linux/arch/arm64/include/asm/io.h

206 lines
6.7 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/io.h
*
* Copyright (C) 1996-2000 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_IO_H
#define __ASM_IO_H
#include <linux/types.h>
mm: reorder includes after introduction of linux/pgtable.h The replacement of <asm/pgrable.h> with <linux/pgtable.h> made the include of the latter in the middle of asm includes. Fix this up with the aid of the below script and manual adjustments here and there. import sys import re if len(sys.argv) is not 3: print "USAGE: %s <file> <header>" % (sys.argv[0]) sys.exit(1) hdr_to_move="#include <linux/%s>" % sys.argv[2] moved = False in_hdrs = False with open(sys.argv[1], "r") as f: lines = f.readlines() for _line in lines: line = _line.rstrip(' ') if line == hdr_to_move: continue if line.startswith("#include <linux/"): in_hdrs = True elif not moved and in_hdrs: moved = True print hdr_to_move print line Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-4-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 12:32:42 +08:00
#include <linux/pgtable.h>
#include <asm/byteorder.h>
#include <asm/barrier.h>
arm64: Fix overlapping VA allocations PCI IO space was intended to be 16MiB, at 32MiB below MODULES_VADDR, but commit d1e6dc91b532d3d3 ("arm64: Add architectural support for PCI") extended this to cover the full 32MiB. The final 8KiB of this 32MiB is also allocated for the fixmap, allowing for potential clashes between the two. This change was masked by assumptions in mem_init and the page table dumping code, which assumed the I/O space to be 16MiB long through seaparte hard-coded definitions. This patch changes the definition of the PCI I/O space allocation to live in asm/memory.h, along with the other VA space allocations. As the fixmap allocation depends on the number of fixmap entries, this is moved below the PCI I/O space allocation. Both the fixmap and PCI I/O space are guarded with 2MB of padding. Sites assuming the I/O space was 16MiB are moved over use new PCI_IO_{START,END} definitions, which will keep in sync with the size of the IO space (now restored to 16MiB). As a useful side effect, the use of the new PCI_IO_{START,END} definitions prevents a build issue in the dumping code due to a (now redundant) missing include of io.h for PCI_IOBASE. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Will Deacon <will.deacon@arm.com> [catalin.marinas@arm.com: reorder FIXADDR and PCI_IO address_markers_idx enum] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-23 02:20:35 +08:00
#include <asm/memory.h>
#include <asm/early_ioremap.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
/*
* Generic IO read/write. These perform native-endian accesses.
*/
#define __raw_writeb __raw_writeb
static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
{
asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writew __raw_writew
static inline void __raw_writew(u16 val, volatile void __iomem *addr)
{
asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writel __raw_writel
static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr)
{
asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writeq __raw_writeq
static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
{
asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_readb __raw_readb
static inline u8 __raw_readb(const volatile void __iomem *addr)
{
u8 val;
asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
"ldarb %w0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
#define __raw_readw __raw_readw
static inline u16 __raw_readw(const volatile void __iomem *addr)
{
u16 val;
asm volatile(ALTERNATIVE("ldrh %w0, [%1]",
"ldarh %w0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
#define __raw_readl __raw_readl
static __always_inline u32 __raw_readl(const volatile void __iomem *addr)
{
u32 val;
asm volatile(ALTERNATIVE("ldr %w0, [%1]",
"ldar %w0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
#define __raw_readq __raw_readq
static inline u64 __raw_readq(const volatile void __iomem *addr)
{
u64 val;
asm volatile(ALTERNATIVE("ldr %0, [%1]",
"ldar %0, [%1]",
ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
: "=r" (val) : "r" (addr));
return val;
}
/* IO barriers */
#define __iormb(v) \
({ \
unsigned long tmp; \
\
arm64: io: Relax implicit barriers in default I/O accessors The arm64 implementation of the default I/O accessors requires barrier instructions to satisfy the memory ordering requirements documented in memory-barriers.txt [1], which are largely derived from the behaviour of I/O accesses on x86. Of particular interest are the requirements that a write to a device must be ordered against prior writes to memory, and a read from a device must be ordered against subsequent reads from memory. We satisfy these requirements using various flavours of DSB: the most expensive barrier we have, since it implies completion of prior accesses. This was deemed necessary when we first implemented the accessors, since accesses to different endpoints could propagate independently and therefore the only way to enforce order is to rely on completion guarantees [2]. Since then, the Armv8 memory model has been retrospectively strengthened to require "other-multi-copy atomicity", a property that requires memory accesses from an observer to become visible to all other observers simultaneously [3]. In other words, propagation of accesses is limited to transitioning from locally observed to globally observed. It recently became apparent that this change also has a subtle impact on our I/O accessors for shared peripherals, allowing us to use the cheaper DMB instruction instead. As a concrete example, consider the following: memcpy(dma_buffer, data, bufsz); writel(DMA_START, dev->ctrl_reg); A DMB ST instruction between the final write to the DMA buffer and the write to the control register will ensure that the writes to the DMA buffer are observed before the write to the control register by all observers. Put another way, if an observer can see the write to the control register, it can also see the writes to memory. This has always been the case and is not sufficient to provide the ordering required by Linux, since there is no guarantee that the master interface of the DMA-capable device has observed either of the accesses. However, in an other-multi-copy atomic world, we can infer two things: 1. A write arriving at an endpoint shared between multiple CPUs is visible to all CPUs 2. A write that is visible to all CPUs is also visible to all other observers in the shareability domain Pieced together, this allows us to use DMB OSHST for our default I/O write accessors and DMB OSHLD for our default I/O read accessors (the outer-shareability is for handling non-cacheable mappings) for shared devices. Memory-mapped, DMA-capable peripherals that are private to a CPU (i.e. inaccessible to other CPUs) still require the DSB, however these are few and far between and typically require special treatment anyway which is outside of the scope of the portable driver API (e.g. GIC, page-table walker, SPE profiler). Note that our mandatory barriers remain as DSBs, since there are cases where they are used to flush the store buffer of the CPU, e.g. when publishing page table updates to the SMMU. [1] https://git.kernel.org/linus/4614bbdee357 [2] https://www.youtube.com/watch?v=i6DayghhA8Q [3] https://www.cl.cam.ac.uk/~pes20/armv8-mca/ Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2019-06-07 22:48:58 +08:00
dma_rmb(); \
\
/* \
* Create a dummy control dependency from the IO read to any \
* later instructions. This ensures that a subsequent call to \
* udelay() will be ordered due to the ISB in get_cycles(). \
*/ \
asm volatile("eor %0, %1, %1\n" \
"cbnz %0, ." \
: "=r" (tmp) : "r" ((unsigned long)(v)) \
: "memory"); \
})
#define __io_par(v) __iormb(v)
arm64: io: Relax implicit barriers in default I/O accessors The arm64 implementation of the default I/O accessors requires barrier instructions to satisfy the memory ordering requirements documented in memory-barriers.txt [1], which are largely derived from the behaviour of I/O accesses on x86. Of particular interest are the requirements that a write to a device must be ordered against prior writes to memory, and a read from a device must be ordered against subsequent reads from memory. We satisfy these requirements using various flavours of DSB: the most expensive barrier we have, since it implies completion of prior accesses. This was deemed necessary when we first implemented the accessors, since accesses to different endpoints could propagate independently and therefore the only way to enforce order is to rely on completion guarantees [2]. Since then, the Armv8 memory model has been retrospectively strengthened to require "other-multi-copy atomicity", a property that requires memory accesses from an observer to become visible to all other observers simultaneously [3]. In other words, propagation of accesses is limited to transitioning from locally observed to globally observed. It recently became apparent that this change also has a subtle impact on our I/O accessors for shared peripherals, allowing us to use the cheaper DMB instruction instead. As a concrete example, consider the following: memcpy(dma_buffer, data, bufsz); writel(DMA_START, dev->ctrl_reg); A DMB ST instruction between the final write to the DMA buffer and the write to the control register will ensure that the writes to the DMA buffer are observed before the write to the control register by all observers. Put another way, if an observer can see the write to the control register, it can also see the writes to memory. This has always been the case and is not sufficient to provide the ordering required by Linux, since there is no guarantee that the master interface of the DMA-capable device has observed either of the accesses. However, in an other-multi-copy atomic world, we can infer two things: 1. A write arriving at an endpoint shared between multiple CPUs is visible to all CPUs 2. A write that is visible to all CPUs is also visible to all other observers in the shareability domain Pieced together, this allows us to use DMB OSHST for our default I/O write accessors and DMB OSHLD for our default I/O read accessors (the outer-shareability is for handling non-cacheable mappings) for shared devices. Memory-mapped, DMA-capable peripherals that are private to a CPU (i.e. inaccessible to other CPUs) still require the DSB, however these are few and far between and typically require special treatment anyway which is outside of the scope of the portable driver API (e.g. GIC, page-table walker, SPE profiler). Note that our mandatory barriers remain as DSBs, since there are cases where they are used to flush the store buffer of the CPU, e.g. when publishing page table updates to the SMMU. [1] https://git.kernel.org/linus/4614bbdee357 [2] https://www.youtube.com/watch?v=i6DayghhA8Q [3] https://www.cl.cam.ac.uk/~pes20/armv8-mca/ Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2019-06-07 22:48:58 +08:00
#define __iowmb() dma_wmb()
/*
* Relaxed I/O memory access primitives. These follow the Device memory
* ordering rules but do not guarantee any ordering relative to Normal memory
* accesses.
*/
#define readb_relaxed(c) ({ u8 __r = __raw_readb(c); __r; })
#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
#define readq_relaxed(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
#define writeb_relaxed(v,c) ((void)__raw_writeb((v),(c)))
#define writew_relaxed(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c)))
#define writel_relaxed(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c)))
#define writeq_relaxed(v,c) ((void)__raw_writeq((__force u64)cpu_to_le64(v),(c)))
/*
* I/O memory access primitives. Reads are ordered relative to any
* following Normal memory access. Writes are ordered relative to any prior
* Normal memory access.
*/
#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(__v); __v; })
#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(__v); __v; })
#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; })
#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(__v); __v; })
#define writeb(v,c) ({ __iowmb(); writeb_relaxed((v),(c)); })
#define writew(v,c) ({ __iowmb(); writew_relaxed((v),(c)); })
#define writel(v,c) ({ __iowmb(); writel_relaxed((v),(c)); })
#define writeq(v,c) ({ __iowmb(); writeq_relaxed((v),(c)); })
/*
* I/O port access primitives.
*/
#define arch_has_dev_port() (1)
arm64: Fix overlapping VA allocations PCI IO space was intended to be 16MiB, at 32MiB below MODULES_VADDR, but commit d1e6dc91b532d3d3 ("arm64: Add architectural support for PCI") extended this to cover the full 32MiB. The final 8KiB of this 32MiB is also allocated for the fixmap, allowing for potential clashes between the two. This change was masked by assumptions in mem_init and the page table dumping code, which assumed the I/O space to be 16MiB long through seaparte hard-coded definitions. This patch changes the definition of the PCI I/O space allocation to live in asm/memory.h, along with the other VA space allocations. As the fixmap allocation depends on the number of fixmap entries, this is moved below the PCI I/O space allocation. Both the fixmap and PCI I/O space are guarded with 2MB of padding. Sites assuming the I/O space was 16MiB are moved over use new PCI_IO_{START,END} definitions, which will keep in sync with the size of the IO space (now restored to 16MiB). As a useful side effect, the use of the new PCI_IO_{START,END} definitions prevents a build issue in the dumping code due to a (now redundant) missing include of io.h for PCI_IOBASE. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Kees Cook <keescook@chromium.org> Cc: Laura Abbott <lauraa@codeaurora.org> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Will Deacon <will.deacon@arm.com> [catalin.marinas@arm.com: reorder FIXADDR and PCI_IO address_markers_idx enum] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2015-01-23 02:20:35 +08:00
#define IO_SPACE_LIMIT (PCI_IO_SIZE - 1)
#define PCI_IOBASE ((void __iomem *)PCI_IO_START)
/*
* String version of I/O memory access operations.
*/
extern void __memcpy_fromio(void *, const volatile void __iomem *, size_t);
extern void __memcpy_toio(volatile void __iomem *, const void *, size_t);
extern void __memset_io(volatile void __iomem *, int, size_t);
#define memset_io(c,v,l) __memset_io((c),(v),(l))
#define memcpy_fromio(a,c,l) __memcpy_fromio((a),(c),(l))
#define memcpy_toio(c,a,l) __memcpy_toio((c),(a),(l))
/*
* I/O memory mapping functions.
*/
extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot);
extern void iounmap(volatile void __iomem *addr);
extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
#define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
/*
* PCI configuration space mapping function.
*
* The PCI specification disallows posted write configuration transactions.
* Add an arch specific pci_remap_cfgspace() definition that is implemented
* through nGnRnE device memory attribute as recommended by the ARM v8
* Architecture reference manual Issue A.k B2.8.2 "Device memory".
*/
#define pci_remap_cfgspace(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
/*
* io{read,write}{16,32,64}be() macros
*/
#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(__v); __v; })
#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(__v); __v; })
#define ioread64be(p) ({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(__v); __v; })
#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
#define iowrite64be(v,p) ({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
#include <asm-generic/io.h>
/*
* More restrictive address range checking than the default implementation
* (PHYS_OFFSET and PHYS_MASK taken into account).
*/
#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);
extern int devmem_is_allowed(unsigned long pfn);
#endif /* __ASM_IO_H */