Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2020-03-16 | Fix CPI calcualtion for -s option (#192) | davidmetz | 1 | -1/+1 | |
This attempt at rounding leads to wrong results, for example: 314689951 cycles 314690101 instructions 0.90 CPI With my change results in: 314689951 cycles 314690101 instructions 0.99 CPI I think this was supposed to be part of rounding behaviour but it doesn't work if only the final digit does it and there is no carry... Instead I changed it to truncate after the second digit | |||||
2020-01-13 | Enable vector unit if present (continuation of ↵ | Andrew Waterman | 1 | -1/+1 | |
77a5df569451571d608650a34183d53df99790ec) | |||||
2019-10-23 | Add --help (#179) | Luís Marques | 1 | -14/+35 | |
2019-10-22 | Implement dup3 syscall (#162) | Luís Marques | 4 | -0/+32 | |
2019-10-22 | Make performance counters always 64 bits wide (#178) | Luís Marques | 4 | -18/+77 | |
This prevents the counters from easily overflowing for a 32-bit pk. | |||||
2019-10-01 | Only accept statically linked binaries (#176) | Luís Marques | 2 | -0/+4 | |
2019-06-11 | configure: Add option to set physical memory start address | Gabriel L. Somlo | 1 | -1/+1 | |
For systems where physical memory is mapped to a start address different from 0x80000000, allow the default to be overridden using the --with-mem-start argument to the configure script. Signed-off-by: Gabriel Somlo <gsomlo@gmail.com> | |||||
2019-05-09 | Allow up to 2 KiB of arguments | Andrew Waterman | 1 | -1/+4 | |
Closes #161 | |||||
2019-03-24 | Fix build with newer newlib | Andrew Waterman | 2 | -2/+3 | |
2019-02-28 | Stub out madvise syscall (#145) | Luís Marques | 2 | -0/+2 | |
2019-01-04 | Implement clock_gettime syscall (#139) | Luís Marques | 1 | -1/+10 | |
2019-01-04 | Page-align the writable data section | Andrew Waterman | 1 | -1/+2 | |
For eventual PMP purposes | |||||
2019-01-04 | Clean up linker scripts a bit | Andrew Waterman | 1 | -4/+1 | |
2018-08-06 | Add some exception handling functions to s-mode to handle exception return ↵ | wxjstz | 1 | -0/+28 | |
from m-mode. (#117) | |||||
2018-07-09 | Properly license all nontrivial files | Andrew Waterman | 7 | -0/+14 | |
2018-04-24 | Enable FPU in PK, regardless of FPU presence | Andrew Waterman | 1 | -1/+1 | |
Otherwise, the emulation code will refuse to emulate FP instructions. | |||||
2018-02-01 | Bump the Linux version PK claims to support | Andrew Waterman | 1 | -1/+1 | |
This makes it more compatible with recent glibc. | |||||
2017-12-12 | Bump encoding.h | Andrew Waterman | 1 | -1/+1 | |
2017-11-03 | Remove the platform interface | Palmer Dabbelt | 2 | -1/+1 | |
We now automatically detect everything that the platform interface used to be used for, so it's now obsolete! | |||||
2017-11-02 | Detect harts that can't boot Linux instead of hard-coding them | Palmer Dabbelt | 1 | -0/+1 | |
This checks to see if a hart can't boot Linux by looking for a compatible "mmu-type" field. If the hart can't boot Linux, then bbl masks it off. | |||||
2017-10-19 | Order __page_alloc before writing vmrs | Andrew Waterman | 1 | -2/+6 | |
2017-08-29 | Stub out sys_prlimit64 | Andrew Waterman | 2 | -0/+2 | |
2017-08-02 | Add a platform interface | Palmer Dabbelt | 1 | -0/+1 | |
SiFive's pk fork is the second one I've had to maintain, and it's a huge pain because people keep just leaving changes all over the tree. I want to introduce an interface that the platform-specific details can live behind so I don't have to keep doing these painful merges. | |||||
2017-04-18 | Increase PK stack size to 3% of memory, up to 8 MiB | Andrew Waterman | 1 | -1/+1 | |
2017-03-27 | Separate page faults from physical memory access exceptions | Andrew Waterman | 1 | -3/+3 | |
2017-03-23 | pk: does not use dtb | Wesley W. Terpstra | 1 | -1/+1 | |
2017-03-22 | SBI: a0+a1 hold hartid+dtb pointer between boot loader stagesfdt | Wesley W. Terpstra | 1 | -3/+3 | |
2017-03-21 | Allow PK access to user memory | Andrew Waterman | 1 | -0/+1 | |
2017-02-22 | Fix PK boot | Andrew Waterman | 1 | -3/+6 | |
2017-02-20 | Don't block for acks on console writes | Andrew Waterman | 3 | -8/+9 | |
2017-02-17 | WIP towards ECALL interface for SBI | Andrew Waterman | 2 | -2/+1 | |
2017-02-15 | Cleanly separate HTIF code; don't poll keyboard on timer interrupt | Andrew Waterman | 1 | -2/+2 | |
2016-12-06 | avoid non-standard predefined macros | Andrew Waterman | 4 | -4/+4 | |
2016-11-13 | Add ability to hard-code an initial environment | Andrew Waterman | 1 | -2/+18 | |
2016-11-13 | For RV32, mmap offset is in 4 KiB increments | Andrew Waterman | 1 | -2/+6 | |
2016-11-13 | Cap pk memory size to 2 GiB for RV32 | Andrew Waterman | 1 | -0/+5 | |
2016-11-13 | Fix ld.so load address at 4 KiB | Andrew Waterman | 1 | -6/+10 | |
2016-11-13 | Add syscall stubs to get through libpthread initializers | Andrew Waterman | 2 | -0/+4 | |
2016-11-02 | Acquire write permissions before zeroing page in ELF loader | Andrew Waterman | 2 | -2/+6 | |
f81b722bf004177eadaf6f1b4b9e699e20257521 is a regression. If a read-only segment does not begin on a page boundary, it would cause the ELF loader to blow up. | |||||
2016-09-21 | make sure pages for ELF sections have correct protection (#40) | Howard Mao | 2 | -2/+20 | |
2016-09-09 | Add -p flag to pk to disable demand paging | Andrew Waterman | 3 | -3/+7 | |
2016-08-16 | add htif section in linker script, with ALIGNs to prevent MMIO and data from ↵ | Sagar Karandikar | 1 | -0/+10 | |
being placed on same page (#32) | |||||
2016-08-10 | when -s is passed, print time, instret, cycle, and CPI | Andrew Waterman | 3 | -6/+19 | |
2016-08-09 | Disallow execution of RVC binaries on non-RVC pk | Andrew Waterman | 2 | -0/+6 | |
2016-07-29 | Align pk trap_entry for RVC | Andrew Waterman | 1 | -0/+1 | |
2016-07-12 | zero-extend RV32 physical addresses for HTIF | Andrew Waterman | 2 | -2/+2 | |
2016-07-12 | Remove uarch counters | Andrew Waterman | 4 | -51/+0 | |
We'll re-add support for the generic performance counter facility once it exists. | |||||
2016-07-06 | Udpate to new PTE format | Andrew Waterman | 1 | -27/+11 | |
2016-04-30 | Move DRAM to high addresses | Andrew Waterman | 6 | -41/+40 | |
2016-04-20 | pk: proxy chdir syscall to fesvr | Garret Kelly | 1 | -0/+6 | |