[patch 00/19] 2.6.23-stable review, arch specific stuff

[patch 00/19] 2.6.23-stable review, arch specific stuff

[Greg KH]

This is the start of the stable review cycle for the 2.6.23.X release.
There are 19 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.

These patches are sent out with a number of different people on the
Cc: line.  If you wish to be a reviewer, please email stable@kernel.org
to add your name to the list.  If you want to be off the reviewer list,
also email us.

Responses should be made by Friday 00:00:00 UTC.  Anything received
after that time might be too late.

This set of patches focuses on arch specific changes.

The diffstat of this review series is included below.

thanks,

greg k-h

-----

 arch/i386/boot/boot.h                  |    8 ++--
 arch/i386/boot/header.S                |   62 +++++++++++++++++++++++----------
 arch/i386/boot/video-bios.c            |    2 -
 arch/i386/boot/video-vesa.c            |    2 -
 arch/i386/boot/video.c                 |    2 -
 arch/i386/kernel/tsc.c                 |    5 +-
 arch/i386/xen/enlighten.c              |   57 ++++++++++++++++++++----------
 arch/i386/xen/mmu.c                    |   29 +++++++++++++--
 arch/i386/xen/multicalls.c             |   29 +++++++++++++--
 arch/i386/xen/multicalls.h             |    3 +
 arch/i386/xen/xen-ops.h                |    1 
 arch/mips/mm/c-r4k.c                   |   21 +++++++++--
 arch/powerpc/math-emu/math.c           |   13 ++++--
 arch/powerpc/platforms/cell/axon_msi.c |    4 +-
 arch/sparc64/kernel/sys_sparc.c        |    2 -
 arch/sparc64/lib/xor.S                 |   12 +++---
 arch/um/Makefile                       |    3 +
 arch/um/include/common-offsets.h       |    1 
 arch/um/include/sysdep-i386/stub.h     |    3 -
 arch/um/kernel/skas/clone.c            |    1 
 arch/um/os-Linux/main.c                |    1 
 arch/um/os-Linux/skas/mem.c            |    1 
 arch/um/os-Linux/skas/process.c        |    2 -
 arch/um/os-Linux/start_up.c            |    1 
 arch/um/os-Linux/tt.c                  |    1 
 arch/um/os-Linux/util.c                |   38 ++++++++++++++++++++
 arch/um/sys-i386/user-offsets.c        |    6 +--
 arch/um/sys-x86_64/user-offsets.c      |    9 ----
 arch/x86_64/mm/init.c                  |    6 ---
 arch/x86_64/mm/pageattr.c              |    9 +++-
 fs/xfs/linux-2.6/xfs_buf.c             |   13 ++++++
 include/asm-mips/hazards.h             |   54 ++++++++++++++++++++++++++++
 include/linux/bootmem.h                |    1 
 include/xen/interface/vcpu.h           |    5 +-
 mm/sparse.c                            |   11 -----
 35 files changed, 307 insertions(+), 111 deletions(-)

[patch 01/19] Fix sparc64 niagara optimized RAID xor asm

[Greg KH]

[-- Attachment #1: fix-sparc64-niagara-optimized-raid-xor-asm.patch --]
[-- Type: text/plain, Size: 2472 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: David Miller <davem@davemloft.net>

patch d060db63fd38a8a75f666576ef9999c28cdc31cf in mainline.

[SPARC64]: Fix register usage in xor_raid_4().

Some typos led to using %i6/%i7 instead of %l6/%l7 in loads which is
really really bad because those are the frame pointer and return PC.

Based upon a raid5 crash report by Bertrand Joel.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/sparc64/lib/xor.S |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/arch/sparc64/lib/xor.S
+++ b/arch/sparc64/lib/xor.S
@@ -491,12 +491,12 @@ xor_niagara_4:		/* %o0=bytes, %o1=dest, 
 	ldda		[%i1 + 0x10] %asi, %i2	/* %i2/%i3 = src1 + 0x10 */
 	xor		%g2, %i4, %g2
 	xor		%g3, %i5, %g3
-	ldda		[%i7 + 0x10] %asi, %i4	/* %i4/%i5 = src2 + 0x10 */
+	ldda		[%l7 + 0x10] %asi, %i4	/* %i4/%i5 = src2 + 0x10 */
 	xor		%l0, %g2, %l0
 	xor		%l1, %g3, %l1
 	stxa		%l0, [%i0 + 0x00] %asi
 	stxa		%l1, [%i0 + 0x08] %asi
-	ldda		[%i6 + 0x10] %asi, %g2	/* %g2/%g3 = src3 + 0x10 */
+	ldda		[%l6 + 0x10] %asi, %g2	/* %g2/%g3 = src3 + 0x10 */
 	ldda		[%i0 + 0x10] %asi, %l0	/* %l0/%l1 = dest + 0x10 */
 
 	xor		%i4, %i2, %i4
@@ -504,12 +504,12 @@ xor_niagara_4:		/* %o0=bytes, %o1=dest, 
 	ldda		[%i1 + 0x20] %asi, %i2	/* %i2/%i3 = src1 + 0x20 */
 	xor		%g2, %i4, %g2
 	xor		%g3, %i5, %g3
-	ldda		[%i7 + 0x20] %asi, %i4	/* %i4/%i5 = src2 + 0x20 */
+	ldda		[%l7 + 0x20] %asi, %i4	/* %i4/%i5 = src2 + 0x20 */
 	xor		%l0, %g2, %l0
 	xor		%l1, %g3, %l1
 	stxa		%l0, [%i0 + 0x10] %asi
 	stxa		%l1, [%i0 + 0x18] %asi
-	ldda		[%i6 + 0x20] %asi, %g2	/* %g2/%g3 = src3 + 0x20 */
+	ldda		[%l6 + 0x20] %asi, %g2	/* %g2/%g3 = src3 + 0x20 */
 	ldda		[%i0 + 0x20] %asi, %l0	/* %l0/%l1 = dest + 0x20 */
 
 	xor		%i4, %i2, %i4
@@ -517,12 +517,12 @@ xor_niagara_4:		/* %o0=bytes, %o1=dest, 
 	ldda		[%i1 + 0x30] %asi, %i2	/* %i2/%i3 = src1 + 0x30 */
 	xor		%g2, %i4, %g2
 	xor		%g3, %i5, %g3
-	ldda		[%i7 + 0x30] %asi, %i4	/* %i4/%i5 = src2 + 0x30 */
+	ldda		[%l7 + 0x30] %asi, %i4	/* %i4/%i5 = src2 + 0x30 */
 	xor		%l0, %g2, %l0
 	xor		%l1, %g3, %l1
 	stxa		%l0, [%i0 + 0x20] %asi
 	stxa		%l1, [%i0 + 0x28] %asi
-	ldda		[%i6 + 0x30] %asi, %g2	/* %g2/%g3 = src3 + 0x30 */
+	ldda		[%l6 + 0x30] %asi, %g2	/* %g2/%g3 = src3 + 0x30 */
 	ldda		[%i0 + 0x30] %asi, %l0	/* %l0/%l1 = dest + 0x30 */
 
 	prefetch	[%i1 + 0x40], #one_read

-- 

[patch 02/19] Fix sparc64 MAP_FIXED handling of framebuffer mmaps

[Greg KH]

[-- Attachment #1: fix-sparc64-map_fixed-handling-of-framebuffer-mmaps.patch --]
[-- Type: text/plain, Size: 1178 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Chris Wright <chrisw@sous-sol.org>

patch d58aa8c7b1cc0add7b03e26bdb8988d98d2f4cd1 in mainline.

From: Chris Wright <chrisw@sous-sol.org>
Date: Tue, 23 Oct 2007 20:36:14 -0700
Subject: [patch 02/19] [PATCH] [SPARC64]: pass correct addr in get_fb_unmapped_area(MAP_FIXED)

Looks like the MAP_FIXED case is using the wrong address hint.  I'd
expect the comment "don't mess with it" means pass the request
straight on through, not change the address requested to -ENOMEM.

Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/sparc64/kernel/sys_sparc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/sparc64/kernel/sys_sparc.c
+++ b/arch/sparc64/kernel/sys_sparc.c
@@ -319,7 +319,7 @@ unsigned long get_fb_unmapped_area(struc
 
 	if (flags & MAP_FIXED) {
 		/* Ok, don't mess with it. */
-		return get_unmapped_area(NULL, addr, len, pgoff, flags);
+		return get_unmapped_area(NULL, orig_addr, len, pgoff, flags);
 	}
 	flags &= ~MAP_SHARED;
 

-- 

[patch 03/19] MIPS: MT: Fix bug in multithreaded kernels.

[Greg KH]

[-- Attachment #1: mips-mt-fix-bug-in-multithreaded-kernels.patch --]
[-- Type: text/plain, Size: 3180 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Ralf Baechle <ralf@linux-mips.org>

patch a76ab5c10d99bdf458067cb495e72c0ee5f09909 in mainline.

When GDB writes a breakpoint into address area of inferior process the
kernel needs to invalidate the modified memory in the inferior which
is done by calling flush_cache_page which in turns calls
r4k_flush_cache_page and local_r4k_flush_cache_page for VSMP or SMTC
kernel via r4k_on_each_cpu().

As the VSMP and SMTC SMP kernels for 34K are running on a single shared
caches it is possible to get away without interprocessor function calls.
This optimization is implemented in r4k_on_each_cpu, so
local_r4k_flush_cache_page is only ever called on the local CPU.

This is where the following code in local_r4k_flush_cache_page() strikes:

        /*
         * If ownes no valid ASID yet, cannot possibly have gotten
         * this page into the cache.
         */
        if (cpu_context(smp_processor_id(), mm) == 0)
                return;

On VSMP and SMTC had a function of cpu_context() for each CPU(TC).

So in case another CPU than the CPU executing local_r4k_cache_flush_page
has not accessed the mm but one of the other CPUs has there may be data
to be flushed in the cache yet local_r4k_cache_flush_page will falsely
return leaving the I-cache inconsistent for the breakpoint.

While the issue was discovered with GDB it also exists in
local_r4k_flush_cache_range() and local_r4k_flush_cache().

Fixed by introducing a new function has_valid_asid which on MT kernels
returns true if a mm is active on any processor in the system.

This is relativly expensive since for memory acccesses in that loop
cache misses have to be assumed but it seems the most viable solution
for 2.6.23 and older -stable kernels.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/mips/mm/c-r4k.c |   21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -360,11 +360,26 @@ static void r4k___flush_cache_all(void)
 	r4k_on_each_cpu(local_r4k___flush_cache_all, NULL, 1, 1);
 }
 
+static inline int has_valid_asid(const struct mm_struct *mm)
+{
+#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+	int i;
+
+	for_each_online_cpu(i)
+		if (cpu_context(i, mm))
+			return 1;
+
+	return 0;
+#else
+	return cpu_context(smp_processor_id(), mm);
+#endif
+}
+
 static inline void local_r4k_flush_cache_range(void * args)
 {
 	struct vm_area_struct *vma = args;
 
-	if (!(cpu_context(smp_processor_id(), vma->vm_mm)))
+	if (!(has_valid_asid(vma->vm_mm)))
 		return;
 
 	r4k_blast_dcache();
@@ -383,7 +398,7 @@ static inline void local_r4k_flush_cache
 {
 	struct mm_struct *mm = args;
 
-	if (!cpu_context(smp_processor_id(), mm))
+	if (!has_valid_asid(mm))
 		return;
 
 	/*
@@ -434,7 +449,7 @@ static inline void local_r4k_flush_cache
 	 * If ownes no valid ASID yet, cannot possibly have gotten
 	 * this page into the cache.
 	 */
-	if (cpu_context(smp_processor_id(), mm) == 0)
+	if (!has_valid_asid(mm))
 		return;
 
 	addr &= PAGE_MASK;

-- 

[patch 04/19] MIPS: R1: Fix hazard barriers to make kernels work on R2 also.

[Greg KH]

[-- Attachment #1: mips-r1-fix-hazard-barriers-to-make-kernels-work-on-r2-also.patch --]
[-- Type: text/plain, Size: 2513 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Ralf Baechle <ralf@linux-mips.org>

patch 572afc248c33c902760f6f24a72c180f0e4f1719 in mainline.

Tested with Malta; inflates malta_defconfig by 3932 bytes.  Ideally there
should be additional configuration to allow getting rid of this overhead
but that would be too much complexity at this stage of the release cycle.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 include/asm-mips/hazards.h |   54 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 1 deletion(-)

--- a/include/asm-mips/hazards.h
+++ b/include/asm-mips/hazards.h
@@ -10,11 +10,12 @@
 #ifndef _ASM_HAZARDS_H
 #define _ASM_HAZARDS_H
 
-
 #ifdef __ASSEMBLY__
 #define ASMMACRO(name, code...) .macro name; code; .endm
 #else
 
+#include <asm/cpu-features.h>
+
 #define ASMMACRO(name, code...)						\
 __asm__(".macro " #name "; " #code "; .endm");				\
 									\
@@ -86,6 +87,57 @@ do {									\
 	: "=r" (tmp));							\
 } while (0)
 
+#elif defined(CONFIG_CPU_MIPSR1)
+
+/*
+ * These are slightly complicated by the fact that we guarantee R1 kernels to
+ * run fine on R2 processors.
+ */
+ASMMACRO(mtc0_tlbw_hazard,
+	_ssnop; _ssnop; _ehb
+	)
+ASMMACRO(tlbw_use_hazard,
+	_ssnop; _ssnop; _ssnop; _ehb
+	)
+ASMMACRO(tlb_probe_hazard,
+	 _ssnop; _ssnop; _ssnop; _ehb
+	)
+ASMMACRO(irq_enable_hazard,
+	 _ssnop; _ssnop; _ssnop; _ehb
+	)
+ASMMACRO(irq_disable_hazard,
+	_ssnop; _ssnop; _ssnop; _ehb
+	)
+ASMMACRO(back_to_back_c0_hazard,
+	 _ssnop; _ssnop; _ssnop; _ehb
+	)
+/*
+ * gcc has a tradition of misscompiling the previous construct using the
+ * address of a label as argument to inline assembler.  Gas otoh has the
+ * annoying difference between la and dla which are only usable for 32-bit
+ * rsp. 64-bit code, so can't be used without conditional compilation.
+ * The alterantive is switching the assembler to 64-bit code which happens
+ * to work right even for 32-bit code ...
+ */
+#define __instruction_hazard()						\
+do {									\
+	unsigned long tmp;						\
+									\
+	__asm__ __volatile__(						\
+	"	.set	mips64r2				\n"	\
+	"	dla	%0, 1f					\n"	\
+	"	jr.hb	%0					\n"	\
+	"	.set	mips0					\n"	\
+	"1:							\n"	\
+	: "=r" (tmp));							\
+} while (0)
+
+#define instruction_hazard()						\
+do {									\
+	if (cpu_has_mips_r2)						\
+		__instruction_hazard();					\
+} while (0)
+
 #elif defined(CONFIG_CPU_R10000)
 
 /*

-- 

[patch 05/19] POWERPC: Fix handling of stfiwx math emulation

[Greg KH]

[-- Attachment #1: powerpc-fix-handling-of-stfiwx-math-emulation.patch --]
[-- Type: text/plain, Size: 1252 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Kumar Gala <galak@kernel.crashing.org>

patch ba02946a903015840ef672ccc9dc8620a7e83de6 in mainline

Its legal for the stfiwx instruction to have RA = 0 as part of its
effective address calculation.  This is illegal for all other XE
form instructions.

Add code to compute the proper effective address for stfiwx if
RA = 0 rather than treating it as illegal.

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/powerpc/math-emu/math.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/arch/powerpc/math-emu/math.c
+++ b/arch/powerpc/math-emu/math.c
@@ -407,11 +407,16 @@ do_mathemu(struct pt_regs *regs)
 
 	case XE:
 		idx = (insn >> 16) & 0x1f;
-		if (!idx)
-			goto illegal;
-
 		op0 = (void *)&current->thread.fpr[(insn >> 21) & 0x1f];
-		op1 = (void *)(regs->gpr[idx] + regs->gpr[(insn >> 11) & 0x1f]);
+		if (!idx) {
+			if (((insn >> 1) & 0x3ff) == STFIWX)
+				op1 = (void *)(regs->gpr[(insn >> 11) & 0x1f]);
+			else
+				goto illegal;
+		} else {
+			op1 = (void *)(regs->gpr[idx] + regs->gpr[(insn >> 11) & 0x1f]);
+		}
+
 		break;
 
 	case XEU:

-- 

[patch 06/19] POWERPC: Make sure to of_node_get() the result of pci_device_to_OF_node()

[Greg KH]

[-- Attachment #1: powerpc-make-sure-to-of_node_get-the-result-of-pci_device_to_of_node.patch --]
[-- Type: text/plain, Size: 1310 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Michael Ellerman <michael@ellerman.id.au>

patch db220b234da9f183b127b9c3077c253b94756e35 in mainline.

pci_device_to_OF_node() returns the device node attached to a PCI device,
but doesn't actually grab a reference - we need to do it ourselves.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/powerpc/platforms/cell/axon_msi.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -126,7 +126,7 @@ static struct axon_msic *find_msi_transl
 	const phandle *ph;
 	struct axon_msic *msic = NULL;
 
-	dn = pci_device_to_OF_node(dev);
+	dn = of_node_get(pci_device_to_OF_node(dev));
 	if (!dn) {
 		dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
 		return NULL;
@@ -183,7 +183,7 @@ static int setup_msi_msg_address(struct 
 	int len;
 	const u32 *prop;
 
-	dn = pci_device_to_OF_node(dev);
+	dn = of_node_get(pci_device_to_OF_node(dev));
 	if (!dn) {
 		dev_dbg(&dev->dev, "axon_msi: no pci_dn found\n");
 		return -ENODEV;

-- 

[uml-devel] [patch 07/19] UML - Stop using libc asm/page.h

[Greg KH]

[-- Attachment #1: uml-stop-using-libc-asm-page.h.patch --]
[-- Type: text/plain, Size: 3751 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeff Dike <jdike@addtoit.com>

commit 71f926f2ea61994470a53c9e11d3ef993197cada in mainline.

uml: stop using libc asm/page.h

Remove includes of asm/page.h from libc code.  This header seems to be
disappearing, and UML doesn't make much use of it anyway.

The one use, PAGE_SHIFT in stub.h, is handled by copying the constant from the
kernel side of the house in common_offsets.h.

[ jdike - added arch/um/kernel/skas/clone.c for -stable ]

Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/include/common-offsets.h   |    1 +
 arch/um/include/sysdep-i386/stub.h |    3 +--
 arch/um/kernel/skas/clone.c        |    1 -
 arch/um/os-Linux/main.c            |    1 -
 arch/um/os-Linux/skas/mem.c        |    1 -
 arch/um/os-Linux/start_up.c        |    1 -
 arch/um/os-Linux/tt.c              |    1 -
 7 files changed, 2 insertions(+), 7 deletions(-)

--- a/arch/um/include/common-offsets.h
+++ b/arch/um/include/common-offsets.h
@@ -10,6 +10,7 @@ OFFSET(HOST_TASK_PID, task_struct, pid);
 
 DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE);
 DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK);
+DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT);
 DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC);
 
 DEFINE_STR(UM_KERN_EMERG, KERN_EMERG);
--- a/arch/um/include/sysdep-i386/stub.h
+++ b/arch/um/include/sysdep-i386/stub.h
@@ -9,7 +9,6 @@
 #include <sys/mman.h>
 #include <asm/ptrace.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include "stub-data.h"
 #include "kern_constants.h"
 #include "uml-config.h"
@@ -19,7 +18,7 @@ extern void stub_clone_handler(void);
 
 #define STUB_SYSCALL_RET EAX
 #define STUB_MMAP_NR __NR_mmap2
-#define MMAP_OFFSET(o) ((o) >> PAGE_SHIFT)
+#define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT)
 
 static inline long stub_syscall0(long syscall)
 {
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -3,7 +3,6 @@
 #include <sys/mman.h>
 #include <sys/time.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include "ptrace_user.h"
 #include "skas.h"
 #include "stub-data.h"
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -12,7 +12,6 @@
 #include <sys/resource.h>
 #include <sys/mman.h>
 #include <sys/user.h>
-#include <asm/page.h>
 #include "kern_util.h"
 #include "as-layout.h"
 #include "mem_user.h"
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -9,7 +9,6 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
-#include <asm/page.h>
 #include <asm/unistd.h>
 #include "mem_user.h"
 #include "mem.h"
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -19,7 +19,6 @@
 #include <sys/mman.h>
 #include <sys/resource.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include <sys/types.h>
 #include "kern_util.h"
 #include "user.h"
--- a/arch/um/os-Linux/tt.c
+++ b/arch/um/os-Linux/tt.c
@@ -17,7 +17,6 @@
 #include <sys/mman.h>
 #include <asm/ptrace.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include "kern_util.h"
 #include "user.h"
 #include "signal_kern.h"

-- 

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel

[patch 07/19] UML - Stop using libc asm/page.h

[Greg KH]

[-- Attachment #1: uml-stop-using-libc-asm-page.h.patch --]
[-- Type: text/plain, Size: 3241 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeff Dike <jdike@addtoit.com>

commit 71f926f2ea61994470a53c9e11d3ef993197cada in mainline.

uml: stop using libc asm/page.h

Remove includes of asm/page.h from libc code.  This header seems to be
disappearing, and UML doesn't make much use of it anyway.

The one use, PAGE_SHIFT in stub.h, is handled by copying the constant from the
kernel side of the house in common_offsets.h.

[ jdike - added arch/um/kernel/skas/clone.c for -stable ]

Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/include/common-offsets.h   |    1 +
 arch/um/include/sysdep-i386/stub.h |    3 +--
 arch/um/kernel/skas/clone.c        |    1 -
 arch/um/os-Linux/main.c            |    1 -
 arch/um/os-Linux/skas/mem.c        |    1 -
 arch/um/os-Linux/start_up.c        |    1 -
 arch/um/os-Linux/tt.c              |    1 -
 7 files changed, 2 insertions(+), 7 deletions(-)

--- a/arch/um/include/common-offsets.h
+++ b/arch/um/include/common-offsets.h
@@ -10,6 +10,7 @@ OFFSET(HOST_TASK_PID, task_struct, pid);
 
 DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE);
 DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK);
+DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT);
 DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC);
 
 DEFINE_STR(UM_KERN_EMERG, KERN_EMERG);
--- a/arch/um/include/sysdep-i386/stub.h
+++ b/arch/um/include/sysdep-i386/stub.h
@@ -9,7 +9,6 @@
 #include <sys/mman.h>
 #include <asm/ptrace.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include "stub-data.h"
 #include "kern_constants.h"
 #include "uml-config.h"
@@ -19,7 +18,7 @@ extern void stub_clone_handler(void);
 
 #define STUB_SYSCALL_RET EAX
 #define STUB_MMAP_NR __NR_mmap2
-#define MMAP_OFFSET(o) ((o) >> PAGE_SHIFT)
+#define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT)
 
 static inline long stub_syscall0(long syscall)
 {
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -3,7 +3,6 @@
 #include <sys/mman.h>
 #include <sys/time.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include "ptrace_user.h"
 #include "skas.h"
 #include "stub-data.h"
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -12,7 +12,6 @@
 #include <sys/resource.h>
 #include <sys/mman.h>
 #include <sys/user.h>
-#include <asm/page.h>
 #include "kern_util.h"
 #include "as-layout.h"
 #include "mem_user.h"
--- a/arch/um/os-Linux/skas/mem.c
+++ b/arch/um/os-Linux/skas/mem.c
@@ -9,7 +9,6 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
-#include <asm/page.h>
 #include <asm/unistd.h>
 #include "mem_user.h"
 #include "mem.h"
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -19,7 +19,6 @@
 #include <sys/mman.h>
 #include <sys/resource.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include <sys/types.h>
 #include "kern_util.h"
 #include "user.h"
--- a/arch/um/os-Linux/tt.c
+++ b/arch/um/os-Linux/tt.c
@@ -17,7 +17,6 @@
 #include <sys/mman.h>
 #include <asm/ptrace.h>
 #include <asm/unistd.h>
-#include <asm/page.h>
 #include "kern_util.h"
 #include "user.h"
 #include "signal_kern.h"

-- 

[uml-devel] [patch 08/19] UML - Fix kernel vs libc symbols clash

[Greg KH]

[-- Attachment #1: uml-fix-kernel-vs-libc-symbols-clash.patch --]
[-- Type: text/plain, Size: 1663 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------

From: Jeff Dike <jdike@addtoit.com>

commit 818f6ef407b448cef63294b9d0f6f8a2af9cb817 in mainline.

uml: fix an IPV6 libc vs kernel symbol clash

On some systems, with IPV6 configured, there is a clash between the kernel's
in6addr_any and the one in libc.

This is handled in the usual (gross) way of defining the kernel symbol out of
the way on the gcc command line.

Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/Makefile |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -60,7 +60,8 @@ SYS_DIR		:= $(ARCH_DIR)/include/sysdep-$
 
 CFLAGS += $(CFLAGS-y) -D__arch_um__ -DSUBARCH=\"$(SUBARCH)\"	\
 	$(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap	\
-	-Din6addr_loopback=kernel_in6addr_loopback
+	-Din6addr_loopback=kernel_in6addr_loopback \
+	-Din6addr_any=kernel_in6addr_any
 
 AFLAGS += $(ARCH_INCLUDE)
 

-- 

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel

[patch 08/19] UML - Fix kernel vs libc symbols clash

[Greg KH]

[-- Attachment #1: uml-fix-kernel-vs-libc-symbols-clash.patch --]
[-- Type: text/plain, Size: 1153 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------

From: Jeff Dike <jdike@addtoit.com>

commit 818f6ef407b448cef63294b9d0f6f8a2af9cb817 in mainline.

uml: fix an IPV6 libc vs kernel symbol clash

On some systems, with IPV6 configured, there is a clash between the kernel's
in6addr_any and the one in libc.

This is handled in the usual (gross) way of defining the kernel symbol out of
the way on the gcc command line.

Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/Makefile |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -60,7 +60,8 @@ SYS_DIR		:= $(ARCH_DIR)/include/sysdep-$
 
 CFLAGS += $(CFLAGS-y) -D__arch_um__ -DSUBARCH=\"$(SUBARCH)\"	\
 	$(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap	\
-	-Din6addr_loopback=kernel_in6addr_loopback
+	-Din6addr_loopback=kernel_in6addr_loopback \
+	-Din6addr_any=kernel_in6addr_any
 
 AFLAGS += $(ARCH_INCLUDE)
 

-- 

[uml-devel] [patch 09/19] UML - stop using libc asm/user.h

[Greg KH]

[-- Attachment #1: uml-stop-using-libc-asm-user.h.patch --]
[-- Type: text/plain, Size: 2939 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeff Dike <jdike@addtoit.com>

commit 189872f968def833727b6bfef83ebd7440c538e6 in mainline.

uml: don't use glibc asm/user.h

Stop including asm/user.h from libc - it seems to be disappearing from
distros.  It's replaced with sys/user.h which defines user_fpregs_struct and
user_fpxregs_struct instead of user_i387_struct and struct user_fxsr_struct on
i386.

As a bonus, on x86_64, I get to dump some stupid typedefs which were needed in
order to get asm/user.h to compile.

Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/sys-i386/user-offsets.c   |    6 +++---
 arch/um/sys-x86_64/user-offsets.c |    9 +--------
 2 files changed, 4 insertions(+), 11 deletions(-)

--- a/arch/um/sys-i386/user-offsets.c
+++ b/arch/um/sys-i386/user-offsets.c
@@ -2,9 +2,9 @@
 #include <stddef.h>
 #include <signal.h>
 #include <sys/poll.h>
+#include <sys/user.h>
 #include <sys/mman.h>
 #include <asm/ptrace.h>
-#include <asm/user.h>
 
 #define DEFINE(sym, val) \
 	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
@@ -48,8 +48,8 @@ void foo(void)
 	OFFSET(HOST_SC_FP_ST, _fpstate, _st);
 	OFFSET(HOST_SC_FXSR_ENV, _fpstate, _fxsr_env);
 
-	DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_i387_struct));
-	DEFINE_LONGS(HOST_XFP_SIZE, sizeof(struct user_fxsr_struct));
+	DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_fpregs_struct));
+	DEFINE_LONGS(HOST_XFP_SIZE, sizeof(struct user_fpxregs_struct));
 
 	DEFINE(HOST_IP, EIP);
 	DEFINE(HOST_SP, UESP);
--- a/arch/um/sys-x86_64/user-offsets.c
+++ b/arch/um/sys-x86_64/user-offsets.c
@@ -3,17 +3,10 @@
 #include <signal.h>
 #include <sys/poll.h>
 #include <sys/mman.h>
+#include <sys/user.h>
 #define __FRAME_OFFSETS
 #include <asm/ptrace.h>
 #include <asm/types.h>
-/* For some reason, x86_64 defines u64 and u32 only in <pci/types.h>, which I
- * refuse to include here, even though they're used throughout the headers.
- * These are used in asm/user.h, and that include can't be avoided because of
- * the sizeof(struct user_regs_struct) below.
- */
-typedef __u64 u64;
-typedef __u32 u32;
-#include <asm/user.h>
 
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))

-- 

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel

[patch 09/19] UML - stop using libc asm/user.h

[Greg KH]

[-- Attachment #1: uml-stop-using-libc-asm-user.h.patch --]
[-- Type: text/plain, Size: 2429 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeff Dike <jdike@addtoit.com>

commit 189872f968def833727b6bfef83ebd7440c538e6 in mainline.

uml: don't use glibc asm/user.h

Stop including asm/user.h from libc - it seems to be disappearing from
distros.  It's replaced with sys/user.h which defines user_fpregs_struct and
user_fpxregs_struct instead of user_i387_struct and struct user_fxsr_struct on
i386.

As a bonus, on x86_64, I get to dump some stupid typedefs which were needed in
order to get asm/user.h to compile.

Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/sys-i386/user-offsets.c   |    6 +++---
 arch/um/sys-x86_64/user-offsets.c |    9 +--------
 2 files changed, 4 insertions(+), 11 deletions(-)

--- a/arch/um/sys-i386/user-offsets.c
+++ b/arch/um/sys-i386/user-offsets.c
@@ -2,9 +2,9 @@
 #include <stddef.h>
 #include <signal.h>
 #include <sys/poll.h>
+#include <sys/user.h>
 #include <sys/mman.h>
 #include <asm/ptrace.h>
-#include <asm/user.h>
 
 #define DEFINE(sym, val) \
 	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
@@ -48,8 +48,8 @@ void foo(void)
 	OFFSET(HOST_SC_FP_ST, _fpstate, _st);
 	OFFSET(HOST_SC_FXSR_ENV, _fpstate, _fxsr_env);
 
-	DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_i387_struct));
-	DEFINE_LONGS(HOST_XFP_SIZE, sizeof(struct user_fxsr_struct));
+	DEFINE_LONGS(HOST_FP_SIZE, sizeof(struct user_fpregs_struct));
+	DEFINE_LONGS(HOST_XFP_SIZE, sizeof(struct user_fpxregs_struct));
 
 	DEFINE(HOST_IP, EIP);
 	DEFINE(HOST_SP, UESP);
--- a/arch/um/sys-x86_64/user-offsets.c
+++ b/arch/um/sys-x86_64/user-offsets.c
@@ -3,17 +3,10 @@
 #include <signal.h>
 #include <sys/poll.h>
 #include <sys/mman.h>
+#include <sys/user.h>
 #define __FRAME_OFFSETS
 #include <asm/ptrace.h>
 #include <asm/types.h>
-/* For some reason, x86_64 defines u64 and u32 only in <pci/types.h>, which I
- * refuse to include here, even though they're used throughout the headers.
- * These are used in asm/user.h, and that include can't be avoided because of
- * the sizeof(struct user_regs_struct) below.
- */
-typedef __u64 u64;
-typedef __u32 u32;
-#include <asm/user.h>
 
 #define DEFINE(sym, val) \
         asm volatile("\n->" #sym " %0 " #val : : "i" (val))

-- 

[uml-devel] [patch 10/19] UML - kill subprocesses on exit

[Greg KH]

[-- Attachment #1: uml-kill-subprocesses-on-exit.patch --]
[-- Type: text/plain, Size: 3566 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Lepton Wu <ytht.net@gmail.com>

commit a24864a1d52a97e345a6bd4862a057f98364d098

uml: definitively kill subprocesses on panic

In a stock 2.6.22.6 kernel, poweroff a user mode linux guest (2.6.22.6 running
in skas0 mode) will halt the host linux.  I think the reason is the kernel
thread abort because of a bug.  Then the sys_reboot in process of user mode
linux guest is not trapped by the user mode linux kernel and is executed by
host.  I think it is better to make sure all of our children process to quit
when user mode linux kernel abort.

[ jdike - the kernel process needs to ignore SIGTERM, plus the waitpid/kill
loop is needed to make sure that all of our children are dead before the
kernel exits ]

Signed-off-by: Lepton Wu <ytht.net@gmail.com>
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/os-Linux/skas/process.c |    2 +-
 arch/um/os-Linux/util.c         |   38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 1 deletion(-)

--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -182,7 +182,7 @@ static int userspace_tramp(void *stack)
 
 	ptrace(PTRACE_TRACEME, 0, 0, 0);
 
-	init_new_thread_signals();
+	signal(SIGTERM, SIG_DFL);
 	err = set_interval(1);
 	if(err)
 		panic("userspace_tramp - setting timer failed, errno = %d\n",
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -105,6 +105,44 @@ int setjmp_wrapper(void (*proc)(void *, 
 
 void os_dump_core(void)
 {
+	int pid;
+
 	signal(SIGSEGV, SIG_DFL);
+
+	/*
+	 * We are about to SIGTERM this entire process group to ensure that
+	 * nothing is around to run after the kernel exits.  The
+	 * kernel wants to abort, not die through SIGTERM, so we
+	 * ignore it here.
+	 */
+
+	signal(SIGTERM, SIG_IGN);
+	kill(0, SIGTERM);
+	/*
+	 * Most of the other processes associated with this UML are
+	 * likely sTopped, so give them a SIGCONT so they see the
+	 * SIGTERM.
+	 */
+	kill(0, SIGCONT);
+
+	/*
+	 * Now, having sent signals to everyone but us, make sure they
+	 * die by ptrace.  Processes can survive what's been done to
+	 * them so far - the mechanism I understand is receiving a
+	 * SIGSEGV and segfaulting immediately upon return.  There is
+	 * always a SIGSEGV pending, and (I'm guessing) signals are
+	 * processed in numeric order so the SIGTERM (signal 15 vs
+	 * SIGSEGV being signal 11) is never handled.
+	 *
+	 * Run a waitpid loop until we get some kind of error.
+	 * Hopefully, it's ECHILD, but there's not a lot we can do if
+	 * it's something else.  Tell os_kill_ptraced_process not to
+	 * wait for the child to report its death because there's
+	 * nothing reasonable to do if that fails.
+	 */
+
+	while ((pid = waitpid(-1, NULL, WNOHANG)) > 0)
+		os_kill_ptraced_process(pid, 0);
+
 	abort();
 }

-- 

-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel

[patch 10/19] UML - kill subprocesses on exit

[Greg KH]

[-- Attachment #1: uml-kill-subprocesses-on-exit.patch --]
[-- Type: text/plain, Size: 3056 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Lepton Wu <ytht.net@gmail.com>

commit a24864a1d52a97e345a6bd4862a057f98364d098

uml: definitively kill subprocesses on panic

In a stock 2.6.22.6 kernel, poweroff a user mode linux guest (2.6.22.6 running
in skas0 mode) will halt the host linux.  I think the reason is the kernel
thread abort because of a bug.  Then the sys_reboot in process of user mode
linux guest is not trapped by the user mode linux kernel and is executed by
host.  I think it is better to make sure all of our children process to quit
when user mode linux kernel abort.

[ jdike - the kernel process needs to ignore SIGTERM, plus the waitpid/kill
loop is needed to make sure that all of our children are dead before the
kernel exits ]

Signed-off-by: Lepton Wu <ytht.net@gmail.com>
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/um/os-Linux/skas/process.c |    2 +-
 arch/um/os-Linux/util.c         |   38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 1 deletion(-)

--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -182,7 +182,7 @@ static int userspace_tramp(void *stack)
 
 	ptrace(PTRACE_TRACEME, 0, 0, 0);
 
-	init_new_thread_signals();
+	signal(SIGTERM, SIG_DFL);
 	err = set_interval(1);
 	if(err)
 		panic("userspace_tramp - setting timer failed, errno = %d\n",
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -105,6 +105,44 @@ int setjmp_wrapper(void (*proc)(void *, 
 
 void os_dump_core(void)
 {
+	int pid;
+
 	signal(SIGSEGV, SIG_DFL);
+
+	/*
+	 * We are about to SIGTERM this entire process group to ensure that
+	 * nothing is around to run after the kernel exits.  The
+	 * kernel wants to abort, not die through SIGTERM, so we
+	 * ignore it here.
+	 */
+
+	signal(SIGTERM, SIG_IGN);
+	kill(0, SIGTERM);
+	/*
+	 * Most of the other processes associated with this UML are
+	 * likely sTopped, so give them a SIGCONT so they see the
+	 * SIGTERM.
+	 */
+	kill(0, SIGCONT);
+
+	/*
+	 * Now, having sent signals to everyone but us, make sure they
+	 * die by ptrace.  Processes can survive what's been done to
+	 * them so far - the mechanism I understand is receiving a
+	 * SIGSEGV and segfaulting immediately upon return.  There is
+	 * always a SIGSEGV pending, and (I'm guessing) signals are
+	 * processed in numeric order so the SIGTERM (signal 15 vs
+	 * SIGSEGV being signal 11) is never handled.
+	 *
+	 * Run a waitpid loop until we get some kind of error.
+	 * Hopefully, it's ECHILD, but there's not a lot we can do if
+	 * it's something else.  Tell os_kill_ptraced_process not to
+	 * wait for the child to report its death because there's
+	 * nothing reasonable to do if that fails.
+	 */
+
+	while ((pid = waitpid(-1, NULL, WNOHANG)) > 0)
+		os_kill_ptraced_process(pid, 0);
+
 	abort();
 }

-- 

[patch 11/19] xen: add batch completion callbacks

[Greg KH]

[-- Attachment #1: xen-multicall-callbacks.patch --]
[-- Type: text/plain, Size: 2330 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeremy Fitzhardinge <jeremy@goop.org>

patch 91e0c5f3dad47838cb2ecc1865ce789a0b7182b1 in mainline.

This adds a mechanism to register a callback function to be called once
a batch of hypercalls has been issued.  This is typically used to unlock
things which must remain locked until the hypercall has taken place.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/i386/xen/multicalls.c |   29 ++++++++++++++++++++++++++---
 arch/i386/xen/multicalls.h |    3 +++
 2 files changed, 29 insertions(+), 3 deletions(-)

--- a/arch/i386/xen/multicalls.c
+++ b/arch/i386/xen/multicalls.c
@@ -32,7 +32,11 @@
 struct mc_buffer {
 	struct multicall_entry entries[MC_BATCH];
 	u64 args[MC_ARGS];
-	unsigned mcidx, argidx;
+	struct callback {
+		void (*fn)(void *);
+		void *data;
+	} callbacks[MC_BATCH];
+	unsigned mcidx, argidx, cbidx;
 };
 
 static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
@@ -43,6 +47,7 @@ void xen_mc_flush(void)
 	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
 	int ret = 0;
 	unsigned long flags;
+	int i;
 
 	BUG_ON(preemptible());
 
@@ -51,8 +56,6 @@ void xen_mc_flush(void)
 	local_irq_save(flags);
 
 	if (b->mcidx) {
-		int i;
-
 		if (HYPERVISOR_multicall(b->entries, b->mcidx) != 0)
 			BUG();
 		for (i = 0; i < b->mcidx; i++)
@@ -65,6 +68,13 @@ void xen_mc_flush(void)
 
 	local_irq_restore(flags);
 
+	for(i = 0; i < b->cbidx; i++) {
+		struct callback *cb = &b->callbacks[i];
+
+		(*cb->fn)(cb->data);
+	}
+	b->cbidx = 0;
+
 	BUG_ON(ret);
 }
 
@@ -88,3 +98,16 @@ struct multicall_space __xen_mc_entry(si
 
 	return ret;
 }
+
+void xen_mc_callback(void (*fn)(void *), void *data)
+{
+	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct callback *cb;
+
+	if (b->cbidx == MC_BATCH)
+		xen_mc_flush();
+
+	cb = &b->callbacks[b->cbidx++];
+	cb->fn = fn;
+	cb->data = data;
+}
--- a/arch/i386/xen/multicalls.h
+++ b/arch/i386/xen/multicalls.h
@@ -42,4 +42,7 @@ static inline void xen_mc_issue(unsigned
 	local_irq_restore(x86_read_percpu(xen_mc_irq_flags));
 }
 
+/* Set up a callback to be called when the current batch is flushed */
+void xen_mc_callback(void (*fn)(void *), void *data);
+
 #endif /* _XEN_MULTICALLS_H */

-- 

[patch 12/19] xen: deal with stale cr3 values when unpinning pagetables

[Greg KH]

[-- Attachment #1: xen-handle-lazy-cr3-on-unpin.patch --]
[-- Type: text/plain, Size: 5898 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeremy Fitzhardinge <jeremy@goop.org>

patch 9f79991d4186089e228274196413572cc000143b in mainline.

When a pagetable is no longer in use, it must be unpinned so that its
pages can be freed.  However, this is only possible if there are no
stray uses of the pagetable.  The code currently deals with all the
usual cases, but there's a rare case where a vcpu is changing cr3, but
is doing so lazily, and the change hasn't actually happened by the time
the pagetable is unpinned, even though it appears to have been completed.

This change adds a second per-cpu cr3 variable - xen_current_cr3 -
which tracks the actual state of the vcpu cr3.  It is only updated once
the actual hypercall to set cr3 has been completed.  Other processors
wishing to unpin a pagetable can check other vcpu's xen_current_cr3
values to see if any cross-cpu IPIs are needed to clean things up.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/i386/xen/enlighten.c |   55 +++++++++++++++++++++++++++++++---------------
 arch/i386/xen/mmu.c       |   29 +++++++++++++++++++++---
 arch/i386/xen/xen-ops.h   |    1 
 3 files changed, 65 insertions(+), 20 deletions(-)

--- a/arch/i386/xen/enlighten.c
+++ b/arch/i386/xen/enlighten.c
@@ -56,7 +56,23 @@ DEFINE_PER_CPU(enum paravirt_lazy_mode, 
 
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
-DEFINE_PER_CPU(unsigned long, xen_cr3);
+
+/*
+ * Note about cr3 (pagetable base) values:
+ *
+ * xen_cr3 contains the current logical cr3 value; it contains the
+ * last set cr3.  This may not be the current effective cr3, because
+ * its update may be being lazily deferred.  However, a vcpu looking
+ * at its own cr3 can use this value knowing that it everything will
+ * be self-consistent.
+ *
+ * xen_current_cr3 contains the actual vcpu cr3; it is set once the
+ * hypercall to set the vcpu cr3 is complete (so it may be a little
+ * out of date, but it will never be set early).  If one vcpu is
+ * looking at another vcpu's cr3 value, it should use this variable.
+ */
+DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
+DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
 
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
@@ -632,32 +648,36 @@ static unsigned long xen_read_cr3(void)
 	return x86_read_percpu(xen_cr3);
 }
 
+static void set_current_cr3(void *v)
+{
+	x86_write_percpu(xen_current_cr3, (unsigned long)v);
+}
+
 static void xen_write_cr3(unsigned long cr3)
 {
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+	unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
+
 	BUG_ON(preemptible());
 
-	if (cr3 == x86_read_percpu(xen_cr3)) {
-		/* just a simple tlb flush */
-		xen_flush_tlb();
-		return;
-	}
+	mcs = xen_mc_entry(sizeof(*op));  /* disables interrupts */
 
+	/* Update while interrupts are disabled, so its atomic with
+	   respect to ipis */
 	x86_write_percpu(xen_cr3, cr3);
 
+	op = mcs.args;
+	op->cmd = MMUEXT_NEW_BASEPTR;
+	op->arg1.mfn = mfn;
 
-	{
-		struct mmuext_op *op;
-		struct multicall_space mcs = xen_mc_entry(sizeof(*op));
-		unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
-
-		op = mcs.args;
-		op->cmd = MMUEXT_NEW_BASEPTR;
-		op->arg1.mfn = mfn;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-		MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+	/* Update xen_update_cr3 once the batch has actually
+	   been submitted. */
+	xen_mc_callback(set_current_cr3, (void *)cr3);
 
-		xen_mc_issue(PARAVIRT_LAZY_CPU);
-	}
+	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
 }
 
 /* Early in boot, while setting up the initial pagetable, assume
@@ -1113,6 +1133,7 @@ asmlinkage void __init xen_start_kernel(
 	/* keep using Xen gdt for now; no urgent need to change it */
 
 	x86_write_percpu(xen_cr3, __pa(pgd));
+	x86_write_percpu(xen_current_cr3, __pa(pgd));
 
 #ifdef CONFIG_SMP
 	/* Don't do the full vcpu_info placement stuff until we have a
--- a/arch/i386/xen/mmu.c
+++ b/arch/i386/xen/mmu.c
@@ -515,20 +515,43 @@ static void drop_other_mm_ref(void *info
 
 	if (__get_cpu_var(cpu_tlbstate).active_mm == mm)
 		leave_mm(smp_processor_id());
+
+	/* If this cpu still has a stale cr3 reference, then make sure
+	   it has been flushed. */
+	if (x86_read_percpu(xen_current_cr3) == __pa(mm->pgd)) {
+		load_cr3(swapper_pg_dir);
+		arch_flush_lazy_cpu_mode();
+	}
 }
 
 static void drop_mm_ref(struct mm_struct *mm)
 {
+	cpumask_t mask;
+	unsigned cpu;
+
 	if (current->active_mm == mm) {
 		if (current->mm == mm)
 			load_cr3(swapper_pg_dir);
 		else
 			leave_mm(smp_processor_id());
+		arch_flush_lazy_cpu_mode();
+	}
+
+	/* Get the "official" set of cpus referring to our pagetable. */
+	mask = mm->cpu_vm_mask;
+
+	/* It's possible that a vcpu may have a stale reference to our
+	   cr3, because its in lazy mode, and it hasn't yet flushed
+	   its set of pending hypercalls yet.  In this case, we can
+	   look at its actual current cr3 value, and force it to flush
+	   if needed. */
+	for_each_online_cpu(cpu) {
+		if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
+			cpu_set(cpu, mask);
 	}
 
-	if (!cpus_empty(mm->cpu_vm_mask))
-		xen_smp_call_function_mask(mm->cpu_vm_mask, drop_other_mm_ref,
-					   mm, 1);
+	if (!cpus_empty(mask))
+		xen_smp_call_function_mask(mask, drop_other_mm_ref, mm, 1);
 }
 #else
 static void drop_mm_ref(struct mm_struct *mm)
--- a/arch/i386/xen/xen-ops.h
+++ b/arch/i386/xen/xen-ops.h
@@ -11,6 +11,7 @@ void xen_copy_trap_info(struct trap_info
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DECLARE_PER_CPU(unsigned long, xen_cr3);
+DECLARE_PER_CPU(unsigned long, xen_current_cr3);
 
 extern struct start_info *xen_start_info;
 extern struct shared_info *HYPERVISOR_shared_info;

-- 

[patch 13/19] xen: fix incorrect vcpu_register_vcpu_info hypercall argument

[Greg KH]

[-- Attachment #1: xen-fix-register_vcpu_info.patch --]
[-- Type: text/plain, Size: 1824 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeremy Fitzhardinge <jeremy@goop.org>

patch e3d2697669abbe26c08dc9b95e2a71c634d096ed in mainline.

The kernel's copy of struct vcpu_register_vcpu_info was out of date,
at best causing the hypercall to fail and the guest kernel to fall
back to the old mechanism, or worse, causing random memory corruption.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Stable Kernel <stable@kernel.org>
Cc: Morten =?utf-8?q?B=C3=B8geskov?= <xen-users@morten.bogeskov.dk>
Cc: Mark Williamson <mark.williamson@cl.cam.ac.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/i386/xen/enlighten.c    |    2 +-
 include/xen/interface/vcpu.h |    5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

--- a/arch/i386/xen/enlighten.c
+++ b/arch/i386/xen/enlighten.c
@@ -116,7 +116,7 @@ static void __init xen_vcpu_setup(int cp
 	info.mfn = virt_to_mfn(vcpup);
 	info.offset = offset_in_page(vcpup);
 
-	printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %x, offset %d\n",
+	printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n",
 	       cpu, vcpup, info.mfn, info.offset);
 
 	/* Check to see if the hypervisor will put the vcpu_info
--- a/include/xen/interface/vcpu.h
+++ b/include/xen/interface/vcpu.h
@@ -160,8 +160,9 @@ struct vcpu_set_singleshot_timer {
  */
 #define VCPUOP_register_vcpu_info   10  /* arg == struct vcpu_info */
 struct vcpu_register_vcpu_info {
-    uint32_t mfn;               /* mfn of page to place vcpu_info */
-    uint32_t offset;            /* offset within page */
+    uint64_t mfn;    /* mfn of page to place vcpu_info */
+    uint32_t offset; /* offset within page */
+    uint32_t rsvd;   /* unused */
 };
 
 #endif /* __XEN_PUBLIC_VCPU_H__ */

-- 

[patch 14/19] xfs: eagerly remove vmap mappings to avoid upsetting Xen

[Greg KH]

[-- Attachment #1: xen-xfs-unmap.patch --]
[-- Type: text/plain, Size: 1667 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Jeremy Fitzhardinge <jeremy@goop.org>

patch ace2e92e193126711cb3a83a3752b2c5b8396950 in mainline.

XFS leaves stray mappings around when it vmaps memory to make it
virtually contigious.  This upsets Xen if one of those pages is being
recycled into a pagetable, since it finds an extra writable mapping of
the page.

This patch solves the problem in a brute force way, by making XFS
always eagerly unmap its mappings.

[ Stable: This works around a bug in 2.6.23.  We may come up with a
better solution for mainline, but this seems like a low-impact fix for
the stable kernel. ]

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: XFS masters <xfs-masters@oss.sgi.com>
Cc: Morten =?utf-8?q?B=C3=B8geskov?= <xen-users@morten.bogeskov.dk>
Cc: Mark Williamson <mark.williamson@cl.cam.ac.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>


---
 fs/xfs/linux-2.6/xfs_buf.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)

--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -187,6 +187,19 @@ free_address(
 {
 	a_list_t	*aentry;
 
+#ifdef CONFIG_XEN
+	/*
+	 * Xen needs to be able to make sure it can get an exclusive
+	 * RO mapping of pages it wants to turn into a pagetable.  If
+	 * a newly allocated page is also still being vmap()ed by xfs,
+	 * it will cause pagetable construction to fail.  This is a
+	 * quick workaround to always eagerly unmap pages so that Xen
+	 * is happy.
+	 */
+	vunmap(addr);
+	return;
+#endif
+
 	aentry = kmalloc(sizeof(a_list_t), GFP_NOWAIT);
 	if (likely(aentry)) {
 		spin_lock(&as_lock);

-- 

[patch 15/19] x86: fix global_flush_tlb() bug

[Greg KH]

[-- Attachment #1: x86-fix-global_flush_tlb-bug.patch --]
[-- Type: text/plain, Size: 2180 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Ingo Molnar <mingo@elte.hu>

patch 9a24d04a3c26c223f22493492c5c9085b8773d4a upstream

While we were reviewing pageattr_32/64.c for unification,
Thomas Gleixner noticed the following serious SMP bug in
global_flush_tlb():

	down_read(&init_mm.mmap_sem);
	list_replace_init(&deferred_pages, &l);
	up_read(&init_mm.mmap_sem);

this is SMP-unsafe because list_replace_init() done on two CPUs in
parallel can corrupt the list.

This bug has been introduced about a year ago in the 64-bit tree:

       commit ea7322decb974a4a3e804f96a0201e893ff88ce3
       Author: Andi Kleen <ak@suse.de>
       Date:   Thu Dec 7 02:14:05 2006 +0100

       [PATCH] x86-64: Speed and clean up cache flushing in change_page_attr

                down_read(&init_mm.mmap_sem);
        -       dpage = xchg(&deferred_pages, NULL);
        +       list_replace_init(&deferred_pages, &l);
                up_read(&init_mm.mmap_sem);

the xchg() based version was SMP-safe, but list_replace_init() is not.
So this "cleanup" introduced a nasty bug.

why this bug never become prominent is a mystery - it can probably be
explained with the (still) relative obscurity of the x86_64 architecture.

the safe fix for now is to write-lock init_mm.mmap_sem.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <ak@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86_64/mm/pageattr.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/arch/x86_64/mm/pageattr.c
+++ b/arch/x86_64/mm/pageattr.c
@@ -229,9 +229,14 @@ void global_flush_tlb(void)
 	struct page *pg, *next;
 	struct list_head l;
 
-	down_read(&init_mm.mmap_sem);
+	/*
+	 * Write-protect the semaphore, to exclude two contexts
+	 * doing a list_replace_init() call in parallel and to
+	 * exclude new additions to the deferred_pages list:
+	 */
+	down_write(&init_mm.mmap_sem);
 	list_replace_init(&deferred_pages, &l);
-	up_read(&init_mm.mmap_sem);
+	up_write(&init_mm.mmap_sem);
 
 	flush_map(&l);
 

-- 

[patch 16/19] x86 setup: handle boot loaders which set up the stack incorrectly

[Greg KH]

[-- Attachment #1: x86-setup-handle-boot-loaders-which-set-up-the-stack-incorrectly.patch --]
[-- Type: text/plain, Size: 3526 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: H. Peter Anvin <hpa@zytor.com>

patch 6b6815c6d5d1dc209701d1661a7a0e09a295db2f in mainline.

Apparently some specific versions of LILO enter the kernel with a
stack pointer that doesn't match the rest of the segments.  Make our
best attempt at untangling the resulting mess.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/i386/boot/boot.h   |    4 +--
 arch/i386/boot/header.S |   62 ++++++++++++++++++++++++++++++++++--------------
 2 files changed, 46 insertions(+), 20 deletions(-)

--- a/arch/i386/boot/boot.h
+++ b/arch/i386/boot/boot.h
@@ -17,6 +17,8 @@
 #ifndef BOOT_BOOT_H
 #define BOOT_BOOT_H
 
+#define STACK_SIZE	512	/* Minimum number of bytes for stack */
+
 #ifndef __ASSEMBLY__
 
 #include <stdarg.h>
@@ -198,8 +200,6 @@ static inline int isdigit(int ch)
 }
 
 /* Heap -- available for dynamic lists. */
-#define STACK_SIZE	512	/* Minimum number of bytes for stack */
-
 extern char _end[];
 extern char *HEAP;
 extern char *heap_end;
--- a/arch/i386/boot/header.S
+++ b/arch/i386/boot/header.S
@@ -173,7 +173,8 @@ ramdisk_size:	.long	0		# its size in byt
 bootsect_kludge:
 		.long	0		# obsolete
 
-heap_end_ptr:	.word	_end+1024	# (Header version 0x0201 or later)
+heap_end_ptr:	.word	_end+STACK_SIZE-512
+					# (Header version 0x0201 or later)
 					# space from here (exclusive) down to
 					# end of setup code can be used by setup
 					# for local heap purposes.
@@ -225,28 +226,53 @@ start_of_setup:
 	int	$0x13
 #endif
 
-# We will have entered with %cs = %ds+0x20, normalize %cs so
-# it is on par with the other segments.
-	pushw	%ds
-	pushw	$setup2
-	lretw
-
-setup2:
 # Force %es = %ds
 	movw	%ds, %ax
 	movw	%ax, %es
 	cld
 
-# Stack paranoia: align the stack and make sure it is good
-# for both 16- and 32-bit references.  In particular, if we
-# were meant to have been using the full 16-bit segment, the
-# caller might have set %sp to zero, which breaks %esp-based
-# references.
-	andw	$~3, %sp	# dword align (might as well...)
-	jnz	1f
-	movw	$0xfffc, %sp	# Make sure we're not zero
-1:	movzwl	%sp, %esp	# Clear upper half of %esp
-	sti
+# Apparently some ancient versions of LILO invoked the kernel
+# with %ss != %ds, which happened to work by accident for the
+# old code.  If the CAN_USE_HEAP flag is set in loadflags, or
+# %ss != %ds, then adjust the stack pointer.
+
+	# Smallest possible stack we can tolerate
+	movw	$(_end+STACK_SIZE), %cx
+
+	movw	heap_end_ptr, %dx
+	addw	$512, %dx
+	jnc	1f
+	xorw	%dx, %dx	# Wraparound - whole segment available
+1:	testb	$CAN_USE_HEAP, loadflags
+	jnz	2f
+
+	# No CAN_USE_HEAP
+	movw	%ss, %dx
+	cmpw	%ax, %dx	# %ds == %ss?
+	movw	%sp, %dx
+	# If so, assume %sp is reasonably set, otherwise use
+	# the smallest possible stack.
+	jne	4f		# -> Smallest possible stack...
+
+	# Make sure the stack is at least minimum size.  Take a value
+	# of zero to mean "full segment."
+2:
+	andw	$~3, %dx	# dword align (might as well...)
+	jnz	3f
+	movw	$0xfffc, %dx	# Make sure we're not zero
+3:	cmpw	%cx, %dx
+	jnb	5f
+4:	movw	%cx, %dx	# Minimum value we can possibly use
+5:	movw	%ax, %ss
+	movzwl	%dx, %esp	# Clear upper half of %esp
+	sti			# Now we should have a working stack
+
+# We will have entered with %cs = %ds+0x20, normalize %cs so
+# it is on par with the other segments.
+	pushw	%ds
+	pushw	$6f
+	lretw
+6:
 
 # Check signature at end of setup
 	cmpl	$0x5a5aaa55, setup_sig

-- 

Re: [patch 16/19] x86 setup: handle boot loaders which set up the stack incorrectly

[H. Peter Anvin]

Greg KH wrote:
> -stable review patch.  If anyone has any objections, please let us know.
> 
> ------------------
> From: H. Peter Anvin <hpa@zytor.com>
> 
> patch 6b6815c6d5d1dc209701d1661a7a0e09a295db2f in mainline.
> 
> Apparently some specific versions of LILO enter the kernel with a
> stack pointer that doesn't match the rest of the segments.  Make our
> best attempt at untangling the resulting mess.
> 
> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

Just FYI:

It has been reported that while this patch fixes old LILO, and possibly 
some other boot loaders (unknown), it has also broken older versions of 
SYSLINUX: they still boot, but the command line is truncated (exactly 
how much depends on the BIOS, but typical values are around 130 bytes.)

This is definitely traceable to a bug in SYSLINUX that was already fixed 
in release 3.50 (the current version of SYSLINUX is 3.52).

I have chosen to leave the patch in mainline, rather than trying yet 
another recipe and hope it doesn't break on some other random 
combination of bootloaders, since:

a) SYSLINUX is generally easily updated, compared to other bootloaders;
b) The failure mode is less severe (it still boots.)

... however, you may choose to call differently.

	-hpa

Re: [patch 16/19] x86 setup: handle boot loaders which set up the stack incorrectly

[Greg KH]

On Wed, Nov 14, 2007 at 11:27:01PM -0800, H. Peter Anvin wrote:
> Greg KH wrote:
>> -stable review patch.  If anyone has any objections, please let us know.
>> ------------------
>> From: H. Peter Anvin <hpa@zytor.com>
>> patch 6b6815c6d5d1dc209701d1661a7a0e09a295db2f in mainline.
>> Apparently some specific versions of LILO enter the kernel with a
>> stack pointer that doesn't match the rest of the segments.  Make our
>> best attempt at untangling the resulting mess.
>> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
>> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
>
> Just FYI:
>
> It has been reported that while this patch fixes old LILO, and possibly 
> some other boot loaders (unknown), it has also broken older versions of 
> SYSLINUX: they still boot, but the command line is truncated (exactly how 
> much depends on the BIOS, but typical values are around 130 bytes.)
>
> This is definitely traceable to a bug in SYSLINUX that was already fixed in 
> release 3.50 (the current version of SYSLINUX is 3.52).
>
> I have chosen to leave the patch in mainline, rather than trying yet 
> another recipe and hope it doesn't break on some other random combination 
> of bootloaders, since:
>
> a) SYSLINUX is generally easily updated, compared to other bootloaders;
> b) The failure mode is less severe (it still boots.)
>
> ... however, you may choose to call differently.

I have no objection to keeping this patch in the tree, as it fixes a
real problem, and matches the upstream kernel version.

thanks,

greg k-h

[patch 17/19] x86 setup: sizeof() is unsigned, unbreak comparisons

[Greg KH]

[-- Attachment #1: x86-setup-sizeof-is-unsigned-unbreak-comparisons.patch --]
[-- Type: text/plain, Size: 2267 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: H. Peter Anvin <hpa@zytor.com>

patch e6e1ace9904b72478f0c5a5aa7bd174cb6f62561 in mainline.


We use signed values for limit checking since the values can go
negative under certain circumstances.  However, sizeof() is unsigned
and forces the comparison to be unsigned, so move the comparison into
the heap_free() macros so we can ensure it is a signed comparison.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/i386/boot/boot.h       |    4 ++--
 arch/i386/boot/video-bios.c |    2 +-
 arch/i386/boot/video-vesa.c |    2 +-
 arch/i386/boot/video.c      |    2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

--- a/arch/i386/boot/boot.h
+++ b/arch/i386/boot/boot.h
@@ -216,9 +216,9 @@ static inline char *__get_heap(size_t s,
 #define GET_HEAP(type, n) \
 	((type *)__get_heap(sizeof(type),__alignof__(type),(n)))
 
-static inline int heap_free(void)
+static inline bool heap_free(size_t n)
 {
-	return heap_end-HEAP;
+	return (int)(heap_end-HEAP) >= (int)n;
 }
 
 /* copy.S */
--- a/arch/i386/boot/video-bios.c
+++ b/arch/i386/boot/video-bios.c
@@ -79,7 +79,7 @@ static int bios_probe(void)
 	video_bios.modes = GET_HEAP(struct mode_info, 0);
 
 	for (mode = 0x14; mode <= 0x7f; mode++) {
-		if (heap_free() < sizeof(struct mode_info))
+		if (!heap_free(sizeof(struct mode_info)))
 			break;
 
 		if (mode_defined(VIDEO_FIRST_BIOS+mode))
--- a/arch/i386/boot/video-vesa.c
+++ b/arch/i386/boot/video-vesa.c
@@ -57,7 +57,7 @@ static int vesa_probe(void)
 	while ((mode = rdfs16(mode_ptr)) != 0xffff) {
 		mode_ptr += 2;
 
-		if (heap_free() < sizeof(struct mode_info))
+		if (!heap_free(sizeof(struct mode_info)))
 			break;	/* Heap full, can't save mode info */
 
 		if (mode & ~0x1ff)
--- a/arch/i386/boot/video.c
+++ b/arch/i386/boot/video.c
@@ -371,7 +371,7 @@ static void save_screen(void)
 	saved.curx = boot_params.screen_info.orig_x;
 	saved.cury = boot_params.screen_info.orig_y;
 
-	if (heap_free() < saved.x*saved.y*sizeof(u16)+512)
+	if (!heap_free(saved.x*saved.y*sizeof(u16)+512))
 		return;		/* Not enough heap to save the screen */
 
 	saved.data = GET_HEAP(u16, saved.x*saved.y);

-- 

[patch 18/19] x86: fix TSC clock source calibration error

[Greg KH]

[-- Attachment #1: x86-fix-tsc-clock-source-calibration-error.patch --]
[-- Type: text/plain, Size: 3436 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Dave Johnson <djohnson@sw.starentnetworks.com>

patch edaf420fdc122e7a42326fe39274c8b8c9b19d41 in mainline.

I ran into this problem on a system that was unable to obtain NTP sync
because the clock was running very slow (over 10000ppm slow). ntpd had
declared all of its peers 'reject' with 'peer_dist' reason.

On investigation, the tsc_khz variable was significantly incorrect
causing xtime to run slow.  After a reboot tsc_khz was correct so I
did a reboot test to see how often the problem occurred:

Test was done on a 2000 Mhz Xeon system.  Of 689 reboots, 8 of them
had unacceptable tsc_khz values (>500ppm):

 range of tsc_khz  # of boots  % of boots
 ----------------  ----------  ----------
        < 1999750           0      0.000%
1999750 - 1999800          21      3.048%
1999800 - 1999850         166     24.128%
1999850 - 1999900         241     35.029%
1999900 - 1999950         211     30.669%
1999950 - 2000000          42      6.105%
2000000 - 2000000           0      0.000%
2000050 - 2000100           0      0.000%
                   [...]
2000100 - 2015000           1      0.145%  << BAD
2015000 - 2030000           6      0.872%  << BAD
2030000 - 2045000           1      0.145%  << BAD
2045000 <                   0      0.000%

The worst boot was 2032.577 Mhz, over 1.5% off!

It appears that on rare occasions, mach_countup() is taking longer to
complete than necessary.

I suspect that this is caused by the CPU taking a periodic SMI
interrupt right at the end of the 30ms calibration loop.  This would
cause the loop to delay while the SMI BIOS hander runs. The resulting
TSC value is beyond what it actually should be resulting in a higher
tsc_khz.

The below patch makes native_calculate_cpu_khz() take the best
(shortest duration, lowest khz) run of it's 3 calibration loops.  If a
SMI goes off causing a bad result (long duration, higher khz) it will
be discarded.

With the patch applied, 300 boots of the same system produce good
results:

 range of tsc_khz  # of boots  % of boots
 ----------------  ----------  ----------
        < 1999750           0      0.000%
1999750 - 1999800          30     10.000%
1999800 - 1999850         166     55.333%
1999850 - 1999900          89     29.667%
1999900 - 1999950          15      5.000%
1999950 <                   0      0.000%

Problem was found and tested against 2.6.18.  Patch is against 2.6.22.

Signed-off-by: Dave Johnson <djohnson@sw.starentnetworks.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/i386/kernel/tsc.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/arch/i386/kernel/tsc.c
+++ b/arch/i386/kernel/tsc.c
@@ -137,7 +137,7 @@ unsigned long native_calculate_cpu_khz(v
 {
 	unsigned long long start, end;
 	unsigned long count;
-	u64 delta64;
+	u64 delta64 = (u64)ULLONG_MAX;
 	int i;
 	unsigned long flags;
 
@@ -149,6 +149,7 @@ unsigned long native_calculate_cpu_khz(v
 		rdtscll(start);
 		mach_countup(&count);
 		rdtscll(end);
+		delta64 = min(delta64, (end - start));
 	}
 	/*
 	 * Error: ECTCNEVERSET
@@ -159,8 +160,6 @@ unsigned long native_calculate_cpu_khz(v
 	if (count <= 1)
 		goto err;
 
-	delta64 = end - start;
-
 	/* cpu freq too fast: */
 	if (delta64 > (1ULL<<32))
 		goto err;

-- 

[patch 19/19] revert "x86_64: allocate sparsemem memmap above 4G"

[Greg KH]

[-- Attachment #1: revert-x86_64-allocate-sparsemem-memmap-above-4g.patch --]
[-- Type: text/plain, Size: 3108 bytes --]

-stable review patch.  If anyone has any objections, please let us know.

------------------
From: Linus Torvalds <torvalds@linux-foundation.org>

Reverted upstream by commit 6a22c57b8d2a62dea7280a6b2ac807a539ef0716

Revert this commit:

	commit 2e1c49db4c640b35df13889b86b9d62215ade4b6
	Author: Zou Nan hai <nanhai.zou@intel.com>
	Date:   Fri Jun 1 00:46:28 2007 -0700
	
	x86_64: allocate sparsemem memmap above 4G

This reverts commit 2e1c49db4c640b35df13889b86b9d62215ade4b6.

First off, testing in Fedora has shown it to cause boot failures,
bisected down by Martin Ebourne, and reported by Dave Jobes.  So the
commit will likely be reverted in the 2.6.23 stable kernels.

Secondly, in the 2.6.24 model, x86-64 has now grown support for
SPARSEMEM_VMEMMAP, which disables the relevant code anyway, so while the
bug is not visible any more, it's become invisible due to the code just
being irrelevant and no longer enabled on the only architecture that
this ever affected.

Reported-by: Dave Jones <davej@redhat.com>
Tested-by: Martin Ebourne <fedora@ebourne.me.uk>
Cc: Zou Nan hai <nanhai.zou@intel.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86_64/mm/init.c   |    6 ------
 include/linux/bootmem.h |    1 -
 mm/sparse.c             |   11 -----------
 3 files changed, 18 deletions(-)

--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -734,12 +734,6 @@ int in_gate_area_no_task(unsigned long a
 	return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
 }
 
-void * __init alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size)
-{
-	return __alloc_bootmem_core(pgdat->bdata, size,
-			SMP_CACHE_BYTES, (4UL*1024*1024*1024), 0);
-}
-
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
 	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -59,7 +59,6 @@ extern void *__alloc_bootmem_core(struct
 				  unsigned long align,
 				  unsigned long goal,
 				  unsigned long limit);
-extern void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size);
 
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 extern void reserve_bootmem(unsigned long addr, unsigned long size);
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -215,12 +215,6 @@ static int __meminit sparse_init_one_sec
 	return 1;
 }
 
-__attribute__((weak)) __init
-void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size)
-{
-	return NULL;
-}
-
 static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 {
 	struct page *map;
@@ -231,11 +225,6 @@ static struct page __init *sparse_early_
 	if (map)
 		return map;
 
-  	map = alloc_bootmem_high_node(NODE_DATA(nid),
-                       sizeof(struct page) * PAGES_PER_SECTION);
-	if (map)
-		return map;
-
 	map = alloc_bootmem_node(NODE_DATA(nid),
 			sizeof(struct page) * PAGES_PER_SECTION);
 	if (map)

--