| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | - There's no need to overwrite the default device method with the default | marius | 2011-11-22 | 1 | -4/+4 |
| * | Use a global __pure2 function instead of a global register variable for | nwhitehorn | 2011-11-17 | 2 | -2/+12 |
| * | Add an extra invariant here which was useful on 64-bit CPUs. | nwhitehorn | 2011-11-17 | 1 | -0/+2 |
| * | Refactor the code that performs physically contiguous memory allocation, | alc | 2011-11-16 | 1 | -7/+9 |
| * | Fix a bug where the pmap_cpu_bootstrap() ap argument could be clobbered. | nwhitehorn | 2011-11-09 | 2 | -2/+4 |
| * | Inline the syscallenter() and syscallret(). This reduces the time measured | kib | 2011-09-11 | 1 | -0/+2 |
| * | Split the vm_page flags PG_WRITEABLE and PG_REFERENCED into atomic | kib | 2011-09-06 | 2 | -26/+26 |
| * | - Move the PG_UNMANAGED flag from m->flags to m->oflags, renaming the flag | kib | 2011-08-09 | 2 | -39/+29 |
| * | This a follow up commit from r224216 for powerpc 32-bit. Increase | andreast | 2011-07-25 | 1 | -2/+2 |
| * | On 64 bit architectures size_t is 8 bytes, thus it should use an 8 bytes | attilio | 2011-07-19 | 1 | -2/+2 |
| * | - Remove the eintrcnt/eintrnames usage and introduce the concept of | attilio | 2011-07-18 | 2 | -4/+10 |
| * | With retirement of cpumask_t and usage of cpuset_t for representing a | attilio | 2011-07-04 | 2 | -12/+4 |
| * | Revert r223479. It is unnecessary and served only to slightly ameliorate | nwhitehorn | 2011-06-26 | 2 | -4/+0 |
| * | Use the ABI-mandated thread pointer register (r2 for ppc32, r13 for ppc64) | nwhitehorn | 2011-06-23 | 10 | -49/+54 |
| * | Clear any outstanding atomic reservations when traps are taken. This fixes | nwhitehorn | 2011-06-23 | 2 | -0/+4 |
| * | Fix merge typo. | andreast | 2011-06-23 | 1 | -1/+1 |
| * | MFC | attilio | 2011-06-04 | 1 | -2/+2 |
| |\ |
|
| | * | Fix a typo derived from a mismerge from mmu_oea that would cause | nwhitehorn | 2011-06-04 | 1 | -2/+2 |
| * | | MFC | attilio | 2011-06-03 | 11 | -309/+68 |
| |\ \
| |/ |
|
| | * | Quantities stored on the stack on ppc64 tend to be twice as large as on | nwhitehorn | 2011-06-03 | 1 | -1/+1 |
| | * | The POWER7 has only 32 SLB slots instead of 64, like other supported | nwhitehorn | 2011-06-02 | 3 | -43/+51 |
| | * | If running under a hypervisor, don't yell at the user about starting | nwhitehorn | 2011-06-02 | 1 | -1/+4 |
| | * | Explicitly initialize the first thread's MSR to PSL_KERNSET. | nwhitehorn | 2011-06-02 | 1 | -1/+1 |
| | * | Include the modules area in the mapped kernel code. This fixes the kernel's | nwhitehorn | 2011-06-02 | 1 | -3/+2 |
| | * | Remove some dead code: unnecessary isyncs and memory sorting, which are | nwhitehorn | 2011-06-02 | 4 | -47/+9 |
| | * | MFpseries: | nwhitehorn | 2011-06-02 | 3 | -213/+0 |
| * | | MFC | attilio | 2011-05-26 | 1 | -0/+1 |
| |\ \
| |/ |
|
| | * | Add a missing isync. | nwhitehorn | 2011-05-26 | 1 | -0/+1 |
| | * | Remove a useless check that served only to make 64-bit PPC systems | nwhitehorn | 2011-05-16 | 1 | -5/+0 |
| * | | MFC | attilio | 2011-05-16 | 1 | -5/+0 |
| * | | Add the powerpc support. | attilio | 2011-05-09 | 2 | -6/+20 |
| |/ |
|
| * | Add leading zeros when printing the physical memory chunks on __powerpc64__. | andreast | 2011-04-19 | 1 | -1/+1 |
| * | Adjust debugging string to match the actual function. | andreast | 2011-04-14 | 1 | -1/+1 |
| * | The macro MOEA_PVO_CHECK is empty and not used. It is a left over from the | andreast | 2011-04-14 | 2 | -24/+0 |
| * | Mostly revert r219468, as I had misremembered the C standard regarding | mdf | 2011-03-11 | 1 | -1/+1 |
| * | Use MAXPATHLEN rather than the size of an extern array when copying the | mdf | 2011-03-10 | 1 | -1/+1 |
| * | Turn off default generation of userland dot symbols on powerpc64 now that | nwhitehorn | 2011-02-18 | 3 | -18/+18 |
| * | Add macro to test the sv_flags of any process. Change some places to test | dchagin | 2011-01-26 | 1 | -3/+3 |
| * | Make MSGBUF_SIZE kernel option a loader tunable kern.msgbufsize. | pluknet | 2011-01-21 | 3 | -6/+5 |
| * | For architectures not using direct map , and requiring real KVA page for | kib | 2011-01-18 | 1 | -1/+1 |
| * | Remove unused variables. Spotted by a cppcheck | andreast | 2011-01-15 | 1 | -10/+1 |
| * | Fix handling of NX pages on capable CPUs. Thanks to kib for prodding me | nwhitehorn | 2011-01-13 | 2 | -11/+9 |
| * | Remove unused variables. Spotted by a cppcheck | andreast | 2011-01-06 | 2 | -6/+0 |
| * | Only keep track of PTE validity statistics for pages not locked in the | nwhitehorn | 2010-12-28 | 1 | -2/+8 |
| * | Garbage-collect unused variable. | nwhitehorn | 2010-12-19 | 2 | -9/+4 |
| * | Add some isync()s related to the 64-bit MMU scratch page to avoid race | nwhitehorn | 2010-12-11 | 2 | -0/+4 |
| * | Add an abstraction layer to the 64-bit AIM MMU's page table manipulation | nwhitehorn | 2010-12-04 | 5 | -644/+983 |
| * | After some off-list discussion, revert a number of changes to the | dim | 2010-11-22 | 1 | -1/+1 |
| * | Apply the STATIC_VNET_DEFINE and STATIC_DPCPU_DEFINE macros throughout | dim | 2010-11-14 | 1 | -1/+1 |
| * | Partially revert r215182. There appears to be a silicon bug on the 970 | nwhitehorn | 2010-11-12 | 1 | -4/+4 |
