linux_dsm_epyc7002/arch/x86/include/asm/io.h
Craig Bergstrom be62a32044 x86/mm: Limit mmap() of /dev/mem to valid physical addresses
One thing /dev/mem access APIs should verify is that there's no way
that excessively large pfn's can leak into the high bits of the
page table entry.

In particular, if people can use "very large physical page addresses"
through /dev/mem to set the bits past bit 58 - SOFTW4 and permission
key bits and NX bit, that could *really* confuse the kernel.

We had an earlier attempt:

  ce56a86e2a ("x86/mm: Limit mmap() of /dev/mem to valid physical addresses")

... which turned out to be too restrictive (breaking mem=... bootups for example) and
had to be reverted in:

  90edaac627 ("Revert "x86/mm: Limit mmap() of /dev/mem to valid physical addresses"")

This v2 attempt modifies the original patch and makes sure that mmap(/dev/mem)
limits the pfns so that it at least fits in the actual pteval_t architecturally:

 - Make sure mmap_mem() actually validates that the offset fits in phys_addr_t

    ( This may be indirectly true due to some other check, but it's not
      entirely obvious. )

 - Change valid_mmap_phys_addr_range() to just use phys_addr_valid()
   on the top byte

    ( Top byte is sufficient, because mmap_mem() has already checked that
      it cannot wrap. )

 - Add a few comments about what the valid_phys_addr_range() vs.
   valid_mmap_phys_addr_range() difference is.

Signed-off-by: Craig Bergstrom <craigb@google.com>
[ Fixed the checks and added comments. ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ Collected the discussion and patches into a commit. ]
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Mauro Carvalho Chehab <mchehab@s-opensource.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sander Eikelenboom <linux@eikelenboom.it>
Cc: Sean Young <sean@mess.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/CA+55aFyEcOMb657vWSmrM13OxmHxC-XxeBmNis=DwVvpJUOogQ@mail.gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-11-16 12:49:48 +01:00

429 lines
12 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#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 readb
#define readw readw
#define readl readl
#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 writeb
#define writew writew
#define writel writel
#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_read(__readq, "q", unsigned long, "=r", )
build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
build_mmio_write(__writeq, "q", unsigned long, "r", )
#define readq_relaxed(a) __readq(a)
#define writeq_relaxed(v, a) __writeq(v, a)
#define __raw_readq __readq
#define __raw_writeq __writeq
/* Let people know that we have them */
#define readq readq
#define writeq writeq
#endif
#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
/**
* 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);
}
#define virt_to_phys virt_to_phys
/**
* 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);
}
#define phys_to_virt phys_to_virt
/*
* 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
/*
* The default ioremap() behavior is non-cached; if you need something
* else, you probably want one of the following.
*/
extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
#define ioremap_nocache ioremap_nocache
extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
#define ioremap_uc ioremap_uc
extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
#define ioremap_cache ioremap_cache
extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val);
#define ioremap_prot ioremap_prot
/**
* 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().
*/
static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
{
return ioremap_nocache(offset, size);
}
#define ioremap ioremap
extern void iounmap(volatile void __iomem *addr);
#define iounmap iounmap
extern void set_iounmap_nonlazy(void);
#ifdef __KERNEL__
#include <asm-generic/iomap.h>
/*
* 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
#ifdef CONFIG_AMD_MEM_ENCRYPT
#include <linux/jump_label.h>
extern struct static_key_false sev_enable_key;
static inline bool sev_key_active(void)
{
return static_branch_unlikely(&sev_enable_key);
}
#else /* !CONFIG_AMD_MEM_ENCRYPT */
static inline bool sev_key_active(void) { return false; }
#endif /* CONFIG_AMD_MEM_ENCRYPT */
#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) \
{ \
if (sev_key_active()) { \
unsigned type *value = (unsigned type *)addr; \
while (count) { \
out##bwl(*value, port); \
value++; \
count--; \
} \
} else { \
asm volatile("rep; outs" #bwl \
: "+S"(addr), "+c"(count) \
: "d"(port) : "memory"); \
} \
} \
\
static inline void ins##bwl(int port, void *addr, unsigned long count) \
{ \
if (sev_key_active()) { \
unsigned type *value = (unsigned type *)addr; \
while (count) { \
*value = in##bwl(port); \
value++; \
count--; \
} \
} else { \
asm volatile("rep; ins" #bwl \
: "+D"(addr), "+c"(count) \
: "d"(port) : "memory"); \
} \
}
BUILDIO(b, b, char)
BUILDIO(w, w, short)
BUILDIO(l, , int)
#define inb inb
#define inw inw
#define inl inl
#define inb_p inb_p
#define inw_p inw_p
#define inl_p inl_p
#define insb insb
#define insw insw
#define insl insl
#define outb outb
#define outw outw
#define outl outl
#define outb_p outb_p
#define outw_p outw_p
#define outl_p outl_p
#define outsb outsb
#define outsw outsw
#define outsl outsl
extern void *xlate_dev_mem_ptr(phys_addr_t phys);
extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
#define xlate_dev_mem_ptr xlate_dev_mem_ptr
#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr
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);
#define ioremap_wc ioremap_wc
extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
#define ioremap_wt ioremap_wt
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
#include <asm-generic/io.h>
#undef PCI_IOBASE
#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
#ifdef CONFIG_X86_PAT
extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size);
extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size);
#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc
#endif
extern bool arch_memremap_can_ram_remap(resource_size_t offset,
unsigned long size,
unsigned long flags);
#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap
extern bool phys_mem_access_encrypted(unsigned long phys_addr,
unsigned long size);
#endif /* _ASM_X86_IO_H */