Add persistent memory driver
Subsystems (3)
cover Add persistent memory driver
PMEM is a modified version of the Block RAM Driver, BRD. The major difference is that BRD allocates its backing store pages from the page cache, whereas PMEM uses reserved memory that has been ioremapped.
One benefit of this approach is that there is a direct mapping between filesystem block numbers and virtual addresses. In PMEM, filesystem blocks N, N+1, N+2, etc. will all be adjacent in the virtual memory space. This property allows us to set up PMD mappings (2 MiB) for DAX.
This patch set is builds upon the work that Matthew Wilcox has been doing for DAX, which has been merged into the v4.0 kernel series.
For more information on PMEM and for some instructions on how to use it, please check out PMEM's github tree:
Boaz Harrosh (1):
pmem: Let each device manage private memory region
Ross Zwisler (5):
pmem: Initial version of persistent memory driver
pmem: Add support for getgeo()
pmem: Add support for rw_page()
pmem: Add support for direct_access()
pmem: Clean up includes
MAINTAINERS | 6 + drivers/block/Kconfig | 41 +++++ drivers/block/Makefile | 1 + drivers/block/pmem.c | 401 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 449 insertions(+) create mode 100644 drivers/block/pmem.c
Signature · 1 line
1.9.3
PATCH 1/6 pmem: Initial version of persistent memory driver
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.
--- MAINTAINERS | 6 + drivers/block/Kconfig | 41 ++++++ drivers/block/Makefile | 1 + drivers/block/pmem.c | 330 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 378 insertions(+) create mode 100644 drivers/block/pmem.c
MAINTAINERS +6 -0
@@ -8052,6 +8052,12 @@ S: Maintained F: Documentation/blockdev/ramdisk.txt F: drivers/block/brd.c +PERSISTENT MEMORY DRIVER +M: Ross Zwisler <[email protected]> +L: [email protected] +S: Supported +F: drivers/block/pmem.c + RANDOM NUMBER DRIVER M: "Theodore Ts'o" <[email protected]> S: Maintained
drivers/block/Kconfig +41 -0
47 lines not on this page · raw message
drivers/block/Makefile +1 -0
@@ -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
drivers/block/pmem.c new file +330 -0
330 lines not on this page · raw message
Signature · 1 line
1.9.3
Re: [PATCH 1/6] pmem: Initial version of persistent memory driver
Just a license nit.
drivers/block/pmem.c line 12
Quoted 11 lines · Ross Zwisler
drivers/block/pmem.c new file +8
-0+* 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.
This states the license is GPL v2.
Quoted 1 line
+MODULE_LICENSE("GPL");
And using
MODULE_LICENSE("GPL v2");would match that statement.
Paul Bolle
PATCH 2/6 pmem: Add support for getgeo()
In reply to Ross ZwislerSome programs require HDIO_GETGEO work, which requires we implement getgeo. Based off of the work done to the NVMe driver in this commit:
commit 4cc09e2dc4cb ("NVMe: Add getgeo to block ops")
--- drivers/block/pmem.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
drivers/block/pmem.c +10 -0
@@ -50,6 +50,15 @@ struct pmem_device {size_t size; }; +static int pmem_getgeo (struct block_device *bd,struct hd_geometry *geo) +{ +/* some standard values */ + geo->heads =1 <<6 ; + geo->sectors =1 <<5 ; + geo->cylinders =get_capacity (bd->bd_disk) >>11 ; +return 0 ; +} +/* * direct translation from (pmem,sector) => void* * We do not require that sector be page aligned.
@@ -176,6 +185,7 @@ out:static const struct block_device_operations pmem_fops = { .owner =THIS_MODULE , + .getgeo = pmem_getgeo, };/* Kernel module stuff */
Signature · 1 line
1.9.3
PATCH 3/6 pmem: Add support for rw_page()
In reply to Ross ZwislerBased on commit a72132c31d58 ("brd: add support for rw_page()")
--- drivers/block/pmem.c | 11 +++++++++++ 1 file changed, 11 insertions(+)
drivers/block/pmem.c +11 -0
@@ -183,8 +183,19 @@ 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 ); +return 0 ; +} +static const struct block_device_operations pmem_fops = { .owner =THIS_MODULE , + .rw_page = pmem_rw_page, .getgeo = pmem_getgeo, };
Signature · 1 line
1.9.3
PATCH 4/6 pmem: Add support for direct_access()
In reply to Ross Zwisler--- drivers/block/pmem.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)
drivers/block/pmem.c +24 -0
@@ -74,6 +74,15 @@ static void *pmem_lookup_pg_addr(struct pmem_device *pmem, sector_t sector)return pmem->virt_addr + offset; } +/* sector must be page aligned */ +static unsigned long pmem_lookup_pfn (struct pmem_device *pmem,sector_t sector) +{ +size_t page_offset = sector >>PAGE_SECTORS_SHIFT ; + +BUG_ON (sector & (PAGE_SECTORS -1 )); +return (pmem->phys_addr >>PAGE_SHIFT ) + page_offset; +} +/* * sector is not required to be page aligned. * n is at most a single page, but could be less.
@@ -193,9 +202,24 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,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; + +if (!pmem) +return -ENODEV ; + + *kaddr =pmem_lookup_pg_addr (pmem, sector); + *pfn =pmem_lookup_pfn (pmem, sector); + +return pmem->size - (sector *512 ); +} +static const struct block_device_operations pmem_fops = { .owner =THIS_MODULE , .rw_page = pmem_rw_page, + .direct_access = pmem_direct_access, .getgeo = pmem_getgeo, };
Signature · 1 line
1.9.3
PATCH 5/6 pmem: Clean up includes
In reply to Ross Zwisler--- drivers/block/pmem.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
drivers/block/pmem.c +1 -3
@@ -16,17 +16,15 @@* Copyright (C) 2007 Novell Inc. */ +#include <asm/cacheflush.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/fs.h> #include <linux/hdreg.h> -#include <linux/highmem.h> #include <linux/init.h> -#include <linux/major.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/slab.h> -#include <linux/uaccess.h> #define SECTOR_SHIFT 9#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
Signature · 1 line
1.9.3
PATCH 6/6 pmem: Let each device manage private memory region
In reply to Ross ZwislerFrom: Boaz Harrosh <[email protected]>
This patch removes any global memory information. And lets each pmem-device manage it's own memory region.
pmem_alloc() Now receives phys_addr and disk_size and will map that region, also pmem_free will do the unmaping.
This is so we can support multiple discontinuous memory regions in the next patch
--- drivers/block/pmem.c | 122 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 75 insertions(+), 47 deletions(-)
drivers/block/pmem.c +75 -47
@@ -30,19 +30,12 @@#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) -/* -* driver-wide physical address and total_size - one single, contiguous memory -* region that we divide up in to same-sized devices -*/ -phys_addr_t phys_addr; -void *virt_addr; -size_t total_size; -struct pmem_device {struct request_queue *pmem_queue;struct gendisk *pmem_disk;struct list_head pmem_list; +/* One contiguous memory region per device */ phys_addr_t phys_addr;void *virt_addr;size_t size;
@@ -237,33 +230,80 @@ MODULE_PARM_DESC(pmem_count, "Number of pmem devices to evenly split allocated sstatic LIST_HEAD (pmem_devices);static int pmem_major; -/* FIXME: move phys_addr, virt_addr, size calls up to caller */ -static struct pmem_device *pmem_alloc (int i) +/* pmem->phys_addr and pmem->size need to be set. +* Will then set virt_addr if successful. +*/ +int pmem_mapmem (struct pmem_device *pmem) +{ +struct resource *res_mem; +int err; + + res_mem =request_mem_region_exclusive (pmem->phys_addr, pmem->size, +"pmem" ); +if (!res_mem) { +pr_warn ("pmem: request_mem_region_exclusive phys=0x%llx size=0x%zx failed\n" , + pmem->phys_addr, pmem->size); +return -EINVAL ; + } + + pmem->virt_addr =ioremap_cache (pmem->phys_addr, pmem->size); +if (unlikely (!pmem->virt_addr)) { + err = -ENXIO ; + goto out_release; + } +return 0 ; + +out_release: +release_mem_region (pmem->phys_addr, pmem->size); +return err; +} + +void pmem_unmapmem (struct pmem_device *pmem) +{ +if (unlikely (!pmem->virt_addr)) +return ; + +iounmap (pmem->virt_addr); +release_mem_region (pmem->phys_addr, pmem->size); + pmem->virt_addr =NULL ; +} + +static struct pmem_device *pmem_alloc (phys_addr_t phys_addr,size_t disk_size, +int i) {struct pmem_device *pmem;struct gendisk *disk; -size_t disk_size = total_size / pmem_count; -size_t disk_sectors = disk_size /512 ; +int err; pmem =kzalloc (sizeof (*pmem),GFP_KERNEL ); -if (!pmem) +if (unlikely (!pmem)) { + err = -ENOMEM ; goto out; + } - pmem->phys_addr = phys_addr + i * disk_size; - pmem->virt_addr = virt_addr + i * disk_size; + pmem->phys_addr = phys_addr; pmem->size = disk_size; - pmem->pmem_queue =blk_alloc_queue (GFP_KERNEL ); -if (!pmem->pmem_queue) + err =pmem_mapmem (pmem); +if (unlikely (err)) goto out_free_dev; + pmem->pmem_queue =blk_alloc_queue (GFP_KERNEL ); +if (unlikely (!pmem->pmem_queue)) { + err = -ENOMEM ; + 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 = pmem->pmem_disk =alloc_disk (0 ); -if (!disk) + disk =alloc_disk (0 ); +if (unlikely (!disk)) { + err = -ENOMEM ; goto out_free_queue; + } + disk->major = pmem_major; disk->first_minor =0 ; disk->fops = &pmem_fops;
@@ -271,22 +311,26 @@ static struct pmem_device *pmem_alloc(int i) disk->queue = pmem->pmem_queue; disk->flags =GENHD_FL_EXT_DEVT ;sprintf (disk->disk_name,"pmem%d" , i); -set_capacity (disk, disk_sectors); +set_capacity (disk, disk_size >>SECTOR_SHIFT ); + pmem->pmem_disk = disk;return pmem; out_free_queue:blk_cleanup_queue (pmem->pmem_queue); +out_unmap: +pmem_unmapmem (pmem); out_free_dev:kfree (pmem); out: -return NULL ; +return ERR_PTR (err); }static void pmem_free (struct pmem_device *pmem) {put_disk (pmem->pmem_disk);blk_cleanup_queue (pmem->pmem_queue); +pmem_unmapmem (pmem);kfree (pmem); }
@@ -300,36 +344,28 @@ static void pmem_del_one(struct pmem_device *pmem)static int __init pmem_init (void ) {int result, i; -struct resource *res_mem;struct pmem_device *pmem, *next; +phys_addr_t phys_addr; +size_t total_size, disk_size; phys_addr = (phys_addr_t ) pmem_start_gb *1024 *1024 *1024 ; total_size = (size_t ) pmem_size_gb *1024 *1024 *1024 ; - - res_mem =request_mem_region_exclusive (phys_addr, total_size,"pmem" ); -if (!res_mem) -return -ENOMEM ; - - virt_addr =ioremap_cache (phys_addr, total_size); -if (!virt_addr) { - result = -ENOMEM ; - goto out_release; - } + disk_size = total_size / pmem_count; result =register_blkdev (0 ,"pmem" ); -if (result <0 ) { - result = -EIO ; - goto out_unmap; - }else +if (result <0 ) +return -EIO ; +else pmem_major = result;for (i =0 ; i < pmem_count; i++) { - pmem =pmem_alloc (i); -if (!pmem) { - result = -ENOMEM ; + pmem =pmem_alloc (phys_addr, disk_size, i); +if (IS_ERR (pmem)) { + result =PTR_ERR (pmem); goto out_free; }list_add_tail (&pmem->pmem_list, &pmem_devices); + phys_addr += disk_size; }list_for_each_entry (pmem, &pmem_devices, pmem_list)
@@ -345,11 +381,6 @@ out_free: }unregister_blkdev (pmem_major,"pmem" ); -out_unmap: -iounmap (virt_addr); - -out_release: -release_mem_region (phys_addr, total_size);return result; }
@@ -361,9 +392,6 @@ static void __exit pmem_exit(void)pmem_del_one (pmem);unregister_blkdev (pmem_major,"pmem" ); -iounmap (virt_addr); -release_mem_region (phys_addr, total_size); -pr_info ("pmem: module unloaded\n" ); }
Signature · 1 line
1.9.3
Re: [PATCH 6/6] pmem: Let each device manage private memory region
Quoted 5 lines · Ross Zwisler
From: Boaz Harrosh <[email protected]>
This patch removes any global memory information. And lets each pmem-device manage it's own memory region.
Quoted 7 lines
pmem_alloc()Now receivesphys_addranddisk_sizeand will map that region, alsopmem_freewill do the unmaping.This is so we can support multiple discontinuous memory regions in the next patch
Signed-off-by Boaz Harrosh <[email protected]>
Yes I wrote this! No! please remove my Signed-off-by
This is completely the wrong API, and completely the wrong convoluted, crap code from the beginning.
Even after my half backed, done as a review enhancer for the better code, that needs to come later.
Sad
Boaz
Quoted 226 lines
Signed-off-by Ross Zwisler <[email protected]>--- drivers/block/pmem.c | 122 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 75 insertions(+), 47 deletions(-)drivers/block/pmem.c +75
-47@@ -30,19 +30,12 @@#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) -/* -* driver-wide physical address and total_size - one single, contiguous memory -* region that we divide up in to same-sized devices -*/ -phys_addr_t phys_addr; -void *virt_addr; -size_t total_size; -struct pmem_device {struct request_queue *pmem_queue;struct gendisk *pmem_disk;struct list_head pmem_list; +/* One contiguous memory region per device */ phys_addr_t phys_addr;void *virt_addr;size_t size;@@ -237,33 +230,80 @@ MODULE_PARM_DESC(pmem_count, "Number of pmem devices to evenly split allocated sstatic LIST_HEAD (pmem_devices);static int pmem_major; -/* FIXME: move phys_addr, virt_addr, size calls up to caller */ -static struct pmem_device *pmem_alloc (int i) +/* pmem->phys_addr and pmem->size need to be set. +* Will then set virt_addr if successful. +*/ +int pmem_mapmem (struct pmem_device *pmem) +{ +struct resource *res_mem; +int err; + + res_mem =request_mem_region_exclusive (pmem->phys_addr, pmem->size, +"pmem" ); +if (!res_mem) { +pr_warn ("pmem: request_mem_region_exclusive phys=0x%llx size=0x%zx failed\n" , + pmem->phys_addr, pmem->size); +return -EINVAL ; + } + + pmem->virt_addr =ioremap_cache (pmem->phys_addr, pmem->size); +if (unlikely (!pmem->virt_addr)) { + err = -ENXIO ; + goto out_release; + } +return 0 ; + +out_release: +release_mem_region (pmem->phys_addr, pmem->size); +return err; +} + +void pmem_unmapmem (struct pmem_device *pmem) +{ +if (unlikely (!pmem->virt_addr)) +return ; + +iounmap (pmem->virt_addr); +release_mem_region (pmem->phys_addr, pmem->size); + pmem->virt_addr =NULL ; +} + +static struct pmem_device *pmem_alloc (phys_addr_t phys_addr,size_t disk_size, +int i) {struct pmem_device *pmem;struct gendisk *disk; -size_t disk_size = total_size / pmem_count; -size_t disk_sectors = disk_size /512 ; +int err; pmem =kzalloc (sizeof (*pmem),GFP_KERNEL ); -if (!pmem) +if (unlikely (!pmem)) { + err = -ENOMEM ; goto out; + } - pmem->phys_addr = phys_addr + i * disk_size; - pmem->virt_addr = virt_addr + i * disk_size; + pmem->phys_addr = phys_addr; pmem->size = disk_size; - pmem->pmem_queue =blk_alloc_queue (GFP_KERNEL ); -if (!pmem->pmem_queue) + err =pmem_mapmem (pmem); +if (unlikely (err)) goto out_free_dev; + pmem->pmem_queue =blk_alloc_queue (GFP_KERNEL ); +if (unlikely (!pmem->pmem_queue)) { + err = -ENOMEM ; + 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 = pmem->pmem_disk =alloc_disk (0 ); -if (!disk) + disk =alloc_disk (0 ); +if (unlikely (!disk)) { + err = -ENOMEM ; goto out_free_queue; + } + disk->major = pmem_major; disk->first_minor =0 ; disk->fops = &pmem_fops;@@ -271,22 +311,26 @@ static struct pmem_device *pmem_alloc(int i) disk->queue = pmem->pmem_queue; disk->flags =GENHD_FL_EXT_DEVT ;sprintf (disk->disk_name,"pmem%d" , i); -set_capacity (disk, disk_sectors); +set_capacity (disk, disk_size >>SECTOR_SHIFT ); + pmem->pmem_disk = disk;return pmem; out_free_queue:blk_cleanup_queue (pmem->pmem_queue); +out_unmap: +pmem_unmapmem (pmem); out_free_dev:kfree (pmem); out: -return NULL ; +return ERR_PTR (err); }static void pmem_free (struct pmem_device *pmem) {put_disk (pmem->pmem_disk);blk_cleanup_queue (pmem->pmem_queue); +pmem_unmapmem (pmem);kfree (pmem); }@@ -300,36 +344,28 @@ static void pmem_del_one(struct pmem_device *pmem)static int __init pmem_init (void ) {int result, i; -struct resource *res_mem;struct pmem_device *pmem, *next; +phys_addr_t phys_addr; +size_t total_size, disk_size; phys_addr = (phys_addr_t ) pmem_start_gb *1024 *1024 *1024 ; total_size = (size_t ) pmem_size_gb *1024 *1024 *1024 ; - - res_mem =request_mem_region_exclusive (phys_addr, total_size,"pmem" ); -if (!res_mem) -return -ENOMEM ; - - virt_addr =ioremap_cache (phys_addr, total_size); -if (!virt_addr) { - result = -ENOMEM ; - goto out_release; - } + disk_size = total_size / pmem_count; result =register_blkdev (0 ,"pmem" ); -if (result <0 ) { - result = -EIO ; - goto out_unmap; - }else +if (result <0 ) +return -EIO ; +else pmem_major = result;for (i =0 ; i < pmem_count; i++) { - pmem =pmem_alloc (i); -if (!pmem) { - result = -ENOMEM ; + pmem =pmem_alloc (phys_addr, disk_size, i); +if (IS_ERR (pmem)) { + result =PTR_ERR (pmem); goto out_free; }list_add_tail (&pmem->pmem_list, &pmem_devices); + phys_addr += disk_size; }list_for_each_entry (pmem, &pmem_devices, pmem_list)@@ -345,11 +381,6 @@ out_free: }unregister_blkdev (pmem_major,"pmem" ); -out_unmap: -iounmap (virt_addr); - -out_release: -release_mem_region (phys_addr, total_size);return result; }@@ -361,9 +392,6 @@ static void __exit pmem_exit(void)pmem_del_one (pmem);unregister_blkdev (pmem_major,"pmem" ); -iounmap (virt_addr); -release_mem_region (phys_addr, total_size); -pr_info ("pmem: module unloaded\n" ); }
Boaz Harrosh
NAKQuoted 17 lines · Ross Zwisler
PMEM is a modified version of the Block RAM Driver, BRD. The major difference is that BRD allocates its backing store pages from the page cache, whereas PMEM uses reserved memory that has been ioremapped.
One benefit of this approach is that there is a direct mapping between filesystem block numbers and virtual addresses. In PMEM, filesystem blocks N, N+1, N+2, etc. will all be adjacent in the virtual memory space. This property allows us to set up PMD mappings (2 MiB) for DAX.
This patch set is builds upon the work that Matthew Wilcox has been doing for DAX, which has been merged into the v4.0 kernel series.
For more information on PMEM and for some instructions on how to use it, please check out PMEM's github tree:
Quoted 9 lines
Boaz Harrosh (1):
pmem: Let each device manage private memory region
Not signed-off-by me.
Quoted 2 lines
Ross Zwisler (5):
pmem: Initial version of persistent memory driver
This is the wrong code
Quoted 1 line
pmem: Add support for
getgeo()
We do not need this patch
Quoted 4 lines
pmem: Add support for
rw_page()
pmem: Add support fordirect_access()
pmem: Clean up includes
NACK!
This is the wrong pmem driver, the wrong API and the wrong bad copy/paste from brd code.
(And thanks Ross for not CCing me I have lots of mail to read every day,
Seriously this is rude, what do I need to feel?)
And very Seriously. Ross what is that joke Kconfig and module-param API, how it is relevant to anything and how it is getting us close to what pmem really needs to be, with the auto-probe. Is this your wait wait we done lots of new work on this? It did not change one bit from the original brd copy/paste.
Boaz
Quoted 7 lines
MAINTAINERS | 6 + drivers/block/Kconfig | 41 +++++ drivers/block/Makefile | 1 + drivers/block/pmem.c | 401 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 449 insertions(+) create mode 100644 drivers/block/pmem.c