kevin/linux
1
Fork 0
Code
24950898ff
linux/include/asm-sparc64/iommu.h

61 lines
1.6 KiB
C
Raw Normal View History

[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-27 22:39:14 -07:00
/* iommu.h: Definitions for the sun5 IOMMU.
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
*
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-27 22:39:14 -07:00
* Copyright (C) 1996, 1999, 2007 David S. Miller (davem@davemloft.net)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
*/
#ifndef _SPARC64_IOMMU_H
#define _SPARC64_IOMMU_H
/* The format of an iopte in the page tables. */
[SPARC64]: Consolidate {sbus,pci}_iommu_arena. Move to asm-sparc64/iommu.h and rename to plain "iommu_arena". Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-24 23:51:18 -07:00
#define IOPTE_VALID 0x8000000000000000UL
#define IOPTE_64K 0x2000000000000000UL
#define IOPTE_STBUF 0x1000000000000000UL
#define IOPTE_INTRA 0x0800000000000000UL
#define IOPTE_CONTEXT 0x07ff800000000000UL
#define IOPTE_PAGE 0x00007fffffffe000UL
#define IOPTE_CACHE 0x0000000000000010UL
#define IOPTE_WRITE 0x0000000000000002UL
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
[SPARC64]: Fix streaming buffer flushing on PCI and SBUS. Firstly, if the direction is TODEVICE, then dirty data in the streaming cache is impossible so we can elide the flush-flag synchronization in that case. Next, the context allocator is broken. It is highly likely that contexts get used multiple times for different dma mappings, which confuses the strbuf flushing code and makes it run inefficiently. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-05-31 16:57:59 -07:00
#define IOMMU_NUM_CTXS 4096
[SPARC64]: Consolidate {sbus,pci}_iommu_arena. Move to asm-sparc64/iommu.h and rename to plain "iommu_arena". Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-24 23:51:18 -07:00
struct iommu_arena {
unsigned long *map;
unsigned int hint;
unsigned int limit;
};
[SPARC64]: Add generic iommu and strbuf structs to iommu.h Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-25 00:12:09 -07:00
struct iommu {
spinlock_t lock;
struct iommu_arena arena;
iopte_t *page_table;
u32 page_table_map_base;
unsigned long iommu_control;
unsigned long iommu_tsbbase;
unsigned long iommu_flush;
[SPARC64]: SUN4U PCI-E controller support. Some minor refactoring in the generic code was necessary for this: 1) This controller requires 8-byte access to the interrupt map and clear register. They are 64-bits on all the other SBUS and PCI controllers anyways, so this was easy to cure. 2) The IMAP register has a different layout and some bits that we need to preserve, so use a read/modify/write when making changes to the IMAP register in generic code. 3) Flushing the entire IOMMU TLB is best done with a single write to a register on this PCI controller, add a iommu->iommu_flushinv for this. Still lacks MSI support, that will come later. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-02 17:31:36 -07:00
unsigned long iommu_flushinv;
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-27 22:39:14 -07:00
unsigned long iommu_tags;
[SPARC64]: Add generic iommu and strbuf structs to iommu.h Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-25 00:12:09 -07:00
unsigned long iommu_ctxflush;
unsigned long write_complete_reg;
unsigned long dummy_page;
unsigned long dummy_page_pa;
unsigned long ctx_lowest_free;
DECLARE_BITMAP(ctx_bitmap, IOMMU_NUM_CTXS);
u32 dma_addr_mask;
};
struct strbuf {
int strbuf_enabled;
unsigned long strbuf_control;
unsigned long strbuf_pflush;
unsigned long strbuf_fsync;
unsigned long strbuf_ctxflush;
unsigned long strbuf_ctxmatch_base;
unsigned long strbuf_flushflag_pa;
volatile unsigned long *strbuf_flushflag;
volatile unsigned long __flushflag_buf[(64+(64-1)) / sizeof(long)];
};
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-27 22:39:14 -07:00
extern int iommu_table_init(struct iommu *iommu, int tsbsize,
u32 dma_offset, u32 dma_addr_mask);
#endif /* !(_SPARC64_IOMMU_H) */
Copy Permalink