Merge branch 'irq/for-arm' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
This is an incremental fix for a patch previously pulled from tip
irq/for-arm.
* 'irq/for-arm' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq: Make the cpuhotplug migration code less noisy
diff --git a/Documentation/Changes b/Documentation/Changes
index 6d88630..f447f05 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -43,7 +43,7 @@
o grub 0.93 # grub --version || grub-install --version
o mcelog 0.6 # mcelog --version
o iptables 1.4.2 # iptables -V
-o openssl & libcrypto 1.0.1k # openssl version
+o openssl & libcrypto 1.0.0 # openssl version
Kernel compilation
diff --git a/Documentation/arm/uefi.txt b/Documentation/arm/uefi.txt
index d60030a..7f1bed8 100644
--- a/Documentation/arm/uefi.txt
+++ b/Documentation/arm/uefi.txt
@@ -58,7 +58,5 @@
--------------------------------------------------------------------------------
linux,uefi-mmap-desc-ver | 32-bit | Version of the mmap descriptor format.
--------------------------------------------------------------------------------
-linux,uefi-stub-kern-ver | string | Copy of linux_banner from build.
---------------------------------------------------------------------------------
For verbose debug messages, specify 'uefi_debug' on the kernel command line.
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 7d9d3c2..aaf6d77 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -104,7 +104,12 @@
- The flags field (introduced in v3.17) is a little-endian 64-bit field
composed as follows:
Bit 0: Kernel endianness. 1 if BE, 0 if LE.
- Bits 1-63: Reserved.
+ Bit 1-2: Kernel Page size.
+ 0 - Unspecified.
+ 1 - 4K
+ 2 - 16K
+ 3 - 64K
+ Bits 3-63: Reserved.
- When image_size is zero, a bootloader should attempt to keep as much
memory as possible free for use by the kernel immediately after the
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 435251f..4b7c3d9 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -8,6 +8,8 @@
- compatible : should be one of
"arm,armv8-pmuv3"
+ "arm.cortex-a57-pmu"
+ "arm.cortex-a53-pmu"
"arm,cortex-a17-pmu"
"arm,cortex-a15-pmu"
"arm,cortex-a12-pmu"
diff --git a/Documentation/devicetree/bindings/input/cypress,cyapa.txt b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
index 635a3b0..8d91ba9 100644
--- a/Documentation/devicetree/bindings/input/cypress,cyapa.txt
+++ b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
@@ -25,7 +25,7 @@
/* Cypress Gen3 touchpad */
touchpad@67 {
compatible = "cypress,cyapa";
- reg = <0x24>;
+ reg = <0x67>;
interrupt-parent = <&gpio>;
interrupts = <2 IRQ_TYPE_EDGE_FALLING>; /* GPIO 2 */
wakeup-source;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
index 391717a..ec96b1f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
@@ -4,8 +4,8 @@
interrupt.
Required Properties:
-- compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc"
- as fallback
+- compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc" or
+ "qca,<soctype>-cpu-intc", "qca,ar7240-misc-intc"
- reg: Base address and size of the controllers memory area
- interrupt-parent: phandle of the parent interrupt controller.
- interrupts: Interrupt specifier for the controllers interrupt.
@@ -13,6 +13,9 @@
- #interrupt-cells : Specifies the number of cells needed to encode interrupt
source, should be 1
+Compatible fallback depends on the SoC. Use ar7100 for ar71xx and ar913x,
+use ar7240 for all other SoCs.
+
Please refer to interrupts.txt in this directory for details of the common
Interrupt Controllers bindings used by client devices.
@@ -28,3 +31,16 @@
interrupt-controller;
#interrupt-cells = <1>;
};
+
+Another example:
+
+ interrupt-controller@18060010 {
+ compatible = "qca,ar9331-misc-intc", qca,ar7240-misc-intc";
+ reg = <0x18060010 0x4>;
+
+ interrupt-parent = <&cpuintc>;
+ interrupts = <6>;
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
index 14531da..703f5784 100644
--- a/Documentation/features/debug/KASAN/arch-support.txt
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | TODO |
| arm: | TODO |
- | arm64: | TODO |
+ | arm64: | ok |
| avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt
index b85d000..c51f114 100644
--- a/Documentation/input/multi-touch-protocol.txt
+++ b/Documentation/input/multi-touch-protocol.txt
@@ -361,7 +361,7 @@
ABS_MT_POSITION_X := T_X
ABS_MT_POSITION_Y := T_Y
ABS_MT_TOOL_X := C_X
- ABS_MT_TOOL_X := C_Y
+ ABS_MT_TOOL_Y := C_Y
Unfortunately, there is not enough information to specify both the touching
ellipse and the tool ellipse, so one has to resort to approximations. One
diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt
index 62328d7..b0e911e 100644
--- a/Documentation/power/pci.txt
+++ b/Documentation/power/pci.txt
@@ -979,20 +979,45 @@
(alternatively, the runtime_suspend() callback will have to check if the
device should really be suspended and return -EAGAIN if that is not the case).
-The runtime PM of PCI devices is disabled by default. It is also blocked by
-pci_pm_init() that runs the pm_runtime_forbid() helper function. If a PCI
-driver implements the runtime PM callbacks and intends to use the runtime PM
-framework provided by the PM core and the PCI subsystem, it should enable this
-feature by executing the pm_runtime_enable() helper function. However, the
-driver should not call the pm_runtime_allow() helper function unblocking
-the runtime PM of the device. Instead, it should allow user space or some
-platform-specific code to do that (user space can do it via sysfs), although
-once it has called pm_runtime_enable(), it must be prepared to handle the
+The runtime PM of PCI devices is enabled by default by the PCI core. PCI
+device drivers do not need to enable it and should not attempt to do so.
+However, it is blocked by pci_pm_init() that runs the pm_runtime_forbid()
+helper function. In addition to that, the runtime PM usage counter of
+each PCI device is incremented by local_pci_probe() before executing the
+probe callback provided by the device's driver.
+
+If a PCI driver implements the runtime PM callbacks and intends to use the
+runtime PM framework provided by the PM core and the PCI subsystem, it needs
+to decrement the device's runtime PM usage counter in its probe callback
+function. If it doesn't do that, the counter will always be different from
+zero for the device and it will never be runtime-suspended. The simplest
+way to do that is by calling pm_runtime_put_noidle(), but if the driver
+wants to schedule an autosuspend right away, for example, it may call
+pm_runtime_put_autosuspend() instead for this purpose. Generally, it
+just needs to call a function that decrements the devices usage counter
+from its probe routine to make runtime PM work for the device.
+
+It is important to remember that the driver's runtime_suspend() callback
+may be executed right after the usage counter has been decremented, because
+user space may already have cuased the pm_runtime_allow() helper function
+unblocking the runtime PM of the device to run via sysfs, so the driver must
+be prepared to cope with that.
+
+The driver itself should not call pm_runtime_allow(), though. Instead, it
+should let user space or some platform-specific code do that (user space can
+do it via sysfs as stated above), but it must be prepared to handle the
runtime PM of the device correctly as soon as pm_runtime_allow() is called
-(which may happen at any time). [It also is possible that user space causes
-pm_runtime_allow() to be called via sysfs before the driver is loaded, so in
-fact the driver has to be prepared to handle the runtime PM of the device as
-soon as it calls pm_runtime_enable().]
+(which may happen at any time, even before the driver is loaded).
+
+When the driver's remove callback runs, it has to balance the decrementation
+of the device's runtime PM usage counter at the probe time. For this reason,
+if it has decremented the counter in its probe callback, it must run
+pm_runtime_get_noresume() in its remove callback. [Since the core carries
+out a runtime resume of the device and bumps up the device's usage counter
+before running the driver's remove callback, the runtime PM of the device
+is effectively disabled for the duration of the remove execution and all
+runtime PM helper functions incrementing the device's usage counter are
+then effectively equivalent to pm_runtime_get_noresume().]
The runtime PM framework works by processing requests to suspend or resume
devices, or to check if they are idle (in which cases it is reasonable to
diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c
index 2bc8abc..6c6247a 100644
--- a/Documentation/ptp/testptp.c
+++ b/Documentation/ptp/testptp.c
@@ -18,6 +18,7 @@
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */
#include <errno.h>
#include <fcntl.h>
#include <inttypes.h>
diff --git a/MAINTAINERS b/MAINTAINERS
index 9f6685f..8addb19 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -822,12 +822,13 @@
ARM PMU PROFILING AND DEBUGGING
M: Will Deacon <will.deacon@arm.com>
+R: Mark Rutland <mark.rutland@arm.com>
S: Maintained
-F: arch/arm/kernel/perf_*
+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: 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: include/linux/perf/arm_pmu.h
@@ -5957,7 +5958,7 @@
KERNEL VIRTUAL MACHINE (KVM) FOR AMD-V
M: Joerg Roedel <joro@8bytes.org>
L: kvm@vger.kernel.org
-W: http://kvm.qumranet.com
+W: http://www.linux-kvm.org/
S: Maintained
F: arch/x86/include/asm/svm.h
F: arch/x86/kvm/svm.c
@@ -5965,7 +5966,7 @@
KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
M: Alexander Graf <agraf@suse.com>
L: kvm-ppc@vger.kernel.org
-W: http://kvm.qumranet.com
+W: http://www.linux-kvm.org/
T: git git://github.com/agraf/linux-2.6.git
S: Supported
F: arch/powerpc/include/asm/kvm*
diff --git a/Makefile b/Makefile
index 1d341eb..fd46821 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
PATCHLEVEL = 3
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
NAME = Hurr durr I'ma sheep
# *DOCUMENTATION*
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 7611b10..0b10ef2 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -48,4 +48,5 @@
generic-y += ucontext.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 07d1811..c62fb03 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -48,6 +48,7 @@
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_BITREVERSE
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP
select HAVE_ARCH_KGDB
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
@@ -169,10 +170,12 @@
config PGTABLE_LEVELS
int
+ default 2 if ARM64_16K_PAGES && ARM64_VA_BITS_36
default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42
default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48
default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39
- default 4 if ARM64_4K_PAGES && ARM64_VA_BITS_48
+ default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47
+ default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48
source "init/Kconfig"
@@ -362,25 +365,37 @@
help
This feature enables 4KB pages support.
+config ARM64_16K_PAGES
+ bool "16KB"
+ help
+ The system will use 16KB pages support. AArch32 emulation
+ requires applications compiled with 16K (or a multiple of 16K)
+ aligned segments.
+
config ARM64_64K_PAGES
bool "64KB"
help
This feature enables 64KB pages support (4KB by default)
allowing only two levels of page tables and faster TLB
- look-up. AArch32 emulation is not available when this feature
- is enabled.
+ look-up. AArch32 emulation requires applications compiled
+ with 64K aligned segments.
endchoice
choice
prompt "Virtual address space size"
default ARM64_VA_BITS_39 if ARM64_4K_PAGES
+ default ARM64_VA_BITS_47 if ARM64_16K_PAGES
default ARM64_VA_BITS_42 if ARM64_64K_PAGES
help
Allows choosing one of multiple possible virtual address
space sizes. The level of translation table is determined by
a combination of page size and virtual address space size.
+config ARM64_VA_BITS_36
+ bool "36-bit" if EXPERT
+ depends on ARM64_16K_PAGES
+
config ARM64_VA_BITS_39
bool "39-bit"
depends on ARM64_4K_PAGES
@@ -389,6 +404,10 @@
bool "42-bit"
depends on ARM64_64K_PAGES
+config ARM64_VA_BITS_47
+ bool "47-bit"
+ depends on ARM64_16K_PAGES
+
config ARM64_VA_BITS_48
bool "48-bit"
@@ -396,8 +415,10 @@
config ARM64_VA_BITS
int
+ default 36 if ARM64_VA_BITS_36
default 39 if ARM64_VA_BITS_39
default 42 if ARM64_VA_BITS_42
+ default 47 if ARM64_VA_BITS_47
default 48 if ARM64_VA_BITS_48
config CPU_BIG_ENDIAN
@@ -427,6 +448,7 @@
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
+ select GENERIC_IRQ_MIGRATION
help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu.
@@ -454,12 +476,8 @@
def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
config HW_PERF_EVENTS
- bool "Enable hardware performance counter support for perf events"
- depends on PERF_EVENTS
- default y
- help
- Enable hardware performance counter support for perf events. If
- disabled, perf events will use software events only.
+ def_bool y
+ depends on ARM_PMU
config SYS_SUPPORTS_HUGETLBFS
def_bool y
@@ -468,7 +486,7 @@
def_bool y
config ARCH_WANT_HUGE_PMD_SHARE
- def_bool y if !ARM64_64K_PAGES
+ def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
config HAVE_ARCH_TRANSPARENT_HUGEPAGE
def_bool y
@@ -505,7 +523,25 @@
config FORCE_MAX_ZONEORDER
int
default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
+ default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE)
default "11"
+ help
+ The kernel memory allocator divides physically contiguous memory
+ blocks into "zones", where each zone is a power of two number of
+ pages. This option selects the largest power of two that the kernel
+ keeps in the memory allocator. If you need to allocate very large
+ blocks of physically contiguous memory, then you may need to
+ increase this value.
+
+ This config option is actually maximum order plus one. For example,
+ a value of 11 means that the largest free memory block is 2^10 pages.
+
+ We make sure that we can allocate upto a HugePage size for each configuration.
+ Hence we have :
+ MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2
+
+ However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
+ 4M allocations matching the default size used by generic code.
menuconfig ARMV8_DEPRECATED
bool "Emulate deprecated/obsolete ARMv8 instructions"
@@ -680,7 +716,7 @@
config COMPAT
bool "Kernel support for 32-bit EL0"
- depends on !ARM64_64K_PAGES || EXPERT
+ depends on ARM64_4K_PAGES || EXPERT
select COMPAT_BINFMT_ELF
select HAVE_UID16
select OLD_SIGSUSPEND3
@@ -691,9 +727,9 @@
the user helper functions, VFP support and the ptrace interface are
handled appropriately by the kernel.
- If you also enabled CONFIG_ARM64_64K_PAGES, please be aware that you
- will only be able to execute AArch32 binaries that were compiled with
- 64k aligned segments.
+ If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware
+ that you will only be able to execute AArch32 binaries that were compiled
+ with page size aligned segments.
If you want to execute 32-bit userspace applications, say Y.
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index d6285ef..c24d6ad 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -77,7 +77,7 @@
If in doubt, say Y
config DEBUG_ALIGN_RODATA
- depends on DEBUG_RODATA && !ARM64_64K_PAGES
+ depends on DEBUG_RODATA && ARM64_4K_PAGES
bool "Align linker sections up to SECTION_SIZE"
help
If this option is enabled, sections that may potentially be marked as
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index f9914d7..f41c676 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -55,6 +55,13 @@
TEXT_OFFSET := 0x00080000
endif
+# KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - 3)) - (1 << 61)
+# in 32-bit arithmetic
+KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \
+ (0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 32))) \
+ + (1 << ($(CONFIG_ARM64_VA_BITS) - 32 - 3)) \
+ - (1 << (64 - 32 - 3)) )) )
+
export TEXT_OFFSET GZFLAGS
core-y += arch/arm64/kernel/ arch/arm64/mm/
diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts
index c627511..734e127 100644
--- a/arch/arm64/boot/dts/arm/juno-r1.dts
+++ b/arch/arm64/boot/dts/arm/juno-r1.dts
@@ -91,17 +91,21 @@
};
};
- pmu {
- compatible = "arm,armv8-pmuv3";
+ pmu_a57 {
+ compatible = "arm,cortex-a57-pmu";
interrupts = <GIC_SPI 02 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 06 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 06 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-affinity = <&A57_0>,
+ <&A57_1>;
+ };
+
+ pmu_a53 {
+ compatible = "arm,cortex-a53-pmu";
+ interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-affinity = <&A57_0>,
- <&A57_1>,
- <&A53_0>,
+ interrupt-affinity = <&A53_0>,
<&A53_1>,
<&A53_2>,
<&A53_3>;
diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts
index d7cbdd4..ffa05ae 100644
--- a/arch/arm64/boot/dts/arm/juno.dts
+++ b/arch/arm64/boot/dts/arm/juno.dts
@@ -91,17 +91,21 @@
};
};
- pmu {
- compatible = "arm,armv8-pmuv3";
+ pmu_a57 {
+ compatible = "arm,cortex-a57-pmu";
interrupts = <GIC_SPI 02 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 06 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 06 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-affinity = <&A57_0>,
+ <&A57_1>;
+ };
+
+ pmu_a53 {
+ compatible = "arm,cortex-a53-pmu";
+ interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-affinity = <&A57_0>,
- <&A57_1>,
- <&A53_0>,
+ interrupt-affinity = <&A53_0>,
<&A53_1>,
<&A53_2>,
<&A53_3>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 34d71dd..c8ccda1 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -109,6 +109,10 @@
CONFIG_SERIAL_8250_MT6577=y
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_SERIAL_SAMSUNG=y
+CONFIG_SERIAL_SAMSUNG_UARTS_4=y
+CONFIG_SERIAL_SAMSUNG_UARTS=4
+CONFIG_SERIAL_SAMSUNG_CONSOLE=y
CONFIG_SERIAL_MSM=y
CONFIG_SERIAL_MSM_CONSOLE=y
CONFIG_SERIAL_OF_PLATFORM=y
@@ -145,6 +149,10 @@
CONFIG_MMC_SDHCI=y
CONFIG_MMC_SDHCI_PLTFM=y
CONFIG_MMC_SPI=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+CONFIG_MMC_DW_PLTFM=y
+CONFIG_MMC_DW_EXYNOS=y
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_SYSCON=y
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index b51f2cc..12eff92 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -193,4 +193,15 @@
str \src, [\tmp, :lo12:\sym]
.endm
+/*
+ * Annotate a function as position independent, i.e., safe to be called before
+ * the kernel virtual mapping is activated.
+ */
+#define ENDPIPROC(x) \
+ .globl __pi_##x; \
+ .type __pi_##x, %function; \
+ .set __pi_##x, x; \
+ .size __pi_##x, . - x; \
+ ENDPROC(x)
+
#endif /* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 35a6778..5e13ad7 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -55,13 +55,42 @@
#define atomic_read(v) READ_ONCE((v)->counter)
#define atomic_set(v, i) (((v)->counter) = (i))
+
+#define atomic_add_return_relaxed atomic_add_return_relaxed
+#define atomic_add_return_acquire atomic_add_return_acquire
+#define atomic_add_return_release atomic_add_return_release
+#define atomic_add_return atomic_add_return
+
+#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v))
+#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v))
+#define atomic_inc_return_release(v) atomic_add_return_release(1, (v))
+#define atomic_inc_return(v) atomic_add_return(1, (v))
+
+#define atomic_sub_return_relaxed atomic_sub_return_relaxed
+#define atomic_sub_return_acquire atomic_sub_return_acquire
+#define atomic_sub_return_release atomic_sub_return_release
+#define atomic_sub_return atomic_sub_return
+
+#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v))
+#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v))
+#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v))
+#define atomic_dec_return(v) atomic_sub_return(1, (v))
+
+#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
+#define atomic_xchg_acquire(v, new) xchg_acquire(&((v)->counter), (new))
+#define atomic_xchg_release(v, new) xchg_release(&((v)->counter), (new))
#define atomic_xchg(v, new) xchg(&((v)->counter), (new))
+
+#define atomic_cmpxchg_relaxed(v, old, new) \
+ cmpxchg_relaxed(&((v)->counter), (old), (new))
+#define atomic_cmpxchg_acquire(v, old, new) \
+ cmpxchg_acquire(&((v)->counter), (old), (new))
+#define atomic_cmpxchg_release(v, old, new) \
+ cmpxchg_release(&((v)->counter), (old), (new))
#define atomic_cmpxchg(v, old, new) cmpxchg(&((v)->counter), (old), (new))
#define atomic_inc(v) atomic_add(1, (v))
#define atomic_dec(v) atomic_sub(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
@@ -75,13 +104,39 @@
#define ATOMIC64_INIT ATOMIC_INIT
#define atomic64_read atomic_read
#define atomic64_set atomic_set
+
+#define atomic64_add_return_relaxed atomic64_add_return_relaxed
+#define atomic64_add_return_acquire atomic64_add_return_acquire
+#define atomic64_add_return_release atomic64_add_return_release
+#define atomic64_add_return atomic64_add_return
+
+#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v))
+#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v))
+#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v))
+#define atomic64_inc_return(v) atomic64_add_return(1, (v))
+
+#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
+#define atomic64_sub_return_acquire atomic64_sub_return_acquire
+#define atomic64_sub_return_release atomic64_sub_return_release
+#define atomic64_sub_return atomic64_sub_return
+
+#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v))
+#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v))
+#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v))
+#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
+
+#define atomic64_xchg_relaxed atomic_xchg_relaxed
+#define atomic64_xchg_acquire atomic_xchg_acquire
+#define atomic64_xchg_release atomic_xchg_release
#define atomic64_xchg atomic_xchg
+
+#define atomic64_cmpxchg_relaxed atomic_cmpxchg_relaxed
+#define atomic64_cmpxchg_acquire atomic_cmpxchg_acquire
+#define atomic64_cmpxchg_release atomic_cmpxchg_release
#define atomic64_cmpxchg atomic_cmpxchg
#define atomic64_inc(v) atomic64_add(1, (v))
#define atomic64_dec(v) atomic64_sub(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0)
#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index b3b5c4a..74d0b8e 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -55,40 +55,47 @@
} \
__LL_SC_EXPORT(atomic_##op);
-#define ATOMIC_OP_RETURN(op, asm_op) \
+#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \
__LL_SC_INLINE int \
-__LL_SC_PREFIX(atomic_##op##_return(int i, atomic_t *v)) \
+__LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \
{ \
unsigned long tmp; \
int result; \
\
- asm volatile("// atomic_" #op "_return\n" \
+ asm volatile("// atomic_" #op "_return" #name "\n" \
" prfm pstl1strm, %2\n" \
-"1: ldxr %w0, %2\n" \
+"1: ld" #acq "xr %w0, %2\n" \
" " #asm_op " %w0, %w0, %w3\n" \
-" stlxr %w1, %w0, %2\n" \
-" cbnz %w1, 1b" \
+" st" #rel "xr %w1, %w0, %2\n" \
+" cbnz %w1, 1b\n" \
+" " #mb \
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i) \
- : "memory"); \
+ : cl); \
\
- smp_mb(); \
return result; \
} \
-__LL_SC_EXPORT(atomic_##op##_return);
+__LL_SC_EXPORT(atomic_##op##_return##name);
-#define ATOMIC_OPS(op, asm_op) \
- ATOMIC_OP(op, asm_op) \
- ATOMIC_OP_RETURN(op, asm_op)
+#define ATOMIC_OPS(...) \
+ ATOMIC_OP(__VA_ARGS__) \
+ ATOMIC_OP_RETURN( , dmb ish, , l, "memory", __VA_ARGS__)
-ATOMIC_OPS(add, add)
-ATOMIC_OPS(sub, sub)
+#define ATOMIC_OPS_RLX(...) \
+ ATOMIC_OPS(__VA_ARGS__) \
+ ATOMIC_OP_RETURN(_relaxed, , , , , __VA_ARGS__)\
+ ATOMIC_OP_RETURN(_acquire, , a, , "memory", __VA_ARGS__)\
+ ATOMIC_OP_RETURN(_release, , , l, "memory", __VA_ARGS__)
+
+ATOMIC_OPS_RLX(add, add)
+ATOMIC_OPS_RLX(sub, sub)
ATOMIC_OP(and, and)
ATOMIC_OP(andnot, bic)
ATOMIC_OP(or, orr)
ATOMIC_OP(xor, eor)
+#undef ATOMIC_OPS_RLX
#undef ATOMIC_OPS
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
@@ -111,40 +118,47 @@
} \
__LL_SC_EXPORT(atomic64_##op);
-#define ATOMIC64_OP_RETURN(op, asm_op) \
+#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \
__LL_SC_INLINE long \
-__LL_SC_PREFIX(atomic64_##op##_return(long i, atomic64_t *v)) \
+__LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \
{ \
long result; \
unsigned long tmp; \
\
- asm volatile("// atomic64_" #op "_return\n" \
+ asm volatile("// atomic64_" #op "_return" #name "\n" \
" prfm pstl1strm, %2\n" \
-"1: ldxr %0, %2\n" \
+"1: ld" #acq "xr %0, %2\n" \
" " #asm_op " %0, %0, %3\n" \
-" stlxr %w1, %0, %2\n" \
-" cbnz %w1, 1b" \
+" st" #rel "xr %w1, %0, %2\n" \
+" cbnz %w1, 1b\n" \
+" " #mb \
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
: "Ir" (i) \
- : "memory"); \
+ : cl); \
\
- smp_mb(); \
return result; \
} \
-__LL_SC_EXPORT(atomic64_##op##_return);
+__LL_SC_EXPORT(atomic64_##op##_return##name);
-#define ATOMIC64_OPS(op, asm_op) \
- ATOMIC64_OP(op, asm_op) \
- ATOMIC64_OP_RETURN(op, asm_op)
+#define ATOMIC64_OPS(...) \
+ ATOMIC64_OP(__VA_ARGS__) \
+ ATOMIC64_OP_RETURN(, dmb ish, , l, "memory", __VA_ARGS__)
-ATOMIC64_OPS(add, add)
-ATOMIC64_OPS(sub, sub)
+#define ATOMIC64_OPS_RLX(...) \
+ ATOMIC64_OPS(__VA_ARGS__) \
+ ATOMIC64_OP_RETURN(_relaxed,, , , , __VA_ARGS__) \
+ ATOMIC64_OP_RETURN(_acquire,, a, , "memory", __VA_ARGS__) \
+ ATOMIC64_OP_RETURN(_release,, , l, "memory", __VA_ARGS__)
+
+ATOMIC64_OPS_RLX(add, add)
+ATOMIC64_OPS_RLX(sub, sub)
ATOMIC64_OP(and, and)
ATOMIC64_OP(andnot, bic)
ATOMIC64_OP(or, orr)
ATOMIC64_OP(xor, eor)
+#undef ATOMIC64_OPS_RLX
#undef ATOMIC64_OPS
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP
@@ -172,7 +186,7 @@
}
__LL_SC_EXPORT(atomic64_dec_if_positive);
-#define __CMPXCHG_CASE(w, sz, name, mb, rel, cl) \
+#define __CMPXCHG_CASE(w, sz, name, mb, acq, rel, cl) \
__LL_SC_INLINE unsigned long \
__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr, \
unsigned long old, \
@@ -182,7 +196,7 @@
\
asm volatile( \
" prfm pstl1strm, %[v]\n" \
- "1: ldxr" #sz "\t%" #w "[oldval], %[v]\n" \
+ "1: ld" #acq "xr" #sz "\t%" #w "[oldval], %[v]\n" \
" eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \
" cbnz %" #w "[tmp], 2f\n" \
" st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \
@@ -199,14 +213,22 @@
} \
__LL_SC_EXPORT(__cmpxchg_case_##name);
-__CMPXCHG_CASE(w, b, 1, , , )
-__CMPXCHG_CASE(w, h, 2, , , )
-__CMPXCHG_CASE(w, , 4, , , )
-__CMPXCHG_CASE( , , 8, , , )
-__CMPXCHG_CASE(w, b, mb_1, dmb ish, l, "memory")
-__CMPXCHG_CASE(w, h, mb_2, dmb ish, l, "memory")
-__CMPXCHG_CASE(w, , mb_4, dmb ish, l, "memory")
-__CMPXCHG_CASE( , , mb_8, dmb ish, l, "memory")
+__CMPXCHG_CASE(w, b, 1, , , , )
+__CMPXCHG_CASE(w, h, 2, , , , )
+__CMPXCHG_CASE(w, , 4, , , , )
+__CMPXCHG_CASE( , , 8, , , , )
+__CMPXCHG_CASE(w, b, acq_1, , a, , "memory")
+__CMPXCHG_CASE(w, h, acq_2, , a, , "memory")
+__CMPXCHG_CASE(w, , acq_4, , a, , "memory")
+__CMPXCHG_CASE( , , acq_8, , a, , "memory")
+__CMPXCHG_CASE(w, b, rel_1, , , l, "memory")
+__CMPXCHG_CASE(w, h, rel_2, , , l, "memory")
+__CMPXCHG_CASE(w, , rel_4, , , l, "memory")
+__CMPXCHG_CASE( , , rel_8, , , l, "memory")
+__CMPXCHG_CASE(w, b, mb_1, dmb ish, , l, "memory")
+__CMPXCHG_CASE(w, h, mb_2, dmb ish, , l, "memory")
+__CMPXCHG_CASE(w, , mb_4, dmb ish, , l, "memory")
+__CMPXCHG_CASE( , , mb_8, dmb ish, , l, "memory")
#undef __CMPXCHG_CASE
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 55d740e..1fce790 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -75,25 +75,33 @@
: "x30");
}
-static inline int atomic_add_return(int i, atomic_t *v)
-{
- register int w0 asm ("w0") = i;
- register atomic_t *x1 asm ("x1") = v;
-
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC(add_return),
- /* LSE atomics */
- " ldaddal %w[i], w30, %[v]\n"
- " add %w[i], %w[i], w30")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
- : "r" (x1)
- : "x30", "memory");
-
- return w0;
+#define ATOMIC_OP_ADD_RETURN(name, mb, cl...) \
+static inline int atomic_add_return##name(int i, atomic_t *v) \
+{ \
+ register int w0 asm ("w0") = i; \
+ register atomic_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC(add_return##name), \
+ /* LSE atomics */ \
+ " ldadd" #mb " %w[i], w30, %[v]\n" \
+ " add %w[i], %w[i], w30") \
+ : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : "x30" , ##cl); \
+ \
+ return w0; \
}
+ATOMIC_OP_ADD_RETURN(_relaxed, )
+ATOMIC_OP_ADD_RETURN(_acquire, a, "memory")
+ATOMIC_OP_ADD_RETURN(_release, l, "memory")
+ATOMIC_OP_ADD_RETURN( , al, "memory")
+
+#undef ATOMIC_OP_ADD_RETURN
+
static inline void atomic_and(int i, atomic_t *v)
{
register int w0 asm ("w0") = i;
@@ -128,27 +136,34 @@
: "x30");
}
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
- register int w0 asm ("w0") = i;
- register atomic_t *x1 asm ("x1") = v;
-
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC(sub_return)
- " nop",
- /* LSE atomics */
- " neg %w[i], %w[i]\n"
- " ldaddal %w[i], w30, %[v]\n"
- " add %w[i], %w[i], w30")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
- : "r" (x1)
- : "x30", "memory");
-
- return w0;
+#define ATOMIC_OP_SUB_RETURN(name, mb, cl...) \
+static inline int atomic_sub_return##name(int i, atomic_t *v) \
+{ \
+ register int w0 asm ("w0") = i; \
+ register atomic_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC(sub_return##name) \
+ " nop", \
+ /* LSE atomics */ \
+ " neg %w[i], %w[i]\n" \
+ " ldadd" #mb " %w[i], w30, %[v]\n" \
+ " add %w[i], %w[i], w30") \
+ : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : "x30" , ##cl); \
+ \
+ return w0; \
}
+ATOMIC_OP_SUB_RETURN(_relaxed, )
+ATOMIC_OP_SUB_RETURN(_acquire, a, "memory")
+ATOMIC_OP_SUB_RETURN(_release, l, "memory")
+ATOMIC_OP_SUB_RETURN( , al, "memory")
+
+#undef ATOMIC_OP_SUB_RETURN
#undef __LL_SC_ATOMIC
#define __LL_SC_ATOMIC64(op) __LL_SC_CALL(atomic64_##op)
@@ -201,25 +216,33 @@
: "x30");
}
-static inline long atomic64_add_return(long i, atomic64_t *v)
-{
- register long x0 asm ("x0") = i;
- register atomic64_t *x1 asm ("x1") = v;
-
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC64(add_return),
- /* LSE atomics */
- " ldaddal %[i], x30, %[v]\n"
- " add %[i], %[i], x30")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
- : "r" (x1)
- : "x30", "memory");
-
- return x0;
+#define ATOMIC64_OP_ADD_RETURN(name, mb, cl...) \
+static inline long atomic64_add_return##name(long i, atomic64_t *v) \
+{ \
+ register long x0 asm ("x0") = i; \
+ register atomic64_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC64(add_return##name), \
+ /* LSE atomics */ \
+ " ldadd" #mb " %[i], x30, %[v]\n" \
+ " add %[i], %[i], x30") \
+ : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : "x30" , ##cl); \
+ \
+ return x0; \
}
+ATOMIC64_OP_ADD_RETURN(_relaxed, )
+ATOMIC64_OP_ADD_RETURN(_acquire, a, "memory")
+ATOMIC64_OP_ADD_RETURN(_release, l, "memory")
+ATOMIC64_OP_ADD_RETURN( , al, "memory")
+
+#undef ATOMIC64_OP_ADD_RETURN
+
static inline void atomic64_and(long i, atomic64_t *v)
{
register long x0 asm ("x0") = i;
@@ -254,27 +277,35 @@
: "x30");
}
-static inline long atomic64_sub_return(long i, atomic64_t *v)
-{
- register long x0 asm ("x0") = i;
- register atomic64_t *x1 asm ("x1") = v;
-
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " nop\n"
- __LL_SC_ATOMIC64(sub_return)
- " nop",
- /* LSE atomics */
- " neg %[i], %[i]\n"
- " ldaddal %[i], x30, %[v]\n"
- " add %[i], %[i], x30")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
- : "r" (x1)
- : "x30", "memory");
-
- return x0;
+#define ATOMIC64_OP_SUB_RETURN(name, mb, cl...) \
+static inline long atomic64_sub_return##name(long i, atomic64_t *v) \
+{ \
+ register long x0 asm ("x0") = i; \
+ register atomic64_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC64(sub_return##name) \
+ " nop", \
+ /* LSE atomics */ \
+ " neg %[i], %[i]\n" \
+ " ldadd" #mb " %[i], x30, %[v]\n" \
+ " add %[i], %[i], x30") \
+ : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : "x30" , ##cl); \
+ \
+ return x0; \
}
+ATOMIC64_OP_SUB_RETURN(_relaxed, )
+ATOMIC64_OP_SUB_RETURN(_acquire, a, "memory")
+ATOMIC64_OP_SUB_RETURN(_release, l, "memory")
+ATOMIC64_OP_SUB_RETURN( , al, "memory")
+
+#undef ATOMIC64_OP_SUB_RETURN
+
static inline long atomic64_dec_if_positive(atomic64_t *v)
{
register long x0 asm ("x0") = (long)v;
@@ -333,14 +364,22 @@
return x0; \
}
-__CMPXCHG_CASE(w, b, 1, )
-__CMPXCHG_CASE(w, h, 2, )
-__CMPXCHG_CASE(w, , 4, )
-__CMPXCHG_CASE(x, , 8, )
-__CMPXCHG_CASE(w, b, mb_1, al, "memory")
-__CMPXCHG_CASE(w, h, mb_2, al, "memory")
-__CMPXCHG_CASE(w, , mb_4, al, "memory")
-__CMPXCHG_CASE(x, , mb_8, al, "memory")
+__CMPXCHG_CASE(w, b, 1, )
+__CMPXCHG_CASE(w, h, 2, )
+__CMPXCHG_CASE(w, , 4, )
+__CMPXCHG_CASE(x, , 8, )
+__CMPXCHG_CASE(w, b, acq_1, a, "memory")
+__CMPXCHG_CASE(w, h, acq_2, a, "memory")
+__CMPXCHG_CASE(w, , acq_4, a, "memory")
+__CMPXCHG_CASE(x, , acq_8, a, "memory")
+__CMPXCHG_CASE(w, b, rel_1, l, "memory")
+__CMPXCHG_CASE(w, h, rel_2, l, "memory")
+__CMPXCHG_CASE(w, , rel_4, l, "memory")
+__CMPXCHG_CASE(x, , rel_8, l, "memory")
+__CMPXCHG_CASE(w, b, mb_1, al, "memory")
+__CMPXCHG_CASE(w, h, mb_2, al, "memory")
+__CMPXCHG_CASE(w, , mb_4, al, "memory")
+__CMPXCHG_CASE(x, , mb_8, al, "memory")
#undef __LL_SC_CMPXCHG
#undef __CMPXCHG_CASE
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index c75b8d0..54efeda 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -115,6 +115,13 @@
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);
+static inline void __local_flush_icache_all(void)
+{
+ asm("ic iallu");
+ dsb(nsh);
+ isb();
+}
+
static inline void __flush_icache_all(void)
{
asm("ic ialluis");
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 899e9f1..9ea611e 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -25,154 +25,151 @@
#include <asm/barrier.h>
#include <asm/lse.h>
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
-{
- unsigned long ret, tmp;
-
- switch (size) {
- case 1:
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " prfm pstl1strm, %2\n"
- "1: ldxrb %w0, %2\n"
- " stlxrb %w1, %w3, %2\n"
- " cbnz %w1, 1b\n"
- " dmb ish",
- /* LSE atomics */
- " nop\n"
- " nop\n"
- " swpalb %w3, %w0, %2\n"
- " nop\n"
- " nop")
- : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
- : "r" (x)
- : "memory");
- break;
- case 2:
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " prfm pstl1strm, %2\n"
- "1: ldxrh %w0, %2\n"
- " stlxrh %w1, %w3, %2\n"
- " cbnz %w1, 1b\n"
- " dmb ish",
- /* LSE atomics */
- " nop\n"
- " nop\n"
- " swpalh %w3, %w0, %2\n"
- " nop\n"
- " nop")
- : "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
- : "r" (x)
- : "memory");
- break;
- case 4:
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " prfm pstl1strm, %2\n"
- "1: ldxr %w0, %2\n"
- " stlxr %w1, %w3, %2\n"
- " cbnz %w1, 1b\n"
- " dmb ish",
- /* LSE atomics */
- " nop\n"
- " nop\n"
- " swpal %w3, %w0, %2\n"
- " nop\n"
- " nop")
- : "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
- : "r" (x)
- : "memory");
- break;
- case 8:
- asm volatile(ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " stlxr %w1, %3, %2\n"
- " cbnz %w1, 1b\n"
- " dmb ish",
- /* LSE atomics */
- " nop\n"
- " nop\n"
- " swpal %3, %0, %2\n"
- " nop\n"
- " nop")
- : "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
- : "r" (x)
- : "memory");
- break;
- default:
- BUILD_BUG();
- }
-
- return ret;
+/*
+ * We need separate acquire parameters for ll/sc and lse, since the full
+ * barrier case is generated as release+dmb for the former and
+ * acquire+release for the latter.
+ */
+#define __XCHG_CASE(w, sz, name, mb, nop_lse, acq, acq_lse, rel, cl) \
+static inline unsigned long __xchg_case_##name(unsigned long x, \
+ volatile void *ptr) \
+{ \
+ unsigned long ret, tmp; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " prfm pstl1strm, %2\n" \
+ "1: ld" #acq "xr" #sz "\t%" #w "0, %2\n" \
+ " st" #rel "xr" #sz "\t%w1, %" #w "3, %2\n" \
+ " 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" \
+ " " #nop_lse) \
+ : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) \
+ : "r" (x) \
+ : cl); \
+ \
+ return ret; \
}
-#define xchg(ptr,x) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __ret = (__typeof__(*(ptr))) \
- __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \
- __ret; \
-})
+__XCHG_CASE(w, b, 1, , , , , , )
+__XCHG_CASE(w, h, 2, , , , , , )
+__XCHG_CASE(w, , 4, , , , , , )
+__XCHG_CASE( , , 8, , , , , , )
+__XCHG_CASE(w, b, acq_1, , , a, a, , "memory")
+__XCHG_CASE(w, h, acq_2, , , a, a, , "memory")
+__XCHG_CASE(w, , acq_4, , , a, a, , "memory")
+__XCHG_CASE( , , acq_8, , , a, a, , "memory")
+__XCHG_CASE(w, b, rel_1, , , , , l, "memory")
+__XCHG_CASE(w, h, rel_2, , , , , l, "memory")
+__XCHG_CASE(w, , rel_4, , , , , l, "memory")
+__XCHG_CASE( , , rel_8, , , , , l, "memory")
+__XCHG_CASE(w, b, mb_1, dmb ish, nop, , a, l, "memory")
+__XCHG_CASE(w, h, mb_2, dmb ish, nop, , a, l, "memory")
+__XCHG_CASE(w, , mb_4, dmb ish, nop, , a, l, "memory")
+__XCHG_CASE( , , mb_8, dmb ish, nop, , a, l, "memory")
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
- unsigned long new, int size)
-{
- switch (size) {
- case 1:
- return __cmpxchg_case_1(ptr, (u8)old, new);
- case 2:
- return __cmpxchg_case_2(ptr, (u16)old, new);
- case 4:
- return __cmpxchg_case_4(ptr, old, new);
- case 8:
- return __cmpxchg_case_8(ptr, old, new);
- default:
- BUILD_BUG();
- }
+#undef __XCHG_CASE
- unreachable();
+#define __XCHG_GEN(sfx) \
+static inline unsigned long __xchg##sfx(unsigned long x, \
+ volatile void *ptr, \
+ int size) \
+{ \
+ switch (size) { \
+ case 1: \
+ return __xchg_case##sfx##_1(x, ptr); \
+ case 2: \
+ return __xchg_case##sfx##_2(x, ptr); \
+ case 4: \
+ return __xchg_case##sfx##_4(x, ptr); \
+ case 8: \
+ return __xchg_case##sfx##_8(x, ptr); \
+ default: \
+ BUILD_BUG(); \
+ } \
+ \
+ unreachable(); \
}
-static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
- unsigned long new, int size)
-{
- switch (size) {
- case 1:
- return __cmpxchg_case_mb_1(ptr, (u8)old, new);
- case 2:
- return __cmpxchg_case_mb_2(ptr, (u16)old, new);
- case 4:
- return __cmpxchg_case_mb_4(ptr, old, new);
- case 8:
- return __cmpxchg_case_mb_8(ptr, old, new);
- default:
- BUILD_BUG();
- }
+__XCHG_GEN()
+__XCHG_GEN(_acq)
+__XCHG_GEN(_rel)
+__XCHG_GEN(_mb)
- unreachable();
+#undef __XCHG_GEN
+
+#define __xchg_wrapper(sfx, ptr, x) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __ret = (__typeof__(*(ptr))) \
+ __xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+ __ret; \
+})
+
+/* xchg */
+#define xchg_relaxed(...) __xchg_wrapper( , __VA_ARGS__)
+#define xchg_acquire(...) __xchg_wrapper(_acq, __VA_ARGS__)
+#define xchg_release(...) __xchg_wrapper(_rel, __VA_ARGS__)
+#define xchg(...) __xchg_wrapper( _mb, __VA_ARGS__)
+
+#define __CMPXCHG_GEN(sfx) \
+static inline unsigned long __cmpxchg##sfx(volatile void *ptr, \
+ unsigned long old, \
+ unsigned long new, \
+ int size) \
+{ \
+ switch (size) { \
+ case 1: \
+ return __cmpxchg_case##sfx##_1(ptr, (u8)old, new); \
+ case 2: \
+ return __cmpxchg_case##sfx##_2(ptr, (u16)old, new); \
+ case 4: \
+ return __cmpxchg_case##sfx##_4(ptr, old, new); \
+ case 8: \
+ return __cmpxchg_case##sfx##_8(ptr, old, new); \
+ default: \
+ BUILD_BUG(); \
+ } \
+ \
+ unreachable(); \
}
-#define cmpxchg(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __ret = (__typeof__(*(ptr))) \
- __cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- __ret; \
+__CMPXCHG_GEN()
+__CMPXCHG_GEN(_acq)
+__CMPXCHG_GEN(_rel)
+__CMPXCHG_GEN(_mb)
+
+#undef __CMPXCHG_GEN
+
+#define __cmpxchg_wrapper(sfx, ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __ret = (__typeof__(*(ptr))) \
+ __cmpxchg##sfx((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))); \
+ __ret; \
})
-#define cmpxchg_local(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __ret = (__typeof__(*(ptr))) \
- __cmpxchg((ptr), (unsigned long)(o), \
- (unsigned long)(n), sizeof(*(ptr))); \
- __ret; \
-})
+/* cmpxchg */
+#define cmpxchg_relaxed(...) __cmpxchg_wrapper( , __VA_ARGS__)
+#define cmpxchg_acquire(...) __cmpxchg_wrapper(_acq, __VA_ARGS__)
+#define cmpxchg_release(...) __cmpxchg_wrapper(_rel, __VA_ARGS__)
+#define cmpxchg(...) __cmpxchg_wrapper( _mb, __VA_ARGS__)
+#define cmpxchg_local cmpxchg_relaxed
+/* cmpxchg64 */
+#define cmpxchg64_relaxed cmpxchg_relaxed
+#define cmpxchg64_acquire cmpxchg_acquire
+#define cmpxchg64_release cmpxchg_release
+#define cmpxchg64 cmpxchg
+#define cmpxchg64_local cmpxchg_local
+
+/* cmpxchg_double */
#define system_has_cmpxchg_double() 1
#define __cmpxchg_double_check(ptr1, ptr2) \
@@ -202,6 +199,7 @@
__ret; \
})
+/* this_cpu_cmpxchg */
#define _protect_cmpxchg_local(pcp, o, n) \
({ \
typeof(*raw_cpu_ptr(&(pcp))) __ret; \
@@ -227,9 +225,4 @@
__ret; \
})
-#define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n))
-#define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n))
-
-#define cmpxchg64_relaxed(ptr,o,n) cmpxchg_local((ptr),(o),(n))
-
#endif /* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 8e797b2..b5e9cee 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -63,4 +63,8 @@
void cpuinfo_store_cpu(void);
void __init cpuinfo_store_boot_cpu(void);
+void __init init_cpu_features(struct cpuinfo_arm64 *info);
+void update_cpu_features(int cpu, struct cpuinfo_arm64 *info,
+ struct cpuinfo_arm64 *boot);
+
#endif /* __ASM_CPU_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 1715707..ca46210 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -10,6 +10,7 @@
#define __ASM_CPUFEATURE_H
#include <asm/hwcap.h>
+#include <asm/sysreg.h>
/*
* In the arm64 world (as in the ARM world), elf_hwcap is used both internally
@@ -34,11 +35,42 @@
#include <linux/kernel.h>
+/* CPU feature register tracking */
+enum ftr_type {
+ FTR_EXACT, /* Use a predefined safe value */
+ FTR_LOWER_SAFE, /* Smaller value is safe */
+ FTR_HIGHER_SAFE,/* Bigger value is safe */
+};
+
+#define FTR_STRICT true /* SANITY check strict matching required */
+#define FTR_NONSTRICT false /* SANITY check ignored */
+
+struct arm64_ftr_bits {
+ bool strict; /* CPU Sanity check: strict matching required ? */
+ enum ftr_type type;
+ u8 shift;
+ u8 width;
+ s64 safe_val; /* safe value for discrete features */
+};
+
+/*
+ * @arm64_ftr_reg - Feature register
+ * @strict_mask Bits which should match across all CPUs for sanity.
+ * @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;
+};
+
struct arm64_cpu_capabilities {
const char *desc;
u16 capability;
bool (*matches)(const struct arm64_cpu_capabilities *);
- void (*enable)(void);
+ void (*enable)(void *); /* Called on all active CPUs */
union {
struct { /* To be used for erratum handling only */
u32 midr_model;
@@ -46,8 +78,11 @@
};
struct { /* Feature register checking */
+ u32 sys_reg;
int field_pos;
int min_field_value;
+ int hwcap_type;
+ unsigned long hwcap;
};
};
};
@@ -75,19 +110,59 @@
__set_bit(num, cpu_hwcaps);
}
-static inline int __attribute_const__ cpuid_feature_extract_field(u64 features,
- int field)
+static inline int __attribute_const__
+cpuid_feature_extract_field_width(u64 features, int field, int width)
{
- return (s64)(features << (64 - 4 - field)) >> (64 - 4);
+ return (s64)(features << (64 - width - field)) >> (64 - width);
}
+static inline int __attribute_const__
+cpuid_feature_extract_field(u64 features, int field)
+{
+ return cpuid_feature_extract_field_width(features, field, 4);
+}
-void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
+static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
+{
+ return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
+}
+
+static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
+{
+ return cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width);
+}
+
+static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
+{
+ return cpuid_feature_extract_field(mmfr0, ID_AA64MMFR0_BIGENDEL_SHIFT) == 0x1 ||
+ cpuid_feature_extract_field(mmfr0, ID_AA64MMFR0_BIGENDEL0_SHIFT) == 0x1;
+}
+
+void __init setup_cpu_features(void);
+
+void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
const char *info);
void check_local_cpu_errata(void);
-void check_local_cpu_features(void);
-bool cpu_supports_mixed_endian_el0(void);
-bool system_supports_mixed_endian_el0(void);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void verify_local_cpu_capabilities(void);
+#else
+static inline void verify_local_cpu_capabilities(void)
+{
+}
+#endif
+
+u64 read_system_reg(u32 id);
+
+static inline bool cpu_supports_mixed_endian_el0(void)
+{
+ return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
+}
+
+static inline bool system_supports_mixed_endian_el0(void)
+{
+ return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));
+}
#endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index ee6403d..31678b2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -72,15 +72,6 @@
#define APM_CPU_PART_POTENZA 0x000
-#define ID_AA64MMFR0_BIGENDEL0_SHIFT 16
-#define ID_AA64MMFR0_BIGENDEL0_MASK (0xf << ID_AA64MMFR0_BIGENDEL0_SHIFT)
-#define ID_AA64MMFR0_BIGENDEL0(mmfr0) \
- (((mmfr0) & ID_AA64MMFR0_BIGENDEL0_MASK) >> ID_AA64MMFR0_BIGENDEL0_SHIFT)
-#define ID_AA64MMFR0_BIGEND_SHIFT 8
-#define ID_AA64MMFR0_BIGEND_MASK (0xf << ID_AA64MMFR0_BIGEND_SHIFT)
-#define ID_AA64MMFR0_BIGEND(mmfr0) \
- (((mmfr0) & ID_AA64MMFR0_BIGEND_MASK) >> ID_AA64MMFR0_BIGEND_SHIFT)
-
#ifndef __ASSEMBLY__
/*
@@ -112,12 +103,6 @@
{
return read_cpuid(CTR_EL0);
}
-
-static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
-{
- return (ID_AA64MMFR0_BIGEND(mmfr0) == 0x1) ||
- (ID_AA64MMFR0_BIGENDEL0(mmfr0) == 0x1);
-}
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 8b9884c..3097045 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -17,6 +17,7 @@
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
+#include <linux/sizes.h>
#include <asm/boot.h>
#include <asm/page.h>
@@ -55,11 +56,7 @@
* Temporary boot-time mappings, used by early_ioremap(),
* before ioremap() is functional.
*/
-#ifdef CONFIG_ARM64_64K_PAGES
-#define NR_FIX_BTMAPS 4
-#else
-#define NR_FIX_BTMAPS 64
-#endif
+#define NR_FIX_BTMAPS (SZ_256K / PAGE_SIZE)
#define FIX_BTMAPS_SLOTS 7
#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 4c47cb2..e54415e 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -17,6 +17,7 @@
#define __ASM_HW_BREAKPOINT_H
#include <asm/cputype.h>
+#include <asm/cpufeature.h>
#ifdef __KERNEL__
@@ -137,13 +138,17 @@
/* Determine number of BRP registers available. */
static inline int get_num_brps(void)
{
- return ((read_cpuid(ID_AA64DFR0_EL1) >> 12) & 0xf) + 1;
+ return 1 +
+ cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+ ID_AA64DFR0_BRPS_SHIFT);
}
/* Determine number of WRP registers available. */
static inline int get_num_wrps(void)
{
- return ((read_cpuid(ID_AA64DFR0_EL1) >> 20) & 0xf) + 1;
+ return 1 +
+ cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+ ID_AA64DFR0_WRPS_SHIFT);
}
#endif /* __KERNEL__ */
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 0ad7351..400b80b 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -52,6 +52,14 @@
extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
#endif
+enum {
+ CAP_HWCAP = 1,
+#ifdef CONFIG_COMPAT
+ CAP_COMPAT_HWCAP,
+ CAP_COMPAT_HWCAP2,
+#endif
+};
+
extern unsigned long elf_hwcap;
#endif
#endif
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index bbb251b..0916929 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -7,7 +7,6 @@
struct pt_regs;
-extern void migrate_irqs(void);
extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
static inline void acpi_irq_init(void)
diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
new file mode 100644
index 0000000..2774fa3
--- /dev/null
+++ b/arch/arm64/include/asm/kasan.h
@@ -0,0 +1,38 @@
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_KASAN
+
+#include <linux/linkage.h>
+#include <asm/memory.h>
+
+/*
+ * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
+ * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/8 of kernel virtual addresses.
+ */
+#define KASAN_SHADOW_START (VA_START)
+#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1UL << (VA_BITS - 3)))
+
+/*
+ * This value is used to map an address to the corresponding shadow
+ * address by the following formula:
+ * shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET;
+ *
+ * (1 << 61) shadow addresses - [KASAN_SHADOW_OFFSET,KASAN_SHADOW_END]
+ * cover all 64-bits of virtual addresses. So KASAN_SHADOW_OFFSET
+ * should satisfy the following equation:
+ * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - (1ULL << 61)
+ */
+#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << (64 - 3)))
+
+void kasan_init(void);
+asmlinkage void kasan_early_init(void);
+
+#else
+static inline void kasan_init(void) { }
+#endif
+
+#endif
+#endif
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
new file mode 100644
index 0000000..a459714
--- /dev/null
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -0,0 +1,83 @@
+/*
+ * Kernel page table mapping
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * 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_KERNEL_PGTABLE_H
+#define __ASM_KERNEL_PGTABLE_H
+
+
+/*
+ * The linear mapping and the start of memory are both 2M aligned (per
+ * the arm64 booting.txt requirements). Hence we can use section mapping
+ * with 4K (section size = 2M) but not with 16K (section size = 32M) or
+ * 64K (section size = 512M).
+ */
+#ifdef CONFIG_ARM64_4K_PAGES
+#define ARM64_SWAPPER_USES_SECTION_MAPS 1
+#else
+#define ARM64_SWAPPER_USES_SECTION_MAPS 0
+#endif
+
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. Both require pgd, pud (4 levels only) and pmd tables to (section)
+ * map the kernel. With the 64K page configuration, swapper and idmap need to
+ * map to pte level. The swapper also maps the FDT (see __create_page_tables
+ * for more information). Note that the number of ID map translation levels
+ * could be increased on the fly if system RAM is out of reach for the default
+ * VA range, so pages required to map highest possible PA are reserved in all
+ * cases.
+ */
+#if ARM64_SWAPPER_USES_SECTION_MAPS
+#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1)
+#define IDMAP_PGTABLE_LEVELS (ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT) - 1)
+#else
+#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS)
+#define IDMAP_PGTABLE_LEVELS (ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT))
+#endif
+
+#define SWAPPER_DIR_SIZE (SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
+#define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
+
+/* Initial memory map size */
+#if ARM64_SWAPPER_USES_SECTION_MAPS
+#define SWAPPER_BLOCK_SHIFT SECTION_SHIFT
+#define SWAPPER_BLOCK_SIZE SECTION_SIZE
+#define SWAPPER_TABLE_SHIFT PUD_SHIFT
+#else
+#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT
+#define SWAPPER_BLOCK_SIZE PAGE_SIZE
+#define SWAPPER_TABLE_SHIFT PMD_SHIFT
+#endif
+
+/* The size of the initial kernel direct mapping */
+#define SWAPPER_INIT_MAP_SIZE (_AC(1, UL) << SWAPPER_TABLE_SHIFT)
+
+/*
+ * Initial memory map attributes.
+ */
+#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#if ARM64_SWAPPER_USES_SECTION_MAPS
+#define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
+#else
+#define SWAPPER_MM_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS)
+#endif
+
+
+#endif /* __ASM_KERNEL_PGTABLE_H */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 6b4c3ad..11ccf6c 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -42,12 +42,14 @@
* PAGE_OFFSET - the virtual address of the start of the kernel image (top
* (VA_BITS - 1))
* VA_BITS - the maximum number of bits for virtual addresses.
+ * VA_START - the first kernel virtual address.
* TASK_SIZE - the maximum size of a user space task.
* TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
* The module space lives between the addresses given by TASK_SIZE
* and PAGE_OFFSET - it must be within 128MB of the kernel text.
*/
#define VA_BITS (CONFIG_ARM64_VA_BITS)
+#define VA_START (UL(0xffffffffffffffff) << VA_BITS)
#define PAGE_OFFSET (UL(0xffffffffffffffff) << (VA_BITS - 1))
#define MODULES_END (PAGE_OFFSET)
#define MODULES_VADDR (MODULES_END - SZ_64M)
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 0302087..990124a 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,15 +17,16 @@
#define __ASM_MMU_H
typedef struct {
- unsigned int id;
- raw_spinlock_t id_lock;
- void *vdso;
+ atomic64_t id;
+ void *vdso;
} mm_context_t;
-#define INIT_MM_CONTEXT(name) \
- .context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock),
-
-#define ASID(mm) ((mm)->context.id & 0xffff)
+/*
+ * This macro is only used by the TLBI code, which cannot race with an
+ * ASID change and therefore doesn't need to reload the counter using
+ * atomic64_read.
+ */
+#define ASID(mm) ((mm)->context.id.counter & 0xffff)
extern void paging_init(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 8ec41e5..c0e8789 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -28,13 +28,6 @@
#include <asm/cputype.h>
#include <asm/pgtable.h>
-#define MAX_ASID_BITS 16
-
-extern unsigned int cpu_last_asid;
-
-void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void __new_context(struct mm_struct *mm);
-
#ifdef CONFIG_PID_IN_CONTEXTIDR
static inline void contextidr_thread_switch(struct task_struct *next)
{
@@ -77,96 +70,38 @@
unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)));
}
-static inline void __cpu_set_tcr_t0sz(u64 t0sz)
-{
- unsigned long tcr;
-
- if (__cpu_uses_extended_idmap())
- 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));
-}
-
-/*
- * Set TCR.T0SZ to the value appropriate for activating the identity map.
- */
-static inline void cpu_set_idmap_tcr_t0sz(void)
-{
- __cpu_set_tcr_t0sz(idmap_t0sz);
-}
-
/*
* Set TCR.T0SZ to its default value (based on VA_BITS)
*/
static inline void cpu_set_default_tcr_t0sz(void)
{
- __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS));
+ unsigned long tcr;
+
+ 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"(TCR_T0SZ(VA_BITS)), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
}
-static inline void switch_new_context(struct mm_struct *mm)
-{
- unsigned long flags;
-
- __new_context(mm);
-
- local_irq_save(flags);
- cpu_switch_mm(mm->pgd, mm);
- local_irq_restore(flags);
-}
-
-static inline void check_and_switch_context(struct mm_struct *mm,
- struct task_struct *tsk)
-{
- /*
- * Required during context switch to avoid speculative page table
- * walking with the wrong TTBR.
- */
- cpu_set_reserved_ttbr0();
-
- if (!((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS))
- /*
- * The ASID is from the current generation, just switch to the
- * new pgd. This condition is only true for calls from
- * context_switch() and interrupts are already disabled.
- */
- cpu_switch_mm(mm->pgd, mm);
- else if (irqs_disabled())
- /*
- * Defer the new ASID allocation until after the context
- * switch critical region since __new_context() cannot be
- * called with interrupts disabled.
- */
- set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
- else
- /*
- * That is a direct call to switch_mm() or activate_mm() with
- * interrupts enabled and a new context.
- */
- switch_new_context(mm);
-}
-
-#define init_new_context(tsk,mm) (__init_new_context(tsk,mm),0)
+/*
+ * It would be nice to return ASIDs back to the allocator, but unfortunately
+ * that introduces a race with a generation rollover where we could erroneously
+ * free an ASID allocated in a future generation. We could workaround this by
+ * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap),
+ * but we'd then need to make sure that we didn't dirty any TLBs afterwards.
+ * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you
+ * take CPU migration into account.
+ */
#define destroy_context(mm) do { } while(0)
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
-#define finish_arch_post_lock_switch \
- finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
-{
- if (test_and_clear_thread_flag(TIF_SWITCH_MM)) {
- struct mm_struct *mm = current->mm;
- unsigned long flags;
-
- __new_context(mm);
-
- local_irq_save(flags);
- cpu_switch_mm(mm->pgd, mm);
- local_irq_restore(flags);
- }
-}
+#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; })
/*
* This is called when "tsk" is about to enter lazy TLB mode.
@@ -194,6 +129,9 @@
{
unsigned int cpu = smp_processor_id();
+ if (prev == next)
+ return;
+
/*
* init_mm.pgd does not contain any user mappings and it is always
* active for kernel addresses in TTBR1. Just set the reserved TTBR0.
@@ -203,8 +141,7 @@
return;
}
- if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
- check_and_switch_context(next, tsk);
+ check_and_switch_context(next, cpu);
}
#define deactivate_mm(tsk,mm) do { } while (0)
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 7d9c7e4..9b2f5a9 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -20,31 +20,22 @@
#define __ASM_PAGE_H
/* PAGE_SHIFT determines the page size */
+/* CONT_SHIFT determines the number of pages which can be tracked together */
#ifdef CONFIG_ARM64_64K_PAGES
#define PAGE_SHIFT 16
+#define CONT_SHIFT 5
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define PAGE_SHIFT 14
+#define CONT_SHIFT 7
#else
#define PAGE_SHIFT 12
+#define CONT_SHIFT 4
#endif
-#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))
-/*
- * The idmap and swapper page tables need some space reserved in the kernel
- * image. Both require pgd, pud (4 levels only) and pmd tables to (section)
- * map the kernel. With the 64K page configuration, swapper and idmap need to
- * map to pte level. The swapper also maps the FDT (see __create_page_tables
- * for more information). Note that the number of ID map translation levels
- * could be increased on the fly if system RAM is out of reach for the default
- * VA range, so 3 pages are reserved in all cases.
- */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS)
-#else
-#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1)
-#endif
-
-#define SWAPPER_DIR_SIZE (SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
-#define IDMAP_DIR_SIZE (3 * PAGE_SIZE)
+#define CONT_SIZE (_AC(1, UL) << (CONT_SHIFT + PAGE_SHIFT))
+#define CONT_MASK (~(CONT_SIZE-1))
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 7642056..c150539 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -27,6 +27,7 @@
#define check_pgt_cache() do { } while (0)
#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
#if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 24154b0..d6739e8 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -16,13 +16,46 @@
#ifndef __ASM_PGTABLE_HWDEF_H
#define __ASM_PGTABLE_HWDEF_H
+/*
+ * Number of page-table levels required to address 'va_bits' wide
+ * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
+ * bits with (PAGE_SHIFT - 3) bits at each page table level. Hence:
+ *
+ * levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), (PAGE_SHIFT - 3))
+ *
+ * where DIV_ROUND_UP(n, d) => (((n) + (d) - 1) / (d))
+ *
+ * We cannot include linux/kernel.h which defines DIV_ROUND_UP here
+ * due to build issues. So we open code DIV_ROUND_UP here:
+ *
+ * ((((va_bits) - PAGE_SHIFT) + (PAGE_SHIFT - 3) - 1) / (PAGE_SHIFT - 3))
+ *
+ * which gets simplified as :
+ */
+#define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3))
+
+/*
+ * Size mapped by an entry at level n ( 0 <= n <= 3)
+ * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
+ * in the final page. The maximum number of translation levels supported by
+ * the architecture is 4. Hence, starting at at level n, we have further
+ * ((4 - n) - 1) levels of translation excluding the offset within the page.
+ * So, the total number of bits mapped by an entry at level n is :
+ *
+ * ((4 - n) - 1) * (PAGE_SHIFT - 3) + PAGE_SHIFT
+ *
+ * Rearranging it a bit we get :
+ * (4 - n) * (PAGE_SHIFT - 3) + 3
+ */
+#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n) ((PAGE_SHIFT - 3) * (4 - (n)) + 3)
+
#define PTRS_PER_PTE (1 << (PAGE_SHIFT - 3))
/*
* PMD_SHIFT determines the size a level 2 page table entry can map.
*/
#if CONFIG_PGTABLE_LEVELS > 2
-#define PMD_SHIFT ((PAGE_SHIFT - 3) * 2 + 3)
+#define PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
#define PMD_MASK (~(PMD_SIZE-1))
#define PTRS_PER_PMD PTRS_PER_PTE
@@ -32,7 +65,7 @@
* PUD_SHIFT determines the size a level 1 page table entry can map.
*/
#if CONFIG_PGTABLE_LEVELS > 3
-#define PUD_SHIFT ((PAGE_SHIFT - 3) * 3 + 3)
+#define PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT)
#define PUD_MASK (~(PUD_SIZE-1))
#define PTRS_PER_PUD PTRS_PER_PTE
@@ -42,7 +75,7 @@
* PGDIR_SHIFT determines the size a top-level page table entry can map
* (depending on the configuration, this level can be 0, 1 or 2).
*/
-#define PGDIR_SHIFT ((PAGE_SHIFT - 3) * CONFIG_PGTABLE_LEVELS + 3)
+#define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS)
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1))
#define PTRS_PER_PGD (1 << (VA_BITS - PGDIR_SHIFT))
@@ -55,6 +88,13 @@
#define SECTION_MASK (~(SECTION_SIZE-1))
/*
+ * Contiguous page definitions.
+ */
+#define CONT_PTES (_AC(1, UL) << CONT_SHIFT)
+/* the the numerical offset of the PTE within a range of CONT_PTES */
+#define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
+
+/*
* Hardware page table definitions.
*
* Level 1 descriptor (PUD).
@@ -83,6 +123,7 @@
#define PMD_SECT_S (_AT(pmdval_t, 3) << 8)
#define PMD_SECT_AF (_AT(pmdval_t, 1) << 10)
#define PMD_SECT_NG (_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_CONT (_AT(pmdval_t, 1) << 52)
#define PMD_SECT_PXN (_AT(pmdval_t, 1) << 53)
#define PMD_SECT_UXN (_AT(pmdval_t, 1) << 54)
@@ -105,6 +146,7 @@
#define PTE_AF (_AT(pteval_t, 1) << 10) /* Access Flag */
#define PTE_NG (_AT(pteval_t, 1) << 11) /* nG */
#define PTE_DBM (_AT(pteval_t, 1) << 51) /* Dirty Bit Management */
+#define PTE_CONT (_AT(pteval_t, 1) << 52) /* Contiguous range */
#define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */
#define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b0329be..c3d22a5 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -41,7 +41,14 @@
* fixed mappings and modules
*/
#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE)
-#define VMALLOC_START (UL(0xffffffffffffffff) << VA_BITS)
+
+#ifndef CONFIG_KASAN
+#define VMALLOC_START (VA_START)
+#else
+#include <asm/kasan.h>
+#define VMALLOC_START (KASAN_SHADOW_END + SZ_64K)
+#endif
+
#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K))
@@ -72,6 +79,7 @@
#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
#define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP)
#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
@@ -79,7 +87,7 @@
#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
-#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
+#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
#define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
@@ -140,6 +148,7 @@
#define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL))
#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))
#ifdef CONFIG_ARM64_HW_AFDBM
#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -202,6 +211,16 @@
return set_pte_bit(pte, __pgprot(PTE_SPECIAL));
}
+static inline pte_t pte_mkcont(pte_t pte)
+{
+ return set_pte_bit(pte, __pgprot(PTE_CONT));
+}
+
+static inline pte_t pte_mknoncont(pte_t pte)
+{
+ return clear_pte_bit(pte, __pgprot(PTE_CONT));
+}
+
static inline void set_pte(pte_t *ptep, pte_t pte)
{
*ptep = pte;
@@ -496,7 +515,7 @@
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
- PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK;
+ PTE_PROT_NONE | PTE_VALID | PTE_WRITE;
/* preserve the hardware dirty information */
if (pte_hw_dirty(pte))
pte = pte_mkdirty(pte);
@@ -646,14 +665,17 @@
unsigned long addr, pte_t *ptep)
{
/*
- * set_pte() does not have a DSB for user mappings, so make sure that
- * the page table write is visible.
+ * We don't do anything here, so there's a very small chance of
+ * us retaking a user fault which we just fixed up. The alternative
+ * is doing a dsb(ishst), but that penalises the fastpath.
*/
- dsb(ishst);
}
#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+#define kc_vaddr_to_offset(v) ((v) & ~VA_START)
+#define kc_offset_to_vaddr(o) ((o) | VA_START)
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/pmu.h b/arch/arm64/include/asm/pmu.h
deleted file mode 100644
index b7710a5..0000000
--- a/arch/arm64/include/asm/pmu.h
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Based on arch/arm/include/asm/pmu.h
- *
- * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
- * Copyright (C) 2012 ARM Ltd.
- *
- * 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_PMU_H
-#define __ASM_PMU_H
-
-#ifdef CONFIG_HW_PERF_EVENTS
-
-/* The events for a given PMU register set. */
-struct pmu_hw_events {
- /*
- * The events that are active on the PMU for the given index.
- */
- struct perf_event **events;
-
- /*
- * A 1 bit for an index indicates that the counter is being used for
- * an event. A 0 means that the counter can be used.
- */
- unsigned long *used_mask;
-
- /*
- * Hardware lock to serialize accesses to PMU registers. Needed for the
- * read/modify/write sequences.
- */
- raw_spinlock_t pmu_lock;
-};
-
-struct arm_pmu {
- struct pmu pmu;
- cpumask_t active_irqs;
- int *irq_affinity;
- const char *name;
- irqreturn_t (*handle_irq)(int irq_num, void *dev);
- void (*enable)(struct hw_perf_event *evt, int idx);
- void (*disable)(struct hw_perf_event *evt, int idx);
- int (*get_event_idx)(struct pmu_hw_events *hw_events,
- struct hw_perf_event *hwc);
- int (*set_event_filter)(struct hw_perf_event *evt,
- struct perf_event_attr *attr);
- u32 (*read_counter)(int idx);
- void (*write_counter)(int idx, u32 val);
- void (*start)(void);
- void (*stop)(void);
- void (*reset)(void *);
- int (*map_event)(struct perf_event *event);
- int num_events;
- atomic_t active_events;
- struct mutex reserve_mutex;
- u64 max_period;
- struct platform_device *plat_device;
- struct pmu_hw_events *(*get_hw_events)(void);
-};
-
-#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
-
-int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type);
-
-u64 armpmu_event_update(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx);
-
-int armpmu_event_set_period(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx);
-
-#endif /* CONFIG_HW_PERF_EVENTS */
-#endif /* __ASM_PMU_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 98f3235..4acb7ca 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -186,6 +186,6 @@
#endif
-void cpu_enable_pan(void);
+void cpu_enable_pan(void *__unused);
#endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index 64d2d48..2eb714c 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -36,17 +36,33 @@
#define __HAVE_ARCH_MEMCPY
extern void *memcpy(void *, const void *, __kernel_size_t);
+extern void *__memcpy(void *, const void *, __kernel_size_t);
#define __HAVE_ARCH_MEMMOVE
extern void *memmove(void *, const void *, __kernel_size_t);
+extern void *__memmove(void *, const void *, __kernel_size_t);
#define __HAVE_ARCH_MEMCHR
extern void *memchr(const void *, int, __kernel_size_t);
#define __HAVE_ARCH_MEMSET
extern void *memset(void *, int, __kernel_size_t);
+extern void *__memset(void *, int, __kernel_size_t);
#define __HAVE_ARCH_MEMCMP
extern int memcmp(const void *, const void *, size_t);
+
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+#endif
+
#endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index a7f3d4b..d48ab5b 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -22,9 +22,6 @@
#include <asm/opcodes.h>
-#define SCTLR_EL1_CP15BEN (0x1 << 5)
-#define SCTLR_EL1_SED (0x1 << 8)
-
/*
* ARMv8 ARM reserves the following encoding for system registers:
* (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
@@ -38,12 +35,162 @@
#define sys_reg(op0, op1, crn, crm, op2) \
((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
-#define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4)
-#define SCTLR_EL1_SPAN (1 << 23)
+#define SYS_MIDR_EL1 sys_reg(3, 0, 0, 0, 0)
+#define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5)
+#define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6)
+
+#define SYS_ID_PFR0_EL1 sys_reg(3, 0, 0, 1, 0)
+#define SYS_ID_PFR1_EL1 sys_reg(3, 0, 0, 1, 1)
+#define SYS_ID_DFR0_EL1 sys_reg(3, 0, 0, 1, 2)
+#define SYS_ID_MMFR0_EL1 sys_reg(3, 0, 0, 1, 4)
+#define SYS_ID_MMFR1_EL1 sys_reg(3, 0, 0, 1, 5)
+#define SYS_ID_MMFR2_EL1 sys_reg(3, 0, 0, 1, 6)
+#define SYS_ID_MMFR3_EL1 sys_reg(3, 0, 0, 1, 7)
+
+#define SYS_ID_ISAR0_EL1 sys_reg(3, 0, 0, 2, 0)
+#define SYS_ID_ISAR1_EL1 sys_reg(3, 0, 0, 2, 1)
+#define SYS_ID_ISAR2_EL1 sys_reg(3, 0, 0, 2, 2)
+#define SYS_ID_ISAR3_EL1 sys_reg(3, 0, 0, 2, 3)
+#define SYS_ID_ISAR4_EL1 sys_reg(3, 0, 0, 2, 4)
+#define SYS_ID_ISAR5_EL1 sys_reg(3, 0, 0, 2, 5)
+#define SYS_ID_MMFR4_EL1 sys_reg(3, 0, 0, 2, 6)
+
+#define SYS_MVFR0_EL1 sys_reg(3, 0, 0, 3, 0)
+#define SYS_MVFR1_EL1 sys_reg(3, 0, 0, 3, 1)
+#define SYS_MVFR2_EL1 sys_reg(3, 0, 0, 3, 2)
+
+#define SYS_ID_AA64PFR0_EL1 sys_reg(3, 0, 0, 4, 0)
+#define SYS_ID_AA64PFR1_EL1 sys_reg(3, 0, 0, 4, 1)
+
+#define SYS_ID_AA64DFR0_EL1 sys_reg(3, 0, 0, 5, 0)
+#define SYS_ID_AA64DFR1_EL1 sys_reg(3, 0, 0, 5, 1)
+
+#define SYS_ID_AA64ISAR0_EL1 sys_reg(3, 0, 0, 6, 0)
+#define SYS_ID_AA64ISAR1_EL1 sys_reg(3, 0, 0, 6, 1)
+
+#define SYS_ID_AA64MMFR0_EL1 sys_reg(3, 0, 0, 7, 0)
+#define SYS_ID_AA64MMFR1_EL1 sys_reg(3, 0, 0, 7, 1)
+
+#define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0)
+#define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1)
+#define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7)
+
+#define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4)
#define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\
(!!x)<<8 | 0x1f)
+/* SCTLR_EL1 */
+#define SCTLR_EL1_CP15BEN (0x1 << 5)
+#define SCTLR_EL1_SED (0x1 << 8)
+#define SCTLR_EL1_SPAN (0x1 << 23)
+
+
+/* id_aa64isar0 */
+#define ID_AA64ISAR0_RDM_SHIFT 28
+#define ID_AA64ISAR0_ATOMICS_SHIFT 20
+#define ID_AA64ISAR0_CRC32_SHIFT 16
+#define ID_AA64ISAR0_SHA2_SHIFT 12
+#define ID_AA64ISAR0_SHA1_SHIFT 8
+#define ID_AA64ISAR0_AES_SHIFT 4
+
+/* id_aa64pfr0 */
+#define ID_AA64PFR0_GIC_SHIFT 24
+#define ID_AA64PFR0_ASIMD_SHIFT 20
+#define ID_AA64PFR0_FP_SHIFT 16
+#define ID_AA64PFR0_EL3_SHIFT 12
+#define ID_AA64PFR0_EL2_SHIFT 8
+#define ID_AA64PFR0_EL1_SHIFT 4
+#define ID_AA64PFR0_EL0_SHIFT 0
+
+#define ID_AA64PFR0_FP_NI 0xf
+#define ID_AA64PFR0_FP_SUPPORTED 0x0
+#define ID_AA64PFR0_ASIMD_NI 0xf
+#define ID_AA64PFR0_ASIMD_SUPPORTED 0x0
+#define ID_AA64PFR0_EL1_64BIT_ONLY 0x1
+#define ID_AA64PFR0_EL0_64BIT_ONLY 0x1
+
+/* id_aa64mmfr0 */
+#define ID_AA64MMFR0_TGRAN4_SHIFT 28
+#define ID_AA64MMFR0_TGRAN64_SHIFT 24
+#define ID_AA64MMFR0_TGRAN16_SHIFT 20
+#define ID_AA64MMFR0_BIGENDEL0_SHIFT 16
+#define ID_AA64MMFR0_SNSMEM_SHIFT 12
+#define ID_AA64MMFR0_BIGENDEL_SHIFT 8
+#define ID_AA64MMFR0_ASID_SHIFT 4
+#define ID_AA64MMFR0_PARANGE_SHIFT 0
+
+#define ID_AA64MMFR0_TGRAN4_NI 0xf
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED 0x0
+#define ID_AA64MMFR0_TGRAN64_NI 0xf
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0
+#define ID_AA64MMFR0_TGRAN16_NI 0x0
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1
+
+/* id_aa64mmfr1 */
+#define ID_AA64MMFR1_PAN_SHIFT 20
+#define ID_AA64MMFR1_LOR_SHIFT 16
+#define ID_AA64MMFR1_HPD_SHIFT 12
+#define ID_AA64MMFR1_VHE_SHIFT 8
+#define ID_AA64MMFR1_VMIDBITS_SHIFT 4
+#define ID_AA64MMFR1_HADBS_SHIFT 0
+
+/* id_aa64dfr0 */
+#define ID_AA64DFR0_CTX_CMPS_SHIFT 28
+#define ID_AA64DFR0_WRPS_SHIFT 20
+#define ID_AA64DFR0_BRPS_SHIFT 12
+#define ID_AA64DFR0_PMUVER_SHIFT 8
+#define ID_AA64DFR0_TRACEVER_SHIFT 4
+#define ID_AA64DFR0_DEBUGVER_SHIFT 0
+
+#define ID_ISAR5_RDM_SHIFT 24
+#define ID_ISAR5_CRC32_SHIFT 16
+#define ID_ISAR5_SHA2_SHIFT 12
+#define ID_ISAR5_SHA1_SHIFT 8
+#define ID_ISAR5_AES_SHIFT 4
+#define ID_ISAR5_SEVL_SHIFT 0
+
+#define MVFR0_FPROUND_SHIFT 28
+#define MVFR0_FPSHVEC_SHIFT 24
+#define MVFR0_FPSQRT_SHIFT 20
+#define MVFR0_FPDIVIDE_SHIFT 16
+#define MVFR0_FPTRAP_SHIFT 12
+#define MVFR0_FPDP_SHIFT 8
+#define MVFR0_FPSP_SHIFT 4
+#define MVFR0_SIMD_SHIFT 0
+
+#define MVFR1_SIMDFMAC_SHIFT 28
+#define MVFR1_FPHP_SHIFT 24
+#define MVFR1_SIMDHP_SHIFT 20
+#define MVFR1_SIMDSP_SHIFT 16
+#define MVFR1_SIMDINT_SHIFT 12
+#define MVFR1_SIMDLS_SHIFT 8
+#define MVFR1_FPDNAN_SHIFT 4
+#define MVFR1_FPFTZ_SHIFT 0
+
+
+#define ID_AA64MMFR0_TGRAN4_SHIFT 28
+#define ID_AA64MMFR0_TGRAN64_SHIFT 24
+#define ID_AA64MMFR0_TGRAN16_SHIFT 20
+
+#define ID_AA64MMFR0_TGRAN4_NI 0xf
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED 0x0
+#define ID_AA64MMFR0_TGRAN64_NI 0xf
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0
+#define ID_AA64MMFR0_TGRAN16_NI 0x0
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1
+
+#if defined(CONFIG_ARM64_4K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN4_SUPPORTED
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN16_SUPPORTED
+#elif defined(CONFIG_ARM64_64K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN64_SUPPORTED
+#endif
+
#ifdef __ASSEMBLY__
.irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index dcd06d1..90c7ff2 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -23,8 +23,10 @@
#include <linux/compiler.h>
-#ifndef CONFIG_ARM64_64K_PAGES
+#ifdef CONFIG_ARM64_4K_PAGES
#define THREAD_SIZE_ORDER 2
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define THREAD_SIZE_ORDER 0
#endif
#define THREAD_SIZE 16384
@@ -111,7 +113,6 @@
#define TIF_RESTORE_SIGMASK 20
#define TIF_SINGLESTEP 21
#define TIF_32BIT 22 /* 32bit process */
-#define TIF_SWITCH_MM 23 /* deferred switch_mm */
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index d6e6b66..ffdaea7 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -37,17 +37,21 @@
static inline void tlb_flush(struct mmu_gather *tlb)
{
- if (tlb->fullmm) {
- flush_tlb_mm(tlb->mm);
- } else {
- struct vm_area_struct vma = { .vm_mm = tlb->mm, };
- /*
- * The intermediate page table levels are already handled by
- * the __(pte|pmd|pud)_free_tlb() functions, so last level
- * TLBI is sufficient here.
- */
- __flush_tlb_range(&vma, tlb->start, tlb->end, true);
- }
+ struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+
+ /*
+ * The ASID allocator will either invalidate the ASID or mark
+ * it as used.
+ */
+ if (tlb->fullmm)
+ return;
+
+ /*
+ * The intermediate page table levels are already handled by
+ * the __(pte|pmd|pud)_free_tlb() functions, so last level
+ * TLBI is sufficient here.
+ */
+ __flush_tlb_range(&vma, tlb->start, tlb->end, true);
}
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 7bd2da0..b460ae2 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -63,6 +63,14 @@
* only require the D-TLB to be invalidated.
* - kaddr - Kernel virtual memory address
*/
+static inline void local_flush_tlb_all(void)
+{
+ dsb(nshst);
+ asm("tlbi vmalle1");
+ dsb(nsh);
+ isb();
+}
+
static inline void flush_tlb_all(void)
{
dsb(ishst);
@@ -73,7 +81,7 @@
static inline void flush_tlb_mm(struct mm_struct *mm)
{
- unsigned long asid = (unsigned long)ASID(mm) << 48;
+ unsigned long asid = ASID(mm) << 48;
dsb(ishst);
asm("tlbi aside1is, %0" : : "r" (asid));
@@ -83,8 +91,7 @@
static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long uaddr)
{
- unsigned long addr = uaddr >> 12 |
- ((unsigned long)ASID(vma->vm_mm) << 48);
+ unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48);
dsb(ishst);
asm("tlbi vale1is, %0" : : "r" (addr));
@@ -101,7 +108,7 @@
unsigned long start, unsigned long end,
bool last_level)
{
- unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
+ unsigned long asid = ASID(vma->vm_mm) << 48;
unsigned long addr;
if ((end - start) > MAX_TLB_RANGE) {
@@ -154,9 +161,8 @@
static inline void __flush_tlb_pgtable(struct mm_struct *mm,
unsigned long uaddr)
{
- unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48);
+ unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
- dsb(ishst);
asm("tlbi vae1is, %0" : : "r" (addr));
dsb(ish);
}
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 22dc9bc..1b6bda2 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -7,6 +7,8 @@
CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET)
CFLAGS_armv8_deprecated.o := -I$(src)
+KASAN_SANITIZE_efi-stub.o := n
+
CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_insn.o = -pg
CFLAGS_REMOVE_return_address.o = -pg
@@ -20,6 +22,14 @@
cpufeature.o alternative.o cacheinfo.o \
smp.o smp_spin_table.o topology.o
+stub-obj := efi-stub.o efi-entry.o
+extra-y := $(stub-obj)
+stub-obj := $(patsubst %.o,%.stub.o,$(stub-obj))
+
+OBJCOPYFLAGS := --prefix-symbols=__efistub_
+$(obj)/%.stub.o: $(obj)/%.o FORCE
+ $(call if_changed,objcopy)
+
arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \
sys_compat.o entry32.o \
../../arm/kernel/opcodes.o
@@ -32,7 +42,7 @@
arm64-obj-$(CONFIG_CPU_IDLE) += cpuidle.o
arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o
arm64-obj-$(CONFIG_KGDB) += kgdb.o
-arm64-obj-$(CONFIG_EFI) += efi.o efi-stub.o efi-entry.o
+arm64-obj-$(CONFIG_EFI) += efi.o $(stub-obj)
arm64-obj-$(CONFIG_PCI) += pci.o
arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o
arm64-obj-$(CONFIG_ACPI) += acpi.o
@@ -40,7 +50,7 @@
obj-y += $(arm64-obj-y) vdso/
obj-m += $(arm64-obj-m)
head-y := head.o
-extra-y := $(head-y) vmlinux.lds
+extra-y += $(head-y) vmlinux.lds
# vDSO - this must be built first to generate the symbol offsets
$(call objectify,$(arm64-obj-y)): $(obj)/vdso/vdso-offsets.h
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index a85843d..3b6d8cc 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -51,6 +51,9 @@
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(__memmove);
EXPORT_SYMBOL(memchr);
EXPORT_SYMBOL(memcmp);
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 8d89cf8..25de8b2 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -60,7 +60,7 @@
DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno));
DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
BLANK();
- DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id));
+ DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter));
BLANK();
DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm));
DEFINE(VMA_VM_FLAGS, offsetof(struct vm_area_struct, vm_flags));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 6ffd914..09eab32 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -88,5 +88,5 @@
void check_local_cpu_errata(void)
{
- check_cpu_capabilities(arm64_errata, "enabling workaround for");
+ update_cpu_capabilities(arm64_errata, "enabling workaround for");
}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 3c9aed3..d0d6074 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -16,12 +16,567 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
-#define pr_fmt(fmt) "alternatives: " fmt
+#define pr_fmt(fmt) "CPU features: " fmt
+#include <linux/bsearch.h>
+#include <linux/sort.h>
#include <linux/types.h>
#include <asm/cpu.h>
#include <asm/cpufeature.h>
+#include <asm/cpu_ops.h>
#include <asm/processor.h>
+#include <asm/sysreg.h>
+
+unsigned long elf_hwcap __read_mostly;
+EXPORT_SYMBOL_GPL(elf_hwcap);
+
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP_DEFAULT \
+ (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
+ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
+ COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
+ COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
+ COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
+ COMPAT_HWCAP_LPAE)
+unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+unsigned int compat_elf_hwcap2 __read_mostly;
+#endif
+
+DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+
+#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+ { \
+ .strict = STRICT, \
+ .type = TYPE, \
+ .shift = SHIFT, \
+ .width = WIDTH, \
+ .safe_val = SAFE_VAL, \
+ }
+
+#define ARM64_FTR_END \
+ { \
+ .width = 0, \
+ }
+
+static 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),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA1_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_AES_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */
+ ARM64_FTR_END,
+};
+
+static 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),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
+ /* Linux doesn't care about the EL3 */
+ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
+ ARM64_FTR_END,
+};
+
+static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
+ /* Linux shouldn't care about secure memory */
+ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_ASID_SHIFT, 4, 0),
+ /*
+ * Differing PARange is fine as long as all peripherals and memory are mapped
+ * within the minimum PARange of all CPUs
+ */
+ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
+ ARM64_FTR_END,
+};
+
+static 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),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HPD_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VHE_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HADBS_SHIFT, 4, 0),
+ ARM64_FTR_END,
+};
+
+static 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 */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */
+ 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
+ */
+ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0), /* 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[] = {
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0), /* InnerShr */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */
+ ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 4, 0), /* TCM */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* ShareLvl */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0), /* OuterShr */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* PMSA */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* VMSA */
+ ARM64_FTR_END,
+};
+
+static 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),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
+ ARM64_FTR_END,
+};
+
+static 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[] = {
+ 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 */
+ ARM64_FTR_END,
+};
+
+
+static 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),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA2_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA1_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_AES_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SEVL_SHIFT, 4, 0),
+ ARM64_FTR_END,
+};
+
+static 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[] = {
+ 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 */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* State1 */
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* State0 */
+ ARM64_FTR_END,
+};
+
+/*
+ * Common ftr bits for a 32bit register with all hidden, strict
+ * attributes, with 4bit feature fields and a default safe value of
+ * 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[] = {
+ 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),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0),
+ ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),
+ ARM64_FTR_END,
+};
+
+static 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[] = {
+ ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 32, 0),
+ ARM64_FTR_END,
+};
+
+static 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, \
+ .name = #id, \
+ .ftr_bits = &((table)[0]), \
+ }
+
+static struct arm64_ftr_reg arm64_ftr_regs[] = {
+
+ /* Op1 = 0, CRn = 0, CRm = 1 */
+ ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0),
+ ARM64_FTR_REG(SYS_ID_PFR1_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_DFR0_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_MMFR0_EL1, ftr_id_mmfr0),
+ ARM64_FTR_REG(SYS_ID_MMFR1_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_MMFR2_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_MMFR3_EL1, ftr_generic_32bits),
+
+ /* Op1 = 0, CRn = 0, CRm = 2 */
+ ARM64_FTR_REG(SYS_ID_ISAR0_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_ISAR1_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_ISAR2_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_ISAR3_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_ISAR4_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_ID_ISAR5_EL1, ftr_id_isar5),
+ ARM64_FTR_REG(SYS_ID_MMFR4_EL1, ftr_id_mmfr4),
+
+ /* Op1 = 0, CRn = 0, CRm = 3 */
+ ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2),
+
+ /* Op1 = 0, CRn = 0, CRm = 4 */
+ ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
+ ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_aa64raz),
+
+ /* Op1 = 0, CRn = 0, CRm = 5 */
+ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
+ ARM64_FTR_REG(SYS_ID_AA64DFR1_EL1, ftr_generic),
+
+ /* Op1 = 0, CRn = 0, CRm = 6 */
+ ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0),
+ ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_aa64raz),
+
+ /* Op1 = 0, CRn = 0, CRm = 7 */
+ ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0),
+ ARM64_FTR_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1),
+
+ /* Op1 = 3, CRn = 0, CRm = 0 */
+ ARM64_FTR_REG(SYS_CTR_EL0, ftr_ctr),
+ ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
+
+ /* Op1 = 3, CRn = 14, CRm = 0 */
+ ARM64_FTR_REG(SYS_CNTFRQ_EL0, ftr_generic32),
+};
+
+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;
+}
+
+/*
+ * get_arm64_ftr_reg - Lookup a feature register entry using its
+ * sys_reg() encoding. With the array arm64_ftr_regs sorted in the
+ * ascending order of sys_id , we use binary search to find a matching
+ * entry.
+ *
+ * returns - Upon success, matching ftr_reg entry for id.
+ * - NULL on failure. It is upto the caller to decide
+ * the impact of a failure.
+ */
+static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
+{
+ return bsearch((const void *)(unsigned long)sys_id,
+ arm64_ftr_regs,
+ ARRAY_SIZE(arm64_ftr_regs),
+ sizeof(arm64_ftr_regs[0]),
+ search_cmp_ftr_reg);
+}
+
+static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val)
+{
+ u64 mask = arm64_ftr_mask(ftrp);
+
+ reg &= ~mask;
+ reg |= (ftr_val << ftrp->shift) & mask;
+ return reg;
+}
+
+static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur)
+{
+ s64 ret = 0;
+
+ switch (ftrp->type) {
+ case FTR_EXACT:
+ ret = ftrp->safe_val;
+ break;
+ case FTR_LOWER_SAFE:
+ ret = new < cur ? new : cur;
+ break;
+ case FTR_HIGHER_SAFE:
+ ret = new > cur ? new : cur;
+ break;
+ default:
+ BUG();
+ }
+
+ 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);
+}
+
+/*
+ * Initialise the CPU feature register from Boot CPU values.
+ * Also initiliases the strict_mask for the register.
+ */
+static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
+{
+ u64 val = 0;
+ u64 strict_mask = ~0x0ULL;
+ struct arm64_ftr_bits *ftrp;
+ struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg);
+
+ BUG_ON(!reg);
+
+ for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
+ s64 ftr_new = arm64_ftr_value(ftrp, new);
+
+ val = arm64_ftr_set_value(ftrp, val, ftr_new);
+ if (!ftrp->strict)
+ strict_mask &= ~arm64_ftr_mask(ftrp);
+ }
+ reg->sys_val = val;
+ reg->strict_mask = strict_mask;
+}
+
+void __init init_cpu_features(struct cpuinfo_arm64 *info)
+{
+ /* Before we start using the tables, make sure it is sorted */
+ sort_ftr_regs();
+
+ init_cpu_ftr_reg(SYS_CTR_EL0, info->reg_ctr);
+ init_cpu_ftr_reg(SYS_DCZID_EL0, info->reg_dczid);
+ init_cpu_ftr_reg(SYS_CNTFRQ_EL0, info->reg_cntfrq);
+ init_cpu_ftr_reg(SYS_ID_AA64DFR0_EL1, info->reg_id_aa64dfr0);
+ init_cpu_ftr_reg(SYS_ID_AA64DFR1_EL1, info->reg_id_aa64dfr1);
+ init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0);
+ init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1);
+ init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0);
+ init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1);
+ init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
+ init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
+ init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
+ init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
+ init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
+ init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
+ init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3);
+ init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4);
+ init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5);
+ init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0);
+ init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
+ init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
+ init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
+ init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
+ init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
+ init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
+ init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
+ init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
+}
+
+static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
+{
+ struct arm64_ftr_bits *ftrp;
+
+ for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
+ s64 ftr_cur = arm64_ftr_value(ftrp, reg->sys_val);
+ s64 ftr_new = arm64_ftr_value(ftrp, new);
+
+ if (ftr_cur == ftr_new)
+ continue;
+ /* Find a safe value */
+ ftr_new = arm64_ftr_safe_value(ftrp, ftr_new, ftr_cur);
+ reg->sys_val = arm64_ftr_set_value(ftrp, reg->sys_val, ftr_new);
+ }
+
+}
+
+static int check_update_ftr_reg(u32 sys_id, int cpu, u64 val, u64 boot)
+{
+ struct arm64_ftr_reg *regp = get_arm64_ftr_reg(sys_id);
+
+ BUG_ON(!regp);
+ update_cpu_ftr_reg(regp, val);
+ if ((boot & regp->strict_mask) == (val & regp->strict_mask))
+ return 0;
+ pr_warn("SANITY CHECK: Unexpected variation in %s. Boot CPU: %#016llx, CPU%d: %#016llx\n",
+ regp->name, boot, cpu, val);
+ return 1;
+}
+
+/*
+ * Update system wide CPU feature registers with the values from a
+ * non-boot CPU. Also performs SANITY checks to make sure that there
+ * aren't any insane variations from that of the boot CPU.
+ */
+void update_cpu_features(int cpu,
+ struct cpuinfo_arm64 *info,
+ struct cpuinfo_arm64 *boot)
+{
+ int taint = 0;
+
+ /*
+ * The kernel can handle differing I-cache policies, but otherwise
+ * caches should look identical. Userspace JITs will make use of
+ * *minLine.
+ */
+ taint |= check_update_ftr_reg(SYS_CTR_EL0, cpu,
+ info->reg_ctr, boot->reg_ctr);
+
+ /*
+ * Userspace may perform DC ZVA instructions. Mismatched block sizes
+ * could result in too much or too little memory being zeroed if a
+ * process is preempted and migrated between CPUs.
+ */
+ taint |= check_update_ftr_reg(SYS_DCZID_EL0, cpu,
+ info->reg_dczid, boot->reg_dczid);
+
+ /* If different, timekeeping will be broken (especially with KVM) */
+ taint |= check_update_ftr_reg(SYS_CNTFRQ_EL0, cpu,
+ info->reg_cntfrq, boot->reg_cntfrq);
+
+ /*
+ * The kernel uses self-hosted debug features and expects CPUs to
+ * support identical debug features. We presently need CTX_CMPs, WRPs,
+ * and BRPs to be identical.
+ * ID_AA64DFR1 is currently RES0.
+ */
+ taint |= check_update_ftr_reg(SYS_ID_AA64DFR0_EL1, cpu,
+ info->reg_id_aa64dfr0, boot->reg_id_aa64dfr0);
+ taint |= check_update_ftr_reg(SYS_ID_AA64DFR1_EL1, cpu,
+ info->reg_id_aa64dfr1, boot->reg_id_aa64dfr1);
+ /*
+ * Even in big.LITTLE, processors should be identical instruction-set
+ * wise.
+ */
+ taint |= check_update_ftr_reg(SYS_ID_AA64ISAR0_EL1, cpu,
+ info->reg_id_aa64isar0, boot->reg_id_aa64isar0);
+ taint |= check_update_ftr_reg(SYS_ID_AA64ISAR1_EL1, cpu,
+ info->reg_id_aa64isar1, boot->reg_id_aa64isar1);
+
+ /*
+ * Differing PARange support is fine as long as all peripherals and
+ * memory are mapped within the minimum PARange of all CPUs.
+ * Linux should not care about secure memory.
+ */
+ taint |= check_update_ftr_reg(SYS_ID_AA64MMFR0_EL1, cpu,
+ info->reg_id_aa64mmfr0, boot->reg_id_aa64mmfr0);
+ taint |= check_update_ftr_reg(SYS_ID_AA64MMFR1_EL1, cpu,
+ info->reg_id_aa64mmfr1, boot->reg_id_aa64mmfr1);
+
+ /*
+ * EL3 is not our concern.
+ * ID_AA64PFR1 is currently RES0.
+ */
+ taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
+ info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
+ taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
+ info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1);
+
+ /*
+ * If we have AArch32, we care about 32-bit features for compat. These
+ * registers should be RES0 otherwise.
+ */
+ taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
+ info->reg_id_dfr0, boot->reg_id_dfr0);
+ taint |= check_update_ftr_reg(SYS_ID_ISAR0_EL1, cpu,
+ info->reg_id_isar0, boot->reg_id_isar0);
+ taint |= check_update_ftr_reg(SYS_ID_ISAR1_EL1, cpu,
+ info->reg_id_isar1, boot->reg_id_isar1);
+ taint |= check_update_ftr_reg(SYS_ID_ISAR2_EL1, cpu,
+ info->reg_id_isar2, boot->reg_id_isar2);
+ taint |= check_update_ftr_reg(SYS_ID_ISAR3_EL1, cpu,
+ info->reg_id_isar3, boot->reg_id_isar3);
+ taint |= check_update_ftr_reg(SYS_ID_ISAR4_EL1, cpu,
+ info->reg_id_isar4, boot->reg_id_isar4);
+ taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu,
+ info->reg_id_isar5, boot->reg_id_isar5);
+
+ /*
+ * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and
+ * ACTLR formats could differ across CPUs and therefore would have to
+ * be trapped for virtualization anyway.
+ */
+ taint |= check_update_ftr_reg(SYS_ID_MMFR0_EL1, cpu,
+ info->reg_id_mmfr0, boot->reg_id_mmfr0);
+ taint |= check_update_ftr_reg(SYS_ID_MMFR1_EL1, cpu,
+ info->reg_id_mmfr1, boot->reg_id_mmfr1);
+ taint |= check_update_ftr_reg(SYS_ID_MMFR2_EL1, cpu,
+ info->reg_id_mmfr2, boot->reg_id_mmfr2);
+ taint |= check_update_ftr_reg(SYS_ID_MMFR3_EL1, cpu,
+ info->reg_id_mmfr3, boot->reg_id_mmfr3);
+ taint |= check_update_ftr_reg(SYS_ID_PFR0_EL1, cpu,
+ info->reg_id_pfr0, boot->reg_id_pfr0);
+ taint |= check_update_ftr_reg(SYS_ID_PFR1_EL1, cpu,
+ info->reg_id_pfr1, boot->reg_id_pfr1);
+ taint |= check_update_ftr_reg(SYS_MVFR0_EL1, cpu,
+ info->reg_mvfr0, boot->reg_mvfr0);
+ taint |= check_update_ftr_reg(SYS_MVFR1_EL1, cpu,
+ info->reg_mvfr1, boot->reg_mvfr1);
+ taint |= check_update_ftr_reg(SYS_MVFR2_EL1, cpu,
+ info->reg_mvfr2, boot->reg_mvfr2);
+
+ /*
+ * Mismatched CPU features are a recipe for disaster. Don't even
+ * pretend to support them.
+ */
+ WARN_TAINT_ONCE(taint, TAINT_CPU_OUT_OF_SPEC,
+ "Unsupported CPU feature variation.\n");
+}
+
+u64 read_system_reg(u32 id)
+{
+ struct arm64_ftr_reg *regp = get_arm64_ftr_reg(id);
+
+ /* We shouldn't get a request for an unsupported register */
+ BUG_ON(!regp);
+ return regp->sys_val;
+}
static bool
feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
@@ -31,34 +586,31 @@
return val >= entry->min_field_value;
}
-#define __ID_FEAT_CHK(reg) \
-static bool __maybe_unused \
-has_##reg##_feature(const struct arm64_cpu_capabilities *entry) \
-{ \
- u64 val; \
- \
- val = read_cpuid(reg##_el1); \
- return feature_matches(val, entry); \
-}
+static bool
+has_cpuid_feature(const struct arm64_cpu_capabilities *entry)
+{
+ u64 val;
-__ID_FEAT_CHK(id_aa64pfr0);
-__ID_FEAT_CHK(id_aa64mmfr1);
-__ID_FEAT_CHK(id_aa64isar0);
+ val = read_system_reg(entry->sys_reg);
+ return feature_matches(val, entry);
+}
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
- .matches = has_id_aa64pfr0_feature,
- .field_pos = 24,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64PFR0_EL1,
+ .field_pos = ID_AA64PFR0_GIC_SHIFT,
.min_field_value = 1,
},
#ifdef CONFIG_ARM64_PAN
{
.desc = "Privileged Access Never",
.capability = ARM64_HAS_PAN,
- .matches = has_id_aa64mmfr1_feature,
- .field_pos = 20,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64MMFR1_EL1,
+ .field_pos = ID_AA64MMFR1_PAN_SHIFT,
.min_field_value = 1,
.enable = cpu_enable_pan,
},
@@ -67,15 +619,101 @@
{
.desc = "LSE atomic instructions",
.capability = ARM64_HAS_LSE_ATOMICS,
- .matches = has_id_aa64isar0_feature,
- .field_pos = 20,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64ISAR0_EL1,
+ .field_pos = ID_AA64ISAR0_ATOMICS_SHIFT,
.min_field_value = 2,
},
#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
{},
};
-void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
+#define HWCAP_CAP(reg, field, min_value, type, cap) \
+ { \
+ .desc = #cap, \
+ .matches = has_cpuid_feature, \
+ .sys_reg = reg, \
+ .field_pos = field, \
+ .min_field_value = min_value, \
+ .hwcap_type = type, \
+ .hwcap = cap, \
+ }
+
+static const struct arm64_cpu_capabilities arm64_hwcaps[] = {
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 2, CAP_HWCAP, HWCAP_PMULL),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 1, CAP_HWCAP, HWCAP_AES),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, 1, CAP_HWCAP, HWCAP_SHA1),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 1, CAP_HWCAP, HWCAP_SHA2),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, 1, CAP_HWCAP, HWCAP_CRC32),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, 2, CAP_HWCAP, HWCAP_ATOMICS),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 0, CAP_HWCAP, HWCAP_FP),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 0, CAP_HWCAP, HWCAP_ASIMD),
+#ifdef CONFIG_COMPAT
+ HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
+ HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
+ HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
+ HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA2_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
+ HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_CRC32_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
+#endif
+ {},
+};
+
+static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
+{
+ switch (cap->hwcap_type) {
+ case CAP_HWCAP:
+ elf_hwcap |= cap->hwcap;
+ break;
+#ifdef CONFIG_COMPAT
+ case CAP_COMPAT_HWCAP:
+ compat_elf_hwcap |= (u32)cap->hwcap;
+ break;
+ case CAP_COMPAT_HWCAP2:
+ compat_elf_hwcap2 |= (u32)cap->hwcap;
+ break;
+#endif
+ default:
+ WARN_ON(1);
+ break;
+ }
+}
+
+/* Check if we have a particular HWCAP enabled */
+static bool cpus_have_hwcap(const struct arm64_cpu_capabilities *cap)
+{
+ bool rc;
+
+ switch (cap->hwcap_type) {
+ case CAP_HWCAP:
+ rc = (elf_hwcap & cap->hwcap) != 0;
+ break;
+#ifdef CONFIG_COMPAT
+ case CAP_COMPAT_HWCAP:
+ rc = (compat_elf_hwcap & (u32)cap->hwcap) != 0;
+ break;
+ case CAP_COMPAT_HWCAP2:
+ rc = (compat_elf_hwcap2 & (u32)cap->hwcap) != 0;
+ break;
+#endif
+ default:
+ WARN_ON(1);
+ rc = false;
+ }
+
+ return rc;
+}
+
+static void setup_cpu_hwcaps(void)
+{
+ int i;
+ const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps;
+
+ for (i = 0; hwcaps[i].desc; i++)
+ if (hwcaps[i].matches(&hwcaps[i]))
+ cap_set_hwcap(&hwcaps[i]);
+}
+
+void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
const char *info)
{
int i;
@@ -88,15 +726,178 @@
pr_info("%s %s\n", info, caps[i].desc);
cpus_set_cap(caps[i].capability);
}
+}
- /* second pass allows enable() to consider interacting capabilities */
- for (i = 0; caps[i].desc; i++) {
- if (cpus_have_cap(caps[i].capability) && caps[i].enable)
- caps[i].enable();
+/*
+ * Run through the enabled capabilities and enable() it on all active
+ * CPUs
+ */
+void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
+{
+ int i;
+
+ for (i = 0; caps[i].desc; i++)
+ if (caps[i].enable && cpus_have_cap(caps[i].capability))
+ on_each_cpu(caps[i].enable, NULL, true);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Flag to indicate if we have computed the system wide
+ * capabilities based on the boot time active CPUs. This
+ * will be used to determine if a new booting CPU should
+ * go through the verification process to make sure that it
+ * supports the system capabilities, without using a hotplug
+ * notifier.
+ */
+static bool sys_caps_initialised;
+
+static inline void set_sys_caps_initialised(void)
+{
+ sys_caps_initialised = true;
+}
+
+/*
+ * __raw_read_system_reg() - Used by a STARTING cpu before cpuinfo is populated.
+ */
+static u64 __raw_read_system_reg(u32 sys_id)
+{
+ switch (sys_id) {
+ case SYS_ID_PFR0_EL1: return (u64)read_cpuid(ID_PFR0_EL1);
+ case SYS_ID_PFR1_EL1: return (u64)read_cpuid(ID_PFR1_EL1);
+ case SYS_ID_DFR0_EL1: return (u64)read_cpuid(ID_DFR0_EL1);
+ case SYS_ID_MMFR0_EL1: return (u64)read_cpuid(ID_MMFR0_EL1);
+ case SYS_ID_MMFR1_EL1: return (u64)read_cpuid(ID_MMFR1_EL1);
+ case SYS_ID_MMFR2_EL1: return (u64)read_cpuid(ID_MMFR2_EL1);
+ case SYS_ID_MMFR3_EL1: return (u64)read_cpuid(ID_MMFR3_EL1);
+ case SYS_ID_ISAR0_EL1: return (u64)read_cpuid(ID_ISAR0_EL1);
+ case SYS_ID_ISAR1_EL1: return (u64)read_cpuid(ID_ISAR1_EL1);
+ case SYS_ID_ISAR2_EL1: return (u64)read_cpuid(ID_ISAR2_EL1);
+ case SYS_ID_ISAR3_EL1: return (u64)read_cpuid(ID_ISAR3_EL1);
+ case SYS_ID_ISAR4_EL1: return (u64)read_cpuid(ID_ISAR4_EL1);
+ case SYS_ID_ISAR5_EL1: return (u64)read_cpuid(ID_ISAR4_EL1);
+ case SYS_MVFR0_EL1: return (u64)read_cpuid(MVFR0_EL1);
+ case SYS_MVFR1_EL1: return (u64)read_cpuid(MVFR1_EL1);
+ case SYS_MVFR2_EL1: return (u64)read_cpuid(MVFR2_EL1);
+
+ case SYS_ID_AA64PFR0_EL1: return (u64)read_cpuid(ID_AA64PFR0_EL1);
+ case SYS_ID_AA64PFR1_EL1: return (u64)read_cpuid(ID_AA64PFR0_EL1);
+ case SYS_ID_AA64DFR0_EL1: return (u64)read_cpuid(ID_AA64DFR0_EL1);
+ case SYS_ID_AA64DFR1_EL1: return (u64)read_cpuid(ID_AA64DFR0_EL1);
+ case SYS_ID_AA64MMFR0_EL1: return (u64)read_cpuid(ID_AA64MMFR0_EL1);
+ case SYS_ID_AA64MMFR1_EL1: return (u64)read_cpuid(ID_AA64MMFR1_EL1);
+ case SYS_ID_AA64ISAR0_EL1: return (u64)read_cpuid(ID_AA64ISAR0_EL1);
+ case SYS_ID_AA64ISAR1_EL1: return (u64)read_cpuid(ID_AA64ISAR1_EL1);
+
+ case SYS_CNTFRQ_EL0: return (u64)read_cpuid(CNTFRQ_EL0);
+ case SYS_CTR_EL0: return (u64)read_cpuid(CTR_EL0);
+ case SYS_DCZID_EL0: return (u64)read_cpuid(DCZID_EL0);
+ default:
+ BUG();
+ return 0;
}
}
-void check_local_cpu_features(void)
+/*
+ * Park the CPU which doesn't have the capability as advertised
+ * by the system.
+ */
+static void fail_incapable_cpu(char *cap_type,
+ const struct arm64_cpu_capabilities *cap)
{
- check_cpu_capabilities(arm64_features, "detected feature:");
+ int cpu = smp_processor_id();
+
+ pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc);
+ /* Mark this CPU absent */
+ set_cpu_present(cpu, 0);
+
+ /* Check if we can park ourselves */
+ if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
+ cpu_ops[cpu]->cpu_die(cpu);
+ asm(
+ "1: wfe\n"
+ " wfi\n"
+ " b 1b");
+}
+
+/*
+ * Run through the enabled system capabilities and enable() it on this CPU.
+ * The capabilities were decided based on the available CPUs at the boot time.
+ * Any new CPU should match the system wide status of the capability. If the
+ * new CPU doesn't have a capability which the system now has enabled, we
+ * cannot do anything to fix it up and could cause unexpected failures. So
+ * we park the CPU.
+ */
+void verify_local_cpu_capabilities(void)
+{
+ int i;
+ const struct arm64_cpu_capabilities *caps;
+
+ /*
+ * If we haven't computed the system capabilities, there is nothing
+ * to verify.
+ */
+ if (!sys_caps_initialised)
+ return;
+
+ caps = arm64_features;
+ for (i = 0; caps[i].desc; i++) {
+ if (!cpus_have_cap(caps[i].capability) || !caps[i].sys_reg)
+ continue;
+ /*
+ * If the new CPU misses an advertised feature, we cannot proceed
+ * further, park the cpu.
+ */
+ if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i]))
+ fail_incapable_cpu("arm64_features", &caps[i]);
+ if (caps[i].enable)
+ caps[i].enable(NULL);
+ }
+
+ for (i = 0, caps = arm64_hwcaps; caps[i].desc; i++) {
+ if (!cpus_have_hwcap(&caps[i]))
+ continue;
+ if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i]))
+ fail_incapable_cpu("arm64_hwcaps", &caps[i]);
+ }
+}
+
+#else /* !CONFIG_HOTPLUG_CPU */
+
+static inline void set_sys_caps_initialised(void)
+{
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static void setup_feature_capabilities(void)
+{
+ update_cpu_capabilities(arm64_features, "detected feature:");
+ enable_cpu_capabilities(arm64_features);
+}
+
+void __init setup_cpu_features(void)
+{
+ u32 cwg;
+ int cls;
+
+ /* Set the CPU feature capabilies */
+ setup_feature_capabilities();
+ setup_cpu_hwcaps();
+
+ /* Advertise that we have computed the system capabilities */
+ set_sys_caps_initialised();
+
+ /*
+ * Check for sane CTR_EL0.CWG value.
+ */
+ cwg = cache_type_cwg();
+ cls = cache_line_size();
+ if (!cwg)
+ pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n",
+ cls);
+ if (L1_CACHE_BYTES < cls)
+ pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n",
+ L1_CACHE_BYTES, cls);
}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 75d5a86..706679d 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -24,8 +24,11 @@
#include <linux/bug.h>
#include <linux/init.h>
#include <linux/kernel.h>
+#include <linux/personality.h>
#include <linux/preempt.h>
#include <linux/printk.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
#include <linux/smp.h>
/*
@@ -35,7 +38,6 @@
*/
DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data);
static struct cpuinfo_arm64 boot_cpu_data;
-static bool mixed_endian_el0 = true;
static char *icache_policy_str[] = {
[ICACHE_POLICY_RESERVED] = "RESERVED/UNKNOWN",
@@ -46,6 +48,127 @@
unsigned long __icache_flags;
+static const char *const hwcap_str[] = {
+ "fp",
+ "asimd",
+ "evtstrm",
+ "aes",
+ "pmull",
+ "sha1",
+ "sha2",
+ "crc32",
+ "atomics",
+ NULL
+};
+
+#ifdef CONFIG_COMPAT
+static const char *const compat_hwcap_str[] = {
+ "swp",
+ "half",
+ "thumb",
+ "26bit",
+ "fastmult",
+ "fpa",
+ "vfp",
+ "edsp",
+ "java",
+ "iwmmxt",
+ "crunch",
+ "thumbee",
+ "neon",
+ "vfpv3",
+ "vfpv3d16",
+ "tls",
+ "vfpv4",
+ "idiva",
+ "idivt",
+ "vfpd32",
+ "lpae",
+ "evtstrm"
+};
+
+static const char *const compat_hwcap2_str[] = {
+ "aes",
+ "pmull",
+ "sha1",
+ "sha2",
+ "crc32",
+ NULL
+};
+#endif /* CONFIG_COMPAT */
+
+static int c_show(struct seq_file *m, void *v)
+{
+ int i, j;
+
+ for_each_online_cpu(i) {
+ struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
+ u32 midr = cpuinfo->reg_midr;
+
+ /*
+ * glibc reads /proc/cpuinfo to determine the number of
+ * online processors, looking for lines beginning with
+ * "processor". Give glibc what it expects.
+ */
+ seq_printf(m, "processor\t: %d\n", i);
+
+ /*
+ * Dump out the common processor features in a single line.
+ * Userspace should read the hwcaps with getauxval(AT_HWCAP)
+ * rather than attempting to parse this, but there's a body of
+ * software which does already (at least for 32-bit).
+ */
+ seq_puts(m, "Features\t:");
+ if (personality(current->personality) == PER_LINUX32) {
+#ifdef CONFIG_COMPAT
+ for (j = 0; compat_hwcap_str[j]; j++)
+ if (compat_elf_hwcap & (1 << j))
+ seq_printf(m, " %s", compat_hwcap_str[j]);
+
+ for (j = 0; compat_hwcap2_str[j]; j++)
+ if (compat_elf_hwcap2 & (1 << j))
+ seq_printf(m, " %s", compat_hwcap2_str[j]);
+#endif /* CONFIG_COMPAT */
+ } else {
+ for (j = 0; hwcap_str[j]; j++)
+ if (elf_hwcap & (1 << j))
+ seq_printf(m, " %s", hwcap_str[j]);
+ }
+ seq_puts(m, "\n");
+
+ seq_printf(m, "CPU implementer\t: 0x%02x\n",
+ MIDR_IMPLEMENTOR(midr));
+ seq_printf(m, "CPU architecture: 8\n");
+ seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr));
+ seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr));
+ seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr));
+ }
+
+ return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ return *pos < 1 ? (void *)1 : NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ ++*pos;
+ return NULL;
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations cpuinfo_op = {
+ .start = c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = c_show
+};
+
static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
{
unsigned int cpu = smp_processor_id();
@@ -69,136 +192,6 @@
pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu);
}
-bool cpu_supports_mixed_endian_el0(void)
-{
- return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
-}
-
-bool system_supports_mixed_endian_el0(void)
-{
- return mixed_endian_el0;
-}
-
-static void update_mixed_endian_el0_support(struct cpuinfo_arm64 *info)
-{
- mixed_endian_el0 &= id_aa64mmfr0_mixed_endian_el0(info->reg_id_aa64mmfr0);
-}
-
-static void update_cpu_features(struct cpuinfo_arm64 *info)
-{
- update_mixed_endian_el0_support(info);
-}
-
-static int check_reg_mask(char *name, u64 mask, u64 boot, u64 cur, int cpu)
-{
- if ((boot & mask) == (cur & mask))
- return 0;
-
- pr_warn("SANITY CHECK: Unexpected variation in %s. Boot CPU: %#016lx, CPU%d: %#016lx\n",
- name, (unsigned long)boot, cpu, (unsigned long)cur);
-
- return 1;
-}
-
-#define CHECK_MASK(field, mask, boot, cur, cpu) \
- check_reg_mask(#field, mask, (boot)->reg_ ## field, (cur)->reg_ ## field, cpu)
-
-#define CHECK(field, boot, cur, cpu) \
- CHECK_MASK(field, ~0ULL, boot, cur, cpu)
-
-/*
- * Verify that CPUs don't have unexpected differences that will cause problems.
- */
-static void cpuinfo_sanity_check(struct cpuinfo_arm64 *cur)
-{
- unsigned int cpu = smp_processor_id();
- struct cpuinfo_arm64 *boot = &boot_cpu_data;
- unsigned int diff = 0;
-
- /*
- * The kernel can handle differing I-cache policies, but otherwise
- * caches should look identical. Userspace JITs will make use of
- * *minLine.
- */
- diff |= CHECK_MASK(ctr, 0xffff3fff, boot, cur, cpu);
-
- /*
- * Userspace may perform DC ZVA instructions. Mismatched block sizes
- * could result in too much or too little memory being zeroed if a
- * process is preempted and migrated between CPUs.
- */
- diff |= CHECK(dczid, boot, cur, cpu);
-
- /* If different, timekeeping will be broken (especially with KVM) */
- diff |= CHECK(cntfrq, boot, cur, cpu);
-
- /*
- * The kernel uses self-hosted debug features and expects CPUs to
- * support identical debug features. We presently need CTX_CMPs, WRPs,
- * and BRPs to be identical.
- * ID_AA64DFR1 is currently RES0.
- */
- diff |= CHECK(id_aa64dfr0, boot, cur, cpu);
- diff |= CHECK(id_aa64dfr1, boot, cur, cpu);
-
- /*
- * Even in big.LITTLE, processors should be identical instruction-set
- * wise.
- */
- diff |= CHECK(id_aa64isar0, boot, cur, cpu);
- diff |= CHECK(id_aa64isar1, boot, cur, cpu);
-
- /*
- * Differing PARange support is fine as long as all peripherals and
- * memory are mapped within the minimum PARange of all CPUs.
- * Linux should not care about secure memory.
- * ID_AA64MMFR1 is currently RES0.
- */
- diff |= CHECK_MASK(id_aa64mmfr0, 0xffffffffffff0ff0, boot, cur, cpu);
- diff |= CHECK(id_aa64mmfr1, boot, cur, cpu);
-
- /*
- * EL3 is not our concern.
- * ID_AA64PFR1 is currently RES0.
- */
- diff |= CHECK_MASK(id_aa64pfr0, 0xffffffffffff0fff, boot, cur, cpu);
- diff |= CHECK(id_aa64pfr1, boot, cur, cpu);
-
- /*
- * If we have AArch32, we care about 32-bit features for compat. These
- * registers should be RES0 otherwise.
- */
- diff |= CHECK(id_dfr0, boot, cur, cpu);
- diff |= CHECK(id_isar0, boot, cur, cpu);
- diff |= CHECK(id_isar1, boot, cur, cpu);
- diff |= CHECK(id_isar2, boot, cur, cpu);
- diff |= CHECK(id_isar3, boot, cur, cpu);
- diff |= CHECK(id_isar4, boot, cur, cpu);
- diff |= CHECK(id_isar5, boot, cur, cpu);
- /*
- * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and
- * ACTLR formats could differ across CPUs and therefore would have to
- * be trapped for virtualization anyway.
- */
- diff |= CHECK_MASK(id_mmfr0, 0xff0fffff, boot, cur, cpu);
- diff |= CHECK(id_mmfr1, boot, cur, cpu);
- diff |= CHECK(id_mmfr2, boot, cur, cpu);
- diff |= CHECK(id_mmfr3, boot, cur, cpu);
- diff |= CHECK(id_pfr0, boot, cur, cpu);
- diff |= CHECK(id_pfr1, boot, cur, cpu);
-
- diff |= CHECK(mvfr0, boot, cur, cpu);
- diff |= CHECK(mvfr1, boot, cur, cpu);
- diff |= CHECK(mvfr2, boot, cur, cpu);
-
- /*
- * Mismatched CPU features are a recipe for disaster. Don't even
- * pretend to support them.
- */
- WARN_TAINT_ONCE(diff, TAINT_CPU_OUT_OF_SPEC,
- "Unsupported CPU feature variation.\n");
-}
-
static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
{
info->reg_cntfrq = arch_timer_get_cntfrq();
@@ -236,15 +229,13 @@
cpuinfo_detect_icache_policy(info);
check_local_cpu_errata();
- check_local_cpu_features();
- update_cpu_features(info);
}
void cpuinfo_store_cpu(void)
{
struct cpuinfo_arm64 *info = this_cpu_ptr(&cpu_data);
__cpuinfo_store_cpu(info);
- cpuinfo_sanity_check(info);
+ update_cpu_features(smp_processor_id(), info, &boot_cpu_data);
}
void __init cpuinfo_store_boot_cpu(void)
@@ -253,4 +244,5 @@
__cpuinfo_store_cpu(info);
boot_cpu_data = *info;
+ init_cpu_features(&boot_cpu_data);
}
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index cebf786..1429044 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -26,14 +26,16 @@
#include <linux/stat.h>
#include <linux/uaccess.h>
-#include <asm/debug-monitors.h>
+#include <asm/cpufeature.h>
#include <asm/cputype.h>
+#include <asm/debug-monitors.h>
#include <asm/system_misc.h>
/* Determine debug architecture. */
u8 debug_monitors_arch(void)
{
- return read_cpuid(ID_AA64DFR0_EL1) & 0xf;
+ return cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+ ID_AA64DFR0_DEBUGVER_SHIFT);
}
/*
@@ -201,7 +203,7 @@
}
/*
- * Call registered single step handers
+ * Call registered single step handlers
* There is no Syndrome info to check for determining the handler.
* So we call all the registered handlers, until the right handler is
* found which returns zero.
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 8ce9b05..a773db9 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -29,7 +29,7 @@
* we want to be. The kernel image wants to be placed at TEXT_OFFSET
* from start of RAM.
*/
-ENTRY(efi_stub_entry)
+ENTRY(entry)
/*
* Create a stack frame to save FP/LR with extra space
* for image_addr variable passed to efi_entry().
@@ -86,8 +86,8 @@
* entries for the VA range of the current image, so no maintenance is
* necessary.
*/
- adr x0, efi_stub_entry
- adr x1, efi_stub_entry_end
+ adr x0, entry
+ adr x1, entry_end
sub x1, x1, x0
bl __flush_dcache_area
@@ -120,5 +120,5 @@
ldp x29, x30, [sp], #32
ret
-efi_stub_entry_end:
-ENDPROC(efi_stub_entry)
+entry_end:
+ENDPROC(entry)
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index e8ca6ea..a48d1f4 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -48,7 +48,6 @@
.mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem),
.page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
.mmlist = LIST_HEAD_INIT(efi_mm.mmlist),
- INIT_MM_CONTEXT(efi_mm)
};
static int uefi_debug __initdata;
@@ -258,7 +257,8 @@
*/
if (!is_normal_ram(md))
prot = __pgprot(PROT_DEVICE_nGnRE);
- else if (md->type == EFI_RUNTIME_SERVICES_CODE)
+ else if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+ !PAGE_ALIGNED(md->phys_addr))
prot = PAGE_KERNEL_EXEC;
else
prot = PAGE_KERNEL;
@@ -343,9 +343,9 @@
else
cpu_switch_mm(mm->pgd, mm);
- flush_tlb_all();
+ local_flush_tlb_all();
if (icache_is_aivivt())
- __flush_icache_all();
+ __local_flush_icache_all();
}
void efi_virtmap_load(void)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 08cafc5..0f03a8f 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -178,6 +178,24 @@
ENDPROC(ftrace_stub)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ /* save return value regs*/
+ .macro save_return_regs
+ sub sp, sp, #64
+ stp x0, x1, [sp]
+ stp x2, x3, [sp, #16]
+ stp x4, x5, [sp, #32]
+ stp x6, x7, [sp, #48]
+ .endm
+
+ /* restore return value regs*/
+ .macro restore_return_regs
+ ldp x0, x1, [sp]
+ ldp x2, x3, [sp, #16]
+ ldp x4, x5, [sp, #32]
+ ldp x6, x7, [sp, #48]
+ add sp, sp, #64
+ .endm
+
/*
* void ftrace_graph_caller(void)
*
@@ -204,11 +222,11 @@
* only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
*/
ENTRY(return_to_handler)
- str x0, [sp, #-16]!
+ save_return_regs
mov x0, x29 // parent's fp
bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
mov x30, x0 // restore the original return address
- ldr x0, [sp], #16
+ restore_return_regs
ret
END(return_to_handler)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 4306c93..7ed3d75 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -430,6 +430,8 @@
b.eq el0_fpsimd_acc
cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception
b.eq el0_fpsimd_exc
+ cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
+ b.eq el0_sp_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0
b.eq el0_undef
cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index c56956a..4c46c54 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -332,21 +332,15 @@
*/
static int __init fpsimd_init(void)
{
- u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
-
- if (pfr & (0xf << 16)) {
+ if (elf_hwcap & HWCAP_FP) {
+ fpsimd_pm_init();
+ fpsimd_hotplug_init();
+ } else {
pr_notice("Floating-point is not implemented\n");
- return 0;
}
- elf_hwcap |= HWCAP_FP;
- if (pfr & (0xf << 20))
+ if (!(elf_hwcap & HWCAP_ASIMD))
pr_notice("Advanced SIMD is not implemented\n");
- else
- elf_hwcap |= HWCAP_ASIMD;
-
- fpsimd_pm_init();
- fpsimd_hotplug_init();
return 0;
}
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 90d09ed..514c1cc 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -29,11 +29,13 @@
#include <asm/asm-offsets.h>
#include <asm/cache.h>
#include <asm/cputype.h>
+#include <asm/kernel-pgtable.h>
#include <asm/memory.h>
-#include <asm/thread_info.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
#include <asm/page.h>
+#include <asm/sysreg.h>
+#include <asm/thread_info.h>
#include <asm/virt.h>
#define __PHYS_OFFSET (KERNEL_START - TEXT_OFFSET)
@@ -46,32 +48,10 @@
#error TEXT_OFFSET must be less than 2MB
#endif
-#ifdef CONFIG_ARM64_64K_PAGES
-#define BLOCK_SHIFT PAGE_SHIFT
-#define BLOCK_SIZE PAGE_SIZE
-#define TABLE_SHIFT PMD_SHIFT
-#else
-#define BLOCK_SHIFT SECTION_SHIFT
-#define BLOCK_SIZE SECTION_SIZE
-#define TABLE_SHIFT PUD_SHIFT
-#endif
-
#define KERNEL_START _text
#define KERNEL_END _end
/*
- * Initial memory map attributes.
- */
-#define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF | PTE_SHARED
-#define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S
-
-#ifdef CONFIG_ARM64_64K_PAGES
-#define MM_MMUFLAGS PTE_ATTRINDX(MT_NORMAL) | PTE_FLAGS
-#else
-#define MM_MMUFLAGS PMD_ATTRINDX(MT_NORMAL) | PMD_FLAGS
-#endif
-
-/*
* Kernel startup entry point.
* ---------------------------
*
@@ -120,8 +100,8 @@
#endif
#ifdef CONFIG_EFI
- .globl stext_offset
- .set stext_offset, stext - efi_head
+ .globl __efistub_stext_offset
+ .set __efistub_stext_offset, stext - efi_head
.align 3
pe_header:
.ascii "PE"
@@ -144,8 +124,8 @@
.long _end - stext // SizeOfCode
.long 0 // SizeOfInitializedData
.long 0 // SizeOfUninitializedData
- .long efi_stub_entry - efi_head // AddressOfEntryPoint
- .long stext_offset // BaseOfCode
+ .long __efistub_entry - efi_head // AddressOfEntryPoint
+ .long __efistub_stext_offset // BaseOfCode
extra_header_fields:
.quad 0 // ImageBase
@@ -162,7 +142,7 @@
.long _end - efi_head // SizeOfImage
// Everything before the kernel image is considered part of the header
- .long stext_offset // SizeOfHeaders
+ .long __efistub_stext_offset // SizeOfHeaders
.long 0 // CheckSum
.short 0xa // Subsystem (EFI application)
.short 0 // DllCharacteristics
@@ -207,9 +187,9 @@
.byte 0
.byte 0 // end of 0 padding of section name
.long _end - stext // VirtualSize
- .long stext_offset // VirtualAddress
+ .long __efistub_stext_offset // VirtualAddress
.long _edata - stext // SizeOfRawData
- .long stext_offset // PointerToRawData
+ .long __efistub_stext_offset // PointerToRawData
.long 0 // PointerToRelocations (0 for executables)
.long 0 // PointerToLineNumbers (0 for executables)
@@ -292,8 +272,11 @@
*/
.macro create_pgd_entry, tbl, virt, tmp1, tmp2
create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2
-#if SWAPPER_PGTABLE_LEVELS == 3
- create_table_entry \tbl, \virt, TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
+#if SWAPPER_PGTABLE_LEVELS > 3
+ create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2
+#endif
+#if SWAPPER_PGTABLE_LEVELS > 2
+ create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
#endif
.endm
@@ -305,15 +288,15 @@
* Corrupts: phys, start, end, pstate
*/
.macro create_block_map, tbl, flags, phys, start, end
- lsr \phys, \phys, #BLOCK_SHIFT
- lsr \start, \start, #BLOCK_SHIFT
+ lsr \phys, \phys, #SWAPPER_BLOCK_SHIFT
+ lsr \start, \start, #SWAPPER_BLOCK_SHIFT
and \start, \start, #PTRS_PER_PTE - 1 // table index
- orr \phys, \flags, \phys, lsl #BLOCK_SHIFT // table entry
- lsr \end, \end, #BLOCK_SHIFT
+ orr \phys, \flags, \phys, lsl #SWAPPER_BLOCK_SHIFT // table entry
+ lsr \end, \end, #SWAPPER_BLOCK_SHIFT
and \end, \end, #PTRS_PER_PTE - 1 // table end index
9999: str \phys, [\tbl, \start, lsl #3] // store the entry
add \start, \start, #1 // next entry
- add \phys, \phys, #BLOCK_SIZE // next block
+ add \phys, \phys, #SWAPPER_BLOCK_SIZE // next block
cmp \start, \end
b.ls 9999b
.endm
@@ -350,7 +333,7 @@
cmp x0, x6
b.lo 1b
- ldr x7, =MM_MMUFLAGS
+ ldr x7, =SWAPPER_MM_MMUFLAGS
/*
* Create the identity mapping.
@@ -444,6 +427,9 @@
str_l x21, __fdt_pointer, x5 // Save FDT pointer
str_l x24, memstart_addr, x6 // Save PHYS_OFFSET
mov x29, #0
+#ifdef CONFIG_KASAN
+ bl kasan_early_init
+#endif
b start_kernel
ENDPROC(__mmap_switched)
@@ -628,10 +614,17 @@
* 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
+ * Other registers depend on the function called upon completion.
+ *
+ * Checks if the selected granule size is supported by the CPU.
+ * If it isn't, park the CPU
*/
.section ".idmap.text", "ax"
__enable_mmu:
+ mrs x1, ID_AA64MMFR0_EL1
+ ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
+ cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
+ b.ne __no_granule_support
ldr x5, =vectors
msr vbar_el1, x5
msr ttbr0_el1, x25 // load TTBR0
@@ -649,3 +642,8 @@
isb
br x27
ENDPROC(__enable_mmu)
+
+__no_granule_support:
+ wfe
+ b __no_granule_support
+ENDPROC(__no_granule_support)
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index bba85c8..b45c95d 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -28,6 +28,7 @@
#include <linux/ptrace.h>
#include <linux/smp.h>
+#include <asm/compat.h>
#include <asm/current.h>
#include <asm/debug-monitors.h>
#include <asm/hw_breakpoint.h>
@@ -163,6 +164,20 @@
HW_BREAKPOINT_RESTORE
};
+static int is_compat_bp(struct perf_event *bp)
+{
+ struct task_struct *tsk = bp->hw.target;
+
+ /*
+ * tsk can be NULL for per-cpu (non-ptrace) breakpoints.
+ * In this case, use the native interface, since we don't have
+ * the notion of a "compat CPU" and could end up relying on
+ * deprecated behaviour if we use unaligned watchpoints in
+ * AArch64 state.
+ */
+ return tsk && is_compat_thread(task_thread_info(tsk));
+}
+
/**
* hw_breakpoint_slot_setup - Find and setup a perf slot according to
* operations
@@ -420,7 +435,7 @@
* Watchpoints can be of length 1, 2, 4 or 8 bytes.
*/
if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
- if (is_compat_task()) {
+ if (is_compat_bp(bp)) {
if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
info->ctrl.len != ARM_BREAKPOINT_LEN_4)
return -EINVAL;
@@ -477,7 +492,7 @@
* AArch32 tasks expect some simple alignment fixups, so emulate
* that here.
*/
- if (is_compat_task()) {
+ if (is_compat_bp(bp)) {
if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
alignment_mask = 0x7;
else
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index 8fae075..bc2abb8 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -47,7 +47,10 @@
#define __HEAD_FLAG_BE 0
#endif
-#define __HEAD_FLAGS (__HEAD_FLAG_BE << 0)
+#define __HEAD_FLAG_PAGE_SIZE ((PAGE_SHIFT - 10) / 2)
+
+#define __HEAD_FLAGS ((__HEAD_FLAG_BE << 0) | \
+ (__HEAD_FLAG_PAGE_SIZE << 1))
/*
* These will output as part of the Image header, which should be little-endian
@@ -59,4 +62,37 @@
_kernel_offset_le = DATA_LE64(TEXT_OFFSET); \
_kernel_flags_le = DATA_LE64(__HEAD_FLAGS);
+#ifdef CONFIG_EFI
+
+/*
+ * The EFI stub has its own symbol namespace prefixed by __efistub_, to
+ * isolate it from the kernel proper. The following symbols are legally
+ * accessed by the stub, so provide some aliases to make them accessible.
+ * Only include data symbols here, or text symbols of functions that are
+ * guaranteed to be safe when executed at another offset than they were
+ * linked at. The routines below are all implemented in assembler in a
+ * position independent manner
+ */
+__efistub_memcmp = __pi_memcmp;
+__efistub_memchr = __pi_memchr;
+__efistub_memcpy = __pi_memcpy;
+__efistub_memmove = __pi_memmove;
+__efistub_memset = __pi_memset;
+__efistub_strlen = __pi_strlen;
+__efistub_strcmp = __pi_strcmp;
+__efistub_strncmp = __pi_strncmp;
+__efistub___flush_dcache_area = __pi___flush_dcache_area;
+
+#ifdef CONFIG_KASAN
+__efistub___memcpy = __pi_memcpy;
+__efistub___memmove = __pi_memmove;
+__efistub___memset = __pi_memset;
+#endif
+
+__efistub__text = _text;
+__efistub__end = _end;
+__efistub__edata = _edata;
+
+#endif
+
#endif /* __ASM_IMAGE_H */
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 11dc3fd..9f17ec0 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -27,7 +27,6 @@
#include <linux/init.h>
#include <linux/irqchip.h>
#include <linux/seq_file.h>
-#include <linux/ratelimit.h>
unsigned long irq_err_count;
@@ -54,64 +53,3 @@
if (!handle_arch_irq)
panic("No interrupt controller found.");
}
-
-#ifdef CONFIG_HOTPLUG_CPU
-static bool migrate_one_irq(struct irq_desc *desc)
-{
- struct irq_data *d = irq_desc_get_irq_data(desc);
- const struct cpumask *affinity = irq_data_get_affinity_mask(d);
- struct irq_chip *c;
- bool ret = false;
-
- /*
- * If this is a per-CPU interrupt, or the affinity does not
- * include this CPU, then we have nothing to do.
- */
- if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
- return false;
-
- if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
- affinity = cpu_online_mask;
- ret = true;
- }
-
- c = irq_data_get_irq_chip(d);
- if (!c->irq_set_affinity)
- pr_debug("IRQ%u: unable to set affinity\n", d->irq);
- else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
- cpumask_copy(irq_data_get_affinity_mask(d), affinity);
-
- return ret;
-}
-
-/*
- * The current CPU has been marked offline. Migrate IRQs off this CPU.
- * If the affinity settings do not allow other CPUs, force them onto any
- * available CPU.
- *
- * Note: we must iterate over all IRQs, whether they have an attached
- * action structure or not, as we need to get chained interrupts too.
- */
-void migrate_irqs(void)
-{
- unsigned int i;
- struct irq_desc *desc;
- unsigned long flags;
-
- local_irq_save(flags);
-
- for_each_irq_desc(i, desc) {
- bool affinity_broken;
-
- raw_spin_lock(&desc->lock);
- affinity_broken = migrate_one_irq(desc);
- raw_spin_unlock(&desc->lock);
-
- if (affinity_broken)
- pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
- i, smp_processor_id());
- }
-
- local_irq_restore(flags);
-}
-#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 876eb8d..f4bc779 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -21,6 +21,7 @@
#include <linux/bitops.h>
#include <linux/elf.h>
#include <linux/gfp.h>
+#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/moduleloader.h>
@@ -34,9 +35,18 @@
void *module_alloc(unsigned long size)
{
- return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
- GFP_KERNEL, PAGE_KERNEL_EXEC, 0,
- NUMA_NO_NODE, __builtin_return_address(0));
+ void *p;
+
+ p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END,
+ GFP_KERNEL, PAGE_KERNEL_EXEC, 0,
+ NUMA_NO_NODE, __builtin_return_address(0));
+
+ if (p && (kasan_module_alloc(p, size) < 0)) {
+ vfree(p);
+ return NULL;
+ }
+
+ return p;
}
enum aarch64_reloc_op {
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index f9a74d4..5b1897e 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -18,651 +18,12 @@
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
-#define pr_fmt(fmt) "hw perfevents: " fmt
-#include <linux/bitmap.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/of_device.h>
-#include <linux/perf_event.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/uaccess.h>
-
-#include <asm/cputype.h>
-#include <asm/irq.h>
#include <asm/irq_regs.h>
-#include <asm/pmu.h>
-/*
- * ARMv8 supports a maximum of 32 events.
- * The cycle counter is included in this total.
- */
-#define ARMPMU_MAX_HWEVENTS 32
-
-static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
-static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
-static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
-
-#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
-
-/* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
-
-int
-armpmu_get_max_events(void)
-{
- int max_events = 0;
-
- if (cpu_pmu != NULL)
- max_events = cpu_pmu->num_events;
-
- return max_events;
-}
-EXPORT_SYMBOL_GPL(armpmu_get_max_events);
-
-int perf_num_counters(void)
-{
- return armpmu_get_max_events();
-}
-EXPORT_SYMBOL_GPL(perf_num_counters);
-
-#define HW_OP_UNSUPPORTED 0xFFFF
-
-#define C(_x) \
- PERF_COUNT_HW_CACHE_##_x
-
-#define CACHE_OP_UNSUPPORTED 0xFFFF
-
-#define PERF_MAP_ALL_UNSUPPORTED \
- [0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
-
-#define PERF_CACHE_MAP_ALL_UNSUPPORTED \
-[0 ... C(MAX) - 1] = { \
- [0 ... C(OP_MAX) - 1] = { \
- [0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \
- }, \
-}
-
-static int
-armpmu_map_cache_event(const unsigned (*cache_map)
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u64 config)
-{
- unsigned int cache_type, cache_op, cache_result, ret;
-
- cache_type = (config >> 0) & 0xff;
- if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
- return -EINVAL;
-
- cache_op = (config >> 8) & 0xff;
- if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
- return -EINVAL;
-
- cache_result = (config >> 16) & 0xff;
- if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
- return -EINVAL;
-
- ret = (int)(*cache_map)[cache_type][cache_op][cache_result];
-
- if (ret == CACHE_OP_UNSUPPORTED)
- return -ENOENT;
-
- return ret;
-}
-
-static int
-armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
-{
- int mapping;
-
- if (config >= PERF_COUNT_HW_MAX)
- return -EINVAL;
-
- mapping = (*event_map)[config];
- return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
-}
-
-static int
-armpmu_map_raw_event(u32 raw_event_mask, u64 config)
-{
- return (int)(config & raw_event_mask);
-}
-
-static int map_cpu_event(struct perf_event *event,
- const unsigned (*event_map)[PERF_COUNT_HW_MAX],
- const unsigned (*cache_map)
- [PERF_COUNT_HW_CACHE_MAX]
- [PERF_COUNT_HW_CACHE_OP_MAX]
- [PERF_COUNT_HW_CACHE_RESULT_MAX],
- u32 raw_event_mask)
-{
- u64 config = event->attr.config;
-
- switch (event->attr.type) {
- case PERF_TYPE_HARDWARE:
- return armpmu_map_event(event_map, config);
- case PERF_TYPE_HW_CACHE:
- return armpmu_map_cache_event(cache_map, config);
- case PERF_TYPE_RAW:
- return armpmu_map_raw_event(raw_event_mask, config);
- }
-
- return -ENOENT;
-}
-
-int
-armpmu_event_set_period(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- s64 left = local64_read(&hwc->period_left);
- s64 period = hwc->sample_period;
- int ret = 0;
-
- if (unlikely(left <= -period)) {
- left = period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- if (unlikely(left <= 0)) {
- left += period;
- local64_set(&hwc->period_left, left);
- hwc->last_period = period;
- ret = 1;
- }
-
- /*
- * Limit the maximum period to prevent the counter value
- * from overtaking the one we are about to program. In
- * effect we are reducing max_period to account for
- * interrupt latency (and we are being very conservative).
- */
- if (left > (armpmu->max_period >> 1))
- left = armpmu->max_period >> 1;
-
- local64_set(&hwc->prev_count, (u64)-left);
-
- armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);
-
- perf_event_update_userpage(event);
-
- return ret;
-}
-
-u64
-armpmu_event_update(struct perf_event *event,
- struct hw_perf_event *hwc,
- int idx)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- u64 delta, prev_raw_count, new_raw_count;
-
-again:
- prev_raw_count = local64_read(&hwc->prev_count);
- new_raw_count = armpmu->read_counter(idx);
-
- if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- new_raw_count) != prev_raw_count)
- goto again;
-
- delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
-
- local64_add(delta, &event->count);
- local64_sub(delta, &hwc->period_left);
-
- return new_raw_count;
-}
-
-static void
-armpmu_read(struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- /* Don't read disabled counters! */
- if (hwc->idx < 0)
- return;
-
- armpmu_event_update(event, hwc, hwc->idx);
-}
-
-static void
-armpmu_stop(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
-
- /*
- * ARM pmu always has to update the counter, so ignore
- * PERF_EF_UPDATE, see comments in armpmu_start().
- */
- if (!(hwc->state & PERF_HES_STOPPED)) {
- armpmu->disable(hwc, hwc->idx);
- barrier(); /* why? */
- armpmu_event_update(event, hwc, hwc->idx);
- hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
- }
-}
-
-static void
-armpmu_start(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
-
- /*
- * ARM pmu always has to reprogram the period, so ignore
- * PERF_EF_RELOAD, see the comment below.
- */
- if (flags & PERF_EF_RELOAD)
- WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
-
- hwc->state = 0;
- /*
- * Set the period again. Some counters can't be stopped, so when we
- * were stopped we simply disabled the IRQ source and the counter
- * may have been left counting. If we don't do this step then we may
- * get an interrupt too soon or *way* too late if the overflow has
- * happened since disabling.
- */
- armpmu_event_set_period(event, hwc, hwc->idx);
- armpmu->enable(hwc, hwc->idx);
-}
-
-static void
-armpmu_del(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct pmu_hw_events *hw_events = armpmu->get_hw_events();
- struct hw_perf_event *hwc = &event->hw;
- int idx = hwc->idx;
-
- WARN_ON(idx < 0);
-
- armpmu_stop(event, PERF_EF_UPDATE);
- hw_events->events[idx] = NULL;
- clear_bit(idx, hw_events->used_mask);
-
- perf_event_update_userpage(event);
-}
-
-static int
-armpmu_add(struct perf_event *event, int flags)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct pmu_hw_events *hw_events = armpmu->get_hw_events();
- struct hw_perf_event *hwc = &event->hw;
- int idx;
- int err = 0;
-
- perf_pmu_disable(event->pmu);
-
- /* If we don't have a space for the counter then finish early. */
- idx = armpmu->get_event_idx(hw_events, hwc);
- if (idx < 0) {
- err = idx;
- goto out;
- }
-
- /*
- * If there is an event in the counter we are going to use then make
- * sure it is disabled.
- */
- event->hw.idx = idx;
- armpmu->disable(hwc, idx);
- hw_events->events[idx] = event;
-
- hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
- if (flags & PERF_EF_START)
- armpmu_start(event, PERF_EF_RELOAD);
-
- /* Propagate our changes to the userspace mapping. */
- perf_event_update_userpage(event);
-
-out:
- perf_pmu_enable(event->pmu);
- return err;
-}
-
-static int
-validate_event(struct pmu *pmu, struct pmu_hw_events *hw_events,
- struct perf_event *event)
-{
- struct arm_pmu *armpmu;
- struct hw_perf_event fake_event = event->hw;
- struct pmu *leader_pmu = event->group_leader->pmu;
-
- if (is_software_event(event))
- return 1;
-
- /*
- * Reject groups spanning multiple HW PMUs (e.g. CPU + CCI). The
- * core perf code won't check that the pmu->ctx == leader->ctx
- * until after pmu->event_init(event).
- */
- if (event->pmu != pmu)
- return 0;
-
- if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
- return 1;
-
- if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
- return 1;
-
- armpmu = to_arm_pmu(event->pmu);
- return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
-}
-
-static int
-validate_group(struct perf_event *event)
-{
- struct perf_event *sibling, *leader = event->group_leader;
- struct pmu_hw_events fake_pmu;
- DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);
-
- /*
- * Initialise the fake PMU. We only need to populate the
- * used_mask for the purposes of validation.
- */
- memset(fake_used_mask, 0, sizeof(fake_used_mask));
- fake_pmu.used_mask = fake_used_mask;
-
- if (!validate_event(event->pmu, &fake_pmu, leader))
- return -EINVAL;
-
- list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
- if (!validate_event(event->pmu, &fake_pmu, sibling))
- return -EINVAL;
- }
-
- if (!validate_event(event->pmu, &fake_pmu, event))
- return -EINVAL;
-
- return 0;
-}
-
-static void
-armpmu_disable_percpu_irq(void *data)
-{
- unsigned int irq = *(unsigned int *)data;
- disable_percpu_irq(irq);
-}
-
-static void
-armpmu_release_hardware(struct arm_pmu *armpmu)
-{
- int irq;
- unsigned int i, irqs;
- struct platform_device *pmu_device = armpmu->plat_device;
-
- irqs = min(pmu_device->num_resources, num_possible_cpus());
- if (!irqs)
- return;
-
- irq = platform_get_irq(pmu_device, 0);
- if (irq <= 0)
- return;
-
- if (irq_is_percpu(irq)) {
- on_each_cpu(armpmu_disable_percpu_irq, &irq, 1);
- free_percpu_irq(irq, &cpu_hw_events);
- } else {
- for (i = 0; i < irqs; ++i) {
- int cpu = i;
-
- if (armpmu->irq_affinity)
- cpu = armpmu->irq_affinity[i];
-
- if (!cpumask_test_and_clear_cpu(cpu, &armpmu->active_irqs))
- continue;
- irq = platform_get_irq(pmu_device, i);
- if (irq > 0)
- free_irq(irq, armpmu);
- }
- }
-}
-
-static void
-armpmu_enable_percpu_irq(void *data)
-{
- unsigned int irq = *(unsigned int *)data;
- enable_percpu_irq(irq, IRQ_TYPE_NONE);
-}
-
-static int
-armpmu_reserve_hardware(struct arm_pmu *armpmu)
-{
- int err, irq;
- unsigned int i, irqs;
- struct platform_device *pmu_device = armpmu->plat_device;
-
- if (!pmu_device)
- return -ENODEV;
-
- irqs = min(pmu_device->num_resources, num_possible_cpus());
- if (!irqs) {
- pr_err("no irqs for PMUs defined\n");
- return -ENODEV;
- }
-
- irq = platform_get_irq(pmu_device, 0);
- if (irq <= 0) {
- pr_err("failed to get valid irq for PMU device\n");
- return -ENODEV;
- }
-
- if (irq_is_percpu(irq)) {
- err = request_percpu_irq(irq, armpmu->handle_irq,
- "arm-pmu", &cpu_hw_events);
-
- if (err) {
- pr_err("unable to request percpu IRQ%d for ARM PMU counters\n",
- irq);
- armpmu_release_hardware(armpmu);
- return err;
- }
-
- on_each_cpu(armpmu_enable_percpu_irq, &irq, 1);
- } else {
- for (i = 0; i < irqs; ++i) {
- int cpu = i;
-
- err = 0;
- irq = platform_get_irq(pmu_device, i);
- if (irq <= 0)
- continue;
-
- if (armpmu->irq_affinity)
- cpu = armpmu->irq_affinity[i];
-
- /*
- * If we have a single PMU interrupt that we can't shift,
- * assume that we're running on a uniprocessor machine and
- * continue. Otherwise, continue without this interrupt.
- */
- if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
- pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
- irq, cpu);
- continue;
- }
-
- err = request_irq(irq, armpmu->handle_irq,
- IRQF_NOBALANCING | IRQF_NO_THREAD,
- "arm-pmu", armpmu);
- if (err) {
- pr_err("unable to request IRQ%d for ARM PMU counters\n",
- irq);
- armpmu_release_hardware(armpmu);
- return err;
- }
-
- cpumask_set_cpu(cpu, &armpmu->active_irqs);
- }
- }
-
- return 0;
-}
-
-static void
-hw_perf_event_destroy(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- atomic_t *active_events = &armpmu->active_events;
- struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;
-
- if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
- armpmu_release_hardware(armpmu);
- mutex_unlock(pmu_reserve_mutex);
- }
-}
-
-static int
-event_requires_mode_exclusion(struct perf_event_attr *attr)
-{
- return attr->exclude_idle || attr->exclude_user ||
- attr->exclude_kernel || attr->exclude_hv;
-}
-
-static int
-__hw_perf_event_init(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- struct hw_perf_event *hwc = &event->hw;
- int mapping, err;
-
- mapping = armpmu->map_event(event);
-
- if (mapping < 0) {
- pr_debug("event %x:%llx not supported\n", event->attr.type,
- event->attr.config);
- return mapping;
- }
-
- /*
- * We don't assign an index until we actually place the event onto
- * hardware. Use -1 to signify that we haven't decided where to put it
- * yet. For SMP systems, each core has it's own PMU so we can't do any
- * clever allocation or constraints checking at this point.
- */
- hwc->idx = -1;
- hwc->config_base = 0;
- hwc->config = 0;
- hwc->event_base = 0;
-
- /*
- * Check whether we need to exclude the counter from certain modes.
- */
- if ((!armpmu->set_event_filter ||
- armpmu->set_event_filter(hwc, &event->attr)) &&
- event_requires_mode_exclusion(&event->attr)) {
- pr_debug("ARM performance counters do not support mode exclusion\n");
- return -EPERM;
- }
-
- /*
- * Store the event encoding into the config_base field.
- */
- hwc->config_base |= (unsigned long)mapping;
-
- if (!hwc->sample_period) {
- /*
- * For non-sampling runs, limit the sample_period to half
- * of the counter width. That way, the new counter value
- * is far less likely to overtake the previous one unless
- * you have some serious IRQ latency issues.
- */
- hwc->sample_period = armpmu->max_period >> 1;
- hwc->last_period = hwc->sample_period;
- local64_set(&hwc->period_left, hwc->sample_period);
- }
-
- err = 0;
- if (event->group_leader != event) {
- err = validate_group(event);
- if (err)
- return -EINVAL;
- }
-
- return err;
-}
-
-static int armpmu_event_init(struct perf_event *event)
-{
- struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
- int err = 0;
- atomic_t *active_events = &armpmu->active_events;
-
- if (armpmu->map_event(event) == -ENOENT)
- return -ENOENT;
-
- event->destroy = hw_perf_event_destroy;
-
- if (!atomic_inc_not_zero(active_events)) {
- mutex_lock(&armpmu->reserve_mutex);
- if (atomic_read(active_events) == 0)
- err = armpmu_reserve_hardware(armpmu);
-
- if (!err)
- atomic_inc(active_events);
- mutex_unlock(&armpmu->reserve_mutex);
- }
-
- if (err)
- return err;
-
- err = __hw_perf_event_init(event);
- if (err)
- hw_perf_event_destroy(event);
-
- return err;
-}
-
-static void armpmu_enable(struct pmu *pmu)
-{
- struct arm_pmu *armpmu = to_arm_pmu(pmu);
- struct pmu_hw_events *hw_events = armpmu->get_hw_events();
- int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
-
- if (enabled)
- armpmu->start();
-}
-
-static void armpmu_disable(struct pmu *pmu)
-{
- struct arm_pmu *armpmu = to_arm_pmu(pmu);
- armpmu->stop();
-}
-
-static void __init armpmu_init(struct arm_pmu *armpmu)
-{
- atomic_set(&armpmu->active_events, 0);
- mutex_init(&armpmu->reserve_mutex);
-
- armpmu->pmu = (struct pmu) {
- .pmu_enable = armpmu_enable,
- .pmu_disable = armpmu_disable,
- .event_init = armpmu_event_init,
- .add = armpmu_add,
- .del = armpmu_del,
- .start = armpmu_start,
- .stop = armpmu_stop,
- .read = armpmu_read,
- };
-}
-
-int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type)
-{
- armpmu_init(armpmu);
- return perf_pmu_register(&armpmu->pmu, name, type);
-}
+#include <linux/of.h>
+#include <linux/perf/arm_pmu.h>
+#include <linux/platform_device.h>
/*
* ARMv8 PMUv3 Performance Events handling code.
@@ -708,6 +69,21 @@
ARMV8_PMUV3_PERFCTR_BUS_CYCLES = 0x1D,
};
+/* ARMv8 Cortex-A53 specific event types. */
+enum armv8_a53_pmu_perf_types {
+ ARMV8_A53_PERFCTR_PREFETCH_LINEFILL = 0xC2,
+};
+
+/* ARMv8 Cortex-A57 specific event types. */
+enum armv8_a57_perf_types {
+ ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD = 0x40,
+ ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST = 0x41,
+ ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD = 0x42,
+ ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST = 0x43,
+ ARMV8_A57_PERFCTR_DTLB_REFILL_LD = 0x4c,
+ ARMV8_A57_PERFCTR_DTLB_REFILL_ST = 0x4d,
+};
+
/* PMUv3 HW events mapping. */
static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
PERF_MAP_ALL_UNSUPPORTED,
@@ -718,6 +94,28 @@
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
};
+/* ARM Cortex-A53 HW events mapping. */
+static const unsigned armv8_a53_perf_map[PERF_COUNT_HW_MAX] = {
+ PERF_MAP_ALL_UNSUPPORTED,
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+};
+
+static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = {
+ PERF_MAP_ALL_UNSUPPORTED,
+ [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
+ [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+};
+
static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
@@ -734,12 +132,60 @@
[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
};
+static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+ [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_A53_PERFCTR_PREFETCH_LINEFILL,
+
+ [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS,
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_ITLB_REFILL,
+
+ [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
+static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD,
+ [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST,
+
+ [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS,
+ [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL,
+
+ [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_DTLB_REFILL_LD,
+ [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_DTLB_REFILL_ST,
+
+ [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_ITLB_REFILL,
+
+ [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+ [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
+
/*
* Perf Events' indices
*/
#define ARMV8_IDX_CYCLE_COUNTER 0
#define ARMV8_IDX_COUNTER0 1
-#define ARMV8_IDX_COUNTER_LAST (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
+#define ARMV8_IDX_COUNTER_LAST(cpu_pmu) \
+ (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
#define ARMV8_MAX_COUNTERS 32
#define ARMV8_COUNTER_MASK (ARMV8_MAX_COUNTERS - 1)
@@ -805,49 +251,34 @@
return pmovsr & ARMV8_OVERFLOWED_MASK;
}
-static inline int armv8pmu_counter_valid(int idx)
+static inline int armv8pmu_counter_valid(struct arm_pmu *cpu_pmu, int idx)
{
- return idx >= ARMV8_IDX_CYCLE_COUNTER && idx <= ARMV8_IDX_COUNTER_LAST;
+ return idx >= ARMV8_IDX_CYCLE_COUNTER &&
+ idx <= ARMV8_IDX_COUNTER_LAST(cpu_pmu);
}
static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
{
- int ret = 0;
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u checking wrong counter %d overflow status\n",
- smp_processor_id(), idx);
- } else {
- counter = ARMV8_IDX_TO_COUNTER(idx);
- ret = pmnc & BIT(counter);
- }
-
- return ret;
+ return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
}
static inline int armv8pmu_select_counter(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u selecting wrong PMNC counter %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmselr_el0, %0" :: "r" (counter));
isb();
return idx;
}
-static inline u32 armv8pmu_read_counter(int idx)
+static inline u32 armv8pmu_read_counter(struct perf_event *event)
{
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
u32 value = 0;
- if (!armv8pmu_counter_valid(idx))
+ if (!armv8pmu_counter_valid(cpu_pmu, idx))
pr_err("CPU%u reading wrong counter %d\n",
smp_processor_id(), idx);
else if (idx == ARMV8_IDX_CYCLE_COUNTER)
@@ -858,9 +289,13 @@
return value;
}
-static inline void armv8pmu_write_counter(int idx, u32 value)
+static inline void armv8pmu_write_counter(struct perf_event *event, u32 value)
{
- if (!armv8pmu_counter_valid(idx))
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ if (!armv8pmu_counter_valid(cpu_pmu, idx))
pr_err("CPU%u writing wrong counter %d\n",
smp_processor_id(), idx);
else if (idx == ARMV8_IDX_CYCLE_COUNTER)
@@ -879,65 +314,34 @@
static inline int armv8pmu_enable_counter(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u enabling wrong PMNC counter %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmcntenset_el0, %0" :: "r" (BIT(counter)));
return idx;
}
static inline int armv8pmu_disable_counter(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u disabling wrong PMNC counter %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmcntenclr_el0, %0" :: "r" (BIT(counter)));
return idx;
}
static inline int armv8pmu_enable_intens(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmintenset_el1, %0" :: "r" (BIT(counter)));
return idx;
}
static inline int armv8pmu_disable_intens(int idx)
{
- u32 counter;
-
- if (!armv8pmu_counter_valid(idx)) {
- pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n",
- smp_processor_id(), idx);
- return -EINVAL;
- }
-
- counter = ARMV8_IDX_TO_COUNTER(idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(idx);
asm volatile("msr pmintenclr_el1, %0" :: "r" (BIT(counter)));
isb();
/* Clear the overflow flag in case an interrupt is pending. */
asm volatile("msr pmovsclr_el0, %0" :: "r" (BIT(counter)));
isb();
+
return idx;
}
@@ -955,10 +359,13 @@
return value;
}
-static void armv8pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void armv8pmu_enable_event(struct perf_event *event)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct hw_perf_event *hwc = &event->hw;
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+ int idx = hwc->idx;
/*
* Enable counter and interrupt, and set the counter to count
@@ -989,10 +396,13 @@
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
-static void armv8pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static void armv8pmu_disable_event(struct perf_event *event)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct hw_perf_event *hwc = &event->hw;
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+ int idx = hwc->idx;
/*
* Disable counter and interrupt
@@ -1016,7 +426,8 @@
{
u32 pmovsr;
struct perf_sample_data data;
- struct pmu_hw_events *cpuc;
+ struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev;
+ struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
struct pt_regs *regs;
int idx;
@@ -1036,7 +447,6 @@
*/
regs = get_irq_regs();
- cpuc = this_cpu_ptr(&cpu_hw_events);
for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
struct perf_event *event = cpuc->events[idx];
struct hw_perf_event *hwc;
@@ -1053,13 +463,13 @@
continue;
hwc = &event->hw;
- armpmu_event_update(event, hwc, idx);
+ armpmu_event_update(event);
perf_sample_data_init(&data, 0, hwc->last_period);
- if (!armpmu_event_set_period(event, hwc, idx))
+ if (!armpmu_event_set_period(event))
continue;
if (perf_event_overflow(event, &data, regs))
- cpu_pmu->disable(hwc, idx);
+ cpu_pmu->disable(event);
}
/*
@@ -1074,10 +484,10 @@
return IRQ_HANDLED;
}
-static void armv8pmu_start(void)
+static void armv8pmu_start(struct arm_pmu *cpu_pmu)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
raw_spin_lock_irqsave(&events->pmu_lock, flags);
/* Enable all counters */
@@ -1085,10 +495,10 @@
raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
}
-static void armv8pmu_stop(void)
+static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
{
unsigned long flags;
- struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+ struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
raw_spin_lock_irqsave(&events->pmu_lock, flags);
/* Disable all counters */
@@ -1097,10 +507,12 @@
}
static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
- struct hw_perf_event *event)
+ struct perf_event *event)
{
int idx;
- unsigned long evtype = event->config_base & ARMV8_EVTYPE_EVENT;
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long evtype = hwc->config_base & ARMV8_EVTYPE_EVENT;
/* Always place a cycle counter into the cycle counter. */
if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) {
@@ -1151,11 +563,14 @@
static void armv8pmu_reset(void *info)
{
+ struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
u32 idx, nb_cnt = cpu_pmu->num_events;
/* The counter and interrupt enable registers are unknown at reset. */
- for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx)
- armv8pmu_disable_event(NULL, idx);
+ for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
+ armv8pmu_disable_counter(idx);
+ armv8pmu_disable_intens(idx);
+ }
/* Initialize & Reset PMNC: C and P bits. */
armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C);
@@ -1166,169 +581,104 @@
static int armv8_pmuv3_map_event(struct perf_event *event)
{
- return map_cpu_event(event, &armv8_pmuv3_perf_map,
+ return armpmu_map_event(event, &armv8_pmuv3_perf_map,
&armv8_pmuv3_perf_cache_map,
ARMV8_EVTYPE_EVENT);
}
-static struct arm_pmu armv8pmu = {
- .handle_irq = armv8pmu_handle_irq,
- .enable = armv8pmu_enable_event,
- .disable = armv8pmu_disable_event,
- .read_counter = armv8pmu_read_counter,
- .write_counter = armv8pmu_write_counter,
- .get_event_idx = armv8pmu_get_event_idx,
- .start = armv8pmu_start,
- .stop = armv8pmu_stop,
- .reset = armv8pmu_reset,
- .max_period = (1LLU << 32) - 1,
-};
-
-static u32 __init armv8pmu_read_num_pmnc_events(void)
+static int armv8_a53_map_event(struct perf_event *event)
{
- u32 nb_cnt;
+ return armpmu_map_event(event, &armv8_a53_perf_map,
+ &armv8_a53_perf_cache_map,
+ ARMV8_EVTYPE_EVENT);
+}
+
+static int armv8_a57_map_event(struct perf_event *event)
+{
+ return armpmu_map_event(event, &armv8_a57_perf_map,
+ &armv8_a57_perf_cache_map,
+ ARMV8_EVTYPE_EVENT);
+}
+
+static void armv8pmu_read_num_pmnc_events(void *info)
+{
+ int *nb_cnt = info;
/* Read the nb of CNTx counters supported from PMNC */
- nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK;
+ *nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK;
- /* Add the CPU cycles counter and return */
- return nb_cnt + 1;
+ /* Add the CPU cycles counter */
+ *nb_cnt += 1;
}
-static struct arm_pmu *__init armv8_pmuv3_pmu_init(void)
+static int armv8pmu_probe_num_events(struct arm_pmu *arm_pmu)
{
- armv8pmu.name = "arm/armv8-pmuv3";
- armv8pmu.map_event = armv8_pmuv3_map_event;
- armv8pmu.num_events = armv8pmu_read_num_pmnc_events();
- armv8pmu.set_event_filter = armv8pmu_set_event_filter;
- return &armv8pmu;
+ return smp_call_function_any(&arm_pmu->supported_cpus,
+ armv8pmu_read_num_pmnc_events,
+ &arm_pmu->num_events, 1);
}
-/*
- * Ensure the PMU has sane values out of reset.
- * This requires SMP to be available, so exists as a separate initcall.
- */
-static int __init
-cpu_pmu_reset(void)
+static void armv8_pmu_init(struct arm_pmu *cpu_pmu)
{
- if (cpu_pmu && cpu_pmu->reset)
- return on_each_cpu(cpu_pmu->reset, NULL, 1);
- return 0;
+ cpu_pmu->handle_irq = armv8pmu_handle_irq,
+ cpu_pmu->enable = armv8pmu_enable_event,
+ cpu_pmu->disable = armv8pmu_disable_event,
+ cpu_pmu->read_counter = armv8pmu_read_counter,
+ cpu_pmu->write_counter = armv8pmu_write_counter,
+ cpu_pmu->get_event_idx = armv8pmu_get_event_idx,
+ cpu_pmu->start = armv8pmu_start,
+ cpu_pmu->stop = armv8pmu_stop,
+ cpu_pmu->reset = armv8pmu_reset,
+ cpu_pmu->max_period = (1LLU << 32) - 1,
+ cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
}
-arch_initcall(cpu_pmu_reset);
-/*
- * PMU platform driver and devicetree bindings.
- */
-static const struct of_device_id armpmu_of_device_ids[] = {
- {.compatible = "arm,armv8-pmuv3"},
+static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
+{
+ armv8_pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv8_pmuv3";
+ cpu_pmu->map_event = armv8_pmuv3_map_event;
+ return armv8pmu_probe_num_events(cpu_pmu);
+}
+
+static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ armv8_pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv8_cortex_a53";
+ cpu_pmu->map_event = armv8_a53_map_event;
+ return armv8pmu_probe_num_events(cpu_pmu);
+}
+
+static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ armv8_pmu_init(cpu_pmu);
+ cpu_pmu->name = "armv8_cortex_a57";
+ cpu_pmu->map_event = armv8_a57_map_event;
+ return armv8pmu_probe_num_events(cpu_pmu);
+}
+
+static const struct of_device_id armv8_pmu_of_device_ids[] = {
+ {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init},
+ {.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init},
+ {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init},
{},
};
-static int armpmu_device_probe(struct platform_device *pdev)
+static int armv8_pmu_device_probe(struct platform_device *pdev)
{
- int i, irq, *irqs;
-
- if (!cpu_pmu)
- return -ENODEV;
-
- /* Don't bother with PPIs; they're already affine */
- irq = platform_get_irq(pdev, 0);
- if (irq >= 0 && irq_is_percpu(irq))
- goto out;
-
- irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
- if (!irqs)
- return -ENOMEM;
-
- for (i = 0; i < pdev->num_resources; ++i) {
- struct device_node *dn;
- int cpu;
-
- dn = of_parse_phandle(pdev->dev.of_node, "interrupt-affinity",
- i);
- if (!dn) {
- pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
- of_node_full_name(pdev->dev.of_node), i);
- break;
- }
-
- for_each_possible_cpu(cpu)
- if (dn == of_cpu_device_node_get(cpu))
- break;
-
- if (cpu >= nr_cpu_ids) {
- pr_warn("Failed to find logical CPU for %s\n",
- dn->name);
- of_node_put(dn);
- break;
- }
- of_node_put(dn);
-
- irqs[i] = cpu;
- }
-
- if (i == pdev->num_resources)
- cpu_pmu->irq_affinity = irqs;
- else
- kfree(irqs);
-
-out:
- cpu_pmu->plat_device = pdev;
- return 0;
+ return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
}
-static struct platform_driver armpmu_driver = {
+static struct platform_driver armv8_pmu_driver = {
.driver = {
- .name = "arm-pmu",
- .of_match_table = armpmu_of_device_ids,
+ .name = "armv8-pmu",
+ .of_match_table = armv8_pmu_of_device_ids,
},
- .probe = armpmu_device_probe,
+ .probe = armv8_pmu_device_probe,
};
-static int __init register_pmu_driver(void)
+static int __init register_armv8_pmu_driver(void)
{
- return platform_driver_register(&armpmu_driver);
+ return platform_driver_register(&armv8_pmu_driver);
}
-device_initcall(register_pmu_driver);
-
-static struct pmu_hw_events *armpmu_get_cpu_events(void)
-{
- return this_cpu_ptr(&cpu_hw_events);
-}
-
-static void __init cpu_pmu_init(struct arm_pmu *armpmu)
-{
- int cpu;
- for_each_possible_cpu(cpu) {
- struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
- events->events = per_cpu(hw_events, cpu);
- events->used_mask = per_cpu(used_mask, cpu);
- raw_spin_lock_init(&events->pmu_lock);
- }
- armpmu->get_hw_events = armpmu_get_cpu_events;
-}
-
-static int __init init_hw_perf_events(void)
-{
- u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
-
- switch ((dfr >> 8) & 0xf) {
- case 0x1: /* PMUv3 */
- cpu_pmu = armv8_pmuv3_pmu_init();
- break;
- }
-
- if (cpu_pmu) {
- pr_info("enabled with %s PMU driver, %d counters available\n",
- cpu_pmu->name, cpu_pmu->num_events);
- cpu_pmu_init(cpu_pmu);
- armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
- } else {
- pr_info("no hardware support available\n");
- }
-
- return 0;
-}
-early_initcall(init_hw_perf_events);
-
+device_initcall(register_armv8_pmu_driver);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 223b093..f75b540 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -44,6 +44,7 @@
#include <linux/hw_breakpoint.h>
#include <linux/personality.h>
#include <linux/notifier.h>
+#include <trace/events/power.h>
#include <asm/compat.h>
#include <asm/cacheflush.h>
@@ -75,8 +76,10 @@
* This should do all the clock switching and wait for interrupt
* tricks
*/
+ trace_cpu_idle_rcuidle(1, smp_processor_id());
cpu_do_idle();
local_irq_enable();
+ trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 6bab21f..556301f 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -28,7 +28,6 @@
#include <linux/console.h>
#include <linux/cache.h>
#include <linux/bootmem.h>
-#include <linux/seq_file.h>
#include <linux/screen_info.h>
#include <linux/init.h>
#include <linux/kexec.h>
@@ -44,7 +43,6 @@
#include <linux/of_fdt.h>
#include <linux/of_platform.h>
#include <linux/efi.h>
-#include <linux/personality.h>
#include <linux/psci.h>
#include <asm/acpi.h>
@@ -54,6 +52,7 @@
#include <asm/elf.h>
#include <asm/cpufeature.h>
#include <asm/cpu_ops.h>
+#include <asm/kasan.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
@@ -64,23 +63,6 @@
#include <asm/efi.h>
#include <asm/xen/hypervisor.h>
-unsigned long elf_hwcap __read_mostly;
-EXPORT_SYMBOL_GPL(elf_hwcap);
-
-#ifdef CONFIG_COMPAT
-#define COMPAT_ELF_HWCAP_DEFAULT \
- (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
- COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
- COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
- COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
- COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
- COMPAT_HWCAP_LPAE)
-unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
-unsigned int compat_elf_hwcap2 __read_mostly;
-#endif
-
-DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
-
phys_addr_t __fdt_pointer __initdata;
/*
@@ -195,104 +177,6 @@
__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
}
-static void __init setup_processor(void)
-{
- u64 features;
- s64 block;
- u32 cwg;
- int cls;
-
- printk("CPU: AArch64 Processor [%08x] revision %d\n",
- read_cpuid_id(), read_cpuid_id() & 15);
-
- sprintf(init_utsname()->machine, ELF_PLATFORM);
- elf_hwcap = 0;
-
- cpuinfo_store_boot_cpu();
-
- /*
- * Check for sane CTR_EL0.CWG value.
- */
- cwg = cache_type_cwg();
- cls = cache_line_size();
- if (!cwg)
- pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n",
- cls);
- if (L1_CACHE_BYTES < cls)
- pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n",
- L1_CACHE_BYTES, cls);
-
- /*
- * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks.
- * The blocks we test below represent incremental functionality
- * for non-negative values. Negative values are reserved.
- */
- features = read_cpuid(ID_AA64ISAR0_EL1);
- block = cpuid_feature_extract_field(features, 4);
- if (block > 0) {
- switch (block) {
- default:
- case 2:
- elf_hwcap |= HWCAP_PMULL;
- case 1:
- elf_hwcap |= HWCAP_AES;
- case 0:
- break;
- }
- }
-
- if (cpuid_feature_extract_field(features, 8) > 0)
- elf_hwcap |= HWCAP_SHA1;
-
- if (cpuid_feature_extract_field(features, 12) > 0)
- elf_hwcap |= HWCAP_SHA2;
-
- if (cpuid_feature_extract_field(features, 16) > 0)
- elf_hwcap |= HWCAP_CRC32;
-
- block = cpuid_feature_extract_field(features, 20);
- if (block > 0) {
- switch (block) {
- default:
- case 2:
- elf_hwcap |= HWCAP_ATOMICS;
- case 1:
- /* RESERVED */
- case 0:
- break;
- }
- }
-
-#ifdef CONFIG_COMPAT
- /*
- * ID_ISAR5_EL1 carries similar information as above, but pertaining to
- * the AArch32 32-bit execution state.
- */
- features = read_cpuid(ID_ISAR5_EL1);
- block = cpuid_feature_extract_field(features, 4);
- if (block > 0) {
- switch (block) {
- default:
- case 2:
- compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
- case 1:
- compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
- case 0:
- break;
- }
- }
-
- if (cpuid_feature_extract_field(features, 8) > 0)
- compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
-
- if (cpuid_feature_extract_field(features, 12) > 0)
- compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
-
- if (cpuid_feature_extract_field(features, 16) > 0)
- compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
-#endif
-}
-
static void __init setup_machine_fdt(phys_addr_t dt_phys)
{
void *dt_virt = fixmap_remap_fdt(dt_phys);
@@ -404,8 +288,9 @@
void __init setup_arch(char **cmdline_p)
{
- setup_processor();
+ pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
+ sprintf(init_utsname()->machine, ELF_PLATFORM);
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
@@ -434,6 +319,9 @@
paging_init();
relocate_initrd();
+
+ kasan_init();
+
request_standard_resources();
early_ioremap_reset();
@@ -491,124 +379,3 @@
return 0;
}
subsys_initcall(topology_init);
-
-static const char *hwcap_str[] = {
- "fp",
- "asimd",
- "evtstrm",
- "aes",
- "pmull",
- "sha1",
- "sha2",
- "crc32",
- "atomics",
- NULL
-};
-
-#ifdef CONFIG_COMPAT
-static const char *compat_hwcap_str[] = {
- "swp",
- "half",
- "thumb",
- "26bit",
- "fastmult",
- "fpa",
- "vfp",
- "edsp",
- "java",
- "iwmmxt",
- "crunch",
- "thumbee",
- "neon",
- "vfpv3",
- "vfpv3d16",
- "tls",
- "vfpv4",
- "idiva",
- "idivt",
- "vfpd32",
- "lpae",
- "evtstrm"
-};
-
-static const char *compat_hwcap2_str[] = {
- "aes",
- "pmull",
- "sha1",
- "sha2",
- "crc32",
- NULL
-};
-#endif /* CONFIG_COMPAT */
-
-static int c_show(struct seq_file *m, void *v)
-{
- int i, j;
-
- for_each_online_cpu(i) {
- struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
- u32 midr = cpuinfo->reg_midr;
-
- /*
- * glibc reads /proc/cpuinfo to determine the number of
- * online processors, looking for lines beginning with
- * "processor". Give glibc what it expects.
- */
- seq_printf(m, "processor\t: %d\n", i);
-
- /*
- * Dump out the common processor features in a single line.
- * Userspace should read the hwcaps with getauxval(AT_HWCAP)
- * rather than attempting to parse this, but there's a body of
- * software which does already (at least for 32-bit).
- */
- seq_puts(m, "Features\t:");
- if (personality(current->personality) == PER_LINUX32) {
-#ifdef CONFIG_COMPAT
- for (j = 0; compat_hwcap_str[j]; j++)
- if (compat_elf_hwcap & (1 << j))
- seq_printf(m, " %s", compat_hwcap_str[j]);
-
- for (j = 0; compat_hwcap2_str[j]; j++)
- if (compat_elf_hwcap2 & (1 << j))
- seq_printf(m, " %s", compat_hwcap2_str[j]);
-#endif /* CONFIG_COMPAT */
- } else {
- for (j = 0; hwcap_str[j]; j++)
- if (elf_hwcap & (1 << j))
- seq_printf(m, " %s", hwcap_str[j]);
- }
- seq_puts(m, "\n");
-
- seq_printf(m, "CPU implementer\t: 0x%02x\n",
- MIDR_IMPLEMENTOR(midr));
- seq_printf(m, "CPU architecture: 8\n");
- seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr));
- seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr));
- seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr));
- }
-
- return 0;
-}
-
-static void *c_start(struct seq_file *m, loff_t *pos)
-{
- return *pos < 1 ? (void *)1 : NULL;
-}
-
-static void *c_next(struct seq_file *m, void *v, loff_t *pos)
-{
- ++*pos;
- return NULL;
-}
-
-static void c_stop(struct seq_file *m, void *v)
-{
-}
-
-const struct seq_operations cpuinfo_op = {
- .start = c_start,
- .next = c_next,
- .stop = c_stop,
- .show = c_show
-};
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dbdaacd..2bbdc0e 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -142,22 +142,27 @@
*/
atomic_inc(&mm->mm_count);
current->active_mm = mm;
- cpumask_set_cpu(cpu, mm_cpumask(mm));
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
- printk("CPU%u: Booted secondary processor\n", cpu);
/*
* TTBR0 is only used for the identity mapping at this stage. Make it
* point to zero page to avoid speculatively fetching new entries.
*/
cpu_set_reserved_ttbr0();
- flush_tlb_all();
+ local_flush_tlb_all();
cpu_set_default_tcr_t0sz();
preempt_disable();
trace_hardirqs_off();
+ /*
+ * If the system has established the capabilities, make sure
+ * this CPU ticks all of those. If it doesn't, the CPU will
+ * fail to come online.
+ */
+ verify_local_cpu_capabilities();
+
if (cpu_ops[cpu]->cpu_postboot)
cpu_ops[cpu]->cpu_postboot();
@@ -178,6 +183,8 @@
* the CPU migration code to notice that the CPU is online
* before we continue.
*/
+ pr_info("CPU%u: Booted secondary processor [%08x]\n",
+ cpu, read_cpuid_id());
set_cpu_online(cpu, true);
complete(&cpu_running);
@@ -232,12 +239,7 @@
/*
* OK - migrate IRQs away from this CPU
*/
- migrate_irqs();
-
- /*
- * Remove this CPU from the vm mask set of all processes.
- */
- clear_tasks_mm_cpumask(cpu);
+ irq_migrate_all_off_this_cpu();
return 0;
}
@@ -325,12 +327,14 @@
void __init smp_cpus_done(unsigned int max_cpus)
{
pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
+ setup_cpu_features();
hyp_mode_check();
apply_alternatives_all();
}
void __init smp_prepare_boot_cpu(void)
{
+ cpuinfo_store_boot_cpu();
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
}
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 8297d50..3c5e4e6 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -90,7 +90,7 @@
else
cpu_switch_mm(mm->pgd, mm);
- flush_tlb_all();
+ local_flush_tlb_all();
/*
* Restore per-cpu offset before any kernel
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index f93aae5..e9b9b53 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -103,12 +103,12 @@
set_fs(fs);
}
-static void dump_backtrace_entry(unsigned long where, unsigned long stack)
+static void dump_backtrace_entry(unsigned long where)
{
+ /*
+ * Note that 'where' can have a physical address, but it's not handled.
+ */
print_ip_sym(where);
- if (in_exception_text(where))
- dump_mem("", "Exception stack", stack,
- stack + sizeof(struct pt_regs), false);
}
static void dump_instr(const char *lvl, struct pt_regs *regs)
@@ -172,12 +172,17 @@
pr_emerg("Call trace:\n");
while (1) {
unsigned long where = frame.pc;
+ unsigned long stack;
int ret;
+ dump_backtrace_entry(where);
ret = unwind_frame(&frame);
if (ret < 0)
break;
- dump_backtrace_entry(where, frame.sp);
+ stack = frame.sp;
+ if (in_exception_text(where))
+ dump_mem("", "Exception stack", stack,
+ stack + sizeof(struct pt_regs), false);
}
}
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 9807333..8a5d97b 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -5,6 +5,7 @@
*/
#include <asm-generic/vmlinux.lds.h>
+#include <asm/kernel-pgtable.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/page.h>
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 5c7e920e..6a7d5cd 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -19,6 +19,7 @@
config KVM
bool "Kernel-based Virtual Machine (KVM) support"
depends on OF
+ depends on !ARM64_16K_PAGES
select MMU_NOTIFIER
select PREEMPT_NOTIFIERS
select ANON_INODES
@@ -33,6 +34,8 @@
select HAVE_KVM_IRQFD
---help---
Support hosting virtualized guest machines.
+ We don't support KVM with 16K page tables yet, due to the multiple
+ levels of fake page tables.
If unsure, say N.
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 91cf535..f34745c 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -53,7 +53,7 @@
{
u64 pfr0;
- pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+ pfr0 = read_system_reg(SYS_ID_AA64PFR0_EL1);
return !!(pfr0 & 0x20);
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d03d3af..87a64e8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -693,13 +693,13 @@
if (p->is_write) {
return ignore_write(vcpu, p);
} else {
- u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
- u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
- u32 el3 = !!((pfr >> 12) & 0xf);
+ u64 dfr = read_system_reg(SYS_ID_AA64DFR0_EL1);
+ u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1);
+ u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT);
- *vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) |
- (((dfr >> 12) & 0xf) << 24) |
- (((dfr >> 28) & 0xf) << 20) |
+ *vcpu_reg(vcpu, p->Rt) = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
+ (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
+ (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) |
(6 << 16) | (el3 << 14) | (el3 << 12));
return true;
}
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 1be9ef2..4699cd7 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -18,6 +18,7 @@
#include <asm/alternative.h>
#include <asm/assembler.h>
+#include <asm/cache.h>
#include <asm/cpufeature.h>
#include <asm/sysreg.h>
@@ -31,49 +32,58 @@
* Returns:
* x0 - bytes not copied
*/
+
+ .macro ldrb1 ptr, regB, val
+ USER(9998f, ldrb \ptr, [\regB], \val)
+ .endm
+
+ .macro strb1 ptr, regB, val
+ strb \ptr, [\regB], \val
+ .endm
+
+ .macro ldrh1 ptr, regB, val
+ USER(9998f, ldrh \ptr, [\regB], \val)
+ .endm
+
+ .macro strh1 ptr, regB, val
+ strh \ptr, [\regB], \val
+ .endm
+
+ .macro ldr1 ptr, regB, val
+ USER(9998f, ldr \ptr, [\regB], \val)
+ .endm
+
+ .macro str1 ptr, regB, val
+ str \ptr, [\regB], \val
+ .endm
+
+ .macro ldp1 ptr, regB, regC, val
+ USER(9998f, ldp \ptr, \regB, [\regC], \val)
+ .endm
+
+ .macro stp1 ptr, regB, regC, val
+ stp \ptr, \regB, [\regC], \val
+ .endm
+
+end .req x5
ENTRY(__copy_from_user)
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN)
- add x5, x1, x2 // upper user buffer boundary
- subs x2, x2, #16
- b.mi 1f
-0:
-USER(9f, ldp x3, x4, [x1], #16)
- subs x2, x2, #16
- stp x3, x4, [x0], #16
- b.pl 0b
-1: adds x2, x2, #8
- b.mi 2f
-USER(9f, ldr x3, [x1], #8 )
- sub x2, x2, #8
- str x3, [x0], #8
-2: adds x2, x2, #4
- b.mi 3f
-USER(9f, ldr w3, [x1], #4 )
- sub x2, x2, #4
- str w3, [x0], #4
-3: adds x2, x2, #2
- b.mi 4f
-USER(9f, ldrh w3, [x1], #2 )
- sub x2, x2, #2
- strh w3, [x0], #2
-4: adds x2, x2, #1
- b.mi 5f
-USER(9f, ldrb w3, [x1] )
- strb w3, [x0]
-5: mov x0, #0
+ add end, x0, x2
+#include "copy_template.S"
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN)
+ mov x0, #0 // Nothing to copy
ret
ENDPROC(__copy_from_user)
.section .fixup,"ax"
.align 2
-9: sub x2, x5, x1
- mov x3, x2
-10: strb wzr, [x0], #1 // zero remaining buffer space
- subs x3, x3, #1
- b.ne 10b
- mov x0, x2 // bytes not copied
+9998:
+ sub x0, end, dst
+9999:
+ strb wzr, [dst], #1 // zero remaining buffer space
+ cmp dst, end
+ b.lo 9999b
ret
.previous
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 1b94661e..81c8fc9 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -20,6 +20,7 @@
#include <asm/alternative.h>
#include <asm/assembler.h>
+#include <asm/cache.h>
#include <asm/cpufeature.h>
#include <asm/sysreg.h>
@@ -33,44 +34,52 @@
* Returns:
* x0 - bytes not copied
*/
+ .macro ldrb1 ptr, regB, val
+ USER(9998f, ldrb \ptr, [\regB], \val)
+ .endm
+
+ .macro strb1 ptr, regB, val
+ USER(9998f, strb \ptr, [\regB], \val)
+ .endm
+
+ .macro ldrh1 ptr, regB, val
+ USER(9998f, ldrh \ptr, [\regB], \val)
+ .endm
+
+ .macro strh1 ptr, regB, val
+ USER(9998f, strh \ptr, [\regB], \val)
+ .endm
+
+ .macro ldr1 ptr, regB, val
+ USER(9998f, ldr \ptr, [\regB], \val)
+ .endm
+
+ .macro str1 ptr, regB, val
+ USER(9998f, str \ptr, [\regB], \val)
+ .endm
+
+ .macro ldp1 ptr, regB, regC, val
+ USER(9998f, ldp \ptr, \regB, [\regC], \val)
+ .endm
+
+ .macro stp1 ptr, regB, regC, val
+ USER(9998f, stp \ptr, \regB, [\regC], \val)
+ .endm
+
+end .req x5
ENTRY(__copy_in_user)
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN)
- add x5, x0, x2 // upper user buffer boundary
- subs x2, x2, #16
- b.mi 1f
-0:
-USER(9f, ldp x3, x4, [x1], #16)
- subs x2, x2, #16
-USER(9f, stp x3, x4, [x0], #16)
- b.pl 0b
-1: adds x2, x2, #8
- b.mi 2f
-USER(9f, ldr x3, [x1], #8 )
- sub x2, x2, #8
-USER(9f, str x3, [x0], #8 )
-2: adds x2, x2, #4
- b.mi 3f
-USER(9f, ldr w3, [x1], #4 )
- sub x2, x2, #4
-USER(9f, str w3, [x0], #4 )
-3: adds x2, x2, #2
- b.mi 4f
-USER(9f, ldrh w3, [x1], #2 )
- sub x2, x2, #2
-USER(9f, strh w3, [x0], #2 )
-4: adds x2, x2, #1
- b.mi 5f
-USER(9f, ldrb w3, [x1] )
-USER(9f, strb w3, [x0] )
-5: mov x0, #0
+ add end, x0, x2
+#include "copy_template.S"
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN)
+ mov x0, #0
ret
ENDPROC(__copy_in_user)
.section .fixup,"ax"
.align 2
-9: sub x0, x5, x0 // bytes not copied
+9998: sub x0, end, dst // bytes not copied
ret
.previous
diff --git a/arch/arm64/lib/copy_template.S b/arch/arm64/lib/copy_template.S
new file mode 100644
index 0000000..410fbdb
--- /dev/null
+++ b/arch/arm64/lib/copy_template.S
@@ -0,0 +1,193 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * 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/>.
+ */
+
+
+/*
+ * Copy a buffer from src to dest (alignment handled by the hardware)
+ *
+ * Parameters:
+ * x0 - dest
+ * x1 - src
+ * x2 - n
+ * Returns:
+ * x0 - dest
+ */
+dstin .req x0
+src .req x1
+count .req x2
+tmp1 .req x3
+tmp1w .req w3
+tmp2 .req x4
+tmp2w .req w4
+dst .req x6
+
+A_l .req x7
+A_h .req x8
+B_l .req x9
+B_h .req x10
+C_l .req x11
+C_h .req x12
+D_l .req x13
+D_h .req x14
+
+ mov dst, dstin
+ cmp count, #16
+ /*When memory length is less than 16, the accessed are not aligned.*/
+ b.lo .Ltiny15
+
+ neg tmp2, src
+ ands tmp2, tmp2, #15/* Bytes to reach alignment. */
+ b.eq .LSrcAligned
+ sub count, count, tmp2
+ /*
+ * Copy the leading memory data from src to dst in an increasing
+ * address order.By this way,the risk of overwritting the source
+ * memory data is eliminated when the distance between src and
+ * dst is less than 16. The memory accesses here are alignment.
+ */
+ tbz tmp2, #0, 1f
+ ldrb1 tmp1w, src, #1
+ strb1 tmp1w, dst, #1
+1:
+ tbz tmp2, #1, 2f
+ ldrh1 tmp1w, src, #2
+ strh1 tmp1w, dst, #2
+2:
+ tbz tmp2, #2, 3f
+ ldr1 tmp1w, src, #4
+ str1 tmp1w, dst, #4
+3:
+ tbz tmp2, #3, .LSrcAligned
+ ldr1 tmp1, src, #8
+ str1 tmp1, dst, #8
+
+.LSrcAligned:
+ cmp count, #64
+ b.ge .Lcpy_over64
+ /*
+ * Deal with small copies quickly by dropping straight into the
+ * exit block.
+ */
+.Ltail63:
+ /*
+ * Copy up to 48 bytes of data. At this point we only need the
+ * bottom 6 bits of count to be accurate.
+ */
+ ands tmp1, count, #0x30
+ b.eq .Ltiny15
+ cmp tmp1w, #0x20
+ b.eq 1f
+ b.lt 2f
+ ldp1 A_l, A_h, src, #16
+ stp1 A_l, A_h, dst, #16
+1:
+ ldp1 A_l, A_h, src, #16
+ stp1 A_l, A_h, dst, #16
+2:
+ ldp1 A_l, A_h, src, #16
+ stp1 A_l, A_h, dst, #16
+.Ltiny15:
+ /*
+ * Prefer to break one ldp/stp into several load/store to access
+ * memory in an increasing address order,rather than to load/store 16
+ * bytes from (src-16) to (dst-16) and to backward the src to aligned
+ * address,which way is used in original cortex memcpy. If keeping
+ * the original memcpy process here, memmove need to satisfy the
+ * precondition that src address is at least 16 bytes bigger than dst
+ * address,otherwise some source data will be overwritten when memove
+ * call memcpy directly. To make memmove simpler and decouple the
+ * memcpy's dependency on memmove, withdrew the original process.
+ */
+ tbz count, #3, 1f
+ ldr1 tmp1, src, #8
+ str1 tmp1, dst, #8
+1:
+ tbz count, #2, 2f
+ ldr1 tmp1w, src, #4
+ str1 tmp1w, dst, #4
+2:
+ tbz count, #1, 3f
+ ldrh1 tmp1w, src, #2
+ strh1 tmp1w, dst, #2
+3:
+ tbz count, #0, .Lexitfunc
+ ldrb1 tmp1w, src, #1
+ strb1 tmp1w, dst, #1
+
+ b .Lexitfunc
+
+.Lcpy_over64:
+ subs count, count, #128
+ b.ge .Lcpy_body_large
+ /*
+ * Less than 128 bytes to copy, so handle 64 here and then jump
+ * to the tail.
+ */
+ ldp1 A_l, A_h, src, #16
+ stp1 A_l, A_h, dst, #16
+ ldp1 B_l, B_h, src, #16
+ ldp1 C_l, C_h, src, #16
+ stp1 B_l, B_h, dst, #16
+ stp1 C_l, C_h, dst, #16
+ ldp1 D_l, D_h, src, #16
+ stp1 D_l, D_h, dst, #16
+
+ tst count, #0x3f
+ b.ne .Ltail63
+ b .Lexitfunc
+
+ /*
+ * Critical loop. Start at a new cache line boundary. Assuming
+ * 64 bytes per line this ensures the entire loop is in one line.
+ */
+ .p2align L1_CACHE_SHIFT
+.Lcpy_body_large:
+ /* pre-get 64 bytes data. */
+ ldp1 A_l, A_h, src, #16
+ ldp1 B_l, B_h, src, #16
+ ldp1 C_l, C_h, src, #16
+ ldp1 D_l, D_h, src, #16
+1:
+ /*
+ * interlace the load of next 64 bytes data block with store of the last
+ * loaded 64 bytes data.
+ */
+ stp1 A_l, A_h, dst, #16
+ ldp1 A_l, A_h, src, #16
+ stp1 B_l, B_h, dst, #16
+ ldp1 B_l, B_h, src, #16
+ stp1 C_l, C_h, dst, #16
+ ldp1 C_l, C_h, src, #16
+ stp1 D_l, D_h, dst, #16
+ ldp1 D_l, D_h, src, #16
+ subs count, count, #64
+ b.ge 1b
+ stp1 A_l, A_h, dst, #16
+ stp1 B_l, B_h, dst, #16
+ stp1 C_l, C_h, dst, #16
+ stp1 D_l, D_h, dst, #16
+
+ tst count, #0x3f
+ b.ne .Ltail63
+.Lexitfunc:
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index a257b47..7512bbb 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -18,6 +18,7 @@
#include <asm/alternative.h>
#include <asm/assembler.h>
+#include <asm/cache.h>
#include <asm/cpufeature.h>
#include <asm/sysreg.h>
@@ -31,44 +32,52 @@
* Returns:
* x0 - bytes not copied
*/
+ .macro ldrb1 ptr, regB, val
+ ldrb \ptr, [\regB], \val
+ .endm
+
+ .macro strb1 ptr, regB, val
+ USER(9998f, strb \ptr, [\regB], \val)
+ .endm
+
+ .macro ldrh1 ptr, regB, val
+ ldrh \ptr, [\regB], \val
+ .endm
+
+ .macro strh1 ptr, regB, val
+ USER(9998f, strh \ptr, [\regB], \val)
+ .endm
+
+ .macro ldr1 ptr, regB, val
+ ldr \ptr, [\regB], \val
+ .endm
+
+ .macro str1 ptr, regB, val
+ USER(9998f, str \ptr, [\regB], \val)
+ .endm
+
+ .macro ldp1 ptr, regB, regC, val
+ ldp \ptr, \regB, [\regC], \val
+ .endm
+
+ .macro stp1 ptr, regB, regC, val
+ USER(9998f, stp \ptr, \regB, [\regC], \val)
+ .endm
+
+end .req x5
ENTRY(__copy_to_user)
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN)
- add x5, x0, x2 // upper user buffer boundary
- subs x2, x2, #16
- b.mi 1f
-0:
- ldp x3, x4, [x1], #16
- subs x2, x2, #16
-USER(9f, stp x3, x4, [x0], #16)
- b.pl 0b
-1: adds x2, x2, #8
- b.mi 2f
- ldr x3, [x1], #8
- sub x2, x2, #8
-USER(9f, str x3, [x0], #8 )
-2: adds x2, x2, #4
- b.mi 3f
- ldr w3, [x1], #4
- sub x2, x2, #4
-USER(9f, str w3, [x0], #4 )
-3: adds x2, x2, #2
- b.mi 4f
- ldrh w3, [x1], #2
- sub x2, x2, #2
-USER(9f, strh w3, [x0], #2 )
-4: adds x2, x2, #1
- b.mi 5f
- ldrb w3, [x1]
-USER(9f, strb w3, [x0] )
-5: mov x0, #0
+ add end, x0, x2
+#include "copy_template.S"
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN)
+ mov x0, #0
ret
ENDPROC(__copy_to_user)
.section .fixup,"ax"
.align 2
-9: sub x0, x5, x0 // bytes not copied
+9998: sub x0, end, dst // bytes not copied
ret
.previous
diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S
index 8636b75..4444c1d 100644
--- a/arch/arm64/lib/memchr.S
+++ b/arch/arm64/lib/memchr.S
@@ -41,4 +41,4 @@
ret
2: mov x0, #0
ret
-ENDPROC(memchr)
+ENDPIPROC(memchr)
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
index 6ea0776..ffbdec0 100644
--- a/arch/arm64/lib/memcmp.S
+++ b/arch/arm64/lib/memcmp.S
@@ -255,4 +255,4 @@
.Lret0:
mov result, #0
ret
-ENDPROC(memcmp)
+ENDPIPROC(memcmp)
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index 8a9a96d..6761393 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -36,166 +36,42 @@
* Returns:
* x0 - dest
*/
-dstin .req x0
-src .req x1
-count .req x2
-tmp1 .req x3
-tmp1w .req w3
-tmp2 .req x4
-tmp2w .req w4
-tmp3 .req x5
-tmp3w .req w5
-dst .req x6
+ .macro ldrb1 ptr, regB, val
+ ldrb \ptr, [\regB], \val
+ .endm
-A_l .req x7
-A_h .req x8
-B_l .req x9
-B_h .req x10
-C_l .req x11
-C_h .req x12
-D_l .req x13
-D_h .req x14
+ .macro strb1 ptr, regB, val
+ strb \ptr, [\regB], \val
+ .endm
+ .macro ldrh1 ptr, regB, val
+ ldrh \ptr, [\regB], \val
+ .endm
+
+ .macro strh1 ptr, regB, val
+ strh \ptr, [\regB], \val
+ .endm
+
+ .macro ldr1 ptr, regB, val
+ ldr \ptr, [\regB], \val
+ .endm
+
+ .macro str1 ptr, regB, val
+ str \ptr, [\regB], \val
+ .endm
+
+ .macro ldp1 ptr, regB, regC, val
+ ldp \ptr, \regB, [\regC], \val
+ .endm
+
+ .macro stp1 ptr, regB, regC, val
+ stp \ptr, \regB, [\regC], \val
+ .endm
+
+ .weak memcpy
+ENTRY(__memcpy)
ENTRY(memcpy)
- mov dst, dstin
- cmp count, #16
- /*When memory length is less than 16, the accessed are not aligned.*/
- b.lo .Ltiny15
-
- neg tmp2, src
- ands tmp2, tmp2, #15/* Bytes to reach alignment. */
- b.eq .LSrcAligned
- sub count, count, tmp2
- /*
- * Copy the leading memory data from src to dst in an increasing
- * address order.By this way,the risk of overwritting the source
- * memory data is eliminated when the distance between src and
- * dst is less than 16. The memory accesses here are alignment.
- */
- tbz tmp2, #0, 1f
- ldrb tmp1w, [src], #1
- strb tmp1w, [dst], #1
-1:
- tbz tmp2, #1, 2f
- ldrh tmp1w, [src], #2
- strh tmp1w, [dst], #2
-2:
- tbz tmp2, #2, 3f
- ldr tmp1w, [src], #4
- str tmp1w, [dst], #4
-3:
- tbz tmp2, #3, .LSrcAligned
- ldr tmp1, [src],#8
- str tmp1, [dst],#8
-
-.LSrcAligned:
- cmp count, #64
- b.ge .Lcpy_over64
- /*
- * Deal with small copies quickly by dropping straight into the
- * exit block.
- */
-.Ltail63:
- /*
- * Copy up to 48 bytes of data. At this point we only need the
- * bottom 6 bits of count to be accurate.
- */
- ands tmp1, count, #0x30
- b.eq .Ltiny15
- cmp tmp1w, #0x20
- b.eq 1f
- b.lt 2f
- ldp A_l, A_h, [src], #16
- stp A_l, A_h, [dst], #16
-1:
- ldp A_l, A_h, [src], #16
- stp A_l, A_h, [dst], #16
-2:
- ldp A_l, A_h, [src], #16
- stp A_l, A_h, [dst], #16
-.Ltiny15:
- /*
- * Prefer to break one ldp/stp into several load/store to access
- * memory in an increasing address order,rather than to load/store 16
- * bytes from (src-16) to (dst-16) and to backward the src to aligned
- * address,which way is used in original cortex memcpy. If keeping
- * the original memcpy process here, memmove need to satisfy the
- * precondition that src address is at least 16 bytes bigger than dst
- * address,otherwise some source data will be overwritten when memove
- * call memcpy directly. To make memmove simpler and decouple the
- * memcpy's dependency on memmove, withdrew the original process.
- */
- tbz count, #3, 1f
- ldr tmp1, [src], #8
- str tmp1, [dst], #8
-1:
- tbz count, #2, 2f
- ldr tmp1w, [src], #4
- str tmp1w, [dst], #4
-2:
- tbz count, #1, 3f
- ldrh tmp1w, [src], #2
- strh tmp1w, [dst], #2
-3:
- tbz count, #0, .Lexitfunc
- ldrb tmp1w, [src]
- strb tmp1w, [dst]
-
-.Lexitfunc:
+#include "copy_template.S"
ret
-
-.Lcpy_over64:
- subs count, count, #128
- b.ge .Lcpy_body_large
- /*
- * Less than 128 bytes to copy, so handle 64 here and then jump
- * to the tail.
- */
- ldp A_l, A_h, [src],#16
- stp A_l, A_h, [dst],#16
- ldp B_l, B_h, [src],#16
- ldp C_l, C_h, [src],#16
- stp B_l, B_h, [dst],#16
- stp C_l, C_h, [dst],#16
- ldp D_l, D_h, [src],#16
- stp D_l, D_h, [dst],#16
-
- tst count, #0x3f
- b.ne .Ltail63
- ret
-
- /*
- * Critical loop. Start at a new cache line boundary. Assuming
- * 64 bytes per line this ensures the entire loop is in one line.
- */
- .p2align L1_CACHE_SHIFT
-.Lcpy_body_large:
- /* pre-get 64 bytes data. */
- ldp A_l, A_h, [src],#16
- ldp B_l, B_h, [src],#16
- ldp C_l, C_h, [src],#16
- ldp D_l, D_h, [src],#16
-1:
- /*
- * interlace the load of next 64 bytes data block with store of the last
- * loaded 64 bytes data.
- */
- stp A_l, A_h, [dst],#16
- ldp A_l, A_h, [src],#16
- stp B_l, B_h, [dst],#16
- ldp B_l, B_h, [src],#16
- stp C_l, C_h, [dst],#16
- ldp C_l, C_h, [src],#16
- stp D_l, D_h, [dst],#16
- ldp D_l, D_h, [src],#16
- subs count, count, #64
- b.ge 1b
- stp A_l, A_h, [dst],#16
- stp B_l, B_h, [dst],#16
- stp C_l, C_h, [dst],#16
- stp D_l, D_h, [dst],#16
-
- tst count, #0x3f
- b.ne .Ltail63
- ret
-ENDPROC(memcpy)
+ENDPIPROC(memcpy)
+ENDPROC(__memcpy)
diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S
index 57b19ea2..a5a4459 100644
--- a/arch/arm64/lib/memmove.S
+++ b/arch/arm64/lib/memmove.S
@@ -57,12 +57,14 @@
D_l .req x13
D_h .req x14
+ .weak memmove
+ENTRY(__memmove)
ENTRY(memmove)
cmp dstin, src
- b.lo memcpy
+ b.lo __memcpy
add tmp1, src, count
cmp dstin, tmp1
- b.hs memcpy /* No overlap. */
+ b.hs __memcpy /* No overlap. */
add dst, dstin, count
add src, src, count
@@ -194,4 +196,5 @@
tst count, #0x3f
b.ne .Ltail63
ret
-ENDPROC(memmove)
+ENDPIPROC(memmove)
+ENDPROC(__memmove)
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
index 7c72dfd..f2670a9 100644
--- a/arch/arm64/lib/memset.S
+++ b/arch/arm64/lib/memset.S
@@ -54,6 +54,8 @@
tmp3w .req w9
tmp3 .req x9
+ .weak memset
+ENTRY(__memset)
ENTRY(memset)
mov dst, dstin /* Preserve return value. */
and A_lw, val, #255
@@ -213,4 +215,5 @@
ands count, count, zva_bits_x
b.ne .Ltail_maybe_long
ret
-ENDPROC(memset)
+ENDPIPROC(memset)
+ENDPROC(__memset)
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
index 42f828b..471fe61 100644
--- a/arch/arm64/lib/strcmp.S
+++ b/arch/arm64/lib/strcmp.S
@@ -231,4 +231,4 @@
lsr data1, data1, #56
sub result, data1, data2, lsr #56
ret
-ENDPROC(strcmp)
+ENDPIPROC(strcmp)
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
index 987b68b..55ccc8e 100644
--- a/arch/arm64/lib/strlen.S
+++ b/arch/arm64/lib/strlen.S
@@ -123,4 +123,4 @@
csinv data1, data1, xzr, le
csel data2, data2, data2a, le
b .Lrealigned
-ENDPROC(strlen)
+ENDPIPROC(strlen)
diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S
index 0224cf5..e267044 100644
--- a/arch/arm64/lib/strncmp.S
+++ b/arch/arm64/lib/strncmp.S
@@ -307,4 +307,4 @@
.Lret0:
mov result, #0
ret
-ENDPROC(strncmp)
+ENDPIPROC(strncmp)
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 773d37a..57f57fd 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,3 +4,6 @@
context.o proc.o pageattr.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_ARM64_PTDUMP) += dump.o
+
+obj-$(CONFIG_KASAN) += kasan_init.o
+KASAN_SANITIZE_kasan_init.o := n
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index eb48d5d..cfa44a6 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -98,7 +98,7 @@
b.lo 1b
dsb sy
ret
-ENDPROC(__flush_dcache_area)
+ENDPIPROC(__flush_dcache_area)
/*
* __inval_cache_range(start, end)
@@ -131,7 +131,7 @@
b.lo 2b
dsb sy
ret
-ENDPROC(__inval_cache_range)
+ENDPIPROC(__inval_cache_range)
ENDPROC(__dma_inv_range)
/*
@@ -171,7 +171,7 @@
b.lo 1b
dsb sy
ret
-ENDPROC(__dma_flush_range)
+ENDPIPROC(__dma_flush_range)
/*
* __dma_map_area(start, size, dir)
@@ -184,7 +184,7 @@
cmp w2, #DMA_FROM_DEVICE
b.eq __dma_inv_range
b __dma_clean_range
-ENDPROC(__dma_map_area)
+ENDPIPROC(__dma_map_area)
/*
* __dma_unmap_area(start, size, dir)
@@ -197,4 +197,4 @@
cmp w2, #DMA_TO_DEVICE
b.ne __dma_inv_range
ret
-ENDPROC(__dma_unmap_area)
+ENDPIPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index d70ff14..f636a26 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -17,135 +17,185 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
-#include <linux/init.h>
+#include <linux/bitops.h>
#include <linux/sched.h>
+#include <linux/slab.h>
#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
+#include <asm/cpufeature.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
-#include <asm/cachetype.h>
-#define asid_bits(reg) \
- (((read_cpuid(ID_AA64MMFR0_EL1) & 0xf0) >> 2) + 8)
-
-#define ASID_FIRST_VERSION (1 << MAX_ASID_BITS)
-
+static u32 asid_bits;
static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
-unsigned int cpu_last_asid = ASID_FIRST_VERSION;
-/*
- * We fork()ed a process, and we need a new context for the child to run in.
- */
-void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
- mm->context.id = 0;
- raw_spin_lock_init(&mm->context.id_lock);
-}
+static atomic64_t asid_generation;
+static unsigned long *asid_map;
-static void flush_context(void)
+static DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(u64, reserved_asids);
+static cpumask_t tlb_flush_pending;
+
+#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
+#define ASID_FIRST_VERSION (1UL << asid_bits)
+#define NUM_USER_ASIDS ASID_FIRST_VERSION
+
+static void flush_context(unsigned int cpu)
{
- /* set the reserved TTBR0 before flushing the TLB */
- cpu_set_reserved_ttbr0();
- flush_tlb_all();
+ int i;
+ u64 asid;
+
+ /* Update the list of reserved ASIDs and the ASID bitmap. */
+ bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
+
+ /*
+ * Ensure the generation bump is observed before we xchg the
+ * active_asids.
+ */
+ smp_wmb();
+
+ for_each_possible_cpu(i) {
+ asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
+ /*
+ * If this CPU has already been through a
+ * rollover, but hasn't run another task in
+ * the meantime, we must preserve its reserved
+ * ASID, as this is the only trace we have of
+ * the process it is still running.
+ */
+ if (asid == 0)
+ asid = per_cpu(reserved_asids, i);
+ __set_bit(asid & ~ASID_MASK, asid_map);
+ per_cpu(reserved_asids, i) = asid;
+ }
+
+ /* Queue a TLB invalidate and flush the I-cache if necessary. */
+ cpumask_setall(&tlb_flush_pending);
+
if (icache_is_aivivt())
__flush_icache_all();
}
-static void set_mm_context(struct mm_struct *mm, unsigned int asid)
+static int is_reserved_asid(u64 asid)
{
- unsigned long flags;
-
- /*
- * Locking needed for multi-threaded applications where the same
- * mm->context.id could be set from different CPUs during the
- * broadcast. This function is also called via IPI so the
- * mm->context.id_lock has to be IRQ-safe.
- */
- raw_spin_lock_irqsave(&mm->context.id_lock, flags);
- if (likely((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) {
- /*
- * Old version of ASID found. Set the new one and reset
- * mm_cpumask(mm).
- */
- mm->context.id = asid;
- cpumask_clear(mm_cpumask(mm));
- }
- raw_spin_unlock_irqrestore(&mm->context.id_lock, flags);
-
- /*
- * Set the mm_cpumask(mm) bit for the current CPU.
- */
- cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+ int cpu;
+ for_each_possible_cpu(cpu)
+ if (per_cpu(reserved_asids, cpu) == asid)
+ return 1;
+ return 0;
}
-/*
- * Reset the ASID on the current CPU. This function call is broadcast from the
- * CPU handling the ASID rollover and holding cpu_asid_lock.
- */
-static void reset_context(void *info)
+static u64 new_context(struct mm_struct *mm, unsigned int cpu)
{
- unsigned int asid;
- unsigned int cpu = smp_processor_id();
- struct mm_struct *mm = current->active_mm;
+ static u32 cur_idx = 1;
+ u64 asid = atomic64_read(&mm->context.id);
+ u64 generation = atomic64_read(&asid_generation);
+
+ if (asid != 0) {
+ /*
+ * If our current ASID was active during a rollover, we
+ * can continue to use it and this was just a false alarm.
+ */
+ if (is_reserved_asid(asid))
+ return generation | (asid & ~ASID_MASK);
+
+ /*
+ * We had a valid ASID in a previous life, so try to re-use
+ * it if possible.
+ */
+ asid &= ~ASID_MASK;
+ if (!__test_and_set_bit(asid, asid_map))
+ goto bump_gen;
+ }
/*
- * current->active_mm could be init_mm for the idle thread immediately
- * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to
- * the reserved value, so no need to reset any context.
+ * Allocate a free ASID. If we can't find one, take a note of the
+ * currently active ASIDs and mark the TLBs as requiring flushes.
+ * We always count from ASID #1, as we use ASID #0 when setting a
+ * reserved TTBR0 for the init_mm.
*/
- if (mm == &init_mm)
- return;
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
+ if (asid != NUM_USER_ASIDS)
+ goto set_asid;
- smp_rmb();
- asid = cpu_last_asid + cpu;
+ /* We're out of ASIDs, so increment the global generation count */
+ generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION,
+ &asid_generation);
+ flush_context(cpu);
- flush_context();
- set_mm_context(mm, asid);
+ /* We have at least 1 ASID per CPU, so this will always succeed */
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
- /* set the new ASID */
+set_asid:
+ __set_bit(asid, asid_map);
+ cur_idx = asid;
+
+bump_gen:
+ asid |= generation;
+ return asid;
+}
+
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
+{
+ unsigned long flags;
+ u64 asid;
+
+ asid = atomic64_read(&mm->context.id);
+
+ /*
+ * The memory ordering here is subtle. We rely on the control
+ * dependency between the generation read and the update of
+ * active_asids to ensure that we are synchronised with a
+ * parallel rollover (i.e. this pairs with the smp_wmb() in
+ * flush_context).
+ */
+ if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
+ && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid))
+ goto switch_mm_fastpath;
+
+ raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+ /* Check that our ASID belongs to the current generation. */
+ asid = atomic64_read(&mm->context.id);
+ if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) {
+ asid = new_context(mm, cpu);
+ atomic64_set(&mm->context.id, asid);
+ }
+
+ if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending))
+ local_flush_tlb_all();
+
+ atomic64_set(&per_cpu(active_asids, cpu), asid);
+ raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+
+switch_mm_fastpath:
cpu_switch_mm(mm->pgd, mm);
}
-void __new_context(struct mm_struct *mm)
+static int asids_init(void)
{
- unsigned int asid;
- unsigned int bits = asid_bits();
+ int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1), 4);
- raw_spin_lock(&cpu_asid_lock);
- /*
- * Check the ASID again, in case the change was broadcast from another
- * CPU before we acquired the lock.
- */
- if (!unlikely((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) {
- cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
- raw_spin_unlock(&cpu_asid_lock);
- return;
- }
- /*
- * At this point, it is guaranteed that the current mm (with an old
- * ASID) isn't active on any other CPU since the ASIDs are changed
- * simultaneously via IPI.
- */
- asid = ++cpu_last_asid;
-
- /*
- * If we've used up all our ASIDs, we need to start a new version and
- * flush the TLB.
- */
- if (unlikely((asid & ((1 << bits) - 1)) == 0)) {
- /* increment the ASID version */
- cpu_last_asid += (1 << MAX_ASID_BITS) - (1 << bits);
- if (cpu_last_asid == 0)
- cpu_last_asid = ASID_FIRST_VERSION;
- asid = cpu_last_asid + smp_processor_id();
- flush_context();
- smp_wmb();
- smp_call_function(reset_context, NULL, 1);
- cpu_last_asid += NR_CPUS - 1;
+ switch (fld) {
+ default:
+ pr_warn("Unknown ASID size (%d); assuming 8-bit\n", fld);
+ /* Fallthrough */
+ case 0:
+ asid_bits = 8;
+ break;
+ case 2:
+ asid_bits = 16;
}
- set_mm_context(mm, asid);
- raw_spin_unlock(&cpu_asid_lock);
+ /* If we end up with more CPUs than ASIDs, expect things to crash */
+ WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+ atomic64_set(&asid_generation, ASID_FIRST_VERSION);
+ asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
+ GFP_KERNEL);
+ if (!asid_map)
+ panic("Failed to allocate bitmap for %lu ASIDs\n",
+ NUM_USER_ASIDS);
+
+ pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
+ return 0;
}
+early_initcall(asids_init);
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index f3d6221..5a22a11 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -67,6 +67,12 @@
{ -1, NULL },
};
+/*
+ * The page dumper groups page table entries of the same type into a single
+ * description. It uses pg_state to track the range information while
+ * iterating over the pte entries. When the continuity is broken it then
+ * dumps out a description of the range.
+ */
struct pg_state {
struct seq_file *seq;
const struct addr_marker *marker;
@@ -114,6 +120,16 @@
.set = "NG",
.clear = " ",
}, {
+ .mask = PTE_CONT,
+ .val = PTE_CONT,
+ .set = "CON",
+ .clear = " ",
+ }, {
+ .mask = PTE_TABLE_BIT,
+ .val = PTE_TABLE_BIT,
+ .set = " ",
+ .clear = "BLK",
+ }, {
.mask = PTE_UXN,
.val = PTE_UXN,
.set = "UXN",
@@ -198,7 +214,7 @@
unsigned long delta;
if (st->current_prot) {
- seq_printf(st->seq, "0x%16lx-0x%16lx ",
+ seq_printf(st->seq, "0x%016lx-0x%016lx ",
st->start_address, addr);
delta = (addr - st->start_address) >> 10;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index aba9ead..066d5ae 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -555,7 +555,7 @@
}
#ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void)
+void cpu_enable_pan(void *__unused)
{
config_sctlr_el1(SCTLR_EL1_SPAN, 0);
}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f5c0680..7a1f9a0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -298,6 +298,9 @@
#define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
pr_notice("Virtual kernel memory layout:\n"
+#ifdef CONFIG_KASAN
+ " kasan : 0x%16lx - 0x%16lx (%6ld GB)\n"
+#endif
" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n"
#ifdef CONFIG_SPARSEMEM_VMEMMAP
" vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n"
@@ -310,6 +313,9 @@
" .init : 0x%p" " - 0x%p" " (%6ld KB)\n"
" .text : 0x%p" " - 0x%p" " (%6ld KB)\n"
" .data : 0x%p" " - 0x%p" " (%6ld KB)\n",
+#ifdef CONFIG_KASAN
+ MLG(KASAN_SHADOW_START, KASAN_SHADOW_END),
+#endif
MLG(VMALLOC_START, VMALLOC_END),
#ifdef CONFIG_SPARSEMEM_VMEMMAP
MLG((unsigned long)vmemmap,
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
new file mode 100644
index 0000000..cf038c7
--- /dev/null
+++ b/arch/arm64/mm/kasan_init.c
@@ -0,0 +1,165 @@
+/*
+ * This file contains kasan initialization code for ARM64.
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ * 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.
+ *
+ */
+
+#define pr_fmt(fmt) "kasan: " fmt
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <linux/start_kernel.h>
+
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
+
+static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr,
+ unsigned long end)
+{
+ pte_t *pte;
+ unsigned long next;
+
+ if (pmd_none(*pmd))
+ pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte);
+
+ pte = pte_offset_kernel(pmd, addr);
+ do {
+ next = addr + PAGE_SIZE;
+ set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page),
+ PAGE_KERNEL));
+ } while (pte++, addr = next, addr != end && pte_none(*pte));
+}
+
+static void __init kasan_early_pmd_populate(pud_t *pud,
+ unsigned long addr,
+ unsigned long end)
+{
+ pmd_t *pmd;
+ unsigned long next;
+
+ if (pud_none(*pud))
+ pud_populate(&init_mm, pud, kasan_zero_pmd);
+
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ kasan_early_pte_populate(pmd, addr, next);
+ } while (pmd++, addr = next, addr != end && pmd_none(*pmd));
+}
+
+static void __init kasan_early_pud_populate(pgd_t *pgd,
+ unsigned long addr,
+ unsigned long end)
+{
+ pud_t *pud;
+ unsigned long next;
+
+ if (pgd_none(*pgd))
+ pgd_populate(&init_mm, pgd, kasan_zero_pud);
+
+ pud = pud_offset(pgd, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ kasan_early_pmd_populate(pud, addr, next);
+ } while (pud++, addr = next, addr != end && pud_none(*pud));
+}
+
+static void __init kasan_map_early_shadow(void)
+{
+ unsigned long addr = KASAN_SHADOW_START;
+ unsigned long end = KASAN_SHADOW_END;
+ unsigned long next;
+ pgd_t *pgd;
+
+ pgd = pgd_offset_k(addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ kasan_early_pud_populate(pgd, addr, next);
+ } while (pgd++, addr = next, addr != end);
+}
+
+asmlinkage void __init kasan_early_init(void)
+{
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << 61));
+ BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE));
+ kasan_map_early_shadow();
+}
+
+static void __init clear_pgds(unsigned long start,
+ unsigned long end)
+{
+ /*
+ * Remove references to kasan page tables from
+ * swapper_pg_dir. pgd_clear() can't be used
+ * here because it's nop on 2,3-level pagetable setups
+ */
+ for (; start < end; start += PGDIR_SIZE)
+ set_pgd(pgd_offset_k(start), __pgd(0));
+}
+
+static void __init cpu_set_ttbr1(unsigned long ttbr1)
+{
+ asm(
+ " msr ttbr1_el1, %0\n"
+ " isb"
+ :
+ : "r" (ttbr1));
+}
+
+void __init kasan_init(void)
+{
+ struct memblock_region *reg;
+
+ /*
+ * We are going to perform proper setup of shadow memory.
+ * At first we should unmap early shadow (clear_pgds() call bellow).
+ * However, instrumented code couldn't execute without shadow memory.
+ * tmp_pg_dir used to keep early shadow mapped until full shadow
+ * setup will be finished.
+ */
+ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir));
+ cpu_set_ttbr1(__pa(tmp_pg_dir));
+ flush_tlb_all();
+
+ clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
+ kasan_mem_to_shadow((void *)MODULES_VADDR));
+
+ for_each_memblock(memory, reg) {
+ void *start = (void *)__phys_to_virt(reg->base);
+ void *end = (void *)__phys_to_virt(reg->base + reg->size);
+
+ if (start >= end)
+ break;
+
+ /*
+ * end + 1 here is intentional. We check several shadow bytes in
+ * advance to slightly speed up fastpath. In some rare cases
+ * we could cross boundary of mapped shadow, so we just map
+ * some more here.
+ */
+ vmemmap_populate((unsigned long)kasan_mem_to_shadow(start),
+ (unsigned long)kasan_mem_to_shadow(end) + 1,
+ pfn_to_nid(virt_to_pfn(start)));
+ }
+
+ memset(kasan_zero_page, 0, PAGE_SIZE);
+ cpu_set_ttbr1(__pa(swapper_pg_dir));
+ flush_tlb_all();
+
+ /* At this point kasan is fully initialized. Enable error messages */
+ init_task.kasan_depth = 0;
+ pr_info("KernelAddressSanitizer initialized\n");
+}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 9211b85..c2fa6b5 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -32,6 +32,7 @@
#include <asm/cputype.h>
#include <asm/fixmap.h>
+#include <asm/kernel-pgtable.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/sizes.h>
@@ -80,19 +81,55 @@
do {
/*
* Need to have the least restrictive permissions available
- * permissions will be fixed up later
+ * permissions will be fixed up later. Default the new page
+ * range as contiguous ptes.
*/
- set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+ set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT));
pfn++;
} while (pte++, i++, i < PTRS_PER_PTE);
}
+/*
+ * Given a PTE with the CONT bit set, determine where the CONT range
+ * starts, and clear the entire range of PTE CONT bits.
+ */
+static void clear_cont_pte_range(pte_t *pte, unsigned long addr)
+{
+ int i;
+
+ pte -= CONT_RANGE_OFFSET(addr);
+ for (i = 0; i < CONT_PTES; i++) {
+ set_pte(pte, pte_mknoncont(*pte));
+ pte++;
+ }
+ flush_tlb_all();
+}
+
+/*
+ * Given a range of PTEs set the pfn and provided page protection flags
+ */
+static void __populate_init_pte(pte_t *pte, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot)
+{
+ unsigned long pfn = __phys_to_pfn(phys);
+
+ do {
+ /* clear all the bits except the pfn, then apply the prot */
+ set_pte(pte, pfn_pte(pfn, prot));
+ pte++;
+ pfn++;
+ addr += PAGE_SIZE;
+ } while (addr != end);
+}
+
static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
- unsigned long end, unsigned long pfn,
+ unsigned long end, phys_addr_t phys,
pgprot_t prot,
void *(*alloc)(unsigned long size))
{
pte_t *pte;
+ unsigned long next;
if (pmd_none(*pmd) || pmd_sect(*pmd)) {
pte = alloc(PTRS_PER_PTE * sizeof(pte_t));
@@ -105,9 +142,27 @@
pte = pte_offset_kernel(pmd, addr);
do {
- set_pte(pte, pfn_pte(pfn, prot));
- pfn++;
- } while (pte++, addr += PAGE_SIZE, addr != end);
+ next = min(end, (addr + CONT_SIZE) & CONT_MASK);
+ if (((addr | next | phys) & ~CONT_MASK) == 0) {
+ /* a block of CONT_PTES */
+ __populate_init_pte(pte, addr, next, phys,
+ prot | __pgprot(PTE_CONT));
+ } else {
+ /*
+ * If the range being split is already inside of a
+ * contiguous range but this PTE isn't going to be
+ * contiguous, then we want to unmark the adjacent
+ * ranges, then update the portion of the range we
+ * are interrested in.
+ */
+ clear_cont_pte_range(pte, addr);
+ __populate_init_pte(pte, addr, next, phys, prot);
+ }
+
+ pte += (next - addr) >> PAGE_SHIFT;
+ phys += next - addr;
+ addr = next;
+ } while (addr != end);
}
void split_pud(pud_t *old_pud, pmd_t *pmd)
@@ -168,8 +223,7 @@
}
}
} else {
- alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
- prot, alloc);
+ alloc_init_pte(pmd, addr, next, phys, prot, alloc);
}
phys += next - addr;
} while (pmd++, addr = next, addr != end);
@@ -353,14 +407,11 @@
* memory addressable from the initial direct kernel mapping.
*
* The initial direct kernel mapping, located at swapper_pg_dir, gives
- * us PUD_SIZE (4K pages) or PMD_SIZE (64K pages) memory starting from
- * PHYS_OFFSET (which must be aligned to 2MB as per
- * Documentation/arm64/booting.txt).
+ * us PUD_SIZE (with SECTION maps) or PMD_SIZE (without SECTION maps,
+ * memory starting from PHYS_OFFSET (which must be aligned to 2MB as
+ * per Documentation/arm64/booting.txt).
*/
- if (IS_ENABLED(CONFIG_ARM64_64K_PAGES))
- limit = PHYS_OFFSET + PMD_SIZE;
- else
- limit = PHYS_OFFSET + PUD_SIZE;
+ limit = PHYS_OFFSET + SWAPPER_INIT_MAP_SIZE;
memblock_set_current_limit(limit);
/* map all the memory banks */
@@ -371,21 +422,24 @@
if (start >= end)
break;
-#ifndef CONFIG_ARM64_64K_PAGES
- /*
- * For the first memory bank align the start address and
- * current memblock limit to prevent create_mapping() from
- * allocating pte page tables from unmapped memory.
- * When 64K pages are enabled, the pte page table for the
- * first PGDIR_SIZE is already present in swapper_pg_dir.
- */
- if (start < limit)
- start = ALIGN(start, PMD_SIZE);
- if (end < limit) {
- limit = end & PMD_MASK;
- memblock_set_current_limit(limit);
+ if (ARM64_SWAPPER_USES_SECTION_MAPS) {
+ /*
+ * For the first memory bank align the start address and
+ * current memblock limit to prevent create_mapping() from
+ * allocating pte page tables from unmapped memory. With
+ * the section maps, if the first block doesn't end on section
+ * size boundary, create_mapping() will try to allocate a pte
+ * page, which may be returned from an unmapped area.
+ * When section maps are not used, the pte page table for the
+ * current limit is already present in swapper_pg_dir.
+ */
+ if (start < limit)
+ start = ALIGN(start, SECTION_SIZE);
+ if (end < limit) {
+ limit = end & SECTION_MASK;
+ memblock_set_current_limit(limit);
+ }
}
-#endif
__map_memblock(start, end);
}
@@ -456,7 +510,7 @@
* point to zero page to avoid speculatively fetching new entries.
*/
cpu_set_reserved_ttbr0();
- flush_tlb_all();
+ local_flush_tlb_all();
cpu_set_default_tcr_t0sz();
}
@@ -498,12 +552,12 @@
return pfn_valid(pte_pfn(*pte));
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#ifdef CONFIG_ARM64_64K_PAGES
+#if !ARM64_SWAPPER_USES_SECTION_MAPS
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
return vmemmap_populate_basepages(start, end, node);
}
-#else /* !CONFIG_ARM64_64K_PAGES */
+#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
unsigned long addr = start;
@@ -638,7 +692,7 @@
{
const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
pgprot_t prot = PAGE_KERNEL | PTE_RDONLY;
- int granularity, size, offset;
+ int size, offset;
void *dt_virt;
/*
@@ -664,24 +718,15 @@
*/
BUILD_BUG_ON(dt_virt_base % SZ_2M);
- if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) {
- BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PMD_SHIFT !=
- __fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT);
+ BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> SWAPPER_TABLE_SHIFT !=
+ __fix_to_virt(FIX_BTMAP_BEGIN) >> SWAPPER_TABLE_SHIFT);
- granularity = PAGE_SIZE;
- } else {
- BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PUD_SHIFT !=
- __fix_to_virt(FIX_BTMAP_BEGIN) >> PUD_SHIFT);
-
- granularity = PMD_SIZE;
- }
-
- offset = dt_phys % granularity;
+ offset = dt_phys % SWAPPER_BLOCK_SIZE;
dt_virt = (void *)dt_virt_base + offset;
/* map the first chunk so we can read the size from the header */
- create_mapping(round_down(dt_phys, granularity), dt_virt_base,
- granularity, prot);
+ create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
+ SWAPPER_BLOCK_SIZE, prot);
if (fdt_check_header(dt_virt) != 0)
return NULL;
@@ -690,9 +735,9 @@
if (size > MAX_FDT_SIZE)
return NULL;
- if (offset + size > granularity)
- create_mapping(round_down(dt_phys, granularity), dt_virt_base,
- round_up(offset + size, granularity), prot);
+ if (offset + size > SWAPPER_BLOCK_SIZE)
+ create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
+ round_up(offset + size, SWAPPER_BLOCK_SIZE), prot);
memblock_reserve(dt_phys, size);
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 71ca104..cb3ba1b 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -28,8 +28,6 @@
#include "mm.h"
-#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
-
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 e4ee7bd..3a4b8b1 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -30,7 +30,9 @@
#ifdef CONFIG_ARM64_64K_PAGES
#define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K
-#else
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define TCR_TG_FLAGS TCR_TG0_16K | TCR_TG1_16K
+#else /* CONFIG_ARM64_4K_PAGES */
#define TCR_TG_FLAGS TCR_TG0_4K | TCR_TG1_4K
#endif
@@ -130,7 +132,7 @@
* - pgd_phys - physical address of new TTB
*/
ENTRY(cpu_do_switch_mm)
- mmid w1, x1 // get mm->context.id
+ mmid x1, x1 // get mm->context.id
bfi x0, x1, #48, #16 // set the ASID
msr ttbr0_el1, x0 // set TTBR0
isb
@@ -146,8 +148,8 @@
* value of the SCTLR_EL1 register.
*/
ENTRY(__cpu_setup)
- tlbi vmalle1is // invalidate I + D TLBs
- dsb ish
+ tlbi vmalle1 // Invalidate local TLB
+ dsb nsh
mov x0, #3 << 20
msr cpacr_el1, x0 // Enable FP/ASIMD
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index f61f2dd..241b9b9 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -20,4 +20,5 @@
generic-y += topology.h
generic-y += trace_clock.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 61cd1e7..91d49c0 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -46,4 +46,5 @@
generic-y += ucontext.h
generic-y += unaligned.h
generic-y += user.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index f17c4dc..945544e 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -59,4 +59,5 @@
generic-y += ucontext.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index b7f6819..1778805 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -43,4 +43,5 @@
generic-y += trace_clock.h
generic-y += types.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 8e47b83..1fa084c 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -7,3 +7,4 @@
generic-y += mm-arch-hooks.h
generic-y += preempt.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index daee37b..db8ddab 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -58,4 +58,5 @@
generic-y += ucontext.h
generic-y += unaligned.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 9de3ba1..502a91d 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -8,3 +8,4 @@
generic-y += preempt.h
generic-y += trace_clock.h
generic-y += vtime.h
+generic-y += word-at-a-time.h
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index e0eb704..fd104bd 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -9,3 +9,4 @@
generic-y += preempt.h
generic-y += sections.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 0b6b40d..5b4ec54 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -57,7 +58,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -67,10 +67,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -179,6 +181,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -206,6 +209,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -271,6 +275,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -370,6 +375,7 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -537,6 +543,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index eeb3a89..6e5198e 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -55,7 +56,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -65,10 +65,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -177,6 +179,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -204,6 +207,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -269,6 +273,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -344,6 +349,7 @@
# CONFIG_NET_VENDOR_SAMSUNG is not set
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -495,6 +501,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 3a70066..f75600b 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -55,7 +56,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -65,10 +65,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -177,6 +179,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -204,6 +207,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -269,6 +273,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -355,6 +360,7 @@
# CONFIG_NET_VENDOR_SEEQ is not set
CONFIG_SMC91X=y
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -517,6 +523,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 0586b32..a42d91c 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -53,7 +54,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -63,10 +63,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -175,6 +177,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -202,6 +205,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -267,6 +271,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -343,6 +348,7 @@
# CONFIG_NET_VENDOR_SAMSUNG is not set
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -488,6 +494,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index ad1dbce..77f4a11 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -55,7 +56,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -65,10 +65,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -177,6 +179,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -204,6 +207,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -269,6 +273,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -345,6 +350,7 @@
# CONFIG_NET_VENDOR_SAMSUNG is not set
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -497,6 +503,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index b44acac..5a329f7 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -54,7 +55,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -64,10 +64,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -176,6 +178,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -203,6 +206,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -271,6 +275,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -364,6 +369,7 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -519,6 +525,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 8afca37..83c80d2 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -64,7 +65,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -74,10 +74,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -186,6 +188,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -213,6 +216,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -281,6 +285,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -410,6 +415,7 @@
# CONFIG_NET_VENDOR_SEEQ is not set
CONFIG_SMC91X=y
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PLIP=m
@@ -599,6 +605,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index ef00875..6cb42c3 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -52,7 +53,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -62,10 +62,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -174,6 +176,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -201,6 +204,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -266,6 +270,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -343,6 +348,7 @@
# CONFIG_NET_VENDOR_SAMSUNG is not set
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -488,6 +494,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 387c2bd..c7508c3 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -53,7 +54,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -63,10 +63,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -175,6 +177,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -202,6 +205,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -267,6 +271,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -343,6 +348,7 @@
# CONFIG_NET_VENDOR_SAMSUNG is not set
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -488,6 +494,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 35355c1..64b7166 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -53,7 +54,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -63,10 +63,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -175,6 +177,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -202,6 +205,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -267,6 +271,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -354,6 +359,7 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_SMSC is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PLIP=m
@@ -510,6 +516,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 8442d26..9a4cab7 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -50,7 +51,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -60,10 +60,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -172,6 +174,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -199,6 +202,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -264,6 +268,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -341,6 +346,7 @@
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_STMICRO is not set
# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -489,6 +495,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
CONFIG_CRYPTO_MANAGER=y
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 0e1b542..1a2eaac 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
+CONFIG_USERFAULTFD=y
CONFIG_SLAB=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
@@ -50,7 +51,6 @@
CONFIG_NET_IPGRE=m
CONFIG_NET_IPVTI=m
CONFIG_NET_FOU_IP_TUNNELS=y
-CONFIG_GENEVE_CORE=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
@@ -60,10 +60,12 @@
# CONFIG_INET_LRO is not set
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
+CONFIG_IPV6=m
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_INET6_AH=m
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_ILA=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_GRE=m
CONFIG_NETFILTER=y
@@ -172,6 +174,7 @@
CONFIG_IP_SET_LIST_SET=m
CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_DUP_IPV4=m
CONFIG_NF_TABLES_ARP=m
CONFIG_NF_LOG_ARP=m
CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -199,6 +202,7 @@
CONFIG_IP_NF_ARP_MANGLE=m
CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_DUP_IPV6=m
CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_NFT_MASQ_IPV6=m
CONFIG_NFT_REDIR_IPV6=m
@@ -264,6 +268,7 @@
CONFIG_MPLS=y
CONFIG_NET_MPLS_GSO=m
CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
# CONFIG_WIRELESS is not set
# CONFIG_UEVENT_HELPER is not set
CONFIG_DEVTMPFS=y
@@ -341,6 +346,7 @@
# CONFIG_NET_VENDOR_SAMSUNG is not set
# CONFIG_NET_VENDOR_SEEQ is not set
# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
# CONFIG_NET_VENDOR_VIA is not set
# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
@@ -489,6 +495,7 @@
CONFIG_TEST_BPF=m
CONFIG_TEST_FIRMWARE=m
CONFIG_TEST_UDELAY=m
+CONFIG_TEST_STATIC_KEYS=m
CONFIG_EARLY_PRINTK=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_CRYPTO_RSA=m
diff --git a/arch/m68k/include/asm/linkage.h b/arch/m68k/include/asm/linkage.h
index 5a822bb..066e74f 100644
--- a/arch/m68k/include/asm/linkage.h
+++ b/arch/m68k/include/asm/linkage.h
@@ -4,4 +4,34 @@
#define __ALIGN .align 4
#define __ALIGN_STR ".align 4"
+/*
+ * Make sure the compiler doesn't do anything stupid with the
+ * arguments on the stack - they are owned by the *caller*, not
+ * the callee. This just fools gcc into not spilling into them,
+ * and keeps it from doing tailcall recursion and/or using the
+ * stack slots for temporaries, since they are live and "used"
+ * all the way to the end of the function.
+ */
+#define asmlinkage_protect(n, ret, args...) \
+ __asmlinkage_protect##n(ret, ##args)
+#define __asmlinkage_protect_n(ret, args...) \
+ __asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args)
+#define __asmlinkage_protect0(ret) \
+ __asmlinkage_protect_n(ret)
+#define __asmlinkage_protect1(ret, arg1) \
+ __asmlinkage_protect_n(ret, "m" (arg1))
+#define __asmlinkage_protect2(ret, arg1, arg2) \
+ __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2))
+#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \
+ __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3))
+#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \
+ __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
+ "m" (arg4))
+#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \
+ __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
+ "m" (arg4), "m" (arg5))
+#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \
+ __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
+ "m" (arg4), "m" (arg5), "m" (arg6))
+
#endif
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 244e0db..0793a7f 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
#include <uapi/asm/unistd.h>
-#define NR_syscalls 356
+#define NR_syscalls 375
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 61fb6cb..5e6fae6 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -361,5 +361,24 @@
#define __NR_memfd_create 353
#define __NR_bpf 354
#define __NR_execveat 355
+#define __NR_socket 356
+#define __NR_socketpair 357
+#define __NR_bind 358
+#define __NR_connect 359
+#define __NR_listen 360
+#define __NR_accept4 361
+#define __NR_getsockopt 362
+#define __NR_setsockopt 363
+#define __NR_getsockname 364
+#define __NR_getpeername 365
+#define __NR_sendto 366
+#define __NR_sendmsg 367
+#define __NR_recvfrom 368
+#define __NR_recvmsg 369
+#define __NR_shutdown 370
+#define __NR_recvmmsg 371
+#define __NR_sendmmsg 372
+#define __NR_userfaultfd 373
+#define __NR_membarrier 374
#endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index a0ec430..5dd0e80 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -376,4 +376,22 @@
.long sys_memfd_create
.long sys_bpf
.long sys_execveat /* 355 */
-
+ .long sys_socket
+ .long sys_socketpair
+ .long sys_bind
+ .long sys_connect
+ .long sys_listen /* 360 */
+ .long sys_accept4
+ .long sys_getsockopt
+ .long sys_setsockopt
+ .long sys_getsockname
+ .long sys_getpeername /* 365 */
+ .long sys_sendto
+ .long sys_sendmsg
+ .long sys_recvfrom
+ .long sys_recvmsg
+ .long sys_shutdown /* 370 */
+ .long sys_recvmmsg
+ .long sys_sendmmsg
+ .long sys_userfaultfd
+ .long sys_membarrier
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index df31353..29acb89d 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -54,4 +54,5 @@
generic-y += unaligned.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 2f222f3..b0ae88c 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -10,3 +10,4 @@
generic-y += preempt.h
generic-y += syscalls.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c
index 15ecb48..eeb3953 100644
--- a/arch/mips/ath79/irq.c
+++ b/arch/mips/ath79/irq.c
@@ -293,8 +293,26 @@
return 0;
}
-IRQCHIP_DECLARE(ath79_misc_intc, "qca,ar7100-misc-intc",
- ath79_misc_intc_of_init);
+
+static int __init ar7100_misc_intc_of_init(
+ struct device_node *node, struct device_node *parent)
+{
+ ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
+ return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7100_misc_intc, "qca,ar7100-misc-intc",
+ ar7100_misc_intc_of_init);
+
+static int __init ar7240_misc_intc_of_init(
+ struct device_node *node, struct device_node *parent)
+{
+ ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
+ return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc",
+ ar7240_misc_intc_of_init);
static int __init ar79_cpu_intc_of_init(
struct device_node *node, struct device_node *parent)
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 89a6284..bd63425 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -933,7 +933,7 @@
while ((boot_mem_map.nr_map < BOOT_MEM_MAP_MAX)
&& (total < MAX_MEMORY)) {
memory = cvmx_bootmem_phy_alloc(mem_alloc_size,
- __pa_symbol(&__init_end), -1,
+ __pa_symbol(&_end), -1,
0x100000,
CVMX_BOOTMEM_FLAG_NO_LOCKING);
if (memory >= 0) {
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 40ec4ca..c7fe4d0 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -17,4 +17,5 @@
generic-y += serial.h
generic-y += trace_clock.h
generic-y += user.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 9801ac9..fe67f12 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -20,6 +20,9 @@
#ifndef cpu_has_tlb
#define cpu_has_tlb (cpu_data[0].options & MIPS_CPU_TLB)
#endif
+#ifndef cpu_has_ftlb
+#define cpu_has_ftlb (cpu_data[0].options & MIPS_CPU_FTLB)
+#endif
#ifndef cpu_has_tlbinv
#define cpu_has_tlbinv (cpu_data[0].options & MIPS_CPU_TLBINV)
#endif
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index cd89e98..82ad15f 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -385,6 +385,7 @@
#define MIPS_CPU_CDMM 0x4000000000ull /* CPU has Common Device Memory Map */
#define MIPS_CPU_BP_GHIST 0x8000000000ull /* R12K+ Branch Prediction Global History */
#define MIPS_CPU_SP 0x10000000000ull /* Small (1KB) page support */
+#define MIPS_CPU_FTLB 0x20000000000ull /* CPU has Fixed-page-size TLB */
/*
* CPU ASE encodings
diff --git a/arch/mips/include/asm/maar.h b/arch/mips/include/asm/maar.h
index b02891f..21d9607 100644
--- a/arch/mips/include/asm/maar.h
+++ b/arch/mips/include/asm/maar.h
@@ -66,6 +66,15 @@
}
/**
+ * maar_init() - initialise MAARs
+ *
+ * Performs initialisation of MAARs for the current CPU, making use of the
+ * platforms implementation of platform_maar_init where necessary and
+ * duplicating the setup it provides on secondary CPUs.
+ */
+extern void maar_init(void);
+
+/**
* struct maar_config - MAAR configuration data
* @lower: The lowest address that the MAAR pair will affect. Must be
* aligned to a 2^16 byte boundary.
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index d75b75e..1f1927a 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -194,6 +194,7 @@
BUILD_CM_R_(gic_status, MIPS_CM_GCB_OFS + 0xd0)
BUILD_CM_R_(cpc_status, MIPS_CM_GCB_OFS + 0xf0)
BUILD_CM_RW(l2_config, MIPS_CM_GCB_OFS + 0x130)
+BUILD_CM_RW(sys_config2, MIPS_CM_GCB_OFS + 0x150)
/* Core Local & Core Other register accessor functions */
BUILD_CM_Cx_RW(reset_release, 0x00)
@@ -316,6 +317,10 @@
#define CM_GCR_L2_CONFIG_ASSOC_SHF 0
#define CM_GCR_L2_CONFIG_ASSOC_MSK (_ULCAST_(0xff) << 0)
+/* GCR_SYS_CONFIG2 register fields */
+#define CM_GCR_SYS_CONFIG2_MAXVPW_SHF 0
+#define CM_GCR_SYS_CONFIG2_MAXVPW_MSK (_ULCAST_(0xf) << 0)
+
/* GCR_Cx_COHERENCE register fields */
#define CM_GCR_Cx_COHERENCE_COHDOMAINEN_SHF 0
#define CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK (_ULCAST_(0xff) << 0)
@@ -405,4 +410,38 @@
return read_gcr_rev();
}
+/**
+ * mips_cm_max_vp_width() - return the width in bits of VP indices
+ *
+ * Return: the width, in bits, of VP indices in fields that combine core & VP
+ * indices.
+ */
+static inline unsigned int mips_cm_max_vp_width(void)
+{
+ extern int smp_num_siblings;
+
+ if (mips_cm_revision() >= CM_REV_CM3)
+ return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK;
+
+ return smp_num_siblings;
+}
+
+/**
+ * mips_cm_vp_id() - calculate the hardware VP ID for a CPU
+ * @cpu: the CPU whose VP ID to calculate
+ *
+ * Hardware such as the GIC uses identifiers for VPs which may not match the
+ * CPU numbers used by Linux. This function calculates the hardware VP
+ * identifier corresponding to a given CPU.
+ *
+ * Return: the VP ID for the CPU.
+ */
+static inline unsigned int mips_cm_vp_id(unsigned int cpu)
+{
+ unsigned int core = cpu_data[cpu].core;
+ unsigned int vp = cpu_vpe_id(&cpu_data[cpu]);
+
+ return (core * mips_cm_max_vp_width()) + vp;
+}
+
#endif /* __MIPS_ASM_MIPS_CM_H__ */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index d3cd8ea..c64781c 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -487,6 +487,8 @@
/* Bits specific to the MIPS32/64 PRA. */
#define MIPS_CONF_MT (_ULCAST_(7) << 7)
+#define MIPS_CONF_MT_TLB (_ULCAST_(1) << 7)
+#define MIPS_CONF_MT_FTLB (_ULCAST_(4) << 7)
#define MIPS_CONF_AR (_ULCAST_(7) << 10)
#define MIPS_CONF_AT (_ULCAST_(3) << 13)
#define MIPS_CONF_M (_ULCAST_(1) << 31)
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index c03088f..cfabadb 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -377,16 +377,18 @@
#define __NR_memfd_create (__NR_Linux + 354)
#define __NR_bpf (__NR_Linux + 355)
#define __NR_execveat (__NR_Linux + 356)
+#define __NR_userfaultfd (__NR_Linux + 357)
+#define __NR_membarrier (__NR_Linux + 358)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 356
+#define __NR_Linux_syscalls 358
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 356
+#define __NR_O32_Linux_syscalls 358
#if _MIPS_SIM == _MIPS_SIM_ABI64
@@ -711,16 +713,18 @@
#define __NR_memfd_create (__NR_Linux + 314)
#define __NR_bpf (__NR_Linux + 315)
#define __NR_execveat (__NR_Linux + 316)
+#define __NR_userfaultfd (__NR_Linux + 317)
+#define __NR_membarrier (__NR_Linux + 318)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 316
+#define __NR_Linux_syscalls 318
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 316
+#define __NR_64_Linux_syscalls 318
#if _MIPS_SIM == _MIPS_SIM_NABI32
@@ -1049,15 +1053,17 @@
#define __NR_memfd_create (__NR_Linux + 318)
#define __NR_bpf (__NR_Linux + 319)
#define __NR_execveat (__NR_Linux + 320)
+#define __NR_userfaultfd (__NR_Linux + 321)
+#define __NR_membarrier (__NR_Linux + 322)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 320
+#define __NR_Linux_syscalls 322
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 320
+#define __NR_N32_Linux_syscalls 322
#endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c
index 4e62bf8..459cb01 100644
--- a/arch/mips/jz4740/board-qi_lb60.c
+++ b/arch/mips/jz4740/board-qi_lb60.c
@@ -26,6 +26,7 @@
#include <linux/power/jz4740-battery.h>
#include <linux/power/gpio-charger.h>
+#include <asm/mach-jz4740/gpio.h>
#include <asm/mach-jz4740/jz4740_fb.h>
#include <asm/mach-jz4740/jz4740_mmc.h>
#include <asm/mach-jz4740/jz4740_nand.h>
diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c
index a74e181..8c6d76c 100644
--- a/arch/mips/jz4740/gpio.c
+++ b/arch/mips/jz4740/gpio.c
@@ -28,6 +28,7 @@
#include <linux/seq_file.h>
#include <asm/mach-jz4740/base.h>
+#include <asm/mach-jz4740/gpio.h>
#define JZ4740_GPIO_BASE_A (32*0)
#define JZ4740_GPIO_BASE_B (32*1)
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 9f71c06..209ded16 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -39,6 +39,7 @@
mfc0 \dest, CP0_CONFIG, 3
andi \dest, \dest, MIPS_CONF3_MT
beqz \dest, \nomt
+ nop
.endm
.section .text.cps-vec
@@ -223,10 +224,9 @@
END(excep_ejtag)
LEAF(mips_cps_core_init)
-#ifdef CONFIG_MIPS_MT
+#ifdef CONFIG_MIPS_MT_SMP
/* Check that the core implements the MT ASE */
has_mt t0, 3f
- nop
.set push
.set mips64r2
@@ -310,8 +310,9 @@
PTR_ADDU t0, t0, t1
/* Calculate this VPEs ID. If the core doesn't support MT use 0 */
+ li t9, 0
+#ifdef CONFIG_MIPS_MT_SMP
has_mt ta2, 1f
- li t9, 0
/* Find the number of VPEs present in the core */
mfc0 t1, CP0_MVPCONF0
@@ -330,6 +331,7 @@
/* Retrieve the VPE ID from EBase.CPUNum */
mfc0 t9, $15, 1
and t9, t9, t1
+#endif
1: /* Calculate a pointer to this VPEs struct vpe_boot_config */
li t1, VPEBOOTCFG_SIZE
@@ -337,7 +339,7 @@
PTR_L ta3, COREBOOTCFG_VPECONFIG(t0)
PTR_ADDU v0, v0, ta3
-#ifdef CONFIG_MIPS_MT
+#ifdef CONFIG_MIPS_MT_SMP
/* If the core doesn't support MT then return */
bnez ta2, 1f
@@ -451,7 +453,7 @@
2: .set pop
-#endif /* CONFIG_MIPS_MT */
+#endif /* CONFIG_MIPS_MT_SMP */
/* Return */
jr ra
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 571a8e6..09a51d0 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -410,16 +410,18 @@
static inline unsigned int decode_config0(struct cpuinfo_mips *c)
{
unsigned int config0;
- int isa;
+ int isa, mt;
config0 = read_c0_config();
/*
* Look for Standard TLB or Dual VTLB and FTLB
*/
- if ((((config0 & MIPS_CONF_MT) >> 7) == 1) ||
- (((config0 & MIPS_CONF_MT) >> 7) == 4))
+ mt = config0 & MIPS_CONF_MT;
+ if (mt == MIPS_CONF_MT_TLB)
c->options |= MIPS_CPU_TLB;
+ else if (mt == MIPS_CONF_MT_FTLB)
+ c->options |= MIPS_CPU_TLB | MIPS_CPU_FTLB;
isa = (config0 & MIPS_CONF_AT) >> 13;
switch (isa) {
@@ -559,15 +561,18 @@
if (cpu_has_tlb) {
if (((config4 & MIPS_CONF4_IE) >> 29) == 2)
c->options |= MIPS_CPU_TLBINV;
+
/*
- * This is a bit ugly. R6 has dropped that field from
- * config4 and the only valid configuration is VTLB+FTLB so
- * set a good value for mmuextdef for that case.
+ * R6 has dropped the MMUExtDef field from config4.
+ * On R6 the fields always describe the FTLB, and only if it is
+ * present according to Config.MT.
*/
- if (cpu_has_mips_r6)
+ if (!cpu_has_mips_r6)
+ mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+ else if (cpu_has_ftlb)
mmuextdef = MIPS_CONF4_MMUEXTDEF_VTLBSIZEEXT;
else
- mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+ mmuextdef = 0;
switch (mmuextdef) {
case MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT:
diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index 423ae83..3375745 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -18,7 +18,7 @@
.set pop
/*
* task_struct *resume(task_struct *prev, task_struct *next,
- * struct thread_info *next_ti, int usedfpu)
+ * struct thread_info *next_ti)
*/
.align 7
LEAF(resume)
@@ -28,30 +28,6 @@
cpu_save_nonscratch a0
LONG_S ra, THREAD_REG31(a0)
- /*
- * check if we need to save FPU registers
- */
- .set push
- .set noreorder
- beqz a3, 1f
- PTR_L t3, TASK_THREAD_INFO(a0)
- .set pop
-
- /*
- * clear saved user stack CU1 bit
- */
- LONG_L t0, ST_OFF(t3)
- li t1, ~ST0_CU1
- and t0, t0, t1
- LONG_S t0, ST_OFF(t3)
-
- .set push
- .set arch=mips64r2
- fpu_save_double a0 t0 t1 # c0_status passed in t0
- # clobbers t1
- .set pop
-1:
-
#if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0
/* Check if we need to store CVMSEG state */
dmfc0 t0, $11,7 /* CvmMemCtl */
diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S
index 5087a4b..ac27ef7 100644
--- a/arch/mips/kernel/r2300_switch.S
+++ b/arch/mips/kernel/r2300_switch.S
@@ -31,18 +31,8 @@
#define ST_OFF (_THREAD_SIZE - 32 - PT_SIZE + PT_STATUS)
/*
- * FPU context is saved iff the process has used it's FPU in the current
- * time slice as indicated by TIF_USEDFPU. In any case, the CU1 bit for user
- * space STATUS register should be 0, so that a process *always* starts its
- * userland with FPU disabled after each context switch.
- *
- * FPU will be enabled as soon as the process accesses FPU again, through
- * do_cpu() trap.
- */
-
-/*
* task_struct *resume(task_struct *prev, task_struct *next,
- * struct thread_info *next_ti, int usedfpu)
+ * struct thread_info *next_ti)
*/
LEAF(resume)
mfc0 t1, CP0_STATUS
@@ -50,22 +40,6 @@
cpu_save_nonscratch a0
sw ra, THREAD_REG31(a0)
- beqz a3, 1f
-
- PTR_L t3, TASK_THREAD_INFO(a0)
-
- /*
- * clear saved user stack CU1 bit
- */
- lw t0, ST_OFF(t3)
- li t1, ~ST0_CU1
- and t0, t0, t1
- sw t0, ST_OFF(t3)
-
- fpu_save_single a0, t0 # clobbers t0
-
-1:
-
#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
PTR_LA t8, __stack_chk_guard
LONG_L t9, TASK_STACK_CANARY(a1)
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 4cc1350..65a74e4 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -36,16 +36,8 @@
lw t1, PT_EPC(sp) # skip syscall on return
subu v0, v0, __NR_O32_Linux # check syscall number
- sltiu t0, v0, __NR_O32_Linux_syscalls + 1
addiu t1, 4 # skip to next instruction
sw t1, PT_EPC(sp)
- beqz t0, illegal_syscall
-
- sll t0, v0, 2
- la t1, sys_call_table
- addu t1, t0
- lw t2, (t1) # syscall routine
- beqz t2, illegal_syscall
sw a3, PT_R26(sp) # save a3 for syscall restarting
@@ -96,6 +88,16 @@
li t1, _TIF_WORK_SYSCALL_ENTRY
and t0, t1
bnez t0, syscall_trace_entry # -> yes
+syscall_common:
+ sltiu t0, v0, __NR_O32_Linux_syscalls + 1
+ beqz t0, illegal_syscall
+
+ sll t0, v0, 2
+ la t1, sys_call_table
+ addu t1, t0
+ lw t2, (t1) # syscall routine
+
+ beqz t2, illegal_syscall
jalr t2 # Do The Real Thing (TM)
@@ -116,7 +118,7 @@
syscall_trace_entry:
SAVE_STATIC
- move s0, t2
+ move s0, v0
move a0, sp
/*
@@ -129,27 +131,18 @@
1: jal syscall_trace_enter
- bltz v0, 2f # seccomp failed? Skip syscall
+ bltz v0, 1f # seccomp failed? Skip syscall
- move t0, s0
+ move v0, s0 # restore syscall
+
RESTORE_STATIC
lw a0, PT_R4(sp) # Restore argument registers
lw a1, PT_R5(sp)
lw a2, PT_R6(sp)
lw a3, PT_R7(sp)
- jalr t0
+ j syscall_common
- li t0, -EMAXERRNO - 1 # error?
- sltu t0, t0, v0
- sw t0, PT_R7(sp) # set error flag
- beqz t0, 1f
-
- lw t1, PT_R2(sp) # syscall number
- negu v0 # error
- sw t1, PT_R0(sp) # save it for syscall restarting
-1: sw v0, PT_R2(sp) # result
-
-2: j syscall_exit
+1: j syscall_exit
/* ------------------------------------------------------------------------ */
@@ -599,3 +592,5 @@
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR sys_execveat
+ PTR sys_userfaultfd
+ PTR sys_membarrier
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index a6f6b76..e732981 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -39,18 +39,11 @@
.set at
#endif
- dsubu t0, v0, __NR_64_Linux # check syscall number
- sltiu t0, t0, __NR_64_Linux_syscalls + 1
#if !defined(CONFIG_MIPS32_O32) && !defined(CONFIG_MIPS32_N32)
ld t1, PT_EPC(sp) # skip syscall on return
daddiu t1, 4 # skip to next instruction
sd t1, PT_EPC(sp)
#endif
- beqz t0, illegal_syscall
-
- dsll t0, v0, 3 # offset into table
- ld t2, (sys_call_table - (__NR_64_Linux * 8))(t0)
- # syscall routine
sd a3, PT_R26(sp) # save a3 for syscall restarting
@@ -59,6 +52,17 @@
and t0, t1, t0
bnez t0, syscall_trace_entry
+syscall_common:
+ dsubu t2, v0, __NR_64_Linux
+ sltiu t0, t2, __NR_64_Linux_syscalls + 1
+ beqz t0, illegal_syscall
+
+ dsll t0, t2, 3 # offset into table
+ dla t2, sys_call_table
+ daddu t0, t2, t0
+ ld t2, (t0) # syscall routine
+ beqz t2, illegal_syscall
+
jalr t2 # Do The Real Thing (TM)
li t0, -EMAXERRNO - 1 # error?
@@ -78,14 +82,14 @@
syscall_trace_entry:
SAVE_STATIC
- move s0, t2
+ move s0, v0
move a0, sp
move a1, v0
jal syscall_trace_enter
- bltz v0, 2f # seccomp failed? Skip syscall
+ bltz v0, 1f # seccomp failed? Skip syscall
- move t0, s0
+ move v0, s0
RESTORE_STATIC
ld a0, PT_R4(sp) # Restore argument registers
ld a1, PT_R5(sp)
@@ -93,19 +97,9 @@
ld a3, PT_R7(sp)
ld a4, PT_R8(sp)
ld a5, PT_R9(sp)
- jalr t0
+ j syscall_common
- li t0, -EMAXERRNO - 1 # error?
- sltu t0, t0, v0
- sd t0, PT_R7(sp) # set error flag
- beqz t0, 1f
-
- ld t1, PT_R2(sp) # syscall number
- dnegu v0 # error
- sd t1, PT_R0(sp) # save it for syscall restarting
-1: sd v0, PT_R2(sp) # result
-
-2: j syscall_exit
+1: j syscall_exit
illegal_syscall:
/* This also isn't a 64-bit syscall, throw an error. */
@@ -436,4 +430,6 @@
PTR sys_memfd_create
PTR sys_bpf /* 5315 */
PTR sys_execveat
+ PTR sys_userfaultfd
+ PTR sys_membarrier
.size sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 4b20106..c794843 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -52,6 +52,7 @@
and t0, t1, t0
bnez t0, n32_syscall_trace_entry
+syscall_common:
jalr t2 # Do The Real Thing (TM)
li t0, -EMAXERRNO - 1 # error?
@@ -75,9 +76,9 @@
move a1, v0
jal syscall_trace_enter
- bltz v0, 2f # seccomp failed? Skip syscall
+ bltz v0, 1f # seccomp failed? Skip syscall
- move t0, s0
+ move t2, s0
RESTORE_STATIC
ld a0, PT_R4(sp) # Restore argument registers
ld a1, PT_R5(sp)
@@ -85,19 +86,9 @@
ld a3, PT_R7(sp)
ld a4, PT_R8(sp)
ld a5, PT_R9(sp)
- jalr t0
+ j syscall_common
- li t0, -EMAXERRNO - 1 # error?
- sltu t0, t0, v0
- sd t0, PT_R7(sp) # set error flag
- beqz t0, 1f
-
- ld t1, PT_R2(sp) # syscall number
- dnegu v0 # error
- sd t1, PT_R0(sp) # save it for syscall restarting
-1: sd v0, PT_R2(sp) # result
-
-2: j syscall_exit
+1: j syscall_exit
not_n32_scall:
/* This is not an n32 compatibility syscall, pass it on to
@@ -429,4 +420,6 @@
PTR sys_memfd_create
PTR sys_bpf
PTR compat_sys_execveat /* 6320 */
+ PTR sys_userfaultfd
+ PTR sys_membarrier
.size sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f543ff4..6369cfd 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -87,6 +87,7 @@
and t0, t1, t0
bnez t0, trace_a_syscall
+syscall_common:
jalr t2 # Do The Real Thing (TM)
li t0, -EMAXERRNO - 1 # error?
@@ -130,9 +131,9 @@
1: jal syscall_trace_enter
- bltz v0, 2f # seccomp failed? Skip syscall
+ bltz v0, 1f # seccomp failed? Skip syscall
- move t0, s0
+ move t2, s0
RESTORE_STATIC
ld a0, PT_R4(sp) # Restore argument registers
ld a1, PT_R5(sp)
@@ -142,19 +143,9 @@
ld a5, PT_R9(sp)
ld a6, PT_R10(sp)
ld a7, PT_R11(sp) # For indirect syscalls
- jalr t0
+ j syscall_common
- li t0, -EMAXERRNO - 1 # error?
- sltu t0, t0, v0
- sd t0, PT_R7(sp) # set error flag
- beqz t0, 1f
-
- ld t1, PT_R2(sp) # syscall number
- dnegu v0 # error
- sd t1, PT_R0(sp) # save it for syscall restarting
-1: sd v0, PT_R2(sp) # result
-
-2: j syscall_exit
+1: j syscall_exit
/* ------------------------------------------------------------------------ */
@@ -584,4 +575,6 @@
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR compat_sys_execveat
+ PTR sys_userfaultfd
+ PTR sys_membarrier
.size sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 35b8316..4795151 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -338,7 +338,7 @@
if (end <= reserved_end)
continue;
#ifdef CONFIG_BLK_DEV_INITRD
- /* mapstart should be after initrd_end */
+ /* Skip zones before initrd and initrd itself */
if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
continue;
#endif
@@ -371,6 +371,14 @@
max_low_pfn = PFN_DOWN(HIGHMEM_START);
}
+#ifdef CONFIG_BLK_DEV_INITRD
+ /*
+ * mapstart should be after initrd_end
+ */
+ if (initrd_end)
+ mapstart = max(mapstart, (unsigned long)PFN_UP(__pa(initrd_end)));
+#endif
+
/*
* Initialize the boot-time allocator with low memory only.
*/
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index a31896c..bd4385a 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -42,6 +42,7 @@
#include <asm/mmu_context.h>
#include <asm/time.h>
#include <asm/setup.h>
+#include <asm/maar.h>
cpumask_t cpu_callin_map; /* Bitmask of started secondaries */
@@ -157,6 +158,7 @@
mips_clockevent_init();
mp_ops->init_secondary();
cpu_report();
+ maar_init();
/*
* XXX parity protection should be folded in here when it's converted
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index f6c44dd..d6d07ad 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -64,6 +64,9 @@
}
if (memsize == 0)
memsize = 256;
+
+ loongson_sysconf.nr_uarts = 1;
+
pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize);
#else
struct boot_params *boot_p;
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index a914dc1..d8117be 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -100,7 +100,7 @@
else
#endif
#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
- if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
+ if (dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8))
dma_flag = __GFP_DMA;
else
#endif
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 66d0f49..8770e61 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -44,6 +44,7 @@
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/fixmap.h>
+#include <asm/maar.h>
/*
* We have up to 8 empty zeroed pages so we can map one of the right colour
@@ -252,6 +253,119 @@
#endif
}
+unsigned __weak platform_maar_init(unsigned num_pairs)
+{
+ struct maar_config cfg[BOOT_MEM_MAP_MAX];
+ unsigned i, num_configured, num_cfg = 0;
+ phys_addr_t skip;
+
+ for (i = 0; i < boot_mem_map.nr_map; i++) {
+ switch (boot_mem_map.map[i].type) {
+ case BOOT_MEM_RAM:
+ case BOOT_MEM_INIT_RAM:
+ break;
+ default:
+ continue;
+ }
+
+ skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
+
+ cfg[num_cfg].lower = boot_mem_map.map[i].addr;
+ cfg[num_cfg].lower += skip;
+
+ cfg[num_cfg].upper = cfg[num_cfg].lower;
+ cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
+ cfg[num_cfg].upper -= skip;
+
+ cfg[num_cfg].attrs = MIPS_MAAR_S;
+ num_cfg++;
+ }
+
+ num_configured = maar_config(cfg, num_cfg, num_pairs);
+ if (num_configured < num_cfg)
+ pr_warn("Not enough MAAR pairs (%u) for all bootmem regions (%u)\n",
+ num_pairs, num_cfg);
+
+ return num_configured;
+}
+
+void maar_init(void)
+{
+ unsigned num_maars, used, i;
+ phys_addr_t lower, upper, attr;
+ static struct {
+ struct maar_config cfgs[3];
+ unsigned used;
+ } recorded = { { { 0 } }, 0 };
+
+ if (!cpu_has_maar)
+ return;
+
+ /* Detect the number of MAARs */
+ write_c0_maari(~0);
+ back_to_back_c0_hazard();
+ num_maars = read_c0_maari() + 1;
+
+ /* MAARs should be in pairs */
+ WARN_ON(num_maars % 2);
+
+ /* Set MAARs using values we recorded already */
+ if (recorded.used) {
+ used = maar_config(recorded.cfgs, recorded.used, num_maars / 2);
+ BUG_ON(used != recorded.used);
+ } else {
+ /* Configure the required MAARs */
+ used = platform_maar_init(num_maars / 2);
+ }
+
+ /* Disable any further MAARs */
+ for (i = (used * 2); i < num_maars; i++) {
+ write_c0_maari(i);
+ back_to_back_c0_hazard();
+ write_c0_maar(0);
+ back_to_back_c0_hazard();
+ }
+
+ if (recorded.used)
+ return;
+
+ pr_info("MAAR configuration:\n");
+ for (i = 0; i < num_maars; i += 2) {
+ write_c0_maari(i);
+ back_to_back_c0_hazard();
+ upper = read_c0_maar();
+
+ write_c0_maari(i + 1);
+ back_to_back_c0_hazard();
+ lower = read_c0_maar();
+
+ attr = lower & upper;
+ lower = (lower & MIPS_MAAR_ADDR) << 4;
+ upper = ((upper & MIPS_MAAR_ADDR) << 4) | 0xffff;
+
+ pr_info(" [%d]: ", i / 2);
+ if (!(attr & MIPS_MAAR_V)) {
+ pr_cont("disabled\n");
+ continue;
+ }
+
+ pr_cont("%pa-%pa", &lower, &upper);
+
+ if (attr & MIPS_MAAR_S)
+ pr_cont(" speculate");
+
+ pr_cont("\n");
+
+ /* Record the setup for use on secondary CPUs */
+ if (used <= ARRAY_SIZE(recorded.cfgs)) {
+ recorded.cfgs[recorded.used].lower = lower;
+ recorded.cfgs[recorded.used].upper = upper;
+ recorded.cfgs[recorded.used].attrs = attr;
+ recorded.used++;
+ }
+ }
+}
+
#ifndef CONFIG_NEED_MULTIPLE_NODES
int page_is_ram(unsigned long pagenr)
{
@@ -334,69 +448,6 @@
#endif
}
-unsigned __weak platform_maar_init(unsigned num_pairs)
-{
- struct maar_config cfg[BOOT_MEM_MAP_MAX];
- unsigned i, num_configured, num_cfg = 0;
- phys_addr_t skip;
-
- for (i = 0; i < boot_mem_map.nr_map; i++) {
- switch (boot_mem_map.map[i].type) {
- case BOOT_MEM_RAM:
- case BOOT_MEM_INIT_RAM:
- break;
- default:
- continue;
- }
-
- skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
-
- cfg[num_cfg].lower = boot_mem_map.map[i].addr;
- cfg[num_cfg].lower += skip;
-
- cfg[num_cfg].upper = cfg[num_cfg].lower;
- cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
- cfg[num_cfg].upper -= skip;
-
- cfg[num_cfg].attrs = MIPS_MAAR_S;
- num_cfg++;
- }
-
- num_configured = maar_config(cfg, num_cfg, num_pairs);
- if (num_configured < num_cfg)
- pr_warn("Not enough MAAR pairs (%u) for all bootmem regions (%u)\n",
- num_pairs, num_cfg);
-
- return num_configured;
-}
-
-static void maar_init(void)
-{
- unsigned num_maars, used, i;
-
- if (!cpu_has_maar)
- return;
-
- /* Detect the number of MAARs */
- write_c0_maari(~0);
- back_to_back_c0_hazard();
- num_maars = read_c0_maari() + 1;
-
- /* MAARs should be in pairs */
- WARN_ON(num_maars % 2);
-
- /* Configure the required MAARs */
- used = platform_maar_init(num_maars / 2);
-
- /* Disable any further MAARs */
- for (i = (used * 2); i < num_maars; i++) {
- write_c0_maari(i);
- back_to_back_c0_hazard();
- write_c0_maar(0);
- back_to_back_c0_hazard();
- }
-}
-
void __init mem_init(void)
{
#ifdef CONFIG_HIGHMEM
diff --git a/arch/mips/net/bpf_jit_asm.S b/arch/mips/net/bpf_jit_asm.S
index e927260..5d2e0c8 100644
--- a/arch/mips/net/bpf_jit_asm.S
+++ b/arch/mips/net/bpf_jit_asm.S
@@ -57,15 +57,28 @@
LEAF(sk_load_word)
is_offset_negative(word)
- .globl sk_load_word_positive
-sk_load_word_positive:
+FEXPORT(sk_load_word_positive)
is_offset_in_header(4, word)
/* Offset within header boundaries */
PTR_ADDU t1, $r_skb_data, offset
+ .set reorder
lw $r_A, 0(t1)
+ .set noreorder
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
wsbh t0, $r_A
rotr $r_A, t0, 16
+# else
+ sll t0, $r_A, 24
+ srl t1, $r_A, 24
+ srl t2, $r_A, 8
+ or t0, t0, t1
+ andi t2, t2, 0xff00
+ andi t1, $r_A, 0xff00
+ or t0, t0, t2
+ sll t1, t1, 8
+ or $r_A, t0, t1
+# endif
#endif
jr $r_ra
move $r_ret, zero
@@ -73,15 +86,24 @@
LEAF(sk_load_half)
is_offset_negative(half)
- .globl sk_load_half_positive
-sk_load_half_positive:
+FEXPORT(sk_load_half_positive)
is_offset_in_header(2, half)
/* Offset within header boundaries */
PTR_ADDU t1, $r_skb_data, offset
+ .set reorder
lh $r_A, 0(t1)
+ .set noreorder
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
wsbh t0, $r_A
seh $r_A, t0
+# else
+ sll t0, $r_A, 24
+ andi t1, $r_A, 0xff00
+ sra t0, t0, 16
+ srl t1, t1, 8
+ or $r_A, t0, t1
+# endif
#endif
jr $r_ra
move $r_ret, zero
@@ -89,8 +111,7 @@
LEAF(sk_load_byte)
is_offset_negative(byte)
- .globl sk_load_byte_positive
-sk_load_byte_positive:
+FEXPORT(sk_load_byte_positive)
is_offset_in_header(1, byte)
/* Offset within header boundaries */
PTR_ADDU t1, $r_skb_data, offset
@@ -148,23 +169,47 @@
NESTED(bpf_slow_path_word, (6 * SZREG), $r_sp)
bpf_slow_path_common(4)
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
wsbh t0, $r_s0
jr $r_ra
rotr $r_A, t0, 16
-#endif
+# else
+ sll t0, $r_s0, 24
+ srl t1, $r_s0, 24
+ srl t2, $r_s0, 8
+ or t0, t0, t1
+ andi t2, t2, 0xff00
+ andi t1, $r_s0, 0xff00
+ or t0, t0, t2
+ sll t1, t1, 8
jr $r_ra
- move $r_A, $r_s0
+ or $r_A, t0, t1
+# endif
+#else
+ jr $r_ra
+ move $r_A, $r_s0
+#endif
END(bpf_slow_path_word)
NESTED(bpf_slow_path_half, (6 * SZREG), $r_sp)
bpf_slow_path_common(2)
#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
jr $r_ra
wsbh $r_A, $r_s0
-#endif
+# else
+ sll t0, $r_s0, 8
+ andi t1, $r_s0, 0xff00
+ andi t0, t0, 0xff00
+ srl t1, t1, 8
+ jr $r_ra
+ or $r_A, t0, t1
+# endif
+#else
jr $r_ra
move $r_A, $r_s0
+#endif
END(bpf_slow_path_half)
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 6edb9ee..1c8dd0f 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -9,3 +9,4 @@
generic-y += preempt.h
generic-y += sections.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 914864e..d63330e 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -61,4 +61,5 @@
generic-y += unaligned.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index ab9f4e0..ac16629 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -7,3 +7,4 @@
generic-y += preempt.h
generic-y += rwsem.h
generic-y += vtime.h
+generic-y += word-at-a-time.h
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 5ad26dd9..9043d2e 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -6,3 +6,4 @@
generic-y += mm-arch-hooks.h
generic-y += preempt.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 92ffe39..a05218f 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -13,3 +13,4 @@
generic-y += trace_clock.h
generic-y += xor.h
generic-y += serial.h
+generic-y += word-at-a-time.h
diff --git a/arch/tile/gxio/mpipe.c b/arch/tile/gxio/mpipe.c
index ee186e1..f102048 100644
--- a/arch/tile/gxio/mpipe.c
+++ b/arch/tile/gxio/mpipe.c
@@ -19,6 +19,7 @@
#include <linux/errno.h>
#include <linux/io.h>
#include <linux/module.h>
+#include <linux/string.h>
#include <gxio/iorpc_globals.h>
#include <gxio/iorpc_mpipe.h>
@@ -29,32 +30,6 @@
/* HACK: Avoid pointless "shadow" warnings. */
#define link link_shadow
-/**
- * strscpy - Copy a C-string into a sized buffer, but only if it fits
- * @dest: Where to copy the string to
- * @src: Where to copy the string from
- * @size: size of destination buffer
- *
- * Use this routine to avoid copying too-long strings.
- * The routine returns the total number of bytes copied
- * (including the trailing NUL) or zero if the buffer wasn't
- * big enough. To ensure that programmers pay attention
- * to the return code, the destination has a single NUL
- * written at the front (if size is non-zero) when the
- * buffer is not big enough.
- */
-static size_t strscpy(char *dest, const char *src, size_t size)
-{
- size_t len = strnlen(src, size) + 1;
- if (len > size) {
- if (size)
- dest[0] = '\0';
- return 0;
- }
- memcpy(dest, src, len);
- return len;
-}
-
int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index)
{
char file[32];
@@ -540,7 +515,7 @@
if (!context)
return GXIO_ERR_NO_DEVICE;
- if (strscpy(name.name, link_name, sizeof(name.name)) == 0)
+ if (strscpy(name.name, link_name, sizeof(name.name)) < 0)
return GXIO_ERR_NO_DEVICE;
return gxio_mpipe_info_instance_aux(context, name);
@@ -559,7 +534,7 @@
rv = gxio_mpipe_info_enumerate_aux(context, idx, &name, &mac);
if (rv >= 0) {
- if (strscpy(link_name, name.name, sizeof(name.name)) == 0)
+ if (strscpy(link_name, name.name, sizeof(name.name)) < 0)
return GXIO_ERR_INVAL_MEMORY_SIZE;
memcpy(link_mac, mac.mac, sizeof(mac.mac));
}
@@ -576,7 +551,7 @@
_gxio_mpipe_link_name_t name;
int rv;
- if (strscpy(name.name, link_name, sizeof(name.name)) == 0)
+ if (strscpy(name.name, link_name, sizeof(name.name)) < 0)
return GXIO_ERR_NO_DEVICE;
rv = gxio_mpipe_link_open_aux(context, name, flags);
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index ba35c41..0b6cacaa 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -40,4 +40,5 @@
generic-y += termios.h
generic-y += trace_clock.h
generic-y += types.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/tile/kernel/usb.c b/arch/tile/kernel/usb.c
index f0da5a2..9f1e05e 100644
--- a/arch/tile/kernel/usb.c
+++ b/arch/tile/kernel/usb.c
@@ -22,6 +22,7 @@
#include <linux/platform_device.h>
#include <linux/usb/tilegx.h>
#include <linux/init.h>
+#include <linux/module.h>
#include <linux/types.h>
static u64 ehci_dmamask = DMA_BIT_MASK(32);
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 149ec55..904f3eb 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -25,4 +25,5 @@
generic-y += switch_to.h
generic-y += topology.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 1fc7a28..256c45b 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -62,4 +62,5 @@
generic-y += unaligned.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e6cf2ad..9727b3b 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -193,7 +193,7 @@
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */
-#define X86_FEATURE_HWP_NOITFY ( 7*32+ 11) /* Intel HWP_NOTIFY */
+#define X86_FEATURE_HWP_NOTIFY ( 7*32+ 11) /* Intel HWP_NOTIFY */
#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */
#define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */
#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index ab5f1d4..ae68be9 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -86,6 +86,7 @@
extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
u32 type, u64 attribute);
+#ifdef CONFIG_KASAN
/*
* CONFIG_KASAN may redefine memset to __memset. __memset function is present
* only in kernel binary. Since the EFI stub linked into a separate binary it
@@ -95,6 +96,7 @@
#undef memcpy
#undef memset
#undef memmove
+#endif
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b98b471..b8c14bb 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -141,6 +141,8 @@
#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10)
#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11)
+#define MSR_PEBS_FRONTEND 0x000003f7
+
#define MSR_IA32_POWER_CTL 0x000001fc
#define MSR_IA32_MC0_CTL 0x00000400
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 655e07a..67f0823 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,6 +41,7 @@
#define PVCLOCK_TSC_STABLE_BIT (1 << 0)
#define PVCLOCK_GUEST_STOPPED (1 << 1)
+/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h
index b0ae1c4..217909b 100644
--- a/arch/x86/include/uapi/asm/bitsperlong.h
+++ b/arch/x86/include/uapi/asm/bitsperlong.h
@@ -1,7 +1,7 @@
#ifndef __ASM_X86_BITSPERLONG_H
#define __ASM_X86_BITSPERLONG_H
-#ifdef __x86_64__
+#if defined(__x86_64__) && !defined(__ILP32__)
# define __BITS_PER_LONG 64
#else
# define __BITS_PER_LONG 32
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 381c8b9..20e242e 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -34,11 +34,10 @@
struct ms_hyperv_info ms_hyperv;
EXPORT_SYMBOL_GPL(ms_hyperv);
-static void (*hv_kexec_handler)(void);
-static void (*hv_crash_handler)(struct pt_regs *regs);
-
#if IS_ENABLED(CONFIG_HYPERV)
static void (*vmbus_handler)(void);
+static void (*hv_kexec_handler)(void);
+static void (*hv_crash_handler)(struct pt_regs *regs);
void hyperv_vector_handler(struct pt_regs *regs)
{
@@ -96,8 +95,8 @@
hv_crash_handler = NULL;
}
EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
-#endif
+#ifdef CONFIG_KEXEC_CORE
static void hv_machine_shutdown(void)
{
if (kexec_in_progress && hv_kexec_handler)
@@ -111,7 +110,8 @@
hv_crash_handler(regs);
native_machine_crash_shutdown(regs);
}
-
+#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_HYPERV */
static uint32_t __init ms_hyperv_platform(void)
{
@@ -186,8 +186,10 @@
no_timer_check = 1;
#endif
+#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
machine_ops.shutdown = hv_machine_shutdown;
machine_ops.crash_shutdown = hv_machine_crash_shutdown;
+#endif
mark_tsc_unstable("running on Hyper-V");
}
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5edf6d8..165be83 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -47,6 +47,7 @@
EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */
EXTRA_REG_LBR = 2, /* lbr_select */
EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */
+ EXTRA_REG_FE = 4, /* fe_* */
EXTRA_REG_MAX /* number of entries needed */
};
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3fefebf..f63360b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -205,6 +205,11 @@
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ /*
+ * Note the low 8 bits eventsel code is not a continuous field, containing
+ * some #GPing bits. These are masked out.
+ */
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
EVENT_EXTRA_END
};
@@ -250,7 +255,7 @@
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */
- INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */
+ INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
EVENT_CONSTRAINT_END
};
@@ -2891,6 +2896,8 @@
PMU_FORMAT_ATTR(ldlat, "config1:0-15");
+PMU_FORMAT_ATTR(frontend, "config1:0-23");
+
static struct attribute *intel_arch3_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
@@ -2907,6 +2914,11 @@
NULL,
};
+static struct attribute *skl_format_attr[] = {
+ &format_attr_frontend.attr,
+ NULL,
+};
+
static __initconst const struct x86_pmu core_pmu = {
.name = "core",
.handle_irq = x86_pmu_handle_irq,
@@ -3516,7 +3528,8 @@
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
+ skl_format_attr);
WARN_ON(!x86_pmu.format_attrs);
x86_pmu.cpu_events = hsw_events_attrs;
pr_cont("Skylake events, ");
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
index 086b12e..f32ac13 100644
--- a/arch/x86/kernel/cpu/perf_event_msr.c
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -10,12 +10,12 @@
PERF_MSR_EVENT_MAX,
};
-bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx)
{
return boot_cpu_has(X86_FEATURE_APERFMPERF);
}
-bool test_intel(int idx)
+static bool test_intel(int idx)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
boot_cpu_data.x86 != 6)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 3d423a1..608fb26 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -37,7 +37,7 @@
{ X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 },
{ X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 },
{ X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 },
- { X86_FEATURE_HWP_NOITFY, CR_EAX, 8, 0x00000006, 0 },
+ { X86_FEATURE_HWP_NOTIFY, CR_EAX, 8, 0x00000006, 0 },
{ X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 },
{ X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 },
{ X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 },
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index e068d66..74ca2fe 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -185,10 +185,9 @@
}
#ifdef CONFIG_KEXEC_FILE
-static int get_nr_ram_ranges_callback(unsigned long start_pfn,
- unsigned long nr_pfn, void *arg)
+static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
{
- int *nr_ranges = arg;
+ unsigned int *nr_ranges = arg;
(*nr_ranges)++;
return 0;
@@ -214,7 +213,7 @@
ced->image = image;
- walk_system_ram_range(0, -1, &nr_ranges,
+ walk_system_ram_res(0, -1, &nr_ranges,
get_nr_ram_ranges_callback);
ced->max_nr_ranges = nr_ranges;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6d0e62a..39e585a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -506,3 +506,58 @@
return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
}
+/*
+ * Called from fs/proc with a reference on @p to find the function
+ * which called into schedule(). This needs to be done carefully
+ * because the task might wake up and we might look at a stack
+ * changing under us.
+ */
+unsigned long get_wchan(struct task_struct *p)
+{
+ unsigned long start, bottom, top, sp, fp, ip;
+ int count = 0;
+
+ if (!p || p == current || p->state == TASK_RUNNING)
+ return 0;
+
+ start = (unsigned long)task_stack_page(p);
+ if (!start)
+ return 0;
+
+ /*
+ * Layout of the stack page:
+ *
+ * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
+ * PADDING
+ * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
+ * stack
+ * ----------- bottom = start + sizeof(thread_info)
+ * thread_info
+ * ----------- start
+ *
+ * The tasks stack pointer points at the location where the
+ * framepointer is stored. The data on the stack is:
+ * ... IP FP ... IP FP
+ *
+ * We need to read FP and IP, so we need to adjust the upper
+ * bound by another unsigned long.
+ */
+ top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
+ top -= 2 * sizeof(unsigned long);
+ bottom = start + sizeof(struct thread_info);
+
+ sp = READ_ONCE(p->thread.sp);
+ if (sp < bottom || sp > top)
+ return 0;
+
+ fp = READ_ONCE(*(unsigned long *)sp);
+ do {
+ if (fp < bottom || fp > top)
+ return 0;
+ ip = READ_ONCE(*(unsigned long *)(fp + sizeof(unsigned long)));
+ if (!in_sched_functions(ip))
+ return ip;
+ fp = READ_ONCE(*(unsigned long *)fp);
+ } while (count++ < 16 && p->state != TASK_RUNNING);
+ return 0;
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c13df2c..737527b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -324,31 +324,3 @@
return prev_p;
}
-
-#define top_esp (THREAD_SIZE - sizeof(unsigned long))
-#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long))
-
-unsigned long get_wchan(struct task_struct *p)
-{
- unsigned long bp, sp, ip;
- unsigned long stack_page;
- int count = 0;
- if (!p || p == current || p->state == TASK_RUNNING)
- return 0;
- stack_page = (unsigned long)task_stack_page(p);
- sp = p->thread.sp;
- if (!stack_page || sp < stack_page || sp > top_esp+stack_page)
- return 0;
- /* include/asm-i386/system.h:switch_to() pushes bp last. */
- bp = *(unsigned long *) sp;
- do {
- if (bp < stack_page || bp > top_ebp+stack_page)
- return 0;
- ip = *(unsigned long *) (bp+4);
- if (!in_sched_functions(ip))
- return ip;
- bp = *(unsigned long *) bp;
- } while (count++ < 16);
- return 0;
-}
-
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3c1bbcf..b35921a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -499,30 +499,6 @@
}
EXPORT_SYMBOL_GPL(set_personality_ia32);
-unsigned long get_wchan(struct task_struct *p)
-{
- unsigned long stack;
- u64 fp, ip;
- int count = 0;
-
- if (!p || p == current || p->state == TASK_RUNNING)
- return 0;
- stack = (unsigned long)task_stack_page(p);
- if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE)
- return 0;
- fp = *(u64 *)(p->thread.sp);
- do {
- if (fp < (unsigned long)stack ||
- fp >= (unsigned long)stack+THREAD_SIZE)
- return 0;
- ip = *(u64 *)(fp+8);
- if (!in_sched_functions(ip))
- return ip;
- fp = *(u64 *)fp;
- } while (count++ < 16);
- return 0;
-}
-
long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
{
int ret = 0;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 94b7d15..2f9ed1f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -514,7 +514,7 @@
struct vcpu_svm *svm = to_svm(vcpu);
if (svm->vmcb->control.next_rip != 0) {
- WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
+ WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
svm->next_rip = svm->vmcb->control.next_rip;
}
@@ -866,64 +866,6 @@
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
-#define MTRR_TYPE_UC_MINUS 7
-#define MTRR2PROTVAL_INVALID 0xff
-
-static u8 mtrr2protval[8];
-
-static u8 fallback_mtrr_type(int mtrr)
-{
- /*
- * WT and WP aren't always available in the host PAT. Treat
- * them as UC and UC- respectively. Everything else should be
- * there.
- */
- switch (mtrr)
- {
- case MTRR_TYPE_WRTHROUGH:
- return MTRR_TYPE_UNCACHABLE;
- case MTRR_TYPE_WRPROT:
- return MTRR_TYPE_UC_MINUS;
- default:
- BUG();
- }
-}
-
-static void build_mtrr2protval(void)
-{
- int i;
- u64 pat;
-
- for (i = 0; i < 8; i++)
- mtrr2protval[i] = MTRR2PROTVAL_INVALID;
-
- /* Ignore the invalid MTRR types. */
- mtrr2protval[2] = 0;
- mtrr2protval[3] = 0;
-
- /*
- * Use host PAT value to figure out the mapping from guest MTRR
- * values to nested page table PAT/PCD/PWT values. We do not
- * want to change the host PAT value every time we enter the
- * guest.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- for (i = 0; i < 8; i++) {
- u8 mtrr = pat >> (8 * i);
-
- if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
- mtrr2protval[mtrr] = __cm_idx2pte(i);
- }
-
- for (i = 0; i < 8; i++) {
- if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
- u8 fallback = fallback_mtrr_type(i);
- mtrr2protval[i] = mtrr2protval[fallback];
- BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
- }
- }
-}
-
static __init int svm_hardware_setup(void)
{
int cpu;
@@ -990,7 +932,6 @@
} else
kvm_disable_tdp();
- build_mtrr2protval();
return 0;
err:
@@ -1145,43 +1086,6 @@
return target_tsc - tsc;
}
-static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
-{
- struct kvm_vcpu *vcpu = &svm->vcpu;
-
- /* Unlike Intel, AMD takes the guest's CR0.CD into account.
- *
- * AMD does not have IPAT. To emulate it for the case of guests
- * with no assigned devices, just set everything to WB. If guests
- * have assigned devices, however, we cannot force WB for RAM
- * pages only, so use the guest PAT directly.
- */
- if (!kvm_arch_has_assigned_device(vcpu->kvm))
- *g_pat = 0x0606060606060606;
- else
- *g_pat = vcpu->arch.pat;
-}
-
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
- u8 mtrr;
-
- /*
- * 1. MMIO: trust guest MTRR, so same as item 3.
- * 2. No passthrough: always map as WB, and force guest PAT to WB as well
- * 3. Passthrough: can't guarantee the result, try to trust guest.
- */
- if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
- return 0;
-
- if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
- kvm_read_cr0(vcpu) & X86_CR0_CD)
- return _PAGE_NOCACHE;
-
- mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
- return mtrr2protval[mtrr];
-}
-
static void init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1278,7 +1182,6 @@
clr_cr_intercept(svm, INTERCEPT_CR3_READ);
clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
save->g_pat = svm->vcpu.arch.pat;
- svm_set_guest_pat(svm, &save->g_pat);
save->cr3 = 0;
save->cr4 = 0;
}
@@ -1673,10 +1576,13 @@
if (!vcpu->fpu_active)
cr0 |= X86_CR0_TS;
-
- /* These are emulated via page tables. */
- cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
-
+ /*
+ * re-enable caching here because the QEMU bios
+ * does not do it - this results in some delay at
+ * reboot
+ */
+ if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
mark_dirty(svm->vmcb, VMCB_CR);
update_cr0_intercept(svm);
@@ -3351,16 +3257,6 @@
case MSR_VM_IGNNE:
vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
- case MSR_IA32_CR_PAT:
- if (npt_enabled) {
- if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
- return 1;
- vcpu->arch.pat = data;
- svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
- mark_dirty(svm->vmcb, VMCB_NPT);
- break;
- }
- /* fall through */
default:
return kvm_set_msr_common(vcpu, msr);
}
@@ -4195,6 +4091,11 @@
return true;
}
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+ return 0;
+}
+
static void svm_cpuid_update(struct kvm_vcpu *vcpu)
{
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6407674..06ef490 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8617,17 +8617,22 @@
u64 ipat = 0;
/* For VT-d and EPT combination
- * 1. MMIO: guest may want to apply WC, trust it.
+ * 1. MMIO: always map as UC
* 2. EPT with VT-d:
* a. VT-d without snooping control feature: can't guarantee the
- * result, try to trust guest. So the same as item 1.
+ * result, try to trust guest.
* b. VT-d with snooping control feature: snooping control feature of
* VT-d engine can guarantee the cache correctness. Just set it
* to WB to keep consistent with host. So the same as item 3.
* 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
* consistent with host MTRR
*/
- if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+ if (is_mmio) {
+ cache = MTRR_TYPE_UNCACHABLE;
+ goto exit;
+ }
+
+ if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
ipat = VMX_EPT_IPAT_BIT;
cache = MTRR_TYPE_WRBACK;
goto exit;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 991466b..92511d4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1708,8 +1708,6 @@
vcpu->pvclock_set_guest_stopped_request = false;
}
- pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
-
/* If the host uses TSC clocksource, then it is stable */
if (use_master_clock)
pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -2007,8 +2005,6 @@
&vcpu->requests);
ka->boot_vcpu_runs_old_kvmclock = tmp;
-
- ka->kvmclock_offset = -get_kernel_ns();
}
vcpu->arch.time = data;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 30564e2..df48430 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1132,7 +1132,7 @@
* has been zapped already via cleanup_highmem().
*/
all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
- set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
+ set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
rodata_test();
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1db84c0..6a28ded 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -705,6 +705,70 @@
}
/*
+ * Iterate the EFI memory map in reverse order because the regions
+ * will be mapped top-down. The end result is the same as if we had
+ * mapped things forward, but doesn't require us to change the
+ * existing implementation of efi_map_region().
+ */
+static inline void *efi_map_next_entry_reverse(void *entry)
+{
+ /* Initial call */
+ if (!entry)
+ return memmap.map_end - memmap.desc_size;
+
+ entry -= memmap.desc_size;
+ if (entry < memmap.map)
+ return NULL;
+
+ return entry;
+}
+
+/*
+ * efi_map_next_entry - Return the next EFI memory map descriptor
+ * @entry: Previous EFI memory map descriptor
+ *
+ * This is a helper function to iterate over the EFI memory map, which
+ * we do in different orders depending on the current configuration.
+ *
+ * To begin traversing the memory map @entry must be %NULL.
+ *
+ * Returns %NULL when we reach the end of the memory map.
+ */
+static void *efi_map_next_entry(void *entry)
+{
+ if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) {
+ /*
+ * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE
+ * config table feature requires us to map all entries
+ * in the same order as they appear in the EFI memory
+ * map. That is to say, entry N must have a lower
+ * virtual address than entry N+1. This is because the
+ * firmware toolchain leaves relative references in
+ * the code/data sections, which are split and become
+ * separate EFI memory regions. Mapping things
+ * out-of-order leads to the firmware accessing
+ * unmapped addresses.
+ *
+ * Since we need to map things this way whether or not
+ * the kernel actually makes use of
+ * EFI_PROPERTIES_TABLE, let's just switch to this
+ * scheme by default for 64-bit.
+ */
+ return efi_map_next_entry_reverse(entry);
+ }
+
+ /* Initial call */
+ if (!entry)
+ return memmap.map;
+
+ entry += memmap.desc_size;
+ if (entry >= memmap.map_end)
+ return NULL;
+
+ return entry;
+}
+
+/*
* Map the efi memory ranges of the runtime services and update new_mmap with
* virtual addresses.
*/
@@ -714,7 +778,8 @@
unsigned long left = 0;
efi_memory_desc_t *md;
- for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+ p = NULL;
+ while ((p = efi_map_next_entry(p))) {
md = p;
if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
#ifdef CONFIG_X86_64
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 63c223d..b56855a 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -28,4 +28,5 @@
generic-y += termios.h
generic-y += topology.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
generic-y += xor.h
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 1e28ddb..8764c24 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -31,7 +31,8 @@
return cpu;
}
-int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
+int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
+ const struct cpumask *online_mask)
{
unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
cpumask_var_t cpus;
@@ -41,7 +42,7 @@
cpumask_clear(cpus);
nr_cpus = nr_uniq_cpus = 0;
- for_each_online_cpu(i) {
+ for_each_cpu(i, online_mask) {
nr_cpus++;
first_sibling = get_first_sibling(i);
if (!cpumask_test_cpu(first_sibling, cpus))
@@ -51,7 +52,7 @@
queue = 0;
for_each_possible_cpu(i) {
- if (!cpu_online(i)) {
+ if (!cpumask_test_cpu(i, online_mask)) {
map[i] = 0;
continue;
}
@@ -95,7 +96,7 @@
if (!map)
return NULL;
- if (!blk_mq_update_queue_map(map, set->nr_hw_queues))
+ if (!blk_mq_update_queue_map(map, set->nr_hw_queues, cpu_online_mask))
return map;
kfree(map);
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 279c5d6..788fffd 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -229,8 +229,6 @@
unsigned int i, first = 1;
ssize_t ret = 0;
- blk_mq_disable_hotplug();
-
for_each_cpu(i, hctx->cpumask) {
if (first)
ret += sprintf(ret + page, "%u", i);
@@ -240,8 +238,6 @@
first = 0;
}
- blk_mq_enable_hotplug();
-
ret += sprintf(ret + page, "\n");
return ret;
}
@@ -343,7 +339,7 @@
struct blk_mq_ctx *ctx;
int i;
- if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
+ if (!hctx->nr_ctx)
return;
hctx_for_each_ctx(hctx, ctx, i)
@@ -358,7 +354,7 @@
struct blk_mq_ctx *ctx;
int i, ret;
- if (!hctx->nr_ctx || !(hctx->flags & BLK_MQ_F_SYSFS_UP))
+ if (!hctx->nr_ctx)
return 0;
ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num);
@@ -381,6 +377,8 @@
struct blk_mq_ctx *ctx;
int i, j;
+ blk_mq_disable_hotplug();
+
queue_for_each_hw_ctx(q, hctx, i) {
blk_mq_unregister_hctx(hctx);
@@ -395,6 +393,9 @@
kobject_put(&q->mq_kobj);
kobject_put(&disk_to_dev(disk)->kobj);
+
+ q->mq_sysfs_init_done = false;
+ blk_mq_enable_hotplug();
}
static void blk_mq_sysfs_init(struct request_queue *q)
@@ -425,27 +426,30 @@
struct blk_mq_hw_ctx *hctx;
int ret, i;
+ blk_mq_disable_hotplug();
+
blk_mq_sysfs_init(q);
ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
- return ret;
+ goto out;
kobject_uevent(&q->mq_kobj, KOBJ_ADD);
queue_for_each_hw_ctx(q, hctx, i) {
- hctx->flags |= BLK_MQ_F_SYSFS_UP;
ret = blk_mq_register_hctx(hctx);
if (ret)
break;
}
- if (ret) {
+ if (ret)
blk_mq_unregister_disk(disk);
- return ret;
- }
+ else
+ q->mq_sysfs_init_done = true;
+out:
+ blk_mq_enable_hotplug();
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(blk_mq_register_disk);
@@ -454,6 +458,9 @@
struct blk_mq_hw_ctx *hctx;
int i;
+ if (!q->mq_sysfs_init_done)
+ return;
+
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
}
@@ -463,6 +470,9 @@
struct blk_mq_hw_ctx *hctx;
int i, ret = 0;
+ if (!q->mq_sysfs_init_done)
+ return ret;
+
queue_for_each_hw_ctx(q, hctx, i) {
ret = blk_mq_register_hctx(hctx);
if (ret)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 9115c6d..ed96474 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -471,17 +471,30 @@
}
EXPORT_SYMBOL(blk_mq_all_tag_busy_iter);
-void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
void *priv)
{
- struct blk_mq_tags *tags = hctx->tags;
+ struct blk_mq_hw_ctx *hctx;
+ int i;
- if (tags->nr_reserved_tags)
- bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
- bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
- false);
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ struct blk_mq_tags *tags = hctx->tags;
+
+ /*
+ * If not software queues are currently mapped to this
+ * hardware queue, there's nothing to check
+ */
+ if (!blk_mq_hw_queue_mapped(hctx))
+ continue;
+
+ if (tags->nr_reserved_tags)
+ bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
+ bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
+ false);
+ }
+
}
-EXPORT_SYMBOL(blk_mq_tag_busy_iter);
static unsigned int bt_unused_tags(struct blk_mq_bitmap_tags *bt)
{
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 9eb2cf4..d468a79 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -58,6 +58,8 @@
extern void blk_mq_tag_init_last_tag(struct blk_mq_tags *tags, unsigned int *last_tag);
extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
+ void *priv);
enum {
BLK_MQ_TAG_CACHE_MIN = 1,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f2d67b4..7785ae96 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -393,14 +393,16 @@
* Ends all I/O on a request. It does not handle partial completions.
* The actual completion happens out-of-order, through a IPI handler.
**/
-void blk_mq_complete_request(struct request *rq)
+void blk_mq_complete_request(struct request *rq, int error)
{
struct request_queue *q = rq->q;
if (unlikely(blk_should_fake_timeout(q)))
return;
- if (!blk_mark_rq_complete(rq))
+ if (!blk_mark_rq_complete(rq)) {
+ rq->errors = error;
__blk_mq_complete_request(rq);
+ }
}
EXPORT_SYMBOL(blk_mq_complete_request);
@@ -616,10 +618,8 @@
* If a request wasn't started before the queue was
* marked dying, kill it here or it'll go unnoticed.
*/
- if (unlikely(blk_queue_dying(rq->q))) {
- rq->errors = -EIO;
- blk_mq_complete_request(rq);
- }
+ if (unlikely(blk_queue_dying(rq->q)))
+ blk_mq_complete_request(rq, -EIO);
return;
}
if (rq->cmd_flags & REQ_NO_TIMEOUT)
@@ -641,24 +641,16 @@
.next = 0,
.next_set = 0,
};
- struct blk_mq_hw_ctx *hctx;
int i;
- queue_for_each_hw_ctx(q, hctx, i) {
- /*
- * If not software queues are currently mapped to this
- * hardware queue, there's nothing to check
- */
- if (!blk_mq_hw_queue_mapped(hctx))
- continue;
-
- blk_mq_tag_busy_iter(hctx, blk_mq_check_expired, &data);
- }
+ blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data);
if (data.next_set) {
data.next = blk_rq_timeout(round_jiffies_up(data.next));
mod_timer(&q->timeout, data.next);
} else {
+ struct blk_mq_hw_ctx *hctx;
+
queue_for_each_hw_ctx(q, hctx, i) {
/* the hctx may be unmapped, so check it here */
if (blk_mq_hw_queue_mapped(hctx))
@@ -1789,13 +1781,19 @@
}
}
-static void blk_mq_map_swqueue(struct request_queue *q)
+static void blk_mq_map_swqueue(struct request_queue *q,
+ const struct cpumask *online_mask)
{
unsigned int i;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
+ /*
+ * Avoid others reading imcomplete hctx->cpumask through sysfs
+ */
+ mutex_lock(&q->sysfs_lock);
+
queue_for_each_hw_ctx(q, hctx, i) {
cpumask_clear(hctx->cpumask);
hctx->nr_ctx = 0;
@@ -1806,16 +1804,17 @@
*/
queue_for_each_ctx(q, ctx, i) {
/* If the cpu isn't online, the cpu is mapped to first hctx */
- if (!cpu_online(i))
+ if (!cpumask_test_cpu(i, online_mask))
continue;
hctx = q->mq_ops->map_queue(q, i);
cpumask_set_cpu(i, hctx->cpumask);
- cpumask_set_cpu(i, hctx->tags->cpumask);
ctx->index_hw = hctx->nr_ctx;
hctx->ctxs[hctx->nr_ctx++] = ctx;
}
+ mutex_unlock(&q->sysfs_lock);
+
queue_for_each_hw_ctx(q, hctx, i) {
struct blk_mq_ctxmap *map = &hctx->ctx_map;
@@ -1851,6 +1850,14 @@
hctx->next_cpu = cpumask_first(hctx->cpumask);
hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
}
+
+ queue_for_each_ctx(q, ctx, i) {
+ if (!cpumask_test_cpu(i, online_mask))
+ continue;
+
+ hctx = q->mq_ops->map_queue(q, i);
+ cpumask_set_cpu(i, hctx->tags->cpumask);
+ }
}
static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set)
@@ -1918,6 +1925,9 @@
kfree(hctx);
}
+ kfree(q->mq_map);
+ q->mq_map = NULL;
+
kfree(q->queue_hw_ctx);
/* ctx kobj stays in queue_ctx */
@@ -2027,13 +2037,15 @@
if (blk_mq_init_hw_queues(q, set))
goto err_hctxs;
+ get_online_cpus();
mutex_lock(&all_q_mutex);
+
list_add_tail(&q->all_q_node, &all_q_list);
- mutex_unlock(&all_q_mutex);
-
blk_mq_add_queue_tag_set(set, q);
+ blk_mq_map_swqueue(q, cpu_online_mask);
- blk_mq_map_swqueue(q);
+ mutex_unlock(&all_q_mutex);
+ put_online_cpus();
return q;
@@ -2057,30 +2069,27 @@
{
struct blk_mq_tag_set *set = q->tag_set;
+ mutex_lock(&all_q_mutex);
+ list_del_init(&q->all_q_node);
+ mutex_unlock(&all_q_mutex);
+
blk_mq_del_queue_tag_set(q);
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
blk_mq_free_hw_queues(q, set);
percpu_ref_exit(&q->mq_usage_counter);
-
- kfree(q->mq_map);
-
- q->mq_map = NULL;
-
- mutex_lock(&all_q_mutex);
- list_del_init(&q->all_q_node);
- mutex_unlock(&all_q_mutex);
}
/* Basically redo blk_mq_init_queue with queue frozen */
-static void blk_mq_queue_reinit(struct request_queue *q)
+static void blk_mq_queue_reinit(struct request_queue *q,
+ const struct cpumask *online_mask)
{
WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
blk_mq_sysfs_unregister(q);
- blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues);
+ blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues, online_mask);
/*
* redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
@@ -2088,7 +2097,7 @@
* involves free and re-allocate memory, worthy doing?)
*/
- blk_mq_map_swqueue(q);
+ blk_mq_map_swqueue(q, online_mask);
blk_mq_sysfs_register(q);
}
@@ -2097,16 +2106,43 @@
unsigned long action, void *hcpu)
{
struct request_queue *q;
+ int cpu = (unsigned long)hcpu;
+ /*
+ * New online cpumask which is going to be set in this hotplug event.
+ * Declare this cpumasks as global as cpu-hotplug operation is invoked
+ * one-by-one and dynamically allocating this could result in a failure.
+ */
+ static struct cpumask online_new;
/*
- * Before new mappings are established, hotadded cpu might already
- * start handling requests. This doesn't break anything as we map
- * offline CPUs to first hardware queue. We will re-init the queue
- * below to get optimal settings.
+ * Before hotadded cpu starts handling requests, new mappings must
+ * be established. Otherwise, these requests in hw queue might
+ * never be dispatched.
+ *
+ * For example, there is a single hw queue (hctx) and two CPU queues
+ * (ctx0 for CPU0, and ctx1 for CPU1).
+ *
+ * Now CPU1 is just onlined and a request is inserted into
+ * ctx1->rq_list and set bit0 in pending bitmap as ctx1->index_hw is
+ * still zero.
+ *
+ * And then while running hw queue, flush_busy_ctxs() finds bit0 is
+ * set in pending bitmap and tries to retrieve requests in
+ * hctx->ctxs[0]->rq_list. But htx->ctxs[0] is a pointer to ctx0,
+ * so the request in ctx1->rq_list is ignored.
*/
- if (action != CPU_DEAD && action != CPU_DEAD_FROZEN &&
- action != CPU_ONLINE && action != CPU_ONLINE_FROZEN)
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ cpumask_copy(&online_new, cpu_online_mask);
+ break;
+ case CPU_UP_PREPARE:
+ cpumask_copy(&online_new, cpu_online_mask);
+ cpumask_set_cpu(cpu, &online_new);
+ break;
+ default:
return NOTIFY_OK;
+ }
mutex_lock(&all_q_mutex);
@@ -2130,7 +2166,7 @@
}
list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_queue_reinit(q);
+ blk_mq_queue_reinit(q, &online_new);
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_unfreeze_queue(q);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 6a48c4c..f4fea79 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -51,7 +51,8 @@
* CPU -> queue mappings
*/
extern unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set);
-extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues);
+extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues,
+ const struct cpumask *online_mask);
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
/*
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 6d88dd1..1970966 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -332,10 +332,6 @@
srlen = cert->raw_serial_size;
q = cert->raw_serial;
}
- if (srlen > 1 && *q == 0) {
- srlen--;
- q++;
- }
ret = -ENOMEM;
desc = kmalloc(sulen + 2 + srlen * 2 + 1, GFP_KERNEL);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 2614a83..42c66b6 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1044,8 +1044,10 @@
goto err_exit;
mutex_lock(&ec->mutex);
+ result = -ENODATA;
list_for_each_entry(handler, &ec->list, node) {
if (value == handler->query_bit) {
+ result = 0;
q->handler = acpi_ec_get_query_handler(handler);
ec_dbg_evt("Query(0x%02x) scheduled",
q->handler->query_bit);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 6da0f9b..c933675 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -372,6 +372,7 @@
/* Interrupt Line values above 0xF are forbidden */
if (dev->irq > 0 && (dev->irq <= 0xF) &&
+ acpi_isa_irq_available(dev->irq) &&
(acpi_isa_irq_to_gsi(dev->irq, &dev_gsi) == 0)) {
dev_warn(&dev->dev, "PCI INT %c: no GSI - using ISA IRQ %d\n",
pin_name(dev->pin), dev->irq);
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 3b4ea98..7c8408b 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -498,8 +498,7 @@
PIRQ_PENALTY_PCI_POSSIBLE;
}
}
- /* Add a penalty for the SCI */
- acpi_irq_penalty[acpi_gbl_FADT.sci_interrupt] += PIRQ_PENALTY_PCI_USING;
+
return 0;
}
@@ -553,6 +552,13 @@
irq = link->irq.possible[i];
}
}
+ if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) {
+ printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. "
+ "Try pci=noacpi or acpi=off\n",
+ acpi_device_name(link->device),
+ acpi_device_bid(link->device));
+ return -ENODEV;
+ }
/* Attempt to enable the link device at this IRQ. */
if (acpi_pci_link_set(link, irq)) {
@@ -821,6 +827,12 @@
}
}
+bool acpi_isa_irq_available(int irq)
+{
+ return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) ||
+ acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS);
+}
+
/*
* Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict with
* PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be use for
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 28cd75c..7ae7cd9 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -892,10 +892,17 @@
u32 microvolt[3] = {0};
int count, ret;
- count = of_property_count_u32_elems(opp->np, "opp-microvolt");
- if (!count)
+ /* Missing property isn't a problem, but an invalid entry is */
+ if (!of_find_property(opp->np, "opp-microvolt", NULL))
return 0;
+ count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+ if (count < 0) {
+ dev_err(dev, "%s: Invalid opp-microvolt property (%d)\n",
+ __func__, count);
+ return count;
+ }
+
/* There can be one or three elements here */
if (count != 1 && count != 3) {
dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
@@ -1063,7 +1070,7 @@
* share a common logic which is isolated here.
*
* Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
* successful.
*
* Locking: The internal device_opp and opp structures are RCU protected.
@@ -1151,7 +1158,7 @@
* mutex locking or synchronize_rcu() blocking calls cannot be used.
*
* Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
* successful.
*/
int dev_pm_opp_enable(struct device *dev, unsigned long freq)
@@ -1177,7 +1184,7 @@
* mutex locking or synchronize_rcu() blocking calls cannot be used.
*
* Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
* successful.
*/
int dev_pm_opp_disable(struct device *dev, unsigned long freq)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f9889b6..674f800 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1486,17 +1486,16 @@
{
const bool write = cmd->rq->cmd_flags & REQ_WRITE;
struct loop_device *lo = cmd->rq->q->queuedata;
- int ret = -EIO;
+ int ret = 0;
- if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY))
+ if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
+ ret = -EIO;
goto failed;
+ }
ret = do_req_filebacked(lo, cmd->rq);
-
failed:
- if (ret)
- cmd->rq->errors = -EIO;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
}
static void loop_queue_write_work(struct work_struct *work)
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index a295b98..1c9e4fe 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -289,7 +289,7 @@
case NULL_IRQ_SOFTIRQ:
switch (queue_mode) {
case NULL_Q_MQ:
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(cmd->rq, cmd->rq->errors);
break;
case NULL_Q_RQ:
blk_complete_request(cmd->rq);
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index b97fc3f..6f04771 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -618,16 +618,15 @@
spin_unlock_irqrestore(req->q->queue_lock, flags);
return;
}
+
if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
if (cmd_rq->ctx == CMD_CTX_CANCELLED)
- req->errors = -EINTR;
- else
- req->errors = status;
+ status = -EINTR;
} else {
- req->errors = nvme_error_status(status);
+ status = nvme_error_status(status);
}
- } else
- req->errors = 0;
+ }
+
if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
u32 result = le32_to_cpup(&cqe->result);
req->special = (void *)(uintptr_t)result;
@@ -650,7 +649,7 @@
}
nvme_free_iod(nvmeq->dev, iod);
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, status);
}
/* length is in bytes. gfp flags indicates whether we may sleep. */
@@ -863,8 +862,7 @@
if (ns && ns->ms && !blk_integrity_rq(req)) {
if (!(ns->pi_type && ns->ms == 8) &&
req->cmd_type != REQ_TYPE_DRV_PRIV) {
- req->errors = -EFAULT;
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, -EFAULT);
return BLK_MQ_RQ_QUEUE_OK;
}
}
@@ -2439,6 +2437,22 @@
list_sort(NULL, &dev->namespaces, ns_cmp);
}
+static void nvme_set_irq_hints(struct nvme_dev *dev)
+{
+ struct nvme_queue *nvmeq;
+ int i;
+
+ for (i = 0; i < dev->online_queues; i++) {
+ nvmeq = dev->queues[i];
+
+ if (!nvmeq->tags || !(*nvmeq->tags))
+ continue;
+
+ irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
+ blk_mq_tags_cpumask(*nvmeq->tags));
+ }
+}
+
static void nvme_dev_scan(struct work_struct *work)
{
struct nvme_dev *dev = container_of(work, struct nvme_dev, scan_work);
@@ -2450,6 +2464,7 @@
return;
nvme_scan_namespaces(dev, le32_to_cpup(&ctrl->nn));
kfree(ctrl);
+ nvme_set_irq_hints(dev);
}
/*
@@ -2953,22 +2968,6 @@
.compat_ioctl = nvme_dev_ioctl,
};
-static void nvme_set_irq_hints(struct nvme_dev *dev)
-{
- struct nvme_queue *nvmeq;
- int i;
-
- for (i = 0; i < dev->online_queues; i++) {
- nvmeq = dev->queues[i];
-
- if (!nvmeq->tags || !(*nvmeq->tags))
- continue;
-
- irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
- blk_mq_tags_cpumask(*nvmeq->tags));
- }
-}
-
static int nvme_dev_start(struct nvme_dev *dev)
{
int result;
@@ -3010,8 +3009,6 @@
if (result)
goto free_tags;
- nvme_set_irq_hints(dev);
-
dev->event_limit = 1;
return result;
@@ -3062,7 +3059,6 @@
} else {
nvme_unfreeze_queues(dev);
nvme_dev_add(dev);
- nvme_set_irq_hints(dev);
}
return 0;
}
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index e93899c..6ca35495 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -144,7 +144,7 @@
do {
virtqueue_disable_cb(vq);
while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
- blk_mq_complete_request(vbr->req);
+ blk_mq_complete_request(vbr->req, vbr->req->errors);
req_done = true;
}
if (unlikely(virtqueue_is_broken(vq)))
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index deb3f00..7676575 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -212,6 +212,9 @@
static int xen_blkif_disconnect(struct xen_blkif *blkif)
{
+ struct pending_req *req, *n;
+ int i = 0, j;
+
if (blkif->xenblkd) {
kthread_stop(blkif->xenblkd);
wake_up(&blkif->shutdown_wq);
@@ -238,25 +241,6 @@
/* Remove all persistent grants and the cache of ballooned pages. */
xen_blkbk_free_caches(blkif);
- return 0;
-}
-
-static void xen_blkif_free(struct xen_blkif *blkif)
-{
- struct pending_req *req, *n;
- int i = 0, j;
-
- xen_blkif_disconnect(blkif);
- xen_vbd_free(&blkif->vbd);
-
- /* Make sure everything is drained before shutting down */
- BUG_ON(blkif->persistent_gnt_c != 0);
- BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0);
- BUG_ON(blkif->free_pages_num != 0);
- BUG_ON(!list_empty(&blkif->persistent_purge_list));
- BUG_ON(!list_empty(&blkif->free_pages));
- BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
-
/* Check that there is no request in use */
list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
list_del(&req->free_list);
@@ -272,6 +256,24 @@
}
WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
+ blkif->nr_ring_pages = 0;
+
+ return 0;
+}
+
+static void xen_blkif_free(struct xen_blkif *blkif)
+{
+
+ xen_blkif_disconnect(blkif);
+ xen_vbd_free(&blkif->vbd);
+
+ /* Make sure everything is drained before shutting down */
+ BUG_ON(blkif->persistent_gnt_c != 0);
+ BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0);
+ BUG_ON(blkif->free_pages_num != 0);
+ BUG_ON(!list_empty(&blkif->persistent_purge_list));
+ BUG_ON(!list_empty(&blkif->free_pages));
+ BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
kmem_cache_free(xen_blkif_cachep, blkif);
}
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 0823a96..6111708 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1142,6 +1142,7 @@
RING_IDX i, rp;
unsigned long flags;
struct blkfront_info *info = (struct blkfront_info *)dev_id;
+ int error;
spin_lock_irqsave(&info->io_lock, flags);
@@ -1182,37 +1183,37 @@
continue;
}
- req->errors = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+ error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
switch (bret->operation) {
case BLKIF_OP_DISCARD:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
struct request_queue *rq = info->rq;
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- req->errors = -EOPNOTSUPP;
+ error = -EOPNOTSUPP;
info->feature_discard = 0;
info->feature_secdiscard = 0;
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
}
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, error);
break;
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- req->errors = -EOPNOTSUPP;
+ error = -EOPNOTSUPP;
}
if (unlikely(bret->status == BLKIF_RSP_ERROR &&
info->shadow[id].req.u.rw.nr_segments == 0)) {
printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- req->errors = -EOPNOTSUPP;
+ error = -EOPNOTSUPP;
}
- if (unlikely(req->errors)) {
- if (req->errors == -EOPNOTSUPP)
- req->errors = 0;
+ if (unlikely(error)) {
+ if (error == -EOPNOTSUPP)
+ error = 0;
info->feature_flush = 0;
xlvbd_flush(info);
}
@@ -1223,7 +1224,7 @@
dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
"request: %x\n", bret->status);
- blk_mq_complete_request(req);
+ blk_mq_complete_request(req, error);
break;
default:
BUG();
diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c
index bb2c2b0..d3c1742 100644
--- a/drivers/clocksource/rockchip_timer.c
+++ b/drivers/clocksource/rockchip_timer.c
@@ -148,7 +148,7 @@
bc_timer.freq = clk_get_rate(timer_clk);
irq = irq_of_parse_and_map(np, 0);
- if (irq == NO_IRQ) {
+ if (!irq) {
pr_err("Failed to map interrupts for '%s'\n", TIMER_NAME);
return;
}
diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c
index edacf39..1cea08c 100644
--- a/drivers/clocksource/timer-keystone.c
+++ b/drivers/clocksource/timer-keystone.c
@@ -152,7 +152,7 @@
int irq, error;
irq = irq_of_parse_and_map(np, 0);
- if (irq == NO_IRQ) {
+ if (!irq) {
pr_err("%s: failed to map interrupts\n", __func__);
return;
}
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index a165b4b..dd24375 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -455,6 +455,15 @@
return desc;
}
+void at_xdmac_init_used_desc(struct at_xdmac_desc *desc)
+{
+ memset(&desc->lld, 0, sizeof(desc->lld));
+ INIT_LIST_HEAD(&desc->descs_list);
+ desc->direction = DMA_TRANS_NONE;
+ desc->xfer_size = 0;
+ desc->active_xfer = false;
+}
+
/* Call must be protected by lock. */
static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
{
@@ -466,7 +475,7 @@
desc = list_first_entry(&atchan->free_descs_list,
struct at_xdmac_desc, desc_node);
list_del(&desc->desc_node);
- desc->active_xfer = false;
+ at_xdmac_init_used_desc(desc);
}
return desc;
@@ -875,14 +884,14 @@
if (xt->src_inc) {
if (xt->src_sgl)
- chan_cc |= AT_XDMAC_CC_SAM_UBS_DS_AM;
+ chan_cc |= AT_XDMAC_CC_SAM_UBS_AM;
else
chan_cc |= AT_XDMAC_CC_SAM_INCREMENTED_AM;
}
if (xt->dst_inc) {
if (xt->dst_sgl)
- chan_cc |= AT_XDMAC_CC_DAM_UBS_DS_AM;
+ chan_cc |= AT_XDMAC_CC_DAM_UBS_AM;
else
chan_cc |= AT_XDMAC_CC_DAM_INCREMENTED_AM;
}
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 3ff284c..09479d4 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -554,10 +554,18 @@
mutex_lock(&dma_list_mutex);
if (chan->client_count == 0) {
+ struct dma_device *device = chan->device;
+
+ dma_cap_set(DMA_PRIVATE, device->cap_mask);
+ device->privatecnt++;
err = dma_chan_get(chan);
- if (err)
+ if (err) {
pr_debug("%s: failed to get %s: (%d)\n",
__func__, dma_chan_name(chan), err);
+ chan = NULL;
+ if (--device->privatecnt == 0)
+ dma_cap_clear(DMA_PRIVATE, device->cap_mask);
+ }
} else
chan = NULL;
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index cf1c87f..bedce03 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1591,7 +1591,6 @@
INIT_LIST_HEAD(&dw->dma.channels);
for (i = 0; i < nr_channels; i++) {
struct dw_dma_chan *dwc = &dw->chan[i];
- int r = nr_channels - i - 1;
dwc->chan.device = &dw->dma;
dma_cookie_init(&dwc->chan);
@@ -1603,7 +1602,7 @@
/* 7 is highest priority & 0 is lowest. */
if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
- dwc->priority = r;
+ dwc->priority = nr_channels - i - 1;
else
dwc->priority = i;
@@ -1622,6 +1621,7 @@
/* Hardware configuration */
if (autocfg) {
unsigned int dwc_params;
+ unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1;
void __iomem *addr = chip->regs + r * sizeof(u32);
dwc_params = dma_read_byaddr(addr, DWC_PARAMS);
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 18c14e1..48d6d9e 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -355,23 +355,23 @@
struct idma64_desc *desc = idma64c->desc;
struct idma64_hw_desc *hw;
size_t bytes = desc->length;
- u64 llp;
- u32 ctlhi;
+ u64 llp = channel_readq(idma64c, LLP);
+ u32 ctlhi = channel_readl(idma64c, CTL_HI);
unsigned int i = 0;
- llp = channel_readq(idma64c, LLP);
do {
hw = &desc->hw[i];
- } while ((hw->llp != llp) && (++i < desc->ndesc));
+ if (hw->llp == llp)
+ break;
+ bytes -= hw->len;
+ } while (++i < desc->ndesc);
if (!i)
return bytes;
- do {
- bytes -= desc->hw[--i].len;
- } while (i);
+ /* The current chunk is not fully transfered yet */
+ bytes += desc->hw[--i].len;
- ctlhi = channel_readl(idma64c, CTL_HI);
return bytes - IDMA64C_CTLH_BLOCK_TS(ctlhi);
}
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index 5cb61ce..fc4156a 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -473,8 +473,10 @@
return;
/* clear the channel mapping in DRCMR */
- reg = pxad_drcmr(chan->drcmr);
- writel_relaxed(0, chan->phy->base + reg);
+ if (chan->drcmr <= DRCMR_CHLNUM) {
+ reg = pxad_drcmr(chan->drcmr);
+ writel_relaxed(0, chan->phy->base + reg);
+ }
spin_lock_irqsave(&pdev->phy_lock, flags);
for (i = 0; i < 32; i++)
@@ -516,8 +518,10 @@
"%s(); phy=%p(%d) misaligned=%d\n", __func__,
phy, phy->idx, misaligned);
- reg = pxad_drcmr(phy->vchan->drcmr);
- writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
+ if (phy->vchan->drcmr <= DRCMR_CHLNUM) {
+ reg = pxad_drcmr(phy->vchan->drcmr);
+ writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
+ }
dalgn = phy_readl_relaxed(phy, DALGN);
if (misaligned)
@@ -887,6 +891,7 @@
struct dma_async_tx_descriptor *tx;
struct pxad_chan *chan = container_of(vc, struct pxad_chan, vc);
+ INIT_LIST_HEAD(&vd->node);
tx = vchan_tx_prep(vc, vd, tx_flags);
tx->tx_submit = pxad_tx_submit;
dev_dbg(&chan->vc.chan.dev->device,
@@ -910,14 +915,18 @@
width = chan->cfg.src_addr_width;
dev_addr = chan->cfg.src_addr;
*dev_src = dev_addr;
- *dcmd |= PXA_DCMD_INCTRGADDR | PXA_DCMD_FLOWSRC;
+ *dcmd |= PXA_DCMD_INCTRGADDR;
+ if (chan->drcmr <= DRCMR_CHLNUM)
+ *dcmd |= PXA_DCMD_FLOWSRC;
}
if (dir == DMA_MEM_TO_DEV) {
maxburst = chan->cfg.dst_maxburst;
width = chan->cfg.dst_addr_width;
dev_addr = chan->cfg.dst_addr;
*dev_dst = dev_addr;
- *dcmd |= PXA_DCMD_INCSRCADDR | PXA_DCMD_FLOWTRG;
+ *dcmd |= PXA_DCMD_INCSRCADDR;
+ if (chan->drcmr <= DRCMR_CHLNUM)
+ *dcmd |= PXA_DCMD_FLOWTRG;
}
if (dir == DMA_MEM_TO_MEM)
*dcmd |= PXA_DCMD_BURST32 | PXA_DCMD_INCTRGADDR |
@@ -1177,6 +1186,16 @@
else
curr = phy_readl_relaxed(chan->phy, DTADR);
+ /*
+ * curr has to be actually read before checking descriptor
+ * completion, so that a curr inside a status updater
+ * descriptor implies the following test returns true, and
+ * preventing reordering of curr load and the test.
+ */
+ rmb();
+ if (is_desc_completed(vd))
+ goto out;
+
for (i = 0; i < sw_desc->nb_desc - 1; i++) {
hw_desc = sw_desc->hw_desc[i];
if (sw_desc->hw_desc[0]->dcmd & PXA_DCMD_INCSRCADDR)
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index a1a500d..1661d518 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -599,13 +599,13 @@
static void sun4i_dma_free_contract(struct virt_dma_desc *vd)
{
struct sun4i_dma_contract *contract = to_sun4i_dma_contract(vd);
- struct sun4i_dma_promise *promise;
+ struct sun4i_dma_promise *promise, *tmp;
/* Free all the demands and completed demands */
- list_for_each_entry(promise, &contract->demands, list)
+ list_for_each_entry_safe(promise, tmp, &contract->demands, list)
kfree(promise);
- list_for_each_entry(promise, &contract->completed_demands, list)
+ list_for_each_entry_safe(promise, tmp, &contract->completed_demands, list)
kfree(promise);
kfree(contract);
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index b23e8d5..8d57b1b 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -59,7 +59,6 @@
#define XGENE_DMA_RING_MEM_RAM_SHUTDOWN 0xD070
#define XGENE_DMA_RING_BLK_MEM_RDY 0xD074
#define XGENE_DMA_RING_BLK_MEM_RDY_VAL 0xFFFFFFFF
-#define XGENE_DMA_RING_DESC_CNT(v) (((v) & 0x0001FFFE) >> 1)
#define XGENE_DMA_RING_ID_GET(owner, num) (((owner) << 6) | (num))
#define XGENE_DMA_RING_DST_ID(v) ((1 << 10) | (v))
#define XGENE_DMA_RING_CMD_OFFSET 0x2C
@@ -379,14 +378,6 @@
return flyby_type[src_cnt];
}
-static u32 xgene_dma_ring_desc_cnt(struct xgene_dma_ring *ring)
-{
- u32 __iomem *cmd_base = ring->cmd_base;
- u32 ring_state = ioread32(&cmd_base[1]);
-
- return XGENE_DMA_RING_DESC_CNT(ring_state);
-}
-
static void xgene_dma_set_src_buffer(__le64 *ext8, size_t *len,
dma_addr_t *paddr)
{
@@ -659,15 +650,12 @@
dma_pool_free(chan->desc_pool, desc, desc->tx.phys);
}
-static int xgene_chan_xfer_request(struct xgene_dma_ring *ring,
- struct xgene_dma_desc_sw *desc_sw)
+static void xgene_chan_xfer_request(struct xgene_dma_chan *chan,
+ struct xgene_dma_desc_sw *desc_sw)
{
+ struct xgene_dma_ring *ring = &chan->tx_ring;
struct xgene_dma_desc_hw *desc_hw;
- /* Check if can push more descriptor to hw for execution */
- if (xgene_dma_ring_desc_cnt(ring) > (ring->slots - 2))
- return -EBUSY;
-
/* Get hw descriptor from DMA tx ring */
desc_hw = &ring->desc_hw[ring->head];
@@ -694,11 +682,13 @@
memcpy(desc_hw, &desc_sw->desc2, sizeof(*desc_hw));
}
+ /* Increment the pending transaction count */
+ chan->pending += ((desc_sw->flags &
+ XGENE_DMA_FLAG_64B_DESC) ? 2 : 1);
+
/* Notify the hw that we have descriptor ready for execution */
iowrite32((desc_sw->flags & XGENE_DMA_FLAG_64B_DESC) ?
2 : 1, ring->cmd);
-
- return 0;
}
/**
@@ -710,7 +700,6 @@
static void xgene_chan_xfer_ld_pending(struct xgene_dma_chan *chan)
{
struct xgene_dma_desc_sw *desc_sw, *_desc_sw;
- int ret;
/*
* If the list of pending descriptors is empty, then we
@@ -735,18 +724,13 @@
if (chan->pending >= chan->max_outstanding)
return;
- ret = xgene_chan_xfer_request(&chan->tx_ring, desc_sw);
- if (ret)
- return;
+ xgene_chan_xfer_request(chan, desc_sw);
/*
* Delete this element from ld pending queue and append it to
* ld running queue
*/
list_move_tail(&desc_sw->node, &chan->ld_running);
-
- /* Increment the pending transaction count */
- chan->pending++;
}
}
@@ -821,7 +805,8 @@
* Decrement the pending transaction count
* as we have processed one
*/
- chan->pending--;
+ chan->pending -= ((desc_sw->flags &
+ XGENE_DMA_FLAG_64B_DESC) ? 2 : 1);
/*
* Delete this node from ld running queue and append it to
@@ -1421,15 +1406,18 @@
struct xgene_dma_ring *ring,
enum xgene_dma_ring_cfgsize cfgsize)
{
+ int ret;
+
/* Setup DMA ring descriptor variables */
ring->pdma = chan->pdma;
ring->cfgsize = cfgsize;
ring->num = chan->pdma->ring_num++;
ring->id = XGENE_DMA_RING_ID_GET(ring->owner, ring->buf_num);
- ring->size = xgene_dma_get_ring_size(chan, cfgsize);
- if (ring->size <= 0)
- return ring->size;
+ ret = xgene_dma_get_ring_size(chan, cfgsize);
+ if (ret <= 0)
+ return ret;
+ ring->size = ret;
/* Allocate memory for DMA ring descriptor */
ring->desc_vaddr = dma_zalloc_coherent(chan->dev, ring->size,
@@ -1482,7 +1470,7 @@
tx_ring->id, tx_ring->num, tx_ring->desc_vaddr);
/* Set the max outstanding request possible to this channel */
- chan->max_outstanding = rx_ring->slots;
+ chan->max_outstanding = tx_ring->slots;
return ret;
}
diff --git a/drivers/dma/zx296702_dma.c b/drivers/dma/zx296702_dma.c
index 39915a6..c017fcd 100644
--- a/drivers/dma/zx296702_dma.c
+++ b/drivers/dma/zx296702_dma.c
@@ -739,7 +739,7 @@
struct dma_chan *chan;
struct zx_dma_chan *c;
- if (request > d->dma_requests)
+ if (request >= d->dma_requests)
return NULL;
chan = dma_get_any_slave_channel(&d->slave);
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 6fd3da9..413fcf2 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -1,6 +1,14 @@
#
# Makefile for linux kernel
#
+
+#
+# ARM64 maps efi runtime services in userspace addresses
+# which don't have KASAN shadow. So dereference of these addresses
+# in efi_call_virt() will cause crash if this code instrumented.
+#
+KASAN_SANITIZE_runtime-wrappers.o := n
+
obj-$(CONFIG_EFI) += efi.o vars.o reboot.o
obj-$(CONFIG_EFI_VARS) += efivars.o
obj-$(CONFIG_EFI_ESRT) += esrt.o
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 816dbe9..bca9a76c 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -14,6 +14,8 @@
cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \
-fno-builtin -fpic -mno-single-pic-base
+cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt
+
KBUILD_CFLAGS := $(cflags-y) \
$(call cc-option,-ffreestanding) \
$(call cc-option,-fno-stack-protector)
@@ -22,7 +24,15 @@
KASAN_SANITIZE := n
lib-y := efi-stub-helper.o
-lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o
+
+# include the stub's generic dependencies from lib/ when building for ARM/arm64
+arm-deps := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c sort.c
+
+$(obj)/lib-%.o: $(srctree)/lib/%.c FORCE
+ $(call if_changed_rule,cc_o_c)
+
+lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o string.o \
+ $(patsubst %.c,lib-%.o,$(arm-deps))
#
# arm64 puts the stub in the kernel proper, which will unnecessarily retain all
@@ -30,10 +40,27 @@
# So let's apply the __init annotations at the section level, by prefixing
# the section names directly. This will ensure that even all the inline string
# literals are covered.
+# The fact that the stub and the kernel proper are essentially the same binary
+# also means that we need to be extra careful to make sure that the stub does
+# not rely on any absolute symbol references, considering that the virtual
+# kernel mapping that the linker uses is not active yet when the stub is
+# executing. So build all C dependencies of the EFI stub into libstub, and do
+# a verification pass to see if any absolute relocations exist in any of the
+# object files.
#
-extra-$(CONFIG_ARM64) := $(lib-y)
-lib-$(CONFIG_ARM64) := $(patsubst %.o,%.init.o,$(lib-y))
+extra-$(CONFIG_EFI_ARMSTUB) := $(lib-y)
+lib-$(CONFIG_EFI_ARMSTUB) := $(patsubst %.o,%.stub.o,$(lib-y))
-OBJCOPYFLAGS := --prefix-alloc-sections=.init
-$(obj)/%.init.o: $(obj)/%.o FORCE
- $(call if_changed,objcopy)
+STUBCOPY_FLAGS-y := -R .debug* -R *ksymtab*
+STUBCOPY_FLAGS-$(CONFIG_ARM64) += --prefix-alloc-sections=.init \
+ --prefix-symbols=__efistub_
+STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS
+
+$(obj)/%.stub.o: $(obj)/%.o FORCE
+ $(call if_changed,stubcopy)
+
+quiet_cmd_stubcopy = STUBCPY $@
+ cmd_stubcopy = if $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; then \
+ $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y) \
+ && (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
+ rm -f $@; /bin/false); else /bin/false; fi
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index e29560e..950c87f 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -13,6 +13,7 @@
*/
#include <linux/efi.h>
+#include <linux/sort.h>
#include <asm/efi.h>
#include "efistub.h"
@@ -305,6 +306,44 @@
*/
#define EFI_RT_VIRTUAL_BASE 0x40000000
+static int cmp_mem_desc(const void *l, const void *r)
+{
+ const efi_memory_desc_t *left = l, *right = r;
+
+ return (left->phys_addr > right->phys_addr) ? 1 : -1;
+}
+
+/*
+ * Returns whether region @left ends exactly where region @right starts,
+ * or false if either argument is NULL.
+ */
+static bool regions_are_adjacent(efi_memory_desc_t *left,
+ efi_memory_desc_t *right)
+{
+ u64 left_end;
+
+ if (left == NULL || right == NULL)
+ return false;
+
+ left_end = left->phys_addr + left->num_pages * EFI_PAGE_SIZE;
+
+ return left_end == right->phys_addr;
+}
+
+/*
+ * Returns whether region @left and region @right have compatible memory type
+ * mapping attributes, and are both EFI_MEMORY_RUNTIME regions.
+ */
+static bool regions_have_compatible_memory_type_attrs(efi_memory_desc_t *left,
+ efi_memory_desc_t *right)
+{
+ static const u64 mem_type_mask = EFI_MEMORY_WB | EFI_MEMORY_WT |
+ EFI_MEMORY_WC | EFI_MEMORY_UC |
+ EFI_MEMORY_RUNTIME;
+
+ return ((left->attribute ^ right->attribute) & mem_type_mask) == 0;
+}
+
/*
* efi_get_virtmap() - create a virtual mapping for the EFI memory map
*
@@ -317,33 +356,52 @@
int *count)
{
u64 efi_virt_base = EFI_RT_VIRTUAL_BASE;
- efi_memory_desc_t *out = runtime_map;
+ efi_memory_desc_t *in, *prev = NULL, *out = runtime_map;
int l;
- for (l = 0; l < map_size; l += desc_size) {
- efi_memory_desc_t *in = (void *)memory_map + l;
+ /*
+ * To work around potential issues with the Properties Table feature
+ * introduced in UEFI 2.5, which may split PE/COFF executable images
+ * in memory into several RuntimeServicesCode and RuntimeServicesData
+ * regions, we need to preserve the relative offsets between adjacent
+ * EFI_MEMORY_RUNTIME regions with the same memory type attributes.
+ * The easiest way to find adjacent regions is to sort the memory map
+ * before traversing it.
+ */
+ sort(memory_map, map_size / desc_size, desc_size, cmp_mem_desc, NULL);
+
+ for (l = 0; l < map_size; l += desc_size, prev = in) {
u64 paddr, size;
+ in = (void *)memory_map + l;
if (!(in->attribute & EFI_MEMORY_RUNTIME))
continue;
+ paddr = in->phys_addr;
+ size = in->num_pages * EFI_PAGE_SIZE;
+
/*
* Make the mapping compatible with 64k pages: this allows
* a 4k page size kernel to kexec a 64k page size kernel and
* vice versa.
*/
- paddr = round_down(in->phys_addr, SZ_64K);
- size = round_up(in->num_pages * EFI_PAGE_SIZE +
- in->phys_addr - paddr, SZ_64K);
+ if (!regions_are_adjacent(prev, in) ||
+ !regions_have_compatible_memory_type_attrs(prev, in)) {
- /*
- * Avoid wasting memory on PTEs by choosing a virtual base that
- * is compatible with section mappings if this region has the
- * appropriate size and physical alignment. (Sections are 2 MB
- * on 4k granule kernels)
- */
- if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
- efi_virt_base = round_up(efi_virt_base, SZ_2M);
+ paddr = round_down(in->phys_addr, SZ_64K);
+ size += in->phys_addr - paddr;
+
+ /*
+ * Avoid wasting memory on PTEs by choosing a virtual
+ * base that is compatible with section mappings if this
+ * region has the appropriate size and physical
+ * alignment. (Sections are 2 MB on 4k granule kernels)
+ */
+ if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
+ efi_virt_base = round_up(efi_virt_base, SZ_2M);
+ else
+ efi_virt_base = round_up(efi_virt_base, SZ_64K);
+ }
in->virt_addr = efi_virt_base + in->phys_addr - paddr;
efi_virt_base += size;
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index ef5d764..b62e2f5 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -147,15 +147,6 @@
if (status)
goto fdt_set_fail;
- /*
- * Add kernel version banner so stub/kernel match can be
- * verified.
- */
- status = fdt_setprop_string(fdt, node, "linux,uefi-stub-kern-ver",
- linux_banner);
- if (status)
- goto fdt_set_fail;
-
return EFI_SUCCESS;
fdt_set_fail:
diff --git a/drivers/firmware/efi/libstub/string.c b/drivers/firmware/efi/libstub/string.c
new file mode 100644
index 0000000..09d5a08
--- /dev/null
+++ b/drivers/firmware/efi/libstub/string.c
@@ -0,0 +1,57 @@
+/*
+ * Taken from:
+ * linux/lib/string.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+
+#ifndef __HAVE_ARCH_STRSTR
+/**
+ * strstr - Find the first substring in a %NUL terminated string
+ * @s1: The string to be searched
+ * @s2: The string to search for
+ */
+char *strstr(const char *s1, const char *s2)
+{
+ size_t l1, l2;
+
+ l2 = strlen(s2);
+ if (!l2)
+ return (char *)s1;
+ l1 = strlen(s1);
+ while (l1 >= l2) {
+ l1--;
+ if (!memcmp(s1, s2, l2))
+ return (char *)s1;
+ s1++;
+ }
+ return NULL;
+}
+#endif
+
+#ifndef __HAVE_ARCH_STRNCMP
+/**
+ * strncmp - Compare two length-limited strings
+ * @cs: One string
+ * @ct: Another string
+ * @count: The maximum number of bytes to compare
+ */
+int strncmp(const char *cs, const char *ct, size_t count)
+{
+ unsigned char c1, c2;
+
+ while (count) {
+ c1 = *cs++;
+ c2 = *ct++;
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (!c1)
+ break;
+ count--;
+ }
+ return 0;
+}
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 1c3fc99..8e99514 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -208,44 +208,6 @@
return ret;
}
-static int amdgpu_cgs_import_gpu_mem(void *cgs_device, int dmabuf_fd,
- cgs_handle_t *handle)
-{
- CGS_FUNC_ADEV;
- int r;
- uint32_t dma_handle;
- struct drm_gem_object *obj;
- struct amdgpu_bo *bo;
- struct drm_device *dev = adev->ddev;
- struct drm_file *file_priv = NULL, *priv;
-
- mutex_lock(&dev->struct_mutex);
- list_for_each_entry(priv, &dev->filelist, lhead) {
- rcu_read_lock();
- if (priv->pid == get_pid(task_pid(current)))
- file_priv = priv;
- rcu_read_unlock();
- if (file_priv)
- break;
- }
- mutex_unlock(&dev->struct_mutex);
- r = dev->driver->prime_fd_to_handle(dev,
- file_priv, dmabuf_fd,
- &dma_handle);
- spin_lock(&file_priv->table_lock);
-
- /* Check if we currently have a reference on the object */
- obj = idr_find(&file_priv->object_idr, dma_handle);
- if (obj == NULL) {
- spin_unlock(&file_priv->table_lock);
- return -EINVAL;
- }
- spin_unlock(&file_priv->table_lock);
- bo = gem_to_amdgpu_bo(obj);
- *handle = (cgs_handle_t)bo;
- return 0;
-}
-
static int amdgpu_cgs_free_gpu_mem(void *cgs_device, cgs_handle_t handle)
{
struct amdgpu_bo *obj = (struct amdgpu_bo *)handle;
@@ -810,7 +772,6 @@
};
static const struct cgs_os_ops amdgpu_cgs_os_ops = {
- amdgpu_cgs_import_gpu_mem,
amdgpu_cgs_add_irq_source,
amdgpu_cgs_irq_get,
amdgpu_cgs_irq_put
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 749420f..cb3c274 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -156,7 +156,8 @@
uint64_t *chunk_array_user;
uint64_t *chunk_array;
struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
- unsigned size, i;
+ unsigned size;
+ int i;
int ret;
if (cs->in.num_chunks == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
index cd6edc4..1e0bba2 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
@@ -1279,8 +1279,7 @@
amdgpu_atombios_encoder_setup_dig_encoder(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0);
}
if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
- amdgpu_atombios_encoder_setup_dig_transmitter(encoder,
- ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0);
+ amdgpu_atombios_encoder_set_backlight_level(amdgpu_encoder, dig->backlight_level);
if (ext_encoder)
amdgpu_atombios_encoder_setup_external_encoder(encoder, ext_encoder, ATOM_ENABLE);
} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 774528a..fab5471 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1262,6 +1262,12 @@
addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT);
+ /* reset addr and status */
+ WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
+
+ if (!addr && !status)
+ return 0;
+
dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
entry->src_id, entry->src_data);
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
@@ -1269,8 +1275,6 @@
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
status);
gmc_v7_0_vm_decode_fault(adev, status, addr, mc_client);
- /* reset addr and status */
- WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 9a07742..7bc9e9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1262,6 +1262,12 @@
addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
mc_client = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_MCCLIENT);
+ /* reset addr and status */
+ WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
+
+ if (!addr && !status)
+ return 0;
+
dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
entry->src_id, entry->src_data);
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
@@ -1269,8 +1275,6 @@
dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
status);
gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client);
- /* reset addr and status */
- WREG32_P(mmVM_CONTEXT1_CNTL2, 1, ~1);
return 0;
}
diff --git a/drivers/gpu/drm/amd/include/cgs_linux.h b/drivers/gpu/drm/amd/include/cgs_linux.h
index 488642f..3b47ae3 100644
--- a/drivers/gpu/drm/amd/include/cgs_linux.h
+++ b/drivers/gpu/drm/amd/include/cgs_linux.h
@@ -27,19 +27,6 @@
#include "cgs_common.h"
/**
- * cgs_import_gpu_mem() - Import dmabuf handle
- * @cgs_device: opaque device handle
- * @dmabuf_fd: DMABuf file descriptor
- * @handle: memory handle (output)
- *
- * Must be called in the process context that dmabuf_fd belongs to.
- *
- * Return: 0 on success, -errno otherwise
- */
-typedef int (*cgs_import_gpu_mem_t)(void *cgs_device, int dmabuf_fd,
- cgs_handle_t *handle);
-
-/**
* cgs_irq_source_set_func() - Callback for enabling/disabling interrupt sources
* @private_data: private data provided to cgs_add_irq_source
* @src_id: interrupt source ID
@@ -114,16 +101,12 @@
typedef int (*cgs_irq_put_t)(void *cgs_device, unsigned src_id, unsigned type);
struct cgs_os_ops {
- cgs_import_gpu_mem_t import_gpu_mem;
-
/* IRQ handling */
cgs_add_irq_source_t add_irq_source;
cgs_irq_get_t irq_get;
cgs_irq_put_t irq_put;
};
-#define cgs_import_gpu_mem(dev,dmabuf_fd,handle) \
- CGS_OS_CALL(import_gpu_mem,dev,dmabuf_fd,handle)
#define cgs_add_irq_source(dev,src_id,num_types,set,handler,private_data) \
CGS_OS_CALL(add_irq_source,dev,src_id,num_types,set,handler, \
private_data)
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index e23df5f..bf27a07 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -53,8 +53,8 @@
struct drm_dp_mst_port *port,
int offset, int size, u8 *bytes);
-static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
- struct drm_dp_mst_branch *mstb);
+static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
+ struct drm_dp_mst_branch *mstb);
static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
struct drm_dp_mst_branch *mstb,
struct drm_dp_mst_port *port);
@@ -804,8 +804,6 @@
struct drm_dp_mst_port *port, *tmp;
bool wake_tx = false;
- cancel_work_sync(&mstb->mgr->work);
-
/*
* destroy all ports - don't need lock
* as there are no more references to the mst branch
@@ -863,29 +861,33 @@
{
struct drm_dp_mst_port *port = container_of(kref, struct drm_dp_mst_port, kref);
struct drm_dp_mst_topology_mgr *mgr = port->mgr;
+
if (!port->input) {
port->vcpi.num_slots = 0;
kfree(port->cached_edid);
- /* we can't destroy the connector here, as
- we might be holding the mode_config.mutex
- from an EDID retrieval */
+ /*
+ * The only time we don't have a connector
+ * on an output port is if the connector init
+ * fails.
+ */
if (port->connector) {
+ /* we can't destroy the connector here, as
+ * we might be holding the mode_config.mutex
+ * from an EDID retrieval */
+
mutex_lock(&mgr->destroy_connector_lock);
list_add(&port->next, &mgr->destroy_connector_list);
mutex_unlock(&mgr->destroy_connector_lock);
schedule_work(&mgr->destroy_connector_work);
return;
}
+ /* no need to clean up vcpi
+ * as if we have no connector we never setup a vcpi */
drm_dp_port_teardown_pdt(port, port->pdt);
-
- if (!port->input && port->vcpi.vcpi > 0)
- drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
}
kfree(port);
-
- (*mgr->cbs->hotplug)(mgr);
}
static void drm_dp_put_port(struct drm_dp_mst_port *port)
@@ -1027,8 +1029,8 @@
}
}
-static void build_mst_prop_path(struct drm_dp_mst_port *port,
- struct drm_dp_mst_branch *mstb,
+static void build_mst_prop_path(const struct drm_dp_mst_branch *mstb,
+ int pnum,
char *proppath,
size_t proppath_size)
{
@@ -1041,7 +1043,7 @@
snprintf(temp, sizeof(temp), "-%d", port_num);
strlcat(proppath, temp, proppath_size);
}
- snprintf(temp, sizeof(temp), "-%d", port->port_num);
+ snprintf(temp, sizeof(temp), "-%d", pnum);
strlcat(proppath, temp, proppath_size);
}
@@ -1105,22 +1107,32 @@
drm_dp_port_teardown_pdt(port, old_pdt);
ret = drm_dp_port_setup_pdt(port);
- if (ret == true) {
+ if (ret == true)
drm_dp_send_link_address(mstb->mgr, port->mstb);
- port->mstb->link_address_sent = true;
- }
}
if (created && !port->input) {
char proppath[255];
- build_mst_prop_path(port, mstb, proppath, sizeof(proppath));
- port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath);
- if (port->port_num >= 8) {
- port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
+ build_mst_prop_path(mstb, port->port_num, proppath, sizeof(proppath));
+ port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath);
+ if (!port->connector) {
+ /* remove it from the port list */
+ mutex_lock(&mstb->mgr->lock);
+ list_del(&port->next);
+ mutex_unlock(&mstb->mgr->lock);
+ /* drop port list reference */
+ drm_dp_put_port(port);
+ goto out;
}
+ if (port->port_num >= DP_MST_LOGICAL_PORT_0) {
+ port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
+ drm_mode_connector_set_tile_property(port->connector);
+ }
+ (*mstb->mgr->cbs->register_connector)(port->connector);
}
+out:
/* put reference to this port */
drm_dp_put_port(port);
}
@@ -1202,10 +1214,9 @@
{
struct drm_dp_mst_port *port;
struct drm_dp_mst_branch *mstb_child;
- if (!mstb->link_address_sent) {
+ if (!mstb->link_address_sent)
drm_dp_send_link_address(mgr, mstb);
- mstb->link_address_sent = true;
- }
+
list_for_each_entry(port, &mstb->ports, next) {
if (port->input)
continue;
@@ -1458,8 +1469,8 @@
mutex_unlock(&mgr->qlock);
}
-static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
- struct drm_dp_mst_branch *mstb)
+static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
+ struct drm_dp_mst_branch *mstb)
{
int len;
struct drm_dp_sideband_msg_tx *txmsg;
@@ -1467,11 +1478,12 @@
txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
if (!txmsg)
- return -ENOMEM;
+ return;
txmsg->dst = mstb;
len = build_link_address(txmsg);
+ mstb->link_address_sent = true;
drm_dp_queue_down_tx(mgr, txmsg);
ret = drm_dp_mst_wait_tx_reply(mstb, txmsg);
@@ -1499,11 +1511,12 @@
}
(*mgr->cbs->hotplug)(mgr);
}
- } else
+ } else {
+ mstb->link_address_sent = false;
DRM_DEBUG_KMS("link address failed %d\n", ret);
+ }
kfree(txmsg);
- return 0;
}
static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
@@ -1978,6 +1991,8 @@
drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL,
DP_MST_EN | DP_UPSTREAM_IS_SRC);
mutex_unlock(&mgr->lock);
+ flush_work(&mgr->work);
+ flush_work(&mgr->destroy_connector_work);
}
EXPORT_SYMBOL(drm_dp_mst_topology_mgr_suspend);
@@ -2263,10 +2278,10 @@
if (port->cached_edid)
edid = drm_edid_duplicate(port->cached_edid);
- else
+ else {
edid = drm_get_edid(connector, &port->aux.ddc);
-
- drm_mode_connector_set_tile_property(connector);
+ drm_mode_connector_set_tile_property(connector);
+ }
drm_dp_put_port(port);
return edid;
}
@@ -2671,7 +2686,7 @@
{
struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work);
struct drm_dp_mst_port *port;
-
+ bool send_hotplug = false;
/*
* Not a regular list traverse as we have to drop the destroy
* connector lock before destroying the connector, to avoid AB->BA
@@ -2694,7 +2709,10 @@
if (!port->input && port->vcpi.vcpi > 0)
drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
kfree(port);
+ send_hotplug = true;
}
+ if (send_hotplug)
+ (*mgr->cbs->hotplug)(mgr);
}
/**
@@ -2747,6 +2765,7 @@
*/
void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr)
{
+ flush_work(&mgr->work);
flush_work(&mgr->destroy_connector_work);
mutex_lock(&mgr->payload_lock);
kfree(mgr->payloads);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 418d299..ca08c47 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -345,7 +345,11 @@
struct drm_crtc *crtc = mode_set->crtc;
int ret;
- if (crtc->funcs->cursor_set) {
+ if (crtc->funcs->cursor_set2) {
+ ret = crtc->funcs->cursor_set2(crtc, NULL, 0, 0, 0, 0, 0);
+ if (ret)
+ error = true;
+ } else if (crtc->funcs->cursor_set) {
ret = crtc->funcs->cursor_set(crtc, NULL, 0, 0, 0);
if (ret)
error = true;
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index d734780..a18164f 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -94,7 +94,18 @@
}
#define DRM_OUTPUT_POLL_PERIOD (10*HZ)
-static void __drm_kms_helper_poll_enable(struct drm_device *dev)
+/**
+ * drm_kms_helper_poll_enable_locked - re-enable output polling.
+ * @dev: drm_device
+ *
+ * This function re-enables the output polling work without
+ * locking the mode_config mutex.
+ *
+ * This is like drm_kms_helper_poll_enable() however it is to be
+ * called from a context where the mode_config mutex is locked
+ * already.
+ */
+void drm_kms_helper_poll_enable_locked(struct drm_device *dev)
{
bool poll = false;
struct drm_connector *connector;
@@ -113,6 +124,8 @@
if (poll)
schedule_delayed_work(&dev->mode_config.output_poll_work, DRM_OUTPUT_POLL_PERIOD);
}
+EXPORT_SYMBOL(drm_kms_helper_poll_enable_locked);
+
static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connector *connector,
uint32_t maxX, uint32_t maxY, bool merge_type_bits)
@@ -174,7 +187,7 @@
/* Re-enable polling in case the global poll config changed. */
if (drm_kms_helper_poll != dev->mode_config.poll_running)
- __drm_kms_helper_poll_enable(dev);
+ drm_kms_helper_poll_enable_locked(dev);
dev->mode_config.poll_running = drm_kms_helper_poll;
@@ -428,7 +441,7 @@
void drm_kms_helper_poll_enable(struct drm_device *dev)
{
mutex_lock(&dev->mode_config.mutex);
- __drm_kms_helper_poll_enable(dev);
+ drm_kms_helper_poll_enable_locked(dev);
mutex_unlock(&dev->mode_config.mutex);
}
EXPORT_SYMBOL(drm_kms_helper_poll_enable);
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index cbdb78e..e6cbaca 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -37,7 +37,6 @@
* DECON stands for Display and Enhancement controller.
*/
-#define DECON_DEFAULT_FRAMERATE 60
#define MIN_FB_WIDTH_FOR_16WORD_BURST 128
#define WINDOWS_NR 2
@@ -165,16 +164,6 @@
return (clkdiv < 0x100) ? clkdiv : 0xff;
}
-static bool decon_mode_fixup(struct exynos_drm_crtc *crtc,
- const struct drm_display_mode *mode,
- struct drm_display_mode *adjusted_mode)
-{
- if (adjusted_mode->vrefresh == 0)
- adjusted_mode->vrefresh = DECON_DEFAULT_FRAMERATE;
-
- return true;
-}
-
static void decon_commit(struct exynos_drm_crtc *crtc)
{
struct decon_context *ctx = crtc->ctx;
@@ -637,7 +626,6 @@
static const struct exynos_drm_crtc_ops decon_crtc_ops = {
.enable = decon_enable,
.disable = decon_disable,
- .mode_fixup = decon_mode_fixup,
.commit = decon_commit,
.enable_vblank = decon_enable_vblank,
.disable_vblank = decon_disable_vblank,
diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c
index d66ade0..124fb9a 100644
--- a/drivers/gpu/drm/exynos/exynos_dp_core.c
+++ b/drivers/gpu/drm/exynos/exynos_dp_core.c
@@ -1383,28 +1383,6 @@
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int exynos_dp_suspend(struct device *dev)
-{
- struct exynos_dp_device *dp = dev_get_drvdata(dev);
-
- exynos_dp_disable(&dp->encoder);
- return 0;
-}
-
-static int exynos_dp_resume(struct device *dev)
-{
- struct exynos_dp_device *dp = dev_get_drvdata(dev);
-
- exynos_dp_enable(&dp->encoder);
- return 0;
-}
-#endif
-
-static const struct dev_pm_ops exynos_dp_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(exynos_dp_suspend, exynos_dp_resume)
-};
-
static const struct of_device_id exynos_dp_match[] = {
{ .compatible = "samsung,exynos5-dp" },
{},
@@ -1417,7 +1395,6 @@
.driver = {
.name = "exynos-dp",
.owner = THIS_MODULE,
- .pm = &exynos_dp_pm_ops,
.of_match_table = exynos_dp_match,
},
};
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index c68a6a2..7f55ba6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -28,7 +28,6 @@
return 0;
}
-EXPORT_SYMBOL_GPL(exynos_drm_subdrv_register);
int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv)
{
@@ -39,7 +38,6 @@
return 0;
}
-EXPORT_SYMBOL_GPL(exynos_drm_subdrv_unregister);
int exynos_drm_device_subdrv_probe(struct drm_device *dev)
{
@@ -69,7 +67,6 @@
return 0;
}
-EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_probe);
int exynos_drm_device_subdrv_remove(struct drm_device *dev)
{
@@ -87,7 +84,6 @@
return 0;
}
-EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_remove);
int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file)
{
@@ -111,7 +107,6 @@
}
return ret;
}
-EXPORT_SYMBOL_GPL(exynos_drm_subdrv_open);
void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file)
{
@@ -122,4 +117,3 @@
subdrv->close(dev, subdrv->dev, file);
}
}
-EXPORT_SYMBOL_GPL(exynos_drm_subdrv_close);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 0872aa2f..ed28823 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -41,20 +41,6 @@
exynos_crtc->ops->disable(exynos_crtc);
}
-static bool
-exynos_drm_crtc_mode_fixup(struct drm_crtc *crtc,
- const struct drm_display_mode *mode,
- struct drm_display_mode *adjusted_mode)
-{
- struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
-
- if (exynos_crtc->ops->mode_fixup)
- return exynos_crtc->ops->mode_fixup(exynos_crtc, mode,
- adjusted_mode);
-
- return true;
-}
-
static void
exynos_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
{
@@ -99,7 +85,6 @@
static struct drm_crtc_helper_funcs exynos_crtc_helper_funcs = {
.enable = exynos_drm_crtc_enable,
.disable = exynos_drm_crtc_disable,
- .mode_fixup = exynos_drm_crtc_mode_fixup,
.mode_set_nofb = exynos_drm_crtc_mode_set_nofb,
.atomic_begin = exynos_crtc_atomic_begin,
.atomic_flush = exynos_crtc_atomic_flush,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 831d2e4..ae9e6b2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -304,6 +304,7 @@
return 0;
}
+#ifdef CONFIG_PM_SLEEP
static int exynos_drm_suspend(struct drm_device *dev, pm_message_t state)
{
struct drm_connector *connector;
@@ -340,6 +341,7 @@
return 0;
}
+#endif
static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
{
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index b7ba21d..6c717ba 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -82,7 +82,6 @@
*
* @enable: enable the device
* @disable: disable the device
- * @mode_fixup: fix mode data before applying it
* @commit: set current hw specific display mode to hw.
* @enable_vblank: specific driver callback for enabling vblank interrupt.
* @disable_vblank: specific driver callback for disabling vblank interrupt.
@@ -103,9 +102,6 @@
struct exynos_drm_crtc_ops {
void (*enable)(struct exynos_drm_crtc *crtc);
void (*disable)(struct exynos_drm_crtc *crtc);
- bool (*mode_fixup)(struct exynos_drm_crtc *crtc,
- const struct drm_display_mode *mode,
- struct drm_display_mode *adjusted_mode);
void (*commit)(struct exynos_drm_crtc *crtc);
int (*enable_vblank)(struct exynos_drm_crtc *crtc);
void (*disable_vblank)(struct exynos_drm_crtc *crtc);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 2a65235..dd3a5e6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1206,23 +1206,6 @@
.set_addr = fimc_dst_set_addr,
};
-static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable)
-{
- DRM_DEBUG_KMS("enable[%d]\n", enable);
-
- if (enable) {
- clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]);
- clk_prepare_enable(ctx->clocks[FIMC_CLK_WB_A]);
- ctx->suspended = false;
- } else {
- clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]);
- clk_disable_unprepare(ctx->clocks[FIMC_CLK_WB_A]);
- ctx->suspended = true;
- }
-
- return 0;
-}
-
static irqreturn_t fimc_irq_handler(int irq, void *dev_id)
{
struct fimc_context *ctx = dev_id;
@@ -1780,6 +1763,24 @@
return 0;
}
+#ifdef CONFIG_PM
+static int fimc_clk_ctrl(struct fimc_context *ctx, bool enable)
+{
+ DRM_DEBUG_KMS("enable[%d]\n", enable);
+
+ if (enable) {
+ clk_prepare_enable(ctx->clocks[FIMC_CLK_GATE]);
+ clk_prepare_enable(ctx->clocks[FIMC_CLK_WB_A]);
+ ctx->suspended = false;
+ } else {
+ clk_disable_unprepare(ctx->clocks[FIMC_CLK_GATE]);
+ clk_disable_unprepare(ctx->clocks[FIMC_CLK_WB_A]);
+ ctx->suspended = true;
+ }
+
+ return 0;
+}
+
#ifdef CONFIG_PM_SLEEP
static int fimc_suspend(struct device *dev)
{
@@ -1806,7 +1807,6 @@
}
#endif
-#ifdef CONFIG_PM
static int fimc_runtime_suspend(struct device *dev)
{
struct fimc_context *ctx = get_fimc_context(dev);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 750a9e6..3d1aba6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -41,7 +41,6 @@
* CPU Interface.
*/
-#define FIMD_DEFAULT_FRAMERATE 60
#define MIN_FB_WIDTH_FOR_16WORD_BURST 128
/* position control register for hardware window 0, 2 ~ 4.*/
@@ -377,16 +376,6 @@
return (clkdiv < 0x100) ? clkdiv : 0xff;
}
-static bool fimd_mode_fixup(struct exynos_drm_crtc *crtc,
- const struct drm_display_mode *mode,
- struct drm_display_mode *adjusted_mode)
-{
- if (adjusted_mode->vrefresh == 0)
- adjusted_mode->vrefresh = FIMD_DEFAULT_FRAMERATE;
-
- return true;
-}
-
static void fimd_commit(struct exynos_drm_crtc *crtc)
{
struct fimd_context *ctx = crtc->ctx;
@@ -882,13 +871,12 @@
return;
val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE;
- writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON);
+ writel(val, ctx->regs + DP_MIE_CLKCON);
}
static const struct exynos_drm_crtc_ops fimd_crtc_ops = {
.enable = fimd_enable,
.disable = fimd_disable,
- .mode_fixup = fimd_mode_fixup,
.commit = fimd_commit,
.enable_vblank = fimd_enable_vblank,
.disable_vblank = fimd_disable_vblank,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 3734c34..c17efdb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -1059,7 +1059,6 @@
return 0;
}
-EXPORT_SYMBOL_GPL(exynos_g2d_get_ver_ioctl);
int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
struct drm_file *file)
@@ -1230,7 +1229,6 @@
g2d_put_cmdlist(g2d, node);
return ret;
}
-EXPORT_SYMBOL_GPL(exynos_g2d_set_cmdlist_ioctl);
int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
struct drm_file *file)
@@ -1293,7 +1291,6 @@
out:
return 0;
}
-EXPORT_SYMBOL_GPL(exynos_g2d_exec_ioctl);
static int g2d_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
{
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index f12fbc3..407afed 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -56,39 +56,35 @@
nr_pages = obj->size >> PAGE_SHIFT;
if (!is_drm_iommu_supported(dev)) {
- dma_addr_t start_addr;
- unsigned int i = 0;
-
obj->pages = drm_calloc_large(nr_pages, sizeof(struct page *));
if (!obj->pages) {
DRM_ERROR("failed to allocate pages.\n");
return -ENOMEM;
}
+ }
- obj->cookie = dma_alloc_attrs(dev->dev,
- obj->size,
- &obj->dma_addr, GFP_KERNEL,
- &obj->dma_attrs);
- if (!obj->cookie) {
- DRM_ERROR("failed to allocate buffer.\n");
+ obj->cookie = dma_alloc_attrs(dev->dev, obj->size, &obj->dma_addr,
+ GFP_KERNEL, &obj->dma_attrs);
+ if (!obj->cookie) {
+ DRM_ERROR("failed to allocate buffer.\n");
+ if (obj->pages)
drm_free_large(obj->pages);
- return -ENOMEM;
- }
+ return -ENOMEM;
+ }
+
+ if (obj->pages) {
+ dma_addr_t start_addr;
+ unsigned int i = 0;
start_addr = obj->dma_addr;
while (i < nr_pages) {
- obj->pages[i] = phys_to_page(start_addr);
+ obj->pages[i] = pfn_to_page(dma_to_pfn(dev->dev,
+ start_addr));
start_addr += PAGE_SIZE;
i++;
}
} else {
- obj->pages = dma_alloc_attrs(dev->dev, obj->size,
- &obj->dma_addr, GFP_KERNEL,
- &obj->dma_attrs);
- if (!obj->pages) {
- DRM_ERROR("failed to allocate buffer.\n");
- return -ENOMEM;
- }
+ obj->pages = obj->cookie;
}
DRM_DEBUG_KMS("dma_addr(0x%lx), size(0x%lx)\n",
@@ -110,15 +106,11 @@
DRM_DEBUG_KMS("dma_addr(0x%lx), size(0x%lx)\n",
(unsigned long)obj->dma_addr, obj->size);
- if (!is_drm_iommu_supported(dev)) {
- dma_free_attrs(dev->dev, obj->size, obj->cookie,
- (dma_addr_t)obj->dma_addr, &obj->dma_attrs);
- drm_free_large(obj->pages);
- } else
- dma_free_attrs(dev->dev, obj->size, obj->pages,
- (dma_addr_t)obj->dma_addr, &obj->dma_attrs);
+ dma_free_attrs(dev->dev, obj->size, obj->cookie,
+ (dma_addr_t)obj->dma_addr, &obj->dma_attrs);
- obj->dma_addr = (dma_addr_t)NULL;
+ if (!is_drm_iommu_supported(dev))
+ drm_free_large(obj->pages);
}
static int exynos_drm_gem_handle_create(struct drm_gem_object *obj,
@@ -156,18 +148,14 @@
* once dmabuf's refcount becomes 0.
*/
if (obj->import_attach)
- goto out;
-
- exynos_drm_free_buf(exynos_gem_obj);
-
-out:
- drm_gem_free_mmap_offset(obj);
+ drm_prime_gem_destroy(obj, exynos_gem_obj->sgt);
+ else
+ exynos_drm_free_buf(exynos_gem_obj);
/* release file pointer to gem object. */
drm_gem_object_release(obj);
kfree(exynos_gem_obj);
- exynos_gem_obj = NULL;
}
unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
@@ -190,8 +178,7 @@
return exynos_gem_obj->size;
}
-
-struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev,
+static struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev,
unsigned long size)
{
struct exynos_drm_gem_obj *exynos_gem_obj;
@@ -212,6 +199,13 @@
return ERR_PTR(ret);
}
+ ret = drm_gem_create_mmap_offset(obj);
+ if (ret < 0) {
+ drm_gem_object_release(obj);
+ kfree(exynos_gem_obj);
+ return ERR_PTR(ret);
+ }
+
DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp);
return exynos_gem_obj;
@@ -313,7 +307,7 @@
drm_gem_object_unreference_unlocked(obj);
}
-int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj,
+static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj,
struct vm_area_struct *vma)
{
struct drm_device *drm_dev = exynos_gem_obj->base.dev;
@@ -342,7 +336,8 @@
int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv)
-{ struct exynos_drm_gem_obj *exynos_gem_obj;
+{
+ struct exynos_drm_gem_obj *exynos_gem_obj;
struct drm_exynos_gem_info *args = data;
struct drm_gem_object *obj;
@@ -402,6 +397,7 @@
struct drm_mode_create_dumb *args)
{
struct exynos_drm_gem_obj *exynos_gem_obj;
+ unsigned int flags;
int ret;
/*
@@ -413,16 +409,12 @@
args->pitch = args->width * ((args->bpp + 7) / 8);
args->size = args->pitch * args->height;
- if (is_drm_iommu_supported(dev)) {
- exynos_gem_obj = exynos_drm_gem_create(dev,
- EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC,
- args->size);
- } else {
- exynos_gem_obj = exynos_drm_gem_create(dev,
- EXYNOS_BO_CONTIG | EXYNOS_BO_WC,
- args->size);
- }
+ if (is_drm_iommu_supported(dev))
+ flags = EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC;
+ else
+ flags = EXYNOS_BO_CONTIG | EXYNOS_BO_WC;
+ exynos_gem_obj = exynos_drm_gem_create(dev, flags, args->size);
if (IS_ERR(exynos_gem_obj)) {
dev_warn(dev->dev, "FB allocation failed.\n");
return PTR_ERR(exynos_gem_obj);
@@ -460,14 +452,9 @@
goto unlock;
}
- ret = drm_gem_create_mmap_offset(obj);
- if (ret)
- goto out;
-
*offset = drm_vma_node_offset_addr(&obj->vma_node);
DRM_DEBUG_KMS("offset = 0x%lx\n", (unsigned long)*offset);
-out:
drm_gem_object_unreference(obj);
unlock:
mutex_unlock(&dev->struct_mutex);
@@ -543,7 +530,6 @@
err_close_vm:
drm_gem_vm_close(vma);
- drm_gem_free_mmap_offset(obj);
return ret;
}
@@ -588,6 +574,8 @@
if (ret < 0)
goto err_free_large;
+ exynos_gem_obj->sgt = sgt;
+
if (sgt->nents == 1) {
/* always physically continuous memory if sgt->nents is 1. */
exynos_gem_obj->flags |= EXYNOS_BO_CONTIG;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index cd62f84..b62d100 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -39,6 +39,7 @@
* - this address could be physical address without IOMMU and
* device address with IOMMU.
* @pages: Array of backing pages.
+ * @sgt: Imported sg_table.
*
* P.S. this object would be transferred to user as kms_bo.handle so
* user can access the buffer through kms_bo.handle.
@@ -52,6 +53,7 @@
dma_addr_t dma_addr;
struct dma_attrs dma_attrs;
struct page **pages;
+ struct sg_table *sgt;
};
struct page **exynos_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask);
@@ -59,10 +61,6 @@
/* destroy a buffer with gem object */
void exynos_drm_gem_destroy(struct exynos_drm_gem_obj *exynos_gem_obj);
-/* create a private gem object and initialize it. */
-struct exynos_drm_gem_obj *exynos_drm_gem_init(struct drm_device *dev,
- unsigned long size);
-
/* create a new buffer with gem object */
struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev,
unsigned int flags,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 425e706..2f5c118 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -786,6 +786,7 @@
return 0;
}
+#ifdef CONFIG_PM
static int rotator_clk_crtl(struct rot_context *rot, bool enable)
{
if (enable) {
@@ -822,7 +823,6 @@
}
#endif
-#ifdef CONFIG_PM
static int rotator_runtime_suspend(struct device *dev)
{
struct rot_context *rot = dev_get_drvdata(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 3e4be5a..6ade068 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -462,11 +462,17 @@
drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
drm_mode_connector_set_path_property(connector, pathprop);
+ return connector;
+}
+
+static void intel_dp_register_mst_connector(struct drm_connector *connector)
+{
+ struct intel_connector *intel_connector = to_intel_connector(connector);
+ struct drm_device *dev = connector->dev;
drm_modeset_lock_all(dev);
intel_connector_add_to_fbdev(intel_connector);
drm_modeset_unlock_all(dev);
drm_connector_register(&intel_connector->base);
- return connector;
}
static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
@@ -512,6 +518,7 @@
static struct drm_dp_mst_topology_cbs mst_cbs = {
.add_connector = intel_dp_add_mst_connector,
+ .register_connector = intel_dp_register_mst_connector,
.destroy_connector = intel_dp_destroy_mst_connector,
.hotplug = intel_dp_mst_hotplug,
};
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index 53c0173..b177857 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -180,7 +180,7 @@
/* Enable polling and queue hotplug re-enabling. */
if (hpd_disabled) {
- drm_kms_helper_poll_enable(dev);
+ drm_kms_helper_poll_enable_locked(dev);
mod_delayed_work(system_wq, &dev_priv->hotplug.reenable_work,
msecs_to_jiffies(HPD_STORM_REENABLE_DELAY));
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 72e0edd..7412cae 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -484,18 +484,18 @@
status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring));
read_pointer = ring->next_context_status_buffer;
- write_pointer = status_pointer & 0x07;
+ write_pointer = status_pointer & GEN8_CSB_PTR_MASK;
if (read_pointer > write_pointer)
- write_pointer += 6;
+ write_pointer += GEN8_CSB_ENTRIES;
spin_lock(&ring->execlist_lock);
while (read_pointer < write_pointer) {
read_pointer++;
status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) +
- (read_pointer % 6) * 8);
+ (read_pointer % GEN8_CSB_ENTRIES) * 8);
status_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) +
- (read_pointer % 6) * 8 + 4);
+ (read_pointer % GEN8_CSB_ENTRIES) * 8 + 4);
if (status & GEN8_CTX_STATUS_IDLE_ACTIVE)
continue;
@@ -521,10 +521,12 @@
spin_unlock(&ring->execlist_lock);
WARN(submit_contexts > 2, "More than two context complete events?\n");
- ring->next_context_status_buffer = write_pointer % 6;
+ ring->next_context_status_buffer = write_pointer % GEN8_CSB_ENTRIES;
I915_WRITE(RING_CONTEXT_STATUS_PTR(ring),
- _MASKED_FIELD(0x07 << 8, ((u32)ring->next_context_status_buffer & 0x07) << 8));
+ _MASKED_FIELD(GEN8_CSB_PTR_MASK << 8,
+ ((u32)ring->next_context_status_buffer &
+ GEN8_CSB_PTR_MASK) << 8));
}
static int execlists_context_queue(struct drm_i915_gem_request *request)
@@ -1422,6 +1424,7 @@
{
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ u8 next_context_status_buffer_hw;
I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff);
@@ -1436,7 +1439,29 @@
_MASKED_BIT_DISABLE(GFX_REPLAY_MODE) |
_MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
POSTING_READ(RING_MODE_GEN7(ring));
- ring->next_context_status_buffer = 0;
+
+ /*
+ * Instead of resetting the Context Status Buffer (CSB) read pointer to
+ * zero, we need to read the write pointer from hardware and use its
+ * value because "this register is power context save restored".
+ * Effectively, these states have been observed:
+ *
+ * | Suspend-to-idle (freeze) | Suspend-to-RAM (mem) |
+ * BDW | CSB regs not reset | CSB regs reset |
+ * CHT | CSB regs not reset | CSB regs not reset |
+ */
+ next_context_status_buffer_hw = (I915_READ(RING_CONTEXT_STATUS_PTR(ring))
+ & GEN8_CSB_PTR_MASK);
+
+ /*
+ * When the CSB registers are reset (also after power-up / gpu reset),
+ * CSB write pointer is set to all 1's, which is not valid, use '5' in
+ * this special case, so the first element read is CSB[0].
+ */
+ if (next_context_status_buffer_hw == GEN8_CSB_PTR_MASK)
+ next_context_status_buffer_hw = (GEN8_CSB_ENTRIES - 1);
+
+ ring->next_context_status_buffer = next_context_status_buffer_hw;
DRM_DEBUG_DRIVER("Execlists enabled for %s\n", ring->name);
memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 64f89f99..3c63bb3 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -25,6 +25,8 @@
#define _INTEL_LRC_H_
#define GEN8_LR_CONTEXT_ALIGN 4096
+#define GEN8_CSB_ENTRIES 6
+#define GEN8_CSB_PTR_MASK 0x07
/* Execlists regs */
#define RING_ELSP(ring) ((ring)->mmio_base+0x230)
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index af7fdb3..7401cf9 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -246,7 +246,8 @@
}
if (power_well->data == SKL_DISP_PW_1) {
- intel_prepare_ddi(dev);
+ if (!dev_priv->power_domains.initializing)
+ intel_prepare_ddi(dev);
gen8_irq_power_well_post_enable(dev_priv, 1 << PIPE_A);
}
}
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index dd845f8..4649bd2 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -618,7 +618,7 @@
adjusted_mode->hdisplay,
adjusted_mode->vdisplay);
- if (qcrtc->index == 0)
+ if (bo->is_primary == false)
recreate_primary = true;
if (bo->surf.stride * bo->surf.height > qdev->vram_size) {
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index c387259..65adb9c 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1624,8 +1624,9 @@
} else
atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
- args.ucAction = ATOM_LCD_BLON;
- atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+ struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+
+ atombios_set_backlight_level(radeon_encoder, dig->backlight_level);
}
break;
case DRM_MODE_DPMS_STANDBY:
@@ -1706,8 +1707,7 @@
atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0);
}
if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
- atombios_dig_transmitter_setup(encoder,
- ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0);
+ atombios_set_backlight_level(radeon_encoder, dig->backlight_level);
if (ext_encoder)
atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE);
break;
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 5e09c06..6cddae4 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -265,7 +265,6 @@
{
struct radeon_connector *master = container_of(mgr, struct radeon_connector, mst_mgr);
struct drm_device *dev = master->base.dev;
- struct radeon_device *rdev = dev->dev_private;
struct radeon_connector *radeon_connector;
struct drm_connector *connector;
@@ -286,12 +285,19 @@
drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
drm_mode_connector_set_path_property(connector, pathprop);
+ return connector;
+}
+
+static void radeon_dp_register_mst_connector(struct drm_connector *connector)
+{
+ struct drm_device *dev = connector->dev;
+ struct radeon_device *rdev = dev->dev_private;
+
drm_modeset_lock_all(dev);
radeon_fb_add_connector(rdev, connector);
drm_modeset_unlock_all(dev);
drm_connector_register(connector);
- return connector;
}
static void radeon_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
@@ -324,6 +330,7 @@
struct drm_dp_mst_topology_cbs mst_cbs = {
.add_connector = radeon_dp_add_mst_connector,
+ .register_connector = radeon_dp_register_mst_connector,
.destroy_connector = radeon_dp_destroy_mst_connector,
.hotplug = radeon_dp_mst_hotplug,
};
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 7214858..1aa657f 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -48,40 +48,10 @@
struct radeon_device *rdev;
};
-/**
- * radeon_fb_helper_set_par - Hide cursor on CRTCs used by fbdev.
- *
- * @info: fbdev info
- *
- * This function hides the cursor on all CRTCs used by fbdev.
- */
-static int radeon_fb_helper_set_par(struct fb_info *info)
-{
- int ret;
-
- ret = drm_fb_helper_set_par(info);
-
- /* XXX: with universal plane support fbdev will automatically disable
- * all non-primary planes (including the cursor)
- */
- if (ret == 0) {
- struct drm_fb_helper *fb_helper = info->par;
- int i;
-
- for (i = 0; i < fb_helper->crtc_count; i++) {
- struct drm_crtc *crtc = fb_helper->crtc_info[i].mode_set.crtc;
-
- radeon_crtc_cursor_set2(crtc, NULL, 0, 0, 0, 0, 0);
- }
- }
-
- return ret;
-}
-
static struct fb_ops radeonfb_ops = {
.owner = THIS_MODULE,
.fb_check_var = drm_fb_helper_check_var,
- .fb_set_par = radeon_fb_helper_set_par,
+ .fb_set_par = drm_fb_helper_set_par,
.fb_fillrect = drm_fb_helper_cfb_fillrect,
.fb_copyarea = drm_fb_helper_cfb_copyarea,
.fb_imageblit = drm_fb_helper_cfb_imageblit,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
index 5ae8f92..8a76821 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
@@ -681,6 +681,14 @@
0, 0,
DRM_MM_SEARCH_DEFAULT,
DRM_MM_CREATE_DEFAULT);
+ if (ret) {
+ (void) vmw_cmdbuf_man_process(man);
+ ret = drm_mm_insert_node_generic(&man->mm, info->node,
+ info->page_size, 0, 0,
+ DRM_MM_SEARCH_DEFAULT,
+ DRM_MM_CREATE_DEFAULT);
+ }
+
spin_unlock_bh(&man->lock);
info->done = !ret;
diff --git a/drivers/hwmon/abx500.c b/drivers/hwmon/abx500.c
index 6cb89c0..1fd4685 100644
--- a/drivers/hwmon/abx500.c
+++ b/drivers/hwmon/abx500.c
@@ -470,6 +470,7 @@
{ .compatible = "stericsson,abx500-temp" },
{},
};
+MODULE_DEVICE_TABLE(of, abx500_temp_match);
#endif
static struct platform_driver abx500_temp_driver = {
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index a3dae6d..82de3de 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -539,6 +539,7 @@
{ .compatible = "gpio-fan", },
{},
};
+MODULE_DEVICE_TABLE(of, of_gpio_fan_match);
#endif /* CONFIG_OF_GPIO */
static int gpio_fan_probe(struct platform_device *pdev)
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 2d9a712..3e23003 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -323,6 +323,7 @@
{ .compatible = "pwm-fan", },
{},
};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match);
static struct platform_driver pwm_fan_driver = {
.probe = pwm_fan_probe,
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3a3738f..cd4510a 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -620,7 +620,7 @@
.name = "C6-SKL",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
- .exit_latency = 75,
+ .exit_latency = 85,
.target_residency = 200,
.enter = &intel_idle,
.enter_freeze = intel_idle_freeze, },
@@ -636,11 +636,19 @@
.name = "C8-SKL",
.desc = "MWAIT 0x40",
.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
- .exit_latency = 174,
+ .exit_latency = 200,
.target_residency = 800,
.enter = &intel_idle,
.enter_freeze = intel_idle_freeze, },
{
+ .name = "C9-SKL",
+ .desc = "MWAIT 0x50",
+ .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 480,
+ .target_residency = 5000,
+ .enter = &intel_idle,
+ .enter_freeze = intel_idle_freeze, },
+ {
.name = "C10-SKL",
.desc = "MWAIT 0x60",
.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 41d6911..f1ccd40 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -245,7 +245,6 @@
props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
if (MLX5_CAP_GEN(mdev, apm))
props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
- props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
if (MLX5_CAP_GEN(mdev, xrc))
props->device_cap_flags |= IB_DEVICE_XRC;
props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
@@ -795,53 +794,6 @@
return 0;
}
-static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn)
-{
- struct mlx5_create_mkey_mbox_in *in;
- struct mlx5_mkey_seg *seg;
- struct mlx5_core_mr mr;
- int err;
-
- in = kzalloc(sizeof(*in), GFP_KERNEL);
- if (!in)
- return -ENOMEM;
-
- seg = &in->seg;
- seg->flags = MLX5_PERM_LOCAL_READ | MLX5_ACCESS_MODE_PA;
- seg->flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
- seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
- seg->start_addr = 0;
-
- err = mlx5_core_create_mkey(dev->mdev, &mr, in, sizeof(*in),
- NULL, NULL, NULL);
- if (err) {
- mlx5_ib_warn(dev, "failed to create mkey, %d\n", err);
- goto err_in;
- }
-
- kfree(in);
- *key = mr.key;
-
- return 0;
-
-err_in:
- kfree(in);
-
- return err;
-}
-
-static void free_pa_mkey(struct mlx5_ib_dev *dev, u32 key)
-{
- struct mlx5_core_mr mr;
- int err;
-
- memset(&mr, 0, sizeof(mr));
- mr.key = key;
- err = mlx5_core_destroy_mkey(dev->mdev, &mr);
- if (err)
- mlx5_ib_warn(dev, "failed to destroy mkey 0x%x\n", key);
-}
-
static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
struct ib_ucontext *context,
struct ib_udata *udata)
@@ -867,13 +819,6 @@
kfree(pd);
return ERR_PTR(-EFAULT);
}
- } else {
- err = alloc_pa_mkey(to_mdev(ibdev), &pd->pa_lkey, pd->pdn);
- if (err) {
- mlx5_core_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn);
- kfree(pd);
- return ERR_PTR(err);
- }
}
return &pd->ibpd;
@@ -884,9 +829,6 @@
struct mlx5_ib_dev *mdev = to_mdev(pd->device);
struct mlx5_ib_pd *mpd = to_mpd(pd);
- if (!pd->uobject)
- free_pa_mkey(mdev, mpd->pa_lkey);
-
mlx5_core_dealloc_pd(mdev->mdev, mpd->pdn);
kfree(mpd);
@@ -1245,18 +1187,10 @@
struct ib_srq_init_attr attr;
struct mlx5_ib_dev *dev;
struct ib_cq_init_attr cq_attr = {.cqe = 1};
- u32 rsvd_lkey;
int ret = 0;
dev = container_of(devr, struct mlx5_ib_dev, devr);
- ret = mlx5_core_query_special_context(dev->mdev, &rsvd_lkey);
- if (ret) {
- pr_err("Failed to query special context %d\n", ret);
- return ret;
- }
- dev->ib_dev.local_dma_lkey = rsvd_lkey;
-
devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL);
if (IS_ERR(devr->p0)) {
ret = PTR_ERR(devr->p0);
@@ -1418,6 +1352,7 @@
strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
dev->ib_dev.owner = THIS_MODULE;
dev->ib_dev.node_type = RDMA_NODE_IB_CA;
+ dev->ib_dev.local_dma_lkey = 0 /* not supported for now */;
dev->num_ports = MLX5_CAP_GEN(mdev, num_ports);
dev->ib_dev.phys_port_cnt = dev->num_ports;
dev->ib_dev.num_comp_vectors =
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bb8cda7..22123b7 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -103,7 +103,6 @@
struct mlx5_ib_pd {
struct ib_pd ibpd;
u32 pdn;
- u32 pa_lkey;
};
/* Use macros here so that don't have to duplicate
@@ -213,7 +212,6 @@
int uuarn;
int create_type;
- u32 pa_lkey;
/* Store signature errors */
bool signature_en;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index c745c6c..6f521a3 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -925,8 +925,6 @@
err = create_kernel_qp(dev, init_attr, qp, &in, &inlen);
if (err)
mlx5_ib_dbg(dev, "err %d\n", err);
- else
- qp->pa_lkey = to_mpd(pd)->pa_lkey;
}
if (err)
@@ -2045,7 +2043,7 @@
mfrpl->mapped_page_list[i] = cpu_to_be64(page_list[i] | perm);
dseg->addr = cpu_to_be64(mfrpl->map);
dseg->byte_count = cpu_to_be32(ALIGN(sizeof(u64) * wr->wr.fast_reg.page_list_len, 64));
- dseg->lkey = cpu_to_be32(pd->pa_lkey);
+ dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
}
static __be32 send_ieth(struct ib_send_wr *wr)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ca28736..4cd5428 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -80,7 +80,7 @@
IPOIB_NUM_WC = 4,
IPOIB_MAX_PATH_REC_QUEUE = 3,
- IPOIB_MAX_MCAST_QUEUE = 3,
+ IPOIB_MAX_MCAST_QUEUE = 64,
IPOIB_FLAG_OPER_UP = 0,
IPOIB_FLAG_INITIALIZED = 1,
@@ -548,6 +548,8 @@
int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
int ipoib_init_qp(struct net_device *dev);
int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 36536ce..f74316e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1149,6 +1149,9 @@
unsigned long dt;
unsigned long flags;
int i;
+ LIST_HEAD(remove_list);
+ struct ipoib_mcast *mcast, *tmcast;
+ struct net_device *dev = priv->dev;
if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
return;
@@ -1176,6 +1179,19 @@
lockdep_is_held(&priv->lock))) != NULL) {
/* was the neigh idle for two GC periods */
if (time_after(neigh_obsolete, neigh->alive)) {
+ u8 *mgid = neigh->daddr + 4;
+
+ /* Is this multicast ? */
+ if (*mgid == 0xff) {
+ mcast = __ipoib_mcast_find(dev, mgid);
+
+ if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+ list_del(&mcast->list);
+ rb_erase(&mcast->rb_node, &priv->multicast_tree);
+ list_add_tail(&mcast->list, &remove_list);
+ }
+ }
+
rcu_assign_pointer(*np,
rcu_dereference_protected(neigh->hnext,
lockdep_is_held(&priv->lock)));
@@ -1191,6 +1207,8 @@
out_unlock:
spin_unlock_irqrestore(&priv->lock, flags);
+ list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
+ ipoib_mcast_leave(dev, mcast);
}
static void ipoib_reap_neigh(struct work_struct *work)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 09a1748..136cbef 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -153,7 +153,7 @@
return mcast;
}
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct rb_node *n = priv->multicast_tree.rb_node;
@@ -508,17 +508,19 @@
rec.hop_limit = priv->broadcast->mcmember.hop_limit;
/*
- * Historically Linux IPoIB has never properly supported SEND
- * ONLY join. It emulated it by not providing all the required
- * attributes, which is enough to prevent group creation and
- * detect if there are full members or not. A major problem
- * with supporting SEND ONLY is detecting when the group is
- * auto-destroyed as IPoIB will cache the MLID..
+ * Send-only IB Multicast joins do not work at the core
+ * IB layer yet, so we can't use them here. However,
+ * we are emulating an Ethernet multicast send, which
+ * does not require a multicast subscription and will
+ * still send properly. The most appropriate thing to
+ * do is to create the group if it doesn't exist as that
+ * most closely emulates the behavior, from a user space
+ * application perspecitive, of Ethernet multicast
+ * operation. For now, we do a full join, maybe later
+ * when the core IB layers support send only joins we
+ * will use them.
*/
-#if 1
- if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
- comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
-#else
+#if 0
if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
rec.join_state = 4;
#endif
@@ -675,7 +677,7 @@
return 0;
}
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret = 0;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 1ace5d8..f58ff96 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -97,6 +97,11 @@
module_param_named(max_sectors, iser_max_sectors, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(max_sectors, "Max number of sectors in a single scsi command (default:1024");
+bool iser_always_reg = true;
+module_param_named(always_register, iser_always_reg, bool, S_IRUGO);
+MODULE_PARM_DESC(always_register,
+ "Always register memory, even for continuous memory regions (default:true)");
+
bool iser_pi_enable = false;
module_param_named(pi_enable, iser_pi_enable, bool, S_IRUGO);
MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)");
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 86f6583..a5edd6e 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -611,6 +611,7 @@
extern bool iser_pi_enable;
extern int iser_pi_guard;
extern unsigned int iser_max_sectors;
+extern bool iser_always_reg;
int iser_assign_reg_ops(struct iser_device *device);
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 2493cc7..4c46d67 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -803,11 +803,12 @@
iser_reg_prot_sg(struct iscsi_iser_task *task,
struct iser_data_buf *mem,
struct iser_fr_desc *desc,
+ bool use_dma_key,
struct iser_mem_reg *reg)
{
struct iser_device *device = task->iser_conn->ib_conn.device;
- if (mem->dma_nents == 1)
+ if (use_dma_key)
return iser_reg_dma(device, mem, reg);
return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg);
@@ -817,11 +818,12 @@
iser_reg_data_sg(struct iscsi_iser_task *task,
struct iser_data_buf *mem,
struct iser_fr_desc *desc,
+ bool use_dma_key,
struct iser_mem_reg *reg)
{
struct iser_device *device = task->iser_conn->ib_conn.device;
- if (mem->dma_nents == 1)
+ if (use_dma_key)
return iser_reg_dma(device, mem, reg);
return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg);
@@ -836,14 +838,17 @@
struct iser_mem_reg *reg = &task->rdma_reg[dir];
struct iser_mem_reg *data_reg;
struct iser_fr_desc *desc = NULL;
+ bool use_dma_key;
int err;
err = iser_handle_unaligned_buf(task, mem, dir);
if (unlikely(err))
return err;
- if (mem->dma_nents != 1 ||
- scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) {
+ use_dma_key = (mem->dma_nents == 1 && !iser_always_reg &&
+ scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL);
+
+ if (!use_dma_key) {
desc = device->reg_ops->reg_desc_get(ib_conn);
reg->mem_h = desc;
}
@@ -853,7 +858,7 @@
else
data_reg = &task->desc.data_reg;
- err = iser_reg_data_sg(task, mem, desc, data_reg);
+ err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg);
if (unlikely(err))
goto err_reg;
@@ -866,7 +871,8 @@
if (unlikely(err))
goto err_reg;
- err = iser_reg_prot_sg(task, mem, desc, prot_reg);
+ err = iser_reg_prot_sg(task, mem, desc,
+ use_dma_key, prot_reg);
if (unlikely(err))
goto err_reg;
}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index ae70cc1..85132d8 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -133,11 +133,15 @@
(unsigned long)comp);
}
- device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_WRITE |
- IB_ACCESS_REMOTE_READ);
- if (IS_ERR(device->mr))
- goto dma_mr_err;
+ if (!iser_always_reg) {
+ int access = IB_ACCESS_LOCAL_WRITE |
+ IB_ACCESS_REMOTE_WRITE |
+ IB_ACCESS_REMOTE_READ;
+
+ device->mr = ib_get_dma_mr(device->pd, access);
+ if (IS_ERR(device->mr))
+ goto dma_mr_err;
+ }
INIT_IB_EVENT_HANDLER(&device->event_handler, device->ib_device,
iser_event_handler);
@@ -147,7 +151,8 @@
return 0;
handler_err:
- ib_dereg_mr(device->mr);
+ if (device->mr)
+ ib_dereg_mr(device->mr);
dma_mr_err:
for (i = 0; i < device->comps_used; i++)
tasklet_kill(&device->comps[i].tasklet);
@@ -173,7 +178,6 @@
static void iser_free_device_ib_res(struct iser_device *device)
{
int i;
- BUG_ON(device->mr == NULL);
for (i = 0; i < device->comps_used; i++) {
struct iser_comp *comp = &device->comps[i];
@@ -184,7 +188,8 @@
}
(void)ib_unregister_event_handler(&device->event_handler);
- (void)ib_dereg_mr(device->mr);
+ if (device->mr)
+ (void)ib_dereg_mr(device->mr);
ib_dealloc_pd(device->pd);
kfree(device->comps);
diff --git a/drivers/input/joystick/Kconfig b/drivers/input/joystick/Kconfig
index 56eb471..4215b53 100644
--- a/drivers/input/joystick/Kconfig
+++ b/drivers/input/joystick/Kconfig
@@ -196,6 +196,7 @@
config JOYSTICK_ZHENHUA
tristate "5-byte Zhenhua RC transmitter"
select SERIO
+ select BITREVERSE
help
Say Y here if you have a Zhen Hua PPM-4CH transmitter which is
supplied with a ready to fly micro electric indoor helicopters
diff --git a/drivers/input/joystick/walkera0701.c b/drivers/input/joystick/walkera0701.c
index b76ac58..a8bc2fe 100644
--- a/drivers/input/joystick/walkera0701.c
+++ b/drivers/input/joystick/walkera0701.c
@@ -150,7 +150,7 @@
if (w->counter == 24) { /* full frame */
walkera0701_parse_frame(w);
w->counter = NO_SYNC;
- if (abs(pulse_time - SYNC_PULSE) < RESERVE) /* new frame sync */
+ if (abs64(pulse_time - SYNC_PULSE) < RESERVE) /* new frame sync */
w->counter = 0;
} else {
if ((pulse_time > (ANALOG_MIN_PULSE - RESERVE)
@@ -161,7 +161,7 @@
} else
w->counter = NO_SYNC;
}
- } else if (abs(pulse_time - SYNC_PULSE - BIN0_PULSE) <
+ } else if (abs64(pulse_time - SYNC_PULSE - BIN0_PULSE) <
RESERVE + BIN1_PULSE - BIN0_PULSE) /* frame sync .. */
w->counter = 0;
diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index b052afe..6639b2b 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -266,7 +266,7 @@
error = omap4_keypad_parse_dt(&pdev->dev, keypad_data);
if (error)
- return error;
+ goto err_free_keypad;
res = request_mem_region(res->start, resource_size(res), pdev->name);
if (!res) {
diff --git a/drivers/input/misc/pm8941-pwrkey.c b/drivers/input/misc/pm8941-pwrkey.c
index 867db8a..e317b75 100644
--- a/drivers/input/misc/pm8941-pwrkey.c
+++ b/drivers/input/misc/pm8941-pwrkey.c
@@ -93,7 +93,7 @@
default:
reset_type = PON_PS_HOLD_TYPE_HARD_RESET;
break;
- };
+ }
error = regmap_update_bits(pwrkey->regmap,
pwrkey->baseaddr + PON_PS_HOLD_RST_CTL,
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 345df9b..5adbced 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -414,7 +414,7 @@
dev->id.product = user_dev->id.product;
dev->id.version = user_dev->id.version;
- for_each_set_bit(i, dev->absbit, ABS_CNT) {
+ for (i = 0; i < ABS_CNT; i++) {
input_abs_set_max(dev, i, user_dev->absmax[i]);
input_abs_set_min(dev, i, user_dev->absmin[i]);
input_abs_set_fuzz(dev, i, user_dev->absfuzz[i]);
diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h
index 73670f2..c0ec261 100644
--- a/drivers/input/mouse/elan_i2c.h
+++ b/drivers/input/mouse/elan_i2c.h
@@ -60,7 +60,7 @@
int (*get_sm_version)(struct i2c_client *client,
u8* ic_type, u8 *version);
int (*get_checksum)(struct i2c_client *client, bool iap, u16 *csum);
- int (*get_product_id)(struct i2c_client *client, u8 *id);
+ int (*get_product_id)(struct i2c_client *client, u16 *id);
int (*get_max)(struct i2c_client *client,
unsigned int *max_x, unsigned int *max_y);
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index fa94530..5e1665b 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -40,7 +40,7 @@
#include "elan_i2c.h"
#define DRIVER_NAME "elan_i2c"
-#define ELAN_DRIVER_VERSION "1.6.0"
+#define ELAN_DRIVER_VERSION "1.6.1"
#define ETP_MAX_PRESSURE 255
#define ETP_FWIDTH_REDUCE 90
#define ETP_FINGER_WIDTH 15
@@ -76,7 +76,7 @@
unsigned int x_res;
unsigned int y_res;
- u8 product_id;
+ u16 product_id;
u8 fw_version;
u8 sm_version;
u8 iap_version;
@@ -98,15 +98,25 @@
u16 *signature_address)
{
switch (iap_version) {
+ case 0x00:
+ case 0x06:
case 0x08:
*validpage_count = 512;
break;
+ case 0x03:
+ case 0x07:
case 0x09:
+ case 0x0A:
+ case 0x0B:
+ case 0x0C:
*validpage_count = 768;
break;
case 0x0D:
*validpage_count = 896;
break;
+ case 0x0E:
+ *validpage_count = 640;
+ break;
default:
/* unknown ic type clear value */
*validpage_count = 0;
@@ -266,11 +276,10 @@
error = elan_get_fwinfo(data->iap_version, &data->fw_validpage_count,
&data->fw_signature_address);
- if (error) {
- dev_err(&data->client->dev,
- "unknown iap version %d\n", data->iap_version);
- return error;
- }
+ if (error)
+ dev_warn(&data->client->dev,
+ "unexpected iap version %#04x (ic type: %#04x), firmware update will not work\n",
+ data->iap_version, data->ic_type);
return 0;
}
@@ -486,6 +495,9 @@
const u8 *fw_signature;
static const u8 signature[] = {0xAA, 0x55, 0xCC, 0x33, 0xFF, 0xFF};
+ if (data->fw_validpage_count == 0)
+ return -EINVAL;
+
/* Look for a firmware with the product id appended. */
fw_name = kasprintf(GFP_KERNEL, ETP_FW_NAME, data->product_id);
if (!fw_name) {
diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c
index 683c840..a679e56 100644
--- a/drivers/input/mouse/elan_i2c_i2c.c
+++ b/drivers/input/mouse/elan_i2c_i2c.c
@@ -276,7 +276,7 @@
return 0;
}
-static int elan_i2c_get_product_id(struct i2c_client *client, u8 *id)
+static int elan_i2c_get_product_id(struct i2c_client *client, u16 *id)
{
int error;
u8 val[3];
@@ -287,7 +287,7 @@
return error;
}
- *id = val[0];
+ *id = le16_to_cpup((__le16 *)val);
return 0;
}
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index ff36a36..cb6aecb 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -183,7 +183,7 @@
return 0;
}
-static int elan_smbus_get_product_id(struct i2c_client *client, u8 *id)
+static int elan_smbus_get_product_id(struct i2c_client *client, u16 *id)
{
int error;
u8 val[3];
@@ -195,7 +195,7 @@
return error;
}
- *id = val[1];
+ *id = be16_to_cpup((__be16 *)val);
return 0;
}
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 994ae78..6025eb4 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -519,18 +519,14 @@
struct synaptics_data *priv = psmouse->private;
priv->mode = 0;
-
- if (priv->absolute_mode) {
+ if (priv->absolute_mode)
priv->mode |= SYN_BIT_ABSOLUTE_MODE;
- if (SYN_CAP_EXTENDED(priv->capabilities))
- priv->mode |= SYN_BIT_W_MODE;
- }
-
- if (!SYN_MODE_WMODE(priv->mode) && priv->disable_gesture)
+ if (priv->disable_gesture)
priv->mode |= SYN_BIT_DISABLE_GESTURE;
-
if (psmouse->rate >= 80)
priv->mode |= SYN_BIT_HIGH_RATE;
+ if (SYN_CAP_EXTENDED(priv->capabilities))
+ priv->mode |= SYN_BIT_W_MODE;
if (synaptics_mode_cmd(psmouse, priv->mode))
return -1;
diff --git a/drivers/input/serio/libps2.c b/drivers/input/serio/libps2.c
index 7551699..316f2c8 100644
--- a/drivers/input/serio/libps2.c
+++ b/drivers/input/serio/libps2.c
@@ -212,12 +212,17 @@
* time before the ACK arrives.
*/
if (ps2_sendbyte(ps2dev, command & 0xff,
- command == PS2_CMD_RESET_BAT ? 1000 : 200))
- goto out;
+ command == PS2_CMD_RESET_BAT ? 1000 : 200)) {
+ serio_pause_rx(ps2dev->serio);
+ goto out_reset_flags;
+ }
- for (i = 0; i < send; i++)
- if (ps2_sendbyte(ps2dev, param[i], 200))
- goto out;
+ for (i = 0; i < send; i++) {
+ if (ps2_sendbyte(ps2dev, param[i], 200)) {
+ serio_pause_rx(ps2dev->serio);
+ goto out_reset_flags;
+ }
+ }
/*
* The reset command takes a long time to execute.
@@ -234,17 +239,18 @@
!(ps2dev->flags & PS2_FLAG_CMD), timeout);
}
+ serio_pause_rx(ps2dev->serio);
+
if (param)
for (i = 0; i < receive; i++)
param[i] = ps2dev->cmdbuf[(receive - 1) - i];
if (ps2dev->cmdcnt && (command != PS2_CMD_RESET_BAT || ps2dev->cmdcnt != 1))
- goto out;
+ goto out_reset_flags;
rc = 0;
- out:
- serio_pause_rx(ps2dev->serio);
+ out_reset_flags:
ps2dev->flags = 0;
serio_continue_rx(ps2dev->serio);
diff --git a/drivers/input/serio/parkbd.c b/drivers/input/serio/parkbd.c
index 26b4593..1e8cd6f 100644
--- a/drivers/input/serio/parkbd.c
+++ b/drivers/input/serio/parkbd.c
@@ -194,6 +194,7 @@
parkbd_port = parkbd_allocate_serio();
if (!parkbd_port) {
parport_release(parkbd_dev);
+ parport_unregister_device(parkbd_dev);
return -ENOMEM;
}
diff --git a/drivers/input/touchscreen/imx6ul_tsc.c b/drivers/input/touchscreen/imx6ul_tsc.c
index ff0b758..8275267 100644
--- a/drivers/input/touchscreen/imx6ul_tsc.c
+++ b/drivers/input/touchscreen/imx6ul_tsc.c
@@ -94,7 +94,7 @@
* TSC module need ADC to get the measure value. So
* before config TSC, we should initialize ADC module.
*/
-static void imx6ul_adc_init(struct imx6ul_tsc *tsc)
+static int imx6ul_adc_init(struct imx6ul_tsc *tsc)
{
int adc_hc = 0;
int adc_gc;
@@ -122,17 +122,23 @@
timeout = wait_for_completion_timeout
(&tsc->completion, ADC_TIMEOUT);
- if (timeout == 0)
+ if (timeout == 0) {
dev_err(tsc->dev, "Timeout for adc calibration\n");
+ return -ETIMEDOUT;
+ }
adc_gs = readl(tsc->adc_regs + REG_ADC_GS);
- if (adc_gs & ADC_CALF)
+ if (adc_gs & ADC_CALF) {
dev_err(tsc->dev, "ADC calibration failed\n");
+ return -EINVAL;
+ }
/* TSC need the ADC work in hardware trigger */
adc_cfg = readl(tsc->adc_regs + REG_ADC_CFG);
adc_cfg |= ADC_HARDWARE_TRIGGER;
writel(adc_cfg, tsc->adc_regs + REG_ADC_CFG);
+
+ return 0;
}
/*
@@ -188,11 +194,17 @@
writel(start, tsc->tsc_regs + REG_TSC_FLOW_CONTROL);
}
-static void imx6ul_tsc_init(struct imx6ul_tsc *tsc)
+static int imx6ul_tsc_init(struct imx6ul_tsc *tsc)
{
- imx6ul_adc_init(tsc);
+ int err;
+
+ err = imx6ul_adc_init(tsc);
+ if (err)
+ return err;
imx6ul_tsc_channel_config(tsc);
imx6ul_tsc_set(tsc);
+
+ return 0;
}
static void imx6ul_tsc_disable(struct imx6ul_tsc *tsc)
@@ -311,9 +323,7 @@
return err;
}
- imx6ul_tsc_init(tsc);
-
- return 0;
+ return imx6ul_tsc_init(tsc);
}
static void imx6ul_tsc_close(struct input_dev *input_dev)
@@ -337,7 +347,7 @@
int tsc_irq;
int adc_irq;
- tsc = devm_kzalloc(&pdev->dev, sizeof(struct imx6ul_tsc), GFP_KERNEL);
+ tsc = devm_kzalloc(&pdev->dev, sizeof(*tsc), GFP_KERNEL);
if (!tsc)
return -ENOMEM;
@@ -345,7 +355,7 @@
if (!input_dev)
return -ENOMEM;
- input_dev->name = "iMX6UL TouchScreen Controller";
+ input_dev->name = "iMX6UL Touchscreen Controller";
input_dev->id.bustype = BUS_HOST;
input_dev->open = imx6ul_tsc_open;
@@ -406,7 +416,7 @@
}
adc_irq = platform_get_irq(pdev, 1);
- if (adc_irq <= 0) {
+ if (adc_irq < 0) {
dev_err(&pdev->dev, "no adc irq resource?\n");
return adc_irq;
}
@@ -491,7 +501,7 @@
goto out;
}
- imx6ul_tsc_init(tsc);
+ retval = imx6ul_tsc_init(tsc);
}
out:
diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c
index 7cce876..1fafc9f 100644
--- a/drivers/input/touchscreen/mms114.c
+++ b/drivers/input/touchscreen/mms114.c
@@ -394,12 +394,12 @@
if (of_property_read_u32(np, "x-size", &pdata->x_size)) {
dev_err(dev, "failed to get x-size property\n");
return NULL;
- };
+ }
if (of_property_read_u32(np, "y-size", &pdata->y_size)) {
dev_err(dev, "failed to get y-size property\n");
return NULL;
- };
+ }
of_property_read_u32(np, "contact-threshold",
&pdata->contact_threshold);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 4664c2a..d9da766 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -43,7 +43,7 @@
endmenu
config IOMMU_IOVA
- bool
+ tristate
config OF_IOMMU
def_bool y
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 2d7349a..041bc18 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3215,6 +3215,8 @@
/* Restrict dma_mask to the width that the iommu can handle */
dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+ /* Ensure we reserve the whole size-aligned region */
+ nrpages = __roundup_pow_of_two(nrpages);
if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
/*
@@ -3711,7 +3713,7 @@
static int __init iommu_init_mempool(void)
{
int ret;
- ret = iommu_iova_cache_init();
+ ret = iova_cache_get();
if (ret)
return ret;
@@ -3725,7 +3727,7 @@
kmem_cache_destroy(iommu_domain_cache);
domain_error:
- iommu_iova_cache_destroy();
+ iova_cache_put();
return -ENOMEM;
}
@@ -3734,7 +3736,7 @@
{
kmem_cache_destroy(iommu_devinfo_cache);
kmem_cache_destroy(iommu_domain_cache);
- iommu_iova_cache_destroy();
+ iova_cache_put();
}
static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index b7c3d92..fa0adef 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -18,42 +18,9 @@
*/
#include <linux/iova.h>
+#include <linux/module.h>
#include <linux/slab.h>
-static struct kmem_cache *iommu_iova_cache;
-
-int iommu_iova_cache_init(void)
-{
- int ret = 0;
-
- iommu_iova_cache = kmem_cache_create("iommu_iova",
- sizeof(struct iova),
- 0,
- SLAB_HWCACHE_ALIGN,
- NULL);
- if (!iommu_iova_cache) {
- pr_err("Couldn't create iova cache\n");
- ret = -ENOMEM;
- }
-
- return ret;
-}
-
-void iommu_iova_cache_destroy(void)
-{
- kmem_cache_destroy(iommu_iova_cache);
-}
-
-struct iova *alloc_iova_mem(void)
-{
- return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
-}
-
-void free_iova_mem(struct iova *iova)
-{
- kmem_cache_free(iommu_iova_cache, iova);
-}
-
void
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
unsigned long start_pfn, unsigned long pfn_32bit)
@@ -72,6 +39,7 @@
iovad->start_pfn = start_pfn;
iovad->dma_32bit_pfn = pfn_32bit;
}
+EXPORT_SYMBOL_GPL(init_iova_domain);
static struct rb_node *
__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
@@ -120,19 +88,14 @@
}
}
-/* Computes the padding size required, to make the
- * the start address naturally aligned on its size
+/*
+ * Computes the padding size required, to make the start address
+ * naturally aligned on the power-of-two order of its size
*/
-static int
-iova_get_pad_size(int size, unsigned int limit_pfn)
+static unsigned int
+iova_get_pad_size(unsigned int size, unsigned int limit_pfn)
{
- unsigned int pad_size = 0;
- unsigned int order = ilog2(size);
-
- if (order)
- pad_size = (limit_pfn + 1) % (1 << order);
-
- return pad_size;
+ return (limit_pfn + 1 - size) & (__roundup_pow_of_two(size) - 1);
}
static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
@@ -242,6 +205,57 @@
rb_insert_color(&iova->node, root);
}
+static struct kmem_cache *iova_cache;
+static unsigned int iova_cache_users;
+static DEFINE_MUTEX(iova_cache_mutex);
+
+struct iova *alloc_iova_mem(void)
+{
+ return kmem_cache_alloc(iova_cache, GFP_ATOMIC);
+}
+EXPORT_SYMBOL(alloc_iova_mem);
+
+void free_iova_mem(struct iova *iova)
+{
+ kmem_cache_free(iova_cache, iova);
+}
+EXPORT_SYMBOL(free_iova_mem);
+
+int iova_cache_get(void)
+{
+ mutex_lock(&iova_cache_mutex);
+ if (!iova_cache_users) {
+ iova_cache = kmem_cache_create(
+ "iommu_iova", sizeof(struct iova), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!iova_cache) {
+ mutex_unlock(&iova_cache_mutex);
+ printk(KERN_ERR "Couldn't create iova cache\n");
+ return -ENOMEM;
+ }
+ }
+
+ iova_cache_users++;
+ mutex_unlock(&iova_cache_mutex);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iova_cache_get);
+
+void iova_cache_put(void)
+{
+ mutex_lock(&iova_cache_mutex);
+ if (WARN_ON(!iova_cache_users)) {
+ mutex_unlock(&iova_cache_mutex);
+ return;
+ }
+ iova_cache_users--;
+ if (!iova_cache_users)
+ kmem_cache_destroy(iova_cache);
+ mutex_unlock(&iova_cache_mutex);
+}
+EXPORT_SYMBOL_GPL(iova_cache_put);
+
/**
* alloc_iova - allocates an iova
* @iovad: - iova domain in question
@@ -265,12 +279,6 @@
if (!new_iova)
return NULL;
- /* If size aligned is set then round the size to
- * to next power of two.
- */
- if (size_aligned)
- size = __roundup_pow_of_two(size);
-
ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
new_iova, size_aligned);
@@ -281,6 +289,7 @@
return new_iova;
}
+EXPORT_SYMBOL_GPL(alloc_iova);
/**
* find_iova - find's an iova for a given pfn
@@ -321,6 +330,7 @@
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return NULL;
}
+EXPORT_SYMBOL_GPL(find_iova);
/**
* __free_iova - frees the given iova
@@ -339,6 +349,7 @@
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
free_iova_mem(iova);
}
+EXPORT_SYMBOL_GPL(__free_iova);
/**
* free_iova - finds and frees the iova for a given pfn
@@ -356,6 +367,7 @@
__free_iova(iovad, iova);
}
+EXPORT_SYMBOL_GPL(free_iova);
/**
* put_iova_domain - destroys the iova doamin
@@ -378,6 +390,7 @@
}
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
}
+EXPORT_SYMBOL_GPL(put_iova_domain);
static int
__is_range_overlap(struct rb_node *node,
@@ -467,6 +480,7 @@
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return iova;
}
+EXPORT_SYMBOL_GPL(reserve_iova);
/**
* copy_reserved_iova - copies the reserved between domains
@@ -493,6 +507,7 @@
}
spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
}
+EXPORT_SYMBOL_GPL(copy_reserved_iova);
struct iova *
split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
@@ -534,3 +549,6 @@
free_iova_mem(prev);
return NULL;
}
+
+MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index cf351c6..a7c8c9f 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -62,7 +62,7 @@
dev_alias->dev_id = alias;
if (pdev != dev_alias->pdev)
- dev_alias->count += its_pci_msi_vec_count(dev_alias->pdev);
+ dev_alias->count += its_pci_msi_vec_count(pdev);
return 0;
}
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index ac7ae2b..25ceae9f 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -719,6 +719,9 @@
out:
spin_unlock(&lpi_lock);
+ if (!bitmap)
+ *base = *nr_ids = 0;
+
return bitmap;
}
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index af2f16b..aeaa061 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -320,6 +320,14 @@
intrmask[i] = gic_read(intrmask_reg);
pending_reg += gic_reg_step;
intrmask_reg += gic_reg_step;
+
+ if (!config_enabled(CONFIG_64BIT) || mips_cm_is64)
+ continue;
+
+ pending[i] |= (u64)gic_read(pending_reg) << 32;
+ intrmask[i] |= (u64)gic_read(intrmask_reg) << 32;
+ pending_reg += gic_reg_step;
+ intrmask_reg += gic_reg_step;
}
bitmap_and(pending, pending, intrmask, gic_shared_intrs);
@@ -426,7 +434,7 @@
spin_lock_irqsave(&gic_lock, flags);
/* Re-route this IRQ */
- gic_map_to_vpe(irq, cpumask_first(&tmp));
+ gic_map_to_vpe(irq, mips_cm_vp_id(cpumask_first(&tmp)));
/* Update the pcpu_masks */
for (i = 0; i < NR_CPUS; i++)
@@ -599,7 +607,7 @@
GIC_SHARED_TO_HWIRQ(intr));
int i;
- gic_map_to_vpe(intr, cpu);
+ gic_map_to_vpe(intr, mips_cm_vp_id(cpu));
for (i = 0; i < NR_CPUS; i++)
clear_bit(intr, pcpu_masks[i].pcpu_mask);
set_bit(intr, pcpu_masks[cpu].pcpu_mask);
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index e51de52..48b5890 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1997,7 +1997,8 @@
if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file)
ret = bitmap_storage_alloc(&store, chunks,
!bitmap->mddev->bitmap_info.external,
- bitmap->cluster_slot);
+ mddev_is_clustered(bitmap->mddev)
+ ? bitmap->cluster_slot : 0);
if (ret)
goto err;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4f5ecbe..c702de1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5409,9 +5409,13 @@
* which will now never happen */
wake_up_process(mddev->sync_thread->tsk);
+ if (mddev->external && test_bit(MD_CHANGE_PENDING, &mddev->flags))
+ return -EBUSY;
mddev_unlock(mddev);
wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
&mddev->recovery));
+ wait_event(mddev->sb_wait,
+ !test_bit(MD_CHANGE_PENDING, &mddev->flags));
mddev_lock_nointr(mddev);
mutex_lock(&mddev->open_mutex);
@@ -8160,6 +8164,7 @@
md_reap_sync_thread(mddev);
clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
goto unlock;
}
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index d222522..d132f06 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -470,8 +470,7 @@
return 0;
out_free_conf:
- if (conf->pool)
- mempool_destroy(conf->pool);
+ mempool_destroy(conf->pool);
kfree(conf->multipaths);
kfree(conf);
mddev->private = NULL;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 63e619b..f8e5db0 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -376,12 +376,6 @@
struct md_rdev *rdev;
bool discard_supported = false;
- rdev_for_each(rdev, mddev) {
- disk_stack_limits(mddev->gendisk, rdev->bdev,
- rdev->data_offset << 9);
- if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
- discard_supported = true;
- }
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
@@ -390,6 +384,12 @@
blk_queue_io_opt(mddev->queue,
(mddev->chunk_sectors << 9) * mddev->raid_disks);
+ rdev_for_each(rdev, mddev) {
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
+ if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ discard_supported = true;
+ }
if (!discard_supported)
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
else
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4517f06..049df6c 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -881,8 +881,7 @@
}
if (bio && bio_data_dir(bio) == WRITE) {
- if (bio->bi_iter.bi_sector >=
- conf->mddev->curr_resync_completed) {
+ if (bio->bi_iter.bi_sector >= conf->next_resync) {
if (conf->start_next_window == MaxSector)
conf->start_next_window =
conf->next_resync +
@@ -1516,7 +1515,7 @@
conf->r1buf_pool = NULL;
spin_lock_irq(&conf->resync_lock);
- conf->next_resync = 0;
+ conf->next_resync = MaxSector - 2 * NEXT_NORMALIO_DISTANCE;
conf->start_next_window = MaxSector;
conf->current_window_requests +=
conf->next_window_requests;
@@ -2843,8 +2842,7 @@
abort:
if (conf) {
- if (conf->r1bio_pool)
- mempool_destroy(conf->r1bio_pool);
+ mempool_destroy(conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
@@ -2946,8 +2944,7 @@
{
struct r1conf *conf = priv;
- if (conf->r1bio_pool)
- mempool_destroy(conf->r1bio_pool);
+ mempool_destroy(conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0fc33eb..7c99a40 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3486,8 +3486,7 @@
printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n",
mdname(mddev));
if (conf) {
- if (conf->r10bio_pool)
- mempool_destroy(conf->r10bio_pool);
+ mempool_destroy(conf->r10bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf);
@@ -3682,8 +3681,7 @@
out_free_conf:
md_unregister_thread(&mddev->thread);
- if (conf->r10bio_pool)
- mempool_destroy(conf->r10bio_pool);
+ mempool_destroy(conf->r10bio_pool);
safe_put_page(conf->tmppage);
kfree(conf->mirrors);
kfree(conf);
@@ -3696,8 +3694,7 @@
{
struct r10conf *conf = priv;
- if (conf->r10bio_pool)
- mempool_destroy(conf->r10bio_pool);
+ mempool_destroy(conf->r10bio_pool);
safe_put_page(conf->tmppage);
kfree(conf->mirrors);
kfree(conf->mirrors_old);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 15ef2c6..49bb8d3 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2271,8 +2271,7 @@
drop_one_stripe(conf))
;
- if (conf->slab_cache)
- kmem_cache_destroy(conf->slab_cache);
+ kmem_cache_destroy(conf->slab_cache);
conf->slab_cache = NULL;
}
@@ -3150,6 +3149,8 @@
spin_unlock_irq(&sh->stripe_lock);
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
+ if (bi)
+ s->to_read--;
while (bi && bi->bi_iter.bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi =
@@ -3169,6 +3170,8 @@
*/
clear_bit(R5_LOCKED, &sh->dev[i].flags);
}
+ s->to_write = 0;
+ s->written = 0;
if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
if (atomic_dec_and_test(&conf->pending_full_writes))
@@ -3300,7 +3303,7 @@
*/
return 0;
- for (i = 0; i < s->failed; i++) {
+ for (i = 0; i < s->failed && i < 2; i++) {
if (fdev[i]->towrite &&
!test_bit(R5_UPTODATE, &fdev[i]->flags) &&
!test_bit(R5_OVERWRITE, &fdev[i]->flags))
@@ -3324,7 +3327,7 @@
sh->sector < sh->raid_conf->mddev->recovery_cp)
/* reconstruct-write isn't being forced */
return 0;
- for (i = 0; i < s->failed; i++) {
+ for (i = 0; i < s->failed && i < 2; i++) {
if (s->failed_num[i] != sh->pd_idx &&
s->failed_num[i] != sh->qd_idx &&
!test_bit(R5_UPTODATE, &fdev[i]->flags) &&
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 0520064..a3eb20b 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -134,9 +134,11 @@
int err = cmd->error;
/* Flag re-tuning needed on CRC errors */
- if (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
+ if ((cmd->opcode != MMC_SEND_TUNING_BLOCK &&
+ cmd->opcode != MMC_SEND_TUNING_BLOCK_HS200) &&
+ (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
(mrq->data && mrq->data->error == -EILSEQ) ||
- (mrq->stop && mrq->stop->error == -EILSEQ))
+ (mrq->stop && mrq->stop->error == -EILSEQ)))
mmc_retune_needed(host);
if (err && cmd->retries && mmc_host_is_spi(host)) {
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index abd933b..5466f25 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -457,7 +457,7 @@
0, &cd_gpio_invert);
if (!ret)
dev_info(host->parent, "Got CD GPIO\n");
- else if (ret != -ENOENT)
+ else if (ret != -ENOENT && ret != -ENOSYS)
return ret;
/*
@@ -481,7 +481,7 @@
ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &ro_gpio_invert);
if (!ret)
dev_info(host->parent, "Got WP GPIO\n");
- else if (ret != -ENOENT)
+ else if (ret != -ENOENT && ret != -ENOSYS)
return ret;
if (of_property_read_bool(np, "disable-wp"))
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 1420f29..8cadd74 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -28,6 +28,7 @@
#include <linux/clk.h>
#include <linux/err.h>
#include <linux/mmc/host.h>
+#include <linux/mmc/slot-gpio.h>
#include <linux/io.h>
#include <linux/regulator/consumer.h>
#include <linux/gpio.h>
@@ -454,12 +455,8 @@
{
struct pxamci_host *host = mmc_priv(mmc);
- if (host->pdata && gpio_is_valid(host->pdata->gpio_card_ro)) {
- if (host->pdata->gpio_card_ro_invert)
- return !gpio_get_value(host->pdata->gpio_card_ro);
- else
- return gpio_get_value(host->pdata->gpio_card_ro);
- }
+ if (host->pdata && gpio_is_valid(host->pdata->gpio_card_ro))
+ return mmc_gpio_get_ro(mmc);
if (host->pdata && host->pdata->get_ro)
return !!host->pdata->get_ro(mmc_dev(mmc));
/*
@@ -551,6 +548,7 @@
static const struct mmc_host_ops pxamci_ops = {
.request = pxamci_request,
+ .get_cd = mmc_gpio_get_cd,
.get_ro = pxamci_get_ro,
.set_ios = pxamci_set_ios,
.enable_sdio_irq = pxamci_enable_sdio_irq,
@@ -790,37 +788,31 @@
gpio_power = host->pdata->gpio_power;
}
if (gpio_is_valid(gpio_power)) {
- ret = gpio_request(gpio_power, "mmc card power");
+ ret = devm_gpio_request(&pdev->dev, gpio_power,
+ "mmc card power");
if (ret) {
- dev_err(&pdev->dev, "Failed requesting gpio_power %d\n", gpio_power);
+ dev_err(&pdev->dev, "Failed requesting gpio_power %d\n",
+ gpio_power);
goto out;
}
gpio_direction_output(gpio_power,
host->pdata->gpio_power_invert);
}
- if (gpio_is_valid(gpio_ro)) {
- ret = gpio_request(gpio_ro, "mmc card read only");
- if (ret) {
- dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
- goto err_gpio_ro;
- }
- gpio_direction_input(gpio_ro);
+ if (gpio_is_valid(gpio_ro))
+ ret = mmc_gpio_request_ro(mmc, gpio_ro);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
+ goto out;
+ } else {
+ mmc->caps |= host->pdata->gpio_card_ro_invert ?
+ MMC_CAP2_RO_ACTIVE_HIGH : 0;
}
- if (gpio_is_valid(gpio_cd)) {
- ret = gpio_request(gpio_cd, "mmc card detect");
- if (ret) {
- dev_err(&pdev->dev, "Failed requesting gpio_cd %d\n", gpio_cd);
- goto err_gpio_cd;
- }
- gpio_direction_input(gpio_cd);
- ret = request_irq(gpio_to_irq(gpio_cd), pxamci_detect_irq,
- IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
- "mmc card detect", mmc);
- if (ret) {
- dev_err(&pdev->dev, "failed to request card detect IRQ\n");
- goto err_request_irq;
- }
+ if (gpio_is_valid(gpio_cd))
+ ret = mmc_gpio_request_cd(mmc, gpio_cd, 0);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed requesting gpio_cd %d\n", gpio_cd);
+ goto out;
}
if (host->pdata && host->pdata->init)
@@ -835,13 +827,7 @@
return 0;
-err_request_irq:
- gpio_free(gpio_cd);
-err_gpio_cd:
- gpio_free(gpio_ro);
-err_gpio_ro:
- gpio_free(gpio_power);
- out:
+out:
if (host) {
if (host->dma_chan_rx)
dma_release_channel(host->dma_chan_rx);
@@ -873,14 +859,6 @@
gpio_ro = host->pdata->gpio_card_ro;
gpio_power = host->pdata->gpio_power;
}
- if (gpio_is_valid(gpio_cd)) {
- free_irq(gpio_to_irq(gpio_cd), mmc);
- gpio_free(gpio_cd);
- }
- if (gpio_is_valid(gpio_ro))
- gpio_free(gpio_ro);
- if (gpio_is_valid(gpio_power))
- gpio_free(gpio_power);
if (host->vcc)
regulator_put(host->vcc);
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index a7b7a67..b981b85 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -210,6 +210,16 @@
#define SDXC_IDMAC_DES0_CES BIT(30) /* card error summary */
#define SDXC_IDMAC_DES0_OWN BIT(31) /* 1-idma owns it, 0-host owns it */
+#define SDXC_CLK_400K 0
+#define SDXC_CLK_25M 1
+#define SDXC_CLK_50M 2
+#define SDXC_CLK_50M_DDR 3
+
+struct sunxi_mmc_clk_delay {
+ u32 output;
+ u32 sample;
+};
+
struct sunxi_idma_des {
u32 config;
u32 buf_size;
@@ -229,6 +239,7 @@
struct clk *clk_mmc;
struct clk *clk_sample;
struct clk *clk_output;
+ const struct sunxi_mmc_clk_delay *clk_delays;
/* irq */
spinlock_t lock;
@@ -654,25 +665,19 @@
/* determine delays */
if (rate <= 400000) {
- oclk_dly = 180;
- sclk_dly = 42;
+ oclk_dly = host->clk_delays[SDXC_CLK_400K].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_400K].sample;
} else if (rate <= 25000000) {
- oclk_dly = 180;
- sclk_dly = 75;
+ oclk_dly = host->clk_delays[SDXC_CLK_25M].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_25M].sample;
} else if (rate <= 50000000) {
if (ios->timing == MMC_TIMING_UHS_DDR50) {
- oclk_dly = 60;
- sclk_dly = 120;
+ oclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].sample;
} else {
- oclk_dly = 90;
- sclk_dly = 150;
+ oclk_dly = host->clk_delays[SDXC_CLK_50M].output;
+ sclk_dly = host->clk_delays[SDXC_CLK_50M].sample;
}
- } else if (rate <= 100000000) {
- oclk_dly = 6;
- sclk_dly = 24;
- } else if (rate <= 200000000) {
- oclk_dly = 3;
- sclk_dly = 12;
} else {
return -EINVAL;
}
@@ -871,6 +876,7 @@
static const struct of_device_id sunxi_mmc_of_match[] = {
{ .compatible = "allwinner,sun4i-a10-mmc", },
{ .compatible = "allwinner,sun5i-a13-mmc", },
+ { .compatible = "allwinner,sun9i-a80-mmc", },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match);
@@ -884,6 +890,20 @@
.hw_reset = sunxi_mmc_hw_reset,
};
+static const struct sunxi_mmc_clk_delay sunxi_mmc_clk_delays[] = {
+ [SDXC_CLK_400K] = { .output = 180, .sample = 180 },
+ [SDXC_CLK_25M] = { .output = 180, .sample = 75 },
+ [SDXC_CLK_50M] = { .output = 90, .sample = 120 },
+ [SDXC_CLK_50M_DDR] = { .output = 60, .sample = 120 },
+};
+
+static const struct sunxi_mmc_clk_delay sun9i_mmc_clk_delays[] = {
+ [SDXC_CLK_400K] = { .output = 180, .sample = 180 },
+ [SDXC_CLK_25M] = { .output = 180, .sample = 75 },
+ [SDXC_CLK_50M] = { .output = 150, .sample = 120 },
+ [SDXC_CLK_50M_DDR] = { .output = 90, .sample = 120 },
+};
+
static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
struct platform_device *pdev)
{
@@ -895,6 +915,11 @@
else
host->idma_des_size_bits = 16;
+ if (of_device_is_compatible(np, "allwinner,sun9i-a80-mmc"))
+ host->clk_delays = sun9i_mmc_clk_delays;
+ else
+ host->clk_delays = sunxi_mmc_clk_delays;
+
ret = mmc_regulator_get_supply(host->mmc);
if (ret) {
if (ret != -EPROBE_DEFER)
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index 5bbd1f0..1fc23e4 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -926,6 +926,11 @@
goto bad;
}
+ if (data_size > ubi->leb_size) {
+ ubi_err(ubi, "bad data_size");
+ goto bad;
+ }
+
if (vol_type == UBI_VID_STATIC) {
/*
* Although from high-level point of view static volumes may
diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c
index 80bdd5b..d85c197 100644
--- a/drivers/mtd/ubi/vtbl.c
+++ b/drivers/mtd/ubi/vtbl.c
@@ -649,6 +649,7 @@
if (ubi->corr_peb_count)
ubi_err(ubi, "%d PEBs are corrupted and not used",
ubi->corr_peb_count);
+ return -ENOSPC;
}
ubi->rsvd_pebs += reserved_pebs;
ubi->avail_pebs -= reserved_pebs;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 275d9fb..eb4489f9 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1601,6 +1601,7 @@
if (ubi->corr_peb_count)
ubi_err(ubi, "%d PEBs are corrupted and not used",
ubi->corr_peb_count);
+ err = -ENOSPC;
goto out_free;
}
ubi->avail_pebs -= reserved_pebs;
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index f8baa89..1f7dd92 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -2051,6 +2051,8 @@
reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA;
else
reg |= PORT_CONTROL_FRAME_MODE_DSA;
+ reg |= PORT_CONTROL_FORWARD_UNKNOWN |
+ PORT_CONTROL_FORWARD_UNKNOWN_MC;
}
if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index b7a0f78..9e59663 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1543,7 +1543,7 @@
}
/* Flush FLI data fifo. */
-static u32
+static int
bfa_flash_fifo_flush(void __iomem *pci_bar)
{
u32 i;
@@ -1573,11 +1573,11 @@
}
/* Read flash status. */
-static u32
+static int
bfa_flash_status_read(void __iomem *pci_bar)
{
union bfa_flash_dev_status_reg dev_status;
- u32 status;
+ int status;
u32 ret_status;
int i;
@@ -1611,11 +1611,11 @@
}
/* Start flash read operation. */
-static u32
+static int
bfa_flash_read_start(void __iomem *pci_bar, u32 offset, u32 len,
char *buf)
{
- u32 status;
+ int status;
/* len must be mutiple of 4 and not exceeding fifo size */
if (len == 0 || len > BFA_FLASH_FIFO_SIZE || (len & 0x03) != 0)
@@ -1703,7 +1703,8 @@
bfa_flash_raw_read(void __iomem *pci_bar, u32 offset, char *buf,
u32 len)
{
- u32 n, status;
+ u32 n;
+ int status;
u32 off, l, s, residue, fifo_sz;
residue = len;
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index cc2d8b4..253f8ed 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -816,7 +816,7 @@
struct net_device *ndev;
struct hip04_priv *priv;
struct resource *res;
- unsigned int irq;
+ int irq;
int ret;
ndev = alloc_etherdev(sizeof(struct hip04_priv));
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 28df374..ac02c67 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -460,8 +460,8 @@
u32 index;
};
-#define EMAC_ETHTOOL_REGS_VER 0
-#define EMAC4_ETHTOOL_REGS_VER 1
-#define EMAC4SYNC_ETHTOOL_REGS_VER 2
+#define EMAC_ETHTOOL_REGS_VER 3
+#define EMAC4_ETHTOOL_REGS_VER 4
+#define EMAC4SYNC_ETHTOOL_REGS_VER 5
#endif /* __IBM_NEWEMAC_CORE_H */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 3e0d200..62488a6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -946,6 +946,13 @@
/* take the lock before we start messing with the ring */
mutex_lock(&hw->aq.arq_mutex);
+ if (hw->aq.arq.count == 0) {
+ i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ "AQRX: Admin queue not initialized.\n");
+ ret_code = I40E_ERR_QUEUE_EMPTY;
+ goto clean_arq_element_err;
+ }
+
/* set next_to_use to head */
ntu = (rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK);
if (ntu == ntc) {
@@ -1007,6 +1014,8 @@
/* Set pending if needed, unlock and return */
if (pending != NULL)
*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+
+clean_arq_element_err:
mutex_unlock(&hw->aq.arq_mutex);
if (i40e_is_nvm_update_op(&e->desc)) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 851c1a15..2fdf978 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2672,7 +2672,8 @@
rx_ctx.lrxqthresh = 2;
rx_ctx.crcstrip = 1;
rx_ctx.l2tsel = 1;
- rx_ctx.showiv = 1;
+ /* this controls whether VLAN is stripped from inner headers */
+ rx_ctx.showiv = 0;
#ifdef I40E_FCOE
rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
#endif
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index f08450b..929d471 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -887,6 +887,13 @@
/* take the lock before we start messing with the ring */
mutex_lock(&hw->aq.arq_mutex);
+ if (hw->aq.arq.count == 0) {
+ i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+ "AQRX: Admin queue not initialized.\n");
+ ret_code = I40E_ERR_QUEUE_EMPTY;
+ goto clean_arq_element_err;
+ }
+
/* set next_to_use to head */
ntu = (rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK);
if (ntu == ntc) {
@@ -948,6 +955,8 @@
/* Set pending if needed, unlock and return */
if (pending != NULL)
*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+
+clean_arq_element_err:
mutex_unlock(&hw->aq.arq_mutex);
return ret_code;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index bd9ea0d..1d4e2e0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1184,10 +1184,11 @@
if (prot == MLX4_PROT_ETH) {
/* manage the steering entry for promisc mode */
if (new_entry)
- new_steering_entry(dev, port, steer, index, qp->qpn);
+ err = new_steering_entry(dev, port, steer,
+ index, qp->qpn);
else
- existing_steering_entry(dev, port, steer,
- index, qp->qpn);
+ err = existing_steering_entry(dev, port, steer,
+ index, qp->qpn);
}
if (err && link && index != -1) {
if (index < dev->caps.num_mgms)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index aa0d5ff..9335e5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -200,25 +200,3 @@
return err;
}
-
-int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey)
-{
- struct mlx5_cmd_query_special_contexts_mbox_in in;
- struct mlx5_cmd_query_special_contexts_mbox_out out;
- int err;
-
- memset(&in, 0, sizeof(in));
- memset(&out, 0, sizeof(out));
- in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
- err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
- if (err)
- return err;
-
- if (out.hdr.status)
- err = mlx5_cmd_status_to_err(&out.hdr);
-
- *rsvd_lkey = be32_to_cpu(out.resd_lkey);
-
- return err;
-}
-EXPORT_SYMBOL(mlx5_core_query_special_context);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 2b32e0c..b4f2123 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6081,7 +6081,7 @@
{
void __iomem *ioaddr = tp->mmio_addr;
struct pci_dev *pdev = tp->pci_dev;
- u16 rg_saw_cnt;
+ int rg_saw_cnt;
u32 data;
static const struct ephy_info e_info_8168h_1[] = {
{ 0x1e, 0x0800, 0x0001 },
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index dd652f2..108a311 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -299,9 +299,10 @@
* Unbound PCI devices are always put in D0, regardless of
* runtime PM status. During probe, the device is set to
* active and the usage count is incremented. If the driver
- * supports runtime PM, it should call pm_runtime_put_noidle()
- * in its probe routine and pm_runtime_get_noresume() in its
- * remove routine.
+ * supports runtime PM, it should call pm_runtime_put_noidle(),
+ * or any other runtime PM helper function decrementing the usage
+ * count, in its probe routine and pm_runtime_get_noresume() in
+ * its remove routine.
*/
pm_runtime_get_sync(dev);
pci_dev->driver = pci_drv;
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index d9de36e..04e2653 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -5,7 +5,7 @@
menu "Performance monitor support"
config ARM_PMU
- depends on PERF_EVENTS && ARM
+ depends on PERF_EVENTS && (ARM || ARM64)
bool "ARM PMU framework"
default y
help
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index cbfc599..126a48c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1957,7 +1957,7 @@
static void scsi_mq_done(struct scsi_cmnd *cmd)
{
trace_scsi_dispatch_cmd_done(cmd);
- blk_mq_complete_request(cmd->request);
+ blk_mq_complete_request(cmd->request, cmd->request->errors);
}
static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index 7ff9627..e570ff0 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -144,6 +144,16 @@
switch_on_temp = 0;
temperature_threshold = control_temp - switch_on_temp;
+ /*
+ * estimate_pid_constants() tries to find appropriate default
+ * values for thermal zones that don't provide them. If a
+ * system integrator has configured a thermal zone with two
+ * passive trip points at the same temperature, that person
+ * hasn't put any effort to set up the thermal zone properly
+ * so just give up.
+ */
+ if (!temperature_threshold)
+ return;
if (!tz->tzp->k_po || force)
tz->tzp->k_po = int_to_frac(sustainable_power) /
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index c68edc1..79e1aa1 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -817,8 +817,9 @@
tristate "Intel TCO Timer/Watchdog"
depends on (X86 || IA64) && PCI
select WATCHDOG_CORE
+ depends on I2C || I2C=n
select LPC_ICH if !EXPERT
- select I2C_I801 if !EXPERT
+ select I2C_I801 if !EXPERT && I2C
---help---
Hardware driver for the intel TCO timer based watchdog devices.
These drivers are included in the Intel 82801 I/O Controller
diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c
index 66c3e65..8a5ce5b 100644
--- a/drivers/watchdog/bcm2835_wdt.c
+++ b/drivers/watchdog/bcm2835_wdt.c
@@ -36,6 +36,13 @@
#define PM_RSTC_WRCFG_FULL_RESET 0x00000020
#define PM_RSTC_RESET 0x00000102
+/*
+ * The Raspberry Pi firmware uses the RSTS register to know which partiton
+ * to boot from. The partiton value is spread into bits 0, 2, 4, 6, 8, 10.
+ * Partiton 63 is a special partition used by the firmware to indicate halt.
+ */
+#define PM_RSTS_RASPBERRYPI_HALT 0x555
+
#define SECS_TO_WDOG_TICKS(x) ((x) << 16)
#define WDOG_TICKS_TO_SECS(x) ((x) >> 16)
@@ -151,8 +158,7 @@
* hard reset.
*/
val = readl_relaxed(wdt->base + PM_RSTS);
- val &= PM_RSTC_WRCFG_CLR;
- val |= PM_PASSWORD | PM_RSTS_HADWRH_SET;
+ val |= PM_PASSWORD | PM_RSTS_RASPBERRYPI_HALT;
writel_relaxed(val, wdt->base + PM_RSTS);
/* Continue with normal reset mechanism */
diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c
index cc1bdfc..006e234 100644
--- a/drivers/watchdog/gef_wdt.c
+++ b/drivers/watchdog/gef_wdt.c
@@ -303,6 +303,7 @@
},
{},
};
+MODULE_DEVICE_TABLE(of, gef_wdt_ids);
static struct platform_driver gef_wdt_driver = {
.driver = {
diff --git a/drivers/watchdog/mena21_wdt.c b/drivers/watchdog/mena21_wdt.c
index 6901300..098fa9c3 100644
--- a/drivers/watchdog/mena21_wdt.c
+++ b/drivers/watchdog/mena21_wdt.c
@@ -253,6 +253,7 @@
{ .compatible = "men,a021-wdt" },
{ },
};
+MODULE_DEVICE_TABLE(of, a21_wdt_ids);
static struct platform_driver a21_wdt_driver = {
.probe = a21_wdt_probe,
diff --git a/drivers/watchdog/moxart_wdt.c b/drivers/watchdog/moxart_wdt.c
index 2789da2..60b0605 100644
--- a/drivers/watchdog/moxart_wdt.c
+++ b/drivers/watchdog/moxart_wdt.c
@@ -168,6 +168,7 @@
{ .compatible = "moxa,moxart-watchdog" },
{ },
};
+MODULE_DEVICE_TABLE(of, moxart_watchdog_match);
static struct platform_driver moxart_wdt_driver = {
.probe = moxart_wdt_probe,
diff --git a/fs/dax.c b/fs/dax.c
index 7ae6df7..bcfb14b 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -569,8 +569,20 @@
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
goto fallback;
+ sector = bh.b_blocknr << (blkbits - 9);
+
if (buffer_unwritten(&bh) || buffer_new(&bh)) {
int i;
+
+ length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
+ bh.b_size);
+ if (length < 0) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
+ goto fallback;
+
for (i = 0; i < PTRS_PER_PMD; i++)
clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
wmb_pmem();
@@ -623,7 +635,6 @@
result = VM_FAULT_NOPAGE;
spin_unlock(ptl);
} else {
- sector = bh.b_blocknr << (blkbits - 9);
length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
bh.b_size);
if (length < 0) {
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 96f3448..fd65b3f 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -652,11 +652,8 @@
{
int err;
- mutex_lock(&inode->i_mutex);
err = security_inode_init_security(inode, dentry, qstr,
&init_xattrs, 0);
- mutex_unlock(&inode->i_mutex);
-
if (err) {
struct ubifs_info *c = dentry->i_sb->s_fs_info;
ubifs_err(c, "cannot initialize security for inode %lu, error %d",
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index 94f9ea8..011dde0 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -1,15 +1,10 @@
#ifndef _ASM_WORD_AT_A_TIME_H
#define _ASM_WORD_AT_A_TIME_H
-/*
- * This says "generic", but it's actually big-endian only.
- * Little-endian can use more efficient versions of these
- * interfaces, see for example
- * arch/x86/include/asm/word-at-a-time.h
- * for those.
- */
-
#include <linux/kernel.h>
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN
struct word_at_a_time {
const unsigned long high_bits, low_bits;
@@ -53,4 +48,73 @@
#define zero_bytemask(mask) (~1ul << __fls(mask))
#endif
+#else
+
+/*
+ * The optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+ return mask*0x0001020304050608ul >> 56;
+}
+
+#else /* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
+}
+
+#endif
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+ unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+ return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+ return count_masked_bytes(mask);
+}
+
+#endif /* __BIG_ENDIAN */
+
#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index 2a747a9..3febb4b 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -240,5 +240,6 @@
extern void drm_kms_helper_poll_disable(struct drm_device *dev);
extern void drm_kms_helper_poll_enable(struct drm_device *dev);
+extern void drm_kms_helper_poll_enable_locked(struct drm_device *dev);
#endif
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 499e9f6..0212d13 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -568,6 +568,10 @@
#define MODE_I2C_READ 4
#define MODE_I2C_STOP 8
+/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */
+#define DP_MST_PHYSICAL_PORT_0 0
+#define DP_MST_LOGICAL_PORT_0 8
+
#define DP_LINK_STATUS_SIZE 6
bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE],
int lane_count);
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 86d0b25..0f408b0 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -374,6 +374,7 @@
struct drm_dp_mst_topology_cbs {
/* create a connector for a port */
struct drm_connector *(*add_connector)(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *path);
+ void (*register_connector)(struct drm_connector *connector);
void (*destroy_connector)(struct drm_dp_mst_topology_mgr *mgr,
struct drm_connector *connector);
void (*hotplug)(struct drm_dp_mst_topology_mgr *mgr);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7235c48..43856d1 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -217,6 +217,7 @@
int acpi_pci_irq_enable (struct pci_dev *dev);
void acpi_penalize_isa_irq(int irq, int active);
+bool acpi_isa_irq_available(int irq);
void acpi_penalize_sci_irq(int irq, int trigger, int polarity);
void acpi_pci_irq_disable (struct pci_dev *dev);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 37d1602..5e7d43a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -145,7 +145,6 @@
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
BLK_MQ_F_TAG_SHARED = 1 << 1,
BLK_MQ_F_SG_MERGE = 1 << 2,
- BLK_MQ_F_SYSFS_UP = 1 << 3,
BLK_MQ_F_DEFER_ISSUE = 1 << 4,
BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
BLK_MQ_F_ALLOC_POLICY_BITS = 1,
@@ -215,7 +214,7 @@
void blk_mq_cancel_requeue_work(struct request_queue *q);
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_abort_requeue_list(struct request_queue *q);
-void blk_mq_complete_request(struct request *rq);
+void blk_mq_complete_request(struct request *rq, int error);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
@@ -224,8 +223,6 @@
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
-void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
- void *priv);
void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
void *priv);
void blk_mq_freeze_queue(struct request_queue *q);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 99da9eb..19c2e94 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -456,6 +456,8 @@
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set *bio_split;
+
+ bool mq_sysfs_init_done;
};
#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 3920a19..92f7177 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -68,8 +68,8 @@
return iova >> iova_shift(iovad);
}
-int iommu_iova_cache_init(void);
-void iommu_iova_cache_destroy(void);
+int iova_cache_get(void);
+void iova_cache_put(void);
struct iova *alloc_iova_mem(void);
void free_iova_mem(struct iova *iova);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ad800e6..6452ff4 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -242,7 +242,6 @@
* percpu counter.
*/
struct mem_cgroup_stat_cpu __percpu *stat;
- spinlock_t pcp_counter_lock;
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
struct cg_proto tcp_mem;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 8eb3b19..250b1ff 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -402,17 +402,6 @@
u8 rsvd[8];
};
-struct mlx5_cmd_query_special_contexts_mbox_in {
- struct mlx5_inbox_hdr hdr;
- u8 rsvd[8];
-};
-
-struct mlx5_cmd_query_special_contexts_mbox_out {
- struct mlx5_outbox_hdr hdr;
- __be32 dump_fill_mkey;
- __be32 resd_lkey;
-};
-
struct mlx5_cmd_layout {
u8 type;
u8 rsvd0[3];
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 27b53f9..8b6d6f2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -845,7 +845,6 @@
int mlx5_register_interface(struct mlx5_interface *intf);
void mlx5_unregister_interface(struct mlx5_interface *intf);
int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
-int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey);
struct mlx5_profile {
u64 mask;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 91c08f6..80001de 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -905,6 +905,27 @@
#endif
}
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+ return page->mem_cgroup;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+ page->mem_cgroup = memcg;
+}
+#else
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+ return NULL;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+}
+#endif
+
/*
* Some inline functions in vmstat.h depend on page_zone()
*/
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ff47651..581abf8 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -230,12 +230,11 @@
struct rcu_synchronize *rs_array);
#define _wait_rcu_gp(checktiny, ...) \
-do { \
- call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \
- const int __n = ARRAY_SIZE(__crcu_array); \
- struct rcu_synchronize __rs_array[__n]; \
- \
- __wait_rcu_gp(checktiny, __n, __crcu_array, __rs_array); \
+do { \
+ call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \
+ struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \
+ __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \
+ __crcu_array, __rs_array); \
} while (0)
#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2b0a30a..4398411 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2708,7 +2708,7 @@
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
else if (skb->ip_summed == CHECKSUM_PARTIAL &&
- skb_checksum_start_offset(skb) <= len)
+ skb_checksum_start_offset(skb) < 0)
skb->ip_summed = CHECKSUM_NONE;
}
diff --git a/include/linux/string.h b/include/linux/string.h
index a8d90db..9ef7795 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -25,6 +25,9 @@
#ifndef __HAVE_ARCH_STRLCPY
size_t strlcpy(char *, const char *, size_t);
#endif
+#ifndef __HAVE_ARCH_STRSCPY
+ssize_t __must_check strscpy(char *, const char *, size_t);
+#endif
#ifndef __HAVE_ARCH_STRCAT
extern char * strcat(char *, const char *);
#endif
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 4a167b3..cb1b9bb 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -63,7 +63,11 @@
#define UNIX_GC_MAYBE_CYCLE 1
struct socket_wq peer_wq;
};
-#define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+static inline struct unix_sock *unix_sk(struct sock *sk)
+{
+ return (struct unix_sock *)sk;
+}
#define peer_wait peer_wq.wait
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index df0e09b..9057d7a 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -11,8 +11,6 @@
#include <linux/types.h>
-#include <linux/compiler.h>
-
#define UFFD_API ((__u64)0xAA)
/*
* After implementing the respective features it will become:
diff --git a/ipc/msg.c b/ipc/msg.c
index 66c4f56..1471db9 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -137,13 +137,6 @@
return retval;
}
- /* ipc_addid() locks msq upon success. */
- id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
- if (id < 0) {
- ipc_rcu_putref(msq, msg_rcu_free);
- return id;
- }
-
msq->q_stime = msq->q_rtime = 0;
msq->q_ctime = get_seconds();
msq->q_cbytes = msq->q_qnum = 0;
@@ -153,6 +146,13 @@
INIT_LIST_HEAD(&msq->q_receivers);
INIT_LIST_HEAD(&msq->q_senders);
+ /* ipc_addid() locks msq upon success. */
+ id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
+ if (id < 0) {
+ ipc_rcu_putref(msq, msg_rcu_free);
+ return id;
+ }
+
ipc_unlock_object(&msq->q_perm);
rcu_read_unlock();
diff --git a/ipc/shm.c b/ipc/shm.c
index 222131e..4178727 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -551,12 +551,6 @@
if (IS_ERR(file))
goto no_file;
- id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
- if (id < 0) {
- error = id;
- goto no_id;
- }
-
shp->shm_cprid = task_tgid_vnr(current);
shp->shm_lprid = 0;
shp->shm_atim = shp->shm_dtim = 0;
@@ -565,6 +559,13 @@
shp->shm_nattch = 0;
shp->shm_file = file;
shp->shm_creator = current;
+
+ id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
+ if (id < 0) {
+ error = id;
+ goto no_id;
+ }
+
list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist);
/*
diff --git a/ipc/util.c b/ipc/util.c
index be42300..0f401d9 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -237,6 +237,10 @@
rcu_read_lock();
spin_lock(&new->lock);
+ current_euid_egid(&euid, &egid);
+ new->cuid = new->uid = euid;
+ new->gid = new->cgid = egid;
+
id = idr_alloc(&ids->ipcs_idr, new,
(next_id < 0) ? 0 : ipcid_to_idx(next_id), 0,
GFP_NOWAIT);
@@ -249,10 +253,6 @@
ids->in_use++;
- current_euid_egid(&euid, &egid);
- new->cuid = new->uid = euid;
- new->gid = new->cgid = egid;
-
if (next_id < 0) {
new->seq = ids->seq++;
if (ids->seq > IPCID_SEQ_MAX)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f548f69..b11756f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1243,11 +1243,7 @@
PERF_EVENT_STATE_INACTIVE;
}
-/*
- * Called at perf_event creation and when events are attached/detached from a
- * group.
- */
-static void perf_event__read_size(struct perf_event *event)
+static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
{
int entry = sizeof(u64); /* value */
int size = 0;
@@ -1263,7 +1259,7 @@
entry += sizeof(u64);
if (event->attr.read_format & PERF_FORMAT_GROUP) {
- nr += event->group_leader->nr_siblings;
+ nr += nr_siblings;
size += sizeof(u64);
}
@@ -1271,14 +1267,11 @@
event->read_size = size;
}
-static void perf_event__header_size(struct perf_event *event)
+static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
{
struct perf_sample_data *data;
- u64 sample_type = event->attr.sample_type;
u16 size = 0;
- perf_event__read_size(event);
-
if (sample_type & PERF_SAMPLE_IP)
size += sizeof(data->ip);
@@ -1303,6 +1296,17 @@
event->header_size = size;
}
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__header_size(struct perf_event *event)
+{
+ __perf_event_read_size(event,
+ event->group_leader->nr_siblings);
+ __perf_event_header_size(event, event->attr.sample_type);
+}
+
static void perf_event__id_header_size(struct perf_event *event)
{
struct perf_sample_data *data;
@@ -1330,6 +1334,27 @@
event->id_header_size = size;
}
+static bool perf_event_validate_size(struct perf_event *event)
+{
+ /*
+ * The values computed here will be over-written when we actually
+ * attach the event.
+ */
+ __perf_event_read_size(event, event->group_leader->nr_siblings + 1);
+ __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
+ perf_event__id_header_size(event);
+
+ /*
+ * Sum the lot; should not exceed the 64k limit we have on records.
+ * Conservative limit to allow for callchains and other variable fields.
+ */
+ if (event->read_size + event->header_size +
+ event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+ return false;
+
+ return true;
+}
+
static void perf_group_attach(struct perf_event *event)
{
struct perf_event *group_leader = event->group_leader, *pos;
@@ -8297,13 +8322,35 @@
if (move_group) {
gctx = group_leader->ctx;
+ mutex_lock_double(&gctx->mutex, &ctx->mutex);
+ } else {
+ mutex_lock(&ctx->mutex);
+ }
+ if (!perf_event_validate_size(event)) {
+ err = -E2BIG;
+ goto err_locked;
+ }
+
+ /*
+ * Must be under the same ctx::mutex as perf_install_in_context(),
+ * because we need to serialize with concurrent event creation.
+ */
+ if (!exclusive_event_installable(event, ctx)) {
+ /* exclusive and group stuff are assumed mutually exclusive */
+ WARN_ON_ONCE(move_group);
+
+ err = -EBUSY;
+ goto err_locked;
+ }
+
+ WARN_ON_ONCE(ctx->parent_ctx);
+
+ if (move_group) {
/*
* See perf_event_ctx_lock() for comments on the details
* of swizzling perf_event::ctx.
*/
- mutex_lock_double(&gctx->mutex, &ctx->mutex);
-
perf_remove_from_context(group_leader, false);
list_for_each_entry(sibling, &group_leader->sibling_list,
@@ -8311,13 +8358,7 @@
perf_remove_from_context(sibling, false);
put_ctx(gctx);
}
- } else {
- mutex_lock(&ctx->mutex);
- }
- WARN_ON_ONCE(ctx->parent_ctx);
-
- if (move_group) {
/*
* Wait for everybody to stop referencing the events through
* the old lists, before installing it on new lists.
@@ -8349,22 +8390,29 @@
perf_event__state_init(group_leader);
perf_install_in_context(ctx, group_leader, group_leader->cpu);
get_ctx(ctx);
+
+ /*
+ * Now that all events are installed in @ctx, nothing
+ * references @gctx anymore, so drop the last reference we have
+ * on it.
+ */
+ put_ctx(gctx);
}
- if (!exclusive_event_installable(event, ctx)) {
- err = -EBUSY;
- mutex_unlock(&ctx->mutex);
- fput(event_file);
- goto err_context;
- }
+ /*
+ * Precalculate sample_data sizes; do while holding ctx::mutex such
+ * that we're serialized against further additions and before
+ * perf_install_in_context() which is the point the event is active and
+ * can use these values.
+ */
+ perf_event__header_size(event);
+ perf_event__id_header_size(event);
perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx);
- if (move_group) {
+ if (move_group)
mutex_unlock(&gctx->mutex);
- put_ctx(gctx);
- }
mutex_unlock(&ctx->mutex);
put_online_cpus();
@@ -8376,12 +8424,6 @@
mutex_unlock(¤t->perf_event_mutex);
/*
- * Precalculate sample_data sizes
- */
- perf_event__header_size(event);
- perf_event__id_header_size(event);
-
- /*
* Drop the reference on the group_event after placing the
* new event on the sibling_list. This ensures destruction
* of the group leader will find the pointer to itself in
@@ -8391,6 +8433,12 @@
fd_install(event_fd, event_file);
return event_fd;
+err_locked:
+ if (move_group)
+ mutex_unlock(&gctx->mutex);
+ mutex_unlock(&ctx->mutex);
+/* err_file: */
+ fput(event_file);
err_context:
perf_unpin_context(ctx);
put_ctx(ctx);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index e3a8c95..a50ddc9 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -12,6 +12,7 @@
#include <linux/seq_file.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
+#include <linux/mutex.h>
#include "internals.h"
@@ -323,18 +324,29 @@
void register_irq_proc(unsigned int irq, struct irq_desc *desc)
{
+ static DEFINE_MUTEX(register_lock);
char name [MAX_NAMELEN];
- if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
+ if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip))
return;
+ /*
+ * irq directories are registered only when a handler is
+ * added, not when the descriptor is created, so multiple
+ * tasks might try to register at the same time.
+ */
+ mutex_lock(®ister_lock);
+
+ if (desc->dir)
+ goto out_unlock;
+
memset(name, 0, MAX_NAMELEN);
sprintf(name, "%d", irq);
/* create /proc/irq/1234 */
desc->dir = proc_mkdir(name, root_irq_dir);
if (!desc->dir)
- return;
+ goto out_unlock;
#ifdef CONFIG_SMP
/* create /proc/irq/<irq>/smp_affinity */
@@ -355,6 +367,9 @@
proc_create_data("spurious", 0444, desc->dir,
&irq_spurious_proc_fops, (void *)(long)irq);
+
+out_unlock:
+ mutex_unlock(®ister_lock);
}
void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 8acfbf7..4e49cc4 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3068,7 +3068,7 @@
static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
int trylock, int read, int check, int hardirqs_off,
struct lockdep_map *nest_lock, unsigned long ip,
- int references)
+ int references, int pin_count)
{
struct task_struct *curr = current;
struct lock_class *class = NULL;
@@ -3157,7 +3157,7 @@
hlock->waittime_stamp = 0;
hlock->holdtime_stamp = lockstat_clock();
#endif
- hlock->pin_count = 0;
+ hlock->pin_count = pin_count;
if (check && !mark_irqflags(curr, hlock))
return 0;
@@ -3343,7 +3343,7 @@
hlock_class(hlock)->subclass, hlock->trylock,
hlock->read, hlock->check, hlock->hardirqs_off,
hlock->nest_lock, hlock->acquire_ip,
- hlock->references))
+ hlock->references, hlock->pin_count))
return 0;
}
@@ -3433,7 +3433,7 @@
hlock_class(hlock)->subclass, hlock->trylock,
hlock->read, hlock->check, hlock->hardirqs_off,
hlock->nest_lock, hlock->acquire_ip,
- hlock->references))
+ hlock->references, hlock->pin_count))
return 0;
}
@@ -3583,7 +3583,7 @@
current->lockdep_recursion = 1;
trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
__lock_acquire(lock, subclass, trylock, read, check,
- irqs_disabled_flags(flags), nest_lock, ip, 0);
+ irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
current->lockdep_recursion = 0;
raw_local_irq_restore(flags);
}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9f75f25..775d36c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3868,6 +3868,7 @@
static void __init
rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
{
+ static struct lock_class_key rcu_exp_sched_rdp_class;
unsigned long flags;
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_node *rnp = rcu_get_root(rsp);
@@ -3883,6 +3884,10 @@
mutex_init(&rdp->exp_funnel_mutex);
rcu_boot_init_nocb_percpu_data(rdp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ if (rsp == &rcu_sched_state)
+ lockdep_set_class_and_name(&rdp->exp_funnel_mutex,
+ &rcu_exp_sched_rdp_class,
+ "rcu_data_exp_sched");
}
/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2f9c928..6159531 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4934,7 +4934,15 @@
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
- do_set_cpus_allowed(idle, cpumask_of(cpu));
+#ifdef CONFIG_SMP
+ /*
+ * Its possible that init_idle() gets called multiple times on a task,
+ * in that case do_set_cpus_allowed() will not do the right thing.
+ *
+ * And since this is boot we can forgo the serialization.
+ */
+ set_cpus_allowed_common(idle, cpumask_of(cpu));
+#endif
/*
* We're having a chicken and egg problem, even though we are
* holding rq->lock, the cpu isn't yet set to this cpu so the
@@ -4951,7 +4959,7 @@
rq->curr = rq->idle = idle;
idle->on_rq = TASK_ON_RQ_QUEUED;
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
idle->on_cpu = 1;
#endif
raw_spin_unlock(&rq->lock);
@@ -4966,7 +4974,7 @@
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
vtime_init_idle(idle, cpu);
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
}
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 841b72f..3a38775 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -217,7 +217,7 @@
continue;
/* Check the deviation from the watchdog clocksource. */
- if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
+ if (abs64(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
cs->name);
pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
diff --git a/lib/string.c b/lib/string.c
index 13d1e84..8dbb7b1 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -27,6 +27,10 @@
#include <linux/bug.h>
#include <linux/errno.h>
+#include <asm/byteorder.h>
+#include <asm/word-at-a-time.h>
+#include <asm/page.h>
+
#ifndef __HAVE_ARCH_STRNCASECMP
/**
* strncasecmp - Case insensitive, length-limited string comparison
@@ -146,6 +150,90 @@
EXPORT_SYMBOL(strlcpy);
#endif
+#ifndef __HAVE_ARCH_STRSCPY
+/**
+ * strscpy - Copy a C-string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @count: Size of destination buffer
+ *
+ * Copy the string, or as much of it as fits, into the dest buffer.
+ * The routine returns the number of characters copied (not including
+ * the trailing NUL) or -E2BIG if the destination buffer wasn't big enough.
+ * The behavior is undefined if the string buffers overlap.
+ * The destination buffer is always NUL terminated, unless it's zero-sized.
+ *
+ * Preferred to strlcpy() since the API doesn't require reading memory
+ * from the src string beyond the specified "count" bytes, and since
+ * the return value is easier to error-check than strlcpy()'s.
+ * In addition, the implementation is robust to the string changing out
+ * from underneath it, unlike the current strlcpy() implementation.
+ *
+ * Preferred to strncpy() since it always returns a valid string, and
+ * doesn't unnecessarily force the tail of the destination buffer to be
+ * zeroed. If the zeroing is desired, it's likely cleaner to use strscpy()
+ * with an overflow test, then just memset() the tail of the dest buffer.
+ */
+ssize_t strscpy(char *dest, const char *src, size_t count)
+{
+ const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+ size_t max = count;
+ long res = 0;
+
+ if (count == 0)
+ return -E2BIG;
+
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ /*
+ * If src is unaligned, don't cross a page boundary,
+ * since we don't know if the next page is mapped.
+ */
+ if ((long)src & (sizeof(long) - 1)) {
+ size_t limit = PAGE_SIZE - ((long)src & (PAGE_SIZE - 1));
+ if (limit < max)
+ max = limit;
+ }
+#else
+ /* If src or dest is unaligned, don't do word-at-a-time. */
+ if (((long) dest | (long) src) & (sizeof(long) - 1))
+ max = 0;
+#endif
+
+ while (max >= sizeof(unsigned long)) {
+ unsigned long c, data;
+
+ c = *(unsigned long *)(src+res);
+ *(unsigned long *)(dest+res) = c;
+ if (has_zero(c, &data, &constants)) {
+ data = prep_zero_mask(c, data, &constants);
+ data = create_zero_mask(data);
+ return res + find_zero(data);
+ }
+ res += sizeof(unsigned long);
+ count -= sizeof(unsigned long);
+ max -= sizeof(unsigned long);
+ }
+
+ while (count) {
+ char c;
+
+ c = src[res];
+ dest[res] = c;
+ if (!c)
+ return res;
+ res++;
+ count--;
+ }
+
+ /* Hit buffer length without finding a NUL; force NUL-termination. */
+ if (res)
+ dest[res-1] = '\0';
+
+ return -E2BIG;
+}
+EXPORT_SYMBOL(strscpy);
+#endif
+
#ifndef __HAVE_ARCH_STRCAT
/**
* strcat - Append one %NUL-terminated string to another
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 71a8998..312a716 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -394,7 +394,7 @@
list_for_each_entry(page, &pool->page_list, page_list) {
if (dma < page->dma)
continue;
- if (dma < (page->dma + pool->allocation))
+ if ((dma - page->dma) < pool->allocation)
return page;
}
return NULL;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 999fb0a..9cc7734 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3202,6 +3202,14 @@
continue;
/*
+ * Shared VMAs have their own reserves and do not affect
+ * MAP_PRIVATE accounting but it is possible that a shared
+ * VMA is using the same page so check and skip such VMAs.
+ */
+ if (iter_vma->vm_flags & VM_MAYSHARE)
+ continue;
+
+ /*
* Unmap the page from other VMAs without their own reserves.
* They get marked to be SIGKILLed if they fault in these
* areas. This is because a future no-page fault on this VMA
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6ddaeba..1fedbde 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -644,12 +644,14 @@
}
/*
+ * Return page count for single (non recursive) @memcg.
+ *
* Implementation Note: reading percpu statistics for memcg.
*
* Both of vmstat[] and percpu_counter has threshold and do periodic
* synchronization to implement "quick" read. There are trade-off between
* reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronizion of counter in memcg's counter.
+ * a periodic synchronization of counter in memcg's counter.
*
* But this _read() function is used for user interface now. The user accounts
* memory usage by memory cgroup and he _always_ requires exact value because
@@ -659,17 +661,24 @@
*
* If there are kernel internal actions which can make use of some not-exact
* value, and reading all cpu value can be performance bottleneck in some
- * common workload, threashold and synchonization as vmstat[] should be
+ * common workload, threshold and synchronization as vmstat[] should be
* implemented.
*/
-static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
- enum mem_cgroup_stat_index idx)
+static unsigned long
+mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx)
{
long val = 0;
int cpu;
+ /* Per-cpu values can be negative, use a signed accumulator */
for_each_possible_cpu(cpu)
val += per_cpu(memcg->stat->count[idx], cpu);
+ /*
+ * Summing races with updates, so val may be negative. Avoid exposing
+ * transient negative values.
+ */
+ if (val < 0)
+ val = 0;
return val;
}
@@ -1254,7 +1263,7 @@
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
- pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+ pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
K(mem_cgroup_read_stat(iter, i)));
}
@@ -2819,14 +2828,11 @@
enum mem_cgroup_stat_index idx)
{
struct mem_cgroup *iter;
- long val = 0;
+ unsigned long val = 0;
- /* Per-cpu values can be negative, use a signed accumulator */
for_each_mem_cgroup_tree(iter, memcg)
val += mem_cgroup_read_stat(iter, idx);
- if (val < 0) /* race ? */
- val = 0;
return val;
}
@@ -3169,7 +3175,7 @@
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
- seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
+ seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
}
@@ -3194,13 +3200,13 @@
(u64)memsw * PAGE_SIZE);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- long long val = 0;
+ unsigned long long val = 0;
if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
continue;
for_each_mem_cgroup_tree(mi, memcg)
val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
- seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
+ seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val);
}
for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
@@ -4179,7 +4185,6 @@
if (memcg_wb_domain_init(memcg, GFP_KERNEL))
goto out_free_stat;
- spin_lock_init(&memcg->pcp_counter_lock);
return memcg;
out_free_stat:
diff --git a/mm/migrate.c b/mm/migrate.c
index 7452a00..842ecd7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -740,6 +740,15 @@
if (PageSwapBacked(page))
SetPageSwapBacked(newpage);
+ /*
+ * Indirectly called below, migrate_page_copy() copies PG_dirty and thus
+ * needs newpage's memcg set to transfer memcg dirty page accounting.
+ * So perform memcg migration in two steps:
+ * 1. set newpage->mem_cgroup (here)
+ * 2. clear page->mem_cgroup (below)
+ */
+ set_page_memcg(newpage, page_memcg(page));
+
mapping = page_mapping(page);
if (!mapping)
rc = migrate_page(mapping, newpage, page, mode);
@@ -756,9 +765,10 @@
rc = fallback_migrate_page(mapping, newpage, page, mode);
if (rc != MIGRATEPAGE_SUCCESS) {
+ set_page_memcg(newpage, NULL);
newpage->mapping = NULL;
} else {
- mem_cgroup_migrate(page, newpage, false);
+ set_page_memcg(page, NULL);
if (page_was_mapped)
remove_migration_ptes(page, newpage);
page->mapping = NULL;
diff --git a/mm/slab.c b/mm/slab.c
index c77ebe6..4fcc5dd 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2190,9 +2190,16 @@
size += BYTES_PER_WORD;
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
- if (size >= kmalloc_size(INDEX_NODE + 1)
- && cachep->object_size > cache_line_size()
- && ALIGN(size, cachep->align) < PAGE_SIZE) {
+ /*
+ * To activate debug pagealloc, off-slab management is necessary
+ * requirement. In early phase of initialization, small sized slab
+ * doesn't get initialized so it would not be possible. So, we need
+ * to check size >= 256. It guarantees that all necessary small
+ * sized slab is initialized in current slab initialization sequence.
+ */
+ if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
+ size >= 256 && cachep->object_size > cache_line_size() &&
+ ALIGN(size, cachep->align) < PAGE_SIZE) {
cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
size = PAGE_SIZE;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 805a95a..830f8a7 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -31,7 +31,6 @@
static const char fmt_hex[] = "%#x\n";
static const char fmt_long_hex[] = "%#lx\n";
static const char fmt_dec[] = "%d\n";
-static const char fmt_udec[] = "%u\n";
static const char fmt_ulong[] = "%lu\n";
static const char fmt_u64[] = "%llu\n";
@@ -202,7 +201,7 @@
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
if (!__ethtool_get_settings(netdev, &cmd))
- ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd));
+ ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd));
}
rtnl_unlock();
return ret;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index dad4dd3..fab4599 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2958,11 +2958,12 @@
*/
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
+ unsigned char *data = skb->data;
+
BUG_ON(len > skb->len);
- skb->len -= len;
- BUG_ON(skb->len < skb->data_len);
- skb_postpull_rcsum(skb, skb->data, len);
- return skb->data += len;
+ __skb_pull(skb, len);
+ skb_postpull_rcsum(skb, data, len);
+ return skb->data;
}
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index cce9738..7d91f46 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -458,12 +458,17 @@
static int dsa_slave_port_attr_set(struct net_device *dev,
struct switchdev_attr *attr)
{
- int ret = 0;
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_switch *ds = p->parent;
+ int ret;
switch (attr->id) {
case SWITCHDEV_ATTR_PORT_STP_STATE:
- if (attr->trans == SWITCHDEV_TRANS_COMMIT)
- ret = dsa_slave_stp_update(dev, attr->u.stp_state);
+ if (attr->trans == SWITCHDEV_TRANS_PREPARE)
+ ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP;
+ else
+ ret = ds->drv->port_stp_update(ds, p->port,
+ attr->u.stp_state);
break;
default:
ret = -EOPNOTSUPP;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6fcbd21..690bcbc 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -340,6 +340,7 @@
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.flowi4_tun_key.tun_id = 0;
+ fl4.flowi4_flags = 0;
no_addr = idev->ifa_list == NULL;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c6ad99a..c81deb8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1737,6 +1737,7 @@
fl4.flowi4_mark = skb->mark;
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+ fl4.flowi4_flags = 0;
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res, 0);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f204089..cb32ce2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1193,7 +1193,8 @@
fl6->flowi6_iif = LOOPBACK_IFINDEX;
- if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
+ if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
+ fl6->flowi6_oif)
flags |= RT6_LOOKUP_F_IFACE;
if (!ipv6_addr_any(&fl6->saddr))
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index f6b090d..afca2eb 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1319,7 +1319,7 @@
tunnel = container_of(work, struct l2tp_tunnel, del_work);
sk = l2tp_tunnel_sock_lookup(tunnel);
if (!sk)
- return;
+ goto out;
sock = sk->sk_socket;
@@ -1341,6 +1341,8 @@
}
l2tp_tunnel_sock_put(sk);
+out:
+ l2tp_tunnel_dec_refcount(tunnel);
}
/* Create a socket for the tunnel, if one isn't set up by
@@ -1636,8 +1638,13 @@
*/
int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
{
+ l2tp_tunnel_inc_refcount(tunnel);
l2tp_tunnel_closeall(tunnel);
- return (false == queue_work(l2tp_wq, &tunnel->del_work));
+ if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
+ l2tp_tunnel_dec_refcount(tunnel);
+ return 1;
+ }
+ return 0;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 197c3f5..b00f1f9 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1208,20 +1208,22 @@
* within this document.
*
* Our basic strategy is to round-robin transports in priorities
- * according to sctp_state_prio_map[] e.g., if no such
+ * according to sctp_trans_score() e.g., if no such
* transport with state SCTP_ACTIVE exists, round-robin through
* SCTP_UNKNOWN, etc. You get the picture.
*/
-static const u8 sctp_trans_state_to_prio_map[] = {
- [SCTP_ACTIVE] = 3, /* best case */
- [SCTP_UNKNOWN] = 2,
- [SCTP_PF] = 1,
- [SCTP_INACTIVE] = 0, /* worst case */
-};
-
static u8 sctp_trans_score(const struct sctp_transport *trans)
{
- return sctp_trans_state_to_prio_map[trans->state];
+ switch (trans->state) {
+ case SCTP_ACTIVE:
+ return 3; /* best case */
+ case SCTP_UNKNOWN:
+ return 2;
+ case SCTP_PF:
+ return 1;
+ default: /* case SCTP_INACTIVE */
+ return 0; /* worst case */
+ }
}
static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1,
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 35df126..6098d4c 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -244,12 +244,13 @@
int error;
struct sctp_transport *transport = (struct sctp_transport *) peer;
struct sctp_association *asoc = transport->asoc;
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
/* Check whether a task is in the sock. */
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy\n", __func__);
/* Try again later. */
@@ -272,10 +273,10 @@
transport, GFP_ATOMIC);
if (error)
- asoc->base.sk->sk_err = -error;
+ sk->sk_err = -error;
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_transport_put(transport);
}
@@ -285,11 +286,12 @@
static void sctp_generate_timeout_event(struct sctp_association *asoc,
sctp_event_timeout_t timeout_type)
{
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
int error = 0;
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy: timer %d\n", __func__,
timeout_type);
@@ -312,10 +314,10 @@
(void *)timeout_type, GFP_ATOMIC);
if (error)
- asoc->base.sk->sk_err = -error;
+ sk->sk_err = -error;
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_association_put(asoc);
}
@@ -365,10 +367,11 @@
int error = 0;
struct sctp_transport *transport = (struct sctp_transport *) data;
struct sctp_association *asoc = transport->asoc;
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy\n", __func__);
/* Try again later. */
@@ -388,11 +391,11 @@
asoc->state, asoc->ep, asoc,
transport, GFP_ATOMIC);
- if (error)
- asoc->base.sk->sk_err = -error;
+ if (error)
+ sk->sk_err = -error;
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_transport_put(transport);
}
@@ -403,10 +406,11 @@
{
struct sctp_transport *transport = (struct sctp_transport *) data;
struct sctp_association *asoc = transport->asoc;
- struct net *net = sock_net(asoc->base.sk);
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
- bh_lock_sock(asoc->base.sk);
- if (sock_owned_by_user(asoc->base.sk)) {
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
pr_debug("%s: sock is busy\n", __func__);
/* Try again later. */
@@ -427,7 +431,7 @@
asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC);
out_unlock:
- bh_unlock_sock(asoc->base.sk);
+ bh_unlock_sock(sk);
sctp_association_put(asoc);
}
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index cb25c89..f1e8daf 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -39,25 +39,6 @@
fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
struct rpcrdma_create_data_internal *cdata)
{
- struct ib_device_attr *devattr = &ia->ri_devattr;
- struct ib_mr *mr;
-
- /* Obtain an lkey to use for the regbufs, which are
- * protected from remote access.
- */
- if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
- ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
- } else {
- mr = ib_get_dma_mr(ia->ri_pd, IB_ACCESS_LOCAL_WRITE);
- if (IS_ERR(mr)) {
- pr_err("%s: ib_get_dma_mr for failed with %lX\n",
- __func__, PTR_ERR(mr));
- return -ENOMEM;
- }
- ia->ri_dma_lkey = ia->ri_dma_mr->lkey;
- ia->ri_dma_mr = mr;
- }
-
return 0;
}
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index d6653f5..5318951 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -189,11 +189,6 @@
struct ib_device_attr *devattr = &ia->ri_devattr;
int depth, delta;
- /* Obtain an lkey to use for the regbufs, which are
- * protected from remote access.
- */
- ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
-
ia->ri_max_frmr_depth =
min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
devattr->max_fast_reg_page_list_len);
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
index 72cf8b1..617b76f 100644
--- a/net/sunrpc/xprtrdma/physical_ops.c
+++ b/net/sunrpc/xprtrdma/physical_ops.c
@@ -23,7 +23,6 @@
physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
struct rpcrdma_create_data_internal *cdata)
{
- struct ib_device_attr *devattr = &ia->ri_devattr;
struct ib_mr *mr;
/* Obtain an rkey to use for RPC data payloads.
@@ -37,15 +36,8 @@
__func__, PTR_ERR(mr));
return -ENOMEM;
}
+
ia->ri_dma_mr = mr;
-
- /* Obtain an lkey to use for regbufs.
- */
- if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
- ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
- else
- ia->ri_dma_lkey = ia->ri_dma_mr->lkey;
-
return 0;
}
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 6829967..eb081ad 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1252,7 +1252,7 @@
goto out_free;
iov->length = size;
- iov->lkey = ia->ri_dma_lkey;
+ iov->lkey = ia->ri_pd->local_dma_lkey;
rb->rg_size = size;
rb->rg_owner = NULL;
return rb;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 0251222..c09414e 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -65,7 +65,6 @@
struct rdma_cm_id *ri_id;
struct ib_pd *ri_pd;
struct ib_mr *ri_dma_mr;
- u32 ri_dma_lkey;
struct completion ri_done;
int ri_async_rc;
unsigned int ri_max_frmr_depth;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 03ee4d3..ef31b40 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2179,8 +2179,21 @@
if (UNIXCB(skb).fp)
scm.fp = scm_fp_dup(UNIXCB(skb).fp);
- sk_peek_offset_fwd(sk, chunk);
+ if (skip) {
+ sk_peek_offset_fwd(sk, chunk);
+ skip -= chunk;
+ }
+ if (UNIXCB(skb).fp)
+ break;
+
+ last = skb;
+ last_len = skb->len;
+ unix_state_lock(sk);
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
+ if (skb)
+ goto again;
+ unix_state_unlock(sk);
break;
}
} while (size);
diff --git a/samples/kprobes/jprobe_example.c b/samples/kprobes/jprobe_example.c
index 9119ac6..c285a3b 100644
--- a/samples/kprobes/jprobe_example.c
+++ b/samples/kprobes/jprobe_example.c
@@ -1,13 +1,13 @@
/*
* Here's a sample kernel module showing the use of jprobes to dump
- * the arguments of do_fork().
+ * the arguments of _do_fork().
*
* For more information on theory of operation of jprobes, see
* Documentation/kprobes.txt
*
* Build and insert the kernel module as done in the kprobe example.
* You will see the trace data in /var/log/messages and on the
- * console whenever do_fork() is invoked to create a new process.
+ * console whenever _do_fork() is invoked to create a new process.
* (Some messages may be suppressed if syslogd is configured to
* eliminate duplicate messages.)
*/
@@ -17,13 +17,13 @@
#include <linux/kprobes.h>
/*
- * Jumper probe for do_fork.
+ * Jumper probe for _do_fork.
* Mirror principle enables access to arguments of the probed routine
* from the probe handler.
*/
-/* Proxy routine having the same arguments as actual do_fork() routine */
-static long jdo_fork(unsigned long clone_flags, unsigned long stack_start,
+/* Proxy routine having the same arguments as actual _do_fork() routine */
+static long j_do_fork(unsigned long clone_flags, unsigned long stack_start,
unsigned long stack_size, int __user *parent_tidptr,
int __user *child_tidptr)
{
@@ -36,9 +36,9 @@
}
static struct jprobe my_jprobe = {
- .entry = jdo_fork,
+ .entry = j_do_fork,
.kp = {
- .symbol_name = "do_fork",
+ .symbol_name = "_do_fork",
},
};
diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c
index 366db1a..727eb21 100644
--- a/samples/kprobes/kprobe_example.c
+++ b/samples/kprobes/kprobe_example.c
@@ -1,13 +1,13 @@
/*
* NOTE: This example is works on x86 and powerpc.
* Here's a sample kernel module showing the use of kprobes to dump a
- * stack trace and selected registers when do_fork() is called.
+ * stack trace and selected registers when _do_fork() is called.
*
* For more information on theory of operation of kprobes, see
* Documentation/kprobes.txt
*
* You will see the trace data in /var/log/messages and on the console
- * whenever do_fork() is invoked to create a new process.
+ * whenever _do_fork() is invoked to create a new process.
*/
#include <linux/kernel.h>
@@ -16,7 +16,7 @@
/* For each probe you need to allocate a kprobe structure */
static struct kprobe kp = {
- .symbol_name = "do_fork",
+ .symbol_name = "_do_fork",
};
/* kprobe pre_handler: called just before the probed instruction is executed */
diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c
index 1041b67..ebb1d1a 100644
--- a/samples/kprobes/kretprobe_example.c
+++ b/samples/kprobes/kretprobe_example.c
@@ -7,7 +7,7 @@
*
* usage: insmod kretprobe_example.ko func=<func_name>
*
- * If no func_name is specified, do_fork is instrumented
+ * If no func_name is specified, _do_fork is instrumented
*
* For more information on theory of operation of kretprobes, see
* Documentation/kprobes.txt
@@ -25,7 +25,7 @@
#include <linux/limits.h>
#include <linux/sched.h>
-static char func_name[NAME_MAX] = "do_fork";
+static char func_name[NAME_MAX] = "_do_fork";
module_param_string(func, func_name, NAME_MAX, S_IRUGO);
MODULE_PARM_DESC(func, "Function to kretprobe; this module will report the"
" function's execution time");
diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan
index 3f874d2..37323b0 100644
--- a/scripts/Makefile.kasan
+++ b/scripts/Makefile.kasan
@@ -5,10 +5,12 @@
call_threshold := 0
endif
+KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET)
+
CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address
CFLAGS_KASAN := $(call cc-option, -fsanitize=kernel-address \
- -fasan-shadow-offset=$(CONFIG_KASAN_SHADOW_OFFSET) \
+ -fasan-shadow-offset=$(KASAN_SHADOW_OFFSET) \
--param asan-stack=1 --param asan-globals=1 \
--param asan-instrumentation-with-call-threshold=$(call_threshold))
diff --git a/scripts/extract-cert.c b/scripts/extract-cert.c
index 6ce5945..b071bf4 100644
--- a/scripts/extract-cert.c
+++ b/scripts/extract-cert.c
@@ -17,13 +17,9 @@
#include <stdint.h>
#include <stdbool.h>
#include <string.h>
-#include <getopt.h>
#include <err.h>
-#include <arpa/inet.h>
#include <openssl/bio.h>
-#include <openssl/evp.h>
#include <openssl/pem.h>
-#include <openssl/pkcs7.h>
#include <openssl/err.h>
#include <openssl/engine.h>
diff --git a/scripts/sign-file.c b/scripts/sign-file.c
index c3899ca..250a7a6 100755
--- a/scripts/sign-file.c
+++ b/scripts/sign-file.c
@@ -20,13 +20,34 @@
#include <getopt.h>
#include <err.h>
#include <arpa/inet.h>
+#include <openssl/opensslv.h>
#include <openssl/bio.h>
#include <openssl/evp.h>
#include <openssl/pem.h>
-#include <openssl/cms.h>
#include <openssl/err.h>
#include <openssl/engine.h>
+/*
+ * Use CMS if we have openssl-1.0.0 or newer available - otherwise we have to
+ * assume that it's not available and its header file is missing and that we
+ * should use PKCS#7 instead. Switching to the older PKCS#7 format restricts
+ * the options we have on specifying the X.509 certificate we want.
+ *
+ * Further, older versions of OpenSSL don't support manually adding signers to
+ * the PKCS#7 message so have to accept that we get a certificate included in
+ * the signature message. Nor do such older versions of OpenSSL support
+ * signing with anything other than SHA1 - so we're stuck with that if such is
+ * the case.
+ */
+#if OPENSSL_VERSION_NUMBER < 0x10000000L
+#define USE_PKCS7
+#endif
+#ifndef USE_PKCS7
+#include <openssl/cms.h>
+#else
+#include <openssl/pkcs7.h>
+#endif
+
struct module_signature {
uint8_t algo; /* Public-key crypto algorithm [0] */
uint8_t hash; /* Digest algorithm [0] */
@@ -110,30 +131,42 @@
struct module_signature sig_info = { .id_type = PKEY_ID_PKCS7 };
char *hash_algo = NULL;
char *private_key_name, *x509_name, *module_name, *dest_name;
- bool save_cms = false, replace_orig;
+ bool save_sig = false, replace_orig;
bool sign_only = false;
unsigned char buf[4096];
- unsigned long module_size, cms_size;
- unsigned int use_keyid = 0, use_signed_attrs = CMS_NOATTR;
+ unsigned long module_size, sig_size;
+ unsigned int use_signed_attrs;
const EVP_MD *digest_algo;
EVP_PKEY *private_key;
+#ifndef USE_PKCS7
CMS_ContentInfo *cms;
+ unsigned int use_keyid = 0;
+#else
+ PKCS7 *pkcs7;
+#endif
X509 *x509;
BIO *b, *bd = NULL, *bm;
int opt, n;
-
OpenSSL_add_all_algorithms();
ERR_load_crypto_strings();
ERR_clear_error();
key_pass = getenv("KBUILD_SIGN_PIN");
+#ifndef USE_PKCS7
+ use_signed_attrs = CMS_NOATTR;
+#else
+ use_signed_attrs = PKCS7_NOATTR;
+#endif
+
do {
opt = getopt(argc, argv, "dpk");
switch (opt) {
- case 'p': save_cms = true; break;
- case 'd': sign_only = true; save_cms = true; break;
+ case 'p': save_sig = true; break;
+ case 'd': sign_only = true; save_sig = true; break;
+#ifndef USE_PKCS7
case 'k': use_keyid = CMS_USE_KEYID; break;
+#endif
case -1: break;
default: format();
}
@@ -157,6 +190,14 @@
replace_orig = true;
}
+#ifdef USE_PKCS7
+ if (strcmp(hash_algo, "sha1") != 0) {
+ fprintf(stderr, "sign-file: %s only supports SHA1 signing\n",
+ OPENSSL_VERSION_TEXT);
+ exit(3);
+ }
+#endif
+
/* Read the private key and the X.509 cert the PKCS#7 message
* will point to.
*/
@@ -213,7 +254,8 @@
bm = BIO_new_file(module_name, "rb");
ERR(!bm, "%s", module_name);
- /* Load the CMS message from the digest buffer. */
+#ifndef USE_PKCS7
+ /* Load the signature message from the digest buffer. */
cms = CMS_sign(NULL, NULL, NULL, NULL,
CMS_NOCERTS | CMS_PARTIAL | CMS_BINARY | CMS_DETACHED | CMS_STREAM);
ERR(!cms, "CMS_sign");
@@ -221,17 +263,31 @@
ERR(!CMS_add1_signer(cms, x509, private_key, digest_algo,
CMS_NOCERTS | CMS_BINARY | CMS_NOSMIMECAP |
use_keyid | use_signed_attrs),
- "CMS_sign_add_signer");
+ "CMS_add1_signer");
ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0,
"CMS_final");
- if (save_cms) {
- char *cms_name;
+#else
+ pkcs7 = PKCS7_sign(x509, private_key, NULL, bm,
+ PKCS7_NOCERTS | PKCS7_BINARY |
+ PKCS7_DETACHED | use_signed_attrs);
+ ERR(!pkcs7, "PKCS7_sign");
+#endif
- ERR(asprintf(&cms_name, "%s.p7s", module_name) < 0, "asprintf");
- b = BIO_new_file(cms_name, "wb");
- ERR(!b, "%s", cms_name);
- ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0, "%s", cms_name);
+ if (save_sig) {
+ char *sig_file_name;
+
+ ERR(asprintf(&sig_file_name, "%s.p7s", module_name) < 0,
+ "asprintf");
+ b = BIO_new_file(sig_file_name, "wb");
+ ERR(!b, "%s", sig_file_name);
+#ifndef USE_PKCS7
+ ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0,
+ "%s", sig_file_name);
+#else
+ ERR(i2d_PKCS7_bio(b, pkcs7) < 0,
+ "%s", sig_file_name);
+#endif
BIO_free(b);
}
@@ -247,9 +303,13 @@
ERR(n < 0, "%s", module_name);
module_size = BIO_number_written(bd);
+#ifndef USE_PKCS7
ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name);
- cms_size = BIO_number_written(bd) - module_size;
- sig_info.sig_len = htonl(cms_size);
+#else
+ ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name);
+#endif
+ sig_size = BIO_number_written(bd) - module_size;
+ sig_info.sig_len = htonl(sig_size);
ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name);
ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name);
diff --git a/security/keys/gc.c b/security/keys/gc.c
index c795237..39eac1f 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -134,6 +134,10 @@
kdebug("- %u", key->serial);
key_check(key);
+ /* Throw away the key data */
+ if (key->type->destroy)
+ key->type->destroy(key);
+
security_key_free(key);
/* deal with the user's key tracking and quota */
@@ -148,10 +152,6 @@
if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
atomic_dec(&key->user->nikeys);
- /* now throw away the key memory */
- if (key->type->destroy)
- key->type->destroy(key);
-
key_user_put(key->user);
kfree(key->description);
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 2975632..c8fe6d1 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -41,6 +41,7 @@
libelf-getphdrnum \
libelf-mmap \
libnuma \
+ numa_num_possible_cpus \
libperl \
libpython \
libpython-version \
@@ -51,7 +52,8 @@
timerfd \
libdw-dwarf-unwind \
zlib \
- lzma
+ lzma \
+ get_cpuid
FEATURE_DISPLAY ?= \
dwarf \
@@ -61,13 +63,15 @@
libbfd \
libelf \
libnuma \
+ numa_num_possible_cpus \
libperl \
libpython \
libslang \
libunwind \
libdw-dwarf-unwind \
zlib \
- lzma
+ lzma \
+ get_cpuid
# Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
# If in the future we need per-feature checks/flags for features not
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 74ca4209..e43a297 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -19,6 +19,7 @@
test-libelf-getphdrnum.bin \
test-libelf-mmap.bin \
test-libnuma.bin \
+ test-numa_num_possible_cpus.bin \
test-libperl.bin \
test-libpython.bin \
test-libpython-version.bin \
@@ -34,7 +35,8 @@
test-compile-x32.bin \
test-zlib.bin \
test-lzma.bin \
- test-bpf.bin
+ test-bpf.bin \
+ test-get_cpuid.bin
CC := $(CROSS_COMPILE)gcc -MD
PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -87,6 +89,9 @@
test-libnuma.bin:
$(BUILD) -lnuma
+test-numa_num_possible_cpus.bin:
+ $(BUILD) -lnuma
+
test-libunwind.bin:
$(BUILD) -lelf
@@ -162,6 +167,9 @@
test-lzma.bin:
$(BUILD) -llzma
+test-get_cpuid.bin:
+ $(BUILD)
+
test-bpf.bin:
$(BUILD)
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 84689a6..33cf6f2 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -77,6 +77,10 @@
# include "test-libnuma.c"
#undef main
+#define main main_test_numa_num_possible_cpus
+# include "test-numa_num_possible_cpus.c"
+#undef main
+
#define main main_test_timerfd
# include "test-timerfd.c"
#undef main
@@ -117,6 +121,10 @@
# include "test-lzma.c"
#undef main
+#define main main_test_get_cpuid
+# include "test-get_cpuid.c"
+#undef main
+
int main(int argc, char *argv[])
{
main_test_libpython();
@@ -136,6 +144,7 @@
main_test_libbfd();
main_test_backtrace();
main_test_libnuma();
+ main_test_numa_num_possible_cpus();
main_test_timerfd();
main_test_stackprotector_all();
main_test_libdw_dwarf_unwind();
@@ -143,6 +152,7 @@
main_test_zlib();
main_test_pthread_attr_setaffinity_np();
main_test_lzma();
+ main_test_get_cpuid();
return 0;
}
diff --git a/tools/build/feature/test-get_cpuid.c b/tools/build/feature/test-get_cpuid.c
new file mode 100644
index 0000000..d7a2c40
--- /dev/null
+++ b/tools/build/feature/test-get_cpuid.c
@@ -0,0 +1,7 @@
+#include <cpuid.h>
+
+int main(void)
+{
+ unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0;
+ return __get_cpuid(0x15, &eax, &ebx, &ecx, &edx);
+}
diff --git a/tools/build/feature/test-numa_num_possible_cpus.c b/tools/build/feature/test-numa_num_possible_cpus.c
new file mode 100644
index 0000000..2606e94
--- /dev/null
+++ b/tools/build/feature/test-numa_num_possible_cpus.c
@@ -0,0 +1,6 @@
+#include <numa.h>
+
+int main(void)
+{
+ return numa_num_possible_cpus();
+}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 4d88593..cf42b09 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3795,7 +3795,7 @@
struct format_field *field;
struct printk_map *printk;
long long val, fval;
- unsigned long addr;
+ unsigned long long addr;
char *str;
unsigned char *hex;
int print;
@@ -3828,13 +3828,30 @@
*/
if (!(field->flags & FIELD_IS_ARRAY) &&
field->size == pevent->long_size) {
- addr = *(unsigned long *)(data + field->offset);
+
+ /* Handle heterogeneous recording and processing
+ * architectures
+ *
+ * CASE I:
+ * Traces recorded on 32-bit devices (32-bit
+ * addressing) and processed on 64-bit devices:
+ * In this case, only 32 bits should be read.
+ *
+ * CASE II:
+ * Traces recorded on 64 bit devices and processed
+ * on 32-bit devices:
+ * In this case, 64 bits must be read.
+ */
+ addr = (pevent->long_size == 8) ?
+ *(unsigned long long *)(data + field->offset) :
+ (unsigned long long)*(unsigned int *)(data + field->offset);
+
/* Check if it matches a print format */
printk = find_printk(pevent, addr);
if (printk)
trace_seq_puts(s, printk->printk);
else
- trace_seq_printf(s, "%lx", addr);
+ trace_seq_printf(s, "%llx", addr);
break;
}
str = malloc(len + 1);
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 4a0501d..c94c9de 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -364,21 +364,6 @@
CYC packets are not requested by default.
-no_force_psb This is a driver option and is not in the IA32_RTIT_CTL MSR.
-
- It stops the driver resetting the byte count to zero whenever
- enabling the trace (for example on context switches) which in
- turn results in no PSB being forced. However some processors
- will produce a PSB anyway.
-
- In any case, there is still a PSB when the trace is enabled for
- the first time.
-
- no_force_psb can be used to slightly decrease the trace size but
- may make it harder for the decoder to recover from errors.
-
- no_force_psb is not selected by default.
-
new snapshot option
-------------------
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 827557f..38a0853 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -573,9 +573,14 @@
msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
NO_LIBNUMA := 1
else
- CFLAGS += -DHAVE_LIBNUMA_SUPPORT
- EXTLIBS += -lnuma
- $(call detected,CONFIG_NUMA)
+ ifeq ($(feature-numa_num_possible_cpus), 0)
+ msg := $(warning Old numa library found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev >= 2.0.8);
+ NO_LIBNUMA := 1
+ else
+ CFLAGS += -DHAVE_LIBNUMA_SUPPORT
+ EXTLIBS += -lnuma
+ $(call detected,CONFIG_NUMA)
+ endif
endif
endif
@@ -621,8 +626,13 @@
endif
ifndef NO_AUXTRACE
- $(call detected,CONFIG_AUXTRACE)
- CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+ ifeq ($(feature-get_cpuid), 0)
+ msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
+ NO_AUXTRACE := 1
+ else
+ $(call detected,CONFIG_AUXTRACE)
+ CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+ endif
endif
# Among the variables below, these:
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb5f18b..c6f9af7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -270,12 +270,13 @@
int ret = 0;
if (module) {
- list_for_each_entry(dso, &host_machine->dsos.head, node) {
- if (!dso->kernel)
- continue;
- if (strncmp(dso->short_name + 1, module,
- dso->short_name_len - 2) == 0)
- goto found;
+ char module_name[128];
+
+ snprintf(module_name, sizeof(module_name), "[%s]", module);
+ map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+ if (map) {
+ dso = map->dso;
+ goto found;
}
pr_debug("Failed to find module %s.\n", module);
return -ENOENT;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a4537e..fc3f7c9 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1580,7 +1580,10 @@
file_offset = page_offset;
head = data_offset - page_offset;
- if (data_size && (data_offset + data_size < file_size))
+ if (data_size == 0)
+ goto out;
+
+ if (data_offset + data_size < file_size)
file_size = data_offset + data_size;
ui_progress__init(&prog, file_size, "Processing events...");
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 415c359..2d065d0 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -196,7 +196,8 @@
memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
}
-static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+static int check_per_pkg(struct perf_evsel *counter,
+ struct perf_counts_values *vals, int cpu, bool *skip)
{
unsigned long *mask = counter->per_pkg_mask;
struct cpu_map *cpus = perf_evsel__cpus(counter);
@@ -218,6 +219,17 @@
counter->per_pkg_mask = mask;
}
+ /*
+ * we do not consider an event that has not run as a good
+ * instance to mark a package as used (skip=1). Otherwise
+ * we may run into a situation where the first CPU in a package
+ * is not running anything, yet the second is, and this function
+ * would mark the package as used after the first CPU and would
+ * not read the values from the second CPU.
+ */
+ if (!(vals->run && vals->ena))
+ return 0;
+
s = cpu_map__get_socket(cpus, cpu);
if (s < 0)
return -1;
@@ -235,7 +247,7 @@
static struct perf_counts_values zero;
bool skip = false;
- if (check_per_pkg(evsel, cpu, &skip)) {
+ if (check_per_pkg(evsel, count, cpu, &skip)) {
pr_err("failed to read per-pkg counter\n");
return -1;
}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 53bb5f5..475d88d 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -38,7 +38,7 @@
#endif
#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
-int elf_getphdrnum(Elf *elf, size_t *dst)
+static int elf_getphdrnum(Elf *elf, size_t *dst)
{
GElf_Ehdr gehdr;
GElf_Ehdr *ehdr;
@@ -1271,8 +1271,6 @@
static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
bool temp)
{
- GElf_Ehdr *ehdr;
-
kcore->elfclass = elfclass;
if (temp)
@@ -1289,9 +1287,7 @@
if (!gelf_newehdr(kcore->elf, elfclass))
goto out_end;
- ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
- if (!ehdr)
- goto out_end;
+ memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr));
return 0;
@@ -1348,23 +1344,18 @@
static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
u64 addr, u64 len)
{
- GElf_Phdr gphdr;
- GElf_Phdr *phdr;
+ GElf_Phdr phdr = {
+ .p_type = PT_LOAD,
+ .p_flags = PF_R | PF_W | PF_X,
+ .p_offset = offset,
+ .p_vaddr = addr,
+ .p_paddr = 0,
+ .p_filesz = len,
+ .p_memsz = len,
+ .p_align = page_size,
+ };
- phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
- if (!phdr)
- return -1;
-
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R | PF_W | PF_X;
- phdr->p_offset = offset;
- phdr->p_vaddr = addr;
- phdr->p_paddr = 0;
- phdr->p_filesz = len;
- phdr->p_memsz = len;
- phdr->p_align = page_size;
-
- if (!gelf_update_phdr(kcore->elf, idx, phdr))
+ if (!gelf_update_phdr(kcore->elf, idx, &phdr))
return -1;
return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7acafb3..c2cd9bf2 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -709,7 +709,7 @@
dir = opendir(procfs__mountpoint());
if (!dir)
- return -1;
+ return false;
/* Walk through the directory. */
while (ret && (d = readdir(dir)) != NULL) {
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9655cb4..bde0ef1 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -71,8 +71,11 @@
unsigned int extra_msr_offset64;
unsigned int extra_delta_offset32;
unsigned int extra_delta_offset64;
+unsigned int aperf_mperf_multiplier = 1;
int do_smi;
double bclk;
+double base_hz;
+double tsc_tweak = 1.0;
unsigned int show_pkg;
unsigned int show_core;
unsigned int show_cpu;
@@ -502,7 +505,7 @@
/* %Busy */
if (has_aperf) {
if (!skip_c0)
- outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc);
+ outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
else
outp += sprintf(outp, "********");
}
@@ -510,7 +513,7 @@
/* Bzy_MHz */
if (has_aperf)
outp += sprintf(outp, "%8.0f",
- 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+ 1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float);
/* TSC_MHz */
outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
@@ -984,6 +987,8 @@
return -3;
if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
return -4;
+ t->aperf = t->aperf * aperf_mperf_multiplier;
+ t->mperf = t->mperf * aperf_mperf_multiplier;
}
if (do_smi) {
@@ -1149,6 +1154,19 @@
int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+
+static void
+calculate_tsc_tweak()
+{
+ unsigned long long msr;
+ unsigned int base_ratio;
+
+ get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
+ base_ratio = (msr >> 8) & 0xFF;
+ base_hz = base_ratio * bclk * 1000000;
+ tsc_tweak = base_hz / tsc_hz;
+}
+
static void
dump_nhm_platform_info(void)
{
@@ -1926,8 +1944,6 @@
switch (model) {
case 0x3A: /* IVB */
- case 0x3E: /* IVB Xeon */
-
case 0x3C: /* HSW */
case 0x3F: /* HSX */
case 0x45: /* HSW */
@@ -2543,6 +2559,13 @@
return 0;
}
+unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
+{
+ if (is_knl(family, model))
+ return 1024;
+ return 1;
+}
+
#define SLM_BCLK_FREQS 5
double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0};
@@ -2744,6 +2767,9 @@
}
}
+ if (has_aperf)
+ aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
+
do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
do_snb_cstates = has_snb_msrs(family, model);
do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
@@ -2762,6 +2788,9 @@
if (debug)
dump_cstate_pstate_config_info();
+ if (has_skl_msrs(family, model))
+ calculate_tsc_tweak();
+
return;
}
@@ -3090,7 +3119,7 @@
}
void print_version() {
- fprintf(stderr, "turbostat version 4.7 17-June, 2015"
+ fprintf(stderr, "turbostat version 4.8 26-Sep, 2015"
" - Len Brown <lenb@kernel.org>\n");
}