OpenCloudOS-Kernel/include/asm-x86_64/dma.h

306 lines
9.8 KiB
C
Raw Normal View History

/* $Id: dma.h,v 1.1.1.1 2001/04/19 20:00:38 ak Exp $
* linux/include/asm/dma.h: Defines for using and allocating dma channels.
* Written by Hennus Bergman, 1992.
* High DMA channel support & info by Hannu Savolainen
* and John Boyd, Nov. 1992.
*/
#ifndef _ASM_DMA_H
#define _ASM_DMA_H
#include <linux/config.h>
#include <linux/spinlock.h> /* And spinlocks */
#include <asm/io.h> /* need byte IO */
#include <linux/delay.h>
#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
#define dma_outb outb_p
#else
#define dma_outb outb
#endif
#define dma_inb inb
/*
* NOTES about DMA transfers:
*
* controller 1: channels 0-3, byte operations, ports 00-1F
* controller 2: channels 4-7, word operations, ports C0-DF
*
* - ALL registers are 8 bits only, regardless of transfer size
* - channel 4 is not used - cascades 1 into 2.
* - channels 0-3 are byte - addresses/counts are for physical bytes
* - channels 5-7 are word - addresses/counts are for physical words
* - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
* - transfer count loaded to registers is 1 less than actual count
* - controller 2 offsets are all even (2x offsets for controller 1)
* - page registers for 5-7 don't use data bit 0, represent 128K pages
* - page registers for 0-3 use bit 0, represent 64K pages
*
* DMA transfers are limited to the lower 16MB of _physical_ memory.
* Note that addresses loaded into registers must be _physical_ addresses,
* not logical addresses (which may differ if paging is active).
*
* Address mapping for channels 0-3:
*
* A23 ... A16 A15 ... A8 A7 ... A0 (Physical addresses)
* | ... | | ... | | ... |
* | ... | | ... | | ... |
* | ... | | ... | | ... |
* P7 ... P0 A7 ... A0 A7 ... A0
* | Page | Addr MSB | Addr LSB | (DMA registers)
*
* Address mapping for channels 5-7:
*
* A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0 (Physical addresses)
* | ... | \ \ ... \ \ \ ... \ \
* | ... | \ \ ... \ \ \ ... \ (not used)
* | ... | \ \ ... \ \ \ ... \
* P7 ... P1 (0) A7 A6 ... A0 A7 A6 ... A0
* | Page | Addr MSB | Addr LSB | (DMA registers)
*
* Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
* and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
* the hardware level, so odd-byte transfers aren't possible).
*
* Transfer count (_not # bytes_) is limited to 64K, represented as actual
* count - 1 : 64K => 0xFFFF, 1 => 0x0000. Thus, count is always 1 or more,
* and up to 128K bytes may be transferred on channels 5-7 in one operation.
*
*/
#define MAX_DMA_CHANNELS 8
[PATCH] x86_64: Add 4GB DMA32 zone Add a new 4GB GFP_DMA32 zone between the GFP_DMA and GFP_NORMAL zones. As a bit of historical background: when the x86-64 port was originally designed we had some discussion if we should use a 16MB DMA zone like i386 or a 4GB DMA zone like IA64 or both. Both was ruled out at this point because it was in early 2.4 when VM is still quite shakey and had bad troubles even dealing with one DMA zone. We settled on the 16MB DMA zone mainly because we worried about older soundcards and the floppy. But this has always caused problems since then because device drivers had trouble getting enough DMA able memory. These days the VM works much better and the wide use of NUMA has proven it can deal with many zones successfully. So this patch adds both zones. This helps drivers who need a lot of memory below 4GB because their hardware is not accessing more (graphic drivers - proprietary and free ones, video frame buffer drivers, sound drivers etc.). Previously they could only use IOMMU+16MB GFP_DMA, which was not enough memory. Another common problem is that hardware who has full memory addressing for >4GB misses it for some control structures in memory (like transmit rings or other metadata). They tended to allocate memory in the 16MB GFP_DMA or the IOMMU/swiotlb then using pci_alloc_consistent, but that can tie up a lot of precious 16MB GFPDMA/IOMMU/swiotlb memory (even on AMD systems the IOMMU tends to be quite small) especially if you have many devices. With the new zone pci_alloc_consistent can just put this stuff into memory below 4GB which works better. One argument was still if the zone should be 4GB or 2GB. The main motivation for 2GB would be an unnamed not so unpopular hardware raid controller (mostly found in older machines from a particular four letter company) who has a strange 2GB restriction in firmware. But that one works ok with swiotlb/IOMMU anyways, so it doesn't really need GFP_DMA32. I chose 4GB to be compatible with IA64 and because it seems to be the most common restriction. The new zone is so far added only for x86-64. For other architectures who don't set up this new zone nothing changes. Architectures can set a compatibility define in Kconfig CONFIG_DMA_IS_DMA32 that will define GFP_DMA32 as GFP_DMA. Otherwise it's a nop because on 32bit architectures it's normally not needed because GFP_NORMAL (=0) is DMA able enough. One problem is still that GFP_DMA means different things on different architectures. e.g. some drivers used to have #ifdef ia64 use GFP_DMA (trusting it to be 4GB) #elif __x86_64__ (use other hacks like the swiotlb because 16MB is not enough) ... . This was quite ugly and is now obsolete. These should be now converted to use GFP_DMA32 unconditionally. I haven't done this yet. Or best only use pci_alloc_consistent/dma_alloc_coherent which will use GFP_DMA32 transparently. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-06 00:25:53 +08:00
/* 16MB ISA DMA zone */
#define MAX_DMA_PFN ((16*1024*1024) >> PAGE_SHIFT)
/* 4GB broken PCI/AGP hardware bus master zone */
#define MAX_DMA32_PFN ((4UL*1024*1024*1024) >> PAGE_SHIFT)
/* Compat define for old dma zone */
#define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
/* 8237 DMA controllers */
#define IO_DMA1_BASE 0x00 /* 8 bit slave DMA, channels 0..3 */
#define IO_DMA2_BASE 0xC0 /* 16 bit master DMA, ch 4(=slave input)..7 */
/* DMA controller registers */
#define DMA1_CMD_REG 0x08 /* command register (w) */
#define DMA1_STAT_REG 0x08 /* status register (r) */
#define DMA1_REQ_REG 0x09 /* request register (w) */
#define DMA1_MASK_REG 0x0A /* single-channel mask (w) */
#define DMA1_MODE_REG 0x0B /* mode register (w) */
#define DMA1_CLEAR_FF_REG 0x0C /* clear pointer flip-flop (w) */
#define DMA1_TEMP_REG 0x0D /* Temporary Register (r) */
#define DMA1_RESET_REG 0x0D /* Master Clear (w) */
#define DMA1_CLR_MASK_REG 0x0E /* Clear Mask */
#define DMA1_MASK_ALL_REG 0x0F /* all-channels mask (w) */
#define DMA2_CMD_REG 0xD0 /* command register (w) */
#define DMA2_STAT_REG 0xD0 /* status register (r) */
#define DMA2_REQ_REG 0xD2 /* request register (w) */
#define DMA2_MASK_REG 0xD4 /* single-channel mask (w) */
#define DMA2_MODE_REG 0xD6 /* mode register (w) */
#define DMA2_CLEAR_FF_REG 0xD8 /* clear pointer flip-flop (w) */
#define DMA2_TEMP_REG 0xDA /* Temporary Register (r) */
#define DMA2_RESET_REG 0xDA /* Master Clear (w) */
#define DMA2_CLR_MASK_REG 0xDC /* Clear Mask */
#define DMA2_MASK_ALL_REG 0xDE /* all-channels mask (w) */
#define DMA_ADDR_0 0x00 /* DMA address registers */
#define DMA_ADDR_1 0x02
#define DMA_ADDR_2 0x04
#define DMA_ADDR_3 0x06
#define DMA_ADDR_4 0xC0
#define DMA_ADDR_5 0xC4
#define DMA_ADDR_6 0xC8
#define DMA_ADDR_7 0xCC
#define DMA_CNT_0 0x01 /* DMA count registers */
#define DMA_CNT_1 0x03
#define DMA_CNT_2 0x05
#define DMA_CNT_3 0x07
#define DMA_CNT_4 0xC2
#define DMA_CNT_5 0xC6
#define DMA_CNT_6 0xCA
#define DMA_CNT_7 0xCE
#define DMA_PAGE_0 0x87 /* DMA page registers */
#define DMA_PAGE_1 0x83
#define DMA_PAGE_2 0x81
#define DMA_PAGE_3 0x82
#define DMA_PAGE_5 0x8B
#define DMA_PAGE_6 0x89
#define DMA_PAGE_7 0x8A
#define DMA_MODE_READ 0x44 /* I/O to memory, no autoinit, increment, single mode */
#define DMA_MODE_WRITE 0x48 /* memory to I/O, no autoinit, increment, single mode */
#define DMA_MODE_CASCADE 0xC0 /* pass thru DREQ->HRQ, DACK<-HLDA only */
#define DMA_AUTOINIT 0x10
extern spinlock_t dma_spin_lock;
static __inline__ unsigned long claim_dma_lock(void)
{
unsigned long flags;
spin_lock_irqsave(&dma_spin_lock, flags);
return flags;
}
static __inline__ void release_dma_lock(unsigned long flags)
{
spin_unlock_irqrestore(&dma_spin_lock, flags);
}
/* enable/disable a specific DMA channel */
static __inline__ void enable_dma(unsigned int dmanr)
{
if (dmanr<=3)
dma_outb(dmanr, DMA1_MASK_REG);
else
dma_outb(dmanr & 3, DMA2_MASK_REG);
}
static __inline__ void disable_dma(unsigned int dmanr)
{
if (dmanr<=3)
dma_outb(dmanr | 4, DMA1_MASK_REG);
else
dma_outb((dmanr & 3) | 4, DMA2_MASK_REG);
}
/* Clear the 'DMA Pointer Flip Flop'.
* Write 0 for LSB/MSB, 1 for MSB/LSB access.
* Use this once to initialize the FF to a known state.
* After that, keep track of it. :-)
* --- In order to do that, the DMA routines below should ---
* --- only be used while holding the DMA lock ! ---
*/
static __inline__ void clear_dma_ff(unsigned int dmanr)
{
if (dmanr<=3)
dma_outb(0, DMA1_CLEAR_FF_REG);
else
dma_outb(0, DMA2_CLEAR_FF_REG);
}
/* set mode (above) for a specific DMA channel */
static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
{
if (dmanr<=3)
dma_outb(mode | dmanr, DMA1_MODE_REG);
else
dma_outb(mode | (dmanr&3), DMA2_MODE_REG);
}
/* Set only the page register bits of the transfer address.
* This is used for successive transfers when we know the contents of
* the lower 16 bits of the DMA current address register, but a 64k boundary
* may have been crossed.
*/
static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
{
switch(dmanr) {
case 0:
dma_outb(pagenr, DMA_PAGE_0);
break;
case 1:
dma_outb(pagenr, DMA_PAGE_1);
break;
case 2:
dma_outb(pagenr, DMA_PAGE_2);
break;
case 3:
dma_outb(pagenr, DMA_PAGE_3);
break;
case 5:
dma_outb(pagenr & 0xfe, DMA_PAGE_5);
break;
case 6:
dma_outb(pagenr & 0xfe, DMA_PAGE_6);
break;
case 7:
dma_outb(pagenr & 0xfe, DMA_PAGE_7);
break;
}
}
/* Set transfer address & page bits for specific DMA channel.
* Assumes dma flipflop is clear.
*/
static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
{
set_dma_page(dmanr, a>>16);
if (dmanr <= 3) {
dma_outb( a & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
dma_outb( (a>>8) & 0xff, ((dmanr&3)<<1) + IO_DMA1_BASE );
} else {
dma_outb( (a>>1) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
dma_outb( (a>>9) & 0xff, ((dmanr&3)<<2) + IO_DMA2_BASE );
}
}
/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
* a specific DMA channel.
* You must ensure the parameters are valid.
* NOTE: from a manual: "the number of transfers is one more
* than the initial word count"! This is taken into account.
* Assumes dma flip-flop is clear.
* NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
*/
static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
{
count--;
if (dmanr <= 3) {
dma_outb( count & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
dma_outb( (count>>8) & 0xff, ((dmanr&3)<<1) + 1 + IO_DMA1_BASE );
} else {
dma_outb( (count>>1) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
dma_outb( (count>>9) & 0xff, ((dmanr&3)<<2) + 2 + IO_DMA2_BASE );
}
}
/* Get DMA residue count. After a DMA transfer, this
* should return zero. Reading this while a DMA transfer is
* still in progress will return unpredictable results.
* If called before the channel has been used, it may return 1.
* Otherwise, it returns the number of _bytes_ left to transfer.
*
* Assumes DMA flip-flop is clear.
*/
static __inline__ int get_dma_residue(unsigned int dmanr)
{
unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
: ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
/* using short to get 16-bit wrap around */
unsigned short count;
count = 1 + dma_inb(io_port);
count += dma_inb(io_port) << 8;
return (dmanr<=3)? count : (count<<1);
}
/* These are in kernel/dma.c: */
extern int request_dma(unsigned int dmanr, const char * device_id); /* reserve a DMA channel */
extern void free_dma(unsigned int dmanr); /* release it again */
/* From PCI */
#ifdef CONFIG_PCI
extern int isa_dma_bridge_buggy;
#else
#define isa_dma_bridge_buggy (0)
#endif
#endif /* _ASM_DMA_H */