From: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Linux: 2.6.34
Patch-mainline: 2.6.34
This patch contains the differences between 2.6.33 and 2.6.34.
Acked-by: Jeff Mahoney <jeffm@suse.com>
Automatically created from "patches.kernel.org/patch-2.6.34" by xen-port-patches.py
--- 12.2.orig/arch/x86/Kconfig 2012-02-08 12:19:19.000000000 +0100
+++ 12.2/arch/x86/Kconfig 2012-02-08 12:25:31.000000000 +0100
@@ -132,7 +132,7 @@ config SBUS
bool
config NEED_DMA_MAP_STATE
- def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG)
+ def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB)
config NEED_SG_DMA_LENGTH
def_bool y
--- 12.2.orig/arch/x86/ia32/ia32entry-xen.S 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/ia32/ia32entry-xen.S 2011-02-01 15:03:03.000000000 +0100
@@ -444,7 +444,7 @@ ia32_sys_call_table:
.quad quiet_ni_syscall /* old mpx syscall holder */
.quad sys_setpgid
.quad quiet_ni_syscall /* old ulimit syscall holder */
- .quad sys32_olduname
+ .quad sys_olduname
.quad sys_umask /* 60 */
.quad sys_chroot
.quad compat_sys_ustat
@@ -467,7 +467,7 @@ ia32_sys_call_table:
.quad compat_sys_settimeofday
.quad sys_getgroups16 /* 80 */
.quad sys_setgroups16
- .quad sys32_old_select
+ .quad compat_sys_old_select
.quad sys_symlink
.quad sys_lstat
.quad sys_readlink /* 85 */
@@ -494,7 +494,7 @@ ia32_sys_call_table:
.quad compat_sys_newstat
.quad compat_sys_newlstat
.quad compat_sys_newfstat
- .quad sys32_uname
+ .quad sys_uname
.quad stub32_iopl /* 110 */
.quad sys_vhangup
.quad quiet_ni_syscall /* old "idle" system call */
@@ -507,7 +507,7 @@ ia32_sys_call_table:
.quad stub32_sigreturn
.quad stub32_clone /* 120 */
.quad sys_setdomainname
- .quad sys_uname
+ .quad sys_newuname
.quad sys_modify_ldt
.quad compat_sys_adjtimex
.quad sys32_mprotect /* 125 */
--- 12.2.orig/arch/x86/include/asm/i8259.h 2012-06-20 12:12:05.000000000 +0200
+++ 12.2/arch/x86/include/asm/i8259.h 2011-04-13 13:58:56.000000000 +0200
@@ -54,6 +54,7 @@ extern struct irq_chip i8259A_chip;
struct legacy_pic {
int nr_legacy_irqs;
+#ifndef CONFIG_XEN
struct irq_chip *chip;
void (*mask)(unsigned int irq);
void (*unmask)(unsigned int irq);
@@ -61,6 +62,7 @@ struct legacy_pic {
void (*restore_mask)(void);
void (*init)(int auto_eoi);
int (*irq_pending)(unsigned int irq);
+#endif
void (*make_irq)(unsigned int irq);
};
--- 12.2.orig/arch/x86/include/mach-xen/asm/fixmap.h 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/fixmap.h 2011-02-01 15:03:03.000000000 +0100
@@ -82,6 +82,9 @@ enum fixed_addresses {
#endif
FIX_DBGP_BASE,
FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+ FIX_OHCI1394_BASE,
+#endif
#ifdef CONFIG_X86_LOCAL_APIC
FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */
#endif
@@ -125,17 +128,20 @@ enum fixed_addresses {
* 256 temporary boot-time mappings, used by early_ioremap(),
* before ioremap() is functional.
*
- * We round it up to the next 256 pages boundary so that we
- * can have a single pgd entry and a single pte table:
+ * If necessary we round it up to the next 256 pages boundary so
+ * that we can have a single pgd entry and a single pte table:
*/
#define NR_FIX_BTMAPS 64
#define FIX_BTMAPS_SLOTS 4
- FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
- (__end_of_permanent_fixed_addresses & 255),
- FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
- FIX_OHCI1394_BASE,
-#endif
+#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+ FIX_BTMAP_END =
+ (__end_of_permanent_fixed_addresses ^
+ (__end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS - 1)) &
+ -PTRS_PER_PTE
+ ? __end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS -
+ (__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1))
+ : __end_of_permanent_fixed_addresses,
+ FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
#ifdef CONFIG_X86_32
FIX_WP_TEST,
#endif
--- 12.2.orig/arch/x86/include/mach-xen/asm/io.h 2011-02-01 14:44:12.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/io.h 2011-02-01 15:03:03.000000000 +0100
@@ -1,8 +1,42 @@
#ifndef _ASM_X86_IO_H
#define _ASM_X86_IO_H
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ * Linus
+ */
+
+ /*
+ * Bit simplified and optimized by Jan Hubicka
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+ *
+ * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+ * isa_read[wl] and isa_write[wl] fixed
+ * - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ */
+
#define ARCH_HAS_IOREMAP_WC
+#include <linux/string.h>
#include <linux/compiler.h>
#include <asm-generic/int-ll64.h>
#include <asm/page.h>
@@ -84,8 +118,6 @@ static inline void writeq(__u64 val, vol
#define readq readq
#define writeq writeq
-#define native_io_delay xen_io_delay
-
/**
* virt_to_phys - map virtual addresses to physical
* @address: address to remap
@@ -181,11 +213,110 @@ static inline void __iomem *ioremap(reso
extern void iounmap(volatile void __iomem *addr);
-#ifdef CONFIG_X86_32
-# include "../../asm/io_32.h"
-#else
-# include "../../asm/io_64.h"
+#ifdef __KERNEL__
+
+#include <asm-generic/iomap.h>
+
+#include <linux/vmalloc.h>
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p) p
+
+static inline void
+memset_io(volatile void __iomem *addr, unsigned char val, size_t count)
+{
+ memset((void __force *)addr, val, count);
+}
+
+static inline void
+memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count)
+{
+ memcpy(dst, (const void __force *)src, count);
+}
+
+static inline void
+memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
+{
+ memcpy((void __force *)dst, src, count);
+}
+
+/*
+ * Cache management
+ *
+ * This needed for two cases
+ * 1. Out of order aware processors
+ * 2. Accidentally out of order processors (PPro errata #51)
+ */
+
+static inline void flush_write_buffers(void)
+{
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+ asm volatile("lock; addl $0,0(%%esp)": : :"memory");
+#endif
+}
+
+#endif /* __KERNEL__ */
+
+extern void native_io_delay(void);
+
+extern int io_delay_type;
+extern void io_delay_init(void);
+
+static inline void slow_down_io(void)
+{
+ native_io_delay();
+#ifdef REALLY_SLOW_IO
+ native_io_delay();
+ native_io_delay();
+ native_io_delay();
#endif
+}
+
+#define BUILDIO(bwl, bw, type) \
+static inline void out##bwl(unsigned type value, int port) \
+{ \
+ asm volatile("out" #bwl " %" #bw "0, %w1" \
+ : : "a"(value), "Nd"(port)); \
+} \
+ \
+static inline unsigned type in##bwl(int port) \
+{ \
+ unsigned type value; \
+ asm volatile("in" #bwl " %w1, %" #bw "0" \
+ : "=a"(value) : "Nd"(port)); \
+ return value; \
+} \
+ \
+static inline void out##bwl##_p(unsigned type value, int port) \
+{ \
+ out##bwl(value, port); \
+ slow_down_io(); \
+} \
+ \
+static inline unsigned type in##bwl##_p(int port) \
+{ \
+ unsigned type value = in##bwl(port); \
+ slow_down_io(); \
+ return value; \
+} \
+ \
+static inline void outs##bwl(int port, const void *addr, unsigned long count) \
+{ \
+ asm volatile("rep; outs" #bwl \
+ : "+S"(addr), "+c"(count) : "d"(port)); \
+} \
+ \
+static inline void ins##bwl(int port, void *addr, unsigned long count) \
+{ \
+ asm volatile("rep; ins" #bwl \
+ : "+D"(addr), "+c"(count) : "d"(port)); \
+}
+
+BUILDIO(b, b, char)
+BUILDIO(w, w, short)
+BUILDIO(l, , int)
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
@@ -200,8 +331,6 @@ extern void iounmap(volatile void __iome
&& bvec_to_pseudophys(vec1) + (vec1)->bv_len \
== bvec_to_pseudophys(vec2))
-#undef __ISA_IO_base
-
#endif
extern void *xlate_dev_mem_ptr(unsigned long phys);
@@ -223,6 +352,7 @@ extern void __iomem *early_ioremap(resou
extern void __iomem *early_memremap(resource_size_t phys_addr,
unsigned long size);
extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void fixup_early_ioremap(void);
#define IO_SPACE_LIMIT 0xffff
--- 12.2.orig/arch/x86/include/mach-xen/asm/irq_vectors.h 2011-02-15 17:33:45.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/irq_vectors.h 2011-02-15 17:49:16.000000000 +0100
@@ -3,11 +3,9 @@
#define MCE_VECTOR 0x12
+#define IA32_SYSCALL_VECTOR 0x80
#ifdef CONFIG_X86_32
# define SYSCALL_VECTOR 0x80
-# define IA32_SYSCALL_VECTOR 0x80
-#else
-# define IA32_SYSCALL_VECTOR 0x80
#endif
#define RESCHEDULE_VECTOR 0
@@ -57,9 +55,17 @@ static inline int invalid_vm86_irq(int i
* are bound using the provided bind/unbind functions.
*/
#define PIRQ_BASE 0
+/* PHYSDEVOP_pirq_eoi_gmfn restriction: */
+#define PIRQ_MAX(n) ((n) < (1 << (PAGE_SHIFT + 3)) - NR_VECTORS \
+ ? (n) : (1 << (PAGE_SHIFT + 3)) - NR_VECTORS)
+
+#define IO_APIC_VECTOR_LIMIT PIRQ_MAX(32 * MAX_IO_APICS)
-#define CPU_VECTOR_LIMIT ( 8 * NR_CPUS )
-#define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS )
+#ifdef CONFIG_SPARSE_IRQ
+# define CPU_VECTOR_LIMIT PIRQ_MAX(64 * NR_CPUS)
+#else
+# define CPU_VECTOR_LIMIT PIRQ_MAX(32 * NR_CPUS)
+#endif
#if defined(CONFIG_X86_IO_APIC)
# ifdef CONFIG_SPARSE_IRQ
--- 12.2.orig/arch/x86/include/mach-xen/asm/pci.h 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/pci.h 2011-02-01 15:03:03.000000000 +0100
@@ -48,8 +48,15 @@ static inline int pci_proc_domain(struct
#ifdef CONFIG_PCI
extern unsigned int pcibios_assign_all_busses(void);
+extern int pci_legacy_init(void);
+# ifdef CONFIG_ACPI
+# define x86_default_pci_init pci_acpi_init
+# else
+# define x86_default_pci_init pci_legacy_init
+# endif
#else
-#define pcibios_assign_all_busses() 0
+# define pcibios_assign_all_busses() 0
+# define x86_default_pci_init NULL
#endif
#include <asm/hypervisor.h>
@@ -97,41 +104,14 @@ extern void pci_iommu_alloc(void);
#define PCI_DMA_BUS_IS_PHYS 0
-#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG) \
- || defined(CONFIG_SWIOTLB)
-
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \
- dma_addr_t ADDR_NAME;
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \
- __u32 LEN_NAME;
-#define pci_unmap_addr(PTR, ADDR_NAME) \
- ((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
- (((PTR)->ADDR_NAME) = (VAL))
-#define pci_unmap_len(PTR, LEN_NAME) \
- ((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
- (((PTR)->LEN_NAME) = (VAL))
-
-#else
-
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0];
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0];
-#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
- do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
-#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
- do { break; } while (pci_unmap_len(PTR, LEN_NAME))
-
-#endif
-
#endif /* __KERNEL__ */
#ifdef CONFIG_X86_64
#include "../../asm/pci_64.h"
#endif
+void dma32_reserve_bootmem(void);
+
/* implement the pci_ DMA API in terms of the generic device dma_ one */
#include <asm-generic/pci-dma-compat.h>
--- 12.2.orig/arch/x86/include/mach-xen/asm/pgalloc.h 2011-02-01 14:50:44.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/pgalloc.h 2011-02-01 15:03:03.000000000 +0100
@@ -27,6 +27,11 @@ pmd_t *early_get_pmd(unsigned long va);
#endif
/*
+ * Flags to use when allocating a user page table page.
+ */
+extern gfp_t __userpte_alloc_gfp;
+
+/*
* Allocate and free page tables.
*/
extern pgd_t *pgd_alloc(struct mm_struct *);
--- 12.2.orig/arch/x86/include/mach-xen/asm/pgtable_32.h 2011-02-01 14:50:44.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/pgtable_32.h 2011-02-01 15:03:03.000000000 +0100
@@ -18,7 +18,6 @@
#include <linux/threads.h>
#include <linux/bitops.h>
-#include <linux/slab.h>
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/sched.h>
@@ -79,7 +78,7 @@ do { \
* The i386 doesn't have any external MMU info: the kernel page
* tables contain all the necessary information.
*/
-#define update_mmu_cache(vma, address, pte) do { } while (0)
+#define update_mmu_cache(vma, address, ptep) do { } while (0)
void make_lowmem_page_readonly(void *va, unsigned int feature);
void make_lowmem_page_writable(void *va, unsigned int feature);
--- 12.2.orig/arch/x86/include/mach-xen/asm/pgtable_64.h 2011-03-23 09:59:12.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/pgtable_64.h 2011-03-23 10:01:13.000000000 +0100
@@ -131,7 +131,7 @@ static inline int pgd_large(pgd_t pgd) {
#define pte_unmap(pte) /* NOP */
#define pte_unmap_nested(pte) /* NOP */
-#define update_mmu_cache(vma, address, pte) do { } while (0)
+#define update_mmu_cache(vma, address, ptep) do { } while (0)
/* Encode and de-code a swap entry */
#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
--- 12.2.orig/arch/x86/include/mach-xen/asm/smp.h 2011-03-03 16:08:16.000000000 +0100
+++ 12.2/arch/x86/include/mach-xen/asm/smp.h 2011-03-03 16:10:16.000000000 +0100
@@ -138,6 +138,8 @@ int native_cpu_disable(void);
void native_cpu_die(unsigned int cpu);
void native_play_dead(void);
void play_dead_common(void);
+void wbinvd_on_cpu(int cpu);
+int wbinvd_on_all_cpus(void);
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
@@ -165,8 +167,19 @@ static inline int num_booting_cpus(void)
{
return cpumask_weight(cpu_callout_mask);
}
+#elif /* !CONFIG_SMP && */ !defined(CONFIG_XEN)
+#define wbinvd_on_cpu(cpu) wbinvd()
+static inline int wbinvd_on_all_cpus(void)
+{
+ wbinvd();
+ return 0;
+}
#endif /* CONFIG_SMP */
+#ifdef CONFIG_XEN
+int wbinvd_on_all_cpus(void);
+#endif
+
extern unsigned disabled_cpus __cpuinitdata;
#include <asm/smp-processor-id.h>
--- 12.2.orig/arch/x86/kernel/acpi/processor_extcntl_xen.c 2011-01-31 17:56:27.000000000 +0100
+++ 12.2/arch/x86/kernel/acpi/processor_extcntl_xen.c 2011-08-23 13:10:36.000000000 +0200
@@ -190,12 +190,12 @@ static struct processor_extcntl_ops xen_
.hotplug = xen_hotplug_notifier,
};
-void arch_acpi_processor_init_extcntl(const struct processor_extcntl_ops **ops)
+static int __init init_extcntl(void)
{
unsigned int pmbits = (xen_start_info->flags & SIF_PM_MASK) >> 8;
if (!pmbits)
- return;
+ return 0;
if (pmbits & XEN_PROCESSOR_PM_CX)
xen_extcntl_ops.pm_ops[PM_TYPE_IDLE] = xen_cx_notifier;
if (pmbits & XEN_PROCESSOR_PM_PX)
@@ -203,6 +203,8 @@ void arch_acpi_processor_init_extcntl(co
if (pmbits & XEN_PROCESSOR_PM_TX)
xen_extcntl_ops.pm_ops[PM_TYPE_THR] = xen_tx_notifier;
- *ops = &xen_extcntl_ops;
+ processor_extcntl_ops = &xen_extcntl_ops;
+
+ return 0;
}
-EXPORT_SYMBOL(arch_acpi_processor_init_extcntl);
+arch_initcall(init_extcntl);
--- 12.2.orig/arch/x86/kernel/apic/io_apic-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/kernel/apic/io_apic-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -34,6 +34,7 @@
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/jiffies.h> /* time_after() */
+#include <linux/slab.h>
#ifdef CONFIG_ACPI
#include <acpi/acpi_bus.h>
#endif
@@ -61,9 +62,12 @@
#include <xen/evtchn.h>
/* Fake i8259 */
-#define make_8259A_irq(_irq) (io_apic_irqs &= ~(1UL<<(_irq)))
-#define disable_8259A_irq(_irq) ((void)0)
-#define i8259A_irq_pending(_irq) (0)
+static void make_8259A_irq(unsigned int irq) { io_apic_irqs &= ~(1UL<<irq); }
+static const struct legacy_pic xen_legacy_pic = {
+ .nr_legacy_irqs = NR_IRQS_LEGACY,
+ .make_irq = make_8259A_irq
+};
+#define legacy_pic (&xen_legacy_pic)
unsigned long io_apic_irqs;
#endif /* CONFIG_XEN */
@@ -78,9 +82,9 @@ unsigned long io_apic_irqs;
*/
int sis_apic_bug = -1;
-static DEFINE_SPINLOCK(ioapic_lock);
+static DEFINE_RAW_SPINLOCK(ioapic_lock);
#ifndef CONFIG_XEN
-static DEFINE_SPINLOCK(vector_lock);
+static DEFINE_RAW_SPINLOCK(vector_lock);
#endif
/*
@@ -102,12 +106,8 @@ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCE
int mp_irq_entries;
#ifndef CONFIG_XEN
-/* Number of legacy interrupts */
-static int nr_legacy_irqs __read_mostly = NR_IRQS_LEGACY;
/* GSI interrupts */
static int nr_irqs_gsi = NR_IRQS_LEGACY;
-#else
-#define nr_legacy_irqs NR_IRQS_LEGACY
#endif
#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
@@ -152,33 +152,10 @@ static struct irq_pin_list *get_one_free
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
#ifdef CONFIG_SPARSE_IRQ
-static struct irq_cfg irq_cfgx[] = {
+static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY];
#else
-static struct irq_cfg irq_cfgx[NR_IRQS] = {
+static struct irq_cfg irq_cfgx[NR_IRQS];
#endif
- [0] = { .vector = IRQ0_VECTOR, },
- [1] = { .vector = IRQ1_VECTOR, },
- [2] = { .vector = IRQ2_VECTOR, },
- [3] = { .vector = IRQ3_VECTOR, },
- [4] = { .vector = IRQ4_VECTOR, },
- [5] = { .vector = IRQ5_VECTOR, },
- [6] = { .vector = IRQ6_VECTOR, },
- [7] = { .vector = IRQ7_VECTOR, },
- [8] = { .vector = IRQ8_VECTOR, },
- [9] = { .vector = IRQ9_VECTOR, },
- [10] = { .vector = IRQ10_VECTOR, },
- [11] = { .vector = IRQ11_VECTOR, },
- [12] = { .vector = IRQ12_VECTOR, },
- [13] = { .vector = IRQ13_VECTOR, },
- [14] = { .vector = IRQ14_VECTOR, },
- [15] = { .vector = IRQ15_VECTOR, },
-};
-
-void __init io_apic_disable_legacy(void)
-{
- nr_legacy_irqs = 0;
- nr_irqs_gsi = 0;
-}
int __init arch_early_irq_init(void)
{
@@ -188,6 +165,11 @@ int __init arch_early_irq_init(void)
int node;
int i;
+ if (!legacy_pic->nr_legacy_irqs) {
+ nr_irqs_gsi = 0;
+ io_apic_irqs = ~0UL;
+ }
+
cfg = irq_cfgx;
count = ARRAY_SIZE(irq_cfgx);
node= cpu_to_node(boot_cpu_id);
@@ -197,8 +179,14 @@ int __init arch_early_irq_init(void)
desc->chip_data = &cfg[i];
zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
- if (i < nr_legacy_irqs)
- cpumask_setall(cfg[i].domain);
+ /*
+ * For legacy IRQ's, start with assigning irq0 to irq15 to
+ * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
+ */
+ if (i < legacy_pic->nr_legacy_irqs) {
+ cfg[i].vector = IRQ0_VECTOR + i;
+ cpumask_set_cpu(0, cfg[i].domain);
+ }
}
return 0;
@@ -443,7 +431,7 @@ static bool io_apic_level_ack_pending(st
struct irq_pin_list *entry;
unsigned long flags;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
for_each_irq_pin(entry, cfg->irq_2_pin) {
unsigned int reg;
int pin;
@@ -452,11 +440,11 @@ static bool io_apic_level_ack_pending(st
reg = io_apic_read(entry->apic, 0x10 + pin*2);
/* Is the remote IRR bit set? */
if (reg & IO_APIC_REDIR_REMOTE_IRR) {
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return true;
}
}
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return false;
}
@@ -472,10 +460,10 @@ static struct IO_APIC_route_entry ioapic
{
union entry_union eu;
unsigned long flags;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return eu.entry;
}
#endif
@@ -499,9 +487,9 @@ __ioapic_write_entry(int apic, int pin,
void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
{
unsigned long flags;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
__ioapic_write_entry(apic, pin, e);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
#ifndef CONFIG_XEN
@@ -515,10 +503,10 @@ static void ioapic_mask_entry(int apic,
unsigned long flags;
union entry_union eu = { .entry.mask = 1 };
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0x10 + 2*pin, eu.w1);
io_apic_write(apic, 0x11 + 2*pin, eu.w2);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
/*
@@ -645,9 +633,9 @@ static void mask_IO_APIC_irq_desc(struct
BUG_ON(!cfg);
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
__mask_IO_APIC_irq(cfg);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
@@ -655,9 +643,9 @@ static void unmask_IO_APIC_irq_desc(stru
struct irq_cfg *cfg = desc->chip_data;
unsigned long flags;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
__unmask_IO_APIC_irq(cfg);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
static void mask_IO_APIC_irq(unsigned int irq)
@@ -914,7 +902,7 @@ static int __init find_isa_irq_apic(int
*/
static int EISA_ELCR(unsigned int irq)
{
- if (irq < nr_legacy_irqs) {
+ if (irq < legacy_pic->nr_legacy_irqs) {
unsigned int port = 0x4d0 + (irq >> 3);
return (inb(port) >> (irq & 7)) & 1;
}
@@ -1190,12 +1178,12 @@ void lock_vector_lock(void)
/* Used to the online set of cpus does not change
* during assign_irq_vector.
*/
- spin_lock(&vector_lock);
+ raw_spin_lock(&vector_lock);
}
void unlock_vector_lock(void)
{
- spin_unlock(&vector_lock);
+ raw_spin_unlock(&vector_lock);
}
static int
@@ -1212,7 +1200,8 @@ __assign_irq_vector(int irq, struct irq_
* Also, we've got to be careful not to trash gate
* 0x80, because int 0x80 is hm, kind of importantish. ;)
*/
- static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
+ static int current_offset = VECTOR_OFFSET_START % 8;
unsigned int old_vector;
int cpu, err;
cpumask_var_t tmp_mask;
@@ -1248,7 +1237,7 @@ next:
if (vector >= first_system_vector) {
/* If out of vectors on large boxen, must share them. */
offset = (offset + 1) % 8;
- vector = FIRST_DEVICE_VECTOR + offset;
+ vector = FIRST_EXTERNAL_VECTOR + offset;
}
if (unlikely(current_vector == vector))
continue;
@@ -1286,9 +1275,9 @@ int assign_irq_vector(int irq, struct ir
int err;
unsigned long flags;
- spin_lock_irqsave(&vector_lock, flags);
+ raw_spin_lock_irqsave(&vector_lock, flags);
err = __assign_irq_vector(irq, cfg, mask);
- spin_unlock_irqrestore(&vector_lock, flags);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
return err;
}
@@ -1322,14 +1311,27 @@ static void __clear_irq_vector(int irq,
void __setup_vector_irq(int cpu)
{
/* Initialize vector_irq on a new cpu */
- /* This function must be called with vector_lock held */
int irq, vector;
struct irq_cfg *cfg;
struct irq_desc *desc;
+ /*
+ * vector_lock will make sure that we don't run into irq vector
+ * assignments that might be happening on another cpu in parallel,
+ * while we setup our initial vector to irq mappings.
+ */
+ raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_irq_desc(irq, desc) {
cfg = desc->chip_data;
+
+ /*
+ * If it is a legacy IRQ handled by the legacy PIC, this cpu
+ * will be part of the irq_cfg's domain.
+ */
+ if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq))
+ cpumask_set_cpu(cpu, cfg->domain);
+
if (!cpumask_test_cpu(cpu, cfg->domain))
continue;
vector = cfg->vector;
@@ -1345,6 +1347,7 @@ void __setup_vector_irq(int cpu)
if (!cpumask_test_cpu(cpu, cfg->domain))
per_cpu(vector_irq, cpu)[vector] = -1;
}
+ raw_spin_unlock(&vector_lock);
}
static struct irq_chip ioapic_chip;
@@ -1501,6 +1504,16 @@ static void setup_IO_APIC_irq(int apic_i
cfg = desc->chip_data;
+#ifndef CONFIG_XEN
+ /*
+ * For legacy irqs, cfg->domain starts with cpu 0 for legacy
+ * controllers like 8259. Now that IO-APIC can handle this irq, update
+ * the cfg->domain.
+ */
+ if (irq < legacy_pic->nr_legacy_irqs && cpumask_test_cpu(0, cfg->domain))
+ apic->vector_allocation_domain(0, cfg->domain);
+#endif
+
if (assign_irq_vector(irq, cfg, apic->target_cpus()))
return;
@@ -1526,8 +1539,10 @@ static void setup_IO_APIC_irq(int apic_i
}
ioapic_register_intr(irq, desc, trigger);
- if (irq < nr_legacy_irqs)
- disable_8259A_irq(irq);
+#ifndef CONFIG_XEN
+ if (irq < legacy_pic->nr_legacy_irqs)
+ legacy_pic->chip->mask(irq);
+#endif
ioapic_write_entry(apic_id, pin, entry);
}
@@ -1538,7 +1553,7 @@ static struct {
static void __init setup_IO_APIC_irqs(void)
{
- int apic_id = 0, pin, idx, irq;
+ int apic_id, pin, idx, irq;
int notcon = 0;
struct irq_desc *desc;
struct irq_cfg *cfg;
@@ -1546,14 +1561,7 @@ static void __init setup_IO_APIC_irqs(vo
apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
-#ifdef CONFIG_ACPI
- if (!acpi_disabled && acpi_ioapic) {
- apic_id = mp_find_ioapic(0);
- if (apic_id < 0)
- apic_id = 0;
- }
-#endif
-
+ for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
idx = find_irq_entry(apic_id, pin, mp_INT);
if (idx == -1) {
@@ -1575,6 +1583,9 @@ static void __init setup_IO_APIC_irqs(vo
irq = pin_2_irq(idx, apic_id, pin);
+ if ((apic_id > 0) && (irq > 16))
+ continue;
+
#ifdef CONFIG_XEN
if (irq < PIRQ_BASE || irq >= PIRQ_BASE + nr_pirqs)
continue;
@@ -1608,6 +1619,60 @@ static void __init setup_IO_APIC_irqs(vo
" (apicid-pin) not connected\n");
}
+/*
+ * for the gsit that is not in first ioapic
+ * but could not use acpi_register_gsi()
+ * like some special sci in IBM x3330
+ */
+void setup_IO_APIC_irq_extra(u32 gsi)
+{
+ int apic_id = 0, pin, idx, irq;
+ int node = cpu_to_node(boot_cpu_id);
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+
+ /*
+ * Convert 'gsi' to 'ioapic.pin'.
+ */
+ apic_id = mp_find_ioapic(gsi);
+ if (apic_id < 0)
+ return;
+
+ pin = mp_find_ioapic_pin(apic_id, gsi);
+ idx = find_irq_entry(apic_id, pin, mp_INT);
+ if (idx == -1)
+ return;
+
+ irq = pin_2_irq(idx, apic_id, pin);
+#ifdef CONFIG_XEN
+ if (irq < PIRQ_BASE || irq >= PIRQ_BASE + nr_pirqs)
+ return;
+#endif
+#ifdef CONFIG_SPARSE_IRQ
+ desc = irq_to_desc(irq);
+ if (desc)
+ return;
+#endif
+ desc = irq_to_desc_alloc_node(irq, node);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+ return;
+ }
+
+ cfg = desc->chip_data;
+ add_pin_to_irq_node(cfg, node, apic_id, pin);
+
+ if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
+ pr_debug("Pin %d-%d already programmed\n",
+ mp_ioapics[apic_id].apicid, pin);
+ return;
+ }
+ set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
+
+ setup_IO_APIC_irq(apic_id, pin, irq, desc,
+ irq_trigger(idx), irq_polarity(idx));
+}
+
#ifndef CONFIG_XEN
/*
* Set up the timer pin, possibly with the 8259A-master behind.
@@ -1672,14 +1737,14 @@ __apicdebuginit(void) print_IO_APIC(void
for (apic = 0; apic < nr_ioapics; apic++) {
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic, 0);
reg_01.raw = io_apic_read(apic, 1);
if (reg_01.bits.version >= 0x10)
reg_02.raw = io_apic_read(apic, 2);
if (reg_01.bits.version >= 0x20)
reg_03.raw = io_apic_read(apic, 3);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
printk("\n");
printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid);
@@ -1718,7 +1783,7 @@ __apicdebuginit(void) print_IO_APIC(void
printk(KERN_DEBUG ".... IRQ redirection table:\n");
printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol"
- " Stat Dmod Deli Vect: \n");
+ " Stat Dmod Deli Vect:\n");
for (i = 0; i <= reg_01.bits.entries; i++) {
struct IO_APIC_route_entry entry;
@@ -1896,12 +1961,12 @@ __apicdebuginit(void) print_PIC(void)
unsigned int v;
unsigned long flags;
- if (!nr_legacy_irqs)
+ if (!legacy_pic->nr_legacy_irqs)
return;
printk(KERN_DEBUG "\nprinting PIC contents\n");
- spin_lock_irqsave(&i8259A_lock, flags);
+ raw_spin_lock_irqsave(&i8259A_lock, flags);
v = inb(0xa1) << 8 | inb(0x21);
printk(KERN_DEBUG "... PIC IMR: %04x\n", v);
@@ -1915,7 +1980,7 @@ __apicdebuginit(void) print_PIC(void)
outb(0x0a,0xa0);
outb(0x0a,0x20);
- spin_unlock_irqrestore(&i8259A_lock, flags);
+ raw_spin_unlock_irqrestore(&i8259A_lock, flags);
printk(KERN_DEBUG "... PIC ISR: %04x\n", v);
@@ -1977,13 +2042,13 @@ void __init enable_IO_APIC(void)
* The number of IO-APIC IRQ registers (== #pins):
*/
for (apic = 0; apic < nr_ioapics; apic++) {
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_01.raw = io_apic_read(apic, 1);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
nr_ioapic_registers[apic] = reg_01.bits.entries+1;
}
- if (!nr_legacy_irqs)
+ if (!legacy_pic->nr_legacy_irqs)
return;
#ifndef CONFIG_XEN
@@ -2043,7 +2108,7 @@ void disable_IO_APIC(void)
*/
clear_IO_APIC();
- if (!nr_legacy_irqs)
+ if (!legacy_pic->nr_legacy_irqs)
return;
/*
@@ -2122,9 +2187,9 @@ void __init setup_ioapic_ids_from_mpc(vo
for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
/* Read the register 0 value */
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic_id, 0);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
old_id = mp_ioapics[apic_id].apicid;
@@ -2183,16 +2248,16 @@ void __init setup_ioapic_ids_from_mpc(vo
mp_ioapics[apic_id].apicid);
reg_00.bits.ID = mp_ioapics[apic_id].apicid;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic_id, 0, reg_00.raw);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
/*
* Sanity check
*/
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic_id, 0);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
if (reg_00.bits.ID != mp_ioapics[apic_id].apicid)
printk("could not set ID!\n");
else
@@ -2275,15 +2340,15 @@ static unsigned int startup_ioapic_irq(u
unsigned long flags;
struct irq_cfg *cfg;
- spin_lock_irqsave(&ioapic_lock, flags);
- if (irq < nr_legacy_irqs) {
- disable_8259A_irq(irq);
- if (i8259A_irq_pending(irq))
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ if (irq < legacy_pic->nr_legacy_irqs) {
+ legacy_pic->chip->mask(irq);
+ if (legacy_pic->irq_pending(irq))
was_pending = 1;
}
cfg = irq_cfg(irq);
__unmask_IO_APIC_irq(cfg);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return was_pending;
}
@@ -2294,9 +2359,9 @@ static int ioapic_retrigger_irq(unsigned
struct irq_cfg *cfg = irq_cfg(irq);
unsigned long flags;
- spin_lock_irqsave(&vector_lock, flags);
+ raw_spin_lock_irqsave(&vector_lock, flags);
apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
- spin_unlock_irqrestore(&vector_lock, flags);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
return 1;
}
@@ -2389,14 +2454,14 @@ set_ioapic_affinity_irq_desc(struct irq_
irq = desc->irq;
cfg = desc->chip_data;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
ret = set_desc_affinity(desc, mask, &dest);
if (!ret) {
/* Only the high 8 bits are valid. */
dest = SET_APIC_LOGICAL_ID(dest);
__target_IO_APIC_irq(irq, dest, cfg);
}
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return ret;
}
@@ -2566,6 +2631,9 @@ void irq_force_complete_move(int irq)
struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg = desc->chip_data;
+ if (!cfg)
+ return;
+
__irq_complete_move(&desc, cfg->vector);
}
#else
@@ -2631,9 +2699,9 @@ static void eoi_ioapic_irq(struct irq_de
irq = desc->irq;
cfg = desc->chip_data;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
__eoi_ioapic_irq(irq, cfg);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
}
static void ack_apic_level(unsigned int irq)
@@ -2816,8 +2884,8 @@ static inline void init_IO_APIC_traps(vo
* so default to an old-fashioned 8259
* interrupt if we can..
*/
- if (irq < nr_legacy_irqs)
- make_8259A_irq(irq);
+ if (irq < legacy_pic->nr_legacy_irqs)
+ legacy_pic->make_irq(irq);
else
/* Strange. Oh, well.. */
desc->chip = &no_irq_chip;
@@ -2975,7 +3043,7 @@ static inline void __init check_timer(vo
/*
* get/set the timer IRQ vector:
*/
- disable_8259A_irq(0);
+ legacy_pic->chip->mask(0);
assign_irq_vector(0, cfg, apic->target_cpus());
/*
@@ -2988,7 +3056,7 @@ static inline void __init check_timer(vo
* automatically.
*/
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
- init_8259A(1);
+ legacy_pic->init(1);
#ifdef CONFIG_X86_32
{
unsigned int ver;
@@ -3047,7 +3115,7 @@ static inline void __init check_timer(vo
if (timer_irq_works()) {
if (nmi_watchdog == NMI_IO_APIC) {
setup_nmi();
- enable_8259A_irq(0);
+ legacy_pic->chip->unmask(0);
}
if (disable_timer_pin_1 > 0)
clear_IO_APIC_pin(0, pin1);
@@ -3070,14 +3138,14 @@ static inline void __init check_timer(vo
*/
replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
- enable_8259A_irq(0);
+ legacy_pic->chip->unmask(0);
if (timer_irq_works()) {
apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
+ legacy_pic->chip->mask(0);
setup_nmi();
- enable_8259A_irq(0);
+ legacy_pic->chip->unmask(0);
}
goto out;
}
@@ -3085,7 +3153,7 @@ static inline void __init check_timer(vo
* Cleanup, just in case ...
*/
local_irq_disable();
- disable_8259A_irq(0);
+ legacy_pic->chip->mask(0);
clear_IO_APIC_pin(apic2, pin2);
apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
}
@@ -3104,22 +3172,22 @@ static inline void __init check_timer(vo
lapic_register_intr(0, desc);
apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
- enable_8259A_irq(0);
+ legacy_pic->chip->unmask(0);
if (timer_irq_works()) {
apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
goto out;
}
local_irq_disable();
- disable_8259A_irq(0);
+ legacy_pic->chip->mask(0);
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
apic_printk(APIC_QUIET, KERN_INFO
"...trying to set up timer as ExtINT IRQ...\n");
- init_8259A(0);
- make_8259A_irq(0);
+ legacy_pic->init(0);
+ legacy_pic->make_irq(0);
apic_write(APIC_LVT0, APIC_DM_EXTINT);
unlock_ExtINT_logic();
@@ -3168,7 +3236,7 @@ void __init setup_IO_APIC(void)
* calling enable_IO_APIC() is moved to setup_local_APIC for BP
*/
#endif
- io_apic_irqs = nr_legacy_irqs ? ~PIC_IRQS : ~0UL;
+ io_apic_irqs = legacy_pic->nr_legacy_irqs ? ~PIC_IRQS : ~0UL;
apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
/*
@@ -3181,7 +3249,7 @@ void __init setup_IO_APIC(void)
#endif
setup_IO_APIC_irqs();
init_IO_APIC_traps();
- if (nr_legacy_irqs)
+ if (legacy_pic->nr_legacy_irqs)
check_timer();
}
@@ -3239,13 +3307,13 @@ static int ioapic_resume(struct sys_devi
data = container_of(dev, struct sysfs_ioapic_data, dev);
entry = data->entry;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
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);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
ioapic_write_entry(dev->id, i, entry[i]);
@@ -3308,7 +3376,7 @@ unsigned int create_irq_nr(unsigned int
if (irq_want < nr_irqs_gsi)
irq_want = nr_irqs_gsi;
- spin_lock_irqsave(&vector_lock, flags);
+ raw_spin_lock_irqsave(&vector_lock, flags);
for (new = irq_want; new < nr_irqs; new++) {
desc_new = irq_to_desc_alloc_node(new, node);
if (!desc_new) {
@@ -3327,14 +3395,11 @@ unsigned int create_irq_nr(unsigned int
irq = new;
break;
}
- spin_unlock_irqrestore(&vector_lock, flags);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+ if (irq > 0)
+ dynamic_irq_init_keep_chip_data(irq);
- if (irq > 0) {
- dynamic_irq_init(irq);
- /* restore it, in case dynamic_irq_init clear it */
- if (desc_new)
- desc_new->chip_data = cfg_new;
- }
return irq;
}
@@ -3356,20 +3421,13 @@ int create_irq(void)
void destroy_irq(unsigned int irq)
{
unsigned long flags;
- struct irq_cfg *cfg;
- struct irq_desc *desc;
- /* store it, in case dynamic_irq_cleanup clear it */
- desc = irq_to_desc(irq);
- cfg = desc->chip_data;
- dynamic_irq_cleanup(irq);
- /* connect back irq_cfg */
- desc->chip_data = cfg;
+ dynamic_irq_cleanup_keep_chip_data(irq);
free_irte(irq);
- spin_lock_irqsave(&vector_lock, flags);
- __clear_irq_vector(irq, cfg);
- spin_unlock_irqrestore(&vector_lock, flags);
+ raw_spin_lock_irqsave(&vector_lock, flags);
+ __clear_irq_vector(irq, get_irq_chip_data(irq));
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
}
#endif /* !CONFIG_XEN */
@@ -3907,9 +3965,9 @@ int __init io_apic_get_redir_entries (in
union IO_APIC_reg_01 reg_01;
unsigned long flags;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_01.raw = io_apic_read(ioapic, 1);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return reg_01.bits.entries;
}
@@ -4001,7 +4059,7 @@ static int __io_apic_set_pci_routing(str
/*
* IRQs < 16 are already in the irq_2_pin[] map
*/
- if (irq >= nr_legacy_irqs) {
+ if (irq >= legacy_pic->nr_legacy_irqs) {
cfg = desc->chip_data;
if (add_pin_to_irq_node_nopanic(cfg, node, ioapic, pin)) {
printk(KERN_INFO "can not add pin %d for irq %d\n",
@@ -4082,9 +4140,9 @@ int __init io_apic_get_unique_id(int ioa
if (physids_empty(apic_id_map))
apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map);
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(ioapic, 0);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
if (apic_id >= get_physical_broadcast()) {
printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
@@ -4118,10 +4176,10 @@ int __init io_apic_get_unique_id(int ioa
if (reg_00.bits.ID != apic_id) {
reg_00.bits.ID = apic_id;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(ioapic, 0, reg_00.raw);
reg_00.raw = io_apic_read(ioapic, 0);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
/* Sanity check */
if (reg_00.bits.ID != apic_id) {
@@ -4142,9 +4200,9 @@ int __init io_apic_get_version(int ioapi
union IO_APIC_reg_01 reg_01;
unsigned long flags;
- spin_lock_irqsave(&ioapic_lock, flags);
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
reg_01.raw = io_apic_read(ioapic, 1);
- spin_unlock_irqrestore(&ioapic_lock, flags);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return reg_01.bits.version;
}
@@ -4177,27 +4235,23 @@ int acpi_get_override_irq(int bus_irq, i
#ifdef CONFIG_SMP
void __init setup_ioapic_dest(void)
{
- int pin, ioapic = 0, irq, irq_entry;
+ int pin, ioapic, irq, irq_entry;
struct irq_desc *desc;
const struct cpumask *mask;
if (skip_ioapic_setup == 1)
return;
-#ifdef CONFIG_ACPI
- if (!acpi_disabled && acpi_ioapic) {
- ioapic = mp_find_ioapic(0);
- if (ioapic < 0)
- ioapic = 0;
- }
-#endif
-
+ for (ioapic = 0; ioapic < nr_ioapics; ioapic++)
for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
irq_entry = find_irq_entry(ioapic, pin, mp_INT);
if (irq_entry == -1)
continue;
irq = pin_2_irq(irq_entry, ioapic, pin);
+ if ((ioapic > 0) && (irq > 16))
+ continue;
+
desc = irq_to_desc(irq);
/*
@@ -4385,3 +4439,26 @@ void __init mp_register_ioapic(int id, u
nr_ioapics++;
}
+
+#ifdef CONFIG_X86_MRST
+/* Enable IOAPIC early just for system timer */
+void __init pre_init_apic_IRQ0(void)
+{
+ struct irq_cfg *cfg;
+ struct irq_desc *desc;
+
+ printk(KERN_INFO "Early APIC setup for system timer0\n");
+#ifndef CONFIG_SMP
+ phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+#endif
+ desc = irq_to_desc_alloc_node(0, 0);
+
+ setup_local_APIC();
+
+ cfg = irq_cfg(0);
+ add_pin_to_irq_node(cfg, 0, 0, 0);
+ set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
+
+ setup_IO_APIC_irq(0, 0, 0, desc, 0, 0);
+}
+#endif
--- 12.2.orig/arch/x86/kernel/cpu/intel.c 2012-02-08 12:11:42.000000000 +0100
+++ 12.2/arch/x86/kernel/cpu/intel.c 2011-11-17 11:47:25.000000000 +0100
@@ -69,6 +69,9 @@ static void __cpuinit early_init_intel(s
* need the microcode to have already been loaded... so if it is
* not, recommend a BIOS update and disable large pages.
*/
+#ifdef CONFIG_XEN
+ if (cpu_has(c, X86_FEATURE_PSE))
+#endif
if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 &&
c->microcode < 0x20e) {
printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n");
--- 12.2.orig/arch/x86/kernel/cpu/intel_cacheinfo.c 2012-03-12 13:40:29.000000000 +0100
+++ 12.2/arch/x86/kernel/cpu/intel_cacheinfo.c 2011-11-17 11:47:29.000000000 +0100
@@ -299,7 +299,7 @@ struct _cache_attr {
unsigned int);
};
-#ifdef CONFIG_AMD_NB
+#if defined(CONFIG_AMD_NB) && !defined(CONFIG_XEN)
/*
* L3 cache descriptors
--- 12.2.orig/arch/x86/kernel/cpu/mcheck/mce_dom0.c 2011-08-15 11:03:49.000000000 +0200
+++ 12.2/arch/x86/kernel/cpu/mcheck/mce_dom0.c 2011-02-01 15:03:03.000000000 +0100
@@ -1,6 +1,7 @@
#include <linux/init.h>
#include <linux/types.h>
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <xen/interface/xen.h>
#include <xen/evtchn.h>
#include <xen/interface/vcpu.h>
--- 12.2.orig/arch/x86/kernel/cpu/mtrr/main-xen.c 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/arch/x86/kernel/cpu/mtrr/main-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -25,12 +25,12 @@ void generic_get_mtrr(unsigned int reg,
*type = op.u.read_memtype.type;
}
-struct mtrr_ops generic_mtrr_ops = {
+const struct mtrr_ops generic_mtrr_ops = {
.use_intel_if = 1,
.get = generic_get_mtrr,
};
-struct mtrr_ops *mtrr_if = &generic_mtrr_ops;
+const struct mtrr_ops *mtrr_if = &generic_mtrr_ops;
unsigned int num_var_ranges;
unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
--- 12.2.orig/arch/x86/kernel/e820-xen.c 2011-09-23 15:55:57.000000000 +0200
+++ 12.2/arch/x86/kernel/e820-xen.c 2011-09-23 15:56:04.000000000 +0200
@@ -12,17 +12,10 @@
#include <linux/types.h>
#include <linux/init.h>
#include <linux/bootmem.h>
-#include <linux/ioport.h>
-#include <linux/string.h>
-#include <linux/kexec.h>
-#include <linux/module.h>
-#include <linux/mm.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/firmware-map.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/setup.h>
@@ -556,31 +549,55 @@ u64 __init e820_remove_range(u64 start,
int checktype)
{
int i;
+ u64 end;
u64 real_removed_size = 0;
if (size > (ULLONG_MAX - start))
size = ULLONG_MAX - start;
+ end = start + size;
+ printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
+ (unsigned long long) start,
+ (unsigned long long) end);
+ if (checktype)
+ e820_print_type(old_type);
+ printk(KERN_CONT "\n");
+
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
u64 final_start, final_end;
+ u64 ei_end;
if (checktype && ei->type != old_type)
continue;
+
+ ei_end = ei->addr + ei->size;
/* totally covered? */
- if (ei->addr >= start &&
- (ei->addr + ei->size) <= (start + size)) {
+ if (ei->addr >= start && ei_end <= end) {
real_removed_size += ei->size;
memset(ei, 0, sizeof(struct e820entry));
continue;
}
+
+ /* new range is totally covered? */
+ if (ei->addr < start && ei_end > end) {
+ e820_add_region(end, ei_end - end, ei->type);
+ ei->size = start - ei->addr;
+ real_removed_size += size;
+ continue;
+ }
+
/* partially covered */
final_start = max(start, ei->addr);
- final_end = min(start + size, ei->addr + ei->size);
+ final_end = min(end, ei_end);
if (final_start >= final_end)
continue;
real_removed_size += final_end - final_start;
+ /*
+ * left range could be head or tail, so need to update
+ * size at first.
+ */
ei->size -= final_end - final_start;
if (ei->addr < final_start)
continue;
@@ -777,320 +794,44 @@ core_initcall(e820_mark_nvs_memory);
#endif
/*
- * Early reserved memory areas.
- */
-#define MAX_EARLY_RES 32
-
-struct early_res {
- u64 start, end;
- char name[16];
- char overlap_ok;
-};
-static struct early_res early_res[MAX_EARLY_RES] __initdata = {
-#ifndef CONFIG_XEN
- { 0, PAGE_SIZE, "BIOS data page", 1 }, /* BIOS data page */
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE)
- /*
- * But first pinch a few for the stack/trampoline stuff
- * FIXME: Don't need the extra page at 4K, but need to fix
- * trampoline before removing it. (see the GDT stuff)
- */
- { PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 },
-#endif
-#endif
- {}
-};
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
- int i;
- struct early_res *r;
-
- for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
- r = &early_res[i];
- if (end > r->start && start < r->end)
- break;
- }
-
- return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
- int j;
-
- for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
- ;
-
- memmove(&early_res[i], &early_res[i + 1],
- (j - 1 - i) * sizeof(struct early_res));
-
- early_res[j - 1].end = 0;
-}
-
-/*
- * Split any existing ranges that:
- * 1) are marked 'overlap_ok', and
- * 2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range. Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
+ * Find a free area with specified alignment in a specific range.
*/
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
{
int i;
- struct early_res *r;
- u64 lower_start, lower_end;
- u64 upper_start, upper_end;
- char name[16];
- for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
- r = &early_res[i];
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+ u64 addr;
+ u64 ei_start, ei_last;
- /* Continue past non-overlapping ranges */
- if (end <= r->start || start >= r->end)
+ if (ei->type != E820_RAM)
continue;
- /*
- * Leave non-ok overlaps as is; let caller
- * panic "Overlapping early reservations"
- * when it hits this overlap.
- */
- if (!r->overlap_ok)
- return;
-
- /*
- * We have an ok overlap. We will drop it from the early
- * reservation map, and add back in any non-overlapping
- * portions (lower or upper) as separate, overlap_ok,
- * non-overlapping ranges.
- */
-
- /* 1. Note any non-overlapping (lower or upper) ranges. */
- strncpy(name, r->name, sizeof(name) - 1);
-
- lower_start = lower_end = 0;
- upper_start = upper_end = 0;
- if (r->start < start) {
- lower_start = r->start;
- lower_end = start;
- }
- if (r->end > end) {
- upper_start = end;
- upper_end = r->end;
- }
-
- /* 2. Drop the original ok overlapping range */
- drop_range(i);
-
- i--; /* resume for-loop on copied down entry */
-
- /* 3. Add back in any non-overlapping ranges. */
- if (lower_end)
- reserve_early_overlap_ok(lower_start, lower_end, name);
- if (upper_end)
- reserve_early_overlap_ok(upper_start, upper_end, name);
- }
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
- int overlap_ok)
-{
- int i;
- struct early_res *r;
-
- i = find_overlapped_early(start, end);
- if (i >= MAX_EARLY_RES)
- panic("Too many early reservations");
- r = &early_res[i];
- if (r->end)
- panic("Overlapping early reservations "
- "%llx-%llx %s to %llx-%llx %s\n",
- start, end - 1, name?name:"", r->start,
- r->end - 1, r->name);
- r->start = start;
- r->end = end;
- r->overlap_ok = overlap_ok;
- if (name)
- strncpy(r->name, name, sizeof(r->name) - 1);
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first. We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
- drop_overlaps_that_are_ok(start, end);
- __reserve_early(start, end, name, 1);
-}
-
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
-{
- if (start >= end)
- return;
-
- drop_overlaps_that_are_ok(start, end);
- __reserve_early(start, end, name, 0);
-}
-
-void __init free_early(u64 start, u64 end)
-{
- struct early_res *r;
- int i;
-
- i = find_overlapped_early(start, end);
- r = &early_res[i];
- if (i >= MAX_EARLY_RES || r->end != end || r->start != start)
- panic("free_early on not reserved area: %llx-%llx!",
- start, end - 1);
-
- drop_range(i);
-}
-
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
- int i, count;
- u64 final_start, final_end;
-
- count = 0;
- for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++)
- count++;
-
- printk(KERN_INFO "(%d early reservations) ==> bootmem [%010llx - %010llx]\n",
- count, start, end);
- for (i = 0; i < count; i++) {
- struct early_res *r = &early_res[i];
- printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i,
- r->start, r->end, r->name);
- final_start = max(start, r->start);
- final_end = min(end, r->end);
- if (final_start >= final_end) {
- printk(KERN_CONT "\n");
- continue;
- }
- printk(KERN_CONT " ==> [%010llx - %010llx]\n",
- final_start, final_end);
- reserve_bootmem_generic(final_start, final_end - final_start,
- BOOTMEM_DEFAULT);
- }
-}
+ ei_last = ei->addr + ei->size;
+ ei_start = ei->addr;
+ addr = find_early_area(ei_start, ei_last, start, end,
+ size, align);
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
- int i;
- u64 addr = *addrp;
- int changed = 0;
- struct early_res *r;
-again:
- i = find_overlapped_early(addr, addr + size);
- r = &early_res[i];
- if (i < MAX_EARLY_RES && r->end) {
- *addrp = addr = round_up(r->end, align);
- changed = 1;
- goto again;
+ if (addr != -1ULL)
+ return addr;
}
- return changed;
+ return -1ULL;
}
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
{
- int i;
- u64 addr = *addrp, last;
- u64 size = *sizep;
- int changed = 0;
-again:
- last = addr + size;
- for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
- struct early_res *r = &early_res[i];
- if (last > r->start && addr < r->start) {
- size = r->start - addr;
- changed = 1;
- goto again;
- }
- if (last > r->end && addr < r->end) {
- addr = round_up(r->end, align);
- size = last - addr;
- changed = 1;
- goto again;
- }
- if (last <= r->end && addr >= r->start) {
- (*sizep)++;
- return 0;
- }
- }
- if (changed) {
- *addrp = addr;
- *sizep = size;
- }
- return changed;
+ return find_e820_area(start, end, size, align);
}
-/*
- * Find a free area with specified alignment in a specific range.
- */
-u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
+u64 __init get_max_mapped(void)
{
- int i;
+ u64 end = max_pfn_mapped;
- for (i = 0; i < e820.nr_map; i++) {
- struct e820entry *ei = &e820.map[i];
- u64 addr, last;
- u64 ei_last;
+ end <<= PAGE_SHIFT;
- if (ei->type != E820_RAM)
- continue;
- addr = round_up(ei->addr, align);
- ei_last = ei->addr + ei->size;
- if (addr < start)
- addr = round_up(start, align);
- if (addr >= ei_last)
- continue;
- while (bad_addr(&addr, size, align) && addr+size <= ei_last)
- ;
- last = addr + size;
- if (last > ei_last)
- continue;
- if (last > end)
- continue;
- return addr;
- }
- return -1ULL;
+ return end;
}
-
/*
* Find next free range after *start
*/
@@ -1100,25 +841,19 @@ u64 __init find_e820_area_size(u64 start
for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
- u64 addr, last;
- u64 ei_last;
+ u64 addr;
+ u64 ei_start, ei_last;
if (ei->type != E820_RAM)
continue;
- addr = round_up(ei->addr, align);
+
ei_last = ei->addr + ei->size;
- if (addr < start)
- addr = round_up(start, align);
- if (addr >= ei_last)
- continue;
- *sizep = ei_last - addr;
- while (bad_addr_size(&addr, sizep, align) &&
- addr + *sizep <= ei_last)
- ;
- last = addr + *sizep;
- if (last > ei_last)
- continue;
- return addr;
+ ei_start = ei->addr;
+ addr = find_early_area_size(ei_start, ei_last, start,
+ sizep, align);
+
+ if (addr != -1ULL)
+ return addr;
}
return -1ULL;
@@ -1548,6 +1283,8 @@ void __init e820_reserve_resources_late(
end = MAX_RESOURCE_SIZE;
if (start >= end)
continue;
+ printk(KERN_DEBUG "reserve RAM buffer: %016llx - %016llx ",
+ start, end);
reserve_region_with_split(&iomem_resource, start, end,
"RAM buffer");
}
--- 12.2.orig/arch/x86/kernel/head32-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/kernel/head32-xen.c 2011-05-09 11:41:42.000000000 +0200
@@ -6,13 +6,12 @@
*/
#include <linux/init.h>
-#include <linux/spinlock.h>
#include <linux/start_kernel.h>
+#include <linux/mm.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/e820.h>
-#include <asm/pgtable.h>
#include <asm/trampoline.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
@@ -48,15 +47,26 @@ void __init i386_start_kernel(void)
BUG_ON(pte_index(hypervisor_virt_start));
#endif
+#ifdef CONFIG_X86_TRAMPOLINE
+ /*
+ * But first pinch a few for the stack/trampoline stuff
+ * FIXME: Don't need the extra page at 4K, but need to fix
+ * trampoline before removing it. (see the GDT stuff)
+ */
+ reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE,
+ "EX TRAMPOLINE");
+#endif
+
reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
#ifndef CONFIG_XEN
#ifdef CONFIG_BLK_DEV_INITRD
/* Reserve INITRD */
if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+ /* Assume only end is not page aligned */
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
- u64 ramdisk_end = ramdisk_image + ramdisk_size;
+ u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
}
#endif
--- 12.2.orig/arch/x86/kernel/head_32-xen.S 2011-08-09 11:03:50.000000000 +0200
+++ 12.2/arch/x86/kernel/head_32-xen.S 2011-08-09 11:07:43.000000000 +0200
@@ -66,8 +66,8 @@ ENTRY(startup_32)
* The linker can't handle this by relocation. Manually set
* base address in stack canary segment descriptor.
*/
- movl $per_cpu__gdt_page,%eax
- movl $per_cpu__stack_canary,%ecx
+ movl $gdt_page,%eax
+ movl $stack_canary,%ecx
movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
shrl $16, %ecx
movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
@@ -78,7 +78,7 @@ ENTRY(startup_32)
# need to be preserved.
movl XEN_START_mfn_list(%esi), %ebx
- movl $(per_cpu__gdt_page - __PAGE_OFFSET), %eax
+ movl $(gdt_page - __PAGE_OFFSET), %eax
shrl $PAGE_SHIFT, %eax
movl (%ebx,%eax,4), %ecx
pushl %ecx # frame number for set_gdt below
@@ -88,7 +88,7 @@ ENTRY(startup_32)
shldl $PAGE_SHIFT, %ecx, %edx
shll $PAGE_SHIFT, %ecx
orl $_PAGE_PRESENT|_PAGE_ACCESSED|_PAGE_DIRTY, %ecx
- movl $per_cpu__gdt_page, %ebx
+ movl $gdt_page, %ebx
movl $__HYPERVISOR_update_va_mapping, %eax
int $0x82
--- 12.2.orig/arch/x86/kernel/ldt-xen.c 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/arch/x86/kernel/ldt-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -7,6 +7,7 @@
*/
#include <linux/errno.h>
+#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/mm.h>
--- 12.2.orig/arch/x86/kernel/mpparse-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/kernel/mpparse-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -691,7 +691,7 @@ static void __init smp_reserve_memory(st
{
unsigned long size = get_mpc_size(mpf->physptr);
- reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+ reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
}
#endif
@@ -724,7 +724,7 @@ static int __init smp_scan_config(unsign
mpf, (u64)virt_to_phys(mpf));
mem = virt_to_phys(mpf);
- reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf");
+ reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
if (mpf->physptr)
smp_reserve_memory(mpf);
#else
--- 12.2.orig/arch/x86/kernel/pci-dma-xen.c 2012-04-04 14:31:34.000000000 +0200
+++ 12.2/arch/x86/kernel/pci-dma-xen.c 2012-04-04 14:10:44.000000000 +0200
@@ -1,6 +1,7 @@
#include <linux/dma-mapping.h>
#include <linux/dma-debug.h>
#include <linux/bootmem.h>
+#include <linux/gfp.h>
#include <linux/pci.h>
#include <linux/kmemleak.h>
@@ -35,7 +36,7 @@ int iommu_detected __read_mostly = 0;
* This variable becomes 1 if iommu=pt is passed on the kernel command line.
* If this variable is 1, IOMMU implementations do no DMA translation for
* devices and allow every device to access to whole physical memory. This is
- * useful if a user want to use an IOMMU only for KVM device assignment to
+ * useful if a user wants to use an IOMMU only for KVM device assignment to
* guests and not for driver dma translation.
*/
int iommu_pass_through __read_mostly;
@@ -63,7 +64,7 @@ int dma_set_mask(struct device *dev, u64
}
EXPORT_SYMBOL(dma_set_mask);
-#if defined(CONFIG_X86_64) && !defined(CONFIG_XEN)
+#if defined(CONFIG_X86_64) && !defined(CONFIG_NUMA) && !defined(CONFIG_XEN)
static __initdata void *dma32_bootmem_ptr;
static unsigned long dma32_bootmem_size __initdata = (128ULL<<20);
@@ -114,6 +115,14 @@ static void __init dma32_free_bootmem(vo
dma32_bootmem_ptr = NULL;
dma32_bootmem_size = 0;
}
+#else
+void __init dma32_reserve_bootmem(void)
+{
+}
+static void __init dma32_free_bootmem(void)
+{
+}
+
#endif
static struct dma_map_ops swiotlb_dma_ops = {
@@ -135,10 +144,9 @@ static struct dma_map_ops swiotlb_dma_op
void __init pci_iommu_alloc(void)
{
-#if defined(CONFIG_X86_64) && !defined(CONFIG_XEN)
/* free the range so iommu could get some range less than 4G */
dma32_free_bootmem();
-#endif
+
if (pci_swiotlb_detect())
goto out;
--- 12.2.orig/arch/x86/kernel/process-xen.c 2011-03-03 16:09:35.000000000 +0100
+++ 12.2/arch/x86/kernel/process-xen.c 2011-03-03 16:10:10.000000000 +0100
@@ -94,6 +94,13 @@ void exit_thread(void)
}
}
+void show_regs(struct pt_regs *regs)
+{
+ show_registers(regs);
+ show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs),
+ regs->bp);
+}
+
void show_regs_common(void)
{
const char *board, *product;
@@ -474,21 +481,39 @@ static int __cpuinit mwait_usable(const
}
/*
- * Check for AMD CPUs, which have potentially C1E support
+ * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e.
+ * For more information see
+ * - Erratum #400 for NPT family 0xf and family 0x10 CPUs
+ * - Erratum #365 for family 0x11 (not affected because C1e not in use)
*/
static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
{
+ u64 val;
if (c->x86_vendor != X86_VENDOR_AMD)
- return 0;
-
- if (c->x86 < 0x0F)
- return 0;
+ goto no_c1e_idle;
/* Family 0x0f models < rev F do not have C1E */
- if (c->x86 == 0x0f && c->x86_model < 0x40)
- return 0;
+ if (c->x86 == 0x0F && c->x86_model >= 0x40)
+ return 1;
- return 1;
+ if (c->x86 == 0x10) {
+ /*
+ * check OSVW bit for CPUs that are not affected
+ * by erratum #400
+ */
+ if (cpu_has(c, X86_FEATURE_OSVW)) {
+ rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
+ if (val >= 2) {
+ rdmsrl(MSR_AMD64_OSVW_STATUS, val);
+ if (!(val & BIT(1)))
+ goto no_c1e_idle;
+ }
+ }
+ return 1;
+ }
+
+no_c1e_idle:
+ return 0;
}
static cpumask_var_t c1e_mask;
@@ -557,7 +582,7 @@ void __cpuinit select_idle_routine(const
#ifndef CONFIG_XEN
#ifdef CONFIG_SMP
if (pm_idle == poll_idle && smp_num_siblings > 1) {
- printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
+ printk_once(KERN_WARNING "WARNING: polling idle and HT enabled,"
" performance may degrade.\n");
}
#endif
--- 12.2.orig/arch/x86/kernel/process_32-xen.c 2012-02-29 14:16:52.000000000 +0100
+++ 12.2/arch/x86/kernel/process_32-xen.c 2012-02-29 14:17:47.000000000 +0100
@@ -177,12 +177,6 @@ void __show_regs(struct pt_regs *regs, i
d6, d7);
}
-void show_regs(struct pt_regs *regs)
-{
- show_registers(regs);
- show_trace(NULL, regs, ®s->sp, regs->bp);
-}
-
void release_thread(struct task_struct *dead_task)
{
BUG_ON(dead_task->mm);
--- 12.2.orig/arch/x86/kernel/process_64-xen.c 2011-02-02 08:47:12.000000000 +0100
+++ 12.2/arch/x86/kernel/process_64-xen.c 2011-02-02 08:47:22.000000000 +0100
@@ -215,12 +215,6 @@ void __show_regs(struct pt_regs *regs, i
printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
}
-void show_regs(struct pt_regs *regs)
-{
- show_registers(regs);
- show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
-}
-
void xen_load_gs_index(unsigned gs)
{
WARN_ON(HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, gs));
@@ -291,12 +285,12 @@ int copy_thread(unsigned long clone_flag
set_tsk_thread_flag(p, TIF_FORK);
- p->thread.fs = me->thread.fs;
- p->thread.gs = me->thread.gs;
p->thread.io_bitmap_ptr = NULL;
savesegment(gs, p->thread.gsindex);
+ p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs;
savesegment(fs, p->thread.fsindex);
+ p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs;
savesegment(es, p->thread.es);
savesegment(ds, p->thread.ds);
--- 12.2.orig/arch/x86/kernel/setup-xen.c 2012-06-06 14:03:27.000000000 +0200
+++ 12.2/arch/x86/kernel/setup-xen.c 2011-06-10 12:06:58.000000000 +0200
@@ -55,7 +55,6 @@
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
-#include <linux/slab.h>
#include <linux/user.h>
#include <linux/delay.h>
@@ -151,7 +150,9 @@ EXPORT_SYMBOL(xen_start_info);
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
+#ifdef CONFIG_DMI
RESERVE_BRK(dmi_alloc, 65536);
+#endif
unsigned int boot_cpu_id __read_mostly;
@@ -348,15 +349,17 @@ static void __init reserve_brk(void)
static void __init relocate_initrd(void)
{
#ifndef CONFIG_XEN
+ /* Assume only end is not page aligned */
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+ u64 area_size = PAGE_ALIGN(ramdisk_size);
u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
u64 ramdisk_here;
unsigned long slop, clen, mapaddr;
char *p, *q;
/* We need to move the initrd down into lowmem */
- ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+ ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
PAGE_SIZE);
if (ramdisk_here == -1ULL)
@@ -365,7 +368,7 @@ static void __init relocate_initrd(void)
/* Note: this includes all the lowmem currently occupied by
the initrd, we rely on that fact to keep the data intact. */
- reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+ reserve_early(ramdisk_here, ramdisk_here + area_size,
"NEW RAMDISK");
initrd_start = ramdisk_here + PAGE_OFFSET;
initrd_end = initrd_start + ramdisk_size;
@@ -416,10 +419,11 @@ static void __init relocate_initrd(void)
static void __init reserve_initrd(void)
{
+ /* Assume only end is not page aligned */
#ifndef CONFIG_XEN
u64 ramdisk_image = boot_params.hdr.ramdisk_image;
u64 ramdisk_size = boot_params.hdr.ramdisk_size;
- u64 ramdisk_end = ramdisk_image + ramdisk_size;
+ u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
if (!boot_params.hdr.type_of_loader ||
@@ -428,7 +432,7 @@ static void __init reserve_initrd(void)
#else
unsigned long ramdisk_image = __pa(xen_start_info->mod_start);
unsigned long ramdisk_size = xen_start_info->mod_len;
- unsigned long ramdisk_end = ramdisk_image + ramdisk_size;
+ unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size);
unsigned long end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
if (!xen_start_info->mod_start || !ramdisk_size)
@@ -671,6 +675,18 @@ static int __init setup_elfcorehdr(char
early_param("elfcorehdr", setup_elfcorehdr);
#endif
+static __init void reserve_ibft_region(void)
+{
+ unsigned long addr, size = 0;
+
+ addr = find_ibft_region(&size);
+
+#ifndef CONFIG_XEN
+ if (size)
+ reserve_early_overlap_ok(addr, addr + size, "ibft");
+#endif
+}
+
#ifdef CONFIG_X86_RESERVE_LOW_64K
static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
{
@@ -734,6 +750,25 @@ static struct dmi_system_id __initdata b
{}
};
+#ifndef CONFIG_XEN
+static void __init trim_bios_range(void)
+{
+ /*
+ * A special case is the first 4Kb of memory;
+ * This is a BIOS owned area, not kernel ram, but generally
+ * not listed as such in the E820 table.
+ */
+ e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+ /*
+ * special case: Some BIOSen report the PC BIOS
+ * area (640->1Mb) as ram even though it is not.
+ * take them out.
+ */
+ e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+ sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+#endif
+
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
@@ -943,7 +978,7 @@ void __init setup_arch(char **cmdline_p)
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
-
+ trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
@@ -1010,6 +1045,8 @@ void __init setup_arch(char **cmdline_p)
*/
find_smp_config();
+ reserve_ibft_region();
+
reserve_trampoline_memory();
#ifdef CONFIG_ACPI_SLEEP
@@ -1080,17 +1117,11 @@ void __init setup_arch(char **cmdline_p)
#endif
initmem_init(0, max_pfn, acpi, k8);
-
-#if defined(CONFIG_X86_64) && !defined(CONFIG_XEN)
- /*
- * dma32_reserve_bootmem() allocates bootmem which may conflict
- * with the crashkernel command line, so do that after
- * reserve_crashkernel()
- */
- dma32_reserve_bootmem();
+#ifndef CONFIG_NO_BOOTMEM
+ early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
#endif
- reserve_ibft_region();
+ dma32_reserve_bootmem();
#ifdef CONFIG_KVM_CLOCK
kvmclock_init();
--- 12.2.orig/arch/x86/kernel/smp-xen.c 2011-02-01 14:50:44.000000000 +0100
+++ 12.2/arch/x86/kernel/smp-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -21,6 +21,7 @@
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
+#include <linux/gfp.h>
#include <asm/mtrr.h>
#include <asm/tlbflush.h>
--- 12.2.orig/arch/x86/kernel/time-xen.c 2012-02-10 13:28:55.000000000 +0100
+++ 12.2/arch/x86/kernel/time-xen.c 2012-02-10 13:29:03.000000000 +0100
@@ -623,7 +623,7 @@ static cycle_t xen_clocksource_read(stru
#endif
}
-static void xen_clocksource_resume(void)
+static void xen_clocksource_resume(struct clocksource *cs)
{
extern void time_resume(void);
@@ -645,18 +645,18 @@ static struct clocksource clocksource_xe
struct vcpu_runstate_info *setup_runstate_area(unsigned int cpu)
{
struct vcpu_register_runstate_memory_area area;
- struct vcpu_runstate_info *runstate = &per_cpu(runstate, cpu);
+ struct vcpu_runstate_info *rs = &per_cpu(runstate, cpu);
int rc;
- set_xen_guest_handle(area.addr.h, runstate);
+ set_xen_guest_handle(area.addr.h, rs);
rc = HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area, cpu, &area);
if (rc) {
BUILD_BUG_ON(RUNSTATE_running);
- memset(runstate, 0, sizeof(*runstate));
+ memset(rs, 0, sizeof(*rs));
WARN_ON(rc != -ENOSYS);
}
- return runstate;
+ return rs;
}
static void init_missing_ticks_accounting(unsigned int cpu)
--- 12.2.orig/arch/x86/kernel/traps-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/kernel/traps-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -527,6 +527,9 @@ dotraplinkage void __kprobes do_debug(st
get_debugreg(dr6, 6);
+ /* Filter out all the reserved bits which are preset to 1 */
+ dr6 &= ~DR6_RESERVED;
+
/* Catch kmemcheck conditions first of all! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
return;
--- 12.2.orig/arch/x86/kernel/vsyscall_64-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/kernel/vsyscall_64-xen.c 2011-09-08 16:12:11.000000000 +0200
@@ -304,7 +304,8 @@ static int __init vsyscall_init(void)
register_sysctl_table(kernel_root_table2);
#endif
on_each_cpu(cpu_vsyscall_init, NULL, 1);
- hotcpu_notifier(cpu_vsyscall_notifier, 0);
+ /* notifier priority > KVM */
+ hotcpu_notifier(cpu_vsyscall_notifier, 30);
return 0;
}
--- 12.2.orig/arch/x86/kernel/x86_init-xen.c 2011-07-11 12:53:48.000000000 +0200
+++ 12.2/arch/x86/kernel/x86_init-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -5,8 +5,12 @@
*/
#include <linux/bitmap.h>
#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/list.h>
+#include <linux/spinlock_types.h>
#include <linux/threads.h>
+#include <asm/pci_x86.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/apic.h>
@@ -68,6 +72,12 @@ struct x86_init_ops x86_init __initdata
.iommu = {
.iommu_init = iommu_init_noop,
},
+
+ .pci = {
+ .init = x86_default_pci_init,
+ .init_irq = x86_default_pci_init_irq,
+ .fixup_irqs = x86_default_pci_fixup_irqs,
+ },
};
struct x86_platform_ops x86_platform = {
--- 12.2.orig/arch/x86/lib/Makefile 2011-09-07 14:42:45.000000000 +0200
+++ 12.2/arch/x86/lib/Makefile 2011-04-13 13:58:56.000000000 +0200
@@ -15,6 +15,7 @@ $(obj)/inat.o: $(obj)/inat-tables.c
clean-files := inat-tables.c
obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
+obj-$(CONFIG_XEN) += cache-smp.o
lib-y := delay.o
lib-y += thunk_$(BITS).o
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ 12.2/arch/x86/lib/cache-smp-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -0,0 +1,27 @@
+#include <linux/smp.h>
+#include <linux/module.h>
+#include <asm/hypervisor.h>
+
+static void __wbinvd(void *dummy)
+{
+ wbinvd();
+}
+
+#ifndef CONFIG_XEN
+void wbinvd_on_cpu(int cpu)
+{
+ smp_call_function_single(cpu, __wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL(wbinvd_on_cpu);
+#endif
+
+int wbinvd_on_all_cpus(void)
+{
+ struct mmuext_op op = { .cmd = MMUEXT_FLUSH_CACHE_GLOBAL };
+
+ if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) == 0)
+ return 0;
+ /* Best effort as fallback. */
+ return on_each_cpu(__wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL(wbinvd_on_all_cpus);
--- 12.2.orig/arch/x86/mm/init-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/mm/init-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -1,3 +1,4 @@
+#include <linux/gfp.h>
#include <linux/initrd.h>
#include <linux/ioport.h>
#include <linux/swap.h>
@@ -283,12 +284,7 @@ unsigned long __init_refok init_memory_m
if (!after_bootmem)
find_early_table_space(end, use_pse, use_gbpages);
-#ifdef CONFIG_X86_32
- for (i = 0; i < nr_range; i++)
- kernel_physical_mapping_init(mr[i].start, mr[i].end,
- mr[i].page_size_mask);
- ret = end;
-#else /* CONFIG_X86_64 */
+#ifdef CONFIG_X86_64
#define addr_to_page(addr) \
((unsigned long *) \
((mfn_to_pfn(((addr) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) \
@@ -320,12 +316,12 @@ unsigned long __init_refok init_memory_m
va += PAGE_SIZE;
}
}
+#undef addr_to_page
+#endif
for (i = 0; i < nr_range; i++)
ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
mr[i].page_size_mask);
-#undef addr_to_page
-#endif
#ifdef CONFIG_X86_32
early_ioremap_page_table_range_init();
@@ -377,11 +373,23 @@ int devmem_is_allowed(unsigned long page
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
- unsigned long addr = begin;
+ unsigned long addr;
+ unsigned long begin_aligned, end_aligned;
+
+ /* Make sure boundaries are page aligned */
+ begin_aligned = PAGE_ALIGN(begin);
+ end_aligned = end & PAGE_MASK;
+
+ if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+ begin = begin_aligned;
+ end = end_aligned;
+ }
- if (addr >= end)
+ if (begin >= end)
return;
+ addr = begin;
+
/*
* If debugging page accesses then do not free this memory but
* mark them not present - any buggy init-section access will
@@ -389,7 +397,7 @@ void free_init_pages(char *what, unsigne
*/
#ifdef CONFIG_DEBUG_PAGEALLOC
printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
- begin, PAGE_ALIGN(end));
+ begin, end);
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
/*
@@ -404,8 +412,7 @@ void free_init_pages(char *what, unsigne
for (; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
- memset((void *)(addr & ~(PAGE_SIZE-1)),
- POISON_FREE_INITMEM, PAGE_SIZE);
+ memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
#ifdef CONFIG_X86_64
if (addr >= __START_KERNEL_map) {
/* make_readonly() reports all kernel addresses. */
@@ -434,6 +441,15 @@ void free_initmem(void)
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
- free_init_pages("initrd memory", start, end);
+ /*
+ * end could be not aligned, and We can not align that,
+ * decompresser could be confused by aligned initrd_end
+ * We already reserve the end partial page before in
+ * - i386_start_kernel()
+ * - x86_64_start_kernel()
+ * - relocate_initrd()
+ * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+ */
+ free_init_pages("initrd memory", start, PAGE_ALIGN(end));
}
#endif
--- 12.2.orig/arch/x86/mm/init_32-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/mm/init_32-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -25,11 +25,11 @@
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/bootmem.h>
-#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/memory_hotplug.h>
#include <linux/initrd.h>
#include <linux/cpumask.h>
+#include <linux/gfp.h>
#include <linux/dma-mapping.h>
#include <linux/scatterlist.h>
@@ -257,6 +257,7 @@ kernel_physical_mapping_init(unsigned lo
unsigned long page_size_mask)
{
int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+ unsigned long last_map_addr = end;
unsigned long start_pfn, end_pfn;
pgd_t *pgd_base = swapper_pg_dir;
int pgd_idx, pmd_idx, pte_ofs;
@@ -376,9 +377,10 @@ repeat:
prot = PAGE_KERNEL_EXEC;
pages_4k++;
- if (mapping_iter == 1)
+ if (mapping_iter == 1) {
set_pte(pte, pfn_pte(pfn, init_prot));
- else
+ last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE;
+ } else
set_pte(pte, pfn_pte(pfn, prot));
}
}
@@ -404,7 +406,7 @@ repeat:
mapping_iter = 2;
goto repeat;
}
- return 0;
+ return last_map_addr;
}
pte_t *kmap_pte;
@@ -750,6 +752,7 @@ static void __init zone_sizes_init(void)
free_area_init_nodes(max_zone_pfns);
}
+#ifndef CONFIG_NO_BOOTMEM
static unsigned long __init setup_node_bootmem(int nodeid,
unsigned long start_pfn,
unsigned long end_pfn,
@@ -766,13 +769,14 @@ static unsigned long __init setup_node_b
printk(KERN_INFO " node %d bootmap %08lx - %08lx\n",
nodeid, bootmap, bootmap + bootmap_size);
free_bootmem_with_active_regions(nodeid, end_pfn);
- early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
return bootmap + bootmap_size;
}
+#endif
void __init setup_bootmem_allocator(void)
{
+#ifndef CONFIG_NO_BOOTMEM
int nodeid;
unsigned long bootmap_size, bootmap;
unsigned long end_xen_pfn = min(max_low_pfn, xen_start_info->nr_pages);
@@ -787,11 +791,17 @@ void __init setup_bootmem_allocator(void
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+#elif defined(CONFIG_XEN)
+ if (max_low_pfn > xen_start_info->nr_pages)
+ reserve_early(xen_start_info->nr_pages << PAGE_SHIFT,
+ max_low_pfn << PAGE_SHIFT, "BALLOON");
+#endif
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
+#ifndef CONFIG_NO_BOOTMEM
for_each_online_node(nodeid) {
unsigned long start_pfn, end_pfn;
@@ -809,6 +819,7 @@ void __init setup_bootmem_allocator(void
bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
bootmap);
}
+#endif
after_bootmem = 1;
}
--- 12.2.orig/arch/x86/mm/init_64-xen.c 2011-06-30 17:10:32.000000000 +0200
+++ 12.2/arch/x86/mm/init_64-xen.c 2011-06-30 17:10:52.000000000 +0200
@@ -32,6 +32,7 @@
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#include <linux/nmi.h>
+#include <linux/gfp.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
@@ -403,9 +404,13 @@ static inline int __meminit make_readonl
* No need for writable mapping of kernel image. This also ensures that
* page and descriptor tables embedded inside don't have writable
* mappings. Exclude the vsyscall area here, allowing alternative
- * instruction patching to work.
+ * instruction patching to work. The range must be in sync with that
+ * passed to reserve_early() (as "TEXT DATA BSS"), since all other
+ * regions can be allocated from under CONFIG_NO_BOOTMEM and thus must
+ * be writable.
*/
- if ((paddr >= __pa_symbol(&_text)) && (paddr < __pa(_brk_end))
+ if ((paddr >= __pa_symbol(&_text))
+ && (paddr < (__pa_symbol(__bss_stop) & PAGE_MASK))
&& !(paddr >= __pa_symbol(&__vsyscall_0)
&& paddr < __pa_symbol(&__vsyscall_0) + PAGE_SIZE))
readonly = 1;
@@ -819,6 +824,7 @@ kernel_physical_mapping_init(unsigned lo
void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
int acpi, int k8)
{
+#ifndef CONFIG_NO_BOOTMEM
unsigned long bootmap_size, bootmap;
e820_register_active_regions(0, start_pfn, end_pfn);
@@ -831,12 +837,19 @@ void __init initmem_init(unsigned long s
PAGE_SIZE);
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
+ reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
/* don't touch min_low_pfn */
bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
0, end_pfn);
free_bootmem_with_active_regions(0, end_pfn);
- early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
- reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
+#else
+ e820_register_active_regions(0, start_pfn, end_pfn);
+#ifdef CONFIG_XEN
+ if (end_pfn > xen_start_info->nr_pages)
+ reserve_early(xen_start_info->nr_pages << PAGE_SHIFT,
+ end_pfn << PAGE_SHIFT, "BALLOON");
+#endif
+#endif
}
#endif
@@ -1249,7 +1262,7 @@ vmemmap_populate(struct page *start_page
if (pmd_none(*pmd)) {
pte_t entry;
- p = vmemmap_alloc_block(PMD_SIZE, node);
+ p = vmemmap_alloc_block_buf(PMD_SIZE, node);
if (!p)
return -ENOMEM;
--- 12.2.orig/arch/x86/mm/ioremap-xen.c 2011-02-07 15:41:45.000000000 +0100
+++ 12.2/arch/x86/mm/ioremap-xen.c 2011-02-07 15:41:54.000000000 +0100
@@ -158,45 +158,6 @@ int create_lookup_pte_addr(struct mm_str
EXPORT_SYMBOL(create_lookup_pte_addr);
-int page_is_ram(unsigned long pagenr)
-{
- resource_size_t addr, end;
- int i;
-
-#ifndef CONFIG_XEN
- /*
- * A special case is the first 4Kb of memory;
- * This is a BIOS owned area, not kernel ram, but generally
- * not listed as such in the E820 table.
- */
- if (pagenr == 0)
- return 0;
-
- /*
- * Second special case: Some BIOSen report the PC BIOS
- * area (640->1Mb) as ram even though it is not.
- */
- if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) &&
- pagenr < (BIOS_END >> PAGE_SHIFT))
- return 0;
-#endif
-
- for (i = 0; i < e820.nr_map; i++) {
- /*
- * Not usable memory:
- */
- if (e820.map[i].type != E820_RAM)
- continue;
- addr = (e820.map[i].addr + PAGE_SIZE-1) >> PAGE_SHIFT;
- end = (e820.map[i].addr + e820.map[i].size) >> PAGE_SHIFT;
-
-
- if ((pagenr >= addr) && (pagenr < end))
- return 1;
- }
- return 0;
-}
-
/*
* Fix up the linear direct mapping of the kernel to avoid cache attribute
* conflicts.
@@ -587,6 +548,10 @@ void __init early_ioremap_init(void)
* The boot-ioremap range spans multiple pmds, for which
* we are not prepared:
*/
+#define __FIXADDR_TOP (-PAGE_SIZE)
+ BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+ != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+#undef __FIXADDR_TOP
if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
WARN_ON(1);
printk(KERN_WARNING "pmd %p != %p\n",
@@ -646,6 +611,22 @@ static inline void __init early_clear_fi
static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
+#ifndef CONFIG_XEN
+void __init fixup_early_ioremap(void)
+{
+ int i;
+
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+ if (prev_map[i]) {
+ WARN_ON(1);
+ break;
+ }
+ }
+
+ early_ioremap_init();
+}
+#endif
+
static int __init check_early_ioremap_leak(void)
{
int count = 0;
--- 12.2.orig/arch/x86/mm/hypervisor.c 2012-05-31 14:45:03.000000000 +0200
+++ 12.2/arch/x86/mm/hypervisor.c 2011-08-09 14:31:55.000000000 +0200
@@ -33,6 +33,7 @@
#include <linux/sched.h>
#include <linux/hardirq.h>
#include <linux/mm.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <asm/page.h>
#include <asm/pgtable.h>
--- 12.2.orig/arch/x86/mm/pageattr-xen.c 2011-03-23 10:00:33.000000000 +0100
+++ 12.2/arch/x86/mm/pageattr-xen.c 2011-03-23 10:01:23.000000000 +0100
@@ -6,13 +6,13 @@
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/sched.h>
-#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#include <linux/pfn.h>
#include <linux/percpu.h>
+#include <linux/gfp.h>
#include <asm/e820.h>
#include <asm/processor.h>
@@ -293,8 +293,29 @@ static inline pgprot_t static_protection
*/
if (kernel_set_to_readonly &&
within(address, (unsigned long)_text,
- (unsigned long)__end_rodata_hpage_align))
- pgprot_val(forbidden) |= _PAGE_RW;
+ (unsigned long)__end_rodata_hpage_align)) {
+ unsigned int level;
+
+ /*
+ * Don't enforce the !RW mapping for the kernel text mapping,
+ * if the current mapping is already using small page mapping.
+ * No need to work hard to preserve large page mappings in this
+ * case.
+ *
+ * This also fixes the Linux Xen paravirt guest boot failure
+ * (because of unexpected read-only mappings for kernel identity
+ * mappings). In this paravirt guest case, the kernel text
+ * mapping and the kernel identity mapping share the same
+ * page-table pages. Thus we can't really use different
+ * protections for the kernel text and identity mappings. Also,
+ * these shared mappings are made of small page mappings.
+ * Thus this don't enforce !RW mapping for small page kernel
+ * text mapping logic will help Linux Xen parvirt guest boot
+ * aswell.
+ */
+ if (lookup_address(address, &level) && (level != PG_LEVEL_4K))
+ pgprot_val(forbidden) |= _PAGE_RW;
+ }
#endif
prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
--- 12.2.orig/arch/x86/mm/pat-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/arch/x86/mm/pat-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -12,7 +12,7 @@
#include <linux/debugfs.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/gfp.h>
+#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/rbtree.h>
--- 12.2.orig/arch/x86/mm/pgtable-xen.c 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/arch/x86/mm/pgtable-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -1,4 +1,5 @@
#include <linux/mm.h>
+#include <linux/gfp.h>
#include <linux/module.h>
#include <xen/features.h>
#include <asm/pgalloc.h>
@@ -10,6 +11,14 @@
#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+#ifdef CONFIG_HIGHPTE
+#define PGALLOC_USER_GFP __GFP_HIGHMEM
+#else
+#define PGALLOC_USER_GFP 0
+#endif
+
+gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
+
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
pte_t *pte = (pte_t *)__get_free_page(PGALLOC_GFP);
@@ -28,11 +37,7 @@ pgtable_t pte_alloc_one(struct mm_struct
{
struct page *pte;
-#ifdef CONFIG_HIGHPTE
- pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0);
-#else
- pte = alloc_pages(PGALLOC_GFP, 0);
-#endif
+ pte = alloc_pages(__userpte_alloc_gfp, 0);
if (pte) {
pgtable_page_ctor(pte);
SetPageForeign(pte, _pte_free);
@@ -41,6 +46,23 @@ pgtable_t pte_alloc_one(struct mm_struct
return pte;
}
+static int __init setup_userpte(char *arg)
+{
+ if (!arg)
+ return -EINVAL;
+
+ /*
+ * "userpte=nohigh" disables allocation of user pagetables in
+ * high memory.
+ */
+ if (strcmp(arg, "nohigh") == 0)
+ __userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+ else
+ return -EINVAL;
+ return 0;
+}
+early_param("userpte", setup_userpte);
+
void __pte_free(pgtable_t pte)
{
if (!PageHighMem(pte)) {
--- 12.2.orig/arch/x86/mm/pgtable_32-xen.c 2011-02-01 14:44:12.000000000 +0100
+++ 12.2/arch/x86/mm/pgtable_32-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -6,7 +6,6 @@
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/highmem.h>
-#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/spinlock.h>
#include <linux/module.h>
@@ -142,6 +141,7 @@ static int __init parse_reservetop(char
address = memparse(arg, &arg);
reserve_top_address(address);
+ fixup_early_ioremap();
return 0;
}
early_param("reservetop", parse_reservetop);
--- 12.2.orig/drivers/acpi/acpi_pad-xen.c 2012-06-01 11:18:36.000000000 +0200
+++ 12.2/drivers/acpi/acpi_pad-xen.c 2012-06-01 11:18:36.000000000 +0200
@@ -27,7 +27,7 @@
#include <acpi/acpi_drivers.h>
#include <asm/hypervisor.h>
-#define ACPI_PROCESSOR_AGGREGATOR_CLASS "processor_aggregator"
+#define ACPI_PROCESSOR_AGGREGATOR_CLASS "acpi_pad"
#define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Xen Processor Aggregator"
#define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
static DEFINE_MUTEX(xen_cpu_lock);
--- 12.2.orig/drivers/acpi/processor_core.c 2012-02-08 12:06:55.000000000 +0100
+++ 12.2/drivers/acpi/processor_core.c 2012-02-08 12:25:09.000000000 +0100
@@ -20,6 +20,15 @@
#define _COMPONENT ACPI_PROCESSOR_COMPONENT
ACPI_MODULE_NAME("processor_core");
+#ifdef CONFIG_PROCESSOR_EXTERNAL_CONTROL
+/*
+ * External processor control logic may register with its own set of
+ * ops to get ACPI related notification. One example is like VMM.
+ */
+const struct processor_extcntl_ops *processor_extcntl_ops;
+EXPORT_SYMBOL(processor_extcntl_ops);
+#endif
+
static int __init set_no_mwait(const struct dmi_system_id *id)
{
printk(KERN_NOTICE PREFIX "%s detected - "
@@ -258,6 +267,8 @@ static bool __init processor_physically_
}
type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0;
+ if (processor_cntl_external())
+ type = ~type;
cpuid = acpi_get_cpuid(handle, type, acpi_id);
if (cpuid == -1)
--- 12.2.orig/drivers/acpi/processor_driver.c 2012-05-23 13:34:56.000000000 +0200
+++ 12.2/drivers/acpi/processor_driver.c 2012-05-23 13:35:30.000000000 +0200
@@ -110,7 +110,9 @@ static struct acpi_driver acpi_processor
#define UNINSTALL_NOTIFY_HANDLER 2
DEFINE_PER_CPU(struct acpi_processor *, processors);
+#ifndef CONFIG_XEN
EXPORT_PER_CPU_SYMBOL(processors);
+#endif
struct acpi_processor_errata errata __read_mostly;
@@ -325,8 +327,8 @@ static int acpi_processor_get_info(struc
*/
if (pr->id == -1) {
if (ACPI_FAILURE(acpi_processor_hotadd_init(pr)) &&
- get_cpu_id(pr->handle, ~device_declaration,
- pr->acpi_id) < 0)
+ acpi_get_cpuid(pr->handle, ~device_declaration,
+ pr->acpi_id) < 0)
return -ENODEV;
}
/*
@@ -572,8 +574,6 @@ static int __cpuinit acpi_processor_add(
strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
device->driver_data = pr;
- processor_extcntl_init();
-
result = acpi_processor_get_info(device);
if (result ||
((pr->id == -1) && !processor_cntl_external())) {
--- 12.2.orig/drivers/acpi/processor_extcntl.c 2011-02-01 14:39:24.000000000 +0100
+++ 12.2/drivers/acpi/processor_extcntl.c 2011-02-01 15:03:03.000000000 +0100
@@ -36,12 +36,6 @@ ACPI_MODULE_NAME("processor_extcntl")
static int processor_extcntl_parse_csd(struct acpi_processor *pr);
static int processor_extcntl_get_performance(struct acpi_processor *pr);
-/*
- * External processor control logic may register with its own set of
- * ops to get ACPI related notification. One example is like VMM.
- */
-const struct processor_extcntl_ops *processor_extcntl_ops;
-EXPORT_SYMBOL(processor_extcntl_ops);
static int processor_notify_smm(void)
{
@@ -102,21 +96,6 @@ int processor_notify_external(struct acp
}
/*
- * External control logic can decide to grab full or part of physical
- * processor control bits. Take a VMM for example, physical processors
- * are owned by VMM and thus existence information like hotplug is
- * always required to be notified to VMM. Similar is processor idle
- * state which is also necessarily controlled by VMM. But for other
- * control bits like performance/throttle states, VMM may choose to
- * control or not upon its own policy.
- */
-void processor_extcntl_init(void)
-{
- if (!processor_extcntl_ops)
- arch_acpi_processor_init_extcntl(&processor_extcntl_ops);
-}
-
-/*
* This is called from ACPI processor init, and targeted to hold
* some tricky housekeeping jobs to satisfy external control model.
* For example, we may put dependency parse stub here for idle
--- 12.2.orig/drivers/char/tpm/tpm_vtpm.c 2011-02-01 14:38:38.000000000 +0100
+++ 12.2/drivers/char/tpm/tpm_vtpm.c 2011-02-01 15:03:03.000000000 +0100
@@ -16,6 +16,7 @@
#include <asm/uaccess.h>
#include <linux/list.h>
+#include <linux/slab.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
--- 12.2.orig/drivers/char/tpm/tpm_xen.c 2012-03-12 13:40:20.000000000 +0100
+++ 12.2/drivers/char/tpm/tpm_xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -37,6 +37,7 @@
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/mutex.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <xen/evtchn.h>
#include <xen/interface/grant_table.h>
--- 12.2.orig/drivers/hwmon/coretemp-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/drivers/hwmon/coretemp-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -233,7 +233,7 @@ static int adjust_tjmax(struct coretemp_
if (err < 0) {
dev_warn(dev,
"Unable to access MSR 0xEE, for Tjmax, left"
- " at default");
+ " at default\n");
} else if (eax & 0x40000000) {
tjmax = tjmax_ee;
}
@@ -413,7 +413,7 @@ static int coretemp_device_add(unsigned
family 6 CPU */
if ((info.x86 == 0x6) && (pdev_entry->x86_model > 0xf))
printk(KERN_WARNING DRVNAME ": Unknown CPU "
- "model 0x%x", pdev_entry->x86_model);
+ "model 0x%x\n", pdev_entry->x86_model);
goto exit_entry_free;
}
--- 12.2.orig/drivers/misc/Kconfig 2012-06-20 12:12:05.000000000 +0200
+++ 12.2/drivers/misc/Kconfig 2012-02-21 11:39:49.000000000 +0100
@@ -427,7 +427,7 @@ config TI_DAC7512
config VMWARE_BALLOON
tristate "VMware Balloon Driver"
- depends on X86
+ depends on X86 && !XEN
help
This is VMware physical memory management driver which acts
like a "balloon" that can be inflated to reclaim physical pages
--- 12.2.orig/drivers/pci/msi-xen.c 2012-04-04 11:03:37.000000000 +0200
+++ 12.2/drivers/pci/msi-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -18,6 +18,7 @@
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/io.h>
+#include <linux/slab.h>
#include <xen/evtchn.h>
--- 12.2.orig/drivers/xen/Kconfig 2012-02-17 14:34:14.000000000 +0100
+++ 12.2/drivers/xen/Kconfig 2012-04-03 13:15:34.000000000 +0200
@@ -23,6 +23,7 @@ config XEN_UNPRIVILEGED_GUEST
select PM_SLEEP
select PM_SLEEP_SMP if SMP
select PM_RUNTIME if PCI
+ select PM_OPS if PCI
select SUSPEND
config XEN_PRIVCMD
@@ -443,7 +444,6 @@ config XEN_SCRUB_PAGES
config XEN_DEV_EVTCHN
tristate "Xen /dev/xen/evtchn device"
- depends on XEN || PARAVIRT_XEN
default PARAVIRT_XEN || XEN_PRIVILEGED_GUEST || m
help
The evtchn driver allows a userspace process to triger event
--- 12.2.orig/drivers/xen/balloon/balloon.c 2012-06-06 14:03:00.000000000 +0200
+++ 12.2/drivers/xen/balloon/balloon.c 2012-01-20 15:02:23.000000000 +0100
@@ -41,6 +41,7 @@
#include <linux/swap.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
+#include <linux/slab.h>
#include <linux/mutex.h>
#include <xen/xen_proc.h>
#include <asm/hypervisor.h>
--- 12.2.orig/drivers/xen/blkback/blkback-pagemap.c 2011-01-31 17:56:27.000000000 +0100
+++ 12.2/drivers/xen/blkback/blkback-pagemap.c 2011-02-01 15:03:03.000000000 +0100
@@ -1,4 +1,5 @@
#include <linux/module.h>
+#include <linux/slab.h>
#include "blkback-pagemap.h"
static int blkback_pagemap_size;
--- 12.2.orig/drivers/xen/blkfront/vbd.c 2012-03-12 16:16:46.000000000 +0100
+++ 12.2/drivers/xen/blkfront/vbd.c 2012-03-12 16:16:59.000000000 +0100
@@ -367,15 +367,14 @@ xlvbd_init_blk_queue(struct gendisk *gd,
/* Hard sector size and max sectors impersonate the equiv. hardware. */
blk_queue_logical_block_size(rq, sector_size);
- blk_queue_max_sectors(rq, 512);
+ blk_queue_max_hw_sectors(rq, 512);
/* Each segment in a request is up to an aligned page in size. */
blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
blk_queue_max_segment_size(rq, PAGE_SIZE);
/* Ensure a merged request will fit in a single I/O ring slot. */
- blk_queue_max_phys_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
- blk_queue_max_hw_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
/* Make sure buffer addresses are sector-aligned. */
blk_queue_dma_alignment(rq, 511);
--- 12.2.orig/drivers/xen/blktap2/blktap.h 2012-06-06 14:02:20.000000000 +0200
+++ 12.2/drivers/xen/blktap2/blktap.h 2011-02-01 15:03:03.000000000 +0100
@@ -1,6 +1,7 @@
#ifndef _BLKTAP_H_
#define _BLKTAP_H_
+#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/cdev.h>
--- 12.2.orig/drivers/xen/blktap2/device.c 2012-02-16 13:32:37.000000000 +0100
+++ 12.2/drivers/xen/blktap2/device.c 2012-02-16 13:33:30.000000000 +0100
@@ -972,15 +972,14 @@ blktap_device_configure(struct blktap *t
/* Hard sector size and max sectors impersonate the equiv. hardware. */
blk_queue_logical_block_size(rq, tap->params.sector_size);
- blk_queue_max_sectors(rq, 512);
+ blk_queue_max_hw_sectors(rq, 512);
/* Each segment in a request is up to an aligned page in size. */
blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
blk_queue_max_segment_size(rq, PAGE_SIZE);
/* Ensure a merged request will fit in a single I/O ring slot. */
- blk_queue_max_phys_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
- blk_queue_max_hw_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
/* Make sure buffer addresses are sector-aligned. */
blk_queue_dma_alignment(rq, 511);
--- 12.2.orig/drivers/xen/blktap2/sysfs.c 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/drivers/xen/blktap2/sysfs.c 2011-02-24 14:59:15.000000000 +0100
@@ -379,13 +379,15 @@ blktap_sysfs_destroy(struct blktap *tap)
}
static ssize_t
-blktap_sysfs_show_verbosity(struct class *class, char *buf)
+blktap_sysfs_show_verbosity(struct class *class, struct class_attribute *attr,
+ char *buf)
{
return sprintf(buf, "%d\n", blktap_debug_level);
}
static ssize_t
-blktap_sysfs_set_verbosity(struct class *class, const char *buf, size_t size)
+blktap_sysfs_set_verbosity(struct class *class, struct class_attribute *attr,
+ const char *buf, size_t size)
{
int level;
@@ -400,7 +402,8 @@ static CLASS_ATTR(verbosity, S_IRUSR | S
blktap_sysfs_show_verbosity, blktap_sysfs_set_verbosity);
static ssize_t
-blktap_sysfs_show_devices(struct class *class, char *buf)
+blktap_sysfs_show_devices(struct class *class, struct class_attribute *attr,
+ char *buf)
{
int i, ret;
struct blktap *tap;
--- 12.2.orig/drivers/xen/blktap2-new/blktap.h 2012-05-31 10:58:55.000000000 +0200
+++ 12.2/drivers/xen/blktap2-new/blktap.h 2011-02-24 15:00:29.000000000 +0100
@@ -2,6 +2,7 @@
#define _BLKTAP_H_
#include <linux/mm.h>
+#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/cdev.h>
#include <linux/init.h>
--- 12.2.orig/drivers/xen/blktap2-new/device.c 2012-02-16 11:02:14.000000000 +0100
+++ 12.2/drivers/xen/blktap2-new/device.c 2012-02-17 08:57:44.000000000 +0100
@@ -294,15 +294,14 @@ blktap_device_configure(struct blktap *t
/* Hard sector size and max sectors impersonate the equiv. hardware. */
blk_queue_logical_block_size(rq, params->sector_size);
- blk_queue_max_sectors(rq, 512);
+ blk_queue_max_hw_sectors(rq, 512);
/* Each segment in a request is up to an aligned page in size. */
blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
blk_queue_max_segment_size(rq, PAGE_SIZE);
/* Ensure a merged request will fit in a single I/O ring slot. */
- blk_queue_max_phys_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
- blk_queue_max_hw_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);
/* Make sure buffer addresses are sector-aligned. */
blk_queue_dma_alignment(rq, 511);
--- 12.2.orig/drivers/xen/blktap2-new/sysfs.c 2012-01-24 11:22:07.000000000 +0100
+++ 12.2/drivers/xen/blktap2-new/sysfs.c 2011-02-24 15:02:50.000000000 +0100
@@ -213,13 +213,15 @@ blktap_sysfs_destroy(struct blktap *tap)
}
static ssize_t
-blktap_sysfs_show_verbosity(struct class *class, char *buf)
+blktap_sysfs_show_verbosity(struct class *class, struct class_attribute *attr,
+ char *buf)
{
return sprintf(buf, "%d\n", blktap_debug_level);
}
static ssize_t
-blktap_sysfs_set_verbosity(struct class *class, const char *buf, size_t size)
+blktap_sysfs_set_verbosity(struct class *class, struct class_attribute *attr,
+ const char *buf, size_t size)
{
int level;
@@ -234,7 +236,8 @@ static CLASS_ATTR(verbosity, S_IRUGO|S_I
blktap_sysfs_show_verbosity, blktap_sysfs_set_verbosity);
static ssize_t
-blktap_sysfs_show_devices(struct class *class, char *buf)
+blktap_sysfs_show_devices(struct class *class, struct class_attribute *attr,
+ char *buf)
{
int i, ret;
struct blktap *tap;
--- 12.2.orig/drivers/xen/char/mem.c 2012-01-20 15:00:49.000000000 +0100
+++ 12.2/drivers/xen/char/mem.c 2012-01-20 15:02:27.000000000 +0100
@@ -3,7 +3,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
- * Added devfs support.
+ * Added devfs support.
* Jan-11-1998, C. Scott Ananian <cananian@alumni.princeton.edu>
* Shared /dev/zero mmapping support, Feb 2000, Kanoj Sarcar <kanoj@sgi.com>
*/
@@ -57,10 +57,10 @@ static inline int range_is_allowed(unsig
}
/*
- * This funcion reads the *physical* memory. The f_pos points directly to the
- * memory location.
+ * This funcion reads the *physical* memory. The f_pos points directly to the
+ * memory location.
*/
-static ssize_t read_mem(struct file * file, char __user * buf,
+static ssize_t read_mem(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long p = *ppos;
@@ -106,7 +106,7 @@ static ssize_t read_mem(struct file * fi
return read;
}
-static ssize_t write_mem(struct file * file, const char __user * buf,
+static ssize_t write_mem(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long p = *ppos, ignored;
@@ -153,7 +153,7 @@ static struct vm_operations_struct mmap_
#endif
};
-static int xen_mmap_mem(struct file * file, struct vm_area_struct * vma)
+static int xen_mmap_mem(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
@@ -183,24 +183,26 @@ static int xen_mmap_mem(struct file * fi
* also note that seeking relative to the "end of file" isn't supported:
* it has no meaning, so it returns -EINVAL.
*/
-static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
+static loff_t memory_lseek(struct file *file, loff_t offset, int orig)
{
loff_t ret;
mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
switch (orig) {
- case 0:
- file->f_pos = offset;
- ret = file->f_pos;
- force_successful_syscall_return();
+ case SEEK_CUR:
+ offset += file->f_pos;
+ case SEEK_SET:
+ /* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */
+ if ((unsigned long long)offset >= ~0xFFFULL) {
+ ret = -EOVERFLOW;
break;
- case 1:
- file->f_pos += offset;
- ret = file->f_pos;
- force_successful_syscall_return();
- break;
- default:
- ret = -EINVAL;
+ }
+ file->f_pos = offset;
+ ret = file->f_pos;
+ force_successful_syscall_return();
+ break;
+ default:
+ ret = -EINVAL;
}
mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
return ret;
--- 12.2.orig/drivers/xen/core/evtchn.c 2012-04-03 16:47:40.000000000 +0200
+++ 12.2/drivers/xen/core/evtchn.c 2011-02-01 15:03:03.000000000 +0100
@@ -31,6 +31,7 @@
*/
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
--- 12.2.orig/drivers/xen/core/gnttab.c 2012-05-23 13:33:34.000000000 +0200
+++ 12.2/drivers/xen/core/gnttab.c 2012-03-12 16:17:09.000000000 +0100
@@ -32,6 +32,7 @@
*/
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/seqlock.h>
--- 12.2.orig/drivers/xen/core/reboot.c 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/drivers/xen/core/reboot.c 2011-02-01 15:03:03.000000000 +0100
@@ -2,6 +2,7 @@
#include <linux/kernel.h>
#include <linux/unistd.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/reboot.h>
#include <linux/sched.h>
#include <linux/sysrq.h>
--- 12.2.orig/drivers/xen/fbfront/xenfb.c 2011-02-17 10:16:12.000000000 +0100
+++ 12.2/drivers/xen/fbfront/xenfb.c 2011-02-01 15:03:03.000000000 +0100
@@ -25,6 +25,7 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
+#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/freezer.h>
#include <asm/hypervisor.h>
--- 12.2.orig/drivers/xen/fbfront/xenkbd.c 2011-05-23 11:12:20.000000000 +0200
+++ 12.2/drivers/xen/fbfront/xenkbd.c 2011-09-20 11:39:37.000000000 +0200
@@ -20,6 +20,7 @@
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/input.h>
#include <asm/hypervisor.h>
#include <xen/evtchn.h>
--- 12.2.orig/drivers/xen/gntdev/gntdev.c 2012-05-23 13:34:59.000000000 +0200
+++ 12.2/drivers/xen/gntdev/gntdev.c 2012-01-20 15:02:32.000000000 +0100
@@ -23,6 +23,7 @@
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/mm.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <xen/gnttab.h>
--- 12.2.orig/drivers/xen/netfront/netfront.h 2012-06-06 13:55:57.000000000 +0200
+++ 12.2/drivers/xen/netfront/netfront.h 2012-06-06 14:03:54.000000000 +0200
@@ -35,6 +35,7 @@
#include <xen/barrier.h>
#include <xen/interface/io/netif.h>
+#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/list.h>
--- 12.2.orig/drivers/xen/pcifront/pcifront.h 2011-01-31 17:32:16.000000000 +0100
+++ 12.2/drivers/xen/pcifront/pcifront.h 2011-02-01 15:03:03.000000000 +0100
@@ -6,6 +6,7 @@
#ifndef __XEN_PCIFRONT_H__
#define __XEN_PCIFRONT_H__
+#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
#include <xen/xenbus.h>
--- 12.2.orig/drivers/xen/scsifront/xenbus.c 2011-02-08 10:05:30.000000000 +0100
+++ 12.2/drivers/xen/scsifront/xenbus.c 2011-02-08 10:06:25.000000000 +0100
@@ -34,6 +34,7 @@
*/
#include <linux/version.h>
+#include <linux/slab.h>
#include "common.h"
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,11)
--- 12.2.orig/drivers/xen/sfc_netfront/accel.h 2011-02-01 14:38:38.000000000 +0100
+++ 12.2/drivers/xen/sfc_netfront/accel.h 2011-02-01 15:03:03.000000000 +0100
@@ -35,6 +35,7 @@
#include <xen/evtchn.h>
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <linux/version.h>
#include <linux/list.h>
--- 12.2.orig/drivers/xen/sfc_netutil/accel_cuckoo_hash.c 2011-10-17 10:45:09.000000000 +0200
+++ 12.2/drivers/xen/sfc_netutil/accel_cuckoo_hash.c 2011-02-01 15:03:03.000000000 +0100
@@ -24,6 +24,7 @@
#include <linux/types.h> /* needed for linux/random.h */
#include <linux/random.h>
+#include <linux/slab.h>
#include "accel_cuckoo_hash.h"
#include "accel_util.h"
--- 12.2.orig/drivers/xen/sfc_netutil/accel_util.c 2011-01-31 17:49:31.000000000 +0100
+++ 12.2/drivers/xen/sfc_netutil/accel_util.c 2011-02-01 15:03:03.000000000 +0100
@@ -22,6 +22,7 @@
****************************************************************************
*/
+#include <linux/slab.h>
#include <linux/if_ether.h>
#include <linux/delay.h>
#include <asm/io.h>
--- 12.2.orig/drivers/xen/xenbus/xenbus_client.c 2011-02-01 14:42:26.000000000 +0100
+++ 12.2/drivers/xen/xenbus/xenbus_client.c 2011-02-01 15:03:03.000000000 +0100
@@ -30,8 +30,8 @@
* IN THE SOFTWARE.
*/
-#if defined(CONFIG_XEN) || defined(MODULE)
#include <linux/slab.h>
+#if defined(CONFIG_XEN) || defined(MODULE)
#include <xen/evtchn.h>
#include <xen/gnttab.h>
#else
--- 12.2.orig/drivers/xen/xenbus/xenbus_dev.c 2011-02-01 14:54:13.000000000 +0100
+++ 12.2/drivers/xen/xenbus/xenbus_dev.c 2011-02-01 15:03:03.000000000 +0100
@@ -33,6 +33,7 @@
*/
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/uio.h>
#include <linux/notifier.h>
--- 12.2.orig/drivers/xen/xenbus/xenbus_probe.c 2011-06-10 12:06:43.000000000 +0200
+++ 12.2/drivers/xen/xenbus/xenbus_probe.c 2011-06-10 12:06:56.000000000 +0200
@@ -47,6 +47,7 @@
#include <linux/notifier.h>
#include <linux/mutex.h>
#include <linux/io.h>
+#include <linux/slab.h>
#include <asm/page.h>
#include <asm/pgtable.h>
--- 12.2.orig/drivers/xen/xenbus/xenbus_probe_backend.c 2011-02-01 14:44:12.000000000 +0100
+++ 12.2/drivers/xen/xenbus/xenbus_probe_backend.c 2011-02-01 15:03:03.000000000 +0100
@@ -42,6 +42,7 @@
#include <linux/ctype.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
+#include <linux/slab.h>
#include <linux/notifier.h>
#include <asm/io.h>
--- 12.2.orig/include/acpi/processor.h 2012-05-23 13:35:16.000000000 +0200
+++ 12.2/include/acpi/processor.h 2012-05-23 13:35:23.000000000 +0200
@@ -439,11 +439,9 @@ static inline int processor_pmthr_extern
extern int processor_notify_external(struct acpi_processor *pr,
int event, int type);
-extern void processor_extcntl_init(void);
extern int processor_extcntl_prepare(struct acpi_processor *pr);
extern int acpi_processor_get_performance_info(struct acpi_processor *pr);
extern int acpi_processor_get_psd(struct acpi_processor *pr);
-void arch_acpi_processor_init_extcntl(const struct processor_extcntl_ops **);
#else
static inline int processor_cntl_external(void) {return 0;}
static inline int processor_pm_external(void) {return 0;}
@@ -454,7 +452,6 @@ static inline int processor_notify_exter
{
return 0;
}
-static inline void processor_extcntl_init(void) {}
static inline int processor_extcntl_prepare(struct acpi_processor *pr)
{
return 0;
--- 12.2.orig/include/xen/xenbus.h 2011-02-02 16:59:07.000000000 +0100
+++ 12.2/include/xen/xenbus.h 2011-12-21 11:17:37.000000000 +0100
@@ -39,6 +39,7 @@
#include <linux/mutex.h>
#include <linux/completion.h>
#include <linux/init.h>
+#include <linux/slab.h>
#include <linux/err.h>
#include <linux/version.h>
#include <xen/interface/xen.h>
--- 12.2.orig/lib/swiotlb-xen.c 2011-02-01 14:55:46.000000000 +0100
+++ 12.2/lib/swiotlb-xen.c 2011-02-01 15:03:03.000000000 +0100
@@ -25,6 +25,8 @@
#include <linux/bootmem.h>
#include <linux/iommu-helper.h>
#include <linux/highmem.h>
+#include <linux/gfp.h>
+
#include <asm/io.h>
#include <asm/pci.h>
#include <asm/dma.h>
--- 12.2.orig/mm/page_alloc.c 2012-02-08 12:13:15.000000000 +0100
+++ 12.2/mm/page_alloc.c 2012-06-20 12:17:44.000000000 +0200
@@ -5058,7 +5058,8 @@ void setup_per_zone_wmarks(void)
high = percpu_pagelist_fraction
? zone->present_pages / percpu_pagelist_fraction
: 5 * zone_batchsize(zone);
- setup_pagelist_highmark(zone_pcp(zone, cpu), high);
+ setup_pagelist_highmark(
+ per_cpu_ptr(zone->pageset, cpu), high);
}
}
#endif
@@ -5682,6 +5683,11 @@ static struct trace_print_flags pageflag
#ifdef CONFIG_MEMORY_FAILURE
{1UL << PG_hwpoison, "hwpoison" },
#endif
+#ifdef CONFIG_XEN
+ {1UL << PG_foreign, "foreign" },
+/* {1UL << PG_netback, "netback" }, */
+ {1UL << PG_blkback, "blkback" },
+#endif
{-1UL, NULL },
};