The patch titled
pci device ensure sysdata initialised v3
has been removed from the -mm tree. Its filename was
pci-device-ensure-sysdata-initialised-v3.patch
This patch was dropped because Yinghai Lu's stuff hits on the same code
------------------------------------------------------
Subject: pci device ensure sysdata initialised v3
From: Andy Whitcroft <apw@xxxxxxxxxxxx>
We have been seeing panic's on NUMA systems in pci_call_probe() in
2.6.19-rc1-mm1 and later. This is related to the changes introduced
in the commit below:
[x86, PCI] Switch pci_bus::sysdata from NUMA node integer to a pointer
0a247a58fc3e2ecfc17654301033e8b8d08df2a2
In this change the sysdata has changed from directly representing
a value (the node number in NUMA) to a pointer to a structure.
However, it seems that we do not always initialise this sysdata
before we probe the device.
Prior to the changes above the node was defaulted to 'NULL'
allocating the devices to node 0 unconditionally. This patch adds
a default sysdata entry (pci_default_sysdata), this is then used
where 'NULL' was used previously. pci_default_sysdata defaults
the node to unknown (-1). This is a more accurate assignment,
mirroring the value returned where no topology support is provided
and no locality information is available.
There are only two uses of this value in the affected architectures
(x86, x86_64) and generic code:
1) in x86_64, dma_alloc_pages() looks up the node in order to
allocate node local memory. Here if the node is invalid we
will default to the first online node. Behaviour here should
be unchanged.
2) in generic, pci_call_probe() looks up the node in order to
restrict execution of the probe on the card local node, to
favor node local allocation. Where this is unknown previously
we would force execution (and thereby allocation) to node 0,
this is arguably wrong and using -1 releases this restriction.
In an ideal world we should be supplying a sysdata for the
appropriate node where it is known. Where it is not known defaulting
to -1 seems a better course, and would help us where node 0 is
short of memory.
Signed-off-by: Andy Whitcroft <apw@xxxxxxxxxxxx>
Cc: Greg KH <greg@xxxxxxxxx>
Cc: Jeff Garzik <jeff@xxxxxxxxxx>
Cc: Yinghai Lu <yinghai.lu@xxxxxxx>
Cc: Cornelia Huck <cornelia.huck@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/i386/pci/common.c | 2 ++
arch/i386/pci/fixup.c | 8 +++++---
arch/i386/pci/legacy.c | 3 ++-
arch/i386/pci/numa.c | 8 +++++---
arch/i386/pci/visws.c | 4 ++--
include/asm-i386/pci.h | 1 +
include/asm-x86_64/pci.h | 1 +
7 files changed, 18 insertions(+), 9 deletions(-)
diff -puN arch/i386/pci/common.c~pci-device-ensure-sysdata-initialised-v3 arch/i386/pci/common.c
--- a/arch/i386/pci/common.c~pci-device-ensure-sysdata-initialised-v3
+++ a/arch/i386/pci/common.c
@@ -27,6 +27,8 @@ unsigned long pirq_table_addr;
struct pci_bus *pci_root_bus;
struct pci_raw_ops *raw_pci_ops;
+struct pci_sysdata pci_default_sysdata = { .node = -1 };
+
static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *value)
{
return raw_pci_ops->read(0, bus->number, devfn, where, size, value);
diff -puN arch/i386/pci/fixup.c~pci-device-ensure-sysdata-initialised-v3 arch/i386/pci/fixup.c
--- a/arch/i386/pci/fixup.c~pci-device-ensure-sysdata-initialised-v3
+++ a/arch/i386/pci/fixup.c
@@ -25,9 +25,11 @@ static void __devinit pci_fixup_i450nx(s
pci_read_config_byte(d, reg++, &subb);
DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
if (busno)
- pci_scan_bus(busno, &pci_root_ops, NULL); /* Bus A */
+ pci_scan_bus(busno, &pci_root_ops,
+ &pci_default_sysdata); /* Bus A */
if (suba < subb)
- pci_scan_bus(suba+1, &pci_root_ops, NULL); /* Bus B */
+ pci_scan_bus(suba+1, &pci_root_ops,
+ &pci_default_sysdata); /* Bus B */
}
pcibios_last_bus = -1;
}
@@ -42,7 +44,7 @@ static void __devinit pci_fixup_i450gx(s
u8 busno;
pci_read_config_byte(d, 0x4a, &busno);
printk(KERN_INFO "PCI: i440KX/GX host bridge %s: secondary bus %02x\n", pci_name(d), busno);
- pci_scan_bus(busno, &pci_root_ops, NULL);
+ pci_scan_bus(busno, &pci_root_ops, &pci_default_sysdata);
pcibios_last_bus = -1;
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82454GX, pci_fixup_i450gx);
diff -puN arch/i386/pci/legacy.c~pci-device-ensure-sysdata-initialised-v3 arch/i386/pci/legacy.c
--- a/arch/i386/pci/legacy.c~pci-device-ensure-sysdata-initialised-v3
+++ a/arch/i386/pci/legacy.c
@@ -26,7 +26,8 @@ static void __devinit pcibios_fixup_peer
l != 0x0000 && l != 0xffff) {
DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l);
printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n);
- pci_scan_bus(n, &pci_root_ops, NULL);
+ pci_scan_bus(n, &pci_root_ops,
+ &pci_default_sysdata);
break;
}
}
diff -puN arch/i386/pci/numa.c~pci-device-ensure-sysdata-initialised-v3 arch/i386/pci/numa.c
--- a/arch/i386/pci/numa.c~pci-device-ensure-sysdata-initialised-v3
+++ a/arch/i386/pci/numa.c
@@ -97,9 +97,11 @@ static void __devinit pci_fixup_i450nx(s
pci_read_config_byte(d, reg++, &subb);
DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
if (busno)
- pci_scan_bus(QUADLOCAL2BUS(quad,busno), &pci_root_ops, NULL); /* Bus A */
+ pci_scan_bus(QUADLOCAL2BUS(quad,busno), &pci_root_ops,
+ &pci_default_sysdata); /* Bus A */
if (suba < subb)
- pci_scan_bus(QUADLOCAL2BUS(quad,suba+1), &pci_root_ops, NULL); /* Bus B */
+ pci_scan_bus(QUADLOCAL2BUS(quad,suba+1), &pci_root_ops,
+ &pci_default_sysdata); /* Bus B */
}
pcibios_last_bus = -1;
}
@@ -124,7 +126,7 @@ static int __init pci_numa_init(void)
printk("Scanning PCI bus %d for quad %d\n",
QUADLOCAL2BUS(quad,0), quad);
pci_scan_bus(QUADLOCAL2BUS(quad,0),
- &pci_root_ops, NULL);
+ &pci_root_ops, &pci_default_sysdata);
}
return 0;
}
diff -puN arch/i386/pci/visws.c~pci-device-ensure-sysdata-initialised-v3 arch/i386/pci/visws.c
--- a/arch/i386/pci/visws.c~pci-device-ensure-sysdata-initialised-v3
+++ a/arch/i386/pci/visws.c
@@ -101,8 +101,8 @@ static int __init pcibios_init(void)
"bridge B (PIIX4) bus: %u\n", pci_bus1, pci_bus0);
raw_pci_ops = &pci_direct_conf1;
- pci_scan_bus(pci_bus0, &pci_root_ops, NULL);
- pci_scan_bus(pci_bus1, &pci_root_ops, NULL);
+ pci_scan_bus(pci_bus0, &pci_root_ops, &pci_default_sysdata);
+ pci_scan_bus(pci_bus1, &pci_root_ops, &pci_default_sysdata);
pci_fixup_irqs(visws_swizzle, visws_map_irq);
pcibios_resource_survey();
return 0;
diff -puN include/asm-i386/pci.h~pci-device-ensure-sysdata-initialised-v3 include/asm-i386/pci.h
--- a/include/asm-i386/pci.h~pci-device-ensure-sysdata-initialised-v3
+++ a/include/asm-i386/pci.h
@@ -7,6 +7,7 @@
struct pci_sysdata {
int node; /* NUMA node */
};
+extern struct pci_sysdata pci_default_sysdata;
#include <linux/mm.h> /* for struct page */
diff -puN include/asm-x86_64/pci.h~pci-device-ensure-sysdata-initialised-v3 include/asm-x86_64/pci.h
--- a/include/asm-x86_64/pci.h~pci-device-ensure-sysdata-initialised-v3
+++ a/include/asm-x86_64/pci.h
@@ -9,6 +9,7 @@ struct pci_sysdata {
int node; /* NUMA node */
void* iommu; /* IOMMU private data */
};
+extern struct pci_sysdata pci_default_sysdata;
#ifdef CONFIG_CALGARY_IOMMU
static inline void* pci_iommu(struct pci_bus *bus)
_
Patches currently in -mm which might be from apw@xxxxxxxxxxxx are
do-not-trigger-oom-killer-for-high-order-allocation-failures.patch
pci-device-ensure-sysdata-initialised-v3.patch
sparsemem-ensure-we-initialise-the-node-mapping-for-sparsemem_static.patch
sparsemem-ensure-we-initialise-the-node-mapping-for-sparsemem_static-fix.patch
sparsemem-clean-up-spelling-error-in-comments.patch
sparsemem-record-when-a-section-has-a-valid-mem_map.patch
sparsemem-record-when-a-section-has-a-valid-mem_map-fix.patch
generic-virtual-memmap-support-for-sparsemem.patch
generic-virtual-memmap-support-for-sparsemem-fix.patch
x86_64-sparsemem_vmemmap-2m-page-size-support.patch
ia64-sparsemem_vmemmap-16k-page-size-support.patch
sparc64-sparsemem_vmemmap-support.patch
ppc64-sparsemem_vmemmap-support.patch
add-a-bitmap-that-is-used-to-track-flags-affecting-a-block-of-pages.patch
add-a-configure-option-to-group-pages-by-mobility.patch
move-free-pages-between-lists-on-steal.patch
group-short-lived-and-reclaimable-kernel-allocations.patch
do-not-group-pages-by-mobility-type-on-low-memory-systems.patch
fix-corruption-of-memmap-on-ia64-sparsemem-when-mem_section-is-not-a-power-of-2.patch
fix-corruption-of-memmap-on-ia64-sparsemem-when-mem_section-is-not-a-power-of-2-fix.patch
bias-the-location-of-pages-freed-for-min_free_kbytes-in-the-same-max_order_nr_pages-blocks.patch
remove-page_group_by_mobility.patch
dont-group-high-order-atomic-allocations.patch
fix-calculation-in-move_freepages_block-for-counting-pages.patch
breakout-page_order-to-internalh-to-avoid-special-knowledge-of-the-buddy-allocator.patch
do-not-depend-on-max_order-when-grouping-pages-by-mobility.patch
print-out-statistics-in-relation-to-fragmentation-avoidance-to-proc-pagetypeinfo.patch
have-kswapd-keep-a-minimum-order-free-other-than-order-0.patch
only-check-absolute-watermarks-for-alloc_high-and-alloc_harder-allocations.patch
rename-gfp_high_movable-to-gfp_highuser_movable-prefetch.patch
page-owner-tracking-leak-detector.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
