summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arc/Kconfig5
-rw-r--r--arch/arc/Makefile2
-rw-r--r--arch/arc/boot/dts/axc001.dtsi2
-rw-r--r--arch/arc/boot/dts/axc003.dtsi2
-rw-r--r--arch/arc/boot/dts/axc003_idu.dtsi2
-rw-r--r--arch/arc/boot/dts/axs10x_mb.dtsi12
-rw-r--r--arch/arc/boot/dts/hsdk.dts2
-rw-r--r--arch/arc/include/asm/arcregs.h2
-rw-r--r--arch/arc/include/asm/cachetype.h8
-rw-r--r--arch/arc/include/asm/cmpxchg.h2
-rw-r--r--arch/arc/include/asm/mmu-arcv2.h2
-rw-r--r--arch/arc/net/bpf_jit_arcv2.c2
-rw-r--r--arch/arm/common/locomo.c2
-rw-r--r--arch/arm/common/sa1111.c2
-rw-r--r--arch/arm/common/scoop.c2
-rw-r--r--arch/arm/mach-imx/Kconfig1
-rw-r--r--arch/arm/mach-imx/mmdc.c2
-rw-r--r--arch/arm/mach-omap1/omap-dma.c2
-rw-r--r--arch/arm/mach-pxa/sharpsl_pm.c2
-rw-r--r--arch/arm/mach-sa1100/jornada720_ssp.c2
-rw-r--r--arch/arm/mach-sa1100/neponset.c2
-rw-r--r--arch/arm64/boot/dts/arm/fvp-base-revc.dts2
-rw-r--r--arch/arm64/boot/dts/broadcom/bcm2712.dtsi8
-rw-r--r--arch/arm64/crypto/aes-ce-ccm-glue.c2
-rw-r--r--arch/arm64/crypto/aes-glue.c2
-rw-r--r--arch/arm64/include/asm/cpucaps.h2
-rw-r--r--arch/arm64/include/asm/cpufeature.h3
-rw-r--r--arch/arm64/include/asm/el2_setup.h4
-rw-r--r--arch/arm64/include/asm/mman.h3
-rw-r--r--arch/arm64/kernel/hyp-stub.S4
-rw-r--r--arch/arm64/kernel/patching.c25
-rw-r--r--arch/arm64/kernel/ptrace.c36
-rw-r--r--arch/arm64/kernel/signal.c83
-rw-r--r--arch/arm64/kernel/stacktrace.c32
-rw-r--r--arch/arm64/kvm/at.c11
-rw-r--r--arch/arm64/kvm/hyp/nvhe/pkvm.c4
-rw-r--r--arch/arm64/kvm/sys_regs.c3
-rw-r--r--arch/arm64/kvm/vgic/vgic-its.c12
-rw-r--r--arch/arm64/mm/context.c4
-rw-r--r--arch/arm64/mm/copypage.c8
-rw-r--r--arch/arm64/mm/init.c17
-rw-r--r--arch/hexagon/Makefile6
-rw-r--r--arch/loongarch/include/asm/hugetlb.h10
-rw-r--r--arch/loongarch/include/asm/inst.h12
-rw-r--r--arch/loongarch/kernel/efi.c2
-rw-r--r--arch/loongarch/kernel/inst.c2
-rw-r--r--arch/loongarch/kernel/smp.c2
-rw-r--r--arch/loongarch/kvm/exit.c31
-rw-r--r--arch/loongarch/kvm/intc/ipi.c6
-rw-r--r--arch/loongarch/kvm/vcpu.c4
-rw-r--r--arch/loongarch/net/bpf_jit.c6
-rw-r--r--arch/mips/pci/pci-xtalk-bridge.c2
-rw-r--r--arch/nios2/kernel/cpuinfo.c10
-rw-r--r--arch/openrisc/kernel/entry.S2
-rw-r--r--arch/openrisc/kernel/head.S32
-rw-r--r--arch/openrisc/kernel/vmlinux.lds.S3
-rw-r--r--arch/powerpc/configs/pmac32_defconfig1
-rw-r--r--arch/powerpc/configs/ppc6xx_defconfig1
-rw-r--r--arch/powerpc/crypto/vmx.c2
-rw-r--r--arch/powerpc/platforms/book3s/vas-api.c36
-rw-r--r--arch/riscv/include/asm/kfence.h4
-rw-r--r--arch/riscv/kernel/jump_label.c12
-rw-r--r--arch/riscv/kernel/setup.c2
-rw-r--r--arch/riscv/kvm/aia.c2
-rw-r--r--arch/riscv/mm/init.c7
-rw-r--r--arch/s390/boot/startup.c2
-rw-r--r--arch/s390/boot/vmem.c6
-rw-r--r--arch/s390/crypto/aes_s390.c2
-rw-r--r--arch/s390/kernel/ipl.c2
-rw-r--r--arch/sh/drivers/push-switch.c2
-rw-r--r--arch/sparc/include/asm/parport_64.h2
-rw-r--r--arch/sparc/kernel/chmc.c2
-rw-r--r--arch/um/drivers/rtc_kern.c2
-rw-r--r--arch/um/drivers/virtio_uml.c2
-rw-r--r--arch/x86/events/intel/core.c13
-rw-r--r--arch/x86/events/intel/ds.c3
-rw-r--r--arch/x86/events/intel/uncore.c1
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/pgtable_types.h8
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/static_call.h15
-rw-r--r--arch/x86/include/asm/sync_core.h6
-rw-r--r--arch/x86/include/asm/xen/hypercall.h36
-rw-r--r--arch/x86/kernel/callthunks.c5
-rw-r--r--arch/x86/kernel/cet.c30
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c43
-rw-r--r--arch/x86/kernel/cpu/common.c38
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c58
-rw-r--r--arch/x86/kernel/cpu/topology.c6
-rw-r--r--arch/x86/kernel/fpu/signal.c20
-rw-r--r--arch/x86/kernel/fpu/xstate.h27
-rw-r--r--arch/x86/kernel/relocate_kernel_64.S8
-rw-r--r--arch/x86/kernel/static_call.c9
-rw-r--r--arch/x86/kernel/vmlinux.lds.S4
-rw-r--r--arch/x86/kvm/cpuid.c31
-rw-r--r--arch/x86/kvm/cpuid.h1
-rw-r--r--arch/x86/kvm/mmu/mmu.c12
-rw-r--r--arch/x86/kvm/mmu/spte.h17
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c5
-rw-r--r--arch/x86/kvm/svm/avic.c6
-rw-r--r--arch/x86/kvm/svm/svm.c9
-rw-r--r--arch/x86/kvm/vmx/posted_intr.h2
-rw-r--r--arch/x86/kvm/x86.c11
-rw-r--r--arch/x86/mm/ident_map.c6
-rw-r--r--arch/x86/mm/pat/set_memory.c4
-rw-r--r--arch/x86/mm/pti.c2
-rw-r--r--arch/x86/xen/enlighten.c65
-rw-r--r--arch/x86/xen/enlighten_hvm.c13
-rw-r--r--arch/x86/xen/enlighten_pv.c4
-rw-r--r--arch/x86/xen/enlighten_pvh.c7
-rw-r--r--arch/x86/xen/xen-asm.S50
-rw-r--r--arch/x86/xen/xen-head.S107
-rw-r--r--arch/x86/xen/xen-ops.h9
115 files changed, 866 insertions, 378 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 5b2488142041..4f2eeda907ec 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -6,6 +6,7 @@
config ARC
def_bool y
select ARC_TIMERS
+ select ARCH_HAS_CPU_CACHE_ALIASING
select ARCH_HAS_CACHE_LINE_SIZE
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DMA_PREP_COHERENT
@@ -297,7 +298,6 @@ config ARC_PAGE_SIZE_16K
config ARC_PAGE_SIZE_4K
bool "4KB"
select HAVE_PAGE_SIZE_4KB
- depends on ARC_MMU_V3 || ARC_MMU_V4
endchoice
@@ -474,7 +474,8 @@ config HIGHMEM
config ARC_HAS_PAE40
bool "Support for the 40-bit Physical Address Extension"
- depends on ISA_ARCV2
+ depends on ARC_MMU_V4
+ depends on !ARC_PAGE_SIZE_4K
select HIGHMEM
select PHYS_ADDR_T_64BIT
help
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 2390dd042e36..fb98478ed1ab 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -6,7 +6,7 @@
KBUILD_DEFCONFIG := haps_hs_smp_defconfig
ifeq ($(CROSS_COMPILE),)
-CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-)
+CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux- arc-linux-gnu-)
endif
cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
index 2a151607b080..88bcc7ab6f5a 100644
--- a/arch/arc/boot/dts/axc001.dtsi
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -54,7 +54,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <30>;
+ ngpios = <30>;
reg = <0>;
interrupt-controller;
#interrupt-cells = <2>;
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index c0a812674ce9..9a2dc39a5cff 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -62,7 +62,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <30>;
+ ngpios = <30>;
reg = <0>;
interrupt-controller;
#interrupt-cells = <2>;
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 67556f4b7057..f31382cb8be4 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -69,7 +69,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <30>;
+ ngpios = <30>;
reg = <0>;
interrupt-controller;
#interrupt-cells = <2>;
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index b64435385304..3add2fe257f8 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -250,7 +250,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <32>;
+ ngpios = <32>;
reg = <0>;
};
@@ -258,7 +258,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <8>;
+ ngpios = <8>;
reg = <1>;
};
@@ -266,7 +266,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <8>;
+ ngpios = <8>;
reg = <2>;
};
};
@@ -281,7 +281,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <30>;
+ ngpios = <30>;
reg = <0>;
};
@@ -289,7 +289,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <10>;
+ ngpios = <10>;
reg = <1>;
};
@@ -297,7 +297,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <8>;
+ ngpios = <8>;
reg = <2>;
};
};
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 41b980df862b..98bb850722a4 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -308,7 +308,7 @@
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <24>;
+ ngpios = <24>;
reg = <0>;
};
};
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 4b13f60fe7ca..005d9e4d187a 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -146,7 +146,7 @@
#ifndef __ASSEMBLY__
-#include <soc/arc/aux.h>
+#include <soc/arc/arc_aux.h>
/* Helpers */
#define TO_KB(bytes) ((bytes) >> 10)
diff --git a/arch/arc/include/asm/cachetype.h b/arch/arc/include/asm/cachetype.h
new file mode 100644
index 000000000000..acd3b6cb4bf5
--- /dev/null
+++ b/arch/arc/include/asm/cachetype.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ARC_CACHETYPE_H
+#define __ASM_ARC_CACHETYPE_H
+
+#define cpu_dcache_is_aliasing() false
+#define cpu_icache_is_aliasing() true
+
+#endif
diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h
index 58045c898340..76f43db0890f 100644
--- a/arch/arc/include/asm/cmpxchg.h
+++ b/arch/arc/include/asm/cmpxchg.h
@@ -48,7 +48,7 @@
\
switch(sizeof((_p_))) { \
case 1: \
- _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \
+ _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *__force)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \
break; \
case 4: \
_prev_ = __cmpxchg(_p_, _o_, _n_); \
diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h
index d85dc0721907..41412642f279 100644
--- a/arch/arc/include/asm/mmu-arcv2.h
+++ b/arch/arc/include/asm/mmu-arcv2.h
@@ -9,7 +9,7 @@
#ifndef _ASM_ARC_MMU_ARCV2_H
#define _ASM_ARC_MMU_ARCV2_H
-#include <soc/arc/aux.h>
+#include <soc/arc/arc_aux.h>
/*
* TLB Management regs
diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c
index 4458e409ca0a..6d989b6d88c6 100644
--- a/arch/arc/net/bpf_jit_arcv2.c
+++ b/arch/arc/net/bpf_jit_arcv2.c
@@ -2916,7 +2916,7 @@ bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond)
addendum = (cond == ARC_CC_AL) ? 0 : INSN_len_normal;
disp = get_displacement(curr_off + addendum, targ_off);
- if (ARC_CC_AL)
+ if (cond == ARC_CC_AL)
return is_valid_far_disp(disp);
else
return is_valid_near_disp(disp);
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 06b0e5fd54a6..cb6ef449b987 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -516,7 +516,7 @@ static void locomo_remove(struct platform_device *dev)
*/
static struct platform_driver locomo_device_driver = {
.probe = locomo_probe,
- .remove_new = locomo_remove,
+ .remove = locomo_remove,
#ifdef CONFIG_PM
.suspend = locomo_suspend,
.resume = locomo_resume,
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 550978dc3c50..9846f30990f7 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -1154,7 +1154,7 @@ static struct dev_pm_ops sa1111_pm_ops = {
*/
static struct platform_driver sa1111_device_driver = {
.probe = sa1111_probe,
- .remove_new = sa1111_remove,
+ .remove = sa1111_remove,
.driver = {
.name = "sa1111",
.pm = &sa1111_pm_ops,
diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c
index 9018c7240166..0b08b6621878 100644
--- a/arch/arm/common/scoop.c
+++ b/arch/arm/common/scoop.c
@@ -250,7 +250,7 @@ static void scoop_remove(struct platform_device *pdev)
static struct platform_driver scoop_driver = {
.probe = scoop_probe,
- .remove_new = scoop_remove,
+ .remove = scoop_remove,
.suspend = scoop_suspend,
.resume = scoop_resume,
.driver = {
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index e4fe059cd861..dc47b2312127 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -6,6 +6,7 @@ menuconfig ARCH_MXC
select CLKSRC_IMX_GPT
select GENERIC_IRQ_CHIP
select GPIOLIB
+ select PINCTRL
select PM_OPP if PM
select SOC_BUS
select SRAM
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index b68cb86dbe4c..e898f7c2733e 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -596,7 +596,7 @@ static struct platform_driver imx_mmdc_driver = {
.of_match_table = imx_mmdc_dt_ids,
},
.probe = imx_mmdc_probe,
- .remove_new = imx_mmdc_remove,
+ .remove = imx_mmdc_remove,
};
static int __init imx_mmdc_init(void)
diff --git a/arch/arm/mach-omap1/omap-dma.c b/arch/arm/mach-omap1/omap-dma.c
index f091f78631d0..aebe5e55ff60 100644
--- a/arch/arm/mach-omap1/omap-dma.c
+++ b/arch/arm/mach-omap1/omap-dma.c
@@ -832,7 +832,7 @@ static void omap_system_dma_remove(struct platform_device *pdev)
static struct platform_driver omap_system_dma_driver = {
.probe = omap_system_dma_probe,
- .remove_new = omap_system_dma_remove,
+ .remove = omap_system_dma_remove,
.driver = {
.name = "omap_dma_system"
},
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index 72fa2e3fd353..0c8d9000df5a 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -919,7 +919,7 @@ static void sharpsl_pm_remove(struct platform_device *pdev)
static struct platform_driver sharpsl_pm_driver = {
.probe = sharpsl_pm_probe,
- .remove_new = sharpsl_pm_remove,
+ .remove = sharpsl_pm_remove,
.suspend = sharpsl_pm_suspend,
.resume = sharpsl_pm_resume,
.driver = {
diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c
index 1956b095e699..d94810217095 100644
--- a/arch/arm/mach-sa1100/jornada720_ssp.c
+++ b/arch/arm/mach-sa1100/jornada720_ssp.c
@@ -188,7 +188,7 @@ static void jornada_ssp_remove(struct platform_device *dev)
struct platform_driver jornadassp_driver = {
.probe = jornada_ssp_probe,
- .remove_new = jornada_ssp_remove,
+ .remove = jornada_ssp_remove,
.driver = {
.name = "jornada_ssp",
},
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index 0ef0ebbf31ac..88fe79f0a4ed 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -423,7 +423,7 @@ static const struct dev_pm_ops neponset_pm_ops = {
static struct platform_driver neponset_device_driver = {
.probe = neponset_probe,
- .remove_new = neponset_remove,
+ .remove = neponset_remove,
.driver = {
.name = "neponset",
.pm = PM_OPS,
diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
index 19973ab4ea6b..9e10d7a6b5a2 100644
--- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts
+++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts
@@ -233,7 +233,7 @@
#interrupt-cells = <0x1>;
compatible = "pci-host-ecam-generic";
device_type = "pci";
- bus-range = <0x0 0x1>;
+ bus-range = <0x0 0xff>;
reg = <0x0 0x40000000 0x0 0x10000000>;
ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>;
interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
index 6e5a984c1d4e..26a29e5e5078 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
@@ -67,7 +67,7 @@
l2_cache_l0: l2-cache-l0 {
compatible = "cache";
cache-size = <0x80000>;
- cache-line-size = <128>;
+ cache-line-size = <64>;
cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set
cache-level = <2>;
cache-unified;
@@ -91,7 +91,7 @@
l2_cache_l1: l2-cache-l1 {
compatible = "cache";
cache-size = <0x80000>;
- cache-line-size = <128>;
+ cache-line-size = <64>;
cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set
cache-level = <2>;
cache-unified;
@@ -115,7 +115,7 @@
l2_cache_l2: l2-cache-l2 {
compatible = "cache";
cache-size = <0x80000>;
- cache-line-size = <128>;
+ cache-line-size = <64>;
cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set
cache-level = <2>;
cache-unified;
@@ -139,7 +139,7 @@
l2_cache_l3: l2-cache-l3 {
compatible = "cache";
cache-size = <0x80000>;
- cache-line-size = <128>;
+ cache-line-size = <64>;
cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set
cache-level = <2>;
cache-unified;
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index a523b519700f..a2b5d6f20f4d 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -18,7 +18,7 @@
#include "aes-ce-setkey.h"
-MODULE_IMPORT_NS(CRYPTO_INTERNAL);
+MODULE_IMPORT_NS("CRYPTO_INTERNAL");
static int num_rounds(struct crypto_aes_ctx *ctx)
{
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index a147e847a5a1..b0150999743f 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -1048,7 +1048,7 @@ unregister_ciphers:
#ifdef USE_V8_CRYPTO_EXTENSIONS
module_cpu_feature_match(AES, aes_init);
-EXPORT_SYMBOL_NS(ce_aes_mac_update, CRYPTO_INTERNAL);
+EXPORT_SYMBOL_NS(ce_aes_mac_update, "CRYPTO_INTERNAL");
#else
module_init(aes_init);
EXPORT_SYMBOL(neon_aes_ecb_encrypt);
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 201a46efd918..cbbf70e0f204 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -44,6 +44,8 @@ cpucap_is_possible(const unsigned int cap)
return IS_ENABLED(CONFIG_ARM64_TLB_RANGE);
case ARM64_HAS_S1POE:
return IS_ENABLED(CONFIG_ARM64_POE);
+ case ARM64_HAS_GCS:
+ return IS_ENABLED(CONFIG_ARM64_GCS);
case ARM64_UNMAP_KERNEL_AT_EL0:
return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
case ARM64_WORKAROUND_843419:
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index b64e49bd9d10..8b4e5a3cd24c 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -847,8 +847,7 @@ static inline bool system_supports_poe(void)
static inline bool system_supports_gcs(void)
{
- return IS_ENABLED(CONFIG_ARM64_GCS) &&
- alternative_has_cap_unlikely(ARM64_HAS_GCS);
+ return alternative_has_cap_unlikely(ARM64_HAS_GCS);
}
static inline bool system_supports_haft(void)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 85ef966c08cd..4ef52d7245bb 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -87,7 +87,7 @@
1 << PMSCR_EL2_PA_SHIFT)
msr_s SYS_PMSCR_EL2, x0 // addresses and physical counter
.Lskip_spe_el2_\@:
- mov x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
+ mov x0, #MDCR_EL2_E2PB_MASK
orr x2, x2, x0 // If we don't have VHE, then
// use EL1&0 translation.
@@ -100,7 +100,7 @@
and x0, x0, TRBIDR_EL1_P
cbnz x0, .Lskip_trace_\@ // If TRBE is available at EL2
- mov x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT)
+ mov x0, #MDCR_EL2_E2TB_MASK
orr x2, x2, x0 // allow the EL1&0 translation
// to own it.
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 1d53022fc7e1..21df8bbd2668 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -7,6 +7,7 @@
#ifndef BUILD_VDSO
#include <linux/compiler.h>
#include <linux/fs.h>
+#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/types.h>
@@ -44,7 +45,7 @@ static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
if (system_supports_mte()) {
if (flags & (MAP_ANONYMOUS | MAP_HUGETLB))
return VM_MTE_ALLOWED;
- if (shmem_file(file))
+ if (shmem_file(file) || is_file_hugepages(file))
return VM_MTE_ALLOWED;
}
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 65f76064c86b..ae990da1eae5 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -114,8 +114,8 @@ SYM_CODE_START_LOCAL(__finalise_el2)
// Use EL2 translations for SPE & TRBE and disable access from EL1
mrs x0, mdcr_el2
- bic x0, x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
- bic x0, x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT)
+ bic x0, x0, #MDCR_EL2_E2PB_MASK
+ bic x0, x0, #MDCR_EL2_E2TB_MASK
msr mdcr_el2, x0
// Transfer the MM state from EL1 to EL2
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
index 7f99723fbb8c..1041bc67a3ee 100644
--- a/arch/arm64/kernel/patching.c
+++ b/arch/arm64/kernel/patching.c
@@ -30,20 +30,17 @@ static bool is_image_text(unsigned long addr)
static void __kprobes *patch_map(void *addr, int fixmap)
{
- unsigned long uintaddr = (uintptr_t) addr;
- bool image = is_image_text(uintaddr);
- struct page *page;
-
- if (image)
- page = phys_to_page(__pa_symbol(addr));
- else if (IS_ENABLED(CONFIG_EXECMEM))
- page = vmalloc_to_page(addr);
- else
- return addr;
-
- BUG_ON(!page);
- return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
- (uintaddr & ~PAGE_MASK));
+ phys_addr_t phys;
+
+ if (is_image_text((unsigned long)addr)) {
+ phys = __pa_symbol(addr);
+ } else {
+ struct page *page = vmalloc_to_page(addr);
+ BUG_ON(!page);
+ phys = page_to_phys(page) + offset_in_page(addr);
+ }
+
+ return (void *)set_fixmap_offset(fixmap, phys);
}
static void __kprobes patch_unmap(int fixmap)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index e4437f62a2cd..f79b0d5f71ac 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -720,6 +720,8 @@ static int fpmr_set(struct task_struct *target, const struct user_regset *regset
if (!system_supports_fpmr())
return -EINVAL;
+ fpmr = target->thread.uw.fpmr;
+
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count);
if (ret)
return ret;
@@ -1427,7 +1429,7 @@ static int tagged_addr_ctrl_get(struct task_struct *target,
{
long ctrl = get_tagged_addr_ctrl(target);
- if (IS_ERR_VALUE(ctrl))
+ if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl)))
return ctrl;
return membuf_write(&to, &ctrl, sizeof(ctrl));
@@ -1441,6 +1443,10 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct
int ret;
long ctrl;
+ ctrl = get_tagged_addr_ctrl(target);
+ if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl)))
+ return ctrl;
+
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
if (ret)
return ret;
@@ -1472,6 +1478,8 @@ static int poe_set(struct task_struct *target, const struct
if (!system_supports_poe())
return -EINVAL;
+ ctrl = target->thread.por_el0;
+
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
if (ret)
return ret;
@@ -1483,6 +1491,22 @@ static int poe_set(struct task_struct *target, const struct
#endif
#ifdef CONFIG_ARM64_GCS
+static void task_gcs_to_user(struct user_gcs *user_gcs,
+ const struct task_struct *target)
+{
+ user_gcs->features_enabled = target->thread.gcs_el0_mode;
+ user_gcs->features_locked = target->thread.gcs_el0_locked;
+ user_gcs->gcspr_el0 = target->thread.gcspr_el0;
+}
+
+static void task_gcs_from_user(struct task_struct *target,
+ const struct user_gcs *user_gcs)
+{
+ target->thread.gcs_el0_mode = user_gcs->features_enabled;
+ target->thread.gcs_el0_locked = user_gcs->features_locked;
+ target->thread.gcspr_el0 = user_gcs->gcspr_el0;
+}
+
static int gcs_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
@@ -1495,9 +1519,7 @@ static int gcs_get(struct task_struct *target,
if (target == current)
gcs_preserve_current_state();
- user_gcs.features_enabled = target->thread.gcs_el0_mode;
- user_gcs.features_locked = target->thread.gcs_el0_locked;
- user_gcs.gcspr_el0 = target->thread.gcspr_el0;
+ task_gcs_to_user(&user_gcs, target);
return membuf_write(&to, &user_gcs, sizeof(user_gcs));
}
@@ -1513,6 +1535,8 @@ static int gcs_set(struct task_struct *target, const struct
if (!system_supports_gcs())
return -EINVAL;
+ task_gcs_to_user(&user_gcs, target);
+
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1);
if (ret)
return ret;
@@ -1520,9 +1544,7 @@ static int gcs_set(struct task_struct *target, const struct
if (user_gcs.features_enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
return -EINVAL;
- target->thread.gcs_el0_mode = user_gcs.features_enabled;
- target->thread.gcs_el0_locked = user_gcs.features_locked;
- target->thread.gcspr_el0 = user_gcs.gcspr_el0;
+ task_gcs_from_user(target, &user_gcs);
return 0;
}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 14ac6fdb872b..99ea26d400ff 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -36,15 +36,8 @@
#include <asm/traps.h>
#include <asm/vdso.h>
-#ifdef CONFIG_ARM64_GCS
#define GCS_SIGNAL_CAP(addr) (((unsigned long)addr) & GCS_CAP_ADDR_MASK)
-static bool gcs_signal_cap_valid(u64 addr, u64 val)
-{
- return val == GCS_SIGNAL_CAP(addr);
-}
-#endif
-
/*
* Do a signal return; undo the signal stack. These are aligned to 128-bit.
*/
@@ -1062,8 +1055,7 @@ static int restore_sigframe(struct pt_regs *regs,
#ifdef CONFIG_ARM64_GCS
static int gcs_restore_signal(void)
{
- unsigned long __user *gcspr_el0;
- u64 cap;
+ u64 gcspr_el0, cap;
int ret;
if (!system_supports_gcs())
@@ -1072,7 +1064,7 @@ static int gcs_restore_signal(void)
if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE))
return 0;
- gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0);
+ gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
/*
* Ensure that any changes to the GCS done via GCS operations
@@ -1087,22 +1079,23 @@ static int gcs_restore_signal(void)
* then faults will be generated on GCS operations - the main
* concern is to protect GCS pages.
*/
- ret = copy_from_user(&cap, gcspr_el0, sizeof(cap));
+ ret = copy_from_user(&cap, (unsigned long __user *)gcspr_el0,
+ sizeof(cap));
if (ret)
return -EFAULT;
/*
* Check that the cap is the actual GCS before replacing it.
*/
- if (!gcs_signal_cap_valid((u64)gcspr_el0, cap))
+ if (cap != GCS_SIGNAL_CAP(gcspr_el0))
return -EINVAL;
/* Invalidate the token to prevent reuse */
- put_user_gcs(0, (__user void*)gcspr_el0, &ret);
+ put_user_gcs(0, (unsigned long __user *)gcspr_el0, &ret);
if (ret != 0)
return -EFAULT;
- write_sysreg_s(gcspr_el0 + 1, SYS_GCSPR_EL0);
+ write_sysreg_s(gcspr_el0 + 8, SYS_GCSPR_EL0);
return 0;
}
@@ -1421,7 +1414,7 @@ static int get_sigframe(struct rt_sigframe_user_layout *user,
static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)
{
- unsigned long __user *gcspr_el0;
+ u64 gcspr_el0;
int ret = 0;
if (!system_supports_gcs())
@@ -1434,18 +1427,20 @@ static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)
* We are entering a signal handler, current register state is
* active.
*/
- gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0);
+ gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
/*
* Push a cap and the GCS entry for the trampoline onto the GCS.
*/
- put_user_gcs((unsigned long)sigtramp, gcspr_el0 - 2, &ret);
- put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 1), gcspr_el0 - 1, &ret);
+ put_user_gcs((unsigned long)sigtramp,
+ (unsigned long __user *)(gcspr_el0 - 16), &ret);
+ put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 8),
+ (unsigned long __user *)(gcspr_el0 - 8), &ret);
if (ret != 0)
return ret;
- gcspr_el0 -= 2;
- write_sysreg_s((unsigned long)gcspr_el0, SYS_GCSPR_EL0);
+ gcspr_el0 -= 16;
+ write_sysreg_s(gcspr_el0, SYS_GCSPR_EL0);
return 0;
}
@@ -1462,10 +1457,33 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
struct rt_sigframe_user_layout *user, int usig)
{
__sigrestore_t sigtramp;
+ int err;
+
+ if (ksig->ka.sa.sa_flags & SA_RESTORER)
+ sigtramp = ksig->ka.sa.sa_restorer;
+ else
+ sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
+
+ err = gcs_signal_entry(sigtramp, ksig);
+ if (err)
+ return err;
+
+ /*
+ * We must not fail from this point onwards. We are going to update
+ * registers, including SP, in order to invoke the signal handler. If
+ * we failed and attempted to deliver a nested SIGSEGV to a handler
+ * after that point, the subsequent sigreturn would end up restoring
+ * the (partial) state for the original signal handler.
+ */
regs->regs[0] = usig;
+ if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
+ regs->regs[1] = (unsigned long)&user->sigframe->info;
+ regs->regs[2] = (unsigned long)&user->sigframe->uc;
+ }
regs->sp = (unsigned long)user->sigframe;
regs->regs[29] = (unsigned long)&user->next_frame->fp;
+ regs->regs[30] = (unsigned long)sigtramp;
regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
/*
@@ -1506,14 +1524,7 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
sme_smstop();
}
- if (ksig->ka.sa.sa_flags & SA_RESTORER)
- sigtramp = ksig->ka.sa.sa_restorer;
- else
- sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
-
- regs->regs[30] = (unsigned long)sigtramp;
-
- return gcs_signal_entry(sigtramp, ksig);
+ return 0;
}
static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
@@ -1537,14 +1548,16 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
err |= setup_sigframe(&user, regs, set, &ua_state);
- if (err == 0) {
+ if (ksig->ka.sa.sa_flags & SA_SIGINFO)
+ err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+ if (err == 0)
err = setup_return(regs, ksig, &user, usig);
- if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
- err |= copy_siginfo_to_user(&frame->info, &ksig->info);
- regs->regs[1] = (unsigned long)&frame->info;
- regs->regs[2] = (unsigned long)&frame->uc;
- }
- }
+
+ /*
+ * We must not fail if setup_return() succeeded - see comment at the
+ * beginning of setup_return().
+ */
if (err == 0)
set_handler_user_access_state();
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index caef85462acb..1d9d51d7627f 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -26,7 +26,6 @@ enum kunwind_source {
KUNWIND_SOURCE_CALLER,
KUNWIND_SOURCE_TASK,
KUNWIND_SOURCE_REGS_PC,
- KUNWIND_SOURCE_REGS_LR,
};
union unwind_flags {
@@ -138,8 +137,10 @@ kunwind_recover_return_address(struct kunwind_state *state)
orig_pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
state->common.pc,
(void *)state->common.fp);
- if (WARN_ON_ONCE(state->common.pc == orig_pc))
+ if (state->common.pc == orig_pc) {
+ WARN_ON_ONCE(state->task == current);
return -EINVAL;
+ }
state->common.pc = orig_pc;
state->flags.fgraph = 1;
}
@@ -178,23 +179,8 @@ int kunwind_next_regs_pc(struct kunwind_state *state)
state->regs = regs;
state->common.pc = regs->pc;
state->common.fp = regs->regs[29];
- state->source = KUNWIND_SOURCE_REGS_PC;
- return 0;
-}
-
-static __always_inline int
-kunwind_next_regs_lr(struct kunwind_state *state)
-{
- /*
- * The stack for the regs was consumed by kunwind_next_regs_pc(), so we
- * cannot consume that again here, but we know the regs are safe to
- * access.
- */
- state->common.pc = state->regs->regs[30];
- state->common.fp = state->regs->regs[29];
state->regs = NULL;
- state->source = KUNWIND_SOURCE_REGS_LR;
-
+ state->source = KUNWIND_SOURCE_REGS_PC;
return 0;
}
@@ -215,12 +201,12 @@ kunwind_next_frame_record_meta(struct kunwind_state *state)
case FRAME_META_TYPE_FINAL:
if (meta == &task_pt_regs(tsk)->stackframe)
return -ENOENT;
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(tsk == current);
return -EINVAL;
case FRAME_META_TYPE_PT_REGS:
return kunwind_next_regs_pc(state);
default:
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(tsk == current);
return -EINVAL;
}
}
@@ -274,11 +260,8 @@ kunwind_next(struct kunwind_state *state)
case KUNWIND_SOURCE_FRAME:
case KUNWIND_SOURCE_CALLER:
case KUNWIND_SOURCE_TASK:
- case KUNWIND_SOURCE_REGS_LR:
- err = kunwind_next_frame_record(state);
- break;
case KUNWIND_SOURCE_REGS_PC:
- err = kunwind_next_regs_lr(state);
+ err = kunwind_next_frame_record(state);
break;
default:
err = -EINVAL;
@@ -436,7 +419,6 @@ static const char *state_source_string(const struct kunwind_state *state)
case KUNWIND_SOURCE_CALLER: return "C";
case KUNWIND_SOURCE_TASK: return "T";
case KUNWIND_SOURCE_REGS_PC: return "P";
- case KUNWIND_SOURCE_REGS_LR: return "L";
default: return "U";
}
}
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 8c5d7990e5b3..3d7eb395e33d 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -739,8 +739,15 @@ static u64 compute_par_s12(struct kvm_vcpu *vcpu, u64 s1_par,
final_attr = s1_parattr;
break;
default:
- /* MemAttr[2]=0, Device from S2 */
- final_attr = s2_memattr & GENMASK(1,0) << 2;
+ /*
+ * MemAttr[2]=0, Device from S2.
+ *
+ * FWB does not influence the way that stage 1
+ * memory types and attributes are combined
+ * with stage 2 Device type and attributes.
+ */
+ final_attr = min(s2_memattr_to_attr(s2_memattr),
+ s1_parattr);
}
} else {
/* Combination of R_HMNDG, R_TNHFM and R_GQFSF */
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 01616c39a810..071993c16de8 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -126,7 +126,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
/* Trap SPE */
if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer), feature_ids)) {
mdcr_set |= MDCR_EL2_TPMS;
- mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+ mdcr_clear |= MDCR_EL2_E2PB_MASK;
}
/* Trap Trace Filter */
@@ -143,7 +143,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
/* Trap External Trace */
if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids))
- mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT;
+ mdcr_clear |= MDCR_EL2_E2TB_MASK;
vcpu->arch.mdcr_el2 |= mdcr_set;
vcpu->arch.mdcr_el2 &= ~mdcr_clear;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 83c6b4a07ef5..e2a5c2918d9e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2618,7 +2618,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 |
ID_AA64MMFR0_EL1_TGRAN4_2 |
ID_AA64MMFR0_EL1_TGRAN64_2 |
- ID_AA64MMFR0_EL1_TGRAN16_2)),
+ ID_AA64MMFR0_EL1_TGRAN16_2 |
+ ID_AA64MMFR0_EL1_ASIDBITS)),
ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 |
ID_AA64MMFR1_EL1_HCX |
ID_AA64MMFR1_EL1_TWED |
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index f4c4494645c3..fb96802799c6 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -608,12 +608,22 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its,
lockdep_assert_held(&its->its_lock);
vgic_get_irq_kref(irq);
+ old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT);
+
+ /*
+ * Put the reference taken on @irq if the store fails. Intentionally do
+ * not return the error as the translation cache is best effort.
+ */
+ if (xa_is_err(old)) {
+ vgic_put_irq(kvm, irq);
+ return;
+ }
+
/*
* We could have raced with another CPU caching the same
* translation behind our back, ensure we don't leak a
* reference if that is the case.
*/
- old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT);
if (old)
vgic_put_irq(kvm, old);
}
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 188197590fc9..b2ac06246327 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -32,9 +32,9 @@ static unsigned long nr_pinned_asids;
static unsigned long *pinned_asid_map;
#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
-#define ASID_FIRST_VERSION (1UL << asid_bits)
+#define ASID_FIRST_VERSION (1UL << 16)
-#define NUM_USER_ASIDS ASID_FIRST_VERSION
+#define NUM_USER_ASIDS (1UL << asid_bits)
#define ctxid2asid(asid) ((asid) & ~ASID_MASK)
#define asid2ctxid(asid, genid) ((asid) | (genid))
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 87b3f1a25535..a86c897017df 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -30,11 +30,13 @@ void copy_highpage(struct page *to, struct page *from)
if (!system_supports_mte())
return;
- if (folio_test_hugetlb(src) &&
- folio_test_hugetlb_mte_tagged(src)) {
- if (!folio_try_hugetlb_mte_tagging(dst))
+ if (folio_test_hugetlb(src)) {
+ if (!folio_test_hugetlb_mte_tagged(src) ||
+ from != folio_page(src, 0))
return;
+ WARN_ON_ONCE(!folio_try_hugetlb_mte_tagging(dst));
+
/*
* Populate tags for all subpages.
*
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d21f67d67cf5..ccdef53872a0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -117,15 +117,6 @@ static void __init arch_reserve_crashkernel(void)
static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
{
- /**
- * Information we get from firmware (e.g. DT dma-ranges) describe DMA
- * bus constraints. Devices using DMA might have their own limitations.
- * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
- * DMA zone on platforms that have RAM there.
- */
- if (memblock_start_of_DRAM() < U32_MAX)
- zone_limit = min(zone_limit, U32_MAX);
-
return min(zone_limit, memblock_end_of_DRAM() - 1) + 1;
}
@@ -141,6 +132,14 @@ static void __init zone_sizes_init(void)
acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address();
dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL);
zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit);
+ /*
+ * Information we get from firmware (e.g. DT dma-ranges) describe DMA
+ * bus constraints. Devices using DMA might have their own limitations.
+ * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
+ * DMA zone on platforms that have RAM there.
+ */
+ if (memblock_start_of_DRAM() < U32_MAX)
+ zone_dma_limit = min(zone_dma_limit, U32_MAX);
arm64_dma_phys_limit = max_zone_phys(zone_dma_limit);
max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile
index 92d005958dfb..ff172cbe5881 100644
--- a/arch/hexagon/Makefile
+++ b/arch/hexagon/Makefile
@@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y)
TIR_NAME := r19
KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__
KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME)
+
+# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0
+# https://github.com/llvm/llvm-project/issues/99714
+ifneq ($(call clang-min-version, 190100),y)
+KBUILD_CFLAGS += -mllvm -hexagon-cext=false
+endif
diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index b837c65a4894..c8e4057734d0 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -24,6 +24,16 @@ static inline int prepare_hugepage_range(struct file *file,
return 0;
}
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
+static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long sz)
+{
+ pte_t clear;
+
+ pte_val(clear) = (unsigned long)invalid_pte_table;
+ set_pte_at(mm, addr, ptep, clear);
+}
+
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index 944482063f14..3089785ca97e 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -683,7 +683,17 @@ DEF_EMIT_REG2I16_FORMAT(blt, blt_op)
DEF_EMIT_REG2I16_FORMAT(bge, bge_op)
DEF_EMIT_REG2I16_FORMAT(bltu, bltu_op)
DEF_EMIT_REG2I16_FORMAT(bgeu, bgeu_op)
-DEF_EMIT_REG2I16_FORMAT(jirl, jirl_op)
+
+static inline void emit_jirl(union loongarch_instruction *insn,
+ enum loongarch_gpr rd,
+ enum loongarch_gpr rj,
+ int offset)
+{
+ insn->reg2i16_format.opcode = jirl_op;
+ insn->reg2i16_format.immediate = offset;
+ insn->reg2i16_format.rd = rd;
+ insn->reg2i16_format.rj = rj;
+}
#define DEF_EMIT_REG2BSTRD_FORMAT(NAME, OP) \
static inline void emit_##NAME(union loongarch_instruction *insn, \
diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
index 2bf86aeda874..de21e72759ee 100644
--- a/arch/loongarch/kernel/efi.c
+++ b/arch/loongarch/kernel/efi.c
@@ -95,7 +95,7 @@ static void __init init_screen_info(void)
memset(si, 0, sizeof(*si));
early_memunmap(si, sizeof(*si));
- memblock_reserve(screen_info.lfb_base, screen_info.lfb_size);
+ memblock_reserve(__screen_info_lfb_base(&screen_info), screen_info.lfb_size);
}
void __init efi_init(void)
diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c
index 3050329556d1..14d7d700bcb9 100644
--- a/arch/loongarch/kernel/inst.c
+++ b/arch/loongarch/kernel/inst.c
@@ -332,7 +332,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm)
return INSN_BREAK;
}
- emit_jirl(&insn, rj, rd, imm >> 2);
+ emit_jirl(&insn, rd, rj, imm >> 2);
return insn.word;
}
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 5d59e9ce2772..fbf747447f13 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -82,7 +82,7 @@ void show_ipi_list(struct seq_file *p, int prec)
for (i = 0; i < NR_IPI; i++) {
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : "");
for_each_online_cpu(cpu)
- seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).ipi_irqs[i]);
+ seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, cpu).ipi_irqs[i], 10);
seq_printf(p, " LoongArch %d %s\n", i + 1, ipi_types[i]);
}
}
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index 69f3e3782cc9..a7893bd01e73 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -156,7 +156,7 @@ static int kvm_handle_csr(struct kvm_vcpu *vcpu, larch_inst inst)
int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu)
{
- int ret;
+ int idx, ret;
unsigned long *val;
u32 addr, rd, rj, opcode;
@@ -167,7 +167,6 @@ int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu)
rj = inst.reg2_format.rj;
opcode = inst.reg2_format.opcode;
addr = vcpu->arch.gprs[rj];
- ret = EMULATE_DO_IOCSR;
run->iocsr_io.phys_addr = addr;
run->iocsr_io.is_write = 0;
val = &vcpu->arch.gprs[rd];
@@ -207,20 +206,28 @@ int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu)
}
if (run->iocsr_io.is_write) {
- if (!kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val))
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ if (ret == 0)
ret = EMULATE_DONE;
- else
+ else {
+ ret = EMULATE_DO_IOCSR;
/* Save data and let user space to write it */
memcpy(run->iocsr_io.data, val, run->iocsr_io.len);
-
+ }
trace_kvm_iocsr(KVM_TRACE_IOCSR_WRITE, run->iocsr_io.len, addr, val);
} else {
- if (!kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val))
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+ ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ if (ret == 0)
ret = EMULATE_DONE;
- else
+ else {
+ ret = EMULATE_DO_IOCSR;
/* Save register id for iocsr read completion */
vcpu->arch.io_gpr = rd;
-
+ }
trace_kvm_iocsr(KVM_TRACE_IOCSR_READ, run->iocsr_io.len, addr, NULL);
}
@@ -359,7 +366,7 @@ static int kvm_handle_gspr(struct kvm_vcpu *vcpu)
int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst)
{
- int ret;
+ int idx, ret;
unsigned int op8, opcode, rd;
struct kvm_run *run = vcpu->run;
@@ -464,8 +471,10 @@ int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst)
* it need not return to user space to handle the mmio
* exception.
*/
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, vcpu->arch.badv,
run->mmio.len, &vcpu->arch.gprs[rd]);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (!ret) {
update_pc(&vcpu->arch);
vcpu->mmio_needed = 0;
@@ -531,7 +540,7 @@ int kvm_complete_mmio_read(struct kvm_vcpu *vcpu, struct kvm_run *run)
int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst)
{
- int ret;
+ int idx, ret;
unsigned int rd, op8, opcode;
unsigned long curr_pc, rd_val = 0;
struct kvm_run *run = vcpu->run;
@@ -631,7 +640,9 @@ int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst)
* it need not return to user space to handle the mmio
* exception.
*/
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, vcpu->arch.badv, run->mmio.len, data);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (!ret)
return EMULATE_DONE;
diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index a233a323e295..93f4acd44523 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -98,7 +98,7 @@ static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int
static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
{
- int i, ret;
+ int i, idx, ret;
uint32_t val = 0, mask = 0;
/*
@@ -107,7 +107,9 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
*/
if ((data >> 27) & 0xf) {
/* Read the old val */
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (unlikely(ret)) {
kvm_err("%s: : read date from addr %llx failed\n", __func__, addr);
return ret;
@@ -121,7 +123,9 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
val &= mask;
}
val |= ((uint32_t)(data >> 32) & ~mask);
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (unlikely(ret))
kvm_err("%s: : write date to addr %llx failed\n", __func__, addr);
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index cab1818be68d..d18a4a270415 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -240,7 +240,7 @@ static void kvm_late_check_requests(struct kvm_vcpu *vcpu)
*/
static int kvm_enter_guest_check(struct kvm_vcpu *vcpu)
{
- int ret;
+ int idx, ret;
/*
* Check conditions before entering the guest
@@ -249,7 +249,9 @@ static int kvm_enter_guest_check(struct kvm_vcpu *vcpu)
if (ret < 0)
return ret;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_check_requests(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
}
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index dd350cba1252..ea357a3edc09 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -181,13 +181,13 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call)
/* Set return value */
emit_insn(ctx, addiw, LOONGARCH_GPR_A0, regmap[BPF_REG_0], 0);
/* Return to the caller */
- emit_insn(ctx, jirl, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0);
+ emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0);
} else {
/*
* Call the next bpf prog and skip the first instruction
* of TCC initialization.
*/
- emit_insn(ctx, jirl, LOONGARCH_GPR_T3, LOONGARCH_GPR_ZERO, 1);
+ emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 1);
}
}
@@ -904,7 +904,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
return ret;
move_addr(ctx, t1, func_addr);
- emit_insn(ctx, jirl, t1, LOONGARCH_GPR_RA, 0);
+ emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0);
move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0);
break;
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 45ddbaa6c123..dae856fb3e5b 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -749,7 +749,7 @@ static void bridge_remove(struct platform_device *pdev)
static struct platform_driver bridge_driver = {
.probe = bridge_probe,
- .remove_new = bridge_remove,
+ .remove = bridge_remove,
.driver = {
.name = "xtalk-bridge",
}
diff --git a/arch/nios2/kernel/cpuinfo.c b/arch/nios2/kernel/cpuinfo.c
index 338849c430a5..7b1e8f9128e9 100644
--- a/arch/nios2/kernel/cpuinfo.c
+++ b/arch/nios2/kernel/cpuinfo.c
@@ -143,11 +143,11 @@ static int show_cpuinfo(struct seq_file *m, void *v)
" DIV:\t\t%s\n"
" BMX:\t\t%s\n"
" CDX:\t\t%s\n",
- cpuinfo.has_mul ? "yes" : "no",
- cpuinfo.has_mulx ? "yes" : "no",
- cpuinfo.has_div ? "yes" : "no",
- cpuinfo.has_bmx ? "yes" : "no",
- cpuinfo.has_cdx ? "yes" : "no");
+ str_yes_no(cpuinfo.has_mul),
+ str_yes_no(cpuinfo.has_mulx),
+ str_yes_no(cpuinfo.has_div),
+ str_yes_no(cpuinfo.has_bmx),
+ str_yes_no(cpuinfo.has_cdx));
seq_printf(m,
"Icache:\t\t%ukB, line length: %u\n",
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index 440711d7bf40..ce6f2b08a35e 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -239,6 +239,8 @@ handler: ;\
/* =====================================================[ exceptions] === */
+ __REF
+
/* ---[ 0x100: RESET exception ]----------------------------------------- */
EXCEPTION_ENTRY(_tng_kernel_start)
diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index 439e00f81e5d..bd760066f1cd 100644
--- a/arch/openrisc/kernel/head.S
+++ b/arch/openrisc/kernel/head.S
@@ -26,15 +26,15 @@
#include <asm/asm-offsets.h>
#include <linux/of_fdt.h>
-#define tophys(rd,rs) \
- l.movhi rd,hi(-KERNELBASE) ;\
+#define tophys(rd,rs) \
+ l.movhi rd,hi(-KERNELBASE) ;\
l.add rd,rd,rs
-#define CLEAR_GPR(gpr) \
+#define CLEAR_GPR(gpr) \
l.movhi gpr,0x0
-#define LOAD_SYMBOL_2_GPR(gpr,symbol) \
- l.movhi gpr,hi(symbol) ;\
+#define LOAD_SYMBOL_2_GPR(gpr,symbol) \
+ l.movhi gpr,hi(symbol) ;\
l.ori gpr,gpr,lo(symbol)
@@ -326,21 +326,21 @@
l.addi r1,r1,-(INT_FRAME_SIZE) ;\
/* r1 is KSP, r30 is __pa(KSP) */ ;\
tophys (r30,r1) ;\
- l.sw PT_GPR12(r30),r12 ;\
+ l.sw PT_GPR12(r30),r12 ;\
l.mfspr r12,r0,SPR_EPCR_BASE ;\
l.sw PT_PC(r30),r12 ;\
l.mfspr r12,r0,SPR_ESR_BASE ;\
l.sw PT_SR(r30),r12 ;\
/* save r31 */ ;\
EXCEPTION_T_LOAD_GPR30(r12) ;\
- l.sw PT_GPR30(r30),r12 ;\
+ l.sw PT_GPR30(r30),r12 ;\
/* save r10 as was prior to exception */ ;\
EXCEPTION_T_LOAD_GPR10(r12) ;\
- l.sw PT_GPR10(r30),r12 ;\
- /* save PT_SP as was prior to exception */ ;\
+ l.sw PT_GPR10(r30),r12 ;\
+ /* save PT_SP as was prior to exception */ ;\
EXCEPTION_T_LOAD_SP(r12) ;\
l.sw PT_SP(r30),r12 ;\
- l.sw PT_GPR13(r30),r13 ;\
+ l.sw PT_GPR13(r30),r13 ;\
/* --> */ ;\
/* save exception r4, set r4 = EA */ ;\
l.sw PT_GPR4(r30),r4 ;\
@@ -357,6 +357,8 @@
/* =====================================================[ exceptions] === */
+ __HEAD
+
/* ---[ 0x100: RESET exception ]----------------------------------------- */
.org 0x100
/* Jump to .init code at _start which lives in the .head section
@@ -394,7 +396,7 @@ _dispatch_do_ipage_fault:
.org 0x500
EXCEPTION_HANDLE(_timer_handler)
-/* ---[ 0x600: Alignment exception ]-------------------------------------- */
+/* ---[ 0x600: Alignment exception ]------------------------------------- */
.org 0x600
EXCEPTION_HANDLE(_alignment_handler)
@@ -424,7 +426,7 @@ _dispatch_do_ipage_fault:
.org 0xc00
EXCEPTION_HANDLE(_sys_call_handler)
-/* ---[ 0xd00: Floating point exception ]--------------------------------- */
+/* ---[ 0xd00: Floating point exception ]-------------------------------- */
.org 0xd00
EXCEPTION_HANDLE(_fpe_trap_handler)
@@ -506,10 +508,10 @@ _dispatch_do_ipage_fault:
/* .text*/
-/* This early stuff belongs in HEAD, but some of the functions below definitely
+/* This early stuff belongs in the .init.text section, but some of the functions below definitely
* don't... */
- __HEAD
+ __INIT
.global _start
_start:
/* Init r0 to zero as per spec */
@@ -816,7 +818,7 @@ secondary_start:
#endif
-/* ========================================[ cache ]=== */
+/* ==========================================================[ cache ]=== */
/* alignment here so we don't change memory offsets with
* memory controller defined
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index bc1306047837..049bff45f612 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -50,6 +50,7 @@ SECTIONS
.text : AT(ADDR(.text) - LOAD_OFFSET)
{
_stext = .;
+ HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
@@ -83,8 +84,6 @@ SECTIONS
. = ALIGN(PAGE_SIZE);
__init_begin = .;
- HEAD_TEXT_SECTION
-
/* Page aligned */
INIT_TEXT_SECTION(PAGE_SIZE)
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index 57ded82c2840..e8b3f67bf3f5 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -208,6 +208,7 @@ CONFIG_FB_ATY=y
CONFIG_FB_ATY_CT=y
CONFIG_FB_ATY_GX=y
CONFIG_FB_3DFX=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
# CONFIG_VGA_CONSOLE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 4d77e17541e9..ca0c90e95837 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -716,6 +716,7 @@ CONFIG_FB_TRIDENT=m
CONFIG_FB_SM501=m
CONFIG_FB_IBM_GXT4500=y
CONFIG_LCD_PLATFORM=m
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
CONFIG_LOGO=y
diff --git a/arch/powerpc/crypto/vmx.c b/arch/powerpc/crypto/vmx.c
index 7eb713cc87c8..0b725e826388 100644
--- a/arch/powerpc/crypto/vmx.c
+++ b/arch/powerpc/crypto/vmx.c
@@ -74,4 +74,4 @@ MODULE_DESCRIPTION("IBM VMX cryptographic acceleration instructions "
"support on Power 8");
MODULE_LICENSE("GPL");
MODULE_VERSION("1.0.0");
-MODULE_IMPORT_NS(CRYPTO_INTERNAL);
+MODULE_IMPORT_NS("CRYPTO_INTERNAL");
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index f381b177ea06..0b6365d85d11 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -464,7 +464,43 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+/*
+ * During mmap() paste address, mapping VMA is saved in VAS window
+ * struct which is used to unmap during migration if the window is
+ * still open. But the user space can remove this mapping with
+ * munmap() before closing the window and the VMA address will
+ * be invalid. Set VAS window VMA to NULL in this function which
+ * is called before VMA free.
+ */
+static void vas_mmap_close(struct vm_area_struct *vma)
+{
+ struct file *fp = vma->vm_file;
+ struct coproc_instance *cp_inst = fp->private_data;
+ struct vas_window *txwin;
+
+ /* Should not happen */
+ if (!cp_inst || !cp_inst->txwin) {
+ pr_err("No attached VAS window for the paste address mmap\n");
+ return;
+ }
+
+ txwin = cp_inst->txwin;
+ /*
+ * task_ref.vma is set in coproc_mmap() during mmap paste
+ * address. So it has to be the same VMA that is getting freed.
+ */
+ if (WARN_ON(txwin->task_ref.vma != vma)) {
+ pr_err("Invalid paste address mmaping\n");
+ return;
+ }
+
+ mutex_lock(&txwin->task_ref.mmap_mutex);
+ txwin->task_ref.vma = NULL;
+ mutex_unlock(&txwin->task_ref.mmap_mutex);
+}
+
static const struct vm_operations_struct vas_vm_ops = {
+ .close = vas_mmap_close,
.fault = vas_mmap_fault,
};
diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h
index 7388edd88986..d08bf7fb3aee 100644
--- a/arch/riscv/include/asm/kfence.h
+++ b/arch/riscv/include/asm/kfence.h
@@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
else
set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
- flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ preempt_disable();
+ local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ preempt_enable();
return true;
}
diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c
index 6eee6f736f68..654ed159c830 100644
--- a/arch/riscv/kernel/jump_label.c
+++ b/arch/riscv/kernel/jump_label.c
@@ -36,9 +36,15 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
insn = RISCV_INSN_NOP;
}
- mutex_lock(&text_mutex);
- patch_insn_write(addr, &insn, sizeof(insn));
- mutex_unlock(&text_mutex);
+ if (early_boot_irqs_disabled) {
+ riscv_patch_in_stop_machine = 1;
+ patch_insn_write(addr, &insn, sizeof(insn));
+ riscv_patch_in_stop_machine = 0;
+ } else {
+ mutex_lock(&text_mutex);
+ patch_insn_write(addr, &insn, sizeof(insn));
+ mutex_unlock(&text_mutex);
+ }
return true;
}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 016b48fcd6f2..45010e71df86 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -227,7 +227,7 @@ static void __init init_resources(void)
static void __init parse_dtb(void)
{
/* Early scan of device tree from init memory */
- if (early_init_dt_scan(dtb_early_va, __pa(dtb_early_va))) {
+ if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) {
const char *name = of_flat_dt_get_machine_name();
if (name) {
diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index dcced4db7fe8..19afd1f23537 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -590,7 +590,7 @@ void kvm_riscv_aia_enable(void)
csr_set(CSR_HIE, BIT(IRQ_S_GEXT));
/* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */
if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF))
- csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF));
+ csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF));
}
void kvm_riscv_aia_disable(void)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 0e8c20adcd98..fc53ce748c80 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1566,7 +1566,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
pmd_clear(pmd);
}
-static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap)
{
struct page *page = pud_page(*pud);
struct ptdesc *ptdesc = page_ptdesc(page);
@@ -1579,7 +1579,8 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
return;
}
- pagetable_pmd_dtor(ptdesc);
+ if (!is_vmemmap)
+ pagetable_pmd_dtor(ptdesc);
if (PageReserved(page))
free_reserved_page(page);
else
@@ -1703,7 +1704,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un
remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap);
if (pgtable_l4_enabled)
- free_pmd_table(pmd_base, pudp);
+ free_pmd_table(pmd_base, pudp, is_vmemmap);
}
}
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index abe6e6c0ab98..6087d38c7235 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -234,6 +234,8 @@ static unsigned long get_vmem_size(unsigned long identity_size,
vsize = round_up(SZ_2G + max_mappable, rte_size) +
round_up(vmemmap_size, rte_size) +
FIXMAP_SIZE + MODULES_LEN + KASLR_LEN;
+ if (IS_ENABLED(CONFIG_KMSAN))
+ vsize += MODULES_LEN * 2;
return size_add(vsize, vmalloc_size);
}
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 145035f84a0e..3fa28db2fe59 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -306,7 +306,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e
pages++;
}
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_4K, pages);
}
@@ -339,7 +339,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
}
pgtable_pte_populate(pmd, addr, next, mode);
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_1M, pages);
}
@@ -372,7 +372,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
}
pgtable_pmd_populate(pud, addr, next, mode);
}
- if (mode == POPULATE_DIRECT)
+ if (mode == POPULATE_IDENTITY)
update_page_count(PG_DIRECT_MAP_2G, pages);
}
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 8cc02d6e0d0f..9c46b1b630b1 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -1168,4 +1168,4 @@ MODULE_ALIAS_CRYPTO("aes-all");
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
MODULE_LICENSE("GPL");
-MODULE_IMPORT_NS(CRYPTO_INTERNAL);
+MODULE_IMPORT_NS("CRYPTO_INTERNAL");
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index edbb52ce3f1e..7d12a1305fc9 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \
if (len >= sizeof(_value)) \
return -E2BIG; \
len = strscpy(_value, buf, sizeof(_value)); \
- if (len < 0) \
+ if ((ssize_t)len < 0) \
return len; \
strim(_value); \
return len; \
diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c
index 1dea43381b5a..2b51ad9d5586 100644
--- a/arch/sh/drivers/push-switch.c
+++ b/arch/sh/drivers/push-switch.c
@@ -110,7 +110,7 @@ static void switch_drv_remove(struct platform_device *pdev)
static struct platform_driver switch_driver = {
.probe = switch_drv_probe,
- .remove_new = switch_drv_remove,
+ .remove = switch_drv_remove,
.driver = {
.name = DRV_NAME,
},
diff --git a/arch/sparc/include/asm/parport_64.h b/arch/sparc/include/asm/parport_64.h
index 4f530a270760..3068809ef9ad 100644
--- a/arch/sparc/include/asm/parport_64.h
+++ b/arch/sparc/include/asm/parport_64.h
@@ -243,7 +243,7 @@ static struct platform_driver ecpp_driver = {
.of_match_table = ecpp_match,
},
.probe = ecpp_probe,
- .remove_new = ecpp_remove,
+ .remove = ecpp_remove,
};
static int parport_pc_find_nonpci_ports(int autoirq, int autodma)
diff --git a/arch/sparc/kernel/chmc.c b/arch/sparc/kernel/chmc.c
index e02074062001..d4c74d6b2e1b 100644
--- a/arch/sparc/kernel/chmc.c
+++ b/arch/sparc/kernel/chmc.c
@@ -814,7 +814,7 @@ static struct platform_driver us3mc_driver = {
.of_match_table = us3mc_match,
},
.probe = us3mc_probe,
- .remove_new = us3mc_remove,
+ .remove = us3mc_remove,
};
static inline bool us3mc_platform(void)
diff --git a/arch/um/drivers/rtc_kern.c b/arch/um/drivers/rtc_kern.c
index 3a1582219c4b..134a58f93c85 100644
--- a/arch/um/drivers/rtc_kern.c
+++ b/arch/um/drivers/rtc_kern.c
@@ -176,7 +176,7 @@ static void uml_rtc_remove(struct platform_device *pdev)
static struct platform_driver uml_rtc_driver = {
.probe = uml_rtc_probe,
- .remove_new = uml_rtc_remove,
+ .remove = uml_rtc_remove,
.driver = {
.name = "uml-rtc",
},
diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index cc3be48a9d6e..65df43fa9be5 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -1465,7 +1465,7 @@ static int virtio_uml_resume(struct platform_device *pdev)
static struct platform_driver virtio_uml_driver = {
.probe = virtio_uml_probe,
- .remove_new = virtio_uml_remove,
+ .remove = virtio_uml_remove,
.driver = {
.name = "virtio-uml",
.of_match_table = virtio_uml_match,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bb284aff7bfd..99c590da0ae2 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -429,6 +429,16 @@ static struct event_constraint intel_lnc_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+static struct extra_reg intel_lnc_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0xfffffffffffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0xfffffffffffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE),
+ INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE),
+ INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0xf, FE),
+ INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE),
+ EVENT_EXTRA_END
+};
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
@@ -6422,7 +6432,7 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu)
intel_pmu_init_glc(pmu);
hybrid(pmu, event_constraints) = intel_lnc_event_constraints;
hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints;
- hybrid(pmu, extra_regs) = intel_rwc_extra_regs;
+ hybrid(pmu, extra_regs) = intel_lnc_extra_regs;
}
static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
@@ -7135,6 +7145,7 @@ __init int intel_pmu_init(void)
case INTEL_METEORLAKE:
case INTEL_METEORLAKE_L:
+ case INTEL_ARROWLAKE_U:
intel_pmu_init_hybrid(hybrid_big_small);
x86_pmu.pebs_latency_data = cmt_latency_data;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8afc4ad3cd16..6ba6549f26fa 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1489,7 +1489,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
* hence we need to drain when changing said
* size.
*/
- intel_pmu_drain_large_pebs(cpuc);
+ intel_pmu_drain_pebs_buffer();
adaptive_pebs_record_size_update();
wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg);
cpuc->active_pebs_data_cfg = pebs_data_cfg;
@@ -2517,6 +2517,7 @@ void __init intel_ds_init(void)
x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
+ case 6:
case 5:
x86_pmu.pebs_ept = 1;
fallthrough;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index d98fac567684..e7aba7349231 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1910,6 +1910,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init),
X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init),
X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init),
+ X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &gnr_uncore_init),
{},
};
MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 17b6590748c0..645aa360628d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -452,6 +452,7 @@
#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */
#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */
#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
+#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */
/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 6f82e75b6149..4b804531b03c 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -36,10 +36,12 @@
#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4
#ifdef CONFIG_X86_64
-#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW5 /* Saved Dirty bit */
+#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW5 /* Saved Dirty bit (leaf) */
+#define _PAGE_BIT_NOPTISHADOW _PAGE_BIT_SOFTW5 /* No PTI shadow (root PGD) */
#else
/* Shared with _PAGE_BIT_UFFD_WP which is not supported on 32 bit */
-#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW2 /* Saved Dirty bit */
+#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW2 /* Saved Dirty bit (leaf) */
+#define _PAGE_BIT_NOPTISHADOW _PAGE_BIT_SOFTW2 /* No PTI shadow (root PGD) */
#endif
/* If _PAGE_BIT_PRESENT is clear, we use these: */
@@ -139,6 +141,8 @@
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
+#define _PAGE_NOPTISHADOW (_AT(pteval_t, 1) << _PAGE_BIT_NOPTISHADOW)
+
/*
* Set of bits not changed in pte_modify. The pte's
* protection key is treated like _PAGE_RW, for
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0975815980c..20e6009381ed 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -230,6 +230,8 @@ static inline unsigned long long l1tf_pfn_limit(void)
return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT);
}
+void init_cpu_devs(void);
+void get_cpu_vendor(struct cpuinfo_x86 *c);
extern void early_cpu_init(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 125c407e2abe..41502bd2afd6 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -65,4 +65,19 @@
extern bool __static_call_fixup(void *tramp, u8 op, void *dest);
+extern void __static_call_update_early(void *tramp, void *func);
+
+#define static_call_update_early(name, _func) \
+({ \
+ typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \
+ if (static_call_initialized) { \
+ __static_call_update(&STATIC_CALL_KEY(name), \
+ STATIC_CALL_TRAMP_ADDR(name), __F);\
+ } else { \
+ WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \
+ __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\
+ __F); \
+ } \
+})
+
#endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
index ab7382f92aff..96bda43538ee 100644
--- a/arch/x86/include/asm/sync_core.h
+++ b/arch/x86/include/asm/sync_core.h
@@ -8,7 +8,7 @@
#include <asm/special_insns.h>
#ifdef CONFIG_X86_32
-static inline void iret_to_self(void)
+static __always_inline void iret_to_self(void)
{
asm volatile (
"pushfl\n\t"
@@ -19,7 +19,7 @@ static inline void iret_to_self(void)
: ASM_CALL_CONSTRAINT : : "memory");
}
#else
-static inline void iret_to_self(void)
+static __always_inline void iret_to_self(void)
{
unsigned int tmp;
@@ -55,7 +55,7 @@ static inline void iret_to_self(void)
* Like all of Linux's memory ordering operations, this is a
* compiler barrier as well.
*/
-static inline void sync_core(void)
+static __always_inline void sync_core(void)
{
/*
* The SERIALIZE instruction is the most straightforward way to
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index a2dd24947eb8..97771b9d33af 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -39,9 +39,11 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/pgtable.h>
+#include <linux/instrumentation.h>
#include <trace/events/xen.h>
+#include <asm/alternative.h>
#include <asm/page.h>
#include <asm/smap.h>
#include <asm/nospec-branch.h>
@@ -86,11 +88,20 @@ struct xen_dm_op_buf;
* there aren't more than 5 arguments...)
*/
-extern struct { char _entry[32]; } hypercall_page[];
+void xen_hypercall_func(void);
+DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func);
-#define __HYPERCALL "call hypercall_page+%c[offset]"
-#define __HYPERCALL_ENTRY(x) \
- [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
+#ifdef MODULE
+#define __ADDRESSABLE_xen_hypercall
+#else
+#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall)
+#endif
+
+#define __HYPERCALL \
+ __ADDRESSABLE_xen_hypercall \
+ "call __SCT__xen_hypercall"
+
+#define __HYPERCALL_ENTRY(x) "a" (x)
#ifdef CONFIG_X86_32
#define __HYPERCALL_RETREG "eax"
@@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_0ARG(); \
asm volatile (__HYPERCALL \
: __HYPERCALL_0PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER0); \
(type)__res; \
})
@@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_1ARG(a1); \
asm volatile (__HYPERCALL \
: __HYPERCALL_1PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER1); \
(type)__res; \
})
@@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_2ARG(a1, a2); \
asm volatile (__HYPERCALL \
: __HYPERCALL_2PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER2); \
(type)__res; \
})
@@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_3ARG(a1, a2, a3); \
asm volatile (__HYPERCALL \
: __HYPERCALL_3PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER3); \
(type)__res; \
})
@@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[];
__HYPERCALL_4ARG(a1, a2, a3, a4); \
asm volatile (__HYPERCALL \
: __HYPERCALL_4PARAM \
- : __HYPERCALL_ENTRY(name) \
+ : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \
: __HYPERCALL_CLOBBER4); \
(type)__res; \
})
@@ -206,12 +217,9 @@ xen_single_call(unsigned int call,
__HYPERCALL_DECLS;
__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
- if (call >= PAGE_SIZE / sizeof(hypercall_page[0]))
- return -EINVAL;
-
- asm volatile(CALL_NOSPEC
+ asm volatile(__HYPERCALL
: __HYPERCALL_5PARAM
- : [thunk_target] "a" (&hypercall_page[call])
+ : __HYPERCALL_ENTRY(call)
: __HYPERCALL_CLOBBER5);
return (long)__res;
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 465647456753..f17d16607882 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -143,11 +143,6 @@ static bool skip_addr(void *dest)
dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE)
return true;
#endif
-#ifdef CONFIG_XEN
- if (dest >= (void *)hypercall_page &&
- dest < (void*)hypercall_page + PAGE_SIZE)
- return true;
-#endif
return false;
}
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
index d2c732a34e5d..303bf74d175b 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code)
static __ro_after_init bool ibt_fatal = true;
+/*
+ * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR.
+ *
+ * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered,
+ * the WFE state of the interrupted context needs to be cleared to let execution
+ * continue. Otherwise when the CPU resumes from the instruction that just
+ * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU
+ * enters a dead loop.
+ *
+ * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't
+ * set WFE. But FRED provides space on the entry stack (in an expanded CS area)
+ * to save and restore the WFE state, thus the WFE state is no longer clobbered,
+ * so software must clear it.
+ */
+static void ibt_clear_fred_wfe(struct pt_regs *regs)
+{
+ /*
+ * No need to do any FRED checks.
+ *
+ * For IDT event delivery, the high-order 48 bits of CS are pushed
+ * as 0s into the stack, and later IRET ignores these bits.
+ *
+ * For FRED, a test to check if fred_cs.wfe is set would be dropped
+ * by compilers.
+ */
+ regs->fred_cs.wfe = 0;
+}
+
static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code)
{
if ((error_code & CP_EC) != CP_ENDBR) {
@@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code)
if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) {
regs->ax = 0;
+ ibt_clear_fred_wfe(regs);
return;
}
@@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code)
if (!ibt_fatal) {
printk(KERN_DEFAULT CUT_HERE);
__warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL);
+ ibt_clear_fred_wfe(regs);
return;
}
BUG();
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d8408aafeed9..79d2e17f6582 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1065,7 +1065,7 @@ static void init_amd(struct cpuinfo_x86 *c)
*/
if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
cpu_has(c, X86_FEATURE_AUTOIBRS))
- WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS));
+ WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS) < 0);
/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 392d09c936d6..e6fa03ed9172 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -178,8 +178,6 @@ struct _cpuid4_info_regs {
struct amd_northbridge *nb;
};
-static unsigned short num_cache_leaves;
-
/* AMD doesn't have CPUID4. Emulate it here to report the same
information to the user. This makes some assumptions about the machine:
L2 not shared, no SMT etc. that is currently true on AMD CPUs.
@@ -717,20 +715,23 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
void init_amd_cacheinfo(struct cpuinfo_x86 *c)
{
+ struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
- num_cache_leaves = find_num_cache_leaves(c);
+ ci->num_leaves = find_num_cache_leaves(c);
} else if (c->extended_cpuid_level >= 0x80000006) {
if (cpuid_edx(0x80000006) & 0xf000)
- num_cache_leaves = 4;
+ ci->num_leaves = 4;
else
- num_cache_leaves = 3;
+ ci->num_leaves = 3;
}
}
void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
{
- num_cache_leaves = find_num_cache_leaves(c);
+ struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+
+ ci->num_leaves = find_num_cache_leaves(c);
}
void init_intel_cacheinfo(struct cpuinfo_x86 *c)
@@ -740,21 +741,21 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
+ struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
if (c->cpuid_level > 3) {
- static int is_initialized;
-
- if (is_initialized == 0) {
- /* Init num_cache_leaves from boot CPU */
- num_cache_leaves = find_num_cache_leaves(c);
- is_initialized++;
- }
+ /*
+ * There should be at least one leaf. A non-zero value means
+ * that the number of leaves has been initialized.
+ */
+ if (!ci->num_leaves)
+ ci->num_leaves = find_num_cache_leaves(c);
/*
* Whenever possible use cpuid(4), deterministic cache
* parameters cpuid leaf to find the cache details
*/
- for (i = 0; i < num_cache_leaves; i++) {
+ for (i = 0; i < ci->num_leaves; i++) {
struct _cpuid4_info_regs this_leaf = {};
int retval;
@@ -790,14 +791,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
* Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
* trace cache
*/
- if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) {
+ if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
/* supports eax=2 call */
int j, n;
unsigned int regs[4];
unsigned char *dp = (unsigned char *)regs;
int only_trace = 0;
- if (num_cache_leaves != 0 && c->x86 == 15)
+ if (ci->num_leaves && c->x86 == 15)
only_trace = 1;
/* Number of times to iterate */
@@ -991,14 +992,12 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
int init_cache_level(unsigned int cpu)
{
- struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
- if (!num_cache_leaves)
+ /* There should be at least one leaf. */
+ if (!ci->num_leaves)
return -ENOENT;
- if (!this_cpu_ci)
- return -EINVAL;
- this_cpu_ci->num_levels = 3;
- this_cpu_ci->num_leaves = num_cache_leaves;
+
return 0;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a5c28975c608..3e9037690814 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -867,7 +867,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
}
-static void get_cpu_vendor(struct cpuinfo_x86 *c)
+void get_cpu_vendor(struct cpuinfo_x86 *c)
{
char *v = c->x86_vendor_id;
int i;
@@ -1649,15 +1649,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
detect_nopl();
}
-void __init early_cpu_init(void)
+void __init init_cpu_devs(void)
{
const struct cpu_dev *const *cdev;
int count = 0;
-#ifdef CONFIG_PROCESSOR_SELECT
- pr_info("KERNEL supported cpus:\n");
-#endif
-
for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
const struct cpu_dev *cpudev = *cdev;
@@ -1665,20 +1661,30 @@ void __init early_cpu_init(void)
break;
cpu_devs[count] = cpudev;
count++;
+ }
+}
+void __init early_cpu_init(void)
+{
#ifdef CONFIG_PROCESSOR_SELECT
- {
- unsigned int j;
-
- for (j = 0; j < 2; j++) {
- if (!cpudev->c_ident[j])
- continue;
- pr_info(" %s %s\n", cpudev->c_vendor,
- cpudev->c_ident[j]);
- }
- }
+ unsigned int i, j;
+
+ pr_info("KERNEL supported cpus:\n");
#endif
+
+ init_cpu_devs();
+
+#ifdef CONFIG_PROCESSOR_SELECT
+ for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) {
+ for (j = 0; j < 2; j++) {
+ if (!cpu_devs[i]->c_ident[j])
+ continue;
+ pr_info(" %s %s\n", cpu_devs[i]->c_vendor,
+ cpu_devs[i]->c_ident[j]);
+ }
}
+#endif
+
early_identify_cpu(&boot_cpu_data);
}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d1de300af173..8ded9f859a3a 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -555,7 +555,9 @@ static void init_intel(struct cpuinfo_x86 *c)
c->x86_vfm == INTEL_WESTMERE_EX))
set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
- if (boot_cpu_has(X86_FEATURE_MWAIT) && c->x86_vfm == INTEL_ATOM_GOLDMONT)
+ if (boot_cpu_has(X86_FEATURE_MWAIT) &&
+ (c->x86_vfm == INTEL_ATOM_GOLDMONT ||
+ c->x86_vfm == INTEL_LUNARLAKE_M))
set_cpu_bug(c, X86_BUG_MONITOR);
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index d18078834ded..dc12fe5ef3ca 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
hyperv_cleanup();
}
#endif /* CONFIG_CRASH_DUMP */
+
+static u64 hv_ref_counter_at_suspend;
+static void (*old_save_sched_clock_state)(void);
+static void (*old_restore_sched_clock_state)(void);
+
+/*
+ * Hyper-V clock counter resets during hibernation. Save and restore clock
+ * offset during suspend/resume, while also considering the time passed
+ * before suspend. This is to make sure that sched_clock using hv tsc page
+ * based clocksource, proceeds from where it left off during suspend and
+ * it shows correct time for the timestamps of kernel messages after resume.
+ */
+static void save_hv_clock_tsc_state(void)
+{
+ hv_ref_counter_at_suspend = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+ /*
+ * Adjust the offsets used by hv tsc clocksource to
+ * account for the time spent before hibernation.
+ * adjusted value = reference counter (time) at suspend
+ * - reference counter (time) now.
+ */
+ hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter());
+}
+
+/*
+ * Functions to override save_sched_clock_state and restore_sched_clock_state
+ * functions of x86_platform. The Hyper-V clock counter is reset during
+ * suspend-resume and the offset used to measure time needs to be
+ * corrected, post resume.
+ */
+static void hv_save_sched_clock_state(void)
+{
+ old_save_sched_clock_state();
+ save_hv_clock_tsc_state();
+}
+
+static void hv_restore_sched_clock_state(void)
+{
+ restore_hv_clock_tsc_state();
+ old_restore_sched_clock_state();
+}
+
+static void __init x86_setup_ops_for_tsc_pg_clock(void)
+{
+ if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+ return;
+
+ old_save_sched_clock_state = x86_platform.save_sched_clock_state;
+ x86_platform.save_sched_clock_state = hv_save_sched_clock_state;
+
+ old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
+ x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
+}
#endif /* CONFIG_HYPERV */
static uint32_t __init ms_hyperv_platform(void)
@@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void)
/* Register Hyper-V specific clocksource */
hv_init_clocksource();
+ x86_setup_ops_for_tsc_pg_clock();
hv_vtl_init_platform();
#endif
/*
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 621a151ccf7d..b2e313ea17bf 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -428,8 +428,8 @@ void __init topology_apply_cmdline_limits_early(void)
{
unsigned int possible = nr_cpu_ids;
- /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' 'noapic' */
- if (!setup_max_cpus || ioapic_is_disabled || apic_is_disabled)
+ /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */
+ if (!setup_max_cpus || apic_is_disabled)
possible = 1;
/* 'possible_cpus=N' */
@@ -443,7 +443,7 @@ void __init topology_apply_cmdline_limits_early(void)
static __init bool restrict_to_up(void)
{
- if (!smp_found_config || ioapic_is_disabled)
+ if (!smp_found_config)
return true;
/*
* XEN PV is special as it does not advertise the local APIC
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 1065ab995305..8f62e0666dea 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -64,16 +64,6 @@ setfx:
}
/*
- * Update the value of PKRU register that was already pushed onto the signal frame.
- */
-static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru)
-{
- if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
- return 0;
- return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
-}
-
-/*
* Signal frame handlers.
*/
static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf)
@@ -168,14 +158,8 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru)
{
- int err = 0;
-
- if (use_xsave()) {
- err = xsave_to_user_sigframe(buf);
- if (!err)
- err = update_pkru_in_sigframe(buf, pkru);
- return err;
- }
+ if (use_xsave())
+ return xsave_to_user_sigframe(buf, pkru);
if (use_fxsr())
return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 0b86a5002c84..aa16f1a1bbcf 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -69,6 +69,28 @@ static inline u64 xfeatures_mask_independent(void)
return fpu_kernel_cfg.independent_features;
}
+/*
+ * Update the value of PKRU register that was already pushed onto the signal frame.
+ */
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru)
+{
+ u64 xstate_bv;
+ int err;
+
+ if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
+ return 0;
+
+ /* Mark PKRU as in-use so that it is restored correctly. */
+ xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU;
+
+ err = __put_user(xstate_bv, &buf->header.xfeatures);
+ if (err)
+ return err;
+
+ /* Update PKRU value in the userspace xsave buffer. */
+ return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
+}
+
/* XSAVE/XRSTOR wrapper functions */
#ifdef CONFIG_X86_64
@@ -256,7 +278,7 @@ static inline u64 xfeatures_need_sigframe_write(void)
* The caller has to zero buf::header before calling this because XSAVE*
* does not touch the reserved fields in the header.
*/
-static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
+static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru)
{
/*
* Include the features which are not xsaved/rstored by the kernel
@@ -281,6 +303,9 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
XSTATE_OP(XSAVE, buf, lmask, hmask, err);
clac();
+ if (!err)
+ err = update_pkru_in_sigframe(buf, mask, pkru);
+
return err;
}
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index e9e88c342f75..540443d699e3 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -13,6 +13,7 @@
#include <asm/pgtable_types.h>
#include <asm/nospec-branch.h>
#include <asm/unwind_hints.h>
+#include <asm/asm-offsets.h>
/*
* Must be relocatable PIC code callable as a C function, in particular
@@ -242,6 +243,13 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
movq CR0(%r8), %r8
movq %rax, %cr3
movq %r8, %cr0
+
+#ifdef CONFIG_KEXEC_JUMP
+ /* Saved in save_processor_state. */
+ movq $saved_context, %rax
+ lgdt saved_context_gdt_desc(%rax)
+#endif
+
movq %rbp, %rax
popf
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 4eefaac64c6c..9eed0c144dad 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -172,6 +172,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
}
EXPORT_SYMBOL_GPL(arch_static_call_transform);
+noinstr void __static_call_update_early(void *tramp, void *func)
+{
+ BUG_ON(system_state != SYSTEM_BOOTING);
+ BUG_ON(!early_boot_irqs_disabled);
+ BUG_ON(static_call_initialized);
+ __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE);
+ sync_core();
+}
+
#ifdef CONFIG_MITIGATION_RETHUNK
/*
* This is called by apply_returns() to fix up static call trampolines,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index fab3ac9a4574..6a17396c8174 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -519,14 +519,10 @@ INIT_PER_CPU(irq_stack_backing_store);
* linker will never mark as relocatable. (Using just ABSOLUTE() is not
* sufficient for that).
*/
-#ifdef CONFIG_XEN
#ifdef CONFIG_XEN_PV
xen_elfnote_entry_value =
ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen);
#endif
-xen_elfnote_hypercall_page_value =
- ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page);
-#endif
#ifdef CONFIG_PVH
xen_elfnote_phys32_entry_value =
ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 097bdc022d0f..ae0b438a2c99 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -36,6 +36,26 @@
u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
EXPORT_SYMBOL_GPL(kvm_cpu_caps);
+struct cpuid_xstate_sizes {
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+};
+
+static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init;
+
+void __init kvm_init_xstate_sizes(void)
+{
+ u32 ign;
+ int i;
+
+ for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) {
+ struct cpuid_xstate_sizes *xs = &xstate_sizes[i];
+
+ cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign);
+ }
+}
+
u32 xstate_required_size(u64 xstate_bv, bool compacted)
{
int feature_bit = 0;
@@ -44,14 +64,15 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted)
xstate_bv &= XFEATURE_MASK_EXTEND;
while (xstate_bv) {
if (xstate_bv & 0x1) {
- u32 eax, ebx, ecx, edx, offset;
- cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx);
+ struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit];
+ u32 offset;
+
/* ECX[1]: 64B alignment in compacted form */
if (compacted)
- offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret;
+ offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret;
else
- offset = ebx;
- ret = max(ret, offset + eax);
+ offset = xs->ebx;
+ ret = max(ret, offset + xs->eax);
}
xstate_bv >>= 1;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index c8dc66eddefd..f16a7b2c2adc 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -31,6 +31,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
u32 *ecx, u32 *edx, bool exact_only);
+void __init kvm_init_xstate_sizes(void);
u32 xstate_required_size(u64 xstate_bv, bool compacted);
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 22e7ad235123..2401606db260 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3364,18 +3364,6 @@ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu,
return true;
}
-static bool is_access_allowed(struct kvm_page_fault *fault, u64 spte)
-{
- if (fault->exec)
- return is_executable_pte(spte);
-
- if (fault->write)
- return is_writable_pte(spte);
-
- /* Fault was on Read access */
- return spte & PT_PRESENT_MASK;
-}
-
/*
* Returns the last level spte pointer of the shadow page walk for the given
* gpa, and sets *spte to the spte value. This spte may be non-preset. If no
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index f332b33bc817..af10bc0380a3 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -462,6 +462,23 @@ static inline bool is_mmu_writable_spte(u64 spte)
}
/*
+ * Returns true if the access indicated by @fault is allowed by the existing
+ * SPTE protections. Note, the caller is responsible for checking that the
+ * SPTE is a shadow-present, leaf SPTE (either before or after).
+ */
+static inline bool is_access_allowed(struct kvm_page_fault *fault, u64 spte)
+{
+ if (fault->exec)
+ return is_executable_pte(spte);
+
+ if (fault->write)
+ return is_writable_pte(spte);
+
+ /* Fault was on Read access */
+ return spte & PT_PRESENT_MASK;
+}
+
+/*
* If the MMU-writable flag is cleared, i.e. the SPTE is write-protected for
* write-tracking, remote TLBs must be flushed, even if the SPTE was read-only,
* as KVM allows stale Writable TLB entries to exist. When dirty logging, KVM
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 4508d868f1cd..2f15e0e33903 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -985,6 +985,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
if (fault->prefetch && is_shadow_present_pte(iter->old_spte))
return RET_PF_SPURIOUS;
+ if (is_shadow_present_pte(iter->old_spte) &&
+ is_access_allowed(fault, iter->old_spte) &&
+ is_last_spte(iter->old_spte, iter->level))
+ return RET_PF_SPURIOUS;
+
if (unlikely(!fault->slot))
new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
else
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 4b74ea91f4e6..65fd245a9953 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -1199,6 +1199,12 @@ bool avic_hardware_setup(void)
return false;
}
+ if (cc_platform_has(CC_ATTR_HOST_SEV_SNP) &&
+ !boot_cpu_has(X86_FEATURE_HV_INUSE_WR_ALLOWED)) {
+ pr_warn("AVIC disabled: missing HvInUseWrAllowed on SNP-enabled system\n");
+ return false;
+ }
+
if (boot_cpu_has(X86_FEATURE_AVIC)) {
pr_info("AVIC enabled\n");
} else if (force_avic) {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index dd15cc635655..21dacd312779 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3201,15 +3201,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
if (data & ~supported_de_cfg)
return 1;
- /*
- * Don't let the guest change the host-programmed value. The
- * MSR is very model specific, i.e. contains multiple bits that
- * are completely unknown to KVM, and the one bit known to KVM
- * is simply a reflection of hardware capabilities.
- */
- if (!msr->host_initiated && data != svm->msr_decfg)
- return 1;
-
svm->msr_decfg = data;
break;
}
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 1715d2ab07be..ad9116a99bcc 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -2,7 +2,7 @@
#ifndef __KVM_X86_VMX_POSTED_INTR_H
#define __KVM_X86_VMX_POSTED_INTR_H
-#include <linux/find.h>
+#include <linux/bitmap.h>
#include <asm/posted_intr.h>
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2e713480933a..c79a8cc57ba4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9976,7 +9976,7 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
{
u64 ret = vcpu->run->hypercall.ret;
- if (!is_64_bit_mode(vcpu))
+ if (!is_64_bit_hypercall(vcpu))
ret = (u32)ret;
kvm_rax_write(vcpu, ret);
++vcpu->stat.hypercalls;
@@ -12724,6 +12724,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm_hv_init_vm(kvm);
kvm_xen_init_vm(kvm);
+ if (ignore_msrs && !report_ignored_msrs) {
+ pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n"
+ "a supported configuration. Lying to the guest about the existence of MSRs\n"
+ "may cause the guest operating system to hang or produce errors. If a guest\n"
+ "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n");
+ }
+
return 0;
out_uninit_mmu:
@@ -13997,6 +14004,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault);
static int __init kvm_x86_init(void)
{
+ kvm_init_xstate_sizes();
+
kvm_mmu_x86_module_init();
mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible();
return 0;
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 437e96fb4977..5ab7bd2f1983 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -174,7 +174,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
if (result)
return result;
- set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag));
+ set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
}
return 0;
@@ -218,14 +218,14 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
if (result)
return result;
if (pgtable_l5_enabled()) {
- set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
+ set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag | _PAGE_NOPTISHADOW));
} else {
/*
* With p4d folded, pgd is equal to p4d.
* The pgd entry has to point to the pud page table in this case.
*/
pud_t *pud = pud_offset(p4d, 0);
- set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag));
+ set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
}
}
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 069e421c2247..95bc50a8541c 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -354,7 +354,7 @@ bool cpu_cache_has_invalidate_memregion(void)
{
return !cpu_feature_enabled(X86_FEATURE_HYPERVISOR);
}
-EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, DEVMEM);
+EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, "DEVMEM");
int cpu_cache_invalidate_memregion(int res_desc)
{
@@ -363,7 +363,7 @@ int cpu_cache_invalidate_memregion(int res_desc)
wbinvd_on_all_cpus();
return 0;
}
-EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, DEVMEM);
+EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, "DEVMEM");
#endif
static void __cpa_flush_all(void *arg)
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 851ec8f1363a..5f0d579932c6 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -132,7 +132,7 @@ pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
* Top-level entries added to init_mm's usermode pgd after boot
* will not be automatically propagated to other mms.
*/
- if (!pgdp_maps_userspace(pgdp))
+ if (!pgdp_maps_userspace(pgdp) || (pgd.pgd & _PAGE_NOPTISHADOW))
return pgd;
/*
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 84e5adbd0925..43dcd8c7badc 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -2,6 +2,7 @@
#include <linux/console.h>
#include <linux/cpu.h>
+#include <linux/instrumentation.h>
#include <linux/kexec.h>
#include <linux/memblock.h>
#include <linux/slab.h>
@@ -21,7 +22,8 @@
#include "xen-ops.h"
-EXPORT_SYMBOL_GPL(hypercall_page);
+DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm);
+EXPORT_STATIC_CALL_TRAMP(xen_hypercall);
/*
* Pointer to the xen_vcpu_info structure or
@@ -68,6 +70,67 @@ EXPORT_SYMBOL(xen_start_flags);
*/
struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;
+static __ref void xen_get_vendor(void)
+{
+ init_cpu_devs();
+ cpu_detect(&boot_cpu_data);
+ get_cpu_vendor(&boot_cpu_data);
+}
+
+void xen_hypercall_setfunc(void)
+{
+ if (static_call_query(xen_hypercall) != xen_hypercall_hvm)
+ return;
+
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
+ static_call_update(xen_hypercall, xen_hypercall_amd);
+ else
+ static_call_update(xen_hypercall, xen_hypercall_intel);
+}
+
+/*
+ * Evaluate processor vendor in order to select the correct hypercall
+ * function for HVM/PVH guests.
+ * Might be called very early in boot before vendor has been set by
+ * early_cpu_init().
+ */
+noinstr void *__xen_hypercall_setfunc(void)
+{
+ void (*func)(void);
+
+ /*
+ * Xen is supported only on CPUs with CPUID, so testing for
+ * X86_FEATURE_CPUID is a test for early_cpu_init() having been
+ * run.
+ *
+ * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty
+ * dependency chain: it is being called via the xen_hypercall static
+ * call when running as a PVH or HVM guest. Hypercalls need to be
+ * noinstr due to PV guests using hypercalls in noinstr code. So we
+ * can safely tag the function body as "instrumentation ok", since
+ * the PV guest requirement is not of interest here (xen_get_vendor()
+ * calls noinstr functions, and static_call_update_early() might do
+ * so, too).
+ */
+ instrumentation_begin();
+
+ if (!boot_cpu_has(X86_FEATURE_CPUID))
+ xen_get_vendor();
+
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON))
+ func = xen_hypercall_amd;
+ else
+ func = xen_hypercall_intel;
+
+ static_call_update_early(xen_hypercall, func);
+
+ instrumentation_end();
+
+ return func;
+}
+
static int xen_cpu_up_online(unsigned int cpu)
{
xen_init_lock_cpu(cpu);
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 24d2957a4726..fe57ff85d004 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void)
/* PVH set up hypercall page in xen_prepare_pvh(). */
if (xen_pvh_domain())
pv_info.name = "Xen PVH";
- else {
- u64 pfn;
- uint32_t msr;
-
+ else
pv_info.name = "Xen HVM";
- msr = cpuid_ebx(base + 2);
- pfn = __pa(hypercall_page);
- wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
- }
xen_setup_features();
@@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void)
if (xen_pv_domain())
return 0;
+ /* Set correct hypercall function. */
+ if (xen_domain)
+ xen_hypercall_setfunc();
+
if (xen_pvh_domain() && nopv) {
/* Guest booting via the Xen-PVH boot entry goes here */
pr_info("\"nopv\" parameter is ignored in PVH guest\n");
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index d6818c6cafda..a8eb7e0c473c 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1341,6 +1341,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si)
xen_domain_type = XEN_PV_DOMAIN;
xen_start_flags = xen_start_info->flags;
+ /* Interrupts are guaranteed to be off initially. */
+ early_boot_irqs_disabled = true;
+ static_call_update_early(xen_hypercall, xen_hypercall_pv);
xen_setup_features();
@@ -1431,7 +1434,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si)
WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
local_irq_disable();
- early_boot_irqs_disabled = true;
xen_raw_console_write("mapping kernel into physical memory\n");
xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base,
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index bf68c329fc01..0e3d930bcb89 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void)
void __init xen_pvh_init(struct boot_params *boot_params)
{
- u32 msr;
- u64 pfn;
-
xen_pvh = 1;
xen_domain_type = XEN_HVM_DOMAIN;
xen_start_flags = pvh_start_info.flags;
- msr = cpuid_ebx(xen_cpuid_base() + 2);
- pfn = __pa(hypercall_page);
- wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
-
x86_init.oem.arch_setup = pvh_arch_setup;
x86_init.oem.banner = xen_banner;
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 83189cf5cdce..b518f36d1ca2 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -20,10 +20,33 @@
#include <linux/init.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <../entry/calling.h>
.pushsection .noinstr.text, "ax"
/*
+ * PV hypercall interface to the hypervisor.
+ *
+ * Called via inline asm(), so better preserve %rcx and %r11.
+ *
+ * Input:
+ * %eax: hypercall number
+ * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall
+ * Output: %rax
+ */
+SYM_FUNC_START(xen_hypercall_pv)
+ ANNOTATE_NOENDBR
+ push %rcx
+ push %r11
+ UNWIND_HINT_SAVE
+ syscall
+ UNWIND_HINT_RESTORE
+ pop %r11
+ pop %rcx
+ RET
+SYM_FUNC_END(xen_hypercall_pv)
+
+/*
* Disabling events is simply a matter of making the event mask
* non-zero.
*/
@@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array)
SYM_CODE_END(xen_early_idt_handler_array)
__FINIT
-hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
/*
* Xen64 iret frame:
*
@@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
* cs
* rip <-- standard iret frame
*
- * flags
+ * flags <-- xen_iret must push from here on
*
- * rcx }
- * r11 }<-- pushed by hypercall page
- * rsp->rax }
+ * rcx
+ * r11
+ * rsp->rax
*/
+.macro xen_hypercall_iret
+ pushq $0 /* Flags */
+ push %rcx
+ push %r11
+ push %rax
+ mov $__HYPERVISOR_iret, %eax
+ syscall /* Do the IRET. */
+#ifdef CONFIG_MITIGATION_SLS
+ int3
+#endif
+.endm
+
SYM_CODE_START(xen_iret)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
- pushq $0
- jmp hypercall_iret
+ xen_hypercall_iret
SYM_CODE_END(xen_iret)
/*
@@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat)
ENDBR
lea 16(%rsp), %rsp /* strip %rcx, %r11 */
mov $-ENOSYS, %rax
- pushq $0
- jmp hypercall_iret
+ xen_hypercall_iret
SYM_CODE_END(xen_entry_SYSENTER_compat)
SYM_CODE_END(xen_entry_SYSCALL_compat)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 7f6c69dbb816..9252652afe59 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -6,9 +6,11 @@
#include <linux/elfnote.h>
#include <linux/init.h>
+#include <linux/instrumentation.h>
#include <asm/boot.h>
#include <asm/asm.h>
+#include <asm/frame.h>
#include <asm/msr.h>
#include <asm/page_types.h>
#include <asm/percpu.h>
@@ -20,28 +22,6 @@
#include <xen/interface/xen-mca.h>
#include <asm/xen/interface.h>
-.pushsection .noinstr.text, "ax"
- .balign PAGE_SIZE
-SYM_CODE_START(hypercall_page)
- .rept (PAGE_SIZE / 32)
- UNWIND_HINT_FUNC
- ANNOTATE_NOENDBR
- ANNOTATE_UNRET_SAFE
- ret
- /*
- * Xen will write the hypercall page, and sort out ENDBR.
- */
- .skip 31, 0xcc
- .endr
-
-#define HYPERCALL(n) \
- .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \
- .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
-#include <asm/xen-hypercalls.h>
-#undef HYPERCALL
-SYM_CODE_END(hypercall_page)
-.popsection
-
#ifdef CONFIG_XEN_PV
__INIT
SYM_CODE_START(startup_xen)
@@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again)
#endif
#endif
+ .pushsection .noinstr.text, "ax"
+/*
+ * Xen hypercall interface to the hypervisor.
+ *
+ * Input:
+ * %eax: hypercall number
+ * 32-bit:
+ * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall
+ * 64-bit:
+ * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall
+ * Output: %[er]ax
+ */
+SYM_FUNC_START(xen_hypercall_hvm)
+ ENDBR
+ FRAME_BEGIN
+ /* Save all relevant registers (caller save and arguments). */
+#ifdef CONFIG_X86_32
+ push %eax
+ push %ebx
+ push %ecx
+ push %edx
+ push %esi
+ push %edi
+#else
+ push %rax
+ push %rcx
+ push %rdx
+ push %rdi
+ push %rsi
+ push %r11
+ push %r10
+ push %r9
+ push %r8
+#ifdef CONFIG_FRAME_POINTER
+ pushq $0 /* Dummy push for stack alignment. */
+#endif
+#endif
+ /* Set the vendor specific function. */
+ call __xen_hypercall_setfunc
+ /* Set ZF = 1 if AMD, Restore saved registers. */
+#ifdef CONFIG_X86_32
+ lea xen_hypercall_amd, %ebx
+ cmp %eax, %ebx
+ pop %edi
+ pop %esi
+ pop %edx
+ pop %ecx
+ pop %ebx
+ pop %eax
+#else
+ lea xen_hypercall_amd(%rip), %rbx
+ cmp %rax, %rbx
+#ifdef CONFIG_FRAME_POINTER
+ pop %rax /* Dummy pop. */
+#endif
+ pop %r8
+ pop %r9
+ pop %r10
+ pop %r11
+ pop %rsi
+ pop %rdi
+ pop %rdx
+ pop %rcx
+ pop %rax
+#endif
+ /* Use correct hypercall function. */
+ jz xen_hypercall_amd
+ jmp xen_hypercall_intel
+SYM_FUNC_END(xen_hypercall_hvm)
+
+SYM_FUNC_START(xen_hypercall_amd)
+ vmmcall
+ RET
+SYM_FUNC_END(xen_hypercall_amd)
+
+SYM_FUNC_START(xen_hypercall_intel)
+ vmcall
+ RET
+SYM_FUNC_END(xen_hypercall_intel)
+ .popsection
+
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux")
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6")
ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0")
@@ -116,8 +177,6 @@ SYM_CODE_END(xen_cpu_bringup_again)
#else
# define FEATURES_DOM0 0
#endif
- ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .globl xen_elfnote_hypercall_page;
- xen_elfnote_hypercall_page: _ASM_PTR xen_elfnote_hypercall_page_value - .)
ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES,
.long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0)
ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic")
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index e1b782e823e6..63c13a2ccf55 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {}
static inline void xen_smp_count_cpus(void) { }
#endif /* CONFIG_SMP */
+#ifdef CONFIG_XEN_PV
+void xen_hypercall_pv(void);
+#endif
+void xen_hypercall_hvm(void);
+void xen_hypercall_amd(void);
+void xen_hypercall_intel(void);
+void xen_hypercall_setfunc(void);
+void *__xen_hypercall_setfunc(void);
+
#endif /* XEN_OPS_H */