Re: [PATCH v13 1/9] LIB: Introduce a generic PIO mapping method

From: dann frazier
Date: Tue Feb 13 2018 - 18:06:00 EST


On Wed, Feb 14, 2018 at 01:45:25AM +0800, John Garry wrote:
> From: Zhichang Yuan <yuanzhichang@xxxxxxxxxxxxx>
>
> In commit 41f8bba7f555 ("of/pci: Add pci_register_io_range() and
> pci_pio_to_address()"), a new I/O space management was supported. With
> that driver, the I/O ranges configured for PCI/PCIe hosts on some
> architectures can be mapped to logical PIO, converted easily between
> CPU address and the corresponding logicial PIO. Based on this, PCI
> I/O devices can be accessed in a memory read/write way through the
> unified in/out accessors.
>
> But on some archs/platforms, there are bus hosts which access I/O
> peripherals with host-local I/O port addresses rather than memory
> addresses after memory-mapped.
>
> To support those devices, a more generic I/O mapping method is introduced
> here. Through this patch, both the CPU addresses and the host-local port
> can be mapped into the logical PIO space with different logical/fake PIOs.
> After this, all the I/O accesses to either PCI MMIO devices or host-local
> I/O peripherals can be unified into the existing I/O accessors defined in
> asm-generic/io.h and be redirected to the right device-specific hooks
> based on the input logical PIO.
>
> Signed-off-by: Zhichang Yuan <yuanzhichang@xxxxxxxxxxxxx>
> Signed-off-by: Gabriele Paoloni <gabriele.paoloni@xxxxxxxxxx>
> Signed-off-by: John Garry <john.garry@xxxxxxxxxx>
> ---
> include/asm-generic/io.h | 2 +
> include/linux/logic_pio.h | 131 ++++++++++++++++++++++
> lib/Kconfig | 15 +++
> lib/Makefile | 2 +
> lib/logic_pio.c | 272 ++++++++++++++++++++++++++++++++++++++++++++++
> 5 files changed, 422 insertions(+)
> create mode 100644 include/linux/logic_pio.h
> create mode 100644 lib/logic_pio.c
>
> diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
> index b4531e3..b7996a79 100644
> --- a/include/asm-generic/io.h
> +++ b/include/asm-generic/io.h
> @@ -351,6 +351,8 @@ static inline void writesq(volatile void __iomem *addr, const void *buffer,
> #define IO_SPACE_LIMIT 0xffff
> #endif
>
> +#include <linux/logic_pio.h>
> +
> /*
> * {in,out}{b,w,l}() access little endian I/O. {in,out}{b,w,l}_p() can be
> * implemented on hardware that needs an additional delay for I/O accesses to
> diff --git a/include/linux/logic_pio.h b/include/linux/logic_pio.h
> new file mode 100644
> index 0000000..b3322fd
> --- /dev/null
> +++ b/include/linux/logic_pio.h
> @@ -0,0 +1,131 @@
> +// SPDX-License-Identifier: GPL-2.0+
> +/*
> + * Copyright (C) 2017 Hisilicon Limited, All Rights Reserved.
> + * Author: Gabriele Paoloni <gabriele.paoloni@xxxxxxxxxx>
> + * Author: Zhichang Yuan <yuanzhichang@xxxxxxxxxxxxx>
> + *
> + */
> +
> +#ifndef __LINUX_LOGIC_PIO_H__
> +#define __LINUX_LOGIC_PIO_H__
> +
> +#ifdef __KERNEL__
> +
> +#include <linux/fwnode.h>
> +
> +#define PIO_INDIRECT 0x01UL /* indirect IO flag */
> +#define PIO_CPU_MMIO 0x00UL /* memory mapped io flag */
> +
> +struct logic_pio_hwaddr {
> + struct list_head list;
> + struct fwnode_handle *fwnode;
> + resource_size_t hw_start;
> + resource_size_t io_start;
> + resource_size_t size; /* range size populated */
> + unsigned long flags;
> +
> + void *devpara; /* private parameter of the host device */
> + struct hostio_ops *ops; /* ops operating on this node */
> +};
> +
> +struct hostio_ops {
> + u32 (*pfin)(void *devobj, unsigned long ptaddr, size_t dlen);
> + void (*pfout)(void *devobj, unsigned long ptaddr, u32 outval,
> + size_t dlen);
> + u32 (*pfins)(void *devobj, unsigned long ptaddr, void *inbuf,
> + size_t dlen, unsigned int count);
> + void (*pfouts)(void *devobj, unsigned long ptaddr,
> + const void *outbuf, size_t dlen, unsigned int count);
> +};
> +
> +#ifdef CONFIG_INDIRECT_PIO
> +u8 logic_inb(unsigned long addr);
> +void logic_outb(u8 value, unsigned long addr);
> +void logic_outw(u16 value, unsigned long addr);
> +void logic_outl(u32 value, unsigned long addr);
> +u16 logic_inw(unsigned long addr);
> +u32 logic_inl(unsigned long addr);
> +void logic_outb(u8 value, unsigned long addr);
> +void logic_outw(u16 value, unsigned long addr);
> +void logic_outl(u32 value, unsigned long addr);
> +void logic_insb(unsigned long addr, void *buffer, unsigned int count);
> +void logic_insl(unsigned long addr, void *buffer, unsigned int count);
> +void logic_insw(unsigned long addr, void *buffer, unsigned int count);
> +void logic_outsb(unsigned long addr, const void *buffer, unsigned int count);
> +void logic_outsw(unsigned long addr, const void *buffer, unsigned int count);
> +void logic_outsl(unsigned long addr, const void *buffer, unsigned int count);
> +
> +#ifndef inb
> +#define inb logic_inb
> +#endif
> +
> +#ifndef inw
> +#define inw logic_inw
> +#endif
> +
> +#ifndef inl
> +#define inl logic_inl
> +#endif
> +
> +#ifndef outb
> +#define outb logic_outb
> +#endif
> +
> +#ifndef outw
> +#define outw logic_outw
> +#endif
> +
> +#ifndef outl
> +#define outl logic_outl
> +#endif
> +
> +#ifndef insb
> +#define insb logic_insb
> +#endif
> +
> +#ifndef insw
> +#define insw logic_insw
> +#endif
> +
> +#ifndef insl
> +#define insl logic_insl
> +#endif
> +
> +#ifndef outsb
> +#define outsb logic_outsb
> +#endif
> +
> +#ifndef outsw
> +#define outsw logic_outsw
> +#endif
> +
> +#ifndef outsl
> +#define outsl logic_outsl
> +#endif
> +
> +/*
> + * Below we reserve 0x4000 bytes for Indirect IO as so far this library is only
> + * used by Hisilicon LPC Host. If needed in future we may reserve a wider IO
> + * area by redefining the macro below.
> + */
> +#define PIO_INDIRECT_SIZE 0x4000
> +#define MMIO_UPPER_LIMIT (IO_SPACE_LIMIT - PIO_INDIRECT_SIZE)
> +#else
> +#define MMIO_UPPER_LIMIT IO_SPACE_LIMIT
> +#endif /* CONFIG_INDIRECT_PIO */
> +
> +
> +struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode);
> +
> +unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode,
> + resource_size_t hw_addr, resource_size_t size);
> +
> +int logic_pio_register_range(struct logic_pio_hwaddr *newrange);
> +
> +
> +extern resource_size_t logic_pio_to_hwaddr(unsigned long pio);
> +
> +extern unsigned long logic_pio_trans_cpuaddr(resource_size_t hw_addr);
> +
> +#endif /* __KERNEL__ */
> +#endif /* __LINUX_LOGIC_PIO_H__ */
> diff --git a/lib/Kconfig b/lib/Kconfig
> index e960894..7ad1e69 100644
> --- a/lib/Kconfig
> +++ b/lib/Kconfig
> @@ -55,6 +55,21 @@ config ARCH_USE_CMPXCHG_LOCKREF
> config ARCH_HAS_FAST_MULTIPLIER
> bool
>
> +config INDIRECT_PIO
> + bool "Access I/O in non-MMIO mode"
> + depends on ARM64
> + help
> + On some platforms where no separate I/O space exists, there are I/O
> + hosts which can not be accessed in MMIO mode. Using the logical PIO
> + mechanism, the host-local I/O resource can be mapped into system
> + logic PIO space shared with MMIO hosts, such as PCI/PCIE, then the
> + system can access the I/O devices with the mapped logic PIO through
> + I/O accessors.
> + This way has a relatively little I/O performance cost. Please make

grammar nit - s/a relatively/relatively/

-dann

> + sure your devices really need this configure item enabled.
> +
> + When in doubt, say N.
> +
> config CRC_CCITT
> tristate "CRC-CCITT functions"
> help
> diff --git a/lib/Makefile b/lib/Makefile
> index a90d4fc..4a9eacd 100644
> --- a/lib/Makefile
> +++ b/lib/Makefile
> @@ -81,6 +81,8 @@ obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
> obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
> obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
>
> +obj-y += logic_pio.o
> +
> obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
>
> obj-$(CONFIG_BTREE) += btree.o
> diff --git a/lib/logic_pio.c b/lib/logic_pio.c
> new file mode 100644
> index 0000000..1006d9d
> --- /dev/null
> +++ b/lib/logic_pio.c
> @@ -0,0 +1,272 @@
> +// SPDX-License-Identifier: GPL-2.0+
> +/*
> + * Copyright (C) 2017 Hisilicon Limited, All Rights Reserved.
> + * Author: Gabriele Paoloni <gabriele.paoloni@xxxxxxxxxx>
> + * Author: Zhichang Yuan <yuanzhichang@xxxxxxxxxxxxx>
> + *
> + */
> +
> +#define pr_fmt(fmt) "LOGIC PIO: " fmt
> +
> +#include <linux/of.h>
> +#include <linux/io.h>
> +#include <linux/logic_pio.h>
> +#include <linux/mm.h>
> +#include <linux/rculist.h>
> +#include <linux/sizes.h>
> +#include <linux/slab.h>
> +
> +/* The unique hardware address list. */
> +static LIST_HEAD(io_range_list);
> +static DEFINE_MUTEX(io_range_mutex);
> +
> +/*
> + * register a new io range node in the io range list.
> + *
> + * @newrange: pointer to the io range to be registered.
> + *
> + * returns 0 on success, the error code in case of failure
> + */
> +int logic_pio_register_range(struct logic_pio_hwaddr *new_range)
> +{
> + struct logic_pio_hwaddr *range;
> + int ret = 0;
> + resource_size_t start = new_range->hw_start;
> + resource_size_t end = new_range->hw_start + new_range->size;
> + resource_size_t allocated_mmio_size = 0;
> + resource_size_t allocated_iio_size = MMIO_UPPER_LIMIT;
> +
> + if (!new_range || !new_range->fwnode || !new_range->size)
> + return -EINVAL;
> +
> + mutex_lock(&io_range_mutex);
> + list_for_each_entry_rcu(range, &io_range_list, list) {
> + if (range->fwnode == new_range->fwnode) {
> + /* range already there */
> + ret = -EFAULT;
> + goto end_register;
> + }
> + if (range->flags == PIO_CPU_MMIO &&
> + new_range->flags == PIO_CPU_MMIO) {
> + /* for MMIO ranges we need to check for overlap */
> + if (start >= range->hw_start + range->size ||
> + end < range->hw_start)
> + allocated_mmio_size += range->size;
> + else {
> + ret = -EFAULT;
> + goto end_register;
> + }
> + } else if (range->flags == PIO_INDIRECT &&
> + new_range->flags == PIO_INDIRECT) {
> + allocated_iio_size += range->size;
> + }
> + }
> +
> + /* range not registered yet, check for available space */
> + if (new_range->flags == PIO_CPU_MMIO) {
> + if (allocated_mmio_size + new_range->size - 1 >
> + MMIO_UPPER_LIMIT) {
> + /* if it's too big check if 64K space can be reserved */
> + if (allocated_mmio_size + SZ_64K - 1 >
> + MMIO_UPPER_LIMIT) {
> + ret = -E2BIG;
> + goto end_register;
> + }
> + new_range->size = SZ_64K;
> + pr_warn("Requested IO range too big, new size set to 64K\n");
> + }
> + new_range->io_start = allocated_mmio_size;
> + } else if (new_range->flags == PIO_INDIRECT) {
> + if (allocated_iio_size + new_range->size - 1 >
> + IO_SPACE_LIMIT) {
> + ret = -E2BIG;
> + goto end_register;
> + }
> + new_range->io_start = allocated_iio_size;
> + } else {
> + /* invalid flag */
> + ret = -EINVAL;
> + goto end_register;
> + }
> +
> + list_add_tail_rcu(&new_range->list, &io_range_list);
> +
> +end_register:
> + mutex_unlock(&io_range_mutex);
> + return ret;
> +}
> +
> +/*
> + * traverse the io_range_list to find the registered node whose device node
> + * and/or physical IO address match to.
> + */
> +struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode)
> +{
> + struct logic_pio_hwaddr *range;
> +
> + list_for_each_entry_rcu(range, &io_range_list, list) {
> + if (range->fwnode == fwnode)
> + return range;
> + }
> + return NULL;
> +}
> +
> +/* return a registered range given an input PIO token */
> +static struct logic_pio_hwaddr *find_io_range(unsigned long pio)
> +{
> + struct logic_pio_hwaddr *range;
> +
> + list_for_each_entry_rcu(range, &io_range_list, list) {
> + if (pio >= range->io_start &&
> + pio < range->io_start + range->size)
> + return range;
> + }
> + pr_err("PIO entry token invalid\n");
> + return NULL;
> +}
> +
> +/*
> + * Translate the input logical pio to the corresponding hardware address.
> + * The input pio should be unique in the whole logical PIO space.
> + */
> +resource_size_t logic_pio_to_hwaddr(unsigned long pio)
> +{
> + struct logic_pio_hwaddr *range;
> + resource_size_t hwaddr = -1;
> +
> + range = find_io_range(pio);
> + if (range)
> + hwaddr = range->hw_start + pio - range->io_start;
> +
> + return hwaddr;
> +}
> +
> +/*
> + * This function is generic for translating a hardware address to logical PIO.
> + * @hw_addr: the hardware address of host, can be CPU address or host-local
> + * address;
> + */
> +unsigned long
> +logic_pio_trans_hwaddr(struct fwnode_handle *fwnode, resource_size_t addr,
> + resource_size_t size)
> +{
> + struct logic_pio_hwaddr *range;
> +
> + range = find_io_range_by_fwnode(fwnode);
> + if (!range || range->flags == PIO_CPU_MMIO) {
> + pr_err("range not found or invalid\n");
> + return -1;
> + }
> + if (range->size < size) {
> + pr_err("resource size %pa cannot fit in IO range size %pa\n",
> + &size, &range->size);
> + return -1;
> + }
> + return addr - range->hw_start + range->io_start;
> +}
> +
> +unsigned long
> +logic_pio_trans_cpuaddr(resource_size_t addr)
> +{
> + struct logic_pio_hwaddr *range;
> +
> + list_for_each_entry_rcu(range, &io_range_list, list) {
> + if (range->flags != PIO_CPU_MMIO)
> + continue;
> + if (addr >= range->hw_start &&
> + addr < range->hw_start + range->size)
> + return addr - range->hw_start +
> + range->io_start;
> + }
> + pr_err("addr not registered in io_range_list\n");
> + return -1;
> +}
> +
> +#if defined(CONFIG_INDIRECT_PIO) && defined(PCI_IOBASE)
> +#define BUILD_LOGIC_IO(bw, type) \
> +type logic_in##bw(unsigned long addr) \
> +{ \
> + type ret = -1; \
> + \
> + if (addr < MMIO_UPPER_LIMIT) { \
> + ret = read##bw(PCI_IOBASE + addr); \
> + } else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) { \
> + struct logic_pio_hwaddr *entry = find_io_range(addr); \
> + \
> + if (entry && entry->ops) \
> + ret = entry->ops->pfin(entry->devpara, \
> + addr, sizeof(type)); \
> + else \
> + WARN_ON_ONCE(1); \
> + } \
> + return ret; \
> +} \
> + \
> +void logic_out##bw(type value, unsigned long addr) \
> +{ \
> + if (addr < MMIO_UPPER_LIMIT) { \
> + write##bw(value, PCI_IOBASE + addr); \
> + } else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) { \
> + struct logic_pio_hwaddr *entry = find_io_range(addr); \
> + \
> + if (entry && entry->ops) \
> + entry->ops->pfout(entry->devpara, \
> + addr, value, sizeof(type)); \
> + else \
> + WARN_ON_ONCE(1); \
> + } \
> +} \
> + \
> +void logic_ins##bw(unsigned long addr, void *buffer, unsigned int count)\
> +{ \
> + if (addr < MMIO_UPPER_LIMIT) { \
> + reads##bw(PCI_IOBASE + addr, buffer, count); \
> + } else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) { \
> + struct logic_pio_hwaddr *entry = find_io_range(addr); \
> + \
> + if (entry && entry->ops) \
> + entry->ops->pfins(entry->devpara, \
> + addr, buffer, sizeof(type), count); \
> + else \
> + WARN_ON_ONCE(1); \
> + } \
> + \
> +} \
> + \
> +void logic_outs##bw(unsigned long addr, const void *buffer, \
> + unsigned int count) \
> +{ \
> + if (addr < MMIO_UPPER_LIMIT) { \
> + writes##bw(PCI_IOBASE + addr, buffer, count); \
> + } else if (addr >= MMIO_UPPER_LIMIT && addr < IO_SPACE_LIMIT) { \
> + struct logic_pio_hwaddr *entry = find_io_range(addr); \
> + \
> + if (entry && entry->ops) \
> + entry->ops->pfouts(entry->devpara, \
> + addr, buffer, sizeof(type), count); \
> + else \
> + WARN_ON_ONCE(1); \
> + } \
> +}
> +
> +BUILD_LOGIC_IO(b, u8)
> +
> +EXPORT_SYMBOL(logic_inb);
> +EXPORT_SYMBOL(logic_outb);
> +EXPORT_SYMBOL(logic_insb);
> +EXPORT_SYMBOL(logic_outsb);
> +
> +BUILD_LOGIC_IO(w, u16)
> +
> +EXPORT_SYMBOL(logic_inw);
> +EXPORT_SYMBOL(logic_outw);
> +EXPORT_SYMBOL(logic_insw);
> +EXPORT_SYMBOL(logic_outsw);
> +
> +BUILD_LOGIC_IO(l, u32)
> +
> +EXPORT_SYMBOL(logic_inl);
> +EXPORT_SYMBOL(logic_outl);
> +EXPORT_SYMBOL(logic_insl);
> +EXPORT_SYMBOL(logic_outsl);
> +#endif /* CONFIG_INDIRECT_PIO && PCI_IOBASE */