Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752445AbbDAPTA (ORCPT ); Wed, 1 Apr 2015 11:19:00 -0400 Received: from mail-wi0-f175.google.com ([209.85.212.175]:36674 "EHLO mail-wi0-f175.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751638AbbDAPS5 (ORCPT ); Wed, 1 Apr 2015 11:18:57 -0400 Message-ID: <551C0C5E.9080003@plexistor.com> Date: Wed, 01 Apr 2015 18:18:54 +0300 From: Boaz Harrosh User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.5.0 MIME-Version: 1.0 To: Christoph Hellwig , linux-nvdimm@ml01.01.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, x86@kernel.org, axboe@kernel.dk CC: ross.zwisler@linux.intel.com, boaz@plexistor.com Subject: Re: [PATCH 2/2] pmem: add a driver for persistent memory References: <1427872339-6688-1-git-send-email-hch@lst.de> <1427872339-6688-3-git-send-email-hch@lst.de> In-Reply-To: <1427872339-6688-3-git-send-email-hch@lst.de> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 10721 Lines: 370 On 04/01/2015 10:12 AM, Christoph Hellwig wrote: > From: Ross Zwisler > > PMEM is a new driver that presents a reserved range of memory as a > block device. This is useful for developing with NV-DIMMs, and > can be used with volatile memory as a development platform. > > This patch contains the initial driver from Ross Zwisler, with > various changes from Boaz Harrosh and me. > > Signed-off-by: Ross Zwisler > [hch: convert to use a platform_device for discovery, fix partition > support, merged various patches from Boaz] > Signed-off-by: Christoph Hellwig > Tested-by: Ross Zwisler > Acked-by: Dan Williams > --- > MAINTAINERS | 6 ++ > drivers/block/Kconfig | 11 +++ > drivers/block/Makefile | 1 + > drivers/block/pmem.c | 260 +++++++++++++++++++++++++++++++++++++++++++++++++ > 4 files changed, 278 insertions(+) > create mode 100644 drivers/block/pmem.c > > diff --git a/MAINTAINERS b/MAINTAINERS > index 1de6afa..4517613 100644 > --- a/MAINTAINERS > +++ b/MAINTAINERS > @@ -8071,6 +8071,12 @@ S: Maintained > F: Documentation/blockdev/ramdisk.txt > F: drivers/block/brd.c > > +PERSISTENT MEMORY DRIVER > +M: Ross Zwisler > +L: linux-nvdimm@lists.01.org > +S: Supported > +F: drivers/block/pmem.c > + > RANDOM NUMBER DRIVER > M: "Theodore Ts'o" > S: Maintained > diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig > index 1b8094d..34753cf 100644 > --- a/drivers/block/Kconfig > +++ b/drivers/block/Kconfig > @@ -404,6 +404,17 @@ config BLK_DEV_RAM_DAX > and will prevent RAM block device backing store memory from being > allocated from highmem (only a problem for highmem systems). > > +config BLK_DEV_PMEM > + tristate "Persistent memory block device support" > + help > + Saying Y here will allow you to use a contiguous range of reserved > + memory as one or more block devices. > + > + To compile this driver as a module, choose M here: the module will be > + called pmem. > + > + If unsure, say N. > + > config CDROM_PKTCDVD > tristate "Packet writing on CD/DVD media" > depends on !UML > diff --git a/drivers/block/Makefile b/drivers/block/Makefile > index 02b688d..9cc6c18 100644 > --- a/drivers/block/Makefile > +++ b/drivers/block/Makefile > @@ -14,6 +14,7 @@ obj-$(CONFIG_PS3_VRAM) += ps3vram.o > obj-$(CONFIG_ATARI_FLOPPY) += ataflop.o > obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o > obj-$(CONFIG_BLK_DEV_RAM) += brd.o > +obj-$(CONFIG_BLK_DEV_PMEM) += pmem.o > obj-$(CONFIG_BLK_DEV_LOOP) += loop.o > obj-$(CONFIG_BLK_CPQ_DA) += cpqarray.o > obj-$(CONFIG_BLK_CPQ_CISS_DA) += cciss.o > diff --git a/drivers/block/pmem.c b/drivers/block/pmem.c > new file mode 100644 > index 0000000..0232ab7 > --- /dev/null > +++ b/drivers/block/pmem.c > @@ -0,0 +1,260 @@ > +/* > + * Persistent Memory Driver > + * Copyright (c) 2014, Intel Corporation. > + * Copyright (c) 2015, Christoph Hellwig . > + * Copyright (c) 2015, Boaz Harrosh . > + * > + * This program is free software; you can redistribute it and/or modify it > + * under the terms and conditions of the GNU General Public License, > + * version 2, as published by the Free Software Foundation. > + * > + * This program is distributed in the hope it will be useful, but WITHOUT > + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or > + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for > + * more details. > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#define PMEM_MINORS 16 > + > +struct pmem_device { > + struct request_queue *pmem_queue; > + struct gendisk *pmem_disk; > + > + /* One contiguous memory region per device */ > + phys_addr_t phys_addr; > + void *virt_addr; > + size_t size; > +}; > + > +static int pmem_major; > +static atomic_t pmem_index; > + > +static void pmem_do_bvec(struct pmem_device *pmem, struct page *page, > + unsigned int len, unsigned int off, int rw, > + sector_t sector) > +{ > + void *mem = kmap_atomic(page); > + size_t pmem_off = sector << 9; > + > + if (rw == READ) { > + memcpy(mem + off, pmem->virt_addr + pmem_off, len); > + flush_dcache_page(page); > + } else { > + flush_dcache_page(page); > + memcpy(pmem->virt_addr + pmem_off, mem + off, len); > + } > + > + kunmap_atomic(mem); > +} > + > +static void pmem_make_request(struct request_queue *q, struct bio *bio) > +{ > + struct block_device *bdev = bio->bi_bdev; > + struct pmem_device *pmem = bdev->bd_disk->private_data; > + int rw; > + struct bio_vec bvec; > + sector_t sector; > + struct bvec_iter iter; > + int err = 0; > + > + if (bio_end_sector(bio) > get_capacity(bdev->bd_disk)) { > + err = -EIO; > + goto out; > + } > + > + BUG_ON(bio->bi_rw & REQ_DISCARD); > + > + rw = bio_data_dir(bio); OK cool I was afraid since you did not like my unlikely patch that you might have missed this fix. > + sector = bio->bi_iter.bi_sector; > + bio_for_each_segment(bvec, bio, iter) { > + pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, bvec.bv_offset, > + rw, sector); > + sector += bvec.bv_len >> 9; > + } > + > +out: > + bio_endio(bio, err); > +} > + > +static int pmem_rw_page(struct block_device *bdev, sector_t sector, > + struct page *page, int rw) > +{ > + struct pmem_device *pmem = bdev->bd_disk->private_data; > + > + pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector); > + page_endio(page, rw & WRITE, 0); You might as well rw & WRITE also for the above pmem_do_bvec call. If there can be such problem than the rw == READ inside pmem_do_bvec will fail as well. > + return 0; > +} > + > +static long pmem_direct_access(struct block_device *bdev, sector_t sector, > + void **kaddr, unsigned long *pfn, long size) > +{ > + struct pmem_device *pmem = bdev->bd_disk->private_data; > + size_t offset = sector << 9; > + > + if (!pmem) > + return -ENODEV; > + > + *kaddr = pmem->virt_addr + offset; > + *pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT; > + > + return pmem->size - offset; > +} > + > +static const struct block_device_operations pmem_fops = { > + .owner = THIS_MODULE, > + .rw_page = pmem_rw_page, > + .direct_access = pmem_direct_access, > +}; > + > +static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res) > +{ > + struct pmem_device *pmem; > + struct gendisk *disk; > + int idx, err; > + > + err = -ENOMEM; > + pmem = kzalloc(sizeof(*pmem), GFP_KERNEL); > + if (!pmem) > + goto out; > + > + pmem->phys_addr = res->start; > + pmem->size = resource_size(res); > + > + err = -EINVAL; > + if (!request_mem_region(pmem->phys_addr, pmem->size, "pmem")) { > + dev_warn(dev, "could not reserve region [0x%llx:0x%zx]\n", > + pmem->phys_addr, pmem->size); > + goto out_free_dev; > + } > + > + /* > + * Map the memory as non-cachable, as we can't write back the contents > + * of the CPU caches in case of a crash. > + */ > + err = -ENOMEM; > + pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size); > + if (!pmem->virt_addr) > + goto out_release_region; You have removed the pmem_mapmem() helper and embedded all this here. The patch to add page-structs that I'm posting on top of this, uses the abstraction to switch between implementations. I'll add the split-out to the page-structs patch. Am heavy testing this set (Together with my small fix to e820) And will report tomorrow if the lab is able to survive the night. Thanks Boaz > + > + pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL); > + if (!pmem->pmem_queue) > + goto out_unmap; > + > + blk_queue_make_request(pmem->pmem_queue, pmem_make_request); > + blk_queue_max_hw_sectors(pmem->pmem_queue, 1024); > + blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY); > + > + disk = alloc_disk(PMEM_MINORS); > + if (!disk) > + goto out_free_queue; > + > + idx = atomic_inc_return(&pmem_index) - 1; > + > + disk->major = pmem_major; > + disk->first_minor = PMEM_MINORS * idx; > + disk->fops = &pmem_fops; > + disk->private_data = pmem; > + disk->queue = pmem->pmem_queue; > + disk->flags = GENHD_FL_EXT_DEVT; > + sprintf(disk->disk_name, "pmem%d", idx); > + disk->driverfs_dev = dev; > + set_capacity(disk, pmem->size >> 9); > + pmem->pmem_disk = disk; > + > + add_disk(disk); > + return pmem; > + > +out_free_queue: > + blk_cleanup_queue(pmem->pmem_queue); > +out_unmap: > + iounmap(pmem->virt_addr); > +out_release_region: > + release_mem_region(pmem->phys_addr, pmem->size); > +out_free_dev: > + kfree(pmem); > +out: > + return ERR_PTR(err); > +} > + > +static void pmem_free(struct pmem_device *pmem) > +{ > + del_gendisk(pmem->pmem_disk); > + put_disk(pmem->pmem_disk); > + blk_cleanup_queue(pmem->pmem_queue); > + iounmap(pmem->virt_addr); > + release_mem_region(pmem->phys_addr, pmem->size); > + kfree(pmem); > +} > + > +static int pmem_probe(struct platform_device *pdev) > +{ > + struct pmem_device *pmem; > + struct resource *res; > + > + if (WARN_ON(pdev->num_resources > 1)) > + return -ENXIO; > + > + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); > + if (!res) > + return -ENXIO; > + > + pmem = pmem_alloc(&pdev->dev, res); > + if (IS_ERR(pmem)) > + return PTR_ERR(pmem); > + > + platform_set_drvdata(pdev, pmem); > + return 0; > +} > + > +static int pmem_remove(struct platform_device *pdev) > +{ > + struct pmem_device *pmem = platform_get_drvdata(pdev); > + > + pmem_free(pmem); > + return 0; > +} > + > +static struct platform_driver pmem_driver = { > + .probe = pmem_probe, > + .remove = pmem_remove, > + .driver = { > + .owner = THIS_MODULE, > + .name = "pmem", > + }, > +}; > + > +static int __init pmem_init(void) > +{ > + int error; > + > + pmem_major = register_blkdev(0, "pmem"); > + if (pmem_major < 0) > + return pmem_major; > + > + error = platform_driver_register(&pmem_driver); > + if (error) > + unregister_blkdev(pmem_major, "pmem"); > + return error; > +} > + > +static void pmem_exit(void) > +{ > + platform_driver_unregister(&pmem_driver); > + unregister_blkdev(pmem_major, "pmem"); > +} > + > +MODULE_AUTHOR("Ross Zwisler "); > +MODULE_LICENSE("GPL v2"); > + > +module_init(pmem_init); > +module_exit(pmem_exit); > -- 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/