| Age | Commit message (Collapse) | Author |
|---|
|
This is a bug fix for using physical arch timers when
the arch_timer_use_virtual boolean is false. It restores the
arch_counter_get_cntpct() function after removal in
0d651e4e "clocksource: arch_timer: use virtual counters"
We need this on certain ARMv7 systems which are architected like this:
* The firmware doesn't know and doesn't care about hypervisor mode and
we don't want to add the complexity of hypervisor there.
* The firmware isn't involved in SMP bringup or resume.
* The ARCH timer come up with an uninitialized offset between the
virtual and physical counters. Each core gets a different random
offset.
* The device boots in "Secure SVC" mode.
* Nothing has touched the reset value of CNTHCTL.PL1PCEN or
CNTHCTL.PL1PCTEN (both default to 1 at reset)
One example of such as system is RK3288 where it is much simpler to
use the physical counter since there's nobody managing the offset and
each time a core goes down and comes back up it will get reinitialized
to some other random value.
Fixes: 0d651e4e65e9 ("clocksource: arch_timer: use virtual counters")
Cc: stable@vger.kernel.org
Signed-off-by: Sonny Rao <sonnyrao@chromium.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
The imx6 PM code seems to be quite creative in its use of irq_data,
using something that is very much a hardware interrupt number where
we expect a virtual one. Yes, it worked so far, but that's only
luck, and it will definitely explode in 3.19.
Fix it by using a pair of helper functions that deal with the
actual hardware.
Tested-by: Fabio Estevam <fabio.estevam@freescale.com>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
mach-imx directly references to the irq field in
struct irq_data, and uses this to directly poke hardware register.
But irq is the *virtual* irq number, something that has nothing
to do with the actual HW irq (stored in the hwirq field). And once
we put the stacked domain code in action, the whole thing explodes,
as these two values are *very* different.
Just replacing all instances of irq with hwirq fixes the issue.
Tested-by: Fabio Estevam <fabio.estevam@freescale.com>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
next/dt
Merge "ARM: BCM5301X: DT changes for v3.19 #2" from Hauke Mehrtens:
ARM: BCM5301X: dts updates
This adds the IRQ number to the main dts file and some new dts files
for newly added devices.
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
* tag 'bcm5301x-dt-2014-12-04' of https://github.com/hauke/linux:
ARM: BCM5301X: Add DT for Buffalo WZR-600DHP2
ARM: BCM5301X: Add DT for Asus RT-N18U
ARM: BCM5301X: Add DT for Buffalo WZR-1750DHP
ARM: BCM5301X: Add DT for Netgear R6300 V2
ARM: BCM5301X: Add buttons for Netgear R6250
ARM: BCM5301X: Add IRQs to Broadcom's bus-axi in DTS file
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
based SoCs
This patch enables the MAX77686 PMIC drivers in the multi_v7_defconfig used
on exynos4412-prime family of SoCs [1]. The exynos4412-prime based boards
are producing the following runtime errors only on the multi_v7_defconfig [2]:
kern.err: deviceless supply vdd_arm not found, using dummy regulator
kern.err: exynos-cpufreq exynos-cpufreq: failed to set cpu voltage to 1287500
kern.err: cpufreq: __target_index: Failed to change cpu frequency: -22
I reviewed the exynos_defconfig, which does not produce these runtime
errors. It was obvious that the exynos_defconfig has the PMIC drivers
enabled, whereas the multi_v7_defconfig does not. This patch has been tested
on a odroid-u2 and a odroid-u3 board. It has resolved the runtime errors.
Therefore, I purpose we enabled these drivers in the multi_v7_defconfig.
[1] http://www.hardkernel.com/main/products/prdt_info.php?g_code=G135270682824
[2] http://storage.armcloud.us/kernel-ci/mainline/v3.18-rc7-48-g7cc78f8/arm-multi_v7_defconfig/lab-tbaker-00/boot-exynos4412-odroidu3.html
Signed-off-by: Tyler Baker <tyler.baker@linaro.org>
Signed-off-by: Olof Johansson <olof@lixom.net>
|
|
The existing MCE code calls flush_tlb hook with IS=0 (single page) resulting
in partial invalidation of TLBs which is not right. This patch fixes
that by passing IS=0xc00 to invalidate whole TLB for successful recovery
from TLB and ERAT errors.
Cc: stable@vger.kernel.org
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
upatepp can get called for a nohpte fault when we find from the linux
page table that the translation was hashed before. In that case
we are sure that there is no existing translation, hence we could
avoid doing tlbie.
We could possibly race with a parallel fault filling the TLB. But
that should be ok because updatepp is only ever relaxing permissions.
We also look at linux pte permission bits when filling hash pte
permission bits. We also hold the linux pte busy bits while
inserting/updating a hashpte entry, hence a paralle update of
linux pte is not possible. On the other hand mprotect involves
ptep_modify_prot_start which cause a hpte invalidate and not updatepp.
Performance number:
We use randbox_access_bench written by Anton.
Kernel with THP disabled and smaller hash page table size.
86.60% random_access_b [kernel.kallsyms] [k] .native_hpte_updatepp
2.10% random_access_b random_access_bench [.] doit
1.99% random_access_b [kernel.kallsyms] [k] .do_raw_spin_lock
1.85% random_access_b [kernel.kallsyms] [k] .native_hpte_insert
1.26% random_access_b [kernel.kallsyms] [k] .native_flush_hash_range
1.18% random_access_b [kernel.kallsyms] [k] .__delay
0.69% random_access_b [kernel.kallsyms] [k] .native_hpte_remove
0.37% random_access_b [kernel.kallsyms] [k] .clear_user_page
0.34% random_access_b [kernel.kallsyms] [k] .__hash_page_64K
0.32% random_access_b [kernel.kallsyms] [k] fast_exception_return
0.30% random_access_b [kernel.kallsyms] [k] .hash_page_mm
With Fix:
27.54% random_access_b random_access_bench [.] doit
22.90% random_access_b [kernel.kallsyms] [k] .native_hpte_insert
5.76% random_access_b [kernel.kallsyms] [k] .native_hpte_remove
5.20% random_access_b [kernel.kallsyms] [k] fast_exception_return
5.12% random_access_b [kernel.kallsyms] [k] .__hash_page_64K
4.80% random_access_b [kernel.kallsyms] [k] .hash_page_mm
3.31% random_access_b [kernel.kallsyms] [k] data_access_common
1.84% random_access_b [kernel.kallsyms] [k] .trace_hardirqs_on_caller
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
|
|
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
|
|
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
|
|
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
|
|
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/nferre/linux-at91 into next/cleanup
Pull "Fifth batch of cleanup/SoC for 3.19" from Nicolas Ferre:
- removal of now dead code and AT91-specific driver
- removal of !DT initialization in some core AT91 drivers
- simplification of Kconfig DT board file selection: now automatic
* tag 'at91-cleanup5' of git://git.kernel.org/pub/scm/linux/kernel/git/nferre/linux-at91:
ARM: at91: remove unused board.h file
ARM: at91: remove unneeded header files
ARM: at91/clocksource: remove !DT PIT initializations
ARM: at91: at91rm9200 ST initialization is now DT only
ARM: at91: remove old AT91-specific drivers
ARM: at91: cleanup initilisation code by removing dead code
ARM: at91/Kconfig: select board files automatically
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/nferre/linux-at91 into next/defconfig
Pull "First batch of defconfigs for AT91 / 3.19:" from Nicolas Ferre:
- use NEON for all C-A5, neon code handles the !NEON case
- add new XDMA driver
- add some useful drivers as we only have a single defconfig for all
AT91SAM9/RM9200
* tag 'at91-defconfig' of git://git.kernel.org/pub/scm/linux/kernel/git/nferre/linux-at91:
ARM: at91/defconfig: add DM9000 to at91_dt
ARM: at91/defconfig: add QT1070 to at91_dt
ARM: at91/defconfig: add TCB PWM driver selection
ARM: at91/defconfig: add the XDMA driver
ARM: at91: sama5: update defconfig
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
commit 68a3c0433077 ([media] ARM: OMAP2: RX-51: update
si4713 platform data) updated board-rx51-peripherals.c
so that si4713 could be easily used on DT boot, but
it ended up introducing a build warning whenever
si4713 isn't enabled.
This patches fixes that warning:
arch/arm/mach-omap2/board-rx51-peripherals.c:1000:36: warning: \
‘rx51_si4713_platform_data’ defined but not used [-Wunused-variable]
static struct si4713_platform_data rx51_si4713_platform_data = {
Cc: Sebastian Reichel <sre@kernel.org>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/mmind/linux-rockchip into next/dt
Pull "last dts changes for 3.19" from Jason Cooper:
- rk3288 thermal driver that got accepted into the thermal tree
- mmc fifo sizes for Cortex-A9 SoCs
- labels for the leds on the RadxaRock
- core system supply for the Marsboard
* tag 'v3.19-rockchip-dts4' of git://git.kernel.org/pub/scm/linux/kernel/git/mmind/linux-rockchip:
ARM: dts: rockchip: Add input voltage supply regulators in pmic for Marsboard
ARM: dts: rockchip: set FIFO size for SDMMC, SDIO and EMMC on rk3066 and rk3188
ARM: dts: rockchip: add label property for leds on Radxa Rock
ARM: dts: rockchip: enable thermal on rk3288-evb board
ARM: dts: rockchip: add main thermal info to rk3288
ARM: dts: rockchip: add RK3288 Thermal data
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
This chip is present on at91sam9261ek board: add it to the at91_dt_defconfig.
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
|
|
As this touch button driver is used on at91sam9x5ek, it's better to enable it.
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
|
|
This is the selection of the new PWM driver using TC Blocks. This driver is
useful so we enable it in both sama5 and at91_dt defconfig files.
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
|
|
Add the Atmel eXtended DMA Controller driver option. This driver is first used
on SAMA5D4 SoCs and only relevant in sama5_defconfig file.
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
|
|
Add neon support for sama5d4 and large blocks/files support.
Signed-off-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Acked-by: Alexandre Belloni <alexandre.belloni@free-electrons.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
|
|
This commit adjusts the registration of the cpufreq-dt driver in the
mvebu platform to indicate to the cpufreq driver that the platform has
independent clocks for each CPU.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Acked-by: Jason Cooper <jason@lakedaemon.net>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux into next/dt2
Pull "ARM: tegra: Device tree changes for v3.19" from Thierry Reding:
The bulk of these changes add memory controller nodes for Tegra30,
Tegra114 and Tegra124. The memory controller implements an IOMMU that
the display controllers are attached to. This allows them to scan out
physically non-contiguous framebuffers and removes one of the primary
users of CMA.
The only other change adds a new MIPI pad control bank to the pin
controller on Tegra124. The corresponding driver patch for this went
into v3.18 as:
3ccc11f6b82c pinctrl: tegra: Add MIPI pad control
* tag 'tegra-for-3.19-dt' of git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux:
ARM: tegra: Enable IOMMU for display controllers on Tegra124
ARM: tegra: Enable IOMMU for display controllers on Tegra114
ARM: tegra: Enable IOMMU for display controllers on Tegra30
ARM: tegra: Add memory controller support for Tegra124
ARM: tegra: Add memory controller support for Tegra114
ARM: tegra: Add memory controller support for Tegra30
ARM: tegra: Add APB_MISC_GP as a MIPI pad control bank
These additional commits are merged as dependencies:
memory: Add NVIDIA Tegra memory controller support
of: Add NVIDIA Tegra memory controller binding
ARM: tegra: Move AHB Kconfig to drivers/amba
amba: Add Kconfig file
clk: tegra: Implement memory-controller clock
powerpc/iommu: Rename iommu_[un]map_sg functions
iommu: Improve error handling when setting bus iommu
iommu: Do more input validation in iommu_map_sg()
iommu: Add iommu_map_sg() function
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux into next/drivers
Pull "ARM: tegra: IOMMU support for v3.19" from Thierry Reding:
This adds the driver pieces required for IOMMU support on Tegra30,
Tegra114 and Tegra124.
* tag 'tegra-for-3.19-iommu' of git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux:
memory: Add NVIDIA Tegra memory controller support
of: Add NVIDIA Tegra memory controller binding
ARM: tegra: Move AHB Kconfig to drivers/amba
amba: Add Kconfig file
clk: tegra: Implement memory-controller clock
powerpc/iommu: Rename iommu_[un]map_sg functions
iommu: Improve error handling when setting bus iommu
iommu: Do more input validation in iommu_map_sg()
iommu: Add iommu_map_sg() function
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
Since PCIe is using SMMUv1 which only supports 15-bit stream ID,
only 7-bit PCI bus id is used to specify stream ID. Therefore,
we only limit the PCI bus range to 0x7f.
Signed-off-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
into next/cleanup
Pull "arm: Xilinx Zynq cleanup patches for v3.19" from Michal Simek:
- Remove unused file and declaration
* tag 'zynq-cleanup-for-3.19' of https://github.com/Xilinx/linux-xlnx:
ARM: zynq: Remove secondary_startup() declaration from header
ARM: zynq: Actually remove hotplug.c
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
next/dt
Pull "arm: Xilinx Zynq dt patches for v3.19" from Michal Simek:
- Declare Digilent and vendor
- Add Zybo board support
- Fix VDMA documentation to be align with the driver
* tag 'zynq-dt-for-3.19' of https://github.com/Xilinx/linux-xlnx:
arm: dts: zynq: Add Digilent ZYBO board
arm: dts: zynq: Move crystal freq. to board level
doc: dt: vendor-prefixes: Add Digilent Inc
Documentation: devicetree: Fix Xilinx VDMA specification
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
into next/soc
Pull "mvebu SoC suspend changes for v3.19" from Jason Cooper:
- Armada 370/XP suspend/resume support
- mvebu SoC driver suspend/resume support
- irqchip
- clocksource
- mbus
- clk
* tag 'mvebu-soc-suspend-3.19' of git://git.infradead.org/linux-mvebu:
ARM: mvebu: add SDRAM controller description for Armada XP
ARM: mvebu: adjust mbus controller description on Armada 370/XP
ARM: mvebu: add suspend/resume DT information for Armada XP GP
ARM: mvebu: synchronize secondary CPU clocks on resume
ARM: mvebu: make sure MMU is disabled in armada_370_xp_cpu_resume
ARM: mvebu: Armada XP GP specific suspend/resume code
ARM: mvebu: reserve the first 10 KB of each memory bank for suspend/resume
ARM: mvebu: implement suspend/resume support for Armada XP
clk: mvebu: add suspend/resume for gatable clocks
bus: mvebu-mbus: provide a mechanism to save SDRAM window configuration
bus: mvebu-mbus: suspend/resume support
clocksource: time-armada-370-xp: add suspend/resume support
irqchip: armada-370-xp: Add suspend/resume support
Documentation: dt-bindings: minimal documentation for MVEBU SDRAM controller
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
This is a squash of several imx_v6_v7_defconfig update patches.
- Enable tlv320aic3x audio codec by default (Phytec PBAB01 board)
- Enable DS1307 rtc and gpio fan by default (TBS2910 board)
- Select thermal related drivers
- Add SNVS power off driver
Signed-off-by: Dmitry Lavnikevich <d.lavnikevich@sam-solutions.com>
Signed-off-by: Soeren Moch <smoch@web.de>
Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: Robin Gong <b38343@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
|
|
Instead of returning a possibly random or'ed together value, let's
always return -EFAULT if rc is set.
Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
|
|
Currently we use a mixture of atomic/non-atomic bitops
and the local_int spin lock to protect the pending_irqs bitmap
and interrupt payload data.
We need to use atomic bitops for the pending_irqs bitmap everywhere
and in addition acquire the local_int lock where interrupt data needs
to be protected.
Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
|
|
The cpu address of a source cpu (responsible for an external irq) is only to
be stored if bit 6 of the ext irq code is set.
If bit 6 is not set, it is to be zeroed out.
The special external irq code used for virtio and pfault uses the cpu addr as a
parameter field. As bit 6 is set, this implementation is correct.
Reviewed-by: Thomas Huth <thuth@linux.vnet.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
|
|
Add iommus properties to the device tree nodes for the two display
controllers found on Tegra124. This will allow the display controllers
to map physically non-contiguous buffers to I/O virtual contiguous
address spaces so that they can be used for scan-out.
Signed-off-by: Thierry Reding <treding@nvidia.com>
|
|
Add iommus properties to the device tree nodes for the two display
controllers found on Tegra114. This will allow the display controllers
to map physically non-contiguous buffers to I/O virtual contiguous
address spaces so that they can be used for scan-out.
Signed-off-by: Thierry Reding <treding@nvidia.com>
|
|
Add iommus properties to the device tree nodes for the two display
controllers found on Tegra30. This will allow the display controllers to
map physically non-contiguous buffers to I/O virtual contiguous address
spaces so that they can be used for scan-out.
Signed-off-by: Thierry Reding <treding@nvidia.com>
|
|
Add the memory controller and wire up the interrupt that is used to
report errors. Provide a reference to the memory controller clock and
mark the device as being an IOMMU by adding an #iommu-cells property.
Signed-off-by: Thierry Reding <treding@nvidia.com>
|
|
Add the device tree node for the memory controller found on Tegra114
SoCs. The memory controller integrates an IOMMU (called SMMU) as well as
various knobs to tweak memory accesses by the various clients.
The old IOMMU device tree node is collapsed into the memory controller
node to more accurately describe the hardware. While this change is
incompatible, the IOMMU driver has never had any users so the change is
not going to cause any breakage.
Signed-off-by: Thierry Reding <treding@nvidia.com>
|
|
Collapses the old memory-controller and IOMMU device tree nodes into a
single node to more accurately describe the hardware.
While this is an incompatible change there are no users of the IOMMU on
Tegra, even though a driver has existed for some time.
Signed-off-by: Thierry Reding <treding@nvidia.com>
|
|
This patch adds the APB_MISC_GP_MIPI_PAD_CTRL_0 as a pin-control bank on
Tegra124 so the new MIPI pad control group can be muxed between CSI and
DSI_B.
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Acked-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
|
|
While fixing an x2apic bug,
17d68b7 KVM: x86: fix guest-initiated crash with x2apic (CVE-2013-6376)
we've made only one cluster available. This means that the amount of
logically addressible x2APICs was reduced to 16 and VCPUs kept
overwriting themselves in that region, so even the first cluster wasn't
set up correctly.
This patch extends x2APIC support back to the logical_map's limit, and
keeps the CVE fixed as messages for non-present APICs are dropped.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
They can't be violated now, but play it safe for the future.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
x2apic allows destinations > 0xff and we don't want them delivered to
lower APICs. They are correctly handled by doing nothing.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Physical mode can't address more than one APIC, but lowest-prio is
allowed, so we just reuse our paths.
SDM 10.6.2.1 Physical Destination:
Also, for any non-broadcast IPI or I/O subsystem initiated interrupt
with lowest priority delivery mode, software must ensure that APICs
defined in the interrupt address are present and enabled to receive
interrupts.
We could warn on top of that.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
False from kvm_irq_delivery_to_apic_fast() means that we don't handle it
in the fast path, but we still return false in cases that were perfectly
handled, fix that.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
0x830 MSR is 0x300 xAPIC MMIO, which is MSR_ICR.
Signed-off-by: Radim KrÄmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
x2APIC has no registers for DFR and ICR2 (see Intel SDM 10.12.1.2 "x2APIC
Register Address Space"). KVM needs to cause #GP on such accesses.
Fix it (DFR and ICR2 on read, ICR2 on write, DFR already handled on writes).
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Certain x86 instructions that use modrm operands only allow memory operand
(i.e., mod012), and cause a #UD exception otherwise. KVM ignores this fact.
Currently, the instructions that are such and are emulated by KVM are MOVBE,
MOVNTPS, MOVNTPD and MOVNTI. MOVBE is the most blunt example, since it may be
emulated by the host regardless of MMIO.
The fix introduces a new group for handling such instructions, marking mod3 as
illegal instruction.
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Instead of checking at each call of set_phys_to_machine() whether a
new p2m page has to be allocated due to writing an entry in a large
invalid or identity area, just map those areas read only and react
to a page fault on write by allocating the new page.
This change will make the common path with no allocation much
faster as it only requires a single write of the new mfn instead
of walking the address translation tables and checking for the
special cases.
Suggested-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
|
|
At start of the day the Xen hypervisor presents a contiguous mfn list
to a pv-domain. In order to support sparse memory this mfn list is
accessed via a three level p2m tree built early in the boot process.
Whenever the system needs the mfn associated with a pfn this tree is
used to find the mfn.
Instead of using a software walked tree for accessing a specific mfn
list entry this patch is creating a virtual address area for the
entire possible mfn list including memory holes. The holes are
covered by mapping a pre-defined page consisting only of "invalid
mfn" entries. Access to a mfn entry is possible by just using the
virtual base address of the mfn list and the pfn as index into that
list. This speeds up the (hot) path of determining the mfn of a
pfn.
Kernel build on a Dell Latitude E6440 (2 cores, HT) in 64 bit Dom0
showed following improvements:
Elapsed time: 32:50 -> 32:35
System: 18:07 -> 17:47
User: 104:00 -> 103:30
Tested with following configurations:
- 64 bit dom0, 8GB RAM
- 64 bit dom0, 128 GB RAM, PCI-area above 4 GB
- 32 bit domU, 512 MB, 8 GB, 43 GB (more wouldn't work even without
the patch)
- 32 bit domU, ballooning up and down
- 32 bit domU, save and restore
- 32 bit domU with PCI passthrough
- 64 bit domU, 8 GB, 2049 MB, 5000 MB
- 64 bit domU, ballooning up and down
- 64 bit domU, save and restore
- 64 bit domU with PCI passthrough
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
|
|
Today get_phys_to_machine() is always called when the mfn for a pfn
is to be obtained. Add a wrapper __pfn_to_mfn() as inline function
to be able to avoid calling get_phys_to_machine() when possible as
soon as the switch to a linear mapped p2m list has been done.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
|
