[0/8] 2.6.27.37-stable review

[0/8] 2.6.27.37-stable review

[Greg KH, gregkh]

This is the start of the stable review cycle for the 2.6.27.37 release.
There are 8 patches in this series, all will be posted as a response to
this one.  If anyone has any issues with these being applied, please let
us know.  If anyone is a maintainer of the proper subsystem, and wants
to add a Signed-off-by: line to the patch, please respond with it.

Responses should be made by Sunday October 11, 23:00:00 UTC.  Anything
received after that time might be too late.

The whole patch series can be found in one patch at:
	kernel.org/pub/linux/kernel/v2.6/stable-review/patch-2.6.27.37-rc1.gz
and the diffstat can be found below.


thanks,

greg k-h

 Makefile                   |    2 +-
 arch/x86/ia32/ia32entry.S  |   56 +++++++++++++++++++++++--------------------
 arch/x86/kvm/x86.c         |    6 ++++
 arch/x86/mm/mmap.c         |   17 +++++++++++-
 drivers/net/iseries_veth.c |    2 +-
 drivers/watchdog/hpwdt.c   |   15 +++++------
 fs/ecryptfs/inode.c        |    2 +
 include/asm-x86/elf.h      |    2 +
 include/linux/kvm_para.h   |    1 +
 kernel/time/timekeeping.c  |   22 +++++++++++++++++
 10 files changed, 87 insertions(+), 38 deletions(-)

[1/8] net: Fix wrong sizeof

[Greg KH, gregkh]

[-- Attachment #1: net-fix-wrong-sizeof.patch --]
[-- Type: text/plain, Size: 821 bytes --]

From: Jean Delvare <khali@linux-fr.org>

commit b607bd900051efc3308c4edc65dd98b34b230021 upstream.

Which is why I have always preferred sizeof(struct foo) over
sizeof(var).

Signed-off-by: Jean Delvare <khali@linux-fr.org>
Acked-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/iseries_veth.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/iseries_veth.c
+++ b/drivers/net/iseries_veth.c
@@ -495,7 +495,7 @@ static void veth_take_cap_ack(struct vet
 			   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);
 	}

[2/8] x86-64: slightly stream-line 32-bit syscall entry code

[Greg KH, gregkh]

[-- Attachment #1: x86-64-slightly-stream-line-32-bit-syscall-entry-code.patch --]
[-- Type: text/plain, Size: 3412 bytes --]

From: Jan Beulich <jbeulich@novell.com>

commit 295286a89107c353b9677bc604361c537fd6a1c0 upstream

x86-64: slightly stream-line 32-bit syscall entry code

[ required for following patch to apply properly ]

Avoid updating registers or memory twice as well as needlessly loading
or copying registers.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/ia32/ia32entry.S |   26 ++++++++++----------------
 1 file changed, 10 insertions(+), 16 deletions(-)

--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -39,11 +39,11 @@
 	.endm 
 
 	/* clobbers %eax */	
-	.macro  CLEAR_RREGS
+	.macro  CLEAR_RREGS _r9=rax
 	xorl 	%eax,%eax
 	movq	%rax,R11(%rsp)
 	movq	%rax,R10(%rsp)
-	movq	%rax,R9(%rsp)
+	movq	%\_r9,R9(%rsp)
 	movq	%rax,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)
@@ -234,20 +233,17 @@ 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 +310,9 @@ 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)
@@ -357,15 +353,13 @@ cstar_tracesys:
 #endif
 	xchgl %r9d,%ebp
 	SAVE_REST
-	CLEAR_RREGS
-	movq %r9,R9(%rsp)
+	CLEAR_RREGS 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

[3/8] x86: Dont leak 64-bit kernel register values to 32-bit processes

[Greg KH, gregkh]

[-- Attachment #1: x86-don-t-leak-64-bit-kernel-register-values-to-32-bit-processes.patch --]
[-- Type: text/plain, Size: 3336 bytes --]

From: Jan Beulich <JBeulich@novell.com>

commit 24e35800cdc4350fc34e2bed37b608a9e13ab3b6 upstream

x86: Don't leak 64-bit kernel register values to 32-bit processes

While 32-bit processes can't directly access R8...R15, they can
gain access to these registers by temporarily switching themselves
into 64-bit mode.

Therefore, registers not preserved anyway by called C functions
(i.e. R8...R11) must be cleared prior to returning to user mode.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
LKML-Reference: <4AC34D73020000780001744A@vpn.id2.novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/ia32/ia32entry.S |   36 +++++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 13 deletions(-)

--- 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 _r9=rax
+	.macro  CLEAR_RREGS offset=0, _r9=rax
 	xorl 	%eax,%eax
-	movq	%rax,R11(%rsp)
-	movq	%rax,R10(%rsp)
-	movq	%\_r9,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
 
 	/*
@@ -172,6 +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*/
@@ -202,7 +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 */
@@ -218,8 +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:
@@ -329,6 +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
@@ -353,7 +361,7 @@ cstar_tracesys:
 #endif
 	xchgl %r9d,%ebp
 	SAVE_REST
-	CLEAR_RREGS r9
+	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
@@ -425,6 +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:			 
@@ -442,8 +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

[4/8] eCryptfs: Prevent lower dentry from going negative during unlink (CVE-2009-2908)

[Greg KH, gregkh]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: ecryptfs-prevent-lower-dentry-from-going-negative-during-unlink.patch --]
[-- Type: text/plain, Size: 1845 bytes --]


From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>

commit 9c2d2056647790c5034d722bd24e9d913ebca73c upstream.

When calling vfs_unlink() on the lower dentry, d_delete() turns the
dentry into a negative dentry when the d_count is 1.  This eventually
caused a NULL pointer deref when a read() or write() was done and the
negative dentry's d_inode was dereferenced in
ecryptfs_read_update_atime() or ecryptfs_getxattr().

Placing mutt's tmpdir in an eCryptfs mount is what initially triggered
the oops and I was able to reproduce it with the following sequence:

open("/tmp/upper/foo", O_RDWR|O_CREAT|O_EXCL|O_NOFOLLOW, 0600) = 3
link("/tmp/upper/foo", "/tmp/upper/bar") = 0
unlink("/tmp/upper/foo")                = 0
open("/tmp/upper/bar", O_RDWR|O_CREAT|O_NOFOLLOW, 0600) = 4
unlink("/tmp/upper/bar")                = 0
write(4, "eCryptfs test\n"..., 14 <unfinished ...>
+++ killed by SIGKILL +++

https://bugs.launchpad.net/ecryptfs/+bug/387073

Reported-by: Loïc Minier <loic.minier@canonical.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: ecryptfs-devel@lists.launchpad.net
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Cc: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/ecryptfs/inode.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -443,6 +443,7 @@ static int ecryptfs_unlink(struct inode 
 	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 
 	d_drop(dentry);
 out_unlock:
 	unlock_dir(lower_dir_dentry);
+	dput(lower_dentry);
 	return rc;
 }
 

[5/8] x86: Increase MIN_GAP to include randomized stack

[Greg KH, gregkh]

[-- Attachment #1: x86-increase-min_gap-to-include-randomized-stack.patch --]
[-- Type: text/plain, Size: 2076 bytes --]

From: Michal Hocko <mhocko@suse.cz>

[ trivial backport to 2.6.27: Chuck Ebbert <cebbert@redhat.com> ]

commit 80938332d8cf652f6b16e0788cf0ca136befe0b5 upstream.

Currently we are not including randomized stack size when calculating
mmap_base address in arch_pick_mmap_layout for topdown case. This might
cause that mmap_base starts in the stack reserved area because stack is
randomized by 1GB for 64b (8MB for 32b) and the minimum gap is 128MB.

If the stack really grows down to mmap_base then we can get silent mmap
region overwrite by the stack values.

Let's include maximum stack randomization size into MIN_GAP which is
used as the low bound for the gap in mmap.

Signed-off-by: Michal Hocko <mhocko@suse.cz>
LKML-Reference: <1252400515-6866-1-git-send-email-mhocko@suse.cz>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>


---
 arch/x86/mm/mmap.c    |   17 +++++++++++++++--
 include/asm-x86/elf.h |    2 ++
 2 files changed, 17 insertions(+), 2 deletions(-)

--- 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)
 
 /*
--- 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)

[6/8] KVM: x86: Disallow hypercalls for guest callers in rings > 0 [CVE-2009-3290]

[Greg KH, gregkh]

[-- Attachment #1: kvm-x86-disallow-hypercalls-for-guest-callers-in-rings-0.patch --]
[-- Type: text/plain, Size: 1653 bytes --]


From: Jan Kiszka <jan.kiszka@siemens.com>

[ backport to 2.6.27 by Chuck Ebbert <cebbert@redhat.com> ]

commit 07708c4af1346ab1521b26a202f438366b7bcffd upstream.

So far unprivileged guest callers running in ring 3 can issue, e.g., MMU
hypercalls. Normally, such callers cannot provide any hand-crafted MMU
command structure as it has to be passed by its physical address, but
they can still crash the guest kernel by passing random addresses.

To close the hole, this patch considers hypercalls valid only if issued
from guest ring 0. This may still be relaxed on a per-hypercall base in
the future once required.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Cc: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kvm/x86.c       |    6 ++++++
 include/linux/kvm_para.h |    1 +
 2 files changed, 7 insertions(+)

--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2571,6 +2571,11 @@ int kvm_emulate_hypercall(struct kvm_vcp
 		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_vcp
 		ret = -KVM_ENOSYS;
 		break;
 	}
+out:
 	vcpu->arch.regs[VCPU_REGS_RAX] = ret;
 	kvm_x86_ops->decache_regs(vcpu);
 	++vcpu->stat.hypercalls;
--- 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

[7/8] [WATCHDOG] hpwdt.c: Add new HP BMC controller.

[Greg KH, gregkh]

[-- Attachment #1: hpwdt.c-add-new-hp-bmc-controller.patch --]
[-- Type: text/plain, Size: 1811 bytes --]

From: Thomas Mingarelli <Thomas.Mingarelli@hp.com>

commit d8100c3abfd32986a8820ce4e614b0223a2d22a9 upstream.

Add the PCI-ID for the upcoming new BMC controller for HP hardware.

Signed-off-by: Thomas Mingarelli <Thomas.Mingarelli@hp.com>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/watchdog/hpwdt.c |   15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

--- 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(stru
 	}
 
 	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);

[8/8] time: catch xtime_nsec underflows and fix them

[Greg KH, gregkh]

[-- Attachment #1: time-catch-xtime_nsec-underflows-and-fix-them.patch --]
[-- Type: text/plain, Size: 4071 bytes --]

From: john stultz <johnstul@us.ibm.com>

commit 6c9bacb41c10ba84ff68f238e234d96f35fb64f7 upstream.

Impact: fix time warp bug

Alex Shi, along with Yanmin Zhang have been noticing occasional time
inconsistencies recently. Through their great diagnosis, they found that
the xtime_nsec value used in update_wall_time was occasionally going
negative. After looking through the code for awhile, I realized we have
the possibility for an underflow when three conditions are met in
update_wall_time():

  1) We have accumulated a second's worth of nanoseconds, so we
     incremented xtime.tv_sec and appropriately decrement xtime_nsec.
     (This doesn't cause xtime_nsec to go negative, but it can cause it
      to be small).

  2) The remaining offset value is large, but just slightly less then
     cycle_interval.

  3) clocksource_adjust() is speeding up the clock, causing a
     corrective amount (compensating for the increase in the multiplier
     being multiplied against the unaccumulated offset value) to be
     subtracted from xtime_nsec.

This can cause xtime_nsec to underflow.

Unfortunately, since we notify the NTP subsystem via second_overflow()
whenever we accumulate a full second, and this effects the error
accumulation that has already occured, we cannot simply revert the
accumulated second from xtime nor move the second accumulation to after
the clocksource_adjust call without a change in behavior.

This leaves us with (at least) two options:

1) Simply return from clocksource_adjust() without making a change if we
   notice the adjustment would cause xtime_nsec to go negative.

This would work, but I'm concerned that if a large adjustment was needed
(due to the error being large), it may be possible to get stuck with an
ever increasing error that becomes too large to correct (since it may
always force xtime_nsec negative). This may just be paranoia on my part.

2) Catch xtime_nsec if it is negative, then add back the amount its
   negative to both xtime_nsec and the error.

This second method is consistent with how we've handled earlier rounding
issues, and also has the benefit that the error being added is always in
the oposite direction also always equal or smaller then the correction
being applied. So the risk of a corner case where things get out of
control is lessened.

This patch fixes bug 11970, as tested by Yanmin Zhang
http://bugzilla.kernel.org/show_bug.cgi?id=11970

Reported-by: alex.shi@intel.com
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Acked-by: Yanmin Zhang <yanmin_zhang@linux.intel.com>
Tested-by: Yanmin Zhang <yanmin_zhang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/time/timekeeping.c |   22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

--- 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;