Imported linux-2.6.27.39 suse/xen patches.

[ipfire-2.x.git] / src / patches / suse-2.6.27.39 / patches.kernel.org / patch-2.6.27.36-37

From: Greg Kroah-Hartman <gregkh@suse.de>
Subject: Linux 2.6.27.37

Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/Makefile b/Makefile
index e7046ea..e063536 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 27
-EXTRAVERSION = .36
+EXTRAVERSION = .37
 NAME = Trembling Tortoise
 
 # *DOCUMENTATION*
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 5e65290..09b59b2 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -21,8 +21,8 @@
 #define __AUDIT_ARCH_LE	   0x40000000
 
 #ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit int_ret_from_sys_call
-#define sysretl_audit int_ret_from_sys_call
+#define sysexit_audit ia32_ret_from_sys_call
+#define sysretl_audit ia32_ret_from_sys_call
 #endif
 
 #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
@@ -39,12 +39,12 @@
 	.endm 
 
 	/* clobbers %eax */	
-	.macro  CLEAR_RREGS
+	.macro  CLEAR_RREGS offset=0, _r9=rax
 	xorl 	%eax,%eax
-	movq	%rax,R11(%rsp)
-	movq	%rax,R10(%rsp)
-	movq	%rax,R9(%rsp)
-	movq	%rax,R8(%rsp)
+	movq	%rax,\offset+R11(%rsp)
+	movq	%rax,\offset+R10(%rsp)
+	movq	%\_r9,\offset+R9(%rsp)
+	movq	%rax,\offset+R8(%rsp)
 	.endm
 
 	/*
@@ -52,11 +52,10 @@
 	 * We don't reload %eax because syscall_trace_enter() returned
 	 * the value it wants us to use in the table lookup.
 	 */
-	.macro LOAD_ARGS32 offset
-	movl \offset(%rsp),%r11d
-	movl \offset+8(%rsp),%r10d
+	.macro LOAD_ARGS32 offset, _r9=0
+	.if \_r9
 	movl \offset+16(%rsp),%r9d
-	movl \offset+24(%rsp),%r8d
+	.endif
 	movl \offset+40(%rsp),%ecx
 	movl \offset+48(%rsp),%edx
 	movl \offset+56(%rsp),%esi
@@ -145,7 +144,7 @@ ENTRY(ia32_sysenter_target)
 	SAVE_ARGS 0,0,1
  	/* no need to do an access_ok check here because rbp has been
  	   32bit zero extended */ 
-1:	movl	(%rbp),%r9d
+1:	movl	(%rbp),%ebp
  	.section __ex_table,"a"
  	.quad 1b,ia32_badarg
  	.previous	
@@ -157,7 +156,7 @@ ENTRY(ia32_sysenter_target)
 	cmpl	$(IA32_NR_syscalls-1),%eax
 	ja	ia32_badsys
 sysenter_do_call:
-	IA32_ARG_FIXUP 1
+	IA32_ARG_FIXUP
 sysenter_dispatch:
 	call	*ia32_sys_call_table(,%rax,8)
 	movq	%rax,RAX-ARGOFFSET(%rsp)
@@ -173,6 +172,10 @@ sysexit_from_sys_call:
 	movl	RIP-R11(%rsp),%edx		/* User %eip */
 	CFI_REGISTER rip,rdx
 	RESTORE_ARGS 1,24,1,1,1,1
+	xorq	%r8,%r8
+	xorq	%r9,%r9
+	xorq	%r10,%r10
+	xorq	%r11,%r11
 	popfq
 	CFI_ADJUST_CFA_OFFSET -8
 	/*CFI_RESTORE rflags*/
@@ -203,7 +206,7 @@ sysexit_from_sys_call:
 
 	.macro auditsys_exit exit,ebpsave=RBP
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
-	jnz int_ret_from_sys_call
+	jnz ia32_ret_from_sys_call
 	TRACE_IRQS_ON
 	sti
 	movl %eax,%esi		/* second arg, syscall return value */
@@ -219,8 +222,9 @@ sysexit_from_sys_call:
 	cli
 	TRACE_IRQS_OFF
 	testl %edi,TI_flags(%r10)
-	jnz int_with_check
-	jmp \exit
+	jz \exit
+	CLEAR_RREGS -ARGOFFSET
+	jmp int_with_check
 	.endm
 
 sysenter_auditsys:
@@ -234,20 +238,17 @@ sysexit_audit:
 #endif
 
 sysenter_tracesys:
-	xchgl	%r9d,%ebp
 #ifdef CONFIG_AUDITSYSCALL
 	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
 	jz	sysenter_auditsys
 #endif
 	SAVE_REST
 	CLEAR_RREGS
-	movq	%r9,R9(%rsp)
 	movq	$-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
 	movq	%rsp,%rdi        /* &pt_regs -> arg1 */
 	call	syscall_trace_enter
 	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
-	xchgl	%ebp,%r9d
 	cmpl	$(IA32_NR_syscalls-1),%eax
 	ja	int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
 	jmp	sysenter_do_call
@@ -314,9 +315,9 @@ ENTRY(ia32_cstar_target)
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
 	CFI_REMEMBER_STATE
 	jnz   cstar_tracesys
-cstar_do_call:	
 	cmpl $IA32_NR_syscalls-1,%eax
 	ja  ia32_badsys
+cstar_do_call:
 	IA32_ARG_FIXUP 1
 cstar_dispatch:
 	call *ia32_sys_call_table(,%rax,8)
@@ -333,6 +334,9 @@ sysretl_from_sys_call:
 	CFI_REGISTER rip,rcx
 	movl EFLAGS-ARGOFFSET(%rsp),%r11d	
 	/*CFI_REGISTER rflags,r11*/
+	xorq	%r10,%r10
+	xorq	%r9,%r9
+	xorq	%r8,%r8
 	TRACE_IRQS_ON
 	movl RSP-ARGOFFSET(%rsp),%esp
 	CFI_RESTORE rsp
@@ -357,15 +361,13 @@ cstar_tracesys:
 #endif
 	xchgl %r9d,%ebp
 	SAVE_REST
-	CLEAR_RREGS
-	movq %r9,R9(%rsp)
+	CLEAR_RREGS 0, r9
 	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
 	movq %rsp,%rdi        /* &pt_regs -> arg1 */
 	call syscall_trace_enter
-	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
+	LOAD_ARGS32 ARGOFFSET, 1  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
 	xchgl %ebp,%r9d
-	movl RSP-ARGOFFSET(%rsp), %r8d
 	cmpl $(IA32_NR_syscalls-1),%eax
 	ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
 	jmp cstar_do_call
@@ -431,6 +433,8 @@ ia32_do_call:
 	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 ia32_sysret:
 	movq %rax,RAX-ARGOFFSET(%rsp)
+ia32_ret_from_sys_call:
+	CLEAR_RREGS -ARGOFFSET
 	jmp int_ret_from_sys_call 
 
 ia32_tracesys:			 
@@ -448,8 +452,8 @@ END(ia32_syscall)
 
 ia32_badsys:
 	movq $0,ORIG_RAX-ARGOFFSET(%rsp)
-	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
-	jmp int_ret_from_sys_call
+	movq $-ENOSYS,%rax
+	jmp ia32_sysret
 
 quiet_ni_syscall:
 	movq $-ENOSYS,%rax
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f7c7142..60ebfd7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2571,6 +2571,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		a3 &= 0xFFFFFFFF;
 	}
 
+	if (kvm_x86_ops->get_cpl(vcpu) != 0) {
+		ret = -KVM_EPERM;
+		goto out;
+	}
+
 	switch (nr) {
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
@@ -2582,6 +2587,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		ret = -KVM_ENOSYS;
 		break;
 	}
+out:
 	vcpu->arch.regs[VCPU_REGS_RAX] = ret;
 	kvm_x86_ops->decache_regs(vcpu);
 	++vcpu->stat.hypercalls;
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 56fe712..47dd8f5 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -29,13 +29,26 @@
 #include <linux/random.h>
 #include <linux/limits.h>
 #include <linux/sched.h>
+#include <asm/elf.h>
+
+static unsigned int stack_maxrandom_size(void)
+{
+	unsigned int max = 0;
+	if ((current->flags & PF_RANDOMIZE) &&
+		!(current->personality & ADDR_NO_RANDOMIZE)) {
+		max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT;
+	}
+
+	return max;
+}
+
 
 /*
  * Top of mmap area (just below the process stack).
  *
- * Leave an at least ~128 MB hole.
+ * Leave an at least ~128 MB hole with possible stack randomization.
  */
-#define MIN_GAP (128*1024*1024)
+#define MIN_GAP (128*1024*1024UL + stack_maxrandom_size())
 #define MAX_GAP (TASK_SIZE/6*5)
 
 /*
diff --git a/drivers/net/iseries_veth.c b/drivers/net/iseries_veth.c
index c46864d..e1db78a 100644
--- a/drivers/net/iseries_veth.c
+++ b/drivers/net/iseries_veth.c
@@ -495,7 +495,7 @@ static void veth_take_cap_ack(struct veth_lpar_connection *cnx,
 			   cnx->remote_lp);
 	} else {
 		memcpy(&cnx->cap_ack_event, event,
-		       sizeof(&cnx->cap_ack_event));
+		       sizeof(cnx->cap_ack_event));
 		cnx->state |= VETH_STATE_GOTCAPACK;
 		veth_kick_statemachine(cnx);
 	}
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index 763c1ea..dad4fe6 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -47,6 +47,7 @@
 #define PCI_BIOS32_PARAGRAPH_LEN	16
 #define PCI_ROM_BASE1			0x000F0000
 #define ROM_SIZE			0x10000
+#define HPWDT_VERSION			"1.01"
 
 struct bios32_service_dir {
 	u32 signature;
@@ -130,12 +131,8 @@ static void *cru_rom_addr;
 static struct cmn_registers cmn_regs;
 
 static struct pci_device_id hpwdt_devices[] = {
-	{
-	 .vendor = PCI_VENDOR_ID_COMPAQ,
-	 .device = 0xB203,
-	 .subvendor = PCI_ANY_ID,
-	 .subdevice = PCI_ANY_ID,
-	},
+	{ PCI_DEVICE(PCI_VENDOR_ID_COMPAQ, 0xB203) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_HP, 0x3306) },
 	{0},			/* terminate list */
 };
 MODULE_DEVICE_TABLE(pci, hpwdt_devices);
@@ -704,10 +701,11 @@ static int __devinit hpwdt_init_one(struct pci_dev *dev,
 	}
 
 	printk(KERN_INFO
-		"hp Watchdog Timer Driver: 1.00"
+		"hp Watchdog Timer Driver: %s"
 		", timer margin: %d seconds (nowayout=%d)"
 		", allow kernel dump: %s (default = 0/OFF).\n",
-		soft_margin, nowayout, (allow_kdump == 0) ? "OFF" : "ON");
+		HPWDT_VERSION, soft_margin, nowayout,
+		(allow_kdump == 0) ? "OFF" : "ON");
 
 	return 0;
 
@@ -757,6 +755,7 @@ static int __init hpwdt_init(void)
 MODULE_AUTHOR("Tom Mingarelli");
 MODULE_DESCRIPTION("hp watchdog driver");
 MODULE_LICENSE("GPL");
+MODULE_VERSION(HPWDT_VERSION);
 MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
 
 module_param(soft_margin, int, 0);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 5e78fc1..1c1220e 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -443,6 +443,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct inode *lower_dir_inode = ecryptfs_inode_to_lower(dir);
 	struct dentry *lower_dir_dentry;
 
+	dget(lower_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
 	rc = vfs_unlink(lower_dir_inode, lower_dentry);
 	if (rc) {
@@ -456,6 +457,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry)
 	d_drop(dentry);
 out_unlock:
 	unlock_dir(lower_dir_dentry);
+	dput(lower_dentry);
 	return rc;
 }
 
diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h
index 7be4733..36343b6 100644
--- a/include/asm-x86/elf.h
+++ b/include/asm-x86/elf.h
@@ -287,6 +287,8 @@ do {									\
 
 #ifdef CONFIG_X86_32
 
+#define STACK_RND_MASK (0x7ff)
+
 #define VDSO_HIGH_BASE		(__fix_to_virt(FIX_VDSO))
 
 #define ARCH_DLINFO		ARCH_DLINFO_IA32(vdso_enabled)
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index 3ddce03..d731092 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -13,6 +13,7 @@
 #define KVM_ENOSYS		1000
 #define KVM_EFAULT		EFAULT
 #define KVM_E2BIG		E2BIG
+#define KVM_EPERM		EPERM
 
 #define KVM_HC_VAPIC_POLL_IRQ		1
 #define KVM_HC_MMU_OP			2
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 521960b..6e22c16 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -477,6 +477,28 @@ void update_wall_time(void)
 	/* correct the clock when NTP error is too big */
 	clocksource_adjust(offset);
 
+	/*
+	 * Since in the loop above, we accumulate any amount of time
+	 * in xtime_nsec over a second into xtime.tv_sec, its possible for
+	 * xtime_nsec to be fairly small after the loop. Further, if we're
+	 * slightly speeding the clocksource up in clocksource_adjust(),
+	 * its possible the required corrective factor to xtime_nsec could
+	 * cause it to underflow.
+	 *
+	 * Now, we cannot simply roll the accumulated second back, since
+	 * the NTP subsystem has been notified via second_overflow. So
+	 * instead we push xtime_nsec forward by the amount we underflowed,
+	 * and add that amount into the error.
+	 *
+	 * We'll correct this error next time through this function, when
+ 	 * xtime_nsec is not as small.
+	 */
+	if (unlikely((s64)clock->xtime_nsec < 0)) {
+		s64 neg = -(s64)clock->xtime_nsec;
+		clock->xtime_nsec = 0;
+		clock->error += neg << (NTP_SCALE_SHIFT - clock->shift);
+	}
+
 	/* store full nanoseconds into xtime */
 	xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift;
 	clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift;