summaryrefslogtreecommitdiffstats
path: root/sys/amd64
Commit message (Expand)AuthorAgeFilesLines
* Change the cap_rights_t type from uint64_t to a structure that we can extendpjd2013-09-051-1/+4
* Tidy up some loose ends in the PCID code:kib2013-09-048-73/+98
* Add support for the 'invpcid' instruction to binutils and DDB'sjhb2013-09-031-1/+1
* Fix two build failures for non-tb configurations, UP [2] and when using gas [1].kib2013-08-312-7/+8
* The pm_save should be cleared on the pmap initialization, and not onkib2013-08-301-1/+1
* Implement support for the process-context identifiers ('PCID') onkib2013-08-3010-113/+527
* Provide a wrapper for the INVPCID instruction, definition of thekib2013-08-301-0/+20
* Implement vector callback for PVHVM and unify event channel implementationsgibbs2013-08-298-218/+79
* Significantly reduce the cost, i.e., run time, of calls to madvise(...,alc2013-08-291-0/+122
* Add support for emulating the byte move instruction "mov r/m8, r8".neel2013-08-271-2/+10
* Revert r254501. Instead, reuse the type stability of the struct pmapkib2013-08-221-6/+0
* Use the generation count of the pv list to work around LOR betweenkib2013-08-221-6/+37
* The PADLOCK_RNG and RDRAND_RNG kernel options are now devices.obrien2013-08-212-2/+4
* Reimplement atomic operations on PDEs and PTEs in pmap.h. This changejkim2013-08-211-35/+8
* Remove empty lines before return statements for style consistency.jkim2013-08-211-5/+0
* Implement atomic_swap() and atomic_testandset().jkim2013-08-211-15/+57
* - Remove the "a" constraint from main output operand for atomic_cmpset().jkim2013-08-211-10/+10
* Use '+' modifier for a memory operand that is both an input and an output.jkim2013-08-211-23/+16
* Remove bogus labels. No functional change.jkim2013-08-211-2/+0
* Use consistent style. No functional change.jkim2013-08-211-12/+12
* Do not create superpage mappings in the iommu.neel2013-08-201-1/+18
* Extract the location of the remapping hardware units from the ACPI DMAR table.neel2013-08-201-60/+54
* Fix breakage caused by r254466 in minidumpsys().neel2013-08-201-4/+8
* When code from r254064 in pmap_ts_referenced() drops pv lock andkib2013-08-181-0/+3
* Add process descriptors support to the GENERIC kernel. It is already beingpjd2013-08-181-0/+1
* Bump up the maximum addressable memory on amd64 systems from 1TB to 4TB.neel2013-08-173-24/+68
* libc: Access _logname_valid more efficiently.jilles2013-08-171-1/+0
* Use an ANSI C definition of initializecpucache() to match the declarationbrooks2013-08-151-1/+1
* Merge acpica_machdep.h for amd64 and i386 and move to x86. In fact, thesejkim2013-08-131-77/+3
* Tidy up global locks for ACPICA. There is no functional change.jkim2013-08-131-3/+3
* Different consumers of the struct vm_page abuse pageq member to keepkib2013-08-101-54/+58
* On all the architectures, avoid to preallocate the physical memoryattilio2013-08-091-4/+10
* The soft and hard busy mechanism rely on the vm object lock to work.attilio2013-08-091-12/+10
* follow up to r254051avg2013-08-091-2/+1
* Use local variables with the appropriate types and eliminate a bunch of casts.neel2013-08-081-31/+31
* Split the pagequeues per NUMA domains, and split pageademon processkib2013-08-071-0/+1
* Change the pmap_ts_referenced() method of amd64 pmap to use sharedkib2013-08-072-8/+55
* enable KDB_TRACE in GENERICsavg2013-08-071-1/+1
* Replace kernel virtual address space allocation with vmem. This providesjeff2013-08-074-12/+17
* - Introduce a specific function, pmap_remove_kernel_pde, for removingjeff2013-08-051-2/+39
* Follow-up commit to fix CR0 issues. Maintaingrehan2013-08-031-4/+38
* Moved clearing of vmm_initialized to avoid the casegrehan2013-08-011-1/+6
* Correctly maintain the CR0/CR4 shadow registers.grehan2013-08-011-11/+54
* Back out r253779 & r253786.obrien2013-07-311-1/+0
* Decouple yarrow from random(4) device.obrien2013-07-291-0/+1
* Revert r253748,253749avg2013-07-281-2/+1
* put contents of cpu.h under _KERNELavg2013-07-281-1/+2
* x86: detect mwait capabilities and extensions, when presentavg2013-07-283-0/+13
* - Use kmem_malloc rather than kmem_alloc() for GDT/LDT/tss allocations etc.jeff2013-07-261-4/+5
* Add support for emulation of the "or r/m, imm8" instruction.neel2013-07-231-3/+60
OpenPOWER on IntegriCloud