/* Handle bad interrupts */
static struct irq_desc bad_irq_desc = {
.handle_irq = handle_bad_irq,
- .lock = SPIN_LOCK_UNLOCKED
+ .lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock),
};
+ #ifdef CONFIG_CPUMASK_OFFSTACK
+ /* We are not allocating bad_irq_desc.affinity or .pending_mask */
+ #error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK."
+ #endif
+
/*
* do_IRQ handles all hardware IRQ's. Decoded IRQs should not
* come via this function. Instead, they should provide their
irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE;
#ifdef CONFIG_SMP
- bad_irq_desc.affinity = CPU_MASK_ALL;
+ cpumask_setall(bad_irq_desc.affinity);
bad_irq_desc.cpu = smp_processor_id();
#endif
init_arch_irq();
struct irq_desc *desc = irq_desc + i;
if (desc->cpu == cpu) {
- unsigned int newcpu = any_online_cpu(desc->affinity);
-
- if (newcpu == NR_CPUS) {
+ unsigned int newcpu = cpumask_any_and(desc->affinity,
+ cpu_online_mask);
+ if (newcpu >= nr_cpu_ids) {
if (printk_ratelimit())
printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
i, cpu);
- cpus_setall(desc->affinity);
- newcpu = any_online_cpu(desc->affinity);
+ cpumask_setall(desc->affinity);
+ newcpu = cpumask_any_and(desc->affinity,
+ cpu_online_mask);
}
route_irq(desc, i, newcpu);
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <asm/trace.h>
+#include <asm/pda.h>
static atomic_t irq_err_count;
static spinlock_t irq_controller_lock;
#endif
};
+ #ifdef CONFIG_CPUMASK_OFFSTACK
+ /* We are not allocating a variable-sized bad_irq_desc.affinity */
+ #error "Blackfin architecture does not support CONFIG_CPUMASK_OFFSTACK."
+ #endif
+
int show_interrupts(struct seq_file *p, void *v)
{
int i = *(loff_t *) v, j;
seq_putc(p, '\n');
skip:
spin_unlock_irqrestore(&irq_desc[i].lock, flags);
- } else if (i == NR_IRQS)
+ } else if (i == NR_IRQS) {
+ seq_printf(p, "NMI: ");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", cpu_pda[j].__nmi_count);
+ seq_printf(p, " CORE Non Maskable Interrupt\n");
seq_printf(p, "Err: %10u\n", atomic_read(&irq_err_count));
+ }
return 0;
}
seq_putc(p, '\n');
skip:
spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+ } else if (i == NR_IRQS) {
+ seq_printf(p, "NMI: ");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", cpu_data(j).__nmi_count);
+ seq_printf(p, " Non-maskable interrupts\n");
}
return 0;
}
#ifdef CONFIG_SMP
static int irq_choose_cpu(unsigned int virt_irq)
{
- cpumask_t mask = irq_desc[virt_irq].affinity;
+ cpumask_t mask;
int cpuid;
+ cpumask_copy(&mask, irq_desc[virt_irq].affinity);
if (cpus_equal(mask, CPU_MASK_ALL)) {
static int irq_rover;
static DEFINE_SPINLOCK(irq_rover_lock);
local_irq_restore(flags);
}
-static void unhandled_perf_irq(struct pt_regs *regs)
-{
- unsigned long pcr, pic;
-
- read_pcr(pcr);
- read_pic(pic);
-
- write_pcr(0);
-
- printk(KERN_EMERG "CPU %d: Got unexpected perf counter IRQ.\n",
- smp_processor_id());
- printk(KERN_EMERG "CPU %d: PCR[%016lx] PIC[%016lx]\n",
- smp_processor_id(), pcr, pic);
-}
-
-/* Almost a direct copy of the powerpc PMC code. */
-static DEFINE_SPINLOCK(perf_irq_lock);
-static void *perf_irq_owner_caller; /* mostly for debugging */
-static void (*perf_irq)(struct pt_regs *regs) = unhandled_perf_irq;
-
-/* Invoked from level 15 PIL handler in trap table. */
-void perfctr_irq(int irq, struct pt_regs *regs)
-{
- clear_softint(1 << irq);
- perf_irq(regs);
-}
-
-int register_perfctr_intr(void (*handler)(struct pt_regs *))
-{
- int ret;
-
- if (!handler)
- return -EINVAL;
-
- spin_lock(&perf_irq_lock);
- if (perf_irq != unhandled_perf_irq) {
- printk(KERN_WARNING "register_perfctr_intr: "
- "perf IRQ busy (reserved by caller %p)\n",
- perf_irq_owner_caller);
- ret = -EBUSY;
- goto out;
- }
-
- perf_irq_owner_caller = __builtin_return_address(0);
- perf_irq = handler;
-
- ret = 0;
-out:
- spin_unlock(&perf_irq_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(register_perfctr_intr);
-
-void release_perfctr_intr(void (*handler)(struct pt_regs *))
-{
- spin_lock(&perf_irq_lock);
- perf_irq_owner_caller = NULL;
- perf_irq = unhandled_perf_irq;
- spin_unlock(&perf_irq_lock);
-}
-EXPORT_SYMBOL_GPL(release_perfctr_intr);
-
#ifdef CONFIG_HOTPLUG_CPU
void fixup_irqs(void)
{
!(irq_desc[irq].status & IRQ_PER_CPU)) {
if (irq_desc[irq].chip->set_affinity)
irq_desc[irq].chip->set_affinity(irq,
- &irq_desc[irq].affinity);
+ irq_desc[irq].affinity);
}
spin_unlock_irqrestore(&irq_desc[irq].lock, flags);
}
CFI_DEF_CFA rsp,0
CFI_REGISTER rsp,rbp
SWAPGS_UNSAFE_STACK
- movq %gs:pda_kernelstack, %rsp
- addq $(PDA_STACKOFFSET),%rsp
+ movq PER_CPU_VAR(kernel_stack), %rsp
+ addq $(KERNEL_STACK_OFFSET),%rsp
/*
* No need to follow this irqs on/off section: the syscall
* disabled irqs, here we enable it straight after entry:
ENTRY(ia32_cstar_target)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,PDA_STACKOFFSET
+ CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
movl %esp,%r8d
CFI_REGISTER rsp,r8
- movq %gs:pda_kernelstack,%rsp
+ movq PER_CPU_VAR(kernel_stack),%rsp
/*
* No need to follow this irqs on/off section: the syscall
* disabled irqs and here we enable it straight after entry:
orl $TS_COMPAT,TI_status(%r10)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
jnz ia32_tracesys
-ia32_do_syscall:
cmpl $(IA32_NR_syscalls-1),%eax
- ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
+ ja ia32_badsys
+ia32_do_call:
IA32_ARG_FIXUP
call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
ia32_sysret:
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
RESTORE_REST
- jmp ia32_do_syscall
+ cmpl $(IA32_NR_syscalls-1),%eax
+ ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
+ jmp ia32_do_call
END(ia32_syscall)
ia32_badsys:
return pgd.pgd;
}
+static inline pgdval_t pgd_flags(pgd_t pgd)
+{
+ return native_pgd_val(pgd) & PTE_FLAGS_MASK;
+}
+
#if PAGETABLE_LEVELS >= 3
#if PAGETABLE_LEVELS == 4
typedef struct { pudval_t pud; } pud_t;
}
#endif /* PAGETABLE_LEVELS == 4 */
+static inline pudval_t pud_flags(pud_t pud)
+{
+ return native_pud_val(pud) & PTE_FLAGS_MASK;
+}
+
typedef struct { pmdval_t pmd; } pmd_t;
static inline pmd_t native_make_pmd(pmdval_t val)
{
return pmd.pmd;
}
+
#else /* PAGETABLE_LEVELS == 2 */
#include <asm-generic/pgtable-nopmd.h>
}
#endif /* PAGETABLE_LEVELS >= 3 */
+static inline pmdval_t pmd_flags(pmd_t pmd)
+{
+ return native_pmd_val(pmd) & PTE_FLAGS_MASK;
+}
+
static inline pte_t native_make_pte(pteval_t val)
{
return (pte_t) { .pte = val };
return pte.pte;
}
- static inline pteval_t native_pte_flags(pte_t pte)
+ static inline pteval_t pte_flags(pte_t pte)
{
return native_pte_val(pte) & PTE_FLAGS_MASK;
}
#endif
#define pte_val(x) native_pte_val(x)
- #define pte_flags(x) native_pte_flags(x)
#define __pte(x) native_make_pte(x)
#endif /* CONFIG_PARAVIRT */
#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H
+#include <asm/page.h>
+
#define FIRST_USER_ADDRESS 0
#define _PAGE_BIT_PRESENT 0 /* is present */
static inline int pmd_large(pmd_t pte)
{
- return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+ return (pmd_flags(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
(_PAGE_PSE | _PAGE_PRESENT);
}
+ static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
+ {
+ pteval_t v = native_pte_val(pte);
+
+ return native_make_pte(v | set);
+ }
+
+ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
+ {
+ pteval_t v = native_pte_val(pte);
+
+ return native_make_pte(v & ~clear);
+ }
+
static inline pte_t pte_mkclean(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+ return pte_clear_flags(pte, _PAGE_DIRTY);
}
static inline pte_t pte_mkold(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+ return pte_clear_flags(pte, _PAGE_ACCESSED);
}
static inline pte_t pte_wrprotect(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_RW);
+ return pte_clear_flags(pte, _PAGE_RW);
}
static inline pte_t pte_mkexec(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_NX);
+ return pte_clear_flags(pte, _PAGE_NX);
}
static inline pte_t pte_mkdirty(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_DIRTY);
+ return pte_set_flags(pte, _PAGE_DIRTY);
}
static inline pte_t pte_mkyoung(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_ACCESSED);
+ return pte_set_flags(pte, _PAGE_ACCESSED);
}
static inline pte_t pte_mkwrite(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_RW);
+ return pte_set_flags(pte, _PAGE_RW);
}
static inline pte_t pte_mkhuge(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_PSE);
+ return pte_set_flags(pte, _PAGE_PSE);
}
static inline pte_t pte_clrhuge(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_PSE);
+ return pte_clear_flags(pte, _PAGE_PSE);
}
static inline pte_t pte_mkglobal(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_GLOBAL);
+ return pte_set_flags(pte, _PAGE_GLOBAL);
}
static inline pte_t pte_clrglobal(pte_t pte)
{
- return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
+ return pte_clear_flags(pte, _PAGE_GLOBAL);
}
static inline pte_t pte_mkspecial(pte_t pte)
{
- return __pte(pte_val(pte) | _PAGE_SPECIAL);
+ return pte_set_flags(pte, _PAGE_SPECIAL);
}
extern pteval_t __supported_pte_mask;
# include "pgtable_64.h"
#endif
+#ifndef __ASSEMBLY__
+#include <linux/mm_types.h>
+
+static inline int pte_none(pte_t pte)
+{
+ return !pte.pte;
+}
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t a, pte_t b)
+{
+ return a.pte == b.pte;
+}
+
+static inline int pte_present(pte_t a)
+{
+ return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+}
+
+static inline int pmd_present(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_PRESENT;
+}
+
+static inline int pmd_none(pmd_t pmd)
+{
+ /* Only check low word on 32-bit platforms, since it might be
+ out of sync with upper half. */
+ return (unsigned long)native_pmd_val(pmd) == 0;
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+ return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pmd_page(pmd) pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+static inline unsigned pmd_index(unsigned long address)
+{
+ return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
+}
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * (Currently stuck as a macro because of indirect forward reference
+ * to linux/mm.h:page_to_nid())
+ */
+#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this function returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+static inline unsigned pte_index(unsigned long address)
+{
+ return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+}
+
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
+{
+ return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+ return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
+}
+
+static inline unsigned long pages_to_mb(unsigned long npg)
+{
+ return npg >> (20 - PAGE_SHIFT);
+}
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
+ remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#if PAGETABLE_LEVELS == 2
+static inline int pud_large(pud_t pud)
+{
+ return 0;
+}
+#endif
+
+#if PAGETABLE_LEVELS > 2
+static inline int pud_none(pud_t pud)
+{
+ return native_pud_val(pud) == 0;
+}
+
+static inline int pud_present(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_PRESENT;
+}
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+ return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pud_page(pud) pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
+
+/* Find an entry in the second-level page table.. */
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+{
+ return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
+}
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+ return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
+static inline int pud_large(pud_t pud)
+{
+ return (pud_flags(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+ (_PAGE_PSE | _PAGE_PRESENT);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+ return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+#endif /* PAGETABLE_LEVELS > 2 */
+
+#if PAGETABLE_LEVELS > 3
+static inline int pgd_present(pgd_t pgd)
+{
+ return pgd_flags(pgd) & _PAGE_PRESENT;
+}
+
+static inline unsigned long pgd_page_vaddr(pgd_t pgd)
+{
+ return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pgd_page(pgd) pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
+
+/* to find an entry in a page-table-directory. */
+static inline unsigned pud_index(unsigned long address)
+{
+ return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
+}
+
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+{
+ return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
+}
+
+static inline int pgd_bad(pgd_t pgd)
+{
+ return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+}
+
+static inline int pgd_none(pgd_t pgd)
+{
+ return !native_pgd_val(pgd);
+}
+#endif /* PAGETABLE_LEVELS > 3 */
+
+#endif /* __ASSEMBLY__ */
+
/*
* the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
*
#include <asm/processor.h>
#include <linux/bitops.h>
#include <linux/threads.h>
- #include <asm/pda.h>
extern pud_t level3_kernel_pgt[512];
extern pud_t level3_ident_pgt[512];
printk("%s:%d: bad pgd %p(%016lx).\n", \
__FILE__, __LINE__, &(e), pgd_val(e))
-#define pgd_none(x) (!pgd_val(x))
-#define pud_none(x) (!pud_val(x))
-
struct mm_struct;
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
native_set_pgd(pgd, native_make_pgd(0));
}
-#define pte_same(a, b) ((a).pte == (b).pte)
-
#endif /* !__ASSEMBLY__ */
#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
#ifndef __ASSEMBLY__
-static inline int pgd_bad(pgd_t pgd)
-{
- return (pgd_val(pgd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pud_bad(pud_t pud)
-{
- return (pud_val(pud) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pmd_bad(pmd_t pmd)
-{
- return (pmd_val(pmd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-#define pte_none(x) (!pte_val((x)))
-#define pte_present(x) (pte_val((x)) & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-#define pages_to_mb(x) ((x) >> (20 - PAGE_SHIFT)) /* FIXME: is this right? */
-
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
/*
* Level 4 access.
*/
-#define pgd_page_vaddr(pgd) \
- ((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_PFN_MASK))
-#define pgd_page(pgd) (pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT))
-#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
static inline int pgd_large(pgd_t pgd) { return 0; }
#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
/* PUD - Level3 access */
-/* to find an entry in a page-table-directory. */
-#define pud_page_vaddr(pud) \
- ((unsigned long)__va(pud_val((pud)) & PHYSICAL_PAGE_MASK))
-#define pud_page(pud) (pfn_to_page(pud_val((pud)) >> PAGE_SHIFT))
-#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
-#define pud_offset(pgd, address) \
- ((pud_t *)pgd_page_vaddr(*(pgd)) + pud_index((address)))
-#define pud_present(pud) (pud_val((pud)) & _PAGE_PRESENT)
-
-static inline int pud_large(pud_t pte)
-{
- return (pud_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
- (_PAGE_PSE | _PAGE_PRESENT);
-}
/* PMD - Level 2 access */
-#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_PFN_MASK))
-#define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
-
-#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-#define pmd_offset(dir, address) ((pmd_t *)pud_page_vaddr(*(dir)) + \
- pmd_index(address))
-#define pmd_none(x) (!pmd_val((x)))
-#define pmd_present(x) (pmd_val((x)) & _PAGE_PRESENT)
-#define pfn_pmd(nr, prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val((prot))))
-#define pmd_pfn(x) ((pmd_val((x)) & __PHYSICAL_MASK) >> PAGE_SHIFT)
-
#define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
#define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) | \
_PAGE_FILE })
/* PTE - Level 1 access. */
-/* page, protection -> pte */
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn((page)), (pgprot))
-
-#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
- pte_index((address)))
-
/* x86-64 always has all page tables mapped. */
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
#define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
extern int kern_addr_valid(unsigned long addr);
extern void cleanup_highmap(void);
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
- remap_pfn_range(vma, vaddr, pfn, size, prot)
-
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
stack_start.sp = temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
(unsigned long)get_cpu_gdt_table(smp_processor_id());
+ initial_gs = per_cpu_offset(smp_processor_id());
#endif
initial_code = (unsigned long)wakeup_long64;
saved_magic = 0x123456789abcdef0;
#ifdef CONFIG_HIBERNATION
if (strncmp(str, "s4_nohwsig", 10) == 0)
acpi_no_s4_hw_signature();
+ if (strncmp(str, "s4_nonvs", 8) == 0)
+ acpi_s4_no_nvs();
#endif
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
- if (strncmp(str, "s4_nonvs", 8) == 0)
- acpi_s4_no_nvs();
str = strchr(str, ',');
if (str != NULL)
str += strspn(str, ", \t");
# error SPURIOUS_APIC_VECTOR definition error
#endif
+ unsigned int num_processors;
+ unsigned disabled_cpus __cpuinitdata;
+ /* Processor that is doing the boot up */
+ unsigned int boot_cpu_physical_apicid = -1U;
+ EXPORT_SYMBOL(boot_cpu_physical_apicid);
+ unsigned int max_physical_apicid;
+
+ /* Bitmask of physically existing CPUs */
+ physid_mask_t phys_cpu_present_map;
+
+ /*
+ * Map cpu index to physical APIC ID
+ */
+ DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
+ DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
+ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
+ EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
+
#ifdef CONFIG_X86_32
/*
* Knob to control our willingness to enable the local APIC.
unsigned int value;
int i, j;
+ if (disable_apic) {
+ #ifdef CONFIG_X86_IO_APIC
+ disable_ioapic_setup();
+ #endif
+ return;
+ }
+
#ifdef CONFIG_X86_32
/* Pound the ESR really hard over the head with a big hammer - mbligh */
if (lapic_is_integrated() && esr_disable) {
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model > 1) ||
- (boot_cpu_data.x86 == 15))
+ (boot_cpu_data.x86 >= 15))
break;
goto no_apic;
case X86_VENDOR_INTEL:
int __init APIC_init_uniprocessor(void)
{
- #ifdef CONFIG_X86_64
if (disable_apic) {
pr_info("Apic disabled\n");
return -1;
}
+ #ifdef CONFIG_X86_64
if (!cpu_has_apic) {
disable_apic = 1;
pr_info("Apic disabled by BIOS\n");
#endif
#if defined(CONFIG_X86_SMP) || defined(CONFIG_X86_64)
- /* are we being called early in kernel startup? */
- if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
- u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
- u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
-
- cpu_to_apicid[cpu] = apicid;
- bios_cpu_apicid[cpu] = apicid;
- } else {
- per_cpu(x86_cpu_to_apicid, cpu) = apicid;
- per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
- }
+ early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
+ early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
#endif
set_cpu_possible(cpu, true);
{
{ 0x06, LVL_1_INST, 8 }, /* 4-way set assoc, 32 byte line size */
{ 0x08, LVL_1_INST, 16 }, /* 4-way set assoc, 32 byte line size */
+ { 0x09, LVL_1_INST, 32 }, /* 4-way set assoc, 64 byte line size */
{ 0x0a, LVL_1_DATA, 8 }, /* 2 way set assoc, 32 byte line size */
{ 0x0c, LVL_1_DATA, 16 }, /* 4-way set assoc, 32 byte line size */
+ { 0x0d, LVL_1_DATA, 16 }, /* 4-way set assoc, 64 byte line size */
+ { 0x21, LVL_2, 256 }, /* 8-way set assoc, 64 byte line size */
{ 0x22, LVL_3, 512 }, /* 4-way set assoc, sectored cache, 64 byte line size */
{ 0x23, LVL_3, 1024 }, /* 8-way set assoc, sectored cache, 64 byte line size */
{ 0x25, LVL_3, 2048 }, /* 8-way set assoc, sectored cache, 64 byte line size */
{ 0x85, LVL_2, 2048 }, /* 8-way set assoc, 32 byte line size */
{ 0x86, LVL_2, 512 }, /* 4-way set assoc, 64 byte line size */
{ 0x87, LVL_2, 1024 }, /* 8-way set assoc, 64 byte line size */
+ { 0xd0, LVL_3, 512 }, /* 4-way set assoc, 64 byte line size */
+ { 0xd1, LVL_3, 1024 }, /* 4-way set assoc, 64 byte line size */
+ { 0xd2, LVL_3, 2048 }, /* 4-way set assoc, 64 byte line size */
+ { 0xd6, LVL_3, 1024 }, /* 8-way set assoc, 64 byte line size */
+ { 0xd7, LVL_3, 2038 }, /* 8-way set assoc, 64 byte line size */
+ { 0xd8, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */
+ { 0xdc, LVL_3, 2048 }, /* 12-way set assoc, 64 byte line size */
+ { 0xdd, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */
+ { 0xde, LVL_3, 8192 }, /* 12-way set assoc, 64 byte line size */
+ { 0xe2, LVL_3, 2048 }, /* 16-way set assoc, 64 byte line size */
+ { 0xe3, LVL_3, 4096 }, /* 16-way set assoc, 64 byte line size */
+ { 0xe4, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */
{ 0x00, 0, 0}
};
union _cpuid4_leaf_ecx ecx;
unsigned long size;
unsigned long can_disable;
- cpumask_t shared_cpu_map; /* future?: only cpus/node is needed */
+ DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+ };
+
+ /* subset of above _cpuid4_info w/o shared_cpu_map */
+ struct _cpuid4_info_regs {
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
+ unsigned long size;
+ unsigned long can_disable;
};
#ifdef CONFIG_PCI
}
static void __cpuinit
- amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
+ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
{
if (index < 3)
return;
}
static int
- __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+ __cpuinit cpuid4_cache_lookup_regs(int index,
+ struct _cpuid4_info_regs *this_leaf)
{
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
return 0;
}
+ static int
+ __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+ {
+ struct _cpuid4_info_regs *leaf_regs =
+ (struct _cpuid4_info_regs *)this_leaf;
+
+ return cpuid4_cache_lookup_regs(index, leaf_regs);
+ }
+
static int __cpuinit find_num_cache_leaves(void)
{
unsigned int eax, ebx, ecx, edx;
* parameters cpuid leaf to find the cache details
*/
for (i = 0; i < num_cache_leaves; i++) {
- struct _cpuid4_info this_leaf;
-
+ struct _cpuid4_info_regs this_leaf;
int retval;
- retval = cpuid4_cache_lookup(i, &this_leaf);
+ retval = cpuid4_cache_lookup_regs(i, &this_leaf);
if (retval >= 0) {
switch(this_leaf.eax.split.level) {
case 1:
num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
if (num_threads_sharing == 1)
- cpu_set(cpu, this_leaf->shared_cpu_map);
+ cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
else {
index_msb = get_count_order(num_threads_sharing);
for_each_online_cpu(i) {
if (cpu_data(i).apicid >> index_msb ==
c->apicid >> index_msb) {
- cpu_set(i, this_leaf->shared_cpu_map);
+ cpumask_set_cpu(i,
+ to_cpumask(this_leaf->shared_cpu_map));
if (i != cpu && per_cpu(cpuid4_info, i)) {
- sibling_leaf = CPUID4_INFO_IDX(i, index);
- cpu_set(cpu, sibling_leaf->shared_cpu_map);
+ sibling_leaf =
+ CPUID4_INFO_IDX(i, index);
+ cpumask_set_cpu(cpu, to_cpumask(
+ sibling_leaf->shared_cpu_map));
}
}
}
int sibling;
this_leaf = CPUID4_INFO_IDX(cpu, index);
- for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
+ for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) {
sibling_leaf = CPUID4_INFO_IDX(sibling, index);
- cpu_clear(cpu, sibling_leaf->shared_cpu_map);
+ cpumask_clear_cpu(cpu,
+ to_cpumask(sibling_leaf->shared_cpu_map));
}
}
#else
int n = 0;
if (len > 1) {
- cpumask_t *mask = &this_leaf->shared_cpu_map;
+ const struct cpumask *mask;
+ mask = to_cpumask(this_leaf->shared_cpu_map);
n = type?
cpulist_scnprintf(buf, len-2, mask) :
cpumask_scnprintf(buf, len-2, mask);
static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
{
- int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+ const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
+ int node = cpu_to_node(cpumask_first(mask));
struct pci_dev *dev = NULL;
ssize_t ret = 0;
int i;
store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
size_t count)
{
- int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
+ const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
+ int node = cpu_to_node(cpumask_first(mask));
struct pci_dev *dev = NULL;
unsigned int ret, index, val;
return -ENOMEM;
}
- static cpumask_t cache_dev_map = CPU_MASK_NONE;
+ static DECLARE_BITMAP(cache_dev_map, NR_CPUS);
/* Add/Remove cache interface for CPU device */
static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
}
kobject_uevent(&(this_object->kobj), KOBJ_ADD);
}
- cpu_set(cpu, cache_dev_map);
+ cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
return 0;
if (per_cpu(cpuid4_info, cpu) == NULL)
return;
- if (!cpu_isset(cpu, cache_dev_map))
+ if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
return;
- cpu_clear(cpu, cache_dev_map);
+ cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map));
for (i = 0; i < num_cache_leaves; i++)
kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/ftrace.h>
+ #include <asm/percpu.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
/* %rsp:at FRAMEEND */
.macro FIXUP_TOP_OF_STACK tmp offset=0
- movq %gs:pda_oldrsp,\tmp
+ movq PER_CPU_VAR(old_rsp),\tmp
movq \tmp,RSP+\offset(%rsp)
movq $__USER_DS,SS+\offset(%rsp)
movq $__USER_CS,CS+\offset(%rsp)
.macro RESTORE_TOP_OF_STACK tmp offset=0
movq RSP+\offset(%rsp),\tmp
- movq \tmp,%gs:pda_oldrsp
+ movq \tmp,PER_CPU_VAR(old_rsp)
movq EFLAGS+\offset(%rsp),\tmp
movq \tmp,R11+\offset(%rsp)
.endm
je 1f
SWAPGS
/*
- * irqcount is used to check if a CPU is already on an interrupt stack
+ * irq_count is used to check if a CPU is already on an interrupt stack
* or not. While this is essentially redundant with preempt_count it is
* a little cheaper to use a separate counter in the PDA (short of
* moving irq_enter into assembly, which would be too much work)
*/
- 1: incl %gs:pda_irqcount
+ 1: incl PER_CPU_VAR(irq_count)
jne 2f
popq_cfi %rax /* move return address... */
- mov %gs:pda_irqstackptr,%rsp
+ mov PER_CPU_VAR(irq_stack_ptr),%rsp
EMPTY_FRAME 0
+ pushq_cfi %rbp /* backlink for unwinder */
pushq_cfi %rax /* ... to the new stack */
/*
* We entered an interrupt context - irqs are off:
ENTRY(system_call)
CFI_STARTPROC simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,PDA_STACKOFFSET
+ CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
*/
ENTRY(system_call_after_swapgs)
- movq %rsp,%gs:pda_oldrsp
- movq %gs:pda_kernelstack,%rsp
+ movq %rsp,PER_CPU_VAR(old_rsp)
+ movq PER_CPU_VAR(kernel_stack),%rsp
/*
* No need to follow this irqs off/on section - it's straight
* and short:
CFI_REGISTER rip,rcx
RESTORE_ARGS 0,-ARG_SKIP,1
/*CFI_REGISTER rflags,r11*/
- movq %gs:pda_oldrsp, %rsp
+ movq PER_CPU_VAR(old_rsp), %rsp
USERGS_SYSRET64
CFI_RESTORE_STATE
XCPT_FRAME
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
- /* 0(%rsp): oldrsp-ARGOFFSET */
+ /* 0(%rsp): old_rsp-ARGOFFSET */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
leaveq
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
#endif
+ #ifdef CONFIG_X86_UV
apicinterrupt UV_BAU_MESSAGE \
uv_bau_message_intr1 uv_bau_message_interrupt
+ #endif
apicinterrupt LOCAL_TIMER_VECTOR \
apic_timer_interrupt smp_apic_timer_interrupt
TRACE_IRQS_OFF
movq %rsp,%rdi /* pt_regs pointer */
xorl %esi,%esi /* no error code */
- movq %gs:pda_data_offset, %rbp
- subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ PER_CPU(init_tss, %rbp)
+ subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
call \do_sym
- addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
END(\sym)
CFI_STARTPROC
pushf
CFI_ADJUST_CFA_OFFSET 8
- DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
+ DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
SWAPGS
gs_change:
movl %edi,%gs
CFI_REL_OFFSET rbp,0
mov %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- incl %gs:pda_irqcount
- cmove %gs:pda_irqstackptr,%rsp
+ incl PER_CPU_VAR(irq_count)
+ cmove PER_CPU_VAR(irq_stack_ptr),%rsp
push %rbp # backlink for old unwinder
call __do_softirq
leaveq
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
ret
CFI_ENDPROC
END(call_softirq)
movq %rdi, %rsp # we don't return, adjust the stack frame
CFI_ENDPROC
DEFAULT_FRAME
- 11: incl %gs:pda_irqcount
+ 11: incl PER_CPU_VAR(irq_count)
movq %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- cmovzq %gs:pda_irqstackptr,%rsp
+ cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
pushq %rbp # backlink for old unwinder
call xen_evtchn_do_upcall
popq %rsp
CFI_DEF_CFA_REGISTER rsp
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
jmp error_exit
CFI_ENDPROC
END(do_hypervisor_callback)
#include <asm/idle.h>
#include <asm/io.h>
#include <asm/smp.h>
+ #include <asm/cpu.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/acpi.h>
int nr_ioapic_registers[MAX_IO_APICS];
/* I/O APIC entries */
- struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+ struct mpc_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
/* MP IRQ source entries */
- struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* # of MP IRQ source entries */
int mp_irq_entries;
if (!cfg->move_in_progress) {
/* it means that domain is not changed */
- if (!cpumask_intersects(&desc->affinity, mask))
+ if (!cpumask_intersects(desc->affinity, mask))
cfg->move_desc_pending = 1;
}
}
static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
- + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
+ + (mp_ioapics[idx].apicaddr & ~PAGE_MASK);
}
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
if (assign_irq_vector(irq, cfg, mask))
return BAD_APICID;
- cpumask_and(&desc->affinity, cfg->domain, mask);
+ cpumask_and(desc->affinity, cfg->domain, mask);
set_extra_move_desc(desc, mask);
- return cpu_mask_to_apicid_and(&desc->affinity, cpu_online_mask);
+ return cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask);
}
static void
int i;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_irqtype == type &&
- (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
- mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
- mp_irqs[i].mp_dstirq == pin)
+ if (mp_irqs[i].irqtype == type &&
+ (mp_irqs[i].dstapic == mp_ioapics[apic].apicid ||
+ mp_irqs[i].dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].dstirq == pin)
return i;
return -1;
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mp_irqtype == type) &&
- (mp_irqs[i].mp_srcbusirq == irq))
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
- return mp_irqs[i].mp_dstirq;
+ return mp_irqs[i].dstirq;
}
return -1;
}
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mp_irqtype == type) &&
- (mp_irqs[i].mp_srcbusirq == irq))
+ (mp_irqs[i].irqtype == type) &&
+ (mp_irqs[i].srcbusirq == irq))
break;
}
if (i < mp_irq_entries) {
int apic;
for(apic = 0; apic < nr_ioapics; apic++) {
- if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic)
return apic;
}
}
return -1;
}
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mp_srcbus;
+ int lbus = mp_irqs[i].srcbus;
for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
- mp_irqs[i].mp_dstapic == MP_APIC_ALL)
+ if (mp_ioapics[apic].apicid == mp_irqs[i].dstapic ||
+ mp_irqs[i].dstapic == MP_APIC_ALL)
break;
if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].mp_irqtype &&
+ !mp_irqs[i].irqtype &&
(bus == lbus) &&
- (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
+ (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
- if (pin == (mp_irqs[i].mp_srcbusirq & 3))
+ if (pin == (mp_irqs[i].srcbusirq & 3))
return irq;
/*
* Use the first all-but-pin matching entry as a
* EISA conforming in the MP table, that means its trigger type must
* be read in from the ELCR */
- #define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mp_srcbusirq))
+ #define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
/* PCI interrupts are always polarity one level triggered,
static int MPBIOS_polarity(int idx)
{
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mp_irqflag & 3)
+ switch (mp_irqs[idx].irqflag & 3)
{
case 0: /* conforms, ie. bus-type dependent polarity */
if (test_bit(bus, mp_bus_not_pci))
static int MPBIOS_trigger(int idx)
{
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
int trigger;
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].irqflag>>2) & 3)
{
case 0: /* conforms, ie. bus-type dependent */
if (test_bit(bus, mp_bus_not_pci))
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
- int bus = mp_irqs[idx].mp_srcbus;
+ int bus = mp_irqs[idx].srcbus;
/*
* Debugging check, we are in big trouble if this message pops up!
*/
- if (mp_irqs[idx].mp_dstirq != pin)
+ if (mp_irqs[idx].dstirq != pin)
printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
if (test_bit(bus, mp_bus_not_pci)) {
- irq = mp_irqs[idx].mp_srcbusirq;
+ irq = mp_irqs[idx].srcbusirq;
} else {
/*
* PCI IRQs are mapped in order
apic_printk(APIC_VERBOSE,KERN_DEBUG
"IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
"IRQ %d Mode:%i Active:%i)\n",
- apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
+ apic, mp_ioapics[apic].apicid, pin, cfg->vector,
irq, trigger, polarity);
- if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+ if (setup_ioapic_entry(mp_ioapics[apic].apicid, irq, &entry,
dest, trigger, polarity, cfg->vector)) {
printk("Failed to setup ioapic entry for ioapic %d, pin %d\n",
- mp_ioapics[apic].mp_apicid, pin);
+ mp_ioapics[apic].apicid, pin);
__clear_irq_vector(irq, cfg);
return;
}
notcon = 1;
apic_printk(APIC_VERBOSE,
KERN_DEBUG " %d-%d",
- mp_ioapics[apic].mp_apicid,
- pin);
+ mp_ioapics[apic].apicid, pin);
} else
apic_printk(APIC_VERBOSE, " %d-%d",
- mp_ioapics[apic].mp_apicid,
- pin);
+ mp_ioapics[apic].apicid, pin);
continue;
}
if (notcon) {
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
- mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
+ mp_ioapics[i].apicid, nr_ioapic_registers[i]);
/*
* We are a bit conservative about what we expect. We have to
spin_unlock_irqrestore(&ioapic_lock, flags);
printk("\n");
- printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type);
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- old_id = mp_ioapics[apic].mp_apicid;
+ old_id = mp_ioapics[apic].apicid;
- if (mp_ioapics[apic].mp_apicid >= get_physical_broadcast()) {
+ if (mp_ioapics[apic].apicid >= get_physical_broadcast()) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
- apic, mp_ioapics[apic].mp_apicid);
+ apic, mp_ioapics[apic].apicid);
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
reg_00.bits.ID);
- mp_ioapics[apic].mp_apicid = reg_00.bits.ID;
+ mp_ioapics[apic].apicid = reg_00.bits.ID;
}
/*
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
if (check_apicid_used(phys_id_present_map,
- mp_ioapics[apic].mp_apicid)) {
+ mp_ioapics[apic].apicid)) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
- apic, mp_ioapics[apic].mp_apicid);
+ apic, mp_ioapics[apic].apicid);
for (i = 0; i < get_physical_broadcast(); i++)
if (!physid_isset(i, phys_id_present_map))
break;
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
i);
physid_set(i, phys_id_present_map);
- mp_ioapics[apic].mp_apicid = i;
+ mp_ioapics[apic].apicid = i;
} else {
physid_mask_t tmp;
- tmp = apicid_to_cpu_present(mp_ioapics[apic].mp_apicid);
+ tmp = apicid_to_cpu_present(mp_ioapics[apic].apicid);
apic_printk(APIC_VERBOSE, "Setting %d in the "
"phys_id_present_map\n",
- mp_ioapics[apic].mp_apicid);
+ mp_ioapics[apic].apicid);
physids_or(phys_id_present_map, phys_id_present_map, tmp);
}
* We need to adjust the IRQ routing table
* if the ID changed.
*/
- if (old_id != mp_ioapics[apic].mp_apicid)
+ if (old_id != mp_ioapics[apic].apicid)
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_dstapic == old_id)
- mp_irqs[i].mp_dstapic
- = mp_ioapics[apic].mp_apicid;
+ if (mp_irqs[i].dstapic == old_id)
+ mp_irqs[i].dstapic
+ = mp_ioapics[apic].apicid;
/*
* Read the right value from the MPC table and
*/
apic_printk(APIC_VERBOSE, KERN_INFO
"...changing IO-APIC physical APIC ID to %d ...",
- mp_ioapics[apic].mp_apicid);
+ mp_ioapics[apic].apicid);
- reg_00.bits.ID = mp_ioapics[apic].mp_apicid;
+ reg_00.bits.ID = mp_ioapics[apic].apicid;
spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0, reg_00.raw);
spin_unlock_irqrestore(&ioapic_lock, flags);
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- if (reg_00.bits.ID != mp_ioapics[apic].mp_apicid)
+ if (reg_00.bits.ID != mp_ioapics[apic].apicid)
printk("could not set ID!\n");
else
apic_printk(APIC_VERBOSE, " ok.\n");
if (cfg->move_in_progress)
send_cleanup_vector(cfg);
- cpumask_copy(&desc->affinity, mask);
+ cpumask_copy(desc->affinity, mask);
}
static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
}
/* everthing is clear. we have right of way */
- migrate_ioapic_irq_desc(desc, &desc->pending_mask);
+ migrate_ioapic_irq_desc(desc, desc->pending_mask);
ret = 0;
desc->status &= ~IRQ_MOVE_PENDING;
- cpumask_clear(&desc->pending_mask);
+ cpumask_clear(desc->pending_mask);
unmask:
unmask_IO_APIC_irq_desc(desc);
continue;
}
- desc->chip->set_affinity(irq, &desc->pending_mask);
+ desc->chip->set_affinity(irq, desc->pending_mask);
spin_unlock_irqrestore(&desc->lock, flags);
}
}
{
if (desc->status & IRQ_LEVEL) {
desc->status |= IRQ_MOVE_PENDING;
- cpumask_copy(&desc->pending_mask, mask);
+ cpumask_copy(desc->pending_mask, mask);
migrate_irq_remapped_level_desc(desc);
return;
}
/* domain has not changed, but affinity did */
me = smp_processor_id();
- if (cpu_isset(me, desc->affinity)) {
+ if (cpumask_test_cpu(me, desc->affinity)) {
*descp = desc = move_irq_desc(desc, me);
/* get the new one */
cfg = desc->chip_data;
vector = ~get_irq_regs()->orig_ax;
me = smp_processor_id();
+
+ if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
*descp = desc = move_irq_desc(desc, me);
/* get the new one */
cfg = desc->chip_data;
#endif
-
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
send_cleanup_vector(cfg);
+ }
}
#else
static inline void irq_complete_move(struct irq_desc **descp) {}
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
+ if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].apicid;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
irq = 0;
spin_lock_irqsave(&vector_lock, flags);
- for (new = irq_want; new < NR_IRQS; new++) {
+ for (new = irq_want; new < nr_irqs; new++) {
if (platform_legacy_irq(new))
continue;
int err;
unsigned dest;
+ if (disable_apic)
+ return -ENXIO;
+
cfg = irq_cfg(irq);
err = assign_irq_vector(irq, cfg, TARGET_CPUS);
if (err)
struct irq_cfg *cfg;
int err;
+ if (disable_apic)
+ return -ENXIO;
+
cfg = irq_cfg(irq);
err = assign_irq_vector(irq, cfg, TARGET_CPUS);
if (!err) {
}
#endif /* CONFIG_HT_IRQ */
- #ifdef CONFIG_X86_64
+ #ifdef CONFIG_X86_UV
/*
* Re-target the irq to the specified CPU and enable the specified MMR located
* on the specified blade to allow the sending of MSIs to the specified CPU.
nr_irqs_gsi = nr;
}
+ #ifdef CONFIG_SPARSE_IRQ
+ int __init arch_probe_nr_irqs(void)
+ {
+ int nr;
+
+ nr = ((8 * nr_cpu_ids) > (32 * nr_ioapics) ?
+ (NR_VECTORS + (8 * nr_cpu_ids)) :
+ (NR_VECTORS + (32 * nr_ioapics)));
+
+ if (nr < nr_irqs && nr > nr_irqs_gsi)
+ nr_irqs = nr;
+
+ return 0;
+ }
+ #endif
+
/* --------------------------------------------------------------------------
ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
return -1;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mp_irqtype == mp_INT &&
- mp_irqs[i].mp_srcbusirq == bus_irq)
+ if (mp_irqs[i].irqtype == mp_INT &&
+ mp_irqs[i].srcbusirq == bus_irq)
break;
if (i >= mp_irq_entries)
return -1;
*/
if (desc->status &
(IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
- mask = &desc->affinity;
+ mask = desc->affinity;
else
mask = TARGET_CPUS;
ioapic_res = ioapic_setup_resources();
for (i = 0; i < nr_ioapics; i++) {
if (smp_found_config) {
- ioapic_phys = mp_ioapics[i].mp_apicaddr;
+ ioapic_phys = mp_ioapics[i].apicaddr;
#ifdef CONFIG_X86_32
if (!ioapic_phys) {
printk(KERN_ERR
}
}
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
- .handler = no_action,
- .mask = CPU_MASK_NONE,
- .name = "cascade",
-};
-
DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
[0 ... IRQ0_VECTOR - 1] = -1,
[IRQ0_VECTOR] = 0,
*/
alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
- /* IPI for invalidation */
- alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
+ /* IPIs for invalidation */
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
/* IPI for generic function call */
alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
#endif
- if (!acpi_ioapic)
- setup_irq(2, &irq2);
-
/* setup after call gates are initialised (usually add in
* the architecture specific gates)
*/
#include <asm/e820.h>
#include <asm/io.h>
#include <asm/setup.h>
+ #include <asm/cpu.h>
void __init pre_intr_init_hook(void)
{
setup_irq(2, &irq2);
}
-void __init pre_setup_arch_hook(void)
+static void voyager_disable_tsc(void)
{
/* Voyagers run their CPUs from independent clocks, so disable
* the TSC code because we can't sync them */
setup_clear_cpu_cap(X86_FEATURE_TSC);
}
+void __init pre_setup_arch_hook(void)
+{
+ voyager_disable_tsc();
+}
+
+void __init pre_time_init_hook(void)
+{
+ voyager_disable_tsc();
+}
+
void __init trap_init_hook(void)
{
}
static void disable_local_vic_irq(unsigned int irq);
static void before_handle_vic_irq(unsigned int irq);
static void after_handle_vic_irq(unsigned int irq);
-static void set_vic_irq_affinity(unsigned int irq, cpumask_t mask);
+static void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask);
static void ack_vic_irq(unsigned int irq);
static void vic_enable_cpi(void);
static void do_boot_cpu(__u8 cpuid);
static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
/* This is for the new dynamic CPU boot code */
-cpumask_t cpu_callin_map = CPU_MASK_NONE;
-cpumask_t cpu_callout_map = CPU_MASK_NONE;
/* The per processor IRQ masks (these are usually kept in sync) */
static __u16 vic_irq_mask[NR_CPUS] __cacheline_aligned;
cpus_addr(phys_cpu_present_map)[0] |=
voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK +
3) << 24;
- cpu_possible_map = phys_cpu_present_map;
+ init_cpu_possible(&phys_cpu_present_map);
printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n",
cpus_addr(phys_cpu_present_map)[0]);
/* Here we set up the VIC to enable SMP */
VOYAGER_SUS_IN_CONTROL_PORT);
current_thread_info()->cpu = boot_cpu_id;
- x86_write_percpu(cpu_number, boot_cpu_id);
+ percpu_write(cpu_number, boot_cpu_id);
}
/*
/* init_tasks (in sched.c) is indexed logically */
stack_start.sp = (void *)idle->thread.sp;
- init_gdt(cpu);
per_cpu(current_task, cpu) = idle;
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
irq_ctx_init(cpu);
* change the mask and then do an interrupt enable CPI to re-enable on
* the selected processors */
-void set_vic_irq_affinity(unsigned int irq, cpumask_t mask)
+void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask)
{
/* Only extended processors handle interrupts */
unsigned long real_mask;
unsigned long irq_mask = 1 << irq;
int cpu;
- real_mask = cpus_addr(mask)[0] & voyager_extended_vic_processors;
+ real_mask = cpus_addr(*mask)[0] & voyager_extended_vic_processors;
- if (cpus_addr(mask)[0] == 0)
+ if (cpus_addr(*mask)[0] == 0)
/* can't have no CPUs to accept the interrupt -- extremely
* bad things will happen */
return;
static void __cpuinit voyager_smp_prepare_boot_cpu(void)
{
- init_gdt(smp_processor_id());
- switch_to_new_gdt();
+ int cpu = smp_processor_id();
+ switch_to_new_gdt(cpu);
- cpu_online_map = cpumask_of_cpu(smp_processor_id());
- cpu_callout_map = cpumask_of_cpu(smp_processor_id());
- cpu_callin_map = CPU_MASK_NONE;
- cpu_present_map = cpumask_of_cpu(smp_processor_id());
+ cpu_set(cpu, cpu_online_map);
+ cpu_set(cpu, cpu_callout_map);
+ cpu_set(cpu, cpu_possible_map);
+ cpu_set(cpu, cpu_present_map);
+
}
static int __cpuinit voyager_cpu_up(unsigned int cpu)
void __init smp_setup_processor_id(void)
{
current_thread_info()->cpu = hard_smp_processor_id();
- x86_write_percpu(cpu_number, hard_smp_processor_id());
}
-static void voyager_send_call_func(cpumask_t callmask)
+static void voyager_send_call_func(const struct cpumask *callmask)
{
- __u32 mask = cpus_addr(callmask)[0] & ~(1 << smp_processor_id());
+ __u32 mask = cpus_addr(*callmask)[0] & ~(1 << smp_processor_id());
send_CPI(mask, VIC_CALL_FUNCTION_CPI);
}
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
+ #include <linux/magic.h>
#include <asm/system.h>
#include <asm/desc.h>
*
* Opcode checker based on code by Richard Brunner
*/
- static int is_prefetch(struct pt_regs *regs, unsigned long addr,
- unsigned long error_code)
+ static int is_prefetch(struct pt_regs *regs, unsigned long error_code,
+ unsigned long addr)
{
unsigned char *instr;
int scan_more = 1;
}
#ifdef CONFIG_X86_64
- static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
- unsigned long error_code)
+ static noinline void pgtable_bad(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
{
unsigned long flags = oops_begin();
int sig = SIGKILL;
- struct task_struct *tsk;
+ struct task_struct *tsk = current;
printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
- current->comm, address);
+ tsk->comm, address);
dump_pagetable(address);
tsk = current;
tsk->thread.cr2 = address;
}
#endif
+ static noinline void no_context(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+ {
+ struct task_struct *tsk = current;
+ unsigned long *stackend;
+
+ #ifdef CONFIG_X86_64
+ unsigned long flags;
+ int sig;
+ #endif
+
+ /* Are we prepared to handle this kernel fault? */
+ if (fixup_exception(regs))
+ return;
+
+ /*
+ * X86_32
+ * Valid to do another page fault here, because if this fault
+ * had been triggered by is_prefetch fixup_exception would have
+ * handled it.
+ *
+ * X86_64
+ * Hall of shame of CPU/BIOS bugs.
+ */
+ if (is_prefetch(regs, error_code, address))
+ return;
+
+ if (is_errata93(regs, address))
+ return;
+
+ /*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+ #ifdef CONFIG_X86_32
+ bust_spinlocks(1);
+ #else
+ flags = oops_begin();
+ #endif
+
+ show_fault_oops(regs, error_code, address);
+
+ stackend = end_of_stack(tsk);
+ if (*stackend != STACK_END_MAGIC)
+ printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
+ tsk->thread.cr2 = address;
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code;
+
+ #ifdef CONFIG_X86_32
+ die("Oops", regs, error_code);
+ bust_spinlocks(0);
+ do_exit(SIGKILL);
+ #else
+ sig = SIGKILL;
+ if (__die("Oops", regs, error_code))
+ sig = 0;
+ /* Executive summary in case the body of the oops scrolled away */
+ printk(KERN_EMERG "CR2: %016lx\n", address);
+ oops_end(flags, regs, sig);
+ #endif
+ }
+
+ static void __bad_area_nosemaphore(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address,
+ int si_code)
+ {
+ struct task_struct *tsk = current;
+
+ /* User mode accesses just cause a SIGSEGV */
+ if (error_code & PF_USER) {
+ /*
+ * It's possible to have interrupts off here.
+ */
+ local_irq_enable();
+
+ /*
+ * Valid to do another page fault here because this one came
+ * from user space.
+ */
+ if (is_prefetch(regs, error_code, address))
+ return;
+
+ if (is_errata100(regs, address))
+ return;
+
+ if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+ printk_ratelimit()) {
+ printk(
+ "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+ task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+ tsk->comm, task_pid_nr(tsk), address,
+ (void *) regs->ip, (void *) regs->sp, error_code);
+ print_vma_addr(" in ", regs->ip);
+ printk("\n");
+ }
+
+ tsk->thread.cr2 = address;
+ /* Kernel addresses are always protection faults */
+ tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+ tsk->thread.trap_no = 14;
+ force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+ return;
+ }
+
+ if (is_f00f_bug(regs, address))
+ return;
+
+ no_context(regs, error_code, address);
+ }
+
+ static noinline void bad_area_nosemaphore(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+ {
+ __bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
+ }
+
+ static void __bad_area(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address,
+ int si_code)
+ {
+ struct mm_struct *mm = current->mm;
+
+ /*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+ up_read(&mm->mmap_sem);
+
+ __bad_area_nosemaphore(regs, error_code, address, si_code);
+ }
+
+ static noinline void bad_area(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+ {
+ __bad_area(regs, error_code, address, SEGV_MAPERR);
+ }
+
+ static noinline void bad_area_access_error(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+ {
+ __bad_area(regs, error_code, address, SEGV_ACCERR);
+ }
+
+ /* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
+ static void out_of_memory(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+ {
+ /*
+ * We ran out of memory, call the OOM killer, and return the userspace
+ * (which will retry the fault, or kill us if we got oom-killed).
+ */
+ up_read(¤t->mm->mmap_sem);
+ pagefault_out_of_memory();
+ }
+
+ static void do_sigbus(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address)
+ {
+ struct task_struct *tsk = current;
+ struct mm_struct *mm = tsk->mm;
+
+ up_read(&mm->mmap_sem);
+
+ /* Kernel mode? Handle exceptions or die */
+ if (!(error_code & PF_USER))
+ no_context(regs, error_code, address);
+ #ifdef CONFIG_X86_32
+ /* User space => ok to do another page fault */
+ if (is_prefetch(regs, error_code, address))
+ return;
+ #endif
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+ force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
+ }
+
+ static noinline void mm_fault_error(struct pt_regs *regs,
+ unsigned long error_code, unsigned long address, unsigned int fault)
+ {
+ if (fault & VM_FAULT_OOM)
+ out_of_memory(regs, error_code, address);
+ else if (fault & VM_FAULT_SIGBUS)
+ do_sigbus(regs, error_code, address);
+ else
+ BUG();
+ }
+
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
{
if ((error_code & PF_WRITE) && !pte_write(*pte))
* There are no security implications to leaving a stale TLB when
* increasing the permissions on a page.
*/
- static int spurious_fault(unsigned long address,
- unsigned long error_code)
+ static noinline int spurious_fault(unsigned long error_code,
+ unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
*
* This assumes no large pages in there.
*/
- static int vmalloc_fault(unsigned long address)
+ static noinline int vmalloc_fault(unsigned long address)
{
#ifdef CONFIG_X86_32
unsigned long pgd_paddr;
int show_unhandled_signals = 1;
+ static inline int access_error(unsigned long error_code, int write,
+ struct vm_area_struct *vma)
+ {
+ if (write) {
+ /* write, present and write, not present */
+ if (unlikely(!(vma->vm_flags & VM_WRITE)))
+ return 1;
+ } else if (unlikely(error_code & PF_PROT)) {
+ /* read, present */
+ return 1;
+ } else {
+ /* read, not present */
+ if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+ return 1;
+ }
+
+ return 0;
+ }
+
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
#endif
void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
+ unsigned long address;
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
- unsigned long address;
- int write, si_code;
+ int write;
int fault;
- #ifdef CONFIG_X86_64
- unsigned long flags;
- int sig;
- #endif
tsk = current;
mm = tsk->mm;
/* get the address */
address = read_cr2();
- si_code = SEGV_MAPERR;
-
+ if (unlikely(notify_page_fault(regs)))
- return;
if (unlikely(kmmio_fault(regs, address)))
return;
return;
/* Can handle a stale RO->RW TLB */
- if (spurious_fault(address, error_code))
+ if (spurious_fault(error_code, address))
return;
+ /* kprobes don't want to hook the spurious faults. */
+ if (notify_page_fault(regs))
+ return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock.
*/
- goto bad_area_nosemaphore;
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
}
-
+ /* kprobes don't want to hook the spurious faults. */
+ if (notify_page_fault(regs))
+ return;
/*
* It's safe to allow irq's after cr2 has been saved and the
* vmalloc fault has been handled.
#ifdef CONFIG_X86_64
if (unlikely(error_code & PF_RSVD))
- pgtable_bad(address, regs, error_code);
+ pgtable_bad(regs, error_code, address);
#endif
/*
* If we're in an interrupt, have no user context or are running in an
* atomic region then we must not take the fault.
*/
- if (unlikely(in_atomic() || !mm))
- goto bad_area_nosemaphore;
+ if (unlikely(in_atomic() || !mm)) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
+ }
/*
* When running in the kernel we expect faults to occur only to
* source. If this is invalid we can skip the address space check,
* thus avoiding the deadlock.
*/
- if (!down_read_trylock(&mm->mmap_sem)) {
+ if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
if ((error_code & PF_USER) == 0 &&
- !search_exception_tables(regs->ip))
- goto bad_area_nosemaphore;
+ !search_exception_tables(regs->ip)) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
+ }
down_read(&mm->mmap_sem);
}
vma = find_vma(mm, address);
- if (!vma)
- goto bad_area;
- if (vma->vm_start <= address)
+ if (unlikely(!vma)) {
+ bad_area(regs, error_code, address);
+ return;
+ }
+ if (likely(vma->vm_start <= address))
goto good_area;
- if (!(vma->vm_flags & VM_GROWSDOWN))
- goto bad_area;
+ if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
+ bad_area(regs, error_code, address);
+ return;
+ }
if (error_code & PF_USER) {
/*
* Accessing the stack below %sp is always a bug.
* and pusha to work. ("enter $65535,$31" pushes
* 32 pointers and then decrements %sp by 65535.)
*/
- if (address + 65536 + 32 * sizeof(unsigned long) < regs->sp)
- goto bad_area;
+ if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
+ bad_area(regs, error_code, address);
+ return;
+ }
}
- if (expand_stack(vma, address))
- goto bad_area;
- /*
- * Ok, we have a good vm_area for this memory access, so
- * we can handle it..
- */
+ if (unlikely(expand_stack(vma, address))) {
+ bad_area(regs, error_code, address);
+ return;
+ }
+
+ /*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
good_area:
- si_code = SEGV_ACCERR;
- write = 0;
- switch (error_code & (PF_PROT|PF_WRITE)) {
- default: /* 3: write, present */
- /* fall through */
- case PF_WRITE: /* write, not present */
- if (!(vma->vm_flags & VM_WRITE))
- goto bad_area;
- write++;
- break;
- case PF_PROT: /* read, present */
- goto bad_area;
- case 0: /* read, not present */
- if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
- goto bad_area;
+ write = error_code & PF_WRITE;
+ if (unlikely(access_error(error_code, write, vma))) {
+ bad_area_access_error(regs, error_code, address);
+ return;
}
/*
*/
fault = handle_mm_fault(mm, vma, address, write);
if (unlikely(fault & VM_FAULT_ERROR)) {
- if (fault & VM_FAULT_OOM)
- goto out_of_memory;
- else if (fault & VM_FAULT_SIGBUS)
- goto do_sigbus;
- BUG();
+ mm_fault_error(regs, error_code, address, fault);
+ return;
}
if (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
}
#endif
up_read(&mm->mmap_sem);
- return;
-
- /*
- * Something tried to access memory that isn't in our memory map..
- * Fix it, but check if it's kernel or user first..
- */
- bad_area:
- up_read(&mm->mmap_sem);
-
- bad_area_nosemaphore:
- /* User mode accesses just cause a SIGSEGV */
- if (error_code & PF_USER) {
- /*
- * It's possible to have interrupts off here.
- */
- local_irq_enable();
-
- /*
- * Valid to do another page fault here because this one came
- * from user space.
- */
- if (is_prefetch(regs, address, error_code))
- return;
-
- if (is_errata100(regs, address))
- return;
-
- if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
- printk_ratelimit()) {
- printk(
- "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
- task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
- tsk->comm, task_pid_nr(tsk), address,
- (void *) regs->ip, (void *) regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
- printk("\n");
- }
-
- tsk->thread.cr2 = address;
- /* Kernel addresses are always protection faults */
- tsk->thread.error_code = error_code | (address >= TASK_SIZE);
- tsk->thread.trap_no = 14;
- force_sig_info_fault(SIGSEGV, si_code, address, tsk);
- return;
- }
-
- if (is_f00f_bug(regs, address))
- return;
-
- no_context:
- /* Are we prepared to handle this kernel fault? */
- if (fixup_exception(regs))
- return;
-
- /*
- * X86_32
- * Valid to do another page fault here, because if this fault
- * had been triggered by is_prefetch fixup_exception would have
- * handled it.
- *
- * X86_64
- * Hall of shame of CPU/BIOS bugs.
- */
- if (is_prefetch(regs, address, error_code))
- return;
-
- if (is_errata93(regs, address))
- return;
-
- /*
- * Oops. The kernel tried to access some bad page. We'll have to
- * terminate things with extreme prejudice.
- */
- #ifdef CONFIG_X86_32
- bust_spinlocks(1);
- #else
- flags = oops_begin();
- #endif
-
- show_fault_oops(regs, error_code, address);
-
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
-
- #ifdef CONFIG_X86_32
- die("Oops", regs, error_code);
- bust_spinlocks(0);
- do_exit(SIGKILL);
- #else
- sig = SIGKILL;
- if (__die("Oops", regs, error_code))
- sig = 0;
- /* Executive summary in case the body of the oops scrolled away */
- printk(KERN_EMERG "CR2: %016lx\n", address);
- oops_end(flags, regs, sig);
- #endif
-
- out_of_memory:
- /*
- * We ran out of memory, call the OOM killer, and return the userspace
- * (which will retry the fault, or kill us if we got oom-killed).
- */
- up_read(&mm->mmap_sem);
- pagefault_out_of_memory();
- return;
-
- do_sigbus:
- up_read(&mm->mmap_sem);
-
- /* Kernel mode? Handle exceptions or die */
- if (!(error_code & PF_USER))
- goto no_context;
- #ifdef CONFIG_X86_32
- /* User space => ok to do another page fault */
- if (is_prefetch(regs, address, error_code))
- return;
- #endif
- tsk->thread.cr2 = address;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 14;
- force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
}
DEFINE_SPINLOCK(pgd_lock);
paired with xen_mc_issue() */
static inline void xen_mc_batch(void)
{
+ unsigned long flags;
/* need to disable interrupts until this entry is complete */
- local_irq_save(__get_cpu_var(xen_mc_irq_flags));
+ local_irq_save(flags);
+ __get_cpu_var(xen_mc_irq_flags) = flags;
}
static inline struct multicall_space xen_mc_entry(size_t args)
xen_mc_flush();
/* restore flags saved in xen_mc_batch */
- local_irq_restore(x86_read_percpu(xen_mc_irq_flags));
+ local_irq_restore(percpu_read(xen_mc_irq_flags));
}
/* Set up a callback to be called when the current batch is flushed */
config SGI_XP
tristate "Support communication between SGI SSIs"
depends on NET
- depends on (IA64_GENERIC || IA64_SGI_SN2 || IA64_SGI_UV || X86_64) && SMP
+ depends on (IA64_GENERIC || IA64_SGI_SN2 || IA64_SGI_UV || X86_UV) && SMP
select IA64_UNCACHED_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2
select GENERIC_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2
select SGI_GRU if (IA64_GENERIC || IA64_SGI_UV || X86_64) && SMP
config SGI_GRU
tristate "SGI GRU driver"
- depends on (X86_64 || IA64_SGI_UV || IA64_GENERIC) && SMP
+ depends on (X86_UV || IA64_SGI_UV || IA64_GENERIC) && SMP
default n
select MMU_NOTIFIER
---help---
depends on EXPERIMENTAL
depends on BACKLIGHT_CLASS_DEVICE
depends on RFKILL
+ depends on POWER_SUPPLY
default n
---help---
This driver adds support for rfkill and backlight control to Dell
rc = efx->phy_op->init(efx);
if (rc)
return rc;
- efx->phy_op->reconfigure(efx);
-
mutex_lock(&efx->mac_lock);
+ efx->phy_op->reconfigure(efx);
rc = falcon_switch_mac(efx);
mutex_unlock(&efx->mac_lock);
if (rc)
efx->mac_op->reconfigure(efx);
efx->port_initialized = true;
- efx->stats_enabled = true;
+ efx_stats_enable(efx);
return 0;
fail:
if (!efx->port_initialized)
return;
+ efx_stats_disable(efx);
efx->phy_op->fini(efx);
efx->port_initialized = false;
* interrupts across them. */
static int efx_wanted_rx_queues(void)
{
- cpumask_t core_mask;
+ cpumask_var_t core_mask;
int count;
int cpu;
- cpus_clear(core_mask);
+ if (!alloc_cpumask_var(&core_mask, GFP_KERNEL)) {
+ printk(KERN_WARNING
+ "efx.c: allocation failure, irq balancing hobbled\n");
+ return 1;
+ }
+
+ cpumask_clear(core_mask);
count = 0;
for_each_online_cpu(cpu) {
- if (!cpu_isset(cpu, core_mask)) {
+ if (!cpumask_test_cpu(cpu, core_mask)) {
++count;
- cpus_or(core_mask, core_mask,
- topology_core_siblings(cpu));
+ cpumask_or(core_mask, core_mask,
+ topology_core_cpumask(cpu));
}
}
+ free_cpumask_var(core_mask);
return count;
}
return 0;
}
+void efx_stats_disable(struct efx_nic *efx)
+{
+ spin_lock(&efx->stats_lock);
+ ++efx->stats_disable_count;
+ spin_unlock(&efx->stats_lock);
+}
+
+void efx_stats_enable(struct efx_nic *efx)
+{
+ spin_lock(&efx->stats_lock);
+ --efx->stats_disable_count;
+ spin_unlock(&efx->stats_lock);
+}
+
/* Context: process, dev_base_lock or RTNL held, non-blocking. */
static struct net_device_stats *efx_net_stats(struct net_device *net_dev)
{
struct net_device_stats *stats = &net_dev->stats;
/* Update stats if possible, but do not wait if another thread
- * is updating them (or resetting the NIC); slightly stale
- * stats are acceptable.
+ * is updating them or if MAC stats fetches are temporarily
+ * disabled; slightly stale stats are acceptable.
*/
if (!spin_trylock(&efx->stats_lock))
return stats;
- if (efx->stats_enabled) {
+ if (!efx->stats_disable_count) {
efx->mac_op->update_stats(efx);
falcon_update_nic_stats(efx);
}
/* Tears down the entire software state and most of the hardware state
* before reset. */
-void efx_reset_down(struct efx_nic *efx, struct ethtool_cmd *ecmd)
+void efx_reset_down(struct efx_nic *efx, enum reset_type method,
+ struct ethtool_cmd *ecmd)
{
EFX_ASSERT_RESET_SERIALISED(efx);
- /* The net_dev->get_stats handler is quite slow, and will fail
- * if a fetch is pending over reset. Serialise against it. */
- spin_lock(&efx->stats_lock);
- efx->stats_enabled = false;
- spin_unlock(&efx->stats_lock);
-
+ efx_stats_disable(efx);
efx_stop_all(efx);
mutex_lock(&efx->mac_lock);
mutex_lock(&efx->spi_lock);
efx->phy_op->get_settings(efx, ecmd);
efx_fini_channels(efx);
+ if (efx->port_initialized && method != RESET_TYPE_INVISIBLE)
+ efx->phy_op->fini(efx);
}
/* This function will always ensure that the locks acquired in
* that we were unable to reinitialise the hardware, and the
* driver should be disabled. If ok is false, then the rx and tx
* engines are not restarted, pending a RESET_DISABLE. */
-int efx_reset_up(struct efx_nic *efx, struct ethtool_cmd *ecmd, bool ok)
+int efx_reset_up(struct efx_nic *efx, enum reset_type method,
+ struct ethtool_cmd *ecmd, bool ok)
{
int rc;
ok = false;
}
+ if (efx->port_initialized && method != RESET_TYPE_INVISIBLE) {
+ if (ok) {
+ rc = efx->phy_op->init(efx);
+ if (rc)
+ ok = false;
+ } else
+ efx->port_initialized = false;
+ }
+
if (ok) {
efx_init_channels(efx);
if (ok) {
efx_start_all(efx);
- efx->stats_enabled = true;
+ efx_stats_enable(efx);
}
return rc;
}
EFX_INFO(efx, "resetting (%d)\n", method);
- efx_reset_down(efx, &ecmd);
+ efx_reset_down(efx, method, &ecmd);
rc = falcon_reset_hw(efx, method);
if (rc) {
/* Leave device stopped if necessary */
if (method == RESET_TYPE_DISABLE) {
- efx_reset_up(efx, &ecmd, false);
+ efx_reset_up(efx, method, &ecmd, false);
rc = -EIO;
} else {
- rc = efx_reset_up(efx, &ecmd, true);
+ rc = efx_reset_up(efx, method, &ecmd, true);
}
out_disable:
efx->rx_checksum_enabled = true;
spin_lock_init(&efx->netif_stop_lock);
spin_lock_init(&efx->stats_lock);
+ efx->stats_disable_count = 1;
mutex_init(&efx->mac_lock);
efx->mac_op = &efx_dummy_mac_operations;
efx->phy_op = &efx_dummy_phy_operations;
* @utime: time spent in user mode, in &cputime_t units
* @stime: time spent in kernel mode, in &cputime_t units
* @sum_exec_runtime: total time spent on the CPU, in nanoseconds
+ * @lock: lock for fields in this struct
*
* This structure groups together three kinds of CPU time that are
* tracked for threads and thread groups. Most things considering
pid_t pid;
pid_t tgid;
- #ifdef CONFIG_CC_STACKPROTECTOR
/* Canary value for the -fstack-protector gcc feature */
unsigned long stack_canary;
- #endif
+
/*
* pointers to (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
extern void thread_info_cache_init(void);
+ #ifdef CONFIG_DEBUG_STACK_USAGE
+ static inline unsigned long stack_not_used(struct task_struct *p)
+ {
+ unsigned long *n = end_of_stack(p);
+
+ do { /* Skip over canary */
+ n++;
+ } while (!*n);
+
+ return (unsigned long)n - (unsigned long)end_of_stack(p);
+ }
+ #endif
+
/* set thread flags in other task's structures
* - see asm/thread_info.h for TIF_xxxx flags available
*/
#include <linux/proc_fs.h>
#include <linux/blkdev.h>
#include <trace/sched.h>
+ #include <linux/magic.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
{
struct task_struct *tsk;
struct thread_info *ti;
+ unsigned long *stackend;
+
int err;
prepare_to_copy(orig);
goto out;
setup_thread_stack(tsk, orig);
+ stackend = end_of_stack(tsk);
+ *stackend = STACK_END_MAGIC; /* for overflow detection */
#ifdef CONFIG_CC_STACKPROTECTOR
tsk->stack_canary = get_random_int();
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
+ retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
desc->irq_count = 0;
desc->irqs_unhandled = 0;
#ifdef CONFIG_SMP
- cpumask_setall(&desc->affinity);
+ cpumask_setall(desc->affinity);
+ #ifdef CONFIG_GENERIC_PENDING_IRQ
+ cpumask_clear(desc->pending_mask);
+ #endif
#endif
spin_unlock_irqrestore(&desc->lock, flags);
}
out_unlock:
spin_unlock(&desc->lock);
}
+EXPORT_SYMBOL_GPL(handle_level_irq);
/**
* handle_fasteoi_irq - irq handler for transparent controllers
}
spin_unlock_irqrestore(&desc->lock, flags);
}
+EXPORT_SYMBOL_GPL(__set_irq_handler);
void
set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
old_desc->kstat_irqs = NULL;
}
- static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
+ static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
struct irq_desc *desc, int cpu)
{
memcpy(desc, old_desc, sizeof(struct irq_desc));
+ if (!init_alloc_desc_masks(desc, cpu, false)) {
+ printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
+ "for migration.\n", irq);
+ return false;
+ }
spin_lock_init(&desc->lock);
desc->cpu = cpu;
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+ init_copy_desc_masks(old_desc, desc);
arch_init_copy_chip_data(old_desc, desc, cpu);
+ return true;
}
static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
desc = irq_desc_ptrs[irq];
if (desc && old_desc != desc)
- goto out_unlock;
+ goto out_unlock;
node = cpu_to_node(cpu);
desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
if (!desc) {
- printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
+ printk(KERN_ERR "irq %d: can not get new irq_desc "
+ "for migration.\n", irq);
+ /* still use old one */
+ desc = old_desc;
+ goto out_unlock;
+ }
+ if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) {
/* still use old one */
+ kfree(desc);
desc = old_desc;
goto out_unlock;
}
- init_copy_one_irq_desc(irq, old_desc, desc, cpu);
irq_desc_ptrs[irq] = desc;
+ spin_unlock_irqrestore(&sparse_irq_lock, flags);
/* free the old one */
free_one_irq_desc(old_desc, desc);
+ spin_unlock(&old_desc->lock);
kfree(old_desc);
+ spin_lock(&desc->lock);
+
+ return desc;
out_unlock:
spin_unlock_irqrestore(&sparse_irq_lock, flags);
if (!sched_feat(SYNC_WAKEUPS))
sync = 0;
+ if (!sync) {
+ if (current->se.avg_overlap < sysctl_sched_migration_cost &&
+ p->se.avg_overlap < sysctl_sched_migration_cost)
+ sync = 1;
+ } else {
+ if (current->se.avg_overlap >= sysctl_sched_migration_cost ||
+ p->se.avg_overlap >= sysctl_sched_migration_cost)
+ sync = 0;
+ }
+
#ifdef CONFIG_SMP
if (sched_feat(LB_WAKEUP_UPDATE)) {
struct sched_domain *sd;
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, int sync, void *key)
{
wait_queue_t *curr, *next;
printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
- {
- unsigned long *n = end_of_stack(p);
- while (!*n)
- n++;
- free = (unsigned long)n - (unsigned long)end_of_stack(p);
- }
+ free = stack_not_used(p);
#endif
printk(KERN_CONT "%5lu %5d %6d\n", free,
task_pid_nr(p), task_pid_nr(p->real_parent));