aboutsummaryrefslogtreecommitdiff
path: root/arch/ia64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/ia64')
-rw-r--r--arch/ia64/Kconfig18
-rw-r--r--arch/ia64/Kconfig.debug11
-rw-r--r--arch/ia64/hp/sim/simserial.c6
-rw-r--r--arch/ia64/ia32/ia32_ioctl.c4
-rw-r--r--arch/ia64/kernel/kprobes.c144
-rw-r--r--arch/ia64/kernel/mca.c120
-rw-r--r--arch/ia64/kernel/mca_drv.c20
-rw-r--r--arch/ia64/kernel/perfmon.c2
-rw-r--r--arch/ia64/kernel/process.c40
-rw-r--r--arch/ia64/kernel/setup.c7
-rw-r--r--arch/ia64/kernel/signal.c11
-rw-r--r--arch/ia64/kernel/smpboot.c1
-rw-r--r--arch/ia64/kernel/traps.c44
-rw-r--r--arch/ia64/lib/Makefile2
-rw-r--r--arch/ia64/lib/swiotlb.c759
-rw-r--r--arch/ia64/mm/discontig.c19
-rw-r--r--arch/ia64/oprofile/Kconfig6
-rw-r--r--arch/ia64/sn/pci/pcibr/pcibr_provider.c4
-rw-r--r--arch/ia64/sn/pci/pcibr/pcibr_reg.c2
19 files changed, 283 insertions, 937 deletions
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1642375fb14..d4de8a4814b 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -26,6 +26,10 @@ config MMU
bool
default y
+config SWIOTLB
+ bool
+ default y
+
config RWSEM_XCHGADD_ALGORITHM
bool
default y
@@ -187,6 +191,7 @@ config IOSAPIC
config IA64_SGI_SN_XP
tristate "Support communication between SGI SSIs"
+ depends on IA64_GENERIC || IA64_SGI_SN2
select IA64_UNCACHED_ALLOCATOR
help
An SGI machine can be divided into multiple Single System
@@ -422,8 +427,21 @@ config GENERIC_PENDING_IRQ
source "arch/ia64/hp/sim/Kconfig"
+menu "Instrumentation Support"
+ depends on EXPERIMENTAL
+
source "arch/ia64/oprofile/Kconfig"
+config KPROBES
+ bool "Kprobes (EXPERIMENTAL)"
+ help
+ Kprobes allows you to trap at almost any kernel address and
+ execute a callback function. register_kprobe() establishes
+ a probepoint and specifies the callback. Kprobes is useful
+ for kernel debugging, non-intrusive instrumentation and testing.
+ If in doubt, say "N".
+endmenu
+
source "arch/ia64/Kconfig.debug"
source "security/Kconfig"
diff --git a/arch/ia64/Kconfig.debug b/arch/ia64/Kconfig.debug
index fda67ac993d..de9d507ba0f 100644
--- a/arch/ia64/Kconfig.debug
+++ b/arch/ia64/Kconfig.debug
@@ -2,17 +2,6 @@ menu "Kernel hacking"
source "lib/Kconfig.debug"
-config KPROBES
- bool "Kprobes"
- depends on DEBUG_KERNEL
- help
- Kprobes allows you to trap at almost any kernel address and
- execute a callback function. register_kprobe() establishes
- a probepoint and specifies the callback. Kprobes is useful
- for kernel debugging, non-intrusive instrumentation and testing.
- If in doubt, say "N".
-
-
choice
prompt "Physical memory granularity"
default IA64_GRANULE_64MB
diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c
index b42ec37be51..19ee635eeb7 100644
--- a/arch/ia64/hp/sim/simserial.c
+++ b/arch/ia64/hp/sim/simserial.c
@@ -642,10 +642,8 @@ static void rs_close(struct tty_struct *tty, struct file * filp)
info->event = 0;
info->tty = 0;
if (info->blocked_open) {
- if (info->close_delay) {
- current->state = TASK_INTERRUPTIBLE;
- schedule_timeout(info->close_delay);
- }
+ if (info->close_delay)
+ schedule_timeout_interruptible(info->close_delay);
wake_up_interruptible(&info->open_wait);
}
info->flags &= ~(ASYNC_NORMAL_ACTIVE|ASYNC_CLOSING);
diff --git a/arch/ia64/ia32/ia32_ioctl.c b/arch/ia64/ia32/ia32_ioctl.c
index 164b211f417..88739394f6d 100644
--- a/arch/ia64/ia32/ia32_ioctl.c
+++ b/arch/ia64/ia32/ia32_ioctl.c
@@ -29,10 +29,8 @@
#define CODE
#include "compat_ioctl.c"
-typedef int (* ioctl32_handler_t)(unsigned int, unsigned int, unsigned long, struct file *);
-
#define COMPATIBLE_IOCTL(cmd) HANDLE_IOCTL((cmd),sys_ioctl)
-#define HANDLE_IOCTL(cmd,handler) { (cmd), (ioctl32_handler_t)(handler), NULL },
+#define HANDLE_IOCTL(cmd,handler) { (cmd), (ioctl_trans_handler_t)(handler), NULL },
#define IOCTL_TABLE_START \
struct ioctl_trans ioctl_start[] = {
#define IOCTL_TABLE_END \
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 471086b808a..801eeaeaf3d 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -26,7 +26,6 @@
#include <linux/config.h>
#include <linux/kprobes.h>
#include <linux/ptrace.h>
-#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/preempt.h>
@@ -38,13 +37,8 @@
extern void jprobe_inst_return(void);
-/* kprobe_status settings */
-#define KPROBE_HIT_ACTIVE 0x00000001
-#define KPROBE_HIT_SS 0x00000002
-
-static struct kprobe *current_kprobe, *kprobe_prev;
-static unsigned long kprobe_status, kprobe_status_prev;
-static struct pt_regs jprobe_saved_regs;
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
enum instruction_type {A, I, M, F, B, L, X, u};
static enum instruction_type bundle_encoding[32][3] = {
@@ -313,21 +307,22 @@ static int __kprobes valid_kprobe_addr(int template, int slot,
return 0;
}
-static inline void save_previous_kprobe(void)
+static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
- kprobe_prev = current_kprobe;
- kprobe_status_prev = kprobe_status;
+ kcb->prev_kprobe.kp = kprobe_running();
+ kcb->prev_kprobe.status = kcb->kprobe_status;
}
-static inline void restore_previous_kprobe(void)
+static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
- current_kprobe = kprobe_prev;
- kprobe_status = kprobe_status_prev;
+ __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+ kcb->kprobe_status = kcb->prev_kprobe.status;
}
-static inline void set_current_kprobe(struct kprobe *p)
+static inline void set_current_kprobe(struct kprobe *p,
+ struct kprobe_ctlblk *kcb)
{
- current_kprobe = p;
+ __get_cpu_var(current_kprobe) = p;
}
static void kretprobe_trampoline(void)
@@ -347,11 +342,12 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
struct kretprobe_instance *ri = NULL;
struct hlist_head *head;
struct hlist_node *node, *tmp;
- unsigned long orig_ret_address = 0;
+ unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address =
((struct fnptr *)kretprobe_trampoline)->ip;
- head = kretprobe_inst_table_head(current);
+ spin_lock_irqsave(&kretprobe_lock, flags);
+ head = kretprobe_inst_table_head(current);
/*
* It is possible to have multiple instances associated with a given
@@ -367,9 +363,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
* kretprobe_trampoline
*/
hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
- if (ri->task != current)
+ if (ri->task != current)
/* another task is sharing our hash bucket */
- continue;
+ continue;
if (ri->rp && ri->rp->handler)
ri->rp->handler(ri, regs);
@@ -389,17 +385,19 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
regs->cr_iip = orig_ret_address;
- unlock_kprobes();
+ reset_current_kprobe();
+ spin_unlock_irqrestore(&kretprobe_lock, flags);
preempt_enable_no_resched();
- /*
- * By returning a non-zero value, we are telling
- * kprobe_handler() that we have handled unlocking
- * and re-enabling preemption.
- */
- return 1;
+ /*
+ * By returning a non-zero value, we are telling
+ * kprobe_handler() that we don't want the post_handler
+ * to run (and have re-enabled preemption)
+ */
+ return 1;
}
+/* Called with kretprobe_lock held */
void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
struct pt_regs *regs)
{
@@ -606,17 +604,22 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
int ret = 0;
struct pt_regs *regs = args->regs;
kprobe_opcode_t *addr = (kprobe_opcode_t *)instruction_pointer(regs);
+ struct kprobe_ctlblk *kcb;
+ /*
+ * We don't want to be preempted for the entire
+ * duration of kprobe processing
+ */
preempt_disable();
+ kcb = get_kprobe_ctlblk();
/* Handle recursion cases */
if (kprobe_running()) {
p = get_kprobe(addr);
if (p) {
- if ( (kprobe_status == KPROBE_HIT_SS) &&
+ if ((kcb->kprobe_status == KPROBE_HIT_SS) &&
(p->ainsn.inst_flag == INST_FLAG_BREAK_INST)) {
ia64_psr(regs)->ss = 0;
- unlock_kprobes();
goto no_kprobe;
}
/* We have reentered the pre_kprobe_handler(), since
@@ -625,17 +628,17 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
* just single step on the instruction of the new probe
* without calling any user handlers.
*/
- save_previous_kprobe();
- set_current_kprobe(p);
+ save_previous_kprobe(kcb);
+ set_current_kprobe(p, kcb);
p->nmissed++;
prepare_ss(p, regs);
- kprobe_status = KPROBE_REENTER;
+ kcb->kprobe_status = KPROBE_REENTER;
return 1;
} else if (args->err == __IA64_BREAK_JPROBE) {
/*
* jprobe instrumented function just completed
*/
- p = current_kprobe;
+ p = __get_cpu_var(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
goto ss_probe;
}
@@ -645,10 +648,8 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
}
}
- lock_kprobes();
p = get_kprobe(addr);
if (!p) {
- unlock_kprobes();
if (!is_ia64_break_inst(regs)) {
/*
* The breakpoint instruction was removed right
@@ -665,8 +666,8 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
goto no_kprobe;
}
- kprobe_status = KPROBE_HIT_ACTIVE;
- set_current_kprobe(p);
+ set_current_kprobe(p, kcb);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (p->pre_handler && p->pre_handler(p, regs))
/*
@@ -678,7 +679,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
ss_probe:
prepare_ss(p, regs);
- kprobe_status = KPROBE_HIT_SS;
+ kcb->kprobe_status = KPROBE_HIT_SS;
return 1;
no_kprobe:
@@ -688,23 +689,25 @@ no_kprobe:
static int __kprobes post_kprobes_handler(struct pt_regs *regs)
{
- if (!kprobe_running())
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ if (!cur)
return 0;
- if ((kprobe_status != KPROBE_REENTER) && current_kprobe->post_handler) {
- kprobe_status = KPROBE_HIT_SSDONE;
- current_kprobe->post_handler(current_kprobe, regs, 0);
+ if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ cur->post_handler(cur, regs, 0);
}
- resume_execution(current_kprobe, regs);
+ resume_execution(cur, regs);
/*Restore back the original saved kprobes variables and continue. */
- if (kprobe_status == KPROBE_REENTER) {
- restore_previous_kprobe();
+ if (kcb->kprobe_status == KPROBE_REENTER) {
+ restore_previous_kprobe(kcb);
goto out;
}
-
- unlock_kprobes();
+ reset_current_kprobe();
out:
preempt_enable_no_resched();
@@ -713,16 +716,15 @@ out:
static int __kprobes kprobes_fault_handler(struct pt_regs *regs, int trapnr)
{
- if (!kprobe_running())
- return 0;
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- if (current_kprobe->fault_handler &&
- current_kprobe->fault_handler(current_kprobe, regs, trapnr))
+ if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
- if (kprobe_status & KPROBE_HIT_SS) {
- resume_execution(current_kprobe, regs);
- unlock_kprobes();
+ if (kcb->kprobe_status & KPROBE_HIT_SS) {
+ resume_execution(cur, regs);
+ reset_current_kprobe();
preempt_enable_no_resched();
}
@@ -733,31 +735,42 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct die_args *args = (struct die_args *)data;
+ int ret = NOTIFY_DONE;
+
switch(val) {
case DIE_BREAK:
- if (pre_kprobes_handler(args))
- return NOTIFY_STOP;
+ /* err is break number from ia64_bad_break() */
+ if (args->err == 0x80200 || args->err == 0x80300)
+ if (pre_kprobes_handler(args))
+ ret = NOTIFY_STOP;
break;
- case DIE_SS:
- if (post_kprobes_handler(args->regs))
- return NOTIFY_STOP;
+ case DIE_FAULT:
+ /* err is vector number from ia64_fault() */
+ if (args->err == 36)
+ if (post_kprobes_handler(args->regs))
+ ret = NOTIFY_STOP;
break;
case DIE_PAGE_FAULT:
- if (kprobes_fault_handler(args->regs, args->trapnr))
- return NOTIFY_STOP;
+ /* kprobe_running() needs smp_processor_id() */
+ preempt_disable();
+ if (kprobe_running() &&
+ kprobes_fault_handler(args->regs, args->trapnr))
+ ret = NOTIFY_STOP;
+ preempt_enable();
default:
break;
}
- return NOTIFY_DONE;
+ return ret;
}
int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
unsigned long addr = ((struct fnptr *)(jp->entry))->ip;
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
/* save architectural state */
- jprobe_saved_regs = *regs;
+ kcb->jprobe_saved_regs = *regs;
/* after rfi, execute the jprobe instrumented function */
regs->cr_iip = addr & ~0xFULL;
@@ -775,7 +788,10 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
{
- *regs = jprobe_saved_regs;
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ *regs = kcb->jprobe_saved_regs;
+ preempt_enable_no_resched();
return 1;
}
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 52c47da1724..355af15287c 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -51,6 +51,9 @@
*
* 2005-08-12 Keith Owens <kaos@sgi.com>
* Convert MCA/INIT handlers to use per event stacks and SAL/OS state.
+ *
+ * 2005-10-07 Keith Owens <kaos@sgi.com>
+ * Add notify_die() hooks.
*/
#include <linux/config.h>
#include <linux/types.h>
@@ -58,7 +61,6 @@
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
-#include <linux/kallsyms.h>
#include <linux/smp_lock.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
@@ -69,6 +71,7 @@
#include <linux/workqueue.h>
#include <asm/delay.h>
+#include <asm/kdebug.h>
#include <asm/machvec.h>
#include <asm/meminit.h>
#include <asm/page.h>
@@ -132,6 +135,14 @@ extern void salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe);
static int mca_init;
+
+static void inline
+ia64_mca_spin(const char *func)
+{
+ printk(KERN_EMERG "%s: spinning here, not returning to SAL\n", func);
+ while (1)
+ cpu_relax();
+}
/*
* IA64_MCA log support
*/
@@ -526,13 +537,16 @@ ia64_mca_wakeup_all(void)
* Outputs : None
*/
static irqreturn_t
-ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *ptregs)
+ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *regs)
{
unsigned long flags;
int cpu = smp_processor_id();
/* Mask all interrupts */
local_irq_save(flags);
+ if (notify_die(DIE_MCA_RENDZVOUS_ENTER, "MCA", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_DONE;
/* Register with the SAL monarch that the slave has
@@ -540,10 +554,18 @@ ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *ptregs)
*/
ia64_sal_mc_rendez();
+ if (notify_die(DIE_MCA_RENDZVOUS_PROCESS, "MCA", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
+
/* Wait for the monarch cpu to exit. */
while (monarch_cpu != -1)
cpu_relax(); /* spin until monarch leaves */
+ if (notify_die(DIE_MCA_RENDZVOUS_LEAVE, "MCA", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
+
/* Enable all interrupts */
local_irq_restore(flags);
return IRQ_HANDLED;
@@ -933,6 +955,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
oops_in_progress = 1; /* FIXME: make printk NMI/MCA/INIT safe */
previous_current = ia64_mca_modify_original_stack(regs, sw, sos, "MCA");
monarch_cpu = cpu;
+ if (notify_die(DIE_MCA_MONARCH_ENTER, "MCA", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
ia64_wait_for_slaves(cpu);
/* Wakeup all the processors which are spinning in the rendezvous loop.
@@ -942,6 +967,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
* spinning in SAL does not work.
*/
ia64_mca_wakeup_all();
+ if (notify_die(DIE_MCA_MONARCH_PROCESS, "MCA", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
/* Get the MCA error record and log it */
ia64_mca_log_sal_error_record(SAL_INFO_TYPE_MCA);
@@ -960,6 +988,9 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
ia64_sal_clear_state_info(SAL_INFO_TYPE_MCA);
sos->os_status = IA64_MCA_CORRECTED;
}
+ if (notify_die(DIE_MCA_MONARCH_LEAVE, "MCA", regs, 0, 0, recover)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
set_curr_task(cpu, previous_current);
monarch_cpu = -1;
@@ -1188,6 +1219,37 @@ ia64_mca_cpe_poll (unsigned long dummy)
#endif /* CONFIG_ACPI */
+static int
+default_monarch_init_process(struct notifier_block *self, unsigned long val, void *data)
+{
+ int c;
+ struct task_struct *g, *t;
+ if (val != DIE_INIT_MONARCH_PROCESS)
+ return NOTIFY_DONE;
+ printk(KERN_ERR "Processes interrupted by INIT -");
+ for_each_online_cpu(c) {
+ struct ia64_sal_os_state *s;
+ t = __va(__per_cpu_mca[c] + IA64_MCA_CPU_INIT_STACK_OFFSET);
+ s = (struct ia64_sal_os_state *)((char *)t + MCA_SOS_OFFSET);
+ g = s->prev_task;
+ if (g) {
+ if (g->pid)
+ printk(" %d", g->pid);
+ else
+ printk(" %d (cpu %d task 0x%p)", g->pid, task_cpu(g), g);
+ }
+ }
+ printk("\n\n");
+ if (read_trylock(&tasklist_lock)) {
+ do_each_thread (g, t) {
+ printk("\nBacktrace of pid %d (%s)\n", t->pid, t->comm);
+ show_stack(t, NULL);
+ } while_each_thread (g, t);
+ read_unlock(&tasklist_lock);
+ }
+ return NOTIFY_DONE;
+}
+
/*
* C portion of the OS INIT handler
*
@@ -1212,8 +1274,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
static atomic_t slaves;
static atomic_t monarchs;
task_t *previous_current;
- int cpu = smp_processor_id(), c;
- struct task_struct *g, *t;
+ int cpu = smp_processor_id();
oops_in_progress = 1; /* FIXME: make printk NMI/MCA/INIT safe */
console_loglevel = 15; /* make sure printks make it to console */
@@ -1253,8 +1314,17 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_INIT;
while (monarch_cpu == -1)
cpu_relax(); /* spin until monarch enters */
+ if (notify_die(DIE_INIT_SLAVE_ENTER, "INIT", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
+ if (notify_die(DIE_INIT_SLAVE_PROCESS, "INIT", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
while (monarch_cpu != -1)
cpu_relax(); /* spin until monarch leaves */
+ if (notify_die(DIE_INIT_SLAVE_LEAVE, "INIT", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
printk("Slave on cpu %d returning to normal service.\n", cpu);
set_curr_task(cpu, previous_current);
ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
@@ -1263,6 +1333,9 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
}
monarch_cpu = cpu;
+ if (notify_die(DIE_INIT_MONARCH_ENTER, "INIT", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
/*
* Wait for a bit. On some machines (e.g., HP's zx2000 and zx6000, INIT can be
@@ -1273,27 +1346,16 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
printk("Delaying for 5 seconds...\n");
udelay(5*1000000);
ia64_wait_for_slaves(cpu);
- printk(KERN_ERR "Processes interrupted by INIT -");
- for_each_online_cpu(c) {
- struct ia64_sal_os_state *s;
- t = __va(__per_cpu_mca[c] + IA64_MCA_CPU_INIT_STACK_OFFSET);
- s = (struct ia64_sal_os_state *)((char *)t + MCA_SOS_OFFSET);
- g = s->prev_task;
- if (g) {
- if (g->pid)
- printk(" %d", g->pid);
- else
- printk(" %d (cpu %d task 0x%p)", g->pid, task_cpu(g), g);
- }
- }
- printk("\n\n");
- if (read_trylock(&tasklist_lock)) {
- do_each_thread (g, t) {
- printk("\nBacktrace of pid %d (%s)\n", t->pid, t->comm);
- show_stack(t, NULL);
- } while_each_thread (g, t);
- read_unlock(&tasklist_lock);
- }
+ /* If nobody intercepts DIE_INIT_MONARCH_PROCESS then we drop through
+ * to default_monarch_init_process() above and just print all the
+ * tasks.
+ */
+ if (notify_die(DIE_INIT_MONARCH_PROCESS, "INIT", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
+ if (notify_die(DIE_INIT_MONARCH_LEAVE, "INIT", regs, 0, 0, 0)
+ == NOTIFY_STOP)
+ ia64_mca_spin(__FUNCTION__);
printk("\nINIT dump complete. Monarch on cpu %d returning to normal service.\n", cpu);
atomic_dec(&monarchs);
set_curr_task(cpu, previous_current);
@@ -1462,6 +1524,10 @@ ia64_mca_init(void)
s64 rc;
struct ia64_sal_retval isrv;
u64 timeout = IA64_MCA_RENDEZ_TIMEOUT; /* platform specific */
+ static struct notifier_block default_init_monarch_nb = {
+ .notifier_call = default_monarch_init_process,
+ .priority = 0/* we need to notified last */
+ };
IA64_MCA_DEBUG("%s: begin\n", __FUNCTION__);
@@ -1555,6 +1621,10 @@ ia64_mca_init(void)
"(status %ld)\n", rc);
return;
}
+ if (register_die_notifier(&default_init_monarch_nb)) {
+ printk(KERN_ERR "Failed to register default monarch INIT process\n");
+ return;
+ }
IA64_MCA_DEBUG("%s: registered OS INIT handler with SAL\n", __FUNCTION__);
diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c
index f081c60ab20..3492e3211a4 100644
--- a/arch/ia64/kernel/mca_drv.c
+++ b/arch/ia64/kernel/mca_drv.c
@@ -88,7 +88,7 @@ mca_page_isolate(unsigned long paddr)
if (!ia64_phys_addr_valid(paddr))
return ISOLATE_NONE;
- if (!pfn_valid(paddr))
+ if (!pfn_valid(paddr >> PAGE_SHIFT))
return ISOLATE_NONE;
/* convert physical address to physical page number */
@@ -108,6 +108,7 @@ mca_page_isolate(unsigned long paddr)
return ISOLATE_NG;
/* add attribute 'Reserved' and register the page */
+ get_page(p);
SetPageReserved(p);
page_isolate[num_page_isolate++] = p;
@@ -546,9 +547,20 @@ recover_from_processor_error(int platform, slidx_table_t *slidx,
(pal_processor_state_info_t*)peidx_psp(peidx);
/*
- * We cannot recover errors with other than bus_check.
+ * Processor recovery status must key off of the PAL recovery
+ * status in the Processor State Parameter.
*/
- if (psp->cc || psp->rc || psp->uc)
+
+ /*
+ * The machine check is corrected.
+ */
+ if (psp->cm == 1)
+ return 1;
+
+ /*
+ * The error was not contained. Software must be reset.
+ */
+ if (psp->us || psp->ci == 0)
return 0;
/*
@@ -569,8 +581,6 @@ recover_from_processor_error(int platform, slidx_table_t *slidx,
return 0;
if (pbci->eb && pbci->bsi > 0)
return 0;
- if (psp->ci == 0)
- return 0;
/*
* This is a local MCA and estimated as recoverble external bus error.
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index f7dfc107cb7..410d4804fa6 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -4940,7 +4940,7 @@ abort_locked:
if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT;
error_args:
- if (args_k) kfree(args_k);
+ kfree(args_k);
DPRINT(("cmd=%s ret=%ld\n", PFM_CMD_NAME(cmd), ret));
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 051e050359e..e92ea64d804 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -4,6 +4,9 @@
* Copyright (C) 1998-2003 Hewlett-Packard Co
* David Mosberger-Tang <davidm@hpl.hp.com>
* 04/11/17 Ashok Raj <ashok.raj@intel.com> Added CPU Hotplug Support
+ *
+ * 2005-10-07 Keith Owens <kaos@sgi.com>
+ * Add notify_die() hooks.
*/
#define __KERNEL_SYSCALLS__ /* see <asm/unistd.h> */
#include <linux/config.h>
@@ -34,6 +37,7 @@
#include <asm/elf.h>
#include <asm/ia32.h>
#include <asm/irq.h>
+#include <asm/kdebug.h>
#include <asm/pgalloc.h>
#include <asm/processor.h>
#include <asm/sal.h>
@@ -197,11 +201,15 @@ void
default_idle (void)
{
local_irq_enable();
- while (!need_resched())
- if (can_do_pal_halt)
- safe_halt();
- else
+ while (!need_resched()) {
+ if (can_do_pal_halt) {
+ local_irq_disable();
+ if (!need_resched())
+ safe_halt();
+ local_irq_enable();
+ } else
cpu_relax();
+ }
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -263,16 +271,16 @@ void __attribute__((noreturn))
cpu_idle (void)
{
void (*mark_idle)(int) = ia64_mark_idle;
+ int cpu = smp_processor_id();
+ set_thread_flag(TIF_POLLING_NRFLAG);
/* endless idle loop with no priority at all */
while (1) {
+ if (!need_resched()) {
+ void (*idle)(void);
#ifdef CONFIG_SMP
- if (!need_resched())
min_xtp();
#endif
- while (!need_resched()) {
- void (*idle)(void);
-
if (__get_cpu_var(cpu_idle_state))
__get_cpu_var(cpu_idle_state) = 0;
@@ -284,17 +292,17 @@ cpu_idle (void)
if (!idle)
idle = default_idle;
(*idle)();
- }
-
- if (mark_idle)
- (*mark_idle)(0);
-
+ if (mark_idle)
+ (*mark_idle)(0);
#ifdef CONFIG_SMP
- normal_xtp();
+ normal_xtp();
#endif
+ }
+ preempt_enable_no_resched();
schedule();
+ preempt_disable();
check_pgt_cache();
- if (cpu_is_offline(smp_processor_id()))
+ if (cpu_is_offline(cpu))
play_dead();
}
}
@@ -804,12 +812,14 @@ cpu_halt (void)
void
machine_restart (char *restart_cmd)
{
+ (void) notify_die(DIE_MACHINE_RESTART, restart_cmd, NULL, 0, 0, 0);
(*efi.reset_system)(EFI_RESET_WARM, 0, 0, NULL);
}
void
machine_halt (void)
{
+ (void) notify_die(DIE_MACHINE_HALT, "", NULL, 0, 0, 0);
cpu_halt();
}
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index c9388a92cf4..5add0bcf87a 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -92,6 +92,13 @@ extern void efi_initialize_iomem_resources(struct resource *,
extern char _text[], _end[], _etext[];
unsigned long ia64_max_cacheline_size;
+
+int dma_get_cache_alignment(void)
+{
+ return ia64_max_cacheline_size;
+}
+EXPORT_SYMBOL(dma_get_cache_alignment);
+
unsigned long ia64_iobase; /* virtual address for I/O accesses */
EXPORT_SYMBOL(ia64_iobase);
struct io_space io_space[MAX_IO_SPACES];
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 774f34b675c..58ce07efc56 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -387,15 +387,14 @@ setup_frame (int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set,
struct sigscratch *scr)
{
extern char __kernel_sigtramp[];
- unsigned long tramp_addr, new_rbs = 0;
+ unsigned long tramp_addr, new_rbs = 0, new_sp;
struct sigframe __user *frame;
long err;
- frame = (void __user *) scr->pt.r12;
+ new_sp = scr->pt.r12;
tramp_addr = (unsigned long) __kernel_sigtramp;
- if ((ka->sa.sa_flags & SA_ONSTACK) && sas_ss_flags((unsigned long) frame) == 0) {
- frame = (void __user *) ((current->sas_ss_sp + current->sas_ss_size)
- & ~(STACK_ALIGN - 1));
+ if ((ka->sa.sa_flags & SA_ONSTACK) && sas_ss_flags(new_sp) == 0) {
+ new_sp = current->sas_ss_sp + current->sas_ss_size;
/*
* We need to check for the register stack being on the signal stack
* separately, because it's switched separately (memory stack is switched
@@ -404,7 +403,7 @@ setup_frame (int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set,
if (!rbs_on_sig_stack(scr->pt.ar_bspstore))
new_rbs = (current->sas_ss_sp + sizeof(long) - 1) & ~(sizeof(long) - 1);
}
- frame = (void __user *) frame - ((sizeof(*frame) + STACK_ALIGN - 1) & ~(STACK_ALIGN - 1));
+ frame = (void __user *) ((new_sp - sizeof(*frame)) & -STACK_ALIGN);
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return force_sigsegv_info(sig, frame);
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 400a4898712..8f44e7d2df6 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -399,6 +399,7 @@ start_secondary (void *unused)
Dprintk("start_secondary: starting CPU 0x%x\n", hard_smp_processor_id());
efi_map_pal_code();
cpu_init();
+ preempt_disable();
smp_callin();
cpu_idle();
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index f970359e7ed..fba5fdd1f96 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -30,17 +30,20 @@ fpswa_interface_t *fpswa_interface;
EXPORT_SYMBOL(fpswa_interface);
struct notifier_block *ia64die_chain;
-static DEFINE_SPINLOCK(die_notifier_lock);
-int register_die_notifier(struct notifier_block *nb)
+int
+register_die_notifier(struct notifier_block *nb)
{
- int err = 0;
- unsigned long flags;
- spin_lock_irqsave(&die_notifier_lock, flags);
- err = notifier_chain_register(&ia64die_chain, nb);
- spin_unlock_irqrestore(&die_notifier_lock, flags);
- return err;
+ return notifier_chain_register(&ia64die_chain, nb);
}
+EXPORT_SYMBOL_GPL(register_die_notifier);
+
+int
+unregister_die_notifier(struct notifier_block *nb)
+{
+ return notifier_chain_unregister(&ia64die_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_die_notifier);
void __init
trap_init (void)
@@ -105,6 +108,7 @@ die (const char *str, struct pt_regs *regs, long err)
if (++die.lock_owner_depth < 3) {
printk("%s[%d]: %s %ld [%d]\n",
current->comm, current->pid, str, err, ++die_counter);
+ (void) notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV);
show_regs(regs);
} else
printk(KERN_ERR "Recursive die() failure, output suppressed\n");
@@ -155,9 +159,8 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
switch (break_num) {
case 0: /* unknown error (used by GCC for __builtin_abort()) */
if (notify_die(DIE_BREAK, "break 0", regs, break_num, TRAP_BRKPT, SIGTRAP)
- == NOTIFY_STOP) {
+ == NOTIFY_STOP)
return;
- }
die_if_kernel("bugcheck!", regs, break_num);
sig = SIGILL; code = ILL_ILLOPC;
break;
@@ -210,15 +213,6 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
sig = SIGILL; code = __ILL_BNDMOD;
break;
- case 0x80200:
- case 0x80300:
- if (notify_die(DIE_BREAK, "kprobe", regs, break_num, TRAP_BRKPT, SIGTRAP)
- == NOTIFY_STOP) {
- return;
- }
- sig = SIGTRAP; code = TRAP_BRKPT;
- break;
-
default:
if (break_num < 0x40000 || break_num > 0x100000)
die_if_kernel("Bad break", regs, break_num);
@@ -226,6 +220,9 @@ __kprobes ia64_bad_break (unsigned long break_num, struct pt_regs *regs)
if (break_num < 0x80000) {
sig = SIGILL; code = __ILL_BREAK;
} else {
+ if (notify_die(DIE_BREAK, "bad break", regs, break_num, TRAP_BRKPT, SIGTRAP)
+ == NOTIFY_STOP)
+ return;
sig = SIGTRAP; code = TRAP_BRKPT;
}
}
@@ -578,12 +575,11 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa,
#endif
break;
case 35: siginfo.si_code = TRAP_BRANCH; ifa = 0; break;
- case 36:
- if (notify_die(DIE_SS, "ss", &regs, vector,
- vector, SIGTRAP) == NOTIFY_STOP)
- return;
- siginfo.si_code = TRAP_TRACE; ifa = 0; break;
+ case 36: siginfo.si_code = TRAP_TRACE; ifa = 0; break;
}
+ if (notify_die(DIE_FAULT, "ia64_fault", &regs, vector, siginfo.si_code, SIGTRAP)
+ == NOTIFY_STOP)
+ return;
siginfo.si_signo = SIGTRAP;
siginfo.si_errno = 0;
siginfo.si_addr = (void __user *) ifa;
diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile
index cb1af597370..ac64664a180 100644
--- a/arch/ia64/lib/Makefile
+++ b/arch/ia64/lib/Makefile
@@ -9,7 +9,7 @@ lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \
bitop.o checksum.o clear_page.o csum_partial_copy.o \
clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o \
flush.o ip_fast_csum.o do_csum.o \
- memset.o strlen.o swiotlb.o
+ memset.o strlen.o
lib-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o
lib-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o
diff --git a/arch/ia64/lib/swiotlb.c b/arch/ia64/lib/swiotlb.c
deleted file mode 100644
index 96edcc0fdcd..00000000000
--- a/arch/ia64/lib/swiotlb.c
+++ /dev/null
@@ -1,759 +0,0 @@
-/*
- * Dynamic DMA mapping support.
- *
- * This implementation is for IA-64 platforms that do not support
- * I/O TLBs (aka DMA address translation hardware).
- * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
- * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
- * Copyright (C) 2000, 2003 Hewlett-Packard Co
- * David Mosberger-Tang <davidm@hpl.hp.com>
- *
- * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API.
- * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid
- * unnecessary i-cache flushing.
- * 04/07/.. ak Better overflow handling. Assorted fixes.
- */
-
-#include <linux/cache.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ctype.h>
-
-#include <asm/io.h>
-#include <asm/pci.h>
-#include <asm/dma.h>
-
-#include <linux/init.h>
-#include <linux/bootmem.h>
-
-#define OFFSET(val,align) ((unsigned long) \
- ( (val) & ( (align) - 1)))
-
-#define SG_ENT_VIRT_ADDRESS(sg) (page_address((sg)->page) + (sg)->offset)
-#define SG_ENT_PHYS_ADDRESS(SG) virt_to_phys(SG_ENT_VIRT_ADDRESS(SG))
-
-/*
- * Maximum allowable number of contiguous slabs to map,
- * must be a power of 2. What is the appropriate value ?
- * The complexity of {map,unmap}_single is linearly dependent on this value.
- */
-#define IO_TLB_SEGSIZE 128
-
-/*
- * log of the size of each IO TLB slab. The number of slabs is command line
- * controllable.
- */
-#define IO_TLB_SHIFT 11
-
-#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
-
-/*
- * Minimum IO TLB size to bother booting with. Systems with mainly
- * 64bit capable cards will only lightly use the swiotlb. If we can't
- * allocate a contiguous 1MB, we're probably in trouble anyway.
- */
-#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
-
-int swiotlb_force;
-
-/*
- * Used to do a quick range check in swiotlb_unmap_single and
- * swiotlb_sync_single_*, to see if the memory was in fact allocated by this
- * API.
- */
-static char *io_tlb_start, *io_tlb_end;
-
-/*
- * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and
- * io_tlb_end. This is command line adjustable via setup_io_tlb_npages.
- */
-static unsigned long io_tlb_nslabs;
-
-/*
- * When the IOMMU overflows we return a fallback buffer. This sets the size.
- */
-static unsigned long io_tlb_overflow = 32*1024;
-
-void *io_tlb_overflow_buffer;
-
-/*
- * This is a free list describing the number of free entries available from
- * each index
- */
-static unsigned int *io_tlb_list;
-static unsigned int io_tlb_index;
-
-/*
- * We need to save away the original address corresponding to a mapped entry
- * for the sync operations.
- */
-static unsigned char **io_tlb_orig_addr;
-
-/*
- * Protect the above data structures in the map and unmap calls
- */
-static DEFINE_SPINLOCK(io_tlb_lock);
-
-static int __init
-setup_io_tlb_npages(char *str)
-{
- if (isdigit(*str)) {
- io_tlb_nslabs = simple_strtoul(str, &str, 0);
- /* avoid tail segment of size < IO_TLB_SEGSIZE */
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
- }
- if (*str == ',')
- ++str;
- if (!strcmp(str, "force"))
- swiotlb_force = 1;
- return 1;
-}
-__setup("swiotlb=", setup_io_tlb_npages);
-/* make io_tlb_overflow tunable too? */
-
-/*
- * Statically reserve bounce buffer space and initialize bounce buffer data
- * structures for the software IO TLB used to implement the PCI DMA API.
- */
-void
-swiotlb_init_with_default_size (size_t default_size)
-{
- unsigned long i;
-
- if (!io_tlb_nslabs) {
- io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
- }
-
- /*
- * Get IO TLB memory from the low pages
- */
- io_tlb_start = alloc_bootmem_low_pages_limit(io_tlb_nslabs *
- (1 << IO_TLB_SHIFT), 0x100000000);
- if (!io_tlb_start)
- panic("Cannot allocate SWIOTLB buffer");
- io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT);
-
- /*
- * Allocate and initialize the free list array. This array is used
- * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
- * between io_tlb_start and io_tlb_end.
- */
- io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int));
- for (i = 0; i < io_tlb_nslabs; i++)
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
- io_tlb_index = 0;
- io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *));
-
- /*
- * Get the overflow emergency buffer
- */
- io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
- printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n",
- virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end));
-}
-
-void
-swiotlb_init (void)
-{
- swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */
-}
-
-/*
- * Systems with larger DMA zones (those that don't support ISA) can
- * initialize the swiotlb later using the slab allocator if needed.
- * This should be just like above, but with some error catching.
- */
-int
-swiotlb_late_init_with_default_size (size_t default_size)
-{
- unsigned long i, req_nslabs = io_tlb_nslabs;
- unsigned int order;
-
- if (!io_tlb_nslabs) {
- io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
- io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
- }
-
- /*
- * Get IO TLB memory from the low pages
- */
- order = get_order(io_tlb_nslabs * (1 << IO_TLB_SHIFT));
- io_tlb_nslabs = SLABS_PER_PAGE << order;
-
- while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
- io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
- order);
- if (io_tlb_start)
- break;
- order--;
- }
-
- if (!io_tlb_start)
- goto cleanup1;
-
- if (order != get_order(io_tlb_nslabs * (1 << IO_TLB_SHIFT))) {
- printk(KERN_WARNING "Warning: only able to allocate %ld MB "
- "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
- io_tlb_nslabs = SLABS_PER_PAGE << order;
- }
- io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT);
- memset(io_tlb_start, 0, io_tlb_nslabs * (1 << IO_TLB_SHIFT));
-
- /*
- * Allocate and initialize the free list array. This array is used
- * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
- * between io_tlb_start and io_tlb_end.
- */
- io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
- get_order(io_tlb_nslabs * sizeof(int)));
- if (!io_tlb_list)
- goto cleanup2;
-
- for (i = 0; i < io_tlb_nslabs; i++)
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
- io_tlb_index = 0;
-
- io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL,
- get_order(io_tlb_nslabs * sizeof(char *)));
- if (!io_tlb_orig_addr)
- goto cleanup3;
-
- memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *));
-
- /*
- * Get the overflow emergency buffer
- */
- io_tlb_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
- get_order(io_tlb_overflow));
- if (!io_tlb_overflow_buffer)
- goto cleanup4;
-
- printk(KERN_INFO "Placing %ldMB software IO TLB between 0x%lx - "
- "0x%lx\n", (io_tlb_nslabs * (1 << IO_TLB_SHIFT)) >> 20,
- virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end));
-
- return 0;
-
-cleanup4:
- free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
- sizeof(char *)));
- io_tlb_orig_addr = NULL;
-cleanup3:
- free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
- sizeof(int)));
- io_tlb_list = NULL;
- io_tlb_end = NULL;
-cleanup2:
- free_pages((unsigned long)io_tlb_start, order);
- io_tlb_start = NULL;
-cleanup1:
- io_tlb_nslabs = req_nslabs;
- return -ENOMEM;
-}
-
-static inline int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr)
-{
- dma_addr_t mask = 0xffffffff;
- /* If the device has a mask, use it, otherwise default to 32 bits */
- if (hwdev && hwdev->dma_mask)
- mask = *hwdev->dma_mask;
- return (addr & ~mask) != 0;
-}
-
-/*
- * Allocates bounce buffer and returns its kernel virtual address.
- */
-static void *
-map_single(struct device *hwdev, char *buffer, size_t size, int dir)
-{
- unsigned long flags;
- char *dma_addr;
- unsigned int nslots, stride, index, wrap;
- int i;
-
- /*
- * For mappings greater than a page, we limit the stride (and
- * hence alignment) to a page size.
- */
- nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- if (size > PAGE_SIZE)
- stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
- else
- stride = 1;
-
- if (!nslots)
- BUG();
-
- /*
- * Find suitable number of IO TLB entries size that will fit this
- * request and allocate a buffer from that IO TLB pool.
- */
- spin_lock_irqsave(&io_tlb_lock, flags);
- {
- wrap = index = ALIGN(io_tlb_index, stride);
-
- if (index >= io_tlb_nslabs)
- wrap = index = 0;
-
- do {
- /*
- * If we find a slot that indicates we have 'nslots'
- * number of contiguous buffers, we allocate the
- * buffers from that slot and mark the entries as '0'
- * indicating unavailable.
- */
- if (io_tlb_list[index] >= nslots) {
- int count = 0;
-
- for (i = index; i < (int) (index + nslots); i++)
- io_tlb_list[i] = 0;
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
- dma_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
- /*
- * Update the indices to avoid searching in
- * the next round.
- */
- io_tlb_index = ((index + nslots) < io_tlb_nslabs
- ? (index + nslots) : 0);
-
- goto found;
- }
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
- } while (index != wrap);
-
- spin_unlock_irqrestore(&io_tlb_lock, flags);
- return NULL;
- }
- found:
- spin_unlock_irqrestore(&io_tlb_lock, flags);
-
- /*
- * Save away the mapping from the original address to the DMA address.
- * This is needed when we sync the memory. Then we sync the buffer if
- * needed.
- */
- io_tlb_orig_addr[index] = buffer;
- if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
- memcpy(dma_addr, buffer, size);
-
- return dma_addr;
-}
-
-/*
- * dma_addr is the kernel virtual address of the bounce buffer to unmap.
- */
-static void
-unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
-{
- unsigned long flags;
- int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
- char *buffer = io_tlb_orig_addr[index];
-
- /*
- * First, sync the memory before unmapping the entry
- */
- if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
- /*
- * bounce... copy the data back into the original buffer * and
- * delete the bounce buffer.
- */
- memcpy(buffer, dma_addr, size);
-
- /*
- * Return the buffer to the free list by setting the corresponding
- * entries to indicate the number of contigous entries available.
- * While returning the entries to the free list, we merge the entries
- * with slots below and above the pool being returned.
- */
- spin_lock_irqsave(&io_tlb_lock, flags);
- {
- count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
- io_tlb_list[index + nslots] : 0);
- /*
- * Step 1: return the slots to the free list, merging the
- * slots with superceeding slots
- */
- for (i = index + nslots - 1; i >= index; i--)
- io_tlb_list[i] = ++count;
- /*
- * Step 2: merge the returned slots with the preceding slots,
- * if available (non zero)
- */
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
- }
- spin_unlock_irqrestore(&io_tlb_lock, flags);
-}
-
-static void
-sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
-{
- int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
- char *buffer = io_tlb_orig_addr[index];
-
- /*
- * bounce... copy the data back into/from the original buffer
- * XXX How do you handle DMA_BIDIRECTIONAL here ?
- */
- if (dir == DMA_FROM_DEVICE)
- memcpy(buffer, dma_addr, size);
- else if (dir == DMA_TO_DEVICE)
- memcpy(dma_addr, buffer, size);
- else
- BUG();
-}
-
-void *
-swiotlb_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags)
-{
- unsigned long dev_addr;
- void *ret;
- int order = get_order(size);
-
- /*
- * XXX fix me: the DMA API should pass us an explicit DMA mask
- * instead, or use ZONE_DMA32 (ia64 overloads ZONE_DMA to be a ~32
- * bit range instead of a 16MB one).
- */
- flags |= GFP_DMA;
-
- ret = (void *)__get_free_pages(flags, order);
- if (ret && address_needs_mapping(hwdev, virt_to_phys(ret))) {
- /*
- * The allocated memory isn't reachable by the device.
- * Fall back on swiotlb_map_single().
- */
- free_pages((unsigned long) ret, order);
- ret = NULL;
- }
- if (!ret) {
- /*
- * We are either out of memory or the device can't DMA
- * to GFP_DMA memory; fall back on
- * swiotlb_map_single(), which will grab memory from
- * the lowest available address range.
- */
- dma_addr_t handle;
- handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE);
- if (dma_mapping_error(handle))
- return NULL;
-
- ret = phys_to_virt(handle);
- }
-
- memset(ret, 0, size);
- dev_addr = virt_to_phys(ret);
-
- /* Confirm address can be DMA'd by device */
- if (address_needs_mapping(hwdev, dev_addr)) {
- printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016lx\n",
- (unsigned long long)*hwdev->dma_mask, dev_addr);
- panic("swiotlb_alloc_coherent: allocated memory is out of "
- "range for device");
- }
- *dma_handle = dev_addr;
- return ret;
-}
-
-void
-swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
- dma_addr_t dma_handle)
-{
- if (!(vaddr >= (void *)io_tlb_start
- && vaddr < (void *)io_tlb_end))
- free_pages((unsigned long) vaddr, get_order(size));
- else
- /* DMA_TO_DEVICE to avoid memcpy in unmap_single */
- swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE);
-}
-
-static void
-swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
-{
- /*
- * Ran out of IOMMU space for this operation. This is very bad.
- * Unfortunately the drivers cannot handle this operation properly.
- * unless they check for pci_dma_mapping_error (most don't)
- * When the mapping is small enough return a static buffer to limit
- * the damage, or panic when the transfer is too big.
- */
- printk(KERN_ERR "PCI-DMA: Out of SW-IOMMU space for %lu bytes at "
- "device %s\n", size, dev ? dev->bus_id : "?");
-
- if (size > io_tlb_overflow && do_panic) {
- if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
- panic("PCI-DMA: Memory would be corrupted\n");
- if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL)
- panic("PCI-DMA: Random memory would be DMAed\n");
- }
-}
-
-/*
- * Map a single buffer of the indicated size for DMA in streaming mode. The
- * PCI address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
- */
-dma_addr_t
-swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
-{
- unsigned long dev_addr = virt_to_phys(ptr);
- void *map;
-
- if (dir == DMA_NONE)
- BUG();
- /*
- * If the pointer passed in happens to be in the device's DMA window,
- * we can safely return the device addr and not worry about bounce
- * buffering it.
- */
- if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force)
- return dev_addr;
-
- /*
- * Oh well, have to allocate and map a bounce buffer.
- */
- map = map_single(hwdev, ptr, size, dir);
- if (!map) {
- swiotlb_full(hwdev, size, dir, 1);
- map = io_tlb_overflow_buffer;
- }
-
- dev_addr = virt_to_phys(map);
-
- /*
- * Ensure that the address returned is DMA'ble
- */
- if (address_needs_mapping(hwdev, dev_addr))
- panic("map_single: bounce buffer is not DMA'ble");
-
- return dev_addr;
-}
-
-/*
- * Since DMA is i-cache coherent, any (complete) pages that were written via
- * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
- * flush them when they get mapped into an executable vm-area.
- */
-static void
-mark_clean(void *addr, size_t size)
-{
- unsigned long pg_addr, end;
-
- pg_addr = PAGE_ALIGN((unsigned long) addr);
- end = (unsigned long) addr + size;
- while (pg_addr + PAGE_SIZE <= end) {
- struct page *page = virt_to_page(pg_addr);
- set_bit(PG_arch_1, &page->flags);
- pg_addr += PAGE_SIZE;
- }
-}
-
-/*
- * Unmap a single streaming mode DMA translation. The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_single call. All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-void
-swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
- int dir)
-{
- char *dma_addr = phys_to_virt(dev_addr);
-
- if (dir == DMA_NONE)
- BUG();
- if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
- unmap_single(hwdev, dma_addr, size, dir);
- else if (dir == DMA_FROM_DEVICE)
- mark_clean(dma_addr, size);
-}
-
-/*
- * Make physical memory consistent for a single streaming mode DMA translation
- * after a transfer.
- *
- * If you perform a swiotlb_map_single() but wish to interrogate the buffer
- * using the cpu, yet do not wish to teardown the PCI dma mapping, you must
- * call this function before doing so. At the next point you give the PCI dma
- * address back to the card, you must first perform a
- * swiotlb_dma_sync_for_device, and then the device again owns the buffer
- */
-void
-swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, int dir)
-{
- char *dma_addr = phys_to_virt(dev_addr);
-
- if (dir == DMA_NONE)
- BUG();
- if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
- sync_single(hwdev, dma_addr, size, dir);
- else if (dir == DMA_FROM_DEVICE)
- mark_clean(dma_addr, size);
-}
-
-void
-swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, int dir)
-{
- char *dma_addr = phys_to_virt(dev_addr);
-
- if (dir == DMA_NONE)
- BUG();
- if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
- sync_single(hwdev, dma_addr, size, dir);
- else if (dir == DMA_FROM_DEVICE)
- mark_clean(dma_addr, size);
-}
-
-/*
- * Map a set of buffers described by scatterlist in streaming mode for DMA.
- * This is the scatter-gather version of the above swiotlb_map_single
- * interface. Here the scatter gather list elements are each tagged with the
- * appropriate dma address and length. They are obtained via
- * sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- * DMA address/length pairs than there are SG table elements.
- * (for example via virtual mapping capabilities)
- * The routine returns the number of addr/length pairs actually
- * used, at most nents.
- *
- * Device ownership issues as mentioned above for swiotlb_map_single are the
- * same here.
- */
-int
-swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
- int dir)
-{
- void *addr;
- unsigned long dev_addr;
- int i;
-
- if (dir == DMA_NONE)
- BUG();
-
- for (i = 0; i < nelems; i++, sg++) {
- addr = SG_ENT_VIRT_ADDRESS(sg);
- dev_addr = virt_to_phys(addr);
- if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
- sg->dma_address = (dma_addr_t) virt_to_phys(map_single(hwdev, addr, sg->length, dir));
- if (!sg->dma_address) {
- /* Don't panic here, we expect map_sg users
- to do proper error handling. */
- swiotlb_full(hwdev, sg->length, dir, 0);
- swiotlb_unmap_sg(hwdev, sg - i, i, dir);
- sg[0].dma_length = 0;
- return 0;
- }
- } else
- sg->dma_address = dev_addr;
- sg->dma_length = sg->length;
- }
- return nelems;
-}
-
-/*
- * Unmap a set of streaming mode DMA translations. Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_single() above.
- */
-void
-swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
- int dir)
-{
- int i;
-
- if (dir == DMA_NONE)
- BUG();
-
- for (i = 0; i < nelems; i++, sg++)
- if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
- unmap_single(hwdev, (void *) phys_to_virt(sg->dma_address), sg->dma_length, dir);
- else if (dir == DMA_FROM_DEVICE)
- mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
-}
-
-/*
- * Make physical memory consistent for a set of streaming mode DMA translations
- * after a transfer.
- *
- * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
- * and usage.
- */
-void
-swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
- int nelems, int dir)
-{
- int i;
-
- if (dir == DMA_NONE)
- BUG();
-
- for (i = 0; i < nelems; i++, sg++)
- if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
- sync_single(hwdev, (void *) sg->dma_address,
- sg->dma_length, dir);
-}
-
-void
-swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
- int nelems, int dir)
-{
- int i;
-
- if (dir == DMA_NONE)
- BUG();
-
- for (i = 0; i < nelems; i++, sg++)
- if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
- sync_single(hwdev, (void *) sg->dma_address,
- sg->dma_length, dir);
-}
-
-int
-swiotlb_dma_mapping_error(dma_addr_t dma_addr)
-{
- return (dma_addr == virt_to_phys(io_tlb_overflow_buffer));
-}
-
-/*
- * Return whether the given PCI device DMA address mask can be supported
- * properly. For example, if your device can only drive the low 24-bits
- * during PCI bus mastering, then you would pass 0x00ffffff as the mask to
- * this function.
- */
-int
-swiotlb_dma_supported (struct device *hwdev, u64 mask)
-{
- return (virt_to_phys (io_tlb_end) - 1) <= mask;
-}
-
-EXPORT_SYMBOL(swiotlb_init);
-EXPORT_SYMBOL(swiotlb_map_single);
-EXPORT_SYMBOL(swiotlb_unmap_single);
-EXPORT_SYMBOL(swiotlb_map_sg);
-EXPORT_SYMBOL(swiotlb_unmap_sg);
-EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
-EXPORT_SYMBOL(swiotlb_sync_single_for_device);
-EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
-EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
-EXPORT_SYMBOL(swiotlb_dma_mapping_error);
-EXPORT_SYMBOL(swiotlb_alloc_coherent);
-EXPORT_SYMBOL(swiotlb_free_coherent);
-EXPORT_SYMBOL(swiotlb_dma_supported);
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index a88cdb7232f..0f776b032d3 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -350,14 +350,12 @@ static void __init initialize_pernode_data(void)
* for best.
* @nid: node id
* @pernodesize: size of this node's pernode data
- * @align: alignment to use for this node's pernode data
*/
-static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize,
- unsigned long align)
+static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
{
void *ptr = NULL;
u8 best = 0xff;
- int bestnode = -1, node;
+ int bestnode = -1, node, anynode = 0;
for_each_online_node(node) {
if (node_isset(node, memory_less_mask))
@@ -366,13 +364,15 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize,
best = node_distance(nid, node);
bestnode = node;
}
+ anynode = node;
}
- ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat,
- pernodesize, align, __pa(MAX_DMA_ADDRESS));
+ if (bestnode == -1)
+ bestnode = anynode;
+
+ ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat, pernodesize,
+ PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
- if (!ptr)
- panic("NO memory for memory less node\n");
return ptr;
}
@@ -413,8 +413,7 @@ static void __init memory_less_nodes(void)
for_each_node_mask(node, memory_less_mask) {
pernodesize = compute_pernodesize(node);
- pernode = memory_less_node_alloc(node, pernodesize,
- (node) ? (node * PERCPU_PAGE_SIZE) : (1024*1024));
+ pernode = memory_less_node_alloc(node, pernodesize);
fill_pernode(node, __pa(pernode), pernodesize);
}
diff --git a/arch/ia64/oprofile/Kconfig b/arch/ia64/oprofile/Kconfig
index 56e6f614b04..97271ab484d 100644
--- a/arch/ia64/oprofile/Kconfig
+++ b/arch/ia64/oprofile/Kconfig
@@ -1,7 +1,3 @@
-
-menu "Profiling support"
- depends on EXPERIMENTAL
-
config PROFILING
bool "Profiling support (EXPERIMENTAL)"
help
@@ -22,5 +18,3 @@ config OPROFILE
If unsure, say N.
-endmenu
-
diff --git a/arch/ia64/sn/pci/pcibr/pcibr_provider.c b/arch/ia64/sn/pci/pcibr/pcibr_provider.c
index 7b03b8084ff..1f500c81002 100644
--- a/arch/ia64/sn/pci/pcibr/pcibr_provider.c
+++ b/arch/ia64/sn/pci/pcibr/pcibr_provider.c
@@ -212,13 +212,13 @@ void pcibr_target_interrupt(struct sn_irq_info *sn_irq_info)
pdi_pcibus_info;
/* Disable the device's IRQ */
- pcireg_intr_enable_bit_clr(pcibus_info, bit);
+ pcireg_intr_enable_bit_clr(pcibus_info, (1 << bit));
/* Change the device's IRQ */
pcireg_intr_addr_addr_set(pcibus_info, bit, xtalk_addr);
/* Re-enable the device's IRQ */
- pcireg_intr_enable_bit_set(pcibus_info, bit);
+ pcireg_intr_enable_bit_set(pcibus_info, (1 << bit));
pcibr_force_interrupt(sn_irq_info);
}
diff --git a/arch/ia64/sn/pci/pcibr/pcibr_reg.c b/arch/ia64/sn/pci/pcibr/pcibr_reg.c
index 4f718c3e93d..5d534091262 100644
--- a/arch/ia64/sn/pci/pcibr/pcibr_reg.c
+++ b/arch/ia64/sn/pci/pcibr/pcibr_reg.c
@@ -131,7 +131,7 @@ void pcireg_intr_enable_bit_clr(struct pcibus_info *pcibus_info, uint64_t bits)
__sn_clrq_relaxed(&ptr->tio.cp_int_enable, bits);
break;
case PCIBR_BRIDGETYPE_PIC:
- __sn_clrq_relaxed(&ptr->pic.p_int_enable, ~bits);
+ __sn_clrq_relaxed(&ptr->pic.p_int_enable, bits);
break;
default:
panic
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-21 02:01:52 +0000