Merge branch 'xen-upstream' of ssh://master.kernel.org/pub/scm/linux/kernel/git/jeremy/xen

5cc97bf2 · Linus Torvalds <[email protected]> · 2007-07-18 10:18:39 -07:00

* 'xen-upstream' of ssh://master.kernel.org/pub/scm/linux/kernel/git/jeremy/xen: (44 commits)
  xen: disable all non-virtual drivers
  xen: use iret directly when possible
  xen: suppress abs symbol warnings for unused reloc pointers
  xen: Attempt to patch inline versions of common operations
  xen: Place vcpu_info structure into per-cpu memory
  xen: handle external requests for shutdown, reboot and sysrq
  xen: machine operations
  xen: add virtual network device driver
  xen: add virtual block device driver.
  xen: add the Xenbus sysfs and virtual device hotplug driver
  xen: Add grant table support
  xen: use the hvc console infrastructure for Xen console
  xen: hack to prevent bad segment register reload
  xen: lazy-mmu operations
  xen: Add support for preemption
  xen: SMP guest support
  xen: Implement sched_clock
  xen: Account for stolen time
  xen: ignore RW mapping of RO pages in pagetable_init
  xen: Complete pagetable pinning
  ...

Commit: 5cc97bf2d8eaa6cab60727c3eba3e85e29062669
Parents: 826ea8f2 · dfdcdd42

Merge commit. Changes below are compared with the first parent: 826ea8f2.

Changes

116 files changed · +15031 −210

File	Status	Add	Del	Content
arch/i386/Kconfig	modified	+2	−0	View file
arch/i386/Makefile	modified	+3	−0	View file
arch/i386/boot/compressed/relocs.c	modified	+2	−0	View file
arch/i386/kernel/asm-offsets.c	modified	+9	−0	View file
arch/i386/kernel/entry.S	modified	+85	−0	View file
arch/i386/kernel/head.S	modified	+4	−1	View file
arch/i386/kernel/paravirt.c	modified	+36	−1	View file
arch/i386/kernel/setup.c	modified	+2	−0	View file
arch/i386/kernel/smp.c	modified	+3	−2	View file
arch/i386/kernel/smpboot.c	modified	+3	−5	View file
arch/i386/kernel/tsc.c	modified	+15	−8	View file
arch/i386/kernel/vmi.c	modified	+2	−2	View file
arch/i386/kernel/vmiclock.c	modified	+3	−3	View file
arch/i386/kernel/vmlinux.lds.S	modified	+1	−0	View file
arch/i386/kernel/vsyscall-note.S	modified	+33	−16	View file
arch/i386/mach-voyager/voyager_thread.c	modified	+1	−1	View file
arch/i386/mm/init.c	modified	+2	−1	View file
arch/i386/mm/pageattr.c	modified	+1	−1	View file
arch/i386/xen/Kconfig	added	+11	−0	View file
arch/i386/xen/Makefile	added	+4	−0	View file
arch/i386/xen/enlighten.c	added	+1144	−0	View file
arch/i386/xen/events.c	added	+590	−0	View file
arch/i386/xen/features.c	added	+29	−0	View file
arch/i386/xen/manage.c	added	+143	−0	View file
arch/i386/xen/mmu.c	added	+564	−0	View file
arch/i386/xen/mmu.h	added	+60	−0	View file
arch/i386/xen/multicalls.c	added	+90	−0	View file
arch/i386/xen/multicalls.h	added	+45	−0	View file
arch/i386/xen/setup.c	added	+96	−0	View file
arch/i386/xen/smp.c	added	+404	−0	View file
arch/i386/xen/time.c	added	+590	−0	View file
arch/i386/xen/xen-asm.S	added	+291	−0	View file
arch/i386/xen/xen-head.S	added	+36	−0	View file
arch/i386/xen/xen-ops.h	added	+71	−0	View file
arch/x86_64/kernel/early_printk.c	modified	+5	−0	View file
arch/x86_64/kernel/mce.c	modified	+1	−1	View file
drivers/Makefile	modified	+2	−0	View file
drivers/acpi/thermal.c	modified	+2	−22	View file
drivers/block/Kconfig	modified	+9	−0	View file
drivers/block/Makefile	modified	+1	−0	View file
drivers/block/xen-blkfront.c	added	+988	−0	View file
drivers/char/Kconfig	modified	+8	−0	View file
drivers/char/Makefile	modified	+1	−0	View file
drivers/char/hvc_xen.c	added	+159	−0	View file
drivers/macintosh/therm_pm72.c	modified	+2	−1	View file
drivers/macintosh/windfarm_core.c	modified	+2	−1	View file
drivers/net/Kconfig	modified	+12	−0	View file
drivers/net/Makefile	modified	+2	−0	View file
drivers/net/hamradio/baycom_epp.c	modified	+1	−1	View file
drivers/net/xen-netfront.c	added	+1863	−0	View file
drivers/pnp/pnpbios/core.c	modified	+1	−1	View file
drivers/sbus/char/bbc_envctrl.c	modified	+2	−3	View file
drivers/sbus/char/envctrl.c	modified	+2	−5	View file
drivers/xen/Makefile	added	+2	−0	View file
drivers/xen/grant-table.c	added	+582	−0	View file
drivers/xen/xenbus/Makefile	added	+7	−0	View file
drivers/xen/xenbus/xenbus_client.c	added	+569	−0	View file
drivers/xen/xenbus/xenbus_comms.c	added	+233	−0	View file
drivers/xen/xenbus/xenbus_comms.h	added	+46	−0	View file
drivers/xen/xenbus/xenbus_probe.c	added	+935	−0	View file
drivers/xen/xenbus/xenbus_probe.h	added	+74	−0	View file
drivers/xen/xenbus/xenbus_xs.c	added	+861	−0	View file
fs/ocfs2/heartbeat.c	modified	+1	−1	View file
include/asm-i386/irq.h	modified	+1	−0	View file
include/asm-i386/mach-default/irq_vectors_limits.h	modified	+1	−1	View file
include/asm-i386/mmu_context.h	modified	+2	−0	View file
include/asm-i386/paravirt.h	modified	+17	−5	View file
include/asm-i386/pgalloc.h	modified	+3	−3	View file
include/asm-i386/setup.h	modified	+4	−0	View file
include/asm-i386/smp.h	modified	+5	−0	View file
include/asm-i386/timer.h	modified	+31	−1	View file
include/asm-i386/vmi_time.h	modified	+1	−1	View file
include/asm-i386/xen/hypercall.h	added	+413	−0	View file
include/asm-i386/xen/hypervisor.h	added	+73	−0	View file
include/asm-i386/xen/interface.h	added	+188	−0	View file
include/linux/elfnote.h	modified	+15	−7	View file
include/linux/kmod.h	modified	+48	−4	View file
include/linux/major.h	modified	+2	−0	View file
include/linux/page-flags.h	modified	+5	−0	View file
include/linux/reboot.h	modified	+5	−0	View file
include/linux/string.h	modified	+4	−0	View file
include/linux/vmalloc.h	modified	+4	−0	View file
include/xen/events.h	added	+48	−0	View file
include/xen/features.h	added	+23	−0	View file
include/xen/grant_table.h	added	+107	−0	View file
include/xen/hvc-console.h	added	+6	−0	View file
include/xen/interface/elfnote.h	added	+133	−0	View file
include/xen/interface/event_channel.h	added	+195	−0	View file
include/xen/interface/features.h	added	+43	−0	View file
include/xen/interface/grant_table.h	added	+375	−0	View file
include/xen/interface/io/blkif.h	added	+94	−0	View file
include/xen/interface/io/console.h	added	+23	−0	View file
include/xen/interface/io/netif.h	added	+158	−0	View file
include/xen/interface/io/ring.h	added	+260	−0	View file
include/xen/interface/io/xenbus.h	added	+44	−0	View file
include/xen/interface/io/xs_wire.h	added	+87	−0	View file
include/xen/interface/memory.h	added	+145	−0	View file
include/xen/interface/physdev.h	added	+145	−0	View file
include/xen/interface/sched.h	added	+77	−0	View file
include/xen/interface/vcpu.h	added	+167	−0	View file
include/xen/interface/version.h	added	+60	−0	View file
include/xen/interface/xen.h	added	+447	−0	View file
include/xen/page.h	added	+179	−0	View file
include/xen/xenbus.h	added	+234	−0	View file
kernel/cpuset.c	modified	+1	−1	View file
kernel/kmod.c	modified	+150	−66	View file
kernel/sys.c	modified	+58	−0	View file
kernel/sysctl.c	modified	+10	−0	View file
lib/Makefile	modified	+1	−1	View file
lib/argv_split.c	added	+105	−0	View file
lib/kobject_uevent.c	modified	+1	−1	View file
mm/util.c	modified	+24	−2	View file
mm/vmalloc.c	modified	+53	−0	View file
net/bridge/br_stp_if.c	modified	+1	−1	View file
net/irda/irias_object.c	modified	+5	−38	View file
security/keys/request_key.c	modified	+2	−1	View file

Only the first 600 diff lines are shown. Download the complete patch.

arch/i386/Kconfig

View file

diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index c7c9c2a..7a11b90 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -222,6 +222,8 @@ config PARAVIRT
 	  However, when run without a hypervisor the kernel is
 	  theoretically slower.  If in doubt, say N.
 
+source "arch/i386/xen/Kconfig"
+
 config VMI
 	bool "VMI Paravirt-ops support"
 	depends on PARAVIRT

arch/i386/Makefile

View file

diff --git a/arch/i386/Makefile b/arch/i386/Makefile
index 181cc29..01f0ff0 100644
--- a/arch/i386/Makefile
+++ b/arch/i386/Makefile
@@ -93,6 +93,9 @@ mflags-$(CONFIG_X86_ES7000)	:= -Iinclude/asm-i386/mach-es7000
 mcore-$(CONFIG_X86_ES7000)	:= mach-default
 core-$(CONFIG_X86_ES7000)	:= arch/i386/mach-es7000/
 
+# Xen paravirtualization support
+core-$(CONFIG_XEN)		+= arch/i386/xen/
+
 # default subarch .h files
 mflags-y += -Iinclude/asm-i386/mach-default
 

arch/i386/boot/compressed/relocs.c

View file

diff --git a/arch/i386/boot/compressed/relocs.c b/arch/i386/boot/compressed/relocs.c
index ce4fda2..b0e21c3 100644
--- a/arch/i386/boot/compressed/relocs.c
+++ b/arch/i386/boot/compressed/relocs.c
@@ -31,6 +31,8 @@ static const char* safe_abs_relocs[] = {
 		"__kernel_rt_sigreturn",
 		"__kernel_sigreturn",
 		"SYSENTER_RETURN",
+		"xen_irq_disable_direct_reloc",
+		"xen_save_fl_direct_reloc",
 };
 
 static int is_safe_abs_reloc(const char* sym_name)

arch/i386/kernel/asm-offsets.c

View file

diff --git a/arch/i386/kernel/asm-offsets.c b/arch/i386/kernel/asm-offsets.c
index 27a776c..25f7eb5 100644
--- a/arch/i386/kernel/asm-offsets.c
+++ b/arch/i386/kernel/asm-offsets.c
@@ -17,6 +17,8 @@
 #include <asm/thread_info.h>
 #include <asm/elf.h>
 
+#include <xen/interface/xen.h>
+
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))
 
@@ -59,6 +61,7 @@ void foo(void)
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
 	OFFSET(TI_restart_block, thread_info, restart_block);
 	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+	OFFSET(TI_cpu, thread_info, cpu);
 	BLANK();
 
 	OFFSET(GDS_size, Xgt_desc_struct, size);
@@ -115,4 +118,10 @@ void foo(void)
 	OFFSET(PARAVIRT_iret, paravirt_ops, iret);
 	OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0);
 #endif
+
+#ifdef CONFIG_XEN
+	BLANK();
+	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
+	OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
+#endif
 }

arch/i386/kernel/entry.S

View file

diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 3c3c220..32980b8 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -1023,6 +1023,91 @@ ENTRY(kernel_thread_helper)
 	CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
 
+#ifdef CONFIG_XEN
+ENTRY(xen_hypervisor_callback)
+	CFI_STARTPROC
+	pushl $0
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	TRACE_IRQS_OFF
+
+	/* Check to see if we got the event in the critical
+	   region in xen_iret_direct, after we've reenabled
+	   events and checked for pending events.  This simulates
+	   iret instruction's behaviour where it delivers a
+	   pending interrupt when enabling interrupts. */
+	movl PT_EIP(%esp),%eax
+	cmpl $xen_iret_start_crit,%eax
+	jb   1f
+	cmpl $xen_iret_end_crit,%eax
+	jae  1f
+
+	call xen_iret_crit_fixup
+
+1:	mov %esp, %eax
+	call xen_evtchn_do_upcall
+	jmp  ret_from_intr
+	CFI_ENDPROC
+ENDPROC(xen_hypervisor_callback)
+
+# Hypervisor uses this for application faults while it executes.
+# We get here for two reasons:
+#  1. Fault while reloading DS, ES, FS or GS
+#  2. Fault while executing IRET
+# Category 1 we fix up by reattempting the load, and zeroing the segment
+# register if the load fails.
+# Category 2 we fix up by jumping to do_iret_error. We cannot use the
+# normal Linux return path in this case because if we use the IRET hypercall
+# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+# We distinguish between categories by maintaining a status value in EAX.
+ENTRY(xen_failsafe_callback)
+	CFI_STARTPROC
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	movl $1,%eax
+1:	mov 4(%esp),%ds
+2:	mov 8(%esp),%es
+3:	mov 12(%esp),%fs
+4:	mov 16(%esp),%gs
+	testl %eax,%eax
+	popl %eax
+	CFI_ADJUST_CFA_OFFSET -4
+	lea 16(%esp),%esp
+	CFI_ADJUST_CFA_OFFSET -16
+	jz 5f
+	addl $16,%esp
+	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
+5:	pushl $0		# EAX == 0 => Category 1 (Bad segment)
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	jmp ret_from_exception
+	CFI_ENDPROC
+
+.section .fixup,"ax"
+6:	xorl %eax,%eax
+	movl %eax,4(%esp)
+	jmp 1b
+7:	xorl %eax,%eax
+	movl %eax,8(%esp)
+	jmp 2b
+8:	xorl %eax,%eax
+	movl %eax,12(%esp)
+	jmp 3b
+9:	xorl %eax,%eax
+	movl %eax,16(%esp)
+	jmp 4b
+.previous
+.section __ex_table,"a"
+	.align 4
+	.long 1b,6b
+	.long 2b,7b
+	.long 3b,8b
+	.long 4b,9b
+.previous
+ENDPROC(xen_failsafe_callback)
+
+#endif	/* CONFIG_XEN */
+
 .section .rodata,"a"
 #include "syscall_table.S"
 

arch/i386/kernel/head.S

View file

diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index 8271466..7c52b22 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -510,7 +510,8 @@ ENTRY(_stext)
 /*
  * BSS section
  */
-.section ".bss.page_aligned","w"
+.section ".bss.page_aligned","wa"
+	.align PAGE_SIZE_asm
 ENTRY(swapper_pg_dir)
 	.fill 1024,4,0
 ENTRY(swapper_pg_pmd)
@@ -538,6 +539,8 @@ fault_msg:
 	.ascii "Int %d: CR2 %p  err %p  EIP %p  CS %p  flags %p\n"
 	.asciz "Stack: %p %p %p %p %p %p %p %p\n"
 
+#include "../xen/xen-head.S"
+
 /*
  * The IDT and GDT 'descriptors' are a strange 48-bit object
  * only used by the lidt and lgdt instructions. They are not

arch/i386/kernel/paravirt.c

View file

diff --git a/arch/i386/kernel/paravirt.c b/arch/i386/kernel/paravirt.c
index faab09a..53f07a8 100644
--- a/arch/i386/kernel/paravirt.c
+++ b/arch/i386/kernel/paravirt.c
@@ -228,6 +228,41 @@ static int __init print_banner(void)
 }
 core_initcall(print_banner);
 
+static struct resource reserve_ioports = {
+	.start = 0,
+	.end = IO_SPACE_LIMIT,
+	.name = "paravirt-ioport",
+	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
+};
+
+static struct resource reserve_iomem = {
+	.start = 0,
+	.end = -1,
+	.name = "paravirt-iomem",
+	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
+};
+
+/*
+ * Reserve the whole legacy IO space to prevent any legacy drivers
+ * from wasting time probing for their hardware.  This is a fairly
+ * brute-force approach to disabling all non-virtual drivers.
+ *
+ * Note that this must be called very early to have any effect.
+ */
+int paravirt_disable_iospace(void)
+{
+	int ret;
+
+	ret = request_resource(&ioport_resource, &reserve_ioports);
+	if (ret == 0) {
+		ret = request_resource(&iomem_resource, &reserve_iomem);
+		if (ret)
+			release_resource(&reserve_ioports);
+	}
+
+	return ret;
+}
+
 struct paravirt_ops paravirt_ops = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -267,7 +302,7 @@ struct paravirt_ops paravirt_ops = {
 	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
-	.get_scheduled_cycles = native_read_tsc,
+	.sched_clock = native_sched_clock,
 	.get_cpu_khz = native_calculate_cpu_khz,
 	.load_tr_desc = native_load_tr_desc,
 	.set_ldt = native_set_ldt,

arch/i386/kernel/setup.c

View file

diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index 2d61e65..74871d0 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -601,6 +601,8 @@ void __init setup_arch(char **cmdline_p)
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
 
+	paravirt_post_allocator_init();
+
 	dmi_scan_machine();
 
 #ifdef CONFIG_X86_GENERICARCH

arch/i386/kernel/smp.c

View file

diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c
index 6299c08..2d35d85 100644
--- a/arch/i386/kernel/smp.c
+++ b/arch/i386/kernel/smp.c
@@ -22,6 +22,7 @@
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
 #include <mach_apic.h>
 
 /*
@@ -249,13 +250,13 @@ static unsigned long flush_va;
 static DEFINE_SPINLOCK(tlbstate_lock);
 
 /*
- * We cannot call mmdrop() because we are in interrupt context, 
+ * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
  *
  * We need to reload %cr3 since the page tables may be going
  * away from under us..
  */
-static inline void leave_mm (unsigned long cpu)
+void leave_mm(unsigned long cpu)
 {
 	if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
 		BUG();

arch/i386/kernel/smpboot.c

View file

diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 0b29545..5910d3f 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -148,7 +148,7 @@ void __init smp_alloc_memory(void)
  * a given CPU
  */
 
-static void __cpuinit smp_store_cpu_info(int id)
+void __cpuinit smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = cpu_data + id;
 
@@ -308,8 +308,7 @@ cpumask_t cpu_coregroup_map(int cpu)
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
-static inline void
-set_cpu_sibling_map(int cpu)
+void set_cpu_sibling_map(int cpu)
 {
 	int i;
 	struct cpuinfo_x86 *c = cpu_data;
@@ -1144,8 +1143,7 @@ void __init native_smp_prepare_boot_cpu(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void
-remove_siblinginfo(int cpu)
+void remove_siblinginfo(int cpu)
 {
 	int sibling;
 	struct cpuinfo_x86 *c = cpu_data;

arch/i386/kernel/tsc.c

View file

diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c
index ea63a30..252f901 100644
--- a/arch/i386/kernel/tsc.c
+++ b/arch/i386/kernel/tsc.c
@@ -84,7 +84,7 @@ static inline int check_tsc_unstable(void)
  *
  *			[email protected] "math is hard, lets go shopping!"
  */
-static unsigned long cyc2ns_scale __read_mostly;
+unsigned long cyc2ns_scale __read_mostly;
 
 #define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
 
@@ -93,15 +93,10 @@ static inline void set_cyc2ns_scale(unsigned long cpu_khz)
 	cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR)/cpu_khz;
 }
 
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
-	return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
-}
-
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
-unsigned long long sched_clock(void)
+unsigned long long native_sched_clock(void)
 {
 	unsigned long long this_offset;
 
@@ -118,12 +113,24 @@ unsigned long long sched_clock(void)
 		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 
 	/* read the Time Stamp Counter: */
-	get_scheduled_cycles(this_offset);
+	rdtscll(this_offset);
 
 	/* return the value in ns */
 	return cycles_2_ns(this_offset);
 }
 
+/* We need to define a real function for sched_clock, to override the
+   weak default version */
+#ifdef CONFIG_PARAVIRT
+unsigned long long sched_clock(void)
+{
+	return paravirt_sched_clock();
+}
+#else
+unsigned long long sched_clock(void)
+	__attribute__((alias("native_sched_clock")));
+#endif
+
 unsigned long native_calculate_cpu_khz(void)
 {
 	unsigned long long start, end;

arch/i386/kernel/vmi.c

View file

diff --git a/arch/i386/kernel/vmi.c b/arch/i386/kernel/vmi.c
index c12720d..72042bb 100644
--- a/arch/i386/kernel/vmi.c
+++ b/arch/i386/kernel/vmi.c
@@ -362,7 +362,7 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
 }
 #endif
 
-static void vmi_allocate_pt(u32 pfn)
+static void vmi_allocate_pt(struct mm_struct *mm, u32 pfn)
 {
 	vmi_set_page_type(pfn, VMI_PAGE_L1);
 	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
@@ -891,7 +891,7 @@ static inline int __init activate_vmi(void)
 		paravirt_ops.setup_boot_clock = vmi_time_bsp_init;
 		paravirt_ops.setup_secondary_clock = vmi_time_ap_init;
 #endif
-		paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles;
+		paravirt_ops.sched_clock = vmi_sched_clock;
  		paravirt_ops.get_cpu_khz = vmi_cpu_khz;
 
 		/* We have true wallclock functions; disable CMOS clock sync */

arch/i386/kernel/vmiclock.c

View file

diff --git a/arch/i386/kernel/vmiclock.c b/arch/i386/kernel/vmiclock.c
index 26a37f8..f9b845f 100644
--- a/arch/i386/kernel/vmiclock.c
+++ b/arch/i386/kernel/vmiclock.c
@@ -64,10 +64,10 @@ int vmi_set_wallclock(unsigned long now)
 	return 0;
 }
 
-/* paravirt_ops.get_scheduled_cycles = vmi_get_sched_cycles */
-unsigned long long vmi_get_sched_cycles(void)
+/* paravirt_ops.sched_clock = vmi_sched_clock */
+unsigned long long vmi_sched_clock(void)
 {
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE);
+	return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
 }
 
 /* paravirt_ops.get_cpu_khz = vmi_cpu_khz */

arch/i386/kernel/vmlinux.lds.S

View file

diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S
index aa87b06..00f1bc4 100644
--- a/arch/i386/kernel/vmlinux.lds.S
+++ b/arch/i386/kernel/vmlinux.lds.S
@@ -88,6 +88,7 @@ SECTIONS
 
   . = ALIGN(4096);
   .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
+	*(.data.page_aligned)
 	*(.data.idt)
   }
 

arch/i386/kernel/vsyscall-note.S

View file

diff --git a/arch/i386/kernel/vsyscall-note.S b/arch/i386/kernel/vsyscall-note.S
index d4b5be4..271f16a 100644
--- a/arch/i386/kernel/vsyscall-note.S
+++ b/arch/i386/kernel/vsyscall-note.S
@@ -3,23 +3,40 @@
  * Here we can supply some information useful to userland.
  */
 
-#include <linux/uts.h>
 #include <linux/version.h>
+#include <linux/elfnote.h>
 
-#define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type)			      \
-	.section name, flags;						      \
-	.balign 4;							      \
-	.long 1f - 0f;		/* name length */			      \
-	.long 3f - 2f;		/* data length */			      \
-	.long type;		/* note type */				      \
-0:	.asciz vendor;		/* vendor name */			      \
-1:	.balign 4;							      \
-2:
+/* Ideally this would use UTS_NAME, but using a quoted string here
+   doesn't work. Remember to change this when changing the
+   kernel's name. */
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
 
-#define ASM_ELF_NOTE_END						      \
-3:	.balign 4;		/* pad out section */			      \
-	.previous
+#ifdef CONFIG_XEN
 
-	ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0)
-	.long LINUX_VERSION_CODE
-	ASM_ELF_NOTE_END
+/*
+ * Add a special note telling glibc's dynamic linker a fake hardware
+ * flavor that it will use to choose the search path for libraries in the
+ * same way it uses real hardware capabilities like "mmx".
+ * We supply "nosegneg" as the fake capability, to indicate that we
+ * do not like negative offsets in instructions using segment overrides,
+ * since we implement those inefficiently.  This makes it possible to
+ * install libraries optimized to avoid those access patterns in someplace
+ * like /lib/i686/tls/nosegneg.  Note that an /etc/ld.so.conf.d/file
+ * corresponding to the bits here is needed to make ldconfig work right.
+ * It should contain:
+ *	hwcap 1 nosegneg
+ * to match the mapping of bit to name that we give here.
+ */
+
+/* Bit used for the pseudo-hwcap for non-negative segments.  We use
+   bit 1 to avoid bugs in some versions of glibc when bit 0 is
+   used; the choice is otherwise arbitrary. */
+#define VDSO_NOTE_NONEGSEG_BIT	1
+
+ELFNOTE_START(GNU, 2, "a")
+	.long 1, 1<<VDSO_NOTE_NONEGSEG_BIT		/* ncaps, mask */
+	.byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg"	/* bit, name */
+ELFNOTE_END
+#endif

arch/i386/mach-voyager/voyager_thread.c

View file

diff --git a/arch/i386/mach-voyager/voyager_thread.c b/arch/i386/mach-voyager/voyager_thread.c
index b4b24e0..f9d5953 100644
--- a/arch/i386/mach-voyager/voyager_thread.c
+++ b/arch/i386/mach-voyager/voyager_thread.c
@@ -52,7 +52,7 @@ execute(const char *string)
 		NULL,
 	};
 
-	if ((ret = call_usermodehelper(argv[0], argv, envp, 1)) != 0) {
+	if ((ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC)) != 0) {
 		printk(KERN_ERR "Voyager failed to run \"%s\": %i\n",
 		       string, ret);
 	}

arch/i386/mm/init.c

View file

diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 7135946..6a68b1a 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -87,7 +87,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
 		pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
 
-		paravirt_alloc_pt(__pa(page_table) >> PAGE_SHIFT);
+		paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
 		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
 	}
@@ -473,6 +473,7 @@ void zap_low_mappings (void)
 
 static int disable_nx __initdata = 0;
 u64 __supported_pte_mask __read_mostly = ~_PAGE_NX;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 /*
  * noexec = on|off

arch/i386/mm/pageattr.c

View file

diff --git a/arch/i386/mm/pageattr.c b/arch/i386/mm/pageattr.c
index 2eb14a7..37992ff 100644
--- a/arch/i386/mm/pageattr.c
+++ b/arch/i386/mm/pageattr.c
@@ -60,7 +60,7 @@ static struct page *split_large_page(unsigned long address, pgprot_t prot,
 	address = __pa(address);
 	addr = address & LARGE_PAGE_MASK; 
 	pbase = (pte_t *)page_address(base);
-	paravirt_alloc_pt(page_to_pfn(base));
+	paravirt_alloc_pt(&init_mm, page_to_pfn(base));
 	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
                set_pte(&pbase[i], pfn_pte(addr >> PAGE_SHIFT,
                                           addr == address ? prot : ref_prot));

arch/i386/xen/Kconfig

View file

diff --git a/arch/i386/xen/Kconfig b/arch/i386/xen/Kconfig
new file mode 100644
index 0000000..9df99e1
--- /dev/null
+++ b/arch/i386/xen/Kconfig
@@ -0,0 +1,11 @@
+#
+# This Kconfig describes xen options
+#
+
+config XEN
+	bool "Enable support for Xen hypervisor"
+	depends on PARAVIRT && X86_CMPXCHG && X86_TSC && !NEED_MULTIPLE_NODES
+	help
+	  This is the Linux Xen port.  Enabling this will allow the
+	  kernel to boot in a paravirtualized environment under the
+	  Xen hypervisor.

arch/i386/xen/Makefile

View file

diff --git a/arch/i386/xen/Makefile b/arch/i386/xen/Makefile
new file mode 100644
index 0000000..343df24
--- /dev/null
+++ b/arch/i386/xen/Makefile
@@ -0,0 +1,4 @@
+obj-y		:= enlighten.o setup.o features.o multicalls.o mmu.o \
+			events.o time.o manage.o xen-asm.o
+
+obj-$(CONFIG_SMP)	+= smp.o

arch/i386/xen/enlighten.c

View file

diff --git a/arch/i386/xen/enlighten.c b/arch/i386/xen/enlighten.c
new file mode 100644
index 0000000..9a8c118
--- /dev/null
+++ b/arch/i386/xen/enlighten.c
@@ -0,0 +1,1144 @@
+/*
+ * Core of Xen paravirt_ops implementation.
+ *
+ * This file contains the xen_paravirt_ops structure itself, and the
+ * implementations for:
+ * - privileged instructions
+ * - interrupt flags
+ * - segment operations
+ * - booting and setup
+ *
+ * Jeremy Fitzhardinge <[email protected]>, XenSource Inc, 2007
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/preempt.h>
+#include <linux/hardirq.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/start_kernel.h>
+#include <linux/sched.h>
+#include <linux/bootmem.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/page-flags.h>
+#include <linux/highmem.h>
+#include <linux/smp.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/physdev.h>