summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/include/asm/user.h6
-rw-r--r--arch/arm/boot/dts/spear1340.dtsi6
-rw-r--r--arch/arm/boot/dts/spear13xx.dtsi6
-rw-r--r--arch/arm/include/asm/user.h4
-rw-r--r--arch/arm/mach-omap2/omap-secure.c13
-rw-r--r--arch/arm64/boot/dts/amd/Makefile4
-rw-r--r--arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts13
-rw-r--r--arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts1
-rw-r--r--arch/arm64/boot/dts/amd/amd-overdrive.dts66
-rw-r--r--arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi224
-rw-r--r--arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi70
-rw-r--r--arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi22
-rw-r--r--arch/arm64/boot/dts/amd/husky.dts84
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi6
-rw-r--r--arch/h8300/include/asm/user.h4
-rw-r--r--arch/ia64/include/asm/user.h6
-rw-r--r--arch/m68k/include/asm/user.h4
-rw-r--r--arch/mips/crypto/crc32-mips.c46
-rw-r--r--arch/mips/include/asm/mach-rc32434/rb.h9
-rw-r--r--arch/mips/lantiq/falcon/sysctrl.c2
-rw-r--r--arch/mips/lantiq/xway/gptu.c2
-rw-r--r--arch/mips/lantiq/xway/sysctrl.c46
-rw-r--r--arch/mips/rb532/gpio.c10
-rw-r--r--arch/mips/sgi-ip22/ip22-gio.c2
-rw-r--r--arch/powerpc/include/asm/user.h5
-rw-r--r--arch/riscv/Kconfig8
-rw-r--r--arch/riscv/Kconfig.socs3
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts2
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts2
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maix_go.dts2
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maixduino.dts2
-rw-r--r--arch/riscv/configs/defconfig5
-rw-r--r--arch/riscv/configs/nommu_k210_defconfig1
-rw-r--r--arch/riscv/configs/nommu_k210_sdcard_defconfig1
-rw-r--r--arch/riscv/configs/nommu_virt_defconfig1
-rw-r--r--arch/riscv/configs/rv32_defconfig5
-rw-r--r--arch/riscv/include/asm/asm.h26
-rw-r--r--arch/riscv/include/asm/cpuidle.h24
-rw-r--r--arch/riscv/include/asm/current.h2
-rw-r--r--arch/riscv/include/asm/module.lds.h6
-rw-r--r--arch/riscv/include/asm/suspend.h36
-rw-r--r--arch/riscv/include/asm/thread_info.h10
-rw-r--r--arch/riscv/kernel/Makefile2
-rw-r--r--arch/riscv/kernel/asm-offsets.c3
-rw-r--r--arch/riscv/kernel/cpu.c6
-rw-r--r--arch/riscv/kernel/cpu_ops_sbi.c2
-rw-r--r--arch/riscv/kernel/head.S27
-rw-r--r--arch/riscv/kernel/module.c4
-rw-r--r--arch/riscv/kernel/perf_callchain.c2
-rw-r--r--arch/riscv/kernel/process.c3
-rw-r--r--arch/riscv/kernel/stacktrace.c6
-rw-r--r--arch/riscv/kernel/suspend.c87
-rw-r--r--arch/riscv/kernel/suspend_entry.S124
-rw-r--r--arch/s390/Kconfig1
-rw-r--r--arch/s390/include/asm/alternative-asm.h12
-rw-r--r--arch/s390/include/asm/alternative.h15
-rw-r--r--arch/s390/include/asm/ap.h60
-rw-r--r--arch/s390/include/asm/ctl_reg.h16
-rw-r--r--arch/s390/include/asm/processor.h17
-rw-r--r--arch/s390/include/asm/spinlock.h2
-rw-r--r--arch/s390/include/asm/syscall_wrapper.h2
-rw-r--r--arch/s390/include/asm/unwind.h13
-rw-r--r--arch/s390/include/asm/user.h4
-rw-r--r--arch/s390/kernel/entry.S10
-rw-r--r--arch/s390/kernel/ipl.c4
-rw-r--r--arch/s390/kernel/kprobes.c8
-rw-r--r--arch/s390/kernel/machine_kexec.c2
-rw-r--r--arch/s390/kernel/os_info.c2
-rw-r--r--arch/s390/kernel/setup.c19
-rw-r--r--arch/s390/kernel/smp.c57
-rw-r--r--arch/s390/kernel/traps.c6
-rw-r--r--arch/s390/kernel/unwind_bc.c12
-rw-r--r--arch/s390/kvm/kvm-s390.c2
-rw-r--r--arch/s390/lib/spinlock.c4
-rw-r--r--arch/s390/lib/test_unwind.c58
-rw-r--r--arch/s390/pci/pci.c5
-rw-r--r--arch/s390/pci/pci_bus.h7
-rw-r--r--arch/s390/pci/pci_clp.c9
-rw-r--r--arch/s390/pci/pci_event.c7
-rw-r--r--arch/sh/include/asm/user.h6
-rw-r--r--arch/um/include/asm/Kbuild1
-rw-r--r--arch/x86/include/asm/kvm_host.h46
-rw-r--r--arch/x86/include/asm/svm.h14
-rw-r--r--arch/x86/include/asm/user_32.h4
-rw-r--r--arch/x86/include/asm/user_64.h4
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kvm/cpuid.c1
-rw-r--r--arch/x86/kvm/emulate.c8
-rw-r--r--arch/x86/kvm/hyperv.c22
-rw-r--r--arch/x86/kvm/i8254.c6
-rw-r--r--arch/x86/kvm/kvm_emulate.h3
-rw-r--r--arch/x86/kvm/lapic.c4
-rw-r--r--arch/x86/kvm/mmu.h32
-rw-r--r--arch/x86/kvm/mmu/mmu.c27
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h82
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c72
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h12
-rw-r--r--arch/x86/kvm/pmu.c18
-rw-r--r--arch/x86/kvm/svm/avic.c14
-rw-r--r--arch/x86/kvm/svm/pmu.c9
-rw-r--r--arch/x86/kvm/svm/svm.c36
-rw-r--r--arch/x86/kvm/svm/svm.h15
-rw-r--r--arch/x86/kvm/svm/svm_onhyperv.c1
-rw-r--r--arch/x86/kvm/trace.h22
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c14
-rw-r--r--arch/x86/kvm/vmx/vmx.c26
-rw-r--r--arch/x86/kvm/x86.c161
-rw-r--r--arch/x86/kvm/xen.c7
-rw-r--r--arch/x86/lib/csum-partial_64.c26
-rw-r--r--arch/x86/um/Kconfig1
111 files changed, 1295 insertions, 824 deletions
diff --git a/arch/alpha/include/asm/user.h b/arch/alpha/include/asm/user.h
index 3df37492c7b7..c9f525a6aab8 100644
--- a/arch/alpha/include/asm/user.h
+++ b/arch/alpha/include/asm/user.h
@@ -45,10 +45,4 @@ struct user {
char u_comm[32]; /* user command name */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_DATA_START_ADDR (u.start_data)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
#endif /* _ALPHA_USER_H */
diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi
index 827e887afbda..13e1bdb3ddbf 100644
--- a/arch/arm/boot/dts/spear1340.dtsi
+++ b/arch/arm/boot/dts/spear1340.dtsi
@@ -134,9 +134,9 @@
reg = <0xb4100000 0x1000>;
interrupts = <0 105 0x4>;
status = "disabled";
- dmas = <&dwdma0 12 0 1>,
- <&dwdma0 13 1 0>;
- dma-names = "tx", "rx";
+ dmas = <&dwdma0 13 0 1>,
+ <&dwdma0 12 1 0>;
+ dma-names = "rx", "tx";
};
thermal@e07008c4 {
diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi
index c87b881b2c8b..913553367687 100644
--- a/arch/arm/boot/dts/spear13xx.dtsi
+++ b/arch/arm/boot/dts/spear13xx.dtsi
@@ -284,9 +284,9 @@
#size-cells = <0>;
interrupts = <0 31 0x4>;
status = "disabled";
- dmas = <&dwdma0 4 0 0>,
- <&dwdma0 5 0 0>;
- dma-names = "tx", "rx";
+ dmas = <&dwdma0 5 0 0>,
+ <&dwdma0 4 0 0>;
+ dma-names = "rx", "tx";
};
rtc@e0580000 {
diff --git a/arch/arm/include/asm/user.h b/arch/arm/include/asm/user.h
index c799a3c49342..167d44b550f4 100644
--- a/arch/arm/include/asm/user.h
+++ b/arch/arm/include/asm/user.h
@@ -77,10 +77,6 @@ struct user{
struct user_fp_struct * u_fp0;/* Used by gdb to help find the values for */
/* the FP registers. */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
/*
* User specific VFP registers. If only VFPv2 is present, registers 16 to 31
diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index 0659ab4cb0af..11677fc2968f 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -59,8 +59,13 @@ static void __init omap_optee_init_check(void)
u32 omap_secure_dispatcher(u32 idx, u32 flag, u32 nargs, u32 arg1, u32 arg2,
u32 arg3, u32 arg4)
{
+ static u32 buf[NR_CPUS][5];
+ u32 *param;
+ int cpu;
u32 ret;
- u32 param[5];
+
+ cpu = get_cpu();
+ param = buf[cpu];
param[0] = nargs;
param[1] = arg1;
@@ -76,6 +81,8 @@ u32 omap_secure_dispatcher(u32 idx, u32 flag, u32 nargs, u32 arg1, u32 arg2,
outer_clean_range(__pa(param), __pa(param + 5));
ret = omap_smc2(idx, flag, __pa(param));
+ put_cpu();
+
return ret;
}
@@ -119,8 +126,8 @@ phys_addr_t omap_secure_ram_mempool_base(void)
#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM)
u32 omap3_save_secure_ram(void __iomem *addr, int size)
{
+ static u32 param[5];
u32 ret;
- u32 param[5];
if (size != OMAP3_SAVE_SECURE_RAM_SZ)
return OMAP3_SAVE_SECURE_RAM_SZ;
@@ -153,8 +160,8 @@ u32 omap3_save_secure_ram(void __iomem *addr, int size)
u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs,
u32 arg1, u32 arg2, u32 arg3, u32 arg4)
{
+ static u32 param[5];
u32 ret;
- u32 param[5];
param[0] = nargs+1; /* RX-51 needs number of arguments + 1 */
param[1] = arg1;
diff --git a/arch/arm64/boot/dts/amd/Makefile b/arch/arm64/boot/dts/amd/Makefile
index 6a6093064a32..68103a8b0ef5 100644
--- a/arch/arm64/boot/dts/amd/Makefile
+++ b/arch/arm64/boot/dts/amd/Makefile
@@ -1,4 +1,2 @@
# SPDX-License-Identifier: GPL-2.0
-dtb-$(CONFIG_ARCH_SEATTLE) += amd-overdrive.dtb \
- amd-overdrive-rev-b0.dtb amd-overdrive-rev-b1.dtb \
- husky.dtb
+dtb-$(CONFIG_ARCH_SEATTLE) += amd-overdrive-rev-b0.dtb amd-overdrive-rev-b1.dtb
diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts
index 8e341be9a399..c290d1ce2b03 100644
--- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts
+++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts
@@ -9,6 +9,7 @@
/dts-v1/;
/include/ "amd-seattle-soc.dtsi"
+/include/ "amd-seattle-cpus.dtsi"
/ {
model = "AMD Seattle (Rev.B0) Development Board (Overdrive)";
@@ -36,14 +37,6 @@
status = "ok";
};
-&gpio2 {
- status = "ok";
-};
-
-&gpio3 {
- status = "ok";
-};
-
&gpio4 {
status = "ok";
};
@@ -79,10 +72,6 @@
};
};
-&ipmi_kcs {
- status = "ok";
-};
-
&smb0 {
/include/ "amd-seattle-xgbe-b.dtsi"
};
diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts
index 92cef05c6b74..e0926f6bb7c3 100644
--- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts
+++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts
@@ -9,6 +9,7 @@
/dts-v1/;
/include/ "amd-seattle-soc.dtsi"
+/include/ "amd-seattle-cpus.dtsi"
/ {
model = "AMD Seattle (Rev.B1) Development Board (Overdrive)";
diff --git a/arch/arm64/boot/dts/amd/amd-overdrive.dts b/arch/arm64/boot/dts/amd/amd-overdrive.dts
deleted file mode 100644
index 41b3a6c0993d..000000000000
--- a/arch/arm64/boot/dts/amd/amd-overdrive.dts
+++ /dev/null
@@ -1,66 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * DTS file for AMD Seattle Overdrive Development Board
- *
- * Copyright (C) 2014 Advanced Micro Devices, Inc.
- */
-
-/dts-v1/;
-
-/include/ "amd-seattle-soc.dtsi"
-
-/ {
- model = "AMD Seattle Development Board (Overdrive)";
- compatible = "amd,seattle-overdrive", "amd,seattle";
-
- chosen {
- stdout-path = &serial0;
- };
-};
-
-&ccp0 {
- status = "ok";
-};
-
-&gpio0 {
- status = "ok";
-};
-
-&gpio1 {
- status = "ok";
-};
-
-&i2c0 {
- status = "ok";
-};
-
-&pcie0 {
- status = "ok";
-};
-
-&spi0 {
- status = "ok";
-};
-
-&spi1 {
- status = "ok";
- sdcard0: sdcard@0 {
- compatible = "mmc-spi-slot";
- reg = <0>;
- spi-max-frequency = <20000000>;
- voltage-ranges = <3200 3400>;
- gpios = <&gpio0 7 0>;
- interrupt-parent = <&gpio0>;
- interrupts = <7 3>;
- pl022,hierarchy = <0>;
- pl022,interface = <0>;
- pl022,com-mode = <0x0>;
- pl022,rx-level-trig = <0>;
- pl022,tx-level-trig = <0>;
- };
-};
-
-&v2m0 {
- arm,msi-base-spi = <64>;
- arm,msi-num-spis = <256>;
-};
diff --git a/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi
new file mode 100644
index 000000000000..93688a0b6820
--- /dev/null
+++ b/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/ {
+ cpus {
+ #address-cells = <0x1>;
+ #size-cells = <0x0>;
+
+ cpu-map {
+ cluster0 {
+ core0 {
+ cpu = <&CPU0>;
+ };
+ core1 {
+ cpu = <&CPU1>;
+ };
+ };
+ cluster1 {
+ core0 {
+ cpu = <&CPU2>;
+ };
+ core1 {
+ cpu = <&CPU3>;
+ };
+ };
+ cluster2 {
+ core0 {
+ cpu = <&CPU4>;
+ };
+ core1 {
+ cpu = <&CPU5>;
+ };
+ };
+ cluster3 {
+ core0 {
+ cpu = <&CPU6>;
+ };
+ core1 {
+ cpu = <&CPU7>;
+ };
+ };
+ };
+
+ CPU0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x0>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_0>;
+
+ };
+
+ CPU1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x1>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_0>;
+ };
+
+ CPU2: cpu@100 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x100>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_1>;
+ };
+
+ CPU3: cpu@101 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x101>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_1>;
+ };
+
+ CPU4: cpu@200 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x200>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_2>;
+ };
+
+ CPU5: cpu@201 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x201>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_2>;
+ };
+
+ CPU6: cpu@300 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x300>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_3>;
+ };
+
+ CPU7: cpu@301 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57";
+ reg = <0x301>;
+ enable-method = "psci";
+
+ i-cache-size = <0xC000>;
+ i-cache-line-size = <64>;
+ i-cache-sets = <256>;
+ d-cache-size = <0x8000>;
+ d-cache-line-size = <64>;
+ d-cache-sets = <256>;
+ l2-cache = <&L2_3>;
+ };
+ };
+
+ L2_0: l2-cache0 {
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-unified;
+ next-level-cache = <&L3>;
+ };
+
+ L2_1: l2-cache1 {
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-unified;
+ next-level-cache = <&L3>;
+ };
+
+ L2_2: l2-cache2 {
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-unified;
+ next-level-cache = <&L3>;
+ };
+
+ L2_3: l2-cache3 {
+ cache-size = <0x100000>;
+ cache-line-size = <64>;
+ cache-sets = <1024>;
+ cache-unified;
+ next-level-cache = <&L3>;
+ };
+
+ L3: l3-cache {
+ cache-level = <3>;
+ cache-size = <0x800000>;
+ cache-line-size = <64>;
+ cache-sets = <8192>;
+ cache-unified;
+ };
+
+ pmu {
+ compatible = "arm,cortex-a57-pmu";
+ interrupts = <0x0 0x7 0x4>,
+ <0x0 0x8 0x4>,
+ <0x0 0x9 0x4>,
+ <0x0 0xa 0x4>,
+ <0x0 0xb 0x4>,
+ <0x0 0xc 0x4>,
+ <0x0 0xd 0x4>,
+ <0x0 0xe 0x4>;
+ interrupt-affinity = <&CPU0>,
+ <&CPU1>,
+ <&CPU2>,
+ <&CPU3>,
+ <&CPU4>,
+ <&CPU5>,
+ <&CPU6>,
+ <&CPU7>;
+ };
+};
diff --git a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi
index b664e7af74eb..690020589d41 100644
--- a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi
+++ b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi
@@ -38,18 +38,6 @@
<1 10 0xff04>;
};
- pmu {
- compatible = "arm,armv8-pmuv3";
- interrupts = <0 7 4>,
- <0 8 4>,
- <0 9 4>,
- <0 10 4>,
- <0 11 4>,
- <0 12 4>,
- <0 13 4>,
- <0 14 4>;
- };
-
smb0: smb {
compatible = "simple-bus";
#address-cells = <2>;
@@ -70,6 +58,7 @@
reg = <0 0xe0300000 0 0xf0000>;
interrupts = <0 355 4>;
clocks = <&sataclk_333mhz>;
+ iommus = <&sata0_smmu 0x0 0x1f>;
dma-coherent;
};
@@ -80,6 +69,27 @@
reg = <0 0xe0d00000 0 0xf0000>;
interrupts = <0 354 4>;
clocks = <&sataclk_333mhz>;
+ iommus = <&sata1_smmu 0x0e>,
+ <&sata1_smmu 0x0f>,
+ <&sata1_smmu 0x1e>;
+ dma-coherent;
+ };
+
+ sata0_smmu: iommu@e0200000 {
+ compatible = "arm,mmu-401";
+ reg = <0 0xe0200000 0 0x10000>;
+ #global-interrupts = <1>;
+ interrupts = <0 332 4>, <0 332 4>;
+ #iommu-cells = <2>;
+ dma-coherent;
+ };
+
+ sata1_smmu: iommu@e0c00000 {
+ compatible = "arm,mmu-401";
+ reg = <0 0xe0c00000 0 0x10000>;
+ #global-interrupts = <1>;
+ interrupts = <0 331 4>, <0 331 4>;
+ #iommu-cells = <1>;
dma-coherent;
};
@@ -201,6 +211,10 @@
reg = <0 0xe0100000 0 0x10000>;
interrupts = <0 3 4>;
dma-coherent;
+ iommus = <&sata1_smmu 0x00>,
+ <&sata1_smmu 0x02>,
+ <&sata1_smmu 0x40>,
+ <&sata1_smmu 0x42>;
};
pcie0: pcie@f0000000 {
@@ -213,12 +227,22 @@
msi-parent = <&v2m0>;
reg = <0 0xf0000000 0 0x10000000>;
- interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+ interrupt-map-mask = <0xff00 0x0 0x0 0x7>;
interrupt-map =
- <0x1000 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x120 0x1>,
- <0x1000 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x121 0x1>,
- <0x1000 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x122 0x1>,
- <0x1000 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x123 0x1>;
+ <0x1100 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x120 0x1>,
+ <0x1100 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x121 0x1>,
+ <0x1100 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x122 0x1>,
+ <0x1100 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x123 0x1>,
+
+ <0x1200 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x124 0x1>,
+ <0x1200 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x125 0x1>,
+ <0x1200 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x126 0x1>,
+ <0x1200 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x127 0x1>,
+
+ <0x1300 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x128 0x1>,
+ <0x1300 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x129 0x1>,
+ <0x1300 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x12a 0x1>,
+ <0x1300 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x12b 0x1>;
dma-coherent;
dma-ranges = <0x43000000 0x0 0x0 0x0 0x0 0x100 0x0>;
@@ -227,8 +251,18 @@
<0x01000000 0x00 0x00000000 0x00 0xefff0000 0x00 0x00010000>,
/* 32-bit MMIO (size=2G) */
<0x02000000 0x00 0x40000000 0x00 0x40000000 0x00 0x80000000>,
- /* 64-bit MMIO (size= 124G) */
+ /* 64-bit MMIO (size= 508G) */
<0x03000000 0x01 0x00000000 0x01 0x00000000 0x7f 0x00000000>;
+ iommu-map = <0x0 &pcie_smmu 0x0 0x10000>;
+ };
+
+ pcie_smmu: iommu@e0a00000 {
+ compatible = "arm,mmu-401";
+ reg = <0 0xe0a00000 0 0x10000>;
+ #global-interrupts = <1>;
+ interrupts = <0 333 4>, <0 333 4>;
+ #iommu-cells = <1>;
+ dma-coherent;
};
/* Perf CCN504 PMU */
diff --git a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi
index d97498361ce3..9259e547e2e8 100644
--- a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi
+++ b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi
@@ -55,7 +55,7 @@
clocks = <&xgmacclk0_dma_250mhz>, <&xgmacclk0_ptp_250mhz>;
clock-names = "dma_clk", "ptp_clk";
phy-mode = "xgmii";
- #stream-id-cells = <16>;
+ iommus = <&xgmac0_smmu 0x00 0x17>; /* 0-7, 16-23 */
dma-coherent;
};
@@ -81,11 +81,11 @@
clocks = <&xgmacclk1_dma_250mhz>, <&xgmacclk1_ptp_250mhz>;
clock-names = "dma_clk", "ptp_clk";
phy-mode = "xgmii";
- #stream-id-cells = <16>;
+ iommus = <&xgmac1_smmu 0x00 0x17>; /* 0-7, 16-23 */
dma-coherent;
};
- xgmac0_smmu: smmu@e0600000 {
+ xgmac0_smmu: iommu@e0600000 {
compatible = "arm,mmu-401";
reg = <0 0xe0600000 0 0x10000>;
#global-interrupts = <1>;
@@ -94,14 +94,11 @@
*/
<0 336 4>,
<0 336 4>;
-
- mmu-masters = <&xgmac0
- 0 1 2 3 4 5 6 7
- 16 17 18 19 20 21 22 23
- >;
+ #iommu-cells = <2>;
+ dma-coherent;
};
- xgmac1_smmu: smmu@e0800000 {
+ xgmac1_smmu: iommu@e0800000 {
compatible = "arm,mmu-401";
reg = <0 0xe0800000 0 0x10000>;
#global-interrupts = <1>;
@@ -110,9 +107,6 @@
*/
<0 335 4>,
<0 335 4>;
-
- mmu-masters = <&xgmac1
- 0 1 2 3 4 5 6 7
- 16 17 18 19 20 21 22 23
- >;
+ #iommu-cells = <2>;
+ dma-coherent;
};
diff --git a/arch/arm64/boot/dts/amd/husky.dts b/arch/arm64/boot/dts/amd/husky.dts
deleted file mode 100644
index 7acde34772cb..000000000000
--- a/arch/arm64/boot/dts/amd/husky.dts
+++ /dev/null
@@ -1,84 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * DTS file for AMD/Linaro 96Boards Enterprise Edition Server (Husky) Board
- * Note: Based-on AMD Seattle Rev.B0
- *
- * Copyright (C) 2015 Advanced Micro Devices, Inc.
- */
-
-/dts-v1/;
-
-/include/ "amd-seattle-soc.dtsi"
-
-/ {
- model = "Linaro 96Boards Enterprise Edition Server (Husky) Board";
- compatible = "amd,seattle-overdrive", "amd,seattle";
-
- chosen {
- stdout-path = &serial0;
- };
-
- psci {
- compatible = "arm,psci-0.2";
- method = "smc";
- };
-};
-
-&ccp0 {
- status = "ok";
- amd,zlib-support = <1>;
-};
-
-/**
- * NOTE: In Rev.B, gpio0 is reserved.
- */
-&gpio1 {
- status = "ok";
-};
-
-&gpio2 {
- status = "ok";
-};
-
-&gpio3 {
- status = "ok";
-};
-
-&gpio4 {
- status = "ok";
-};
-
-&i2c0 {
- status = "ok";
-};
-
-&i2c1 {
- status = "ok";
-};
-
-&pcie0 {
- status = "ok";
-};
-
-&spi0 {
- status = "ok";
-};
-
-&spi1 {
- status = "ok";
- sdcard0: sdcard@0 {
- compatible = "mmc-spi-slot";
- reg = <0>;
- spi-max-frequency = <20000000>;
- voltage-ranges = <3200 3400>;
- pl022,hierarchy = <0>;
- pl022,interface = <0>;
- pl022,com-mode = <0x0>;
- pl022,rx-level-trig = <0>;
- pl022,tx-level-trig = <0>;
- };
-};
-
-&smb0 {
- /include/ "amd-seattle-xgbe-b.dtsi"
-};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 01b01e320411..35d1939e690b 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -536,9 +536,9 @@
clock-names = "i2c";
clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
QORIQ_CLK_PLL_DIV(1)>;
- dmas = <&edma0 1 39>,
- <&edma0 1 38>;
- dma-names = "tx", "rx";
+ dmas = <&edma0 1 38>,
+ <&edma0 1 39>;
+ dma-names = "rx", "tx";
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 687fea6d8afa..4e7bd04d9798 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -499,9 +499,9 @@
interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
QORIQ_CLK_PLL_DIV(2)>;
- dmas = <&edma0 1 39>,
- <&edma0 1 38>;
- dma-names = "tx", "rx";
+ dmas = <&edma0 1 38>,
+ <&edma0 1 39>;
+ dma-names = "rx", "tx";
status = "disabled";
};
diff --git a/arch/h8300/include/asm/user.h b/arch/h8300/include/asm/user.h
index 2298909f24c6..161653d84b34 100644
--- a/arch/h8300/include/asm/user.h
+++ b/arch/h8300/include/asm/user.h
@@ -67,9 +67,5 @@ struct user {
unsigned long magic; /* To uniquely identify a core file */
char u_comm[32]; /* User command that was responsible */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
#endif
diff --git a/arch/ia64/include/asm/user.h b/arch/ia64/include/asm/user.h
index 0ba486651b7c..ec03d3ab8715 100644
--- a/arch/ia64/include/asm/user.h
+++ b/arch/ia64/include/asm/user.h
@@ -50,10 +50,4 @@ struct user {
char u_comm[32]; /* user command name */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_DATA_START_ADDR (u.start_data)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
#endif /* _ASM_IA64_USER_H */
diff --git a/arch/m68k/include/asm/user.h b/arch/m68k/include/asm/user.h
index 509d555977c8..61413bff613a 100644
--- a/arch/m68k/include/asm/user.h
+++ b/arch/m68k/include/asm/user.h
@@ -79,9 +79,5 @@ struct user{
unsigned long magic; /* To uniquely identify a core file */
char u_comm[32]; /* User command that was responsible */
};
-#define NBPG 4096
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
#endif
diff --git a/arch/mips/crypto/crc32-mips.c b/arch/mips/crypto/crc32-mips.c
index 0a03529cf317..3e4f5ba104f8 100644
--- a/arch/mips/crypto/crc32-mips.c
+++ b/arch/mips/crypto/crc32-mips.c
@@ -28,7 +28,7 @@ enum crc_type {
};
#ifndef TOOLCHAIN_SUPPORTS_CRC
-#define _ASM_MACRO_CRC32(OP, SZ, TYPE) \
+#define _ASM_SET_CRC(OP, SZ, TYPE) \
_ASM_MACRO_3R(OP, rt, rs, rt2, \
".ifnc \\rt, \\rt2\n\t" \
".error \"invalid operands \\\"" #OP " \\rt,\\rs,\\rt2\\\"\"\n\t" \
@@ -37,30 +37,36 @@ _ASM_MACRO_3R(OP, rt, rs, rt2, \
((SZ) << 6) | ((TYPE) << 8)) \
_ASM_INSN32_IF_MM(0x00000030 | (__rs << 16) | (__rt << 21) | \
((SZ) << 14) | ((TYPE) << 3)))
-_ASM_MACRO_CRC32(crc32b, 0, 0);
-_ASM_MACRO_CRC32(crc32h, 1, 0);
-_ASM_MACRO_CRC32(crc32w, 2, 0);
-_ASM_MACRO_CRC32(crc32d, 3, 0);
-_ASM_MACRO_CRC32(crc32cb, 0, 1);
-_ASM_MACRO_CRC32(crc32ch, 1, 1);
-_ASM_MACRO_CRC32(crc32cw, 2, 1);
-_ASM_MACRO_CRC32(crc32cd, 3, 1);
-#define _ASM_SET_CRC ""
+#define _ASM_UNSET_CRC(op, SZ, TYPE) ".purgem " #op "\n\t"
#else /* !TOOLCHAIN_SUPPORTS_CRC */
-#define _ASM_SET_CRC ".set\tcrc\n\t"
+#define _ASM_SET_CRC(op, SZ, TYPE) ".set\tcrc\n\t"
+#define _ASM_UNSET_CRC(op, SZ, TYPE)
#endif
-#define _CRC32(crc, value, size, type) \
-do { \
- __asm__ __volatile__( \
- ".set push\n\t" \
- _ASM_SET_CRC \
- #type #size " %0, %1, %0\n\t" \
- ".set pop" \
- : "+r" (crc) \
- : "r" (value)); \
+#define __CRC32(crc, value, op, SZ, TYPE) \
+do { \
+ __asm__ __volatile__( \
+ ".set push\n\t" \
+ _ASM_SET_CRC(op, SZ, TYPE) \
+ #op " %0, %1, %0\n\t" \
+ _ASM_UNSET_CRC(op, SZ, TYPE) \
+ ".set pop" \
+ : "+r" (crc) \
+ : "r" (value)); \
} while (0)
+#define _CRC32_crc32b(crc, value) __CRC32(crc, value, crc32b, 0, 0)
+#define _CRC32_crc32h(crc, value) __CRC32(crc, value, crc32h, 1, 0)
+#define _CRC32_crc32w(crc, value) __CRC32(crc, value, crc32w, 2, 0)
+#define _CRC32_crc32d(crc, value) __CRC32(crc, value, crc32d, 3, 0)
+#define _CRC32_crc32cb(crc, value) __CRC32(crc, value, crc32cb, 0, 1)
+#define _CRC32_crc32ch(crc, value) __CRC32(crc, value, crc32ch, 1, 1)
+#define _CRC32_crc32cw(crc, value) __CRC32(crc, value, crc32cw, 2, 1)
+#define _CRC32_crc32cd(crc, value) __CRC32(crc, value, crc32cd, 3, 1)
+
+#define _CRC32(crc, value, size, op) \
+ _CRC32_##op##size(crc, value)
+
#define CRC32(crc, value, size) \
_CRC32(crc, value, size, crc32)
diff --git a/arch/mips/include/asm/mach-rc32434/rb.h b/arch/mips/include/asm/mach-rc32434/rb.h
index 34d179ca020b..dd9d4b026e62 100644
--- a/arch/mips/include/asm/mach-rc32434/rb.h
+++ b/arch/mips/include/asm/mach-rc32434/rb.h
@@ -29,15 +29,6 @@
#define DEV3TC 0x01003C
#define BTCS 0x010040
#define BTCOMPARE 0x010044
-#define GPIOBASE 0x050000
-/* Offsets relative to GPIOBASE */
-#define GPIOFUNC 0x00
-#define GPIOCFG 0x04
-#define GPIOD 0x08
-#define GPIOILEVEL 0x0C
-#define GPIOISTAT 0x10
-#define GPIONMIEN 0x14
-#define IMASK6 0x38
#define LO_WPX (1 << 0)
#define LO_ALE (1 << 1)
#define LO_CLE (1 << 2)
diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c
index 64726c670ca6..5204fc6d6d50 100644
--- a/arch/mips/lantiq/falcon/sysctrl.c
+++ b/arch/mips/lantiq/falcon/sysctrl.c
@@ -167,6 +167,8 @@ static inline void clkdev_add_sys(const char *dev, unsigned int module,
{
struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL);
+ if (!clk)
+ return;
clk->cl.dev_id = dev;
clk->cl.con_id = NULL;
clk->cl.clk = clk;
diff --git a/arch/mips/lantiq/xway/gptu.c b/arch/mips/lantiq/xway/gptu.c
index 3d5683e75cf1..200fe9ff641d 100644
--- a/arch/mips/lantiq/xway/gptu.c
+++ b/arch/mips/lantiq/xway/gptu.c
@@ -122,6 +122,8 @@ static inline void clkdev_add_gptu(struct device *dev, const char *con,
{
struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL);
+ if (!clk)
+ return;
clk->cl.dev_id = dev_name(dev);
clk->cl.con_id = con;
clk->cl.clk = clk;
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index 917fac1636b7..084f6caba5f2 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -315,6 +315,8 @@ static void clkdev_add_pmu(const char *dev, const char *con, bool deactivate,
{
struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL);
+ if (!clk)
+ return;
clk->cl.dev_id = dev;
clk->cl.con_id = con;
clk->cl.clk = clk;
@@ -338,6 +340,8 @@ static void clkdev_add_cgu(const char *dev, const char *con,
{
struct clk *clk = kzalloc(sizeof(struct clk), GFP_KERNEL);
+ if (!clk)
+ return;
clk->cl.dev_id = dev;
clk->cl.con_id = con;
clk->cl.clk = clk;
@@ -356,24 +360,28 @@ static void clkdev_add_pci(void)
struct clk *clk_ext = kzalloc(sizeof(struct clk), GFP_KERNEL);
/* main pci clock */
- clk->cl.dev_id = "17000000.pci";
- clk->cl.con_id = NULL;
- clk->cl.clk = clk;
- clk->rate = CLOCK_33M;
- clk->rates = valid_pci_rates;
- clk->enable = pci_enable;
- clk->disable = pmu_disable;
- clk->module = 0;
- clk->bits = PMU_PCI;
- clkdev_add(&clk->cl);
+ if (clk) {
+ clk->cl.dev_id = "17000000.pci";
+ clk->cl.con_id = NULL;
+ clk->cl.clk = clk;
+ clk->rate = CLOCK_33M;
+ clk->rates = valid_pci_rates;
+ clk->enable = pci_enable;
+ clk->disable = pmu_disable;
+ clk->module = 0;
+ clk->bits = PMU_PCI;
+ clkdev_add(&clk->cl);
+ }
/* use internal/external bus clock */
- clk_ext->cl.dev_id = "17000000.pci";
- clk_ext->cl.con_id = "external";
- clk_ext->cl.clk = clk_ext;
- clk_ext->enable = pci_ext_enable;
- clk_ext->disable = pci_ext_disable;
- clkdev_add(&clk_ext->cl);
+ if (clk_ext) {
+ clk_ext->cl.dev_id = "17000000.pci";
+ clk_ext->cl.con_id = "external";
+ clk_ext->cl.clk = clk_ext;
+ clk_ext->enable = pci_ext_enable;
+ clk_ext->disable = pci_ext_disable;
+ clkdev_add(&clk_ext->cl);
+ }
}
/* xway socs can generate clocks on gpio pins */
@@ -393,9 +401,15 @@ static void clkdev_add_clkout(void)
char *name;
name = kzalloc(sizeof("clkout0"), GFP_KERNEL);
+ if (!name)
+ continue;
sprintf(name, "clkout%d", i);
clk = kzalloc(sizeof(struct clk), GFP_KERNEL);
+ if (!clk) {
+ kfree(name);
+ continue;
+ }
clk->cl.dev_id = "1f103000.cgu";
clk->cl.con_id = name;
clk->cl.clk = clk;
diff --git a/arch/mips/rb532/gpio.c b/arch/mips/rb532/gpio.c
index 94f02ada4082..29c21b9d42da 100644
--- a/arch/mips/rb532/gpio.c
+++ b/arch/mips/rb532/gpio.c
@@ -37,6 +37,16 @@
#include <asm/mach-rc32434/rb.h>
#include <asm/mach-rc32434/gpio.h>
+#define GPIOBASE 0x050000
+/* Offsets relative to GPIOBASE */
+#define GPIOFUNC 0x00
+#define GPIOCFG 0x04
+#define GPIOD 0x08
+#define GPIOILEVEL 0x0C
+#define GPIOISTAT 0x10
+#define GPIONMIEN 0x14
+#define IMASK6 0x38
+
struct rb532_gpio_chip {
struct gpio_chip chip;
void __iomem *regbase;
diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c
index dfc52f661ad0..38d12f417e48 100644
--- a/arch/mips/sgi-ip22/ip22-gio.c
+++ b/arch/mips/sgi-ip22/ip22-gio.c
@@ -363,6 +363,8 @@ static void ip22_check_gio(int slotno, unsigned long addr, int irq)
printk(KERN_INFO "GIO: slot %d : %s (id %x)\n",
slotno, name, id);
gio_dev = kzalloc(sizeof *gio_dev, GFP_KERNEL);
+ if (!gio_dev)
+ return;
gio_dev->name = name;
gio_dev->slotno = slotno;
gio_dev->id.id = id;
diff --git a/arch/powerpc/include/asm/user.h b/arch/powerpc/include/asm/user.h
index 99443b8594e7..7fae7e597ba4 100644
--- a/arch/powerpc/include/asm/user.h
+++ b/arch/powerpc/include/asm/user.h
@@ -44,9 +44,4 @@ struct user {
char u_comm[32]; /* user command name */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_DATA_START_ADDR (u.start_data)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
#endif /* _ASM_POWERPC_USER_H */
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index ea8ec8a960bd..00fd9c548f26 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -16,6 +16,7 @@ config RISCV
select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_HAS_BINFMT_FLAT
+ select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEBUG_VIRTUAL if MMU
select ARCH_HAS_DEBUG_WX
@@ -47,6 +48,7 @@ config RISCV
select CLONE_BACKWARDS
select CLINT_TIMER if !MMU
select COMMON_CLK
+ select CPU_PM if CPU_IDLE
select EDAC_SUPPORT
select GENERIC_ARCH_TOPOLOGY if SMP
select GENERIC_ATOMIC64 if !64BIT
@@ -533,4 +535,10 @@ source "kernel/power/Kconfig"
endmenu
+menu "CPU Power Management"
+
+source "drivers/cpuidle/Kconfig"
+
+endmenu
+
source "arch/riscv/kvm/Kconfig"
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index c112ab2a9052..34592d00dde8 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -36,6 +36,9 @@ config SOC_VIRT
select GOLDFISH
select RTC_DRV_GOLDFISH if RTC_CLASS
select SIFIVE_PLIC
+ select PM_GENERIC_DOMAINS if PM
+ select PM_GENERIC_DOMAINS_OF if PM && OF
+ select RISCV_SBI_CPUIDLE if CPU_IDLE
help
This enables support for QEMU Virt Machine.
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
index 984872f3d3a9..b9e30df127fe 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
@@ -203,6 +203,8 @@
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
+ spi-tx-bus-width = <4>;
+ spi-rx-bus-width = <4>;
m25p,fast-read;
broken-flash-reset;
};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
index 7ba99b4da304..8d23401b0bbb 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
@@ -205,6 +205,8 @@
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
+ spi-tx-bus-width = <4>;
+ spi-rx-bus-width = <4>;
m25p,fast-read;
broken-flash-reset;
};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
index be9b12c9b374..24fd83b43d9d 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
@@ -213,6 +213,8 @@
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
+ spi-tx-bus-width = <4>;
+ spi-rx-bus-width = <4>;
m25p,fast-read;
broken-flash-reset;
};
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
index 031c0c28f819..25341f38292a 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
@@ -178,6 +178,8 @@
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <50000000>;
+ spi-tx-bus-width = <4>;
+ spi-rx-bus-width = <4>;
m25p,fast-read;
broken-flash-reset;
};
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 7cd10ded7bf8..30e3017f22bc 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -15,11 +15,14 @@ CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_PROFILING=y
CONFIG_SOC_MICROCHIP_POLARFIRE=y
CONFIG_SOC_SIFIVE=y
CONFIG_SOC_VIRT=y
CONFIG_SMP=y
CONFIG_HOTPLUG_CPU=y
+CONFIG_PM=y
+CONFIG_CPU_IDLE=y
CONFIG_VIRTUALIZATION=y
CONFIG_KVM=m
CONFIG_JUMP_LABEL=y
@@ -64,8 +67,6 @@ CONFIG_INPUT_MOUSEDEV=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_OF_PLATFORM=y
-CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
-CONFIG_HVC_RISCV_SBI=y
CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_HW_RANDOM_VIRTIO=y
diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig
index 3f42ed87dde8..2438fa39f8ae 100644
--- a/arch/riscv/configs/nommu_k210_defconfig
+++ b/arch/riscv/configs/nommu_k210_defconfig
@@ -21,7 +21,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
# CONFIG_AIO is not set
# CONFIG_IO_URING is not set
# CONFIG_ADVISE_SYSCALLS is not set
-# CONFIG_MEMBARRIER is not set
# CONFIG_KALLSYMS is not set
CONFIG_EMBEDDED=y
# CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig
index af64b95e88cc..9a133e63ae5b 100644
--- a/arch/riscv/configs/nommu_k210_sdcard_defconfig
+++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig
@@ -13,7 +13,6 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
# CONFIG_AIO is not set
# CONFIG_IO_URING is not set
# CONFIG_ADVISE_SYSCALLS is not set
-# CONFIG_MEMBARRIER is not set
# CONFIG_KALLSYMS is not set
CONFIG_EMBEDDED=y
# CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig
index e1c9864b6237..5269fbb6b4fc 100644
--- a/arch/riscv/configs/nommu_virt_defconfig
+++ b/arch/riscv/configs/nommu_virt_defconfig
@@ -19,7 +19,6 @@ CONFIG_EXPERT=y
# CONFIG_AIO is not set
# CONFIG_IO_URING is not set
# CONFIG_ADVISE_SYSCALLS is not set
-# CONFIG_MEMBARRIER is not set
# CONFIG_KALLSYMS is not set
# CONFIG_VM_EVENT_COUNTERS is not set
# CONFIG_COMPAT_BRK is not set
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
index e0e5c7c09ab8..7e5efdc3829d 100644
--- a/arch/riscv/configs/rv32_defconfig
+++ b/arch/riscv/configs/rv32_defconfig
@@ -15,11 +15,14 @@ CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
+CONFIG_PROFILING=y
CONFIG_SOC_SIFIVE=y
CONFIG_SOC_VIRT=y
CONFIG_ARCH_RV32I=y
CONFIG_SMP=y
CONFIG_HOTPLUG_CPU=y
+CONFIG_PM=y
+CONFIG_CPU_IDLE=y
CONFIG_VIRTUALIZATION=y
CONFIG_KVM=m
CONFIG_JUMP_LABEL=y
@@ -62,8 +65,6 @@ CONFIG_INPUT_MOUSEDEV=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_OF_PLATFORM=y
-CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
-CONFIG_HVC_RISCV_SBI=y
CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM=y
CONFIG_HW_RANDOM_VIRTIO=y
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 618d7c5af1a2..8c2549b16ac0 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -67,4 +67,30 @@
#error "Unexpected __SIZEOF_SHORT__"
#endif
+#ifdef __ASSEMBLY__
+
+/* Common assembly source macros */
+
+#ifdef CONFIG_XIP_KERNEL
+.macro XIP_FIXUP_OFFSET reg
+ REG_L t0, _xip_fixup
+ add \reg, \reg, t0
+.endm
+.macro XIP_FIXUP_FLASH_OFFSET reg
+ la t1, __data_loc
+ REG_L t1, _xip_phys_offset
+ sub \reg, \reg, t1
+ add \reg, \reg, t0
+.endm
+_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
+_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET
+#else
+.macro XIP_FIXUP_OFFSET reg
+.endm
+.macro XIP_FIXUP_FLASH_OFFSET reg
+.endm
+#endif /* CONFIG_XIP_KERNEL */
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_RISCV_ASM_H */
diff --git a/arch/riscv/include/asm/cpuidle.h b/arch/riscv/include/asm/cpuidle.h
new file mode 100644
index 000000000000..71fdc607d4bc
--- /dev/null
+++ b/arch/riscv/include/asm/cpuidle.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021 Allwinner Ltd
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#ifndef _ASM_RISCV_CPUIDLE_H
+#define _ASM_RISCV_CPUIDLE_H
+
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
+static inline void cpu_do_idle(void)
+{
+ /*
+ * Add mb() here to ensure that all
+ * IO/MEM accesses are completed prior
+ * to entering WFI.
+ */
+ mb();
+ wait_for_interrupt();
+}
+
+#endif
diff --git a/arch/riscv/include/asm/current.h b/arch/riscv/include/asm/current.h
index 1de233d8e8de..21774d868c65 100644
--- a/arch/riscv/include/asm/current.h
+++ b/arch/riscv/include/asm/current.h
@@ -33,6 +33,8 @@ static __always_inline struct task_struct *get_current(void)
#define current get_current()
+register unsigned long current_stack_pointer __asm__("sp");
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_RISCV_CURRENT_H */
diff --git a/arch/riscv/include/asm/module.lds.h b/arch/riscv/include/asm/module.lds.h
index 4254ff2ff049..1075beae1ac6 100644
--- a/arch/riscv/include/asm/module.lds.h
+++ b/arch/riscv/include/asm/module.lds.h
@@ -2,8 +2,8 @@
/* Copyright (C) 2017 Andes Technology Corporation */
#ifdef CONFIG_MODULE_SECTIONS
SECTIONS {
- .plt (NOLOAD) : { BYTE(0) }
- .got (NOLOAD) : { BYTE(0) }
- .got.plt (NOLOAD) : { BYTE(0) }
+ .plt : { BYTE(0) }
+ .got : { BYTE(0) }
+ .got.plt : { BYTE(0) }
}
#endif
diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h
new file mode 100644
index 000000000000..8be391c2aecb
--- /dev/null
+++ b/arch/riscv/include/asm/suspend.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#ifndef _ASM_RISCV_SUSPEND_H
+#define _ASM_RISCV_SUSPEND_H
+
+#include <asm/ptrace.h>
+
+struct suspend_context {
+ /* Saved and restored by low-level functions */
+ struct pt_regs regs;
+ /* Saved and restored by high-level functions */
+ unsigned long scratch;
+ unsigned long tvec;
+ unsigned long ie;
+#ifdef CONFIG_MMU
+ unsigned long satp;
+#endif
+};
+
+/* Low-level CPU suspend entry function */
+int __cpu_suspend_enter(struct suspend_context *context);
+
+/* High-level CPU suspend which will save context and call finish() */
+int cpu_suspend(unsigned long arg,
+ int (*finish)(unsigned long arg,
+ unsigned long entry,
+ unsigned long context));
+
+/* Low-level CPU resume entry function */
+int __cpu_resume_enter(unsigned long hartid, unsigned long context);
+
+#endif
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 60da0dcacf14..74d888c8d631 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -11,11 +11,17 @@
#include <asm/page.h>
#include <linux/const.h>
+#ifdef CONFIG_KASAN
+#define KASAN_STACK_ORDER 1
+#else
+#define KASAN_STACK_ORDER 0
+#endif
+
/* thread information allocation */
#ifdef CONFIG_64BIT
-#define THREAD_SIZE_ORDER (2)
+#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER)
#else
-#define THREAD_SIZE_ORDER (1)
+#define THREAD_SIZE_ORDER (1 + KASAN_STACK_ORDER)
#endif
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index e0133d113216..87adbe47bc15 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -48,6 +48,8 @@ obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o
+obj-$(CONFIG_CPU_PM) += suspend_entry.o suspend.o
+
obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o
obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index df0519a64eaf..df9444397908 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -13,6 +13,7 @@
#include <asm/thread_info.h>
#include <asm/ptrace.h>
#include <asm/cpu_ops_sbi.h>
+#include <asm/suspend.h>
void asm_offsets(void);
@@ -113,6 +114,8 @@ void asm_offsets(void)
OFFSET(PT_BADADDR, pt_regs, badaddr);
OFFSET(PT_CAUSE, pt_regs, cause);
+ OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs);
+
OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero);
OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra);
OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp);
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index d2a936195295..ccb617791e56 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -69,11 +69,11 @@ int riscv_of_parent_hartid(struct device_node *node)
.uprop = #UPROP, \
.isa_ext_id = EXTID, \
}
-/**
+/*
* Here are the ordering rules of extension naming defined by RISC-V
* specification :
* 1. All extensions should be separated from other multi-letter extensions
- * from other multi-letter extensions by an underscore.
+ * by an underscore.
* 2. The first letter following the 'Z' conventionally indicates the most
* closely related alphabetical extension category, IMAFDQLCBKJTPVH.
* If multiple 'Z' extensions are named, they should be ordered first
@@ -110,7 +110,7 @@ static void print_isa_ext(struct seq_file *f)
}
}
-/**
+/*
* These are the only valid base (single letter) ISA extensions as per the spec.
* It also specifies the canonical order in which it appears in the spec.
* Some of the extension may just be a place holder for now (B, K, P, J).
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index 2e16f6732cdf..4f5a6f84e2a4 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -21,7 +21,7 @@ const struct cpu_operations cpu_ops_sbi;
* be invoked from multiple threads in parallel. Define a per cpu data
* to handle that.
*/
-DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
unsigned long priv)
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index ec07f991866a..893b8bb69391 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -16,26 +16,6 @@
#include <asm/image.h>
#include "efi-header.S"
-#ifdef CONFIG_XIP_KERNEL
-.macro XIP_FIXUP_OFFSET reg
- REG_L t0, _xip_fixup
- add \reg, \reg, t0
-.endm
-.macro XIP_FIXUP_FLASH_OFFSET reg
- la t0, __data_loc
- REG_L t1, _xip_phys_offset
- sub \reg, \reg, t1
- add \reg, \reg, t0
-.endm
-_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
-_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET
-#else
-.macro XIP_FIXUP_OFFSET reg
-.endm
-.macro XIP_FIXUP_FLASH_OFFSET reg
-.endm
-#endif /* CONFIG_XIP_KERNEL */
-
__HEAD
ENTRY(_start)
/*
@@ -89,7 +69,8 @@ pe_head_start:
.align 2
#ifdef CONFIG_MMU
-relocate:
+ .global relocate_enable_mmu
+relocate_enable_mmu:
/* Relocate return address */
la a1, kernel_map
XIP_FIXUP_OFFSET a1
@@ -184,7 +165,7 @@ secondary_start_sbi:
/* Enable virtual memory and relocate to virtual address */
la a0, swapper_pg_dir
XIP_FIXUP_OFFSET a0
- call relocate
+ call relocate_enable_mmu
#endif
call setup_trap_vector
tail smp_callin
@@ -328,7 +309,7 @@ clear_bss_done:
#ifdef CONFIG_MMU
la a0, early_pg_dir
XIP_FIXUP_OFFSET a0
- call relocate
+ call relocate_enable_mmu
#endif /* CONFIG_MMU */
call setup_trap_vector
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 4a48287513c3..c29cef90d1dd 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -69,7 +69,7 @@ static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
return 0;
}
-static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
+static int apply_r_riscv_rvc_branch_rela(struct module *me, u32 *location,
Elf_Addr v)
{
ptrdiff_t offset = (void *)v - (void *)location;
@@ -301,7 +301,7 @@ static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
[R_RISCV_64] = apply_r_riscv_64_rela,
[R_RISCV_BRANCH] = apply_r_riscv_branch_rela,
[R_RISCV_JAL] = apply_r_riscv_jal_rela,
- [R_RISCV_RVC_BRANCH] = apply_r_riscv_rcv_branch_rela,
+ [R_RISCV_RVC_BRANCH] = apply_r_riscv_rvc_branch_rela,
[R_RISCV_RVC_JUMP] = apply_r_riscv_rvc_jump_rela,
[R_RISCV_PCREL_HI20] = apply_r_riscv_pcrel_hi20_rela,
[R_RISCV_PCREL_LO12_I] = apply_r_riscv_pcrel_lo12_i_rela,
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
index 55faa4991b87..3348a61de7d9 100644
--- a/arch/riscv/kernel/perf_callchain.c
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -68,7 +68,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
static bool fill_callchain(void *entry, unsigned long pc)
{
- return perf_callchain_store(entry, pc);
+ return perf_callchain_store(entry, pc) == 0;
}
void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 03ac3aa611f5..504b496787aa 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -23,6 +23,7 @@
#include <asm/string.h>
#include <asm/switch_to.h>
#include <asm/thread_info.h>
+#include <asm/cpuidle.h>
register unsigned long gp_in_global __asm__("gp");
@@ -37,7 +38,7 @@ extern asmlinkage void ret_from_kernel_thread(void);
void arch_cpu_idle(void)
{
- wait_for_interrupt();
+ cpu_do_idle();
raw_local_irq_enable();
}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 14d2b53ec322..08d11a53f39e 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -14,8 +14,6 @@
#include <asm/stacktrace.h>
-register unsigned long sp_in_global __asm__("sp");
-
#ifdef CONFIG_FRAME_POINTER
void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
@@ -30,7 +28,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
pc = instruction_pointer(regs);
} else if (task == NULL || task == current) {
fp = (unsigned long)__builtin_frame_address(0);
- sp = sp_in_global;
+ sp = current_stack_pointer;
pc = (unsigned long)walk_stackframe;
} else {
/* task blocked in __switch_to */
@@ -78,7 +76,7 @@ void notrace walk_stackframe(struct task_struct *task,
sp = user_stack_pointer(regs);
pc = instruction_pointer(regs);
} else if (task == NULL || task == current) {
- sp = sp_in_global;
+ sp = current_stack_pointer;
pc = (unsigned long)walk_stackframe;
} else {
/* task blocked in __switch_to */
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
new file mode 100644
index 000000000000..9ba24fb8cc93
--- /dev/null
+++ b/arch/riscv/kernel/suspend.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/ftrace.h>
+#include <asm/csr.h>
+#include <asm/suspend.h>
+
+static void suspend_save_csrs(struct suspend_context *context)
+{
+ context->scratch = csr_read(CSR_SCRATCH);
+ context->tvec = csr_read(CSR_TVEC);
+ context->ie = csr_read(CSR_IE);
+
+ /*
+ * No need to save/restore IP CSR (i.e. MIP or SIP) because:
+ *
+ * 1. For no-MMU (M-mode) kernel, the bits in MIP are set by
+ * external devices (such as interrupt controller, timer, etc).
+ * 2. For MMU (S-mode) kernel, the bits in SIP are set by
+ * M-mode firmware and external devices (such as interrupt
+ * controller, etc).
+ */
+
+#ifdef CONFIG_MMU
+ context->satp = csr_read(CSR_SATP);
+#endif
+}
+
+static void suspend_restore_csrs(struct suspend_context *context)
+{
+ csr_write(CSR_SCRATCH, context->scratch);
+ csr_write(CSR_TVEC, context->tvec);
+ csr_write(CSR_IE, context->ie);
+
+#ifdef CONFIG_MMU
+ csr_write(CSR_SATP, context->satp);
+#endif
+}
+
+int cpu_suspend(unsigned long arg,
+ int (*finish)(unsigned long arg,
+ unsigned long entry,
+ unsigned long context))
+{
+ int rc = 0;
+ struct suspend_context context = { 0 };
+
+ /* Finisher should be non-NULL */
+ if (!finish)
+ return -EINVAL;
+
+ /* Save additional CSRs*/
+ suspend_save_csrs(&context);
+
+ /*
+ * Function graph tracer state gets incosistent when the kernel
+ * calls functions that never return (aka finishers) hence disable
+ * graph tracing during their execution.
+ */
+ pause_graph_tracing();
+
+ /* Save context on stack */
+ if (__cpu_suspend_enter(&context)) {
+ /* Call the finisher */
+ rc = finish(arg, __pa_symbol(__cpu_resume_enter),
+ (ulong)&context);
+
+ /*
+ * Should never reach here, unless the suspend finisher
+ * fails. Successful cpu_suspend() should return from
+ * __cpu_resume_entry()
+ */
+ if (!rc)
+ rc = -EOPNOTSUPP;
+ }
+
+ /* Enable function graph tracer */
+ unpause_graph_tracing();
+
+ /* Restore additional CSRs */
+ suspend_restore_csrs(&context);
+
+ return rc;
+}
diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S
new file mode 100644
index 000000000000..4b07b809a2b8
--- /dev/null
+++ b/arch/riscv/kernel/suspend_entry.S
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/csr.h>
+
+ .text
+ .altmacro
+ .option norelax
+
+ENTRY(__cpu_suspend_enter)
+ /* Save registers (except A0 and T0-T6) */
+ REG_S ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+ REG_S sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+ REG_S gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+ REG_S tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+ REG_S s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+ REG_S s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+ REG_S a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+ REG_S a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+ REG_S a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+ REG_S a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+ REG_S a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+ REG_S a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+ REG_S a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+ REG_S s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+ REG_S s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+ REG_S s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+ REG_S s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+ REG_S s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+ REG_S s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+ REG_S s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+ REG_S s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+ REG_S s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+ REG_S s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+
+ /* Save CSRs */
+ csrr t0, CSR_EPC
+ REG_S t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+ csrr t0, CSR_STATUS
+ REG_S t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+ csrr t0, CSR_TVAL
+ REG_S t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+ csrr t0, CSR_CAUSE
+ REG_S t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+
+ /* Return non-zero value */
+ li a0, 1
+
+ /* Return to C code */
+ ret
+END(__cpu_suspend_enter)
+
+ENTRY(__cpu_resume_enter)
+ /* Load the global pointer */
+ .option push
+ .option norelax
+ la gp, __global_pointer$
+ .option pop
+
+#ifdef CONFIG_MMU
+ /* Save A0 and A1 */
+ add t0, a0, zero
+ add t1, a1, zero
+
+ /* Enable MMU */
+ la a0, swapper_pg_dir
+ XIP_FIXUP_OFFSET a0
+ call relocate_enable_mmu
+
+ /* Restore A0 and A1 */
+ add a0, t0, zero
+ add a1, t1, zero
+#endif
+
+ /* Make A0 point to suspend context */
+ add a0, a1, zero
+
+ /* Restore CSRs */
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0)
+ csrw CSR_EPC, t0
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0)
+ csrw CSR_STATUS, t0
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0)
+ csrw CSR_TVAL, t0
+ REG_L t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0)
+ csrw CSR_CAUSE, t0
+
+ /* Restore registers (except A0 and T0-T6) */
+ REG_L ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0)
+ REG_L sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0)
+ REG_L gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0)
+ REG_L tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0)
+ REG_L s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0)
+ REG_L s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0)
+ REG_L a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0)
+ REG_L a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0)
+ REG_L a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0)
+ REG_L a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0)
+ REG_L a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0)
+ REG_L a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0)
+ REG_L a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0)
+ REG_L s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0)
+ REG_L s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0)
+ REG_L s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0)
+ REG_L s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0)
+ REG_L s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0)
+ REG_L s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0)
+ REG_L s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0)
+ REG_L s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0)
+ REG_L s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0)
+ REG_L s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0)
+
+ /* Return zero value */
+ add a0, zero, zero
+
+ /* Return to C code */
+ ret
+END(__cpu_resume_enter)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 9b80e8bed3f6..77b5a03de13a 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -58,6 +58,7 @@ config S390
select ALTERNATE_USER_ADDRESS_SPACE
select ARCH_32BIT_USTAT_F_TINODE
select ARCH_BINFMT_ELF_STATE
+ select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM
select ARCH_ENABLE_MEMORY_HOTREMOVE
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
diff --git a/arch/s390/include/asm/alternative-asm.h b/arch/s390/include/asm/alternative-asm.h
index 955d620db23e..bb3837d7387c 100644
--- a/arch/s390/include/asm/alternative-asm.h
+++ b/arch/s390/include/asm/alternative-asm.h
@@ -37,9 +37,15 @@
* a 2-byte nop if the size of the area is not divisible by 6.
*/
.macro alt_pad_fill bytes
- .fill ( \bytes ) / 6, 6, 0xc0040000
- .fill ( \bytes ) % 6 / 4, 4, 0x47000000
- .fill ( \bytes ) % 6 % 4 / 2, 2, 0x0700
+ .rept ( \bytes ) / 6
+ brcl 0,0
+ .endr
+ .rept ( \bytes ) % 6 / 4
+ nop
+ .endr
+ .rept ( \bytes ) % 6 % 4 / 2
+ nopr
+ .endr
.endm
/*
diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index d3880ca764ee..3f2856ed6808 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -71,11 +71,18 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
".if " oldinstr_pad_len(num) " > 6\n" \
"\tjg " e_oldinstr_pad_end "f\n" \
"6620:\n" \
- "\t.fill (" oldinstr_pad_len(num) " - (6620b-662b)) / 2, 2, 0x0700\n" \
+ "\t.rept (" oldinstr_pad_len(num) " - (6620b-662b)) / 2\n" \
+ "\tnopr\n" \
".else\n" \
- "\t.fill " oldinstr_pad_len(num) " / 6, 6, 0xc0040000\n" \
- "\t.fill " oldinstr_pad_len(num) " %% 6 / 4, 4, 0x47000000\n" \
- "\t.fill " oldinstr_pad_len(num) " %% 6 %% 4 / 2, 2, 0x0700\n" \
+ "\t.rept " oldinstr_pad_len(num) " / 6\n" \
+ "\t.brcl 0,0\n" \
+ "\t.endr\n" \
+ "\t.rept " oldinstr_pad_len(num) " %% 6 / 4\n" \
+ "\tnop\n" \
+ "\t.endr\n" \
+ "\t.rept " oldinstr_pad_len(num) " %% 6 %% 4 / 2\n" \
+ "\tnopr\n" \
+ ".endr\n" \
".endif\n"
#define OLDINSTR(oldinstr, num) \
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index ae75da592ccb..b515cfa62bd9 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -60,11 +60,11 @@ static inline bool ap_instructions_available(void)
unsigned long reg1 = 0;
asm volatile(
- " lgr 0,%[reg0]\n" /* qid into gr0 */
- " lghi 1,0\n" /* 0 into gr1 */
- " lghi 2,0\n" /* 0 into gr2 */
- " .long 0xb2af0000\n" /* PQAP(TAPQ) */
- "0: la %[reg1],1\n" /* 1 into reg1 */
+ " lgr 0,%[reg0]\n" /* qid into gr0 */
+ " lghi 1,0\n" /* 0 into gr1 */
+ " lghi 2,0\n" /* 0 into gr2 */
+ " .insn rre,0xb2af0000,0,0\n" /* PQAP(TAPQ) */
+ "0: la %[reg1],1\n" /* 1 into reg1 */
"1:\n"
EX_TABLE(0b, 1b)
: [reg1] "+&d" (reg1)
@@ -86,11 +86,11 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
unsigned long reg2;
asm volatile(
- " lgr 0,%[qid]\n" /* qid into gr0 */
- " lghi 2,0\n" /* 0 into gr2 */
- " .long 0xb2af0000\n" /* PQAP(TAPQ) */
- " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
- " lgr %[reg2],2\n" /* gr2 into reg2 */
+ " lgr 0,%[qid]\n" /* qid into gr0 */
+ " lghi 2,0\n" /* 0 into gr2 */
+ " .insn rre,0xb2af0000,0,0\n" /* PQAP(TAPQ) */
+ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
+ " lgr %[reg2],2\n" /* gr2 into reg2 */
: [reg1] "=&d" (reg1), [reg2] "=&d" (reg2)
: [qid] "d" (qid)
: "cc", "0", "1", "2");
@@ -128,9 +128,9 @@ static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
struct ap_queue_status reg1;
asm volatile(
- " lgr 0,%[reg0]\n" /* qid arg into gr0 */
- " .long 0xb2af0000\n" /* PQAP(RAPQ) */
- " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
+ " lgr 0,%[reg0]\n" /* qid arg into gr0 */
+ " .insn rre,0xb2af0000,0,0\n" /* PQAP(RAPQ) */
+ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
: [reg1] "=&d" (reg1)
: [reg0] "d" (reg0)
: "cc", "0", "1");
@@ -149,9 +149,9 @@ static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
struct ap_queue_status reg1;
asm volatile(
- " lgr 0,%[reg0]\n" /* qid arg into gr0 */
- " .long 0xb2af0000\n" /* PQAP(ZAPQ) */
- " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
+ " lgr 0,%[reg0]\n" /* qid arg into gr0 */
+ " .insn rre,0xb2af0000,0,0\n" /* PQAP(ZAPQ) */
+ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
: [reg1] "=&d" (reg1)
: [reg0] "d" (reg0)
: "cc", "0", "1");
@@ -190,10 +190,10 @@ static inline int ap_qci(struct ap_config_info *config)
struct ap_config_info *reg2 = config;
asm volatile(
- " lgr 0,%[reg0]\n" /* QCI fc into gr0 */
- " lgr 2,%[reg2]\n" /* ptr to config into gr2 */
- " .long 0xb2af0000\n" /* PQAP(QCI) */
- "0: la %[reg1],0\n" /* good case, QCI fc available */
+ " lgr 0,%[reg0]\n" /* QCI fc into gr0 */
+ " lgr 2,%[reg2]\n" /* ptr to config into gr2 */
+ " .insn rre,0xb2af0000,0,0\n" /* PQAP(QCI) */
+ "0: la %[reg1],0\n" /* good case, QCI fc available */
"1:\n"
EX_TABLE(0b, 1b)
: [reg1] "+&d" (reg1)
@@ -246,11 +246,11 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
reg1.qirqctrl = qirqctrl;
asm volatile(
- " lgr 0,%[reg0]\n" /* qid param into gr0 */
- " lgr 1,%[reg1]\n" /* irq ctrl into gr1 */
- " lgr 2,%[reg2]\n" /* ni addr into gr2 */
- " .long 0xb2af0000\n" /* PQAP(AQIC) */
- " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
+ " lgr 0,%[reg0]\n" /* qid param into gr0 */
+ " lgr 1,%[reg1]\n" /* irq ctrl into gr1 */
+ " lgr 2,%[reg2]\n" /* ni addr into gr2 */
+ " .insn rre,0xb2af0000,0,0\n" /* PQAP(AQIC) */
+ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
: [reg1] "+&d" (reg1)
: [reg0] "d" (reg0), [reg2] "d" (reg2)
: "cc", "0", "1", "2");
@@ -297,11 +297,11 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
reg1.value = apinfo->val;
asm volatile(
- " lgr 0,%[reg0]\n" /* qid param into gr0 */
- " lgr 1,%[reg1]\n" /* qact in info into gr1 */
- " .long 0xb2af0000\n" /* PQAP(QACT) */
- " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
- " lgr %[reg2],2\n" /* qact out info into reg2 */
+ " lgr 0,%[reg0]\n" /* qid param into gr0 */
+ " lgr 1,%[reg1]\n" /* qact in info into gr1 */
+ " .insn rre,0xb2af0000,0,0\n" /* PQAP(QACT) */
+ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */
+ " lgr %[reg2],2\n" /* qact out info into reg2 */
: [reg1] "+&d" (reg1), [reg2] "=&d" (reg2)
: [reg0] "d" (reg0)
: "cc", "0", "1", "2");
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index c800199a376b..82388da3f95f 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -74,8 +74,17 @@ static __always_inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
__ctl_load(reg, cr, cr);
}
-void smp_ctl_set_bit(int cr, int bit);
-void smp_ctl_clear_bit(int cr, int bit);
+void smp_ctl_set_clear_bit(int cr, int bit, bool set);
+
+static inline void ctl_set_bit(int cr, int bit)
+{
+ smp_ctl_set_clear_bit(cr, bit, true);
+}
+
+static inline void ctl_clear_bit(int cr, int bit)
+{
+ smp_ctl_set_clear_bit(cr, bit, false);
+}
union ctlreg0 {
unsigned long val;
@@ -130,8 +139,5 @@ union ctlreg15 {
};
};
-#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
-#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
-
#endif /* __ASSEMBLY__ */
#endif /* __ASM_CTL_REG_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 84ec63145325..eee8d96fb38e 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -319,11 +319,18 @@ extern void (*s390_base_pgm_handler_fn)(struct pt_regs *regs);
extern int memcpy_real(void *, unsigned long, size_t);
extern void memcpy_absolute(void *, void *, size_t);
-#define mem_assign_absolute(dest, val) do { \
- __typeof__(dest) __tmp = (val); \
- \
- BUILD_BUG_ON(sizeof(__tmp) != sizeof(val)); \
- memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \
+#define put_abs_lowcore(member, x) do { \
+ unsigned long __abs_address = offsetof(struct lowcore, member); \
+ __typeof__(((struct lowcore *)0)->member) __tmp = (x); \
+ \
+ memcpy_absolute(__va(__abs_address), &__tmp, sizeof(__tmp)); \
+} while (0)
+
+#define get_abs_lowcore(x, member) do { \
+ unsigned long __abs_address = offsetof(struct lowcore, member); \
+ __typeof__(((struct lowcore *)0)->member) *__ptr = &(x); \
+ \
+ memcpy_absolute(__ptr, __va(__abs_address), sizeof(*__ptr)); \
} while (0)
extern int s390_isolate_bp(void);
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 888a2f1c9ee3..24a54443c865 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -78,7 +78,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp)
{
typecheck(int, lp->lock);
asm_inline volatile(
- ALTERNATIVE("", ".long 0xb2fa0070", 49) /* NIAI 7 */
+ ALTERNATIVE("", ".insn rre,0xb2fa0000,7,0", 49) /* NIAI 7 */
" sth %1,%0\n"
: "=R" (((unsigned short *) &lp->lock)[1])
: "d" (0) : "cc", "memory");
diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h
index ad2c996e7e93..fde7e6b1df48 100644
--- a/arch/s390/include/asm/syscall_wrapper.h
+++ b/arch/s390/include/asm/syscall_wrapper.h
@@ -162,4 +162,4 @@
__diag_pop(); \
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
-#endif /* _ASM_X86_SYSCALL_WRAPPER_H */
+#endif /* _ASM_S390_SYSCALL_WRAPPER_H */
diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h
index 5ebf534ef753..0bf06f1682d8 100644
--- a/arch/s390/include/asm/unwind.h
+++ b/arch/s390/include/asm/unwind.h
@@ -4,6 +4,8 @@
#include <linux/sched.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
+#include <linux/llist.h>
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
@@ -36,10 +38,21 @@ struct unwind_state {
struct pt_regs *regs;
unsigned long sp, ip;
int graph_idx;
+ struct llist_node *kr_cur;
bool reliable;
bool error;
};
+/* Recover the return address modified by kretprobe and ftrace_graph. */
+static inline unsigned long unwind_recover_ret_addr(struct unwind_state *state,
+ unsigned long ip)
+{
+ ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL);
+ if (is_kretprobe_trampoline(ip))
+ ip = kretprobe_find_ret_addr(state->task, (void *)state->sp, &state->kr_cur);
+ return ip;
+}
+
void __unwind_start(struct unwind_state *state, struct task_struct *task,
struct pt_regs *regs, unsigned long first_frame);
bool unwind_next_frame(struct unwind_state *state);
diff --git a/arch/s390/include/asm/user.h b/arch/s390/include/asm/user.h
index 0ca572ced21b..8e8aaf48582e 100644
--- a/arch/s390/include/asm/user.h
+++ b/arch/s390/include/asm/user.h
@@ -67,9 +67,5 @@ struct user {
unsigned long magic; /* To uniquely identify a core file */
char u_comm[32]; /* User command that was responsible */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
#endif /* _S390_USER_H */
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index a601a518b569..59b69c8ab5e1 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -121,22 +121,22 @@ _LPP_OFFSET = __LC_LPP
.endm
.macro BPOFF
- ALTERNATIVE "", ".long 0xb2e8c000", 82
+ ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,12,0", 82
.endm
.macro BPON
- ALTERNATIVE "", ".long 0xb2e8d000", 82
+ ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,13,0", 82
.endm
.macro BPENTER tif_ptr,tif_mask
- ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .long 0xb2e8d000", \
+ ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .insn rrf,0xb2e80000,0,0,13,0", \
"", 82
.endm
.macro BPEXIT tif_ptr,tif_mask
TSTMSK \tif_ptr,\tif_mask
- ALTERNATIVE "jz .+8; .long 0xb2e8c000", \
- "jnz .+8; .long 0xb2e8d000", 82
+ ALTERNATIVE "jz .+8; .insn rrf,0xb2e80000,0,0,12,0", \
+ "jnz .+8; .insn rrf,0xb2e80000,0,0,13,0", 82
.endm
/*
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 28ae7df26c4a..1cc85b8ff42e 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1646,8 +1646,8 @@ static void dump_reipl_run(struct shutdown_trigger *trigger)
csum = (__force unsigned int)
csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0);
- mem_assign_absolute(S390_lowcore.ipib, ipib);
- mem_assign_absolute(S390_lowcore.ipib_checksum, csum);
+ put_abs_lowcore(ipib, ipib);
+ put_abs_lowcore(ipib_checksum, csum);
dump_run(trigger);
}
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index e32c14fd1282..0032bdbe8e3f 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -284,11 +284,11 @@ NOKPROBE_SYMBOL(pop_kprobe);
void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
{
- ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14];
- ri->fp = NULL;
+ ri->ret_addr = (kprobe_opcode_t *)regs->gprs[14];
+ ri->fp = (void *)regs->gprs[15];
/* Replace the return addr with trampoline addr */
- regs->gprs[14] = (unsigned long) &__kretprobe_trampoline;
+ regs->gprs[14] = (unsigned long)&__kretprobe_trampoline;
}
NOKPROBE_SYMBOL(arch_prepare_kretprobe);
@@ -385,7 +385,7 @@ NOKPROBE_SYMBOL(arch_kretprobe_fixup_return);
*/
void trampoline_probe_handler(struct pt_regs *regs)
{
- kretprobe_trampoline_handler(regs, NULL);
+ kretprobe_trampoline_handler(regs, (void *)regs->gprs[15]);
}
NOKPROBE_SYMBOL(trampoline_probe_handler);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 088d57a3083f..b2ef014a9287 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -226,7 +226,7 @@ void arch_crash_save_vmcoreinfo(void)
vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31);
vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31);
vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
- mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
+ put_abs_lowcore(vmcore_info, paddr_vmcoreinfo_note());
}
void machine_shutdown(void)
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index 6b5b64e67eee..1acc2e05d70f 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -63,7 +63,7 @@ void __init os_info_init(void)
os_info.version_minor = OS_INFO_VERSION_MINOR;
os_info.magic = OS_INFO_MAGIC;
os_info.csum = os_info_csum(&os_info);
- mem_assign_absolute(S390_lowcore.os_info, __pa(ptr));
+ put_abs_lowcore(os_info, __pa(ptr));
}
#ifdef CONFIG_CRASH_DUMP
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 84e23fcc1106..d860ac300919 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -481,11 +481,11 @@ static void __init setup_lowcore_dat_off(void)
lc->mcck_stack = mcck_stack + STACK_INIT_OFFSET;
/* Setup absolute zero lowcore */
- mem_assign_absolute(S390_lowcore.restart_stack, lc->restart_stack);
- mem_assign_absolute(S390_lowcore.restart_fn, lc->restart_fn);
- mem_assign_absolute(S390_lowcore.restart_data, lc->restart_data);
- mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source);
- mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw);
+ put_abs_lowcore(restart_stack, lc->restart_stack);
+ put_abs_lowcore(restart_fn, lc->restart_fn);
+ put_abs_lowcore(restart_data, lc->restart_data);
+ put_abs_lowcore(restart_source, lc->restart_source);
+ put_abs_lowcore(restart_psw, lc->restart_psw);
lc->spinlock_lockval = arch_spin_lockval(0);
lc->spinlock_index = 0;
@@ -501,6 +501,7 @@ static void __init setup_lowcore_dat_off(void)
static void __init setup_lowcore_dat_on(void)
{
struct lowcore *lc = lowcore_ptr[0];
+ int cr;
__ctl_clear_bit(0, 28);
S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT;
@@ -509,10 +510,10 @@ static void __init setup_lowcore_dat_on(void)
S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT;
__ctl_store(S390_lowcore.cregs_save_area, 0, 15);
__ctl_set_bit(0, 28);
- mem_assign_absolute(S390_lowcore.restart_flags, RESTART_FLAG_CTLREGS);
- mem_assign_absolute(S390_lowcore.program_new_psw, lc->program_new_psw);
- memcpy_absolute(&S390_lowcore.cregs_save_area, lc->cregs_save_area,
- sizeof(S390_lowcore.cregs_save_area));
+ put_abs_lowcore(restart_flags, RESTART_FLAG_CTLREGS);
+ put_abs_lowcore(program_new_psw, lc->program_new_psw);
+ for (cr = 0; cr < ARRAY_SIZE(lc->cregs_save_area); cr++)
+ put_abs_lowcore(cregs_save_area[cr], lc->cregs_save_area[cr]);
}
static struct resource code_resource = {
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 127da1850b06..30c91d565933 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -213,7 +213,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
if (nmi_alloc_mcesa(&lc->mcesad))
goto out;
lowcore_ptr[cpu] = lc;
- pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc);
+ pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, __pa(lc));
return 0;
out:
@@ -326,10 +326,17 @@ static void pcpu_delegate(struct pcpu *pcpu,
/* Stop target cpu (if func returns this stops the current cpu). */
pcpu_sigp_retry(pcpu, SIGP_STOP, 0);
/* Restart func on the target cpu and stop the current cpu. */
- mem_assign_absolute(lc->restart_stack, stack);
- mem_assign_absolute(lc->restart_fn, (unsigned long) func);
- mem_assign_absolute(lc->restart_data, (unsigned long) data);
- mem_assign_absolute(lc->restart_source, source_cpu);
+ if (lc) {
+ lc->restart_stack = stack;
+ lc->restart_fn = (unsigned long)func;
+ lc->restart_data = (unsigned long)data;
+ lc->restart_source = source_cpu;
+ } else {
+ put_abs_lowcore(restart_stack, stack);
+ put_abs_lowcore(restart_fn, (unsigned long)func);
+ put_abs_lowcore(restart_data, (unsigned long)data);
+ put_abs_lowcore(restart_source, source_cpu);
+ }
__bpon();
asm volatile(
"0: sigp 0,%0,%2 # sigp restart to target cpu\n"
@@ -570,39 +577,27 @@ static void smp_ctl_bit_callback(void *info)
}
static DEFINE_SPINLOCK(ctl_lock);
-static unsigned long ctlreg;
-/*
- * Set a bit in a control register of all cpus
- */
-void smp_ctl_set_bit(int cr, int bit)
+void smp_ctl_set_clear_bit(int cr, int bit, bool set)
{
- struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr };
-
- spin_lock(&ctl_lock);
- memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg));
- __set_bit(bit, &ctlreg);
- memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg));
- spin_unlock(&ctl_lock);
- on_each_cpu(smp_ctl_bit_callback, &parms, 1);
-}
-EXPORT_SYMBOL(smp_ctl_set_bit);
-
-/*
- * Clear a bit in a control register of all cpus
- */
-void smp_ctl_clear_bit(int cr, int bit)
-{
- struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr };
+ struct ec_creg_mask_parms parms = { .cr = cr, };
+ u64 ctlreg;
+ if (set) {
+ parms.orval = 1UL << bit;
+ parms.andval = -1UL;
+ } else {
+ parms.orval = 0;
+ parms.andval = ~(1UL << bit);
+ }
spin_lock(&ctl_lock);
- memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg));
- __clear_bit(bit, &ctlreg);
- memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg));
+ get_abs_lowcore(ctlreg, cregs_save_area[cr]);
+ ctlreg = (ctlreg & parms.andval) | parms.orval;
+ put_abs_lowcore(cregs_save_area[cr], ctlreg);
spin_unlock(&ctl_lock);
on_each_cpu(smp_ctl_bit_callback, &parms, 1);
}
-EXPORT_SYMBOL(smp_ctl_clear_bit);
+EXPORT_SYMBOL(smp_ctl_set_clear_bit);
#ifdef CONFIG_CRASH_DUMP
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 674c65019434..1d2aa448d103 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -141,10 +141,10 @@ static inline void do_fp_trap(struct pt_regs *regs, __u32 fpc)
do_trap(regs, SIGFPE, si_code, "floating point exception");
}
-static void translation_exception(struct pt_regs *regs)
+static void translation_specification_exception(struct pt_regs *regs)
{
/* May never happen. */
- panic("Translation exception");
+ panic("Translation-Specification Exception");
}
static void illegal_op(struct pt_regs *regs)
@@ -368,7 +368,7 @@ static void (*pgm_check_table[128])(struct pt_regs *regs) = {
[0x0f] = hfp_divide_exception,
[0x10] = do_dat_exception,
[0x11] = do_dat_exception,
- [0x12] = translation_exception,
+ [0x12] = translation_specification_exception,
[0x13] = special_op_exception,
[0x14] = default_trap_handler,
[0x15] = operand_exception,
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index 707fd99f6734..0ece156fdd7c 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -64,8 +64,8 @@ bool unwind_next_frame(struct unwind_state *state)
ip = READ_ONCE_NOCHECK(sf->gprs[8]);
reliable = false;
regs = NULL;
- if (!__kernel_text_address(ip)) {
- /* skip bogus %r14 */
+ /* skip bogus %r14 or if is the same as regs->psw.addr */
+ if (!__kernel_text_address(ip) || state->ip == unwind_recover_ret_addr(state, ip)) {
state->regs = NULL;
return unwind_next_frame(state);
}
@@ -103,13 +103,11 @@ bool unwind_next_frame(struct unwind_state *state)
if (sp & 0x7)
goto out_err;
- ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp);
-
/* Update unwind state */
state->sp = sp;
- state->ip = ip;
state->regs = regs;
state->reliable = reliable;
+ state->ip = unwind_recover_ret_addr(state, ip);
return true;
out_err:
@@ -161,12 +159,10 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
ip = READ_ONCE_NOCHECK(sf->gprs[8]);
}
- ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL);
-
/* Update unwind state */
state->sp = sp;
- state->ip = ip;
state->reliable = true;
+ state->ip = unwind_recover_ret_addr(state, ip);
if (!first_frame)
return;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ab73d99483fe..156d1c25a3c1 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3462,7 +3462,7 @@ void exit_sie(struct kvm_vcpu *vcpu)
/* Kick a guest cpu out of SIE to process a request synchronously */
void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
{
- kvm_make_request(req, vcpu);
+ __kvm_make_request(req, vcpu);
kvm_s390_vcpu_request(vcpu);
}
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 692dc84cd19c..5e7ea8b111e8 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -75,7 +75,7 @@ static inline int arch_load_niai4(int *lock)
int owner;
asm_inline volatile(
- ALTERNATIVE("", ".long 0xb2fa0040", 49) /* NIAI 4 */
+ ALTERNATIVE("", ".insn rre,0xb2fa0000,4,0", 49) /* NIAI 4 */
" l %0,%1\n"
: "=d" (owner) : "Q" (*lock) : "memory");
return owner;
@@ -86,7 +86,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new)
int expected = old;
asm_inline volatile(
- ALTERNATIVE("", ".long 0xb2fa0080", 49) /* NIAI 8 */
+ ALTERNATIVE("", ".insn rre,0xb2fa0000,8,0", 49) /* NIAI 8 */
" cs %0,%3,%1\n"
: "=d" (old), "=Q" (*lock)
: "0" (old), "d" (new), "Q" (*lock)
diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c
index c01f02887de4..9bb067321ab4 100644
--- a/arch/s390/lib/test_unwind.c
+++ b/arch/s390/lib/test_unwind.c
@@ -47,7 +47,7 @@ static void print_backtrace(char *bt)
static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs,
unsigned long sp)
{
- int frame_count, prev_is_func2, seen_func2_func1;
+ int frame_count, prev_is_func2, seen_func2_func1, seen_kretprobe_trampoline;
const int max_frames = 128;
struct unwind_state state;
size_t bt_pos = 0;
@@ -63,6 +63,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs,
frame_count = 0;
prev_is_func2 = 0;
seen_func2_func1 = 0;
+ seen_kretprobe_trampoline = 0;
unwind_for_each_frame(&state, task, regs, sp) {
unsigned long addr = unwind_get_return_address(&state);
char sym[KSYM_SYMBOL_LEN];
@@ -88,6 +89,8 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs,
if (prev_is_func2 && str_has_prefix(sym, "unwindme_func1"))
seen_func2_func1 = 1;
prev_is_func2 = str_has_prefix(sym, "unwindme_func2");
+ if (str_has_prefix(sym, "__kretprobe_trampoline+0x0/"))
+ seen_kretprobe_trampoline = 1;
}
/* Check the results. */
@@ -103,6 +106,10 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs,
kunit_err(current_test, "Maximum number of frames exceeded\n");
ret = -EINVAL;
}
+ if (seen_kretprobe_trampoline) {
+ kunit_err(current_test, "__kretprobe_trampoline+0x0 in unwinding results\n");
+ ret = -EINVAL;
+ }
if (ret || force_bt)
print_backtrace(bt);
kfree(bt);
@@ -132,36 +139,50 @@ static struct unwindme *unwindme;
#define UWM_PGM 0x40 /* Unwind from program check handler */
#define UWM_KPROBE_ON_FTRACE 0x80 /* Unwind from kprobe handler called via ftrace. */
#define UWM_FTRACE 0x100 /* Unwind from ftrace handler. */
-#define UWM_KRETPROBE 0x200 /* Unwind kretprobe handlers. */
+#define UWM_KRETPROBE 0x200 /* Unwind through kretprobed function. */
+#define UWM_KRETPROBE_HANDLER 0x400 /* Unwind from kretprobe handler. */
-static __always_inline unsigned long get_psw_addr(void)
+static __always_inline struct pt_regs fake_pt_regs(void)
{
- unsigned long psw_addr;
+ struct pt_regs regs;
+
+ memset(&regs, 0, sizeof(regs));
+ regs.gprs[15] = current_stack_pointer();
asm volatile(
"basr %[psw_addr],0\n"
- : [psw_addr] "=d" (psw_addr));
- return psw_addr;
+ : [psw_addr] "=d" (regs.psw.addr));
+ return regs;
}
static int kretprobe_ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
{
struct unwindme *u = unwindme;
+ if (!(u->flags & UWM_KRETPROBE_HANDLER))
+ return 0;
+
u->ret = test_unwind(NULL, (u->flags & UWM_REGS) ? regs : NULL,
(u->flags & UWM_SP) ? u->sp : 0);
return 0;
}
-static noinline notrace void test_unwind_kretprobed_func(void)
+static noinline notrace int test_unwind_kretprobed_func(struct unwindme *u)
{
- asm volatile(" nop\n");
+ struct pt_regs regs;
+
+ if (!(u->flags & UWM_KRETPROBE))
+ return 0;
+
+ regs = fake_pt_regs();
+ return test_unwind(NULL, (u->flags & UWM_REGS) ? &regs : NULL,
+ (u->flags & UWM_SP) ? u->sp : 0);
}
-static noinline void test_unwind_kretprobed_func_caller(void)
+static noinline int test_unwind_kretprobed_func_caller(struct unwindme *u)
{
- test_unwind_kretprobed_func();
+ return test_unwind_kretprobed_func(u);
}
static int test_unwind_kretprobe(struct unwindme *u)
@@ -187,10 +208,12 @@ static int test_unwind_kretprobe(struct unwindme *u)
return -EINVAL;
}
- test_unwind_kretprobed_func_caller();
+ ret = test_unwind_kretprobed_func_caller(u);
unregister_kretprobe(&my_kretprobe);
unwindme = NULL;
- return u->ret;
+ if (u->flags & UWM_KRETPROBE_HANDLER)
+ ret = u->ret;
+ return ret;
}
static int kprobe_pre_handler(struct kprobe *p, struct pt_regs *regs)
@@ -304,16 +327,13 @@ static noinline int unwindme_func4(struct unwindme *u)
return 0;
} else if (u->flags & (UWM_PGM | UWM_KPROBE_ON_FTRACE)) {
return test_unwind_kprobe(u);
- } else if (u->flags & (UWM_KRETPROBE)) {
+ } else if (u->flags & (UWM_KRETPROBE | UWM_KRETPROBE_HANDLER)) {
return test_unwind_kretprobe(u);
} else if (u->flags & UWM_FTRACE) {
return test_unwind_ftrace(u);
} else {
- struct pt_regs regs;
+ struct pt_regs regs = fake_pt_regs();
- memset(&regs, 0, sizeof(regs));
- regs.psw.addr = get_psw_addr();
- regs.gprs[15] = current_stack_pointer();
return test_unwind(NULL,
(u->flags & UWM_REGS) ? &regs : NULL,
(u->flags & UWM_SP) ? u->sp : 0);
@@ -452,6 +472,10 @@ static const struct test_params param_list[] = {
TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_SP),
TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_REGS),
TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_SP | UWM_REGS),
+ TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER),
+ TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_SP),
+ TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_REGS),
+ TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_SP | UWM_REGS),
};
/*
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 792f8e0f2178..e563cb65c0c4 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -69,6 +69,7 @@ struct zpci_dev *get_zdev_by_fid(u32 fid)
list_for_each_entry(tmp, &zpci_list, entry) {
if (tmp->fid == fid) {
zdev = tmp;
+ zpci_zdev_get(zdev);
break;
}
}
@@ -399,7 +400,7 @@ EXPORT_SYMBOL(pci_iounmap);
static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
int size, u32 *val)
{
- struct zpci_dev *zdev = get_zdev_by_bus(bus, devfn);
+ struct zpci_dev *zdev = zdev_from_bus(bus, devfn);
return (zdev) ? zpci_cfg_load(zdev, where, val, size) : -ENODEV;
}
@@ -407,7 +408,7 @@ static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
int size, u32 val)
{
- struct zpci_dev *zdev = get_zdev_by_bus(bus, devfn);
+ struct zpci_dev *zdev = zdev_from_bus(bus, devfn);
return (zdev) ? zpci_cfg_store(zdev, where, val, size) : -ENODEV;
}
diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h
index e359d2686178..e96c9860e064 100644
--- a/arch/s390/pci/pci_bus.h
+++ b/arch/s390/pci/pci_bus.h
@@ -19,7 +19,8 @@ void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error);
void zpci_release_device(struct kref *kref);
static inline void zpci_zdev_put(struct zpci_dev *zdev)
{
- kref_put(&zdev->kref, zpci_release_device);
+ if (zdev)
+ kref_put(&zdev->kref, zpci_release_device);
}
static inline void zpci_zdev_get(struct zpci_dev *zdev)
@@ -32,8 +33,8 @@ void zpci_free_domain(int domain);
int zpci_setup_bus_resources(struct zpci_dev *zdev,
struct list_head *resources);
-static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus,
- unsigned int devfn)
+static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus,
+ unsigned int devfn)
{
struct zpci_bus *zbus = bus->sysdata;
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 63f3e057c168..1057d7af4a55 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -23,6 +23,8 @@
#include <asm/clp.h>
#include <uapi/asm/clp.h>
+#include "pci_bus.h"
+
bool zpci_unique_uid;
void update_uid_checking(bool new)
@@ -404,8 +406,11 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data)
return;
zdev = get_zdev_by_fid(entry->fid);
- if (!zdev)
- zpci_create_device(entry->fid, entry->fh, entry->config_state);
+ if (zdev) {
+ zpci_zdev_put(zdev);
+ return;
+ }
+ zpci_create_device(entry->fid, entry->fh, entry->config_state);
}
int clp_scan_pci_devices(void)
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 2e3e5b278925..ea9db5cea64e 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -269,7 +269,7 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
if (!pdev)
- return;
+ goto no_pdev;
switch (ccdf->pec) {
case 0x003a: /* Service Action or Error Recovery Successful */
@@ -286,6 +286,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
break;
}
pci_dev_put(pdev);
+no_pdev:
+ zpci_zdev_put(zdev);
}
void zpci_event_error(void *data)
@@ -314,6 +316,7 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
{
struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
+ bool existing_zdev = !!zdev;
enum zpci_state state;
zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n",
@@ -378,6 +381,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
default:
break;
}
+ if (existing_zdev)
+ zpci_zdev_put(zdev);
}
void zpci_event_availability(void *data)
diff --git a/arch/sh/include/asm/user.h b/arch/sh/include/asm/user.h
index 7dfd3f6461e6..12ea0f3f4419 100644
--- a/arch/sh/include/asm/user.h
+++ b/arch/sh/include/asm/user.h
@@ -52,10 +52,4 @@ struct user {
char u_comm[32]; /* user command name */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_DATA_START_ADDR (u.start_data)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
#endif /* __ASM_SH_USER_H */
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index b08bd2966253..f1f3f52f1e9c 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -24,7 +24,6 @@ generic-y += softirq_stack.h
generic-y += switch_to.h
generic-y += topology.h
generic-y += trace_clock.h
-generic-y += word-at-a-time.h
generic-y += kprobes.h
generic-y += mm_hooks.h
generic-y += vga.h
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4138939532c6..d23e80a56eb8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -249,6 +249,7 @@ enum x86_intercept_stage;
#define PFERR_SGX_BIT 15
#define PFERR_GUEST_FINAL_BIT 32
#define PFERR_GUEST_PAGE_BIT 33
+#define PFERR_IMPLICIT_ACCESS_BIT 48
#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
@@ -259,6 +260,7 @@ enum x86_intercept_stage;
#define PFERR_SGX_MASK (1U << PFERR_SGX_BIT)
#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT)
#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
+#define PFERR_IMPLICIT_ACCESS (1ULL << PFERR_IMPLICIT_ACCESS_BIT)
#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \
PFERR_WRITE_MASK | \
@@ -430,7 +432,7 @@ struct kvm_mmu {
void (*inject_page_fault)(struct kvm_vcpu *vcpu,
struct x86_exception *fault);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- gpa_t gva_or_gpa, u32 access,
+ gpa_t gva_or_gpa, u64 access,
struct x86_exception *exception);
int (*sync_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp);
@@ -512,6 +514,7 @@ struct kvm_pmu {
u64 global_ctrl_mask;
u64 global_ovf_ctrl_mask;
u64 reserved_bits;
+ u64 raw_event_mask;
u8 version;
struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
@@ -1040,14 +1043,16 @@ struct kvm_x86_msr_filter {
struct msr_bitmap_range ranges[16];
};
-#define APICV_INHIBIT_REASON_DISABLE 0
-#define APICV_INHIBIT_REASON_HYPERV 1
-#define APICV_INHIBIT_REASON_NESTED 2
-#define APICV_INHIBIT_REASON_IRQWIN 3
-#define APICV_INHIBIT_REASON_PIT_REINJ 4
-#define APICV_INHIBIT_REASON_X2APIC 5
-#define APICV_INHIBIT_REASON_BLOCKIRQ 6
-#define APICV_INHIBIT_REASON_ABSENT 7
+enum kvm_apicv_inhibit {
+ APICV_INHIBIT_REASON_DISABLE,
+ APICV_INHIBIT_REASON_HYPERV,
+ APICV_INHIBIT_REASON_NESTED,
+ APICV_INHIBIT_REASON_IRQWIN,
+ APICV_INHIBIT_REASON_PIT_REINJ,
+ APICV_INHIBIT_REASON_X2APIC,
+ APICV_INHIBIT_REASON_BLOCKIRQ,
+ APICV_INHIBIT_REASON_ABSENT,
+};
struct kvm_arch {
unsigned long n_used_mmu_pages;
@@ -1401,7 +1406,7 @@ struct kvm_x86_ops {
void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
void (*enable_irq_window)(struct kvm_vcpu *vcpu);
void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
- bool (*check_apicv_inhibit_reasons)(ulong bit);
+ bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason);
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
@@ -1585,7 +1590,7 @@ void kvm_mmu_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-void kvm_mmu_init_vm(struct kvm *kvm);
+int kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
@@ -1795,11 +1800,22 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
bool kvm_apicv_activated(struct kvm *kvm);
void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
-void kvm_request_apicv_update(struct kvm *kvm, bool activate,
- unsigned long bit);
+void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason, bool set);
+void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason, bool set);
+
+static inline void kvm_set_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason)
+{
+ kvm_set_or_clear_apicv_inhibit(kvm, reason, true);
+}
-void __kvm_request_apicv_update(struct kvm *kvm, bool activate,
- unsigned long bit);
+static inline void kvm_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason)
+{
+ kvm_set_or_clear_apicv_inhibit(kvm, reason, false);
+}
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 7eb2df5417fb..f70a5108d464 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -221,8 +221,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2)
+#define SVM_TSC_RATIO_RSVD 0xffffff0000000000ULL
+#define SVM_TSC_RATIO_MIN 0x0000000000000001ULL
+#define SVM_TSC_RATIO_MAX 0x000000ffffffffffULL
+#define SVM_TSC_RATIO_DEFAULT 0x0100000000ULL
+
+
/* AVIC */
-#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFFULL)
#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
@@ -230,9 +236,11 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12)
#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62)
#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63)
-#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFF)
+#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFFULL)
+
+#define AVIC_DOORBELL_PHYSICAL_ID_MASK GENMASK_ULL(11, 0)
-#define AVIC_DOORBELL_PHYSICAL_ID_MASK (0xFF)
+#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1
#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0
diff --git a/arch/x86/include/asm/user_32.h b/arch/x86/include/asm/user_32.h
index d72c3d66e94f..8963915e533f 100644
--- a/arch/x86/include/asm/user_32.h
+++ b/arch/x86/include/asm/user_32.h
@@ -124,9 +124,5 @@ struct user{
char u_comm[32]; /* User command that was responsible */
int u_debugreg[8];
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
#endif /* _ASM_X86_USER_32_H */
diff --git a/arch/x86/include/asm/user_64.h b/arch/x86/include/asm/user_64.h
index db909923611c..1dd10f07ccd6 100644
--- a/arch/x86/include/asm/user_64.h
+++ b/arch/x86/include/asm/user_64.h
@@ -130,9 +130,5 @@ struct user {
unsigned long error_code; /* CPU error code or 0 */
unsigned long fault_address; /* CR3 or 0 */
};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
#endif /* _ASM_X86_USER_64_H */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 79e0b8d63ffa..a22deb58f86d 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -517,7 +517,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
} else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) {
ipi_bitmap <<= min - apic_id;
min = apic_id;
- } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
+ } else if (apic_id > min && apic_id < min + KVM_IPI_CLUSTER_SIZE) {
max = apic_id < max ? max : apic_id;
} else {
ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a00cd97b2623..b24ca7f4ed7c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -735,6 +735,7 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
if (function > READ_ONCE(max_cpuid_80000000))
return entry;
}
+ break;
default:
break;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index f9c00c89829b..89b11e7dca8a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3540,8 +3540,10 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt)
{
u64 tsc_aux = 0;
- if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux))
+ if (!ctxt->ops->guest_has_rdpid(ctxt))
return emulate_ud(ctxt);
+
+ ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux);
ctxt->dst.val = tsc_aux;
return X86EMUL_CONTINUE;
}
@@ -3642,7 +3644,7 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
msr_data = (u32)reg_read(ctxt, VCPU_REGS_RAX)
| ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32);
- r = ctxt->ops->set_msr(ctxt, msr_index, msr_data);
+ r = ctxt->ops->set_msr_with_filter(ctxt, msr_index, msr_data);
if (r == X86EMUL_IO_NEEDED)
return r;
@@ -3659,7 +3661,7 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt)
u64 msr_data;
int r;
- r = ctxt->ops->get_msr(ctxt, msr_index, &msr_data);
+ r = ctxt->ops->get_msr_with_filter(ctxt, msr_index, &msr_data);
if (r == X86EMUL_IO_NEEDED)
return r;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index a32f54ab84a2..123b677111c5 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -122,9 +122,13 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic,
else
hv->synic_auto_eoi_used--;
- __kvm_request_apicv_update(vcpu->kvm,
- !hv->synic_auto_eoi_used,
- APICV_INHIBIT_REASON_HYPERV);
+ /*
+ * Inhibit APICv if any vCPU is using SynIC's AutoEOI, which relies on
+ * the hypervisor to manually inject IRQs.
+ */
+ __kvm_set_or_clear_apicv_inhibit(vcpu->kvm,
+ APICV_INHIBIT_REASON_HYPERV,
+ !!hv->synic_auto_eoi_used);
up_write(&vcpu->kvm->arch.apicv_update_lock);
}
@@ -239,7 +243,7 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic);
int ret;
- if (!synic->active && !host)
+ if (!synic->active && (!host || data))
return 1;
trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host);
@@ -285,6 +289,9 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
case HV_X64_MSR_EOM: {
int i;
+ if (!synic->active)
+ break;
+
for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
kvm_hv_notify_acked_sint(vcpu, i);
break;
@@ -449,6 +456,9 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
struct kvm_lapic_irq irq;
int ret, vector;
+ if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm))
+ return -EINVAL;
+
if (sint >= ARRAY_SIZE(synic->sint))
return -EINVAL;
@@ -661,7 +671,7 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
- if (!synic->active && !host)
+ if (!synic->active && (!host || config))
return 1;
if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode &&
@@ -690,7 +700,7 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer);
struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu);
- if (!synic->active && !host)
+ if (!synic->active && (!host || count))
return 1;
trace_kvm_hv_stimer_set_count(hv_stimer_to_vcpu(stimer)->vcpu_id,
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 0b65a764ed3a..1c83076091af 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -305,15 +305,13 @@ void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject)
* So, deactivate APICv when PIT is in reinject mode.
*/
if (reinject) {
- kvm_request_apicv_update(kvm, false,
- APICV_INHIBIT_REASON_PIT_REINJ);
+ kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PIT_REINJ);
/* The initial state is preserved while ps->reinject == 0. */
kvm_pit_reset_reinject(pit);
kvm_register_irq_ack_notifier(kvm, &ps->irq_ack_notifier);
kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
} else {
- kvm_request_apicv_update(kvm, true,
- APICV_INHIBIT_REASON_PIT_REINJ);
+ kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PIT_REINJ);
kvm_unregister_irq_ack_notifier(kvm, &ps->irq_ack_notifier);
kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
}
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 840ddb4a9302..8dff25d267b7 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -210,6 +210,8 @@ struct x86_emulate_ops {
int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt);
void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+ int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
+ int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
@@ -226,6 +228,7 @@ struct x86_emulate_ops {
bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt);
bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt);
bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt);
+ bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);
void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 80a2020c4db4..66b0eb0bda94 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1024,6 +1024,10 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
*r = -1;
if (irq->shorthand == APIC_DEST_SELF) {
+ if (KVM_BUG_ON(!src, kvm)) {
+ *r = 0;
+ return true;
+ }
*r = kvm_apic_set_irq(src->vcpu, irq, dest_map);
return true;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bf8dbc4bb12a..e6cae6f22683 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -214,27 +214,27 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
*/
static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
unsigned pte_access, unsigned pte_pkey,
- unsigned pfec)
+ u64 access)
{
- int cpl = static_call(kvm_x86_get_cpl)(vcpu);
+ /* strip nested paging fault error codes */
+ unsigned int pfec = access;
unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu);
/*
- * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1.
+ * For explicit supervisor accesses, SMAP is disabled if EFLAGS.AC = 1.
+ * For implicit supervisor accesses, SMAP cannot be overridden.
*
- * If CPL = 3, SMAP applies to all supervisor-mode data accesses
- * (these are implicit supervisor accesses) regardless of the value
- * of EFLAGS.AC.
+ * SMAP works on supervisor accesses only, and not_smap can
+ * be set or not set when user access with neither has any bearing
+ * on the result.
*
- * This computes (cpl < 3) && (rflags & X86_EFLAGS_AC), leaving
- * the result in X86_EFLAGS_AC. We then insert it in place of
- * the PFERR_RSVD_MASK bit; this bit will always be zero in pfec,
- * but it will be one in index if SMAP checks are being overridden.
- * It is important to keep this branchless.
+ * We put the SMAP checking bit in place of the PFERR_RSVD_MASK bit;
+ * this bit will always be zero in pfec, but it will be one in index
+ * if SMAP checks are being disabled.
*/
- unsigned long smap = (cpl - 3) & (rflags & X86_EFLAGS_AC);
- int index = (pfec >> 1) +
- (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
+ u64 implicit_access = access & PFERR_IMPLICIT_ACCESS;
+ bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC;
+ int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1;
bool fault = (mmu->permissions[index] >> pte_access) & 1;
u32 errcode = PFERR_PRESENT_MASK;
@@ -317,12 +317,12 @@ static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count)
atomic64_add(count, &kvm->stat.pages[level - 1]);
}
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access,
struct x86_exception *exception);
static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu,
struct kvm_mmu *mmu,
- gpa_t gpa, u32 access,
+ gpa_t gpa, u64 access,
struct x86_exception *exception)
{
if (mmu != &vcpu->arch.nested_mmu)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 51671cb34fb6..8f19ea752704 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2696,8 +2696,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
if (*sptep == spte) {
ret = RET_PF_SPURIOUS;
} else {
- trace_kvm_mmu_set_spte(level, gfn, sptep);
flush |= mmu_spte_update(sptep, spte);
+ trace_kvm_mmu_set_spte(level, gfn, sptep);
}
if (wrprot) {
@@ -3703,7 +3703,7 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu)
}
static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- gpa_t vaddr, u32 access,
+ gpa_t vaddr, u64 access,
struct x86_exception *exception)
{
if (exception)
@@ -4591,11 +4591,11 @@ static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept)
* - X86_CR4_SMAP is set in CR4
* - A user page is accessed
* - The access is not a fetch
- * - Page fault in kernel mode
- * - if CPL = 3 or X86_EFLAGS_AC is clear
+ * - The access is supervisor mode
+ * - If implicit supervisor access or X86_EFLAGS_AC is clear
*
- * Here, we cover the first three conditions.
- * The fourth is computed dynamically in permission_fault();
+ * Here, we cover the first four conditions.
+ * The fifth is computed dynamically in permission_fault();
* PFERR_RSVD_MASK bit will be set in PFEC if the access is
* *not* subject to SMAP restrictions.
*/
@@ -5768,17 +5768,24 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
kvm_mmu_zap_all_fast(kvm);
}
-void kvm_mmu_init_vm(struct kvm *kvm)
+int kvm_mmu_init_vm(struct kvm *kvm)
{
struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+ int r;
+ INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+ INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+ INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
- kvm_mmu_init_tdp_mmu(kvm);
+ r = kvm_mmu_init_tdp_mmu(kvm);
+ if (r < 0)
+ return r;
node->track_write = kvm_mmu_pte_write;
node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
kvm_page_track_register_notifier(kvm, node);
+ return 0;
}
void kvm_mmu_uninit_vm(struct kvm *kvm)
@@ -5842,8 +5849,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
if (is_tdp_mmu_enabled(kvm)) {
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
- flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start,
- gfn_end, flush);
+ flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
+ gfn_end, true, flush);
}
if (flush)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 252c77805eb9..01fee5f67ac3 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -34,9 +34,8 @@
#define PT_HAVE_ACCESSED_DIRTY(mmu) true
#ifdef CONFIG_X86_64
#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
- #define CMPXCHG cmpxchg
+ #define CMPXCHG "cmpxchgq"
#else
- #define CMPXCHG cmpxchg64
#define PT_MAX_FULL_LEVELS 2
#endif
#elif PTTYPE == 32
@@ -52,7 +51,7 @@
#define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
#define PT_HAVE_ACCESSED_DIRTY(mmu) true
- #define CMPXCHG cmpxchg
+ #define CMPXCHG "cmpxchgl"
#elif PTTYPE == PTTYPE_EPT
#define pt_element_t u64
#define guest_walker guest_walkerEPT
@@ -65,7 +64,9 @@
#define PT_GUEST_DIRTY_SHIFT 9
#define PT_GUEST_ACCESSED_SHIFT 8
#define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad)
- #define CMPXCHG cmpxchg64
+ #ifdef CONFIG_X86_64
+ #define CMPXCHG "cmpxchgq"
+ #endif
#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
#else
#error Invalid PTTYPE value
@@ -147,43 +148,36 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
pt_element_t __user *ptep_user, unsigned index,
pt_element_t orig_pte, pt_element_t new_pte)
{
- int npages;
- pt_element_t ret;
- pt_element_t *table;
- struct page *page;
-
- npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
- if (likely(npages == 1)) {
- table = kmap_atomic(page);
- ret = CMPXCHG(&table[index], orig_pte, new_pte);
- kunmap_atomic(table);
-
- kvm_release_page_dirty(page);
- } else {
- struct vm_area_struct *vma;
- unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK;
- unsigned long pfn;
- unsigned long paddr;
-
- mmap_read_lock(current->mm);
- vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE);
- if (!vma || !(vma->vm_flags & VM_PFNMAP)) {
- mmap_read_unlock(current->mm);
- return -EFAULT;
- }
- pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- paddr = pfn << PAGE_SHIFT;
- table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB);
- if (!table) {
- mmap_read_unlock(current->mm);
- return -EFAULT;
- }
- ret = CMPXCHG(&table[index], orig_pte, new_pte);
- memunmap(table);
- mmap_read_unlock(current->mm);
- }
+ signed char r;
- return (ret != orig_pte);
+ if (!user_access_begin(ptep_user, sizeof(pt_element_t)))
+ return -EFAULT;
+
+#ifdef CMPXCHG
+ asm volatile("1:" LOCK_PREFIX CMPXCHG " %[new], %[ptr]\n"
+ "setnz %b[r]\n"
+ "2:"
+ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %k[r])
+ : [ptr] "+m" (*ptep_user),
+ [old] "+a" (orig_pte),
+ [r] "=q" (r)
+ : [new] "r" (new_pte)
+ : "memory");
+#else
+ asm volatile("1:" LOCK_PREFIX "cmpxchg8b %[ptr]\n"
+ "setnz %b[r]\n"
+ "2:"
+ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %k[r])
+ : [ptr] "+m" (*ptep_user),
+ [old] "+A" (orig_pte),
+ [r] "=q" (r)
+ : [new_lo] "b" ((u32)new_pte),
+ [new_hi] "c" ((u32)(new_pte >> 32))
+ : "memory");
+#endif
+
+ user_access_end();
+ return r;
}
static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
@@ -339,7 +333,7 @@ static inline bool FNAME(is_last_gpte)(struct kvm_mmu *mmu,
*/
static int FNAME(walk_addr_generic)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- gpa_t addr, u32 access)
+ gpa_t addr, u64 access)
{
int ret;
pt_element_t pte;
@@ -347,7 +341,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
gfn_t table_gfn;
u64 pt_access, pte_access;
unsigned index, accessed_dirty, pte_pkey;
- unsigned nested_access;
+ u64 nested_access;
gpa_t pte_gpa;
bool have_ad;
int offset;
@@ -540,7 +534,7 @@ error:
}
static int FNAME(walk_addr)(struct guest_walker *walker,
- struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
+ struct kvm_vcpu *vcpu, gpa_t addr, u64 access)
{
return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
access);
@@ -988,7 +982,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- gpa_t addr, u32 access,
+ gpa_t addr, u64 access,
struct x86_exception *exception)
{
struct guest_walker walker;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index e7e7876251b3..d71d177ae6b8 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -14,21 +14,24 @@ static bool __read_mostly tdp_mmu_enabled = true;
module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
/* Initializes the TDP MMU for the VM, if enabled. */
-bool kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
{
+ struct workqueue_struct *wq;
+
if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled))
- return false;
+ return 0;
+
+ wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
+ if (!wq)
+ return -ENOMEM;
/* This should not be changed for the lifetime of the VM. */
kvm->arch.tdp_mmu_enabled = true;
-
INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
- kvm->arch.tdp_mmu_zap_wq =
- alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
-
- return true;
+ kvm->arch.tdp_mmu_zap_wq = wq;
+ return 1;
}
/* Arbitrarily returns true so that this may be used in if statements. */
@@ -906,10 +909,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
}
/*
- * Tears down the mappings for the range of gfns, [start, end), and frees the
- * non-root pages mapping GFNs strictly within that range. Returns true if
- * SPTEs have been cleared and a TLB flush is needed before releasing the
- * MMU lock.
+ * Zap leafs SPTEs for the range of gfns, [start, end). Returns true if SPTEs
+ * have been cleared and a TLB flush is needed before releasing the MMU lock.
*
* If can_yield is true, will release the MMU lock and reschedule if the
* scheduler needs the CPU or there is contention on the MMU lock. If this
@@ -917,42 +918,25 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
* the caller must ensure it does not supply too large a GFN range, or the
* operation can cause a soft lockup.
*/
-static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
- gfn_t start, gfn_t end, bool can_yield, bool flush)
+static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
+ gfn_t start, gfn_t end, bool can_yield, bool flush)
{
- bool zap_all = (start == 0 && end >= tdp_mmu_max_gfn_host());
struct tdp_iter iter;
- /*
- * No need to try to step down in the iterator when zapping all SPTEs,
- * zapping the top-level non-leaf SPTEs will recurse on their children.
- */
- int min_level = zap_all ? root->role.level : PG_LEVEL_4K;
-
end = min(end, tdp_mmu_max_gfn_host());
lockdep_assert_held_write(&kvm->mmu_lock);
rcu_read_lock();
- for_each_tdp_pte_min_level(iter, root, min_level, start, end) {
+ for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) {
if (can_yield &&
tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) {
flush = false;
continue;
}
- if (!is_shadow_present_pte(iter.old_spte))
- continue;
-
- /*
- * If this is a non-last-level SPTE that covers a larger range
- * than should be zapped, continue, and zap the mappings at a
- * lower level, except when zapping all SPTEs.
- */
- if (!zap_all &&
- (iter.gfn < start ||
- iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) &&
+ if (!is_shadow_present_pte(iter.old_spte) ||
!is_last_spte(iter.old_spte, iter.level))
continue;
@@ -960,17 +944,13 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
flush = true;
}
- /*
- * Need to flush before releasing RCU. TODO: do it only if intermediate
- * page tables were zapped; there is no need to flush under RCU protection
- * if no 'struct kvm_mmu_page' is freed.
- */
- if (flush)
- kvm_flush_remote_tlbs_with_address(kvm, start, end - start);
-
rcu_read_unlock();
- return false;
+ /*
+ * Because this flow zaps _only_ leaf SPTEs, the caller doesn't need
+ * to provide RCU protection as no 'struct kvm_mmu_page' will be freed.
+ */
+ return flush;
}
/*
@@ -979,13 +959,13 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
* SPTEs have been cleared and a TLB flush is needed before releasing the
* MMU lock.
*/
-bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
- gfn_t end, bool can_yield, bool flush)
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
+ bool can_yield, bool flush)
{
struct kvm_mmu_page *root;
for_each_tdp_mmu_root_yield_safe(kvm, root, as_id)
- flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
+ flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush);
return flush;
}
@@ -1233,8 +1213,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
bool flush)
{
- return __kvm_tdp_mmu_zap_gfn_range(kvm, range->slot->as_id, range->start,
- range->end, range->may_block, flush);
+ return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start,
+ range->end, range->may_block, flush);
}
typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 5e5ef2576c81..c163f7cc23ca 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -15,14 +15,8 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool shared);
-bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start,
gfn_t end, bool can_yield, bool flush);
-static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id,
- gfn_t start, gfn_t end, bool flush)
-{
- return __kvm_tdp_mmu_zap_gfn_range(kvm, as_id, start, end, true, flush);
-}
-
bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
void kvm_tdp_mmu_zap_all(struct kvm *kvm);
void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
@@ -72,7 +66,7 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr,
u64 *spte);
#ifdef CONFIG_X86_64
-bool kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+int kvm_mmu_init_tdp_mmu(struct kvm *kvm);
void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; }
@@ -93,7 +87,7 @@ static inline bool is_tdp_mmu(struct kvm_mmu *mmu)
return sp && is_tdp_mmu_page(sp) && sp->root_count;
}
#else
-static inline bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return false; }
+static inline int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return 0; }
static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {}
static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; }
static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; }
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index b1a02993782b..eca39f56c231 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -96,8 +96,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
u64 config, bool exclude_user,
- bool exclude_kernel, bool intr,
- bool in_tx, bool in_tx_cp)
+ bool exclude_kernel, bool intr)
{
struct perf_event *event;
struct perf_event_attr attr = {
@@ -116,16 +115,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
attr.sample_period = get_sample_period(pmc, pmc->counter);
- if (in_tx)
- attr.config |= HSW_IN_TX;
- if (in_tx_cp) {
+ if ((attr.config & HSW_IN_TX_CHECKPOINTED) &&
+ guest_cpuid_is_intel(pmc->vcpu)) {
/*
* HSW_IN_TX_CHECKPOINTED is not supported with nonzero
* period. Just clear the sample period so at least
* allocating the counter doesn't fail.
*/
attr.sample_period = 0;
- attr.config |= HSW_IN_TX_CHECKPOINTED;
}
event = perf_event_create_kernel_counter(&attr, -1, current,
@@ -185,6 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
u32 type = PERF_TYPE_RAW;
struct kvm *kvm = pmc->vcpu->kvm;
struct kvm_pmu_event_filter *filter;
+ struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu);
bool allow_event = true;
if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
@@ -221,7 +219,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
}
if (type == PERF_TYPE_RAW)
- config = eventsel & AMD64_RAW_EVENT_MASK;
+ config = eventsel & pmu->raw_event_mask;
if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
return;
@@ -232,9 +230,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
pmc_reprogram_counter(pmc, type, config,
!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
- eventsel & ARCH_PERFMON_EVENTSEL_INT,
- (eventsel & HSW_IN_TX),
- (eventsel & HSW_IN_TX_CHECKPOINTED));
+ eventsel & ARCH_PERFMON_EVENTSEL_INT);
}
EXPORT_SYMBOL_GPL(reprogram_gp_counter);
@@ -270,7 +266,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc),
!(en_field & 0x2), /* exclude user */
!(en_field & 0x1), /* exclude kernel */
- pmi, false, false);
+ pmi);
}
EXPORT_SYMBOL_GPL(reprogram_fixed_counter);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index b37b353ec086..a1cf9c31273b 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -726,7 +726,7 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
- int idx, ret = -EINVAL;
+ int idx, ret = 0;
if (!kvm_arch_has_assigned_device(kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP))
@@ -737,7 +737,13 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
idx = srcu_read_lock(&kvm->irq_srcu);
irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
- WARN_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+ if (guest_irq >= irq_rt->nr_rt_entries ||
+ hlist_empty(&irq_rt->map[guest_irq])) {
+ pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+ guest_irq, irq_rt->nr_rt_entries);
+ goto out;
+ }
hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
struct vcpu_data vcpu_info;
@@ -822,7 +828,7 @@ out:
return ret;
}
-bool avic_check_apicv_inhibit_reasons(ulong bit)
+bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
{
ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
BIT(APICV_INHIBIT_REASON_ABSENT) |
@@ -833,7 +839,7 @@ bool avic_check_apicv_inhibit_reasons(ulong bit)
BIT(APICV_INHIBIT_REASON_X2APIC) |
BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
- return supported & BIT(bit);
+ return supported & BIT(reason);
}
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index d4de52409335..24eb935b6f85 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -262,12 +262,10 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* MSR_EVNTSELn */
pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
if (pmc) {
- if (data == pmc->eventsel)
- return 0;
- if (!(data & pmu->reserved_bits)) {
+ data &= ~pmu->reserved_bits;
+ if (data != pmc->eventsel)
reprogram_gp_counter(pmc, data);
- return 0;
- }
+ return 0;
}
return 1;
@@ -284,6 +282,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
pmu->reserved_bits = 0xfffffff000280000ull;
+ pmu->raw_event_mask = AMD64_RAW_EVENT_MASK;
pmu->version = 1;
/* not applicable to AMD; but clean them to prevent any fall out */
pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0884c3414a1b..bd4c64b362d2 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -62,20 +62,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
-#define SVM_FEATURE_LBRV (1 << 1)
-#define SVM_FEATURE_SVML (1 << 2)
-#define SVM_FEATURE_TSC_RATE (1 << 4)
-#define SVM_FEATURE_VMCB_CLEAN (1 << 5)
-#define SVM_FEATURE_FLUSH_ASID (1 << 6)
-#define SVM_FEATURE_DECODE_ASSIST (1 << 7)
-#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
-
#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
-#define TSC_RATIO_RSVD 0xffffff0000000000ULL
-#define TSC_RATIO_MIN 0x0000000000000001ULL
-#define TSC_RATIO_MAX 0x000000ffffffffffULL
-
static bool erratum_383_found __read_mostly;
u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
@@ -87,7 +75,6 @@ u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
static uint64_t osvw_len = 4, osvw_status;
static DEFINE_PER_CPU(u64, current_tsc_ratio);
-#define TSC_RATIO_DEFAULT 0x0100000000ULL
static const struct svm_direct_access_msrs {
u32 index; /* Index of the MSR */
@@ -480,7 +467,7 @@ static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (tsc_scaling)
- wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
+ wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
cpu_svm_disable();
@@ -526,8 +513,8 @@ static int svm_hardware_enable(void)
* Set the default value, even if we don't use TSC scaling
* to avoid having stale value in the msr
*/
- wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
- __this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT);
+ wrmsrl(MSR_AMD64_TSC_RATIO, SVM_TSC_RATIO_DEFAULT);
+ __this_cpu_write(current_tsc_ratio, SVM_TSC_RATIO_DEFAULT);
}
@@ -2723,7 +2710,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
}
- if (data & TSC_RATIO_RSVD)
+ if (data & SVM_TSC_RATIO_RSVD)
return 1;
svm->tsc_ratio_msr = data;
@@ -2918,7 +2905,7 @@ static int interrupt_window_interception(struct kvm_vcpu *vcpu)
* In this case AVIC was temporarily disabled for
* requesting the IRQ window and we have to re-enable it.
*/
- kvm_request_apicv_update(vcpu->kvm, true, APICV_INHIBIT_REASON_IRQWIN);
+ kvm_clear_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN);
++vcpu->stat.irq_window_exits;
return 1;
@@ -3516,7 +3503,7 @@ static void svm_enable_irq_window(struct kvm_vcpu *vcpu)
* via AVIC. In such case, we need to temporarily disable AVIC,
* and fallback to injecting IRQ via V_IRQ.
*/
- kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_IRQWIN);
+ kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN);
svm_set_vintr(svm);
}
}
@@ -3948,6 +3935,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_cpuid_entry2 *best;
+ struct kvm *kvm = vcpu->kvm;
vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
boot_cpu_has(X86_FEATURE_XSAVE) &&
@@ -3974,16 +3962,14 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
* is exposed to the guest, disable AVIC.
*/
if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC))
- kvm_request_apicv_update(vcpu->kvm, false,
- APICV_INHIBIT_REASON_X2APIC);
+ kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_X2APIC);
/*
* Currently, AVIC does not work with nested virtualization.
* So, we disable AVIC when cpuid for SVM is set in the L1 guest.
*/
if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM))
- kvm_request_apicv_update(vcpu->kvm, false,
- APICV_INHIBIT_REASON_NESTED);
+ kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_NESTED);
}
init_vmcb_after_set_cpuid(vcpu);
}
@@ -4766,10 +4752,10 @@ static __init int svm_hardware_setup(void)
} else {
pr_info("TSC scaling supported\n");
kvm_has_tsc_control = true;
- kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX;
- kvm_tsc_scaling_ratio_frac_bits = 32;
}
}
+ kvm_max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX;
+ kvm_tsc_scaling_ratio_frac_bits = 32;
tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e37bb3508cfa..f77a7d2d39dd 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -22,6 +22,8 @@
#include <asm/svm.h>
#include <asm/sev-common.h>
+#include "kvm_cache_regs.h"
+
#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
#define IOPM_SIZE PAGE_SIZE * 3
@@ -569,17 +571,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
/* avic.c */
-#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
-#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
-#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
-
-#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0)
-#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12)
-#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62)
-#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63)
-
-#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
-
int avic_ga_log_notifier(u32 ga_tag);
void avic_vm_destroy(struct kvm *kvm);
int avic_vm_init(struct kvm *kvm);
@@ -592,7 +583,7 @@ void __avic_vcpu_put(struct kvm_vcpu *vcpu);
void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu);
void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
-bool avic_check_apicv_inhibit_reasons(ulong bit);
+bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason);
void avic_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
void avic_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr);
bool avic_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c
index 98aa981c04ec..8cdc62c74a96 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.c
+++ b/arch/x86/kvm/svm/svm_onhyperv.c
@@ -4,7 +4,6 @@
*/
#include <linux/kvm_host.h>
-#include "kvm_cache_regs.h"
#include <asm/mshyperv.h>
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 193f5ba930d1..e3a24b8f04be 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1339,23 +1339,25 @@ TRACE_EVENT(kvm_hv_stimer_cleanup,
__entry->vcpu_id, __entry->timer_index)
);
-TRACE_EVENT(kvm_apicv_update_request,
- TP_PROTO(bool activate, unsigned long bit),
- TP_ARGS(activate, bit),
+TRACE_EVENT(kvm_apicv_inhibit_changed,
+ TP_PROTO(int reason, bool set, unsigned long inhibits),
+ TP_ARGS(reason, set, inhibits),
TP_STRUCT__entry(
- __field(bool, activate)
- __field(unsigned long, bit)
+ __field(int, reason)
+ __field(bool, set)
+ __field(unsigned long, inhibits)
),
TP_fast_assign(
- __entry->activate = activate;
- __entry->bit = bit;
+ __entry->reason = reason;
+ __entry->set = set;
+ __entry->inhibits = inhibits;
),
- TP_printk("%s bit=%lu",
- __entry->activate ? "activate" : "deactivate",
- __entry->bit)
+ TP_printk("%s reason=%u, inhibits=0x%lx",
+ __entry->set ? "set" : "cleared",
+ __entry->reason, __entry->inhibits)
);
TRACE_EVENT(kvm_apicv_accept_irq,
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 0684e519181b..bc3f8512bb64 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -389,6 +389,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
struct kvm_pmc *pmc;
u32 msr = msr_info->index;
u64 data = msr_info->data;
+ u64 reserved_bits;
switch (msr) {
case MSR_CORE_PERF_FIXED_CTR_CTRL:
@@ -443,7 +444,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
if (data == pmc->eventsel)
return 0;
- if (!(data & pmu->reserved_bits)) {
+ reserved_bits = pmu->reserved_bits;
+ if ((pmc->idx == 2) &&
+ (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED))
+ reserved_bits ^= HSW_IN_TX_CHECKPOINTED;
+ if (!(data & reserved_bits)) {
reprogram_gp_counter(pmc, data);
return 0;
}
@@ -485,6 +490,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
pmu->version = 0;
pmu->reserved_bits = 0xffffffff00200000ull;
+ pmu->raw_event_mask = X86_RAW_EVENT_MASK;
entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
if (!entry || !vcpu->kvm->arch.enable_pmu)
@@ -533,8 +539,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
entry = kvm_find_cpuid_entry(vcpu, 7, 0);
if (entry &&
(boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
- (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
- pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+ (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) {
+ pmu->reserved_bits ^= HSW_IN_TX;
+ pmu->raw_event_mask |= (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED);
+ }
bitmap_set(pmu->all_valid_pmc_idx,
0, pmu->nr_arch_gp_counters);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e8963f5af618..04d170c4b61e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2866,21 +2866,17 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct vmx_uret_msr *msr = vmx_find_uret_msr(vmx, MSR_EFER);
/* Nothing to do if hardware doesn't support EFER. */
- if (!msr)
+ if (!vmx_find_uret_msr(vmx, MSR_EFER))
return 0;
vcpu->arch.efer = efer;
- if (efer & EFER_LMA) {
- vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
- msr->data = efer;
- } else {
- vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
+ if (efer & EFER_LMA)
+ vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE);
+ else
+ vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE);
- msr->data = efer & ~EFER_LME;
- }
vmx_setup_uret_msrs(vmx);
return 0;
}
@@ -2906,7 +2902,6 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
static void exit_lmode(struct kvm_vcpu *vcpu)
{
- vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA);
}
@@ -7705,14 +7700,14 @@ static void vmx_hardware_unsetup(void)
free_kvm_area();
}
-static bool vmx_check_apicv_inhibit_reasons(ulong bit)
+static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
{
ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
BIT(APICV_INHIBIT_REASON_ABSENT) |
BIT(APICV_INHIBIT_REASON_HYPERV) |
BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
- return supported & BIT(bit);
+ return supported & BIT(reason);
}
static struct kvm_x86_ops vmx_x86_ops __initdata = {
@@ -7980,12 +7975,11 @@ static __init int hardware_setup(void)
if (!enable_apicv)
vmx_x86_ops.sync_pir_to_irr = NULL;
- if (cpu_has_vmx_tsc_scaling()) {
+ if (cpu_has_vmx_tsc_scaling())
kvm_has_tsc_control = true;
- kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
- kvm_tsc_scaling_ratio_frac_bits = 48;
- }
+ kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;
+ kvm_tsc_scaling_ratio_frac_bits = 48;
kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection();
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02cf0a7e1d14..0c0ca599a353 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1748,9 +1748,6 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
{
struct msr_data msr;
- if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
- return KVM_MSR_RET_FILTERED;
-
switch (index) {
case MSR_FS_BASE:
case MSR_GS_BASE:
@@ -1832,9 +1829,6 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
struct msr_data msr;
int ret;
- if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
- return KVM_MSR_RET_FILTERED;
-
switch (index) {
case MSR_TSC_AUX:
if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX))
@@ -1871,6 +1865,20 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
return ret;
}
+static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data)
+{
+ if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
+ return KVM_MSR_RET_FILTERED;
+ return kvm_get_msr_ignored_check(vcpu, index, data, false);
+}
+
+static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data)
+{
+ if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
+ return KVM_MSR_RET_FILTERED;
+ return kvm_set_msr_ignored_check(vcpu, index, data, false);
+}
+
int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
{
return kvm_get_msr_ignored_check(vcpu, index, data, false);
@@ -1953,7 +1961,7 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
u64 data;
int r;
- r = kvm_get_msr(vcpu, ecx, &data);
+ r = kvm_get_msr_with_filter(vcpu, ecx, &data);
if (!r) {
trace_kvm_msr_read(ecx, data);
@@ -1978,7 +1986,7 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
u64 data = kvm_read_edx_eax(vcpu);
int r;
- r = kvm_set_msr(vcpu, ecx, data);
+ r = kvm_set_msr_with_filter(vcpu, ecx, data);
if (!r) {
trace_kvm_msr_write(ecx, data);
@@ -5938,7 +5946,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
smp_wmb();
kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
- kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
+ kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT);
r = 0;
split_irqchip_unlock:
mutex_unlock(&kvm->lock);
@@ -6335,7 +6343,7 @@ set_identity_unlock:
/* Write kvm->irq_routing before enabling irqchip_in_kernel. */
smp_wmb();
kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL;
- kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
+ kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_ABSENT);
create_irqchip_unlock:
mutex_unlock(&kvm->lock);
break;
@@ -6726,7 +6734,7 @@ void kvm_get_segment(struct kvm_vcpu *vcpu,
static_call(kvm_x86_get_segment)(vcpu, var, seg);
}
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access,
struct x86_exception *exception)
{
struct kvm_mmu *mmu = vcpu->arch.mmu;
@@ -6746,7 +6754,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
}
EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read);
@@ -6756,7 +6764,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read);
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
access |= PFERR_FETCH_MASK;
return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
}
@@ -6766,7 +6774,7 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
access |= PFERR_WRITE_MASK;
return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
}
@@ -6782,7 +6790,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
}
static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
- struct kvm_vcpu *vcpu, u32 access,
+ struct kvm_vcpu *vcpu, u64 access,
struct x86_exception *exception)
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
@@ -6819,7 +6827,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
unsigned offset;
int ret;
@@ -6844,7 +6852,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception)
{
- u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
/*
* FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
@@ -6863,9 +6871,11 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
struct x86_exception *exception, bool system)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
- u32 access = 0;
+ u64 access = 0;
- if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3)
+ if (system)
+ access |= PFERR_IMPLICIT_ACCESS;
+ else if (static_call(kvm_x86_get_cpl)(vcpu) == 3)
access |= PFERR_USER_MASK;
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
@@ -6881,7 +6891,7 @@ static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
}
static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
- struct kvm_vcpu *vcpu, u32 access,
+ struct kvm_vcpu *vcpu, u64 access,
struct x86_exception *exception)
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
@@ -6915,9 +6925,11 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v
bool system)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
- u32 access = PFERR_WRITE_MASK;
+ u64 access = PFERR_WRITE_MASK;
- if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3)
+ if (system)
+ access |= PFERR_IMPLICIT_ACCESS;
+ else if (static_call(kvm_x86_get_cpl)(vcpu) == 3)
access |= PFERR_USER_MASK;
return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
@@ -6984,7 +6996,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
bool write)
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
- u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0)
+ u64 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0)
| (write ? PFERR_WRITE_MASK : 0);
/*
@@ -7627,13 +7639,13 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
return;
}
-static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
- u32 msr_index, u64 *pdata)
+static int emulator_get_msr_with_filter(struct x86_emulate_ctxt *ctxt,
+ u32 msr_index, u64 *pdata)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
int r;
- r = kvm_get_msr(vcpu, msr_index, pdata);
+ r = kvm_get_msr_with_filter(vcpu, msr_index, pdata);
if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_RDMSR, 0,
complete_emulated_rdmsr, r)) {
@@ -7644,13 +7656,13 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
return r;
}
-static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
- u32 msr_index, u64 data)
+static int emulator_set_msr_with_filter(struct x86_emulate_ctxt *ctxt,
+ u32 msr_index, u64 data)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
int r;
- r = kvm_set_msr(vcpu, msr_index, data);
+ r = kvm_set_msr_with_filter(vcpu, msr_index, data);
if (r && kvm_msr_user_space(vcpu, msr_index, KVM_EXIT_X86_WRMSR, data,
complete_emulated_msr_access, r)) {
@@ -7661,6 +7673,18 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
return r;
}
+static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
+ u32 msr_index, u64 *pdata)
+{
+ return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+}
+
+static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
+ u32 msr_index, u64 data)
+{
+ return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
+}
+
static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
@@ -7724,6 +7748,11 @@ static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt)
return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR);
}
+static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt)
+{
+ return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID);
+}
+
static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
{
return kvm_register_read_raw(emul_to_vcpu(ctxt), reg);
@@ -7794,6 +7823,8 @@ static const struct x86_emulate_ops emulate_ops = {
.set_dr = emulator_set_dr,
.get_smbase = emulator_get_smbase,
.set_smbase = emulator_set_smbase,
+ .set_msr_with_filter = emulator_set_msr_with_filter,
+ .get_msr_with_filter = emulator_get_msr_with_filter,
.set_msr = emulator_set_msr,
.get_msr = emulator_get_msr,
.check_pmc = emulator_check_pmc,
@@ -7806,6 +7837,7 @@ static const struct x86_emulate_ops emulate_ops = {
.guest_has_long_mode = emulator_guest_has_long_mode,
.guest_has_movbe = emulator_guest_has_movbe,
.guest_has_fxsr = emulator_guest_has_fxsr,
+ .guest_has_rdpid = emulator_guest_has_rdpid,
.set_nmi_mask = emulator_set_nmi_mask,
.get_hflags = emulator_get_hflags,
.exiting_smm = emulator_exiting_smm,
@@ -9058,15 +9090,29 @@ bool kvm_apicv_activated(struct kvm *kvm)
}
EXPORT_SYMBOL_GPL(kvm_apicv_activated);
+
+static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
+ enum kvm_apicv_inhibit reason, bool set)
+{
+ if (set)
+ __set_bit(reason, inhibits);
+ else
+ __clear_bit(reason, inhibits);
+
+ trace_kvm_apicv_inhibit_changed(reason, set, *inhibits);
+}
+
static void kvm_apicv_init(struct kvm *kvm)
{
+ unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons;
+
init_rwsem(&kvm->arch.apicv_update_lock);
- set_bit(APICV_INHIBIT_REASON_ABSENT,
- &kvm->arch.apicv_inhibit_reasons);
+ set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true);
+
if (!enable_apicv)
- set_bit(APICV_INHIBIT_REASON_DISABLE,
- &kvm->arch.apicv_inhibit_reasons);
+ set_or_clear_apicv_inhibit(inhibits,
+ APICV_INHIBIT_REASON_ABSENT, true);
}
static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
@@ -9740,24 +9786,21 @@ out:
}
EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv);
-void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit)
+void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason, bool set)
{
unsigned long old, new;
lockdep_assert_held_write(&kvm->arch.apicv_update_lock);
- if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(bit))
+ if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason))
return;
old = new = kvm->arch.apicv_inhibit_reasons;
- if (activate)
- __clear_bit(bit, &new);
- else
- __set_bit(bit, &new);
+ set_or_clear_apicv_inhibit(&new, reason, set);
if (!!old != !!new) {
- trace_kvm_apicv_update_request(activate, bit);
/*
* Kick all vCPUs before setting apicv_inhibit_reasons to avoid
* false positives in the sanity check WARN in svm_vcpu_run().
@@ -9776,20 +9819,22 @@ void __kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit)
unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE);
kvm_zap_gfn_range(kvm, gfn, gfn+1);
}
- } else
+ } else {
kvm->arch.apicv_inhibit_reasons = new;
+ }
}
-void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit)
+void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason, bool set)
{
if (!enable_apicv)
return;
down_write(&kvm->arch.apicv_update_lock);
- __kvm_request_apicv_update(kvm, activate, bit);
+ __kvm_set_or_clear_apicv_inhibit(kvm, reason, set);
up_write(&kvm->arch.apicv_update_lock);
}
-EXPORT_SYMBOL_GPL(kvm_request_apicv_update);
+EXPORT_SYMBOL_GPL(kvm_set_or_clear_apicv_inhibit);
static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
{
@@ -10937,7 +10982,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm)
{
- bool inhibit = false;
+ bool set = false;
struct kvm_vcpu *vcpu;
unsigned long i;
@@ -10945,11 +10990,11 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm)
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) {
- inhibit = true;
+ set = true;
break;
}
}
- __kvm_request_apicv_update(kvm, !inhibit, APICV_INHIBIT_REASON_BLOCKIRQ);
+ __kvm_set_or_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_BLOCKIRQ, set);
up_write(&kvm->arch.apicv_update_lock);
}
@@ -11557,10 +11602,8 @@ int kvm_arch_hardware_setup(void *opaque)
u64 max = min(0x7fffffffULL,
__scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz));
kvm_max_guest_tsc_khz = max;
-
- kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits;
}
-
+ kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits;
kvm_init_msr_list();
return 0;
}
@@ -11629,12 +11672,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
ret = kvm_page_track_init(kvm);
if (ret)
- return ret;
+ goto out;
+
+ ret = kvm_mmu_init_vm(kvm);
+ if (ret)
+ goto out_page_track;
INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
- INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
- INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
- INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
atomic_set(&kvm->arch.noncoherent_dma_count, 0);
@@ -11666,10 +11710,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm_apicv_init(kvm);
kvm_hv_init_vm(kvm);
- kvm_mmu_init_vm(kvm);
kvm_xen_init_vm(kvm);
return static_call(kvm_x86_vm_init)(kvm);
+
+out_page_track:
+ kvm_page_track_cleanup(kvm);
+out:
+ return ret;
}
int kvm_arch_post_init_vm(struct kvm *kvm)
@@ -12593,7 +12641,7 @@ void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_c
{
struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
struct x86_exception fault;
- u32 access = error_code &
+ u64 access = error_code &
(PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK);
if (!(error_code & PFERR_PRESENT_MASK) ||
@@ -12933,7 +12981,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log);
-EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_accept_irq);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 4aa0f2b31665..bf6cc25eee76 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -39,8 +39,8 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn)
}
do {
- ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, false, true,
- gpa, PAGE_SIZE, false);
+ ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, KVM_HOST_USES_PFN,
+ gpa, PAGE_SIZE);
if (ret)
goto out;
@@ -1025,8 +1025,7 @@ static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm
break;
idx = srcu_read_lock(&kvm->srcu);
- rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa,
- PAGE_SIZE, false);
+ rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa, PAGE_SIZE);
srcu_read_unlock(&kvm->srcu, idx);
} while(!rc);
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 1f8a8f895173..50734a23034c 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -93,7 +93,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
buff += 8;
}
if (len & 7) {
-#ifdef CONFIG_DCACHE_WORD_ACCESS
unsigned int shift = (8 - (len & 7)) * 8;
unsigned long trail;
@@ -103,31 +102,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
"adcq $0,%[res]"
: [res] "+r" (temp64)
: [trail] "r" (trail));
-#else
- if (len & 4) {
- asm("addq %[val],%[res]\n\t"
- "adcq $0,%[res]"
- : [res] "+r" (temp64)
- : [val] "r" ((u64)*(u32 *)buff)
- : "memory");
- buff += 4;
- }
- if (len & 2) {
- asm("addq %[val],%[res]\n\t"
- "adcq $0,%[res]"
- : [res] "+r" (temp64)
- : [val] "r" ((u64)*(u16 *)buff)
- : "memory");
- buff += 2;
- }
- if (len & 1) {
- asm("addq %[val],%[res]\n\t"
- "adcq $0,%[res]"
- : [res] "+r" (temp64)
- : [val] "r" ((u64)*(u8 *)buff)
- : "memory");
- }
-#endif
}
result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
if (unlikely(odd)) {
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index ead7e5b3a975..1bcd42c53039 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -9,6 +9,7 @@ endmenu
config UML_X86
def_bool y
select ARCH_BINFMT_ELF_EXTRA_PHDRS if X86_32
+ select DCACHE_WORD_ACCESS
config 64BIT
bool "64-bit kernel" if "$(SUBARCH)" = "x86"