linux/drivers/acpi/nfit.h

193 lines
4.5 KiB
C
Raw Normal View History

/*
* NVDIMM Firmware Interface Table - NFIT
*
* Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that 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.
*/
#ifndef __NFIT_H__
#define __NFIT_H__
#include <linux/libnvdimm.h>
#include <linux/types.h>
#include <linux/uuid.h>
#include <linux/acpi.h>
#include <acpi/acuuid.h>
#define UUID_NFIT_BUS "2f10e7a4-9e91-11e4-89d3-123b93f75cba"
#define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66"
#define ACPI_NFIT_MEM_FAILED_MASK (ACPI_NFIT_MEM_SAVE_FAILED \
| ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \
| ACPI_NFIT_MEM_NOT_ARMED)
enum nfit_uuids {
NFIT_SPA_VOLATILE,
NFIT_SPA_PM,
NFIT_SPA_DCR,
NFIT_SPA_BDW,
NFIT_SPA_VDISK,
NFIT_SPA_VCD,
NFIT_SPA_PDISK,
NFIT_SPA_PCD,
NFIT_DEV_BUS,
NFIT_DEV_DIMM,
NFIT_UUID_MAX,
};
enum nfit_fic {
NFIT_FIC_BYTE = 0x101, /* byte-addressable energy backed */
NFIT_FIC_BLK = 0x201, /* block-addressable non-energy backed */
NFIT_FIC_BYTEN = 0x301, /* byte-addressable non-energy backed */
};
enum {
nd_blk: change aperture mapping from WC to WB This should result in a pretty sizeable performance gain for reads. For rough comparison I did some simple read testing using PMEM to compare reads of write combining (WC) mappings vs write-back (WB). This was done on a random lab machine. PMEM reads from a write combining mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=100000 100000+0 records in 100000+0 records out 409600000 bytes (410 MB) copied, 9.2855 s, 44.1 MB/s PMEM reads from a write-back mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=1000000 1000000+0 records in 1000000+0 records out 4096000000 bytes (4.1 GB) copied, 3.44034 s, 1.2 GB/s To be able to safely support a write-back aperture I needed to add support for the "read flush" _DSM flag, as outlined in the DSM spec: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf This flag tells the ND BLK driver that it needs to flush the cache lines associated with the aperture after the aperture is moved but before any new data is read. This ensures that any stale cache lines from the previous contents of the aperture will be discarded from the processor cache, and the new data will be read properly from the DIMM. We know that the cache lines are clean and will be discarded without any writeback because either a) the previous aperture operation was a read, and we never modified the contents of the aperture, or b) the previous aperture operation was a write and we must have written back the dirtied contents of the aperture to the DIMM before the I/O was completed. In order to add support for the "read flush" flag I needed to add a generic routine to invalidate cache lines, mmio_flush_range(). This is protected by the ARCH_HAS_MMIO_FLUSH Kconfig variable, and is currently only supported on x86. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-08-27 19:14:20 +00:00
ND_BLK_READ_FLUSH = 1,
ND_BLK_DCR_LATCH = 2,
};
struct nfit_spa {
struct acpi_nfit_system_address *spa;
struct list_head list;
int is_registered;
};
struct nfit_dcr {
struct acpi_nfit_control_region *dcr;
struct list_head list;
};
struct nfit_bdw {
struct acpi_nfit_data_region *bdw;
struct list_head list;
};
struct nfit_idt {
struct acpi_nfit_interleave *idt;
struct list_head list;
};
struct nfit_flush {
struct acpi_nfit_flush_address *flush;
struct list_head list;
};
struct nfit_memdev {
struct acpi_nfit_memory_map *memdev;
struct list_head list;
};
/* assembled tables for a given dimm/memory-device */
struct nfit_mem {
struct nvdimm *nvdimm;
struct acpi_nfit_memory_map *memdev_dcr;
struct acpi_nfit_memory_map *memdev_pmem;
struct acpi_nfit_memory_map *memdev_bdw;
struct acpi_nfit_control_region *dcr;
struct acpi_nfit_data_region *bdw;
struct acpi_nfit_system_address *spa_dcr;
struct acpi_nfit_system_address *spa_bdw;
struct acpi_nfit_interleave *idt_dcr;
struct acpi_nfit_interleave *idt_bdw;
struct nfit_flush *nfit_flush;
struct list_head list;
2015-06-08 18:27:06 +00:00
struct acpi_device *adev;
unsigned long dsm_mask;
};
struct acpi_nfit_desc {
struct nvdimm_bus_descriptor nd_desc;
struct acpi_table_header acpi_header;
struct acpi_nfit_header *nfit;
struct mutex spa_map_mutex;
struct mutex init_mutex;
struct list_head spa_maps;
struct list_head memdevs;
struct list_head flushes;
struct list_head dimms;
struct list_head spas;
struct list_head dcrs;
struct list_head bdws;
struct list_head idts;
struct nvdimm_bus *nvdimm_bus;
struct device *dev;
2015-06-08 18:27:06 +00:00
unsigned long dimm_dsm_force_en;
unsigned long bus_dsm_force_en;
tools/testing/nvdimm: libnvdimm unit test infrastructure 'libnvdimm' is the first driver sub-system in the kernel to implement mocking for unit test coverage. The nfit_test module gets built as an external module and arranges for external module replacements of nfit, libnvdimm, nd_pmem, and nd_blk. These replacements use the linker --wrap option to redirect calls to ioremap() + request_mem_region() to custom defined unit test resources. The end result is a fully functional nvdimm_bus, as far as userspace is concerned, but with the capability to perform otherwise destructive tests on emulated resources. Q: Why not use QEMU for this emulation? QEMU is not suitable for unit testing. QEMU's role is to faithfully emulate the platform. A unit test's role is to unfaithfully implement the platform with the goal of triggering bugs in the corners of the sub-system implementation. As bugs are discovered in platforms, or the sub-system itself, the unit tests are extended to backstop a fix with a reproducer unit test. Another problem with QEMU is that it would require coordination of 3 software projects instead of 2 (kernel + libndctl [1]) to maintain and execute the tests. The chances for bit rot and the difficulty of getting the tests running goes up non-linearly the more components involved. Q: Why submit this to the kernel tree instead of external modules in libndctl? Simple, to alleviate the same risk that out-of-tree external modules face. Updates to drivers/nvdimm/ can be immediately evaluated to see if they have any impact on tools/testing/nvdimm/. Q: What are the negative implications of merging this? It is a unique maintenance burden because the purpose of mocking an interface to enable a unit test is to purposefully short circuit the semantics of a routine to enable testing. For example __wrap_ioremap_cache() fakes the pmem driver into "ioremap()'ing" a test resource buffer allocated by dma_alloc_coherent(). The future maintenance burden hits when someone changes the semantics of ioremap_cache() and wonders what the implications are for the unit test. [1]: https://github.com/pmem/ndctl Cc: <linux-acpi@vger.kernel.org> Cc: Lv Zheng <lv.zheng@intel.com> Cc: Robert Moore <robert.moore@intel.com> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-06-17 21:23:32 +00:00
int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
void *iobuf, u64 len, int rw);
};
enum nd_blk_mmio_selector {
BDW,
DCR,
};
nd_blk: change aperture mapping from WC to WB This should result in a pretty sizeable performance gain for reads. For rough comparison I did some simple read testing using PMEM to compare reads of write combining (WC) mappings vs write-back (WB). This was done on a random lab machine. PMEM reads from a write combining mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=100000 100000+0 records in 100000+0 records out 409600000 bytes (410 MB) copied, 9.2855 s, 44.1 MB/s PMEM reads from a write-back mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=1000000 1000000+0 records in 1000000+0 records out 4096000000 bytes (4.1 GB) copied, 3.44034 s, 1.2 GB/s To be able to safely support a write-back aperture I needed to add support for the "read flush" _DSM flag, as outlined in the DSM spec: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf This flag tells the ND BLK driver that it needs to flush the cache lines associated with the aperture after the aperture is moved but before any new data is read. This ensures that any stale cache lines from the previous contents of the aperture will be discarded from the processor cache, and the new data will be read properly from the DIMM. We know that the cache lines are clean and will be discarded without any writeback because either a) the previous aperture operation was a read, and we never modified the contents of the aperture, or b) the previous aperture operation was a write and we must have written back the dirtied contents of the aperture to the DIMM before the I/O was completed. In order to add support for the "read flush" flag I needed to add a generic routine to invalidate cache lines, mmio_flush_range(). This is protected by the ARCH_HAS_MMIO_FLUSH Kconfig variable, and is currently only supported on x86. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-08-27 19:14:20 +00:00
struct nd_blk_addr {
union {
void __iomem *base;
void __pmem *aperture;
};
};
struct nfit_blk {
struct nfit_blk_mmio {
nd_blk: change aperture mapping from WC to WB This should result in a pretty sizeable performance gain for reads. For rough comparison I did some simple read testing using PMEM to compare reads of write combining (WC) mappings vs write-back (WB). This was done on a random lab machine. PMEM reads from a write combining mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=100000 100000+0 records in 100000+0 records out 409600000 bytes (410 MB) copied, 9.2855 s, 44.1 MB/s PMEM reads from a write-back mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=1000000 1000000+0 records in 1000000+0 records out 4096000000 bytes (4.1 GB) copied, 3.44034 s, 1.2 GB/s To be able to safely support a write-back aperture I needed to add support for the "read flush" _DSM flag, as outlined in the DSM spec: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf This flag tells the ND BLK driver that it needs to flush the cache lines associated with the aperture after the aperture is moved but before any new data is read. This ensures that any stale cache lines from the previous contents of the aperture will be discarded from the processor cache, and the new data will be read properly from the DIMM. We know that the cache lines are clean and will be discarded without any writeback because either a) the previous aperture operation was a read, and we never modified the contents of the aperture, or b) the previous aperture operation was a write and we must have written back the dirtied contents of the aperture to the DIMM before the I/O was completed. In order to add support for the "read flush" flag I needed to add a generic routine to invalidate cache lines, mmio_flush_range(). This is protected by the ARCH_HAS_MMIO_FLUSH Kconfig variable, and is currently only supported on x86. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-08-27 19:14:20 +00:00
struct nd_blk_addr addr;
u64 size;
u64 base_offset;
u32 line_size;
u32 num_lines;
u32 table_size;
struct acpi_nfit_interleave *idt;
struct acpi_nfit_system_address *spa;
} mmio[2];
struct nd_region *nd_region;
u64 bdw_offset; /* post interleave offset */
u64 stat_offset;
u64 cmd_offset;
void __iomem *nvdimm_flush;
u32 dimm_flags;
};
enum spa_map_type {
SPA_MAP_CONTROL,
SPA_MAP_APERTURE,
};
struct nfit_spa_mapping {
struct acpi_nfit_desc *acpi_desc;
struct acpi_nfit_system_address *spa;
struct list_head list;
struct kref kref;
nd_blk: change aperture mapping from WC to WB This should result in a pretty sizeable performance gain for reads. For rough comparison I did some simple read testing using PMEM to compare reads of write combining (WC) mappings vs write-back (WB). This was done on a random lab machine. PMEM reads from a write combining mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=100000 100000+0 records in 100000+0 records out 409600000 bytes (410 MB) copied, 9.2855 s, 44.1 MB/s PMEM reads from a write-back mapping: # dd of=/dev/null if=/dev/pmem0 bs=4096 count=1000000 1000000+0 records in 1000000+0 records out 4096000000 bytes (4.1 GB) copied, 3.44034 s, 1.2 GB/s To be able to safely support a write-back aperture I needed to add support for the "read flush" _DSM flag, as outlined in the DSM spec: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf This flag tells the ND BLK driver that it needs to flush the cache lines associated with the aperture after the aperture is moved but before any new data is read. This ensures that any stale cache lines from the previous contents of the aperture will be discarded from the processor cache, and the new data will be read properly from the DIMM. We know that the cache lines are clean and will be discarded without any writeback because either a) the previous aperture operation was a read, and we never modified the contents of the aperture, or b) the previous aperture operation was a write and we must have written back the dirtied contents of the aperture to the DIMM before the I/O was completed. In order to add support for the "read flush" flag I needed to add a generic routine to invalidate cache lines, mmio_flush_range(). This is protected by the ARCH_HAS_MMIO_FLUSH Kconfig variable, and is currently only supported on x86. Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-08-27 19:14:20 +00:00
enum spa_map_type type;
struct nd_blk_addr addr;
};
static inline struct nfit_spa_mapping *to_spa_map(struct kref *kref)
{
return container_of(kref, struct nfit_spa_mapping, kref);
}
static inline struct acpi_nfit_memory_map *__to_nfit_memdev(
struct nfit_mem *nfit_mem)
{
if (nfit_mem->memdev_dcr)
return nfit_mem->memdev_dcr;
return nfit_mem->memdev_pmem;
}
static inline struct acpi_nfit_desc *to_acpi_desc(
struct nvdimm_bus_descriptor *nd_desc)
{
return container_of(nd_desc, struct acpi_nfit_desc, nd_desc);
}
tools/testing/nvdimm: libnvdimm unit test infrastructure 'libnvdimm' is the first driver sub-system in the kernel to implement mocking for unit test coverage. The nfit_test module gets built as an external module and arranges for external module replacements of nfit, libnvdimm, nd_pmem, and nd_blk. These replacements use the linker --wrap option to redirect calls to ioremap() + request_mem_region() to custom defined unit test resources. The end result is a fully functional nvdimm_bus, as far as userspace is concerned, but with the capability to perform otherwise destructive tests on emulated resources. Q: Why not use QEMU for this emulation? QEMU is not suitable for unit testing. QEMU's role is to faithfully emulate the platform. A unit test's role is to unfaithfully implement the platform with the goal of triggering bugs in the corners of the sub-system implementation. As bugs are discovered in platforms, or the sub-system itself, the unit tests are extended to backstop a fix with a reproducer unit test. Another problem with QEMU is that it would require coordination of 3 software projects instead of 2 (kernel + libndctl [1]) to maintain and execute the tests. The chances for bit rot and the difficulty of getting the tests running goes up non-linearly the more components involved. Q: Why submit this to the kernel tree instead of external modules in libndctl? Simple, to alleviate the same risk that out-of-tree external modules face. Updates to drivers/nvdimm/ can be immediately evaluated to see if they have any impact on tools/testing/nvdimm/. Q: What are the negative implications of merging this? It is a unique maintenance burden because the purpose of mocking an interface to enable a unit test is to purposefully short circuit the semantics of a routine to enable testing. For example __wrap_ioremap_cache() fakes the pmem driver into "ioremap()'ing" a test resource buffer allocated by dma_alloc_coherent(). The future maintenance burden hits when someone changes the semantics of ioremap_cache() and wonders what the implications are for the unit test. [1]: https://github.com/pmem/ndctl Cc: <linux-acpi@vger.kernel.org> Cc: Lv Zheng <lv.zheng@intel.com> Cc: Robert Moore <robert.moore@intel.com> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-06-17 21:23:32 +00:00
const u8 *to_nfit_uuid(enum nfit_uuids id);
int acpi_nfit_init(struct acpi_nfit_desc *nfit, acpi_size sz);
extern const struct attribute_group *acpi_nfit_attribute_groups[];
#endif /* __NFIT_H__ */