+ ;
+
+ /* binary search */
+ for( old=-1 ; old != offset ; offset=(min+max)/2 ) {
+ score = start_contest( kSetAndTest, offset, NUM_ITER );
+
+ printk("score %d, offset %d\n", score, offset );
+
+ if( score > 0 )
+ max = offset;
+ else
+ min = offset;
+ old = offset;
+ }
+ score = start_contest( kSetAndTest, min, NUM_ITER );
+ score2 = start_contest( kSetAndTest, max, NUM_ITER );
+
+ printk( "Min %d (score %d), Max %d (score %d)\n", min, score, max, score2 );
+ score = abs( score );
+ score2 = abs( score2 );
+ offset = (score < score2) ? min : max;
+
+ /* guard against inaccurate mttb */
+ for( i=0; i<10; i++ ) {
+ start_contest( kSetAndTest, offset, NUM_ITER/10 );
+
+ if( (score2=start_contest(kTest, offset, NUM_ITER)) < 0 )
+ score2 = -score2;
+ if( score2 <= score || score2 < 20 )
+ break;
+ }
+ printk("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
+
+ /* exiting */
+ tbsync->cmd = kExit;
+ wmb();
+ tbsync->handshake = 1;
+ while( tbsync->ack )
+ ;
+ tbsync->handshake = 0;
+ kfree( tbsync );
+ tbsync = NULL;
+ running = 0;
+
+ /* all done */
+ smp_tb_synchronized = 1;
+}
diff --git a/arch/ppc/kernel/smp.c b/arch/ppc/kernel/smp.c
new file mode 100644
index 000000000000..e70b587b9e51
--- /dev/null
+++ b/arch/ppc/kernel/smp.c
@@ -0,0 +1,399 @@
+/*
+ * Smp support for ppc.
+ *
+ * Written by Cort Dougan (cort@cs.nmt.edu) borrowing a great
+ * deal of code from the sparc and intel versions.
+ *
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ *
+ */
+
+#include <linux/config.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/cache.h>
+
+#include <asm/ptrace.h>
+#include <asm/atomic.h>
+#include <asm/irq.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/smp.h>
+#include <asm/residual.h>
+#include <asm/time.h>
+#include <asm/thread_info.h>
+#include <asm/tlbflush.h>
+#include <asm/xmon.h>
+
+volatile int smp_commenced;
+int smp_tb_synchronized;
+struct cpuinfo_PPC cpu_data[NR_CPUS];
+struct klock_info_struct klock_info = { KLOCK_CLEAR, 0 };
+atomic_t ipi_recv;
+atomic_t ipi_sent;
+cpumask_t cpu_online_map;
+cpumask_t cpu_possible_map;
+int smp_hw_index[NR_CPUS];
+struct thread_info *secondary_ti;
+
+EXPORT_SYMBOL(cpu_online_map);
+EXPORT_SYMBOL(cpu_possible_map);
+
+/* SMP operations for this machine */
+static struct smp_ops_t *smp_ops;
+
+/* all cpu mappings are 1-1 -- Cort */
+volatile unsigned long cpu_callin_map[NR_CPUS];
+
+int start_secondary(void *);
+void smp_call_function_interrupt(void);
+static int __smp_call_function(void (*func) (void *info), void *info,
+ int wait, int target);
+
+/* Low level assembly function used to backup CPU 0 state */
+extern void __save_cpu_setup(void);
+
+/* Since OpenPIC has only 4 IPIs, we use slightly different message numbers.
+ *
+ * Make sure this matches openpic_request_IPIs in open_pic.c, or what shows up
+ * in /proc/interrupts will be wrong!!! --Troy */
+#define PPC_MSG_CALL_FUNCTION 0
+#define PPC_MSG_RESCHEDULE 1
+#define PPC_MSG_INVALIDATE_TLB 2
+#define PPC_MSG_XMON_BREAK 3
+
+static inline void
+smp_message_pass(int target, int msg, unsigned long data, int wait)
+{
+ if (smp_ops){
+ atomic_inc(&ipi_sent);
+ smp_ops->message_pass(target,msg,data,wait);
+ }
+}
+
+/*
+ * Common functions
+ */
+void smp_message_recv(int msg, struct pt_regs *regs)
+{
+ atomic_inc(&ipi_recv);
+
+ switch( msg ) {
+ case PPC_MSG_CALL_FUNCTION:
+ smp_call_function_interrupt();
+ break;
+ case PPC_MSG_RESCHEDULE:
+ set_need_resched();
+ break;
+ case PPC_MSG_INVALIDATE_TLB:
+ _tlbia();
+ break;
+#ifdef CONFIG_XMON
+ case PPC_MSG_XMON_BREAK:
+ xmon(regs);
+ break;
+#endif /* CONFIG_XMON */
+ default:
+ printk("SMP %d: smp_message_recv(): unknown msg %d\n",
+ smp_processor_id(), msg);
+ break;
+ }
+}
+
+/*
+ * 750's don't broadcast tlb invalidates so
+ * we have to emulate that behavior.
+ * -- Cort
+ */
+void smp_send_tlb_invalidate(int cpu)
+{
+ if ( PVR_VER(mfspr(SPRN_PVR)) == 8 )
+ smp_message_pass(MSG_ALL_BUT_SELF, PPC_MSG_INVALIDATE_TLB, 0, 0);
+}
+
+void smp_send_reschedule(int cpu)
+{
+ /*
+ * This is only used if `cpu' is running an idle task,
+ * so it will reschedule itself anyway...
+ *
+ * This isn't the case anymore since the other CPU could be
+ * sleeping and won't reschedule until the next interrupt (such
+ * as the timer).
+ * -- Cort
+ */
+ /* This is only used if `cpu' is running an idle task,
+ so it will reschedule itself anyway... */
+ smp_message_pass(cpu, PPC_MSG_RESCHEDULE, 0, 0);
+}
+
+#ifdef CONFIG_XMON
+void smp_send_xmon_break(int cpu)
+{
+ smp_message_pass(cpu, PPC_MSG_XMON_BREAK, 0, 0);
+}
+#endif /* CONFIG_XMON */
+
+static void stop_this_cpu(void *dummy)
+{
+ local_irq_disable();
+ while (1)
+ ;
+}
+
+void smp_send_stop(void)
+{
+ smp_call_function(stop_this_cpu, NULL, 1, 0);
+}
+
+/*
+ * Structure and data for smp_call_function(). This is designed to minimise
+ * static memory requirements. It also looks cleaner.
+ * Stolen from the i386 version.
+ */
+static DEFINE_SPINLOCK(call_lock);
+
+static struct call_data_struct {
+ void (*func) (void *info);
+ void *info;
+ atomic_t started;
+ atomic_t finished;
+ int wait;
+} *call_data;
+
+/*
+ * this function sends a 'generic call function' IPI to all other CPUs
+ * in the system.
+ */
+
+int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
+ int wait)
+/*
+ * [SUMMARY] Run a function on all other CPUs.
+ * <func> The function to run. This must be fast and non-blocking.
+ * <info> An arbitrary pointer to pass to the function.
+ * <nonatomic> currently unused.
+ * <wait> If true, wait (atomically) until function has completed on other CPUs.
+ * [RETURNS] 0 on success, else a negative status code. Does not return until
+ * remote CPUs are nearly ready to execute <<func>> or are or have executed.
+ *
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler.
+ */
+{
+ /* FIXME: get cpu lock with hotplug cpus, or change this to
+ bitmask. --RR */
+ if (num_online_cpus() <= 1)
+ return 0;
+ /* Can deadlock when called with interrupts disabled */
+ WARN_ON(irqs_disabled());
+ return __smp_call_function(func, info, wait, MSG_ALL_BUT_SELF);
+}
+
+static int __smp_call_function(void (*func) (void *info), void *info,
+ int wait, int target)
+{
+ struct call_data_struct data;
+ int ret = -1;
+ int timeout;
+ int ncpus = 1;
+
+ if (target == MSG_ALL_BUT_SELF)
+ ncpus = num_online_cpus() - 1;
+ else if (target == MSG_ALL)
+ ncpus = num_online_cpus();
+
+ data.func = func;
+ data.info = info;
+ atomic_set(&data.started, 0);
+ data.wait = wait;
+ if (wait)
+ atomic_set(&data.finished, 0);
+
+ spin_lock(&call_lock);
+ call_data = &data;
+ /* Send a message to all other CPUs and wait for them to respond */
+ smp_message_pass(target, PPC_MSG_CALL_FUNCTION, 0, 0);
+
+ /* Wait for response */
+ timeout = 1000000;
+ while (atomic_read(&data.started) != ncpus) {
+ if (--timeout == 0) {
+ printk("smp_call_function on cpu %d: other cpus not responding (%d)\n",
+ smp_processor_id(), atomic_read(&data.started));
+ goto out;
+ }
+ barrier();
+ udelay(1);
+ }
+
+ if (wait) {
+ timeout = 1000000;
+ while (atomic_read(&data.finished) != ncpus) {
+ if (--timeout == 0) {
+ printk("smp_call_function on cpu %d: other cpus not finishing (%d/%d)\n",
+ smp_processor_id(), atomic_read(&data.finished), atomic_read(&data.started));
+ goto out;
+ }
+ barrier();
+ udelay(1);
+ }
+ }
+ ret = 0;
+
+ out:
+ spin_unlock(&call_lock);
+ return ret;
+}
+
+void smp_call_function_interrupt(void)
+{
+ void (*func) (void *info) = call_data->func;
+ void *info = call_data->info;
+ int wait = call_data->wait;
+
+ /*
+ * Notify initiating CPU that I've grabbed the data and am
+ * about to execute the function
+ */
+ atomic_inc(&call_data->started);
+ /*
+ * At this point the info structure may be out of scope unless wait==1
+ */
+ (*func)(info);
+ if (wait)
+ atomic_inc(&call_data->finished);
+}
+
+static void __devinit smp_store_cpu_info(int id)
+{
+ struct cpuinfo_PPC *c = &cpu_data[id];
+
+ /* assume bogomips are same for everything */
+ c->loops_per_jiffy = loops_per_jiffy;
+ c->pvr = mfspr(SPRN_PVR);
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+ int num_cpus, i;
+
+ /* Fixup boot cpu */
+ smp_store_cpu_info(smp_processor_id());
+ cpu_callin_map[smp_processor_id()] = 1;
+
+ smp_ops = ppc_md.smp_ops;
+ if (smp_ops == NULL) {
+ printk("SMP not supported on this machine.\n");
+ return;
+ }
+
+ /* Probe platform for CPUs: always linear. */
+ num_cpus = smp_ops->probe();
+ for (i = 0; i < num_cpus; ++i)
+ cpu_set(i, cpu_possible_map);
+
+ /* Backup CPU 0 state */
+ __save_cpu_setup();
+
+ if (smp_ops->space_timers)
+ smp_ops->space_timers(num_cpus);
+}
+
+void __devinit smp_prepare_boot_cpu(void)
+{
+ cpu_set(smp_processor_id(), cpu_online_map);
+ cpu_set(smp_processor_id(), cpu_possible_map);
+}
+
+int __init setup_profiling_timer(unsigned int multiplier)
+{
+ return 0;
+}
+
+/* Processor coming up starts here */
+int __devinit start_secondary(void *unused)
+{
+ int cpu;
+
+ atomic_inc(&init_mm.mm_count);
+ current->active_mm = &init_mm;
+
+ cpu = smp_processor_id();
+ smp_store_cpu_info(cpu);
+ set_dec(tb_ticks_per_jiffy);
+ cpu_callin_map[cpu] = 1;
+
+ printk("CPU %i done callin...\n", cpu);
+ smp_ops->setup_cpu(cpu);
+ printk("CPU %i done setup...\n", cpu);
+ local_irq_enable();
+ smp_ops->take_timebase();
+ printk("CPU %i done timebase take...\n", cpu);
+
+ cpu_idle();
+ return 0;
+}
+
+int __cpu_up(unsigned int cpu)
+{
+ struct task_struct *p;
+ char buf[32];
+ int c;
+
+ /* create a process for the processor */
+ /* only regs.msr is actually used, and 0 is OK for it */
+ p = fork_idle(cpu);
+ if (IS_ERR(p))
+ panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p));
+ secondary_ti = p->thread_info;
+ p->thread_info->cpu = cpu;
+
+ /*
+ * There was a cache flush loop here to flush the cache
+ * to memory for the first 8MB of RAM. The cache flush
+ * has been pushed into the kick_cpu function for those
+ * platforms that need it.
+ */
+
+ /* wake up cpu */
+ smp_ops->kick_cpu(cpu);
+
+ /*
+ * wait to see if the cpu made a callin (is actually up).
+ * use this value that I found through experimentation.
+ * -- Cort
+ */
+ for (c = 1000; c && !cpu_callin_map[cpu]; c--)
+ udelay(100);
+
+ if (!cpu_callin_map[cpu]) {
+ sprintf(buf, "didn't find cpu %u", cpu);
+ if (ppc_md.progress) ppc_md.progress(buf, 0x360+cpu);
+ printk("Processor %u is stuck.\n", cpu);
+ return -ENOENT;
+ }
+
+ sprintf(buf, "found cpu %u", cpu);
+ if (ppc_md.progress) ppc_md.progress(buf, 0x350+cpu);
+ printk("Processor %d found.\n", cpu);
+
+ smp_ops->give_timebase();
+ cpu_set(cpu, cpu_online_map);
+ return 0;
+}
+
+void smp_cpus_done(unsigned int max_cpus)
+{
+ smp_ops->setup_cpu(0);
+}
diff --git a/arch/ppc/kernel/softemu8xx.c b/arch/ppc/kernel/softemu8xx.c
new file mode 100644
index 000000000000..9bbb6bf7b645
--- /dev/null
+++ b/arch/ppc/kernel/softemu8xx.c
@@ -0,0 +1,147 @@
+/*
+ * Software emulation of some PPC instructions for the 8xx core.
+ *
+ * Copyright (C) 1998 Dan Malek (dmalek@jlc.net)
+ *
+ * Software floating emuation for the MPC8xx processor. I did this mostly
+ * because it was easier than trying to get the libraries compiled for
+ * software floating point. The goal is still to get the libraries done,
+ * but I lost patience and needed some hacks to at least get init and
+ * shells running. The first problem is the setjmp/longjmp that save
+ * and restore the floating point registers.
+ *
+ * For this emulation, our working registers are found on the register
+ * save area.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+
+extern void
+print_8xx_pte(struct mm_struct *mm, unsigned long addr);
+extern int
+get_8xx_pte(struct mm_struct *mm, unsigned long addr);
+
+/* Eventually we may need a look-up table, but this works for now.
+*/
+#define LFS 48
+#define LFD 50
+#define LFDU 51
+#define STFD 54
+#define STFDU 55
+#define FMR 63
+
+/*
+ * We return 0 on success, 1 on unimplemented instruction, and EFAULT
+ * if a load/store faulted.
+ */
+int
+Soft_emulate_8xx(struct pt_regs *regs)
+{
+ uint inst, instword;
+ uint flreg, idxreg, disp;
+ uint retval;
+ signed short sdisp;
+ uint *ea, *ip;
+
+ retval = 0;
+
+ instword = *((uint *)regs->nip);
+ inst = instword >> 26;
+
+ flreg = (instword >> 21) & 0x1f;
+ idxreg = (instword >> 16) & 0x1f;
+ disp = instword & 0xffff;
+
+ ea = (uint *)(regs->gpr[idxreg] + disp);
+ ip = (uint *)&current->thread.fpr[flreg];
+
+ switch ( inst )
+ {
+ case LFD:
+ /* this is a 16 bit quantity that is sign extended
+ * so use a signed short here -- Cort
+ */
+ sdisp = (instword & 0xffff);
+ ea = (uint *)(regs->gpr[idxreg] + sdisp);
+ if (copy_from_user(ip, ea, sizeof(double)))
+ retval = -EFAULT;
+ break;
+
+ case LFDU:
+ if (copy_from_user(ip, ea, sizeof(double)))
+ retval = -EFAULT;
+ else
+ regs->gpr[idxreg] = (uint)ea;
+ break;
+ case LFS:
+ sdisp = (instword & 0xffff);
+ ea = (uint *)(regs->gpr[idxreg] + sdisp);
+ if (copy_from_user(ip, ea, sizeof(float)))
+ retval = -EFAULT;
+ break;
+ case STFD:
+ /* this is a 16 bit quantity that is sign extended
+ * so use a signed short here -- Cort
+ */
+ sdisp = (instword & 0xffff);
+ ea = (uint *)(regs->gpr[idxreg] + sdisp);
+ if (copy_to_user(ea, ip, sizeof(double)))
+ retval = -EFAULT;
+ break;
+
+ case STFDU:
+ if (copy_to_user(ea, ip, sizeof(double)))
+ retval = -EFAULT;
+ else
+ regs->gpr[idxreg] = (uint)ea;
+ break;
+ case FMR:
+ /* assume this is a fp move -- Cort */
+ memcpy( ip, &current->thread.fpr[(instword>>11)&0x1f],
+ sizeof(double) );
+ break;
+ default:
+ retval = 1;
+ printk("Bad emulation %s/%d\n"
+ " NIP: %08lx instruction: %08x opcode: %x "
+ "A: %x B: %x C: %x code: %x rc: %x\n",
+ current->comm,current->pid,
+ regs->nip,
+ instword,inst,
+ (instword>>16)&0x1f,
+ (instword>>11)&0x1f,
+ (instword>>6)&0x1f,
+ (instword>>1)&0x3ff,
+ instword&1);
+ {
+ int pa;
+ print_8xx_pte(current->mm,regs->nip);
+ pa = get_8xx_pte(current->mm,regs->nip) & PAGE_MASK;
+ pa |= (regs->nip & ~PAGE_MASK);
+ pa = (unsigned long)__va(pa);
+ printk("Kernel VA for NIP %x ", pa);
+ print_8xx_pte(current->mm,pa);
+ }
+
+ }
+
+ if (retval == 0)
+ regs->nip += 4;
+ return(retval);
+}
+
diff --git a/arch/ppc/kernel/swsusp.S b/arch/ppc/kernel/swsusp.S
new file mode 100644
index 000000000000..55148bb88d39
--- /dev/null
+++ b/arch/ppc/kernel/swsusp.S
@@ -0,0 +1,349 @@
+#include <linux/config.h>
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/offsets.h>
+
+
+/*
+ * Structure for storing CPU registers on the save area.
+ */
+#define SL_SP 0
+#define SL_PC 4
+#define SL_MSR 8
+#define SL_SDR1 0xc
+#define SL_SPRG0 0x10 /* 4 sprg's */
+#define SL_DBAT0 0x20
+#define SL_IBAT0 0x28
+#define SL_DBAT1 0x30
+#define SL_IBAT1 0x38
+#define SL_DBAT2 0x40
+#define SL_IBAT2 0x48
+#define SL_DBAT3 0x50
+#define SL_IBAT3 0x58
+#define SL_TB 0x60
+#define SL_R2 0x68
+#define SL_CR 0x6c
+#define SL_LR 0x70
+#define SL_R12 0x74 /* r12 to r31 */
+#define SL_SIZE (SL_R12 + 80)
+
+ .section .data
+ .align 5
+
+_GLOBAL(swsusp_save_area)
+ .space SL_SIZE
+
+
+ .section .text
+ .align 5
+
+_GLOBAL(swsusp_arch_suspend)
+
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+
+ mflr r0
+ stw r0,SL_LR(r11)
+ mfcr r0
+ stw r0,SL_CR(r11)
+ stw r1,SL_SP(r11)
+ stw r2,SL_R2(r11)
+ stmw r12,SL_R12(r11)
+
+ /* Save MSR & SDR1 */
+ mfmsr r4
+ stw r4,SL_MSR(r11)
+ mfsdr1 r4
+ stw r4,SL_SDR1(r11)
+
+ /* Get a stable timebase and save it */
+1: mftbu r4
+ stw r4,SL_TB(r11)
+ mftb r5
+ stw r5,SL_TB+4(r11)
+ mftbu r3
+ cmpw r3,r4
+ bne 1b
+
+ /* Save SPRGs */
+ mfsprg r4,0
+ stw r4,SL_SPRG0(r11)
+ mfsprg r4,1
+ stw r4,SL_SPRG0+4(r11)
+ mfsprg r4,2
+ stw r4,SL_SPRG0+8(r11)
+ mfsprg r4,3
+ stw r4,SL_SPRG0+12(r11)
+
+ /* Save BATs */
+ mfdbatu r4,0
+ stw r4,SL_DBAT0(r11)
+ mfdbatl r4,0
+ stw r4,SL_DBAT0+4(r11)
+ mfdbatu r4,1
+ stw r4,SL_DBAT1(r11)
+ mfdbatl r4,1
+ stw r4,SL_DBAT1+4(r11)
+ mfdbatu r4,2
+ stw r4,SL_DBAT2(r11)
+ mfdbatl r4,2
+ stw r4,SL_DBAT2+4(r11)
+ mfdbatu r4,3
+ stw r4,SL_DBAT3(r11)
+ mfdbatl r4,3
+ stw r4,SL_DBAT3+4(r11)
+ mfibatu r4,0
+ stw r4,SL_IBAT0(r11)
+ mfibatl r4,0
+ stw r4,SL_IBAT0+4(r11)
+ mfibatu r4,1
+ stw r4,SL_IBAT1(r11)
+ mfibatl r4,1
+ stw r4,SL_IBAT1+4(r11)
+ mfibatu r4,2
+ stw r4,SL_IBAT2(r11)
+ mfibatl r4,2
+ stw r4,SL_IBAT2+4(r11)
+ mfibatu r4,3
+ stw r4,SL_IBAT3(r11)
+ mfibatl r4,3
+ stw r4,SL_IBAT3+4(r11)
+
+#if 0
+ /* Backup various CPU config stuffs */
+ bl __save_cpu_setup
+#endif
+ /* Call the low level suspend stuff (we should probably have made
+ * a stackframe...
+ */
+ bl swsusp_save
+
+ /* Restore LR from the save area */
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+ lwz r0,SL_LR(r11)
+ mtlr r0
+
+ blr
+
+
+/* Resume code */
+_GLOBAL(swsusp_arch_resume)
+
+ /* Stop pending alitvec streams and memory accesses */
+BEGIN_FTR_SECTION
+ DSSALL
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ sync
+
+ /* Disable MSR:DR to make sure we don't take a TLB or
+ * hash miss during the copy, as our hash table will
+ * for a while be unuseable. For .text, we assume we are
+ * covered by a BAT. This works only for non-G5 at this
+ * point. G5 will need a better approach, possibly using
+ * a small temporary hash table filled with large mappings,
+ * disabling the MMU completely isn't a good option for
+ * performance reasons.
+ * (Note that 750's may have the same performance issue as
+ * the G5 in this case, we should investigate using moving
+ * BATs for these CPUs)
+ */
+ mfmsr r0
+ sync
+ rlwinm r0,r0,0,28,26 /* clear MSR_DR */
+ mtmsr r0
+ sync
+ isync
+
+ /* Load ptr the list of pages to copy in r3 */
+ lis r11,(pagedir_nosave - KERNELBASE)@h
+ ori r11,r11,pagedir_nosave@l
+ lwz r10,0(r11)
+
+ /* Copy the pages. This is a very basic implementation, to
+ * be replaced by something more cache efficient */
+1:
+ tophys(r3,r10)
+ li r0,256
+ mtctr r0
+ lwz r11,pbe_address(r3) /* source */
+ tophys(r5,r11)
+ lwz r10,pbe_orig_address(r3) /* destination */
+ tophys(r6,r10)
+2:
+ lwz r8,0(r5)
+ lwz r9,4(r5)
+ lwz r10,8(r5)
+ lwz r11,12(r5)
+ addi r5,r5,16
+ stw r8,0(r6)
+ stw r9,4(r6)
+ stw r10,8(r6)
+ stw r11,12(r6)
+ addi r6,r6,16
+ bdnz 2b
+ lwz r10,pbe_next(r3)
+ cmpwi 0,r10,0
+ bne 1b
+
+ /* Do a very simple cache flush/inval of the L1 to ensure
+ * coherency of the icache
+ */
+ lis r3,0x0002
+ mtctr r3
+ li r3, 0
+1:
+ lwz r0,0(r3)
+ addi r3,r3,0x0020
+ bdnz 1b
+ isync
+ sync
+
+ /* Now flush those cache lines */
+ lis r3,0x0002
+ mtctr r3
+ li r3, 0
+1:
+ dcbf 0,r3
+ addi r3,r3,0x0020
+ bdnz 1b
+ sync
+
+ /* Ok, we are now running with the kernel data of the old
+ * kernel fully restored. We can get to the save area
+ * easily now. As for the rest of the code, it assumes the
+ * loader kernel and the booted one are exactly identical
+ */
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+ tophys(r11,r11)
+
+#if 0
+ /* Restore various CPU config stuffs */
+ bl __restore_cpu_setup
+#endif
+ /* Restore the BATs, and SDR1. Then we can turn on the MMU.
+ * This is a bit hairy as we are running out of those BATs,
+ * but first, our code is probably in the icache, and we are
+ * writing the same value to the BAT, so that should be fine,
+ * though a better solution will have to be found long-term
+ */
+ lwz r4,SL_SDR1(r11)
+ mtsdr1 r4
+ lwz r4,SL_SPRG0(r11)
+ mtsprg 0,r4
+ lwz r4,SL_SPRG0+4(r11)
+ mtsprg 1,r4
+ lwz r4,SL_SPRG0+8(r11)
+ mtsprg 2,r4
+ lwz r4,SL_SPRG0+12(r11)
+ mtsprg 3,r4
+
+#if 0
+ lwz r4,SL_DBAT0(r11)
+ mtdbatu 0,r4
+ lwz r4,SL_DBAT0+4(r11)
+ mtdbatl 0,r4
+ lwz r4,SL_DBAT1(r11)
+ mtdbatu 1,r4
+ lwz r4,SL_DBAT1+4(r11)
+ mtdbatl 1,r4
+ lwz r4,SL_DBAT2(r11)
+ mtdbatu 2,r4
+ lwz r4,SL_DBAT2+4(r11)
+ mtdbatl 2,r4
+ lwz r4,SL_DBAT3(r11)
+ mtdbatu 3,r4
+ lwz r4,SL_DBAT3+4(r11)
+ mtdbatl 3,r4
+ lwz r4,SL_IBAT0(r11)
+ mtibatu 0,r4
+ lwz r4,SL_IBAT0+4(r11)
+ mtibatl 0,r4
+ lwz r4,SL_IBAT1(r11)
+ mtibatu 1,r4
+ lwz r4,SL_IBAT1+4(r11)
+ mtibatl 1,r4
+ lwz r4,SL_IBAT2(r11)
+ mtibatu 2,r4
+ lwz r4,SL_IBAT2+4(r11)
+ mtibatl 2,r4
+ lwz r4,SL_IBAT3(r11)
+ mtibatu 3,r4
+ lwz r4,SL_IBAT3+4(r11)
+ mtibatl 3,r4
+#endif
+
+BEGIN_FTR_SECTION
+ li r4,0
+ mtspr SPRN_DBAT4U,r4
+ mtspr SPRN_DBAT4L,r4
+ mtspr SPRN_DBAT5U,r4
+ mtspr SPRN_DBAT5L,r4
+ mtspr SPRN_DBAT6U,r4
+ mtspr SPRN_DBAT6L,r4
+ mtspr SPRN_DBAT7U,r4
+ mtspr SPRN_DBAT7L,r4
+ mtspr SPRN_IBAT4U,r4
+ mtspr SPRN_IBAT4L,r4
+ mtspr SPRN_IBAT5U,r4
+ mtspr SPRN_IBAT5L,r4
+ mtspr SPRN_IBAT6U,r4
+ mtspr SPRN_IBAT6L,r4
+ mtspr SPRN_IBAT7U,r4
+ mtspr SPRN_IBAT7L,r4
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_HIGH_BATS)
+
+ /* Flush all TLBs */
+ lis r4,0x1000
+1: addic. r4,r4,-0x1000
+ tlbie r4
+ blt 1b
+ sync
+
+ /* restore the MSR and turn on the MMU */
+ lwz r3,SL_MSR(r11)
+ bl turn_on_mmu
+ tovirt(r11,r11)
+
+ /* Restore TB */
+ li r3,0
+ mttbl r3
+ lwz r3,SL_TB(r11)
+ lwz r4,SL_TB+4(r11)
+ mttbu r3
+ mttbl r4
+
+ /* Kick decrementer */
+ li r0,1
+ mtdec r0
+
+ /* Restore the callee-saved registers and return */
+ lwz r0,SL_CR(r11)
+ mtcr r0
+ lwz r2,SL_R2(r11)
+ lmw r12,SL_R12(r11)
+ lwz r1,SL_SP(r11)
+ lwz r0,SL_LR(r11)
+ mtlr r0
+
+ // XXX Note: we don't really need to call swsusp_resume
+
+ li r3,0
+ blr
+
+/* FIXME:This construct is actually not useful since we don't shut
+ * down the instruction MMU, we could just flip back MSR-DR on.
+ */
+turn_on_mmu:
+ mflr r4
+ mtsrr0 r4
+ mtsrr1 r3
+ sync
+ isync
+ rfi
+
diff --git a/arch/ppc/kernel/syscalls.c b/arch/ppc/kernel/syscalls.c
new file mode 100644
index 000000000000..124313ce3c09
--- /dev/null
+++ b/arch/ppc/kernel/syscalls.c
@@ -0,0 +1,272 @@
+/*
+ * arch/ppc/kernel/sys_ppc.c
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/i386/kernel/sys_i386.c"
+ * Adapted from the i386 version by Gary Thomas
+ * Modified by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras (paulus@cs.anu.edu.au).
+ *
+ * This file contains various random system calls that
+ * have a non-standard calling sequence on the Linux/PPC
+ * platform.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/syscalls.h>
+#include <linux/mman.h>
+#include <linux/sys.h>
+#include <linux/ipc.h>
+#include <linux/utsname.h>
+#include <linux/file.h>
+#include <linux/unistd.h>
+
+#include <asm/uaccess.h>
+#include <asm/ipc.h>
+#include <asm/semaphore.h>
+
+void
+check_bugs(void)
+{
+}
+
+/*
+ * sys_ipc() is the de-multiplexer for the SysV IPC calls..
+ *
+ * This is really horribly ugly.
+ */
+int
+sys_ipc (uint call, int first, int second, int third, void __user *ptr, long fifth)
+{
+ int version, ret;
+
+ version = call >> 16; /* hack for backward compatibility */
+ call &= 0xffff;
+
+ ret = -ENOSYS;
+ switch (call) {
+ case SEMOP:
+ ret = sys_semtimedop (first, (struct sembuf __user *)ptr,
+ second, NULL);
+ break;
+ case SEMTIMEDOP:
+ ret = sys_semtimedop (first, (struct sembuf __user *)ptr,
+ second, (const struct timespec __user *) fifth);
+ break;
+ case SEMGET:
+ ret = sys_semget (first, second, third);
+ break;
+ case SEMCTL: {
+ union semun fourth;
+
+ if (!ptr)
+ break;
+ if ((ret = access_ok(VERIFY_READ, ptr, sizeof(long)) ? 0 : -EFAULT)
+ || (ret = get_user(fourth.__pad, (void __user *__user *)ptr)))
+ break;
+ ret = sys_semctl (first, second, third, fourth);
+ break;
+ }
+ case MSGSND:
+ ret = sys_msgsnd (first, (struct msgbuf __user *) ptr, second, third);
+ break;
+ case MSGRCV:
+ switch (version) {
+ case 0: {
+ struct ipc_kludge tmp;
+
+ if (!ptr)
+ break;
+ if ((ret = access_ok(VERIFY_READ, ptr, sizeof(tmp)) ? 0 : -EFAULT)
+ || (ret = copy_from_user(&tmp,
+ (struct ipc_kludge __user *) ptr,
+ sizeof (tmp)) ? -EFAULT : 0))
+ break;
+ ret = sys_msgrcv (first, tmp.msgp, second, tmp.msgtyp,
+ third);
+ break;
+ }
+ default:
+ ret = sys_msgrcv (first, (struct msgbuf __user *) ptr,
+ second, fifth, third);
+ break;
+ }
+ break;
+ case MSGGET:
+ ret = sys_msgget ((key_t) first, second);
+ break;
+ case MSGCTL:
+ ret = sys_msgctl (first, second, (struct msqid_ds __user *) ptr);
+ break;
+ case SHMAT: {
+ ulong raddr;
+
+ if ((ret = access_ok(VERIFY_WRITE, (ulong __user *) third,
+ sizeof(ulong)) ? 0 : -EFAULT))
+ break;
+ ret = do_shmat (first, (char __user *) ptr, second, &raddr);
+ if (ret)
+ break;
+ ret = put_user (raddr, (ulong __user *) third);
+ break;
+ }
+ case SHMDT:
+ ret = sys_shmdt ((char __user *)ptr);
+ break;
+ case SHMGET:
+ ret = sys_shmget (first, second, third);
+ break;
+ case SHMCTL:
+ ret = sys_shmctl (first, second, (struct shmid_ds __user *) ptr);
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * sys_pipe() is the normal C calling standard for creating
+ * a pipe. It's not the way unix traditionally does this, though.
+ */
+int sys_pipe(int __user *fildes)
+{
+ int fd[2];
+ int error;
+
+ error = do_pipe(fd);
+ if (!error) {
+ if (copy_to_user(fildes, fd, 2*sizeof(int)))
+ error = -EFAULT;
+ }
+ return error;
+}
+
+static inline unsigned long
+do_mmap2(unsigned long addr, size_t len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ struct file * file = NULL;
+ int ret = -EBADF;
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+ if (!(flags & MAP_ANONYMOUS)) {
+ if (!(file = fget(fd)))
+ goto out;
+ }
+
+ down_write(&current->mm->mmap_sem);
+ ret = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(&current->mm->mmap_sem);
+ if (file)
+ fput(file);
+out:
+ return ret;
+}
+
+unsigned long sys_mmap2(unsigned long addr, size_t len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long pgoff)
+{
+ return do_mmap2(addr, len, prot, flags, fd, pgoff);
+}
+
+unsigned long sys_mmap(unsigned long addr, size_t len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, off_t offset)
+{
+ int err = -EINVAL;
+
+ if (offset & ~PAGE_MASK)
+ goto out;
+
+ err = do_mmap2(addr, len, prot, flags, fd, offset >> PAGE_SHIFT);
+out:
+ return err;
+}
+
+/*
+ * Due to some executables calling the wrong select we sometimes
+ * get wrong args. This determines how the args are being passed
+ * (a single ptr to them all args passed) then calls
+ * sys_select() with the appropriate args. -- Cort
+ */
+int
+ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp)
+{
+ if ( (unsigned long)n >= 4096 )
+ {
+ unsigned long __user *buffer = (unsigned long __user *)n;
+ if (!access_ok(VERIFY_READ, buffer, 5*sizeof(unsigned long))
+ || __get_user(n, buffer)
+ || __get_user(inp, ((fd_set __user * __user *)(buffer+1)))
+ || __get_user(outp, ((fd_set __user * __user *)(buffer+2)))
+ || __get_user(exp, ((fd_set __user * __user *)(buffer+3)))
+ || __get_user(tvp, ((struct timeval __user * __user *)(buffer+4))))
+ return -EFAULT;
+ }
+ return sys_select(n, inp, outp, exp, tvp);
+}
+
+int sys_uname(struct old_utsname __user * name)
+{
+ int err = -EFAULT;
+
+ down_read(&uts_sem);
+ if (name && !copy_to_user(name, &system_utsname, sizeof (*name)))
+ err = 0;
+ up_read(&uts_sem);
+ return err;
+}
+
+int sys_olduname(struct oldold_utsname __user * name)
+{
+ int error;
+
+ if (!name)
+ return -EFAULT;
+ if (!access_ok(VERIFY_WRITE,name,sizeof(struct oldold_utsname)))
+ return -EFAULT;
+
+ down_read(&uts_sem);
+ error = __copy_to_user(&name->sysname,&system_utsname.sysname,__OLD_UTS_LEN);
+ error -= __put_user(0,name->sysname+__OLD_UTS_LEN);
+ error -= __copy_to_user(&name->nodename,&system_utsname.nodename,__OLD_UTS_LEN);
+ error -= __put_user(0,name->nodename+__OLD_UTS_LEN);
+ error -= __copy_to_user(&name->release,&system_utsname.release,__OLD_UTS_LEN);
+ error -= __put_user(0,name->release+__OLD_UTS_LEN);
+ error -= __copy_to_user(&name->version,&system_utsname.version,__OLD_UTS_LEN);
+ error -= __put_user(0,name->version+__OLD_UTS_LEN);
+ error -= __copy_to_user(&name->machine,&system_utsname.machine,__OLD_UTS_LEN);
+ error = __put_user(0,name->machine+__OLD_UTS_LEN);
+ up_read(&uts_sem);
+
+ error = error ? -EFAULT : 0;
+ return error;
+}
+
+/*
+ * We put the arguments in a different order so we only use 6
+ * registers for arguments, rather than 7 as sys_fadvise64_64 needs
+ * (because `offset' goes in r5/r6).
+ */
+long ppc_fadvise64_64(int fd, int advice, loff_t offset, loff_t len)
+{
+ return sys_fadvise64_64(fd, offset, len, advice);
+}
diff --git a/arch/ppc/kernel/temp.c b/arch/ppc/kernel/temp.c
new file mode 100644
index 000000000000..fe8bb634ead0
--- /dev/null
+++ b/arch/ppc/kernel/temp.c
@@ -0,0 +1,272 @@
+/*
+ * temp.c Thermal management for cpu's with Thermal Assist Units
+ *
+ * Written by Troy Benjegerdes <hozer@drgw.net>
+ *
+ * TODO:
+ * dynamic power management to limit peak CPU temp (using ICTC)
+ * calibration???
+ *
+ * Silly, crazy ideas: use cpu load (from scheduler) and ICTC to extend battery
+ * life in portables, and add a 'performance/watt' metric somewhere in /proc
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+
+#include <asm/segment.h>
+#include <asm/io.h>
+#include <asm/reg.h>
+#include <asm/nvram.h>
+#include <asm/cache.h>
+#include <asm/8xx_immap.h>
+#include <asm/machdep.h>
+
+static struct tau_temp
+{
+ int interrupts;
+ unsigned char low;
+ unsigned char high;
+ unsigned char grew;
+} tau[NR_CPUS];
+
+struct timer_list tau_timer;
+
+#undef DEBUG
+
+/* TODO: put these in a /proc interface, with some sanity checks, and maybe
+ * dynamic adjustment to minimize # of interrupts */
+/* configurable values for step size and how much to expand the window when
+ * we get an interrupt. These are based on the limit that was out of range */
+#define step_size 2 /* step size when temp goes out of range */
+#define window_expand 1 /* expand the window by this much */
+/* configurable values for shrinking the window */
+#define shrink_timer 2*HZ /* period between shrinking the window */
+#define min_window 2 /* minimum window size, degrees C */
+
+void set_thresholds(unsigned long cpu)
+{
+#ifdef CONFIG_TAU_INT
+ /*
+ * setup THRM1,
+ * threshold, valid bit, enable interrupts, interrupt when below threshold
+ */
+ mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TIE | THRM1_TID);
+
+ /* setup THRM2,
+ * threshold, valid bit, enable interrupts, interrupt when above threshhold
+ */
+ mtspr (SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | THRM1_TIE);
+#else
+ /* same thing but don't enable interrupts */
+ mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TID);
+ mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V);
+#endif
+}
+
+void TAUupdate(int cpu)
+{
+ unsigned thrm;
+
+#ifdef DEBUG
+ printk("TAUupdate ");
+#endif
+
+ /* if both thresholds are crossed, the step_sizes cancel out
+ * and the window winds up getting expanded twice. */
+ if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */
+ if(thrm & THRM1_TIN){ /* crossed low threshold */
+ if (tau[cpu].low >= step_size){
+ tau[cpu].low -= step_size;
+ tau[cpu].high -= (step_size - window_expand);
+ }
+ tau[cpu].grew = 1;
+#ifdef DEBUG
+ printk("low threshold crossed ");
+#endif
+ }
+ }
+ if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */
+ if(thrm & THRM1_TIN){ /* crossed high threshold */
+ if (tau[cpu].high <= 127-step_size){
+ tau[cpu].low += (step_size - window_expand);
+ tau[cpu].high += step_size;
+ }
+ tau[cpu].grew = 1;
+#ifdef DEBUG
+ printk("high threshold crossed ");
+#endif
+ }
+ }
+
+#ifdef DEBUG
+ printk("grew = %d\n", tau[cpu].grew);
+#endif
+
+#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */
+ set_thresholds(cpu);
+#endif
+
+}
+
+#ifdef CONFIG_TAU_INT
+/*
+ * TAU interrupts - called when we have a thermal assist unit interrupt
+ * with interrupts disabled
+ */
+
+void TAUException(struct pt_regs * regs)
+{
+ int cpu = smp_processor_id();
+
+ irq_enter();
+ tau[cpu].interrupts++;
+
+ TAUupdate(cpu);
+
+ irq_exit();
+}
+#endif /* CONFIG_TAU_INT */
+
+static void tau_timeout(void * info)
+{
+ int cpu;
+ unsigned long flags;
+ int size;
+ int shrink;
+
+ /* disabling interrupts *should* be okay */
+ local_irq_save(flags);
+ cpu = smp_processor_id();
+
+#ifndef CONFIG_TAU_INT
+ TAUupdate(cpu);
+#endif
+
+ size = tau[cpu].high - tau[cpu].low;
+ if (size > min_window && ! tau[cpu].grew) {
+ /* do an exponential shrink of half the amount currently over size */
+ shrink = (2 + size - min_window) / 4;
+ if (shrink) {
+ tau[cpu].low += shrink;
+ tau[cpu].high -= shrink;
+ } else { /* size must have been min_window + 1 */
+ tau[cpu].low += 1;
+#if 1 /* debug */
+ if ((tau[cpu].high - tau[cpu].low) != min_window){
+ printk(KERN_ERR "temp.c: line %d, logic error\n", __LINE__);
+ }
+#endif
+ }
+ }
+
+ tau[cpu].grew = 0;
+
+ set_thresholds(cpu);
+
+ /*
+ * Do the enable every time, since otherwise a bunch of (relatively)
+ * complex sleep code needs to be added. One mtspr every time
+ * tau_timeout is called is probably not a big deal.
+ *
+ * Enable thermal sensor and set up sample interval timer
+ * need 20 us to do the compare.. until a nice 'cpu_speed' function
+ * call is implemented, just assume a 500 mhz clock. It doesn't really
+ * matter if we take too long for a compare since it's all interrupt
+ * driven anyway.
+ *
+ * use a extra long time.. (60 us @ 500 mhz)
+ */
+ mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E);
+
+ local_irq_restore(flags);
+}
+
+static void tau_timeout_smp(unsigned long unused)
+{
+
+ /* schedule ourselves to be run again */
+ mod_timer(&tau_timer, jiffies + shrink_timer) ;
+ on_each_cpu(tau_timeout, NULL, 1, 0);
+}
+
+/*
+ * setup the TAU
+ *
+ * Set things up to use THRM1 as a temperature lower bound, and THRM2 as an upper bound.
+ * Start off at zero
+ */
+
+int tau_initialized = 0;
+
+void __init TAU_init_smp(void * info)
+{
+ unsigned long cpu = smp_processor_id();
+
+ /* set these to a reasonable value and let the timer shrink the
+ * window */
+ tau[cpu].low = 5;
+ tau[cpu].high = 120;
+
+ set_thresholds(cpu);
+}
+
+int __init TAU_init(void)
+{
+ /* We assume in SMP that if one CPU has TAU support, they
+ * all have it --BenH
+ */
+ if (!cpu_has_feature(CPU_FTR_TAU)) {
+ printk("Thermal assist unit not available\n");
+ tau_initialized = 0;
+ return 1;
+ }
+
+
+ /* first, set up the window shrinking timer */
+ init_timer(&tau_timer);
+ tau_timer.function = tau_timeout_smp;
+ tau_timer.expires = jiffies + shrink_timer;
+ add_timer(&tau_timer);
+
+ on_each_cpu(TAU_init_smp, NULL, 1, 0);
+
+ printk("Thermal assist unit ");
+#ifdef CONFIG_TAU_INT
+ printk("using interrupts, ");
+#else
+ printk("using timers, ");
+#endif
+ printk("shrink_timer: %d jiffies\n", shrink_timer);
+ tau_initialized = 1;
+
+ return 0;
+}
+
+__initcall(TAU_init);
+
+/*
+ * return current temp
+ */
+
+u32 cpu_temp_both(unsigned long cpu)
+{
+ return ((tau[cpu].high << 16) | tau[cpu].low);
+}
+
+int cpu_temp(unsigned long cpu)
+{
+ return ((tau[cpu].high + tau[cpu].low) / 2);
+}
+
+int tau_interrupts(unsigned long cpu)
+{
+ return (tau[cpu].interrupts);
+}
diff --git a/arch/ppc/kernel/time.c b/arch/ppc/kernel/time.c
new file mode 100644
index 000000000000..50724139402c
--- /dev/null
+++ b/arch/ppc/kernel/time.c
@@ -0,0 +1,447 @@
+/*
+ * Common time routines among all ppc machines.
+ *
+ * Written by Cort Dougan (cort@cs.nmt.edu) to merge
+ * Paul Mackerras' version and mine for PReP and Pmac.
+ * MPC8xx/MBX changes by Dan Malek (dmalek@jlc.net).
+ *
+ * First round of bugfixes by Gabriel Paubert (paubert@iram.es)
+ * to make clock more stable (2.4.0-test5). The only thing
+ * that this code assumes is that the timebases have been synchronized
+ * by firmware on SMP and are never stopped (never do sleep
+ * on SMP then, nap and doze are OK).
+ *
+ * TODO (not necessarily in this file):
+ * - improve precision and reproducibility of timebase frequency
+ * measurement at boot time.
+ * - get rid of xtime_lock for gettimeofday (generic kernel problem
+ * to be implemented on all architectures for SMP scalability and
+ * eventually implementing gettimeofday without entering the kernel).
+ * - put all time/clock related variables in a single structure
+ * to minimize number of cache lines touched by gettimeofday()
+ * - for astronomical applications: add a new function to get
+ * non ambiguous timestamps even around leap seconds. This needs
+ * a new timestamp format and a good name.
+ *
+ *
+ * The following comment is partially obsolete (at least the long wait
+ * is no more a valid reason):
+ * Since the MPC8xx has a programmable interrupt timer, I decided to
+ * use that rather than the decrementer. Two reasons: 1.) the clock
+ * frequency is low, causing 2.) a long wait in the timer interrupt
+ * while ((d = get_dec()) == dval)
+ * loop. The MPC8xx can be driven from a variety of input clocks,
+ * so a number of assumptions have been made here because the kernel
+ * parameter HZ is a constant. We assume (correctly, today :-) that
+ * the MPC8xx on the MBX board is driven from a 32.768 kHz crystal.
+ * This is then divided by 4, providing a 8192 Hz clock into the PIT.
+ * Since it is not possible to get a nice 100 Hz clock out of this, without
+ * creating a software PLL, I have set HZ to 128. -- Dan
+ *
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ */
+
+#include <linux/config.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/kernel_stat.h>
+#include <linux/mc146818rtc.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/profile.h>
+
+#include <asm/segment.h>
+#include <asm/io.h>
+#include <asm/nvram.h>
+#include <asm/cache.h>
+#include <asm/8xx_immap.h>
+#include <asm/machdep.h>
+
+#include <asm/time.h>
+
+/* XXX false sharing with below? */
+u64 jiffies_64 = INITIAL_JIFFIES;
+
+EXPORT_SYMBOL(jiffies_64);
+
+unsigned long disarm_decr[NR_CPUS];
+
+extern struct timezone sys_tz;
+
+/* keep track of when we need to update the rtc */
+time_t last_rtc_update;
+
+/* The decrementer counts down by 128 every 128ns on a 601. */
+#define DECREMENTER_COUNT_601 (1000000000 / HZ)
+
+unsigned tb_ticks_per_jiffy;
+unsigned tb_to_us;
+unsigned tb_last_stamp;
+unsigned long tb_to_ns_scale;
+
+extern unsigned long wall_jiffies;
+
+static long time_offset;
+
+DEFINE_SPINLOCK(rtc_lock);
+
+EXPORT_SYMBOL(rtc_lock);
+
+/* Timer interrupt helper function */
+static inline int tb_delta(unsigned *jiffy_stamp) {
+ int delta;
+ if (__USE_RTC()) {
+ delta = get_rtcl();
+ if (delta < *jiffy_stamp) *jiffy_stamp -= 1000000000;
+ delta -= *jiffy_stamp;
+ } else {
+ delta = get_tbl() - *jiffy_stamp;
+ }
+ return delta;
+}
+
+#ifdef CONFIG_SMP
+unsigned long profile_pc(struct pt_regs *regs)
+{
+ unsigned long pc = instruction_pointer(regs);
+
+ if (in_lock_functions(pc))
+ return regs->link;
+
+ return pc;
+}
+EXPORT_SYMBOL(profile_pc);
+#endif
+
+/*
+ * timer_interrupt - gets called when the decrementer overflows,
+ * with interrupts disabled.
+ * We set it up to overflow again in 1/HZ seconds.
+ */
+void timer_interrupt(struct pt_regs * regs)
+{
+ int next_dec;
+ unsigned long cpu = smp_processor_id();
+ unsigned jiffy_stamp = last_jiffy_stamp(cpu);
+ extern void do_IRQ(struct pt_regs *);
+
+ if (atomic_read(&ppc_n_lost_interrupts) != 0)
+ do_IRQ(regs);
+
+ irq_enter();
+
+ while ((next_dec = tb_ticks_per_jiffy - tb_delta(&jiffy_stamp)) <= 0) {
+ jiffy_stamp += tb_ticks_per_jiffy;
+
+ profile_tick(CPU_PROFILING, regs);
+ update_process_times(user_mode(regs));
+
+ if (smp_processor_id())
+ continue;
+
+ /* We are in an interrupt, no need to save/restore flags */
+ write_seqlock(&xtime_lock);
+ tb_last_stamp = jiffy_stamp;
+ do_timer(regs);
+
+ /*
+ * update the rtc when needed, this should be performed on the
+ * right fraction of a second. Half or full second ?
+ * Full second works on mk48t59 clocks, others need testing.
+ * Note that this update is basically only used through
+ * the adjtimex system calls. Setting the HW clock in
+ * any other way is a /dev/rtc and userland business.
+ * This is still wrong by -0.5/+1.5 jiffies because of the
+ * timer interrupt resolution and possible delay, but here we
+ * hit a quantization limit which can only be solved by higher
+ * resolution timers and decoupling time management from timer
+ * interrupts. This is also wrong on the clocks
+ * which require being written at the half second boundary.
+ * We should have an rtc call that only sets the minutes and
+ * seconds like on Intel to avoid problems with non UTC clocks.
+ */
+ if ( ppc_md.set_rtc_time && (time_status & STA_UNSYNC) == 0 &&
+ xtime.tv_sec - last_rtc_update >= 659 &&
+ abs((xtime.tv_nsec / 1000) - (1000000-1000000/HZ)) < 500000/HZ &&
+ jiffies - wall_jiffies == 1) {
+ if (ppc_md.set_rtc_time(xtime.tv_sec+1 + time_offset) == 0)
+ last_rtc_update = xtime.tv_sec+1;
+ else
+ /* Try again one minute later */
+ last_rtc_update += 60;
+ }
+ write_sequnlock(&xtime_lock);
+ }
+ if ( !disarm_decr[smp_processor_id()] )
+ set_dec(next_dec);
+ last_jiffy_stamp(cpu) = jiffy_stamp;
+
+ if (ppc_md.heartbeat && !ppc_md.heartbeat_count--)
+ ppc_md.heartbeat();
+
+ irq_exit();
+}
+
+/*
+ * This version of gettimeofday has microsecond resolution.
+ */
+void do_gettimeofday(struct timeval *tv)
+{
+ unsigned long flags;
+ unsigned long seq;
+ unsigned delta, lost_ticks, usec, sec;
+
+ do {
+ seq = read_seqbegin_irqsave(&xtime_lock, flags);
+ sec = xtime.tv_sec;
+ usec = (xtime.tv_nsec / 1000);
+ delta = tb_ticks_since(tb_last_stamp);
+#ifdef CONFIG_SMP
+ /* As long as timebases are not in sync, gettimeofday can only
+ * have jiffy resolution on SMP.
+ */
+ if (!smp_tb_synchronized)
+ delta = 0;
+#endif /* CONFIG_SMP */
+ lost_ticks = jiffies - wall_jiffies;
+ } while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
+
+ usec += mulhwu(tb_to_us, tb_ticks_per_jiffy * lost_ticks + delta);
+ while (usec >= 1000000) {
+ sec++;
+ usec -= 1000000;
+ }
+ tv->tv_sec = sec;
+ tv->tv_usec = usec;
+}
+
+EXPORT_SYMBOL(do_gettimeofday);
+
+int do_settimeofday(struct timespec *tv)
+{
+ time_t wtm_sec, new_sec = tv->tv_sec;
+ long wtm_nsec, new_nsec = tv->tv_nsec;
+ unsigned long flags;
+ int tb_delta;
+
+ if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+ return -EINVAL;
+
+ write_seqlock_irqsave(&xtime_lock, flags);
+ /* Updating the RTC is not the job of this code. If the time is
+ * stepped under NTP, the RTC will be update after STA_UNSYNC
+ * is cleared. Tool like clock/hwclock either copy the RTC
+ * to the system time, in which case there is no point in writing
+ * to the RTC again, or write to the RTC but then they don't call
+ * settimeofday to perform this operation. Note also that
+ * we don't touch the decrementer since:
+ * a) it would lose timer interrupt synchronization on SMP
+ * (if it is working one day)
+ * b) it could make one jiffy spuriously shorter or longer
+ * which would introduce another source of uncertainty potentially
+ * harmful to relatively short timers.
+ */
+
+ /* This works perfectly on SMP only if the tb are in sync but
+ * guarantees an error < 1 jiffy even if they are off by eons,
+ * still reasonable when gettimeofday resolution is 1 jiffy.
+ */
+ tb_delta = tb_ticks_since(last_jiffy_stamp(smp_processor_id()));
+ tb_delta += (jiffies - wall_jiffies) * tb_ticks_per_jiffy;
+
+ new_nsec -= 1000 * mulhwu(tb_to_us, tb_delta);
+
+ wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - new_sec);
+ wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - new_nsec);
+
+ set_normalized_timespec(&xtime, new_sec, new_nsec);
+ set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
+
+ /* In case of a large backwards jump in time with NTP, we want the
+ * clock to be updated as soon as the PLL is again in lock.
+ */
+ last_rtc_update = new_sec - 658;
+
+ time_adjust = 0; /* stop active adjtime() */
+ time_status |= STA_UNSYNC;
+ time_state = TIME_ERROR; /* p. 24, (a) */
+ time_maxerror = NTP_PHASE_LIMIT;
+ time_esterror = NTP_PHASE_LIMIT;
+ write_sequnlock_irqrestore(&xtime_lock, flags);
+ clock_was_set();
+ return 0;
+}
+
+EXPORT_SYMBOL(do_settimeofday);
+
+/* This function is only called on the boot processor */
+void __init time_init(void)
+{
+ time_t sec, old_sec;
+ unsigned old_stamp, stamp, elapsed;
+
+ if (ppc_md.time_init != NULL)
+ time_offset = ppc_md.time_init();
+
+ if (__USE_RTC()) {
+ /* 601 processor: dec counts down by 128 every 128ns */
+ tb_ticks_per_jiffy = DECREMENTER_COUNT_601;
+ /* mulhwu_scale_factor(1000000000, 1000000) is 0x418937 */
+ tb_to_us = 0x418937;
+ } else {
+ ppc_md.calibrate_decr();
+ tb_to_ns_scale = mulhwu(tb_to_us, 1000 << 10);
+ }
+
+ /* Now that the decrementer is calibrated, it can be used in case the
+ * clock is stuck, but the fact that we have to handle the 601
+ * makes things more complex. Repeatedly read the RTC until the
+ * next second boundary to try to achieve some precision. If there
+ * is no RTC, we still need to set tb_last_stamp and
+ * last_jiffy_stamp(cpu 0) to the current stamp.
+ */
+ stamp = get_native_tbl();
+ if (ppc_md.get_rtc_time) {
+ sec = ppc_md.get_rtc_time();
+ elapsed = 0;
+ do {
+ old_stamp = stamp;
+ old_sec = sec;
+ stamp = get_native_tbl();
+ if (__USE_RTC() && stamp < old_stamp)
+ old_stamp -= 1000000000;
+ elapsed += stamp - old_stamp;
+ sec = ppc_md.get_rtc_time();
+ } while ( sec == old_sec && elapsed < 2*HZ*tb_ticks_per_jiffy);
+ if (sec==old_sec)
+ printk("Warning: real time clock seems stuck!\n");
+ xtime.tv_sec = sec;
+ xtime.tv_nsec = 0;
+ /* No update now, we just read the time from the RTC ! */
+ last_rtc_update = xtime.tv_sec;
+ }
+ last_jiffy_stamp(0) = tb_last_stamp = stamp;
+
+ /* Not exact, but the timer interrupt takes care of this */
+ set_dec(tb_ticks_per_jiffy);
+
+ /* If platform provided a timezone (pmac), we correct the time */
+ if (time_offset) {
+ sys_tz.tz_minuteswest = -time_offset / 60;
+ sys_tz.tz_dsttime = 0;
+ xtime.tv_sec -= time_offset;
+ }
+ set_normalized_timespec(&wall_to_monotonic,
+ -xtime.tv_sec, -xtime.tv_nsec);
+}
+
+#define FEBRUARY 2
+#define STARTOFTIME 1970
+#define SECDAY 86400L
+#define SECYR (SECDAY * 365)
+
+/*
+ * Note: this is wrong for 2100, but our signed 32-bit time_t will
+ * have overflowed long before that, so who cares. -- paulus
+ */
+#define leapyear(year) ((year) % 4 == 0)
+#define days_in_year(a) (leapyear(a) ? 366 : 365)
+#define days_in_month(a) (month_days[(a) - 1])
+
+static int month_days[12] = {
+ 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31
+};
+
+void to_tm(int tim, struct rtc_time * tm)
+{
+ register int i;
+ register long hms, day, gday;
+
+ gday = day = tim / SECDAY;
+ hms = tim % SECDAY;
+
+ /* Hours, minutes, seconds are easy */
+ tm->tm_hour = hms / 3600;
+ tm->tm_min = (hms % 3600) / 60;
+ tm->tm_sec = (hms % 3600) % 60;
+
+ /* Number of years in days */
+ for (i = STARTOFTIME; day >= days_in_year(i); i++)
+ day -= days_in_year(i);
+ tm->tm_year = i;
+
+ /* Number of months in days left */
+ if (leapyear(tm->tm_year))
+ days_in_month(FEBRUARY) = 29;
+ for (i = 1; day >= days_in_month(i); i++)
+ day -= days_in_month(i);
+ days_in_month(FEBRUARY) = 28;
+ tm->tm_mon = i;
+
+ /* Days are what is left over (+1) from all that. */
+ tm->tm_mday = day + 1;
+
+ /*
+ * Determine the day of week. Jan. 1, 1970 was a Thursday.
+ */
+ tm->tm_wday = (gday + 4) % 7;
+}
+
+/* Auxiliary function to compute scaling factors */
+/* Actually the choice of a timebase running at 1/4 the of the bus
+ * frequency giving resolution of a few tens of nanoseconds is quite nice.
+ * It makes this computation very precise (27-28 bits typically) which
+ * is optimistic considering the stability of most processor clock
+ * oscillators and the precision with which the timebase frequency
+ * is measured but does not harm.
+ */
+unsigned mulhwu_scale_factor(unsigned inscale, unsigned outscale) {
+ unsigned mlt=0, tmp, err;
+ /* No concern for performance, it's done once: use a stupid
+ * but safe and compact method to find the multiplier.
+ */
+ for (tmp = 1U<<31; tmp != 0; tmp >>= 1) {
+ if (mulhwu(inscale, mlt|tmp) < outscale) mlt|=tmp;
+ }
+ /* We might still be off by 1 for the best approximation.
+ * A side effect of this is that if outscale is too large
+ * the returned value will be zero.
+ * Many corner cases have been checked and seem to work,
+ * some might have been forgotten in the test however.
+ */
+ err = inscale*(mlt+1);
+ if (err <= inscale/2) mlt++;
+ return mlt;
+}
+
+unsigned long long sched_clock(void)
+{
+ unsigned long lo, hi, hi2;
+ unsigned long long tb;
+
+ if (!__USE_RTC()) {
+ do {
+ hi = get_tbu();
+ lo = get_tbl();
+ hi2 = get_tbu();
+ } while (hi2 != hi);
+ tb = ((unsigned long long) hi << 32) | lo;
+ tb = (tb * tb_to_ns_scale) >> 10;
+ } else {
+ do {
+ hi = get_rtcu();
+ lo = get_rtcl();
+ hi2 = get_rtcu();
+ } while (hi2 != hi);
+ tb = ((unsigned long long) hi) * 1000000000 + lo;
+ }
+ return tb;
+}
diff --git a/arch/ppc/kernel/traps.c b/arch/ppc/kernel/traps.c
new file mode 100644
index 000000000000..ed5c7acdca70
--- /dev/null
+++ b/arch/ppc/kernel/traps.c
@@ -0,0 +1,886 @@
+/*
+ * arch/ppc/kernel/traps.c
+ *
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Modified by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras (paulus@cs.anu.edu.au)
+ */
+
+/*
+ * This file handles the architecture-dependent parts of hardware exceptions
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/a.out.h>
+#include <linux/interrupt.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/prctl.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/reg.h>
+#include <asm/xmon.h>
+#ifdef CONFIG_PMAC_BACKLIGHT
+#include <asm/backlight.h>
+#endif
+#include <asm/perfmon.h>
+
+#ifdef CONFIG_XMON
+void (*debugger)(struct pt_regs *regs) = xmon;
+int (*debugger_bpt)(struct pt_regs *regs) = xmon_bpt;
+int (*debugger_sstep)(struct pt_regs *regs) = xmon_sstep;
+int (*debugger_iabr_match)(struct pt_regs *regs) = xmon_iabr_match;
+int (*debugger_dabr_match)(struct pt_regs *regs) = xmon_dabr_match;
+void (*debugger_fault_handler)(struct pt_regs *regs);
+#else
+#ifdef CONFIG_KGDB
+void (*debugger)(struct pt_regs *regs);
+int (*debugger_bpt)(struct pt_regs *regs);
+int (*debugger_sstep)(struct pt_regs *regs);
+int (*debugger_iabr_match)(struct pt_regs *regs);
+int (*debugger_dabr_match)(struct pt_regs *regs);
+void (*debugger_fault_handler)(struct pt_regs *regs);
+#else
+#define debugger(regs) do { } while (0)
+#define debugger_bpt(regs) 0
+#define debugger_sstep(regs) 0
+#define debugger_iabr_match(regs) 0
+#define debugger_dabr_match(regs) 0
+#define debugger_fault_handler ((void (*)(struct pt_regs *))0)
+#endif
+#endif
+
+/*
+ * Trap & Exception support
+ */
+
+DEFINE_SPINLOCK(die_lock);
+
+void die(const char * str, struct pt_regs * fp, long err)
+{
+ static int die_counter;
+ int nl = 0;
+ console_verbose();
+ spin_lock_irq(&die_lock);
+#ifdef CONFIG_PMAC_BACKLIGHT
+ set_backlight_enable(1);
+ set_backlight_level(BACKLIGHT_MAX);
+#endif
+ printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
+#ifdef CONFIG_PREEMPT
+ printk("PREEMPT ");
+ nl = 1;
+#endif
+#ifdef CONFIG_SMP
+ printk("SMP NR_CPUS=%d ", NR_CPUS);
+ nl = 1;
+#endif
+ if (nl)
+ printk("\n");
+ show_regs(fp);
+ spin_unlock_irq(&die_lock);
+ /* do_exit() should take care of panic'ing from an interrupt
+ * context so we don't handle it here
+ */
+ do_exit(err);
+}
+
+void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
+{
+ siginfo_t info;
+
+ if (!user_mode(regs)) {
+ debugger(regs);
+ die("Exception in kernel mode", regs, signr);
+ }
+ info.si_signo = signr;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = (void __user *) addr;
+ force_sig_info(signr, &info, current);
+}
+
+/*
+ * I/O accesses can cause machine checks on powermacs.
+ * Check if the NIP corresponds to the address of a sync
+ * instruction for which there is an entry in the exception
+ * table.
+ * Note that the 601 only takes a machine check on TEA
+ * (transfer error ack) signal assertion, and does not
+ * set any of the top 16 bits of SRR1.
+ * -- paulus.
+ */
+static inline int check_io_access(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_PMAC
+ unsigned long msr = regs->msr;
+ const struct exception_table_entry *entry;
+ unsigned int *nip = (unsigned int *)regs->nip;
+
+ if (((msr & 0xffff0000) == 0 || (msr & (0x80000 | 0x40000)))
+ && (entry = search_exception_tables(regs->nip)) != NULL) {
+ /*
+ * Check that it's a sync instruction, or somewhere
+ * in the twi; isync; nop sequence that inb/inw/inl uses.
+ * As the address is in the exception table
+ * we should be able to read the instr there.
+ * For the debug message, we look at the preceding
+ * load or store.
+ */
+ if (*nip == 0x60000000) /* nop */
+ nip -= 2;
+ else if (*nip == 0x4c00012c) /* isync */
+ --nip;
+ if (*nip == 0x7c0004ac || (*nip >> 26) == 3) {
+ /* sync or twi */
+ unsigned int rb;
+
+ --nip;
+ rb = (*nip >> 11) & 0x1f;
+ printk(KERN_DEBUG "%s bad port %lx at %p\n",
+ (*nip & 0x100)? "OUT to": "IN from",
+ regs->gpr[rb] - _IO_BASE, nip);
+ regs->msr |= MSR_RI;
+ regs->nip = entry->fixup;
+ return 1;
+ }
+ }
+#endif /* CONFIG_PPC_PMAC */
+ return 0;
+}
+
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+/* On 4xx, the reason for the machine check or program exception
+ is in the ESR. */
+#define get_reason(regs) ((regs)->dsisr)
+#ifndef CONFIG_E500
+#define get_mc_reason(regs) ((regs)->dsisr)
+#else
+#define get_mc_reason(regs) (mfspr(SPRN_MCSR))
+#endif
+#define REASON_FP 0
+#define REASON_ILLEGAL ESR_PIL
+#define REASON_PRIVILEGED ESR_PPR
+#define REASON_TRAP ESR_PTR
+
+/* single-step stuff */
+#define single_stepping(regs) (current->thread.dbcr0 & DBCR0_IC)
+#define clear_single_step(regs) (current->thread.dbcr0 &= ~DBCR0_IC)
+
+#else
+/* On non-4xx, the reason for the machine check or program
+ exception is in the MSR. */
+#define get_reason(regs) ((regs)->msr)
+#define get_mc_reason(regs) ((regs)->msr)
+#define REASON_FP 0x100000
+#define REASON_ILLEGAL 0x80000
+#define REASON_PRIVILEGED 0x40000
+#define REASON_TRAP 0x20000
+
+#define single_stepping(regs) ((regs)->msr & MSR_SE)
+#define clear_single_step(regs) ((regs)->msr &= ~MSR_SE)
+#endif
+
+/*
+ * This is "fall-back" implementation for configurations
+ * which don't provide platform-specific machine check info
+ */
+void __attribute__ ((weak))
+platform_machine_check(struct pt_regs *regs)
+{
+}
+
+void MachineCheckException(struct pt_regs *regs)
+{
+ unsigned long reason = get_mc_reason(regs);
+
+ if (user_mode(regs)) {
+ regs->msr |= MSR_RI;
+ _exception(SIGBUS, regs, BUS_ADRERR, regs->nip);
+ return;
+ }
+
+#if defined(CONFIG_8xx) && defined(CONFIG_PCI)
+ /* the qspan pci read routines can cause machine checks -- Cort */
+ bad_page_fault(regs, regs->dar, SIGBUS);
+ return;
+#endif
+
+ if (debugger_fault_handler) {
+ debugger_fault_handler(regs);
+ regs->msr |= MSR_RI;
+ return;
+ }
+
+ if (check_io_access(regs))
+ return;
+
+#if defined(CONFIG_4xx) && !defined(CONFIG_440A)
+ if (reason & ESR_IMCP) {
+ printk("Instruction");
+ mtspr(SPRN_ESR, reason & ~ESR_IMCP);
+ } else
+ printk("Data");
+ printk(" machine check in kernel mode.\n");
+#elif defined(CONFIG_440A)
+ printk("Machine check in kernel mode.\n");
+ if (reason & ESR_IMCP){
+ printk("Instruction Synchronous Machine Check exception\n");
+ mtspr(SPRN_ESR, reason & ~ESR_IMCP);
+ }
+ else {
+ u32 mcsr = mfspr(SPRN_MCSR);
+ if (mcsr & MCSR_IB)
+ printk("Instruction Read PLB Error\n");
+ if (mcsr & MCSR_DRB)
+ printk("Data Read PLB Error\n");
+ if (mcsr & MCSR_DWB)
+ printk("Data Write PLB Error\n");
+ if (mcsr & MCSR_TLBP)
+ printk("TLB Parity Error\n");
+ if (mcsr & MCSR_ICP){
+ flush_instruction_cache();
+ printk("I-Cache Parity Error\n");
+ }
+ if (mcsr & MCSR_DCSP)
+ printk("D-Cache Search Parity Error\n");
+ if (mcsr & MCSR_DCFP)
+ printk("D-Cache Flush Parity Error\n");
+ if (mcsr & MCSR_IMPE)
+ printk("Machine Check exception is imprecise\n");
+
+ /* Clear MCSR */
+ mtspr(SPRN_MCSR, mcsr);
+ }
+#elif defined (CONFIG_E500)
+ printk("Machine check in kernel mode.\n");
+ printk("Caused by (from MCSR=%lx): ", reason);
+
+ if (reason & MCSR_MCP)
+ printk("Machine Check Signal\n");
+ if (reason & MCSR_ICPERR)
+ printk("Instruction Cache Parity Error\n");
+ if (reason & MCSR_DCP_PERR)
+ printk("Data Cache Push Parity Error\n");
+ if (reason & MCSR_DCPERR)
+ printk("Data Cache Parity Error\n");
+ if (reason & MCSR_GL_CI)
+ printk("Guarded Load or Cache-Inhibited stwcx.\n");
+ if (reason & MCSR_BUS_IAERR)
+ printk("Bus - Instruction Address Error\n");
+ if (reason & MCSR_BUS_RAERR)
+ printk("Bus - Read Address Error\n");
+ if (reason & MCSR_BUS_WAERR)
+ printk("Bus - Write Address Error\n");
+ if (reason & MCSR_BUS_IBERR)
+ printk("Bus - Instruction Data Error\n");
+ if (reason & MCSR_BUS_RBERR)
+ printk("Bus - Read Data Bus Error\n");
+ if (reason & MCSR_BUS_WBERR)
+ printk("Bus - Read Data Bus Error\n");
+ if (reason & MCSR_BUS_IPERR)
+ printk("Bus - Instruction Parity Error\n");
+ if (reason & MCSR_BUS_RPERR)
+ printk("Bus - Read Parity Error\n");
+#else /* !CONFIG_4xx && !CONFIG_E500 */
+ printk("Machine check in kernel mode.\n");
+ printk("Caused by (from SRR1=%lx): ", reason);
+ switch (reason & 0x601F0000) {
+ case 0x80000:
+ printk("Machine check signal\n");
+ break;
+ case 0: /* for 601 */
+ case 0x40000:
+ case 0x140000: /* 7450 MSS error and TEA */
+ printk("Transfer error ack signal\n");
+ break;
+ case 0x20000:
+ printk("Data parity error signal\n");
+ break;
+ case 0x10000:
+ printk("Address parity error signal\n");
+ break;
+ case 0x20000000:
+ printk("L1 Data Cache error\n");
+ break;
+ case 0x40000000:
+ printk("L1 Instruction Cache error\n");
+ break;
+ case 0x00100000:
+ printk("L2 data cache parity error\n");
+ break;
+ default:
+ printk("Unknown values in msr\n");
+ }
+#endif /* CONFIG_4xx */
+
+ /*
+ * Optional platform-provided routine to print out
+ * additional info, e.g. bus error registers.
+ */
+ platform_machine_check(regs);
+
+ debugger(regs);
+ die("machine check", regs, SIGBUS);
+}
+
+void SMIException(struct pt_regs *regs)
+{
+ debugger(regs);
+#if !(defined(CONFIG_XMON) || defined(CONFIG_KGDB))
+ show_regs(regs);
+ panic("System Management Interrupt");
+#endif
+}
+
+void UnknownException(struct pt_regs *regs)
+{
+ printk("Bad trap at PC: %lx, MSR: %lx, vector=%lx %s\n",
+ regs->nip, regs->msr, regs->trap, print_tainted());
+ _exception(SIGTRAP, regs, 0, 0);
+}
+
+void InstructionBreakpoint(struct pt_regs *regs)
+{
+ if (debugger_iabr_match(regs))
+ return;
+ _exception(SIGTRAP, regs, TRAP_BRKPT, 0);
+}
+
+void RunModeException(struct pt_regs *regs)
+{
+ _exception(SIGTRAP, regs, 0, 0);
+}
+
+/* Illegal instruction emulation support. Originally written to
+ * provide the PVR to user applications using the mfspr rd, PVR.
+ * Return non-zero if we can't emulate, or -EFAULT if the associated
+ * memory access caused an access fault. Return zero on success.
+ *
+ * There are a couple of ways to do this, either "decode" the instruction
+ * or directly match lots of bits. In this case, matching lots of
+ * bits is faster and easier.
+ *
+ */
+#define INST_MFSPR_PVR 0x7c1f42a6
+#define INST_MFSPR_PVR_MASK 0xfc1fffff
+
+#define INST_DCBA 0x7c0005ec
+#define INST_DCBA_MASK 0x7c0007fe
+
+#define INST_MCRXR 0x7c000400
+#define INST_MCRXR_MASK 0x7c0007fe
+
+#define INST_STRING 0x7c00042a
+#define INST_STRING_MASK 0x7c0007fe
+#define INST_STRING_GEN_MASK 0x7c00067e
+#define INST_LSWI 0x7c0004aa
+#define INST_LSWX 0x7c00042a
+#define INST_STSWI 0x7c0005aa
+#define INST_STSWX 0x7c00052a
+
+static int emulate_string_inst(struct pt_regs *regs, u32 instword)
+{
+ u8 rT = (instword >> 21) & 0x1f;
+ u8 rA = (instword >> 16) & 0x1f;
+ u8 NB_RB = (instword >> 11) & 0x1f;
+ u32 num_bytes;
+ u32 EA;
+ int pos = 0;
+
+ /* Early out if we are an invalid form of lswx */
+ if ((instword & INST_STRING_MASK) == INST_LSWX)
+ if ((rA >= rT) || (NB_RB >= rT) || (rT == rA) || (rT == NB_RB))
+ return -EINVAL;
+
+ /* Early out if we are an invalid form of lswi */
+ if ((instword & INST_STRING_MASK) == INST_LSWI)
+ if ((rA >= rT) || (rT == rA))
+ return -EINVAL;
+
+ EA = (rA == 0) ? 0 : regs->gpr[rA];
+
+ switch (instword & INST_STRING_MASK) {
+ case INST_LSWX:
+ case INST_STSWX:
+ EA += NB_RB;
+ num_bytes = regs->xer & 0x7f;
+ break;
+ case INST_LSWI:
+ case INST_STSWI:
+ num_bytes = (NB_RB == 0) ? 32 : NB_RB;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ while (num_bytes != 0)
+ {
+ u8 val;
+ u32 shift = 8 * (3 - (pos & 0x3));
+
+ switch ((instword & INST_STRING_MASK)) {
+ case INST_LSWX:
+ case INST_LSWI:
+ if (get_user(val, (u8 __user *)EA))
+ return -EFAULT;
+ /* first time updating this reg,
+ * zero it out */
+ if (pos == 0)
+ regs->gpr[rT] = 0;
+ regs->gpr[rT] |= val << shift;
+ break;
+ case INST_STSWI:
+ case INST_STSWX:
+ val = regs->gpr[rT] >> shift;
+ if (put_user(val, (u8 __user *)EA))
+ return -EFAULT;
+ break;
+ }
+ /* move EA to next address */
+ EA += 1;
+ num_bytes--;
+
+ /* manage our position within the register */
+ if (++pos == 4) {
+ pos = 0;
+ if (++rT == 32)
+ rT = 0;
+ }
+ }
+
+ return 0;
+}
+
+static int emulate_instruction(struct pt_regs *regs)
+{
+ u32 instword;
+ u32 rd;
+
+ if (!user_mode(regs))
+ return -EINVAL;
+ CHECK_FULL_REGS(regs);
+
+ if (get_user(instword, (u32 __user *)(regs->nip)))
+ return -EFAULT;
+
+ /* Emulate the mfspr rD, PVR.
+ */
+ if ((instword & INST_MFSPR_PVR_MASK) == INST_MFSPR_PVR) {
+ rd = (instword >> 21) & 0x1f;
+ regs->gpr[rd] = mfspr(SPRN_PVR);
+ return 0;
+ }
+
+ /* Emulating the dcba insn is just a no-op. */
+ if ((instword & INST_DCBA_MASK) == INST_DCBA)
+ return 0;
+
+ /* Emulate the mcrxr insn. */
+ if ((instword & INST_MCRXR_MASK) == INST_MCRXR) {
+ int shift = (instword >> 21) & 0x1c;
+ unsigned long msk = 0xf0000000UL >> shift;
+
+ regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk);
+ regs->xer &= ~0xf0000000UL;
+ return 0;
+ }
+
+ /* Emulate load/store string insn. */
+ if ((instword & INST_STRING_GEN_MASK) == INST_STRING)
+ return emulate_string_inst(regs, instword);
+
+ return -EINVAL;
+}
+
+/*
+ * After we have successfully emulated an instruction, we have to
+ * check if the instruction was being single-stepped, and if so,
+ * pretend we got a single-step exception. This was pointed out
+ * by Kumar Gala. -- paulus
+ */
+static void emulate_single_step(struct pt_regs *regs)
+{
+ if (single_stepping(regs)) {
+ clear_single_step(regs);
+ _exception(SIGTRAP, regs, TRAP_TRACE, 0);
+ }
+}
+
+/*
+ * Look through the list of trap instructions that are used for BUG(),
+ * BUG_ON() and WARN_ON() and see if we hit one. At this point we know
+ * that the exception was caused by a trap instruction of some kind.
+ * Returns 1 if we should continue (i.e. it was a WARN_ON) or 0
+ * otherwise.
+ */
+extern struct bug_entry __start___bug_table[], __stop___bug_table[];
+
+#ifndef CONFIG_MODULES
+#define module_find_bug(x) NULL
+#endif
+
+static struct bug_entry *find_bug(unsigned long bugaddr)
+{
+ struct bug_entry *bug;
+
+ for (bug = __start___bug_table; bug < __stop___bug_table; ++bug)
+ if (bugaddr == bug->bug_addr)
+ return bug;
+ return module_find_bug(bugaddr);
+}
+
+int check_bug_trap(struct pt_regs *regs)
+{
+ struct bug_entry *bug;
+ unsigned long addr;
+
+ if (regs->msr & MSR_PR)
+ return 0; /* not in kernel */
+ addr = regs->nip; /* address of trap instruction */
+ if (addr < PAGE_OFFSET)
+ return 0;
+ bug = find_bug(regs->nip);
+ if (bug == NULL)
+ return 0;
+ if (bug->line & BUG_WARNING_TRAP) {
+ /* this is a WARN_ON rather than BUG/BUG_ON */
+#ifdef CONFIG_XMON
+ xmon_printf(KERN_ERR "Badness in %s at %s:%d\n",
+ bug->function, bug->file,
+ bug->line & ~BUG_WARNING_TRAP);
+#endif /* CONFIG_XMON */
+ printk(KERN_ERR "Badness in %s at %s:%d\n",
+ bug->function, bug->file,
+ bug->line & ~BUG_WARNING_TRAP);
+ dump_stack();
+ return 1;
+ }
+#ifdef CONFIG_XMON
+ xmon_printf(KERN_CRIT "kernel BUG in %s at %s:%d!\n",
+ bug->function, bug->file, bug->line);
+ xmon(regs);
+#endif /* CONFIG_XMON */
+ printk(KERN_CRIT "kernel BUG in %s at %s:%d!\n",
+ bug->function, bug->file, bug->line);
+
+ return 0;
+}
+
+void ProgramCheckException(struct pt_regs *regs)
+{
+ unsigned int reason = get_reason(regs);
+ extern int do_mathemu(struct pt_regs *regs);
+
+#ifdef CONFIG_MATH_EMULATION
+ /* (reason & REASON_ILLEGAL) would be the obvious thing here,
+ * but there seems to be a hardware bug on the 405GP (RevD)
+ * that means ESR is sometimes set incorrectly - either to
+ * ESR_DST (!?) or 0. In the process of chasing this with the
+ * hardware people - not sure if it can happen on any illegal
+ * instruction or only on FP instructions, whether there is a
+ * pattern to occurences etc. -dgibson 31/Mar/2003 */
+ if (!(reason & REASON_TRAP) && do_mathemu(regs) == 0) {
+ emulate_single_step(regs);
+ return;
+ }
+#endif /* CONFIG_MATH_EMULATION */
+
+ if (reason & REASON_FP) {
+ /* IEEE FP exception */
+ int code = 0;
+ u32 fpscr;
+
+ /* We must make sure the FP state is consistent with
+ * our MSR_FP in regs
+ */
+ preempt_disable();
+ if (regs->msr & MSR_FP)
+ giveup_fpu(current);
+ preempt_enable();
+
+ fpscr = current->thread.fpscr;
+ fpscr &= fpscr << 22; /* mask summary bits with enables */
+ if (fpscr & FPSCR_VX)
+ code = FPE_FLTINV;
+ else if (fpscr & FPSCR_OX)
+ code = FPE_FLTOVF;
+ else if (fpscr & FPSCR_UX)
+ code = FPE_FLTUND;
+ else if (fpscr & FPSCR_ZX)
+ code = FPE_FLTDIV;
+ else if (fpscr & FPSCR_XX)
+ code = FPE_FLTRES;
+ _exception(SIGFPE, regs, code, regs->nip);
+ return;
+ }
+
+ if (reason & REASON_TRAP) {
+ /* trap exception */
+ if (debugger_bpt(regs))
+ return;
+ if (check_bug_trap(regs)) {
+ regs->nip += 4;
+ return;
+ }
+ _exception(SIGTRAP, regs, TRAP_BRKPT, 0);
+ return;
+ }
+
+ /* Try to emulate it if we should. */
+ if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
+ switch (emulate_instruction(regs)) {
+ case 0:
+ regs->nip += 4;
+ emulate_single_step(regs);
+ return;
+ case -EFAULT:
+ _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+ return;
+ }
+ }
+
+ if (reason & REASON_PRIVILEGED)
+ _exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
+ else
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+}
+
+void SingleStepException(struct pt_regs *regs)
+{
+ regs->msr &= ~(MSR_SE | MSR_BE); /* Turn off 'trace' bits */
+ if (debugger_sstep(regs))
+ return;
+ _exception(SIGTRAP, regs, TRAP_TRACE, 0);
+}
+
+void AlignmentException(struct pt_regs *regs)
+{
+ int fixed;
+
+ fixed = fix_alignment(regs);
+ if (fixed == 1) {
+ regs->nip += 4; /* skip over emulated instruction */
+ return;
+ }
+ if (fixed == -EFAULT) {
+ /* fixed == -EFAULT means the operand address was bad */
+ if (user_mode(regs))
+ _exception(SIGSEGV, regs, SEGV_ACCERR, regs->dar);
+ else
+ bad_page_fault(regs, regs->dar, SIGSEGV);
+ return;
+ }
+ _exception(SIGBUS, regs, BUS_ADRALN, regs->dar);
+}
+
+void StackOverflow(struct pt_regs *regs)
+{
+ printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n",
+ current, regs->gpr[1]);
+ debugger(regs);
+ show_regs(regs);
+ panic("kernel stack overflow");
+}
+
+void nonrecoverable_exception(struct pt_regs *regs)
+{
+ printk(KERN_ERR "Non-recoverable exception at PC=%lx MSR=%lx\n",
+ regs->nip, regs->msr);
+ debugger(regs);
+ die("nonrecoverable exception", regs, SIGKILL);
+}
+
+void trace_syscall(struct pt_regs *regs)
+{
+ printk("Task: %p(%d), PC: %08lX/%08lX, Syscall: %3ld, Result: %s%ld %s\n",
+ current, current->pid, regs->nip, regs->link, regs->gpr[0],
+ regs->ccr&0x10000000?"Error=":"", regs->gpr[3], print_tainted());
+}
+
+#ifdef CONFIG_8xx
+void SoftwareEmulation(struct pt_regs *regs)
+{
+ extern int do_mathemu(struct pt_regs *);
+ extern int Soft_emulate_8xx(struct pt_regs *);
+ int errcode;
+
+ CHECK_FULL_REGS(regs);
+
+ if (!user_mode(regs)) {
+ debugger(regs);
+ die("Kernel Mode Software FPU Emulation", regs, SIGFPE);
+ }
+
+#ifdef CONFIG_MATH_EMULATION
+ errcode = do_mathemu(regs);
+#else
+ errcode = Soft_emulate_8xx(regs);
+#endif
+ if (errcode) {
+ if (errcode > 0)
+ _exception(SIGFPE, regs, 0, 0);
+ else if (errcode == -EFAULT)
+ _exception(SIGSEGV, regs, 0, 0);
+ else
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ } else
+ emulate_single_step(regs);
+}
+#endif /* CONFIG_8xx */
+
+#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+
+void DebugException(struct pt_regs *regs, unsigned long debug_status)
+{
+ if (debug_status & DBSR_IC) { /* instruction completion */
+ regs->msr &= ~MSR_DE;
+ if (user_mode(regs)) {
+ current->thread.dbcr0 &= ~DBCR0_IC;
+ } else {
+ /* Disable instruction completion */
+ mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_IC);
+ /* Clear the instruction completion event */
+ mtspr(SPRN_DBSR, DBSR_IC);
+ if (debugger_sstep(regs))
+ return;
+ }
+ _exception(SIGTRAP, regs, TRAP_TRACE, 0);
+ }
+}
+#endif /* CONFIG_4xx || CONFIG_BOOKE */
+
+#if !defined(CONFIG_TAU_INT)
+void TAUException(struct pt_regs *regs)
+{
+ printk("TAU trap at PC: %lx, MSR: %lx, vector=%lx %s\n",
+ regs->nip, regs->msr, regs->trap, print_tainted());
+}
+#endif /* CONFIG_INT_TAU */
+
+void AltivecUnavailException(struct pt_regs *regs)
+{
+ static int kernel_altivec_count;
+
+#ifndef CONFIG_ALTIVEC
+ if (user_mode(regs)) {
+ /* A user program has executed an altivec instruction,
+ but this kernel doesn't support altivec. */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return;
+ }
+#endif
+ /* The kernel has executed an altivec instruction without
+ first enabling altivec. Whinge but let it do it. */
+ if (++kernel_altivec_count < 10)
+ printk(KERN_ERR "AltiVec used in kernel (task=%p, pc=%lx)\n",
+ current, regs->nip);
+ regs->msr |= MSR_VEC;
+}
+
+#ifdef CONFIG_ALTIVEC
+void AltivecAssistException(struct pt_regs *regs)
+{
+ int err;
+
+ preempt_disable();
+ if (regs->msr & MSR_VEC)
+ giveup_altivec(current);
+ preempt_enable();
+
+ err = emulate_altivec(regs);
+ if (err == 0) {
+ regs->nip += 4; /* skip emulated instruction */
+ emulate_single_step(regs);
+ return;
+ }
+
+ if (err == -EFAULT) {
+ /* got an error reading the instruction */
+ _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+ } else {
+ /* didn't recognize the instruction */
+ /* XXX quick hack for now: set the non-Java bit in the VSCR */
+ printk(KERN_ERR "unrecognized altivec instruction "
+ "in %s at %lx\n", current->comm, regs->nip);
+ current->thread.vscr.u[3] |= 0x10000;
+ }
+}
+#endif /* CONFIG_ALTIVEC */
+
+void PerformanceMonitorException(struct pt_regs *regs)
+{
+ perf_irq(regs);
+}
+
+#ifdef CONFIG_FSL_BOOKE
+void CacheLockingException(struct pt_regs *regs, unsigned long address,
+ unsigned long error_code)
+{
+ /* We treat cache locking instructions from the user
+ * as priv ops, in the future we could try to do
+ * something smarter
+ */
+ if (error_code & (ESR_DLK|ESR_ILK))
+ _exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
+ return;
+}
+#endif /* CONFIG_FSL_BOOKE */
+
+#ifdef CONFIG_SPE
+void SPEFloatingPointException(struct pt_regs *regs)
+{
+ unsigned long spefscr;
+ int fpexc_mode;
+ int code = 0;
+
+ spefscr = current->thread.spefscr;
+ fpexc_mode = current->thread.fpexc_mode;
+
+ /* Hardware does not neccessarily set sticky
+ * underflow/overflow/invalid flags */
+ if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) {
+ code = FPE_FLTOVF;
+ spefscr |= SPEFSCR_FOVFS;
+ }
+ else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) {
+ code = FPE_FLTUND;
+ spefscr |= SPEFSCR_FUNFS;
+ }
+ else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV))
+ code = FPE_FLTDIV;
+ else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) {
+ code = FPE_FLTINV;
+ spefscr |= SPEFSCR_FINVS;
+ }
+ else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES))
+ code = FPE_FLTRES;
+
+ current->thread.spefscr = spefscr;
+
+ _exception(SIGFPE, regs, code, regs->nip);
+ return;
+}
+#endif
+
+void __init trap_init(void)
+{
+}
diff --git a/arch/ppc/kernel/vecemu.c b/arch/ppc/kernel/vecemu.c
new file mode 100644
index 000000000000..604d0947cb20
--- /dev/null
+++ b/arch/ppc/kernel/vecemu.c
@@ -0,0 +1,345 @@
+/*
+ * Routines to emulate some Altivec/VMX instructions, specifically
+ * those that can trap when given denormalized operands in Java mode.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
+
+/* Functions in vector.S */
+extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b);
+extern void vsubfp(vector128 *dst, vector128 *a, vector128 *b);
+extern void vmaddfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
+extern void vnmsubfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
+extern void vrefp(vector128 *dst, vector128 *src);
+extern void vrsqrtefp(vector128 *dst, vector128 *src);
+extern void vexptep(vector128 *dst, vector128 *src);
+
+static unsigned int exp2s[8] = {
+ 0x800000,
+ 0x8b95c2,
+ 0x9837f0,
+ 0xa5fed7,
+ 0xb504f3,
+ 0xc5672a,
+ 0xd744fd,
+ 0xeac0c7
+};
+
+/*
+ * Computes an estimate of 2^x. The `s' argument is the 32-bit
+ * single-precision floating-point representation of x.
+ */
+static unsigned int eexp2(unsigned int s)
+{
+ int exp, pwr;
+ unsigned int mant, frac;
+
+ /* extract exponent field from input */
+ exp = ((s >> 23) & 0xff) - 127;
+ if (exp > 7) {
+ /* check for NaN input */
+ if (exp == 128 && (s & 0x7fffff) != 0)
+ return s | 0x400000; /* return QNaN */
+ /* 2^-big = 0, 2^+big = +Inf */
+ return (s & 0x80000000)? 0: 0x7f800000; /* 0 or +Inf */
+ }
+ if (exp < -23)
+ return 0x3f800000; /* 1.0 */
+
+ /* convert to fixed point integer in 9.23 representation */
+ pwr = (s & 0x7fffff) | 0x800000;
+ if (exp > 0)
+ pwr <<= exp;
+ else
+ pwr >>= -exp;
+ if (s & 0x80000000)
+ pwr = -pwr;
+
+ /* extract integer part, which becomes exponent part of result */
+ exp = (pwr >> 23) + 126;
+ if (exp >= 254)
+ return 0x7f800000;
+ if (exp < -23)
+ return 0;
+
+ /* table lookup on top 3 bits of fraction to get mantissa */
+ mant = exp2s[(pwr >> 20) & 7];
+
+ /* linear interpolation using remaining 20 bits of fraction */
+ asm("mulhwu %0,%1,%2" : "=r" (frac)
+ : "r" (pwr << 12), "r" (0x172b83ff));
+ asm("mulhwu %0,%1,%2" : "=r" (frac) : "r" (frac), "r" (mant));
+ mant += frac;
+
+ if (exp >= 0)
+ return mant + (exp << 23);
+
+ /* denormalized result */
+ exp = -exp;
+ mant += 1 << (exp - 1);
+ return mant >> exp;
+}
+
+/*
+ * Computes an estimate of log_2(x). The `s' argument is the 32-bit
+ * single-precision floating-point representation of x.
+ */
+static unsigned int elog2(unsigned int s)
+{
+ int exp, mant, lz, frac;
+
+ exp = s & 0x7f800000;
+ mant = s & 0x7fffff;
+ if (exp == 0x7f800000) { /* Inf or NaN */
+ if (mant != 0)
+ s |= 0x400000; /* turn NaN into QNaN */
+ return s;
+ }
+ if ((exp | mant) == 0) /* +0 or -0 */
+ return 0xff800000; /* return -Inf */
+
+ if (exp == 0) {
+ /* denormalized */
+ asm("cntlzw %0,%1" : "=r" (lz) : "r" (mant));
+ mant <<= lz - 8;
+ exp = (-118 - lz) << 23;
+ } else {
+ mant |= 0x800000;
+ exp -= 127 << 23;
+ }
+
+ if (mant >= 0xb504f3) { /* 2^0.5 * 2^23 */
+ exp |= 0x400000; /* 0.5 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xb504f334)); /* 2^-0.5 * 2^32 */
+ }
+ if (mant >= 0x9837f0) { /* 2^0.25 * 2^23 */
+ exp |= 0x200000; /* 0.25 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xd744fccb)); /* 2^-0.25 * 2^32 */
+ }
+ if (mant >= 0x8b95c2) { /* 2^0.125 * 2^23 */
+ exp |= 0x100000; /* 0.125 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xeac0c6e8)); /* 2^-0.125 * 2^32 */
+ }
+ if (mant > 0x800000) { /* 1.0 * 2^23 */
+ /* calculate (mant - 1) * 1.381097463 */
+ /* 1.381097463 == 0.125 / (2^0.125 - 1) */
+ asm("mulhwu %0,%1,%2" : "=r" (frac)
+ : "r" ((mant - 0x800000) << 1), "r" (0xb0c7cd3a));
+ exp += frac;
+ }
+ s = exp & 0x80000000;
+ if (exp != 0) {
+ if (s)
+ exp = -exp;
+ asm("cntlzw %0,%1" : "=r" (lz) : "r" (exp));
+ lz = 8 - lz;
+ if (lz > 0)
+ exp >>= lz;
+ else if (lz < 0)
+ exp <<= -lz;
+ s += ((lz + 126) << 23) + exp;
+ }
+ return s;
+}
+
+#define VSCR_SAT 1
+
+static int ctsxs(unsigned int x, int scale, unsigned int *vscrp)
+{
+ int exp, mant;
+
+ exp = (x >> 23) & 0xff;
+ mant = x & 0x7fffff;
+ if (exp == 255 && mant != 0)
+ return 0; /* NaN -> 0 */
+ exp = exp - 127 + scale;
+ if (exp < 0)
+ return 0; /* round towards zero */
+ if (exp >= 31) {
+ /* saturate, unless the result would be -2^31 */
+ if (x + (scale << 23) != 0xcf000000)
+ *vscrp |= VSCR_SAT;
+ return (x & 0x80000000)? 0x80000000: 0x7fffffff;
+ }
+ mant |= 0x800000;
+ mant = (mant << 7) >> (30 - exp);
+ return (x & 0x80000000)? -mant: mant;
+}
+
+static unsigned int ctuxs(unsigned int x, int scale, unsigned int *vscrp)
+{
+ int exp;
+ unsigned int mant;
+
+ exp = (x >> 23) & 0xff;
+ mant = x & 0x7fffff;
+ if (exp == 255 && mant != 0)
+ return 0; /* NaN -> 0 */
+ exp = exp - 127 + scale;
+ if (exp < 0)
+ return 0; /* round towards zero */
+ if (x & 0x80000000) {
+ /* negative => saturate to 0 */
+ *vscrp |= VSCR_SAT;
+ return 0;
+ }
+ if (exp >= 32) {
+ /* saturate */
+ *vscrp |= VSCR_SAT;
+ return 0xffffffff;
+ }
+ mant |= 0x800000;
+ mant = (mant << 8) >> (31 - exp);
+ return mant;
+}
+
+/* Round to floating integer, towards 0 */
+static unsigned int rfiz(unsigned int x)
+{
+ int exp;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if (exp < 0)
+ return x & 0x80000000; /* |x| < 1.0 rounds to 0 */
+ return x & ~(0x7fffff >> exp);
+}
+
+/* Round to floating integer, towards +/- Inf */
+static unsigned int rfii(unsigned int x)
+{
+ int exp, mask;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if ((x & 0x7fffffff) == 0)
+ return x; /* +/-0 -> +/-0 */
+ if (exp < 0)
+ /* 0 < |x| < 1.0 rounds to +/- 1.0 */
+ return (x & 0x80000000) | 0x3f800000;
+ mask = 0x7fffff >> exp;
+ /* mantissa overflows into exponent - that's OK,
+ it can't overflow into the sign bit */
+ return (x + mask) & ~mask;
+}
+
+/* Round to floating integer, to nearest */
+static unsigned int rfin(unsigned int x)
+{
+ int exp, half;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if (exp < -1)
+ return x & 0x80000000; /* |x| < 0.5 -> +/-0 */
+ if (exp == -1)
+ /* 0.5 <= |x| < 1.0 rounds to +/- 1.0 */
+ return (x & 0x80000000) | 0x3f800000;
+ half = 0x400000 >> exp;
+ /* add 0.5 to the magnitude and chop off the fraction bits */
+ return (x + half) & ~(0x7fffff >> exp);
+}
+
+int emulate_altivec(struct pt_regs *regs)
+{
+ unsigned int instr, i;
+ unsigned int va, vb, vc, vd;
+ vector128 *vrs;
+
+ if (get_user(instr, (unsigned int __user *) regs->nip))
+ return -EFAULT;
+ if ((instr >> 26) != 4)
+ return -EINVAL; /* not an altivec instruction */
+ vd = (instr >> 21) & 0x1f;
+ va = (instr >> 16) & 0x1f;
+ vb = (instr >> 11) & 0x1f;
+ vc = (instr >> 6) & 0x1f;
+
+ vrs = current->thread.vr;
+ switch (instr & 0x3f) {
+ case 10:
+ switch (vc) {
+ case 0: /* vaddfp */
+ vaddfp(&vrs[vd], &vrs[va], &vrs[vb]);
+ break;
+ case 1: /* vsubfp */
+ vsubfp(&vrs[vd], &vrs[va], &vrs[vb]);
+ break;
+ case 4: /* vrefp */
+ vrefp(&vrs[vd], &vrs[vb]);
+ break;
+ case 5: /* vrsqrtefp */
+ vrsqrtefp(&vrs[vd], &vrs[vb]);
+ break;
+ case 6: /* vexptefp */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = eexp2(vrs[vb].u[i]);
+ break;
+ case 7: /* vlogefp */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = elog2(vrs[vb].u[i]);
+ break;
+ case 8: /* vrfin */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = rfin(vrs[vb].u[i]);
+ break;
+ case 9: /* vrfiz */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = rfiz(vrs[vb].u[i]);
+ break;
+ case 10: /* vrfip */
+ for (i = 0; i < 4; ++i) {
+ u32 x = vrs[vb].u[i];
+ x = (x & 0x80000000)? rfiz(x): rfii(x);
+ vrs[vd].u[i] = x;
+ }
+ break;
+ case 11: /* vrfim */
+ for (i = 0; i < 4; ++i) {
+ u32 x = vrs[vb].u[i];
+ x = (x & 0x80000000)? rfii(x): rfiz(x);
+ vrs[vd].u[i] = x;
+ }
+ break;
+ case 14: /* vctuxs */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va,
+ &current->thread.vscr.u[3]);
+ break;
+ case 15: /* vctsxs */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va,
+ &current->thread.vscr.u[3]);
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case 46: /* vmaddfp */
+ vmaddfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
+ break;
+ case 47: /* vnmsubfp */
+ vnmsubfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
diff --git a/arch/ppc/kernel/vector.S b/arch/ppc/kernel/vector.S
new file mode 100644
index 000000000000..82a21346bf80
--- /dev/null
+++ b/arch/ppc/kernel/vector.S
@@ -0,0 +1,217 @@
+#include <asm/ppc_asm.h>
+#include <asm/processor.h>
+
+/*
+ * The routines below are in assembler so we can closely control the
+ * usage of floating-point registers. These routines must be called
+ * with preempt disabled.
+ */
+ .data
+fpzero:
+ .long 0
+fpone:
+ .long 0x3f800000 /* 1.0 in single-precision FP */
+fphalf:
+ .long 0x3f000000 /* 0.5 in single-precision FP */
+
+ .text
+/*
+ * Internal routine to enable floating point and set FPSCR to 0.
+ * Don't call it from C; it doesn't use the normal calling convention.
+ */
+fpenable:
+ mfmsr r10
+ ori r11,r10,MSR_FP
+ mtmsr r11
+ isync
+ stfd fr0,24(r1)
+ stfd fr1,16(r1)
+ stfd fr31,8(r1)
+ lis r11,fpzero@ha
+ mffs fr31
+ lfs fr1,fpzero@l(r11)
+ mtfsf 0xff,fr1
+ blr
+
+fpdisable:
+ mtfsf 0xff,fr31
+ lfd fr31,8(r1)
+ lfd fr1,16(r1)
+ lfd fr0,24(r1)
+ mtmsr r10
+ isync
+ blr
+
+/*
+ * Vector add, floating point.
+ */
+ .globl vaddfp
+vaddfp:
+ stwu r1,-32(r1)
+ mflr r0
+ stw r0,36(r1)
+ bl fpenable
+ li r0,4
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ lfsx fr1,r5,r6
+ fadds fr0,fr0,fr1
+ stfsx fr0,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ bl fpdisable
+ lwz r0,36(r1)
+ mtlr r0
+ addi r1,r1,32
+ blr
+
+/*
+ * Vector subtract, floating point.
+ */
+ .globl vsubfp
+vsubfp:
+ stwu r1,-32(r1)
+ mflr r0
+ stw r0,36(r1)
+ bl fpenable
+ li r0,4
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ lfsx fr1,r5,r6
+ fsubs fr0,fr0,fr1
+ stfsx fr0,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ bl fpdisable
+ lwz r0,36(r1)
+ mtlr r0
+ addi r1,r1,32
+ blr
+
+/*
+ * Vector multiply and add, floating point.
+ */
+ .globl vmaddfp
+vmaddfp:
+ stwu r1,-48(r1)
+ mflr r0
+ stw r0,52(r1)
+ bl fpenable
+ stfd fr2,32(r1)
+ li r0,4
+ mtctr r0
+ li r7,0
+1: lfsx fr0,r4,r7
+ lfsx fr1,r5,r7
+ lfsx fr2,r6,r7
+ fmadds fr0,fr0,fr2,fr1
+ stfsx fr0,r3,r7
+ addi r7,r7,4
+ bdnz 1b
+ lfd fr2,32(r1)
+ bl fpdisable
+ lwz r0,52(r1)
+ mtlr r0
+ addi r1,r1,48
+ blr
+
+/*
+ * Vector negative multiply and subtract, floating point.
+ */
+ .globl vnmsubfp
+vnmsubfp:
+ stwu r1,-48(r1)
+ mflr r0
+ stw r0,52(r1)
+ bl fpenable
+ stfd fr2,32(r1)
+ li r0,4
+ mtctr r0
+ li r7,0
+1: lfsx fr0,r4,r7
+ lfsx fr1,r5,r7
+ lfsx fr2,r6,r7
+ fnmsubs fr0,fr0,fr2,fr1
+ stfsx fr0,r3,r7
+ addi r7,r7,4
+ bdnz 1b
+ lfd fr2,32(r1)
+ bl fpdisable
+ lwz r0,52(r1)
+ mtlr r0
+ addi r1,r1,48
+ blr
+
+/*
+ * Vector reciprocal estimate. We just compute 1.0/x.
+ * r3 -> destination, r4 -> source.
+ */
+ .globl vrefp
+vrefp:
+ stwu r1,-32(r1)
+ mflr r0
+ stw r0,36(r1)
+ bl fpenable
+ lis r9,fpone@ha
+ li r0,4
+ lfs fr1,fpone@l(r9)
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ fdivs fr0,fr1,fr0
+ stfsx fr0,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ bl fpdisable
+ lwz r0,36(r1)
+ mtlr r0
+ addi r1,r1,32
+ blr
+
+/*
+ * Vector reciprocal square-root estimate, floating point.
+ * We use the frsqrte instruction for the initial estimate followed
+ * by 2 iterations of Newton-Raphson to get sufficient accuracy.
+ * r3 -> destination, r4 -> source.
+ */
+ .globl vrsqrtefp
+vrsqrtefp:
+ stwu r1,-48(r1)
+ mflr r0
+ stw r0,52(r1)
+ bl fpenable
+ stfd fr2,32(r1)
+ stfd fr3,40(r1)
+ stfd fr4,48(r1)
+ stfd fr5,56(r1)
+ lis r9,fpone@ha
+ lis r8,fphalf@ha
+ li r0,4
+ lfs fr4,fpone@l(r9)
+ lfs fr5,fphalf@l(r8)
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ frsqrte fr1,fr0 /* r = frsqrte(s) */
+ fmuls fr3,fr1,fr0 /* r * s */
+ fmuls fr2,fr1,fr5 /* r * 0.5 */
+ fnmsubs fr3,fr1,fr3,fr4 /* 1 - s * r * r */
+ fmadds fr1,fr2,fr3,fr1 /* r = r + 0.5 * r * (1 - s * r * r) */
+ fmuls fr3,fr1,fr0 /* r * s */
+ fmuls fr2,fr1,fr5 /* r * 0.5 */
+ fnmsubs fr3,fr1,fr3,fr4 /* 1 - s * r * r */
+ fmadds fr1,fr2,fr3,fr1 /* r = r + 0.5 * r * (1 - s * r * r) */
+ stfsx fr1,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ lfd fr5,56(r1)
+ lfd fr4,48(r1)
+ lfd fr3,40(r1)
+ lfd fr2,32(r1)
+ bl fpdisable
+ lwz r0,36(r1)
+ mtlr r0
+ addi r1,r1,32
+ blr
diff --git a/arch/ppc/kernel/vmlinux.lds.S b/arch/ppc/kernel/vmlinux.lds.S
new file mode 100644
index 000000000000..0c0e714b84de
--- /dev/null
+++ b/arch/ppc/kernel/vmlinux.lds.S
@@ -0,0 +1,192 @@
+#include <asm-generic/vmlinux.lds.h>
+
+OUTPUT_ARCH(powerpc:common)
+jiffies = jiffies_64 + 4;
+SECTIONS
+{
+ /* Read-only sections, merged into text segment: */
+ . = + SIZEOF_HEADERS;
+ .interp : { *(.interp) }
+ .hash : { *(.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .rel.text : { *(.rel.text) }
+ .rela.text : { *(.rela.text) }
+ .rel.data : { *(.rel.data) }
+ .rela.data : { *(.rela.data) }
+ .rel.rodata : { *(.rel.rodata) }
+ .rela.rodata : { *(.rela.rodata) }
+ .rel.got : { *(.rel.got) }
+ .rela.got : { *(.rela.got) }
+ .rel.ctors : { *(.rel.ctors) }
+ .rela.ctors : { *(.rela.ctors) }
+ .rel.dtors : { *(.rel.dtors) }
+ .rela.dtors : { *(.rela.dtors) }
+ .rel.bss : { *(.rel.bss) }
+ .rela.bss : { *(.rela.bss) }
+ .rel.plt : { *(.rel.plt) }
+ .rela.plt : { *(.rela.plt) }
+/* .init : { *(.init) } =0*/
+ .plt : { *(.plt) }
+ .text :
+ {
+ *(.text)
+ SCHED_TEXT
+ LOCK_TEXT
+ *(.fixup)
+ *(.got1)
+ __got2_start = .;
+ *(.got2)
+ __got2_end = .;
+ }
+ _etext = .;
+ PROVIDE (etext = .);
+
+ RODATA
+ .fini : { *(.fini) } =0
+ .ctors : { *(.ctors) }
+ .dtors : { *(.dtors) }
+
+ .fixup : { *(.fixup) }
+
+ __ex_table : {
+ __start___ex_table = .;
+ *(__ex_table)
+ __stop___ex_table = .;
+ }
+
+ __bug_table : {
+ __start___bug_table = .;
+ *(__bug_table)
+ __stop___bug_table = .;
+ }
+
+ /* Read-write section, merged into data segment: */
+ . = ALIGN(4096);
+ .data :
+ {
+ *(.data)
+ *(.data1)
+ *(.sdata)
+ *(.sdata2)
+ *(.got.plt) *(.got)
+ *(.dynamic)
+ CONSTRUCTORS
+ }
+
+ . = ALIGN(4096);
+ __nosave_begin = .;
+ .data_nosave : { *(.data.nosave) }
+ . = ALIGN(4096);
+ __nosave_end = .;
+
+ . = ALIGN(32);
+ .data.cacheline_aligned : { *(.data.cacheline_aligned) }
+
+ _edata = .;
+ PROVIDE (edata = .);
+
+ . = ALIGN(8192);
+ .data.init_task : { *(.data.init_task) }
+
+ . = ALIGN(4096);
+ __init_begin = .;
+ .init.text : {
+ _sinittext = .;
+ *(.init.text)
+ _einittext = .;
+ }
+ .init.data : {
+ *(.init.data);
+ __vtop_table_begin = .;
+ *(.vtop_fixup);
+ __vtop_table_end = .;
+ __ptov_table_begin = .;
+ *(.ptov_fixup);
+ __ptov_table_end = .;
+ }
+ . = ALIGN(16);
+ __setup_start = .;
+ .init.setup : { *(.init.setup) }
+ __setup_end = .;
+ __initcall_start = .;
+ .initcall.init : {
+ *(.initcall1.init)
+ *(.initcall2.init)
+ *(.initcall3.init)
+ *(.initcall4.init)
+ *(.initcall5.init)
+ *(.initcall6.init)
+ *(.initcall7.init)
+ }
+ __initcall_end = .;
+
+ __con_initcall_start = .;
+ .con_initcall.init : { *(.con_initcall.init) }
+ __con_initcall_end = .;
+
+ SECURITY_INIT
+
+ __start___ftr_fixup = .;
+ __ftr_fixup : { *(__ftr_fixup) }
+ __stop___ftr_fixup = .;
+
+ . = ALIGN(32);
+ __per_cpu_start = .;
+ .data.percpu : { *(.data.percpu) }
+ __per_cpu_end = .;
+
+ . = ALIGN(4096);
+ __initramfs_start = .;
+ .init.ramfs : { *(.init.ramfs) }
+ __initramfs_end = .;
+
+ . = ALIGN(4096);
+ __init_end = .;
+
+ . = ALIGN(4096);
+ __pmac_begin = .;
+ .pmac.text : { *(.pmac.text) }
+ .pmac.data : { *(.pmac.data) }
+ . = ALIGN(4096);
+ __pmac_end = .;
+
+ . = ALIGN(4096);
+ __prep_begin = .;
+ .prep.text : { *(.prep.text) }
+ .prep.data : { *(.prep.data) }
+ . = ALIGN(4096);
+ __prep_end = .;
+
+ . = ALIGN(4096);
+ __chrp_begin = .;
+ .chrp.text : { *(.chrp.text) }
+ .chrp.data : { *(.chrp.data) }
+ . = ALIGN(4096);
+ __chrp_end = .;
+
+ . = ALIGN(4096);
+ __openfirmware_begin = .;
+ .openfirmware.text : { *(.openfirmware.text) }
+ .openfirmware.data : { *(.openfirmware.data) }
+ . = ALIGN(4096);
+ __openfirmware_end = .;
+
+ __bss_start = .;
+ .bss :
+ {
+ *(.sbss) *(.scommon)
+ *(.dynbss)
+ *(.bss)
+ *(COMMON)
+ }
+ __bss_stop = .;
+
+ _end = . ;
+ PROVIDE (end = .);
+
+ /* Sections to be discarded. */
+ /DISCARD/ : {
+ *(.exitcall.exit)
+ }
+}