Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754221AbZCJH5e (ORCPT ); Tue, 10 Mar 2009 03:57:34 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753610AbZCJH42 (ORCPT ); Tue, 10 Mar 2009 03:56:28 -0400 Received: from hera.kernel.org ([140.211.167.34]:56886 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753365AbZCJH4Y (ORCPT ); Tue, 10 Mar 2009 03:56:24 -0400 From: Tejun Heo To: mingo@elte.hu, rusty@rustcorp.com.au, tglx@linutronix.de, x86@kernel.org, linux-kernel@vger.kernel.org, hpa@zytor.com, Paul Mundt , rmk@arm.linux.org.uk, starvik@axis.com, ralf@linux-mips.org, davem@davemloft.net, cooloney@kernel.org, kyle@mcmartin.ca, matthew@wil.cx, grundler@parisc-linux.org, takata@linux-m32r.org, benh@kernel.crashing.org, rth@twiddle.net, ink@jurassic.park.msu.ru, schwidefsky@de.ibm.com, heiko.carstens@de.ibm.com Cc: Tejun Heo Subject: [PATCH 4/5] percpu: generalize embedding first chunk setup helper Date: Tue, 10 Mar 2009 16:53:50 +0900 Message-Id: <1236671631-9305-5-git-send-email-tj@kernel.org> X-Mailer: git-send-email 1.6.0.2 In-Reply-To: <1236671631-9305-1-git-send-email-tj@kernel.org> References: <1236671631-9305-1-git-send-email-tj@kernel.org> X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.0 (hera.kernel.org [127.0.0.1]); Tue, 10 Mar 2009 07:53:59 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7360 Lines: 205 Impact: code reorganization Separate out embedding first chunk setup helper from x86 embedding first chunk allocator and put it in mm/percpu.c. This will be used by the default percpu first chunk allocator and possibly by other archs. Signed-off-by: Tejun Heo --- arch/x86/kernel/setup_percpu.c | 54 +++---------------------- include/linux/percpu.h | 4 ++ mm/percpu.c | 86 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 96 insertions(+), 48 deletions(-) diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index e41c51f..400331b 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -257,31 +257,13 @@ static ssize_t __init setup_pcpu_remap(size_t static_size) * Embedding allocator * * The first chunk is sized to just contain the static area plus - * module and dynamic reserves, and allocated as a contiguous area - * using bootmem allocator and used as-is without being mapped into - * vmalloc area. This enables the first chunk to piggy back on the - * linear physical PMD mapping and doesn't add any additional pressure - * to TLB. Note that if the needed size is smaller than the minimum - * unit size, the leftover is returned to the bootmem allocator. + * module and dynamic reserves and embedded into linear physical + * mapping so that it can use PMD mapping without additional TLB + * pressure. */ -static void *pcpue_ptr __initdata; -static size_t pcpue_size __initdata; -static size_t pcpue_unit_size __initdata; - -static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) -{ - size_t off = (size_t)pageno << PAGE_SHIFT; - - if (off >= pcpue_size) - return NULL; - - return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off); -} - static ssize_t __init setup_pcpu_embed(size_t static_size) { - unsigned int cpu; - size_t dyn_size; + size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE; /* * If large page isn't supported, there's no benefit in doing @@ -291,32 +273,8 @@ static ssize_t __init setup_pcpu_embed(size_t static_size) if (!cpu_has_pse || pcpu_need_numa()) return -EINVAL; - /* allocate and copy */ - pcpue_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + - PERCPU_DYNAMIC_RESERVE); - pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); - dyn_size = pcpue_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; - - pcpue_ptr = pcpu_alloc_bootmem(0, num_possible_cpus() * pcpue_unit_size, - PAGE_SIZE); - if (!pcpue_ptr) - return -ENOMEM; - - for_each_possible_cpu(cpu) { - void *ptr = pcpue_ptr + cpu * pcpue_unit_size; - - free_bootmem(__pa(ptr + pcpue_size), - pcpue_unit_size - pcpue_size); - memcpy(ptr, __per_cpu_load, static_size); - } - - /* we're ready, commit */ - pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", - pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); - - return pcpu_setup_first_chunk(pcpue_get_page, static_size, - PERCPU_FIRST_CHUNK_RESERVE, dyn_size, - pcpue_unit_size, pcpue_ptr, NULL); + return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE, + reserve - PERCPU_FIRST_CHUNK_RESERVE, -1); } /* diff --git a/include/linux/percpu.h b/include/linux/percpu.h index fb455dc..ee5615d 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -111,6 +111,10 @@ extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, void *base_addr, pcpu_populate_pte_fn_t populate_pte_fn); +extern ssize_t __init pcpu_embed_first_chunk( + size_t static_size, size_t reserved_size, + ssize_t dyn_size, ssize_t unit_size); + /* * Use this to get to a cpu's version of the per-cpu object * dynamically allocated. Non-atomic access to the current CPU's diff --git a/mm/percpu.c b/mm/percpu.c index 2f94661..1aa5d8f 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1238,3 +1238,89 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); return pcpu_unit_size; } + +/* + * Embedding first chunk setup helper. + */ +static void *pcpue_ptr __initdata; +static size_t pcpue_size __initdata; +static size_t pcpue_unit_size __initdata; + +static struct page * __init pcpue_get_page(unsigned int cpu, int pageno) +{ + size_t off = (size_t)pageno << PAGE_SHIFT; + + if (off >= pcpue_size) + return NULL; + + return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off); +} + +/** + * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: free size for dynamic allocation in bytes, -1 for auto + * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto + * + * This is a helper to ease setting up embedded first percpu chunk and + * can be called where pcpu_setup_first_chunk() is expected. + * + * If this function is used to setup the first chunk, it is allocated + * as a contiguous area using bootmem allocator and used as-is without + * being mapped into vmalloc area. This enables the first chunk to + * piggy back on the linear physical mapping which often uses larger + * page size. + * + * When @dyn_size is positive, dynamic area might be larger than + * specified to fill page alignment. Also, when @dyn_size is auto, + * @dyn_size does not fill the whole first chunk but only what's + * necessary for page alignment after static and reserved areas. + * + * If the needed size is smaller than the minimum or specified unit + * size, the leftover is returned to the bootmem allocator. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access on success, -errno on failure. + */ +ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size, + ssize_t dyn_size, ssize_t unit_size) +{ + unsigned int cpu; + + /* determine parameters and allocate */ + pcpue_size = PFN_ALIGN(static_size + reserved_size + + (dyn_size >= 0 ? dyn_size : 0)); + if (dyn_size != 0) + dyn_size = pcpue_size - static_size - reserved_size; + + if (unit_size >= 0) { + BUG_ON(unit_size < pcpue_size); + pcpue_unit_size = unit_size; + } else + pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); + + pcpue_ptr = __alloc_bootmem_nopanic( + num_possible_cpus() * pcpue_unit_size, + PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + if (!pcpue_ptr) + return -ENOMEM; + + /* return the leftover and copy */ + for_each_possible_cpu(cpu) { + void *ptr = pcpue_ptr + cpu * pcpue_unit_size; + + free_bootmem(__pa(ptr + pcpue_size), + pcpue_unit_size - pcpue_size); + memcpy(ptr, __per_cpu_load, static_size); + } + + /* we're ready, commit */ + pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", + pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); + + return pcpu_setup_first_chunk(pcpue_get_page, static_size, + reserved_size, dyn_size, + pcpue_unit_size, pcpue_ptr, NULL); +} -- 1.6.0.2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/