Merge tag 'acpi-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull ACPI updates from Rafael Wysocki:
"First off, the ACPICA code in the kernel is updated to upstream
revision 20160831 that brings in a few bug fixes and cleanups. In
particular, it is possible to mask GPEs now (and the sysfs interface
for GPE control is fixed on top of that), problems related to the
table loading mechanism are fixed and all code related to FADT version
2 (which has never been part of the ACPI specification) is dropped.
On the new features front, there is a new watchdog driver based on the
ACPI WDAT (ACPI Watchdog Action Table), needed on some platforms to
replace the iTCO watchdog that doesn't work there, and some UART
devices get new definitions of built-in properties (to be accessed via
the generic device properties API).
Also, included is a fix for an ACPI-related PCI resorces allocation
issue and a few problems in the EC driver and in the button and
battery drivers are fixed.
In addition to that, the ACPI CPPC library is updated to make batching
of requests sent over the PCC channel possible (which reduces the PCC
usage overhead substantially in some cases) and to support functional
fixed hardware (FFH) type of CPPC registers access (which will allow
CPPC to be used on x86 too in the future).
As usual, there are some assorted fixes and cleanups too.
Specifics:
- Update of the ACPICA code in the kernel to upstream revision
20160831 with the following major changes:
* New mechanism for GPE masking.
* Fixes for issues related to the LoadTable operator and table
loading.
* Fixes for issues related to so-called module-level code (MLC),
that is AML that doesn't belong to any methods.
* Change of the return value of the _OSI method to reflect the
Windows behavior.
* GAS (Generic Address Structure) support fix related to 32-bit
FADT addresses.
* Elimination of unnecessary FADT version 2 support.
* ACPI tools fixes and cleanups.
From Bob Moore, Lv Zheng, and Jung-uk Kim.
- ACPI sysfs interface updates to fix GPE handling (on top of the new
GPE masking mechanism in ACPICA) and issues related to table
loading (Lv Zheng).
- New watchdog driver based on the ACPI WDAT (ACPI Watchdog Action
Table), needed on some platforms to replace the iTCO watchdog that
doesn't work there and related updates of the intel_pmc_ipc,
i2c/i801 and MFD/lcp_ich drivers (Mika Westerberg).
- Driver core fix to prevent it from leaking secondary fwnode objects
during device removal (Lukas Wunner).
- New definitions of built-in properties for UART in ACPI-based x86
SoC drivers and a 8250_dw driver quirk for the APM X-Gene SoC
(Heikki Krogerus).
- New device ID for the Vulcan SPI controller and constification of
local strucures in the AMD SoC (APD) ACPI driver (Kamlakant Patel,
Julia Lawall).
- Fix for a bug causing the allocation of PCI resorces to fail if
ACPI-enumerated child platform devices are registered below the PCI
devices in question (Mika Westerberg).
- Change of the default polarity for PCI legacy IRQs to high on
systems booting wth ACPI on platforms with a GIC interrupt
controller model fixing the discrepancy between the specification
and HW behavior (Lorenzo Pieralisi).
- Fixes for the handling of system suspend/resume in the ACPI EC
driver and update of that driver to make it cope with the cases
when the EC device defined in the ECDT has to be used throughout
the entire system life cycle (Lv Zheng).
- Update of the ACPI CPPC library to allow it to batch requests sent
over the PCC channel (to reduce overhead), to support the fixed
functional hardware (FFH) CPPC registers access type, to notify the
mailbox framework about TX completions when the interrupt flag is
set for the PCC mailbox, and to support HW-Reduced Communication
Subspace type 2 (Ashwin Chaugule, Prashanth Prakash, Srinivas
Pandruvada, Hoan Tran).
- ACPI button driver fix and documentation update related to the
handling of laptop lids (Lv Zheng).
- ACPI battery driver initialization fix (Carlos Garnacho).
- ACPI GPIO enumeration documentation update (Mika Westerberg).
- Assorted updates of the core ACPI bus type code (Lukas Wunner, Lv
Zheng).
- Assorted cleanups of the ACPI table parsing code and the
x86-specific ACPI code (Al Stone).
- Fixes for assorted ACPI-related issues found in linux-next (Wei
Yongjun)"
* tag 'acpi-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (98 commits)
ACPI / documentation: Use recommended name in GPIO property names
watchdog: wdat_wdt: Fix warning for using 0 as NULL
watchdog: wdat_wdt: fix return value check in wdat_wdt_probe()
platform/x86: intel_pmc_ipc: Do not create iTCO watchdog when WDAT table exists
i2c: i801: Do not create iTCO watchdog when WDAT table exists
mfd: lpc_ich: Do not create iTCO watchdog when WDAT table exists
ACPI / bus: Adjust ACPI subsystem initialization for new table loading mode
ACPICA: Parser: Fix a regression in LoadTable support
ACPICA: Tables: Fix "UNLOAD" code path lock issues
ACPI / watchdog: Add support for WDAT hardware watchdog
ACPI / platform: Pay attention to parent device's resources
PCI: Add pci_find_resource()
ACPI / CPPC: Support PCC with interrupt flag
ACPI / sysfs: Update sysfs signature handling code
ACPI / sysfs: Fix an issue for LoadTable opcode
ACPICA: Tables: Fix a regression in acpi_tb_find_table()
ACPI / tables: Remove duplicated include from tables.c
ACPI / APD: constify local structures
x86: ACPI: make variable names clearer in acpi_parse_madt_lapic_entries()
x86: ACPI: remove extraneous white space after semicolon
...
diff --git a/.mailmap b/.mailmap
index de22dae..1dab0a1 100644
--- a/.mailmap
+++ b/.mailmap
@@ -69,6 +69,7 @@
James Bottomley <jejb@titanic.il.steeleye.com>
James E Wilson <wilson@specifix.com>
James Ketrenos <jketreno@io.(none)>
+Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
<javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
Jean Tourrilhes <jt@hpl.hp.com>
Jeff Garzik <jgarzik@pretzel.yyz.us>
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index ccc6032..405da11 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -61,3 +61,5 @@
| Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 |
| Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 |
| Cavium | ThunderX SMMUv2 | #27704 | N/A |
+| | | | |
+| Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 |
diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index e774128..ef5fbe9 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -25,6 +25,12 @@
- always-on : a boolean property. If present, the timer is powered through an
always-on power domain, therefore it never loses context.
+- fsl,erratum-a008585 : A boolean property. Indicates the presence of
+ QorIQ erratum A-008585, which says that reading the counter is
+ unreliable unless the same value is returned by back-to-back reads.
+ This also affects writes to the tval register, due to the implicit
+ counter read.
+
** Optional properties:
- arm,cpu-registers-not-fw-configured : Firmware does not initialize
diff --git a/Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt b/Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt
new file mode 100644
index 0000000..f223313
--- /dev/null
+++ b/Documentation/devicetree/bindings/devfreq/event/rockchip-dfi.txt
@@ -0,0 +1,19 @@
+
+* Rockchip rk3399 DFI device
+
+Required properties:
+- compatible: Must be "rockchip,rk3399-dfi".
+- reg: physical base address of each DFI and length of memory mapped region
+- rockchip,pmu: phandle to the syscon managing the "pmu general register files"
+- clocks: phandles for clock specified in "clock-names" property
+- clock-names : the name of clock used by the DFI, must be "pclk_ddr_mon";
+
+Example:
+ dfi: dfi@0xff630000 {
+ compatible = "rockchip,rk3399-dfi";
+ reg = <0x00 0xff630000 0x00 0x4000>;
+ rockchip,pmu = <&pmugrf>;
+ clocks = <&cru PCLK_DDR_MON>;
+ clock-names = "pclk_ddr_mon";
+ status = "disabled";
+ };
diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
new file mode 100644
index 0000000..7a9e860
--- /dev/null
+++ b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
@@ -0,0 +1,209 @@
+* Rockchip rk3399 DMC(Dynamic Memory Controller) device
+
+Required properties:
+- compatible: Must be "rockchip,rk3399-dmc".
+- devfreq-events: Node to get DDR loading, Refer to
+ Documentation/devicetree/bindings/devfreq/
+ rockchip-dfi.txt
+- interrupts: The interrupt number to the CPU. The interrupt
+ specifier format depends on the interrupt controller.
+ It should be DCF interrupts, when DDR dvfs finish,
+ it will happen.
+- clocks: Phandles for clock specified in "clock-names" property
+- clock-names : The name of clock used by the DFI, must be
+ "pclk_ddr_mon";
+- operating-points-v2: Refer to Documentation/devicetree/bindings/power/opp.txt
+ for details.
+- center-supply: DMC supply node.
+- status: Marks the node enabled/disabled.
+
+Following properties are ddr timing:
+
+- rockchip,dram_speed_bin : Value reference include/dt-bindings/clock/ddr.h,
+ it select ddr3 cl-trp-trcd type, default value
+ "DDR3_DEFAULT".it must selected according to
+ "Speed Bin" in ddr3 datasheet, DO NOT use
+ smaller "Speed Bin" than ddr3 exactly is.
+
+- rockchip,pd_idle : Config the PD_IDLE value, defined the power-down
+ idle period, memories are places into power-down
+ mode if bus is idle for PD_IDLE DFI clocks.
+
+- rockchip,sr_idle : Configure the SR_IDLE value, defined the
+ selfrefresh idle period, memories are places
+ into self-refresh mode if bus is idle for
+ SR_IDLE*1024 DFI clocks (DFI clocks freq is
+ half of dram's clocks), defaule value is "0".
+
+- rockchip,sr_mc_gate_idle : Defined the self-refresh with memory and
+ controller clock gating idle period, memories
+ are places into self-refresh mode and memory
+ controller clock arg gating if bus is idle for
+ sr_mc_gate_idle*1024 DFI clocks.
+
+- rockchip,srpd_lite_idle : Defined the self-refresh power down idle
+ period, memories are places into self-refresh
+ power down mode if bus is idle for
+ srpd_lite_idle*1024 DFI clocks. This parameter
+ is for LPDDR4 only.
+
+- rockchip,standby_idle : Defined the standby idle period, memories are
+ places into self-refresh than controller, pi,
+ phy and dram clock will gating if bus is idle
+ for standby_idle * DFI clocks.
+
+- rockchip,dram_dll_disb_freq : It's defined the DDR3 dll bypass frequency in
+ MHz, when ddr freq less than DRAM_DLL_DISB_FREQ,
+ ddr3 dll will bypssed note: if dll was bypassed,
+ the odt also stop working.
+
+- rockchip,phy_dll_disb_freq : Defined the PHY dll bypass frequency in
+ MHz (Mega Hz), when ddr freq less than
+ DRAM_DLL_DISB_FREQ, phy dll will bypssed.
+ note: phy dll and phy odt are independent.
+
+- rockchip,ddr3_odt_disb_freq : When dram type is DDR3, this parameter defined
+ the odt disable frequency in MHz (Mega Hz),
+ when ddr frequency less then ddr3_odt_disb_freq,
+ the odt on dram side and controller side are
+ both disabled.
+
+- rockchip,ddr3_drv : When dram type is DDR3, this parameter define
+ the dram side driver stength in ohm, default
+ value is DDR3_DS_40ohm.
+
+- rockchip,ddr3_odt : When dram type is DDR3, this parameter define
+ the dram side ODT stength in ohm, default value
+ is DDR3_ODT_120ohm.
+
+- rockchip,phy_ddr3_ca_drv : When dram type is DDR3, this parameter define
+ the phy side CA line(incluing command line,
+ address line and clock line) driver strength.
+ Default value is PHY_DRV_ODT_40.
+
+- rockchip,phy_ddr3_dq_drv : When dram type is DDR3, this parameter define
+ the phy side DQ line(incluing DQS/DQ/DM line)
+ driver strength. default value is PHY_DRV_ODT_40.
+
+- rockchip,phy_ddr3_odt : When dram type is DDR3, this parameter define the
+ phy side odt strength, default value is
+ PHY_DRV_ODT_240.
+
+- rockchip,lpddr3_odt_disb_freq : When dram type is LPDDR3, this parameter defined
+ then odt disable frequency in MHz (Mega Hz),
+ when ddr frequency less then ddr3_odt_disb_freq,
+ the odt on dram side and controller side are
+ both disabled.
+
+- rockchip,lpddr3_drv : When dram type is LPDDR3, this parameter define
+ the dram side driver stength in ohm, default
+ value is LP3_DS_34ohm.
+
+- rockchip,lpddr3_odt : When dram type is LPDDR3, this parameter define
+ the dram side ODT stength in ohm, default value
+ is LP3_ODT_240ohm.
+
+- rockchip,phy_lpddr3_ca_drv : When dram type is LPDDR3, this parameter define
+ the phy side CA line(incluing command line,
+ address line and clock line) driver strength.
+ default value is PHY_DRV_ODT_40.
+
+- rockchip,phy_lpddr3_dq_drv : When dram type is LPDDR3, this parameter define
+ the phy side DQ line(incluing DQS/DQ/DM line)
+ driver strength. default value is
+ PHY_DRV_ODT_40.
+
+- rockchip,phy_lpddr3_odt : When dram type is LPDDR3, this parameter define
+ the phy side odt strength, default value is
+ PHY_DRV_ODT_240.
+
+- rockchip,lpddr4_odt_disb_freq : When dram type is LPDDR4, this parameter
+ defined the odt disable frequency in
+ MHz (Mega Hz), when ddr frequency less then
+ ddr3_odt_disb_freq, the odt on dram side and
+ controller side are both disabled.
+
+- rockchip,lpddr4_drv : When dram type is LPDDR4, this parameter define
+ the dram side driver stength in ohm, default
+ value is LP4_PDDS_60ohm.
+
+- rockchip,lpddr4_dq_odt : When dram type is LPDDR4, this parameter define
+ the dram side ODT on dqs/dq line stength in ohm,
+ default value is LP4_DQ_ODT_40ohm.
+
+- rockchip,lpddr4_ca_odt : When dram type is LPDDR4, this parameter define
+ the dram side ODT on ca line stength in ohm,
+ default value is LP4_CA_ODT_40ohm.
+
+- rockchip,phy_lpddr4_ca_drv : When dram type is LPDDR4, this parameter define
+ the phy side CA line(incluing command address
+ line) driver strength. default value is
+ PHY_DRV_ODT_40.
+
+- rockchip,phy_lpddr4_ck_cs_drv : When dram type is LPDDR4, this parameter define
+ the phy side clock line and cs line driver
+ strength. default value is PHY_DRV_ODT_80.
+
+- rockchip,phy_lpddr4_dq_drv : When dram type is LPDDR4, this parameter define
+ the phy side DQ line(incluing DQS/DQ/DM line)
+ driver strength. default value is PHY_DRV_ODT_80.
+
+- rockchip,phy_lpddr4_odt : When dram type is LPDDR4, this parameter define
+ the phy side odt strength, default value is
+ PHY_DRV_ODT_60.
+
+Example:
+ dmc_opp_table: dmc_opp_table {
+ compatible = "operating-points-v2";
+
+ opp00 {
+ opp-hz = /bits/ 64 <300000000>;
+ opp-microvolt = <900000>;
+ };
+ opp01 {
+ opp-hz = /bits/ 64 <666000000>;
+ opp-microvolt = <900000>;
+ };
+ };
+
+ dmc: dmc {
+ compatible = "rockchip,rk3399-dmc";
+ devfreq-events = <&dfi>;
+ interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&cru SCLK_DDRCLK>;
+ clock-names = "dmc_clk";
+ operating-points-v2 = <&dmc_opp_table>;
+ center-supply = <&ppvar_centerlogic>;
+ upthreshold = <15>;
+ downdifferential = <10>;
+ rockchip,ddr3_speed_bin = <21>;
+ rockchip,pd_idle = <0x40>;
+ rockchip,sr_idle = <0x2>;
+ rockchip,sr_mc_gate_idle = <0x3>;
+ rockchip,srpd_lite_idle = <0x4>;
+ rockchip,standby_idle = <0x2000>;
+ rockchip,dram_dll_dis_freq = <300>;
+ rockchip,phy_dll_dis_freq = <125>;
+ rockchip,auto_pd_dis_freq = <666>;
+ rockchip,ddr3_odt_dis_freq = <333>;
+ rockchip,ddr3_drv = <DDR3_DS_40ohm>;
+ rockchip,ddr3_odt = <DDR3_ODT_120ohm>;
+ rockchip,phy_ddr3_ca_drv = <PHY_DRV_ODT_40>;
+ rockchip,phy_ddr3_dq_drv = <PHY_DRV_ODT_40>;
+ rockchip,phy_ddr3_odt = <PHY_DRV_ODT_240>;
+ rockchip,lpddr3_odt_dis_freq = <333>;
+ rockchip,lpddr3_drv = <LP3_DS_34ohm>;
+ rockchip,lpddr3_odt = <LP3_ODT_240ohm>;
+ rockchip,phy_lpddr3_ca_drv = <PHY_DRV_ODT_40>;
+ rockchip,phy_lpddr3_dq_drv = <PHY_DRV_ODT_40>;
+ rockchip,phy_lpddr3_odt = <PHY_DRV_ODT_240>;
+ rockchip,lpddr4_odt_dis_freq = <333>;
+ rockchip,lpddr4_drv = <LP4_PDDS_60ohm>;
+ rockchip,lpddr4_dq_odt = <LP4_DQ_ODT_40ohm>;
+ rockchip,lpddr4_ca_odt = <LP4_CA_ODT_40ohm>;
+ rockchip,phy_lpddr4_ca_drv = <PHY_DRV_ODT_40>;
+ rockchip,phy_lpddr4_ck_cs_drv = <PHY_DRV_ODT_80>;
+ rockchip,phy_lpddr4_dq_drv = <PHY_DRV_ODT_80>;
+ rockchip,phy_lpddr4_odt = <PHY_DRV_ODT_60>;
+ status = "disabled";
+ };
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a4f4d69..25037de 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -698,6 +698,15 @@
loops can be debugged more effectively on production
systems.
+ clocksource.arm_arch_timer.fsl-a008585=
+ [ARM64]
+ Format: <bool>
+ Enable/disable the workaround of Freescale/NXP
+ erratum A-008585. This can be useful for KVM
+ guests, if the guest device tree doesn't show the
+ erratum. If unspecified, the workaround is
+ enabled based on the device tree.
+
clearcpuid=BITNUM [X86]
Disable CPUID feature X for the kernel. See
arch/x86/include/asm/cpufeatures.h for the valid bit
diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt
index 477927b..ea8d7b4 100644
--- a/Documentation/static-keys.txt
+++ b/Documentation/static-keys.txt
@@ -15,6 +15,8 @@
DEFINE_STATIC_KEY_TRUE(key);
DEFINE_STATIC_KEY_FALSE(key);
+DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
static_branch_likely()
static_branch_unlikely()
@@ -140,6 +142,13 @@
key is initialized false, a 'static_branch_inc()', will change the branch to
true. And then a 'static_branch_dec()', will again make the branch false.
+Where an array of keys is required, it can be defined as:
+
+ DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+
+or:
+
+ DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
4) Architecture level code patching interface, 'jump labels'
diff --git a/MAINTAINERS b/MAINTAINERS
index 01bff8e..c8926c1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -913,15 +913,17 @@
ARM PMU PROFILING AND DEBUGGING
M: Will Deacon <will.deacon@arm.com>
-R: Mark Rutland <mark.rutland@arm.com>
+M: Mark Rutland <mark.rutland@arm.com>
S: Maintained
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
F: arch/arm*/kernel/perf_*
F: arch/arm/oprofile/common.c
F: arch/arm*/kernel/hw_breakpoint.c
F: arch/arm*/include/asm/hw_breakpoint.h
F: arch/arm*/include/asm/perf_event.h
-F: drivers/perf/arm_pmu.c
+F: drivers/perf/*
F: include/linux/perf/arm_pmu.h
+F: Documentation/devicetree/bindings/arm/pmu.txt
ARM PORT
M: Russell King <linux@armlinux.org.uk>
@@ -3282,6 +3284,7 @@
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
T: git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates)
+F: Documentation/cpu-freq/
F: drivers/cpufreq/
F: include/linux/cpufreq.h
@@ -8745,7 +8748,7 @@
F: include/linux/oprofile.h
ORACLE CLUSTER FILESYSTEM 2 (OCFS2)
-M: Mark Fasheh <mfasheh@suse.com>
+M: Mark Fasheh <mfasheh@versity.com>
M: Joel Becker <jlbec@evilplan.org>
L: ocfs2-devel@oss.oracle.com (moderated for non-subscribers)
W: http://ocfs2.wiki.kernel.org
@@ -11626,7 +11629,7 @@
THERMAL/CPU_COOLING
M: Amit Daniel Kachhap <amit.kachhap@gmail.com>
M: Viresh Kumar <viresh.kumar@linaro.org>
-M: Javi Merino <javi.merino@arm.com>
+M: Javi Merino <javi.merino@kernel.org>
L: linux-pm@vger.kernel.org
S: Supported
F: Documentation/thermal/cpu-cooling-api.txt
diff --git a/Makefile b/Makefile
index ce2ddb3..80b8671 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
PATCHLEVEL = 8
SUBLEVEL = 0
-EXTRAVERSION = -rc8
+EXTRAVERSION =
NAME = Psychotic Stoned Sheep
# *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a9c4e48..b2113c2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1,6 +1,7 @@
config ARM
bool
default y
+ select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index af11c2f..fc6d541 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -779,7 +779,7 @@
orrne r0, r0, #1 @ MMU enabled
movne r1, #0xfffffffd @ domain 0 = client
bic r6, r6, #1 << 31 @ 32-bit translation system
- bic r6, r6, #3 << 0 @ use only ttbr0
+ bic r6, r6, #(7 << 0) | (1 << 4) @ use only ttbr0
mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer
mcrne p15, 0, r1, c3, c0, 0 @ load domain access control
mcrne p15, 0, r6, c2, c0, 2 @ load ttb control
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 01986de..36cc7cc 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -28,7 +28,7 @@
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
-CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
+CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
CONFIG_CPUFREQ_DT=y
CONFIG_CPU_IDLE=y
CONFIG_ARM_EXYNOS_CPUIDLE=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index ea3566f..5845910 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -135,7 +135,7 @@
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
-CONFIG_CPU_FREQ_GOV_SCHEDUTIL=m
+CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
CONFIG_QORIQ_CPUFREQ=y
CONFIG_CPU_IDLE=y
CONFIG_ARM_CPUIDLE=y
diff --git a/arch/arm/include/asm/clocksource.h b/arch/arm/include/asm/clocksource.h
new file mode 100644
index 0000000..0b350a7
--- /dev/null
+++ b/arch/arm/include/asm/clocksource.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+ bool vdso_direct; /* Usable for direct VDSO access? */
+};
+
+#endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index d009f79..bf02dbd 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -111,7 +111,7 @@
/* The ARM override for dma_max_pfn() */
static inline unsigned long dma_max_pfn(struct device *dev)
{
- return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask);
+ return dma_to_pfn(dev, *dev->dma_mask);
}
#define dma_max_pfn(dev) dma_max_pfn(dev)
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 40ecd5f..f676feb 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -88,6 +88,8 @@
return;
for_each_child_of_node(cpus, cpu) {
+ const __be32 *cell;
+ int prop_bytes;
u32 hwid;
if (of_node_cmp(cpu->type, "cpu"))
@@ -99,7 +101,8 @@
* properties is considered invalid to build the
* cpu_logical_map.
*/
- if (of_property_read_u32(cpu, "reg", &hwid)) {
+ cell = of_get_property(cpu, "reg", &prop_bytes);
+ if (!cell || prop_bytes < sizeof(*cell)) {
pr_debug(" * %s missing reg property\n",
cpu->full_name);
of_node_put(cpu);
@@ -107,10 +110,15 @@
}
/*
- * 8 MSBs must be set to 0 in the DT since the reg property
+ * Bits n:24 must be set to 0 in the DT since the reg property
* defines the MPIDR[23:0].
*/
- if (hwid & ~MPIDR_HWID_BITMASK) {
+ do {
+ hwid = be32_to_cpu(*cell++);
+ prop_bytes -= sizeof(*cell);
+ } while (!hwid && prop_bytes > 0);
+
+ if (prop_bytes || (hwid & ~MPIDR_HWID_BITMASK)) {
of_node_put(cpu);
return;
}
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 1506385..b942349 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -596,12 +596,6 @@
.attrs = armv7_pmuv1_event_attrs,
};
-static const struct attribute_group *armv7_pmuv1_attr_groups[] = {
- &armv7_pmuv1_events_attr_group,
- &armv7_pmu_format_attr_group,
- NULL,
-};
-
ARMV7_EVENT_ATTR(mem_access, ARMV7_PERFCTR_MEM_ACCESS);
ARMV7_EVENT_ATTR(l1i_cache, ARMV7_PERFCTR_L1_ICACHE_ACCESS);
ARMV7_EVENT_ATTR(l1d_cache_wb, ARMV7_PERFCTR_L1_DCACHE_WB);
@@ -653,12 +647,6 @@
.attrs = armv7_pmuv2_event_attrs,
};
-static const struct attribute_group *armv7_pmuv2_attr_groups[] = {
- &armv7_pmuv2_events_attr_group,
- &armv7_pmu_format_attr_group,
- NULL,
-};
-
/*
* Perf Events' indices
*/
@@ -1208,7 +1196,10 @@
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a8";
cpu_pmu->map_event = armv7_a8_map_event;
- cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv1_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1217,7 +1208,10 @@
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a9";
cpu_pmu->map_event = armv7_a9_map_event;
- cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv1_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1226,7 +1220,10 @@
armv7pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a5";
cpu_pmu->map_event = armv7_a5_map_event;
- cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv1_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1236,7 +1233,10 @@
cpu_pmu->name = "armv7_cortex_a15";
cpu_pmu->map_event = armv7_a15_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1246,7 +1246,10 @@
cpu_pmu->name = "armv7_cortex_a7";
cpu_pmu->map_event = armv7_a7_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1256,7 +1259,10 @@
cpu_pmu->name = "armv7_cortex_a12";
cpu_pmu->map_event = armv7_a12_map_event;
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return armv7_probe_num_events(cpu_pmu);
}
@@ -1264,7 +1270,10 @@
{
int ret = armv7_a12_pmu_init(cpu_pmu);
cpu_pmu->name = "armv7_cortex_a17";
- cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv7_pmuv2_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv7_pmu_format_attr_group;
return ret;
}
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 994e971..a0affd1 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -270,7 +270,7 @@
if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
return false;
- if (strcmp(tk->tkr_mono.clock->name, "arch_sys_counter") != 0)
+ if (!tk->tkr_mono.clock->archdata.vdso_direct)
return false;
return true;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index bc3f00f..17c14a1d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -4,6 +4,7 @@
select ACPI_GENERIC_GSI if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
select ACPI_MCFG if ACPI
+ select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -102,10 +103,8 @@
select NO_BOOTMEM
select OF
select OF_EARLY_FLATTREE
- select OF_NUMA if NUMA && OF
select OF_RESERVED_MEM
select PCI_ECAM if ACPI
- select PERF_USE_VMALLOC
select POWER_RESET
select POWER_SUPPLY
select SPARSE_IRQ
@@ -122,6 +121,9 @@
config MMU
def_bool y
+config DEBUG_RODATA
+ def_bool y
+
config ARM64_PAGE_SHIFT
int
default 16 if ARM64_64K_PAGES
@@ -415,18 +417,13 @@
config ARM64_ERRATUM_843419
bool "Cortex-A53: 843419: A load or store might access an incorrect address"
- depends on MODULES
default y
- select ARM64_MODULE_CMODEL_LARGE
+ select ARM64_MODULE_CMODEL_LARGE if MODULES
help
- This option builds kernel modules using the large memory model in
- order to avoid the use of the ADRP instruction, which can cause
- a subsequent memory access to use an incorrect address on Cortex-A53
- parts up to r0p4.
-
- Note that the kernel itself must be linked with a version of ld
- which fixes potentially affected ADRP instructions through the
- use of veneers.
+ This option links the kernel with '--fix-cortex-a53-843419' and
+ builds modules using the large memory model in order to avoid the use
+ of the ADRP instruction, which can cause a subsequent memory access
+ to use an incorrect address on Cortex-A53 parts up to r0p4.
If unsure, say Y.
@@ -582,7 +579,8 @@
# Common NUMA Features
config NUMA
bool "Numa Memory Allocation and Scheduler Support"
- depends on SMP
+ select ACPI_NUMA if ACPI
+ select OF_NUMA
help
Enable NUMA (Non Uniform Memory Access) support.
@@ -603,11 +601,18 @@
def_bool y
depends on NUMA
+config HAVE_SETUP_PER_CPU_AREA
+ def_bool y
+ depends on NUMA
+
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+ def_bool y
+ depends on NUMA
+
source kernel/Kconfig.preempt
source kernel/Kconfig.hz
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
- depends on !HIBERNATION
def_bool y
config ARCH_HAS_HOLES_MEMORYMODEL
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 0cc758c..b661fe7 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -49,16 +49,6 @@
If in doubt, say Y.
-config DEBUG_RODATA
- bool "Make kernel text and rodata read-only"
- default y
- help
- If this is set, kernel text and rodata will be made read-only. This
- is to help catch accidental or malicious attempts to change the
- kernel's executable code.
-
- If in doubt, say Y.
-
config DEBUG_ALIGN_RODATA
depends on DEBUG_RODATA
bool "Align linker sections up to SECTION_SIZE"
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index be5d824..4a4318b 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -159,7 +159,6 @@
select CLKSRC_MMIO
select CLKSRC_OF
select GENERIC_CLOCKEVENTS
- select HAVE_CLK
select PINCTRL
select RESET_CONTROLLER
help
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 5b54f8c..ab51aed 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -18,6 +18,14 @@
LDFLAGS_vmlinux += -pie -Bsymbolic
endif
+ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
+ ifeq ($(call ld-option, --fix-cortex-a53-843419),)
+$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum)
+ else
+LDFLAGS_vmlinux += --fix-cortex-a53-843419
+ endif
+endif
+
KBUILD_DEFCONFIG := defconfig
# Check for binutils support for specific extensions
@@ -38,10 +46,12 @@
KBUILD_CPPFLAGS += -mbig-endian
AS += -EB
LD += -EB
+UTS_MACHINE := aarch64_be
else
KBUILD_CPPFLAGS += -mlittle-endian
AS += -EL
LD += -EL
+UTS_MACHINE := aarch64
endif
CHECKFLAGS += -D__aarch64__
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index f43d2c4..44e1d7f 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,4 +1,3 @@
-generic-y += bug.h
generic-y += bugs.h
generic-y += clkdev.h
generic-y += cputime.h
@@ -10,7 +9,6 @@
generic-y += early_ioremap.h
generic-y += emergency-restart.h
generic-y += errno.h
-generic-y += ftrace.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
@@ -27,12 +25,10 @@
generic-y += msgbuf.h
generic-y += msi.h
generic-y += mutex.h
-generic-y += pci.h
generic-y += poll.h
generic-y += preempt.h
generic-y += resource.h
generic-y += rwsem.h
-generic-y += sections.h
generic-y += segment.h
generic-y += sembuf.h
generic-y += serial.h
@@ -45,7 +41,6 @@
generic-y += switch_to.h
generic-y += termbits.h
generic-y += termios.h
-generic-y += topology.h
generic-y += trace_clock.h
generic-y += types.h
generic-y += unaligned.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 5420cb0..e517088 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -12,7 +12,7 @@
#ifndef _ASM_ACPI_H
#define _ASM_ACPI_H
-#include <linux/mm.h>
+#include <linux/memblock.h>
#include <linux/psci.h>
#include <asm/cputype.h>
@@ -32,7 +32,11 @@
static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
acpi_size size)
{
- if (!page_is_ram(phys >> PAGE_SHIFT))
+ /*
+ * EFI's reserve_regions() call adds memory with the WB attribute
+ * to memblock via early_init_dt_add_memory_arch().
+ */
+ if (!memblock_is_memory(phys))
return ioremap(phys, size);
return ioremap_cache(phys, size);
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 8746ff6..55101bd 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -2,6 +2,7 @@
#define __ASM_ALTERNATIVE_H
#include <asm/cpufeature.h>
+#include <asm/insn.h>
#ifndef __ASSEMBLY__
@@ -90,24 +91,15 @@
.endm
/*
- * Begin an alternative code sequence.
+ * Alternative sequences
*
- * The code that follows this macro will be assembled and linked as
- * normal. There are no restrictions on this code.
- */
-.macro alternative_if_not cap
- .pushsection .altinstructions, "a"
- altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
- .popsection
-661:
-.endm
-
-/*
- * Provide the alternative code sequence.
+ * The code for the case where the capability is not present will be
+ * assembled and linked as normal. There are no restrictions on this
+ * code.
*
- * The code that follows this macro is assembled into a special
- * section to be used for dynamic patching. Code that follows this
- * macro must:
+ * The code for the case where the capability is present will be
+ * assembled into a special section to be used for dynamic patching.
+ * Code for that case must:
*
* 1. Be exactly the same length (in bytes) as the default code
* sequence.
@@ -116,8 +108,38 @@
* alternative sequence it is defined in (branches into an
* alternative sequence are not fixed up).
*/
+
+/*
+ * Begin an alternative code sequence.
+ */
+.macro alternative_if_not cap
+ .set .Lasm_alt_mode, 0
+ .pushsection .altinstructions, "a"
+ altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
+ .popsection
+661:
+.endm
+
+.macro alternative_if cap
+ .set .Lasm_alt_mode, 1
+ .pushsection .altinstructions, "a"
+ altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
+ .popsection
+ .pushsection .altinstr_replacement, "ax"
+ .align 2 /* So GAS knows label 661 is suitably aligned */
+661:
+.endm
+
+/*
+ * Provide the other half of the alternative code sequence.
+ */
.macro alternative_else
-662: .pushsection .altinstr_replacement, "ax"
+662:
+ .if .Lasm_alt_mode==0
+ .pushsection .altinstr_replacement, "ax"
+ .else
+ .popsection
+ .endif
663:
.endm
@@ -125,11 +147,25 @@
* Complete an alternative code sequence.
*/
.macro alternative_endif
-664: .popsection
+664:
+ .if .Lasm_alt_mode==0
+ .popsection
+ .endif
.org . - (664b-663b) + (662b-661b)
.org . - (662b-661b) + (664b-663b)
.endm
+/*
+ * Provides a trivial alternative or default sequence consisting solely
+ * of NOPs. The number of NOPs is chosen automatically to match the
+ * previous case.
+ */
+.macro alternative_else_nop_endif
+alternative_else
+ nops (662b-661b) / AARCH64_INSN_SIZE
+alternative_endif
+.endm
+
#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \
alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index fbe0ca3..eaa5bbe 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -20,13 +20,55 @@
#define __ASM_ARCH_TIMER_H
#include <asm/barrier.h>
+#include <asm/sysreg.h>
#include <linux/bug.h>
#include <linux/init.h>
+#include <linux/jump_label.h>
#include <linux/types.h>
#include <clocksource/arm_arch_timer.h>
+#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585)
+extern struct static_key_false arch_timer_read_ool_enabled;
+#define needs_fsl_a008585_workaround() \
+ static_branch_unlikely(&arch_timer_read_ool_enabled)
+#else
+#define needs_fsl_a008585_workaround() false
+#endif
+
+u32 __fsl_a008585_read_cntp_tval_el0(void);
+u32 __fsl_a008585_read_cntv_tval_el0(void);
+u64 __fsl_a008585_read_cntvct_el0(void);
+
+/*
+ * The number of retries is an arbitrary value well beyond the highest number
+ * of iterations the loop has been observed to take.
+ */
+#define __fsl_a008585_read_reg(reg) ({ \
+ u64 _old, _new; \
+ int _retries = 200; \
+ \
+ do { \
+ _old = read_sysreg(reg); \
+ _new = read_sysreg(reg); \
+ _retries--; \
+ } while (unlikely(_old != _new) && _retries); \
+ \
+ WARN_ON_ONCE(!_retries); \
+ _new; \
+})
+
+#define arch_timer_reg_read_stable(reg) \
+({ \
+ u64 _val; \
+ if (needs_fsl_a008585_workaround()) \
+ _val = __fsl_a008585_read_##reg(); \
+ else \
+ _val = read_sysreg(reg); \
+ _val; \
+})
+
/*
* These register accessors are marked inline so the compiler can
* nicely work out which register we want, and chuck away the rest of
@@ -38,19 +80,19 @@
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("msr cntp_ctl_el0, %0" : : "r" (val));
+ write_sysreg(val, cntp_ctl_el0);
break;
case ARCH_TIMER_REG_TVAL:
- asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
+ write_sysreg(val, cntp_tval_el0);
break;
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("msr cntv_ctl_el0, %0" : : "r" (val));
+ write_sysreg(val, cntv_ctl_el0);
break;
case ARCH_TIMER_REG_TVAL:
- asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
+ write_sysreg(val, cntv_tval_el0);
break;
}
}
@@ -61,48 +103,38 @@
static __always_inline
u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
{
- u32 val;
-
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("mrs %0, cntp_ctl_el0" : "=r" (val));
- break;
+ return read_sysreg(cntp_ctl_el0);
case ARCH_TIMER_REG_TVAL:
- asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
- break;
+ return arch_timer_reg_read_stable(cntp_tval_el0);
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
- asm volatile("mrs %0, cntv_ctl_el0" : "=r" (val));
- break;
+ return read_sysreg(cntv_ctl_el0);
case ARCH_TIMER_REG_TVAL:
- asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
- break;
+ return arch_timer_reg_read_stable(cntv_tval_el0);
}
}
- return val;
+ BUG();
}
static inline u32 arch_timer_get_cntfrq(void)
{
- u32 val;
- asm volatile("mrs %0, cntfrq_el0" : "=r" (val));
- return val;
+ return read_sysreg(cntfrq_el0);
}
static inline u32 arch_timer_get_cntkctl(void)
{
- u32 cntkctl;
- asm volatile("mrs %0, cntkctl_el1" : "=r" (cntkctl));
- return cntkctl;
+ return read_sysreg(cntkctl_el1);
}
static inline void arch_timer_set_cntkctl(u32 cntkctl)
{
- asm volatile("msr cntkctl_el1, %0" : : "r" (cntkctl));
+ write_sysreg(cntkctl, cntkctl_el1);
}
static inline u64 arch_counter_get_cntpct(void)
@@ -116,12 +148,8 @@
static inline u64 arch_counter_get_cntvct(void)
{
- u64 cval;
-
isb();
- asm volatile("mrs %0, cntvct_el0" : "=r" (cval));
-
- return cval;
+ return arch_timer_reg_read_stable(cntvct_el0);
}
static inline int arch_timer_arch_init(void)
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index d5025c6..28bfe61 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -87,6 +87,15 @@
.endm
/*
+ * NOP sequence
+ */
+ .macro nops, num
+ .rept \num
+ nop
+ .endr
+ .endm
+
+/*
* Emit an entry into the exception table
*/
.macro _asm_extable, from, to
@@ -216,11 +225,26 @@
.macro mmid, rd, rn
ldr \rd, [\rn, #MM_CONTEXT_ID]
.endm
+/*
+ * read_ctr - read CTR_EL0. If the system has mismatched
+ * cache line sizes, provide the system wide safe value
+ * from arm64_ftr_reg_ctrel0.sys_val
+ */
+ .macro read_ctr, reg
+alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE
+ mrs \reg, ctr_el0 // read CTR
+ nop
+alternative_else
+ ldr_l \reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL
+alternative_endif
+ .endm
+
/*
- * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ * raw_dcache_line_size - get the minimum D-cache line size on this CPU
+ * from the CTR register.
*/
- .macro dcache_line_size, reg, tmp
+ .macro raw_dcache_line_size, reg, tmp
mrs \tmp, ctr_el0 // read CTR
ubfm \tmp, \tmp, #16, #19 // cache line size encoding
mov \reg, #4 // bytes per word
@@ -228,9 +252,20 @@
.endm
/*
- * icache_line_size - get the minimum I-cache line size from the CTR register.
+ * dcache_line_size - get the safe D-cache line size across all CPUs
*/
- .macro icache_line_size, reg, tmp
+ .macro dcache_line_size, reg, tmp
+ read_ctr \tmp
+ ubfm \tmp, \tmp, #16, #19 // cache line size encoding
+ mov \reg, #4 // bytes per word
+ lsl \reg, \reg, \tmp // actual cache line size
+ .endm
+
+/*
+ * raw_icache_line_size - get the minimum I-cache line size on this CPU
+ * from the CTR register.
+ */
+ .macro raw_icache_line_size, reg, tmp
mrs \tmp, ctr_el0 // read CTR
and \tmp, \tmp, #0xf // cache line size encoding
mov \reg, #4 // bytes per word
@@ -238,6 +273,16 @@
.endm
/*
+ * icache_line_size - get the safe I-cache line size across all CPUs
+ */
+ .macro icache_line_size, reg, tmp
+ read_ctr \tmp
+ and \tmp, \tmp, #0xf // cache line size encoding
+ mov \reg, #4 // bytes per word
+ lsl \reg, \reg, \tmp // actual cache line size
+ .endm
+
+/*
* tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
*/
.macro tcr_set_idmap_t0sz, valreg, tmpreg
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index b5890be..7457ce0 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -86,8 +86,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC(add_return##name), \
+ __LL_SC_ATOMIC(add_return##name) \
+ __nops(1), \
/* LSE atomics */ \
" ldadd" #mb " %w[i], w30, %[v]\n" \
" add %w[i], %w[i], w30") \
@@ -112,8 +112,8 @@
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC(and),
+ __LL_SC_ATOMIC(and)
+ __nops(1),
/* LSE atomics */
" mvn %w[i], %w[i]\n"
" stclr %w[i], %[v]")
@@ -130,8 +130,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC(fetch_and##name), \
+ __LL_SC_ATOMIC(fetch_and##name) \
+ __nops(1), \
/* LSE atomics */ \
" mvn %w[i], %w[i]\n" \
" ldclr" #mb " %w[i], %w[i], %[v]") \
@@ -156,8 +156,8 @@
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC(sub),
+ __LL_SC_ATOMIC(sub)
+ __nops(1),
/* LSE atomics */
" neg %w[i], %w[i]\n"
" stadd %w[i], %[v]")
@@ -174,9 +174,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
__LL_SC_ATOMIC(sub_return##name) \
- " nop", \
+ __nops(2), \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], w30, %[v]\n" \
@@ -203,8 +202,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC(fetch_sub##name), \
+ __LL_SC_ATOMIC(fetch_sub##name) \
+ __nops(1), \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], %w[i], %[v]") \
@@ -284,8 +283,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC64(add_return##name), \
+ __LL_SC_ATOMIC64(add_return##name) \
+ __nops(1), \
/* LSE atomics */ \
" ldadd" #mb " %[i], x30, %[v]\n" \
" add %[i], %[i], x30") \
@@ -310,8 +309,8 @@
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC64(and),
+ __LL_SC_ATOMIC64(and)
+ __nops(1),
/* LSE atomics */
" mvn %[i], %[i]\n"
" stclr %[i], %[v]")
@@ -328,8 +327,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC64(fetch_and##name), \
+ __LL_SC_ATOMIC64(fetch_and##name) \
+ __nops(1), \
/* LSE atomics */ \
" mvn %[i], %[i]\n" \
" ldclr" #mb " %[i], %[i], %[v]") \
@@ -354,8 +353,8 @@
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC64(sub),
+ __LL_SC_ATOMIC64(sub)
+ __nops(1),
/* LSE atomics */
" neg %[i], %[i]\n"
" stadd %[i], %[v]")
@@ -372,9 +371,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
__LL_SC_ATOMIC64(sub_return##name) \
- " nop", \
+ __nops(2), \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], x30, %[v]\n" \
@@ -401,8 +399,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_ATOMIC64(fetch_sub##name), \
+ __LL_SC_ATOMIC64(fetch_sub##name) \
+ __nops(1), \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], %[i], %[v]") \
@@ -426,13 +424,8 @@
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
- " nop\n"
__LL_SC_ATOMIC64(dec_if_positive)
- " nop\n"
- " nop\n"
- " nop\n"
- " nop\n"
- " nop",
+ __nops(6),
/* LSE atomics */
"1: ldr x30, %[v]\n"
" subs %[ret], x30, #1\n"
@@ -464,9 +457,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- __LL_SC_CMPXCHG(name) \
- " nop", \
+ __LL_SC_CMPXCHG(name) \
+ __nops(2), \
/* LSE atomics */ \
" mov " #w "30, %" #w "[old]\n" \
" cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \
@@ -517,10 +509,8 @@
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
- " nop\n" \
- " nop\n" \
- " nop\n" \
- __LL_SC_CMPXCHG_DBL(name), \
+ __LL_SC_CMPXCHG_DBL(name) \
+ __nops(3), \
/* LSE atomics */ \
" casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
" eor %[old1], %[old1], %[oldval1]\n" \
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 4eea7f6..4e0497f 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -20,6 +20,9 @@
#ifndef __ASSEMBLY__
+#define __nops(n) ".rept " #n "\nnop\n.endr\n"
+#define nops(n) asm volatile(__nops(n))
+
#define sev() asm volatile("sev" : : : "memory")
#define wfe() asm volatile("wfe" : : : "memory")
#define wfi() asm volatile("wfi" : : : "memory")
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index c64268d..2e5fb97 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -68,6 +68,7 @@
extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void flush_icache_range(unsigned long start, unsigned long end);
extern void __flush_dcache_area(void *addr, size_t len);
+extern void __clean_dcache_area_poc(void *addr, size_t len);
extern void __clean_dcache_area_pou(void *addr, size_t len);
extern long __flush_cache_user_range(unsigned long start, unsigned long end);
@@ -85,7 +86,7 @@
*/
extern void __dma_map_area(const void *, size_t, int);
extern void __dma_unmap_area(const void *, size_t, int);
-extern void __dma_flush_range(const void *, const void *);
+extern void __dma_flush_area(const void *, size_t);
/*
* Copy user data from/to a page which is mapped into a different
diff --git a/arch/arm64/include/asm/clocksource.h b/arch/arm64/include/asm/clocksource.h
new file mode 100644
index 0000000..0b350a7
--- /dev/null
+++ b/arch/arm64/include/asm/clocksource.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+ bool vdso_direct; /* Usable for direct VDSO access? */
+};
+
+#endif
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index bd86a79..91b26d2 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -43,10 +43,8 @@
" cbnz %w1, 1b\n" \
" " #mb, \
/* LSE atomics */ \
- " nop\n" \
- " nop\n" \
" swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \
- " nop\n" \
+ __nops(3) \
" " #nop_lse) \
: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) \
: "r" (x) \
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 7099f26..758d74f 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -9,6 +9,8 @@
#ifndef __ASM_CPUFEATURE_H
#define __ASM_CPUFEATURE_H
+#include <linux/jump_label.h>
+
#include <asm/hwcap.h>
#include <asm/sysreg.h>
@@ -37,8 +39,9 @@
#define ARM64_WORKAROUND_CAVIUM_27456 12
#define ARM64_HAS_32BIT_EL0 13
#define ARM64_HYP_OFFSET_LOW 14
+#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15
-#define ARM64_NCAPS 15
+#define ARM64_NCAPS 16
#ifndef __ASSEMBLY__
@@ -63,7 +66,7 @@
enum ftr_type type;
u8 shift;
u8 width;
- s64 safe_val; /* safe value for discrete features */
+ s64 safe_val; /* safe value for FTR_EXACT features */
};
/*
@@ -72,13 +75,14 @@
* @sys_val Safe value across the CPUs (system view)
*/
struct arm64_ftr_reg {
- u32 sys_id;
- const char *name;
- u64 strict_mask;
- u64 sys_val;
- struct arm64_ftr_bits *ftr_bits;
+ const char *name;
+ u64 strict_mask;
+ u64 sys_val;
+ const struct arm64_ftr_bits *ftr_bits;
};
+extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
+
/* scope of capability check */
enum {
SCOPE_SYSTEM,
@@ -109,6 +113,7 @@
};
extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
bool this_cpu_has_cap(unsigned int cap);
@@ -121,16 +126,21 @@
{
if (num >= ARM64_NCAPS)
return false;
- return test_bit(num, cpu_hwcaps);
+ if (__builtin_constant_p(num))
+ return static_branch_unlikely(&cpu_hwcap_keys[num]);
+ else
+ return test_bit(num, cpu_hwcaps);
}
static inline void cpus_set_cap(unsigned int num)
{
- if (num >= ARM64_NCAPS)
+ if (num >= ARM64_NCAPS) {
pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
num, ARM64_NCAPS);
- else
+ } else {
__set_bit(num, cpu_hwcaps);
+ static_branch_enable(&cpu_hwcap_keys[num]);
+ }
}
static inline int __attribute_const__
@@ -157,7 +167,7 @@
return cpuid_feature_extract_unsigned_field_width(features, field, 4);
}
-static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
+static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
{
return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
}
@@ -170,7 +180,7 @@
cpuid_feature_extract_unsigned_field(features, field);
}
-static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
+static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val)
{
return (s64)cpuid_feature_extract_field(val, ftrp->shift, ftrp->sign);
}
@@ -193,11 +203,11 @@
void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
const char *info);
void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps);
-void check_local_cpu_errata(void);
-void __init enable_errata_workarounds(void);
+void check_local_cpu_capabilities(void);
-void verify_local_cpu_errata(void);
-void verify_local_cpu_capabilities(void);
+void update_cpu_errata_workarounds(void);
+void __init enable_errata_workarounds(void);
+void verify_local_cpu_errata_workarounds(void);
u64 read_system_reg(u32 id);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 9d9fd4b..26a68dd 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -93,11 +93,7 @@
#include <asm/sysreg.h>
-#define read_cpuid(reg) ({ \
- u64 __val; \
- asm("mrs_s %0, " __stringify(SYS_ ## reg) : "=r" (__val)); \
- __val; \
-})
+#define read_cpuid(reg) read_sysreg_s(SYS_ ## reg)
/*
* The CPU ID never changes at run time, so we might as well tell the
diff --git a/arch/arm64/include/asm/dcc.h b/arch/arm64/include/asm/dcc.h
index 65e0190..836b056 100644
--- a/arch/arm64/include/asm/dcc.h
+++ b/arch/arm64/include/asm/dcc.h
@@ -21,21 +21,16 @@
#define __ASM_DCC_H
#include <asm/barrier.h>
+#include <asm/sysreg.h>
static inline u32 __dcc_getstatus(void)
{
- u32 ret;
-
- asm volatile("mrs %0, mdccsr_el0" : "=r" (ret));
-
- return ret;
+ return read_sysreg(mdccsr_el0);
}
static inline char __dcc_getchar(void)
{
- char c;
-
- asm volatile("mrs %0, dbgdtrrx_el0" : "=r" (c));
+ char c = read_sysreg(dbgdtrrx_el0);
isb();
return c;
@@ -47,8 +42,7 @@
* The typecast is to make absolutely certain that 'c' is
* zero-extended.
*/
- asm volatile("msr dbgdtrtx_el0, %0"
- : : "r" ((unsigned long)(unsigned char)c));
+ write_sysreg((unsigned char)c, dbgdtrtx_el0);
isb();
}
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index f772e15..d14c478 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -78,6 +78,23 @@
#define ESR_ELx_IL (UL(1) << 25)
#define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1)
+
+/* ISS field definitions shared by different classes */
+#define ESR_ELx_WNR (UL(1) << 6)
+
+/* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_EA (UL(1) << 9)
+#define ESR_ELx_S1PTW (UL(1) << 7)
+
+/* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
+#define ESR_ELx_FSC (0x3F)
+#define ESR_ELx_FSC_TYPE (0x3C)
+#define ESR_ELx_FSC_EXTABT (0x10)
+#define ESR_ELx_FSC_ACCESS (0x08)
+#define ESR_ELx_FSC_FAULT (0x04)
+#define ESR_ELx_FSC_PERM (0x0C)
+
+/* ISS field definitions for Data Aborts */
#define ESR_ELx_ISV (UL(1) << 24)
#define ESR_ELx_SAS_SHIFT (22)
#define ESR_ELx_SAS (UL(3) << ESR_ELx_SAS_SHIFT)
@@ -86,16 +103,9 @@
#define ESR_ELx_SRT_MASK (UL(0x1F) << ESR_ELx_SRT_SHIFT)
#define ESR_ELx_SF (UL(1) << 15)
#define ESR_ELx_AR (UL(1) << 14)
-#define ESR_ELx_EA (UL(1) << 9)
#define ESR_ELx_CM (UL(1) << 8)
-#define ESR_ELx_S1PTW (UL(1) << 7)
-#define ESR_ELx_WNR (UL(1) << 6)
-#define ESR_ELx_FSC (0x3F)
-#define ESR_ELx_FSC_TYPE (0x3C)
-#define ESR_ELx_FSC_EXTABT (0x10)
-#define ESR_ELx_FSC_ACCESS (0x08)
-#define ESR_ELx_FSC_FAULT (0x04)
-#define ESR_ELx_FSC_PERM (0x0C)
+
+/* ISS field definitions for exceptions taken in to Hyp */
#define ESR_ELx_CV (UL(1) << 24)
#define ESR_ELx_COND_SHIFT (20)
#define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -109,6 +119,62 @@
((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL | \
((imm) & 0xffff))
+/* ISS field definitions for System instruction traps */
+#define ESR_ELx_SYS64_ISS_RES0_SHIFT 22
+#define ESR_ELx_SYS64_ISS_RES0_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_RES0_SHIFT)
+#define ESR_ELx_SYS64_ISS_DIR_MASK 0x1
+#define ESR_ELx_SYS64_ISS_DIR_READ 0x1
+#define ESR_ELx_SYS64_ISS_DIR_WRITE 0x0
+
+#define ESR_ELx_SYS64_ISS_RT_SHIFT 5
+#define ESR_ELx_SYS64_ISS_RT_MASK (UL(0x1f) << ESR_ELx_SYS64_ISS_RT_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRM_SHIFT 1
+#define ESR_ELx_SYS64_ISS_CRM_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRM_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRN_SHIFT 10
+#define ESR_ELx_SYS64_ISS_CRN_MASK (UL(0xf) << ESR_ELx_SYS64_ISS_CRN_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP1_SHIFT 14
+#define ESR_ELx_SYS64_ISS_OP1_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP1_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP2_SHIFT 17
+#define ESR_ELx_SYS64_ISS_OP2_MASK (UL(0x7) << ESR_ELx_SYS64_ISS_OP2_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP0_SHIFT 20
+#define ESR_ELx_SYS64_ISS_OP0_MASK (UL(0x3) << ESR_ELx_SYS64_ISS_OP0_SHIFT)
+#define ESR_ELx_SYS64_ISS_SYS_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \
+ ESR_ELx_SYS64_ISS_OP1_MASK | \
+ ESR_ELx_SYS64_ISS_OP2_MASK | \
+ ESR_ELx_SYS64_ISS_CRN_MASK | \
+ ESR_ELx_SYS64_ISS_CRM_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_VAL(op0, op1, op2, crn, crm) \
+ (((op0) << ESR_ELx_SYS64_ISS_OP0_SHIFT) | \
+ ((op1) << ESR_ELx_SYS64_ISS_OP1_SHIFT) | \
+ ((op2) << ESR_ELx_SYS64_ISS_OP2_SHIFT) | \
+ ((crn) << ESR_ELx_SYS64_ISS_CRN_SHIFT) | \
+ ((crm) << ESR_ELx_SYS64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_SYS64_ISS_SYS_OP_MASK (ESR_ELx_SYS64_ISS_SYS_MASK | \
+ ESR_ELx_SYS64_ISS_DIR_MASK)
+/*
+ * User space cache operations have the following sysreg encoding
+ * in System instructions.
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 14 }, WRITE (L=0)
+ */
+#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC 14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU 11
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC 10
+#define ESR_ELx_SYS64_ISS_CRM_IC_IVAU 5
+
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \
+ ESR_ELx_SYS64_ISS_OP1_MASK | \
+ ESR_ELx_SYS64_ISS_OP2_MASK | \
+ ESR_ELx_SYS64_ISS_CRN_MASK | \
+ ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \
+ (ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_WRITE)
+
+#define ESR_ELx_SYS64_ISS_SYS_CTR ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0)
+#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 115ea2a..9510ace 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -18,6 +18,7 @@
#include <asm/cputype.h>
#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
#include <asm/virt.h>
#ifdef __KERNEL__
@@ -98,18 +99,18 @@
#define AARCH64_DBG_REG_WCR (AARCH64_DBG_REG_WVR + ARM_MAX_WRP)
/* Debug register names. */
-#define AARCH64_DBG_REG_NAME_BVR "bvr"
-#define AARCH64_DBG_REG_NAME_BCR "bcr"
-#define AARCH64_DBG_REG_NAME_WVR "wvr"
-#define AARCH64_DBG_REG_NAME_WCR "wcr"
+#define AARCH64_DBG_REG_NAME_BVR bvr
+#define AARCH64_DBG_REG_NAME_BCR bcr
+#define AARCH64_DBG_REG_NAME_WVR wvr
+#define AARCH64_DBG_REG_NAME_WCR wcr
/* Accessor macros for the debug registers. */
#define AARCH64_DBG_READ(N, REG, VAL) do {\
- asm volatile("mrs %0, dbg" REG #N "_el1" : "=r" (VAL));\
+ VAL = read_sysreg(dbg##REG##N##_el1);\
} while (0)
#define AARCH64_DBG_WRITE(N, REG, VAL) do {\
- asm volatile("msr dbg" REG #N "_el1, %0" :: "r" (VAL));\
+ write_sysreg(VAL, dbg##REG##N##_el1);\
} while (0)
struct task_struct;
@@ -141,8 +142,6 @@
}
#endif
-extern struct pmu perf_ops_bp;
-
/* Determine number of BRP registers available. */
static inline int get_num_brps(void)
{
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 1dbaa90..bc85366 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -246,7 +246,8 @@
static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
{ return (val); }
-__AARCH64_INSN_FUNCS(adr_adrp, 0x1F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000)
__AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000)
__AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800)
__AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800)
@@ -318,6 +319,11 @@
bool aarch64_insn_is_nop(u32 insn);
bool aarch64_insn_is_branch_imm(u32 insn);
+static inline bool aarch64_insn_is_adr_adrp(u32 insn)
+{
+ return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
+}
+
int aarch64_insn_read(void *addr, u32 *insnp);
int aarch64_insn_write(void *addr, u32 insn);
enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
@@ -398,6 +404,9 @@
int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+s32 aarch64_insn_adrp_get_offset(u32 insn);
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset);
+
bool aarch32_insn_is_wide(u32 insn);
#define A32_RN_OFFSET 16
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 9b6e408..0bba427 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -40,25 +40,25 @@
#define __raw_writeb __raw_writeb
static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
{
- asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writew __raw_writew
static inline void __raw_writew(u16 val, volatile void __iomem *addr)
{
- asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writel __raw_writel
static inline void __raw_writel(u32 val, volatile void __iomem *addr)
{
- asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_writeq __raw_writeq
static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
{
- asm volatile("str %0, [%1]" : : "r" (val), "r" (addr));
+ asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
}
#define __raw_readb __raw_readb
@@ -184,17 +184,6 @@
#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
#define iowrite64be(v,p) ({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p) __va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p) p
-
#include <asm-generic/io.h>
/*
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index b6bb834..dff1098 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -99,14 +99,10 @@
.macro kern_hyp_va reg
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
and \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK
-alternative_else
- nop
-alternative_endif
-alternative_if_not ARM64_HYP_OFFSET_LOW
- nop
-alternative_else
+alternative_else_nop_endif
+alternative_if ARM64_HYP_OFFSET_LOW
and \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK
-alternative_endif
+alternative_else_nop_endif
.endm
#else
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 31b7322..ba62df8 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -214,7 +214,7 @@
#ifndef CONFIG_SPARSEMEM_VMEMMAP
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
#else
#define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
#define __page_to_voff(kaddr) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
@@ -222,11 +222,15 @@
#define page_to_virt(page) ((void *)((__page_to_voff(page)) | PAGE_OFFSET))
#define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
-#define virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
+#define _virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
+ PHYS_OFFSET) >> PAGE_SHIFT)
#endif
#endif
+#define _virt_addr_is_linear(kaddr) (((u64)(kaddr)) >= PAGE_OFFSET)
+#define virt_addr_valid(kaddr) (_virt_addr_is_linear(kaddr) && \
+ _virt_addr_valid(kaddr))
+
#include <asm-generic/memory_model.h>
#endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index b1892a0..a501853 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -27,22 +27,17 @@
#include <asm-generic/mm_hooks.h>
#include <asm/cputype.h>
#include <asm/pgtable.h>
+#include <asm/sysreg.h>
#include <asm/tlbflush.h>
-#ifdef CONFIG_PID_IN_CONTEXTIDR
static inline void contextidr_thread_switch(struct task_struct *next)
{
- asm(
- " msr contextidr_el1, %0\n"
- " isb"
- :
- : "r" (task_pid_nr(next)));
+ if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR))
+ return;
+
+ write_sysreg(task_pid_nr(next), contextidr_el1);
+ isb();
}
-#else
-static inline void contextidr_thread_switch(struct task_struct *next)
-{
-}
-#endif
/*
* Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0.
@@ -51,11 +46,8 @@
{
unsigned long ttbr = virt_to_phys(empty_zero_page);
- asm(
- " msr ttbr0_el1, %0 // set TTBR0\n"
- " isb"
- :
- : "r" (ttbr));
+ write_sysreg(ttbr, ttbr0_el1);
+ isb();
}
/*
@@ -81,13 +73,11 @@
if (!__cpu_uses_extended_idmap())
return;
- asm volatile (
- " mrs %0, tcr_el1 ;"
- " bfi %0, %1, %2, %3 ;"
- " msr tcr_el1, %0 ;"
- " isb"
- : "=&r" (tcr)
- : "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
+ tcr = read_sysreg(tcr_el1);
+ tcr &= ~TCR_T0SZ_MASK;
+ tcr |= t0sz << TCR_T0SZ_OFFSET;
+ write_sysreg(tcr, tcr_el1);
+ isb();
}
#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS))
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index c3ae239..eb0c2bd 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -208,6 +208,7 @@
#define TCR_T1SZ(x) ((UL(64) - (x)) << TCR_T1SZ_OFFSET)
#define TCR_TxSZ(x) (TCR_T0SZ(x) | TCR_T1SZ(x))
#define TCR_TxSZ_WIDTH 6
+#define TCR_T0SZ_MASK (((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
#define TCR_IRGN0_SHIFT 8
#define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 39f5252..2142c77 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -70,12 +70,13 @@
#define PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
#define __P000 PAGE_NONE
#define __P001 PAGE_READONLY
#define __P010 PAGE_COPY
#define __P011 PAGE_COPY
-#define __P100 PAGE_READONLY_EXEC
+#define __P100 PAGE_EXECONLY
#define __P101 PAGE_READONLY_EXEC
#define __P110 PAGE_COPY_EXEC
#define __P111 PAGE_COPY_EXEC
@@ -84,7 +85,7 @@
#define __S001 PAGE_READONLY
#define __S010 PAGE_SHARED
#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY_EXEC
+#define __S100 PAGE_EXECONLY
#define __S101 PAGE_READONLY_EXEC
#define __S110 PAGE_SHARED_EXEC
#define __S111 PAGE_SHARED_EXEC
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e20bd43..ffbb9a5 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -73,7 +73,7 @@
#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE))
#define pte_exec(pte) (!(pte_val(pte) & PTE_UXN))
#define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT))
-#define pte_user(pte) (!!(pte_val(pte) & PTE_USER))
+#define pte_ng(pte) (!!(pte_val(pte) & PTE_NG))
#ifdef CONFIG_ARM64_HW_AFDBM
#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -84,8 +84,8 @@
#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte))
#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_not_user(pte) \
- ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
+#define pte_valid_global(pte) \
+ ((pte_val(pte) & (PTE_VALID | PTE_NG)) == PTE_VALID)
#define pte_valid_young(pte) \
((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
@@ -155,6 +155,16 @@
return clear_pte_bit(pte, __pgprot(PTE_CONT));
}
+static inline pte_t pte_clear_rdonly(pte_t pte)
+{
+ return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+}
+
+static inline pte_t pte_mkpresent(pte_t pte)
+{
+ return set_pte_bit(pte, __pgprot(PTE_VALID));
+}
+
static inline pmd_t pmd_mkcont(pmd_t pmd)
{
return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
@@ -168,7 +178,7 @@
* Only if the new pte is valid and kernel, otherwise TLB maintenance
* or update_mmu_cache() have the necessary barriers.
*/
- if (pte_valid_not_user(pte)) {
+ if (pte_valid_global(pte)) {
dsb(ishst);
isb();
}
@@ -202,7 +212,7 @@
pte_val(pte) &= ~PTE_RDONLY;
else
pte_val(pte) |= PTE_RDONLY;
- if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+ if (pte_ng(pte) && pte_exec(pte) && !pte_special(pte))
__sync_icache_dcache(pte, addr);
}
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ace0a96..df2e53d 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -37,7 +37,6 @@
#include <asm/ptrace.h>
#include <asm/types.h>
-#ifdef __KERNEL__
#define STACK_TOP_MAX TASK_SIZE_64
#ifdef CONFIG_COMPAT
#define AARCH32_VECTORS_BASE 0xffff0000
@@ -49,7 +48,6 @@
extern phys_addr_t arm64_dma_phys_limit;
#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1)
-#endif /* __KERNEL__ */
struct debug_info {
/* Have we suspended stepping by a debugger? */
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
new file mode 100644
index 0000000..4e7e706
--- /dev/null
+++ b/arch/arm64/include/asm/sections.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2016 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SECTIONS_H
+#define __ASM_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char __alt_instructions[], __alt_instructions_end[];
+extern char __exception_text_start[], __exception_text_end[];
+extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
+extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+extern char __hyp_text_start[], __hyp_text_end[];
+extern char __idmap_text_start[], __idmap_text_end[];
+extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __mmuoff_data_start[], __mmuoff_data_end[];
+
+#endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 89206b5..cae331d 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -66,8 +66,7 @@
ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
" stxr %w1, %w0, %2\n"
-" nop\n"
-" nop\n",
+ __nops(2),
/* LSE atomics */
" mov %w1, %w0\n"
" cas %w0, %w0, %2\n"
@@ -99,9 +98,7 @@
/* LSE atomics */
" mov %w2, %w5\n"
" ldadda %w2, %w0, %3\n"
-" nop\n"
-" nop\n"
-" nop\n"
+ __nops(3)
)
/* Did we get the lock? */
@@ -165,8 +162,8 @@
" stlrh %w1, %0",
/* LSE atomics */
" mov %w1, #1\n"
- " nop\n"
- " staddlh %w1, %0")
+ " staddlh %w1, %0\n"
+ __nops(1))
: "=Q" (lock->owner), "=&r" (tmp)
:
: "memory");
@@ -212,7 +209,7 @@
" cbnz %w0, 1b\n"
" stxr %w0, %w2, %1\n"
" cbnz %w0, 2b\n"
- " nop",
+ __nops(1),
/* LSE atomics */
"1: mov %w0, wzr\n"
"2: casa %w0, %w2, %1\n"
@@ -241,8 +238,7 @@
/* LSE atomics */
" mov %w0, wzr\n"
" casa %w0, %w2, %1\n"
- " nop\n"
- " nop")
+ __nops(2))
: "=&r" (tmp), "+Q" (rw->lock)
: "r" (0x80000000)
: "memory");
@@ -290,8 +286,8 @@
" add %w0, %w0, #1\n"
" tbnz %w0, #31, 1b\n"
" stxr %w1, %w0, %2\n"
- " nop\n"
- " cbnz %w1, 2b",
+ " cbnz %w1, 2b\n"
+ __nops(1),
/* LSE atomics */
"1: wfe\n"
"2: ldxr %w0, %2\n"
@@ -317,9 +313,8 @@
" cbnz %w1, 1b",
/* LSE atomics */
" movn %w0, #0\n"
- " nop\n"
- " nop\n"
- " staddl %w0, %2")
+ " staddl %w0, %2\n"
+ __nops(2))
: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
:
: "memory");
@@ -344,7 +339,7 @@
" tbnz %w1, #31, 1f\n"
" casa %w0, %w1, %2\n"
" sbc %w1, %w1, %w0\n"
- " nop\n"
+ __nops(1)
"1:")
: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
:
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index 024d623..b8a313f 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -47,4 +47,7 @@
int arch_hibernation_header_save(void *addr, unsigned int max_size);
int arch_hibernation_header_restore(void *addr);
+/* Used to resume on the CPU we hibernated on */
+int hibernate_resume_nonboot_cpu_disable(void);
+
#endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cc06794..e8d46e8 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -100,6 +100,7 @@
/* SCTLR_EL1 specific flags. */
#define SCTLR_EL1_UCI (1 << 26)
#define SCTLR_EL1_SPAN (1 << 23)
+#define SCTLR_EL1_UCT (1 << 15)
#define SCTLR_EL1_SED (1 << 8)
#define SCTLR_EL1_CP15BEN (1 << 5)
@@ -253,16 +254,6 @@
" .endm\n"
);
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
- u32 val;
-
- asm volatile("mrs %0, sctlr_el1" : "=r" (val));
- val &= ~clear;
- val |= set;
- asm volatile("msr sctlr_el1, %0" : : "r" (val));
-}
-
/*
* Unlike read_cpuid, calls to read_sysreg are never expected to be
* optimized away or replaced with synthetic values.
@@ -273,12 +264,41 @@
__val; \
})
+/*
+ * The "Z" constraint normally means a zero immediate, but when combined with
+ * the "%x0" template means XZR.
+ */
#define write_sysreg(v, r) do { \
u64 __val = (u64)v; \
- asm volatile("msr " __stringify(r) ", %0" \
- : : "r" (__val)); \
+ asm volatile("msr " __stringify(r) ", %x0" \
+ : : "rZ" (__val)); \
} while (0)
+/*
+ * For registers without architectural names, or simply unsupported by
+ * GAS.
+ */
+#define read_sysreg_s(r) ({ \
+ u64 __val; \
+ asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val)); \
+ __val; \
+})
+
+#define write_sysreg_s(v, r) do { \
+ u64 __val = (u64)v; \
+ asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val)); \
+} while (0)
+
+static inline void config_sctlr_el1(u32 clear, u32 set)
+{
+ u32 val;
+
+ val = read_sysreg(sctlr_el1);
+ val &= ~clear;
+ val |= set;
+ write_sysreg(val, sctlr_el1);
+}
+
#endif
#endif /* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 57f110b..bc81243 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -56,12 +56,6 @@
__show_ratelimited; \
})
-#define UDBG_UNDEFINED (1 << 0)
-#define UDBG_SYSCALL (1 << 1)
-#define UDBG_BADABORT (1 << 2)
-#define UDBG_SEGV (1 << 3)
-#define UDBG_BUS (1 << 4)
-
#endif /* __ASSEMBLY__ */
#endif /* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index abd64bd..e9ea5a6 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -75,6 +75,9 @@
/*
* struct thread_info can be accessed directly via sp_el0.
+ *
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
*/
static inline struct thread_info *current_thread_info(void)
{
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b460ae2..deab523 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -25,6 +25,24 @@
#include <asm/cputype.h>
/*
+ * Raw TLBI operations.
+ *
+ * Where necessary, use the __tlbi() macro to avoid asm()
+ * boilerplate. Drivers and most kernel code should use the TLB
+ * management routines in preference to the macro below.
+ *
+ * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending
+ * on whether a particular TLBI operation takes an argument or
+ * not. The macros handles invoking the asm with or without the
+ * register argument as appropriate.
+ */
+#define __TLBI_0(op, arg) asm ("tlbi " #op)
+#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0" : : "r" (arg))
+#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
+
+#define __tlbi(op, ...) __TLBI_N(op, ##__VA_ARGS__, 1, 0)
+
+/*
* TLB Management
* ==============
*
@@ -66,7 +84,7 @@
static inline void local_flush_tlb_all(void)
{
dsb(nshst);
- asm("tlbi vmalle1");
+ __tlbi(vmalle1);
dsb(nsh);
isb();
}
@@ -74,7 +92,7 @@
static inline void flush_tlb_all(void)
{
dsb(ishst);
- asm("tlbi vmalle1is");
+ __tlbi(vmalle1is);
dsb(ish);
isb();
}
@@ -84,7 +102,7 @@
unsigned long asid = ASID(mm) << 48;
dsb(ishst);
- asm("tlbi aside1is, %0" : : "r" (asid));
+ __tlbi(aside1is, asid);
dsb(ish);
}
@@ -94,7 +112,7 @@
unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48);
dsb(ishst);
- asm("tlbi vale1is, %0" : : "r" (addr));
+ __tlbi(vale1is, addr);
dsb(ish);
}
@@ -122,9 +140,9 @@
dsb(ishst);
for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
if (last_level)
- asm("tlbi vale1is, %0" : : "r"(addr));
+ __tlbi(vale1is, addr);
else
- asm("tlbi vae1is, %0" : : "r"(addr));
+ __tlbi(vae1is, addr);
}
dsb(ish);
}
@@ -149,7 +167,7 @@
dsb(ishst);
for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
- asm("tlbi vaae1is, %0" : : "r"(addr));
+ __tlbi(vaae1is, addr);
dsb(ish);
isb();
}
@@ -163,7 +181,7 @@
{
unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
- asm("tlbi vae1is, %0" : : "r" (addr));
+ __tlbi(vae1is, addr);
dsb(ish);
}
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 9cd03f3..02e9035 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -19,6 +19,7 @@
#define __ASM_TRAP_H
#include <linux/list.h>
+#include <asm/sections.h>
struct pt_regs;
@@ -39,9 +40,6 @@
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
- extern char __irqentry_text_start[];
- extern char __irqentry_text_end[];
-
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
@@ -54,8 +52,6 @@
static inline int in_exception_text(unsigned long ptr)
{
- extern char __exception_text_start[];
- extern char __exception_text_end[];
int in;
in = ptr >= (unsigned long)&__exception_text_start &&
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 1788545..fea1073 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -45,6 +45,8 @@
#ifndef __ASSEMBLY__
#include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/sysreg.h>
/*
* __boot_cpu_mode records what mode CPUs were booted in.
@@ -75,10 +77,7 @@
static inline bool is_kernel_in_hyp_mode(void)
{
- u64 el;
-
- asm("mrs %0, CurrentEL" : "=r" (el));
- return el == CurrentEL_EL2;
+ return read_sysreg(CurrentEL) == CurrentEL_EL2;
}
#ifdef CONFIG_ARM64_VHE
@@ -87,14 +86,6 @@
static inline void verify_cpu_run_el(void) {}
#endif
-/* The section containing the hypervisor idmap text */
-extern char __hyp_idmap_text_start[];
-extern char __hyp_idmap_text_end[];
-
-/* The section containing the hypervisor text */
-extern char __hyp_text_start[];
-extern char __hyp_text_end[];
-
#endif /* __ASSEMBLY__ */
#endif /* ! __ASM__VIRT_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 14f7b65..7d66bba 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -10,6 +10,8 @@
CFLAGS_REMOVE_insn.o = -pg
CFLAGS_REMOVE_return_address.o = -pg
+CFLAGS_setup.o = -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
# Object file lists.
arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
entry-fpsimd.o process.o ptrace.o setup.o signal.o \
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
index f85149c..f01fab6 100644
--- a/arch/arm64/kernel/acpi_numa.c
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -105,8 +105,10 @@
int ret;
ret = acpi_numa_init();
- if (ret)
+ if (ret) {
+ pr_info("Failed to initialise from firmware\n");
return ret;
+ }
return srat_disabled() ? -EINVAL : 0;
}
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d2ee1b2..06d650f 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -25,14 +25,13 @@
#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/insn.h>
+#include <asm/sections.h>
#include <linux/stop_machine.h>
#define __ALT_PTR(a,f) (u32 *)((void *)&(a)->f + (a)->f)
#define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset)
#define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset)
-extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
-
struct alt_region {
struct alt_instr *begin;
struct alt_instr *end;
@@ -59,6 +58,8 @@
BUG();
}
+#define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
+
static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
{
u32 insn;
@@ -80,6 +81,25 @@
offset = target - (unsigned long)insnptr;
insn = aarch64_set_branch_offset(insn, offset);
}
+ } else if (aarch64_insn_is_adrp(insn)) {
+ s32 orig_offset, new_offset;
+ unsigned long target;
+
+ /*
+ * If we're replacing an adrp instruction, which uses PC-relative
+ * immediate addressing, adjust the offset to reflect the new
+ * PC. adrp operates on 4K aligned addresses.
+ */
+ orig_offset = aarch64_insn_adrp_get_offset(insn);
+ target = align_down(altinsnptr, SZ_4K) + orig_offset;
+ new_offset = target - align_down(insnptr, SZ_4K);
+ insn = aarch64_insn_adrp_set_offset(insn, new_offset);
+ } else if (aarch64_insn_uses_literal(insn)) {
+ /*
+ * Disallow patching unhandled instructions using PC relative
+ * literal addresses
+ */
+ BUG();
}
return insn;
@@ -124,8 +144,8 @@
{
static int patched = 0;
struct alt_region region = {
- .begin = __alt_instructions,
- .end = __alt_instructions_end,
+ .begin = (struct alt_instr *)__alt_instructions,
+ .end = (struct alt_instr *)__alt_instructions_end,
};
/* We always have a CPU 0 at this point (__init) */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 05070b7..4a2f0f0 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -23,6 +23,7 @@
#include <linux/dma-mapping.h>
#include <linux/kvm_host.h>
#include <linux/suspend.h>
+#include <asm/cpufeature.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/smp_plat.h>
@@ -145,5 +146,6 @@
DEFINE(HIBERN_PBE_ORIG, offsetof(struct pbe, orig_address));
DEFINE(HIBERN_PBE_ADDR, offsetof(struct pbe, address));
DEFINE(HIBERN_PBE_NEXT, offsetof(struct pbe, next));
+ DEFINE(ARM64_FTR_SYSVAL, offsetof(struct arm64_ftr_reg, sys_val));
return 0;
}
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index b8629d5..9617301 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -39,7 +39,7 @@
if (level > MAX_CACHE_LEVEL)
return CACHE_TYPE_NOCACHE;
- asm volatile ("mrs %x0, clidr_el1" : "=r" (clidr));
+ clidr = read_sysreg(clidr_el1);
return CLIDR_CTYPE(clidr, level);
}
@@ -55,11 +55,9 @@
WARN_ON(preemptible());
- /* Put value into CSSELR */
- asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+ write_sysreg(csselr, csselr_el1);
isb();
- /* Read result out of CCSIDR */
- asm volatile("mrs %x0, ccsidr_el1" : "=r" (ccsidr));
+ ccsidr = read_sysreg(ccsidr_el1);
return ccsidr;
}
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 82b0fc2..0150394 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -30,6 +30,21 @@
entry->midr_range_max);
}
+static bool
+has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
+ int scope)
+{
+ WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+ return (read_cpuid_cachetype() & arm64_ftr_reg_ctrel0.strict_mask) !=
+ (arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
+}
+
+static void cpu_enable_trap_ctr_access(void *__unused)
+{
+ /* Clear SCTLR_EL1.UCT */
+ config_sctlr_el1(SCTLR_EL1_UCT, 0);
+}
+
#define MIDR_RANGE(model, min, max) \
.def_scope = SCOPE_LOCAL_CPU, \
.matches = is_affected_midr_range, \
@@ -108,6 +123,13 @@
},
#endif
{
+ .desc = "Mismatched cache line size",
+ .capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
+ .matches = has_mismatched_cache_line_size,
+ .def_scope = SCOPE_LOCAL_CPU,
+ .enable = cpu_enable_trap_ctr_access,
+ },
+ {
}
};
@@ -116,7 +138,7 @@
* and the related information is freed soon after. If the new CPU requires
* an errata not detected at boot, fail this CPU.
*/
-void verify_local_cpu_errata(void)
+void verify_local_cpu_errata_workarounds(void)
{
const struct arm64_cpu_capabilities *caps = arm64_errata;
@@ -131,7 +153,7 @@
}
}
-void check_local_cpu_errata(void)
+void update_cpu_errata_workarounds(void)
{
update_cpu_capabilities(arm64_errata, "enabling workaround for");
}
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index c7cfb8f..e137cea 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -17,6 +17,7 @@
*/
#include <linux/acpi.h>
+#include <linux/cache.h>
#include <linux/errno.h>
#include <linux/of.h>
#include <linux/string.h>
@@ -28,7 +29,7 @@
extern const struct cpu_operations acpi_parking_protocol_ops;
extern const struct cpu_operations cpu_psci_ops;
-const struct cpu_operations *cpu_ops[NR_CPUS];
+const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
&smp_spin_table_ops,
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 62272ea..d577f26 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -46,6 +46,9 @@
DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
+EXPORT_SYMBOL(cpu_hwcap_keys);
+
#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
{ \
.sign = SIGNED, \
@@ -74,7 +77,7 @@
cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused);
-static struct arm64_ftr_bits ftr_id_aa64isar0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0),
@@ -87,7 +90,7 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0),
@@ -101,7 +104,7 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
@@ -119,7 +122,7 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
@@ -130,7 +133,7 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
@@ -139,7 +142,7 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_ctr[] = {
+static const struct arm64_ftr_bits ftr_ctr[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */
@@ -147,15 +150,21 @@
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */
/*
* Linux can handle differing I-cache policies. Userspace JITs will
- * make use of *minLine
+ * make use of *minLine.
+ * If we have differing I-cache policies, report it as the weakest - AIVIVT.
*/
- ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0), /* L1Ip */
+ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_AIVIVT), /* L1Ip */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_mmfr0[] = {
+struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
+ .name = "SYS_CTR_EL0",
+ .ftr_bits = ftr_ctr
+};
+
+static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0xf), /* InnerShr */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */
ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */
@@ -167,7 +176,7 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
@@ -178,14 +187,14 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_mvfr2[] = {
+static const struct arm64_ftr_bits ftr_mvfr2[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* FPMisc */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* SIMDMisc */
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_dczid[] = {
+static const struct arm64_ftr_bits ftr_dczid[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 5, 27, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 1, 1), /* DZP */
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* BS */
@@ -193,7 +202,7 @@
};
-static struct arm64_ftr_bits ftr_id_isar5[] = {
+static const struct arm64_ftr_bits ftr_id_isar5[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 20, 4, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0),
@@ -204,14 +213,14 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_mmfr4[] = {
+static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* ac2 */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_pfr0[] = {
+static const struct arm64_ftr_bits ftr_id_pfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 16, 0), /* RAZ */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* State3 */
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0), /* State2 */
@@ -220,7 +229,7 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_id_dfr0[] = {
+static const struct arm64_ftr_bits ftr_id_dfr0[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
@@ -238,7 +247,7 @@
* 0. Covers the following 32bit registers:
* id_isar[0-4], id_mmfr[1-3], id_pfr1, mvfr[0-1]
*/
-static struct arm64_ftr_bits ftr_generic_32bits[] = {
+static const struct arm64_ftr_bits ftr_generic_32bits[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0),
ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
@@ -250,29 +259,32 @@
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_generic[] = {
+static const struct arm64_ftr_bits ftr_generic[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0),
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_generic32[] = {
+static const struct arm64_ftr_bits ftr_generic32[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 32, 0),
ARM64_FTR_END,
};
-static struct arm64_ftr_bits ftr_aa64raz[] = {
+static const struct arm64_ftr_bits ftr_aa64raz[] = {
ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0),
ARM64_FTR_END,
};
-#define ARM64_FTR_REG(id, table) \
- { \
- .sys_id = id, \
+#define ARM64_FTR_REG(id, table) { \
+ .sys_id = id, \
+ .reg = &(struct arm64_ftr_reg){ \
.name = #id, \
.ftr_bits = &((table)[0]), \
- }
+ }}
-static struct arm64_ftr_reg arm64_ftr_regs[] = {
+static const struct __ftr_reg_entry {
+ u32 sys_id;
+ struct arm64_ftr_reg *reg;
+} arm64_ftr_regs[] = {
/* Op1 = 0, CRn = 0, CRm = 1 */
ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0),
@@ -315,7 +327,7 @@
ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
/* Op1 = 3, CRn = 0, CRm = 0 */
- ARM64_FTR_REG(SYS_CTR_EL0, ftr_ctr),
+ { SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
/* Op1 = 3, CRn = 14, CRm = 0 */
@@ -324,7 +336,7 @@
static int search_cmp_ftr_reg(const void *id, const void *regp)
{
- return (int)(unsigned long)id - (int)((const struct arm64_ftr_reg *)regp)->sys_id;
+ return (int)(unsigned long)id - (int)((const struct __ftr_reg_entry *)regp)->sys_id;
}
/*
@@ -339,14 +351,20 @@
*/
static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
{
- return bsearch((const void *)(unsigned long)sys_id,
+ const struct __ftr_reg_entry *ret;
+
+ ret = bsearch((const void *)(unsigned long)sys_id,
arm64_ftr_regs,
ARRAY_SIZE(arm64_ftr_regs),
sizeof(arm64_ftr_regs[0]),
search_cmp_ftr_reg);
+ if (ret)
+ return ret->reg;
+ return NULL;
}
-static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val)
+static u64 arm64_ftr_set_value(const struct arm64_ftr_bits *ftrp, s64 reg,
+ s64 ftr_val)
{
u64 mask = arm64_ftr_mask(ftrp);
@@ -355,7 +373,8 @@
return reg;
}
-static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur)
+static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new,
+ s64 cur)
{
s64 ret = 0;
@@ -376,27 +395,13 @@
return ret;
}
-static int __init sort_cmp_ftr_regs(const void *a, const void *b)
-{
- return ((const struct arm64_ftr_reg *)a)->sys_id -
- ((const struct arm64_ftr_reg *)b)->sys_id;
-}
-
-static void __init swap_ftr_regs(void *a, void *b, int size)
-{
- struct arm64_ftr_reg tmp = *(struct arm64_ftr_reg *)a;
- *(struct arm64_ftr_reg *)a = *(struct arm64_ftr_reg *)b;
- *(struct arm64_ftr_reg *)b = tmp;
-}
-
static void __init sort_ftr_regs(void)
{
- /* Keep the array sorted so that we can do the binary search */
- sort(arm64_ftr_regs,
- ARRAY_SIZE(arm64_ftr_regs),
- sizeof(arm64_ftr_regs[0]),
- sort_cmp_ftr_regs,
- swap_ftr_regs);
+ int i;
+
+ /* Check that the array is sorted so that we can do the binary search */
+ for (i = 1; i < ARRAY_SIZE(arm64_ftr_regs); i++)
+ BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id);
}
/*
@@ -407,7 +412,7 @@
{
u64 val = 0;
u64 strict_mask = ~0x0ULL;
- struct arm64_ftr_bits *ftrp;
+ const struct arm64_ftr_bits *ftrp;
struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg);
BUG_ON(!reg);
@@ -464,7 +469,7 @@
static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
{
- struct arm64_ftr_bits *ftrp;
+ const struct arm64_ftr_bits *ftrp;
for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
s64 ftr_cur = arm64_ftr_value(ftrp, reg->sys_val);
@@ -1004,25 +1009,35 @@
* cannot do anything to fix it up and could cause unexpected failures. So
* we park the CPU.
*/
-void verify_local_cpu_capabilities(void)
+static void verify_local_cpu_capabilities(void)
{
-
- check_early_cpu_features();
-
- /*
- * If we haven't computed the system capabilities, there is nothing
- * to verify.
- */
- if (!sys_caps_initialised)
- return;
-
- verify_local_cpu_errata();
+ verify_local_cpu_errata_workarounds();
verify_local_cpu_features(arm64_features);
verify_local_elf_hwcaps(arm64_elf_hwcaps);
if (system_supports_32bit_el0())
verify_local_elf_hwcaps(compat_elf_hwcaps);
}
+void check_local_cpu_capabilities(void)
+{
+ /*
+ * All secondary CPUs should conform to the early CPU features
+ * in use by the kernel based on boot CPU.
+ */
+ check_early_cpu_features();
+
+ /*
+ * If we haven't finalised the system capabilities, this CPU gets
+ * a chance to update the errata work arounds.
+ * Otherwise, this CPU should verify that it has all the system
+ * advertised capabilities.
+ */
+ if (!sys_caps_initialised)
+ update_cpu_errata_workarounds();
+ else
+ verify_local_cpu_capabilities();
+}
+
static void __init setup_feature_capabilities(void)
{
update_cpu_capabilities(arm64_features, "detected feature:");
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index ed1b84f..b3d5b3e 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -363,8 +363,6 @@
}
cpuinfo_detect_icache_policy(info);
-
- check_local_cpu_errata();
}
void cpuinfo_store_cpu(void)
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 91fff48..73ae90e 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -46,16 +46,14 @@
{
unsigned long flags;
local_dbg_save(flags);
- asm volatile("msr mdscr_el1, %0" :: "r" (mdscr));
+ write_sysreg(mdscr, mdscr_el1);
local_dbg_restore(flags);
}
NOKPROBE_SYMBOL(mdscr_write);
static u32 mdscr_read(void)
{
- u32 mdscr;
- asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr));
- return mdscr;
+ return read_sysreg(mdscr_el1);
}
NOKPROBE_SYMBOL(mdscr_read);
@@ -132,36 +130,18 @@
/*
* OS lock clearing.
*/
-static void clear_os_lock(void *unused)
+static int clear_os_lock(unsigned int cpu)
{
- asm volatile("msr oslar_el1, %0" : : "r" (0));
+ write_sysreg(0, oslar_el1);
+ isb();
+ return 0;
}
-static int os_lock_notify(struct notifier_block *self,
- unsigned long action, void *data)
-{
- if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
- clear_os_lock(NULL);
- return NOTIFY_OK;
-}
-
-static struct notifier_block os_lock_nb = {
- .notifier_call = os_lock_notify,
-};
-
static int debug_monitors_init(void)
{
- cpu_notifier_register_begin();
-
- /* Clear the OS lock. */
- on_each_cpu(clear_os_lock, NULL, 1);
- isb();
-
- /* Register hotplug handler. */
- __register_cpu_notifier(&os_lock_nb);
-
- cpu_notifier_register_done();
- return 0;
+ return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
+ "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+ clear_os_lock, NULL);
}
postcore_initcall(debug_monitors_init);
@@ -254,7 +234,7 @@
return 0;
if (user_mode(regs)) {
- send_user_sigtrap(TRAP_HWBKPT);
+ send_user_sigtrap(TRAP_TRACE);
/*
* ptrace will disable single step unless explicitly
@@ -382,7 +362,7 @@
static int __init debug_traps_init(void)
{
hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
- TRAP_HWBKPT, "single-step handler");
+ TRAP_TRACE, "single-step handler");
hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
TRAP_BRKPT, "ptrace BRK handler");
return 0;
@@ -435,8 +415,10 @@
/* ptrace API */
void user_enable_single_step(struct task_struct *task)
{
- set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
- set_regs_spsr_ss(task_pt_regs(task));
+ struct thread_info *ti = task_thread_info(task);
+
+ if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP))
+ set_regs_spsr_ss(task_pt_regs(task));
}
NOKPROBE_SYMBOL(user_enable_single_step);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 441420c..223d54a 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -104,7 +104,7 @@
str x20, [sp, #S_ORIG_ADDR_LIMIT]
mov x20, #TASK_SIZE_64
str x20, [tsk, #TI_ADDR_LIMIT]
- ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+ /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
.endif /* \el == 0 */
mrs x22, elr_el1
mrs x23, spsr_el1
@@ -150,13 +150,7 @@
ldr x23, [sp, #S_SP] // load return stack pointer
msr sp_el0, x23
#ifdef CONFIG_ARM64_ERRATUM_845719
-alternative_if_not ARM64_WORKAROUND_845719
- nop
- nop
-#ifdef CONFIG_PID_IN_CONTEXTIDR
- nop
-#endif
-alternative_else
+alternative_if ARM64_WORKAROUND_845719
tbz x22, #4, 1f
#ifdef CONFIG_PID_IN_CONTEXTIDR
mrs x29, contextidr_el1
@@ -165,7 +159,7 @@
msr contextidr_el1, xzr
#endif
1:
-alternative_endif
+alternative_else_nop_endif
#endif
.endif
msr elr_el1, x21 // set up the return data
@@ -707,18 +701,13 @@
* Ok, we need to do extra processing, enter the slow path.
*/
work_pending:
- tbnz x1, #TIF_NEED_RESCHED, work_resched
- /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
mov x0, sp // 'regs'
- enable_irq // enable interrupts for do_notify_resume()
bl do_notify_resume
- b ret_to_user
-work_resched:
#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_off // the IRQs are off here, inform the tracing code
+ bl trace_hardirqs_on // enabled while in userspace
#endif
- bl schedule
-
+ ldr x1, [tsk, #TI_FLAGS] // re-check for single-step
+ b finish_ret_to_user
/*
* "slow" syscall return path.
*/
@@ -727,6 +716,7 @@
ldr x1, [tsk, #TI_FLAGS]
and x2, x1, #_TIF_WORK_MASK
cbnz x2, work_pending
+finish_ret_to_user:
enable_step_tsk x1, x2
kernel_exit 0
ENDPROC(ret_to_user)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 3e7b050..427f6d3 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -208,13 +208,23 @@
__INIT
+ /*
+ * The following callee saved general purpose registers are used on the
+ * primary lowlevel boot path:
+ *
+ * Register Scope Purpose
+ * x21 stext() .. start_kernel() FDT pointer passed at boot in x0
+ * x23 stext() .. start_kernel() physical misalignment/KASLR offset
+ * x28 __create_page_tables() callee preserved temp register
+ * x19/x20 __primary_switch() callee preserved temp registers
+ */
ENTRY(stext)
bl preserve_boot_args
- bl el2_setup // Drop to EL1, w20=cpu_boot_mode
- adrp x24, __PHYS_OFFSET
- and x23, x24, MIN_KIMG_ALIGN - 1 // KASLR offset, defaults to 0
+ bl el2_setup // Drop to EL1, w0=cpu_boot_mode
+ adrp x23, __PHYS_OFFSET
+ and x23, x23, MIN_KIMG_ALIGN - 1 // KASLR offset, defaults to 0
bl set_cpu_boot_mode_flag
- bl __create_page_tables // x25=TTBR0, x26=TTBR1
+ bl __create_page_tables
/*
* The following calls CPU setup code, see arch/arm64/mm/proc.S for
* details.
@@ -222,9 +232,7 @@
* the TCR will have been set.
*/
bl __cpu_setup // initialise processor
- adr_l x27, __primary_switch // address to jump to after
- // MMU has been enabled
- b __enable_mmu
+ b __primary_switch
ENDPROC(stext)
/*
@@ -311,23 +319,21 @@
* been enabled
*/
__create_page_tables:
- adrp x25, idmap_pg_dir
- adrp x26, swapper_pg_dir
mov x28, lr
/*
* Invalidate the idmap and swapper page tables to avoid potential
* dirty cache lines being evicted.
*/
- mov x0, x25
- add x1, x26, #SWAPPER_DIR_SIZE
+ adrp x0, idmap_pg_dir
+ adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE
bl __inval_cache_range
/*
* Clear the idmap and swapper page tables.
*/
- mov x0, x25
- add x6, x26, #SWAPPER_DIR_SIZE
+ adrp x0, idmap_pg_dir
+ adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
@@ -340,7 +346,7 @@
/*
* Create the identity mapping.
*/
- mov x0, x25 // idmap_pg_dir
+ adrp x0, idmap_pg_dir
adrp x3, __idmap_text_start // __pa(__idmap_text_start)
#ifndef CONFIG_ARM64_VA_BITS_48
@@ -390,7 +396,7 @@
/*
* Map the kernel image (starting with PHYS_OFFSET).
*/
- mov x0, x26 // swapper_pg_dir
+ adrp x0, swapper_pg_dir
mov_q x5, KIMAGE_VADDR + TEXT_OFFSET // compile time __va(_text)
add x5, x5, x23 // add KASLR displacement
create_pgd_entry x0, x5, x3, x6
@@ -405,8 +411,8 @@
* accesses (MMU disabled), invalidate the idmap and swapper page
* tables again to remove any speculatively loaded cache lines.
*/
- mov x0, x25
- add x1, x26, #SWAPPER_DIR_SIZE
+ adrp x0, idmap_pg_dir
+ adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE
dmb sy
bl __inval_cache_range
@@ -416,14 +422,27 @@
/*
* The following fragment of code is executed with the MMU enabled.
+ *
+ * x0 = __PHYS_OFFSET
*/
- .set initial_sp, init_thread_union + THREAD_START_SP
__primary_switched:
- mov x28, lr // preserve LR
+ adrp x4, init_thread_union
+ add sp, x4, #THREAD_SIZE
+ msr sp_el0, x4 // Save thread_info
+
adr_l x8, vectors // load VBAR_EL1 with virtual
msr vbar_el1, x8 // vector table address
isb
+ stp xzr, x30, [sp, #-16]!
+ mov x29, sp
+
+ str_l x21, __fdt_pointer, x5 // Save FDT pointer
+
+ ldr_l x4, kimage_vaddr // Save the offset between
+ sub x4, x4, x0 // the kernel virtual and
+ str_l x4, kimage_voffset, x5 // physical mappings
+
// Clear BSS
adr_l x0, __bss_start
mov x1, xzr
@@ -432,17 +451,6 @@
bl __pi_memset
dsb ishst // Make zero page visible to PTW
- adr_l sp, initial_sp, x4
- mov x4, sp
- and x4, x4, #~(THREAD_SIZE - 1)
- msr sp_el0, x4 // Save thread_info
- str_l x21, __fdt_pointer, x5 // Save FDT pointer
-
- ldr_l x4, kimage_vaddr // Save the offset between
- sub x4, x4, x24 // the kernel virtual and
- str_l x4, kimage_voffset, x5 // physical mappings
-
- mov x29, #0
#ifdef CONFIG_KASAN
bl kasan_early_init
#endif
@@ -454,8 +462,8 @@
bl kaslr_early_init // parse FDT for KASLR options
cbz x0, 0f // KASLR disabled? just proceed
orr x23, x23, x0 // record KASLR offset
- ret x28 // we must enable KASLR, return
- // to __enable_mmu()
+ ldp x29, x30, [sp], #16 // we must enable KASLR, return
+ ret // to __primary_switch()
0:
#endif
b start_kernel
@@ -465,7 +473,7 @@
* end early head section, begin head code that is also used for
* hotplug and needs to have the same protections as the text region
*/
- .section ".text","ax"
+ .section ".idmap.text","ax"
ENTRY(kimage_vaddr)
.quad _text - TEXT_OFFSET
@@ -490,7 +498,7 @@
CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1
CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1
msr sctlr_el1, x0
- mov w20, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1
+ mov w0, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1
isb
ret
@@ -586,7 +594,7 @@
cbz x2, install_el2_stub
- mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
+ mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
isb
ret
@@ -601,7 +609,7 @@
PSR_MODE_EL1h)
msr spsr_el2, x0
msr elr_el2, lr
- mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
+ mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
eret
ENDPROC(el2_setup)
@@ -611,27 +619,39 @@
*/
set_cpu_boot_mode_flag:
adr_l x1, __boot_cpu_mode
- cmp w20, #BOOT_CPU_MODE_EL2
+ cmp w0, #BOOT_CPU_MODE_EL2
b.ne 1f
add x1, x1, #4
-1: str w20, [x1] // This CPU has booted in EL1
+1: str w0, [x1] // This CPU has booted in EL1
dmb sy
dc ivac, x1 // Invalidate potentially stale cache line
ret
ENDPROC(set_cpu_boot_mode_flag)
/*
+ * These values are written with the MMU off, but read with the MMU on.
+ * Writers will invalidate the corresponding address, discarding up to a
+ * 'Cache Writeback Granule' (CWG) worth of data. The linker script ensures
+ * sufficient alignment that the CWG doesn't overlap another section.
+ */
+ .pushsection ".mmuoff.data.write", "aw"
+/*
* We need to find out the CPU boot mode long after boot, so we need to
* store it in a writable variable.
*
* This is not in .bss, because we set it sufficiently early that the boot-time
* zeroing of .bss would clobber it.
*/
- .pushsection .data..cacheline_aligned
- .align L1_CACHE_SHIFT
ENTRY(__boot_cpu_mode)
.long BOOT_CPU_MODE_EL2
.long BOOT_CPU_MODE_EL1
+/*
+ * The booting CPU updates the failed status @__early_cpu_boot_status,
+ * with MMU turned off.
+ */
+ENTRY(__early_cpu_boot_status)
+ .long 0
+
.popsection
/*
@@ -639,7 +659,7 @@
* cores are held until we're ready for them to initialise.
*/
ENTRY(secondary_holding_pen)
- bl el2_setup // Drop to EL1, w20=cpu_boot_mode
+ bl el2_setup // Drop to EL1, w0=cpu_boot_mode
bl set_cpu_boot_mode_flag
mrs x0, mpidr_el1
mov_q x1, MPIDR_HWID_BITMASK
@@ -666,12 +686,10 @@
/*
* Common entry point for secondary CPUs.
*/
- adrp x25, idmap_pg_dir
- adrp x26, swapper_pg_dir
bl __cpu_setup // initialise processor
-
- adr_l x27, __secondary_switch // address to jump to after enabling the MMU
- b __enable_mmu
+ bl __enable_mmu
+ ldr x8, =__secondary_switched
+ br x8
ENDPROC(secondary_startup)
__secondary_switched:
@@ -706,33 +724,27 @@
dc ivac, \tmp1 // Invalidate potentially stale cache line
.endm
- .pushsection .data..cacheline_aligned
- .align L1_CACHE_SHIFT
-ENTRY(__early_cpu_boot_status)
- .long 0
- .popsection
-
/*
* Enable the MMU.
*
* x0 = SCTLR_EL1 value for turning on the MMU.
- * x27 = *virtual* address to jump to upon completion
*
- * Other registers depend on the function called upon completion.
+ * Returns to the caller via x30/lr. This requires the caller to be covered
+ * by the .idmap.text section.
*
* Checks if the selected granule size is supported by the CPU.
* If it isn't, park the CPU
*/
- .section ".idmap.text", "ax"
ENTRY(__enable_mmu)
- mrs x22, sctlr_el1 // preserve old SCTLR_EL1 value
mrs x1, ID_AA64MMFR0_EL1
ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
b.ne __no_granule_support
update_early_cpu_boot_status 0, x1, x2
- msr ttbr0_el1, x25 // load TTBR0
- msr ttbr1_el1, x26 // load TTBR1
+ adrp x1, idmap_pg_dir
+ adrp x2, swapper_pg_dir
+ msr ttbr0_el1, x1 // load TTBR0
+ msr ttbr1_el1, x2 // load TTBR1
isb
msr sctlr_el1, x0
isb
@@ -744,29 +756,7 @@
ic iallu
dsb nsh
isb
-#ifdef CONFIG_RANDOMIZE_BASE
- mov x19, x0 // preserve new SCTLR_EL1 value
- blr x27
-
- /*
- * If we return here, we have a KASLR displacement in x23 which we need
- * to take into account by discarding the current kernel mapping and
- * creating a new one.
- */
- msr sctlr_el1, x22 // disable the MMU
- isb
- bl __create_page_tables // recreate kernel mapping
-
- tlbi vmalle1 // Remove any stale TLB entries
- dsb nsh
-
- msr sctlr_el1, x19 // re-enable the MMU
- isb
- ic iallu // flush instructions fetched
- dsb nsh // via old mapping
- isb
-#endif
- br x27
+ ret
ENDPROC(__enable_mmu)
__no_granule_support:
@@ -775,11 +765,11 @@
1:
wfe
wfi
- b 1b
+ b 1b
ENDPROC(__no_granule_support)
-__primary_switch:
#ifdef CONFIG_RELOCATABLE
+__relocate_kernel:
/*
* Iterate over each entry in the relocation table, and apply the
* relocations in place.
@@ -801,14 +791,46 @@
add x13, x13, x23 // relocate
str x13, [x11, x23]
b 0b
+1: ret
+ENDPROC(__relocate_kernel)
+#endif
-1:
+__primary_switch:
+#ifdef CONFIG_RANDOMIZE_BASE
+ mov x19, x0 // preserve new SCTLR_EL1 value
+ mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value
+#endif
+
+ bl __enable_mmu
+#ifdef CONFIG_RELOCATABLE
+ bl __relocate_kernel
+#ifdef CONFIG_RANDOMIZE_BASE
+ ldr x8, =__primary_switched
+ adrp x0, __PHYS_OFFSET
+ blr x8
+
+ /*
+ * If we return here, we have a KASLR displacement in x23 which we need
+ * to take into account by discarding the current kernel mapping and
+ * creating a new one.
+ */
+ msr sctlr_el1, x20 // disable the MMU
+ isb
+ bl __create_page_tables // recreate kernel mapping
+
+ tlbi vmalle1 // Remove any stale TLB entries
+ dsb nsh
+
+ msr sctlr_el1, x19 // re-enable the MMU
+ isb
+ ic iallu // flush instructions fetched
+ dsb nsh // via old mapping
+ isb
+
+ bl __relocate_kernel
+#endif
#endif
ldr x8, =__primary_switched
+ adrp x0, __PHYS_OFFSET
br x8
ENDPROC(__primary_switch)
-
-__secondary_switch:
- ldr x8, =__secondary_switched
- br x8
-ENDPROC(__secondary_switch)
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 46f29b6..e56d848 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -36,8 +36,8 @@
.macro break_before_make_ttbr_switch zero_page, page_table
msr ttbr1_el1, \zero_page
isb
- tlbi vmalle1is
- dsb ish
+ tlbi vmalle1
+ dsb nsh
msr ttbr1_el1, \page_table
isb
.endm
@@ -96,7 +96,7 @@
add x1, x10, #PAGE_SIZE
/* Clean the copied page to PoU - based on flush_icache_range() */
- dcache_line_size x2, x3
+ raw_dcache_line_size x2, x3
sub x3, x2, #1
bic x4, x10, x3
2: dc cvau, x4 /* clean D line / unified line */
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 65d81f9..d55a7b0 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -15,9 +15,9 @@
* License terms: GNU General Public License (GPL) version 2
*/
#define pr_fmt(x) "hibernate: " x
+#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <linux/mm.h>
-#include <linux/notifier.h>
#include <linux/pm.h>
#include <linux/sched.h>
#include <linux/suspend.h>
@@ -26,6 +26,7 @@
#include <asm/barrier.h>
#include <asm/cacheflush.h>
+#include <asm/cputype.h>
#include <asm/irqflags.h>
#include <asm/memory.h>
#include <asm/mmu_context.h>
@@ -34,6 +35,7 @@
#include <asm/pgtable-hwdef.h>
#include <asm/sections.h>
#include <asm/smp.h>
+#include <asm/smp_plat.h>
#include <asm/suspend.h>
#include <asm/sysreg.h>
#include <asm/virt.h>
@@ -54,12 +56,6 @@
/* Do we need to reset el2? */
#define el2_reset_needed() (is_hyp_mode_available() && !is_kernel_in_hyp_mode())
-/*
- * Start/end of the hibernate exit code, this must be copied to a 'safe'
- * location in memory, and executed from there.
- */
-extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
-
/* temporary el2 vectors in the __hibernate_exit_text section. */
extern char hibernate_el2_vectors[];
@@ -67,6 +63,12 @@
extern char __hyp_stub_vectors[];
/*
+ * The logical cpu number we should resume on, initialised to a non-cpu
+ * number.
+ */
+static int sleep_cpu = -EINVAL;
+
+/*
* Values that may not change over hibernate/resume. We put the build number
* and date in here so that we guarantee not to resume with a different
* kernel.
@@ -88,6 +90,8 @@
* re-configure el2.
*/
phys_addr_t __hyp_stub_vectors;
+
+ u64 sleep_cpu_mpidr;
} resume_hdr;
static inline void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i)
@@ -130,12 +134,22 @@
else
hdr->__hyp_stub_vectors = 0;
+ /* Save the mpidr of the cpu we called cpu_suspend() on... */
+ if (sleep_cpu < 0) {
+ pr_err("Failing to hibernate on an unkown CPU.\n");
+ return -ENODEV;
+ }
+ hdr->sleep_cpu_mpidr = cpu_logical_map(sleep_cpu);
+ pr_info("Hibernating on CPU %d [mpidr:0x%llx]\n", sleep_cpu,
+ hdr->sleep_cpu_mpidr);
+
return 0;
}
EXPORT_SYMBOL(arch_hibernation_header_save);
int arch_hibernation_header_restore(void *addr)
{
+ int ret;
struct arch_hibernate_hdr_invariants invariants;
struct arch_hibernate_hdr *hdr = addr;
@@ -145,6 +159,24 @@
return -EINVAL;
}
+ sleep_cpu = get_logical_index(hdr->sleep_cpu_mpidr);
+ pr_info("Hibernated on CPU %d [mpidr:0x%llx]\n", sleep_cpu,
+ hdr->sleep_cpu_mpidr);
+ if (sleep_cpu < 0) {
+ pr_crit("Hibernated on a CPU not known to this kernel!\n");
+ sleep_cpu = -EINVAL;
+ return -EINVAL;
+ }
+ if (!cpu_online(sleep_cpu)) {
+ pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n");
+ ret = cpu_up(sleep_cpu);
+ if (ret) {
+ pr_err("Failed to bring hibernate-CPU up!\n");
+ sleep_cpu = -EINVAL;
+ return ret;
+ }
+ }
+
resume_hdr = *hdr;
return 0;
@@ -241,6 +273,7 @@
return rc;
}
+#define dcache_clean_range(start, end) __flush_dcache_area(start, (end - start))
int swsusp_arch_suspend(void)
{
@@ -256,10 +289,16 @@
local_dbg_save(flags);
if (__cpu_suspend_enter(&state)) {
+ sleep_cpu = smp_processor_id();
ret = swsusp_save();
} else {
- /* Clean kernel to PoC for secondary core startup */
- __flush_dcache_area(LMADDR(KERNEL_START), KERNEL_END - KERNEL_START);
+ /* Clean kernel core startup/idle code to PoC*/
+ dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end);
+ dcache_clean_range(__idmap_text_start, __idmap_text_end);
+
+ /* Clean kvm setup code to PoC? */
+ if (el2_reset_needed())
+ dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
/*
* Tell the hibernation core that we've just restored
@@ -267,6 +306,7 @@
*/
in_suspend = 0;
+ sleep_cpu = -EINVAL;
__cpu_suspend_exit();
}
@@ -275,6 +315,33 @@
return ret;
}
+static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
+{
+ pte_t pte = *src_pte;
+
+ if (pte_valid(pte)) {
+ /*
+ * Resume will overwrite areas that may be marked
+ * read only (code, rodata). Clear the RDONLY bit from
+ * the temporary mappings we use during restore.
+ */
+ set_pte(dst_pte, pte_clear_rdonly(pte));
+ } else if (debug_pagealloc_enabled() && !pte_none(pte)) {
+ /*
+ * debug_pagealloc will removed the PTE_VALID bit if
+ * the page isn't in use by the resume kernel. It may have
+ * been in use by the original kernel, in which case we need
+ * to put it back in our copy to do the restore.
+ *
+ * Before marking this entry valid, check the pfn should
+ * be mapped.
+ */
+ BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+ set_pte(dst_pte, pte_mkpresent(pte_clear_rdonly(pte)));
+ }
+}
+
static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
unsigned long end)
{
@@ -290,13 +357,7 @@
src_pte = pte_offset_kernel(src_pmd, start);
do {
- if (!pte_none(*src_pte))
- /*
- * Resume will overwrite areas that may be marked
- * read only (code, rodata). Clear the RDONLY bit from
- * the temporary mappings we use during restore.
- */
- set_pte(dst_pte, __pte(pte_val(*src_pte) & ~PTE_RDONLY));
+ _copy_pte(dst_pte, src_pte, addr);
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
return 0;
@@ -483,27 +544,12 @@
return rc;
}
-static int check_boot_cpu_online_pm_callback(struct notifier_block *nb,
- unsigned long action, void *ptr)
+int hibernate_resume_nonboot_cpu_disable(void)
{
- if (action == PM_HIBERNATION_PREPARE &&
- cpumask_first(cpu_online_mask) != 0) {
- pr_warn("CPU0 is offline.\n");
- return notifier_from_errno(-ENODEV);
+ if (sleep_cpu < 0) {
+ pr_err("Failing to resume from hibernate on an unkown CPU.\n");
+ return -ENODEV;
}
- return NOTIFY_OK;
+ return freeze_secondary_cpus(sleep_cpu);
}
-
-static int __init check_boot_cpu_online_init(void)
-{
- /*
- * Set this pm_notifier callback with a lower priority than
- * cpu_hotplug_pm_callback, so that cpu_hotplug_pm_callback will be
- * called earlier to disable cpu hotplug before the cpu online check.
- */
- pm_notifier(check_boot_cpu_online_pm_callback, -INT_MAX);
-
- return 0;
-}
-core_initcall(check_boot_cpu_online_init);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 26a6bf7..948b7314 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -857,7 +857,7 @@
/*
* CPU initialisation.
*/
-static void hw_breakpoint_reset(void *unused)
+static int hw_breakpoint_reset(unsigned int cpu)
{
int i;
struct perf_event **slots;
@@ -888,28 +888,14 @@
write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
}
}
-}
-static int hw_breakpoint_reset_notify(struct notifier_block *self,
- unsigned long action,
- void *hcpu)
-{
- if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) {
- local_irq_disable();
- hw_breakpoint_reset(NULL);
- local_irq_enable();
- }
- return NOTIFY_OK;
+ return 0;
}
-static struct notifier_block hw_breakpoint_reset_nb = {
- .notifier_call = hw_breakpoint_reset_notify,
-};
-
#ifdef CONFIG_CPU_PM
-extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *));
+extern void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int));
#else
-static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+static inline void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int))
{
}
#endif
@@ -919,36 +905,34 @@
*/
static int __init arch_hw_breakpoint_init(void)
{
+ int ret;
+
core_num_brps = get_num_brps();
core_num_wrps = get_num_wrps();
pr_info("found %d breakpoint and %d watchpoint registers.\n",
core_num_brps, core_num_wrps);
- cpu_notifier_register_begin();
-
- /*
- * Reset the breakpoint resources. We assume that a halting
- * debugger will leave the world in a nice state for us.
- */
- smp_call_function(hw_breakpoint_reset, NULL, 1);
- hw_breakpoint_reset(NULL);
-
/* Register debug fault handlers. */
hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP,
TRAP_HWBKPT, "hw-breakpoint handler");
hook_debug_fault_code(DBG_ESR_EVT_HWWP, watchpoint_handler, SIGTRAP,
TRAP_HWBKPT, "hw-watchpoint handler");
- /* Register hotplug notifier. */
- __register_cpu_notifier(&hw_breakpoint_reset_nb);
-
- cpu_notifier_register_done();
+ /*
+ * Reset the breakpoint resources. We assume that a halting
+ * debugger will leave the world in a nice state for us.
+ */
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
+ "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+ hw_breakpoint_reset, NULL);
+ if (ret)
+ pr_err("failed to register CPU hotplug notifier: %d\n", ret);
/* Register cpu_suspend hw breakpoint restore hook */
cpu_suspend_set_dbg_restorer(hw_breakpoint_reset);
- return 0;
+ return ret;
}
arch_initcall(arch_hw_breakpoint_init);
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 63f9432..6f2ac4f 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -96,7 +96,7 @@
if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX))
page = vmalloc_to_page(addr);
- else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA))
+ else if (!module)
page = pfn_to_page(PHYS_PFN(__pa(addr)));
else
return addr;
@@ -1202,6 +1202,19 @@
BUG();
}
+s32 aarch64_insn_adrp_get_offset(u32 insn)
+{
+ BUG_ON(!aarch64_insn_is_adrp(insn));
+ return aarch64_insn_decode_immediate(AARCH64_INSN_IMM_ADR, insn) << 12;
+}
+
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset)
+{
+ BUG_ON(!aarch64_insn_is_adrp(insn));
+ return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn,
+ offset >> 12);
+}
+
/*
* Extract the Op/CR data from a msr/mrs instruction.
*/
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index b054691..769f24e 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -6,6 +6,7 @@
* published by the Free Software Foundation.
*/
+#include <linux/cache.h>
#include <linux/crc32.h>
#include <linux/init.h>
#include <linux/libfdt.h>
@@ -20,7 +21,7 @@
#include <asm/pgtable.h>
#include <asm/sections.h>
-u64 __read_mostly module_alloc_base;
+u64 __ro_after_init module_alloc_base;
u16 __initdata memstart_offset_seed;
static __init u64 get_kaslr_seed(void *fdt)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 838ccf1..a9310a6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -24,6 +24,7 @@
#include <asm/sysreg.h>
#include <asm/virt.h>
+#include <linux/acpi.h>
#include <linux/of.h>
#include <linux/perf/arm_pmu.h>
#include <linux/platform_device.h>
@@ -190,13 +191,23 @@
#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS 0xED
/* PMUv3 HW events mapping. */
+
+/*
+ * ARMv8 Architectural defined events, not all of these may
+ * be supported on any given implementation. Undefined events will
+ * be disabled at run-time.
+ */
static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED,
[PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
[PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
};
/* ARM Cortex-A53 HW events mapping. */
@@ -258,6 +269,15 @@
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+ [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE,
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
+
+ [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL,
+ [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
+ [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB,
+
[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
[C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
@@ -523,12 +543,6 @@
.attrs = armv8_pmuv3_format_attrs,
};
-static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
- &armv8_pmuv3_events_attr_group,
- &armv8_pmuv3_format_attr_group,
- NULL,
-};
-
/*
* Perf Events' indices
*/
@@ -905,9 +919,22 @@
static int armv8_pmuv3_map_event(struct perf_event *event)
{
- return armpmu_map_event(event, &armv8_pmuv3_perf_map,
- &armv8_pmuv3_perf_cache_map,
- ARMV8_PMU_EVTYPE_EVENT);
+ int hw_event_id;
+ struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+
+ hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map,
+ &armv8_pmuv3_perf_cache_map,
+ ARMV8_PMU_EVTYPE_EVENT);
+ if (hw_event_id < 0)
+ return hw_event_id;
+
+ /* disable micro/arch events not supported by this PMU */
+ if ((hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) &&
+ !test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
+ return -EOPNOTSUPP;
+ }
+
+ return hw_event_id;
}
static int armv8_a53_map_event(struct perf_event *event)
@@ -985,7 +1012,10 @@
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_pmuv3";
cpu_pmu->map_event = armv8_pmuv3_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -994,7 +1024,10 @@
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cortex_a53";
cpu_pmu->map_event = armv8_a53_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1003,7 +1036,10 @@
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cortex_a57";
cpu_pmu->map_event = armv8_a57_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1012,7 +1048,10 @@
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cortex_a72";
cpu_pmu->map_event = armv8_a57_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1021,7 +1060,10 @@
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_cavium_thunder";
cpu_pmu->map_event = armv8_thunder_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1030,7 +1072,10 @@
armv8_pmu_init(cpu_pmu);
cpu_pmu->name = "armv8_brcm_vulcan";
cpu_pmu->map_event = armv8_vulcan_map_event;
- cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
return armv8pmu_probe_pmu(cpu_pmu);
}
@@ -1044,21 +1089,32 @@
{},
};
+/*
+ * Non DT systems have their micro/arch events probed at run-time.
+ * A fairly complete list of generic events are provided and ones that
+ * aren't supported by the current PMU are disabled.
+ */
+static const struct pmu_probe_info armv8_pmu_probe_table[] = {
+ PMU_PROBE(0, 0, armv8_pmuv3_init), /* enable all defined counters */
+ { /* sentinel value */ }
+};
+
static int armv8_pmu_device_probe(struct platform_device *pdev)
{
- return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
+ if (acpi_disabled)
+ return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+ NULL);
+
+ return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+ armv8_pmu_probe_table);
}
static struct platform_driver armv8_pmu_driver = {
.driver = {
- .name = "armv8-pmu",
+ .name = ARMV8_PMU_PDEV_NAME,
.of_match_table = armv8_pmu_of_device_ids,
},
.probe = armv8_pmu_device_probe,
};
-static int __init register_armv8_pmu_driver(void)
-{
- return platform_driver_register(&armv8_pmu_driver);
-}
-device_initcall(register_armv8_pmu_driver);
+builtin_platform_driver(armv8_pmu_driver);
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index 37e47a9..d1731bf 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -16,6 +16,7 @@
#include <linux/kernel.h>
#include <linux/kprobes.h>
#include <linux/module.h>
+#include <linux/kallsyms.h>
#include <asm/kprobes.h>
#include <asm/insn.h>
#include <asm/sections.h>
@@ -122,7 +123,7 @@
static bool __kprobes
is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end)
{
- while (scan_start > scan_end) {
+ while (scan_start >= scan_end) {
/*
* atomic region starts from exclusive load and ends with
* exclusive store.
@@ -142,33 +143,30 @@
{
enum kprobe_insn decoded;
kprobe_opcode_t insn = le32_to_cpu(*addr);
- kprobe_opcode_t *scan_start = addr - 1;
- kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
-#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
- struct module *mod;
-#endif
+ kprobe_opcode_t *scan_end = NULL;
+ unsigned long size = 0, offset = 0;
- if (addr >= (kprobe_opcode_t *)_text &&
- scan_end < (kprobe_opcode_t *)_text)
- scan_end = (kprobe_opcode_t *)_text;
-#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
- else {
- preempt_disable();
- mod = __module_address((unsigned long)addr);
- if (mod && within_module_init((unsigned long)addr, mod) &&
- !within_module_init((unsigned long)scan_end, mod))
- scan_end = (kprobe_opcode_t *)mod->init_layout.base;
- else if (mod && within_module_core((unsigned long)addr, mod) &&
- !within_module_core((unsigned long)scan_end, mod))
- scan_end = (kprobe_opcode_t *)mod->core_layout.base;
- preempt_enable();
+ /*
+ * If there's a symbol defined in front of and near enough to
+ * the probe address assume it is the entry point to this
+ * code and use it to further limit how far back we search
+ * when determining if we're in an atomic sequence. If we could
+ * not find any symbol skip the atomic test altogether as we
+ * could otherwise end up searching irrelevant text/literals.
+ * KPROBES depends on KALLSYMS so this last case should never
+ * happen.
+ */
+ if (kallsyms_lookup_size_offset((unsigned long) addr, &size, &offset)) {
+ if (offset < (MAX_ATOMIC_CONTEXT_SIZE*sizeof(kprobe_opcode_t)))
+ scan_end = addr - (offset / sizeof(kprobe_opcode_t));
+ else
+ scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
}
-#endif
decoded = arm_probe_decode_insn(insn, asi);
- if (decoded == INSN_REJECTED ||
- is_probed_address_atomic(scan_start, scan_end))
- return INSN_REJECTED;
+ if (decoded != INSN_REJECTED && scan_end)
+ if (is_probed_address_atomic(addr - 1, scan_end))
+ return INSN_REJECTED;
return decoded;
}
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index c6b0f40..f5077ea 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -19,7 +19,7 @@
#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/kprobes.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/slab.h>
#include <linux/stop_machine.h>
#include <linux/stringify.h>
@@ -31,7 +31,7 @@
#include <asm/insn.h>
#include <asm/uaccess.h>
#include <asm/irq.h>
-#include <asm-generic/sections.h>
+#include <asm/sections.h>
#include "decode-insn.h"
@@ -166,13 +166,18 @@
}
/*
- * The D-flag (Debug mask) is set (masked) upon debug exception entry.
- * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive
- * probe i.e. when probe hit from kprobe handler context upon
- * executing the pre/post handlers. In this case we return with
- * D-flag clear so that single-stepping can be carried-out.
- *
- * Leave D-flag set in all other cases.
+ * When PSTATE.D is set (masked), then software step exceptions can not be
+ * generated.
+ * SPSR's D bit shows the value of PSTATE.D immediately before the
+ * exception was taken. PSTATE.D is set while entering into any exception
+ * mode, however software clears it for any normal (none-debug-exception)
+ * mode in the exception entry. Therefore, when we are entering into kprobe
+ * breakpoint handler from any normal mode then SPSR.D bit is already
+ * cleared, however it is set when we are entering from any debug exception
+ * mode.
+ * Since we always need to generate single step exception after a kprobe
+ * breakpoint exception therefore we need to clear it unconditionally, when
+ * we become sure that the current breakpoint exception is for kprobe.
*/
static void __kprobes
spsr_set_debug_flag(struct pt_regs *regs, int mask)
@@ -245,10 +250,7 @@
set_ss_context(kcb, slot); /* mark pending ss */
- if (kcb->kprobe_status == KPROBE_REENTER)
- spsr_set_debug_flag(regs, 0);
- else
- WARN_ON(regs->pstate & PSR_D_BIT);
+ spsr_set_debug_flag(regs, 0);
/* IRQs and single stepping do not mix well. */
kprobes_save_local_irqflag(kcb, regs);
@@ -333,8 +335,6 @@
BUG();
kernel_disable_single_step();
- if (kcb->kprobe_status == KPROBE_REENTER)
- spsr_set_debug_flag(regs, 1);
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
@@ -457,9 +457,6 @@
kprobes_restore_local_irqflag(kcb, regs);
kernel_disable_single_step();
- if (kcb->kprobe_status == KPROBE_REENTER)
- spsr_set_debug_flag(regs, 1);
-
post_kprobe_handler(kcb, regs);
}
@@ -543,9 +540,6 @@
bool arch_within_kprobe_blacklist(unsigned long addr)
{
- extern char __idmap_text_start[], __idmap_text_end[];
- extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
if ((addr >= (unsigned long)__kprobes_text_start &&
addr < (unsigned long)__kprobes_text_end) ||
(addr >= (unsigned long)__entry_text_start &&
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 6cd2612..a4f5f76 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -202,7 +202,7 @@
static void tls_thread_flush(void)
{
- asm ("msr tpidr_el0, xzr");
+ write_sysreg(0, tpidr_el0);
if (is_compat_task()) {
current->thread.tp_value = 0;
@@ -213,7 +213,7 @@
* with a stale shadow state during context switch.
*/
barrier();
- asm ("msr tpidrro_el0, xzr");
+ write_sysreg(0, tpidrro_el0);
}
}
@@ -253,7 +253,7 @@
* Read the current TLS pointer from tpidr_el0 as it may be
* out-of-sync with the saved value.
*/
- asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p)));
+ *task_user_tls(p) = read_sysreg(tpidr_el0);
if (stack_start) {
if (is_compat_thread(task_thread_info(p)))
@@ -289,17 +289,15 @@
{
unsigned long tpidr, tpidrro;
- asm("mrs %0, tpidr_el0" : "=r" (tpidr));
+ tpidr = read_sysreg(tpidr_el0);
*task_user_tls(current) = tpidr;
tpidr = *task_user_tls(next);
tpidrro = is_compat_thread(task_thread_info(next)) ?
next->thread.tp_value : 0;
- asm(
- " msr tpidr_el0, %0\n"
- " msr tpidrro_el0, %1"
- : : "r" (tpidr), "r" (tpidrro));
+ write_sysreg(tpidr, tpidr_el0);
+ write_sysreg(tpidrro, tpidrro_el0);
}
/* Restore the UAO state depending on next's addr_limit */
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index 51b73cd..ce704a4 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -34,7 +34,7 @@
/* Setup the list loop variables. */
mov x17, x1 /* x17 = kimage_start */
mov x16, x0 /* x16 = kimage_head */
- dcache_line_size x15, x0 /* x15 = dcache line size */
+ raw_dcache_line_size x15, x0 /* x15 = dcache line size */
mov x14, xzr /* x14 = entry ptr */
mov x13, xzr /* x13 = copy dest */
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 536dce2..f534f49 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -206,10 +206,15 @@
for_each_memblock(memory, region) {
res = alloc_bootmem_low(sizeof(*res));
- res->name = "System RAM";
+ if (memblock_is_nomap(region)) {
+ res->name = "reserved";
+ res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ } else {
+ res->name = "System RAM";
+ res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ }
res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
- res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
request_resource(&iomem_resource, res);
@@ -228,7 +233,7 @@
{
pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
- sprintf(init_utsname()->machine, ELF_PLATFORM);
+ sprintf(init_utsname()->machine, UTS_MACHINE);
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index a8eafdb..404dd67 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -402,15 +402,31 @@
asmlinkage void do_notify_resume(struct pt_regs *regs,
unsigned int thread_flags)
{
- if (thread_flags & _TIF_SIGPENDING)
- do_signal(regs);
+ /*
+ * The assembly code enters us with IRQs off, but it hasn't
+ * informed the tracing code of that for efficiency reasons.
+ * Update the trace code with the current status.
+ */
+ trace_hardirqs_off();
+ do {
+ if (thread_flags & _TIF_NEED_RESCHED) {
+ schedule();
+ } else {
+ local_irq_enable();
- if (thread_flags & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
- tracehook_notify_resume(regs);
- }
+ if (thread_flags & _TIF_SIGPENDING)
+ do_signal(regs);
- if (thread_flags & _TIF_FOREIGN_FPSTATE)
- fpsimd_restore_current_state();
+ if (thread_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
+ if (thread_flags & _TIF_FOREIGN_FPSTATE)
+ fpsimd_restore_current_state();
+ }
+
+ local_irq_disable();
+ thread_flags = READ_ONCE(current_thread_info()->flags);
+ } while (thread_flags & _TIF_WORK_MASK);
}
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index ccf79d8..b8799e7 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -73,10 +73,9 @@
str x2, [x0, #SLEEP_STACK_DATA_SYSTEM_REGS + CPU_CTX_SP]
/* find the mpidr_hash */
- ldr x1, =sleep_save_stash
- ldr x1, [x1]
+ ldr_l x1, sleep_save_stash
mrs x7, mpidr_el1
- ldr x9, =mpidr_hash
+ adr_l x9, mpidr_hash
ldr x10, [x9, #MPIDR_HASH_MASK]
/*
* Following code relies on the struct mpidr_hash
@@ -95,36 +94,30 @@
mov x0, #1
ret
ENDPROC(__cpu_suspend_enter)
- .ltorg
+ .pushsection ".idmap.text", "ax"
ENTRY(cpu_resume)
bl el2_setup // if in EL2 drop to EL1 cleanly
+ bl __cpu_setup
/* enable the MMU early - so we can access sleep_save_stash by va */
- adr_l lr, __enable_mmu /* __cpu_setup will return here */
- adr_l x27, _resume_switched /* __enable_mmu will branch here */
- adrp x25, idmap_pg_dir
- adrp x26, swapper_pg_dir
- b __cpu_setup
-ENDPROC(cpu_resume)
-
- .pushsection ".idmap.text", "ax"
-_resume_switched:
+ bl __enable_mmu
ldr x8, =_cpu_resume
br x8
-ENDPROC(_resume_switched)
+ENDPROC(cpu_resume)
.ltorg
.popsection
ENTRY(_cpu_resume)
mrs x1, mpidr_el1
- adrp x8, mpidr_hash
- add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
- /* retrieve mpidr_hash members to compute the hash */
+ adr_l x8, mpidr_hash // x8 = struct mpidr_hash virt address
+
+ /* retrieve mpidr_hash members to compute the hash */
ldr x2, [x8, #MPIDR_HASH_MASK]
ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS]
ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
- /* x7 contains hash index, let's use it to grab context pointer */
+
+ /* x7 contains hash index, let's use it to grab context pointer */
ldr_l x0, sleep_save_stash
ldr x0, [x0, x7, lsl #3]
add x29, x0, #SLEEP_STACK_DATA_CALLEE_REGS
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 3ff173e..d3f151c 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -233,7 +233,7 @@
* this CPU ticks all of those. If it doesn't, the CPU will
* fail to come online.
*/
- verify_local_cpu_capabilities();
+ check_local_cpu_capabilities();
if (cpu_ops[cpu]->cpu_postboot)
cpu_ops[cpu]->cpu_postboot();
@@ -431,8 +431,19 @@
void __init smp_prepare_boot_cpu(void)
{
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+ /*
+ * Initialise the static keys early as they may be enabled by the
+ * cpufeature code.
+ */
+ jump_label_init();
cpuinfo_store_boot_cpu();
save_boot_cpu_run_el();
+ /*
+ * Run the errata work around checks on the boot CPU, once we have
+ * initialised the cpu feature infrastructure from
+ * cpuinfo_store_boot_cpu() above.
+ */
+ update_cpu_errata_workarounds();
}
static u64 __init of_get_cpu_mpidr(struct device_node *dn)
@@ -613,6 +624,7 @@
}
bootcpu_valid = true;
+ early_map_cpu_to_node(0, of_node_to_nid(dn));
/*
* cpu_logical_map has already been
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 18a71bc..9a00eee 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -29,7 +29,8 @@
#include <asm/smp_plat.h>
extern void secondary_holding_pen(void);
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
+volatile unsigned long __section(".mmuoff.data.read")
+secondary_holding_pen_release = INVALID_HWID;
static phys_addr_t cpu_release_addr[NR_CPUS];
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d9751a4..c2efddf 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -43,6 +43,9 @@
unsigned long fp = frame->fp;
unsigned long irq_stack_ptr;
+ if (!tsk)
+ tsk = current;
+
/*
* Switching between stacks is valid when tracing current and in
* non-preemptible context.
@@ -67,7 +70,7 @@
frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- if (tsk && tsk->ret_stack &&
+ if (tsk->ret_stack &&
(frame->pc == (unsigned long)return_to_handler)) {
/*
* This is a case where function graph tracer has
@@ -152,6 +155,27 @@
return trace->nr_entries >= trace->max_entries;
}
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+ struct stack_trace_data data;
+ struct stackframe frame;
+
+ data.trace = trace;
+ data.skip = trace->skip;
+ data.no_sched_functions = 0;
+
+ frame.fp = regs->regs[29];
+ frame.sp = regs->sp;
+ frame.pc = regs->pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ frame.graph = current->curr_ret_stack;
+#endif
+
+ walk_stackframe(current, &frame, save_trace, &data);
+ if (trace->nr_entries < trace->max_entries)
+ trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
struct stack_trace_data data;
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index b616e36..ad73414 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -23,8 +23,8 @@
* time the notifier runs debug exceptions might have been enabled already,
* with HW breakpoints registers content still in an unknown state.
*/
-static void (*hw_breakpoint_restore)(void *);
-void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+static int (*hw_breakpoint_restore)(unsigned int);
+void __init cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int))
{
/* Prevent multiple restore hook initializations */
if (WARN_ON(hw_breakpoint_restore))
@@ -34,6 +34,8 @@
void notrace __cpu_suspend_exit(void)
{
+ unsigned int cpu = smp_processor_id();
+
/*
* We are resuming from reset with the idmap active in TTBR0_EL1.
* We must uninstall the idmap and restore the expected MMU
@@ -45,7 +47,7 @@
* Restore per-cpu offset before any kernel
* subsystem relying on it has a chance to run.
*/
- set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+ set_my_cpu_offset(per_cpu_offset(cpu));
/*
* Restore HW breakpoint registers to sane values
@@ -53,7 +55,7 @@
* through local_dbg_restore.
*/
if (hw_breakpoint_restore)
- hw_breakpoint_restore(NULL);
+ hw_breakpoint_restore(cpu);
}
/*
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 28c511b..abaf582 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -94,7 +94,7 @@
* See comment in tls_thread_flush.
*/
barrier();
- asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
+ write_sysreg(regs->regs[0], tpidrro_el0);
return 0;
default:
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index e04f838..5ff020f 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -142,6 +142,11 @@
unsigned long irq_stack_ptr;
int skip;
+ pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
+
+ if (!tsk)
+ tsk = current;
+
/*
* Switching between stacks is valid when tracing current and in
* non-preemptible context.
@@ -151,11 +156,6 @@
else
irq_stack_ptr = 0;
- pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
-
- if (!tsk)
- tsk = current;
-
if (tsk == current) {
frame.fp = (unsigned long)__builtin_frame_address(0);
frame.sp = current_stack_pointer;
@@ -447,36 +447,29 @@
: "=r" (res) \
: "r" (address), "i" (-EFAULT) )
-asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
{
unsigned long address;
- int ret;
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
+ int ret = 0;
- /* if this is a write with: Op0=1, Op2=1, Op1=3, CRn=7 */
- if ((esr & 0x01fffc01) == 0x0012dc00) {
- int rt = (esr >> 5) & 0x1f;
- int crm = (esr >> 1) & 0x0f;
+ address = (rt == 31) ? 0 : regs->regs[rt];
- address = (rt == 31) ? 0 : regs->regs[rt];
-
- switch (crm) {
- case 11: /* DC CVAU, gets promoted */
- __user_cache_maint("dc civac", address, ret);
- break;
- case 10: /* DC CVAC, gets promoted */
- __user_cache_maint("dc civac", address, ret);
- break;
- case 14: /* DC CIVAC */
- __user_cache_maint("dc civac", address, ret);
- break;
- case 5: /* IC IVAU */
- __user_cache_maint("ic ivau", address, ret);
- break;
- default:
- force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
- return;
- }
- } else {
+ switch (crm) {
+ case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case ESR_ELx_SYS64_ISS_CRM_DC_CVAC: /* DC CVAC, gets promoted */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case ESR_ELx_SYS64_ISS_CRM_DC_CIVAC: /* DC CIVAC */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case ESR_ELx_SYS64_ISS_CRM_IC_IVAU: /* IC IVAU */
+ __user_cache_maint("ic ivau", address, ret);
+ break;
+ default:
force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
return;
}
@@ -487,6 +480,48 @@
regs->pc += 4;
}
+static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+ regs->regs[rt] = arm64_ftr_reg_ctrel0.sys_val;
+ regs->pc += 4;
+}
+
+struct sys64_hook {
+ unsigned int esr_mask;
+ unsigned int esr_val;
+ void (*handler)(unsigned int esr, struct pt_regs *regs);
+};
+
+static struct sys64_hook sys64_hooks[] = {
+ {
+ .esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL,
+ .handler = user_cache_maint_handler,
+ },
+ {
+ /* Trap read access to CTR_EL0 */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ,
+ .handler = ctr_read_handler,
+ },
+ {},
+};
+
+asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+{
+ struct sys64_hook *hook;
+
+ for (hook = sys64_hooks; hook->handler; hook++)
+ if ((hook->esr_mask & esr) == hook->esr_val) {
+ hook->handler(esr, regs);
+ return;
+ }
+
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+}
+
long compat_arm_syscall(struct pt_regs *regs);
asmlinkage long do_ni_syscall(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 076312b..a2c2478 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,12 +18,13 @@
* Author: Will Deacon <will.deacon@arm.com>
*/
-#include <linux/kernel.h>
+#include <linux/cache.h>
#include <linux/clocksource.h>
#include <linux/elf.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/gfp.h>
+#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/signal.h>
@@ -37,8 +38,7 @@
#include <asm/vdso_datapage.h>
extern char vdso_start, vdso_end;
-static unsigned long vdso_pages;
-static struct page **vdso_pagelist;
+static unsigned long vdso_pages __ro_after_init;
/*
* The vDSO data page.
@@ -53,9 +53,9 @@
/*
* Create and map the vectors page for AArch32 tasks.
*/
-static struct page *vectors_page[1];
+static struct page *vectors_page[1] __ro_after_init;
-static int alloc_vectors_page(void)
+static int __init alloc_vectors_page(void)
{
extern char __kuser_helper_start[], __kuser_helper_end[];
extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
@@ -88,7 +88,7 @@
{
struct mm_struct *mm = current->mm;
unsigned long addr = AARCH32_VECTORS_BASE;
- static struct vm_special_mapping spec = {
+ static const struct vm_special_mapping spec = {
.name = "[vectors]",
.pages = vectors_page,
@@ -110,11 +110,19 @@
}
#endif /* CONFIG_COMPAT */
-static struct vm_special_mapping vdso_spec[2];
+static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
+ {
+ .name = "[vvar]",
+ },
+ {
+ .name = "[vdso]",
+ },
+};
static int __init vdso_init(void)
{
int i;
+ struct page **vdso_pagelist;
if (memcmp(&vdso_start, "\177ELF", 4)) {
pr_err("vDSO is not a valid ELF object!\n");
@@ -138,16 +146,8 @@
for (i = 0; i < vdso_pages; i++)
vdso_pagelist[i + 1] = pfn_to_page(PHYS_PFN(__pa(&vdso_start)) + i);
- /* Populate the special mapping structures */
- vdso_spec[0] = (struct vm_special_mapping) {
- .name = "[vvar]",
- .pages = vdso_pagelist,
- };
-
- vdso_spec[1] = (struct vm_special_mapping) {
- .name = "[vdso]",
- .pages = &vdso_pagelist[1],
- };
+ vdso_spec[0].pages = &vdso_pagelist[0];
+ vdso_spec[1].pages = &vdso_pagelist[1];
return 0;
}
@@ -201,7 +201,7 @@
*/
void update_vsyscall(struct timekeeper *tk)
{
- u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
+ u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
++vdso_data->tb_seq_count;
smp_wmb();
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 659963d..5ce9b29 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -185,6 +185,25 @@
_data = .;
_sdata = .;
RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+
+ /*
+ * Data written with the MMU off but read with the MMU on requires
+ * cache lines to be invalidated, discarding up to a Cache Writeback
+ * Granule (CWG) of data from the cache. Keep the section that
+ * requires this type of maintenance to be in its own Cache Writeback
+ * Granule (CWG) area so the cache maintenance operations don't
+ * interfere with adjacent data.
+ */
+ .mmuoff.data.write : ALIGN(SZ_2K) {
+ __mmuoff_data_start = .;
+ *(.mmuoff.data.write)
+ }
+ . = ALIGN(SZ_2K);
+ .mmuoff.data.read : {
+ *(.mmuoff.data.read)
+ __mmuoff_data_end = .;
+ }
+
PECOFF_EDATA_PADDING
_edata = .;
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 7ce9315..2726635 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -46,10 +46,6 @@
hvc #0
ldr lr, [sp], #16
ret
-alternative_else
+alternative_else_nop_endif
b __vhe_hyp_call
- nop
- nop
- nop
-alternative_endif
ENDPROC(__kvm_call_hyp)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e51367d..f302fdb 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -36,6 +36,7 @@
#include <asm/kvm_host.h>
#include <asm/kvm_mmu.h>
#include <asm/perf_event.h>
+#include <asm/sysreg.h>
#include <trace/events/kvm.h>
@@ -67,11 +68,9 @@
/* Make sure noone else changes CSSELR during this! */
local_irq_disable();
- /* Put value into CSSELR */
- asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+ write_sysreg(csselr, csselr_el1);
isb();
- /* Read result out of CCSIDR */
- asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr));
+ ccsidr = read_sysreg(ccsidr_el1);
local_irq_enable();
return ccsidr;
@@ -174,9 +173,7 @@
if (p->is_write) {
return ignore_write(vcpu, p);
} else {
- u32 val;
- asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
- p->regval = val;
+ p->regval = read_sysreg(dbgauthstatus_el1);
return true;
}
}
@@ -429,10 +426,7 @@
static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
- u64 amair;
-
- asm volatile("mrs %0, amair_el1\n" : "=r" (amair));
- vcpu_sys_reg(vcpu, AMAIR_EL1) = amair;
+ vcpu_sys_reg(vcpu, AMAIR_EL1) = read_sysreg(amair_el1);
}
static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
@@ -456,8 +450,9 @@
{
u64 pmcr, val;
- asm volatile("mrs %0, pmcr_el0\n" : "=r" (pmcr));
- /* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) is reset to UNKNOWN
+ pmcr = read_sysreg(pmcr_el0);
+ /*
+ * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
* except PMCR.E resetting to zero.
*/
val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
@@ -557,9 +552,9 @@
return false;
if (!(p->Op2 & 1))
- asm volatile("mrs %0, pmceid0_el0\n" : "=r" (pmceid));
+ pmceid = read_sysreg(pmceid0_el0);
else
- asm volatile("mrs %0, pmceid1_el0\n" : "=r" (pmceid));
+ pmceid = read_sysreg(pmceid1_el0);
p->regval = pmceid;
@@ -1833,11 +1828,7 @@
static void get_##reg(struct kvm_vcpu *v, \
const struct sys_reg_desc *r) \
{ \
- u64 val; \
- \
- asm volatile("mrs %0, " __stringify(reg) "\n" \
- : "=r" (val)); \
- ((struct sys_reg_desc *)r)->val = val; \
+ ((struct sys_reg_desc *)r)->val = read_sysreg(reg); \
}
FUNCTION_INVARIANT(midr_el1)
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index ed90578..46af718 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -26,6 +26,7 @@
#include <asm/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
+#include <asm/sysreg.h>
#include <linux/init.h>
#include "sys_regs.h"
@@ -43,10 +44,7 @@
static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
- u64 actlr;
-
- asm volatile("mrs %0, actlr_el1\n" : "=r" (actlr));
- vcpu_sys_reg(vcpu, ACTLR_EL1) = actlr;
+ vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
}
/*
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index 4c1e700..c3cd65e 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -29,14 +29,11 @@
* x1 - src
*/
ENTRY(copy_page)
-alternative_if_not ARM64_HAS_NO_HW_PREFETCH
- nop
- nop
-alternative_else
+alternative_if ARM64_HAS_NO_HW_PREFETCH
# Prefetch two cache lines ahead.
prfm pldl1strm, [x1, #128]
prfm pldl1strm, [x1, #256]
-alternative_endif
+alternative_else_nop_endif
ldp x2, x3, [x1]
ldp x4, x5, [x1, #16]
@@ -52,11 +49,9 @@
1:
subs x18, x18, #128
-alternative_if_not ARM64_HAS_NO_HW_PREFETCH
- nop
-alternative_else
+alternative_if ARM64_HAS_NO_HW_PREFETCH
prfm pldl1strm, [x1, #384]
-alternative_endif
+alternative_else_nop_endif
stnp x2, x3, [x0]
ldp x2, x3, [x1]
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 07d7352..58b5a90 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -105,19 +105,20 @@
ENDPROC(__clean_dcache_area_pou)
/*
+ * __dma_inv_area(start, size)
+ * - start - virtual start address of region
+ * - size - size in question
+ */
+__dma_inv_area:
+ add x1, x1, x0
+ /* FALLTHROUGH */
+
+/*
* __inval_cache_range(start, end)
* - start - start address of region
* - end - end address of region
*/
ENTRY(__inval_cache_range)
- /* FALLTHROUGH */
-
-/*
- * __dma_inv_range(start, end)
- * - start - virtual start address of region
- * - end - virtual end address of region
- */
-__dma_inv_range:
dcache_line_size x2, x3
sub x3, x2, #1
tst x1, x3 // end cache line aligned?
@@ -136,46 +137,43 @@
dsb sy
ret
ENDPIPROC(__inval_cache_range)
-ENDPROC(__dma_inv_range)
+ENDPROC(__dma_inv_area)
/*
- * __dma_clean_range(start, end)
- * - start - virtual start address of region
- * - end - virtual end address of region
+ * __clean_dcache_area_poc(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned to the PoC.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
*/
-__dma_clean_range:
- dcache_line_size x2, x3
- sub x3, x2, #1
- bic x0, x0, x3
-1:
-alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
- dc cvac, x0
-alternative_else
- dc civac, x0
-alternative_endif
- add x0, x0, x2
- cmp x0, x1
- b.lo 1b
- dsb sy
- ret
-ENDPROC(__dma_clean_range)
+ENTRY(__clean_dcache_area_poc)
+ /* FALLTHROUGH */
/*
- * __dma_flush_range(start, end)
+ * __dma_clean_area(start, size)
* - start - virtual start address of region
- * - end - virtual end address of region
+ * - size - size in question
*/
-ENTRY(__dma_flush_range)
- dcache_line_size x2, x3
- sub x3, x2, #1
- bic x0, x0, x3
-1: dc civac, x0 // clean & invalidate D / U line
- add x0, x0, x2
- cmp x0, x1
- b.lo 1b
- dsb sy
+__dma_clean_area:
+ dcache_by_line_op cvac, sy, x0, x1, x2, x3
ret
-ENDPIPROC(__dma_flush_range)
+ENDPIPROC(__clean_dcache_area_poc)
+ENDPROC(__dma_clean_area)
+
+/*
+ * __dma_flush_area(start, size)
+ *
+ * clean & invalidate D / U line
+ *
+ * - start - virtual start address of region
+ * - size - size in question
+ */
+ENTRY(__dma_flush_area)
+ dcache_by_line_op civac, sy, x0, x1, x2, x3
+ ret
+ENDPIPROC(__dma_flush_area)
/*
* __dma_map_area(start, size, dir)
@@ -184,10 +182,9 @@
* - dir - DMA direction
*/
ENTRY(__dma_map_area)
- add x1, x1, x0
cmp w2, #DMA_FROM_DEVICE
- b.eq __dma_inv_range
- b __dma_clean_range
+ b.eq __dma_inv_area
+ b __dma_clean_area
ENDPIPROC(__dma_map_area)
/*
@@ -197,8 +194,7 @@
* - dir - DMA direction
*/
ENTRY(__dma_unmap_area)
- add x1, x1, x0
cmp w2, #DMA_TO_DEVICE
- b.ne __dma_inv_range
+ b.ne __dma_inv_area
ret
ENDPIPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index c4284c4..bdacead 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,6 +20,7 @@
#include <linux/gfp.h>
#include <linux/acpi.h>
#include <linux/bootmem.h>
+#include <linux/cache.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/genalloc.h>
@@ -30,7 +31,7 @@
#include <asm/cacheflush.h>
-static int swiotlb __read_mostly;
+static int swiotlb __ro_after_init;
static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
bool coherent)
@@ -168,7 +169,7 @@
return ptr;
/* remove any dirty cache lines on the kernel alias */
- __dma_flush_range(ptr, ptr + size);
+ __dma_flush_area(ptr, size);
/* create a coherent mapping */
page = virt_to_page(ptr);
@@ -387,7 +388,7 @@
void *page_addr = page_address(page);
memset(page_addr, 0, atomic_pool_size);
- __dma_flush_range(page_addr, page_addr + atomic_pool_size);
+ __dma_flush_area(page_addr, atomic_pool_size);
atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
if (!atomic_pool)
@@ -548,7 +549,7 @@
/* Thankfully, all cache ops are by VA so we can ignore phys here */
static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
{
- __dma_flush_range(virt, virt + PAGE_SIZE);
+ __dma_flush_area(virt, PAGE_SIZE);
}
static void *__iommu_alloc_attrs(struct device *dev, size_t size,
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index 81acd47..c9f118c 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -2,7 +2,7 @@
* Based on arch/arm/mm/extable.c
*/
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/uaccess.h>
int fixup_exception(struct pt_regs *regs)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 05d2bd7..53d9159 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -18,7 +18,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
@@ -251,8 +251,7 @@
good_area:
/*
* Check that the permissions on the VMA allow for the fault which
- * occurred. If we encountered a write or exec fault, we must have
- * appropriate permissions, otherwise we allow any permission.
+ * occurred.
*/
if (!(vma->vm_flags & vm_flags)) {
fault = VM_FAULT_BADACCESS;
@@ -288,7 +287,7 @@
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
+ unsigned long vm_flags = VM_READ | VM_WRITE;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (notify_page_fault(regs, esr))
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 43a76b0..8377329 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -25,8 +25,6 @@
#include <asm/cachetype.h>
#include <asm/tlbflush.h>
-#include "mm.h"
-
void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index bbb7ee7..21c489b 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -23,6 +23,7 @@
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/bootmem.h>
+#include <linux/cache.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>
@@ -34,6 +35,7 @@
#include <linux/dma-contiguous.h>
#include <linux/efi.h>
#include <linux/swiotlb.h>
+#include <linux/vmalloc.h>
#include <asm/boot.h>
#include <asm/fixmap.h>
@@ -47,16 +49,14 @@
#include <asm/tlb.h>
#include <asm/alternative.h>
-#include "mm.h"
-
/*
* We need to be able to catch inadvertent references to memstart_addr
* that occur (potentially in generic code) before arm64_memblock_init()
* executes, which assigns it its actual value. So use a default value
* that cannot be mistaken for a real physical address.
*/
-s64 memstart_addr __read_mostly = -1;
-phys_addr_t arm64_dma_phys_limit __read_mostly;
+s64 memstart_addr __ro_after_init = -1;
+phys_addr_t arm64_dma_phys_limit __ro_after_init;
#ifdef CONFIG_BLK_DEV_INITRD
static int __init early_initrd(char *p)
@@ -485,7 +485,12 @@
{
free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)),
0, "unused kernel");
- fixup_init();
+ /*
+ * Unmap the __init region but leave the VM area in place. This
+ * prevents the region from being reused for kernel modules, which
+ * is not supported by kallsyms.
+ */
+ unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
}
#ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h
deleted file mode 100644
index 71fe9898..0000000
--- a/arch/arm64/mm/mm.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-void fixup_init(void);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 4989948..05615a3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/cache.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/errno.h>
@@ -42,11 +43,9 @@
#include <asm/memblock.h>
#include <asm/mmu_context.h>
-#include "mm.h"
-
u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
-u64 kimage_voffset __read_mostly;
+u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
/*
@@ -399,16 +398,6 @@
section_size, PAGE_KERNEL_RO);
}
-void fixup_init(void)
-{
- /*
- * Unmap the __init region but leave the VM area in place. This
- * prevents the region from being reused for kernel modules, which
- * is not supported by kallsyms.
- */
- unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
-}
-
static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
pgprot_t prot, struct vm_struct *vma)
{
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 5bb15ea..778a985 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -17,6 +17,8 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#define pr_fmt(fmt) "NUMA: " fmt
+
#include <linux/acpi.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
@@ -24,6 +26,7 @@
#include <linux/of.h>
#include <asm/acpi.h>
+#include <asm/sections.h>
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
@@ -38,10 +41,9 @@
{
if (!opt)
return -EINVAL;
- if (!strncmp(opt, "off", 3)) {
- pr_info("%s\n", "NUMA turned off");
+ if (!strncmp(opt, "off", 3))
numa_off = true;
- }
+
return 0;
}
early_param("numa", numa_parse_early_param);
@@ -93,7 +95,6 @@
*/
static void __init setup_node_to_cpumask_map(void)
{
- unsigned int cpu;
int node;
/* setup nr_node_ids if not done yet */
@@ -106,11 +107,8 @@
cpumask_clear(node_to_cpumask_map[node]);
}
- for_each_possible_cpu(cpu)
- set_cpu_numa_node(cpu, NUMA_NO_NODE);
-
/* cpumask_of_node() will now work */
- pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids);
+ pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
}
/*
@@ -118,18 +116,77 @@
*/
void numa_store_cpu_info(unsigned int cpu)
{
- map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+ map_cpu_to_node(cpu, cpu_to_node_map[cpu]);
}
void __init early_map_cpu_to_node(unsigned int cpu, int nid)
{
/* fallback to node 0 */
- if (nid < 0 || nid >= MAX_NUMNODES)
+ if (nid < 0 || nid >= MAX_NUMNODES || numa_off)
nid = 0;
cpu_to_node_map[cpu] = nid;
+
+ /*
+ * We should set the numa node of cpu0 as soon as possible, because it
+ * has already been set up online before. cpu_to_node(0) will soon be
+ * called.
+ */
+ if (!cpu)
+ set_cpu_numa_node(cpu, nid);
}
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init early_cpu_to_node(int cpu)
+{
+ return cpu_to_node_map[cpu];
+}
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+ return node_distance(from, to);
+}
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
+ size_t align)
+{
+ int nid = early_cpu_to_node(cpu);
+
+ return memblock_virt_alloc_try_nid(size, align,
+ __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+ memblock_free_early(__pa(ptr), size);
+}
+
+void __init setup_per_cpu_areas(void)
+{
+ unsigned long delta;
+ unsigned int cpu;
+ int rc;
+
+ /*
+ * Always reserve area for module percpu variables. That's
+ * what the legacy allocator did.
+ */
+ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+ PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+ pcpu_cpu_distance,
+ pcpu_fc_alloc, pcpu_fc_free);
+ if (rc < 0)
+ panic("Failed to initialize percpu areas.");
+
+ delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+ for_each_possible_cpu(cpu)
+ __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+}
+#endif
+
/**
* numa_add_memblk - Set node id to memblk
* @nid: NUMA node ID of the new memblk
@@ -145,13 +202,13 @@
ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
if (ret < 0) {
- pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+ pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
start, (end - 1), nid);
return ret;
}
node_set(nid, numa_nodes_parsed);
- pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
+ pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n",
start, (end - 1), nid);
return ret;
}
@@ -166,19 +223,18 @@
void *nd;
int tnid;
- pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
- nid, start_pfn << PAGE_SHIFT,
- (end_pfn << PAGE_SHIFT) - 1);
+ pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+ nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
nd = __va(nd_pa);
/* report and initialize */
- pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n",
+ pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n",
nd_pa, nd_pa + nd_size - 1);
tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
if (tnid != nid)
- pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid);
+ pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
node_data[nid] = nd;
memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
@@ -235,8 +291,7 @@
numa_distance[i * numa_distance_cnt + j] = i == j ?
LOCAL_DISTANCE : REMOTE_DISTANCE;
- pr_debug("NUMA: Initialized distance table, cnt=%d\n",
- numa_distance_cnt);
+ pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt);
return 0;
}
@@ -257,20 +312,20 @@
void __init numa_set_distance(int from, int to, int distance)
{
if (!numa_distance) {
- pr_warn_once("NUMA: Warning: distance table not allocated yet\n");
+ pr_warn_once("Warning: distance table not allocated yet\n");
return;
}
if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
from < 0 || to < 0) {
- pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+ pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
if ((u8)distance != distance ||
(from == to && distance != LOCAL_DISTANCE)) {
- pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+ pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
@@ -297,7 +352,7 @@
/* Check that valid nid is set to memblks */
for_each_memblock(memory, mblk)
if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
- pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+ pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
mblk->nid, mblk->base,
mblk->base + mblk->size - 1);
return -EINVAL;
@@ -335,8 +390,10 @@
if (ret < 0)
return ret;
- if (nodes_empty(numa_nodes_parsed))
+ if (nodes_empty(numa_nodes_parsed)) {
+ pr_info("No NUMA configuration found\n");
return -EINVAL;
+ }
ret = numa_register_nodes();
if (ret < 0)
@@ -344,10 +401,6 @@
setup_node_to_cpumask_map();
- /* init boot processor */
- cpu_to_node_map[0] = 0;
- map_cpu_to_node(0, 0);
-
return 0;
}
@@ -367,10 +420,8 @@
if (numa_off)
pr_info("NUMA disabled\n"); /* Forced off on command line. */
- else
- pr_info("No NUMA configuration found\n");
- pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
- 0LLU, PFN_PHYS(max_pfn) - 1);
+ pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
+ 0LLU, PFN_PHYS(max_pfn) - 1);
for_each_memblock(memory, mblk) {
ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index ca6d268..8def55e 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -139,4 +139,43 @@
__pgprot(0),
__pgprot(PTE_VALID));
}
-#endif
+#ifdef CONFIG_HIBERNATION
+/*
+ * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
+ * is used to determine if a linear map page has been marked as not-valid by
+ * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
+ * This is based on kern_addr_valid(), which almost does what we need.
+ *
+ * Because this is only called on the kernel linear map, p?d_sect() implies
+ * p?d_present(). When debug_pagealloc is enabled, sections mappings are
+ * disabled.
+ */
+bool kernel_page_present(struct page *page)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+ unsigned long addr = (unsigned long)page_address(page);
+
+ pgd = pgd_offset_k(addr);
+ if (pgd_none(*pgd))
+ return false;
+
+ pud = pud_offset(pgd, addr);
+ if (pud_none(*pud))
+ return false;
+ if (pud_sect(*pud))
+ return true;
+
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return false;
+ if (pmd_sect(*pmd))
+ return true;
+
+ pte = pte_offset_kernel(pmd, addr);
+ return pte_valid(*pte);
+}
+#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index ae11d4e..371c5f0 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -26,8 +26,6 @@
#include <asm/page.h>
#include <asm/tlbflush.h>
-#include "mm.h"
-
static struct kmem_cache *pgd_cache;
pgd_t *pgd_alloc(struct mm_struct *mm)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 9d37e96..352c73b 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -83,6 +83,7 @@
*
* x0: Address of context pointer
*/
+ .pushsection ".idmap.text", "ax"
ENTRY(cpu_do_resume)
ldp x2, x3, [x0]
ldp x4, x5, [x0, #16]
@@ -120,6 +121,7 @@
isb
ret
ENDPROC(cpu_do_resume)
+ .popsection
#endif
/*
@@ -134,17 +136,12 @@
bfi x0, x1, #48, #16 // set the ASID
msr ttbr0_el1, x0 // set TTBR0
isb
-alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
- ret
- nop
- nop
- nop
-alternative_else
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
ic iallu
dsb nsh
isb
+alternative_else_nop_endif
ret
-alternative_endif
ENDPROC(cpu_do_switch_mm)
.pushsection ".idmap.text", "ax"
@@ -181,6 +178,7 @@
* Initialise the processor for turning the MMU on. Return in x0 the
* value of the SCTLR_EL1 register.
*/
+ .pushsection ".idmap.text", "ax"
ENTRY(__cpu_setup)
tlbi vmalle1 // Invalidate local TLB
dsb nsh
@@ -266,3 +264,4 @@
crval:
.word 0xfcffffff // clear
.word 0x34d5d91d // set
+ .popsection
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 5a9b87b..c1eb1ff 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1619,6 +1619,12 @@
return -ENOMEM;
}
+ /*
+ * Clear the OF_POPULATED flag that was set by of_irq_init()
+ * so that all GPIO devices will be probed.
+ */
+ of_node_clear_flag(gpio_node, OF_POPULATED);
+
return 0;
}
/*
diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S
index d7b9918..1910223 100644
--- a/arch/mips/dec/int-handler.S
+++ b/arch/mips/dec/int-handler.S
@@ -146,7 +146,25 @@
/*
* Find irq with highest priority
*/
- PTR_LA t1,cpu_mask_nr_tbl
+ # open coded PTR_LA t1, cpu_mask_nr_tbl
+#if (_MIPS_SZPTR == 32)
+ # open coded la t1, cpu_mask_nr_tbl
+ lui t1, %hi(cpu_mask_nr_tbl)
+ addiu t1, %lo(cpu_mask_nr_tbl)
+
+#endif
+#if (_MIPS_SZPTR == 64)
+ # open coded dla t1, cpu_mask_nr_tbl
+ .set push
+ .set noat
+ lui t1, %highest(cpu_mask_nr_tbl)
+ lui AT, %hi(cpu_mask_nr_tbl)
+ daddiu t1, t1, %higher(cpu_mask_nr_tbl)
+ daddiu AT, AT, %lo(cpu_mask_nr_tbl)
+ dsll t1, 32
+ daddu t1, t1, AT
+ .set pop
+#endif
1: lw t2,(t1)
nop
and t2,t0
@@ -195,7 +213,25 @@
/*
* Find irq with highest priority
*/
- PTR_LA t1,asic_mask_nr_tbl
+ # open coded PTR_LA t1,asic_mask_nr_tbl
+#if (_MIPS_SZPTR == 32)
+ # open coded la t1, asic_mask_nr_tbl
+ lui t1, %hi(asic_mask_nr_tbl)
+ addiu t1, %lo(asic_mask_nr_tbl)
+
+#endif
+#if (_MIPS_SZPTR == 64)
+ # open coded dla t1, asic_mask_nr_tbl
+ .set push
+ .set noat
+ lui t1, %highest(asic_mask_nr_tbl)
+ lui AT, %hi(asic_mask_nr_tbl)
+ daddiu t1, t1, %higher(asic_mask_nr_tbl)
+ daddiu AT, AT, %lo(asic_mask_nr_tbl)
+ dsll t1, 32
+ daddu t1, t1, AT
+ .set pop
+#endif
2: lw t2,(t1)
nop
and t2,t0
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index 58e7874..4fafeef 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -458,10 +458,21 @@
static inline unsigned int mips_cm_max_vp_width(void)
{
extern int smp_num_siblings;
+ uint32_t cfg;
if (mips_cm_revision() >= CM_REV_CM3)
return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK;
+ if (mips_cm_present()) {
+ /*
+ * We presume that all cores in the system will have the same
+ * number of VP(E)s, and if that ever changes then this will
+ * need revisiting.
+ */
+ cfg = read_gcr_cl_config() & CM_GCR_Cx_CONFIG_PVPE_MSK;
+ return (cfg >> CM_GCR_Cx_CONFIG_PVPE_SHF) + 1;
+ }
+
if (IS_ENABLED(CONFIG_SMP))
return smp_num_siblings;
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index def9d8d..7dd2dd4 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -660,8 +660,6 @@
#define MIPS_CONF7_IAR (_ULCAST_(1) << 10)
#define MIPS_CONF7_AR (_ULCAST_(1) << 16)
-/* FTLB probability bits for R6 */
-#define MIPS_CONF7_FTLBP_SHIFT (18)
/* WatchLo* register definitions */
#define MIPS_WATCHLO_IRW (_ULCAST_(0x7) << 0)
diff --git a/arch/mips/include/asm/uprobes.h b/arch/mips/include/asm/uprobes.h
index 34c325c..70a4a2f 100644
--- a/arch/mips/include/asm/uprobes.h
+++ b/arch/mips/include/asm/uprobes.h
@@ -36,7 +36,6 @@
unsigned long resume_epc;
u32 insn[2];
u32 ixol[2];
- union mips_instruction orig_inst[MAX_UINSN_BYTES / 4];
};
struct arch_uprobe_task {
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index a88d442..dd31754 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -352,7 +352,12 @@
static int mips_ftlb_disabled;
static int mips_has_ftlb_configured;
-static int set_ftlb_enable(struct cpuinfo_mips *c, int enable);
+enum ftlb_flags {
+ FTLB_EN = 1 << 0,
+ FTLB_SET_PROB = 1 << 1,
+};
+
+static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags);
static int __init ftlb_disable(char *s)
{
@@ -371,8 +376,6 @@
return 1;
}
- back_to_back_c0_hazard();
-
config4 = read_c0_config4();
/* Check that FTLB has been disabled */
@@ -531,7 +534,7 @@
return 3;
}
-static int set_ftlb_enable(struct cpuinfo_mips *c, int enable)
+static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags)
{
unsigned int config;
@@ -542,33 +545,33 @@
case CPU_P6600:
/* proAptiv & related cores use Config6 to enable the FTLB */
config = read_c0_config6();
- /* Clear the old probability value */
- config &= ~(3 << MIPS_CONF6_FTLBP_SHIFT);
- if (enable)
- /* Enable FTLB */
- write_c0_config6(config |
- (calculate_ftlb_probability(c)
- << MIPS_CONF6_FTLBP_SHIFT)
- | MIPS_CONF6_FTLBEN);
+
+ if (flags & FTLB_EN)
+ config |= MIPS_CONF6_FTLBEN;
else
- /* Disable FTLB */
- write_c0_config6(config & ~MIPS_CONF6_FTLBEN);
+ config &= ~MIPS_CONF6_FTLBEN;
+
+ if (flags & FTLB_SET_PROB) {
+ config &= ~(3 << MIPS_CONF6_FTLBP_SHIFT);
+ config |= calculate_ftlb_probability(c)
+ << MIPS_CONF6_FTLBP_SHIFT;
+ }
+
+ write_c0_config6(config);
+ back_to_back_c0_hazard();
break;
case CPU_I6400:
- /* I6400 & related cores use Config7 to configure FTLB */
- config = read_c0_config7();
- /* Clear the old probability value */
- config &= ~(3 << MIPS_CONF7_FTLBP_SHIFT);
- write_c0_config7(config | (calculate_ftlb_probability(c)
- << MIPS_CONF7_FTLBP_SHIFT));
- break;
+ /* There's no way to disable the FTLB */
+ if (!(flags & FTLB_EN))
+ return 1;
+ return 0;
case CPU_LOONGSON3:
/* Flush ITLB, DTLB, VTLB and FTLB */
write_c0_diag(LOONGSON_DIAG_ITLB | LOONGSON_DIAG_DTLB |
LOONGSON_DIAG_VTLB | LOONGSON_DIAG_FTLB);
/* Loongson-3 cores use Config6 to enable the FTLB */
config = read_c0_config6();
- if (enable)
+ if (flags & FTLB_EN)
/* Enable FTLB */
write_c0_config6(config & ~MIPS_CONF6_FTLBDIS);
else
@@ -788,6 +791,7 @@
PAGE_SIZE, config4);
/* Switch FTLB off */
set_ftlb_enable(c, 0);
+ mips_ftlb_disabled = 1;
break;
}
c->tlbsizeftlbsets = 1 <<
@@ -852,7 +856,7 @@
c->scache.flags = MIPS_CACHE_NOT_PRESENT;
/* Enable FTLB if present and not disabled */
- set_ftlb_enable(c, !mips_ftlb_disabled);
+ set_ftlb_enable(c, mips_ftlb_disabled ? 0 : FTLB_EN);
ok = decode_config0(c); /* Read Config registers. */
BUG_ON(!ok); /* Arch spec violation! */
@@ -902,6 +906,9 @@
}
}
+ /* configure the FTLB write probability */
+ set_ftlb_enable(c, (mips_ftlb_disabled ? 0 : FTLB_EN) | FTLB_SET_PROB);
+
mips_probe_watch_registers(c);
#ifndef CONFIG_MIPS_CPS
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 17326a9..dc0b296 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -142,9 +142,8 @@
PTR_LA k1, __r4k_wait
ori k0, 0x1f /* 32 byte rollback region */
xori k0, 0x1f
- bne k0, k1, 9f
+ bne k0, k1, \handler
MTC0 k0, CP0_EPC
-9:
.set pop
.endm
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 3be0e6b..0d57909 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -764,7 +764,6 @@
device_tree_init();
sparse_init();
plat_swiotlb_setup();
- paging_init();
dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
/* Tell bootmem about cma reserved memblock section */
@@ -877,6 +876,7 @@
prefill_possible_map();
cpu_cache_init();
+ paging_init();
}
unsigned long kernelsp[NR_CPUS];
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index e9d9fc6..6183ad8 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -513,7 +513,7 @@
* in which case the CPC will refuse to power down the core.
*/
do {
- mips_cm_lock_other(core, vpe_id);
+ mips_cm_lock_other(core, 0);
mips_cpc_lock_other(core);
stat = read_cpc_co_stat_conf();
stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK;
diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c
index 1149b30..4c7c155 100644
--- a/arch/mips/kernel/uprobes.c
+++ b/arch/mips/kernel/uprobes.c
@@ -157,7 +157,6 @@
int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs)
{
struct uprobe_task *utask = current->utask;
- union mips_instruction insn;
/*
* Now find the EPC where to resume after the breakpoint has been
@@ -168,10 +167,10 @@
unsigned long epc;
epc = regs->cp0_epc;
- __compute_return_epc_for_insn(regs, insn);
+ __compute_return_epc_for_insn(regs,
+ (union mips_instruction) aup->insn[0]);
aup->resume_epc = regs->cp0_epc;
}
-
utask->autask.saved_trap_nr = current->thread.trap_nr;
current->thread.trap_nr = UPROBE_TRAP_NR;
regs->cp0_epc = current->utask->xol_vaddr;
@@ -257,7 +256,7 @@
ra = regs->regs[31];
/* Replace the return address with the trampoline address */
- regs->regs[31] = ra;
+ regs->regs[31] = trampoline_vaddr;
return ra;
}
@@ -280,24 +279,6 @@
return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
}
-/**
- * set_orig_insn - Restore the original instruction.
- * @mm: the probed process address space.
- * @auprobe: arch specific probepoint information.
- * @vaddr: the virtual address to insert the opcode.
- *
- * For mm @mm, restore the original opcode (opcode) at @vaddr.
- * Return 0 (success) or a negative errno.
- *
- * This overrides the weak version in kernel/events/uprobes.c.
- */
-int set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
- unsigned long vaddr)
-{
- return uprobe_write_opcode(mm, vaddr,
- *(uprobe_opcode_t *)&auprobe->orig_inst[0].word);
-}
-
void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
void *src, unsigned long len)
{
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 2c3749d..72f7478 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -440,6 +440,9 @@
#ifdef CONFIG_HIGHMEM
unsigned long tmp;
+ if (cpu_has_dc_aliases)
+ return;
+
for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) {
struct page *page = pfn_to_page(tmp);
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index ec5b216..7e7364b 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -39,6 +39,9 @@
#include <linux/console.h>
#endif
+#define ROCIT_CONFIG_GEN0 0x1f403000
+#define ROCIT_CONFIG_GEN0_PCI_IOCU BIT(7)
+
extern void malta_be_init(void);
extern int malta_be_handler(struct pt_regs *regs, int is_fixup);
@@ -107,6 +110,8 @@
static int __init plat_enable_iocoherency(void)
{
int supported = 0;
+ u32 cfg;
+
if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO) {
if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
@@ -129,7 +134,8 @@
} else if (mips_cm_numiocu() != 0) {
/* Nothing special needs to be done to enable coherency */
pr_info("CMP IOCU detected\n");
- if ((*(unsigned int *)0xbf403000 & 0x81) != 0x81) {
+ cfg = __raw_readl((u32 *)CKSEG1ADDR(ROCIT_CONFIG_GEN0));
+ if (!(cfg & ROCIT_CONFIG_GEN0_PCI_IOCU)) {
pr_crit("IOCU OPERATION DISABLED BY SWITCH - DEFAULTING TO SW IO COHERENCY\n");
return 0;
}
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index 8c2a8c9..c1263fc 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -25,6 +25,7 @@
#define HPAGE_MASK (~(HPAGE_SIZE - 1UL))
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index 26d9e77..ce2233f 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -43,6 +43,7 @@
int hard_smp_processor_id(void);
#define raw_smp_processor_id() (current_thread_info()->cpu)
+void smp_fill_in_cpu_possible_map(void);
void smp_fill_in_sib_core_maps(void);
void cpu_play_dead(void);
@@ -72,6 +73,7 @@
#define smp_fill_in_sib_core_maps() do { } while (0)
#define smp_fetch_global_regs() do { } while (0)
#define smp_fetch_global_pmu() do { } while (0)
+#define smp_fill_in_cpu_possible_map() do { } while (0)
#endif /* !(CONFIG_SMP) */
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 599f120..6b7331d 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -31,6 +31,7 @@
#include <linux/initrd.h>
#include <linux/module.h>
#include <linux/start_kernel.h>
+#include <linux/bootmem.h>
#include <asm/io.h>
#include <asm/processor.h>
@@ -50,6 +51,8 @@
#include <asm/elf.h>
#include <asm/mdesc.h>
#include <asm/cacheflush.h>
+#include <asm/dma.h>
+#include <asm/irq.h>
#ifdef CONFIG_IP_PNP
#include <net/ipconfig.h>
@@ -590,6 +593,22 @@
pause_patch();
}
+void __init alloc_irqstack_bootmem(void)
+{
+ unsigned int i, node;
+
+ for_each_possible_cpu(i) {
+ node = cpu_to_node(i);
+
+ softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
+ THREAD_SIZE,
+ THREAD_SIZE, 0);
+ hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
+ THREAD_SIZE,
+ THREAD_SIZE, 0);
+ }
+}
+
void __init setup_arch(char **cmdline_p)
{
/* Initialize PROM console and command line. */
@@ -650,6 +669,13 @@
paging_init();
init_sparc64_elf_hwcap();
+ smp_fill_in_cpu_possible_map();
+ /*
+ * Once the OF device tree and MDESC have been setup and nr_cpus has
+ * been parsed, we know the list of possible cpus. Therefore we can
+ * allocate the IRQ stacks.
+ */
+ alloc_irqstack_bootmem();
}
extern int stop_a_enabled;
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 8a6151a..d3035ba 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1227,6 +1227,20 @@
xcall_deliver_impl = hypervisor_xcall_deliver;
}
+void __init smp_fill_in_cpu_possible_map(void)
+{
+ int possible_cpus = num_possible_cpus();
+ int i;
+
+ if (possible_cpus > nr_cpu_ids)
+ possible_cpus = nr_cpu_ids;
+
+ for (i = 0; i < possible_cpus; i++)
+ set_cpu_possible(i, true);
+ for (; i < NR_CPUS; i++)
+ set_cpu_possible(i, false);
+}
+
void smp_fill_in_sib_core_maps(void)
{
unsigned int i;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index e16fdd2..3f291d8 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -484,6 +484,7 @@
tsb_grow(mm, MM_TSB_BASE, mm_rss);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
+ mm_rss *= REAL_HPAGE_PER_HPAGE;
if (unlikely(mm_rss >
mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) {
if (mm->context.tsb_block[MM_TSB_HUGE].tsb)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 65457c9..7ac6b62 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1160,7 +1160,7 @@
return numa_latency[from][to];
}
-static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
+static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
{
int i;
@@ -1173,8 +1173,8 @@
return i;
}
-static void find_numa_latencies_for_group(struct mdesc_handle *md, u64 grp,
- int index)
+static void __init find_numa_latencies_for_group(struct mdesc_handle *md,
+ u64 grp, int index)
{
u64 arc;
@@ -2081,7 +2081,6 @@
{
unsigned long end_pfn, shift, phys_base;
unsigned long real_end, i;
- int node;
setup_page_offset();
@@ -2250,21 +2249,6 @@
/* Setup bootmem... */
last_valid_pfn = end_pfn = bootmem_init(phys_base);
- /* Once the OF device tree and MDESC have been setup, we know
- * the list of possible cpus. Therefore we can allocate the
- * IRQ stacks.
- */
- for_each_possible_cpu(i) {
- node = cpu_to_node(i);
-
- softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
- THREAD_SIZE,
- THREAD_SIZE, 0);
- hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node),
- THREAD_SIZE,
- THREAD_SIZE, 0);
- }
-
kernel_physical_mapping_init();
{
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 3659d37..c56a195 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -174,10 +174,25 @@
return;
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
- if (pmd_val(pmd) & _PAGE_PMD_HUGE)
- mm->context.thp_pte_count++;
- else
- mm->context.thp_pte_count--;
+ /*
+ * Note that this routine only sets pmds for THP pages.
+ * Hugetlb pages are handled elsewhere. We need to check
+ * for huge zero page. Huge zero pages are like hugetlb
+ * pages in that there is no RSS, but there is the need
+ * for TSB entries. So, huge zero page counts go into
+ * hugetlb_pte_count.
+ */
+ if (pmd_val(pmd) & _PAGE_PMD_HUGE) {
+ if (is_huge_zero_page(pmd_page(pmd)))
+ mm->context.hugetlb_pte_count++;
+ else
+ mm->context.thp_pte_count++;
+ } else {
+ if (is_huge_zero_page(pmd_page(orig)))
+ mm->context.hugetlb_pte_count--;
+ else
+ mm->context.thp_pte_count--;
+ }
/* Do not try to allocate the TSB hash table if we
* don't have one already. We have various locks held
@@ -204,6 +219,9 @@
}
}
+/*
+ * This routine is only called when splitting a THP
+ */
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
@@ -213,6 +231,15 @@
set_pmd_at(vma->vm_mm, address, pmdp, entry);
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+ /*
+ * set_pmd_at() will not be called in a way to decrement
+ * thp_pte_count when splitting a THP, so do it now.
+ * Sanity check pmd before doing the actual decrement.
+ */
+ if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
+ !is_huge_zero_page(pmd_page(entry)))
+ (vma->vm_mm)->context.thp_pte_count--;
}
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 6725ed4..f2b7711 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -469,8 +469,10 @@
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
+ unsigned long mm_rss = get_mm_rss(mm);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- unsigned long total_huge_pte_count;
+ unsigned long saved_hugetlb_pte_count;
+ unsigned long saved_thp_pte_count;
#endif
unsigned int i;
@@ -483,10 +485,12 @@
* will re-increment the counters as the parent PTEs are
* copied into the child address space.
*/
- total_huge_pte_count = mm->context.hugetlb_pte_count +
- mm->context.thp_pte_count;
+ saved_hugetlb_pte_count = mm->context.hugetlb_pte_count;
+ saved_thp_pte_count = mm->context.thp_pte_count;
mm->context.hugetlb_pte_count = 0;
mm->context.thp_pte_count = 0;
+
+ mm_rss -= saved_thp_pte_count * (HPAGE_SIZE / PAGE_SIZE);
#endif
/* copy_mm() copies over the parent's mm_struct before calling
@@ -499,11 +503,13 @@
/* If this is fork, inherit the parent's TSB size. We would
* grow it to that size on the first page fault anyways.
*/
- tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
+ tsb_grow(mm, MM_TSB_BASE, mm_rss);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (unlikely(total_huge_pte_count))
- tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
+ if (unlikely(saved_hugetlb_pte_count + saved_thp_pte_count))
+ tsb_grow(mm, MM_TSB_HUGE,
+ (saved_hugetlb_pte_count + saved_thp_pte_count) *
+ REAL_HPAGE_PER_HPAGE);
#endif
if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d172c61..02fff3e 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1002,7 +1002,6 @@
testb $3, CS+8(%rsp)
jz .Lerror_kernelspace
-.Lerror_entry_from_usermode_swapgs:
/*
* We entered from user mode or we're pretending to have entered
* from user mode due to an IRET fault.
@@ -1045,7 +1044,8 @@
* gsbase and proceed. We'll fix up the exception and land in
* .Lgs_change's error handler with kernel gsbase.
*/
- jmp .Lerror_entry_from_usermode_swapgs
+ SWAPGS
+ jmp .Lerror_entry_done
.Lbstep_iret:
/* Fix truncated RIP */
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 4f74119..3dab75f 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -22,7 +22,7 @@
ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
- if (hdr->e_type != ET_DYN)
+ if (GET_LE(&hdr->e_type) != ET_DYN)
fail("input is not a shared object\n");
/* Walk the segment table. */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6fa8594..dee8a70 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -81,7 +81,7 @@
/* Initialize cr4 shadow for this CPU. */
static inline void cr4_init_shadow(void)
{
- this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
+ this_cpu_write(cpu_tlbstate.cr4, __read_cr4_safe());
}
/* Set in this cpu's CR4. */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 809eda0..bcc9ccc 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -804,21 +804,20 @@
identify_cpu_without_cpuid(c);
/* cyrix could have cpuid enabled via c_identify()*/
- if (!have_cpuid_p())
- return;
+ if (have_cpuid_p()) {
+ cpu_detect(c);
+ get_cpu_vendor(c);
+ get_cpu_cap(c);
- cpu_detect(c);
- get_cpu_vendor(c);
- get_cpu_cap(c);
+ if (this_cpu->c_early_init)
+ this_cpu->c_early_init(c);
- if (this_cpu->c_early_init)
- this_cpu->c_early_init(c);
+ c->cpu_index = 0;
+ filter_cpuid_features(c, false);
- c->cpu_index = 0;
- filter_cpuid_features(c, false);
-
- if (this_cpu->c_bsp_init)
- this_cpu->c_bsp_init(c);
+ if (this_cpu->c_bsp_init)
+ this_cpu->c_bsp_init(c);
+ }
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
fpu__init_system(c);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0fa60f5..98c9cd6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1137,9 +1137,7 @@
* auditing all the early-boot CR4 manipulation would be needed to
* rule it out.
*/
- if (boot_cpu_data.cpuid_level >= 0)
- /* A CPU has %cr4 if and only if it has CPUID. */
- mmu_cr4_features = __read_cr4();
+ mmu_cr4_features = __read_cr4_safe();
memblock_set_current_limit(get_max_mapped());
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 80cc7c0..e1d5ea6 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -94,54 +94,50 @@
return to_acpi_device(acpi_desc->dev);
}
-static int xlat_status(void *buf, unsigned int cmd)
+static int xlat_status(void *buf, unsigned int cmd, u32 status)
{
struct nd_cmd_clear_error *clear_err;
struct nd_cmd_ars_status *ars_status;
- struct nd_cmd_ars_start *ars_start;
- struct nd_cmd_ars_cap *ars_cap;
u16 flags;
switch (cmd) {
case ND_CMD_ARS_CAP:
- ars_cap = buf;
- if ((ars_cap->status & 0xffff) == NFIT_ARS_CAP_NONE)
+ if ((status & 0xffff) == NFIT_ARS_CAP_NONE)
return -ENOTTY;
/* Command failed */
- if (ars_cap->status & 0xffff)
+ if (status & 0xffff)
return -EIO;
/* No supported scan types for this range */
flags = ND_ARS_PERSISTENT | ND_ARS_VOLATILE;
- if ((ars_cap->status >> 16 & flags) == 0)
+ if ((status >> 16 & flags) == 0)
return -ENOTTY;
break;
case ND_CMD_ARS_START:
- ars_start = buf;
/* ARS is in progress */
- if ((ars_start->status & 0xffff) == NFIT_ARS_START_BUSY)
+ if ((status & 0xffff) == NFIT_ARS_START_BUSY)
return -EBUSY;
/* Command failed */
- if (ars_start->status & 0xffff)
+ if (status & 0xffff)
return -EIO;
break;
case ND_CMD_ARS_STATUS:
ars_status = buf;
/* Command failed */
- if (ars_status->status & 0xffff)
+ if (status & 0xffff)
return -EIO;
/* Check extended status (Upper two bytes) */
- if (ars_status->status == NFIT_ARS_STATUS_DONE)
+ if (status == NFIT_ARS_STATUS_DONE)
return 0;
/* ARS is in progress */
- if (ars_status->status == NFIT_ARS_STATUS_BUSY)
+ if (status == NFIT_ARS_STATUS_BUSY)
return -EBUSY;
/* No ARS performed for the current boot */
- if (ars_status->status == NFIT_ARS_STATUS_NONE)
+ if (status == NFIT_ARS_STATUS_NONE)
return -EAGAIN;
/*
@@ -149,19 +145,19 @@
* agent wants the scan to stop. If we didn't overflow
* then just continue with the returned results.
*/
- if (ars_status->status == NFIT_ARS_STATUS_INTR) {
+ if (status == NFIT_ARS_STATUS_INTR) {
if (ars_status->flags & NFIT_ARS_F_OVERFLOW)
return -ENOSPC;
return 0;
}
/* Unknown status */
- if (ars_status->status >> 16)
+ if (status >> 16)
return -EIO;
break;
case ND_CMD_CLEAR_ERROR:
clear_err = buf;
- if (clear_err->status & 0xffff)
+ if (status & 0xffff)
return -EIO;
if (!clear_err->cleared)
return -EIO;
@@ -172,6 +168,9 @@
break;
}
+ /* all other non-zero status results in an error */
+ if (status)
+ return -EIO;
return 0;
}
@@ -186,10 +185,10 @@
struct nd_cmd_pkg *call_pkg = NULL;
const char *cmd_name, *dimm_name;
unsigned long cmd_mask, dsm_mask;
+ u32 offset, fw_status = 0;
acpi_handle handle;
unsigned int func;
const u8 *uuid;
- u32 offset;
int rc, i;
func = cmd;
@@ -317,6 +316,15 @@
out_obj->buffer.pointer + offset, out_size);
offset += out_size;
}
+
+ /*
+ * Set fw_status for all the commands with a known format to be
+ * later interpreted by xlat_status().
+ */
+ if (i >= 1 && ((cmd >= ND_CMD_ARS_CAP && cmd <= ND_CMD_CLEAR_ERROR)
+ || (cmd >= ND_CMD_SMART && cmd <= ND_CMD_VENDOR)))
+ fw_status = *(u32 *) out_obj->buffer.pointer;
+
if (offset + in_buf.buffer.length < buf_len) {
if (i >= 1) {
/*
@@ -325,7 +333,7 @@
*/
rc = buf_len - offset - in_buf.buffer.length;
if (cmd_rc)
- *cmd_rc = xlat_status(buf, cmd);
+ *cmd_rc = xlat_status(buf, cmd, fw_status);
} else {
dev_err(dev, "%s:%s underrun cmd: %s buf_len: %d out_len: %d\n",
__func__, dimm_name, cmd_name, buf_len,
@@ -335,7 +343,7 @@
} else {
rc = 0;
if (cmd_rc)
- *cmd_rc = xlat_status(buf, cmd);
+ *cmd_rc = xlat_status(buf, cmd, fw_status);
}
out:
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index a1f2aff..e023066 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -45,7 +45,7 @@
* and checks that the PM domain pointer is a real generic PM domain.
* Any failure results in NULL being returned.
*/
-struct generic_pm_domain *pm_genpd_lookup_dev(struct device *dev)
+static struct generic_pm_domain *genpd_lookup_dev(struct device *dev)
{
struct generic_pm_domain *genpd = NULL, *gpd;
@@ -586,7 +586,7 @@
}
late_initcall(genpd_poweroff_unused);
-#ifdef CONFIG_PM_SLEEP
+#if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_GENERIC_DOMAINS_OF)
/**
* pm_genpd_present - Check if the given PM domain has been initialized.
@@ -606,6 +606,10 @@
return false;
}
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+
static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
struct device *dev)
{
@@ -613,9 +617,8 @@
}
/**
- * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
+ * genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
* @genpd: PM domain to power off, if possible.
- * @timed: True if latency measurements are allowed.
*
* Check if the given PM domain can be powered off (during system suspend or
* hibernation) and do that if so. Also, in that case propagate to its masters.
@@ -625,8 +628,7 @@
* executed sequentially, so it is guaranteed that it will never run twice in
* parallel).
*/
-static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd,
- bool timed)
+static void genpd_sync_poweroff(struct generic_pm_domain *genpd)
{
struct gpd_link *link;
@@ -639,28 +641,26 @@
/* Choose the deepest state when suspending */
genpd->state_idx = genpd->state_count - 1;
- genpd_power_off(genpd, timed);
+ genpd_power_off(genpd, false);
genpd->status = GPD_STATE_POWER_OFF;
list_for_each_entry(link, &genpd->slave_links, slave_node) {
genpd_sd_counter_dec(link->master);
- pm_genpd_sync_poweroff(link->master, timed);
+ genpd_sync_poweroff(link->master);
}
}
/**
- * pm_genpd_sync_poweron - Synchronously power on a PM domain and its masters.
+ * genpd_sync_poweron - Synchronously power on a PM domain and its masters.
* @genpd: PM domain to power on.
- * @timed: True if latency measurements are allowed.
*
* This function is only called in "noirq" and "syscore" stages of system power
* transitions, so it need not acquire locks (all of the "noirq" callbacks are
* executed sequentially, so it is guaranteed that it will never run twice in
* parallel).
*/
-static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd,
- bool timed)
+static void genpd_sync_poweron(struct generic_pm_domain *genpd)
{
struct gpd_link *link;
@@ -668,11 +668,11 @@
return;
list_for_each_entry(link, &genpd->slave_links, slave_node) {
- pm_genpd_sync_poweron(link->master, timed);
+ genpd_sync_poweron(link->master);
genpd_sd_counter_inc(link->master);
}
- genpd_power_on(genpd, timed);
+ genpd_power_on(genpd, false);
genpd->status = GPD_STATE_ACTIVE;
}
@@ -784,7 +784,7 @@
* the same PM domain, so it is not necessary to use locking here.
*/
genpd->suspended_count++;
- pm_genpd_sync_poweroff(genpd, true);
+ genpd_sync_poweroff(genpd);
return 0;
}
@@ -814,7 +814,7 @@
* guaranteed that this function will never run twice in parallel for
* the same PM domain, so it is not necessary to use locking here.
*/
- pm_genpd_sync_poweron(genpd, true);
+ genpd_sync_poweron(genpd);
genpd->suspended_count--;
if (genpd->dev_ops.stop && genpd->dev_ops.start)
@@ -902,12 +902,12 @@
if (genpd->suspended_count++ == 0)
/*
* The boot kernel might put the domain into arbitrary state,
- * so make it appear as powered off to pm_genpd_sync_poweron(),
+ * so make it appear as powered off to genpd_sync_poweron(),
* so that it tries to power it on in case it was really off.
*/
genpd->status = GPD_STATE_POWER_OFF;
- pm_genpd_sync_poweron(genpd, true);
+ genpd_sync_poweron(genpd);
if (genpd->dev_ops.stop && genpd->dev_ops.start)
ret = pm_runtime_force_resume(dev);
@@ -962,9 +962,9 @@
if (suspend) {
genpd->suspended_count++;
- pm_genpd_sync_poweroff(genpd, false);
+ genpd_sync_poweroff(genpd);
} else {
- pm_genpd_sync_poweron(genpd, false);
+ genpd_sync_poweron(genpd);
genpd->suspended_count--;
}
}
@@ -1056,14 +1056,8 @@
dev_pm_put_subsys_data(dev);
}
-/**
- * __pm_genpd_add_device - Add a device to an I/O PM domain.
- * @genpd: PM domain to add the device to.
- * @dev: Device to be added.
- * @td: Set of PM QoS timing parameters to attach to the device.
- */
-int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
- struct gpd_timing_data *td)
+static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
+ struct gpd_timing_data *td)
{
struct generic_pm_domain_data *gpd_data;
int ret = 0;
@@ -1103,15 +1097,28 @@
return ret;
}
-EXPORT_SYMBOL_GPL(__pm_genpd_add_device);
/**
- * pm_genpd_remove_device - Remove a device from an I/O PM domain.
- * @genpd: PM domain to remove the device from.
- * @dev: Device to be removed.
+ * __pm_genpd_add_device - Add a device to an I/O PM domain.
+ * @genpd: PM domain to add the device to.
+ * @dev: Device to be added.
+ * @td: Set of PM QoS timing parameters to attach to the device.
*/
-int pm_genpd_remove_device(struct generic_pm_domain *genpd,
- struct device *dev)
+int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
+ struct gpd_timing_data *td)
+{
+ int ret;
+
+ mutex_lock(&gpd_list_lock);
+ ret = genpd_add_device(genpd, dev, td);
+ mutex_unlock(&gpd_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__pm_genpd_add_device);
+
+static int genpd_remove_device(struct generic_pm_domain *genpd,
+ struct device *dev)
{
struct generic_pm_domain_data *gpd_data;
struct pm_domain_data *pdd;
@@ -1119,10 +1126,6 @@
dev_dbg(dev, "%s()\n", __func__);
- if (!genpd || genpd != pm_genpd_lookup_dev(dev))
- return -EINVAL;
-
- /* The above validation also means we have existing domain_data. */
pdd = dev->power.subsys_data->domain_data;
gpd_data = to_gpd_data(pdd);
dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
@@ -1154,15 +1157,24 @@
return ret;
}
-EXPORT_SYMBOL_GPL(pm_genpd_remove_device);
/**
- * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
- * @genpd: Master PM domain to add the subdomain to.
- * @subdomain: Subdomain to be added.
+ * pm_genpd_remove_device - Remove a device from an I/O PM domain.
+ * @genpd: PM domain to remove the device from.
+ * @dev: Device to be removed.
*/
-int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
- struct generic_pm_domain *subdomain)
+int pm_genpd_remove_device(struct generic_pm_domain *genpd,
+ struct device *dev)
+{
+ if (!genpd || genpd != genpd_lookup_dev(dev))
+ return -EINVAL;
+
+ return genpd_remove_device(genpd, dev);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_remove_device);
+
+static int genpd_add_subdomain(struct generic_pm_domain *genpd,
+ struct generic_pm_domain *subdomain)
{
struct gpd_link *link, *itr;
int ret = 0;
@@ -1205,6 +1217,23 @@
kfree(link);
return ret;
}
+
+/**
+ * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
+ * @genpd: Master PM domain to add the subdomain to.
+ * @subdomain: Subdomain to be added.
+ */
+int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
+ struct generic_pm_domain *subdomain)
+{
+ int ret;
+
+ mutex_lock(&gpd_list_lock);
+ ret = genpd_add_subdomain(genpd, subdomain);
+ mutex_unlock(&gpd_list_lock);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(pm_genpd_add_subdomain);
/**
@@ -1278,27 +1307,17 @@
genpd->device_count = 0;
genpd->max_off_time_ns = -1;
genpd->max_off_time_changed = true;
+ genpd->provider = NULL;
+ genpd->has_provider = false;
genpd->domain.ops.runtime_suspend = genpd_runtime_suspend;
genpd->domain.ops.runtime_resume = genpd_runtime_resume;
genpd->domain.ops.prepare = pm_genpd_prepare;
- genpd->domain.ops.suspend = pm_generic_suspend;
- genpd->domain.ops.suspend_late = pm_generic_suspend_late;
genpd->domain.ops.suspend_noirq = pm_genpd_suspend_noirq;
genpd->domain.ops.resume_noirq = pm_genpd_resume_noirq;
- genpd->domain.ops.resume_early = pm_generic_resume_early;
- genpd->domain.ops.resume = pm_generic_resume;
- genpd->domain.ops.freeze = pm_generic_freeze;
- genpd->domain.ops.freeze_late = pm_generic_freeze_late;
genpd->domain.ops.freeze_noirq = pm_genpd_freeze_noirq;
genpd->domain.ops.thaw_noirq = pm_genpd_thaw_noirq;
- genpd->domain.ops.thaw_early = pm_generic_thaw_early;
- genpd->domain.ops.thaw = pm_generic_thaw;
- genpd->domain.ops.poweroff = pm_generic_poweroff;
- genpd->domain.ops.poweroff_late = pm_generic_poweroff_late;
genpd->domain.ops.poweroff_noirq = pm_genpd_suspend_noirq;
genpd->domain.ops.restore_noirq = pm_genpd_restore_noirq;
- genpd->domain.ops.restore_early = pm_generic_restore_early;
- genpd->domain.ops.restore = pm_generic_restore;
genpd->domain.ops.complete = pm_genpd_complete;
if (genpd->flags & GENPD_FLAG_PM_CLK) {
@@ -1328,7 +1347,71 @@
}
EXPORT_SYMBOL_GPL(pm_genpd_init);
+static int genpd_remove(struct generic_pm_domain *genpd)
+{
+ struct gpd_link *l, *link;
+
+ if (IS_ERR_OR_NULL(genpd))
+ return -EINVAL;
+
+ mutex_lock(&genpd->lock);
+
+ if (genpd->has_provider) {
+ mutex_unlock(&genpd->lock);
+ pr_err("Provider present, unable to remove %s\n", genpd->name);
+ return -EBUSY;
+ }
+
+ if (!list_empty(&genpd->master_links) || genpd->device_count) {
+ mutex_unlock(&genpd->lock);
+ pr_err("%s: unable to remove %s\n", __func__, genpd->name);
+ return -EBUSY;
+ }
+
+ list_for_each_entry_safe(link, l, &genpd->slave_links, slave_node) {
+ list_del(&link->master_node);
+ list_del(&link->slave_node);
+ kfree(link);
+ }
+
+ list_del(&genpd->gpd_list_node);
+ mutex_unlock(&genpd->lock);
+ cancel_work_sync(&genpd->power_off_work);
+ pr_debug("%s: removed %s\n", __func__, genpd->name);
+
+ return 0;
+}
+
+/**
+ * pm_genpd_remove - Remove a generic I/O PM domain
+ * @genpd: Pointer to PM domain that is to be removed.
+ *
+ * To remove the PM domain, this function:
+ * - Removes the PM domain as a subdomain to any parent domains,
+ * if it was added.
+ * - Removes the PM domain from the list of registered PM domains.
+ *
+ * The PM domain will only be removed, if the associated provider has
+ * been removed, it is not a parent to any other PM domain and has no
+ * devices associated with it.
+ */
+int pm_genpd_remove(struct generic_pm_domain *genpd)
+{
+ int ret;
+
+ mutex_lock(&gpd_list_lock);
+ ret = genpd_remove(genpd);
+ mutex_unlock(&gpd_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pm_genpd_remove);
+
#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+
+typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
+ void *data);
+
/*
* Device Tree based PM domain providers.
*
@@ -1340,8 +1423,8 @@
* maps a PM domain specifier retrieved from the device tree to a PM domain.
*
* Two simple mapping functions have been provided for convenience:
- * - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
- * - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by
+ * - genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
+ * - genpd_xlate_onecell() for mapping of multiple PM domains per node by
* index.
*/
@@ -1366,7 +1449,7 @@
static DEFINE_MUTEX(of_genpd_mutex);
/**
- * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping
+ * genpd_xlate_simple() - Xlate function for direct node-domain mapping
* @genpdspec: OF phandle args to map into a PM domain
* @data: xlate function private data - pointer to struct generic_pm_domain
*
@@ -1374,7 +1457,7 @@
* have their own device tree nodes. The private data of xlate function needs
* to be a valid pointer to struct generic_pm_domain.
*/
-struct generic_pm_domain *__of_genpd_xlate_simple(
+static struct generic_pm_domain *genpd_xlate_simple(
struct of_phandle_args *genpdspec,
void *data)
{
@@ -1382,10 +1465,9 @@
return ERR_PTR(-EINVAL);
return data;
}
-EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple);
/**
- * __of_genpd_xlate_onecell() - Xlate function using a single index.
+ * genpd_xlate_onecell() - Xlate function using a single index.
* @genpdspec: OF phandle args to map into a PM domain
* @data: xlate function private data - pointer to struct genpd_onecell_data
*
@@ -1394,7 +1476,7 @@
* A single cell is used as an index into an array of PM domains specified in
* the genpd_onecell_data struct when registering the provider.
*/
-struct generic_pm_domain *__of_genpd_xlate_onecell(
+static struct generic_pm_domain *genpd_xlate_onecell(
struct of_phandle_args *genpdspec,
void *data)
{
@@ -1414,16 +1496,15 @@
return genpd_data->domains[idx];
}
-EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell);
/**
- * __of_genpd_add_provider() - Register a PM domain provider for a node
+ * genpd_add_provider() - Register a PM domain provider for a node
* @np: Device node pointer associated with the PM domain provider.
* @xlate: Callback for decoding PM domain from phandle arguments.
* @data: Context pointer for @xlate callback.
*/
-int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
- void *data)
+static int genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+ void *data)
{
struct of_genpd_provider *cp;
@@ -1442,7 +1523,83 @@
return 0;
}
-EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
+
+/**
+ * of_genpd_add_provider_simple() - Register a simple PM domain provider
+ * @np: Device node pointer associated with the PM domain provider.
+ * @genpd: Pointer to PM domain associated with the PM domain provider.
+ */
+int of_genpd_add_provider_simple(struct device_node *np,
+ struct generic_pm_domain *genpd)
+{
+ int ret = -EINVAL;
+
+ if (!np || !genpd)
+ return -EINVAL;
+
+ mutex_lock(&gpd_list_lock);
+
+ if (pm_genpd_present(genpd))
+ ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
+
+ if (!ret) {
+ genpd->provider = &np->fwnode;
+ genpd->has_provider = true;
+ }
+
+ mutex_unlock(&gpd_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(of_genpd_add_provider_simple);
+
+/**
+ * of_genpd_add_provider_onecell() - Register a onecell PM domain provider
+ * @np: Device node pointer associated with the PM domain provider.
+ * @data: Pointer to the data associated with the PM domain provider.
+ */
+int of_genpd_add_provider_onecell(struct device_node *np,
+ struct genpd_onecell_data *data)
+{
+ unsigned int i;
+ int ret = -EINVAL;
+
+ if (!np || !data)
+ return -EINVAL;
+
+ mutex_lock(&gpd_list_lock);
+
+ for (i = 0; i < data->num_domains; i++) {
+ if (!data->domains[i])
+ continue;
+ if (!pm_genpd_present(data->domains[i]))
+ goto error;
+
+ data->domains[i]->provider = &np->fwnode;
+ data->domains[i]->has_provider = true;
+ }
+
+ ret = genpd_add_provider(np, genpd_xlate_onecell, data);
+ if (ret < 0)
+ goto error;
+
+ mutex_unlock(&gpd_list_lock);
+
+ return 0;
+
+error:
+ while (i--) {
+ if (!data->domains[i])
+ continue;
+ data->domains[i]->provider = NULL;
+ data->domains[i]->has_provider = false;
+ }
+
+ mutex_unlock(&gpd_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(of_genpd_add_provider_onecell);
/**
* of_genpd_del_provider() - Remove a previously registered PM domain provider
@@ -1451,10 +1608,21 @@
void of_genpd_del_provider(struct device_node *np)
{
struct of_genpd_provider *cp;
+ struct generic_pm_domain *gpd;
+ mutex_lock(&gpd_list_lock);
mutex_lock(&of_genpd_mutex);
list_for_each_entry(cp, &of_genpd_providers, link) {
if (cp->node == np) {
+ /*
+ * For each PM domain associated with the
+ * provider, set the 'has_provider' to false
+ * so that the PM domain can be safely removed.
+ */
+ list_for_each_entry(gpd, &gpd_list, gpd_list_node)
+ if (gpd->provider == &np->fwnode)
+ gpd->has_provider = false;
+
list_del(&cp->link);
of_node_put(cp->node);
kfree(cp);
@@ -1462,11 +1630,12 @@
}
}
mutex_unlock(&of_genpd_mutex);
+ mutex_unlock(&gpd_list_lock);
}
EXPORT_SYMBOL_GPL(of_genpd_del_provider);
/**
- * of_genpd_get_from_provider() - Look-up PM domain
+ * genpd_get_from_provider() - Look-up PM domain
* @genpdspec: OF phandle args to use for look-up
*
* Looks for a PM domain provider under the node specified by @genpdspec and if
@@ -1476,7 +1645,7 @@
* Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
* on failure.
*/
-struct generic_pm_domain *of_genpd_get_from_provider(
+static struct generic_pm_domain *genpd_get_from_provider(
struct of_phandle_args *genpdspec)
{
struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
@@ -1499,7 +1668,109 @@
return genpd;
}
-EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
+
+/**
+ * of_genpd_add_device() - Add a device to an I/O PM domain
+ * @genpdspec: OF phandle args to use for look-up PM domain
+ * @dev: Device to be added.
+ *
+ * Looks-up an I/O PM domain based upon phandle args provided and adds
+ * the device to the PM domain. Returns a negative error code on failure.
+ */
+int of_genpd_add_device(struct of_phandle_args *genpdspec, struct device *dev)
+{
+ struct generic_pm_domain *genpd;
+ int ret;
+
+ mutex_lock(&gpd_list_lock);
+
+ genpd = genpd_get_from_provider(genpdspec);
+ if (IS_ERR(genpd)) {
+ ret = PTR_ERR(genpd);
+ goto out;
+ }
+
+ ret = genpd_add_device(genpd, dev, NULL);
+
+out:
+ mutex_unlock(&gpd_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(of_genpd_add_device);
+
+/**
+ * of_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
+ * @parent_spec: OF phandle args to use for parent PM domain look-up
+ * @subdomain_spec: OF phandle args to use for subdomain look-up
+ *
+ * Looks-up a parent PM domain and subdomain based upon phandle args
+ * provided and adds the subdomain to the parent PM domain. Returns a
+ * negative error code on failure.
+ */
+int of_genpd_add_subdomain(struct of_phandle_args *parent_spec,
+ struct of_phandle_args *subdomain_spec)
+{
+ struct generic_pm_domain *parent, *subdomain;
+ int ret;
+
+ mutex_lock(&gpd_list_lock);
+
+ parent = genpd_get_from_provider(parent_spec);
+ if (IS_ERR(parent)) {
+ ret = PTR_ERR(parent);
+ goto out;
+ }
+
+ subdomain = genpd_get_from_provider(subdomain_spec);
+ if (IS_ERR(subdomain)) {
+ ret = PTR_ERR(subdomain);
+ goto out;
+ }
+
+ ret = genpd_add_subdomain(parent, subdomain);
+
+out:
+ mutex_unlock(&gpd_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(of_genpd_add_subdomain);
+
+/**
+ * of_genpd_remove_last - Remove the last PM domain registered for a provider
+ * @provider: Pointer to device structure associated with provider
+ *
+ * Find the last PM domain that was added by a particular provider and
+ * remove this PM domain from the list of PM domains. The provider is
+ * identified by the 'provider' device structure that is passed. The PM
+ * domain will only be removed, if the provider associated with domain
+ * has been removed.
+ *
+ * Returns a valid pointer to struct generic_pm_domain on success or
+ * ERR_PTR() on failure.
+ */
+struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
+{
+ struct generic_pm_domain *gpd, *genpd = ERR_PTR(-ENOENT);
+ int ret;
+
+ if (IS_ERR_OR_NULL(np))
+ return ERR_PTR(-EINVAL);
+
+ mutex_lock(&gpd_list_lock);
+ list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+ if (gpd->provider == &np->fwnode) {
+ ret = genpd_remove(gpd);
+ genpd = ret ? ERR_PTR(ret) : gpd;
+ break;
+ }
+ }
+ mutex_unlock(&gpd_list_lock);
+
+ return genpd;
+}
+EXPORT_SYMBOL_GPL(of_genpd_remove_last);
/**
* genpd_dev_pm_detach - Detach a device from its PM domain.
@@ -1515,14 +1786,14 @@
unsigned int i;
int ret = 0;
- pd = pm_genpd_lookup_dev(dev);
- if (!pd)
+ pd = dev_to_genpd(dev);
+ if (IS_ERR(pd))
return;
dev_dbg(dev, "removing from PM domain %s\n", pd->name);
for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
- ret = pm_genpd_remove_device(pd, dev);
+ ret = genpd_remove_device(pd, dev);
if (ret != -EAGAIN)
break;
@@ -1596,9 +1867,11 @@
return -ENOENT;
}
- pd = of_genpd_get_from_provider(&pd_args);
+ mutex_lock(&gpd_list_lock);
+ pd = genpd_get_from_provider(&pd_args);
of_node_put(pd_args.np);
if (IS_ERR(pd)) {
+ mutex_unlock(&gpd_list_lock);
dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
__func__, PTR_ERR(pd));
return -EPROBE_DEFER;
@@ -1607,13 +1880,14 @@
dev_dbg(dev, "adding to PM domain %s\n", pd->name);
for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
- ret = pm_genpd_add_device(pd, dev);
+ ret = genpd_add_device(pd, dev, NULL);
if (ret != -EAGAIN)
break;
mdelay(i);
cond_resched();
}
+ mutex_unlock(&gpd_list_lock);
if (ret < 0) {
dev_err(dev, "failed to add to PM domain %s: %d",
@@ -1636,7 +1910,7 @@
/*** debugfs support ***/
-#ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_DEBUG_FS
#include <linux/pm.h>
#include <linux/device.h>
#include <linux/debugfs.h>
@@ -1784,4 +2058,4 @@
debugfs_remove_recursive(pm_genpd_debugfs_dir);
}
__exitcall(pm_genpd_debug_exit);
-#endif /* CONFIG_PM_ADVANCED_DEBUG */
+#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index df0c709..4c7c6da 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -584,7 +584,6 @@
struct clk *clk;
unsigned long freq, old_freq;
unsigned long u_volt, u_volt_min, u_volt_max;
- unsigned long ou_volt, ou_volt_min, ou_volt_max;
int ret;
if (unlikely(!target_freq)) {
@@ -620,11 +619,7 @@
}
old_opp = _find_freq_ceil(opp_table, &old_freq);
- if (!IS_ERR(old_opp)) {
- ou_volt = old_opp->u_volt;
- ou_volt_min = old_opp->u_volt_min;
- ou_volt_max = old_opp->u_volt_max;
- } else {
+ if (IS_ERR(old_opp)) {
dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n",
__func__, old_freq, PTR_ERR(old_opp));
}
@@ -683,7 +678,8 @@
restore_voltage:
/* This shouldn't harm even if the voltages weren't updated earlier */
if (!IS_ERR(old_opp))
- _set_opp_voltage(dev, reg, ou_volt, ou_volt_min, ou_volt_max);
+ _set_opp_voltage(dev, reg, old_opp->u_volt,
+ old_opp->u_volt_min, old_opp->u_volt_max);
return ret;
}
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 1dfd3dd..5552211 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -71,8 +71,18 @@
u32 version;
int ret;
- if (!opp_table->supported_hw)
- return true;
+ if (!opp_table->supported_hw) {
+ /*
+ * In the case that no supported_hw has been set by the
+ * platform but there is an opp-supported-hw value set for
+ * an OPP then the OPP should not be enabled as there is
+ * no way to see if the hardware supports it.
+ */
+ if (of_find_property(np, "opp-supported-hw", NULL))
+ return false;
+ else
+ return true;
+ }
while (count--) {
ret = of_property_read_u32_index(np, "opp-supported-hw", count,
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 5677886..8a753fd 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -305,6 +305,16 @@
This must be disabled for hardware validation purposes to detect any
hardware anomalies of missing events.
+config FSL_ERRATUM_A008585
+ bool "Workaround for Freescale/NXP Erratum A-008585"
+ default y
+ depends on ARM_ARCH_TIMER && ARM64
+ help
+ This option enables a workaround for Freescale/NXP Erratum
+ A-008585 ("ARM generic timer may contain an erroneous
+ value"). The workaround will only be active if the
+ fsl,erratum-a008585 property is found in the timer node.
+
config ARM_GLOBAL_TIMER
bool "Support for the ARM global timer" if COMPILE_TEST
select CLKSRC_OF if OF
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 5770054..73c487d 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -94,6 +94,43 @@
* Architected system timer support.
*/
+#ifdef CONFIG_FSL_ERRATUM_A008585
+DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
+EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+
+static int fsl_a008585_enable = -1;
+
+static int __init early_fsl_a008585_cfg(char *buf)
+{
+ int ret;
+ bool val;
+
+ ret = strtobool(buf, &val);
+ if (ret)
+ return ret;
+
+ fsl_a008585_enable = val;
+ return 0;
+}
+early_param("clocksource.arm_arch_timer.fsl-a008585", early_fsl_a008585_cfg);
+
+u32 __fsl_a008585_read_cntp_tval_el0(void)
+{
+ return __fsl_a008585_read_reg(cntp_tval_el0);
+}
+
+u32 __fsl_a008585_read_cntv_tval_el0(void)
+{
+ return __fsl_a008585_read_reg(cntv_tval_el0);
+}
+
+u64 __fsl_a008585_read_cntvct_el0(void)
+{
+ return __fsl_a008585_read_reg(cntvct_el0);
+}
+EXPORT_SYMBOL(__fsl_a008585_read_cntvct_el0);
+#endif /* CONFIG_FSL_ERRATUM_A008585 */
+
static __always_inline
void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
struct clock_event_device *clk)
@@ -243,6 +280,40 @@
arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
}
+#ifdef CONFIG_FSL_ERRATUM_A008585
+static __always_inline void fsl_a008585_set_next_event(const int access,
+ unsigned long evt, struct clock_event_device *clk)
+{
+ unsigned long ctrl;
+ u64 cval = evt + arch_counter_get_cntvct();
+
+ ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+ ctrl |= ARCH_TIMER_CTRL_ENABLE;
+ ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+
+ if (access == ARCH_TIMER_PHYS_ACCESS)
+ write_sysreg(cval, cntp_cval_el0);
+ else if (access == ARCH_TIMER_VIRT_ACCESS)
+ write_sysreg(cval, cntv_cval_el0);
+
+ arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+}
+
+static int fsl_a008585_set_next_event_virt(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ fsl_a008585_set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+ return 0;
+}
+
+static int fsl_a008585_set_next_event_phys(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ fsl_a008585_set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+ return 0;
+}
+#endif /* CONFIG_FSL_ERRATUM_A008585 */
+
static int arch_timer_set_next_event_virt(unsigned long evt,
struct clock_event_device *clk)
{
@@ -271,6 +342,19 @@
return 0;
}
+static void fsl_a008585_set_sne(struct clock_event_device *clk)
+{
+#ifdef CONFIG_FSL_ERRATUM_A008585
+ if (!static_branch_unlikely(&arch_timer_read_ool_enabled))
+ return;
+
+ if (arch_timer_uses_ppi == VIRT_PPI)
+ clk->set_next_event = fsl_a008585_set_next_event_virt;
+ else
+ clk->set_next_event = fsl_a008585_set_next_event_phys;
+#endif
+}
+
static void __arch_timer_setup(unsigned type,
struct clock_event_device *clk)
{
@@ -299,6 +383,8 @@
default:
BUG();
}
+
+ fsl_a008585_set_sne(clk);
} else {
clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
clk->name = "arch_mem_timer";
@@ -515,15 +601,19 @@
arch_timer_read_counter = arch_counter_get_cntvct;
else
arch_timer_read_counter = arch_counter_get_cntpct;
+
+ clocksource_counter.archdata.vdso_direct = true;
+
+#ifdef CONFIG_FSL_ERRATUM_A008585
+ /*
+ * Don't use the vdso fastpath if errata require using
+ * the out-of-line counter accessor.
+ */
+ if (static_branch_unlikely(&arch_timer_read_ool_enabled))
+ clocksource_counter.archdata.vdso_direct = false;
+#endif
} else {
arch_timer_read_counter = arch_counter_get_cntvct_mem;
-
- /* If the clocksource name is "arch_sys_counter" the
- * VDSO will attempt to read the CP15-based counter.
- * Ensure this does not happen when CP15-based
- * counter is not available.
- */
- clocksource_counter.name = "arch_mem_counter";
}
start_count = arch_timer_read_counter();
@@ -800,6 +890,15 @@
arch_timer_c3stop = !of_property_read_bool(np, "always-on");
+#ifdef CONFIG_FSL_ERRATUM_A008585
+ if (fsl_a008585_enable < 0)
+ fsl_a008585_enable = of_property_read_bool(np, "fsl,erratum-a008585");
+ if (fsl_a008585_enable) {
+ static_branch_enable(&arch_timer_read_ool_enabled);
+ pr_info("Enabling workaround for FSL erratum A-008585\n");
+ }
+#endif
+
/*
* If we cannot rely on firmware initializing the timer registers then
* we should use the physical timers instead.
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 74919aa..d8b164a 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -194,7 +194,7 @@
If in doubt, say N.
config CPU_FREQ_GOV_SCHEDUTIL
- tristate "'schedutil' cpufreq policy governor"
+ bool "'schedutil' cpufreq policy governor"
depends on CPU_FREQ && SMP
select CPU_FREQ_GOV_ATTR_SET
select IRQ_WORK
@@ -208,9 +208,6 @@
frequency tipping point is at utilization/capacity equal to 80% in
both cases.
- To compile this driver as a module, choose M here: the module will
- be called cpufreq_schedutil.
-
If in doubt, say N.
comment "CPU frequency scaling drivers"
@@ -225,7 +222,7 @@
help
This adds a generic DT based cpufreq driver for frequency management.
It supports both uniprocessor (UP) and symmetric multiprocessor (SMP)
- systems which share clock and voltage across all CPUs.
+ systems.
If in doubt, say N.
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 6588ec5..1b2f28f 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -19,10 +19,19 @@
#include <linux/delay.h>
#include <linux/cpu.h>
#include <linux/cpufreq.h>
+#include <linux/dmi.h>
#include <linux/vmalloc.h>
+#include <asm/unaligned.h>
+
#include <acpi/cppc_acpi.h>
+/* Minimum struct length needed for the DMI processor entry we want */
+#define DMI_ENTRY_PROCESSOR_MIN_LENGTH 48
+
+/* Offest in the DMI processor structure for the max frequency */
+#define DMI_PROCESSOR_MAX_SPEED 0x14
+
/*
* These structs contain information parsed from per CPU
* ACPI _CPC structures.
@@ -32,6 +41,39 @@
*/
static struct cppc_cpudata **all_cpu_data;
+/* Capture the max KHz from DMI */
+static u64 cppc_dmi_max_khz;
+
+/* Callback function used to retrieve the max frequency from DMI */
+static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
+{
+ const u8 *dmi_data = (const u8 *)dm;
+ u16 *mhz = (u16 *)private;
+
+ if (dm->type == DMI_ENTRY_PROCESSOR &&
+ dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
+ u16 val = (u16)get_unaligned((const u16 *)
+ (dmi_data + DMI_PROCESSOR_MAX_SPEED));
+ *mhz = val > *mhz ? val : *mhz;
+ }
+}
+
+/* Look up the max frequency in DMI */
+static u64 cppc_get_dmi_max_khz(void)
+{
+ u16 mhz = 0;
+
+ dmi_walk(cppc_find_dmi_mhz, &mhz);
+
+ /*
+ * Real stupid fallback value, just in case there is no
+ * actual value set.
+ */
+ mhz = mhz ? mhz : 1;
+
+ return (1000 * mhz);
+}
+
static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation)
@@ -42,7 +84,7 @@
cpu = all_cpu_data[policy->cpu];
- cpu->perf_ctrls.desired_perf = target_freq;
+ cpu->perf_ctrls.desired_perf = (u64)target_freq * policy->max / cppc_dmi_max_khz;
freqs.old = policy->cur;
freqs.new = target_freq;
@@ -94,8 +136,10 @@
return ret;
}
- policy->min = cpu->perf_caps.lowest_perf;
- policy->max = cpu->perf_caps.highest_perf;
+ cppc_dmi_max_khz = cppc_get_dmi_max_khz();
+
+ policy->min = cpu->perf_caps.lowest_perf * cppc_dmi_max_khz / cpu->perf_caps.highest_perf;
+ policy->max = cppc_dmi_max_khz;
policy->cpuinfo.min_freq = policy->min;
policy->cpuinfo.max_freq = policy->max;
policy->cpuinfo.transition_latency = cppc_get_transition_latency(cpu_num);
@@ -113,7 +157,8 @@
cpu->cur_policy = policy;
/* Set policy->cur to max now. The governors will adjust later. */
- policy->cur = cpu->perf_ctrls.desired_perf = cpu->perf_caps.highest_perf;
+ policy->cur = cppc_dmi_max_khz;
+ cpu->perf_ctrls.desired_perf = cpu->perf_caps.highest_perf;
ret = cppc_set_perf(cpu_num, &cpu->perf_ctrls);
if (ret)
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 2ee40fd..7126762 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -11,6 +11,8 @@
#include <linux/of.h>
#include <linux/platform_device.h>
+#include "cpufreq-dt.h"
+
static const struct of_device_id machines[] __initconst = {
{ .compatible = "allwinner,sun4i-a10", },
{ .compatible = "allwinner,sun5i-a10s", },
@@ -40,6 +42,7 @@
{ .compatible = "samsung,exynos5250", },
#ifndef CONFIG_BL_SWITCHER
{ .compatible = "samsung,exynos5420", },
+ { .compatible = "samsung,exynos5433", },
{ .compatible = "samsung,exynos5800", },
#endif
@@ -51,6 +54,7 @@
{ .compatible = "renesas,r8a7779", },
{ .compatible = "renesas,r8a7790", },
{ .compatible = "renesas,r8a7791", },
+ { .compatible = "renesas,r8a7792", },
{ .compatible = "renesas,r8a7793", },
{ .compatible = "renesas,r8a7794", },
{ .compatible = "renesas,sh73a0", },
@@ -68,6 +72,8 @@
{ .compatible = "sigma,tango4" },
+ { .compatible = "ti,am33xx", },
+ { .compatible = "ti,dra7", },
{ .compatible = "ti,omap2", },
{ .compatible = "ti,omap3", },
{ .compatible = "ti,omap4", },
@@ -91,7 +97,8 @@
if (!match)
return -ENODEV;
- return PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt", -1,
- NULL, 0));
+ return PTR_ERR_OR_ZERO(platform_device_register_data(NULL, "cpufreq-dt",
+ -1, match->data,
+ sizeof(struct cpufreq_dt_platform_data)));
}
device_initcall(cpufreq_dt_platdev_init);
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 3957de8..5c07ae0 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -25,6 +25,8 @@
#include <linux/slab.h>
#include <linux/thermal.h>
+#include "cpufreq-dt.h"
+
struct private_data {
struct device *cpu_dev;
struct thermal_cooling_device *cdev;
@@ -353,6 +355,7 @@
static int dt_cpufreq_probe(struct platform_device *pdev)
{
+ struct cpufreq_dt_platform_data *data = dev_get_platdata(&pdev->dev);
int ret;
/*
@@ -366,7 +369,8 @@
if (ret)
return ret;
- dt_cpufreq_driver.driver_data = dev_get_platdata(&pdev->dev);
+ if (data && data->have_governor_per_policy)
+ dt_cpufreq_driver.flags |= CPUFREQ_HAVE_GOVERNOR_PER_POLICY;
ret = cpufreq_register_driver(&dt_cpufreq_driver);
if (ret)
diff --git a/drivers/cpufreq/cpufreq-dt.h b/drivers/cpufreq/cpufreq-dt.h
new file mode 100644
index 0000000..54d774e
--- /dev/null
+++ b/drivers/cpufreq/cpufreq-dt.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright (C) 2016 Linaro
+ * Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CPUFREQ_DT_H__
+#define __CPUFREQ_DT_H__
+
+#include <linux/types.h>
+
+struct cpufreq_dt_platform_data {
+ bool have_governor_per_policy;
+};
+
+#endif /* __CPUFREQ_DT_H__ */
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 3dd4884..3a64136 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -916,58 +916,18 @@
.release = cpufreq_sysfs_release,
};
-static int add_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+static int add_cpu_dev_symlink(struct cpufreq_policy *policy,
+ struct device *dev)
{
- struct device *cpu_dev;
-
- pr_debug("%s: Adding symlink for CPU: %u\n", __func__, cpu);
-
- if (!policy)
- return 0;
-
- cpu_dev = get_cpu_device(cpu);
- if (WARN_ON(!cpu_dev))
- return 0;
-
- return sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq");
+ dev_dbg(dev, "%s: Adding symlink\n", __func__);
+ return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
}
-static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+static void remove_cpu_dev_symlink(struct cpufreq_policy *policy,
+ struct device *dev)
{
- struct device *cpu_dev;
-
- pr_debug("%s: Removing symlink for CPU: %u\n", __func__, cpu);
-
- cpu_dev = get_cpu_device(cpu);
- if (WARN_ON(!cpu_dev))
- return;
-
- sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
-}
-
-/* Add/remove symlinks for all related CPUs */
-static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
-{
- unsigned int j;
- int ret = 0;
-
- /* Some related CPUs might not be present (physically hotplugged) */
- for_each_cpu(j, policy->real_cpus) {
- ret = add_cpu_dev_symlink(policy, j);
- if (ret)
- break;
- }
-
- return ret;
-}
-
-static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
-{
- unsigned int j;
-
- /* Some related CPUs might not be present (physically hotplugged) */
- for_each_cpu(j, policy->real_cpus)
- remove_cpu_dev_symlink(policy, j);
+ dev_dbg(dev, "%s: Removing symlink\n", __func__);
+ sysfs_remove_link(&dev->kobj, "cpufreq");
}
static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
@@ -999,7 +959,7 @@
return ret;
}
- return cpufreq_add_dev_symlink(policy);
+ return 0;
}
__weak struct cpufreq_governor *cpufreq_default_governor(void)
@@ -1073,13 +1033,9 @@
static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
{
- struct device *dev = get_cpu_device(cpu);
struct cpufreq_policy *policy;
int ret;
- if (WARN_ON(!dev))
- return NULL;
-
policy = kzalloc(sizeof(*policy), GFP_KERNEL);
if (!policy)
return NULL;
@@ -1133,7 +1089,6 @@
down_write(&policy->rwsem);
cpufreq_stats_free_table(policy);
- cpufreq_remove_dev_symlink(policy);
kobj = &policy->kobj;
cmp = &policy->kobj_unregister;
up_write(&policy->rwsem);
@@ -1215,8 +1170,8 @@
if (new_policy) {
/* related_cpus should at least include policy->cpus. */
cpumask_copy(policy->related_cpus, policy->cpus);
- /* Remember CPUs present at the policy creation time. */
- cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
+ /* Clear mask of registered CPUs */
+ cpumask_clear(policy->real_cpus);
}
/*
@@ -1331,6 +1286,8 @@
return ret;
}
+static void cpufreq_offline(unsigned int cpu);
+
/**
* cpufreq_add_dev - the cpufreq interface for a CPU device.
* @dev: CPU device.
@@ -1340,22 +1297,28 @@
{
struct cpufreq_policy *policy;
unsigned cpu = dev->id;
+ int ret;
dev_dbg(dev, "%s: adding CPU%u\n", __func__, cpu);
- if (cpu_online(cpu))
- return cpufreq_online(cpu);
+ if (cpu_online(cpu)) {
+ ret = cpufreq_online(cpu);
+ if (ret)
+ return ret;
+ }
- /*
- * A hotplug notifier will follow and we will handle it as CPU online
- * then. For now, just create the sysfs link, unless there is no policy
- * or the link is already present.
- */
+ /* Create sysfs link on CPU registration */
policy = per_cpu(cpufreq_cpu_data, cpu);
if (!policy || cpumask_test_and_set_cpu(cpu, policy->real_cpus))
return 0;
- return add_cpu_dev_symlink(policy, cpu);
+ ret = add_cpu_dev_symlink(policy, dev);
+ if (ret) {
+ cpumask_clear_cpu(cpu, policy->real_cpus);
+ cpufreq_offline(cpu);
+ }
+
+ return ret;
}
static void cpufreq_offline(unsigned int cpu)
@@ -1436,7 +1399,7 @@
cpufreq_offline(cpu);
cpumask_clear_cpu(cpu, policy->real_cpus);
- remove_cpu_dev_symlink(policy, cpu);
+ remove_cpu_dev_symlink(policy, dev);
if (cpumask_empty(policy->real_cpus))
cpufreq_policy_free(policy, true);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index e415349..642dd0f 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -260,7 +260,7 @@
}
static void dbs_update_util_handler(struct update_util_data *data, u64 time,
- unsigned long util, unsigned long max)
+ unsigned int flags)
{
struct cpu_dbs_info *cdbs = container_of(data, struct cpu_dbs_info, update_util);
struct policy_dbs_info *policy_dbs = cdbs->policy_dbs;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index be9eade..806f203 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -181,6 +181,8 @@
* @cpu: CPU number for this instance data
* @update_util: CPUFreq utility callback information
* @update_util_set: CPUFreq utility callback is set
+ * @iowait_boost: iowait-related boost fraction
+ * @last_update: Time of the last update.
* @pstate: Stores P state limits for this CPU
* @vid: Stores VID limits for this CPU
* @pid: Stores PID parameters for this CPU
@@ -206,6 +208,7 @@
struct vid_data vid;
struct _pid pid;
+ u64 last_update;
u64 last_sample_time;
u64 prev_aperf;
u64 prev_mperf;
@@ -216,6 +219,7 @@
struct acpi_processor_performance acpi_perf_data;
bool valid_pss_table;
#endif
+ unsigned int iowait_boost;
};
static struct cpudata **all_cpu_data;
@@ -229,6 +233,7 @@
* @p_gain_pct: PID proportional gain
* @i_gain_pct: PID integral gain
* @d_gain_pct: PID derivative gain
+ * @boost_iowait: Whether or not to use iowait boosting.
*
* Stores per CPU model static PID configuration data.
*/
@@ -240,6 +245,7 @@
int p_gain_pct;
int d_gain_pct;
int i_gain_pct;
+ bool boost_iowait;
};
/**
@@ -1029,7 +1035,7 @@
},
};
-static struct cpu_defaults silvermont_params = {
+static const struct cpu_defaults silvermont_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
@@ -1037,6 +1043,7 @@
.p_gain_pct = 14,
.d_gain_pct = 0,
.i_gain_pct = 4,
+ .boost_iowait = true,
},
.funcs = {
.get_max = atom_get_max_pstate,
@@ -1050,7 +1057,7 @@
},
};
-static struct cpu_defaults airmont_params = {
+static const struct cpu_defaults airmont_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
@@ -1058,6 +1065,7 @@
.p_gain_pct = 14,
.d_gain_pct = 0,
.i_gain_pct = 4,
+ .boost_iowait = true,
},
.funcs = {
.get_max = atom_get_max_pstate,
@@ -1071,7 +1079,7 @@
},
};
-static struct cpu_defaults knl_params = {
+static const struct cpu_defaults knl_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
@@ -1091,7 +1099,7 @@
},
};
-static struct cpu_defaults bxt_params = {
+static const struct cpu_defaults bxt_params = {
.pid_policy = {
.sample_rate_ms = 10,
.deadband = 0,
@@ -1099,6 +1107,7 @@
.p_gain_pct = 14,
.d_gain_pct = 0,
.i_gain_pct = 4,
+ .boost_iowait = true,
},
.funcs = {
.get_max = core_get_max_pstate,
@@ -1222,36 +1231,18 @@
static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
{
struct sample *sample = &cpu->sample;
- u64 cummulative_iowait, delta_iowait_us;
- u64 delta_iowait_mperf;
- u64 mperf, now;
- int32_t cpu_load;
+ int32_t busy_frac, boost;
- cummulative_iowait = get_cpu_iowait_time_us(cpu->cpu, &now);
+ busy_frac = div_fp(sample->mperf, sample->tsc);
- /*
- * Convert iowait time into number of IO cycles spent at max_freq.
- * IO is considered as busy only for the cpu_load algorithm. For
- * performance this is not needed since we always try to reach the
- * maximum P-State, so we are already boosting the IOs.
- */
- delta_iowait_us = cummulative_iowait - cpu->prev_cummulative_iowait;
- delta_iowait_mperf = div64_u64(delta_iowait_us * cpu->pstate.scaling *
- cpu->pstate.max_pstate, MSEC_PER_SEC);
+ boost = cpu->iowait_boost;
+ cpu->iowait_boost >>= 1;
- mperf = cpu->sample.mperf + delta_iowait_mperf;
- cpu->prev_cummulative_iowait = cummulative_iowait;
+ if (busy_frac < boost)
+ busy_frac = boost;
- /*
- * The load can be estimated as the ratio of the mperf counter
- * running at a constant frequency during active periods
- * (C0) and the time stamp counter running at the same frequency
- * also during C-states.
- */
- cpu_load = div64_u64(int_tofp(100) * mperf, sample->tsc);
- cpu->sample.busy_scaled = cpu_load;
-
- return get_avg_pstate(cpu) - pid_calc(&cpu->pid, cpu_load);
+ sample->busy_scaled = busy_frac * 100;
+ return get_avg_pstate(cpu) - pid_calc(&cpu->pid, sample->busy_scaled);
}
static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
@@ -1325,15 +1316,29 @@
sample->mperf,
sample->aperf,
sample->tsc,
- get_avg_frequency(cpu));
+ get_avg_frequency(cpu),
+ fp_toint(cpu->iowait_boost * 100));
}
static void intel_pstate_update_util(struct update_util_data *data, u64 time,
- unsigned long util, unsigned long max)
+ unsigned int flags)
{
struct cpudata *cpu = container_of(data, struct cpudata, update_util);
- u64 delta_ns = time - cpu->sample.time;
+ u64 delta_ns;
+ if (pid_params.boost_iowait) {
+ if (flags & SCHED_CPUFREQ_IOWAIT) {
+ cpu->iowait_boost = int_tofp(1);
+ } else if (cpu->iowait_boost) {
+ /* Clear iowait_boost if the CPU may have been idle. */
+ delta_ns = time - cpu->last_update;
+ if (delta_ns > TICK_NSEC)
+ cpu->iowait_boost = 0;
+ }
+ cpu->last_update = time;
+ }
+
+ delta_ns = time - cpu->sample.time;
if ((s64)delta_ns >= pid_params.sample_rate_ns) {
bool sample_taken = intel_pstate_sample(cpu, time);
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index be42f10..1b9bcd7 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -123,7 +123,7 @@
priv.cpu_clk = of_clk_get_by_name(np, "cpu_clk");
if (IS_ERR(priv.cpu_clk)) {
- dev_err(priv.dev, "Unable to get cpuclk");
+ dev_err(priv.dev, "Unable to get cpuclk\n");
return PTR_ERR(priv.cpu_clk);
}
@@ -132,7 +132,7 @@
priv.ddr_clk = of_clk_get_by_name(np, "ddrclk");
if (IS_ERR(priv.ddr_clk)) {
- dev_err(priv.dev, "Unable to get ddrclk");
+ dev_err(priv.dev, "Unable to get ddrclk\n");
err = PTR_ERR(priv.ddr_clk);
goto out_cpu;
}
@@ -142,7 +142,7 @@
priv.powersave_clk = of_clk_get_by_name(np, "powersave");
if (IS_ERR(priv.powersave_clk)) {
- dev_err(priv.dev, "Unable to get powersave");
+ dev_err(priv.dev, "Unable to get powersave\n");
err = PTR_ERR(priv.powersave_clk);
goto out_ddr;
}
@@ -155,7 +155,7 @@
if (!err)
return 0;
- dev_err(priv.dev, "Failed to register cpufreq driver");
+ dev_err(priv.dev, "Failed to register cpufreq driver\n");
clk_disable_unprepare(priv.powersave_clk);
out_ddr:
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index e8a7bf5..ea7a4e1 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -105,7 +105,6 @@
static struct platform_driver scpi_cpufreq_platdrv = {
.driver = {
.name = "scpi-cpufreq",
- .owner = THIS_MODULE,
},
.probe = scpi_cpufreq_probe,
.remove = scpi_cpufreq_remove,
diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c
index 0404203..b366e6d 100644
--- a/drivers/cpufreq/sti-cpufreq.c
+++ b/drivers/cpufreq/sti-cpufreq.c
@@ -163,7 +163,7 @@
reg_fields = sti_cpufreq_match();
if (!reg_fields) {
- dev_err(dev, "This SoC doesn't support voltage scaling");
+ dev_err(dev, "This SoC doesn't support voltage scaling\n");
return -ENODEV;
}
diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index 4ba3d3f..f440d38 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -121,6 +121,7 @@
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev) {
pr_err("Failed to allocate cpuidle device\n");
+ ret = -ENOMEM;
goto out_fail;
}
dev->cpu = cpu;
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index a5be56e..41254e7 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -76,7 +76,7 @@
config ARM_EXYNOS_BUS_DEVFREQ
tristate "ARM EXYNOS Generic Memory Bus DEVFREQ Driver"
- depends on ARCH_EXYNOS
+ depends on ARCH_EXYNOS || COMPILE_TEST
select DEVFREQ_GOV_SIMPLE_ONDEMAND
select DEVFREQ_GOV_PASSIVE
select DEVFREQ_EVENT_EXYNOS_PPMU
@@ -91,14 +91,26 @@
This does not yet operate with optimal voltages.
config ARM_TEGRA_DEVFREQ
- tristate "Tegra DEVFREQ Driver"
- depends on ARCH_TEGRA_124_SOC
- select DEVFREQ_GOV_SIMPLE_ONDEMAND
- select PM_OPP
- help
- This adds the DEVFREQ driver for the Tegra family of SoCs.
- It reads ACTMON counters of memory controllers and adjusts the
- operating frequencies and voltages with OPP support.
+ tristate "Tegra DEVFREQ Driver"
+ depends on ARCH_TEGRA_124_SOC
+ select DEVFREQ_GOV_SIMPLE_ONDEMAND
+ select PM_OPP
+ help
+ This adds the DEVFREQ driver for the Tegra family of SoCs.
+ It reads ACTMON counters of memory controllers and adjusts the
+ operating frequencies and voltages with OPP support.
+
+config ARM_RK3399_DMC_DEVFREQ
+ tristate "ARM RK3399 DMC DEVFREQ Driver"
+ depends on ARCH_ROCKCHIP
+ select DEVFREQ_EVENT_ROCKCHIP_DFI
+ select DEVFREQ_GOV_SIMPLE_ONDEMAND
+ select PM_DEVFREQ_EVENT
+ select PM_OPP
+ help
+ This adds the DEVFREQ driver for the RK3399 DMC(Dynamic Memory Controller).
+ It sets the frequency for the memory controller and reads the usage counts
+ from hardware.
source "drivers/devfreq/event/Kconfig"
diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile
index 09f11d9..fbff40a 100644
--- a/drivers/devfreq/Makefile
+++ b/drivers/devfreq/Makefile
@@ -8,6 +8,7 @@
# DEVFREQ Drivers
obj-$(CONFIG_ARM_EXYNOS_BUS_DEVFREQ) += exynos-bus.o
+obj-$(CONFIG_ARM_RK3399_DMC_DEVFREQ) += rk3399_dmc.o
obj-$(CONFIG_ARM_TEGRA_DEVFREQ) += tegra-devfreq.o
# DEVFREQ Event Drivers
diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig
index eb6f74a..0fdae86 100644
--- a/drivers/devfreq/event/Kconfig
+++ b/drivers/devfreq/event/Kconfig
@@ -15,7 +15,7 @@
config DEVFREQ_EVENT_EXYNOS_NOCP
tristate "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver"
- depends on ARCH_EXYNOS
+ depends on ARCH_EXYNOS || COMPILE_TEST
select PM_OPP
help
This add the devfreq-event driver for Exynos SoC. It provides NoC
@@ -23,11 +23,18 @@
config DEVFREQ_EVENT_EXYNOS_PPMU
tristate "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver"
- depends on ARCH_EXYNOS
+ depends on ARCH_EXYNOS || COMPILE_TEST
select PM_OPP
help
This add the devfreq-event driver for Exynos SoC. It provides PPMU
(Platform Performance Monitoring Unit) counters to estimate the
utilization of each module.
+config DEVFREQ_EVENT_ROCKCHIP_DFI
+ tristate "ROCKCHIP DFI DEVFREQ event Driver"
+ depends on ARCH_ROCKCHIP
+ help
+ This add the devfreq-event driver for Rockchip SoC. It provides DFI
+ (DDR Monitor Module) driver to count ddr load.
+
endif # PM_DEVFREQ_EVENT
diff --git a/drivers/devfreq/event/Makefile b/drivers/devfreq/event/Makefile
index 3d6afd3..dda7090 100644
--- a/drivers/devfreq/event/Makefile
+++ b/drivers/devfreq/event/Makefile
@@ -2,3 +2,4 @@
obj-$(CONFIG_DEVFREQ_EVENT_EXYNOS_NOCP) += exynos-nocp.o
obj-$(CONFIG_DEVFREQ_EVENT_EXYNOS_PPMU) += exynos-ppmu.o
+obj-$(CONFIG_DEVFREQ_EVENT_ROCKCHIP_DFI) += rockchip-dfi.o
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 845bf25..f55cf0e 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -406,8 +406,6 @@
of_property_read_string(node, "event-name", &desc[j].name);
j++;
-
- of_node_put(node);
}
info->desc = desc;
diff --git a/drivers/devfreq/event/rockchip-dfi.c b/drivers/devfreq/event/rockchip-dfi.c
new file mode 100644
index 0000000..43fcc5a
--- /dev/null
+++ b/drivers/devfreq/event/rockchip-dfi.c
@@ -0,0 +1,256 @@
+/*
+ * Copyright (c) 2016, Fuzhou Rockchip Electronics Co., Ltd
+ * Author: Lin Huang <hl@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/devfreq-event.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/of.h>
+
+#define RK3399_DMC_NUM_CH 2
+
+/* DDRMON_CTRL */
+#define DDRMON_CTRL 0x04
+#define CLR_DDRMON_CTRL (0x1f0000 << 0)
+#define LPDDR4_EN (0x10001 << 4)
+#define HARDWARE_EN (0x10001 << 3)
+#define LPDDR3_EN (0x10001 << 2)
+#define SOFTWARE_EN (0x10001 << 1)
+#define SOFTWARE_DIS (0x10000 << 1)
+#define TIME_CNT_EN (0x10001 << 0)
+
+#define DDRMON_CH0_COUNT_NUM 0x28
+#define DDRMON_CH0_DFI_ACCESS_NUM 0x2c
+#define DDRMON_CH1_COUNT_NUM 0x3c
+#define DDRMON_CH1_DFI_ACCESS_NUM 0x40
+
+/* pmu grf */
+#define PMUGRF_OS_REG2 0x308
+#define DDRTYPE_SHIFT 13
+#define DDRTYPE_MASK 7
+
+enum {
+ DDR3 = 3,
+ LPDDR3 = 6,
+ LPDDR4 = 7,
+ UNUSED = 0xFF
+};
+
+struct dmc_usage {
+ u32 access;
+ u32 total;
+};
+
+/*
+ * The dfi controller can monitor DDR load. It has an upper and lower threshold
+ * for the operating points. Whenever the usage leaves these bounds an event is
+ * generated to indicate the DDR frequency should be changed.
+ */
+struct rockchip_dfi {
+ struct devfreq_event_dev *edev;
+ struct devfreq_event_desc *desc;
+ struct dmc_usage ch_usage[RK3399_DMC_NUM_CH];
+ struct device *dev;
+ void __iomem *regs;
+ struct regmap *regmap_pmu;
+ struct clk *clk;
+};
+
+static void rockchip_dfi_start_hardware_counter(struct devfreq_event_dev *edev)
+{
+ struct rockchip_dfi *info = devfreq_event_get_drvdata(edev);
+ void __iomem *dfi_regs = info->regs;
+ u32 val;
+ u32 ddr_type;
+
+ /* get ddr type */
+ regmap_read(info->regmap_pmu, PMUGRF_OS_REG2, &val);
+ ddr_type = (val >> DDRTYPE_SHIFT) & DDRTYPE_MASK;
+
+ /* clear DDRMON_CTRL setting */
+ writel_relaxed(CLR_DDRMON_CTRL, dfi_regs + DDRMON_CTRL);
+
+ /* set ddr type to dfi */
+ if (ddr_type == LPDDR3)
+ writel_relaxed(LPDDR3_EN, dfi_regs + DDRMON_CTRL);
+ else if (ddr_type == LPDDR4)
+ writel_relaxed(LPDDR4_EN, dfi_regs + DDRMON_CTRL);
+
+ /* enable count, use software mode */
+ writel_relaxed(SOFTWARE_EN, dfi_regs + DDRMON_CTRL);
+}
+
+static void rockchip_dfi_stop_hardware_counter(struct devfreq_event_dev *edev)
+{
+ struct rockchip_dfi *info = devfreq_event_get_drvdata(edev);
+ void __iomem *dfi_regs = info->regs;
+
+ writel_relaxed(SOFTWARE_DIS, dfi_regs + DDRMON_CTRL);
+}
+
+static int rockchip_dfi_get_busier_ch(struct devfreq_event_dev *edev)
+{
+ struct rockchip_dfi *info = devfreq_event_get_drvdata(edev);
+ u32 tmp, max = 0;
+ u32 i, busier_ch = 0;
+ void __iomem *dfi_regs = info->regs;
+
+ rockchip_dfi_stop_hardware_counter(edev);
+
+ /* Find out which channel is busier */
+ for (i = 0; i < RK3399_DMC_NUM_CH; i++) {
+ info->ch_usage[i].access = readl_relaxed(dfi_regs +
+ DDRMON_CH0_DFI_ACCESS_NUM + i * 20) * 4;
+ info->ch_usage[i].total = readl_relaxed(dfi_regs +
+ DDRMON_CH0_COUNT_NUM + i * 20);
+ tmp = info->ch_usage[i].access;
+ if (tmp > max) {
+ busier_ch = i;
+ max = tmp;
+ }
+ }
+ rockchip_dfi_start_hardware_counter(edev);
+
+ return busier_ch;
+}
+
+static int rockchip_dfi_disable(struct devfreq_event_dev *edev)
+{
+ struct rockchip_dfi *info = devfreq_event_get_drvdata(edev);
+
+ rockchip_dfi_stop_hardware_counter(edev);
+ clk_disable_unprepare(info->clk);
+
+ return 0;
+}
+
+static int rockchip_dfi_enable(struct devfreq_event_dev *edev)
+{
+ struct rockchip_dfi *info = devfreq_event_get_drvdata(edev);
+ int ret;
+
+ ret = clk_prepare_enable(info->clk);
+ if (ret) {
+ dev_err(&edev->dev, "failed to enable dfi clk: %d\n", ret);
+ return ret;
+ }
+
+ rockchip_dfi_start_hardware_counter(edev);
+ return 0;
+}
+
+static int rockchip_dfi_set_event(struct devfreq_event_dev *edev)
+{
+ return 0;
+}
+
+static int rockchip_dfi_get_event(struct devfreq_event_dev *edev,
+ struct devfreq_event_data *edata)
+{
+ struct rockchip_dfi *info = devfreq_event_get_drvdata(edev);
+ int busier_ch;
+
+ busier_ch = rockchip_dfi_get_busier_ch(edev);
+
+ edata->load_count = info->ch_usage[busier_ch].access;
+ edata->total_count = info->ch_usage[busier_ch].total;
+
+ return 0;
+}
+
+static const struct devfreq_event_ops rockchip_dfi_ops = {
+ .disable = rockchip_dfi_disable,
+ .enable = rockchip_dfi_enable,
+ .get_event = rockchip_dfi_get_event,
+ .set_event = rockchip_dfi_set_event,
+};
+
+static const struct of_device_id rockchip_dfi_id_match[] = {
+ { .compatible = "rockchip,rk3399-dfi" },
+ { },
+};
+
+static int rockchip_dfi_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct rockchip_dfi *data;
+ struct resource *res;
+ struct devfreq_event_desc *desc;
+ struct device_node *np = pdev->dev.of_node, *node;
+
+ data = devm_kzalloc(dev, sizeof(struct rockchip_dfi), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ data->regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(data->regs))
+ return PTR_ERR(data->regs);
+
+ data->clk = devm_clk_get(dev, "pclk_ddr_mon");
+ if (IS_ERR(data->clk)) {
+ dev_err(dev, "Cannot get the clk dmc_clk\n");
+ return PTR_ERR(data->clk);
+ };
+
+ /* try to find the optional reference to the pmu syscon */
+ node = of_parse_phandle(np, "rockchip,pmu", 0);
+ if (node) {
+ data->regmap_pmu = syscon_node_to_regmap(node);
+ if (IS_ERR(data->regmap_pmu))
+ return PTR_ERR(data->regmap_pmu);
+ }
+ data->dev = dev;
+
+ desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ desc->ops = &rockchip_dfi_ops;
+ desc->driver_data = data;
+ desc->name = np->name;
+ data->desc = desc;
+
+ data->edev = devm_devfreq_event_add_edev(&pdev->dev, desc);
+ if (IS_ERR(data->edev)) {
+ dev_err(&pdev->dev,
+ "failed to add devfreq-event device\n");
+ return PTR_ERR(data->edev);
+ }
+
+ platform_set_drvdata(pdev, data);
+
+ return 0;
+}
+
+static struct platform_driver rockchip_dfi_driver = {
+ .probe = rockchip_dfi_probe,
+ .driver = {
+ .name = "rockchip-dfi",
+ .of_match_table = rockchip_dfi_id_match,
+ },
+};
+module_platform_driver(rockchip_dfi_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Lin Huang <hl@rock-chips.com>");
+MODULE_DESCRIPTION("Rockchip DFI driver");
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
new file mode 100644
index 0000000..e24b73d
--- /dev/null
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -0,0 +1,470 @@
+/*
+ * Copyright (c) 2016, Fuzhou Rockchip Electronics Co., Ltd.
+ * Author: Lin Huang <hl@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/devfreq.h>
+#include <linux/devfreq-event.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/regulator/consumer.h>
+#include <linux/rwsem.h>
+#include <linux/suspend.h>
+
+#include <soc/rockchip/rockchip_sip.h>
+
+struct dram_timing {
+ unsigned int ddr3_speed_bin;
+ unsigned int pd_idle;
+ unsigned int sr_idle;
+ unsigned int sr_mc_gate_idle;
+ unsigned int srpd_lite_idle;
+ unsigned int standby_idle;
+ unsigned int auto_pd_dis_freq;
+ unsigned int dram_dll_dis_freq;
+ unsigned int phy_dll_dis_freq;
+ unsigned int ddr3_odt_dis_freq;
+ unsigned int ddr3_drv;
+ unsigned int ddr3_odt;
+ unsigned int phy_ddr3_ca_drv;
+ unsigned int phy_ddr3_dq_drv;
+ unsigned int phy_ddr3_odt;
+ unsigned int lpddr3_odt_dis_freq;
+ unsigned int lpddr3_drv;
+ unsigned int lpddr3_odt;
+ unsigned int phy_lpddr3_ca_drv;
+ unsigned int phy_lpddr3_dq_drv;
+ unsigned int phy_lpddr3_odt;
+ unsigned int lpddr4_odt_dis_freq;
+ unsigned int lpddr4_drv;
+ unsigned int lpddr4_dq_odt;
+ unsigned int lpddr4_ca_odt;
+ unsigned int phy_lpddr4_ca_drv;
+ unsigned int phy_lpddr4_ck_cs_drv;
+ unsigned int phy_lpddr4_dq_drv;
+ unsigned int phy_lpddr4_odt;
+};
+
+struct rk3399_dmcfreq {
+ struct device *dev;
+ struct devfreq *devfreq;
+ struct devfreq_simple_ondemand_data ondemand_data;
+ struct clk *dmc_clk;
+ struct devfreq_event_dev *edev;
+ struct mutex lock;
+ struct dram_timing timing;
+
+ /*
+ * DDR Converser of Frequency (DCF) is used to implement DDR frequency
+ * conversion without the participation of CPU, we will implement and
+ * control it in arm trust firmware.
+ */
+ wait_queue_head_t wait_dcf_queue;
+ int irq;
+ int wait_dcf_flag;
+ struct regulator *vdd_center;
+ unsigned long rate, target_rate;
+ unsigned long volt, target_volt;
+ struct dev_pm_opp *curr_opp;
+};
+
+static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
+ u32 flags)
+{
+ struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(dev);
+ struct dev_pm_opp *opp;
+ unsigned long old_clk_rate = dmcfreq->rate;
+ unsigned long target_volt, target_rate;
+ int err;
+
+ rcu_read_lock();
+ opp = devfreq_recommended_opp(dev, freq, flags);
+ if (IS_ERR(opp)) {
+ rcu_read_unlock();
+ return PTR_ERR(opp);
+ }
+
+ target_rate = dev_pm_opp_get_freq(opp);
+ target_volt = dev_pm_opp_get_voltage(opp);
+
+ dmcfreq->rate = dev_pm_opp_get_freq(dmcfreq->curr_opp);
+ dmcfreq->volt = dev_pm_opp_get_voltage(dmcfreq->curr_opp);
+
+ rcu_read_unlock();
+
+ if (dmcfreq->rate == target_rate)
+ return 0;
+
+ mutex_lock(&dmcfreq->lock);
+
+ /*
+ * If frequency scaling from low to high, adjust voltage first.
+ * If frequency scaling from high to low, adjust frequency first.
+ */
+ if (old_clk_rate < target_rate) {
+ err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
+ target_volt);
+ if (err) {
+ dev_err(dev, "Cannot to set voltage %lu uV\n",
+ target_volt);
+ goto out;
+ }
+ }
+ dmcfreq->wait_dcf_flag = 1;
+
+ err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
+ if (err) {
+ dev_err(dev, "Cannot to set frequency %lu (%d)\n",
+ target_rate, err);
+ regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
+ dmcfreq->volt);
+ goto out;
+ }
+
+ /*
+ * Wait until bcf irq happen, it means freq scaling finish in
+ * arm trust firmware, use 100ms as timeout time.
+ */
+ if (!wait_event_timeout(dmcfreq->wait_dcf_queue,
+ !dmcfreq->wait_dcf_flag, HZ / 10))
+ dev_warn(dev, "Timeout waiting for dcf interrupt\n");
+
+ /*
+ * Check the dpll rate,
+ * There only two result we will get,
+ * 1. Ddr frequency scaling fail, we still get the old rate.
+ * 2. Ddr frequency scaling sucessful, we get the rate we set.
+ */
+ dmcfreq->rate = clk_get_rate(dmcfreq->dmc_clk);
+
+ /* If get the incorrect rate, set voltage to old value. */
+ if (dmcfreq->rate != target_rate) {
+ dev_err(dev, "Get wrong ddr frequency, Request frequency %lu,\
+ Current frequency %lu\n", target_rate, dmcfreq->rate);
+ regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
+ dmcfreq->volt);
+ goto out;
+ } else if (old_clk_rate > target_rate)
+ err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
+ target_volt);
+ if (err)
+ dev_err(dev, "Cannot to set vol %lu uV\n", target_volt);
+
+ dmcfreq->curr_opp = opp;
+out:
+ mutex_unlock(&dmcfreq->lock);
+ return err;
+}
+
+static int rk3399_dmcfreq_get_dev_status(struct device *dev,
+ struct devfreq_dev_status *stat)
+{
+ struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(dev);
+ struct devfreq_event_data edata;
+ int ret = 0;
+
+ ret = devfreq_event_get_event(dmcfreq->edev, &edata);
+ if (ret < 0)
+ return ret;
+
+ stat->current_frequency = dmcfreq->rate;
+ stat->busy_time = edata.load_count;
+ stat->total_time = edata.total_count;
+
+ return ret;
+}
+
+static int rk3399_dmcfreq_get_cur_freq(struct device *dev, unsigned long *freq)
+{
+ struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(dev);
+
+ *freq = dmcfreq->rate;
+
+ return 0;
+}
+
+static struct devfreq_dev_profile rk3399_devfreq_dmc_profile = {
+ .polling_ms = 200,
+ .target = rk3399_dmcfreq_target,
+ .get_dev_status = rk3399_dmcfreq_get_dev_status,
+ .get_cur_freq = rk3399_dmcfreq_get_cur_freq,
+};
+
+static __maybe_unused int rk3399_dmcfreq_suspend(struct device *dev)
+{
+ struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(dev);
+ int ret = 0;
+
+ ret = devfreq_event_disable_edev(dmcfreq->edev);
+ if (ret < 0) {
+ dev_err(dev, "failed to disable the devfreq-event devices\n");
+ return ret;
+ }
+
+ ret = devfreq_suspend_device(dmcfreq->devfreq);
+ if (ret < 0) {
+ dev_err(dev, "failed to suspend the devfreq devices\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev)
+{
+ struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(dev);
+ int ret = 0;
+
+ ret = devfreq_event_enable_edev(dmcfreq->edev);
+ if (ret < 0) {
+ dev_err(dev, "failed to enable the devfreq-event devices\n");
+ return ret;
+ }
+
+ ret = devfreq_resume_device(dmcfreq->devfreq);
+ if (ret < 0) {
+ dev_err(dev, "failed to resume the devfreq devices\n");
+ return ret;
+ }
+ return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend,
+ rk3399_dmcfreq_resume);
+
+static irqreturn_t rk3399_dmc_irq(int irq, void *dev_id)
+{
+ struct rk3399_dmcfreq *dmcfreq = dev_id;
+ struct arm_smccc_res res;
+
+ dmcfreq->wait_dcf_flag = 0;
+ wake_up(&dmcfreq->wait_dcf_queue);
+
+ /* Clear the DCF interrupt */
+ arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
+ ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ,
+ 0, 0, 0, 0, &res);
+
+ return IRQ_HANDLED;
+}
+
+static int of_get_ddr_timings(struct dram_timing *timing,
+ struct device_node *np)
+{
+ int ret = 0;
+
+ ret = of_property_read_u32(np, "rockchip,ddr3_speed_bin",
+ &timing->ddr3_speed_bin);
+ ret |= of_property_read_u32(np, "rockchip,pd_idle",
+ &timing->pd_idle);
+ ret |= of_property_read_u32(np, "rockchip,sr_idle",
+ &timing->sr_idle);
+ ret |= of_property_read_u32(np, "rockchip,sr_mc_gate_idle",
+ &timing->sr_mc_gate_idle);
+ ret |= of_property_read_u32(np, "rockchip,srpd_lite_idle",
+ &timing->srpd_lite_idle);
+ ret |= of_property_read_u32(np, "rockchip,standby_idle",
+ &timing->standby_idle);
+ ret |= of_property_read_u32(np, "rockchip,auto_pd_dis_freq",
+ &timing->auto_pd_dis_freq);
+ ret |= of_property_read_u32(np, "rockchip,dram_dll_dis_freq",
+ &timing->dram_dll_dis_freq);
+ ret |= of_property_read_u32(np, "rockchip,phy_dll_dis_freq",
+ &timing->phy_dll_dis_freq);
+ ret |= of_property_read_u32(np, "rockchip,ddr3_odt_dis_freq",
+ &timing->ddr3_odt_dis_freq);
+ ret |= of_property_read_u32(np, "rockchip,ddr3_drv",
+ &timing->ddr3_drv);
+ ret |= of_property_read_u32(np, "rockchip,ddr3_odt",
+ &timing->ddr3_odt);
+ ret |= of_property_read_u32(np, "rockchip,phy_ddr3_ca_drv",
+ &timing->phy_ddr3_ca_drv);
+ ret |= of_property_read_u32(np, "rockchip,phy_ddr3_dq_drv",
+ &timing->phy_ddr3_dq_drv);
+ ret |= of_property_read_u32(np, "rockchip,phy_ddr3_odt",
+ &timing->phy_ddr3_odt);
+ ret |= of_property_read_u32(np, "rockchip,lpddr3_odt_dis_freq",
+ &timing->lpddr3_odt_dis_freq);
+ ret |= of_property_read_u32(np, "rockchip,lpddr3_drv",
+ &timing->lpddr3_drv);
+ ret |= of_property_read_u32(np, "rockchip,lpddr3_odt",
+ &timing->lpddr3_odt);
+ ret |= of_property_read_u32(np, "rockchip,phy_lpddr3_ca_drv",
+ &timing->phy_lpddr3_ca_drv);
+ ret |= of_property_read_u32(np, "rockchip,phy_lpddr3_dq_drv",
+ &timing->phy_lpddr3_dq_drv);
+ ret |= of_property_read_u32(np, "rockchip,phy_lpddr3_odt",
+ &timing->phy_lpddr3_odt);
+ ret |= of_property_read_u32(np, "rockchip,lpddr4_odt_dis_freq",
+ &timing->lpddr4_odt_dis_freq);
+ ret |= of_property_read_u32(np, "rockchip,lpddr4_drv",
+ &timing->lpddr4_drv);
+ ret |= of_property_read_u32(np, "rockchip,lpddr4_dq_odt",
+ &timing->lpddr4_dq_odt);
+ ret |= of_property_read_u32(np, "rockchip,lpddr4_ca_odt",
+ &timing->lpddr4_ca_odt);
+ ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_ca_drv",
+ &timing->phy_lpddr4_ca_drv);
+ ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_ck_cs_drv",
+ &timing->phy_lpddr4_ck_cs_drv);
+ ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_dq_drv",
+ &timing->phy_lpddr4_dq_drv);
+ ret |= of_property_read_u32(np, "rockchip,phy_lpddr4_odt",
+ &timing->phy_lpddr4_odt);
+
+ return ret;
+}
+
+static int rk3399_dmcfreq_probe(struct platform_device *pdev)
+{
+ struct arm_smccc_res res;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = pdev->dev.of_node;
+ struct rk3399_dmcfreq *data;
+ int ret, irq, index, size;
+ uint32_t *timing;
+ struct dev_pm_opp *opp;
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(&pdev->dev, "Cannot get the dmc interrupt resource\n");
+ return -EINVAL;
+ }
+ data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ mutex_init(&data->lock);
+
+ data->vdd_center = devm_regulator_get(dev, "center");
+ if (IS_ERR(data->vdd_center)) {
+ dev_err(dev, "Cannot get the regulator \"center\"\n");
+ return PTR_ERR(data->vdd_center);
+ }
+
+ data->dmc_clk = devm_clk_get(dev, "dmc_clk");
+ if (IS_ERR(data->dmc_clk)) {
+ dev_err(dev, "Cannot get the clk dmc_clk\n");
+ return PTR_ERR(data->dmc_clk);
+ };
+
+ data->irq = irq;
+ ret = devm_request_irq(dev, irq, rk3399_dmc_irq, 0,
+ dev_name(dev), data);
+ if (ret) {
+ dev_err(dev, "Failed to request dmc irq: %d\n", ret);
+ return ret;
+ }
+
+ init_waitqueue_head(&data->wait_dcf_queue);
+ data->wait_dcf_flag = 0;
+
+ data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
+ if (IS_ERR(data->edev))
+ return -EPROBE_DEFER;
+
+ ret = devfreq_event_enable_edev(data->edev);
+ if (ret < 0) {
+ dev_err(dev, "failed to enable devfreq-event devices\n");
+ return ret;
+ }
+
+ /*
+ * Get dram timing and pass it to arm trust firmware,
+ * the dram drvier in arm trust firmware will get these
+ * timing and to do dram initial.
+ */
+ if (!of_get_ddr_timings(&data->timing, np)) {
+ timing = &data->timing.ddr3_speed_bin;
+ size = sizeof(struct dram_timing) / 4;
+ for (index = 0; index < size; index++) {
+ arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, *timing++, index,
+ ROCKCHIP_SIP_CONFIG_DRAM_SET_PARAM,
+ 0, 0, 0, 0, &res);
+ if (res.a0) {
+ dev_err(dev, "Failed to set dram param: %ld\n",
+ res.a0);
+ return -EINVAL;
+ }
+ }
+ }
+
+ arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
+ ROCKCHIP_SIP_CONFIG_DRAM_INIT,
+ 0, 0, 0, 0, &res);
+
+ /*
+ * We add a devfreq driver to our parent since it has a device tree node
+ * with operating points.
+ */
+ if (dev_pm_opp_of_add_table(dev)) {
+ dev_err(dev, "Invalid operating-points in device tree.\n");
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ of_property_read_u32(np, "upthreshold",
+ &data->ondemand_data.upthreshold);
+ of_property_read_u32(np, "downdifferential",
+ &data->ondemand_data.downdifferential);
+
+ data->rate = clk_get_rate(data->dmc_clk);
+
+ rcu_read_lock();
+ opp = devfreq_recommended_opp(dev, &data->rate, 0);
+ if (IS_ERR(opp)) {
+ rcu_read_unlock();
+ return PTR_ERR(opp);
+ }
+ rcu_read_unlock();
+ data->curr_opp = opp;
+
+ rk3399_devfreq_dmc_profile.initial_freq = data->rate;
+
+ data->devfreq = devfreq_add_device(dev,
+ &rk3399_devfreq_dmc_profile,
+ "simple_ondemand",
+ &data->ondemand_data);
+ if (IS_ERR(data->devfreq))
+ return PTR_ERR(data->devfreq);
+ devm_devfreq_register_opp_notifier(dev, data->devfreq);
+
+ data->dev = dev;
+ platform_set_drvdata(pdev, data);
+
+ return 0;
+}
+
+static const struct of_device_id rk3399dmc_devfreq_of_match[] = {
+ { .compatible = "rockchip,rk3399-dmc" },
+ { },
+};
+
+static struct platform_driver rk3399_dmcfreq_driver = {
+ .probe = rk3399_dmcfreq_probe,
+ .driver = {
+ .name = "rk3399-dmc-freq",
+ .pm = &rk3399_dmcfreq_pm,
+ .of_match_table = rk3399dmc_devfreq_of_match,
+ },
+};
+module_platform_driver(rk3399_dmcfreq_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Lin Huang <hl@rock-chips.com>");
+MODULE_DESCRIPTION("RK3399 dmcfreq driver with devfreq framework");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index df7ab245..39c01b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1708,11 +1708,11 @@
DRM_INFO("amdgpu: finishing device.\n");
adev->shutdown = true;
+ drm_crtc_force_disable_all(adev->ddev);
/* evict vram memory */
amdgpu_bo_evict_vram(adev);
amdgpu_ib_pool_fini(adev);
amdgpu_fence_driver_fini(adev);
- drm_crtc_force_disable_all(adev->ddev);
amdgpu_fbdev_fini(adev);
r = amdgpu_fini(adev);
kfree(adev->ip_block_status);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 7ea8aa7..6bc712f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -175,6 +175,7 @@
void (*fini)(struct nvkm_device *, bool suspend);
resource_size_t (*resource_addr)(struct nvkm_device *, unsigned bar);
resource_size_t (*resource_size)(struct nvkm_device *, unsigned bar);
+ bool cpu_coherent;
};
struct nvkm_device_quirk {
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 6190035..864323b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -209,7 +209,8 @@
nvbo->tile_flags = tile_flags;
nvbo->bo.bdev = &drm->ttm.bdev;
- nvbo->force_coherent = flags & TTM_PL_FLAG_UNCACHED;
+ if (!nvxx_device(&drm->device)->func->cpu_coherent)
+ nvbo->force_coherent = flags & TTM_PL_FLAG_UNCACHED;
nvbo->page_shift = 12;
if (drm->client.vm) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
index b1b6932..62ad030 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
@@ -1614,6 +1614,7 @@
.fini = nvkm_device_pci_fini,
.resource_addr = nvkm_device_pci_resource_addr,
.resource_size = nvkm_device_pci_resource_size,
+ .cpu_coherent = !IS_ENABLED(CONFIG_ARM),
};
int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 939682f..9b638bd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -245,6 +245,7 @@
.fini = nvkm_device_tegra_fini,
.resource_addr = nvkm_device_tegra_resource_addr,
.resource_size = nvkm_device_tegra_resource_size,
+ .cpu_coherent = false,
};
int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c
index edec30f..0a7b6ed 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/dmanv04.c
@@ -37,7 +37,10 @@
{
struct nv04_fifo_chan *chan = nv04_fifo_chan(base);
struct nvkm_instmem *imem = chan->fifo->base.engine.subdev.device->imem;
+
+ mutex_lock(&chan->fifo->base.engine.subdev.mutex);
nvkm_ramht_remove(imem->ramht, cookie);
+ mutex_unlock(&chan->fifo->base.engine.subdev.mutex);
}
static int
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index e6abc09..1f78ec2 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3015,6 +3015,12 @@
if (rdev->pdev->device == 0x6811 &&
rdev->pdev->revision == 0x81)
max_mclk = 120000;
+ /* limit sclk/mclk on Jet parts for stability */
+ if (rdev->pdev->device == 0x6665 &&
+ rdev->pdev->revision == 0xc3) {
+ max_sclk = 75000;
+ max_mclk = 80000;
+ }
if (rps->vce_active) {
rps->evclk = rdev->pm.dpm.vce_states[rdev->pm.dpm.vce_level].evclk;
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index 9688bfa..611b6b9 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -122,7 +122,7 @@
return 0;
cmd = urb->transfer_buffer;
- for (i = y; i < height ; i++) {
+ for (i = y; i < y + height ; i++) {
const int line_offset = fb->base.pitches[0] * i;
const int byte_offset = line_offset + (x * bpp);
const int dev_byte_offset = (fb->base.width * bpp * i) + (x * bpp);
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index 5d11fea..f3135ae 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -950,6 +950,12 @@
.flags = INPUT_DEVICE_ID_MATCH_EVBIT |
INPUT_DEVICE_ID_MATCH_ABSBIT,
.evbit = { BIT_MASK(EV_ABS) },
+ .absbit = { BIT_MASK(ABS_Z) },
+ },
+ {
+ .flags = INPUT_DEVICE_ID_MATCH_EVBIT |
+ INPUT_DEVICE_ID_MATCH_ABSBIT,
+ .evbit = { BIT_MASK(EV_ABS) },
.absbit = { BIT_MASK(ABS_WHEEL) },
},
{
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index cc07ba0..27fa8b8 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -240,6 +240,9 @@
unsigned long flags;
u32 val;
+ /* Reset ECC hardware */
+ davinci_nand_readl(info, NAND_4BIT_ECC1_OFFSET);
+
spin_lock_irqsave(&davinci_nand_lock, flags);
/* Start 4-bit ECC calculation for read/write */
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index a59361c..5513bfd9 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -2169,7 +2169,7 @@
return 0;
return_error:
- if (info->dma)
+ if (!IS_ERR_OR_NULL(info->dma))
dma_release_channel(info->dma);
if (nand_chip->ecc.priv) {
nand_bch_free(nand_chip->ecc.priv);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index e21f7cc..8d6208c 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -21,6 +21,7 @@
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
+#include <linux/workqueue.h>
#include <linux/can.h>
#include <linux/can/dev.h>
#include <linux/can/skb.h>
@@ -501,9 +502,8 @@
/*
* CAN device restart for bus-off recovery
*/
-static void can_restart(unsigned long data)
+static void can_restart(struct net_device *dev)
{
- struct net_device *dev = (struct net_device *)data;
struct can_priv *priv = netdev_priv(dev);
struct net_device_stats *stats = &dev->stats;
struct sk_buff *skb;
@@ -543,6 +543,14 @@
netdev_err(dev, "Error %d during restart", err);
}
+static void can_restart_work(struct work_struct *work)
+{
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct can_priv *priv = container_of(dwork, struct can_priv, restart_work);
+
+ can_restart(priv->dev);
+}
+
int can_restart_now(struct net_device *dev)
{
struct can_priv *priv = netdev_priv(dev);
@@ -556,8 +564,8 @@
if (priv->state != CAN_STATE_BUS_OFF)
return -EBUSY;
- /* Runs as soon as possible in the timer context */
- mod_timer(&priv->restart_timer, jiffies);
+ cancel_delayed_work_sync(&priv->restart_work);
+ can_restart(dev);
return 0;
}
@@ -578,8 +586,8 @@
netif_carrier_off(dev);
if (priv->restart_ms)
- mod_timer(&priv->restart_timer,
- jiffies + (priv->restart_ms * HZ) / 1000);
+ schedule_delayed_work(&priv->restart_work,
+ msecs_to_jiffies(priv->restart_ms));
}
EXPORT_SYMBOL_GPL(can_bus_off);
@@ -688,6 +696,7 @@
return NULL;
priv = netdev_priv(dev);
+ priv->dev = dev;
if (echo_skb_max) {
priv->echo_skb_max = echo_skb_max;
@@ -697,7 +706,7 @@
priv->state = CAN_STATE_STOPPED;
- init_timer(&priv->restart_timer);
+ INIT_DELAYED_WORK(&priv->restart_work, can_restart_work);
return dev;
}
@@ -778,8 +787,6 @@
if (!netif_carrier_ok(dev))
netif_carrier_on(dev);
- setup_timer(&priv->restart_timer, can_restart, (unsigned long)dev);
-
return 0;
}
EXPORT_SYMBOL_GPL(open_candev);
@@ -794,7 +801,7 @@
{
struct can_priv *priv = netdev_priv(dev);
- del_timer_sync(&priv->restart_timer);
+ cancel_delayed_work_sync(&priv->restart_work);
can_flush_echo_skb(dev);
}
EXPORT_SYMBOL_GPL(close_candev);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 8d4f849..5414563 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -453,25 +453,29 @@
static int bcmgenet_get_settings(struct net_device *dev,
struct ethtool_cmd *cmd)
{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
if (!netif_running(dev))
return -EINVAL;
- if (!dev->phydev)
+ if (!priv->phydev)
return -ENODEV;
- return phy_ethtool_gset(dev->phydev, cmd);
+ return phy_ethtool_gset(priv->phydev, cmd);
}
static int bcmgenet_set_settings(struct net_device *dev,
struct ethtool_cmd *cmd)
{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
if (!netif_running(dev))
return -EINVAL;
- if (!dev->phydev)
+ if (!priv->phydev)
return -ENODEV;
- return phy_ethtool_sset(dev->phydev, cmd);
+ return phy_ethtool_sset(priv->phydev, cmd);
}
static int bcmgenet_set_rx_csum(struct net_device *dev,
@@ -937,7 +941,7 @@
e->eee_active = p->eee_active;
e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);
- return phy_ethtool_get_eee(dev->phydev, e);
+ return phy_ethtool_get_eee(priv->phydev, e);
}
static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
@@ -954,7 +958,7 @@
if (!p->eee_enabled) {
bcmgenet_eee_enable_set(dev, false);
} else {
- ret = phy_init_eee(dev->phydev, 0);
+ ret = phy_init_eee(priv->phydev, 0);
if (ret) {
netif_err(priv, hw, dev, "EEE initialization failed\n");
return ret;
@@ -964,12 +968,14 @@
bcmgenet_eee_enable_set(dev, true);
}
- return phy_ethtool_set_eee(dev->phydev, e);
+ return phy_ethtool_set_eee(priv->phydev, e);
}
static int bcmgenet_nway_reset(struct net_device *dev)
{
- return genphy_restart_aneg(dev->phydev);
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ return genphy_restart_aneg(priv->phydev);
}
/* standard ethtool support functions. */
@@ -996,13 +1002,12 @@
static int bcmgenet_power_down(struct bcmgenet_priv *priv,
enum bcmgenet_power_mode mode)
{
- struct net_device *ndev = priv->dev;
int ret = 0;
u32 reg;
switch (mode) {
case GENET_POWER_CABLE_SENSE:
- phy_detach(ndev->phydev);
+ phy_detach(priv->phydev);
break;
case GENET_POWER_WOL_MAGIC:
@@ -1063,6 +1068,7 @@
/* ioctl handle special commands that are not present in ethtool. */
static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
int val = 0;
if (!netif_running(dev))
@@ -1072,10 +1078,10 @@
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSMIIREG:
- if (!dev->phydev)
+ if (!priv->phydev)
val = -ENODEV;
else
- val = phy_mii_ioctl(dev->phydev, rq, cmd);
+ val = phy_mii_ioctl(priv->phydev, rq, cmd);
break;
default:
@@ -2458,7 +2464,6 @@
{
struct bcmgenet_priv *priv = container_of(
work, struct bcmgenet_priv, bcmgenet_irq_work);
- struct net_device *ndev = priv->dev;
netif_dbg(priv, intr, priv->dev, "%s\n", __func__);
@@ -2471,7 +2476,7 @@
/* Link UP/DOWN event */
if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) {
- phy_mac_interrupt(ndev->phydev,
+ phy_mac_interrupt(priv->phydev,
!!(priv->irq0_stat & UMAC_IRQ_LINK_UP));
priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT;
}
@@ -2833,7 +2838,7 @@
/* Monitor link interrupts now */
bcmgenet_link_intr_enable(priv);
- phy_start(dev->phydev);
+ phy_start(priv->phydev);
}
static int bcmgenet_open(struct net_device *dev)
@@ -2932,7 +2937,7 @@
struct bcmgenet_priv *priv = netdev_priv(dev);
netif_tx_stop_all_queues(dev);
- phy_stop(dev->phydev);
+ phy_stop(priv->phydev);
bcmgenet_intr_disable(priv);
bcmgenet_disable_rx_napi(priv);
bcmgenet_disable_tx_napi(priv);
@@ -2958,7 +2963,7 @@
bcmgenet_netif_stop(dev);
/* Really kill the PHY state machine and disconnect from it */
- phy_disconnect(dev->phydev);
+ phy_disconnect(priv->phydev);
/* Disable MAC receive */
umac_enable_set(priv, CMD_RX_EN, false);
@@ -3517,7 +3522,7 @@
bcmgenet_netif_stop(dev);
- phy_suspend(dev->phydev);
+ phy_suspend(priv->phydev);
netif_device_detach(dev);
@@ -3581,7 +3586,7 @@
if (priv->wolopts)
clk_disable_unprepare(priv->clk_wol);
- phy_init_hw(dev->phydev);
+ phy_init_hw(priv->phydev);
/* Speed settings must be restored */
bcmgenet_mii_config(priv->dev);
@@ -3614,7 +3619,7 @@
netif_device_attach(dev);
- phy_resume(dev->phydev);
+ phy_resume(priv->phydev);
if (priv->eee.eee_enabled)
bcmgenet_eee_enable_set(dev, true);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 0f0868c..1e2dc34 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -597,6 +597,7 @@
/* MDIO bus variables */
wait_queue_head_t wq;
+ struct phy_device *phydev;
bool internal_phy;
struct device_node *phy_dn;
struct device_node *mdio_dn;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e907acd..457c3bc 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -86,7 +86,7 @@
void bcmgenet_mii_setup(struct net_device *dev)
{
struct bcmgenet_priv *priv = netdev_priv(dev);
- struct phy_device *phydev = dev->phydev;
+ struct phy_device *phydev = priv->phydev;
u32 reg, cmd_bits = 0;
bool status_changed = false;
@@ -183,9 +183,9 @@
if (GENET_IS_V4(priv))
return;
- if (dev->phydev) {
- phy_init_hw(dev->phydev);
- phy_start_aneg(dev->phydev);
+ if (priv->phydev) {
+ phy_init_hw(priv->phydev);
+ phy_start_aneg(priv->phydev);
}
}
@@ -236,7 +236,6 @@
static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
{
- struct net_device *ndev = priv->dev;
u32 reg;
/* Speed settings are set in bcmgenet_mii_setup() */
@@ -245,14 +244,14 @@
bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL);
if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
- fixed_phy_set_link_update(ndev->phydev,
+ fixed_phy_set_link_update(priv->phydev,
bcmgenet_fixed_phy_link_update);
}
int bcmgenet_mii_config(struct net_device *dev)
{
struct bcmgenet_priv *priv = netdev_priv(dev);
- struct phy_device *phydev = dev->phydev;
+ struct phy_device *phydev = priv->phydev;
struct device *kdev = &priv->pdev->dev;
const char *phy_name = NULL;
u32 id_mode_dis = 0;
@@ -303,7 +302,7 @@
* capabilities, use that knowledge to also configure the
* Reverse MII interface correctly.
*/
- if ((phydev->supported & PHY_BASIC_FEATURES) ==
+ if ((priv->phydev->supported & PHY_BASIC_FEATURES) ==
PHY_BASIC_FEATURES)
port_ctrl = PORT_MODE_EXT_RVMII_25;
else
@@ -372,7 +371,7 @@
return -ENODEV;
}
} else {
- phydev = dev->phydev;
+ phydev = priv->phydev;
phydev->dev_flags = phy_flags;
ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
@@ -383,6 +382,8 @@
}
}
+ priv->phydev = phydev;
+
/* Configure port multiplexer based on what the probed PHY device since
* reading the 'max-speed' property determines the maximum supported
* PHY speed which is needed for bcmgenet_mii_config() to configure
@@ -390,7 +391,7 @@
*/
ret = bcmgenet_mii_config(dev);
if (ret) {
- phy_disconnect(phydev);
+ phy_disconnect(priv->phydev);
return ret;
}
@@ -400,7 +401,7 @@
* Ethernet MAC ISRs
*/
if (priv->internal_phy)
- phydev->irq = PHY_IGNORE_INTERRUPT;
+ priv->phydev->irq = PHY_IGNORE_INTERRUPT;
return 0;
}
@@ -605,6 +606,7 @@
}
+ priv->phydev = phydev;
priv->phy_interface = pd->phy_interface;
return 0;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index a2551bc..ea967df 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -18122,14 +18122,14 @@
rtnl_lock();
- /* We needn't recover from permanent error */
- if (state == pci_channel_io_frozen)
- tp->pcierr_recovery = true;
-
/* We probably don't have netdev yet */
if (!netdev || !netif_running(netdev))
goto done;
+ /* We needn't recover from permanent error */
+ if (state == pci_channel_io_frozen)
+ tp->pcierr_recovery = true;
+
tg3_phy_stop(tp);
tg3_netif_stop(tp);
@@ -18226,7 +18226,7 @@
rtnl_lock();
- if (!netif_running(netdev))
+ if (!netdev || !netif_running(netdev))
goto done;
tg3_full_lock(tp, 0);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 01f7e81..692ee24 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -89,10 +89,10 @@
.driver_data = 0,
}, {
.name = "imx25-fec",
- .driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_HAS_RACC,
+ .driver_data = FEC_QUIRK_USE_GASKET,
}, {
.name = "imx27-fec",
- .driver_data = FEC_QUIRK_HAS_RACC,
+ .driver_data = 0,
}, {
.name = "imx28-fec",
.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
@@ -180,6 +180,7 @@
/* FEC receive acceleration */
#define FEC_RACC_IPDIS (1 << 1)
#define FEC_RACC_PRODIS (1 << 2)
+#define FEC_RACC_SHIFT16 BIT(7)
#define FEC_RACC_OPTIONS (FEC_RACC_IPDIS | FEC_RACC_PRODIS)
/*
@@ -945,9 +946,11 @@
#if !defined(CONFIG_M5272)
if (fep->quirks & FEC_QUIRK_HAS_RACC) {
- /* set RX checksum */
val = readl(fep->hwp + FEC_RACC);
+ /* align IP header */
+ val |= FEC_RACC_SHIFT16;
if (fep->csum_flags & FLAG_RX_CSUM_ENABLED)
+ /* set RX checksum */
val |= FEC_RACC_OPTIONS;
else
val &= ~FEC_RACC_OPTIONS;
@@ -1428,6 +1431,12 @@
prefetch(skb->data - NET_IP_ALIGN);
skb_put(skb, pkt_len - 4);
data = skb->data;
+
+#if !defined(CONFIG_M5272)
+ if (fep->quirks & FEC_QUIRK_HAS_RACC)
+ data = skb_pull_inline(skb, 2);
+#endif
+
if (!is_copybreak && need_swap)
swap_buffer(data, pkt_len);
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 715583f..4d7bbd2 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -99,8 +99,11 @@
nvdimm_map->size = size;
kref_init(&nvdimm_map->kref);
- if (!request_mem_region(offset, size, dev_name(&nvdimm_bus->dev)))
+ if (!request_mem_region(offset, size, dev_name(&nvdimm_bus->dev))) {
+ dev_err(&nvdimm_bus->dev, "failed to request %pa + %zd for %s\n",
+ &offset, size, dev_name(dev));
goto err_request_region;
+ }
if (flags)
nvdimm_map->mem = memremap(offset, size, flags);
@@ -171,6 +174,9 @@
kref_get(&nvdimm_map->kref);
nvdimm_bus_unlock(dev);
+ if (!nvdimm_map)
+ return NULL;
+
if (devm_add_action_or_reset(dev, nvdimm_map_put, nvdimm_map))
return NULL;
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 8024a0e..0b78a82 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -52,10 +52,28 @@
struct nd_region_data {
int ns_count;
int ns_active;
- unsigned int flush_mask;
- void __iomem *flush_wpq[0][0];
+ unsigned int hints_shift;
+ void __iomem *flush_wpq[0];
};
+static inline void __iomem *ndrd_get_flush_wpq(struct nd_region_data *ndrd,
+ int dimm, int hint)
+{
+ unsigned int num = 1 << ndrd->hints_shift;
+ unsigned int mask = num - 1;
+
+ return ndrd->flush_wpq[dimm * num + (hint & mask)];
+}
+
+static inline void ndrd_set_flush_wpq(struct nd_region_data *ndrd, int dimm,
+ int hint, void __iomem *flush)
+{
+ unsigned int num = 1 << ndrd->hints_shift;
+ unsigned int mask = num - 1;
+
+ ndrd->flush_wpq[dimm * num + (hint & mask)] = flush;
+}
+
static inline struct nd_namespace_index *to_namespace_index(
struct nvdimm_drvdata *ndd, int i)
{
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index e8d5ba7..4c0ac4a 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -38,7 +38,7 @@
dev_dbg(dev, "%s: map %d flush address%s\n", nvdimm_name(nvdimm),
nvdimm->num_flush, nvdimm->num_flush == 1 ? "" : "es");
- for (i = 0; i < nvdimm->num_flush; i++) {
+ for (i = 0; i < (1 << ndrd->hints_shift); i++) {
struct resource *res = &nvdimm->flush_wpq[i];
unsigned long pfn = PHYS_PFN(res->start);
void __iomem *flush_page;
@@ -54,14 +54,15 @@
if (j < i)
flush_page = (void __iomem *) ((unsigned long)
- ndrd->flush_wpq[dimm][j] & PAGE_MASK);
+ ndrd_get_flush_wpq(ndrd, dimm, j)
+ & PAGE_MASK);
else
flush_page = devm_nvdimm_ioremap(dev,
- PHYS_PFN(pfn), PAGE_SIZE);
+ PFN_PHYS(pfn), PAGE_SIZE);
if (!flush_page)
return -ENXIO;
- ndrd->flush_wpq[dimm][i] = flush_page
- + (res->start & ~PAGE_MASK);
+ ndrd_set_flush_wpq(ndrd, dimm, i, flush_page
+ + (res->start & ~PAGE_MASK));
}
return 0;
@@ -93,7 +94,10 @@
return -ENOMEM;
dev_set_drvdata(dev, ndrd);
- ndrd->flush_mask = (1 << ilog2(num_flush)) - 1;
+ if (!num_flush)
+ return 0;
+
+ ndrd->hints_shift = ilog2(num_flush);
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
struct nvdimm *nvdimm = nd_mapping->nvdimm;
@@ -900,8 +904,8 @@
*/
wmb();
for (i = 0; i < nd_region->ndr_mappings; i++)
- if (ndrd->flush_wpq[i][0])
- writeq(1, ndrd->flush_wpq[i][idx & ndrd->flush_mask]);
+ if (ndrd_get_flush_wpq(ndrd, i, 0))
+ writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));
wmb();
}
EXPORT_SYMBOL_GPL(nvdimm_flush);
@@ -925,7 +929,7 @@
for (i = 0; i < nd_region->ndr_mappings; i++)
/* flush hints present, flushing required */
- if (ndrd->flush_wpq[i][0])
+ if (ndrd_get_flush_wpq(ndrd, i, 0))
return 1;
/*
diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c
index ed5a097..f63d4b0d 100644
--- a/drivers/of/of_numa.c
+++ b/drivers/of/of_numa.c
@@ -16,6 +16,8 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#define pr_fmt(fmt) "OF: NUMA: " fmt
+
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/nodemask.h>
@@ -49,10 +51,9 @@
if (r)
continue;
- pr_debug("NUMA: CPU on %u\n", nid);
+ pr_debug("CPU on %u\n", nid);
if (nid >= MAX_NUMNODES)
- pr_warn("NUMA: Node id %u exceeds maximum value\n",
- nid);
+ pr_warn("Node id %u exceeds maximum value\n", nid);
else
node_set(nid, numa_nodes_parsed);
}
@@ -63,13 +64,9 @@
struct device_node *np = NULL;
struct resource rsrc;
u32 nid;
- int r = 0;
+ int i, r;
- for (;;) {
- np = of_find_node_by_type(np, "memory");
- if (!np)
- break;
-
+ for_each_node_by_type(np, "memory") {
r = of_property_read_u32(np, "numa-node-id", &nid);
if (r == -EINVAL)
/*
@@ -78,27 +75,23 @@
* "numa-node-id" property
*/
continue;
- else if (r)
- /* some other error */
- break;
- r = of_address_to_resource(np, 0, &rsrc);
- if (r) {
- pr_err("NUMA: bad reg property in memory node\n");
- break;
+ if (nid >= MAX_NUMNODES) {
+ pr_warn("Node id %u exceeds maximum value\n", nid);
+ r = -EINVAL;
}
- pr_debug("NUMA: base = %llx len = %llx, node = %u\n",
- rsrc.start, rsrc.end - rsrc.start + 1, nid);
+ for (i = 0; !r && !of_address_to_resource(np, i, &rsrc); i++)
+ r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
-
- r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
- if (r)
- break;
+ if (!i || r) {
+ of_node_put(np);
+ pr_err("bad property in memory node\n");
+ return r ? : -EINVAL;
+ }
}
- of_node_put(np);
- return r;
+ return 0;
}
static int __init of_numa_parse_distance_map_v1(struct device_node *map)
@@ -107,17 +100,17 @@
int entry_count;
int i;
- pr_info("NUMA: parsing numa-distance-map-v1\n");
+ pr_info("parsing numa-distance-map-v1\n");
matrix = of_get_property(map, "distance-matrix", NULL);
if (!matrix) {
- pr_err("NUMA: No distance-matrix property in distance-map\n");
+ pr_err("No distance-matrix property in distance-map\n");
return -EINVAL;
}
entry_count = of_property_count_u32_elems(map, "distance-matrix");
if (entry_count <= 0) {
- pr_err("NUMA: Invalid distance-matrix\n");
+ pr_err("Invalid distance-matrix\n");
return -EINVAL;
}
@@ -132,7 +125,7 @@
matrix++;
numa_set_distance(nodea, nodeb, distance);
- pr_debug("NUMA: distance[node%d -> node%d] = %d\n",
+ pr_debug("distance[node%d -> node%d] = %d\n",
nodea, nodeb, distance);
/* Set default distance of node B->A same as A->B */
@@ -166,8 +159,6 @@
np = of_node_get(device);
while (np) {
- struct device_node *parent;
-
r = of_property_read_u32(np, "numa-node-id", &nid);
/*
* -EINVAL indicates the property was not found, and
@@ -178,22 +169,15 @@
if (r != -EINVAL)
break;
- parent = of_get_parent(np);
- of_node_put(np);
- np = parent;
+ np = of_get_next_parent(np);
}
if (np && r)
- pr_warn("NUMA: Invalid \"numa-node-id\" property in node %s\n",
+ pr_warn("Invalid \"numa-node-id\" property in node %s\n",
np->name);
of_node_put(np);
- if (!r) {
- if (nid >= MAX_NUMNODES)
- pr_warn("NUMA: Node id %u exceeds maximum value\n",
- nid);
- else
- return nid;
- }
+ if (!r)
+ return nid;
return NUMA_NO_NODE;
}
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f5e1008..3037081 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -534,6 +534,24 @@
return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
}
+static ssize_t armpmu_cpumask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev));
+ return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus);
+}
+
+static DEVICE_ATTR(cpus, S_IRUGO, armpmu_cpumask_show, NULL);
+
+static struct attribute *armpmu_common_attrs[] = {
+ &dev_attr_cpus.attr,
+ NULL,
+};
+
+static struct attribute_group armpmu_common_attr_group = {
+ .attrs = armpmu_common_attrs,
+};
+
static void armpmu_init(struct arm_pmu *armpmu)
{
atomic_set(&armpmu->active_events, 0);
@@ -549,7 +567,10 @@
.stop = armpmu_stop,
.read = armpmu_read,
.filter_match = armpmu_filter_match,
+ .attr_groups = armpmu->attr_groups,
};
+ armpmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] =
+ &armpmu_common_attr_group;
}
/* Set at runtime when we know what CPU type we are. */
@@ -602,7 +623,7 @@
irqs = min(pmu_device->num_resources, num_possible_cpus());
irq = platform_get_irq(pmu_device, 0);
- if (irq >= 0 && irq_is_percpu(irq)) {
+ if (irq > 0 && irq_is_percpu(irq)) {
on_each_cpu_mask(&cpu_pmu->supported_cpus,
cpu_pmu_disable_percpu_irq, &irq, 1);
free_percpu_irq(irq, &hw_events->percpu_pmu);
@@ -616,7 +637,7 @@
if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
continue;
irq = platform_get_irq(pmu_device, i);
- if (irq >= 0)
+ if (irq > 0)
free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
}
}
@@ -638,7 +659,7 @@
}
irq = platform_get_irq(pmu_device, 0);
- if (irq >= 0 && irq_is_percpu(irq)) {
+ if (irq > 0 && irq_is_percpu(irq)) {
err = request_percpu_irq(irq, handler, "arm-pmu",
&hw_events->percpu_pmu);
if (err) {
@@ -919,7 +940,7 @@
/* Check the IRQ type and prohibit a mix of PPIs and SPIs */
irq = platform_get_irq(pdev, i);
- if (irq >= 0) {
+ if (irq > 0) {
bool spi = !irq_is_percpu(irq);
if (i > 0 && spi != using_spi) {
@@ -970,7 +991,7 @@
if (cpumask_weight(&pmu->supported_cpus) == 0) {
int irq = platform_get_irq(pdev, 0);
- if (irq >= 0 && irq_is_percpu(irq)) {
+ if (irq > 0 && irq_is_percpu(irq)) {
/* If using PPIs, check the affinity of the partition */
int ret;
@@ -1029,7 +1050,7 @@
ret = of_pmu_irq_cfg(pmu);
if (!ret)
ret = init_fn(pmu);
- } else {
+ } else if (probe_table) {
cpumask_setall(&pmu->supported_cpus);
ret = probe_current_pmu(pmu, probe_table);
}
@@ -1039,6 +1060,7 @@
goto out_free;
}
+
ret = cpu_pmu_init(pmu);
if (ret)
goto out_free;
diff --git a/drivers/power/avs/smartreflex.c b/drivers/power/avs/smartreflex.c
index db9973b..fa0f19b 100644
--- a/drivers/power/avs/smartreflex.c
+++ b/drivers/power/avs/smartreflex.c
@@ -136,7 +136,7 @@
if (IS_ERR(fck)) {
dev_err(&sr->pdev->dev, "%s: unable to get fck for device %s\n",
- __func__, dev_name(&sr->pdev->dev));
+ __func__, dev_name(&sr->pdev->dev));
return;
}
@@ -170,8 +170,8 @@
{
if (!sr_class || !(sr_class->enable) || !(sr_class->configure)) {
dev_warn(&sr->pdev->dev,
- "%s: smartreflex class driver not registered\n",
- __func__);
+ "%s: smartreflex class driver not registered\n",
+ __func__);
return;
}
@@ -183,8 +183,8 @@
{
if (!sr_class || !(sr_class->disable)) {
dev_warn(&sr->pdev->dev,
- "%s: smartreflex class driver not registered\n",
- __func__);
+ "%s: smartreflex class driver not registered\n",
+ __func__);
return;
}
@@ -225,9 +225,8 @@
error:
list_del(&sr_info->node);
- dev_err(&sr_info->pdev->dev, "%s: ERROR in registering"
- "interrupt handler. Smartreflex will"
- "not function as desired\n", __func__);
+ dev_err(&sr_info->pdev->dev, "%s: ERROR in registering interrupt handler. Smartreflex will not function as desired\n",
+ __func__);
return ret;
}
@@ -263,7 +262,7 @@
if (timeout >= SR_DISABLE_TIMEOUT)
dev_warn(&sr->pdev->dev, "%s: Smartreflex disable timedout\n",
- __func__);
+ __func__);
/* Disable MCUDisableAcknowledge interrupt & clear pending interrupt */
sr_modify_reg(sr, ERRCONFIG_V1, ERRCONFIG_MCUDISACKINTEN,
@@ -308,7 +307,7 @@
if (timeout >= SR_DISABLE_TIMEOUT)
dev_warn(&sr->pdev->dev, "%s: Smartreflex disable timedout\n",
- __func__);
+ __func__);
/* Disable MCUDisableAcknowledge interrupt & clear pending interrupt */
sr_write_reg(sr, IRQENABLE_CLR, IRQENABLE_MCUDISABLEACKINT);
@@ -322,7 +321,7 @@
if (!sr->nvalue_table) {
dev_warn(&sr->pdev->dev, "%s: Missing ntarget value table\n",
- __func__);
+ __func__);
return NULL;
}
@@ -356,8 +355,8 @@
u8 senp_shift, senn_shift;
if (!sr) {
- pr_warn("%s: NULL omap_sr from %pF\n", __func__,
- (void *)_RET_IP_);
+ pr_warn("%s: NULL omap_sr from %pF\n",
+ __func__, (void *)_RET_IP_);
return -EINVAL;
}
@@ -387,8 +386,8 @@
vpboundint_st = ERRCONFIG_VPBOUNDINTST_V2;
break;
default:
- dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex"
- "module without specifying the ip\n", __func__);
+ dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex module without specifying the ip\n",
+ __func__);
return -EINVAL;
}
@@ -423,8 +422,8 @@
u32 vpboundint_en, vpboundint_st;
if (!sr) {
- pr_warn("%s: NULL omap_sr from %pF\n", __func__,
- (void *)_RET_IP_);
+ pr_warn("%s: NULL omap_sr from %pF\n",
+ __func__, (void *)_RET_IP_);
return -EINVAL;
}
@@ -440,8 +439,8 @@
vpboundint_st = ERRCONFIG_VPBOUNDINTST_V2;
break;
default:
- dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex"
- "module without specifying the ip\n", __func__);
+ dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex module without specifying the ip\n",
+ __func__);
return -EINVAL;
}
@@ -478,8 +477,8 @@
u8 senp_shift, senn_shift;
if (!sr) {
- pr_warn("%s: NULL omap_sr from %pF\n", __func__,
- (void *)_RET_IP_);
+ pr_warn("%s: NULL omap_sr from %pF\n",
+ __func__, (void *)_RET_IP_);
return -EINVAL;
}
@@ -504,8 +503,8 @@
senp_shift = SRCONFIG_SENPENABLE_V2_SHIFT;
break;
default:
- dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex"
- "module without specifying the ip\n", __func__);
+ dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex module without specifying the ip\n",
+ __func__);
return -EINVAL;
}
@@ -537,8 +536,8 @@
IRQENABLE_MCUBOUNDSINT | IRQENABLE_MCUDISABLEACKINT);
break;
default:
- dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex"
- "module without specifying the ip\n", __func__);
+ dev_err(&sr->pdev->dev, "%s: Trying to Configure smartreflex module without specifying the ip\n",
+ __func__);
return -EINVAL;
}
@@ -563,16 +562,16 @@
int ret;
if (!sr) {
- pr_warn("%s: NULL omap_sr from %pF\n", __func__,
- (void *)_RET_IP_);
+ pr_warn("%s: NULL omap_sr from %pF\n",
+ __func__, (void *)_RET_IP_);
return -EINVAL;
}
volt_data = omap_voltage_get_voltdata(sr->voltdm, volt);
if (IS_ERR(volt_data)) {
- dev_warn(&sr->pdev->dev, "%s: Unable to get voltage table"
- "for nominal voltage %ld\n", __func__, volt);
+ dev_warn(&sr->pdev->dev, "%s: Unable to get voltage table for nominal voltage %ld\n",
+ __func__, volt);
return PTR_ERR(volt_data);
}
@@ -615,8 +614,8 @@
void sr_disable(struct omap_sr *sr)
{
if (!sr) {
- pr_warn("%s: NULL omap_sr from %pF\n", __func__,
- (void *)_RET_IP_);
+ pr_warn("%s: NULL omap_sr from %pF\n",
+ __func__, (void *)_RET_IP_);
return;
}
@@ -658,13 +657,13 @@
struct omap_sr *sr_info;
if (!class_data) {
- pr_warning("%s:, Smartreflex class data passed is NULL\n",
+ pr_warn("%s:, Smartreflex class data passed is NULL\n",
__func__);
return -EINVAL;
}
if (sr_class) {
- pr_warning("%s: Smartreflex class driver already registered\n",
+ pr_warn("%s: Smartreflex class driver already registered\n",
__func__);
return -EBUSY;
}
@@ -696,7 +695,7 @@
struct omap_sr *sr = _sr_lookup(voltdm);
if (IS_ERR(sr)) {
- pr_warning("%s: omap_sr struct for voltdm not found\n", __func__);
+ pr_warn("%s: omap_sr struct for voltdm not found\n", __func__);
return;
}
@@ -704,8 +703,8 @@
return;
if (!sr_class || !(sr_class->enable) || !(sr_class->configure)) {
- dev_warn(&sr->pdev->dev, "%s: smartreflex class driver not"
- "registered\n", __func__);
+ dev_warn(&sr->pdev->dev, "%s: smartreflex class driver not registered\n",
+ __func__);
return;
}
@@ -728,7 +727,7 @@
struct omap_sr *sr = _sr_lookup(voltdm);
if (IS_ERR(sr)) {
- pr_warning("%s: omap_sr struct for voltdm not found\n", __func__);
+ pr_warn("%s: omap_sr struct for voltdm not found\n", __func__);
return;
}
@@ -736,8 +735,8 @@
return;
if (!sr_class || !(sr_class->disable)) {
- dev_warn(&sr->pdev->dev, "%s: smartreflex class driver not"
- "registered\n", __func__);
+ dev_warn(&sr->pdev->dev, "%s: smartreflex class driver not registered\n",
+ __func__);
return;
}
@@ -760,7 +759,7 @@
struct omap_sr *sr = _sr_lookup(voltdm);
if (IS_ERR(sr)) {
- pr_warning("%s: omap_sr struct for voltdm not found\n", __func__);
+ pr_warn("%s: omap_sr struct for voltdm not found\n", __func__);
return;
}
@@ -768,8 +767,8 @@
return;
if (!sr_class || !(sr_class->disable)) {
- dev_warn(&sr->pdev->dev, "%s: smartreflex class driver not"
- "registered\n", __func__);
+ dev_warn(&sr->pdev->dev, "%s: smartreflex class driver not registered\n",
+ __func__);
return;
}
@@ -787,8 +786,8 @@
void omap_sr_register_pmic(struct omap_sr_pmic_data *pmic_data)
{
if (!pmic_data) {
- pr_warning("%s: Trying to register NULL PMIC data structure"
- "with smartreflex\n", __func__);
+ pr_warn("%s: Trying to register NULL PMIC data structure with smartreflex\n",
+ __func__);
return;
}
@@ -801,7 +800,7 @@
struct omap_sr *sr_info = data;
if (!sr_info) {
- pr_warning("%s: omap_sr struct not found\n", __func__);
+ pr_warn("%s: omap_sr struct not found\n", __func__);
return -EINVAL;
}
@@ -815,13 +814,13 @@
struct omap_sr *sr_info = data;
if (!sr_info) {
- pr_warning("%s: omap_sr struct not found\n", __func__);
+ pr_warn("%s: omap_sr struct not found\n", __func__);
return -EINVAL;
}
/* Sanity check */
if (val > 1) {
- pr_warning("%s: Invalid argument %lld\n", __func__, val);
+ pr_warn("%s: Invalid argument %lld\n", __func__, val);
return -EINVAL;
}
@@ -848,19 +847,13 @@
int i, ret = 0;
sr_info = devm_kzalloc(&pdev->dev, sizeof(struct omap_sr), GFP_KERNEL);
- if (!sr_info) {
- dev_err(&pdev->dev, "%s: unable to allocate sr_info\n",
- __func__);
+ if (!sr_info)
return -ENOMEM;
- }
sr_info->name = devm_kzalloc(&pdev->dev,
SMARTREFLEX_NAME_LEN, GFP_KERNEL);
- if (!sr_info->name) {
- dev_err(&pdev->dev, "%s: unable to allocate SR instance name\n",
- __func__);
+ if (!sr_info->name)
return -ENOMEM;
- }
platform_set_drvdata(pdev, sr_info);
@@ -912,7 +905,7 @@
if (sr_class) {
ret = sr_late_init(sr_info);
if (ret) {
- pr_warning("%s: Error in SR late init\n", __func__);
+ pr_warn("%s: Error in SR late init\n", __func__);
goto err_list_del;
}
}
@@ -923,7 +916,7 @@
if (IS_ERR_OR_NULL(sr_dbg_dir)) {
ret = PTR_ERR(sr_dbg_dir);
pr_err("%s:sr debugfs dir creation failed(%d)\n",
- __func__, ret);
+ __func__, ret);
goto err_list_del;
}
}
@@ -945,8 +938,8 @@
nvalue_dir = debugfs_create_dir("nvalue", sr_info->dbg_dir);
if (IS_ERR_OR_NULL(nvalue_dir)) {
- dev_err(&pdev->dev, "%s: Unable to create debugfs directory"
- "for n-values\n", __func__);
+ dev_err(&pdev->dev, "%s: Unable to create debugfs directory for n-values\n",
+ __func__);
ret = PTR_ERR(nvalue_dir);
goto err_debugfs;
}
@@ -1053,12 +1046,12 @@
if (sr_pmic_data && sr_pmic_data->sr_pmic_init)
sr_pmic_data->sr_pmic_init();
else
- pr_warning("%s: No PMIC hook to init smartreflex\n", __func__);
+ pr_warn("%s: No PMIC hook to init smartreflex\n", __func__);
ret = platform_driver_probe(&smartreflex_driver, omap_sr_probe);
if (ret) {
pr_err("%s: platform driver register failed for SR\n",
- __func__);
+ __func__);
return ret;
}
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index ba9af4a..ec6381e 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -486,6 +486,8 @@
else
shost->dma_boundary = 0xffffffff;
+ shost->use_blk_mq = scsi_use_blk_mq;
+
device_initialize(&shost->shost_gendev);
dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
shost->shost_gendev.bus = &scsi_bus_type;
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 1f36aca..1deb6ad 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -1160,7 +1160,6 @@
bool scsi_use_blk_mq = false;
#endif
module_param_named(use_blk_mq, scsi_use_blk_mq, bool, S_IWUSR | S_IRUGO);
-EXPORT_SYMBOL_GPL(scsi_use_blk_mq);
static int __init init_scsi(void)
{
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 57a4b99..85c8a51 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -29,6 +29,7 @@
extern void scsi_exit_hosts(void);
/* scsi.c */
+extern bool scsi_use_blk_mq;
extern int scsi_setup_command_freelist(struct Scsi_Host *shost);
extern void scsi_destroy_command_freelist(struct Scsi_Host *shost);
#ifdef CONFIG_SCSI_LOGGING
diff --git a/drivers/soc/samsung/pm_domains.c b/drivers/soc/samsung/pm_domains.c
index 4822346..7112004 100644
--- a/drivers/soc/samsung/pm_domains.c
+++ b/drivers/soc/samsung/pm_domains.c
@@ -215,29 +215,22 @@
/* Assign the child power domains to their parents */
for_each_matching_node(np, exynos_pm_domain_of_match) {
- struct generic_pm_domain *child_domain, *parent_domain;
- struct of_phandle_args args;
+ struct of_phandle_args child, parent;
- args.np = np;
- args.args_count = 0;
- child_domain = of_genpd_get_from_provider(&args);
- if (IS_ERR(child_domain))
- continue;
+ child.np = np;
+ child.args_count = 0;
if (of_parse_phandle_with_args(np, "power-domains",
- "#power-domain-cells", 0, &args) != 0)
+ "#power-domain-cells", 0,
+ &parent) != 0)
continue;
- parent_domain = of_genpd_get_from_provider(&args);
- if (IS_ERR(parent_domain))
- continue;
-
- if (pm_genpd_add_subdomain(parent_domain, child_domain))
+ if (of_genpd_add_subdomain(&parent, &child))
pr_warn("%s failed to add subdomain: %s\n",
- parent_domain->name, child_domain->name);
+ parent.np->name, child.np->name);
else
pr_info("%s has as child subdomain: %s.\n",
- parent_domain->name, child_domain->name);
+ parent.np->name, child.np->name);
}
return 0;
diff --git a/drivers/staging/board/board.c b/drivers/staging/board/board.c
index 45807d8..86dc411 100644
--- a/drivers/staging/board/board.c
+++ b/drivers/staging/board/board.c
@@ -140,7 +140,6 @@
const char *domain)
{
struct of_phandle_args pd_args;
- struct generic_pm_domain *pd;
struct device_node *np;
np = of_find_node_by_path(domain);
@@ -151,14 +150,8 @@
pd_args.np = np;
pd_args.args_count = 0;
- pd = of_genpd_get_from_provider(&pd_args);
- if (IS_ERR(pd)) {
- pr_err("Cannot find genpd %s (%ld)\n", domain, PTR_ERR(pd));
- return PTR_ERR(pd);
- }
- pr_debug("Found genpd %s for device %s\n", pd->name, pdev->name);
- return pm_genpd_add_device(pd, &pdev->dev);
+ return of_genpd_add_device(&pd_args, &pdev->dev);
}
#else
static inline int board_staging_add_dev_domain(struct platform_device *pdev,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 98d3654..bbb4b3e 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1842,6 +1842,16 @@
ocfs2_commit_trans(osb, handle);
out:
+ /*
+ * The mmapped page won't be unlocked in ocfs2_free_write_ctxt(),
+ * even in case of error here like ENOSPC and ENOMEM. So, we need
+ * to unlock the target page manually to prevent deadlocks when
+ * retrying again on ENOSPC, or when returning non-VM_FAULT_LOCKED
+ * to VM code.
+ */
+ if (wc->w_target_locked)
+ unlock_page(mmap_page);
+
ocfs2_free_write_ctxt(inode, wc);
if (data_ac) {
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 5261751..5f52709 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -32,6 +32,7 @@
* CAN common private data
*/
struct can_priv {
+ struct net_device *dev;
struct can_device_stats can_stats;
struct can_bittiming bittiming, data_bittiming;
@@ -47,7 +48,7 @@
u32 ctrlmode_static; /* static enabled options for driver/hardware */
int restart_ms;
- struct timer_list restart_timer;
+ struct delayed_work restart_work;
int (*do_set_bittiming)(struct net_device *dev);
int (*do_set_data_bittiming)(struct net_device *dev);
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 797d9c8..ad4f1f3 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -228,7 +228,11 @@
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_PM_SLEEP_SMP
-extern int disable_nonboot_cpus(void);
+extern int freeze_secondary_cpus(int primary);
+static inline int disable_nonboot_cpus(void)
+{
+ return freeze_secondary_cpus(0);
+}
extern void enable_nonboot_cpus(void);
#else /* !CONFIG_PM_SLEEP_SMP */
static inline int disable_nonboot_cpus(void) { return 0; }
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 34bd805..eb445a4 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -47,6 +47,8 @@
CPUHP_AP_PERF_METAG_STARTING,
CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
CPUHP_AP_ARM_VFP_STARTING,
+ CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
+ CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
CPUHP_AP_PERF_ARM_STARTING,
CPUHP_AP_ARM_L2X0_STARTING,
CPUHP_AP_ARM_ARCH_TIMER_STARTING,
diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h
index 0a83a1e..4db00b0 100644
--- a/include/linux/devfreq-event.h
+++ b/include/linux/devfreq-event.h
@@ -148,11 +148,6 @@
return -EINVAL;
}
-static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev)
-{
- return ERR_PTR(-EINVAL);
-}
-
static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
struct device *dev, int index)
{
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 66533e1..dc69df0 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -718,7 +718,7 @@
#define dma_mmap_writecombine dma_mmap_wc
#endif
-#ifdef CONFIG_NEED_DMA_MAP_STATE
+#if defined(CONFIG_NEED_DMA_MAP_STATE) || defined(CONFIG_DMA_API_DEBUG)
#define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME
#define DEFINE_DMA_UNMAP_LEN(LEN_NAME) __u32 LEN_NAME
#define dma_unmap_addr(PTR, ADDR_NAME) ((PTR)->ADDR_NAME)
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 661af56..a534c7f 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -21,6 +21,8 @@
*
* DEFINE_STATIC_KEY_TRUE(key);
* DEFINE_STATIC_KEY_FALSE(key);
+ * DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+ * DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
* static_branch_likely()
* static_branch_unlikely()
*
@@ -270,6 +272,16 @@
#define DEFINE_STATIC_KEY_FALSE(name) \
struct static_key_false name = STATIC_KEY_FALSE_INIT
+#define DEFINE_STATIC_KEY_ARRAY_TRUE(name, count) \
+ struct static_key_true name[count] = { \
+ [0 ... (count) - 1] = STATIC_KEY_TRUE_INIT, \
+ }
+
+#define DEFINE_STATIC_KEY_ARRAY_FALSE(name, count) \
+ struct static_key_false name[count] = { \
+ [0 ... (count) - 1] = STATIC_KEY_FALSE_INIT, \
+ }
+
extern bool ____wrong_branch_error(void);
#define static_key_enabled(x) \
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index d351fd3..e5fb813 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -120,5 +120,5 @@
struct rtmsg;
int ipmr_get_route(struct net *net, struct sk_buff *skb,
__be32 saddr, __be32 daddr,
- struct rtmsg *rtm, int nowait);
+ struct rtmsg *rtm, int nowait, u32 portid);
#endif
diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index 3987b64..19a1c0c 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -116,7 +116,7 @@
struct rtmsg;
extern int ip6mr_get_route(struct net *net, struct sk_buff *skb,
- struct rtmsg *rtm, int nowait);
+ struct rtmsg *rtm, int nowait, u32 portid);
#ifdef CONFIG_IPV6_MROUTE
extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb);
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index e188438..9ff07d3 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -14,7 +14,7 @@
#include <linux/interrupt.h>
#include <linux/perf_event.h>
-
+#include <linux/sysfs.h>
#include <asm/cputype.h>
/*
@@ -77,6 +77,13 @@
struct arm_pmu *percpu_pmu;
};
+enum armpmu_attr_groups {
+ ARMPMU_ATTR_GROUP_COMMON,
+ ARMPMU_ATTR_GROUP_EVENTS,
+ ARMPMU_ATTR_GROUP_FORMATS,
+ ARMPMU_NR_ATTR_GROUPS
+};
+
struct arm_pmu {
struct pmu pmu;
cpumask_t active_irqs;
@@ -111,6 +118,8 @@
struct pmu_hw_events __percpu *hw_events;
struct list_head entry;
struct notifier_block cpu_pm_nb;
+ /* the attr_groups array must be NULL-terminated */
+ const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1];
};
#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
@@ -151,6 +160,8 @@
const struct of_device_id *of_table,
const struct pmu_probe_info *probe_table);
+#define ARMV8_PMU_PDEV_NAME "armv8-pmu"
+
#endif /* CONFIG_ARM_PMU */
#endif /* __ARM_PMU_H__ */
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 31fec85..a09fe5c 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -51,6 +51,8 @@
struct mutex lock;
struct dev_power_governor *gov;
struct work_struct power_off_work;
+ struct fwnode_handle *provider; /* Identity of the domain provider */
+ bool has_provider;
const char *name;
atomic_t sd_count; /* Number of subdomains with power "on" */
enum gpd_status status; /* Current state of the domain */
@@ -116,7 +118,6 @@
return to_gpd_data(dev->power.subsys_data->domain_data);
}
-extern struct generic_pm_domain *pm_genpd_lookup_dev(struct device *dev);
extern int __pm_genpd_add_device(struct generic_pm_domain *genpd,
struct device *dev,
struct gpd_timing_data *td);
@@ -129,6 +130,7 @@
struct generic_pm_domain *target);
extern int pm_genpd_init(struct generic_pm_domain *genpd,
struct dev_power_governor *gov, bool is_off);
+extern int pm_genpd_remove(struct generic_pm_domain *genpd);
extern struct dev_power_governor simple_qos_governor;
extern struct dev_power_governor pm_domain_always_on_gov;
@@ -138,10 +140,6 @@
{
return ERR_PTR(-ENOSYS);
}
-static inline struct generic_pm_domain *pm_genpd_lookup_dev(struct device *dev)
-{
- return NULL;
-}
static inline int __pm_genpd_add_device(struct generic_pm_domain *genpd,
struct device *dev,
struct gpd_timing_data *td)
@@ -168,6 +166,10 @@
{
return -ENOSYS;
}
+static inline int pm_genpd_remove(struct generic_pm_domain *genpd)
+{
+ return -ENOTSUPP;
+}
#endif
static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
@@ -192,57 +194,57 @@
unsigned int num_domains;
};
-typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
- void *data);
-
#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
-int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
- void *data);
+int of_genpd_add_provider_simple(struct device_node *np,
+ struct generic_pm_domain *genpd);
+int of_genpd_add_provider_onecell(struct device_node *np,
+ struct genpd_onecell_data *data);
void of_genpd_del_provider(struct device_node *np);
-struct generic_pm_domain *of_genpd_get_from_provider(
- struct of_phandle_args *genpdspec);
-
-struct generic_pm_domain *__of_genpd_xlate_simple(
- struct of_phandle_args *genpdspec,
- void *data);
-struct generic_pm_domain *__of_genpd_xlate_onecell(
- struct of_phandle_args *genpdspec,
- void *data);
+extern int of_genpd_add_device(struct of_phandle_args *args,
+ struct device *dev);
+extern int of_genpd_add_subdomain(struct of_phandle_args *parent,
+ struct of_phandle_args *new_subdomain);
+extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
int genpd_dev_pm_attach(struct device *dev);
#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
-static inline int __of_genpd_add_provider(struct device_node *np,
- genpd_xlate_t xlate, void *data)
+static inline int of_genpd_add_provider_simple(struct device_node *np,
+ struct generic_pm_domain *genpd)
{
- return 0;
+ return -ENOTSUPP;
}
+
+static inline int of_genpd_add_provider_onecell(struct device_node *np,
+ struct genpd_onecell_data *data)
+{
+ return -ENOTSUPP;
+}
+
static inline void of_genpd_del_provider(struct device_node *np) {}
-static inline struct generic_pm_domain *of_genpd_get_from_provider(
- struct of_phandle_args *genpdspec)
+static inline int of_genpd_add_device(struct of_phandle_args *args,
+ struct device *dev)
{
- return NULL;
+ return -ENODEV;
}
-#define __of_genpd_xlate_simple NULL
-#define __of_genpd_xlate_onecell NULL
+static inline int of_genpd_add_subdomain(struct of_phandle_args *parent,
+ struct of_phandle_args *new_subdomain)
+{
+ return -ENODEV;
+}
static inline int genpd_dev_pm_attach(struct device *dev)
{
return -ENODEV;
}
-#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
-static inline int of_genpd_add_provider_simple(struct device_node *np,
- struct generic_pm_domain *genpd)
+static inline
+struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
{
- return __of_genpd_add_provider(np, __of_genpd_xlate_simple, genpd);
+ return ERR_PTR(-ENOTSUPP);
}
-static inline int of_genpd_add_provider_onecell(struct device_node *np,
- struct genpd_onecell_data *data)
-{
- return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data);
-}
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
#ifdef CONFIG_PM
extern int dev_pm_domain_attach(struct device *dev, bool power_on);
diff --git a/include/linux/property.h b/include/linux/property.h
index 3a2f9ae..856e50b 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -190,7 +190,7 @@
.length = ARRAY_SIZE(_val_) * sizeof(_type_), \
.is_array = true, \
.is_string = false, \
- { .pointer = { _type_##_data = _val_ } }, \
+ { .pointer = { ._type_##_data = _val_ } }, \
}
#define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 62c68e5..98fe95f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3469,15 +3469,20 @@
return task_rlimit_max(current, limit);
}
+#define SCHED_CPUFREQ_RT (1U << 0)
+#define SCHED_CPUFREQ_DL (1U << 1)
+#define SCHED_CPUFREQ_IOWAIT (1U << 2)
+
+#define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL)
+
#ifdef CONFIG_CPU_FREQ
struct update_util_data {
- void (*func)(struct update_util_data *data,
- u64 time, unsigned long util, unsigned long max);
+ void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
};
void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
- void (*func)(struct update_util_data *data, u64 time,
- unsigned long util, unsigned long max));
+ void (*func)(struct update_util_data *data, u64 time,
+ unsigned int flags));
void cpufreq_remove_update_util_hook(int cpu);
#endif /* CONFIG_CPU_FREQ */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 7693e39..d971837 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -245,6 +245,7 @@
return unlikely(suspend_freeze_state == FREEZE_STATE_ENTER);
}
+extern void __init pm_states_init(void);
extern void freeze_set_ops(const struct platform_freeze_ops *ops);
extern void freeze_wake(void);
@@ -279,6 +280,7 @@
static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {}
static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; }
static inline bool idle_should_freeze(void) { return false; }
+static inline void __init pm_states_init(void) {}
static inline void freeze_set_ops(const struct platform_freeze_ops *ops) {}
static inline void freeze_wake(void) {}
#endif /* !CONFIG_SUSPEND */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b17cc48..4a529c9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -257,6 +257,7 @@
static inline void workingset_node_pages_dec(struct radix_tree_node *node)
{
+ VM_BUG_ON(!workingset_node_pages(node));
node->count--;
}
@@ -272,6 +273,7 @@
static inline void workingset_node_shadows_dec(struct radix_tree_node *node)
{
+ VM_BUG_ON(!workingset_node_shadows(node));
node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
}
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ce93c4b..ced0df3 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -554,6 +554,9 @@
atomic_t refcnt;
+ /* How many times this chunk have been sent, for prsctp RTX policy */
+ int sent_count;
+
/* This is our link to the per-transport transmitted list. */
struct list_head transmitted_list;
@@ -603,16 +606,6 @@
/* This needs to be recoverable for SCTP_SEND_FAILED events. */
struct sctp_sndrcvinfo sinfo;
- /* We use this field to record param for prsctp policies,
- * for TTL policy, it is the time_to_drop of this chunk,
- * for RTX policy, it is the max_sent_count of this chunk,
- * for PRIO policy, it is the priority of this chunk.
- */
- unsigned long prsctp_param;
-
- /* How many times this chunk have been sent, for prsctp RTX policy */
- int sent_count;
-
/* Which association does this belong to? */
struct sctp_association *asoc;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 0dee7af..7e4cd53 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -771,12 +771,9 @@
shost->tmf_in_progress;
}
-extern bool scsi_use_blk_mq;
-
static inline bool shost_use_blk_mq(struct Scsi_Host *shost)
{
- return scsi_use_blk_mq;
-
+ return shost->use_blk_mq;
}
extern int scsi_queue_work(struct Scsi_Host *, struct work_struct *);
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 19e5030..54e3aad 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -69,7 +69,8 @@
u64 mperf,
u64 aperf,
u64 tsc,
- u32 freq
+ u32 freq,
+ u32 io_boost
),
TP_ARGS(core_busy,
@@ -79,7 +80,8 @@
mperf,
aperf,
tsc,
- freq
+ freq,
+ io_boost
),
TP_STRUCT__entry(
@@ -91,6 +93,7 @@
__field(u64, aperf)
__field(u64, tsc)
__field(u32, freq)
+ __field(u32, io_boost)
),
TP_fast_assign(
@@ -102,9 +105,10 @@
__entry->aperf = aperf;
__entry->tsc = tsc;
__entry->freq = freq;
+ __entry->io_boost = io_boost;
),
- TP_printk("core_busy=%lu scaled=%lu from=%lu to=%lu mperf=%llu aperf=%llu tsc=%llu freq=%lu ",
+ TP_printk("core_busy=%lu scaled=%lu from=%lu to=%lu mperf=%llu aperf=%llu tsc=%llu freq=%lu io_boost=%lu",
(unsigned long)__entry->core_busy,
(unsigned long)__entry->scaled_busy,
(unsigned long)__entry->from,
@@ -112,7 +116,8 @@
(unsigned long long)__entry->mperf,
(unsigned long long)__entry->aperf,
(unsigned long long)__entry->tsc,
- (unsigned long)__entry->freq
+ (unsigned long)__entry->freq,
+ (unsigned long)__entry->io_boost
)
);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5e8dab5..d6b729b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3446,9 +3446,28 @@
* Except for the root, subtree_control must be zero for a cgroup
* with tasks so that child cgroups don't compete against tasks.
*/
- if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) {
- ret = -EBUSY;
- goto out_unlock;
+ if (enable && cgroup_parent(cgrp)) {
+ struct cgrp_cset_link *link;
+
+ /*
+ * Because namespaces pin csets too, @cgrp->cset_links
+ * might not be empty even when @cgrp is empty. Walk and
+ * verify each cset.
+ */
+ spin_lock_irq(&css_set_lock);
+
+ ret = 0;
+ list_for_each_entry(link, &cgrp->cset_links, cset_link) {
+ if (css_set_populated(link->cset)) {
+ ret = -EBUSY;
+ break;
+ }
+ }
+
+ spin_unlock_irq(&css_set_lock);
+
+ if (ret)
+ goto out_unlock;
}
/* save and update control masks and prepare csses */
@@ -3899,7 +3918,9 @@
* cgroup_task_count - count the number of tasks in a cgroup.
* @cgrp: the cgroup in question
*
- * Return the number of tasks in the cgroup.
+ * Return the number of tasks in the cgroup. The returned number can be
+ * higher than the actual number of tasks due to css_set references from
+ * namespace roots and temporary usages.
*/
static int cgroup_task_count(const struct cgroup *cgrp)
{
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 341bf80..ebbf027 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1024,12 +1024,13 @@
#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;
-int disable_nonboot_cpus(void)
+int freeze_secondary_cpus(int primary)
{
- int cpu, first_cpu, error = 0;
+ int cpu, error = 0;
cpu_maps_update_begin();
- first_cpu = cpumask_first(cpu_online_mask);
+ if (!cpu_online(primary))
+ primary = cpumask_first(cpu_online_mask);
/*
* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
@@ -1038,7 +1039,7 @@
pr_info("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
- if (cpu == first_cpu)
+ if (cpu == primary)
continue;
trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index c27e533..2b4c20a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -325,8 +325,7 @@
/*
* Return in pmask the portion of a cpusets's cpus_allowed that
* are online. If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus. The top
- * cpuset always has some cpus online.
+ * until we find one that does have some online cpus.
*
* One way or another, we guarantee to return some non-empty subset
* of cpu_online_mask.
@@ -335,8 +334,20 @@
*/
static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
{
- while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
+ while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
cs = parent_cs(cs);
+ if (unlikely(!cs)) {
+ /*
+ * The top cpuset doesn't have any online cpu as a
+ * consequence of a race between cpuset_hotplug_work
+ * and cpu hotplug notifier. But we know the top
+ * cpuset's effective_cpus is on its way to to be
+ * identical to cpu_online_mask.
+ */
+ cpumask_copy(pmask, cpu_online_mask);
+ return;
+ }
+ }
cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
}
@@ -2074,7 +2085,7 @@
* which could have been changed by cpuset just after it inherits the
* state from the parent and before it sits on the cgroup's task list.
*/
-void cpuset_fork(struct task_struct *task)
+static void cpuset_fork(struct task_struct *task)
{
if (task_css_is_root(task, cpuset_cgrp_id))
return;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 68d3ebc..e8517b6 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -186,7 +186,7 @@
config DPM_WATCHDOG
bool "Device suspend/resume watchdog"
- depends on PM_DEBUG && PSTORE
+ depends on PM_DEBUG && PSTORE && EXPERT
---help---
Sets up a watchdog timer to capture drivers that are
locked up attempting to suspend/resume a device.
@@ -197,7 +197,7 @@
config DPM_WATCHDOG_TIMEOUT
int "Watchdog timeout in seconds"
range 1 120
- default 60
+ default 120
depends on DPM_WATCHDOG
config PM_TRACE
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 33c79b6..b26dbc4 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -306,8 +306,10 @@
if (error)
printk(KERN_ERR "PM: Error %d creating hibernation image\n",
error);
- if (!in_suspend)
+ if (!in_suspend) {
events_check_enabled = false;
+ clear_free_pages();
+ }
platform_leave(platform_mode);
@@ -1189,22 +1191,6 @@
return 1;
}
-static int __init page_poison_nohibernate_setup(char *str)
-{
-#ifdef CONFIG_PAGE_POISONING_ZERO
- /*
- * The zeroing option for page poison skips the checks on alloc.
- * since hibernation doesn't save free pages there's no way to
- * guarantee the pages will still be zeroed.
- */
- if (!strcmp(str, "on")) {
- pr_info("Disabling hibernation due to page poisoning\n");
- return nohibernate_setup(str);
- }
-#endif
- return 1;
-}
-
__setup("noresume", noresume_setup);
__setup("resume_offset=", resume_offset_setup);
__setup("resume=", resume_setup);
@@ -1212,4 +1198,3 @@
__setup("resumewait", resumewait_setup);
__setup("resumedelay=", resumedelay_setup);
__setup("nohibernate", nohibernate_setup);
-__setup("page_poison=", page_poison_nohibernate_setup);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 5ea50b1..281a697 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -644,6 +644,7 @@
return error;
hibernate_image_size_init();
hibernate_reserved_size_init();
+ pm_states_init();
power_kobj = kobject_create_and_add("power", NULL);
if (!power_kobj)
return -ENOMEM;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 242d8b8..56d1d0d 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -110,6 +110,8 @@
extern void free_basic_memory_bitmaps(void);
extern int hibernate_preallocate_memory(void);
+extern void clear_free_pages(void);
+
/**
* Auxiliary structure used for reading the snapshot image data and
* metadata from and writing them to the list of page backup entries
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index b022284..4f0f060 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1132,6 +1132,28 @@
pr_debug("PM: Basic memory bitmaps freed\n");
}
+void clear_free_pages(void)
+{
+#ifdef CONFIG_PAGE_POISONING_ZERO
+ struct memory_bitmap *bm = free_pages_map;
+ unsigned long pfn;
+
+ if (WARN_ON(!(free_pages_map)))
+ return;
+
+ memory_bm_position_reset(bm);
+ pfn = memory_bm_next_pfn(bm);
+ while (pfn != BM_END_OF_MAP) {
+ if (pfn_valid(pfn))
+ clear_highpage(pfn_to_page(pfn));
+
+ pfn = memory_bm_next_pfn(bm);
+ }
+ memory_bm_position_reset(bm);
+ pr_info("PM: free pages cleared after restore\n");
+#endif /* PAGE_POISONING_ZERO */
+}
+
/**
* snapshot_additional_pages - Estimate the number of extra pages needed.
* @zone: Memory zone to carry out the computation for.
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 0acab9d..1e7f5da 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -118,10 +118,18 @@
*/
static bool relative_states;
+void __init pm_states_init(void)
+{
+ /*
+ * freeze state should be supported even without any suspend_ops,
+ * initialize pm_states accordingly here
+ */
+ pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2];
+}
+
static int __init sleep_states_setup(char *str)
{
relative_states = !strncmp(str, "1", 1);
- pm_states[PM_SUSPEND_FREEZE] = pm_labels[relative_states ? 0 : 2];
return 1;
}
@@ -211,7 +219,7 @@
{
if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin)
return freeze_ops->begin();
- else if (suspend_ops->begin)
+ else if (suspend_ops && suspend_ops->begin)
return suspend_ops->begin(state);
else
return 0;
@@ -221,7 +229,7 @@
{
if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end)
freeze_ops->end();
- else if (suspend_ops->end)
+ else if (suspend_ops && suspend_ops->end)
suspend_ops->end();
}
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 1141954..dbc5144 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -33,7 +33,7 @@
*/
void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
void (*func)(struct update_util_data *data, u64 time,
- unsigned long util, unsigned long max))
+ unsigned int flags))
{
if (WARN_ON(!data || !func))
return;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index a84641b..69e0689 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -12,7 +12,6 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cpufreq.h>
-#include <linux/module.h>
#include <linux/slab.h>
#include <trace/events/power.h>
@@ -48,11 +47,14 @@
struct sugov_policy *sg_policy;
unsigned int cached_raw_freq;
+ unsigned long iowait_boost;
+ unsigned long iowait_boost_max;
+ u64 last_update;
/* The fields below are only needed when sharing a policy. */
unsigned long util;
unsigned long max;
- u64 last_update;
+ unsigned int flags;
};
static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
@@ -144,24 +146,75 @@
return cpufreq_driver_resolve_freq(policy, freq);
}
+static void sugov_get_util(unsigned long *util, unsigned long *max)
+{
+ struct rq *rq = this_rq();
+ unsigned long cfs_max;
+
+ cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
+
+ *util = min(rq->cfs.avg.util_avg, cfs_max);
+ *max = cfs_max;
+}
+
+static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
+ unsigned int flags)
+{
+ if (flags & SCHED_CPUFREQ_IOWAIT) {
+ sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+ } else if (sg_cpu->iowait_boost) {
+ s64 delta_ns = time - sg_cpu->last_update;
+
+ /* Clear iowait_boost if the CPU apprears to have been idle. */
+ if (delta_ns > TICK_NSEC)
+ sg_cpu->iowait_boost = 0;
+ }
+}
+
+static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
+ unsigned long *max)
+{
+ unsigned long boost_util = sg_cpu->iowait_boost;
+ unsigned long boost_max = sg_cpu->iowait_boost_max;
+
+ if (!boost_util)
+ return;
+
+ if (*util * boost_max < *max * boost_util) {
+ *util = boost_util;
+ *max = boost_max;
+ }
+ sg_cpu->iowait_boost >>= 1;
+}
+
static void sugov_update_single(struct update_util_data *hook, u64 time,
- unsigned long util, unsigned long max)
+ unsigned int flags)
{
struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
+ unsigned long util, max;
unsigned int next_f;
+ sugov_set_iowait_boost(sg_cpu, time, flags);
+ sg_cpu->last_update = time;
+
if (!sugov_should_update_freq(sg_policy, time))
return;
- next_f = util == ULONG_MAX ? policy->cpuinfo.max_freq :
- get_next_freq(sg_cpu, util, max);
+ if (flags & SCHED_CPUFREQ_RT_DL) {
+ next_f = policy->cpuinfo.max_freq;
+ } else {
+ sugov_get_util(&util, &max);
+ sugov_iowait_boost(sg_cpu, &util, &max);
+ next_f = get_next_freq(sg_cpu, util, max);
+ }
sugov_update_commit(sg_policy, time, next_f);
}
static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
- unsigned long util, unsigned long max)
+ unsigned long util, unsigned long max,
+ unsigned int flags)
{
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
@@ -169,9 +222,11 @@
u64 last_freq_update_time = sg_policy->last_freq_update_time;
unsigned int j;
- if (util == ULONG_MAX)
+ if (flags & SCHED_CPUFREQ_RT_DL)
return max_f;
+ sugov_iowait_boost(sg_cpu, &util, &max);
+
for_each_cpu(j, policy->cpus) {
struct sugov_cpu *j_sg_cpu;
unsigned long j_util, j_max;
@@ -186,41 +241,50 @@
* frequency update and the time elapsed between the last update
* of the CPU utilization and the last frequency update is long
* enough, don't take the CPU into account as it probably is
- * idle now.
+ * idle now (and clear iowait_boost for it).
*/
delta_ns = last_freq_update_time - j_sg_cpu->last_update;
- if (delta_ns > TICK_NSEC)
+ if (delta_ns > TICK_NSEC) {
+ j_sg_cpu->iowait_boost = 0;
continue;
-
- j_util = j_sg_cpu->util;
- if (j_util == ULONG_MAX)
+ }
+ if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
return max_f;
+ j_util = j_sg_cpu->util;
j_max = j_sg_cpu->max;
if (j_util * max > j_max * util) {
util = j_util;
max = j_max;
}
+
+ sugov_iowait_boost(j_sg_cpu, &util, &max);
}
return get_next_freq(sg_cpu, util, max);
}
static void sugov_update_shared(struct update_util_data *hook, u64 time,
- unsigned long util, unsigned long max)
+ unsigned int flags)
{
struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+ unsigned long util, max;
unsigned int next_f;
+ sugov_get_util(&util, &max);
+
raw_spin_lock(&sg_policy->update_lock);
sg_cpu->util = util;
sg_cpu->max = max;
+ sg_cpu->flags = flags;
+
+ sugov_set_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
if (sugov_should_update_freq(sg_policy, time)) {
- next_f = sugov_next_freq_shared(sg_cpu, util, max);
+ next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
sugov_update_commit(sg_policy, time, next_f);
}
@@ -444,10 +508,13 @@
sg_cpu->sg_policy = sg_policy;
if (policy_is_shared(policy)) {
- sg_cpu->util = ULONG_MAX;
+ sg_cpu->util = 0;
sg_cpu->max = 0;
+ sg_cpu->flags = SCHED_CPUFREQ_RT;
sg_cpu->last_update = 0;
sg_cpu->cached_raw_freq = 0;
+ sg_cpu->iowait_boost = 0;
+ sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
sugov_update_shared);
} else {
@@ -495,28 +562,15 @@
.limits = sugov_limits,
};
-static int __init sugov_module_init(void)
-{
- return cpufreq_register_governor(&schedutil_gov);
-}
-
-static void __exit sugov_module_exit(void)
-{
- cpufreq_unregister_governor(&schedutil_gov);
-}
-
-MODULE_AUTHOR("Rafael J. Wysocki <rafael.j.wysocki@intel.com>");
-MODULE_DESCRIPTION("Utilization-based CPU frequency selection");
-MODULE_LICENSE("GPL");
-
#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
struct cpufreq_governor *cpufreq_default_governor(void)
{
return &schedutil_gov;
}
-
-fs_initcall(sugov_module_init);
-#else
-module_init(sugov_module_init);
#endif
-module_exit(sugov_module_exit);
+
+static int __init sugov_register(void)
+{
+ return cpufreq_register_governor(&schedutil_gov);
+}
+fs_initcall(sugov_register);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 1ce8867..9747796 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -735,9 +735,8 @@
return;
}
- /* kick cpufreq (see the comment in linux/cpufreq.h). */
- if (cpu_of(rq) == smp_processor_id())
- cpufreq_trigger_update(rq_clock(rq));
+ /* kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL);
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 039de34..a5cd07b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2875,12 +2875,7 @@
static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
{
- struct rq *rq = rq_of(cfs_rq);
- int cpu = cpu_of(rq);
-
- if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
- unsigned long max = rq->cpu_capacity_orig;
-
+ if (&this_rq()->cfs == cfs_rq) {
/*
* There are a few boundary cases this might miss but it should
* get called often enough that that should (hopefully) not be
@@ -2897,8 +2892,7 @@
*
* See cpu_util().
*/
- cpufreq_update_util(rq_clock(rq),
- min(cfs_rq->avg.util_avg, max), max);
+ cpufreq_update_util(rq_of(cfs_rq), 0);
}
}
@@ -3159,10 +3153,7 @@
static inline void update_load_avg(struct sched_entity *se, int not_used)
{
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- struct rq *rq = rq_of(cfs_rq);
-
- cpufreq_trigger_update(rq_clock(rq));
+ cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
}
static inline void
@@ -4509,6 +4500,14 @@
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
+ /*
+ * If in_iowait is set, the code below may not trigger any cpufreq
+ * utilization updates, so do it here explicitly with the IOWAIT flag
+ * passed.
+ */
+ if (p->in_iowait)
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
+
for_each_sched_entity(se) {
if (se->on_rq)
break;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d5690b7..2516b8d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -957,9 +957,8 @@
if (unlikely((s64)delta_exec <= 0))
return;
- /* Kick cpufreq (see the comment in linux/cpufreq.h). */
- if (cpu_of(rq) == smp_processor_id())
- cpufreq_trigger_update(rq_clock(rq));
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c64fc51..b7fc1ce 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1763,27 +1763,13 @@
/**
* cpufreq_update_util - Take a note about CPU utilization changes.
- * @time: Current time.
- * @util: Current utilization.
- * @max: Utilization ceiling.
+ * @rq: Runqueue to carry out the update for.
+ * @flags: Update reason flags.
*
- * This function is called by the scheduler on every invocation of
- * update_load_avg() on the CPU whose utilization is being updated.
+ * This function is called by the scheduler on the CPU whose utilization is
+ * being updated.
*
* It can only be called from RCU-sched read-side critical sections.
- */
-static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
-{
- struct update_util_data *data;
-
- data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
- if (data)
- data->func(data, time, util, max);
-}
-
-/**
- * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
- * @time: Current time.
*
* The way cpufreq is currently arranged requires it to evaluate the CPU
* performance state (frequency/voltage) on a regular basis to prevent it from
@@ -1797,13 +1783,23 @@
* but that really is a band-aid. Going forward it should be replaced with
* solutions targeted more specifically at RT and DL tasks.
*/
-static inline void cpufreq_trigger_update(u64 time)
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
{
- cpufreq_update_util(time, ULONG_MAX, 0);
+ struct update_util_data *data;
+
+ data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+ if (data)
+ data->func(data, rq_clock(rq), flags);
+}
+
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags)
+{
+ if (cpu_of(rq) == smp_processor_id())
+ cpufreq_update_util(rq, flags);
}
#else
-static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
-static inline void cpufreq_trigger_update(u64 time) {}
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
#endif /* CONFIG_CPU_FREQ */
#ifdef arch_scale_freq_capacity
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 22f4cd9..afcc550 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -76,8 +76,6 @@
no longer necessary to write zeros when GFP_ZERO is used on
allocation.
- Enabling page poisoning with this option will disable hibernation
-
If unsure, say N
bool
diff --git a/mm/filemap.c b/mm/filemap.c
index 8a287df..2d0986a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -110,6 +110,62 @@
* ->tasklist_lock (memory_failure, collect_procs_ao)
*/
+static int page_cache_tree_insert(struct address_space *mapping,
+ struct page *page, void **shadowp)
+{
+ struct radix_tree_node *node;
+ void **slot;
+ int error;
+
+ error = __radix_tree_create(&mapping->page_tree, page->index, 0,
+ &node, &slot);
+ if (error)
+ return error;
+ if (*slot) {
+ void *p;
+
+ p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+ if (!radix_tree_exceptional_entry(p))
+ return -EEXIST;
+
+ mapping->nrexceptional--;
+ if (!dax_mapping(mapping)) {
+ if (shadowp)
+ *shadowp = p;
+ if (node)
+ workingset_node_shadows_dec(node);
+ } else {
+ /* DAX can replace empty locked entry with a hole */
+ WARN_ON_ONCE(p !=
+ (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+ RADIX_DAX_ENTRY_LOCK));
+ /* DAX accounts exceptional entries as normal pages */
+ if (node)
+ workingset_node_pages_dec(node);
+ /* Wakeup waiters for exceptional entry lock */
+ dax_wake_mapping_entry_waiter(mapping, page->index,
+ false);
+ }
+ }
+ radix_tree_replace_slot(slot, page);
+ mapping->nrpages++;
+ if (node) {
+ workingset_node_pages_inc(node);
+ /*
+ * Don't track node that contains actual pages.
+ *
+ * Avoid acquiring the list_lru lock if already
+ * untracked. The list_empty() test is safe as
+ * node->private_list is protected by
+ * mapping->tree_lock.
+ */
+ if (!list_empty(&node->private_list))
+ list_lru_del(&workingset_shadow_nodes,
+ &node->private_list);
+ }
+ return 0;
+}
+
static void page_cache_tree_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
@@ -561,7 +617,7 @@
spin_lock_irqsave(&mapping->tree_lock, flags);
__delete_from_page_cache(old, NULL);
- error = radix_tree_insert(&mapping->page_tree, offset, new);
+ error = page_cache_tree_insert(mapping, new, NULL);
BUG_ON(error);
mapping->nrpages++;
@@ -584,62 +640,6 @@
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
-static int page_cache_tree_insert(struct address_space *mapping,
- struct page *page, void **shadowp)
-{
- struct radix_tree_node *node;
- void **slot;
- int error;
-
- error = __radix_tree_create(&mapping->page_tree, page->index, 0,
- &node, &slot);
- if (error)
- return error;
- if (*slot) {
- void *p;
-
- p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
- if (!radix_tree_exceptional_entry(p))
- return -EEXIST;
-
- mapping->nrexceptional--;
- if (!dax_mapping(mapping)) {
- if (shadowp)
- *shadowp = p;
- if (node)
- workingset_node_shadows_dec(node);
- } else {
- /* DAX can replace empty locked entry with a hole */
- WARN_ON_ONCE(p !=
- (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
- RADIX_DAX_ENTRY_LOCK));
- /* DAX accounts exceptional entries as normal pages */
- if (node)
- workingset_node_pages_dec(node);
- /* Wakeup waiters for exceptional entry lock */
- dax_wake_mapping_entry_waiter(mapping, page->index,
- false);
- }
- }
- radix_tree_replace_slot(slot, page);
- mapping->nrpages++;
- if (node) {
- workingset_node_pages_inc(node);
- /*
- * Don't track node that contains actual pages.
- *
- * Avoid acquiring the list_lru lock if already
- * untracked. The list_empty() test is safe as
- * node->private_list is protected by
- * mapping->tree_lock.
- */
- if (!list_empty(&node->private_list))
- list_lru_del(&workingset_shadow_nodes,
- &node->private_list);
- }
- return 0;
-}
-
static int __add_to_page_cache_locked(struct page *page,
struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask,
diff --git a/mm/ksm.c b/mm/ksm.c
index 73d43ba..5048083 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -283,7 +283,8 @@
{
struct rmap_item *rmap_item;
- rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL);
+ rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL |
+ __GFP_NORETRY | __GFP_NOWARN);
if (rmap_item)
ksm_rmap_items++;
return rmap_item;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b58906b..9d29ba0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1555,8 +1555,8 @@
{
gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
int nid = page_to_nid(page);
- nodemask_t nmask = node_online_map;
- struct page *new_page;
+ nodemask_t nmask = node_states[N_MEMORY];
+ struct page *new_page = NULL;
/*
* TODO: allocate a destination hugepage from a nearest neighbor node,
@@ -1567,14 +1567,14 @@
return alloc_huge_page_node(page_hstate(compound_head(page)),
next_node_in(nid, nmask));
- if (nid != next_node_in(nid, nmask))
- node_clear(nid, nmask);
+ node_clear(nid, nmask);
if (PageHighMem(page)
|| (zone_idx(page_zone(page)) == ZONE_MOVABLE))
gfp_mask |= __GFP_HIGHMEM;
- new_page = __alloc_pages_nodemask(gfp_mask, 0,
+ if (!nodes_empty(nmask))
+ new_page = __alloc_pages_nodemask(gfp_mask, 0,
node_zonelist(nid, gfp_mask), &nmask);
if (!new_page)
new_page = __alloc_pages(gfp_mask, 0,
diff --git a/mm/mmap.c b/mm/mmap.c
index ca9d91b..69cad56 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -88,6 +88,11 @@
* w: (no) no w: (no) no w: (copy) copy w: (no) no
* x: (no) no x: (no) yes x: (no) yes x: (yes) yes
*
+ * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
+ * MAP_PRIVATE:
+ * r: (no) no
+ * w: (no) no
+ * x: (yes) yes
*/
pgprot_t protection_map[16] = {
__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
diff --git a/mm/workingset.c b/mm/workingset.c
index 69551cf..617475f 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -418,21 +418,19 @@
* no pages, so we expect to be able to remove them all and
* delete and free the empty node afterwards.
*/
-
- BUG_ON(!node->count);
- BUG_ON(node->count & RADIX_TREE_COUNT_MASK);
+ BUG_ON(!workingset_node_shadows(node));
+ BUG_ON(workingset_node_pages(node));
for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
if (node->slots[i]) {
BUG_ON(!radix_tree_exceptional_entry(node->slots[i]));
node->slots[i] = NULL;
- BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT));
- node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+ workingset_node_shadows_dec(node);
BUG_ON(!mapping->nrexceptional);
mapping->nrexceptional--;
}
}
- BUG_ON(node->count);
+ BUG_ON(workingset_node_shadows(node));
inc_node_state(page_pgdat(virt_to_page(node)), WORKINGSET_NODERECLAIM);
if (!__radix_tree_delete_node(&mapping->page_tree, node))
BUG();
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a87bcd2..5f006e1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2123,7 +2123,7 @@
int ipmr_get_route(struct net *net, struct sk_buff *skb,
__be32 saddr, __be32 daddr,
- struct rtmsg *rtm, int nowait)
+ struct rtmsg *rtm, int nowait, u32 portid)
{
struct mfc_cache *cache;
struct mr_table *mrt;
@@ -2168,6 +2168,7 @@
return -ENOMEM;
}
+ NETLINK_CB(skb2).portid = portid;
skb_push(skb2, sizeof(struct iphdr));
skb_reset_network_header(skb2);
iph = ip_hdr(skb2);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b5b47a26..62c3ed0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2503,7 +2503,8 @@
IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
int err = ipmr_get_route(net, skb,
fl4->saddr, fl4->daddr,
- r, nowait);
+ r, nowait, portid);
+
if (err <= 0) {
if (!nowait) {
if (err == 0)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 08323bd..a756b87 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2329,10 +2329,9 @@
}
#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
- struct ipv6_pinfo *np = inet6_sk(sk);
pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
msg,
- &np->daddr, ntohs(inet->inet_dport),
+ &sk->sk_v6_daddr, ntohs(inet->inet_dport),
tp->snd_cwnd, tcp_left_out(tp),
tp->snd_ssthresh, tp->prior_ssthresh,
tp->packets_out);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5288cec..d48d557 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1966,12 +1966,14 @@
len = 0;
tcp_for_write_queue_from_safe(skb, next, sk) {
copy = min_t(int, skb->len, probe_size - len);
- if (nskb->ip_summed)
+ if (nskb->ip_summed) {
skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
- else
- nskb->csum = skb_copy_and_csum_bits(skb, 0,
- skb_put(nskb, copy),
- copy, nskb->csum);
+ } else {
+ __wsum csum = skb_copy_and_csum_bits(skb, 0,
+ skb_put(nskb, copy),
+ copy, 0);
+ nskb->csum = csum_block_add(nskb->csum, csum, len);
+ }
if (skb->len <= copy) {
/* We've eaten all the data from this skb.
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 704274c..edc3daa 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -648,7 +648,6 @@
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
- fl6.flowi6_proto = skb->protocol;
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index fccb5dd..7f4265b 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2285,8 +2285,8 @@
return 1;
}
-int ip6mr_get_route(struct net *net,
- struct sk_buff *skb, struct rtmsg *rtm, int nowait)
+int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
+ int nowait, u32 portid)
{
int err;
struct mr6_table *mrt;
@@ -2331,6 +2331,7 @@
return -ENOMEM;
}
+ NETLINK_CB(skb2).portid = portid;
skb_reset_transport_header(skb2);
skb_put(skb2, sizeof(struct ipv6hdr));
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e3a224b..269218a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3202,7 +3202,9 @@
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
- int err = ip6mr_get_route(net, skb, rtm, nowait);
+ int err = ip6mr_get_route(net, skb, rtm, nowait,
+ portid);
+
if (err <= 0) {
if (!nowait) {
if (err == 0)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index e87cd81..4a60cd5 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -53,7 +53,7 @@
u32 *tlv = (u32 *)(skbdata);
u16 totlen = nla_total_size(dlen); /*alignment + hdr */
char *dptr = (char *)tlv + NLA_HDRLEN;
- u32 htlv = attrtype << 16 | dlen;
+ u32 htlv = attrtype << 16 | (dlen + NLA_HDRLEN);
*tlv = htonl(htlv);
memset(dptr, 0, totlen - NLA_HDRLEN);
@@ -627,7 +627,7 @@
struct tcf_ife_info *ife = to_ife(a);
int action = ife->tcf_action;
struct ifeheadr *ifehdr = (struct ifeheadr *)skb->data;
- u16 ifehdrln = ifehdr->metalen;
+ int ifehdrln = (int)ifehdr->metalen;
struct meta_tlvhdr *tlv = (struct meta_tlvhdr *)(ifehdr->tlv_data);
spin_lock(&ife->tcf_lock);
@@ -740,8 +740,6 @@
return TC_ACT_SHOT;
}
- iethh = eth_hdr(skb);
-
err = skb_cow_head(skb, hdrm);
if (unlikely(err)) {
ife->tcf_qstats.drops++;
@@ -752,6 +750,7 @@
if (!(at & AT_EGRESS))
skb_push(skb, skb->dev->hard_header_len);
+ iethh = (struct ethhdr *)skb->data;
__skb_push(skb, hdrm);
memcpy(skb->data, iethh, skb->mac_len);
skb_reset_mac_header(skb);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f27ffee..ca0516e 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1153,6 +1153,7 @@
if (!skb)
return NULL;
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
qdisc_bstats_update(sch, skb);
@@ -1256,6 +1257,7 @@
}
bstats_update(&cl->bstats, skb);
+ qdisc_qstats_backlog_inc(sch, skb);
++sch->q.qlen;
agg = cl->agg;
@@ -1476,6 +1478,7 @@
qdisc_reset(cl->qdisc);
}
}
+ sch->qstats.backlog = 0;
sch->q.qlen = 0;
}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index add3cc7..20a350b 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -400,6 +400,7 @@
enqueue:
ret = qdisc_enqueue(skb, child, to_free);
if (likely(ret == NET_XMIT_SUCCESS)) {
+ qdisc_qstats_backlog_inc(sch, skb);
sch->q.qlen++;
increment_qlen(skb, q);
} else if (net_xmit_drop_count(ret)) {
@@ -428,6 +429,7 @@
if (skb) {
qdisc_bstats_update(sch, skb);
+ qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
decrement_qlen(skb, q);
}
@@ -450,6 +452,7 @@
struct sfb_sched_data *q = qdisc_priv(sch);
qdisc_reset(q->qdisc);
+ sch->qstats.backlog = 0;
sch->q.qlen = 0;
q->slot = 0;
q->double_buffering = false;
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index a55e547..0a3dbec 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -179,6 +179,11 @@
msg, msg->expires_at, jiffies);
}
+ if (asoc->peer.prsctp_capable &&
+ SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags))
+ msg->expires_at =
+ jiffies + msecs_to_jiffies(sinfo->sinfo_timetolive);
+
/* This is the biggest possible DATA chunk that can fit into
* the packet
*/
@@ -335,7 +340,7 @@
/* Check whether this message has expired. */
int sctp_chunk_abandoned(struct sctp_chunk *chunk)
{
- if (!chunk->asoc->prsctp_enable ||
+ if (!chunk->asoc->peer.prsctp_capable ||
!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags)) {
struct sctp_datamsg *msg = chunk->msg;
@@ -349,14 +354,14 @@
}
if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
- time_after(jiffies, chunk->prsctp_param)) {
+ time_after(jiffies, chunk->msg->expires_at)) {
if (chunk->sent_count)
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
else
chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
return 1;
} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
- chunk->sent_count > chunk->prsctp_param) {
+ chunk->sent_count > chunk->sinfo.sinfo_timetolive) {
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
return 1;
}
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 72e54a4..107233d 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -326,7 +326,7 @@
sctp_chunk_hold(chunk);
sctp_outq_tail_data(q, chunk);
- if (chunk->asoc->prsctp_enable &&
+ if (chunk->asoc->peer.prsctp_capable &&
SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
chunk->asoc->sent_cnt_removable++;
if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
@@ -383,7 +383,7 @@
list_for_each_entry_safe(chk, temp, queue, transmitted_list) {
if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
- chk->prsctp_param <= sinfo->sinfo_timetolive)
+ chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
continue;
list_del_init(&chk->transmitted_list);
@@ -418,7 +418,7 @@
list_for_each_entry_safe(chk, temp, queue, list) {
if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
- chk->prsctp_param <= sinfo->sinfo_timetolive)
+ chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
continue;
list_del_init(&chk->list);
@@ -442,7 +442,7 @@
{
struct sctp_transport *transport;
- if (!asoc->prsctp_enable || !asoc->sent_cnt_removable)
+ if (!asoc->peer.prsctp_capable || !asoc->sent_cnt_removable)
return;
msg_len = sctp_prsctp_prune_sent(asoc, sinfo,
@@ -1055,7 +1055,7 @@
/* Mark as failed send. */
sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
- if (asoc->prsctp_enable &&
+ if (asoc->peer.prsctp_capable &&
SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
asoc->sent_cnt_removable--;
sctp_chunk_free(chunk);
@@ -1347,7 +1347,7 @@
tsn = ntohl(tchunk->subh.data_hdr->tsn);
if (TSN_lte(tsn, ctsn)) {
list_del_init(&tchunk->transmitted_list);
- if (asoc->prsctp_enable &&
+ if (asoc->peer.prsctp_capable &&
SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
asoc->sent_cnt_removable--;
sctp_chunk_free(tchunk);
diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c
index f3508aa..cef0cee 100644
--- a/net/sctp/sctp_diag.c
+++ b/net/sctp/sctp_diag.c
@@ -272,28 +272,17 @@
return err;
}
-static int sctp_tsp_dump(struct sctp_transport *tsp, void *p)
+static int sctp_sock_dump(struct sock *sk, void *p)
{
- struct sctp_endpoint *ep = tsp->asoc->ep;
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_comm_param *commp = p;
- struct sock *sk = ep->base.sk;
struct sk_buff *skb = commp->skb;
struct netlink_callback *cb = commp->cb;
const struct inet_diag_req_v2 *r = commp->r;
- struct sctp_association *assoc =
- list_entry(ep->asocs.next, struct sctp_association, asocs);
+ struct sctp_association *assoc;
int err = 0;
- /* find the ep only once through the transports by this condition */
- if (tsp->asoc != assoc)
- goto out;
-
- if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family)
- goto out;
-
lock_sock(sk);
- if (sk != assoc->base.sk)
- goto release;
list_for_each_entry(assoc, &ep->asocs, asocs) {
if (cb->args[4] < cb->args[1])
goto next;
@@ -312,7 +301,7 @@
cb->nlh->nlmsg_seq,
NLM_F_MULTI, cb->nlh) < 0) {
cb->args[3] = 1;
- err = 2;
+ err = 1;
goto release;
}
cb->args[3] = 1;
@@ -321,7 +310,7 @@
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0, cb->nlh) < 0) {
- err = 2;
+ err = 1;
goto release;
}
next:
@@ -333,10 +322,35 @@
cb->args[4] = 0;
release:
release_sock(sk);
+ sock_put(sk);
return err;
+}
+
+static int sctp_get_sock(struct sctp_transport *tsp, void *p)
+{
+ struct sctp_endpoint *ep = tsp->asoc->ep;
+ struct sctp_comm_param *commp = p;
+ struct sock *sk = ep->base.sk;
+ struct netlink_callback *cb = commp->cb;
+ const struct inet_diag_req_v2 *r = commp->r;
+ struct sctp_association *assoc =
+ list_entry(ep->asocs.next, struct sctp_association, asocs);
+
+ /* find the ep only once through the transports by this condition */
+ if (tsp->asoc != assoc)
+ goto out;
+
+ if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family)
+ goto out;
+
+ sock_hold(sk);
+ cb->args[5] = (long)sk;
+
+ return 1;
+
out:
cb->args[2]++;
- return err;
+ return 0;
}
static int sctp_ep_dump(struct sctp_endpoint *ep, void *p)
@@ -472,10 +486,18 @@
* 2 : to record the transport pos of this time's traversal
* 3 : to mark if we have dumped the ep info of the current asoc
* 4 : to work as a temporary variable to traversal list
+ * 5 : to save the sk we get from travelsing the tsp list.
*/
if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
goto done;
- sctp_for_each_transport(sctp_tsp_dump, net, cb->args[2], &commp);
+
+next:
+ cb->args[5] = 0;
+ sctp_for_each_transport(sctp_get_sock, net, cb->args[2], &commp);
+
+ if (cb->args[5] && !sctp_sock_dump((struct sock *)cb->args[5], &commp))
+ goto next;
+
done:
cb->args[1] = cb->args[4];
cb->args[4] = 0;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 8c77b87..46ffecc 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -706,20 +706,6 @@
return retval;
}
-static void sctp_set_prsctp_policy(struct sctp_chunk *chunk,
- const struct sctp_sndrcvinfo *sinfo)
-{
- if (!chunk->asoc->prsctp_enable)
- return;
-
- if (SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags))
- chunk->prsctp_param =
- jiffies + msecs_to_jiffies(sinfo->sinfo_timetolive);
- else if (SCTP_PR_RTX_ENABLED(sinfo->sinfo_flags) ||
- SCTP_PR_PRIO_ENABLED(sinfo->sinfo_flags))
- chunk->prsctp_param = sinfo->sinfo_timetolive;
-}
-
/* Make a DATA chunk for the given association from the provided
* parameters. However, do not populate the data payload.
*/
@@ -753,7 +739,6 @@
retval->subh.data_hdr = sctp_addto_chunk(retval, sizeof(dp), &dp);
memcpy(&retval->sinfo, sinfo, sizeof(struct sctp_sndrcvinfo));
- sctp_set_prsctp_policy(retval, sinfo);
nodata:
return retval;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9fc417a..8ed2d99 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4469,17 +4469,21 @@
const union sctp_addr *paddr, void *p)
{
struct sctp_transport *transport;
- int err = 0;
+ int err = -ENOENT;
rcu_read_lock();
transport = sctp_addrs_lookup_transport(net, laddr, paddr);
if (!transport || !sctp_transport_hold(transport))
goto out;
- err = cb(transport, p);
+
+ sctp_association_hold(transport->asoc);
sctp_transport_put(transport);
-out:
rcu_read_unlock();
+ err = cb(transport, p);
+ sctp_association_put(transport->asoc);
+
+out:
return err;
}
EXPORT_SYMBOL_GPL(sctp_transport_lookup_process);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 17dbbe6..8a398b3 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -465,6 +465,8 @@
if (vsock_is_pending(sk)) {
vsock_remove_pending(listener, sk);
+
+ listener->sk_ack_backlog--;
} else if (!vsk->rejected) {
/* We are not on the pending list and accept() did not reject
* us, so we must have been accepted by our user process. We
@@ -475,8 +477,6 @@
goto out;
}
- listener->sk_ack_backlog--;
-
/* We need to remove ourself from the global connected sockets list so
* incoming packets can't find this socket, and to reduce the reference
* count.
@@ -2010,5 +2010,5 @@
MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Virtual Socket Family");
-MODULE_VERSION("1.0.1.0-k");
+MODULE_VERSION("1.0.2.0-k");
MODULE_LICENSE("GPL v2");
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 42396a7..a68f031 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -363,6 +363,7 @@
strcmp(".sched.text", txtname) == 0 ||
strcmp(".spinlock.text", txtname) == 0 ||
strcmp(".irqentry.text", txtname) == 0 ||
+ strcmp(".softirqentry.text", txtname) == 0 ||
strcmp(".kprobes.text", txtname) == 0 ||
strcmp(".text.unlikely", txtname) == 0;
}
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 96e2486..2d48011 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -134,6 +134,7 @@
".sched.text" => 1,
".spinlock.text" => 1,
".irqentry.text" => 1,
+ ".softirqentry.text" => 1,
".kprobes.text" => 1,
".text.unlikely" => 1,
);
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index dd48f42..f64c57b 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -603,7 +603,8 @@
return -ENOMEM;
sprintf(t->label[i], "label%d", i);
- t->flush[i] = test_alloc(t, sizeof(u64) * NUM_HINTS,
+ t->flush[i] = test_alloc(t, max(PAGE_SIZE,
+ sizeof(u64) * NUM_HINTS),
&t->flush_dma[i]);
if (!t->flush[i])
return -ENOMEM;