aboutsummaryrefslogtreecommitdiff
path: root/include/linux/percpu.h
AgeCommit message (Collapse)AuthorFilesLines
2009-02-09percpu: make PER_CPU_BASE_SECTION overridable by archesBrian Gerst1-1/+7
Impact: bug fix IA-64 needs to put percpu data in the seperate section even on UP. Fixes regression caused by "percpu: refactor percpu.h" Signed-off-by: Brian Gerst <[email protected]> Acked-by: Tony Luck <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2009-01-20percpu: refactor percpu.hBrian Gerst1-18/+23
Impact: cleanup Refactor the DEFINE_PER_CPU_* macros and add .data.percpu.first section. Signed-off-by: Brian Gerst <[email protected]> Signed-off-by: Tejun Heo <[email protected]>
2008-09-05Merge commit '63cc8c75156462d4b42cbdd76c293b7eee7ddbfe':Ingo Molnar1-0/+7
"percpu: introduce DEFINE_PER_CPU_PAGE_ALIGNED() macro" into x86/core Conflicts: arch/x86/kernel/cpu/common.c Signed-off-by: Ingo Molnar <[email protected]>
2008-07-26mm/allocpercpu.c: make 4 functions staticAdrian Bunk1-29/+0
This patch makes the following needlessly global functions static: - percpu_depopulate() - __percpu_depopulate_mask() - percpu_populate() - __percpu_populate_mask() Signed-off-by: Adrian Bunk <[email protected]> Acked-by: Christoph Lameter <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2008-05-25percpu: introduce DEFINE_PER_CPU_PAGE_ALIGNED() macroEric Dumazet1-0/+7
While examining holes in percpu section I found this : c05f5000 D per_cpu__current_task c05f5000 D __per_cpu_start c05f5004 D per_cpu__cpu_number c05f5008 D per_cpu__irq_regs c05f500c d per_cpu__cpu_devices c05f5040 D per_cpu__cyc2ns <Big Hole of about 4000 bytes> c05f6000 d per_cpu__cpuid4_info c05f6004 d per_cpu__cache_kobject c05f6008 d per_cpu__index_kobject <Big Hole of about 4000 bytes> c05f7000 D per_cpu__gdt_page This is because gdt_page is a percpu variable, defined with a page alignement, and linker is doing its job, two times because of .o nesting in the build process. I introduced a new macro DEFINE_PER_CPU_PAGE_ALIGNED() to avoid wasting this space. All page aligned variables (only one at this time) are put in a separate subsection .data.percpu.page_aligned, at the very begining of percpu zone. Before patch , on a x86_32 machine : .data.percpu 30232 3227471872 .data.percpu 22168 3227471872 Thats 8064 bytes saved for each CPU. Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: Ingo Molnar <[email protected]> Signed-off-by: Thomas Gleixner <[email protected]>
2008-05-14per_cpu: fix DEFINE_PER_CPU_SHARED_ALIGNED for modulesEric Dumazet1-1/+7
Current module loader lookups ".data.percpu" ELF section to perform per_cpu relocation. But DEFINE_PER_CPU_SHARED_ALIGNED() uses another section (".data.percpu.shared_aligned"), currently only handled in vmlinux.lds, not by module loader. To correct this problem, instead of adding logic into module loader, or using at build time a module.lds file for all arches to group ".data.percpu.shared_aligned" into ".data.percpu", just use ".data.percpu" for modules. Alignment requirements are correctly handled by ld and module loader. Signed-off-by: Eric Dumazet <[email protected]> Cc: Rusty Russell <[email protected]> Cc: Fenghua Yu <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2008-04-29Remove superfluous include of string.h from percpu.hRobert P. J. Day1-1/+0
There's nothing in percpu.h that requires an explicit inclusion of string.h. Signed-off-by: Robert P. J. Day <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2008-02-06PERCPU : __percpu_alloc_mask() can dynamically size percpu_data storageEric Dumazet1-1/+1
Instead of allocating a fix sized array of NR_CPUS pointers for percpu_data, we can use nr_cpu_ids, which is generally < NR_CPUS. Signed-off-by: Eric Dumazet <[email protected]> Cc: Christoph Lameter <[email protected]> Cc: "David S. Miller" <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2008-01-30ia64: use generic percpu[email protected]1-4/+0
ia64 has a special processor specific mapping that can be used to locate the offset for the current per cpu area. Cc: [email protected] Signed-off-by: Mike Travis <[email protected]> Acked-by: Tony Luck <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2008-01-30percpu: move arch XX_PER_CPU_XX definitions into linux/percpu.h[email protected]1-0/+24
- Special consideration for IA64: Add the ability to specify arch specific per cpu flags - remove .data.percpu attribute from DEFINE_PER_CPU for non-smp case. The arch definitions are all the same. So move them into linux/percpu.h. We cannot move DECLARE_PER_CPU since some include files just include asm/percpu.h to avoid include recursion problems. Cc: Rusty Russell <[email protected]> Cc: Andi Kleen <[email protected]> Signed-off-by: Christoph Lameter <[email protected]> Signed-off-by: Mike Travis <[email protected]> Signed-off-by: Thomas Gleixner <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2007-07-16Remove unnecessary includes of spinlock.h under include/linuxRobert P. J. Day1-1/+1
Remove the obviously unnecessary includes of <linux/spinlock.h> under the include/linux/ directory, and fix the couple errors that are introduced as a result of that. Signed-off-by: Robert P. J. Day <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2007-05-02[PATCH] x86-64: Account for module percpu space separately from kernel percpuJeremy Fitzhardinge1-1/+8
Rather than using a single constant PERCPU_ENOUGH_ROOM, compute it as the sum of kernel_percpu + PERCPU_MODULE_RESERVE. This is now common to all architectures; if an architecture wants to set PERCPU_ENOUGH_ROOM to something special, then it may do so (ia64 is the only one which does). Signed-off-by: Jeremy Fitzhardinge <[email protected]> Signed-off-by: Andi Kleen <[email protected]> Cc: Rusty Russell <[email protected]> Cc: Eric W. Biederman <[email protected]> Cc: Andi Kleen <[email protected]>
2006-10-06[PATCH] Fix typo in "syntax error if percpu macros are incorrectly used" patchJan Blunck1-1/+1
Trivial typo fix in the "syntax error if percpu macros are incorrectly used" patch. I misspelled "identifier" in all places. D'Oh! Thanks to Dirk Mueller to point this out. Signed-off-by: Jan Blunck <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2006-09-29[PATCH] __percpu_alloc_mask() has to be __always_inline in UP caseAl Viro1-1/+1
... or we'll end up with cpu_online_map being evaluated on UP. In modules. cpumask.h is very careful to avoid that, and for a very good reason. So should we... PS: yes, it really triggers (on alpha). Signed-off-by: Al Viro <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2006-09-26[PATCH] CPU hotplug compatible alloc_percpu()Martin Peschke1-19/+60
This patch splits alloc_percpu() up into two phases. Likewise for free_percpu(). This allows clients to limit initial allocations to online cpu's, and to populate or depopulate per-cpu data at run time as needed: struct my_struct *obj; /* initial allocation for online cpu's */ obj = percpu_alloc(sizeof(struct my_struct), GFP_KERNEL); ... /* populate per-cpu data for cpu coming online */ ptr = percpu_populate(obj, sizeof(struct my_struct), GFP_KERNEL, cpu); ... /* access per-cpu object */ ptr = percpu_ptr(obj, smp_processor_id()); ... /* depopulate per-cpu data for cpu going offline */ percpu_depopulate(obj, cpu); ... /* final removal */ percpu_free(obj); Signed-off-by: Martin Peschke <[email protected]> Cc: Paul Jackson <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2006-09-26[PATCH] trigger a syntax error if percpu macros are incorrectly usedJan Blunck1-2/+8
get_cpu_var()/per_cpu()/__get_cpu_var() arguments must be simple identifiers. Otherwise the arch dependent implementations might break. This patch enforces the correct usage of the macros by producing a syntax error if the variable is not a simple identifier. Signed-off-by: Jan Blunck <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2006-01-08[PATCH] remove unused blkp field in percpu_dataEric Dumazet1-1/+0
I found that blkp field was not used in kernel tree. As most of the times NR_CPUS is a power of two and kmalloc() memory blocks too, this extra field basically doubles the memory space allocated in __alloc_percpu() to store the 'struct percpu_data' (for example, if NR_CPUS=8 on i386, kmalloc(4*8+4) returns a 64 bytes block instead of a 32 bytes block after this patch) Signed-off-by: Eric Dumazet <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2006-01-08[PATCH] slab: remove unused align parameter from alloc_percpuPekka Enberg1-4/+3
__alloc_percpu and alloc_percpu both take an 'align' argument which is completely ignored. snmp6_mib_init() in net/ipv6/af_inet6.c attempts to use it, but it will be ignored. Therefore, remove the 'align' argument and fixup the lone caller. Signed-off-by: Matthew Dobson <[email protected]> Acked-by: Manfred Spraul <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2005-11-13[PATCH] Shut up per_cpu_ptr() on UPPaul Mundt1-1/+1
Currently per_cpu_ptr() doesn't really do anything with 'cpu' in the UP case. This is problematic in the cases where this is the only place the variable is referenced: CC kernel/workqueue.o kernel/workqueue.c: In function `current_is_keventd': kernel/workqueue.c:460: warning: unused variable `cpu' Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2005-04-16Linux-2.6.12-rc2Linus Torvalds1-0/+61
Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
Powered by cgit, Gruvboxed by Blaster4385.