Commit message (Collapse) | Author | Age | Files | Lines | ||
---|---|---|---|---|---|---|
... | ||||||
* | no real solution for the offset.h-chicken-egg-problem, but this does all I wnat | Harald Koerfgen | 2000-05-24 | 1 | -0/+0 | |
| | ||||||
* | Housekeeping | Harald Koerfgen | 2000-05-23 | 2 | -99/+1 | |
| | ||||||
* | Update defconfig files. | Ralf Baechle | 2000-05-23 | 1 | -0/+47 | |
| | ||||||
* | Implement a more dynamic method of associating IRQs with PCI devices. | Kanoj Sarcar | 2000-05-19 | 1 | -2/+1 | |
| | | | | | Instead of encoding bus/slot numbers in the IRQ, have seperate arrays to store that information. | |||||
* | irq.h: With the current scheme of encoding the bus number into the | Kanoj Sarcar | 2000-05-18 | 2 | -5/+5 | |
| | | | | | | | pci irq, we need to bump up NR_IRQs to handle more than 4 PCI busses. io.h: Port numbers are really "unsigned long", since they need to contain the nasids too. ip27-pci.c: Encode the nasid into the port number for isp1020 for pio. | |||||
* | Some cleaning of the support for machines with HZ other than a | Ralf Baechle | 2000-05-16 | 1 | -0/+2 | |
| | | | | | architecture specific standard value. Not entirely at the point where we can send this to Linus. | |||||
* | Fix SOCK_ constant definitions for all architectures. Patch sent to | Ralf Baechle | 2000-05-16 | 1 | -15/+14 | |
| | | | | | Linus. Our diffs relativ to Linus' latest and greatest is getting fairly small now. | |||||
* | Remove references to dead flag ASYNC_IOC3. | Ralf Baechle | 2000-05-16 | 1 | -1/+1 | |
| | ||||||
* | Move the intercpu intr irq numbers to the lowest possible. Assign | Kanoj Sarcar | 2000-05-15 | 1 | -8/+5 | |
| | | | | | | | all PCI irqs above that. Fix pci_map_irq to not just have 2 bits for slot number, else irq numbers will not be unique. Include the bus number as part of the irq for now, so that scsi controllers on various PCI busses get unique irq numbers. | |||||
* | Fix copyright message. Linus flamed me on these messages so please | Ralf Baechle | 2000-05-15 | 3 | -48/+31 | |
| | | | | | make sure for the future that the (C) notice is ok. ``unpublished proprietary information of Silicon Graphics'' isn't good ... | |||||
* | Merge with Linux 2.3.99-pre7 and various other bits. | Ralf Baechle | 2000-05-12 | 4 | -1/+6 | |
| | ||||||
* | Rudimentary nmi support to be able to do simple debugging on SMP | Kanoj Sarcar | 2000-05-12 | 1 | -0/+131 | |
| | | | | machines. | |||||
* | SMP FPU management: similar to what sparc does, no lazy fpu context | Kanoj Sarcar | 2000-05-11 | 2 | -0/+25 | |
| | | | | | | switching in SMP mode, use PF_USEDFPU to determine whether a program used the fpu in the last time quantum and so needs the fpu context to be saved during context switch. | |||||
* | Some infrastructure for supporting multiple pci busses on origin200/2000. | Leo Dagum | 2000-05-11 | 3 | -2/+14 | |
| | | | | | | | nasid and widget id get incoded in pci_dev->irq. pcibr_setup() now does some rudimentary probing for bridge widgets hanging off its xbow. We're not seeing interrupts from remote devices at the cpu, so mscsi card's are turned off for now. | |||||
* | Fix the way we use the watchlo/watchhi registers to get to the task | Kanoj Sarcar | 2000-05-04 | 1 | -1/+3 | |
| | | | | | struct of the currently executing thread: handle sign extension on the watchlo register. | |||||
* | Fix NUMA compile problem. | Kanoj Sarcar | 2000-05-03 | 1 | -2/+0 | |
| | ||||||
* | Merge with 2.3.99-pre6. | Ralf Baechle | 2000-04-28 | 1 | -2/+2 | |
| | ||||||
* | sigprocmask needs to be 32-bitized. | Kanoj Sarcar | 2000-04-27 | 1 | -0/+1 | |
| | ||||||
* | We use the ST0_CU0 bit to determine whether we are coming into | Kanoj Sarcar | 2000-04-25 | 2 | -17/+14 | |
| | | | | | | | | | | kernel mode for the first time from user mode (on intr/exception/ syscall etc). If so, we need to set the sp to point to the kernel stack. On UP kernels, the kernel stack pointer is stored in the global variable "kernelsp". For SMP kernel, the physical address of the current task structure is stuffed into the watchlo/watchhi registers, so on first entry into the kernel, we need to munge this value properly to setup the sp register. | |||||
* | Fix the init_new_context code not to zap the percpu tlbpid array when | Kanoj Sarcar | 2000-04-24 | 1 | -19/+12 | |
| | | | | | | doing a clone-vm operation. Also, the intercpu tlbflush code now properly does its job by flushing the tlbpid only on the current processor, and not on all. | |||||
* | Change all instances of __SMP__ to CONFIG_SMP and include | Ralf Baechle | 2000-04-23 | 7 | -11/+21 | |
| | | | | <linux/config.h> where necessary. | |||||
* | First cut at intercpu tlb flushing. | Kanoj Sarcar | 2000-04-22 | 2 | -1/+15 | |
| | ||||||
* | Per cpu tlbpid (asid) management for SMP. The asid cache is now per | Kanoj Sarcar | 2000-04-22 | 2 | -11/+46 | |
| | | | | cpu, and stays in cpu_data[]. | |||||
* | Delete unused junk "current_pgd". | Kanoj Sarcar | 2000-04-21 | 1 | -3/+0 | |
| | ||||||
* | Removing until needed ... | Pat Gefre | 2000-04-21 | 6 | -259/+3 | |
| | ||||||
* | Removing until needed ..... | Pat Gefre | 2000-04-21 | 28 | -17020/+0 | |
| | ||||||
* | Merge with Linux 2.3.99-pre4. | Ralf Baechle | 2000-04-19 | 1 | -2/+1 | |
| | ||||||
* | Pause fix for mips64. | Ralf Baechle | 2000-04-19 | 1 | -2/+2 | |
| | ||||||
* | Intercpu interrupt changes: add in dedicated intr levels for reschedule | Kanoj Sarcar | 2000-04-17 | 1 | -2/+6 | |
| | | | | and call function interrupts (tlbflush for later). | |||||
* | More intercpu interrupt work: we now have a low level inter cpu intr | Kanoj Sarcar | 2000-04-17 | 1 | -3/+3 | |
| | | | | handler. | |||||
* | The state of the two interrupt mask registers for the 128 intr levels | Kanoj Sarcar | 2000-04-12 | 1 | -0/+2 | |
| | | | | for each cpu in the hub is now stored in the per processor data area. | |||||
* | Starting to merge in the SN1 (IP35) I/O changes | Pat Gefre | 2000-04-11 | 7 | -66/+495 | |
| | ||||||
* | Fixed endianness for inb/outb functions. | Leo Dagum | 2000-04-10 | 1 | -18/+18 | |
| | ||||||
* | Include files for ip35/ip37 I/O | Pat Gefre | 2000-04-10 | 24 | -0/+15963 | |
| | ||||||
* | *** empty log message *** | Pat Gefre | 2000-04-10 | 4 | -0/+1057 | |
| | ||||||
* | New code to install and enable interrupt handlers for intercpu intrs. | Kanoj Sarcar | 2000-04-08 | 1 | -0/+2 | |
| | ||||||
* | Fix this UP/MP microoptimization business with cpu_data[] and | Kanoj Sarcar | 2000-04-08 | 1 | -6/+4 | |
| | | | | | boot_cpu_data once and for all. Generic mips64/IP27 code wants to do cpu_data[cpuid] everywhere ... | |||||
* | Clear the TS bit from the master's status register (don't know why | Kanoj Sarcar | 2000-04-07 | 1 | -0/+1 | |
| | | | | | | | | PROM is getting the bit set before entry into kernel). Fix per cpu frequency reporting. Fix bug so that we do not clear information about mips4 availability. Have the slaves flush their cache/tlb and set status based on what the master processor did. | |||||
* | Initial attempt at seperating out per-cpu and per-hub code that needs to | Kanoj Sarcar | 2000-04-07 | 2 | -0/+5 | |
| | | | | be executed in a multicpu, multinode environment. | |||||
* | Minor cleanup to get rid of annoying compile time warning. | Leo Dagum | 2000-04-07 | 1 | -6/+6 | |
| | ||||||
* | Added a few klconfig functions from IRIX. This triggered some house cleaning, | Kanoj Sarcar | 2000-04-04 | 3 | -1/+16 | |
| | | | | | ie, moving type declarations into sn/types.h and moving klconfig code from ip27-init.c into ip27-klconfig.c. | |||||
* | Rudimentary code to launch slave processors by the master processor. | Kanoj Sarcar | 2000-04-04 | 2 | -0/+154 | |
| | | | | Completely untested, never executed ... | |||||
* | Rudimentary sendintr() routine to send intrs to other cpus. This needs to | Kanoj Sarcar | 2000-04-01 | 4 | -3/+199 | |
| | | | | | | pull in defines from intr.h/intr_public.h. Also, need to store percpu information regarding cpu slice # for cpu, hardware nasid and compact node id. | |||||
* | Fix the ext2 bitop routines to enable root disk bootups. | Kanoj Sarcar | 2000-03-31 | 1 | -4/+4 | |
| | ||||||
* | spin_trylock acts on a word memory pointer, and can not use test_and_set_bit | Kanoj Sarcar | 2000-03-31 | 1 | -1/+18 | |
| | | | | | which works on a double-word memory pointer. Wrong results ensue otherwise due to in memory format of data (aka endianness). | |||||
* | Put an instruction in the branch delay slot of the read_unlock() | Kanoj Sarcar | 2000-03-31 | 1 | -0/+1 | |
| | | | | | block which is compiled .noreorder, to prevent the assembler from putting something destructive. | |||||
* | Added QLOGICFC_SLOT5 definition to Origin 'hacks' section at bottom. | Leo Dagum | 2000-03-30 | 1 | -0/+1 | |
| | ||||||
* | Set ST0_FR the right way. | Ralf Baechle | 2000-03-28 | 1 | -6/+12 | |
| | ||||||
* | Merge with Linux 2.3.99-pre3. | Ralf Baechle | 2000-03-27 | 1 | -3/+5 | |
| | ||||||
* | ip27-irq.c, system.h: implement SMP intr on/off primitives similar to i386. | Kanoj Sarcar | 2000-03-26 | 1 | -6/+19 | |
| | | | | | process.c, smp.c: minor initialization code. SMP compiles still hang at the scsi probing stage, no improvements. |