Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Fix vmalloc for mips64. | Ralf Baechle | 2001-05-23 | 1 | -0/+7 |
| | |||||
* | Merge with Linux 2.4.3. | Ralf Baechle | 2001-04-05 | 1 | -15/+16 |
| | | | | | | | Note that mingetty does no longer work with serial console, you have to switch to another getty like getty_ps. This commit also includes a fix for a setitimer bug which did prevent getty_ps from working on older kernels. | ||||
* | Lots of cleanup from Keith with additional tweaks by me. More to | Ralf Baechle | 2001-03-18 | 1 | -5/+15 |
| | | | | come. Stay frightened :-) | ||||
* | On mips64 get_context / set_context operate on 64-bit, not 32-bit values. | Ralf Baechle | 2001-02-10 | 1 | -2/+2 |
| | |||||
* | Use the same definition of flush_icache_page() that is used in stock | Kanoj Sarcar | 2000-11-29 | 1 | -4/+4 |
| | | | | Linux 2.4. | ||||
* | Merge with 2.4.0-test11. | Ralf Baechle | 2000-11-28 | 1 | -3/+0 |
| | |||||
* | Merge with Linux 2.4.0-test10. | Ralf Baechle | 2000-11-23 | 1 | -0/+2 |
| | |||||
* | Add access function for the cp0 info register. | Ralf Baechle | 2000-09-23 | 1 | -0/+13 |
| | |||||
* | Delete usage of PG_skip flag from mips64-DISCONTIG code. It was only | Kanoj Sarcar | 2000-09-07 | 1 | -1/+1 |
| | | | | | | | being used to flag mem_map entries corresponding to holes for counting and reporting during boot time. The current code reports more accurate figures, based on what is found at szmem() time (the old code was reporting more total memory than szmem() had probed). | ||||
* | Fix CONFIG_DISCONTIGMEM. | Ralf Baechle | 2000-08-09 | 1 | -1/+1 |
| | |||||
* | Merge with Linux 2.4.0-test6-pre8. | Ralf Baechle | 2000-08-08 | 1 | -4/+4 |
| | |||||
* | Merge with Linu 2.4.0-test6-pre6. | Ralf Baechle | 2000-08-08 | 1 | -1/+2 |
| | |||||
* | Delete unused definition of pte_page. | Kanoj Sarcar | 2000-08-04 | 1 | -5/+0 |
| | |||||
* | Shave of 50% of lat_mmap. Our cache routines were plain stupid. | Ralf Baechle | 2000-07-31 | 1 | -4/+4 |
| | |||||
* | Optimized cache flushing on r10k/o200s, assuming processor handles | Kanoj Sarcar | 2000-07-27 | 1 | -0/+24 |
| | | | | | VCEs in hardwire, and system guarantees io coherency. Only need to do cache flushes for icache coherency. | ||||
* | Name change: the generic call flush_cache_all() does not do anything | Kanoj Sarcar | 2000-07-24 | 1 | -3/+4 |
| | | | | | anymore. All the flush_cache_all() calls in MIPS code is changed to call flush_cache_l1(), and ends up flushing the L1 i/d caches. | ||||
* | Introduce a new cpu specific routine to flush the L2 cache. This helps | Kanoj Sarcar | 2000-07-24 | 1 | -2/+10 |
| | | | | | | the stability of DISCONTIGMEM kernels. The L2 flushing is needed during bootup. With this, the initialization hacks of scanning the node memories at boot up time is not needed any more. | ||||
* | Fix VMALLOC_END so that all the translations can be held in the pair | Kanoj Sarcar | 2000-07-06 | 1 | -1/+1 |
| | | | | of page tables that manage the vmalloc space. | ||||
* | Vmalloc/vfree fixes: use swapper_pg_dir[0] for the vmalloc range | Kanoj Sarcar | 2000-07-06 | 1 | -1/+6 |
| | | | | | | translations, use a kernel pmd table that points into the kptbl[]. This is to make the generic part of vmalloc()/vfree() find pgd/pmd/pte that it expects. | ||||
* | Make flush_icache_page() nicer. | Ulf Carlsson | 2000-07-05 | 1 | -1/+6 |
| | |||||
* | flush_icache_page takes struct page * as argument as opposed to | Ulf Carlsson | 2000-07-04 | 1 | -1/+1 |
| | | | | flush_cache_page that still takes unsigned long. | ||||
* | Implement a functional vmalloc(). THe vmalloc range address translations | Kanoj Sarcar | 2000-06-30 | 1 | -1/+3 |
| | | | | | | | | are stashed in an array of page tables, starting from kptbl[]. The fast tlbmiss handler quickly checks to see if the faulting address is in the vmalloc range, and if so, it uses the translations in the kptbl to update the tlbs. Still to do: tlb invalid faults in the vmalloc range needs to be handled properly. | ||||
* | Explain pgd/pmd allocation failure strategies. Create a global bad-pmd-table, | Kanoj Sarcar | 2000-06-27 | 1 | -16/+9 |
| | | | | | | | distinct from invalid-pmd-table for use during pmd allocation failure (so as to differentiate pgd_bad and pgd_none). The bad page table must have invalid pte entries to catch any user references to the range of virtual addresses it covers. | ||||
* | Delete pmd_present/pgd_present. Explain pgd/pmd/pte allocation and | Kanoj Sarcar | 2000-06-26 | 1 | -7/+11 |
| | | | | | initialization. Make sure to allocate only one page for the page table (prevent memory leaks), since only one page is freed up. | ||||
* | R3000 cache handling. flush_icache_page now actually flushes | Ralf Baechle | 2000-06-20 | 1 | -5/+4 |
| | | | | something. | ||||
* | Misc mm type bug fixes. | Kanoj Sarcar | 2000-03-16 | 1 | -1/+1 |
| | |||||
* | Move from using cacheable noncoherent mappings to cacheable coherent | Kanoj Sarcar | 2000-03-13 | 1 | -5/+5 |
| | | | | | exclusive on write mappings. This is needed for SMP anyway, and seems to prevent the random data bus errors that we have been seeing. | ||||
* | Merge with Linux 2.3.49. | Ralf Baechle | 2000-03-07 | 1 | -1/+2 |
| | |||||
* | Merge with 2.3.48. | Ralf Baechle | 2000-03-02 | 1 | -1/+2 |
| | |||||
* | Changes to make DISCONTIGMEM compile and boot after the upgrades, as | Kanoj Sarcar | 2000-02-27 | 1 | -2/+2 |
| | | | | | well as substitution of some platform specific fields by their new generic counterparts. | ||||
* | Merge with 2.3.47. Guys, this is buggy as shit. You've been warned. | Ralf Baechle | 2000-02-24 | 1 | -6/+38 |
| | |||||
* | Merge with 2.3.43. I did ignore all modifications to the qlogicisp.c | Ralf Baechle | 2000-02-23 | 1 | -1/+6 |
| | | | | driver due to the Origin A64 hacks. | ||||
* | Clean up the discontig case page -> physaddr and physaddr -> page macros. | Kanoj Sarcar | 2000-02-10 | 1 | -7/+9 |
| | | | | Probably needs to be debugged once we achieve single user. | ||||
* | Okay, we can now touch remote node memory, setup bootmem data structures | Kanoj Sarcar | 2000-02-10 | 1 | -1/+1 |
| | | | | per node and allocate per node mem_maps. | ||||
* | Add in code for a CONFIG_DISCONTIGMEM compile. Still to be debugged. | Kanoj Sarcar | 2000-02-06 | 1 | -1/+16 |
| | |||||
* | Merge with Linux 2.3.32. | Ralf Baechle | 2000-02-04 | 1 | -241/+13 |
| | |||||
* | Merge with 2.3.27. | Ralf Baechle | 2000-01-29 | 1 | -15/+6 |
| | |||||
* | Merge with Linux 2.3.23. The new bootmem stuff has broken various | Ralf Baechle | 2000-01-27 | 1 | -8/+35 |
| | | | | | platforms. At this time I've only verified that IP22 support compiles and IP27 actually works. | ||||
* | - IOC3 driver now will panic when encountering a RX/TX PCI DMA error. | Ralf Baechle | 2000-01-17 | 1 | -4/+2 |
| | | | | | | | | | - IOC3 driver does no longer use GFP_DMA which given the _very_ small number of available GFP_DMA pages might have deadlocked the system. - First cut of Origin support. Last minute change: Do no longer use ARC memory / MD hub memory configuration information but klconfig.h stuff. Simpler, faster, shorter. - Zillions of MIPS64 fixes. | ||||
* | Merge with Linux 2.3.21. | Ralf Baechle | 1999-12-04 | 1 | -118/+153 |
| | |||||
* | Merge with 2.3.19. | Ralf Baechle | 1999-10-09 | 1 | -3/+0 |
| | |||||
* | MIPS 64, day 2. | Ralf Baechle | 1999-08-19 | 1 | -0/+859 |