IO-mapping

Now, on normal PCs the bus address is exactly the same as the physicaladdress, and things are very simple indeed. However, they are that simplebecause the memory and the devices share the same address space, and that isnot generally necessarily true on other PCI/ISA setups.

    Now, just as an example, on the PReP (PowerPC Reference Platform), theCPU sees a memory map something like this (this is from memory):

       0-2 GB           "real memory"

       2 GB-3 GB     "system IO" (inb/out and similar accesses on x86)

       3 GB-4 GB     "IO memory" (shared memory over the IO bus)

Now, that looks simple enough. However, when you look at the same thing fromthe viewpoint of the devices, you have the reverse, and the physical memoryaddress 0 actually shows up as address 2 GB for any IO master.So when the CPU wants any bus master to write to physical memory 0, it has to give the master address 0x80000000 as the memory address.

So, for example, depending on how the kernel is actually mapped on the PPC, you can end up with a setup like this:

 physical address:  0

 virtual address:     0xC0000000

 bus address:         0x80000000

 

where all the addresses actually point to the same thing.  It's just seen through different translations..Similarly, on the Alpha, the normal translation is

 physical address:  0

 virtual address:     0xfffffc0000000000

 bus address:         0x40000000

(but there are also Alphas where the physical address and the bus address are the same).

Anyway, the way to look up all these translations, you do

       #include

       phys_addr = virt_to_phys(virt_addr);

       virt_addr = phys_to_virt(phys_addr);

        bus_addr = virt_to_bus(virt_addr);

       virt_addr = bus_to_virt(bus_addr);

 

Now, when do you need these?

there are actually _three_ different ways of lookingat memory addresses, and in this case we actually want the third, the so-called "bus address".

Essentially, the three ways of addressing memory are (this is "real memory",

that is, normal RAM--see later about other details):

 - CPU untranslated.  This is the "physical" address.  Physical address 0 is what the CPU sees when it drives zeroes on the memory bus.

 

 - CPU translated address. This is the "virtual" address, and is completely internal to the CPU itself with the CPU doing the appropriate translations into "CPU untranslated".

 

 - bus address. This is the address of memory as seen by OTHER devices,    not the CPU. Now, in theory there could be many different bus addresses, with each device seeing memory in some device-specific way, but happily most hardware designers aren't actually actively trying to make    things any more complex than necessary, so you can assume that all external hardware sees the memory the same way.

You want the _virtual_ address when you are actually going to access that pointer from the kernel. So you can have something like this:

       /*

        * this is the hardware "mailbox" we use to communicate with

        * the controller. The controller sees this directly.

        */

       struct mailbox {

              __u32 status;

              __u32 bufstart;

              __u32 buflen;

              ..

       } mbox;

 

              unsigned char * retbuffer;

 

              /* get the address from the controller */

              retbuffer = bus_to_virt(mbox.bufstart);

              switch (retbuffer[0]) {

                     case STATUS_OK:

                            ...

on the other hand, you want the bus address when you have a buffer that you want to give to the controller:

       /* ask the controller to read the sense status into "sense_buffer" */

       mbox.bufstart = virt_to_bus(&sense_buffer);

       mbox.buflen = sizeof(sense_buffer);

       mbox.status = 0;

       notify_controller(&mbox);

And you generally _never_ want to use the physical address, because you can't use that from the CPU (the CPU only uses translated virtual addresses), and you can't use it from the bus master.

 

So why do we care about the physical address at all? We do need the physical address in some cases, it's just not very often in normal code.  The physical address is needed if you use memory mappings, for example, because the "remap_page_range()" mm function wants the physical address of the memory to be remapped.

 

This memory is called "PCI memory" or "shared memory" or "IO memory" or whatever, and there is only one way to access it: the readb/writeb and related functions. You should never take the address of such memory, because there is really nothing you can do with such an address: it's not conceptually in the same memory space as "real memory" at all, so you cannot just dereference a pointer.