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

89 lines
2.5 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
*/
#ifndef _ASM_IO_H
#define _ASM_IO_H
#include <linux/kernel.h>
#include <linux/types.h>
#include <asm/addrspace.h>
#include <asm/cpu.h>
#include <asm/page.h>
#include <asm/pgtable-bits.h>
#include <asm/string.h>
extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size);
extern void __init early_iounmap(void __iomem *addr, unsigned long size);
#define early_memremap early_ioremap
#define early_memunmap early_iounmap
#ifdef CONFIG_ARCH_IOREMAP
static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
pgprot_t prot)
{
switch (pgprot_val(prot) & _CACHE_MASK) {
case _CACHE_CC:
return (void __iomem *)(unsigned long)(CACHE_BASE + offset);
case _CACHE_SUC:
return (void __iomem *)(unsigned long)(UNCACHE_BASE + offset);
case _CACHE_WUC:
return (void __iomem *)(unsigned long)(WRITECOMBINE_BASE + offset);
default:
return NULL;
}
}
#define ioremap(offset, size) \
ioremap_prot((offset), (size), PAGE_KERNEL_SUC)
#define iounmap(addr) ((void)(addr))
#endif
/*
* On LoongArch, ioremap() has two variants, ioremap_wc() and ioremap_cache().
* They map bus memory into CPU space, the mapped memory is marked uncachable
* (_CACHE_SUC), uncachable but accelerated by write-combine (_CACHE_WUC) and
* cachable (_CACHE_CC) respectively for CPU access.
*
* @offset: bus address of the memory
* @size: size of the resource to map
*/
#define ioremap_wc(offset, size) \
ioremap_prot((offset), (size), \
wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC)
#define ioremap_cache(offset, size) \
ioremap_prot((offset), (size), PAGE_KERNEL)
#define mmiowb() wmb()
LoongArch: Define the __io_aw() hook as mmiowb() Commit fb24ea52f78e0d595852e ("drivers: Remove explicit invocations of mmiowb()") remove all mmiowb() in drivers, but it says: "NOTE: mmiowb() has only ever guaranteed ordering in conjunction with spin_unlock(). However, pairing each mmiowb() removal in this patch with the corresponding call to spin_unlock() is not at all trivial, so there is a small chance that this change may regress any drivers incorrectly relying on mmiowb() to order MMIO writes between CPUs using lock-free synchronisation." The mmio in radeon_ring_commit() is protected by a mutex rather than a spinlock, but in the mutex fastpath it behaves similar to spinlock. We can add mmiowb() calls in the radeon driver but the maintainer says he doesn't like such a workaround, and radeon is not the only example of mutex protected mmio. So we should extend the mmiowb tracking system from spinlock to mutex, and maybe other locking primitives. This is not easy and error prone, so we solve it in the architectural code, by simply defining the __io_aw() hook as mmiowb(). And we no longer need to override queued_spin_unlock() so use the generic definition. Without this, we get such an error when run 'glxgears' on weak ordering architectures such as LoongArch: radeon 0000:04:00.0: ring 0 stalled for more than 10324msec radeon 0000:04:00.0: ring 3 stalled for more than 10240msec radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000001f412 last fence id 0x000000000001f414 on ring 3) radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000000f940 last fence id 0x000000000000f941 on ring 0) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn't update BO_VA (-35) Link: https://lore.kernel.org/dri-devel/29df7e26-d7a8-4f67-b988-44353c4270ac@amd.com/T/#t Link: https://lore.kernel.org/linux-arch/20240301130532.3953167-1-chenhuacai@loongson.cn/T/#t Cc: stable@vger.kernel.org Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
2024-03-19 15:50:34 +08:00
#define __io_aw() mmiowb()
#ifdef CONFIG_KFENCE
#define virt_to_phys(kaddr) \
({ \
(likely((unsigned long)kaddr < vm_map_base)) ? __pa((unsigned long)kaddr) : \
page_to_phys(tlb_virt_to_page((unsigned long)kaddr)) + offset_in_page((unsigned long)kaddr);\
})
#define phys_to_virt(paddr) \
({ \
extern char *__kfence_pool; \
(unlikely(__kfence_pool == NULL)) ? __va((unsigned long)paddr) : \
page_address(phys_to_page((unsigned long)paddr)) + offset_in_page((unsigned long)paddr);\
})
#endif
#include <asm-generic/io.h>
#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);
#endif /* _ASM_IO_H */