- 07 Apr, 2017 9 commits
-
-
Paolo Bonzini authored
Now use bit 6 of EPTP to optionally enable A/D bits for EPTP. Another thing to change is that, when EPT accessed and dirty bits are not in use, VMX treats accesses to guest paging structures as data reads. When they are in use (bit 6 of EPTP is set), they are treated as writes and the corresponding EPT dirty bit is set. The MMU didn't know this detail, so this patch adds it. We also have to fix up the exit qualification. It may be wrong because KVM sets bit 6 but the guest might not. L1 emulates EPT A/D bits using write permissions, so in principle it may be possible for EPT A/D bits to be used by L1 even though not available in hardware. The problem is that guest page-table walks will be treated as reads rather than writes, so they would not cause an EPT violation. Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com> [Fixed typo in walk_addr_generic() comment and changed bit clear + conditional-set pattern in handle_ept_violation() to conditional-clear] Signed-off-by:
Radim Krčmář <rkrcmar@redhat.com>
-
Paolo Bonzini authored
This prepares the MMU paging code for EPT accessed and dirty bits, which can be enabled optionally at runtime. Code that updates the accessed and dirty bits will need a pointer to the struct kvm_mmu. Signed-off-by:
-
Paolo Bonzini authored
handle_ept_violation is checking for "guest-linear-address invalid" + "not a paging-structure walk". However, _all_ EPT violations without a valid guest linear address are paging structure walks, because those EPT violations happen when loading the guest PDPTEs. Therefore, the check can never be true, and even if it were, KVM doesn't care about the guest linear address; it only uses the guest *physical* address VMCS field. So, remove the check altogether. Signed-off-by:
Jim Mattson <jmattson@google.com> Reviewed-by:
David Hildenbrand <david@redhat.com> Signed-off-by:
-
Paolo Bonzini authored
Large pages at the PDPE level can be emulated by the MMU, so the bit can be set unconditionally in the EPT capabilities MSR. The same is true of 2MB EPT pages, though all Intel processors with EPT in practice support those. Reviewed-by:
-
Paolo Bonzini authored
Legacy device assignment has been deprecated since 4.2 (released 1.5 years ago). VFIO is better and everyone should have switched to it. If they haven't, this should convince them. :) Reviewed-by:
Alex Williamson <alex.williamson@redhat.com> Signed-off-by:
-
Paolo Bonzini authored
Virtual NMIs are only missing in Prescott and Yonah chips. Both are obsolete for virtualization usage---Yonah is 32-bit only even---so drop vNMI emulation. Signed-off-by: -
Borislav Petkov authored
MCG_CAP[63:9] bits are reserved on AMD. However, on an AMD guest, this MSR returns 0x100010a. More specifically, bit 24 is set, which is simply wrong. That bit is MCG_SER_P and is present only on Intel. Thus, clean up the reserved bits in order not to confuse guests. Signed-off-by:
Borislav Petkov <bp@suse.de> Cc: Joerg Roedel <joro@8bytes.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Signed-off-by:
-
David Hildenbrand authored
Let's combine it in a single function vmx_switch_vmcs(). Signed-off-by:
-
Jim Mattson authored
According to the Intel SDM, volume 3, section 28.3.2: Creating and Using Cached Translation Information, "No linear mappings are used while EPT is in use." INVEPT will invalidate both the guest-physical mappings and the combined mappings in the TLBs and paging-structure caches, so an INVVPID is superfluous. Signed-off-by:
-
- 06 Apr, 2017 1 commit
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/kvm-mipsRadim Krčmář authored
From: James Hogan <james.hogan@imgtec.com> KVM: MIPS: VZ support, Octeon III, and TLBR Add basic support for the MIPS Virtualization Module (generally known as MIPS VZ) in KVM. We primarily support the ImgTec P5600, P6600, I6400, and Cavium Octeon III cores so far. Support is included for the following VZ / guest hardware features: - MIPS32 and MIPS64, r5 (VZ requires r5 or later) and r6 - TLBs with GuestID (IMG cores) or Root ASID Dealias (Octeon III) - Shared physical root/guest TLB (IMG cores) - FPU / MSA - Cop0 timer (up to 1GHz for now due to soft timer limit) - Segmentation control (EVA) - Hardware page table walker (HTW) both for root and guest TLB Also included is a proper implementation of the TLBR instruction for the trap & emulate MIPS KVM implementation. Preliminary MIPS architecture changes are applied directly with Ralf's ack.
-
- 29 Mar, 2017 17 commits
-
-
Stefan Raspl authored
Add column '%Total' next to 'Total' for easier comparison of numbers between hosts. Signed-off-by:
Stefan Raspl <raspl@linux.vnet.ibm.com> Marc Hartmayer <mhartmay@linux.vnet.ibm.com> Signed-off-by:
-
Stefan Raspl authored
Provide an interactive command to reset the tracepoint statistics. Requires some extra work for debugfs, as the counters cannot be reset. On the up side, this offers us the opportunity to have debugfs values reset on startup and whenever a filter is modified, becoming consistent with the tracepoint provider. As a bonus, 'kvmstat -dt' will now provide useful output, instead of mixing values in totally different orders of magnitude. Furthermore, we avoid unnecessary resets when any of the filters is "changed" interactively to the previous value. Signed-off-by:
Janosch Frank <frankja@linux.vnet.ibm.com> Signed-off-by:
-
Stefan Raspl authored
Provide a real simple way to erase any active filter. Signed-off-by:
Marc Hartmayer <mhartmay@linux.vnet.ibm.com> Signed-off-by:
-
Stefan Raspl authored
Add a new option '-g'/'--guest' to select a particular process by providing the QEMU guest name. Notes: - The logic to figure out the pid corresponding to the guest name might look scary, but works pretty reliably in practice; in the unlikely event that it returns add'l flukes, it will bail out and hint at using '-p' instead, no harm done. - Mixing '-g' and '-p' is possible, and the final instance specified on the command line is the significant one. This is consistent with current behavior for '-p' which, if specified multiple times, also regards the final instance as the significant one. Signed-off-by:
-
Stefan Raspl authored
Behavior on empty/0 input for regex and pid filtering was inconsistent, as the former would keep the current filter, while the latter would (naturally) remove any pid filtering. Make things consistent by falling back to the default filter on empty input for the regex filter dialogue. Signed-off-by:
-
Stefan Raspl authored
If a user defines a regex filter through the interactive command, display the active regex in the header's second line. Signed-off-by:
-
Stefan Raspl authored
Print helpful messages in case users enter invalid input or invalid pids in the interactive pid filter dialogue. Signed-off-by:
-
Stefan Raspl authored
Improve consistency in the interactive dialogue for pid filtering by removing any filters on empty input (in addition to entering 0). Signed-off-by:
-
Stefan Raspl authored
When running kvm_stat with option '-p' to filter per process, display the QEMU guest name next to the pid, if available. Signed-off-by:
-
Stefan Raspl authored
Apart from the source code, there does not seem to be a place that documents the interactive capabilities of kvm_stat yet. Signed-off-by:
-
Stefan Raspl authored
Whenever a user adds a filter, we * redraw the header immediately for a snappy response * print a message indicating to the user that we're busy while the noticeable delay induced by updating all of the stats objects takes place * update the statistics ASAP (i.e. after 0.25s instead of 3s) to be consistent with behavior on startup To do so, we split the Tui's refresh() method to allow for drawing header and stats separately, and trigger a header refresh whenever we are about to do something that takes a while - like updating filters. Signed-off-by:
-
Stefan Raspl authored
Provides all missing empty lines as required for full PEP compliance. Signed-off-by:
-
Stefan Raspl authored
Updating the fields of the TracepointProvider does not propagate changes to the tracepoints. This shows when a pid filter is enabled, whereby subsequent extensions of the fields of the Tracepoint provider (e.g. by toggling drilldown) will not modify the tracepoints as required. To reproduce, select a specific process via interactive command 'p', and enable drilldown via 'x' - none of the fields with the braces will appear although they should. The fix will always leave all available fields in the TracepointProvider enabled. Signed-off-by:
-
Stefan Raspl authored
Addresses - eliminate extra import - missing variable initialization - type redefinition from int to float - passing of int type argument instead of string - a couple of PEP8-reported indentation/formatting glitches - remove unused variable drilldown in class Tui Signed-off-by:
-
Stefan Raspl authored
SIGINT causes ugly unhandled exceptions in log and batch mode, which we prevent by catching the exceptions accordingly. Signed-off-by:
-
Stefan Raspl authored
The previous version was catching all exceptions, including SIGINT. We only want to catch the curses exceptions here. Signed-off-by:
Sascha Silbe <silbe@linux.vnet.ibm.com> Reviewed-by:
-
Stefan Raspl authored
When running kvm_stat in interactive mode, the cursor appears at the lower left corner, which looks a bit distracting. This patch hides the cursor by turning it invisible. Signed-off-by:
-
- 28 Mar, 2017 13 commits
-
-
James Hogan authored
Properly implement emulation of the TLBR instruction for Trap & Emulate. This instruction reads the TLB entry pointed at by the CP0_Index register into the other TLB registers, which may have the side effect of changing the current ASID. Therefore abstract the CP0_EntryHi and ASID changing code into a common function in the process. A comment indicated that Linux doesn't use TLBR, which is true during normal use, however dumping of the TLB does use it (for example with the relatively recent 'x' magic sysrq key), as does a wired TLB entries test case in my KVM tests. Signed-off-by:
James Hogan <james.hogan@imgtec.com> Acked-by:
Ralf Baechle <ralf@linux-mips.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Krčmář" <rkrcmar@redhat.com> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org
-
James Hogan authored
Octeon III has VZ ASE support, so allow KVM to be enabled on Octeon CPUs as it should now be functional. Signed-off-by: -
James Hogan authored
Octeon III implements a read-only guest CP0_PRid register, so add cases to the KVM register access API for Octeon to ensure the correct value is read and writes are ignored. Signed-off-by: -
James Hogan authored
Octeon III doesn't implement the optional GuestCtl0.CG bit to allow guest mode to execute virtual address based CACHE instructions, so implement emulation of a few important ones specifically for Octeon III in response to a GPSI exception. Currently the main reason to perform these operations is for icache synchronisation, so they are implemented as a simple icache flush with local_flush_icache_range(). Signed-off-by: -
James Hogan authored
Set up hardware virtualisation on Octeon III cores, configuring guest interrupt routing and carving out half of the root TLB for guest use, restoring it back again afterwards. We need to be careful to inhibit TLB shutdown machine check exceptions while invalidating guest TLB entries, since TLB invalidation is not available so guest entries must be invalidated by setting them to unique unmapped addresses, which could conflict with mappings set by the guest or root if recently repartitioned. Signed-off-by: -
James Hogan authored
Octeon CPUs don't report the correct dcache line size in CP0_Config1.DL, so encode the correct value for the guest CP0_Config1.DL based on cpu_dcache_line_size(). Signed-off-by: -
James Hogan authored
When TLB entries are invalidated in the presence of a virtually tagged icache, such as that found on Octeon CPUs, flush the icache so that we don't get a reserved instruction exception even though the TLB mapping is removed. Signed-off-by: -
James Hogan authored
Cache management is implemented separately for Cavium Octeon CPUs, so r4k_blast_[id]cache aren't available. Instead for Octeon perform a local icache flush using local_flush_icache_range(), and for other platforms which don't use c-r4k.c use __flush_cache_all() / flush_icache_all(). Signed-off-by: -
James Hogan authored
Add accessors for some VZ related Cavium Octeon III specific COP0 registers, along with field definitions. These will mostly be used by KVM to set up interrupt routing and partition the TLB between root and guest. Signed-off-by:
-
James Hogan authored
Create a trace event for guest mode changes, and enable VZ's GuestCtl0.MC bit after the trace event is enabled to trap all guest mode changes. The MC bit causes Guest Hardware Field Change (GHFC) exceptions whenever a guest mode change occurs (such as an exception entry or return from exception), so we need to handle this exception now. The MC bit is only enabled when restoring register state, so enabling the trace event won't take immediate effect. Tracing guest mode changes can be particularly handy when trying to work out what a guest OS gets up to before something goes wrong, especially if the problem occurs as a result of some previous guest userland exception which would otherwise be invisible in the trace. Signed-off-by: -
James Hogan authored
Transfer timer state to the VZ guest context (CP0_GTOffset & guest CP0_Count) when entering guest mode, enabling direct guest access to it, and transfer back to soft timer when saving guest register state. This usually allows guest code to directly read CP0_Count (via MFC0 and RDHWR) and read/write CP0_Compare, without trapping to the hypervisor for it to emulate the guest timer. Writing to CP0_Count or CP0_Cause.DC is much less common and still triggers a hypervisor GPSI exception, in which case the timer state is transferred back to an hrtimer before emulating the write. We are careful to prevent small amounts of drift from building up due to undeterministic time intervals between reading of the ktime and reading of CP0_Count. Some drift is expected however, since the system clocksource may use a different timer to the local CP0_Count timer used by VZ. This is permitted to prevent guest CP0_Count from appearing to go backwards. Signed-off-by: -
James Hogan authored
Add emulation of Memory Accessibility Attribute Registers (MAARs) when necessary. We can't actually do anything with whatever the guest provides, but it may not be possible to clear Guest.Config5.MRP so we have to emulate at least a pair of MAARs. Signed-off-by: -
James Hogan authored
When restoring guest state after another VCPU has run, be sure to clear CP0_LLAddr.LLB in order to break any interrupted atomic critical section. Without this SMP guest atomics don't work when LLB is present as one guest can complete the atomic section started by another guest. MIPS VZ guest read of CP0_LLAddr causes Guest Privileged Sensitive Instruction (GPSI) exception due to the address being root physical. Handle this by reporting only the LLB bit, which contains the bit for whether a ll/sc atomic is in progress without any reason for failure. Similarly on P5600 a guest write to CP0_LLAddr also causes a GPSI exception. Handle this also by clearing the guest LLB bit from root mode. Signed-off-by:
-
