12 files changed, 163 insertions, 85 deletions

diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index 9f63ae0f404b..b7808a89d945 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -159,9 +159,15 @@ char *__acpi_map_table(unsigned long phys, unsigned long size)
 #endif
 
 #ifdef CONFIG_PCI_MMCONFIG
-static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size)
+/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
+struct acpi_table_mcfg_config *pci_mmcfg_config;
+int pci_mmcfg_config_num;
+
+int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size)
 {
         struct acpi_table_mcfg *mcfg;
+        unsigned long i;
+        int config_size;
 
         if (!phys_addr || !size)
                 return -EINVAL;
@@ -172,18 +178,38 @@ static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size)
                 return -ENODEV;
         }
 
-        if (mcfg->base_reserved) {
-                printk(KERN_ERR PREFIX "MMCONFIG not in low 4GB of memory\n");
+        /* how many config structures do we have */
+        pci_mmcfg_config_num = 0;
+        i = size - sizeof(struct acpi_table_mcfg);
+        while (i >= sizeof(struct acpi_table_mcfg_config)) {
+                ++pci_mmcfg_config_num;
+                i -= sizeof(struct acpi_table_mcfg_config);
+        };
+        if (pci_mmcfg_config_num == 0) {
+                printk(KERN_ERR PREFIX "MMCONFIG has no entries\n");
                 return -ENODEV;
         }
 
-        pci_mmcfg_base_addr = mcfg->base_address;
+        config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config);
+        pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL);
+        if (!pci_mmcfg_config) {
+                printk(KERN_WARNING PREFIX
+                       "No memory for MCFG config tables\n");
+                return -ENOMEM;
+        }
+
+        memcpy(pci_mmcfg_config, &mcfg->config, config_size);
+        for (i = 0; i < pci_mmcfg_config_num; ++i) {
+                if (mcfg->config[i].base_reserved) {
+                        printk(KERN_ERR PREFIX
+                               "MMCONFIG not in low 4GB of memory\n");
+                        return -ENODEV;
+                }
+        }
 
         return 0;
 }
-#else
-#define acpi_parse_mcfg NULL
-#endif /* !CONFIG_PCI_MMCONFIG */
+#endif /* CONFIG_PCI_MMCONFIG */
 
 #ifdef CONFIG_X86_LOCAL_APIC
 static int __init
@@ -507,6 +533,22 @@ acpi_unmap_lsapic(int cpu)
 EXPORT_SYMBOL(acpi_unmap_lsapic);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
+int
+acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
+{
+        /* TBD */
+        return -EINVAL;
+}
+EXPORT_SYMBOL(acpi_register_ioapic);
+
+int
+acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
+{
+        /* TBD */
+        return -EINVAL;
+}
+EXPORT_SYMBOL(acpi_unregister_ioapic);
+
 static unsigned long __init
 acpi_scan_rsdp (
         unsigned long           start,
@@ -1123,7 +1165,6 @@ int __init acpi_boot_init(void)
         acpi_process_madt();
 
         acpi_table_parse(ACPI_HPET, acpi_parse_hpet);
-        acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg);
 
         return 0;
 }
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 93df90bbb87e..bd1dbf3bd223 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -35,6 +35,7 @@
 #include <asm/desc.h>
 #include <asm/arch_hooks.h>
 #include <asm/hpet.h>
+#include <asm/i8253.h>
 
 #include <mach_apic.h>
 
@@ -879,7 +880,6 @@ fake_ioapic_page:
  */
 static unsigned int __devinit get_8254_timer_count(void)
 {
-        extern spinlock_t i8253_lock;
         unsigned long flags;
 
         unsigned int count;
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index d48ce9290963..064211d5f41b 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -228,10 +228,10 @@
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/desc.h>
+#include <asm/i8253.h>
 
 #include "io_ports.h"
 
-extern spinlock_t i8253_lock;
 extern unsigned long get_cmos_time(void);
 extern void machine_real_restart(unsigned char *, int);
 
@@ -1168,8 +1168,7 @@ static void get_time_diff(void)
 static void reinit_timer(void)
 {
 #ifdef INIT_TIMER_AFTER_SUSPEND
-        unsigned long   flags;
-        extern spinlock_t i8253_lock;
+        unsigned long flags;
 
         spin_lock_irqsave(&i8253_lock, flags);
         /* set the clock to 100 Hz */
diff --git a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c
index 1a49adb1f4a6..e86ea486c311 100644
--- a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c
@@ -190,7 +190,7 @@ static __init struct pci_dev *gx_detect_chipset(void)
 
         /* detect which companion chip is used */
         while ((gx_pci = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, gx_pci)) != NULL) {
-                if ((pci_match_device (gx_chipset_tbl, gx_pci)) != NULL) {
+                if ((pci_match_id(gx_chipset_tbl, gx_pci)) != NULL) {
                         return gx_pci;
                 }
         }
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 35eb8e29c485..6578f40bd501 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -37,6 +37,7 @@
 #include <asm/smp.h>
 #include <asm/desc.h>
 #include <asm/timer.h>
+#include <asm/i8259.h>
 
 #include <mach_apic.h>
 
@@ -1566,7 +1567,6 @@ void print_all_local_APICs (void)
 
 void /*__init*/ print_PIC(void)
 {
-        extern spinlock_t i8259A_lock;
         unsigned int v;
         unsigned long flags;
 
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 3762f6b35ab2..a6d8c45961d3 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -127,48 +127,23 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
                 regs->eip = (unsigned long)&p->ainsn.insn;
 }
 
-struct task_struct  *arch_get_kprobe_task(void *ptr)
-{
-        return ((struct thread_info *) (((unsigned long) ptr) &
-                                        (~(THREAD_SIZE -1))))->task;
-}
-
 void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
 {
         unsigned long *sara = (unsigned long *)&regs->esp;
-        struct kretprobe_instance *ri;
-        static void *orig_ret_addr;
+        struct kretprobe_instance *ri;
+
+        if ((ri = get_free_rp_inst(rp)) != NULL) {
+                ri->rp = rp;
+                ri->task = current;
+                ri->ret_addr = (kprobe_opcode_t *) *sara;
 
-        /*
-         * Save the return address when the return probe hits
-         * the first time, and use it to populate the (krprobe
-         * instance)->ret_addr for subsequent return probes at
-         * the same addrress since stack address would have
-         * the kretprobe_trampoline by then.
-         */
-        if (((void*) *sara) != kretprobe_trampoline)
-                orig_ret_addr = (void*) *sara;
-
-        if ((ri = get_free_rp_inst(rp)) != NULL) {
-                ri->rp = rp;
-                ri->stack_addr = sara;
-                ri->ret_addr = orig_ret_addr;
-                add_rp_inst(ri);
                 /* Replace the return addr with trampoline addr */
                 *sara = (unsigned long) &kretprobe_trampoline;
-        } else {
-                rp->nmissed++;
-        }
-}
 
-void arch_kprobe_flush_task(struct task_struct *tk)
-{
-        struct kretprobe_instance *ri;
-        while ((ri = get_rp_inst_tsk(tk)) != NULL) {
-                *((unsigned long *)(ri->stack_addr)) =
-                                        (unsigned long) ri->ret_addr;
-                recycle_rp_inst(ri);
-        }
+                add_rp_inst(ri);
+        } else {
+                rp->nmissed++;
+        }
 }
 
 /*
@@ -286,36 +261,59 @@ no_kprobe:
  */
 int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-        struct task_struct *tsk;
-        struct kretprobe_instance *ri;
-        struct hlist_head *head;
-        struct hlist_node *node;
-        unsigned long *sara = ((unsigned long *) &regs->esp) - 1;
-
-        tsk = arch_get_kprobe_task(sara);
-        head = kretprobe_inst_table_head(tsk);
-
-        hlist_for_each_entry(ri, node, head, hlist) {
-                if (ri->stack_addr == sara && ri->rp) {
-                        if (ri->rp->handler)
-                                ri->rp->handler(ri, regs);
-                }
-        }
-        return 0;
-}
+        struct kretprobe_instance *ri = NULL;
+        struct hlist_head *head;
+        struct hlist_node *node, *tmp;
+        unsigned long orig_ret_address = 0;
+        unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
 
-void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
-                                                unsigned long flags)
-{
-        struct kretprobe_instance *ri;
-        /* RA already popped */
-        unsigned long *sara = ((unsigned long *)&regs->esp) - 1;
+        head = kretprobe_inst_table_head(current);
 
-        while ((ri = get_rp_inst(sara))) {
-                regs->eip = (unsigned long)ri->ret_addr;
+        /*
+         * It is possible to have multiple instances associated with a given
+         * task either because an multiple functions in the call path
+         * have a return probe installed on them, and/or more then one return
+         * return probe was registered for a target function.
+         *
+         * We can handle this because:
+         *     - instances are always inserted at the head of the list
+         *     - when multiple return probes are registered for the same
+         *       function, the first instance's ret_addr will point to the
+         *       real return address, and all the rest will point to
+         *       kretprobe_trampoline
+         */
+        hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+                        /* another task is sharing our hash bucket */
+                        continue;
+
+                if (ri->rp && ri->rp->handler)
+                        ri->rp->handler(ri, regs);
+
+                orig_ret_address = (unsigned long)ri->ret_addr;
                 recycle_rp_inst(ri);
+
+                if (orig_ret_address != trampoline_address)
+                        /*
+                         * This is the real return address. Any other
+                         * instances associated with this task are for
+                         * other calls deeper on the call stack
+                         */
+                        break;
         }
-        regs->eflags &= ~TF_MASK;
+
+        BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
+        regs->eip = orig_ret_address;
+
+        unlock_kprobes();
+        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;
 }
 
 /*
@@ -403,8 +401,7 @@ static inline int post_kprobe_handler(struct pt_regs *regs)
                 current_kprobe->post_handler(current_kprobe, regs, 0);
         }
 
-        if (current_kprobe->post_handler != trampoline_post_handler)
-                resume_execution(current_kprobe, regs);
+        resume_execution(current_kprobe, regs);
         regs->eflags |= kprobe_saved_eflags;
 
         /*Restore back the original saved kprobes variables and continue. */
@@ -534,3 +531,13 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
         }
         return 0;
 }
+
+static struct kprobe trampoline_p = {
+        .addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+        .pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init_kprobes(void)
+{
+        return register_kprobe(&trampoline_p);
+}
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 5f8cfa6b7940..ba243a4cc119 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -617,6 +617,33 @@ handle_io_bitmap(struct thread_struct *next, struct tss_struct *tss)
 }
 
 /*
+ * This function selects if the context switch from prev to next
+ * has to tweak the TSC disable bit in the cr4.
+ */
+static inline void disable_tsc(struct task_struct *prev_p,
+                               struct task_struct *next_p)
+{
+        struct thread_info *prev, *next;
+
+        /*
+         * gcc should eliminate the ->thread_info dereference if
+         * has_secure_computing returns 0 at compile time (SECCOMP=n).
+         */
+        prev = prev_p->thread_info;
+        next = next_p->thread_info;
+
+        if (has_secure_computing(prev) || has_secure_computing(next)) {
+                /* slow path here */
+                if (has_secure_computing(prev) &&
+                    !has_secure_computing(next)) {
+                        write_cr4(read_cr4() & ~X86_CR4_TSD);
+                } else if (!has_secure_computing(prev) &&
+                           has_secure_computing(next))
+                        write_cr4(read_cr4() | X86_CR4_TSD);
+        }
+}
+
+/*
  *      switch_to(x,yn) should switch tasks from x to y.
  *
  * We fsave/fwait so that an exception goes off at the right time
@@ -695,6 +722,8 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
         if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr))
                 handle_io_bitmap(next, tss);
 
+        disable_tsc(prev_p, next_p);
+
         return prev_p;
 }
 
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 442a6e937b19..3db9a04aec6e 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -289,3 +289,5 @@ ENTRY(sys_call_table)
         .long sys_add_key
         .long sys_request_key
         .long sys_keyctl
+        .long sys_ioprio_set
+        .long sys_ioprio_get            /* 290 */
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index e68d9fdb0759..2854c357377f 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -68,7 +68,8 @@
 
 #include "io_ports.h"
 
-extern spinlock_t i8259A_lock;
+#include <asm/i8259.h>
+
 int pit_latch_buggy;              /* extern */
 
 #include "do_timer.h"
@@ -85,6 +86,8 @@ extern unsigned long wall_jiffies;
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
 
+#include <asm/i8253.h>
+
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
diff --git a/arch/i386/kernel/timers/timer_cyclone.c b/arch/i386/kernel/timers/timer_cyclone.c
index f6f1206a11bb..13892a65c941 100644
--- a/arch/i386/kernel/timers/timer_cyclone.c
+++ b/arch/i386/kernel/timers/timer_cyclone.c
@@ -17,9 +17,9 @@
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/fixmap.h>
-#include "io_ports.h"
+#include <asm/i8253.h>
 
-extern spinlock_t i8253_lock;
+#include "io_ports.h"
 
 /* Number of usecs that the last interrupt was delayed */
 static int delay_at_last_interrupt;
diff --git a/arch/i386/kernel/timers/timer_pit.c b/arch/i386/kernel/timers/timer_pit.c
index 967d5453cd0e..06de036a820c 100644
--- a/arch/i386/kernel/timers/timer_pit.c
+++ b/arch/i386/kernel/timers/timer_pit.c
@@ -15,9 +15,8 @@
 #include <asm/smp.h>
 #include <asm/io.h>
 #include <asm/arch_hooks.h>
+#include <asm/i8253.h>
 
-extern spinlock_t i8259A_lock;
-extern spinlock_t i8253_lock;
 #include "do_timer.h"
 #include "io_ports.h"
 
@@ -166,7 +165,6 @@ struct init_timer_opts __initdata timer_pit_init = {
 
 void setup_pit_timer(void)
 {
-        extern spinlock_t i8253_lock;
         unsigned long flags;
 
         spin_lock_irqsave(&i8253_lock, flags);
diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c
index f46e625bab67..8f4e4d5bc560 100644
--- a/arch/i386/kernel/timers/timer_tsc.c
+++ b/arch/i386/kernel/timers/timer_tsc.c
@@ -24,6 +24,7 @@
 #include "mach_timer.h"
 
 #include <asm/hpet.h>
+#include <asm/i8253.h>
 
 #ifdef CONFIG_HPET_TIMER
 static unsigned long hpet_usec_quotient;
@@ -35,8 +36,6 @@ static inline void cpufreq_delayed_get(void);
 
 int tsc_disable __devinitdata = 0;
 
-extern spinlock_t i8253_lock;
-
 static int use_tsc;
 /* Number of usecs that the last interrupt was delayed */
 static int delay_at_last_interrupt;