From patchwork Mon Mar 1 23:25:08 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marcelo Tosatti X-Patchwork-Id: 83088 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter.kernel.org (8.14.3/8.14.3) with ESMTP id o21NVrt4008529 for ; Mon, 1 Mar 2010 23:31:53 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752003Ab0CAXbv (ORCPT ); Mon, 1 Mar 2010 18:31:51 -0500 Received: from mx1.redhat.com ([209.132.183.28]:12685 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751714Ab0CAXbv (ORCPT ); Mon, 1 Mar 2010 18:31:51 -0500 Received: from int-mx02.intmail.prod.int.phx2.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) by mx1.redhat.com (8.13.8/8.13.8) with ESMTP id o21NVhh4023114 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Mon, 1 Mar 2010 18:31:43 -0500 Received: from ns3.rdu.redhat.com (ns3.rdu.redhat.com [10.11.255.199]) by int-mx02.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id o21NVg6Z007504; Mon, 1 Mar 2010 18:31:42 -0500 Received: from amt.cnet (vpn-11-64.rdu.redhat.com [10.11.11.64]) by ns3.rdu.redhat.com (8.13.8/8.13.8) with ESMTP id o21NVdXo012781; Mon, 1 Mar 2010 18:31:40 -0500 Received: from amt.cnet (amt.cnet [127.0.0.1]) by amt.cnet (Postfix) with ESMTP id 003FC68A17C; Mon, 1 Mar 2010 20:25:11 -0300 (BRT) Received: (from marcelo@localhost) by amt.cnet (8.14.3/8.14.3/Submit) id o21NP8Qu022044; Mon, 1 Mar 2010 20:25:08 -0300 Date: Mon, 1 Mar 2010 20:25:08 -0300 From: Marcelo Tosatti To: Paul Brook Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org, john cooper , avi@redhat.com Subject: Re: [Qemu-devel] [patch uq/master 2/2] Add option to use file backed guest memory Message-ID: <20100301232508.GA13703@amt.cnet> References: <20100224211117.958583246@amt.cnet> <20100224211507.913712224@amt.cnet> <201002280128.16649.paul@codesourcery.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <201002280128.16649.paul@codesourcery.com> User-Agent: Mutt/1.5.20 (2009-08-17) X-Scanned-By: MIMEDefang 2.67 on 10.5.11.12 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter.kernel.org [140.211.167.41]); Mon, 01 Mar 2010 23:31:54 +0000 (UTC) Index: qemu/cpu-all.h =================================================================== --- qemu.orig/cpu-all.h +++ qemu/cpu-all.h @@ -847,6 +847,9 @@ extern uint8_t *phys_ram_dirty; extern ram_addr_t ram_size; extern ram_addr_t last_ram_offset; +extern const char *mem_path; +extern int mem_prealloc; + /* physical memory access */ /* MMIO pages are identified by a combination of an IO device index and Index: qemu/exec.c =================================================================== --- qemu.orig/exec.c +++ qemu/exec.c @@ -2529,6 +2529,99 @@ void qemu_flush_coalesced_mmio_buffer(vo kvm_flush_coalesced_mmio_buffer(); } +#if defined(__linux__) && !defined(TARGET_S390X) + +#include + +#define HUGETLBFS_MAGIC 0x958458f6 + +static long gethugepagesize(const char *path) +{ + struct statfs fs; + int ret; + + do { + ret = statfs(path, &fs); + } while (ret != 0 && errno == EINTR); + + if (ret != 0) { + perror("statfs"); + return 0; + } + + if (fs.f_type != HUGETLBFS_MAGIC) + fprintf(stderr, "Warning: path not on HugeTLBFS: %s\n", path); + + return fs.f_bsize; +} + +static void *file_ram_alloc(ram_addr_t memory, const char *path) +{ + char *filename; + void *area; + int fd; +#ifdef MAP_POPULATE + int flags; +#endif + unsigned long hpagesize; + + hpagesize = gethugepagesize(path); + if (!hpagesize) { + return NULL; + } + + if (memory < hpagesize) { + return NULL; + } + + if (kvm_enabled() && !kvm_has_sync_mmu()) { + fprintf(stderr, "host lacks kvm mmu notifiers, -mem-path unsupported\n"); + return NULL; + } + + if (asprintf(&filename, "%s/qemu_back_mem.XXXXXX", path) == -1) { + return NULL; + } + + fd = mkstemp(filename); + if (fd < 0) { + perror("mkstemp"); + free(filename); + return NULL; + } + unlink(filename); + free(filename); + + memory = (memory+hpagesize-1) & ~(hpagesize-1); + + /* + * ftruncate is not supported by hugetlbfs in older + * hosts, so don't bother bailing out on errors. + * If anything goes wrong with it under other filesystems, + * mmap will fail. + */ + if (ftruncate(fd, memory)) + perror("ftruncate"); + +#ifdef MAP_POPULATE + /* NB: MAP_POPULATE won't exhaustively alloc all phys pages in the case + * MAP_PRIVATE is requested. For mem_prealloc we mmap as MAP_SHARED + * to sidestep this quirk. + */ + flags = mem_prealloc ? MAP_POPULATE | MAP_SHARED : MAP_PRIVATE; + area = mmap(0, memory, PROT_READ | PROT_WRITE, flags, fd, 0); +#else + area = mmap(0, memory, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); +#endif + if (area == MAP_FAILED) { + perror("file_ram_alloc: can't mmap RAM pages"); + close(fd); + return (NULL); + } + return area; +} +#endif + ram_addr_t qemu_ram_alloc(ram_addr_t size) { RAMBlock *new_block; @@ -2536,16 +2629,28 @@ ram_addr_t qemu_ram_alloc(ram_addr_t siz size = TARGET_PAGE_ALIGN(size); new_block = qemu_malloc(sizeof(*new_block)); + if (mem_path) { +#if defined (__linux__) && !defined(TARGET_S390X) + new_block->host = file_ram_alloc(size, mem_path); + if (!new_block->host) + exit(1); +#else + fprintf(stderr, "-mem-path option unsupported\n"); + exit(1); +#endif + } else { #if defined(TARGET_S390X) && defined(CONFIG_KVM) - /* XXX S390 KVM requires the topmost vma of the RAM to be < 256GB */ - new_block->host = mmap((void*)0x1000000, size, PROT_EXEC|PROT_READ|PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, -1, 0); + /* XXX S390 KVM requires the topmost vma of the RAM to be < 256GB */ + new_block->host = mmap((void*)0x1000000, size, + PROT_EXEC|PROT_READ|PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); #else - new_block->host = qemu_vmalloc(size); + new_block->host = qemu_vmalloc(size); #endif #ifdef MADV_MERGEABLE - madvise(new_block->host, size, MADV_MERGEABLE); + madvise(new_block->host, size, MADV_MERGEABLE); #endif + } new_block->offset = last_ram_offset; new_block->length = size; Index: qemu/qemu-options.hx =================================================================== --- qemu.orig/qemu-options.hx +++ qemu/qemu-options.hx @@ -314,6 +314,22 @@ a suffix of ``M'' or ``G'' can be used t gigabytes respectively. ETEXI +DEF("mem-path", HAS_ARG, QEMU_OPTION_mempath, + "-mem-path FILE provide backing storage for guest RAM\n") +STEXI +@item -mem-path @var{path} +Allocate guest RAM from a temporarily created file in @var{path}. +ETEXI + +#ifdef MAP_POPULATE +DEF("mem-prealloc", 0, QEMU_OPTION_mem_prealloc, + "-mem-prealloc preallocate guest memory (use with -mem-path)\n") +STEXI +@item -mem-prealloc +Preallocate memory when using -mem-path. +ETEXI +#endif + DEF("k", HAS_ARG, QEMU_OPTION_k, "-k language use keyboard layout (for example 'fr' for French)\n") STEXI Index: qemu/vl.c =================================================================== --- qemu.orig/vl.c +++ qemu/vl.c @@ -185,6 +185,10 @@ enum vga_retrace_method vga_retrace_meth DisplayType display_type = DT_DEFAULT; const char* keyboard_layout = NULL; ram_addr_t ram_size; +const char *mem_path = NULL; +#ifdef MAP_POPULATE +int mem_prealloc = 0; /* force preallocation of physical target memory */ +#endif int nb_nics; NICInfo nd_table[MAX_NICS]; int vm_running; @@ -5216,6 +5220,14 @@ int main(int argc, char **argv, char **e ram_size = value; break; } + case QEMU_OPTION_mempath: + mem_path = optarg; + break; +#ifdef MAP_POPULATE + case QEMU_OPTION_mem_prealloc: + mem_prealloc = 1; + break; +#endif case QEMU_OPTION_d: { int mask;