Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753448Ab0K2Kpj (ORCPT ); Mon, 29 Nov 2010 05:45:39 -0500 Received: from mga09.intel.com ([134.134.136.24]:5721 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753321Ab0K2Kpa (ORCPT ); Mon, 29 Nov 2010 05:45:30 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.59,275,1288594800"; d="scan'208";a="681922333" X-Mailbox-Line: From shaohui.zheng@intel.com Mon Nov 29 17:19:36 2010 Message-Id: <20101129091936.116394523@intel.com> References: <20101129091750.950277284@intel.com> User-Agent: quilt/0.46-1 Date: Mon, 29 Nov 2010 17:17:56 +0800 From: shaohui.zheng@intel.com To: akpm@linux-foundation.org, linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org, haicheng.li@linux.intel.com, lethal@linux-sh.org, ak@linux.intel.com, shaohui.zheng@linux.intel.com, rientjes@google.com, dave@linux.vnet.ibm.com, gregkh@suse.de, Shaohui Zheng , Haicheng Li , Wu Fengguang Subject: [6/8, v5] From: Shaohui Zheng Content-Disposition: inline; filename=006-hotplug-emulator-extend-memory-probe-interface-to-support-numa.patch Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5950 Lines: 184 Subject: [6/8, v5] NUMA Hotplug Emulator: extend memory probe interface to support NUMA Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists. Add a memory section(128M) to node 3(boots with mem=1024m) echo 0x40000000,3 > memory/probe And more we make it friendly, it is possible to add memory to do echo 3g > memory/probe echo 1024m,3 > memory/probe It maintains backwards compatibility. Another format suggested by Dave Hansen: echo physical_address=0x40000000 numa_node=3 > memory/probe it is more explicit to show meaning of the parameters. Signed-off-by: Shaohui Zheng Signed-off-by: Haicheng Li Signed-off-by: Wu Fengguang --- Index: linux-hpe4/arch/x86/Kconfig =================================================================== --- linux-hpe4.orig/arch/x86/Kconfig 2010-11-29 14:43:51.529065999 +0800 +++ linux-hpe4/arch/x86/Kconfig 2010-11-29 14:43:54.569066000 +0800 @@ -1276,10 +1276,6 @@ def_bool y depends on ARCH_SPARSEMEM_ENABLE -config ARCH_MEMORY_PROBE - def_bool X86_64 - depends on MEMORY_HOTPLUG - config ILLEGAL_POINTER_VALUE hex default 0 if X86_32 Index: linux-hpe4/drivers/base/memory.c =================================================================== --- linux-hpe4.orig/drivers/base/memory.c 2010-11-29 14:43:51.539066000 +0800 +++ linux-hpe4/drivers/base/memory.c 2010-11-29 14:43:54.569066000 +0800 @@ -329,27 +329,76 @@ * will not need to do it from userspace. The fake hot-add code * as well as ppc64 will do all of their discovery in userspace * and will require this interface. + * + * Parameter format 1: physical_address,numa_node + * Parameter format 2: physical_address=0x40000000 numa_node=3 */ #ifdef CONFIG_ARCH_MEMORY_PROBE -static ssize_t -memory_probe_store(struct class *class, struct class_attribute *attr, - const char *buf, size_t count) +ssize_t parse_memory_probe_store(const char *buf, size_t count) { - u64 phys_addr; - int nid; + u64 phys_addr = 0; + int nid = 0; int ret; + char *p = NULL, *q = NULL; + /* format: physical_address=0x40000000 numa_node=3 */ + p = strchr(buf, '='); + if (p != NULL) { + *p = '\0'; + q = strchr(buf, ' '); + if (q == NULL) { + if (strcmp(buf, "physical_address") != 0) + ret = -EPERM; + else + phys_addr = memparse(p+1, NULL); + } else { + *q++ = '\0'; + p = strchr(q, '='); + if (strcmp(buf, "physical_address") == 0) + phys_addr = memparse(p+1, NULL); + if (strcmp(buf, "numa_node") == 0) + nid = simple_strtoul(p+1, NULL, 0); + if (strcmp(q, "physical_address") == 0) + phys_addr = memparse(p+1, NULL); + if (strcmp(q, "numa_node") == 0) + nid = simple_strtoul(p+1, NULL, 0); + } + } else { /* physical_address,numa_node */ + p = strchr(buf, ','); + if (p != NULL && strlen(p+1) > 0) { + /* nid specified */ + *p++ = '\0'; + nid = simple_strtoul(p, NULL, 0); + phys_addr = memparse(buf, NULL); + } else { + phys_addr = memparse(buf, NULL); + nid = memory_add_physaddr_to_nid(phys_addr); + } + } - phys_addr = simple_strtoull(buf, NULL, 0); - - nid = memory_add_physaddr_to_nid(phys_addr); - ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT); + if (nid < 0 || nid > nr_node_ids - 1) { + printk(KERN_ERR "Invalid node id %d(0<=nid<%d).\n", nid, nr_node_ids); + ret = -EPERM; + } else { + printk(KERN_INFO "Add a memory section to node: %d.\n", nid); + ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT); + if (ret) + count = ret; + } if (ret) count = ret; return count; } -static CLASS_ATTR(probe, S_IWUSR, NULL, memory_probe_store); +EXPORT_SYMBOL(parse_memory_probe_store); + +static ssize_t +memory_probe_store(struct class *class, struct class_attribute *attr, + const char *buf, size_t count) +{ + return parse_memory_probe_store(buf, count); +} + static int memory_probe_init(void) { Index: linux-hpe4/mm/Kconfig =================================================================== --- linux-hpe4.orig/mm/Kconfig 2010-11-29 14:43:51.549066001 +0800 +++ linux-hpe4/mm/Kconfig 2010-11-29 14:43:54.569066000 +0800 @@ -174,6 +174,17 @@ default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC default "4" +config ARCH_MEMORY_PROBE + def_bool y + bool "Memory hotplug emulation" + depends on MEMORY_HOTPLUG + ---help--- + Enable memory hotplug emulation. Reserve memory with grub parameter + "mem=N"(such as mem=1024M), where N is the initial memory size, the + rest physical memory will be removed from e820 table; the memory probe + interface is for memory hot-add to specified node in software method. + This is for debuging and testing purpose + # # support for memory compaction config COMPACTION Index: linux-hpe4/include/linux/memory_hotplug.h =================================================================== --- linux-hpe4.orig/include/linux/memory_hotplug.h 2010-11-29 14:43:51.559066001 +0800 +++ linux-hpe4/include/linux/memory_hotplug.h 2010-11-29 14:43:54.569066000 +0800 @@ -211,6 +211,14 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); +#ifdef CONFIG_ARCH_MEMORY_PROBE +extern ssize_t parse_memory_probe_store(const char *buf, size_t count); +#else +static inline ssize_t parse_memory_probe_store(const char *buf, size_t count) +{ + return 0; +} +#endif /* CONFIG_ARCH_MEMORY_PROBE */ #ifdef CONFIG_ARCH_MEMORY_PROBE extern ssize_t parse_memory_probe_store(const char *buf, size_t count); -- Thanks & Regards, Shaohui -- 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/