Hang is observed on virtual machines during CPU hotplug,
especially in big guests with many CPUs. (It reproducible
more often if host is over-committed).
It happens because master CPU gives up waiting on
secondary CPU and allows it to run wild. As result
AP causes locking or crashing system. For example
as described here:
https://lkml.org/lkml/2014/3/6/257
If master CPU have sent STARTUP IPI successfully,
and AP signalled to master CPU that it's ready
to start initialization, make master CPU wait
indefinitely till AP is onlined.
To ensure that AP won't ever run wild, make it
wait at early startup till master CPU confirms its
intention to wait for AP. If AP doesn't respond in 10
seconds, the master CPU will timeout and cancel
AP onlining.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1401975765-22328-4-git-send-email-imammedo@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
currently if AP wake up is failed, master CPU marks AP as not
present in do_boot_cpu() by calling set_cpu_present(cpu, false).
That leads to following list corruption on the next physical CPU
hotplug:
[ 418.107336] WARNING: CPU: 1 PID: 45 at lib/list_debug.c:33 __list_add+0xbe/0xd0()
[ 418.115268] list_add corruption. prev->next should be next (ffff88003dc57600), but was ffff88003e20c3a0. (prev=ffff88003e20c3a0).
[ 418.123693] Modules linked in: nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6t_REJECT ipt_REJECT cfg80211 xt_conntrack rfkill ee
[ 418.138979] CPU: 1 PID: 45 Comm: kworker/u10:1 Not tainted 3.14.0-rc6+ #387
[ 418.149989] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2007
[ 418.165750] Workqueue: kacpi_hotplug acpi_hotplug_work_fn
[ 418.166433] 0000000000000021 ffff880038ca7988 ffffffff8159b22d 0000000000000021
[ 418.176460] ffff880038ca79d8 ffff880038ca79c8 ffffffff8106942c ffff880038ca79e8
[ 418.177453] ffff88003e20c3a0 ffff88003dc57600 ffff88003e20c3a0 00000000ffffffea
[ 418.178445] Call Trace:
[ 418.185811] [<ffffffff8159b22d>] dump_stack+0x49/0x5c
[ 418.186440] [<ffffffff8106942c>] warn_slowpath_common+0x8c/0xc0
[ 418.187192] [<ffffffff81069516>] warn_slowpath_fmt+0x46/0x50
[ 418.191231] [<ffffffff8136ef51>] ? acpi_ns_get_node+0xb7/0xc7
[ 418.193889] [<ffffffff812f796e>] __list_add+0xbe/0xd0
[ 418.196649] [<ffffffff812e2aa9>] kobject_add_internal+0x79/0x200
[ 418.208610] [<ffffffff812e2e18>] kobject_add_varg+0x38/0x60
[ 418.213831] [<ffffffff812e2ef4>] kobject_add+0x44/0x70
[ 418.229961] [<ffffffff813e2c60>] device_add+0xd0/0x550
[ 418.234991] [<ffffffff813f0e95>] ? pm_runtime_init+0xe5/0xf0
[ 418.250226] [<ffffffff813e32be>] device_register+0x1e/0x30
[ 418.255296] [<ffffffff813e82a3>] register_cpu+0xe3/0x130
[ 418.266539] [<ffffffff81592be5>] arch_register_cpu+0x65/0x150
[ 418.285845] [<ffffffff81355c0d>] acpi_processor_hotadd_init+0x5a/0x9b
...
Which is caused by the fact that generic_processor_info() allocates
logical CPU id by calling:
cpu = cpumask_next_zero(-1, cpu_present_mask);
which returns id of previously failed to wake up CPU, since its
bit is cleared by do_boot_cpu() and as result register_cpu()
tries to register another CPU with the same id as already
present but failed to be onlined CPU.
Taking in account that AP will not do anything if master CPU
failed to wake it up, there is no reason to mark that AP as not
present and break next cpu hotplug attempts. As a side effect of
not marking AP as not present, user would be allowed to online
it again later.
Also fix memory corruption in acpi_unmap_lsapic()
if during CPU hotplug master CPU failed to wake up AP
it set percpu x86_cpu_to_apicid to BAD_APICID=0xFFFF for AP.
However following attempt to unplug that CPU will lead to
out of bound write access to __apicid_to_node[] which is
32768 items long on x86_64 kernel.
So with above fix of cpu_present_mask make sure that a present
CPU has a valid APIC ID by not setting x86_cpu_to_apicid
to BAD_APICID in do_boot_cpu() on failure and allow
acpi_processor_remove()->acpi_unmap_lsapic() cleanly remove CPU.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1401975765-22328-2-git-send-email-imammedo@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Purely cosmetic, no changes in .o,
1. As Jim pointed out arch_uprobe->def looks ambiguous, rename it to
->defparam.
2. Add the comment into default_post_xol_op() to explain "regs->sp +=".
3. Remove the stale part of the comment in arch_uprobe_analyze_insn().
Suggested-by: Jim Keniston <jkenisto@us.ibm.com>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Since af06d66ee32b (x86: fix setup of PVH Dom0 memory map) in Xen, PVH
dom0 need only use the memory memory provided by Xen which has already
setup all the correct holes.
xen_memory_setup() then ends up being trivial for a PVH guest so
introduce a new function (xen_auto_xlated_memory_setup()).
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Tested-by: Roger Pau Monné <roger.pau@citrix.com>
Update of TLB shootdown code for UV3.
Kernel function native_flush_tlb_others() calls
uv_flush_tlb_others() on UV to invalidate tlb page definitions
on remote cpus. The UV systems have a hardware 'broadcast assist
unit' which can be used to broadcast shootdown messages to all
cpu's of selected nodes.
The behavior of the BAU has changed only slightly with UV3:
- UV3 is recognized with is_uv3_hub().
- UV2 functions and structures (uv2_xxx) are in most cases
simply renamed to uv2_3_xxx.
- Some UV2 error workarounds are not needed for UV3.
(see uv_bau_message_interrupt and enable_timeouts)
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Link: http://lkml.kernel.org/r/E1WkgWh-0001yJ-3K@eag09.americas.sgi.com
[ Removed a few linebreak uglies. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Merge drm-fixes into drm-next.
Both i915 and radeon need this done for later patches.
Conflicts:
drivers/gpu/drm/drm_crtc_helper.c
drivers/gpu/drm/i915/i915_drv.h
drivers/gpu/drm/i915/i915_gem.c
drivers/gpu/drm/i915/i915_gem_execbuffer.c
drivers/gpu/drm/i915/i915_gem_gtt.c
We pass actual buffer size to opal_validate_flash() OPAL API call
and in return it contains output buffer size.
Commit cc146d1d (Fix little endian issues) missed to set the size
param before making OPAL call. So firmware image validation fails.
This patch sets size variable before making OPAL call.
Signed-off-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Tested-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The hcall macros may call out to c code for tracing, so we need
to set up a valid r2. This fixes an oops found when testing
ibmvscsi as a module.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
__clear_user and copy_page load from the TOC and are also exported
to modules. This means we have to use _GLOBAL_TOC() so that we
create the global entry point that sets up the TOC.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
powerpc sets a low SECTION_SIZE_BITS to accomodate small pseries
boxes. We default to 16MB memory blocks, and boxes with a lot
of memory end up with enormous numbers of sysfs memory nodes.
Set a more reasonable default for powernv of 256MB.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The pseries platform code unconditionally overrides
memory_block_size_bytes regardless of the running platform.
Create a ppc_md hook that so each platform can choose to
do what it wants.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
struct OpalMemoryErrorData is passed to us from firmware, so we
have to byteswap it.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When eeh is not enabled, and hotplug two pci devices on the same bus, eeh
related sysfs would be added twice for the first added pci device. Since the
eeh_dev is not created when eeh is not enabled.
This patch adds the check, if eeh is not enabled, eeh sysfs will not be
created.
After applying this patch, following warnings are reduced:
sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:00.0/eeh_mode'
sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:00.0/eeh_config_addr'
sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:00.0/eeh_pe_config_addr'
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
commit 8f9c0119d7 (compat: fs: Generic compat_sys_sendfile
implementation) changed the PowerPC 64bit sendfile call from
sys_sendile64 to sys_sendfile.
Unfortunately this broke sendfile of lengths greater than 2G because
sys_sendfile caps at MAX_NON_LFS. Restore what we had previously which
fixes the bug.
Cc: stable@vger.kernel.org
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This provides debugfs files to access the LPC bus on Power8
non-virtualized using the appropriate OPAL firmware calls.
The usage is simple: one file per space (IO, MEM and FW),
lseek to the address and read/write the data. IO and MEM always
generate series of byte accesses. FW can generate word and dword
accesses if aligned properly.
Based on an original patch from Rob Lippert and reworked.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We had a mix & match of flags used when creating legacy ports
depending on where we found them in the device-tree. Among others
we were missing UPF_SKIP_TEST for some kind of ISA ports which is
a problem as quite a few UARTs out there don't support the loopback
test (such as a lot of BMCs).
Let's pick the set of flags used by the SoC code and generalize it
which means autoconf, no loopback test, irq maybe shared and fixed
port.
Sending to stable as the lack of UPF_SKIP_TEST is breaking
serial on some machines so I want this back into distros
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: stable@vger.kernel.org
There are a couple of places where xmon is using %x to print values that
are unsigned long.
I found this out the hard way recently:
0:mon> p c000000000d0e7c8 c00000033dc90000 00000000a0000089 c000000000000000
return value is 0x96300500
Which is calling find_linux_pte_or_hugepte(), the result should be a
kernel pointer. After decoding the page tables by hand I discovered the
correct value was c000000396300500.
So fix up that case and a few others.
We also use a mix of 0x%x, %x and %u to print cpu numbers. So
standardise on 0x%x.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When running as a powernv "host" system on P8, we need to switch
the endianness of interrupt handlers. This does it via the appropriate
call to the OPAL firmware which may result in just switching HID0:HILE
but depending on the processor version might need to do a few more
things. This call must be done early before any other processor has
been brought out of firmware.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Merge misc updates from Andrew Morton:
- a few fixes for 3.16. Cc'ed to stable so they'll get there somehow.
- various misc fixes and cleanups
- most of the ocfs2 queue. Review is slow...
- most of MM. The MM queue is pretty huge this time, but not much in
the way of feature work.
- some tweaks under kernel/
- printk maintenance work
- updates to lib/
- checkpatch updates
- tweaks to init/
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (276 commits)
fs/autofs4/dev-ioctl.c: add __init to autofs_dev_ioctl_init
fs/ncpfs/getopt.c: replace simple_strtoul by kstrtoul
init/main.c: remove an ifdef
kthreads: kill CLONE_KERNEL, change kernel_thread(kernel_init) to avoid CLONE_SIGHAND
init/main.c: add initcall_blacklist kernel parameter
init/main.c: don't use pr_debug()
fs/binfmt_flat.c: make old_reloc() static
fs/binfmt_elf.c: fix bool assignements
fs/efs: convert printk(KERN_DEBUG to pr_debug
fs/efs: add pr_fmt / use __func__
fs/efs: convert printk to pr_foo()
scripts/checkpatch.pl: device_initcall is not the only __initcall substitute
checkpatch: check stable email address
checkpatch: warn on unnecessary void function return statements
checkpatch: prefer kstrto<foo> to sscanf(buf, "%<lhuidx>", &bar);
checkpatch: add warning for kmalloc/kzalloc with multiply
checkpatch: warn on #defines ending in semicolon
checkpatch: make --strict a default for files in drivers/net and net/
checkpatch: always warn on missing blank line after variable declaration block
checkpatch: fix wildcard DT compatible string checking
...
... instead of naked numbers.
Stuff in sysrq.c used to set it to 8 which is supposed to mean above
default level so set it to DEBUG instead as we're terminating/killing all
tasks and we want to be verbose there.
Also, correct the check in x86_64_start_kernel which should be >= as
we're clearly issuing the string there for all debug levels, not only
the magical 10.
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Joe Perches <joe@perches.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tracking dirty status on 2 level pages requires very ugly macros and
taking into account how old the machines who can operate without PAE
mode only are, lets drop soft dirty tracker from them for code
simplicity (note I can't drop all the macros from 2 level pages by now
since _PAGE_BIT_PROTNONE and _PAGE_BIT_FILE are still used even without
tracker).
Linus proposed to completely rip off softdirty support on x86-32 (even
with PAE) and since for CRIU we're not planning to support native x86-32
mode, lets do that.
(Softdirty tracker is relatively new feature which is mostly used by
CRIU so I don't expect if such API change would cause problems for
userspace).
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Steven Noonan <steven@uplinklabs.net>
Cc: Rik van Riel <riel@redhat.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Performing vma lookups without taking the mm->mmap_sem is asking for
trouble. While doing the search, the vma in question can be modified or
even removed before returning to the caller. Take the lock (shared) in
order to avoid races while iterating through the vmacache and/or rbtree.
[akpm@linux-foundation.org: CSE current->active_mm, per Vineet]
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Acked-by: Vineet Gupta <vgupta@synopsys.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When it was introduced, zone_reclaim_mode made sense as NUMA distances
punished and workloads were generally partitioned to fit into a NUMA
node. NUMA machines are now common but few of the workloads are
NUMA-aware and it's routine to see major performance degradation due to
zone_reclaim_mode being enabled but relatively few can identify the
problem.
Those that require zone_reclaim_mode are likely to be able to detect
when it needs to be enabled and tune appropriately so lets have a
sensible default for the bulk of users.
This patch (of 2):
zone_reclaim_mode causes processes to prefer reclaiming memory from
local node instead of spilling over to other nodes. This made sense
initially when NUMA machines were almost exclusively HPC and the
workload was partitioned into nodes. The NUMA penalties were
sufficiently high to justify reclaiming the memory. On current machines
and workloads it is often the case that zone_reclaim_mode destroys
performance but not all users know how to detect this. Favour the
common case and disable it by default. Users that are sophisticated
enough to know they need zone_reclaim_mode will detect it.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently, "cma=" kernel parameter is used to specify the size of CMA,
but we can't specify where it is located. We want to locate CMA below
4GB for devices only supporting 32-bit addressing on 64-bit systems
without iommu.
This enables to specify the placement of CMA by extending "cma=" kernel
parameter.
Examples:
1. locate 64MB CMA below 4GB by "cma=64M@0-4G"
2. locate 64MB CMA exact at 512MB by "cma=64M@512M"
Note that the DMA contiguous memory allocator on x86 assumes that
page_address() works for the pages to allocate. So this change requires
to limit end address of contiguous memory area upto max_pfn_mapped to
prevent from locating it on highmem area by the argument of
dma_contiguous_reserve().
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The DMA Contiguous Memory Allocator support on x86 is disabled when
swiotlb config option is enabled. So DMA CMA is always disabled on
x86_64 because swiotlb is always enabled. This attempts to support for
DMA CMA with enabling swiotlb config option.
The contiguous memory allocator on x86 is integrated in the function
dma_generic_alloc_coherent() which is .alloc callback in nommu_dma_ops
for dma_alloc_coherent().
x86_swiotlb_alloc_coherent() which is .alloc callback in swiotlb_dma_ops
tries to allocate with dma_generic_alloc_coherent() firstly and then
swiotlb_alloc_coherent() is called as a fallback.
The main part of supporting DMA CMA with swiotlb is that changing
x86_swiotlb_free_coherent() which is .free callback in swiotlb_dma_ops
for dma_free_coherent() so that it can distinguish memory allocated by
dma_generic_alloc_coherent() from one allocated by
swiotlb_alloc_coherent() and release it with dma_generic_free_coherent()
which can handle contiguous memory. This change requires making
is_swiotlb_buffer() global function.
This also needs to change .free callback in the dma_map_ops for amd_gart
and sta2x11, because these dma_ops are also using
dma_generic_alloc_coherent().
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patchset enhances the DMA Contiguous Memory Allocator on x86.
Currently the DMA CMA is only supported with pci-nommu dma_map_ops and
furthermore it can't be enabled on x86_64. But I would like to allocate
big contiguous memory with dma_alloc_coherent() and tell it to the device
that requires it, regardless of which dma mapping implementation is
actually used in the system.
So this makes it work with swiotlb and intel-iommu dma_map_ops, too. And
this also extends "cma=" kernel parameter to specify placement constraint
by the physical address range of memory allocations. For example, CMA
allocates memory below 4GB by "cma=64M@0-4G", it is required for the
devices only supporting 32-bit addressing on 64-bit systems without iommu.
This patch (of 5):
Calling dma_alloc_coherent() with __GFP_ZERO must return zeroed memory.
But when the contiguous memory allocator (CMA) is enabled on x86 and the
memory region is allocated by dma_alloc_from_contiguous(), it doesn't
return zeroed memory. Because dma_generic_alloc_coherent() forgot to fill
the memory region with zero if it was allocated by
dma_alloc_from_contiguous()
Most implementations of dma_alloc_coherent() return zeroed memory
regardless of whether __GFP_ZERO is specified. So this fixes it by
unconditionally zeroing the allocated memory region.
Alternatively, we could fix dma_alloc_from_contiguous() to return zeroed
out memory and remove memset() from all caller of it. But we can't simply
remove the memset on arm because __dma_clear_buffer() is used there for
ensuring cache flushing and it is used in many places. Of course we can
do redundant memset in dma_alloc_from_contiguous(), but I think this patch
is less impact for fixing this problem.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On system with 2TiB ram, current x86_64 have 128M as section size, and
one memory_block only include one section. So will have 16400 entries
under /sys/devices/system/memory/.
Current code try to use block id to find block pointer in /sys for any
section, and reuse that block pointer. that finding will take some time
even after commit 7c243c7168 ("mm: speedup in __early_pfn_to_nid")
that will skip the search in that case during booting up.
So solution could be increase block size just like SGI UV system did.
(harded code to 2g).
This patch is trying to probe the block size to make it match mmio remap
size. for example, Intel Nehalem later system will have memory range [0,
TOML), [4g, TOMH]. If the memory hole is 2g and total is 128g, TOM will
be 2g, and TOM2 will be 130g.
We could use 2g as block size instead of default 128M. That will reduce
number of entries in /sys/devices/system/memory/
On system 6TiB system will reduce boot time by 35 seconds.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
_PAGE_NUMA is currently an alias of _PROT_PROTNONE to trap NUMA hinting
faults on x86. Care is taken such that _PAGE_NUMA is used only in
situations where the VMA flags distinguish between NUMA hinting faults
and prot_none faults. This decision was x86-specific and conceptually
it is difficult requiring special casing to distinguish between PROTNONE
and NUMA ptes based on context.
Fundamentally, we only need the _PAGE_NUMA bit to tell the difference
between an entry that is really unmapped and a page that is protected
for NUMA hinting faults as if the PTE is not present then a fault will
be trapped.
Swap PTEs on x86-64 use the bits after _PAGE_GLOBAL for the offset.
This patch shrinks the maximum possible swap size and uses the bit to
uniquely distinguish between NUMA hinting ptes and swap ptes.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Steven Noonan <steven@uplinklabs.net>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__get_cpu_var() is used for multiple purposes in the kernel source. One
of them is address calculation via the form &__get_cpu_var(x). This
calculates the address for the instance of the percpu variable of the
current processor based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less
registers are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these
operations are used throughout then specialized macros can be defined in
non -x86 arches as well in order to optimize per cpu access by f.e. using
a global register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Signed-off-by: Christoph Lameter <cl@linux.com>
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org> [compilation only]
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
