mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 04:59:04 +07:00
67a3e8fe90
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>
353 lines
10 KiB
C
353 lines
10 KiB
C
#ifndef _ASM_X86_IO_H
|
|
#define _ASM_X86_IO_H
|
|
|
|
/*
|
|
* This file contains the definitions for the x86 IO instructions
|
|
* inb/inw/inl/outb/outw/outl and the "string versions" of the same
|
|
* (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
|
|
* versions of the single-IO instructions (inb_p/inw_p/..).
|
|
*
|
|
* This file is not meant to be obfuscating: it's just complicated
|
|
* to (a) handle it all in a way that makes gcc able to optimize it
|
|
* as well as possible and (b) trying to avoid writing the same thing
|
|
* over and over again with slight variations and possibly making a
|
|
* mistake somewhere.
|
|
*/
|
|
|
|
/*
|
|
* Thanks to James van Artsdalen for a better timing-fix than
|
|
* the two short jumps: using outb's to a nonexistent port seems
|
|
* to guarantee better timings even on fast machines.
|
|
*
|
|
* On the other hand, I'd like to be sure of a non-existent port:
|
|
* I feel a bit unsafe about using 0x80 (should be safe, though)
|
|
*
|
|
* Linus
|
|
*/
|
|
|
|
/*
|
|
* Bit simplified and optimized by Jan Hubicka
|
|
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
|
|
*
|
|
* isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
|
|
* isa_read[wl] and isa_write[wl] fixed
|
|
* - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
|
|
*/
|
|
|
|
#define ARCH_HAS_IOREMAP_WC
|
|
#define ARCH_HAS_IOREMAP_WT
|
|
|
|
#include <linux/string.h>
|
|
#include <linux/compiler.h>
|
|
#include <asm/page.h>
|
|
#include <asm/early_ioremap.h>
|
|
#include <asm/pgtable_types.h>
|
|
|
|
#define build_mmio_read(name, size, type, reg, barrier) \
|
|
static inline type name(const volatile void __iomem *addr) \
|
|
{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \
|
|
:"m" (*(volatile type __force *)addr) barrier); return ret; }
|
|
|
|
#define build_mmio_write(name, size, type, reg, barrier) \
|
|
static inline void name(type val, volatile void __iomem *addr) \
|
|
{ asm volatile("mov" size " %0,%1": :reg (val), \
|
|
"m" (*(volatile type __force *)addr) barrier); }
|
|
|
|
build_mmio_read(readb, "b", unsigned char, "=q", :"memory")
|
|
build_mmio_read(readw, "w", unsigned short, "=r", :"memory")
|
|
build_mmio_read(readl, "l", unsigned int, "=r", :"memory")
|
|
|
|
build_mmio_read(__readb, "b", unsigned char, "=q", )
|
|
build_mmio_read(__readw, "w", unsigned short, "=r", )
|
|
build_mmio_read(__readl, "l", unsigned int, "=r", )
|
|
|
|
build_mmio_write(writeb, "b", unsigned char, "q", :"memory")
|
|
build_mmio_write(writew, "w", unsigned short, "r", :"memory")
|
|
build_mmio_write(writel, "l", unsigned int, "r", :"memory")
|
|
|
|
build_mmio_write(__writeb, "b", unsigned char, "q", )
|
|
build_mmio_write(__writew, "w", unsigned short, "r", )
|
|
build_mmio_write(__writel, "l", unsigned int, "r", )
|
|
|
|
#define readb_relaxed(a) __readb(a)
|
|
#define readw_relaxed(a) __readw(a)
|
|
#define readl_relaxed(a) __readl(a)
|
|
#define __raw_readb __readb
|
|
#define __raw_readw __readw
|
|
#define __raw_readl __readl
|
|
|
|
#define writeb_relaxed(v, a) __writeb(v, a)
|
|
#define writew_relaxed(v, a) __writew(v, a)
|
|
#define writel_relaxed(v, a) __writel(v, a)
|
|
#define __raw_writeb __writeb
|
|
#define __raw_writew __writew
|
|
#define __raw_writel __writel
|
|
|
|
#define mmiowb() barrier()
|
|
|
|
#ifdef CONFIG_X86_64
|
|
|
|
build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
|
|
build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
|
|
|
|
#define readq_relaxed(a) readq(a)
|
|
#define writeq_relaxed(v, a) writeq(v, a)
|
|
|
|
#define __raw_readq(a) readq(a)
|
|
#define __raw_writeq(val, addr) writeq(val, addr)
|
|
|
|
/* Let people know that we have them */
|
|
#define readq readq
|
|
#define writeq writeq
|
|
|
|
#endif
|
|
|
|
/**
|
|
* virt_to_phys - map virtual addresses to physical
|
|
* @address: address to remap
|
|
*
|
|
* The returned physical address is the physical (CPU) mapping for
|
|
* the memory address given. It is only valid to use this function on
|
|
* addresses directly mapped or allocated via kmalloc.
|
|
*
|
|
* This function does not give bus mappings for DMA transfers. In
|
|
* almost all conceivable cases a device driver should not be using
|
|
* this function
|
|
*/
|
|
|
|
static inline phys_addr_t virt_to_phys(volatile void *address)
|
|
{
|
|
return __pa(address);
|
|
}
|
|
|
|
/**
|
|
* phys_to_virt - map physical address to virtual
|
|
* @address: address to remap
|
|
*
|
|
* The returned virtual address is a current CPU mapping for
|
|
* the memory address given. It is only valid to use this function on
|
|
* addresses that have a kernel mapping
|
|
*
|
|
* This function does not handle bus mappings for DMA transfers. In
|
|
* almost all conceivable cases a device driver should not be using
|
|
* this function
|
|
*/
|
|
|
|
static inline void *phys_to_virt(phys_addr_t address)
|
|
{
|
|
return __va(address);
|
|
}
|
|
|
|
/*
|
|
* Change "struct page" to physical address.
|
|
*/
|
|
#define page_to_phys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
|
|
|
|
/*
|
|
* ISA I/O bus memory addresses are 1:1 with the physical address.
|
|
* However, we truncate the address to unsigned int to avoid undesirable
|
|
* promitions in legacy drivers.
|
|
*/
|
|
static inline unsigned int isa_virt_to_bus(volatile void *address)
|
|
{
|
|
return (unsigned int)virt_to_phys(address);
|
|
}
|
|
#define isa_page_to_bus(page) ((unsigned int)page_to_phys(page))
|
|
#define isa_bus_to_virt phys_to_virt
|
|
|
|
/*
|
|
* However PCI ones are not necessarily 1:1 and therefore these interfaces
|
|
* are forbidden in portable PCI drivers.
|
|
*
|
|
* Allow them on x86 for legacy drivers, though.
|
|
*/
|
|
#define virt_to_bus virt_to_phys
|
|
#define bus_to_virt phys_to_virt
|
|
|
|
/**
|
|
* ioremap - map bus memory into CPU space
|
|
* @offset: bus address of the memory
|
|
* @size: size of the resource to map
|
|
*
|
|
* ioremap performs a platform specific sequence of operations to
|
|
* make bus memory CPU accessible via the readb/readw/readl/writeb/
|
|
* writew/writel functions and the other mmio helpers. The returned
|
|
* address is not guaranteed to be usable directly as a virtual
|
|
* address.
|
|
*
|
|
* If the area you are trying to map is a PCI BAR you should have a
|
|
* look at pci_iomap().
|
|
*/
|
|
extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
|
|
extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
|
|
extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
|
|
extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
|
|
unsigned long prot_val);
|
|
|
|
/*
|
|
* The default ioremap() behavior is non-cached:
|
|
*/
|
|
static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
|
|
{
|
|
return ioremap_nocache(offset, size);
|
|
}
|
|
|
|
extern void iounmap(volatile void __iomem *addr);
|
|
|
|
extern void set_iounmap_nonlazy(void);
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <asm-generic/iomap.h>
|
|
|
|
/*
|
|
* Convert a virtual cached pointer to an uncached pointer
|
|
*/
|
|
#define xlate_dev_kmem_ptr(p) p
|
|
|
|
static inline void
|
|
memset_io(volatile void __iomem *addr, unsigned char val, size_t count)
|
|
{
|
|
memset((void __force *)addr, val, count);
|
|
}
|
|
|
|
static inline void
|
|
memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count)
|
|
{
|
|
memcpy(dst, (const void __force *)src, count);
|
|
}
|
|
|
|
static inline void
|
|
memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
|
|
{
|
|
memcpy((void __force *)dst, src, count);
|
|
}
|
|
|
|
/*
|
|
* ISA space is 'always mapped' on a typical x86 system, no need to
|
|
* explicitly ioremap() it. The fact that the ISA IO space is mapped
|
|
* to PAGE_OFFSET is pure coincidence - it does not mean ISA values
|
|
* are physical addresses. The following constant pointer can be
|
|
* used as the IO-area pointer (it can be iounmapped as well, so the
|
|
* analogy with PCI is quite large):
|
|
*/
|
|
#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
|
|
|
|
/*
|
|
* Cache management
|
|
*
|
|
* This needed for two cases
|
|
* 1. Out of order aware processors
|
|
* 2. Accidentally out of order processors (PPro errata #51)
|
|
*/
|
|
|
|
static inline void flush_write_buffers(void)
|
|
{
|
|
#if defined(CONFIG_X86_PPRO_FENCE)
|
|
asm volatile("lock; addl $0,0(%%esp)": : :"memory");
|
|
#endif
|
|
}
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
extern void native_io_delay(void);
|
|
|
|
extern int io_delay_type;
|
|
extern void io_delay_init(void);
|
|
|
|
#if defined(CONFIG_PARAVIRT)
|
|
#include <asm/paravirt.h>
|
|
#else
|
|
|
|
static inline void slow_down_io(void)
|
|
{
|
|
native_io_delay();
|
|
#ifdef REALLY_SLOW_IO
|
|
native_io_delay();
|
|
native_io_delay();
|
|
native_io_delay();
|
|
#endif
|
|
}
|
|
|
|
#endif
|
|
|
|
#define BUILDIO(bwl, bw, type) \
|
|
static inline void out##bwl(unsigned type value, int port) \
|
|
{ \
|
|
asm volatile("out" #bwl " %" #bw "0, %w1" \
|
|
: : "a"(value), "Nd"(port)); \
|
|
} \
|
|
\
|
|
static inline unsigned type in##bwl(int port) \
|
|
{ \
|
|
unsigned type value; \
|
|
asm volatile("in" #bwl " %w1, %" #bw "0" \
|
|
: "=a"(value) : "Nd"(port)); \
|
|
return value; \
|
|
} \
|
|
\
|
|
static inline void out##bwl##_p(unsigned type value, int port) \
|
|
{ \
|
|
out##bwl(value, port); \
|
|
slow_down_io(); \
|
|
} \
|
|
\
|
|
static inline unsigned type in##bwl##_p(int port) \
|
|
{ \
|
|
unsigned type value = in##bwl(port); \
|
|
slow_down_io(); \
|
|
return value; \
|
|
} \
|
|
\
|
|
static inline void outs##bwl(int port, const void *addr, unsigned long count) \
|
|
{ \
|
|
asm volatile("rep; outs" #bwl \
|
|
: "+S"(addr), "+c"(count) : "d"(port)); \
|
|
} \
|
|
\
|
|
static inline void ins##bwl(int port, void *addr, unsigned long count) \
|
|
{ \
|
|
asm volatile("rep; ins" #bwl \
|
|
: "+D"(addr), "+c"(count) : "d"(port)); \
|
|
}
|
|
|
|
BUILDIO(b, b, char)
|
|
BUILDIO(w, w, short)
|
|
BUILDIO(l, , int)
|
|
|
|
extern void *xlate_dev_mem_ptr(phys_addr_t phys);
|
|
extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
|
|
|
|
extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
|
|
enum page_cache_mode pcm);
|
|
extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
|
|
extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
|
|
|
|
extern bool is_early_ioremap_ptep(pte_t *ptep);
|
|
|
|
#ifdef CONFIG_XEN
|
|
#include <xen/xen.h>
|
|
struct bio_vec;
|
|
|
|
extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
|
|
const struct bio_vec *vec2);
|
|
|
|
#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
|
|
(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \
|
|
(!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
|
|
#endif /* CONFIG_XEN */
|
|
|
|
#define IO_SPACE_LIMIT 0xffff
|
|
|
|
#ifdef CONFIG_MTRR
|
|
extern int __must_check arch_phys_wc_index(int handle);
|
|
#define arch_phys_wc_index arch_phys_wc_index
|
|
|
|
extern int __must_check arch_phys_wc_add(unsigned long base,
|
|
unsigned long size);
|
|
extern void arch_phys_wc_del(int handle);
|
|
#define arch_phys_wc_add arch_phys_wc_add
|
|
#endif
|
|
|
|
#endif /* _ASM_X86_IO_H */
|