diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-12 09:16:56 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-12 09:16:56 -0800 |
commit | a26be149facb22d30cd92cadb26f651d6fe802c9 (patch) | |
tree | c467bd0cae818ef793e9a694b4cd2bdc88d9ff6b /include | |
parent | cdd305454ebd181fa35b648c0921fe7df27d6f3b (diff) | |
parent | a20cc76b9efae10c20123049df361adcd7f0e0b3 (diff) | |
download | linux-a26be149facb22d30cd92cadb26f651d6fe802c9.tar.bz2 |
Merge tag 'iommu-updates-v3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull IOMMU updates from Joerg Roedel:
"This time with:
- Generic page-table framework for ARM IOMMUs using the LPAE
page-table format, ARM-SMMU and Renesas IPMMU make use of it
already.
- Break out the IO virtual address allocator from the Intel IOMMU so
that it can be used by other DMA-API implementations too. The
first user will be the ARM64 common DMA-API implementation for
IOMMUs
- Device tree support for Renesas IPMMU
- Various fixes and cleanups all over the place"
* tag 'iommu-updates-v3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (36 commits)
iommu/amd: Convert non-returned local variable to boolean when relevant
iommu: Update my email address
iommu/amd: Use wait_event in put_pasid_state_wait
iommu/amd: Fix amd_iommu_free_device()
iommu/arm-smmu: Avoid build warning
iommu/fsl: Various cleanups
iommu/fsl: Use %pa to print phys_addr_t
iommu/omap: Print phys_addr_t using %pa
iommu: Make more drivers depend on COMPILE_TEST
iommu/ipmmu-vmsa: Fix IOMMU lookup when multiple IOMMUs are registered
iommu: Disable on !MMU builds
iommu/fsl: Remove unused fsl_of_pamu_ids[]
iommu/fsl: Fix section mismatch
iommu/ipmmu-vmsa: Use the ARM LPAE page table allocator
iommu: Fix trace_map() to report original iova and original size
iommu/arm-smmu: add support for iova_to_phys through ATS1PR
iopoll: Introduce memory-mapped IO polling macros
iommu/arm-smmu: don't touch the secure STLBIALL register
iommu/arm-smmu: make use of generic LPAE allocator
iommu: io-pgtable-arm: add non-secure quirk
...
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/iopoll.h | 144 | ||||
-rw-r--r-- | include/linux/iova.h | 41 | ||||
-rw-r--r-- | include/linux/platform_data/ipmmu-vmsa.h | 24 | ||||
-rw-r--r-- | include/trace/events/iommu.h | 31 |
4 files changed, 199 insertions, 41 deletions
diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h new file mode 100644 index 000000000000..1c30014ed176 --- /dev/null +++ b/include/linux/iopoll.h @@ -0,0 +1,144 @@ +/* + * Copyright (c) 2012-2014 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_IOPOLL_H +#define _LINUX_IOPOLL_H + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/hrtimer.h> +#include <linux/delay.h> +#include <linux/errno.h> +#include <linux/io.h> + +/** + * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs + * @op: accessor function (takes @addr as its only argument) + * @addr: Address to poll + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @sleep_us: Maximum time to sleep between reads in us (0 + * tight-loops). Should be less than ~20ms since usleep_range + * is used (see Documentation/timers/timers-howto.txt). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + */ +#define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \ +({ \ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + might_sleep_if(sleep_us); \ + for (;;) { \ + (val) = op(addr); \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + (val) = op(addr); \ + break; \ + } \ + if (sleep_us) \ + usleep_range((sleep_us >> 2) + 1, sleep_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + +/** + * readx_poll_timeout_atomic - Periodically poll an address until a condition is met or a timeout occurs + * @op: accessor function (takes @addr as its only argument) + * @addr: Address to poll + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @delay_us: Time to udelay between reads in us (0 tight-loops). Should + * be less than ~10us since udelay is used (see + * Documentation/timers/timers-howto.txt). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + */ +#define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \ +({ \ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + for (;;) { \ + (val) = op(addr); \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + (val) = op(addr); \ + break; \ + } \ + if (delay_us) \ + udelay(delay_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + + +#define readb_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readb, addr, val, cond, delay_us, timeout_us) + +#define readb_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readb, addr, val, cond, delay_us, timeout_us) + +#define readw_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readw, addr, val, cond, delay_us, timeout_us) + +#define readw_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readw, addr, val, cond, delay_us, timeout_us) + +#define readl_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readl, addr, val, cond, delay_us, timeout_us) + +#define readl_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readl, addr, val, cond, delay_us, timeout_us) + +#define readq_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readq, addr, val, cond, delay_us, timeout_us) + +#define readq_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readq, addr, val, cond, delay_us, timeout_us) + +#define readb_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readb_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readb_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readb_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readw_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readw_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readw_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readw_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readl_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readl_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readl_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readl_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readq_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readq_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readq_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readq_relaxed, addr, val, cond, delay_us, timeout_us) + +#endif /* _LINUX_IOPOLL_H */ diff --git a/include/linux/iova.h b/include/linux/iova.h index 19e81d5ccb6d..3920a19d8194 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -16,9 +16,6 @@ #include <linux/rbtree.h> #include <linux/dma-mapping.h> -/* IO virtual address start page frame number */ -#define IOVA_START_PFN (1) - /* iova structure */ struct iova { struct rb_node node; @@ -31,6 +28,8 @@ struct iova_domain { spinlock_t iova_rbtree_lock; /* Lock to protect update of rbtree */ struct rb_root rbroot; /* iova domain rbtree root */ struct rb_node *cached32_node; /* Save last alloced node */ + unsigned long granule; /* pfn granularity for this domain */ + unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; }; @@ -39,6 +38,39 @@ static inline unsigned long iova_size(struct iova *iova) return iova->pfn_hi - iova->pfn_lo + 1; } +static inline unsigned long iova_shift(struct iova_domain *iovad) +{ + return __ffs(iovad->granule); +} + +static inline unsigned long iova_mask(struct iova_domain *iovad) +{ + return iovad->granule - 1; +} + +static inline size_t iova_offset(struct iova_domain *iovad, dma_addr_t iova) +{ + return iova & iova_mask(iovad); +} + +static inline size_t iova_align(struct iova_domain *iovad, size_t size) +{ + return ALIGN(size, iovad->granule); +} + +static inline dma_addr_t iova_dma_addr(struct iova_domain *iovad, struct iova *iova) +{ + return (dma_addr_t)iova->pfn_lo << iova_shift(iovad); +} + +static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) +{ + return iova >> iova_shift(iovad); +} + +int iommu_iova_cache_init(void); +void iommu_iova_cache_destroy(void); + struct iova *alloc_iova_mem(void); void free_iova_mem(struct iova *iova); void free_iova(struct iova_domain *iovad, unsigned long pfn); @@ -49,7 +81,8 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); -void init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit); +void init_iova_domain(struct iova_domain *iovad, unsigned long granule, + unsigned long start_pfn, unsigned long pfn_32bit); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); struct iova *split_and_remove_iova(struct iova_domain *iovad, diff --git a/include/linux/platform_data/ipmmu-vmsa.h b/include/linux/platform_data/ipmmu-vmsa.h deleted file mode 100644 index 5275b3ac6d37..000000000000 --- a/include/linux/platform_data/ipmmu-vmsa.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * IPMMU VMSA Platform Data - * - * Copyright (C) 2014 Renesas Electronics Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - */ - -#ifndef __IPMMU_VMSA_H__ -#define __IPMMU_VMSA_H__ - -struct ipmmu_vmsa_master { - const char *name; - unsigned int utlb; -}; - -struct ipmmu_vmsa_platform_data { - const struct ipmmu_vmsa_master *masters; - unsigned int num_masters; -}; - -#endif /* __IPMMU_VMSA_H__ */ diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h index a8f5c32d174b..2c7befb10f13 100644 --- a/include/trace/events/iommu.h +++ b/include/trace/events/iommu.h @@ -83,7 +83,7 @@ DEFINE_EVENT(iommu_device_event, detach_device_from_domain, TP_ARGS(dev) ); -DECLARE_EVENT_CLASS(iommu_map_unmap, +TRACE_EVENT(map, TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size), @@ -92,7 +92,7 @@ DECLARE_EVENT_CLASS(iommu_map_unmap, TP_STRUCT__entry( __field(u64, iova) __field(u64, paddr) - __field(int, size) + __field(size_t, size) ), TP_fast_assign( @@ -101,26 +101,31 @@ DECLARE_EVENT_CLASS(iommu_map_unmap, __entry->size = size; ), - TP_printk("IOMMU: iova=0x%016llx paddr=0x%016llx size=0x%x", + TP_printk("IOMMU: iova=0x%016llx paddr=0x%016llx size=%zu", __entry->iova, __entry->paddr, __entry->size ) ); -DEFINE_EVENT(iommu_map_unmap, map, +TRACE_EVENT(unmap, - TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size), - - TP_ARGS(iova, paddr, size) -); + TP_PROTO(unsigned long iova, size_t size, size_t unmapped_size), -DEFINE_EVENT_PRINT(iommu_map_unmap, unmap, + TP_ARGS(iova, size, unmapped_size), - TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size), + TP_STRUCT__entry( + __field(u64, iova) + __field(size_t, size) + __field(size_t, unmapped_size) + ), - TP_ARGS(iova, paddr, size), + TP_fast_assign( + __entry->iova = iova; + __entry->size = size; + __entry->unmapped_size = unmapped_size; + ), - TP_printk("IOMMU: iova=0x%016llx size=0x%x", - __entry->iova, __entry->size + TP_printk("IOMMU: iova=0x%016llx size=%zu unmapped_size=%zu", + __entry->iova, __entry->size, __entry->unmapped_size ) ); |