Pull miscellaneous into release branch
Conflicts:
arch/ia64/kernel/mca.c
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 5865130..230a6f9 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -7,6 +7,7 @@
#define ASM_OFFSETS_C 1
#include <linux/sched.h>
+#include <linux/pid.h>
#include <linux/clocksource.h>
#include <asm-ia64/processor.h>
@@ -34,6 +35,9 @@
DEFINE(SIGFRAME_SIZE, sizeof (struct sigframe));
DEFINE(UNW_FRAME_INFO_SIZE, sizeof (struct unw_frame_info));
+ BUILD_BUG_ON(sizeof(struct upid) != 32);
+ DEFINE(IA64_UPID_SHIFT, 5);
+
BLANK();
DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
@@ -51,6 +55,9 @@
DEFINE(IA64_TASK_BLOCKED_OFFSET,offsetof (struct task_struct, blocked));
DEFINE(IA64_TASK_CLEAR_CHILD_TID_OFFSET,offsetof (struct task_struct, clear_child_tid));
DEFINE(IA64_TASK_GROUP_LEADER_OFFSET, offsetof (struct task_struct, group_leader));
+ DEFINE(IA64_TASK_TGIDLINK_OFFSET, offsetof (struct task_struct, pids[PIDTYPE_PID].pid));
+ DEFINE(IA64_PID_LEVEL_OFFSET, offsetof (struct pid, level));
+ DEFINE(IA64_PID_UPID_OFFSET, offsetof (struct pid, numbers[0]));
DEFINE(IA64_TASK_PENDING_OFFSET,offsetof (struct task_struct, pending));
DEFINE(IA64_TASK_PID_OFFSET, offsetof (struct task_struct, pid));
DEFINE(IA64_TASK_REAL_PARENT_OFFSET, offsetof (struct task_struct, real_parent));
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index fbe742a..90ef338 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -24,6 +24,7 @@
static atomic_t kdump_cpu_frozen;
atomic_t kdump_in_progress;
static int kdump_on_init = 1;
+static int kdump_on_fatal_mca = 1;
static inline Elf64_Word
*append_elf_note(Elf64_Word *buf, char *name, unsigned type, void *data,
@@ -118,6 +119,7 @@
static void
machine_kdump_on_init(void)
{
+ crash_save_vmcoreinfo();
local_irq_disable();
kexec_disable_iosapic();
machine_kexec(ia64_kimage);
@@ -148,7 +150,7 @@
struct ia64_mca_notify_die *nd;
struct die_args *args = data;
- if (!kdump_on_init)
+ if (!kdump_on_init && !kdump_on_fatal_mca)
return NOTIFY_DONE;
if (!ia64_kimage) {
@@ -173,32 +175,38 @@
return NOTIFY_DONE;
switch (val) {
- case DIE_INIT_MONARCH_PROCESS:
+ case DIE_INIT_MONARCH_PROCESS:
+ if (kdump_on_init) {
atomic_set(&kdump_in_progress, 1);
*(nd->monarch_cpu) = -1;
- break;
- case DIE_INIT_MONARCH_LEAVE:
+ }
+ break;
+ case DIE_INIT_MONARCH_LEAVE:
+ if (kdump_on_init)
machine_kdump_on_init();
- break;
- case DIE_INIT_SLAVE_LEAVE:
- if (atomic_read(&kdump_in_progress))
- unw_init_running(kdump_cpu_freeze, NULL);
- break;
- case DIE_MCA_RENDZVOUS_LEAVE:
- if (atomic_read(&kdump_in_progress))
- unw_init_running(kdump_cpu_freeze, NULL);
- break;
- case DIE_MCA_MONARCH_LEAVE:
- /* die_register->signr indicate if MCA is recoverable */
- if (!args->signr)
- machine_kdump_on_init();
- break;
+ break;
+ case DIE_INIT_SLAVE_LEAVE:
+ if (atomic_read(&kdump_in_progress))
+ unw_init_running(kdump_cpu_freeze, NULL);
+ break;
+ case DIE_MCA_RENDZVOUS_LEAVE:
+ if (atomic_read(&kdump_in_progress))
+ unw_init_running(kdump_cpu_freeze, NULL);
+ break;
+ case DIE_MCA_MONARCH_LEAVE:
+ /* die_register->signr indicate if MCA is recoverable */
+ if (kdump_on_fatal_mca && !args->signr) {
+ atomic_set(&kdump_in_progress, 1);
+ *(nd->monarch_cpu) = -1;
+ machine_kdump_on_init();
+ }
+ break;
}
return NOTIFY_DONE;
}
#ifdef CONFIG_SYSCTL
-static ctl_table kdump_on_init_table[] = {
+static ctl_table kdump_ctl_table[] = {
{
.ctl_name = CTL_UNNUMBERED,
.procname = "kdump_on_init",
@@ -207,6 +215,14 @@
.mode = 0644,
.proc_handler = &proc_dointvec,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "kdump_on_fatal_mca",
+ .data = &kdump_on_fatal_mca,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
{ .ctl_name = 0 }
};
@@ -215,7 +231,7 @@
.ctl_name = CTL_KERN,
.procname = "kernel",
.mode = 0555,
- .child = kdump_on_init_table,
+ .child = kdump_ctl_table,
},
{ .ctl_name = 0 }
};
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 357b7e2..c1625c7 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -61,13 +61,29 @@
.prologue
.altrp b6
.body
+ add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16
+ ;;
+ ld8 r17=[r17] // r17 = current->group_leader
add r9=TI_FLAGS+IA64_TASK_SIZE,r16
;;
ld4 r9=[r9]
- add r8=IA64_TASK_TGID_OFFSET,r16
+ add r17=IA64_TASK_TGIDLINK_OFFSET,r17
;;
and r9=TIF_ALLWORK_MASK,r9
- ld4 r8=[r8] // r8 = current->tgid
+ ld8 r17=[r17] // r17 = current->group_leader->pids[PIDTYPE_PID].pid
+ ;;
+ add r8=IA64_PID_LEVEL_OFFSET,r17
+ ;;
+ ld4 r8=[r8] // r8 = pid->level
+ add r17=IA64_PID_UPID_OFFSET,r17 // r17 = &pid->numbers[0]
+ ;;
+ shl r8=r8,IA64_UPID_SHIFT
+ ;;
+ add r17=r17,r8 // r17 = &pid->numbers[pid->level]
+ ;;
+ ld4 r8=[r17] // r8 = pid->numbers[pid->level].nr
+ ;;
+ mov r17=0
;;
cmp.ne p8,p0=0,r9
(p8) br.spnt.many fsys_fallback_syscall
@@ -126,15 +142,25 @@
.altrp b6
.body
add r9=TI_FLAGS+IA64_TASK_SIZE,r16
+ add r17=IA64_TASK_TGIDLINK_OFFSET,r16
;;
ld4 r9=[r9]
tnat.z p6,p7=r32 // check argument register for being NaT
+ ld8 r17=[r17] // r17 = current->pids[PIDTYPE_PID].pid
;;
and r9=TIF_ALLWORK_MASK,r9
- add r8=IA64_TASK_PID_OFFSET,r16
+ add r8=IA64_PID_LEVEL_OFFSET,r17
add r18=IA64_TASK_CLEAR_CHILD_TID_OFFSET,r16
;;
- ld4 r8=[r8]
+ ld4 r8=[r8] // r8 = pid->level
+ add r17=IA64_PID_UPID_OFFSET,r17 // r17 = &pid->numbers[0]
+ ;;
+ shl r8=r8,IA64_UPID_SHIFT
+ ;;
+ add r17=r17,r8 // r17 = &pid->numbers[pid->level]
+ ;;
+ ld4 r8=[r17] // r8 = pid->numbers[pid->level].nr
+ ;;
cmp.ne p8,p0=0,r9
mov r17=-1
;;
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index d8be23f..5538471 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -472,7 +472,7 @@
static unsigned char count;
static long last_time;
- if (jiffies - last_time > 5*HZ)
+ if (time_after(jiffies, last_time + 5 * HZ))
count = 0;
if (++count < 5) {
last_time = jiffies;
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 8d9a446..233434f 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -78,6 +78,20 @@
{ u, u, u }, /* 1F */
};
+/* Insert a long branch code */
+static void __kprobes set_brl_inst(void *from, void *to)
+{
+ s64 rel = ((s64) to - (s64) from) >> 4;
+ bundle_t *brl;
+ brl = (bundle_t *) ((u64) from & ~0xf);
+ brl->quad0.template = 0x05; /* [MLX](stop) */
+ brl->quad0.slot0 = NOP_M_INST; /* nop.m 0x0 */
+ brl->quad0.slot1_p0 = ((rel >> 20) & 0x7fffffffff) << 2;
+ brl->quad1.slot1_p1 = (((rel >> 20) & 0x7fffffffff) << 2) >> (64 - 46);
+ /* brl.cond.sptk.many.clr rel<<4 (qp=0) */
+ brl->quad1.slot2 = BRL_INST(rel >> 59, rel & 0xfffff);
+}
+
/*
* In this function we check to see if the instruction
* is IP relative instruction and update the kprobe
@@ -496,6 +510,77 @@
regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip;
}
+/* Check the instruction in the slot is break */
+static int __kprobes __is_ia64_break_inst(bundle_t *bundle, uint slot)
+{
+ unsigned int major_opcode;
+ unsigned int template = bundle->quad0.template;
+ unsigned long kprobe_inst;
+
+ /* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */
+ if (slot == 1 && bundle_encoding[template][1] == L)
+ slot++;
+
+ /* Get Kprobe probe instruction at given slot*/
+ get_kprobe_inst(bundle, slot, &kprobe_inst, &major_opcode);
+
+ /* For break instruction,
+ * Bits 37:40 Major opcode to be zero
+ * Bits 27:32 X6 to be zero
+ * Bits 32:35 X3 to be zero
+ */
+ if (major_opcode || ((kprobe_inst >> 27) & 0x1FF)) {
+ /* Not a break instruction */
+ return 0;
+ }
+
+ /* Is a break instruction */
+ return 1;
+}
+
+/*
+ * In this function, we check whether the target bundle modifies IP or
+ * it triggers an exception. If so, it cannot be boostable.
+ */
+static int __kprobes can_boost(bundle_t *bundle, uint slot,
+ unsigned long bundle_addr)
+{
+ unsigned int template = bundle->quad0.template;
+
+ do {
+ if (search_exception_tables(bundle_addr + slot) ||
+ __is_ia64_break_inst(bundle, slot))
+ return 0; /* exception may occur in this bundle*/
+ } while ((++slot) < 3);
+ template &= 0x1e;
+ if (template >= 0x10 /* including B unit */ ||
+ template == 0x04 /* including X unit */ ||
+ template == 0x06) /* undefined */
+ return 0;
+
+ return 1;
+}
+
+/* Prepare long jump bundle and disables other boosters if need */
+static void __kprobes prepare_booster(struct kprobe *p)
+{
+ unsigned long addr = (unsigned long)p->addr & ~0xFULL;
+ unsigned int slot = (unsigned long)p->addr & 0xf;
+ struct kprobe *other_kp;
+
+ if (can_boost(&p->ainsn.insn[0].bundle, slot, addr)) {
+ set_brl_inst(&p->ainsn.insn[1].bundle, (bundle_t *)addr + 1);
+ p->ainsn.inst_flag |= INST_FLAG_BOOSTABLE;
+ }
+
+ /* disables boosters in previous slots */
+ for (; addr < (unsigned long)p->addr; addr++) {
+ other_kp = get_kprobe((void *)addr);
+ if (other_kp)
+ other_kp->ainsn.inst_flag &= ~INST_FLAG_BOOSTABLE;
+ }
+}
+
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
unsigned long addr = (unsigned long) p->addr;
@@ -530,6 +615,8 @@
prepare_break_inst(template, slot, major_opcode, kprobe_inst, p, qp);
+ prepare_booster(p);
+
return 0;
}
@@ -543,7 +630,9 @@
src = &p->opcode.bundle;
flush_icache_range((unsigned long)p->ainsn.insn,
- (unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t));
+ (unsigned long)p->ainsn.insn +
+ sizeof(kprobe_opcode_t) * MAX_INSN_SIZE);
+
switch (p->ainsn.slot) {
case 0:
dest->quad0.slot0 = src->quad0.slot0;
@@ -584,13 +673,13 @@
void __kprobes arch_remove_kprobe(struct kprobe *p)
{
mutex_lock(&kprobe_mutex);
- free_insn_slot(p->ainsn.insn, 0);
+ free_insn_slot(p->ainsn.insn, p->ainsn.inst_flag & INST_FLAG_BOOSTABLE);
mutex_unlock(&kprobe_mutex);
}
/*
* We are resuming execution after a single step fault, so the pt_regs
* structure reflects the register state after we executed the instruction
- * located in the kprobe (p->ainsn.insn.bundle). We still need to adjust
+ * located in the kprobe (p->ainsn.insn->bundle). We still need to adjust
* the ip to point back to the original stack address. To set the IP address
* to original stack address, handle the case where we need to fixup the
* relative IP address and/or fixup branch register.
@@ -607,7 +696,7 @@
if (slot == 1 && bundle_encoding[template][1] == L)
slot = 2;
- if (p->ainsn.inst_flag) {
+ if (p->ainsn.inst_flag & ~INST_FLAG_BOOSTABLE) {
if (p->ainsn.inst_flag & INST_FLAG_FIX_RELATIVE_IP_ADDR) {
/* Fix relative IP address */
@@ -686,33 +775,12 @@
static int __kprobes is_ia64_break_inst(struct pt_regs *regs)
{
unsigned int slot = ia64_psr(regs)->ri;
- unsigned int template, major_opcode;
- unsigned long kprobe_inst;
unsigned long *kprobe_addr = (unsigned long *)regs->cr_iip;
bundle_t bundle;
memcpy(&bundle, kprobe_addr, sizeof(bundle_t));
- template = bundle.quad0.template;
- /* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */
- if (slot == 1 && bundle_encoding[template][1] == L)
- slot++;
-
- /* Get Kprobe probe instruction at given slot*/
- get_kprobe_inst(&bundle, slot, &kprobe_inst, &major_opcode);
-
- /* For break instruction,
- * Bits 37:40 Major opcode to be zero
- * Bits 27:32 X6 to be zero
- * Bits 32:35 X3 to be zero
- */
- if (major_opcode || ((kprobe_inst >> 27) & 0x1FF) ) {
- /* Not a break instruction */
- return 0;
- }
-
- /* Is a break instruction */
- return 1;
+ return __is_ia64_break_inst(&bundle, slot);
}
static int __kprobes pre_kprobes_handler(struct die_args *args)
@@ -802,6 +870,19 @@
return 1;
ss_probe:
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PM)
+ if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
+ /* Boost up -- we can execute copied instructions directly */
+ ia64_psr(regs)->ri = p->ainsn.slot;
+ regs->cr_iip = (unsigned long)&p->ainsn.insn->bundle & ~0xFULL;
+ /* turn single stepping off */
+ ia64_psr(regs)->ss = 0;
+
+ reset_current_kprobe();
+ preempt_enable_no_resched();
+ return 1;
+ }
+#endif
prepare_ss(p, regs);
kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 607006a..e51bced 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -69,6 +69,7 @@
* 2007-04-27 Russ Anderson <rja@sgi.com>
* Support multiple cpus going through OS_MCA in the same event.
*/
+#include <linux/jiffies.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/sched.h>
@@ -295,7 +296,8 @@
if (mlogbuf_finished)
return;
- if (mlogbuf_timestamp && (mlogbuf_timestamp + 30*HZ > jiffies)) {
+ if (mlogbuf_timestamp &&
+ time_before(jiffies, mlogbuf_timestamp + 30 * HZ)) {
printk(KERN_ERR "INIT: mlogbuf_dump is interrupted by INIT "
" and the system seems to be messed up.\n");
ia64_mlogbuf_finish(0);
@@ -1311,20 +1313,17 @@
} else {
/* Dump buffered message to console */
ia64_mlogbuf_finish(1);
-#ifdef CONFIG_KEXEC
- atomic_set(&kdump_in_progress, 1);
- monarch_cpu = -1;
-#endif
}
+
if (__get_cpu_var(ia64_mca_tr_reload)) {
mca_insert_tr(0x1); /*Reload dynamic itrs*/
mca_insert_tr(0x2); /*Reload dynamic itrs*/
}
+
if (notify_die(DIE_MCA_MONARCH_LEAVE, "MCA", regs, (long)&nd, 0, recover)
== NOTIFY_STOP)
ia64_mca_spin(__func__);
-
if (atomic_dec_return(&mca_count) > 0) {
int i;
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index a2aabfd..d1d24f4 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -4204,10 +4204,10 @@
do_each_thread (g, t) {
if (t->thread.pfm_context == ctx) {
ret = 0;
- break;
+ goto out;
}
} while_each_thread (g, t);
-
+out:
read_unlock(&tasklist_lock);
DPRINT(("pfm_check_task_exist: ret=%d ctx=%p\n", ret, ctx));
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index b86a072..5015ca1 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -177,6 +177,29 @@
return 0;
}
+/*
+ * Similar to "filter_rsvd_memory()", but the reserved memory ranges
+ * are not filtered out.
+ */
+int __init
+filter_memory(unsigned long start, unsigned long end, void *arg)
+{
+ void (*func)(unsigned long, unsigned long, int);
+
+#if IGNORE_PFN0
+ if (start == PAGE_OFFSET) {
+ printk(KERN_WARNING "warning: skipping physical page 0\n");
+ start += PAGE_SIZE;
+ if (start >= end)
+ return 0;
+ }
+#endif
+ func = arg;
+ if (start < end)
+ call_pernode_memory(__pa(start), end - start, func);
+ return 0;
+}
+
static void __init
sort_regions (struct rsvd_region *rsvd_region, int max)
{
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 32ee597..16483be 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -400,9 +400,9 @@
/* Setup the per cpu irq handling data structures */
__setup_vector_irq(cpuid);
cpu_set(cpuid, cpu_online_map);
- unlock_ipi_calllock();
per_cpu(cpu_state, cpuid) = CPU_ONLINE;
spin_unlock(&vector_lock);
+ unlock_ipi_calllock();
smp_setup_percpu_timer();
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 6903361..ff0e7c1 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -13,6 +13,7 @@
* 2001/08/13 Correct size of extended floats (float_fsz) from 16 to 10 bytes.
* 2001/01/17 Add support emulation of unaligned kernel accesses.
*/
+#include <linux/jiffies.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/tty.h>
@@ -1290,7 +1291,7 @@
{
static unsigned long count, last_time;
- if (jiffies - last_time > 5*HZ)
+ if (time_after(jiffies, last_time + 5 * HZ))
count = 0;
if (count < 5) {
last_time = jiffies;