summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig3
-rw-r--r--arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts2
-rw-r--r--arch/arm/boot/dts/bcm63138.dtsi14
-rw-r--r--arch/arm/boot/dts/sama5d3_emac.dtsi2
-rw-r--r--arch/arm/boot/dts/stm32mp157c.dtsi4
-rw-r--r--arch/arm/boot/dts/sun8i-r40.dtsi3
-rw-r--r--arch/arm64/Kconfig1
-rw-r--r--arch/arm64/include/asm/jump_label.h38
-rw-r--r--arch/arm64/kernel/Makefile1
-rw-r--r--arch/arm64/kernel/crash_core.c19
-rw-r--r--arch/arm64/kernel/jump_label.c6
-rw-r--r--arch/arm64/kernel/machine_kexec.c11
-rw-r--r--arch/arm64/kvm/guest.c55
-rw-r--r--arch/arm64/mm/hugetlbpage.c50
-rw-r--r--arch/hexagon/include/asm/bitops.h4
-rw-r--r--arch/hexagon/kernel/dma.c2
-rw-r--r--arch/mips/include/asm/mach-lantiq/xway/xway_dma.h1
-rw-r--r--arch/mips/lantiq/xway/dma.c4
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h1
-rw-r--r--arch/powerpc/include/asm/iommu.h2
-rw-r--r--arch/powerpc/include/asm/mmu_context.h1
-rw-r--r--arch/powerpc/include/asm/setup.h1
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S4
-rw-r--r--arch/powerpc/kernel/iommu.c25
-rw-r--r--arch/powerpc/kernel/tm.S20
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c91
-rw-r--r--arch/powerpc/kvm/book3s_64_vio_hv.c39
-rw-r--r--arch/powerpc/lib/checksum_64.S3
-rw-r--r--arch/powerpc/lib/code-patching.c6
-rw-r--r--arch/powerpc/mm/init_64.c49
-rw-r--r--arch/powerpc/mm/mem.c2
-rw-r--r--arch/powerpc/mm/mmu_context_iommu.c34
-rw-r--r--arch/powerpc/mm/numa.c7
-rw-r--r--arch/powerpc/mm/pkeys.c2
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda-tce.c2
-rw-r--r--arch/riscv/include/asm/asm-prototypes.h7
-rw-r--r--arch/riscv/kernel/setup.c7
-rw-r--r--arch/s390/Kconfig1
-rw-r--r--arch/s390/crypto/paes_s390.c2
-rw-r--r--arch/s390/include/asm/jump_label.h40
-rw-r--r--arch/s390/kernel/jump_label.c11
-rw-r--r--arch/s390/kernel/vmlinux.lds.S1
-rw-r--r--arch/s390/kvm/kvm-s390.c4
-rw-r--r--arch/s390/mm/gmap.c4
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/boot/compressed/mem_encrypt.S19
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/crypto/aegis128-aesni-glue.c1
-rw-r--r--arch/x86/crypto/aegis128l-aesni-glue.c1
-rw-r--r--arch/x86/crypto/aegis256-aesni-glue.c1
-rw-r--r--arch/x86/crypto/morus1280-sse2-glue.c1
-rw-r--r--arch/x86/crypto/morus640-sse2-glue.c1
-rw-r--r--arch/x86/entry/calling.h2
-rw-r--r--arch/x86/events/intel/lbr.c4
-rw-r--r--arch/x86/hyperv/hv_apic.c8
-rw-r--r--arch/x86/include/asm/alternative-asm.h20
-rw-r--r--arch/x86/include/asm/alternative.h11
-rw-r--r--arch/x86/include/asm/asm.h57
-rw-r--r--arch/x86/include/asm/bug.h98
-rw-r--r--arch/x86/include/asm/cpufeature.h82
-rw-r--r--arch/x86/include/asm/elf.h3
-rw-r--r--arch/x86/include/asm/extable.h3
-rw-r--r--arch/x86/include/asm/fixmap.h10
-rw-r--r--arch/x86/include/asm/fpu/internal.h2
-rw-r--r--arch/x86/include/asm/futex.h6
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h16
-rw-r--r--arch/x86/include/asm/jump_label.h80
-rw-r--r--arch/x86/include/asm/kvm_host.h5
-rw-r--r--arch/x86/include/asm/mem_encrypt.h7
-rw-r--r--arch/x86/include/asm/paravirt_types.h56
-rw-r--r--arch/x86/include/asm/pgtable-2level.h9
-rw-r--r--arch/x86/include/asm/pgtable_64.h3
-rw-r--r--arch/x86/include/asm/ptrace.h2
-rw-r--r--arch/x86/include/asm/refcount.h74
-rw-r--r--arch/x86/include/asm/uaccess.h22
-rw-r--r--arch/x86/include/uapi/asm/kvm.h1
-rw-r--r--arch/x86/kernel/apm_32.c2
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.h17
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c27
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c53
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c2
-rw-r--r--arch/x86/kernel/eisa.c10
-rw-r--r--arch/x86/kernel/head64.c20
-rw-r--r--arch/x86/kernel/head_64.S16
-rw-r--r--arch/x86/kernel/jump_label.c62
-rw-r--r--arch/x86/kernel/kprobes/core.c38
-rw-r--r--arch/x86/kernel/kvmclock.c52
-rw-r--r--arch/x86/kernel/macros.S16
-rw-r--r--arch/x86/kernel/module.c6
-rw-r--r--arch/x86/kernel/paravirt.c4
-rw-r--r--arch/x86/kernel/topology.c4
-rw-r--r--arch/x86/kernel/traps.c16
-rw-r--r--arch/x86/kernel/vmlinux.lds.S19
-rw-r--r--arch/x86/kvm/lapic.c22
-rw-r--r--arch/x86/kvm/mmu.c9
-rw-r--r--arch/x86/kvm/svm.c7
-rw-r--r--arch/x86/kvm/vmx.c138
-rw-r--r--arch/x86/kvm/x86.c101
-rw-r--r--arch/x86/lib/checksum_32.S4
-rw-r--r--arch/x86/lib/copy_user_64.S90
-rw-r--r--arch/x86/lib/csum-copy_64.S8
-rw-r--r--arch/x86/lib/getuser.S12
-rw-r--r--arch/x86/lib/putuser.S10
-rw-r--r--arch/x86/lib/usercopy_32.c126
-rw-r--r--arch/x86/lib/usercopy_64.c4
-rw-r--r--arch/x86/mm/extable.c114
-rw-r--r--arch/x86/mm/fault.c26
-rw-r--r--arch/x86/mm/init.c4
-rw-r--r--arch/x86/mm/mem_encrypt.c24
-rw-r--r--arch/x86/mm/pgtable.c9
-rw-r--r--arch/x86/platform/efi/efi_32.c3
-rw-r--r--arch/x86/tools/relocs.c10
-rw-r--r--arch/x86/um/asm/elf.h3
-rw-r--r--arch/x86/xen/mmu_pv.c8
-rw-r--r--arch/x86/xen/pmu.c2
-rw-r--r--arch/xtensa/Kconfig1
-rw-r--r--arch/xtensa/Makefile4
-rw-r--r--arch/xtensa/kernel/Makefile4
-rw-r--r--arch/xtensa/platforms/iss/setup.c25
121 files changed, 1401 insertions, 933 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 6801123932a5..9d329608913e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -359,6 +359,9 @@ config HAVE_PERF_USER_STACK_DUMP
config HAVE_ARCH_JUMP_LABEL
bool
+config HAVE_ARCH_JUMP_LABEL_RELATIVE
+ bool
+
config HAVE_RCU_TABLE_FREE
bool
diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
index b10dccd0958f..3b1baa8605a7 100644
--- a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
@@ -11,6 +11,7 @@
#include "sama5d2-pinfunc.h"
#include <dt-bindings/mfd/atmel-flexcom.h>
#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/at91.h>
/ {
model = "Atmel SAMA5D2 PTC EK";
@@ -299,6 +300,7 @@
<PIN_PA30__NWE_NANDWE>,
<PIN_PB2__NRD_NANDOE>;
bias-pull-up;
+ atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>;
};
ale_cle_rdy_cs {
diff --git a/arch/arm/boot/dts/bcm63138.dtsi b/arch/arm/boot/dts/bcm63138.dtsi
index 43ee992ccdcf..6df61518776f 100644
--- a/arch/arm/boot/dts/bcm63138.dtsi
+++ b/arch/arm/boot/dts/bcm63138.dtsi
@@ -106,21 +106,23 @@
global_timer: timer@1e200 {
compatible = "arm,cortex-a9-global-timer";
reg = <0x1e200 0x20>;
- interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
clocks = <&axi_clk>;
};
local_timer: local-timer@1e600 {
compatible = "arm,cortex-a9-twd-timer";
reg = <0x1e600 0x20>;
- interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
+ IRQ_TYPE_EDGE_RISING)>;
clocks = <&axi_clk>;
};
twd_watchdog: watchdog@1e620 {
compatible = "arm,cortex-a9-twd-wdt";
reg = <0x1e620 0x20>;
- interrupts = <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
+ IRQ_TYPE_LEVEL_HIGH)>;
};
armpll: armpll {
@@ -158,7 +160,7 @@
serial0: serial@600 {
compatible = "brcm,bcm6345-uart";
reg = <0x600 0x1b>;
- interrupts = <GIC_SPI 32 0>;
+ interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&periph_clk>;
clock-names = "periph";
status = "disabled";
@@ -167,7 +169,7 @@
serial1: serial@620 {
compatible = "brcm,bcm6345-uart";
reg = <0x620 0x1b>;
- interrupts = <GIC_SPI 33 0>;
+ interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&periph_clk>;
clock-names = "periph";
status = "disabled";
@@ -180,7 +182,7 @@
reg = <0x2000 0x600>, <0xf0 0x10>;
reg-names = "nand", "nand-int-base";
status = "disabled";
- interrupts = <GIC_SPI 38 0>;
+ interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "nand";
};
diff --git a/arch/arm/boot/dts/sama5d3_emac.dtsi b/arch/arm/boot/dts/sama5d3_emac.dtsi
index 7cb235ef0fb6..6e9e1c2f9def 100644
--- a/arch/arm/boot/dts/sama5d3_emac.dtsi
+++ b/arch/arm/boot/dts/sama5d3_emac.dtsi
@@ -41,7 +41,7 @@
};
macb1: ethernet@f802c000 {
- compatible = "cdns,at91sam9260-macb", "cdns,macb";
+ compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb";
reg = <0xf802c000 0x100>;
interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>;
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi
index 661be948ab74..185541a5b69f 100644
--- a/arch/arm/boot/dts/stm32mp157c.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c.dtsi
@@ -1078,8 +1078,8 @@
interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&rcc SPI6_K>;
resets = <&rcc SPI6_R>;
- dmas = <&mdma1 34 0x0 0x40008 0x0 0x0 0>,
- <&mdma1 35 0x0 0x40002 0x0 0x0 0>;
+ dmas = <&mdma1 34 0x0 0x40008 0x0 0x0>,
+ <&mdma1 35 0x0 0x40002 0x0 0x0>;
dma-names = "rx", "tx";
status = "disabled";
};
diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi
index ffd9f00f74a4..5f547c161baf 100644
--- a/arch/arm/boot/dts/sun8i-r40.dtsi
+++ b/arch/arm/boot/dts/sun8i-r40.dtsi
@@ -800,8 +800,7 @@
};
hdmi_phy: hdmi-phy@1ef0000 {
- compatible = "allwinner,sun8i-r40-hdmi-phy",
- "allwinner,sun50i-a64-hdmi-phy";
+ compatible = "allwinner,sun8i-r40-hdmi-phy";
reg = <0x01ef0000 0x10000>;
clocks = <&ccu CLK_BUS_HDMI1>, <&ccu CLK_HDMI_SLOW>,
<&ccu 7>, <&ccu 16>;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1b1a0e95c751..16e1e2c1e77b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -104,6 +104,7 @@ config ARM64
select HAVE_ARCH_BITREVERSE
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 1b5e0e843c3a..472023498d71 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -26,13 +26,16 @@
#define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE
-static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch(struct static_key *key,
+ bool branch)
{
- asm goto("1: nop\n\t"
- ".pushsection __jump_table, \"aw\"\n\t"
- ".align 3\n\t"
- ".quad 1b, %l[l_yes], %c0\n\t"
- ".popsection\n\t"
+ asm_volatile_goto(
+ "1: nop \n\t"
+ " .pushsection __jump_table, \"aw\" \n\t"
+ " .align 3 \n\t"
+ " .long 1b - ., %l[l_yes] - . \n\t"
+ " .quad %c0 - . \n\t"
+ " .popsection \n\t"
: : "i"(&((char *)key)[branch]) : : l_yes);
return false;
@@ -40,13 +43,16 @@ l_yes:
return true;
}
-static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key *key,
+ bool branch)
{
- asm goto("1: b %l[l_yes]\n\t"
- ".pushsection __jump_table, \"aw\"\n\t"
- ".align 3\n\t"
- ".quad 1b, %l[l_yes], %c0\n\t"
- ".popsection\n\t"
+ asm_volatile_goto(
+ "1: b %l[l_yes] \n\t"
+ " .pushsection __jump_table, \"aw\" \n\t"
+ " .align 3 \n\t"
+ " .long 1b - ., %l[l_yes] - . \n\t"
+ " .quad %c0 - . \n\t"
+ " .popsection \n\t"
: : "i"(&((char *)key)[branch]) : : l_yes);
return false;
@@ -54,13 +60,5 @@ l_yes:
return true;
}
-typedef u64 jump_label_t;
-
-struct jump_entry {
- jump_label_t code;
- jump_label_t target;
- jump_label_t key;
-};
-
#endif /* __ASSEMBLY__ */
#endif /* __ASM_JUMP_LABEL_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 95ac7374d723..4c8b13bede80 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \
arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o
arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+arm64-obj-$(CONFIG_CRASH_CORE) += crash_core.o
arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o
arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o
diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c
new file mode 100644
index 000000000000..ca4c3e12d8c5
--- /dev/null
+++ b/arch/arm64/kernel/crash_core.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ */
+
+#include <linux/crash_core.h>
+#include <asm/memory.h>
+
+void arch_crash_save_vmcoreinfo(void)
+{
+ VMCOREINFO_NUMBER(VA_BITS);
+ /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
+ vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
+ kimage_voffset);
+ vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
+ PHYS_OFFSET);
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+}
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
index e0756416e567..646b9562ee64 100644
--- a/arch/arm64/kernel/jump_label.c
+++ b/arch/arm64/kernel/jump_label.c
@@ -25,12 +25,12 @@
void arch_jump_label_transform(struct jump_entry *entry,
enum jump_label_type type)
{
- void *addr = (void *)entry->code;
+ void *addr = (void *)jump_entry_code(entry);
u32 insn;
if (type == JUMP_LABEL_JMP) {
- insn = aarch64_insn_gen_branch_imm(entry->code,
- entry->target,
+ insn = aarch64_insn_gen_branch_imm(jump_entry_code(entry),
+ jump_entry_target(entry),
AARCH64_INSN_BRANCH_NOLINK);
} else {
insn = aarch64_insn_gen_nop();
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index f6a5c6bc1434..922add8adb74 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -358,14 +358,3 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
}
}
#endif /* CONFIG_HIBERNATION */
-
-void arch_crash_save_vmcoreinfo(void)
-{
- VMCOREINFO_NUMBER(VA_BITS);
- /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
- vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
- kimage_voffset);
- vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
- PHYS_OFFSET);
- vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
-}
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 07256b08226c..a6c9fbaeaefc 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id)
return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
}
+static int validate_core_offset(const struct kvm_one_reg *reg)
+{
+ u64 off = core_reg_offset_from_id(reg->id);
+ int size;
+
+ switch (off) {
+ case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+ KVM_REG_ARM_CORE_REG(regs.regs[30]):
+ case KVM_REG_ARM_CORE_REG(regs.sp):
+ case KVM_REG_ARM_CORE_REG(regs.pc):
+ case KVM_REG_ARM_CORE_REG(regs.pstate):
+ case KVM_REG_ARM_CORE_REG(sp_el1):
+ case KVM_REG_ARM_CORE_REG(elr_el1):
+ case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+ KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+ size = sizeof(__u64);
+ break;
+
+ case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+ KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+ size = sizeof(__uint128_t);
+ break;
+
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+ size = sizeof(__u32);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (KVM_REG_SIZE(reg->id) == size &&
+ IS_ALIGNED(off, size / sizeof(__u32)))
+ return 0;
+
+ return -EINVAL;
+}
+
static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
/*
@@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
(off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
return -ENOENT;
+ if (validate_core_offset(reg))
+ return -EINVAL;
+
if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
return -EFAULT;
@@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
(off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
return -ENOENT;
+ if (validate_core_offset(reg))
+ return -EINVAL;
+
if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
return -EINVAL;
@@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
}
if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
- u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK;
+ u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
switch (mode) {
case PSR_AA32_MODE_USR:
+ if (!system_supports_32bit_el0())
+ return -EINVAL;
+ break;
case PSR_AA32_MODE_FIQ:
case PSR_AA32_MODE_IRQ:
case PSR_AA32_MODE_SVC:
case PSR_AA32_MODE_ABT:
case PSR_AA32_MODE_UND:
+ if (!vcpu_el1_is_32bit(vcpu))
+ return -EINVAL;
+ break;
case PSR_MODE_EL0t:
case PSR_MODE_EL1t:
case PSR_MODE_EL1h:
+ if (vcpu_el1_is_32bit(vcpu))
+ return -EINVAL;
break;
default:
err = -EINVAL;
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 192b3ba07075..f58ea503ad01 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -117,11 +117,14 @@ static pte_t get_clear_flush(struct mm_struct *mm,
/*
* If HW_AFDBM is enabled, then the HW could turn on
- * the dirty bit for any page in the set, so check
- * them all. All hugetlb entries are already young.
+ * the dirty or accessed bit for any page in the set,
+ * so check them all.
*/
if (pte_dirty(pte))
orig_pte = pte_mkdirty(orig_pte);
+
+ if (pte_young(pte))
+ orig_pte = pte_mkyoung(orig_pte);
}
if (valid) {
@@ -320,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
}
+/*
+ * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
+ * and write permission.
+ *
+ * For a contiguous huge pte range we need to check whether or not write
+ * permission has to change only on the first pte in the set. Then for
+ * all the contiguous ptes we need to check whether or not there is a
+ * discrepancy between dirty or young.
+ */
+static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
+{
+ int i;
+
+ if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
+ return 1;
+
+ for (i = 0; i < ncontig; i++) {
+ pte_t orig_pte = huge_ptep_get(ptep + i);
+
+ if (pte_dirty(pte) != pte_dirty(orig_pte))
+ return 1;
+
+ if (pte_young(pte) != pte_young(orig_pte))
+ return 1;
+ }
+
+ return 0;
+}
+
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
- int ncontig, i, changed = 0;
+ int ncontig, i;
size_t pgsize = 0;
unsigned long pfn = pte_pfn(pte), dpfn;
pgprot_t hugeprot;
@@ -336,19 +368,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
dpfn = pgsize >> PAGE_SHIFT;
+ if (!__cont_access_flags_changed(ptep, pte, ncontig))
+ return 0;
+
orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
- if (!pte_same(orig_pte, pte))
- changed = 1;
- /* Make sure we don't lose the dirty state */
+ /* Make sure we don't lose the dirty or young state */
if (pte_dirty(orig_pte))
pte = pte_mkdirty(pte);
+ if (pte_young(orig_pte))
+ pte = pte_mkyoung(pte);
+
hugeprot = pte_pgprot(pte);
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
- return changed;
+ return 1;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h
index 5e4a59b3ec1b..2691a1857d20 100644
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -211,7 +211,7 @@ static inline long ffz(int x)
* This is defined the same way as ffs.
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
*/
-static inline long fls(int x)
+static inline int fls(int x)
{
int r;
@@ -232,7 +232,7 @@ static inline long fls(int x)
* the libc and compiler builtin ffs routines, therefore
* differs in spirit from the above ffz (man ffs).
*/
-static inline long ffs(int x)
+static inline int ffs(int x)
{
int r;
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index 77459df34e2e..7ebe7ad19d15 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -60,7 +60,7 @@ static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size,
panic("Can't create %s() memory pool!", __func__);
else
gen_pool_add(coherent_pool,
- pfn_to_virt(max_low_pfn),
+ (unsigned long)pfn_to_virt(max_low_pfn),
hexagon_coherent_pool_size, -1);
}
diff --git a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h
index 4901833498f7..8441b2698e64 100644
--- a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h
+++ b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h
@@ -40,6 +40,7 @@ struct ltq_dma_channel {
int desc; /* the current descriptor */
struct ltq_dma_desc *desc_base; /* the descriptor base */
int phys; /* physical addr */
+ struct device *dev;
};
enum {
diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c
index 4b9fbb6744ad..664f2f7f55c1 100644
--- a/arch/mips/lantiq/xway/dma.c
+++ b/arch/mips/lantiq/xway/dma.c
@@ -130,7 +130,7 @@ ltq_dma_alloc(struct ltq_dma_channel *ch)
unsigned long flags;
ch->desc = 0;
- ch->desc_base = dma_zalloc_coherent(NULL,
+ ch->desc_base = dma_zalloc_coherent(ch->dev,
LTQ_DESC_NUM * LTQ_DESC_SIZE,
&ch->phys, GFP_ATOMIC);
@@ -182,7 +182,7 @@ ltq_dma_free(struct ltq_dma_channel *ch)
if (!ch->desc_base)
return;
ltq_dma_close(ch);
- dma_free_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE,
+ dma_free_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE,
ch->desc_base, ch->phys);
}
EXPORT_SYMBOL_GPL(ltq_dma_free);
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 13a688fc8cd0..2fdc865ca374 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1051,7 +1051,6 @@ static inline void vmemmap_remove_mapping(unsigned long start,
return hash__vmemmap_remove_mapping(start, page_size);
}
#endif
-struct page *realmode_pfn_to_page(unsigned long pfn);
static inline pte_t pmd_pte(pmd_t pmd)
{
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index ab3a4fba38e3..3d4b88cb8599 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -220,8 +220,6 @@ extern void iommu_del_device(struct device *dev);
extern int __init tce_iommu_bus_notifier_init(void);
extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
unsigned long *hpa, enum dma_data_direction *direction);
-extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
- unsigned long *hpa, enum dma_data_direction *direction);
#else
static inline void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number,
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b2f89b621b15..b694d6af1150 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -38,6 +38,7 @@ extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
unsigned long ua, unsigned int pageshift, unsigned long *hpa);
extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
unsigned long ua, unsigned int pageshift, unsigned long *hpa);
+extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua);
extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
#endif
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 1a951b00465d..1fffbba8d6a5 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex);
extern unsigned int rtas_data;
extern unsigned long long memory_limit;
+extern bool init_mem_is_free;
extern unsigned long klimit;
extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ea04dfb8c092..2d8fc8c9da7a 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1314,9 +1314,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
#ifdef CONFIG_PPC_DENORMALISATION
mfspr r10,SPRN_HSRR1
- mfspr r11,SPRN_HSRR0 /* save HSRR0 */
andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */
- addi r11,r11,-4 /* HSRR0 is next instruction */
bne+ denorm_assist
#endif
@@ -1382,6 +1380,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
*/
XVCPSGNDP32(32)
denorm_done:
+ mfspr r11,SPRN_HSRR0
+ subi r11,r11,4
mtspr SPRN_HSRR0,r11
mtcrf 0x80,r9
ld r9,PACA_EXGEN+EX_R9(r13)
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index af7a20dc6e09..19b4c628f3be 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1013,31 +1013,6 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
}
EXPORT_SYMBOL_GPL(iommu_tce_xchg);
-#ifdef CONFIG_PPC_BOOK3S_64
-long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
- unsigned long *hpa, enum dma_data_direction *direction)
-{
- long ret;
-
- ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
-
- if (!ret && ((*direction == DMA_FROM_DEVICE) ||
- (*direction == DMA_BIDIRECTIONAL))) {
- struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT);
-
- if (likely(pg)) {
- SetPageDirty(pg);
- } else {
- tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
- ret = -EFAULT;
- }
- }
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm);
-#endif
-
int iommu_take_ownership(struct iommu_table *tbl)
{
unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 6bffbc5affe7..7716374786bd 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -176,13 +176,27 @@ _GLOBAL(tm_reclaim)
std r1, PACATMSCRATCH(r13)
ld r1, PACAR1(r13)
- /* Store the PPR in r11 and reset to decent value */
std r11, GPR11(r1) /* Temporary stash */
+ /*
+ * Move the saved user r1 to the kernel stack in case PACATMSCRATCH is
+ * clobbered by an exception once we turn on MSR_RI below.
+ */
+ ld r11, PACATMSCRATCH(r13)
+ std r11, GPR1(r1)
+
+ /*
+ * Store r13 away so we can free up the scratch SPR for the SLB fault
+ * handler (needed once we start accessing the thread_struct).
+ */
+ GET_SCRATCH0(r11)
+ std r11, GPR13(r1)
+
/* Reset MSR RI so we can take SLB faults again */
li r11, MSR_RI
mtmsrd r11, 1
+ /* Store the PPR in r11 and reset to decent value */
mfspr r11, SPRN_PPR
HMT_MEDIUM
@@ -207,11 +221,11 @@ _GLOBAL(tm_reclaim)
SAVE_GPR(8, r7) /* user r8 */
SAVE_GPR(9, r7) /* user r9 */
SAVE_GPR(10, r7) /* user r10 */
- ld r3, PACATMSCRATCH(r13) /* user r1 */
+ ld r3, GPR1(r1) /* user r1 */
ld r4, GPR7(r1) /* user r7 */
ld r5, GPR11(r1) /* user r11 */
ld r6, GPR12(r1) /* user r12 */
- GET_SCRATCH0(8) /* user r13 */
+ ld r8, GPR13(r1) /* user r13 */
std r3, GPR1(r7)
std r4, GPR7(r7)
std r5, GPR11(r7)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index fd6e8c13685f..933c574e1cf7 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -525,8 +525,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned long ea, unsigned long dsisr)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long mmu_seq, pte_size;
- unsigned long gpa, gfn, hva, pfn;
+ unsigned long mmu_seq;
+ unsigned long gpa, gfn, hva;
struct kvm_memory_slot *memslot;
struct page *page = NULL;
long ret;
@@ -623,9 +623,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
*/
hva = gfn_to_hva_memslot(memslot, gfn);
if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
- pfn = page_to_pfn(page);
upgrade_write = true;
} else {
+ unsigned long pfn;
+
/* Call KVM generic code to do the slow-path check */
pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
writing, upgrade_p);
@@ -639,63 +640,45 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
}
}
- /* See if we can insert a 1GB or 2MB large PTE here */
- level = 0;
- if (page && PageCompound(page)) {
- pte_size = PAGE_SIZE << compound_order(compound_head(page));
- if (pte_size >= PUD_SIZE &&
- (gpa & (PUD_SIZE - PAGE_SIZE)) ==
- (hva & (PUD_SIZE - PAGE_SIZE))) {
- level = 2;
- pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1);
- } else if (pte_size >= PMD_SIZE &&
- (gpa & (PMD_SIZE - PAGE_SIZE)) ==
- (hva & (PMD_SIZE - PAGE_SIZE))) {
- level = 1;
- pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
- }
- }
-
/*
- * Compute the PTE value that we need to insert.
+ * Read the PTE from the process' radix tree and use that
+ * so we get the shift and attribute bits.
*/
- if (page) {
- pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE |
- _PAGE_ACCESSED;
- if (writing || upgrade_write)
- pgflags |= _PAGE_WRITE | _PAGE_DIRTY;
- pte = pfn_pte(pfn, __pgprot(pgflags));
+ local_irq_disable();
+ ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+ pte = *ptep;
+ local_irq_enable();
+
+ /* Get pte level from shift/size */
+ if (shift == PUD_SHIFT &&
+ (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+ (hva & (PUD_SIZE - PAGE_SIZE))) {
+ level = 2;
+ } else if (shift == PMD_SHIFT &&
+ (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+ (hva & (PMD_SIZE - PAGE_SIZE))) {
+ level = 1;
} else {
- /*
- * Read the PTE from the process' radix tree and use that
- * so we get the attribute bits.
- */
- local_irq_disable();
- ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
- pte = *ptep;
- local_irq_enable();
- if (shift == PUD_SHIFT &&
- (gpa & (PUD_SIZE - PAGE_SIZE)) ==
- (hva & (PUD_SIZE - PAGE_SIZE))) {
- level = 2;
- } else if (shift == PMD_SHIFT &&
- (gpa & (PMD_SIZE - PAGE_SIZE)) ==
- (hva & (PMD_SIZE - PAGE_SIZE))) {
- level = 1;
- } else if (shift && shift != PAGE_SHIFT) {
- /* Adjust PFN */
- unsigned long mask = (1ul << shift) - PAGE_SIZE;
- pte = __pte(pte_val(pte) | (hva & mask));
- }
- pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
- if (writing || upgrade_write) {
- if (pte_val(pte) & _PAGE_WRITE)
- pte = __pte(pte_val(pte) | _PAGE_DIRTY);
- } else {
- pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+ level = 0;
+ if (shift > PAGE_SHIFT) {
+ /*
+ * If the pte maps more than one page, bring over
+ * bits from the virtual address to get the real
+ * address of the specific single page we want.
+ */
+ unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+ pte = __pte(pte_val(pte) | (hva & rpnmask));
}
}
+ pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
+ if (writing || upgrade_write) {
+ if (pte_val(pte) & _PAGE_WRITE)
+ pte = __pte(pte_val(pte) | _PAGE_DIRTY);
+ } else {
+ pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+ }
+
/* Allocate space in the tree and write the PTE */
ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 506a4d400458..6821ead4b4eb 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -187,12 +187,35 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
+static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
+ unsigned long entry, unsigned long *hpa,
+ enum dma_data_direction *direction)
+{
+ long ret;
+
+ ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+
+ if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+ (*direction == DMA_BIDIRECTIONAL))) {
+ __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+ /*
+ * kvmppc_rm_tce_iommu_do_map() updates the UA cache after
+ * calling this so we still get here a valid UA.
+ */
+ if (pua && *pua)
+ mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua));
+ }
+
+ return ret;
+}
+
+static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl,
+ unsigned long entry)
{
unsigned long hpa = 0;
enum dma_data_direction dir = DMA_NONE;
- iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+ iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
}
static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -224,7 +247,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
unsigned long hpa = 0;
long ret;
- if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+ if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir))
/*
* real mode xchg can fail if struct page crosses
* a page boundary
@@ -236,7 +259,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
if (ret)
- iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+ iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
return ret;
}
@@ -282,7 +305,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
return H_CLOSED;
- ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+ ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
if (ret) {
mm_iommu_mapped_dec(mem);
/*
@@ -371,7 +394,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
return ret;
WARN_ON_ONCE_RM(1);
- kvmppc_rm_clear_tce(stit->tbl, entry);
+ kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
}
kvmppc_tce_put(stt, entry, tce);
@@ -520,7 +543,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
goto unlock_exit;
WARN_ON_ONCE_RM(1);
- kvmppc_rm_clear_tce(stit->tbl, entry);
+ kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
}
kvmppc_tce_put(stt, entry + i, tce);
@@ -571,7 +594,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
return ret;
WARN_ON_ONCE_RM(1);
- kvmppc_rm_clear_tce(stit->tbl, entry);
+ kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
}
}
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 886ed94b9c13..d05c8af4ac51 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -443,6 +443,9 @@ _GLOBAL(csum_ipv6_magic)
addc r0, r8, r9
ld r10, 0(r4)
ld r11, 8(r4)
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+ rotldi r5, r5, 8
+#endif
adde r0, r0, r10
add r5, r5, r7
adde r0, r0, r11
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 850f3b8f4da5..6ae2777c220d 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -28,6 +28,12 @@ static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
{
int err;
+ /* Make sure we aren't patching a freed init section */
+ if (init_mem_is_free && init_section_contains(exec_addr, 4)) {
+ pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr);
+ return 0;
+ }
+
__put_user_size(instr, patch_addr, 4, err);
if (err)
return err;
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 51ce091914f9..7a9886f98b0c 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -308,55 +308,6 @@ void register_page_bootmem_memmap(unsigned long section_nr,
{
}
-/*
- * We do not have access to the sparsemem vmemmap, so we fallback to
- * walking the list of sparsemem blocks which we already maintain for
- * the sake of crashdump. In the long run, we might want to maintain
- * a tree if performance of that linear walk becomes a problem.
- *
- * realmode_pfn_to_page functions can fail due to:
- * 1) As real sparsemem blocks do not lay in RAM continously (they
- * are in virtual address space which is not available in the real mode),
- * the requested page struct can be split between blocks so get_page/put_page
- * may fail.
- * 2) When huge pages are used, the get_page/put_page API will fail
- * in real mode as the linked addresses in the page struct are virtual
- * too.
- */
-struct page *realmode_pfn_to_page(unsigned long pfn)
-{
- struct vmemmap_backing *vmem_back;
- struct page *page;
- unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
- unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
-
- for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
- if (pg_va < vmem_back->virt_addr)
- continue;
-
- /* After vmemmap_list entry free is possible, need check all */
- if ((pg_va + sizeof(struct page)) <=
- (vmem_back->virt_addr + page_size)) {
- page = (struct page *) (vmem_back->phys + pg_va -
- vmem_back->virt_addr);
- return page;
- }
- }
-
- /* Probably that page struct is split between real pages */
- return NULL;
-}
-EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
-
-#else
-
-struct page *realmode_pfn_to_page(unsigned long pfn)
-{
- struct page *page = pfn_to_page(pfn);
- return page;
-}
-EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
-
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 5c8530d0c611..04ccb274a620 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -63,6 +63,7 @@
#endif
unsigned long long memory_limit;
+bool init_mem_is_free;
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
@@ -396,6 +397,7 @@ void free_initmem(void)
{
ppc_md.progress = ppc_printk_progress;
mark_initmem_nx();
+ init_mem_is_free = true;
free_initmem_default(POISON_FREE_INITMEM);
}
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index c9ee9e23845f..56c2234cc6ae 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -18,11 +18,15 @@
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/swap.h>
+#include <linux/sizes.h>
#include <asm/mmu_context.h>
#include <asm/pte-walk.h>
static DEFINE_MUTEX(mem_list_mutex);
+#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY 0x1
+#define MM_IOMMU_TABLE_GROUP_PAGE_MASK ~(SZ_4K - 1)
+
struct mm_iommu_table_group_mem_t {
struct list_head next;
struct rcu_head rcu;
@@ -263,6 +267,9 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
if (!page)
continue;
+ if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
+ SetPageDirty(page);
+
put_page(page);
mem->hpas[i] = 0;
}
@@ -360,7 +367,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
return ret;
}
-EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
unsigned long ua, unsigned long entries)
@@ -390,7 +396,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
if (pageshift > mem->pageshift)
return -EFAULT;
- *hpa = *va | (ua & ~PAGE_MASK);
+ *hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
return 0;
}
@@ -413,11 +419,31 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
if (!pa)
return -EFAULT;
- *hpa = *pa | (ua & ~PAGE_MASK);
+ *hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);
return 0;
}
-EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm);
+
+extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
+{
+ struct mm_iommu_table_group_mem_t *mem;
+ long entry;
+ void *va;
+ unsigned long *pa;
+
+ mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE);
+ if (!mem)
+ return;
+
+ entry = (ua - mem->ua) >> PAGE_SHIFT;
+ va = &mem->hpas[entry];
+
+ pa = (void *) vmalloc_to_phys(va);
+ if (!pa)
+ return;
+
+ *pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
+}
long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
{
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 35ac5422903a..59d07bd5374a 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu)
int new_nid;
/* Use associativity from first thread for all siblings */
- vphn_get_associativity(cpu, associativity);
+ if (vphn_get_associativity(cpu, associativity))
+ return cpu_to_node(cpu);
+
new_nid = associativity_to_nid(associativity);
if (new_nid < 0 || !node_possible(new_nid))
new_nid = first_online_node;
@@ -1452,7 +1454,8 @@ static struct timer_list topology_timer;
static void reset_topology_timer(void)
{
- mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
+ if (vphn_enabled)
+ mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
}
#ifdef CONFIG_SMP
diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c
index 333b1f80c435..b271b283c785 100644
--- a/arch/powerpc/mm/pkeys.c
+++ b/arch/powerpc/mm/pkeys.c
@@ -45,7 +45,7 @@ static void scan_pkey_feature(void)
* Since any pkey can be used for data or execute, we will just treat
* all keys as equal and track them as one entity.
*/
- pkeys_total = be32_to_cpu(vals[0]);
+ pkeys_total = vals[0];
pkeys_devtree_defined = true;
}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
index 6c5db1acbe8d..fe9691040f54 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c
@@ -276,7 +276,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
level_shift = entries_shift + 3;
level_shift = max_t(unsigned int, level_shift, PAGE_SHIFT);
- if ((level_shift - 3) * levels + page_shift >= 60)
+ if ((level_shift - 3) * levels + page_shift >= 55)
return -EINVAL;
/* Allocate TCE table */
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..c9fecd120d18
--- /dev/null
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_PROTOTYPES_H
+
+#include <linux/ftrace.h>
+#include <asm-generic/asm-prototypes.h>
+
+#endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index db20dc630e7e..aee603123030 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -85,15 +85,8 @@ atomic_t hart_lottery;
#ifdef CONFIG_BLK_DEV_INITRD
static void __init setup_initrd(void)
{
- extern char __initramfs_start[];
- extern unsigned long __initramfs_size;
unsigned long size;
- if (__initramfs_size > 0) {
- initrd_start = (unsigned long)(&__initramfs_start);
- initrd_end = initrd_start + __initramfs_size;
- }
-
if (initrd_start >= initrd_end) {
printk(KERN_INFO "initrd not found or empty");
goto disable;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 9a9c7a6fe925..12dc4c1af96c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -120,6 +120,7 @@ config S390
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL_RELATIVE
select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_SOFT_DIRTY
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index 80b27294c1de..ab9a0ebecc19 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -208,7 +208,7 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
walk->dst.virt.addr, walk->src.virt.addr, n);
if (k)
ret = blkcipher_walk_done(desc, walk, nbytes - k);
- if (n < k) {
+ if (k < n) {
if (__cbc_paes_set_key(ctx) != 0)
return blkcipher_walk_done(desc, walk, -EIO);
memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 40f651292aa7..e2d3e6c43395 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -14,41 +14,33 @@
* We use a brcl 0,2 instruction for jump labels at compile time so it
* can be easily distinguished from a hotpatch generated instruction.
*/
-static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+static inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
- ".pushsection __jump_table, \"aw\"\n"
- ".balign 8\n"
- ".quad 0b, %l[label], %0\n"
- ".popsection\n"
- : : "X" (&((char *)key)[branch]) : : label);
-
+ asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
+ ".pushsection __jump_table,\"aw\"\n"
+ ".balign 8\n"
+ ".long 0b-.,%l[label]-.\n"
+ ".quad %0-.\n"
+ ".popsection\n"
+ : : "X" (&((char *)key)[branch]) : : label);
return false;
label:
return true;
}
-static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("0: brcl 15, %l[label]\n"
- ".pushsection __jump_table, \"aw\"\n"
- ".balign 8\n"
- ".quad 0b, %l[label], %0\n"
- ".popsection\n"
- : : "X" (&((char *)key)[branch]) : : label);
-
+ asm_volatile_goto("0: brcl 15,%l[label]\n"
+ ".pushsection __jump_table,\"aw\"\n"
+ ".balign 8\n"
+ ".long 0b-.,%l[label]-.\n"
+ ".quad %0-.\n"
+ ".popsection\n"
+ : : "X" (&((char *)key)[branch]) : : label);
return false;
label:
return true;
}
-typedef unsigned long jump_label_t;
-
-struct jump_entry {
- jump_label_t code;
- jump_label_t target;
- jump_label_t key;
-};
-
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index 43f8430fb67d..50a1798604a8 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -33,13 +33,13 @@ static void jump_label_make_branch(struct jump_entry *entry, struct insn *insn)
{
/* brcl 15,offset */
insn->opcode = 0xc0f4;
- insn->offset = (entry->target - entry->code) >> 1;
+ insn->offset = (jump_entry_target(entry) - jump_entry_code(entry)) >> 1;
}
static void jump_label_bug(struct jump_entry *entry, struct insn *expected,
struct insn *new)
{
- unsigned char *ipc = (unsigned char *)entry->code;
+ unsigned char *ipc = (unsigned char *)jump_entry_code(entry);
unsigned char *ipe = (unsigned char *)expected;
unsigned char *ipn = (unsigned char *)new;
@@ -59,6 +59,7 @@ static void __jump_label_transform(struct jump_entry *entry,
enum jump_label_type type,
int init)
{
+ void *code = (void *)jump_entry_code(entry);
struct insn old, new;
if (type == JUMP_LABEL_JMP) {
@@ -69,13 +70,13 @@ static void __jump_label_transform(struct jump_entry *entry,
jump_label_make_nop(entry, &new);
}
if (init) {
- if (memcmp((void *)entry->code, &orignop, sizeof(orignop)))
+ if (memcmp(code, &orignop, sizeof(orignop)))
jump_label_bug(entry, &orignop, &new);
} else {
- if (memcmp((void *)entry->code, &old, sizeof(old)))
+ if (memcmp(code, &old, sizeof(old)))
jump_label_bug(entry, &old, &new);
}
- s390_kernel_write((void *)entry->code, &new, sizeof(new));
+ s390_kernel_write(code, &new, sizeof(new));
}
static int __sm_arch_jump_label_transform(void *data)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index b43f8d33a369..457713f48734 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -64,6 +64,7 @@ SECTIONS
__start_ro_after_init = .;
.data..ro_after_init : {
*(.data..ro_after_init)
+ JUMP_TABLE_DATA
}
EXCEPTION_TABLE(16)
. = ALIGN(PAGE_SIZE);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f69333fd2fa3..ac5da6b0b862 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -481,7 +481,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_S390_HPAGE_1M:
r = 0;
- if (hpage)
+ if (hpage && !kvm_is_ucontrol(kvm))
r = 1;
break;
case KVM_CAP_S390_MEM_OP:
@@ -691,7 +691,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
mutex_lock(&kvm->lock);
if (kvm->created_vcpus)
r = -EBUSY;
- else if (!hpage || kvm->arch.use_cmma)
+ else if (!hpage || kvm->arch.use_cmma || kvm_is_ucontrol(kvm))
r = -EINVAL;
else {
r = 0;
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index bb44990c8212..911c7ded35f1 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -708,11 +708,13 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
vmaddr |= gaddr & ~PMD_MASK;
/* Find vma in the parent mm */
vma = find_vma(gmap->mm, vmaddr);
+ if (!vma)
+ continue;
/*
* We do not discard pages that are backed by
* hugetlbfs, so we don't have to refault them.
*/
- if (vma && is_vm_hugetlb_page(vma))
+ if (is_vm_hugetlb_page(vma))
continue;
size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
zap_page_range(vma, vmaddr, size);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a0be022f91d..603f374f871d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -119,6 +119,7 @@ config X86
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN if X86_64
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS if MMU
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8f6e7eb8ae9f..5b562e464009 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -193,7 +193,6 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
-asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1)
@@ -237,6 +236,13 @@ archscripts: scripts_basic
archheaders:
$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
+archmacros:
+ $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s
+
+ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,-
+export ASM_MACRO_FLAGS
+KBUILD_CFLAGS += $(ASM_MACRO_FLAGS)
+
###
# Kernel objects
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index eaa843a52907..a480356e0ed8 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -25,20 +25,6 @@ ENTRY(get_sev_encryption_bit)
push %ebx
push %ecx
push %edx
- push %edi
-
- /*
- * RIP-relative addressing is needed to access the encryption bit
- * variable. Since we are running in 32-bit mode we need this call/pop
- * sequence to get the proper relative addressing.
- */
- call 1f
-1: popl %edi
- subl $1b, %edi
-
- movl enc_bit(%edi), %eax
- cmpl $0, %eax
- jge .Lsev_exit
/* Check if running under a hypervisor */
movl $1, %eax
@@ -69,15 +55,12 @@ ENTRY(get_sev_encryption_bit)
movl %ebx, %eax
andl $0x3f, %eax /* Return the encryption bit location */
- movl %eax, enc_bit(%edi)
jmp .Lsev_exit
.Lno_sev:
xor %eax, %eax
- movl %eax, enc_bit(%edi)
.Lsev_exit:
- pop %edi
pop %edx
pop %ecx
pop %ebx
@@ -113,8 +96,6 @@ ENTRY(set_sev_encryption_mask)
ENDPROC(set_sev_encryption_mask)
.data
-enc_bit:
- .int 0xffffffff
#ifdef CONFIG_AMD_MEM_ENCRYPT
.balign 8
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 0eb9f92f3717..6c3ab05c231d 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -247,6 +247,7 @@ CONFIG_USB_HIDDEV=y
CONFIG_USB=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index e32fc1f274d8..ac9ae487cfeb 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -243,6 +243,7 @@ CONFIG_USB_HIDDEV=y
CONFIG_USB=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index acd11b3bf639..2a356b948720 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -379,7 +379,6 @@ static int __init crypto_aegis128_aesni_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
!boot_cpu_has(X86_FEATURE_AES) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c
index 2071c3d1ae07..dbe8bb980da1 100644
--- a/arch/x86/crypto/aegis128l-aesni-glue.c
+++ b/arch/x86/crypto/aegis128l-aesni-glue.c
@@ -379,7 +379,6 @@ static int __init crypto_aegis128l_aesni_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
!boot_cpu_has(X86_FEATURE_AES) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c
index b5f2a8fd5a71..8bebda2de92f 100644
--- a/arch/x86/crypto/aegis256-aesni-glue.c
+++ b/arch/x86/crypto/aegis256-aesni-glue.c
@@ -379,7 +379,6 @@ static int __init crypto_aegis256_aesni_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
!boot_cpu_has(X86_FEATURE_AES) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c
index 95cf857d2cbb..f40244eaf14d 100644
--- a/arch/x86/crypto/morus1280-sse2-glue.c
+++ b/arch/x86/crypto/morus1280-sse2-glue.c
@@ -40,7 +40,6 @@ MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
static int __init crypto_morus1280_sse2_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c
index 615fb7bc9a32..9afaf8f8565a 100644
--- a/arch/x86/crypto/morus640-sse2-glue.c
+++ b/arch/x86/crypto/morus640-sse2-glue.c
@@ -40,7 +40,6 @@ MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
static int __init crypto_morus640_sse2_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2) ||
- !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 352e70cd33e8..708b46a54578 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -338,7 +338,7 @@ For 32-bit we have the following conventions - kernel is built with
.macro CALL_enter_from_user_mode
#ifdef CONFIG_CONTEXT_TRACKING
#ifdef HAVE_JUMP_LABEL
- STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+ STATIC_BRANCH_JMP l_yes=.Lafter_call_\@, key=context_tracking_enabled, branch=1
#endif
call enter_from_user_mode
.Lafter_call_\@:
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f3e006bed9a7..c88ed39582a1 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void)
x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
x86_pmu.lbr_sel_map = snb_lbr_sel_map;
+
+ /* Knights Landing does have MISPREDICT bit */
+ if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
+ x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
}
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 5b0f613428c2..2c43e3055948 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -95,8 +95,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val)
*/
static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
{
- struct ipi_arg_ex **arg;
- struct ipi_arg_ex *ipi_arg;
+ struct hv_send_ipi_ex **arg;
+ struct hv_send_ipi_ex *ipi_arg;
unsigned long flags;
int nr_bank = 0;
int ret = 1;
@@ -105,7 +105,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
return false;
local_irq_save(flags);
- arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
+ arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
ipi_arg = *arg;
if (unlikely(!ipi_arg))
@@ -135,7 +135,7 @@ ipi_mask_ex_done:
static bool __send_ipi_mask(const struct cpumask *mask, int vector)
{
int cur_cpu, vcpu;
- struct ipi_arg_non_ex ipi_arg;
+ struct hv_send_ipi ipi_arg;
int ret = 1;
trace_hyperv_send_ipi_mask(mask, vector);
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 31b627b43a8e..8e4ea39e55d0 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -7,16 +7,24 @@
#include <asm/asm.h>
#ifdef CONFIG_SMP
- .macro LOCK_PREFIX
-672: lock
+.macro LOCK_PREFIX_HERE
.pushsection .smp_locks,"a"
.balign 4
- .long 672b - .
+ .long 671f - . # offset
.popsection
- .endm
+671:
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+ LOCK_PREFIX_HERE
+ lock \insn
+.endm
#else
- .macro LOCK_PREFIX
- .endm
+.macro LOCK_PREFIX_HERE
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+.endm
#endif
/*
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4cd6a3b71824..d7faa16622d8 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -31,15 +31,8 @@
*/
#ifdef CONFIG_SMP
-#define LOCK_PREFIX_HERE \
- ".pushsection .smp_locks,\"a\"\n" \
- ".balign 4\n" \
- ".long 671f - .\n" /* offset */ \
- ".popsection\n" \
- "671:"
-
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
-
+#define LOCK_PREFIX_HERE "LOCK_PREFIX_HERE\n\t"
+#define LOCK_PREFIX "LOCK_PREFIX "
#else /* ! CONFIG_SMP */
#define LOCK_PREFIX_HERE ""
#define LOCK_PREFIX ""
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 990770f9e76b..21b086786404 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -120,16 +120,32 @@
/* Exception table entry */
#ifdef __ASSEMBLY__
# define _ASM_EXTABLE_HANDLE(from, to, handler) \
- .pushsection "__ex_table","a" ; \
- .balign 4 ; \
- .long (from) - . ; \
- .long (to) - . ; \
- .long (handler) - . ; \
+ ASM_EXTABLE_HANDLE from to handler
+
+.macro ASM_EXTABLE_HANDLE from:req to:req handler:req
+ .pushsection "__ex_table","a"
+ .balign 4
+ .long (\from) - .
+ .long (\to) - .
+ .long (\handler) - .
.popsection
+.endm
+#else /* __ASSEMBLY__ */
+
+# define _ASM_EXTABLE_HANDLE(from, to, handler) \
+ "ASM_EXTABLE_HANDLE from=" #from " to=" #to \
+ " handler=\"" #handler "\"\n\t"
+
+/* For C file, we already have NOKPROBE_SYMBOL macro */
+
+#endif /* __ASSEMBLY__ */
# define _ASM_EXTABLE(from, to) \
_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+# define _ASM_EXTABLE_UA(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
+
# define _ASM_EXTABLE_FAULT(from, to) \
_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
@@ -145,6 +161,7 @@
_ASM_PTR (entry); \
.popsection
+#ifdef __ASSEMBLY__
.macro ALIGN_DESTINATION
/* check for bad alignment of destination */
movl %edi,%ecx
@@ -165,34 +182,10 @@
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
+ _ASM_EXTABLE_UA(100b, 103b)
+ _ASM_EXTABLE_UA(101b, 103b)
.endm
-
-#else
-# define _EXPAND_EXTABLE_HANDLE(x) #x
-# define _ASM_EXTABLE_HANDLE(from, to, handler) \
- " .pushsection \"__ex_table\",\"a\"\n" \
- " .balign 4\n" \
- " .long (" #from ") - .\n" \
- " .long (" #to ") - .\n" \
- " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \
- " .popsection\n"
-
-# define _ASM_EXTABLE(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
-
-# define _ASM_EXTABLE_FAULT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
-
-# define _ASM_EXTABLE_EX(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
-
-# define _ASM_EXTABLE_REFCOUNT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
-
-/* For C file, we already have NOKPROBE_SYMBOL macro */
-#endif
+#endif /* __ASSEMBLY__ */
#ifndef __ASSEMBLY__
/*
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 6804d6642767..5090035e6d16 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -4,6 +4,8 @@
#include <linux/stringify.h>
+#ifndef __ASSEMBLY__
+
/*
* Despite that some emulators terminate on UD2, we use it for WARN().
*
@@ -20,53 +22,15 @@
#define LEN_UD2 2
-#ifdef CONFIG_GENERIC_BUG
-
-#ifdef CONFIG_X86_32
-# define __BUG_REL(val) ".long " __stringify(val)
-#else
-# define __BUG_REL(val) ".long " __stringify(val) " - 2b"
-#endif
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-
-#define _BUG_FLAGS(ins, flags) \
-do { \
- asm volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \
- "\t.word %c1" "\t# bug_entry::line\n" \
- "\t.word %c2" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c3\n" \
- ".popsection" \
- : : "i" (__FILE__), "i" (__LINE__), \
- "i" (flags), \
- "i" (sizeof(struct bug_entry))); \
-} while (0)
-
-#else /* !CONFIG_DEBUG_BUGVERBOSE */
-
#define _BUG_FLAGS(ins, flags) \
do { \
- asm volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t.word %c0" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c1\n" \
- ".popsection" \
- : : "i" (flags), \
+ asm volatile("ASM_BUG ins=\"" ins "\" file=%c0 line=%c1 " \
+ "flags=%c2 size=%c3" \
+ : : "i" (__FILE__), "i" (__LINE__), \
+ "i" (flags), \
"i" (sizeof(struct bug_entry))); \
} while (0)
-#endif /* CONFIG_DEBUG_BUGVERBOSE */
-
-#else
-
-#define _BUG_FLAGS(ins, flags) asm volatile(ins)
-
-#endif /* CONFIG_GENERIC_BUG */
-
#define HAVE_ARCH_BUG
#define BUG() \
do { \
@@ -82,4 +46,54 @@ do { \
#include <asm-generic/bug.h>
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_GENERIC_BUG
+
+#ifdef CONFIG_X86_32
+.macro __BUG_REL val:req
+ .long \val
+.endm
+#else
+.macro __BUG_REL val:req
+ .long \val - 2b
+.endm
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+1: \ins
+ .pushsection __bug_table,"aw"
+2: __BUG_REL val=1b # bug_entry::bug_addr
+ __BUG_REL val=\file # bug_entry::file
+ .word \line # bug_entry::line
+ .word \flags # bug_entry::flags
+ .org 2b+\size
+ .popsection
+.endm
+
+#else /* !CONFIG_DEBUG_BUGVERBOSE */
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+1: \ins
+ .pushsection __bug_table,"aw"
+2: __BUG_REL val=1b # bug_entry::bug_addr
+ .word \flags # bug_entry::flags
+ .org 2b+\size
+ .popsection
+.endm
+
+#endif /* CONFIG_DEBUG_BUGVERBOSE */
+
+#else /* CONFIG_GENERIC_BUG */
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+ \ins
+.endm
+
+#endif /* CONFIG_GENERIC_BUG */
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aced6c9290d6..7d442722ef24 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -2,10 +2,10 @@
#ifndef _ASM_X86_CPUFEATURE_H
#define _ASM_X86_CPUFEATURE_H
-#include <asm/processor.h>
-
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
#include <asm/asm.h>
#include <linux/bitops.h>
@@ -161,37 +161,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline __pure bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto("1: jmp 6f\n"
- "2:\n"
- ".skip -(((5f-4f) - (2b-1b)) > 0) * "
- "((5f-4f) - (2b-1b)),0x90\n"
- "3:\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 4f - .\n" /* repl offset */
- " .word %P[always]\n" /* always replace */
- " .byte 3b - 1b\n" /* src len */
- " .byte 5f - 4f\n" /* repl len */
- " .byte 3b - 2b\n" /* pad len */
- ".previous\n"
- ".section .altinstr_replacement,\"ax\"\n"
- "4: jmp %l[t_no]\n"
- "5:\n"
- ".previous\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 0\n" /* no replacement */
- " .word %P[feature]\n" /* feature bit */
- " .byte 3b - 1b\n" /* src len */
- " .byte 0\n" /* repl len */
- " .byte 0\n" /* pad len */
- ".previous\n"
- ".section .altinstr_aux,\"ax\"\n"
- "6:\n"
- " testb %[bitnum],%[cap_byte]\n"
- " jnz %l[t_yes]\n"
- " jmp %l[t_no]\n"
- ".previous\n"
+ asm_volatile_goto("STATIC_CPU_HAS bitnum=%[bitnum] "
+ "cap_byte=\"%[cap_byte]\" "
+ "feature=%P[feature] t_yes=%l[t_yes] "
+ "t_no=%l[t_no] always=%P[always]"
: : [feature] "i" (bit),
[always] "i" (X86_FEATURE_ALWAYS),
[bitnum] "i" (1 << (bit & 7)),
@@ -226,5 +199,44 @@ t_no:
#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
boot_cpu_data.x86_model
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#else /* __ASSEMBLY__ */
+
+.macro STATIC_CPU_HAS bitnum:req cap_byte:req feature:req t_yes:req t_no:req always:req
+1:
+ jmp 6f
+2:
+ .skip -(((5f-4f) - (2b-1b)) > 0) * ((5f-4f) - (2b-1b)),0x90
+3:
+ .section .altinstructions,"a"
+ .long 1b - . /* src offset */
+ .long 4f - . /* repl offset */
+ .word \always /* always replace */
+ .byte 3b - 1b /* src len */
+ .byte 5f - 4f /* repl len */
+ .byte 3b - 2b /* pad len */
+ .previous
+ .section .altinstr_replacement,"ax"
+4:
+ jmp \t_no
+5:
+ .previous
+ .section .altinstructions,"a"
+ .long 1b - . /* src offset */
+ .long 0 /* no replacement */
+ .word \feature /* feature bit */
+ .byte 3b - 1b /* src len */
+ .byte 0 /* repl len */
+ .byte 0 /* pad len */
+ .previous
+ .section .altinstr_aux,"ax"
+6:
+ testb \bitnum,\cap_byte
+ jnz \t_yes
+ jmp \t_no
+ .previous
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
#endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 0d157d2a1e2a..a357031d85b5 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -62,8 +62,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
#define R_X86_64_8 14 /* Direct 8 bit sign extended */
#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM 16
+#define R_X86_64_PC64 24 /* Place relative 64-bit signed */
/*
* These are used to set parameters in the core dumps.
diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h
index f9c3a5d502f4..d8c2198d543b 100644
--- a/arch/x86/include/asm/extable.h
+++ b/arch/x86/include/asm/extable.h
@@ -29,7 +29,8 @@ struct pt_regs;
(b)->handler = (tmp).handler - (delta); \
} while (0)
-extern int fixup_exception(struct pt_regs *regs, int trapnr);
+extern int fixup_exception(struct pt_regs *regs, int trapnr,
+ unsigned long error_code, unsigned long fault_addr);
extern int fixup_bug(struct pt_regs *regs, int trapnr);
extern bool ex_has_fault_handler(unsigned long ip);
extern void early_fixup_exception(struct pt_regs *regs, int trapnr);
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index e203169931c7..6390bd8c141b 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -14,6 +14,16 @@
#ifndef _ASM_X86_FIXMAP_H
#define _ASM_X86_FIXMAP_H
+/*
+ * Exposed to assembly code for setting up initial page tables. Cannot be
+ * calculated in assembly code (fixmap entries are an enum), but is sanity
+ * checked in the actual fixmap C code to make sure that the fixmap is
+ * covered fully.
+ */
+#define FIXMAP_PMD_NUM 2
+/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */
+#define FIXMAP_PMD_TOP 507
+
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
#include <asm/acpi.h>
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a38bf5a1e37a..068ff7689268 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -226,7 +226,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
"3: movl $-2,%[err]\n\t" \
"jmp 2b\n\t" \
".popsection\n\t" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: [err] "=r" (err) \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index de4d68852d3a..13c83fe97988 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -20,7 +20,7 @@
"3:\tmov\t%3, %1\n" \
"\tjmp\t2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (oldval), "=r" (ret), "+m" (*uaddr) \
: "i" (-EFAULT), "0" (oparg), "1" (0))
@@ -36,8 +36,8 @@
"4:\tmov\t%5, %1\n" \
"\tjmp\t3b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=&a" (oldval), "=&r" (ret), \
"+m" (*uaddr), "=&r" (tem) \
: "r" (oparg), "i" (-EFAULT), "1" (0))
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index e977b6b3a538..00e01d215f74 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -726,19 +726,21 @@ struct hv_enlightened_vmcs {
#define HV_STIMER_AUTOENABLE (1ULL << 3)
#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F)
-struct ipi_arg_non_ex {
- u32 vector;
- u32 reserved;
- u64 cpu_mask;
-};
-
struct hv_vpset {
u64 format;
u64 valid_bank_mask;
u64 bank_contents[];
};
-struct ipi_arg_ex {
+/* HvCallSendSyntheticClusterIpi hypercall */
+struct hv_send_ipi {
+ u32 vector;
+ u32 reserved;
+ u64 cpu_mask;
+};
+
+/* HvCallSendSyntheticClusterIpiEx hypercall */
+struct hv_send_ipi_ex {
u32 vector;
u32 reserved;
struct hv_vpset vp_set;
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 8c0de4282659..a5fb34fe56a4 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -2,19 +2,6 @@
#ifndef _ASM_X86_JUMP_LABEL_H
#define _ASM_X86_JUMP_LABEL_H
-#ifndef HAVE_JUMP_LABEL
-/*
- * For better or for worse, if jump labels (the gcc extension) are missing,
- * then the entire static branch patching infrastructure is compiled out.
- * If that happens, the code in here will malfunction. Raise a compiler
- * error instead.
- *
- * In theory, jump labels and the static branch patching infrastructure
- * could be decoupled to fix this.
- */
-#error asm/jump_label.h included on a non-jump-label kernel
-#endif
-
#define JUMP_LABEL_NOP_SIZE 5
#ifdef CONFIG_X86_64
@@ -33,14 +20,9 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
- ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
- ".pushsection __jump_table, \"aw\" \n\t"
- _ASM_ALIGN "\n\t"
- _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
- ".popsection \n\t"
- : : "i" (key), "i" (branch) : : l_yes);
-
+ asm_volatile_goto("STATIC_BRANCH_NOP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+ "branch=\"%c1\""
+ : : "i" (key), "i" (branch) : : l_yes);
return false;
l_yes:
return true;
@@ -48,13 +30,8 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
- ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t"
- "2:\n\t"
- ".pushsection __jump_table, \"aw\" \n\t"
- _ASM_ALIGN "\n\t"
- _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
- ".popsection \n\t"
+ asm_volatile_goto("STATIC_BRANCH_JMP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+ "branch=\"%c1\""
: : "i" (key), "i" (branch) : : l_yes);
return false;
@@ -62,49 +39,28 @@ l_yes:
return true;
}
-#ifdef CONFIG_X86_64
-typedef u64 jump_label_t;
-#else
-typedef u32 jump_label_t;
-#endif
-
-struct jump_entry {
- jump_label_t code;
- jump_label_t target;
- jump_label_t key;
-};
-
#else /* __ASSEMBLY__ */
-.macro STATIC_JUMP_IF_TRUE target, key, def
-.Lstatic_jump_\@:
- .if \def
- /* Equivalent to "jmp.d32 \target" */
- .byte 0xe9
- .long \target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
- .else
- .byte STATIC_KEY_INIT_NOP
- .endif
+.macro STATIC_BRANCH_NOP l_yes:req key:req branch:req
+.Lstatic_branch_nop_\@:
+ .byte STATIC_KEY_INIT_NOP
+.Lstatic_branch_no_after_\@:
.pushsection __jump_table, "aw"
_ASM_ALIGN
- _ASM_PTR .Lstatic_jump_\@, \target, \key
+ .long .Lstatic_branch_nop_\@ - ., \l_yes - .
+ _ASM_PTR \key + \branch - .
.popsection
.endm
-.macro STATIC_JUMP_IF_FALSE target, key, def
-.Lstatic_jump_\@:
- .if \def
- .byte STATIC_KEY_INIT_NOP
- .else
- /* Equivalent to "jmp.d32 \target" */
- .byte 0xe9
- .long \target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
- .endif
+.macro STATIC_BRANCH_JMP l_yes:req key:req branch:req
+.Lstatic_branch_jmp_\@:
+ .byte 0xe9
+ .long \l_yes - .Lstatic_branch_jmp_after_\@
+.Lstatic_branch_jmp_after_\@:
.pushsection __jump_table, "aw"
_ASM_ALIGN
- _ASM_PTR .Lstatic_jump_\@, \target, \key + 1
+ .long .Lstatic_branch_jmp_\@ - ., \l_yes - .
+ _ASM_PTR \key + \branch - .
.popsection
.endm
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8e90488c3d56..09b2e3e2cf1b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -869,6 +869,8 @@ struct kvm_arch {
bool x2apic_format;
bool x2apic_broadcast_quirk_disabled;
+
+ bool guest_can_read_msr_platform_info;
};
struct kvm_vm_stat {
@@ -1022,6 +1024,7 @@ struct kvm_x86_ops {
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
+ bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
@@ -1055,6 +1058,7 @@ struct kvm_x86_ops {
bool (*umip_emulated)(void);
int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
+ void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
@@ -1482,6 +1486,7 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
+void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
int kvm_is_in_guest(void);
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c0643831706e..616f8e637bc3 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void);
+void __init mem_encrypt_free_decrypted_mem(void);
bool sme_active(void);
bool sev_active(void);
+#define __bss_decrypted __attribute__((__section__(".bss..decrypted")))
+
#else /* !CONFIG_AMD_MEM_ENCRYPT */
#define sme_me_mask 0ULL
@@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0;
static inline int __init
early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
+#define __bss_decrypted
+
#endif /* CONFIG_AMD_MEM_ENCRYPT */
/*
@@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0;
#define __sme_pa(x) (__pa(x) | sme_me_mask)
#define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask)
+extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[];
+
#endif /* __ASSEMBLY__ */
#endif /* __X86_MEM_ENCRYPT_H__ */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 4b75acc23b30..83ce282eed0a 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -346,23 +346,11 @@ extern struct pv_lock_ops pv_lock_ops;
#define paravirt_clobber(clobber) \
[paravirt_clobber] "i" (clobber)
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type, clobber) \
- "771:\n\t" insn_string "\n" "772:\n" \
- ".pushsection .parainstructions,\"a\"\n" \
- _ASM_ALIGN "\n" \
- _ASM_PTR " 771b\n" \
- " .byte " type "\n" \
- " .byte 772b-771b\n" \
- " .short " clobber "\n" \
- ".popsection\n"
-
/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string) \
- _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
+#define paravirt_call \
+ "PARAVIRT_CALL type=\"%c[paravirt_typenum]\"" \
+ " clobber=\"%c[paravirt_clobber]\"" \
+ " pv_opptr=\"%c[paravirt_opptr]\";"
/* Simple instruction patching code. */
#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
@@ -391,16 +379,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
int paravirt_disable_iospace(void);
/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
-#define PARAVIRT_CALL \
- ANNOTATE_RETPOLINE_SAFE \
- "call *%c[paravirt_opptr];"
-
-/*
* These macros are intended to wrap calls through one of the paravirt
* ops structs, so that they can be later identified and patched at
* runtime.
@@ -537,7 +515,7 @@ int paravirt_disable_iospace(void);
/* since this condition will never hold */ \
if (sizeof(rettype) > sizeof(unsigned long)) { \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -547,7 +525,7 @@ int paravirt_disable_iospace(void);
__ret = (rettype)((((u64)__edx) << 32) | __eax); \
} else { \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -574,7 +552,7 @@ int paravirt_disable_iospace(void);
PVOP_VCALL_ARGS; \
PVOP_TEST_NULL(op); \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -694,6 +672,26 @@ struct paravirt_patch_site {
extern struct paravirt_patch_site __parainstructions[],
__parainstructions_end[];
+#else /* __ASSEMBLY__ */
+
+/*
+ * This generates an indirect call based on the operation type number.
+ * The type number, computed in PARAVIRT_PATCH, is derived from the
+ * offset into the paravirt_patch_template structure, and can therefore be
+ * freely converted back into a structure offset.
+ */
+.macro PARAVIRT_CALL type:req clobber:req pv_opptr:req
+771: ANNOTATE_RETPOLINE_SAFE
+ call *\pv_opptr
+772: .pushsection .parainstructions,"a"
+ _ASM_ALIGN
+ _ASM_PTR 771b
+ .byte \type
+ .byte 772b-771b
+ .short \clobber
+ .popsection
+.endm
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 24c6cf5f16b7..60d0f9015317 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -19,9 +19,6 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte)
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd);
-#endif
*pmdp = pmd;
}
@@ -61,9 +58,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
#ifdef CONFIG_SMP
static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0));
-#endif
return __pmd(xchg((pmdval_t *)xp, 0));
}
#else
@@ -73,9 +67,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
#ifdef CONFIG_SMP
static inline pud_t native_pudp_get_and_clear(pud_t *xp)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
- pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0));
-#endif
return __pud(xchg((pudval_t *)xp, 0));
}
#else
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index ce2b59047cb8..9c85b54bf03c 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -14,6 +14,7 @@
#include <asm/processor.h>
#include <linux/bitops.h>
#include <linux/threads.h>
+#include <asm/fixmap.h>
extern p4d_t level4_kernel_pgt[512];
extern p4d_t level4_ident_pgt[512];
@@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pmd_t level2_fixmap_pgt[512];
extern pmd_t level2_ident_pgt[512];
-extern pte_t level1_fixmap_pgt[512];
+extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
extern pgd_t init_top_pgt[];
#define swapper_pg_dir init_top_pgt
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6de1fd3d0097..5e58a74bfd3a 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -37,8 +37,10 @@ struct pt_regs {
unsigned short __esh;
unsigned short fs;
unsigned short __fsh;
+ /* On interrupt, gs and __gsh store the vector number. */
unsigned short gs;
unsigned short __gsh;
+ /* On interrupt, this is the error code. */
unsigned long orig_ax;
unsigned long ip;
unsigned short cs;
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 19b90521954c..c92909da0686 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -4,6 +4,41 @@
* x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from
* PaX/grsecurity.
*/
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm.h>
+#include <asm/bug.h>
+
+.macro REFCOUNT_EXCEPTION counter:req
+ .pushsection .text..refcount
+111: lea \counter, %_ASM_CX
+112: ud2
+ ASM_UNREACHABLE
+ .popsection
+113: _ASM_EXTABLE_REFCOUNT(112b, 113b)
+.endm
+
+/* Trigger refcount exception if refcount result is negative. */
+.macro REFCOUNT_CHECK_LT_ZERO counter:req
+ js 111f
+ REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+/* Trigger refcount exception if refcount result is zero or negative. */
+.macro REFCOUNT_CHECK_LE_ZERO counter:req
+ jz 111f
+ REFCOUNT_CHECK_LT_ZERO counter="\counter"
+.endm
+
+/* Trigger refcount exception unconditionally. */
+.macro REFCOUNT_ERROR counter:req
+ jmp 111f
+ REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+#else /* __ASSEMBLY__ */
+
#include <linux/refcount.h>
#include <asm/bug.h>
@@ -15,34 +50,11 @@
* central refcount exception. The fixup address for the exception points
* back to the regular execution flow in .text.
*/
-#define _REFCOUNT_EXCEPTION \
- ".pushsection .text..refcount\n" \
- "111:\tlea %[counter], %%" _ASM_CX "\n" \
- "112:\t" ASM_UD2 "\n" \
- ASM_UNREACHABLE \
- ".popsection\n" \
- "113:\n" \
- _ASM_EXTABLE_REFCOUNT(112b, 113b)
-
-/* Trigger refcount exception if refcount result is negative. */
-#define REFCOUNT_CHECK_LT_ZERO \
- "js 111f\n\t" \
- _REFCOUNT_EXCEPTION
-
-/* Trigger refcount exception if refcount result is zero or negative. */
-#define REFCOUNT_CHECK_LE_ZERO \
- "jz 111f\n\t" \
- REFCOUNT_CHECK_LT_ZERO
-
-/* Trigger refcount exception unconditionally. */
-#define REFCOUNT_ERROR \
- "jmp 111f\n\t" \
- _REFCOUNT_EXCEPTION
static __always_inline void refcount_add(unsigned int i, refcount_t *r)
{
asm volatile(LOCK_PREFIX "addl %1,%0\n\t"
- REFCOUNT_CHECK_LT_ZERO
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: "ir" (i)
: "cc", "cx");
@@ -51,7 +63,7 @@ static __always_inline void refcount_add(unsigned int i, refcount_t *r)
static __always_inline void refcount_inc(refcount_t *r)
{
asm volatile(LOCK_PREFIX "incl %0\n\t"
- REFCOUNT_CHECK_LT_ZERO
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: : "cc", "cx");
}
@@ -59,7 +71,7 @@ static __always_inline void refcount_inc(refcount_t *r)
static __always_inline void refcount_dec(refcount_t *r)
{
asm volatile(LOCK_PREFIX "decl %0\n\t"
- REFCOUNT_CHECK_LE_ZERO
+ "REFCOUNT_CHECK_LE_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: : "cc", "cx");
}
@@ -67,13 +79,15 @@ static __always_inline void refcount_dec(refcount_t *r)
static __always_inline __must_check
bool refcount_sub_and_test(unsigned int i, refcount_t *r)
{
- GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
+ GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%0\"",
r->refs.counter, "er", i, "%0", e, "cx");
}
static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
{
- GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
+ GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl",
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%0\"",
r->refs.counter, "%0", e, "cx");
}
@@ -91,7 +105,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
/* Did we try to increment from/to an undesirable state? */
if (unlikely(c < 0 || c == INT_MAX || result < c)) {
- asm volatile(REFCOUNT_ERROR
+ asm volatile("REFCOUNT_ERROR counter=\"%[counter]\""
: : [counter] "m" (r->refs.counter)
: "cc", "cx");
break;
@@ -107,4 +121,6 @@ static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r)
return refcount_add_not_zero(1, r);
}
+#endif /* __ASSEMBLY__ */
+
#endif
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index aae77eb8491c..b5e58cc0c5e7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -198,8 +198,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
"4: movl %3,%0\n" \
" jmp 3b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=r" (err) \
: "A" (x), "r" (addr), "i" (errret), "0" (err))
@@ -340,8 +340,8 @@ do { \
" xorl %%edx,%%edx\n" \
" jmp 3b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=r" (retval), "=&A"(x) \
: "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \
"i" (errret), "0" (retval)); \
@@ -386,7 +386,7 @@ do { \
" xor"itype" %"rtype"1,%"rtype"1\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
@@ -398,7 +398,7 @@ do { \
"3: mov %3,%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
@@ -474,7 +474,7 @@ struct __large_struct { unsigned long buf[100]; };
"3: mov %3,%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r"(err) \
: ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
@@ -602,7 +602,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "q" (__new), "1" (__old) \
: "memory" \
@@ -618,7 +618,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
@@ -634,7 +634,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
@@ -653,7 +653,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 86299efa804a..fd23d5778ea1 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -377,6 +377,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index ec00d1ff5098..f7151cd03cb0 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp)
return 0;
}
+#ifdef CONFIG_PROC_FS
static int proc_apm_show(struct seq_file *m, void *v)
{
unsigned short bx;
@@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v)
units);
return 0;
}
+#endif
static int apm(void *unused)
{
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 4e588f36228f..285eb3ec4200 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e)
e <= QOS_L3_MBM_LOCAL_EVENT_ID);
}
+struct rdt_parse_data {
+ struct rdtgroup *rdtgrp;
+ char *buf;
+};
+
/**
* struct rdt_resource - attributes of an RDT resource
* @rid: The index of the resource
@@ -423,16 +428,19 @@ struct rdt_resource {
struct rdt_cache cache;
struct rdt_membw membw;
const char *format_str;
- int (*parse_ctrlval) (void *data, struct rdt_resource *r,
- struct rdt_domain *d);
+ int (*parse_ctrlval)(struct rdt_parse_data *data,
+ struct rdt_resource *r,
+ struct rdt_domain *d);
struct list_head evt_list;
int num_rmid;
unsigned int mon_scale;
unsigned long fflags;
};
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
-int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d);
extern struct mutex rdtgroup_mutex;
@@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
int update_domains(struct rdt_resource *r, int closid);
+int closids_supported(void);
void closid_free(int closid);
int alloc_rmid(void);
void free_rmid(u32 rmid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index af358ca05160..0f53049719cd 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return true;
}
-int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d)
{
- unsigned long data;
- char *buf = _buf;
+ unsigned long bw_val;
if (d->have_new_ctrl) {
rdt_last_cmd_printf("duplicate domain %d\n", d->id);
return -EINVAL;
}
- if (!bw_validate(buf, &data, r))
+ if (!bw_validate(data->buf, &bw_val, r))
return -EINVAL;
- d->new_ctrl = data;
+ d->new_ctrl = bw_val;
d->have_new_ctrl = true;
return 0;
@@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
return true;
}
-struct rdt_cbm_parse_data {
- struct rdtgroup *rdtgrp;
- char *buf;
-};
-
/*
* Read one cache bit mask (hex). Check that it is valid for the current
* resource type.
*/
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d)
{
- struct rdt_cbm_parse_data *data = _data;
struct rdtgroup *rdtgrp = data->rdtgrp;
u32 cbm_val;
@@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
static int parse_line(char *line, struct rdt_resource *r,
struct rdtgroup *rdtgrp)
{
- struct rdt_cbm_parse_data data;
+ struct rdt_parse_data data;
char *dom = NULL, *id;
struct rdt_domain *d;
unsigned long dom_id;
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+ r->rid == RDT_RESOURCE_MBA) {
+ rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
+ return -EINVAL;
+ }
+
next:
if (!line || line[0] == '\0')
return 0;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index b799c00bef09..1b8e86a5d5e1 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...)
* limited as the number of resources grows.
*/
static int closid_free_map;
+static int closid_free_map_len;
+
+int closids_supported(void)
+{
+ return closid_free_map_len;
+}
static void closid_init(void)
{
@@ -111,6 +117,7 @@ static void closid_init(void)
/* CLOSID 0 is always reserved for the default group */
closid_free_map &= ~1;
+ closid_free_map_len = rdt_min_closid;
}
static int closid_alloc(void)
@@ -802,7 +809,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
sw_shareable = 0;
exclusive = 0;
seq_printf(seq, "%d=", dom->id);
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
if (!closid_allocated(i))
continue;
mode = rdtgroup_mode_by_closid(i);
@@ -989,7 +996,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
/* Check for overlap with other resource groups */
ctrl = d->ctrl_val;
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
ctrl_b = (unsigned long *)ctrl;
mode = rdtgroup_mode_by_closid(i);
if (closid_allocated(i) && i != closid &&
@@ -1024,16 +1031,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
{
int closid = rdtgrp->closid;
struct rdt_resource *r;
+ bool has_cache = false;
struct rdt_domain *d;
for_each_alloc_enabled_rdt_resource(r) {
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
+ has_cache = true;
list_for_each_entry(d, &r->domains, list) {
if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
- rdtgrp->closid, false))
+ rdtgrp->closid, false)) {
+ rdt_last_cmd_puts("schemata overlaps\n");
return false;
+ }
}
}
+ if (!has_cache) {
+ rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n");
+ return false;
+ }
+
return true;
}
@@ -1085,7 +1103,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
rdtgrp->mode = RDT_MODE_SHAREABLE;
} else if (!strcmp(buf, "exclusive")) {
if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
- rdt_last_cmd_printf("schemata overlaps\n");
ret = -EINVAL;
goto out;
}
@@ -1155,8 +1172,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
struct rdt_resource *r;
struct rdt_domain *d;
unsigned int size;
- bool sep = false;
- u32 cbm;
+ bool sep;
+ u32 ctrl;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
@@ -1174,6 +1191,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
}
for_each_alloc_enabled_rdt_resource(r) {
+ sep = false;
seq_printf(s, "%*s:", max_name_width, r->name);
list_for_each_entry(d, &r->domains, list) {
if (sep)
@@ -1181,8 +1199,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
size = 0;
} else {
- cbm = d->ctrl_val[rdtgrp->closid];
- size = rdtgroup_cbm_to_size(r, d, cbm);
+ ctrl = (!is_mba_sc(r) ?
+ d->ctrl_val[rdtgrp->closid] :
+ d->mbps_val[rdtgrp->closid]);
+ if (r->rid == RDT_RESOURCE_MBA)
+ size = ctrl;
+ else
+ size = rdtgroup_cbm_to_size(r, d, ctrl);
}
seq_printf(s, "%d=%u", d->id, size);
sep = true;
@@ -2336,12 +2359,18 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
u32 *ctrl;
for_each_alloc_enabled_rdt_resource(r) {
+ /*
+ * Only initialize default allocations for CBM cache
+ * resources
+ */
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
list_for_each_entry(d, &r->domains, list) {
d->have_new_ctrl = false;
d->new_ctrl = r->cache.shareable_bits;
used_b = r->cache.shareable_bits;
ctrl = d->ctrl_val;
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
if (closid_allocated(i) && i != closid) {
mode = rdtgroup_mode_by_closid(i);
if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
@@ -2373,6 +2402,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
}
for_each_alloc_enabled_rdt_resource(r) {
+ /*
+ * Only initialize default allocations for CBM cache
+ * resources
+ */
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
ret = update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("failed to initialize allocations\n");
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 953b3ce92dcc..ef8fd1f2ede0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1315,7 +1315,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
local_irq_disable();
ist_end_non_atomic();
} else {
- if (!fixup_exception(regs, X86_TRAP_MC))
+ if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
mce_panic("Failed kernel mode recovery", &m, NULL);
}
diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c
index f260e452e4f8..e8c8c5d78dbd 100644
--- a/arch/x86/kernel/eisa.c
+++ b/arch/x86/kernel/eisa.c
@@ -7,11 +7,17 @@
#include <linux/eisa.h>
#include <linux/io.h>
+#include <xen/xen.h>
+
static __init int eisa_bus_probe(void)
{
- void __iomem *p = ioremap(0x0FFFD9, 4);
+ void __iomem *p;
+
+ if (xen_pv_domain() && !xen_initial_domain())
+ return 0;
- if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24))
+ p = ioremap(0x0FFFD9, 4);
+ if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24))
EISA_bus = 1;
iounmap(p);
return 0;
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 8047379e575a..ddee1f0870c4 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -35,6 +35,7 @@
#include <asm/bootparam_utils.h>
#include <asm/microcode.h>
#include <asm/kasan.h>
+#include <asm/fixmap.h>
/*
* Manage page tables very early on.
@@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr)
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
+ unsigned long vaddr, vaddr_end;
unsigned long load_delta, *p;
unsigned long pgtable_flags;
pgdval_t *pgd;
@@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
pud[511] += load_delta;
pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
- pmd[506] += load_delta;
+ for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+ pmd[i] += load_delta;
/*
* Set up the identity mapping for the switchover. These
@@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr,
sme_encrypt_kernel(bp);
/*
+ * Clear the memory encryption mask from the .bss..decrypted section.
+ * The bss section will be memset to zero later in the initialization so
+ * there is no need to zero it after changing the memory encryption
+ * attribute.
+ */
+ if (mem_encrypt_active()) {
+ vaddr = (unsigned long)__start_bss_decrypted;
+ vaddr_end = (unsigned long)__end_bss_decrypted;
+ for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+ i = pmd_index(vaddr);
+ pmd[i] -= sme_get_me_mask();
+ }
+ }
+
+ /*
* Return the SME encryption mask (if SME is active) to be used as a
* modifier for the initial pgdir entry programmed into CR3.
*/
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 15ebc2fc166e..a3618cf04cf6 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -24,6 +24,7 @@
#include "../entry/calling.h"
#include <asm/export.h>
#include <asm/nospec-branch.h>
+#include <asm/fixmap.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
@@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt)
KERNEL_IMAGE_SIZE/PMD_SIZE)
NEXT_PAGE(level2_fixmap_pgt)
- .fill 506,8,0
- .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
- /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
- .fill 5,8,0
+ .fill (512 - 4 - FIXMAP_PMD_NUM),8,0
+ pgtno = 0
+ .rept (FIXMAP_PMD_NUM)
+ .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \
+ + _PAGE_TABLE_NOENC;
+ pgtno = pgtno + 1
+ .endr
+ /* 6 MB reserved space + a 2MB hole */
+ .fill 4,8,0
NEXT_PAGE(level1_fixmap_pgt)
+ .rept (FIXMAP_PMD_NUM)
.fill 512,8,0
+ .endr
#undef PMDS
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index eeea935e9bb5..aac0c1f7e354 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -42,55 +42,40 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
void *(*poker)(void *, const void *, size_t),
int init)
{
- union jump_code_union code;
+ union jump_code_union jmp;
const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
+ const void *expect, *code;
+ int line;
+
+ jmp.jump = 0xe9;
+ jmp.offset = jump_entry_target(entry) -
+ (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
if (early_boot_irqs_disabled)
poker = text_poke_early;
if (type == JUMP_LABEL_JMP) {
if (init) {
- /*
- * Jump label is enabled for the first time.
- * So we expect a default_nop...
- */
- if (unlikely(memcmp((void *)entry->code, default_nop, 5)
- != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = default_nop; line = __LINE__;
} else {
- /*
- * ...otherwise expect an ideal_nop. Otherwise
- * something went horribly wrong.
- */
- if (unlikely(memcmp((void *)entry->code, ideal_nop, 5)
- != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = ideal_nop; line = __LINE__;
}
- code.jump = 0xe9;
- code.offset = entry->target -
- (entry->code + JUMP_LABEL_NOP_SIZE);
+ code = &jmp.code;
} else {
- /*
- * We are disabling this jump label. If it is not what
- * we think it is, then something must have gone wrong.
- * If this is the first initialization call, then we
- * are converting the default nop to the ideal nop.
- */
if (init) {
- if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = default_nop; line = __LINE__;
} else {
- code.jump = 0xe9;
- code.offset = entry->target -
- (entry->code + JUMP_LABEL_NOP_SIZE);
- if (unlikely(memcmp((void *)entry->code, &code, 5) != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = &jmp.code; line = __LINE__;
}
- memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
+
+ code = ideal_nop;
}
+ if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE))
+ bug_at((void *)jump_entry_code(entry), line);
+
/*
* Make text_poke_bp() a default fallback poker.
*
@@ -99,11 +84,14 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
* always nop being the 'currently valid' instruction
*
*/
- if (poker)
- (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
- else
- text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE,
- (void *)entry->code + JUMP_LABEL_NOP_SIZE);
+ if (poker) {
+ (*poker)((void *)jump_entry_code(entry), code,
+ JUMP_LABEL_NOP_SIZE);
+ return;
+ }
+
+ text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE,
+ (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
}
void arch_jump_label_transform(struct jump_entry *entry,
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index b0d1e81c96bb..f72a47b602e2 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1020,50 +1020,12 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
*/
if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
-
- /*
- * In case the user-specified fault handler returned
- * zero, try to fix up.
- */
- if (fixup_exception(regs, trapnr))
- return 1;
-
- /*
- * fixup routine could not handle it,
- * Let do_page_fault() fix it.
- */
}
return 0;
}
NOKPROBE_SYMBOL(kprobe_fault_handler);
-/*
- * Wrapper routine for handling exceptions.
- */
-int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
- void *data)
-{
- struct die_args *args = data;
- int ret = NOTIFY_DONE;
-
- if (args->regs && user_mode(args->regs))
- return ret;
-
- if (val == DIE_GPF) {
- /*
- * To be potentially processing a kprobe fault and to
- * trust the result from kprobe_running(), we have
- * be non-preemptible.
- */
- if (!preemptible() && kprobe_running() &&
- kprobe_fault_handler(args->regs, args->trapnr))
- ret = NOTIFY_STOP;
- }
- return ret;
-}
-NOKPROBE_SYMBOL(kprobe_exceptions_notify);
-
bool arch_within_kprobe_blacklist(unsigned long addr)
{
bool is_in_entry_trampoline_section = false;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1e6764648af3..013fe3d21dbb 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -28,6 +28,7 @@
#include <linux/sched/clock.h>
#include <linux/mm.h>
#include <linux/slab.h>
+#include <linux/set_memory.h>
#include <asm/hypervisor.h>
#include <asm/mem_encrypt.h>
@@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
static struct pvclock_vsyscall_time_info
- hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
-static struct pvclock_wall_clock wall_clock;
+ hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
+static struct pvclock_wall_clock wall_clock __bss_decrypted;
static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+static struct pvclock_vsyscall_time_info *hvclock_mem;
static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
{
@@ -236,6 +238,45 @@ static void kvm_shutdown(void)
native_machine_shutdown();
}
+static void __init kvmclock_init_mem(void)
+{
+ unsigned long ncpus;
+ unsigned int order;
+ struct page *p;
+ int r;
+
+ if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus())
+ return;
+
+ ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE;
+ order = get_order(ncpus * sizeof(*hvclock_mem));
+
+ p = alloc_pages(GFP_KERNEL, order);
+ if (!p) {
+ pr_warn("%s: failed to alloc %d pages", __func__, (1U << order));
+ return;
+ }
+
+ hvclock_mem = page_address(p);
+
+ /*
+ * hvclock is shared between the guest and the hypervisor, must
+ * be mapped decrypted.
+ */
+ if (sev_active()) {
+ r = set_memory_decrypted((unsigned long) hvclock_mem,
+ 1UL << order);
+ if (r) {
+ __free_pages(p, order);
+ hvclock_mem = NULL;
+ pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n");
+ return;
+ }
+ }
+
+ memset(hvclock_mem, 0, PAGE_SIZE << order);
+}
+
static int __init kvm_setup_vsyscall_timeinfo(void)
{
#ifdef CONFIG_X86_64
@@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void)
kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
#endif
+
+ kvmclock_init_mem();
+
return 0;
}
early_initcall(kvm_setup_vsyscall_timeinfo);
@@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu)
/* Use the static page for the first CPUs, allocate otherwise */
if (cpu < HVC_BOOT_ARRAY_SIZE)
p = &hv_clock_boot[cpu];
+ else if (hvclock_mem)
+ p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE;
else
- p = kzalloc(sizeof(*p), GFP_KERNEL);
+ return -ENOMEM;
per_cpu(hv_clock_per_cpu, cpu) = p;
return p ? 0 : -ENOMEM;
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
new file mode 100644
index 000000000000..161c95059044
--- /dev/null
+++ b/arch/x86/kernel/macros.S
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file includes headers whose assembly part includes macros which are
+ * commonly used. The macros are precompiled into assmebly file which is later
+ * assembled together with each compiled file.
+ */
+
+#include <linux/compiler.h>
+#include <asm/refcount.h>
+#include <asm/alternative-asm.h>
+#include <asm/bug.h>
+#include <asm/paravirt.h>
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/jump_label.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index f58336af095c..b052e883dd8c 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -201,6 +201,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
goto overflow;
#endif
break;
+ case R_X86_64_PC64:
+ if (*(u64 *)loc != 0)
+ goto invalid_relocation;
+ val -= (u64)loc;
+ *(u64 *)loc = val;
+ break;
default:
pr_err("%s: Unknown rela relocation: %llu\n",
me->name, ELF64_R_TYPE(rel[i].r_info));
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index afdb303285f8..8dc69d82567e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -91,7 +91,7 @@ unsigned paravirt_patch_call(void *insnbuf,
if (len < 5) {
#ifdef CONFIG_RETPOLINE
- WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+ WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr);
#endif
return len; /* call too long for patch site */
}
@@ -111,7 +111,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
if (len < 5) {
#ifdef CONFIG_RETPOLINE
- WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+ WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
#endif
return len; /* call too long for patch site */
}
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 12cbe2b88c0f..738bf42b0218 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -111,8 +111,10 @@ int arch_register_cpu(int num)
/*
* Currently CPU0 is only hotpluggable on Intel platforms. Other
* vendors can add hotplug support later.
+ * Xen PV guests don't support CPU0 hotplug at all.
*/
- if (c->x86_vendor != X86_VENDOR_INTEL)
+ if (c->x86_vendor != X86_VENDOR_INTEL ||
+ boot_cpu_has(X86_FEATURE_XENPV))
cpu0_hotpluggable = 0;
/*
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e6db475164ed..16c95cb90496 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -206,7 +206,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
}
if (!user_mode(regs)) {
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, error_code, 0))
return 0;
tsk->thread.error_code = error_code;
@@ -551,11 +551,21 @@ do_general_protection(struct pt_regs *regs, long error_code)
tsk = current;
if (!user_mode(regs)) {
- if (fixup_exception(regs, X86_TRAP_GP))
+ if (fixup_exception(regs, X86_TRAP_GP, error_code, 0))
return;
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
+
+ /*
+ * To be potentially processing a kprobe fault and to
+ * trust the result from kprobe_running(), we have to
+ * be non-preemptible.
+ */
+ if (!preemptible() && kprobe_running() &&
+ kprobe_fault_handler(regs, X86_TRAP_GP))
+ return;
+
if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
die("general protection fault", regs, error_code);
@@ -838,7 +848,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
cond_local_irq_enable(regs);
if (!user_mode(regs)) {
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, error_code, 0))
return;
task->thread.error_code = error_code;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 8bde0a419f86..5dd3317d761f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -65,6 +65,23 @@ jiffies_64 = jiffies;
#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
+/*
+ * This section contains data which will be mapped as decrypted. Memory
+ * encryption operates on a page basis. Make this section PMD-aligned
+ * to avoid splitting the pages while mapping the section early.
+ *
+ * Note: We use a separate section so that only this section gets
+ * decrypted to avoid exposing more than we wish.
+ */
+#define BSS_DECRYPTED \
+ . = ALIGN(PMD_SIZE); \
+ __start_bss_decrypted = .; \
+ *(.bss..decrypted); \
+ . = ALIGN(PAGE_SIZE); \
+ __start_bss_decrypted_unused = .; \
+ . = ALIGN(PMD_SIZE); \
+ __end_bss_decrypted = .; \
+
#else
#define X86_ALIGN_RODATA_BEGIN
@@ -74,6 +91,7 @@ jiffies_64 = jiffies;
#define ALIGN_ENTRY_TEXT_BEGIN
#define ALIGN_ENTRY_TEXT_END
+#define BSS_DECRYPTED
#endif
@@ -355,6 +373,7 @@ SECTIONS
__bss_start = .;
*(.bss..page_aligned)
*(.bss)
+ BSS_DECRYPTED
. = ALIGN(PAGE_SIZE);
__bss_stop = .;
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 17c0472c5b34..fbb0e6df121b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1344,9 +1344,8 @@ EXPORT_SYMBOL_GPL(kvm_lapic_reg_read);
static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
{
- return kvm_apic_hw_enabled(apic) &&
- addr >= apic->base_address &&
- addr < apic->base_address + LAPIC_MMIO_LENGTH;
+ return addr >= apic->base_address &&
+ addr < apic->base_address + LAPIC_MMIO_LENGTH;
}
static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
@@ -1358,6 +1357,15 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
if (!apic_mmio_in_range(apic, address))
return -EOPNOTSUPP;
+ if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) {
+ if (!kvm_check_has_quirk(vcpu->kvm,
+ KVM_X86_QUIRK_LAPIC_MMIO_HOLE))
+ return -EOPNOTSUPP;
+
+ memset(data, 0xff, len);
+ return 0;
+ }
+
kvm_lapic_reg_read(apic, offset, len, data);
return 0;
@@ -1917,6 +1925,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
if (!apic_mmio_in_range(apic, address))
return -EOPNOTSUPP;
+ if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) {
+ if (!kvm_check_has_quirk(vcpu->kvm,
+ KVM_X86_QUIRK_LAPIC_MMIO_HOLE))
+ return -EOPNOTSUPP;
+
+ return 0;
+ }
+
/*
* APIC register must be aligned on 128-bits boundary.
* 32/64/128 bits registers must be accessed thru 32 bits.
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e24ea7067373..d7e9bce6ff61 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -899,7 +899,7 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
{
/*
* Make sure the write to vcpu->mode is not reordered in front of
- * reads to sptes. If it does, kvm_commit_zap_page() can see us
+ * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us
* OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
*/
smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE);
@@ -5417,7 +5417,12 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
{
MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
- kvm_init_mmu(vcpu, true);
+ /*
+ * kvm_mmu_setup() is called only on vCPU initialization.
+ * Therefore, no need to reset mmu roots as they are not yet
+ * initialized.
+ */
+ kvm_init_mmu(vcpu, false);
}
static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 89c4c5aa15f1..d96092b35936 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1226,8 +1226,7 @@ static __init int sev_hardware_setup(void)
min_sev_asid = cpuid_edx(0x8000001F);
/* Initialize SEV ASID bitmap */
- sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid),
- sizeof(unsigned long), GFP_KERNEL);
+ sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
if (!sev_asid_bitmap)
return 1;
@@ -1405,7 +1404,7 @@ static __exit void svm_hardware_unsetup(void)
int cpu;
if (svm_sev_enabled())
- kfree(sev_asid_bitmap);
+ bitmap_free(sev_asid_bitmap);
for_each_possible_cpu(cpu)
svm_cpu_uninit(cpu);
@@ -7149,6 +7148,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.check_intercept = svm_check_intercept,
.handle_external_intr = svm_handle_external_intr,
+ .request_immediate_exit = __kvm_request_immediate_exit,
+
.sched_in = svm_sched_in,
.pmu_ops = &amd_pmu_ops,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 533a327372c8..06412ba46aa3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -397,6 +397,7 @@ struct loaded_vmcs {
int cpu;
bool launched;
bool nmi_known_unmasked;
+ bool hv_timer_armed;
/* Support for vnmi-less CPUs */
int soft_vnmi_blocked;
ktime_t entry_time;
@@ -1019,6 +1020,8 @@ struct vcpu_vmx {
int ple_window;
bool ple_window_dirty;
+ bool req_immediate_exit;
+
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
@@ -2864,6 +2867,8 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
u16 fs_sel, gs_sel;
int i;
+ vmx->req_immediate_exit = false;
+
if (vmx->loaded_cpu_state)
return;
@@ -5393,9 +5398,10 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
* To use VMXON (and later other VMX instructions), a guest
* must first be able to turn on cr4.VMXE (see handle_vmon()).
* So basically the check on whether to allow nested VMX
- * is here.
+ * is here. We operate under the default treatment of SMM,
+ * so VMX cannot be enabled under SMM.
*/
- if (!nested_vmx_allowed(vcpu))
+ if (!nested_vmx_allowed(vcpu) || is_smm(vcpu))
return 1;
}
@@ -6183,6 +6189,27 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
nested_mark_vmcs12_pages_dirty(vcpu);
}
+static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ void *vapic_page;
+ u32 vppr;
+ int rvi;
+
+ if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
+ !nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+ WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
+ return false;
+
+ rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+
+ vapic_page = kmap(vmx->nested.virtual_apic_page);
+ vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
+ kunmap(vmx->nested.virtual_apic_page);
+
+ return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
bool nested)
{
@@ -7966,6 +7993,9 @@ static __init int hardware_setup(void)
kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
}
+ if (!cpu_has_vmx_preemption_timer())
+ kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit;
+
if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
u64 vmx_msr;
@@ -9208,7 +9238,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
static int handle_preemption_timer(struct kvm_vcpu *vcpu)
{
- kvm_lapic_expired_hv_timer(vcpu);
+ if (!to_vmx(vcpu)->req_immediate_exit)
+ kvm_lapic_expired_hv_timer(vcpu);
return 1;
}
@@ -10595,24 +10626,43 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
msrs[i].host, false);
}
-static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val)
+{
+ vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val);
+ if (!vmx->loaded_vmcs->hv_timer_armed)
+ vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ vmx->loaded_vmcs->hv_timer_armed = true;
+}
+
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 tscl;
u32 delta_tsc;
- if (vmx->hv_deadline_tsc == -1)
+ if (vmx->req_immediate_exit) {
+ vmx_arm_hv_timer(vmx, 0);
return;
+ }
- tscl = rdtsc();
- if (vmx->hv_deadline_tsc > tscl)
- /* sure to be 32 bit only because checked on set_hv_timer */
- delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
- cpu_preemption_timer_multi);
- else
- delta_tsc = 0;
+ if (vmx->hv_deadline_tsc != -1) {
+ tscl = rdtsc();
+ if (vmx->hv_deadline_tsc > tscl)
+ /* set_hv_timer ensures the delta fits in 32-bits */
+ delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+ cpu_preemption_timer_multi);
+ else
+ delta_tsc = 0;
- vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+ vmx_arm_hv_timer(vmx, delta_tsc);
+ return;
+ }
+
+ if (vmx->loaded_vmcs->hv_timer_armed)
+ vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ vmx->loaded_vmcs->hv_timer_armed = false;
}
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
@@ -10672,7 +10722,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
atomic_switch_perf_msrs(vmx);
- vmx_arm_hv_timer(vcpu);
+ vmx_update_hv_timer(vcpu);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -11427,16 +11477,18 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (vcpu->arch.virtual_tsc_khz == 0)
- return;
-
- /* Make sure short timeouts reliably trigger an immediate vmexit.
- * hrtimer_start does not guarantee this. */
- if (preemption_timeout <= 1) {
+ /*
+ * A timer value of zero is architecturally guaranteed to cause
+ * a VMExit prior to executing any instructions in the guest.
+ */
+ if (preemption_timeout == 0) {
vmx_preemption_timer_fn(&vmx->nested.preemption_timer);
return;
}
+ if (vcpu->arch.virtual_tsc_khz == 0)
+ return;
+
preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
preemption_timeout *= 1000000;
do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
@@ -11646,11 +11698,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
* bits 15:8 should be zero in posted_intr_nv,
* the descriptor address has been already checked
* in nested_get_vmcs12_pages.
+ *
+ * bits 5:0 of posted_intr_desc_addr should be zero.
*/
if (nested_cpu_has_posted_intr(vmcs12) &&
(!nested_cpu_has_vid(vmcs12) ||
!nested_exit_intr_ack_set(vcpu) ||
- vmcs12->posted_intr_nv & 0xff00))
+ (vmcs12->posted_intr_nv & 0xff00) ||
+ (vmcs12->posted_intr_desc_addr & 0x3f) ||
+ (!page_address_valid(vcpu, vmcs12->posted_intr_desc_addr))))
return -EINVAL;
/* tpr shadow is needed by all apicv features. */
@@ -12076,11 +12132,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
exec_control = vmcs12->pin_based_vm_exec_control;
- /* Preemption timer setting is only taken from vmcs01. */
- exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ /* Preemption timer setting is computed directly in vmx_vcpu_run. */
exec_control |= vmcs_config.pin_based_exec_ctrl;
- if (vmx->hv_deadline_tsc == -1)
- exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ vmx->loaded_vmcs->hv_timer_armed = false;
/* Posted interrupts setting is only taken from vmcs12. */
if (nested_cpu_has_posted_intr(vmcs12)) {
@@ -12318,6 +12373,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
@@ -12863,6 +12921,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
return 0;
}
+static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+ to_vmx(vcpu)->req_immediate_exit = true;
+}
+
static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu)
{
ktime_t remaining =
@@ -13253,12 +13316,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
- if (vmx->hv_deadline_tsc == -1)
- vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
- else
- vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
+
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
@@ -13462,18 +13520,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
return -ERANGE;
vmx->hv_deadline_tsc = tscl + delta_tsc;
- vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
-
return delta_tsc == 0;
}
static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->hv_deadline_tsc = -1;
- vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
- PIN_BASED_VMX_PREEMPTION_TIMER);
+ to_vmx(vcpu)->hv_deadline_tsc = -1;
}
#endif
@@ -13954,6 +14006,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
return -EINVAL;
+ /*
+ * SMM temporarily disables VMX, so we cannot be in guest mode,
+ * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags
+ * must be zero.
+ */
+ if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags)
+ return -EINVAL;
+
if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
!(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
return -EINVAL;
@@ -14097,6 +14157,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.apicv_post_state_restore = vmx_apicv_post_state_restore,
.hwapic_irr_update = vmx_hwapic_irr_update,
.hwapic_isr_update = vmx_hwapic_isr_update,
+ .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
.sync_pir_to_irr = vmx_sync_pir_to_irr,
.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
@@ -14130,6 +14191,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.umip_emulated = vmx_umip_emulated,
.check_nested_events = vmx_check_nested_events,
+ .request_immediate_exit = vmx_request_immediate_exit,
.sched_in = vmx_sched_in,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 542f6315444d..edbf00ec56b3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -628,7 +628,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
gfn_t gfn;
int r;
- if (is_long_mode(vcpu) || !is_pae(vcpu))
+ if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
return false;
if (!test_bit(VCPU_EXREG_PDPTR,
@@ -2537,7 +2537,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_PLATFORM_INFO:
if (!msr_info->host_initiated ||
- data & ~MSR_PLATFORM_INFO_CPUID_FAULT ||
(!(data & MSR_PLATFORM_INFO_CPUID_FAULT) &&
cpuid_fault_enabled(vcpu)))
return 1;
@@ -2780,6 +2779,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vcpu->arch.osvw.status;
break;
case MSR_PLATFORM_INFO:
+ if (!msr_info->host_initiated &&
+ !vcpu->kvm->arch.guest_can_read_msr_platform_info)
+ return 1;
msr_info->data = vcpu->arch.msr_platform_info;
break;
case MSR_MISC_FEATURES_ENABLES:
@@ -2927,6 +2929,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_SPLIT_IRQCHIP:
case KVM_CAP_IMMEDIATE_EXIT:
case KVM_CAP_GET_MSR_FEATURES:
+ case KVM_CAP_MSR_PLATFORM_INFO:
r = 1;
break;
case KVM_CAP_SYNC_REGS:
@@ -4007,19 +4010,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size));
+ r = -EFAULT;
if (get_user(user_data_size, &user_kvm_nested_state->size))
- return -EFAULT;
+ break;
r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state,
user_data_size);
if (r < 0)
- return r;
+ break;
if (r > user_data_size) {
if (put_user(r, &user_kvm_nested_state->size))
- return -EFAULT;
- return -E2BIG;
+ r = -EFAULT;
+ else
+ r = -E2BIG;
+ break;
}
+
r = 0;
break;
}
@@ -4031,19 +4038,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
if (!kvm_x86_ops->set_nested_state)
break;
+ r = -EFAULT;
if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state)))
- return -EFAULT;
+ break;
+ r = -EINVAL;
if (kvm_state.size < sizeof(kvm_state))
- return -EINVAL;
+ break;
if (kvm_state.flags &
~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE))
- return -EINVAL;
+ break;
/* nested_run_pending implies guest_mode. */
if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING)
- return -EINVAL;
+ break;
r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
break;
@@ -4350,6 +4359,10 @@ split_irqchip_unlock:
kvm->arch.pause_in_guest = true;
r = 0;
break;
+ case KVM_CAP_MSR_PLATFORM_INFO:
+ kvm->arch.guest_can_read_msr_platform_info = cap->args[0];
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
@@ -7361,6 +7374,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+ smp_send_reschedule(vcpu->cpu);
+}
+EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit);
+
/*
* Returns 1 to let vcpu_run() continue the guest execution loop without
* exiting to the userspace. Otherwise, the value will be returned to the
@@ -7565,7 +7584,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (req_immediate_exit) {
kvm_make_request(KVM_REQ_EVENT, vcpu);
- smp_send_reschedule(vcpu->cpu);
+ kvm_x86_ops->request_immediate_exit(vcpu);
}
trace_kvm_entry(vcpu->vcpu_id);
@@ -7829,6 +7848,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
return 0;
}
+/* Swap (qemu) user FPU context for the guest FPU context. */
+static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
+{
+ preempt_disable();
+ copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
+ /* PKRU is separately restored in kvm_x86_ops->run. */
+ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+ ~XFEATURE_MASK_PKRU);
+ preempt_enable();
+ trace_kvm_fpu(1);
+}
+
+/* When vcpu_run ends, restore user space FPU context. */
+static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
+{
+ preempt_disable();
+ copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
+ copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+ preempt_enable();
+ ++vcpu->stat.fpu_reload;
+ trace_kvm_fpu(0);
+}
+
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
@@ -8177,7 +8219,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
- if (!is_long_mode(vcpu) && is_pae(vcpu)) {
+ if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
mmu_reset_needed = 1;
}
@@ -8406,29 +8448,6 @@ static void fx_init(struct kvm_vcpu *vcpu)
vcpu->arch.cr0 |= X86_CR0_ET;
}
-/* Swap (qemu) user FPU context for the guest FPU context. */
-void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
-{
- preempt_disable();
- copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
- /* PKRU is separately restored in kvm_x86_ops->run. */
- __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
- ~XFEATURE_MASK_PKRU);
- preempt_enable();
- trace_kvm_fpu(1);
-}
-
-/* When vcpu_run ends, restore user space FPU context. */
-void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
-{
- preempt_disable();
- copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
- copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
- preempt_enable();
- ++vcpu->stat.fpu_reload;
- trace_kvm_fpu(0);
-}
-
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
@@ -8852,6 +8871,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
pvclock_update_vm_gtod_copy(kvm);
+ kvm->arch.guest_can_read_msr_platform_info = true;
+
INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
@@ -9200,6 +9221,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
kvm_page_track_flush_slot(kvm, slot);
}
+static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ return (is_guest_mode(vcpu) &&
+ kvm_x86_ops->guest_apic_has_interrupt &&
+ kvm_x86_ops->guest_apic_has_interrupt(vcpu));
+}
+
static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
{
if (!list_empty_careful(&vcpu->async_pf.done))
@@ -9224,7 +9252,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
return true;
if (kvm_arch_interrupt_allowed(vcpu) &&
- kvm_cpu_has_interrupt(vcpu))
+ (kvm_cpu_has_interrupt(vcpu) ||
+ kvm_guest_apic_has_interrupt(vcpu)))
return true;
if (kvm_hv_has_stimer_pending(vcpu))
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 46e71a74e612..ad8e0906d1ea 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -273,11 +273,11 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
#define SRC(y...) \
9999: y; \
- _ASM_EXTABLE(9999b, 6001f)
+ _ASM_EXTABLE_UA(9999b, 6001f)
#define DST(y...) \
9999: y; \
- _ASM_EXTABLE(9999b, 6002f)
+ _ASM_EXTABLE_UA(9999b, 6002f)
#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 020f75cc8cf6..db4e5aa0858b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -92,26 +92,26 @@ ENTRY(copy_user_generic_unrolled)
60: jmp copy_user_handle_tail /* ecx is zerorest also */
.previous
- _ASM_EXTABLE(1b,30b)
- _ASM_EXTABLE(2b,30b)
- _ASM_EXTABLE(3b,30b)
- _ASM_EXTABLE(4b,30b)
- _ASM_EXTABLE(5b,30b)
- _ASM_EXTABLE(6b,30b)
- _ASM_EXTABLE(7b,30b)
- _ASM_EXTABLE(8b,30b)
- _ASM_EXTABLE(9b,30b)
- _ASM_EXTABLE(10b,30b)
- _ASM_EXTABLE(11b,30b)
- _ASM_EXTABLE(12b,30b)
- _ASM_EXTABLE(13b,30b)
- _ASM_EXTABLE(14b,30b)
- _ASM_EXTABLE(15b,30b)
- _ASM_EXTABLE(16b,30b)
- _ASM_EXTABLE(18b,40b)
- _ASM_EXTABLE(19b,40b)
- _ASM_EXTABLE(21b,50b)
- _ASM_EXTABLE(22b,50b)
+ _ASM_EXTABLE_UA(1b, 30b)
+ _ASM_EXTABLE_UA(2b, 30b)
+ _ASM_EXTABLE_UA(3b, 30b)
+ _ASM_EXTABLE_UA(4b, 30b)
+ _ASM_EXTABLE_UA(5b, 30b)
+ _ASM_EXTABLE_UA(6b, 30b)
+ _ASM_EXTABLE_UA(7b, 30b)
+ _ASM_EXTABLE_UA(8b, 30b)
+ _ASM_EXTABLE_UA(9b, 30b)
+ _ASM_EXTABLE_UA(10b, 30b)
+ _ASM_EXTABLE_UA(11b, 30b)
+ _ASM_EXTABLE_UA(12b, 30b)
+ _ASM_EXTABLE_UA(13b, 30b)
+ _ASM_EXTABLE_UA(14b, 30b)
+ _ASM_EXTABLE_UA(15b, 30b)
+ _ASM_EXTABLE_UA(16b, 30b)
+ _ASM_EXTABLE_UA(18b, 40b)
+ _ASM_EXTABLE_UA(19b, 40b)
+ _ASM_EXTABLE_UA(21b, 50b)
+ _ASM_EXTABLE_UA(22b, 50b)
ENDPROC(copy_user_generic_unrolled)
EXPORT_SYMBOL(copy_user_generic_unrolled)
@@ -156,8 +156,8 @@ ENTRY(copy_user_generic_string)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,11b)
- _ASM_EXTABLE(3b,12b)
+ _ASM_EXTABLE_UA(1b, 11b)
+ _ASM_EXTABLE_UA(3b, 12b)
ENDPROC(copy_user_generic_string)
EXPORT_SYMBOL(copy_user_generic_string)
@@ -189,7 +189,7 @@ ENTRY(copy_user_enhanced_fast_string)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,12b)
+ _ASM_EXTABLE_UA(1b, 12b)
ENDPROC(copy_user_enhanced_fast_string)
EXPORT_SYMBOL(copy_user_enhanced_fast_string)
@@ -319,27 +319,27 @@ ENTRY(__copy_user_nocache)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(20b,.L_fixup_8b_copy)
- _ASM_EXTABLE(21b,.L_fixup_8b_copy)
- _ASM_EXTABLE(30b,.L_fixup_4b_copy)
- _ASM_EXTABLE(31b,.L_fixup_4b_copy)
- _ASM_EXTABLE(40b,.L_fixup_1b_copy)
- _ASM_EXTABLE(41b,.L_fixup_1b_copy)
+ _ASM_EXTABLE_UA(1b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(2b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(3b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(4b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(5b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(6b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(7b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(8b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(9b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(10b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(11b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(12b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(13b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(14b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(15b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(16b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(20b, .L_fixup_8b_copy)
+ _ASM_EXTABLE_UA(21b, .L_fixup_8b_copy)
+ _ASM_EXTABLE_UA(30b, .L_fixup_4b_copy)
+ _ASM_EXTABLE_UA(31b, .L_fixup_4b_copy)
+ _ASM_EXTABLE_UA(40b, .L_fixup_1b_copy)
+ _ASM_EXTABLE_UA(41b, .L_fixup_1b_copy)
ENDPROC(__copy_user_nocache)
EXPORT_SYMBOL(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 45a53dfe1859..a4a379e79259 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -31,14 +31,18 @@
.macro source
10:
- _ASM_EXTABLE(10b, .Lbad_source)
+ _ASM_EXTABLE_UA(10b, .Lbad_source)
.endm
.macro dest
20:
- _ASM_EXTABLE(20b, .Lbad_dest)
+ _ASM_EXTABLE_UA(20b, .Lbad_dest)
.endm
+ /*
+ * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
+ * potentially unmapped kernel address.
+ */
.macro ignore L=.Lignore
30:
_ASM_EXTABLE(30b, \L)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 49b167f73215..74fdff968ea3 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -132,12 +132,12 @@ bad_get_user_8:
END(bad_get_user_8)
#endif
- _ASM_EXTABLE(1b,bad_get_user)
- _ASM_EXTABLE(2b,bad_get_user)
- _ASM_EXTABLE(3b,bad_get_user)
+ _ASM_EXTABLE_UA(1b, bad_get_user)
+ _ASM_EXTABLE_UA(2b, bad_get_user)
+ _ASM_EXTABLE_UA(3b, bad_get_user)
#ifdef CONFIG_X86_64
- _ASM_EXTABLE(4b,bad_get_user)
+ _ASM_EXTABLE_UA(4b, bad_get_user)
#else
- _ASM_EXTABLE(4b,bad_get_user_8)
- _ASM_EXTABLE(5b,bad_get_user_8)
+ _ASM_EXTABLE_UA(4b, bad_get_user_8)
+ _ASM_EXTABLE_UA(5b, bad_get_user_8)
#endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 96dce5fe2a35..d2e5c9c39601 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -94,10 +94,10 @@ bad_put_user:
EXIT
END(bad_put_user)
- _ASM_EXTABLE(1b,bad_put_user)
- _ASM_EXTABLE(2b,bad_put_user)
- _ASM_EXTABLE(3b,bad_put_user)
- _ASM_EXTABLE(4b,bad_put_user)
+ _ASM_EXTABLE_UA(1b, bad_put_user)
+ _ASM_EXTABLE_UA(2b, bad_put_user)
+ _ASM_EXTABLE_UA(3b, bad_put_user)
+ _ASM_EXTABLE_UA(4b, bad_put_user)
#ifdef CONFIG_X86_32
- _ASM_EXTABLE(5b,bad_put_user)
+ _ASM_EXTABLE_UA(5b, bad_put_user)
#endif
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7add8ba06887..71fb58d44d58 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -47,8 +47,8 @@ do { \
"3: lea 0(%2,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(0b,3b) \
- _ASM_EXTABLE(1b,2b) \
+ _ASM_EXTABLE_UA(0b, 3b) \
+ _ASM_EXTABLE_UA(1b, 2b) \
: "=&c"(size), "=&D" (__d0) \
: "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
} while (0)
@@ -153,44 +153,44 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
"101: lea 0(%%eax,%0,4),%0\n"
" jmp 100b\n"
".previous\n"
- _ASM_EXTABLE(1b,100b)
- _ASM_EXTABLE(2b,100b)
- _ASM_EXTABLE(3b,100b)
- _ASM_EXTABLE(4b,100b)
- _ASM_EXTABLE(5b,100b)
- _ASM_EXTABLE(6b,100b)
- _ASM_EXTABLE(7b,100b)
- _ASM_EXTABLE(8b,100b)
- _ASM_EXTABLE(9b,100b)
- _ASM_EXTABLE(10b,100b)
- _ASM_EXTABLE(11b,100b)
- _ASM_EXTABLE(12b,100b)
- _ASM_EXTABLE(13b,100b)
- _ASM_EXTABLE(14b,100b)
- _ASM_EXTABLE(15b,100b)
- _ASM_EXTABLE(16b,100b)
- _ASM_EXTABLE(17b,100b)
- _ASM_EXTABLE(18b,100b)
- _ASM_EXTABLE(19b,100b)
- _ASM_EXTABLE(20b,100b)
- _ASM_EXTABLE(21b,100b)
- _ASM_EXTABLE(22b,100b)
- _ASM_EXTABLE(23b,100b)
- _ASM_EXTABLE(24b,100b)
- _ASM_EXTABLE(25b,100b)
- _ASM_EXTABLE(26b,100b)
- _ASM_EXTABLE(27b,100b)
- _ASM_EXTABLE(28b,100b)
- _ASM_EXTABLE(29b,100b)
- _ASM_EXTABLE(30b,100b)
- _ASM_EXTABLE(31b,100b)
- _ASM_EXTABLE(32b,100b)
- _ASM_EXTABLE(33b,100b)
- _ASM_EXTABLE(34b,100b)
- _ASM_EXTABLE(35b,100b)
- _ASM_EXTABLE(36b,100b)
- _ASM_EXTABLE(37b,100b)
- _ASM_EXTABLE(99b,101b)
+ _ASM_EXTABLE_UA(1b, 100b)
+ _ASM_EXTABLE_UA(2b, 100b)
+ _ASM_EXTABLE_UA(3b, 100b)
+ _ASM_EXTABLE_UA(4b, 100b)
+ _ASM_EXTABLE_UA(5b, 100b)
+ _ASM_EXTABLE_UA(6b, 100b)
+ _ASM_EXTABLE_UA(7b, 100b)
+ _ASM_EXTABLE_UA(8b, 100b)
+ _ASM_EXTABLE_UA(9b, 100b)
+ _ASM_EXTABLE_UA(10b, 100b)
+ _ASM_EXTABLE_UA(11b, 100b)
+ _ASM_EXTABLE_UA(12b, 100b)
+ _ASM_EXTABLE_UA(13b, 100b)
+ _ASM_EXTABLE_UA(14b, 100b)
+ _ASM_EXTABLE_UA(15b, 100b)
+ _ASM_EXTABLE_UA(16b, 100b)
+ _ASM_EXTABLE_UA(17b, 100b)
+ _ASM_EXTABLE_UA(18b, 100b)
+ _ASM_EXTABLE_UA(19b, 100b)
+ _ASM_EXTABLE_UA(20b, 100b)
+ _ASM_EXTABLE_UA(21b, 100b)
+ _ASM_EXTABLE_UA(22b, 100b)
+ _ASM_EXTABLE_UA(23b, 100b)
+ _ASM_EXTABLE_UA(24b, 100b)
+ _ASM_EXTABLE_UA(25b, 100b)
+ _ASM_EXTABLE_UA(26b, 100b)
+ _ASM_EXTABLE_UA(27b, 100b)
+ _ASM_EXTABLE_UA(28b, 100b)
+ _ASM_EXTABLE_UA(29b, 100b)
+ _ASM_EXTABLE_UA(30b, 100b)
+ _ASM_EXTABLE_UA(31b, 100b)
+ _ASM_EXTABLE_UA(32b, 100b)
+ _ASM_EXTABLE_UA(33b, 100b)
+ _ASM_EXTABLE_UA(34b, 100b)
+ _ASM_EXTABLE_UA(35b, 100b)
+ _ASM_EXTABLE_UA(36b, 100b)
+ _ASM_EXTABLE_UA(37b, 100b)
+ _ASM_EXTABLE_UA(99b, 101b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
@@ -259,26 +259,26 @@ static unsigned long __copy_user_intel_nocache(void *to,
"9: lea 0(%%eax,%0,4),%0\n"
"16: jmp 8b\n"
".previous\n"
- _ASM_EXTABLE(0b,16b)
- _ASM_EXTABLE(1b,16b)
- _ASM_EXTABLE(2b,16b)
- _ASM_EXTABLE(21b,16b)
- _ASM_EXTABLE(3b,16b)
- _ASM_EXTABLE(31b,16b)
- _ASM_EXTABLE(4b,16b)
- _ASM_EXTABLE(41b,16b)
- _ASM_EXTABLE(10b,16b)
- _ASM_EXTABLE(51b,16b)
- _ASM_EXTABLE(11b,16b)
- _ASM_EXTABLE(61b,16b)
- _ASM_EXTABLE(12b,16b)
- _ASM_EXTABLE(71b,16b)
- _ASM_EXTABLE(13b,16b)
- _ASM_EXTABLE(81b,16b)
- _ASM_EXTABLE(14b,16b)
- _ASM_EXTABLE(91b,16b)
- _ASM_EXTABLE(6b,9b)
- _ASM_EXTABLE(7b,16b)
+ _ASM_EXTABLE_UA(0b, 16b)
+ _ASM_EXTABLE_UA(1b, 16b)
+ _ASM_EXTABLE_UA(2b, 16b)
+ _ASM_EXTABLE_UA(21b, 16b)
+ _ASM_EXTABLE_UA(3b, 16b)
+ _ASM_EXTABLE_UA(31b, 16b)
+ _ASM_EXTABLE_UA(4b, 16b)
+ _ASM_EXTABLE_UA(41b, 16b)
+ _ASM_EXTABLE_UA(10b, 16b)
+ _ASM_EXTABLE_UA(51b, 16b)
+ _ASM_EXTABLE_UA(11b, 16b)
+ _ASM_EXTABLE_UA(61b, 16b)
+ _ASM_EXTABLE_UA(12b, 16b)
+ _ASM_EXTABLE_UA(71b, 16b)
+ _ASM_EXTABLE_UA(13b, 16b)
+ _ASM_EXTABLE_UA(81b, 16b)
+ _ASM_EXTABLE_UA(14b, 16b)
+ _ASM_EXTABLE_UA(91b, 16b)
+ _ASM_EXTABLE_UA(6b, 9b)
+ _ASM_EXTABLE_UA(7b, 16b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
@@ -321,9 +321,9 @@ do { \
"3: lea 0(%3,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(4b,5b) \
- _ASM_EXTABLE(0b,3b) \
- _ASM_EXTABLE(1b,2b) \
+ _ASM_EXTABLE_UA(4b, 5b) \
+ _ASM_EXTABLE_UA(0b, 3b) \
+ _ASM_EXTABLE_UA(1b, 2b) \
: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
: "3"(size), "0"(size), "1"(to), "2"(from) \
: "memory"); \
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 9c5606d88f61..fefe64436398 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -37,8 +37,8 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
"3: lea 0(%[size1],%[size8],8),%[size8]\n"
" jmp 2b\n"
".previous\n"
- _ASM_EXTABLE(0b,3b)
- _ASM_EXTABLE(1b,2b)
+ _ASM_EXTABLE_UA(0b, 3b)
+ _ASM_EXTABLE_UA(1b, 2b)
: [size8] "=&c"(size), [dst] "=&D" (__d0)
: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
clac();
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 45f5d6cf65ae..6521134057e8 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -8,7 +8,8 @@
#include <asm/kdebug.h>
typedef bool (*ex_handler_t)(const struct exception_table_entry *,
- struct pt_regs *, int);
+ struct pt_regs *, int, unsigned long,
+ unsigned long);
static inline unsigned long
ex_fixup_addr(const struct exception_table_entry *x)
@@ -22,7 +23,9 @@ ex_fixup_handler(const struct exception_table_entry *x)
}
__visible bool ex_handler_default(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
return true;
@@ -30,7 +33,9 @@ __visible bool ex_handler_default(const struct exception_table_entry *fixup,
EXPORT_SYMBOL(ex_handler_default);
__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
regs->ax = trapnr;
@@ -43,7 +48,9 @@ EXPORT_SYMBOL_GPL(ex_handler_fault);
* result of a refcount inc/dec/add/sub.
*/
__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
/* First unconditionally saturate the refcount. */
*(int *)regs->cx = INT_MIN / 2;
@@ -96,7 +103,9 @@ EXPORT_SYMBOL(ex_handler_refcount);
* out all the FPU registers) if we can't restore from the task's FPU state.
*/
__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
@@ -108,9 +117,79 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL_GPL(ex_handler_fprestore);
+/* Helper to check whether a uaccess fault indicates a kernel bug. */
+static bool bogus_uaccess(struct pt_regs *regs, int trapnr,
+ unsigned long fault_addr)
+{
+ /* This is the normal case: #PF with a fault address in userspace. */
+ if (trapnr == X86_TRAP_PF && fault_addr < TASK_SIZE_MAX)
+ return false;
+
+ /*
+ * This code can be reached for machine checks, but only if the #MC
+ * handler has already decided that it looks like a candidate for fixup.
+ * This e.g. happens when attempting to access userspace memory which
+ * the CPU can't access because of uncorrectable bad memory.
+ */
+ if (trapnr == X86_TRAP_MC)
+ return false;
+
+ /*
+ * There are two remaining exception types we might encounter here:
+ * - #PF for faulting accesses to kernel addresses
+ * - #GP for faulting accesses to noncanonical addresses
+ * Complain about anything else.
+ */
+ if (trapnr != X86_TRAP_PF && trapnr != X86_TRAP_GP) {
+ WARN(1, "unexpected trap %d in uaccess\n", trapnr);
+ return false;
+ }
+
+ /*
+ * This is a faulting memory access in kernel space, on a kernel
+ * address, in a usercopy function. This can e.g. be caused by improper
+ * use of helpers like __put_user and by improper attempts to access
+ * userspace addresses in KERNEL_DS regions.
+ * The one (semi-)legitimate exception are probe_kernel_{read,write}(),
+ * which can be invoked from places like kgdb, /dev/mem (for reading)
+ * and privileged BPF code (for reading).
+ * The probe_kernel_*() functions set the kernel_uaccess_faults_ok flag
+ * to tell us that faulting on kernel addresses, and even noncanonical
+ * addresses, in a userspace accessor does not necessarily imply a
+ * kernel bug, root might just be doing weird stuff.
+ */
+ if (current->kernel_uaccess_faults_ok)
+ return false;
+
+ /* This is bad. Refuse the fixup so that we go into die(). */
+ if (trapnr == X86_TRAP_PF) {
+ pr_emerg("BUG: pagefault on kernel address 0x%lx in non-whitelisted uaccess\n",
+ fault_addr);
+ } else {
+ pr_emerg("BUG: GPF in non-whitelisted uaccess (non-canonical address?)\n");
+ }
+ return true;
+}
+
+__visible bool ex_handler_uaccess(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
+{
+ if (bogus_uaccess(regs, trapnr, fault_addr))
+ return false;
+ regs->ip = ex_fixup_addr(fixup);
+ return true;
+}
+EXPORT_SYMBOL(ex_handler_uaccess);
+
__visible bool ex_handler_ext(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
+ if (bogus_uaccess(regs, trapnr, fault_addr))
+ return false;
/* Special hack for uaccess_err */
current->thread.uaccess_err = 1;
regs->ip = ex_fixup_addr(fixup);
@@ -119,7 +198,9 @@ __visible bool ex_handler_ext(const struct exception_table_entry *fixup,
EXPORT_SYMBOL(ex_handler_ext);
__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, regs->ip, (void *)regs->ip))
@@ -134,7 +215,9 @@ __visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup
EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, (unsigned int)regs->dx,
@@ -148,12 +231,14 @@ __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup
EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (static_cpu_has(X86_BUG_NULL_SEG))
asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
asm volatile ("mov %0, %%fs" : : "rm" (0));
- return ex_handler_default(fixup, regs, trapnr);
+ return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr);
}
EXPORT_SYMBOL(ex_handler_clear_fs);
@@ -170,7 +255,8 @@ __visible bool ex_has_fault_handler(unsigned long ip)
return handler == ex_handler_fault;
}
-int fixup_exception(struct pt_regs *regs, int trapnr)
+int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
+ unsigned long fault_addr)
{
const struct exception_table_entry *e;
ex_handler_t handler;
@@ -194,7 +280,7 @@ int fixup_exception(struct pt_regs *regs, int trapnr)
return 0;
handler = ex_fixup_handler(e);
- return handler(e, regs, trapnr);
+ return handler(e, regs, trapnr, error_code, fault_addr);
}
extern unsigned int early_recursion_flag;
@@ -230,9 +316,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
* result in a hard-to-debug panic.
*
* Keep in mind that not all vectors actually get here. Early
- * fage faults, for example, are special.
+ * page faults, for example, are special.
*/
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, regs->orig_ax, 0))
return;
if (fixup_bug(regs, trapnr))
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 47bebfe6efa7..cf16dfec2734 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -44,17 +44,19 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
static nokprobe_inline int kprobes_fault(struct pt_regs *regs)
{
- int ret = 0;
-
- /* kprobe_running() needs smp_processor_id() */
- if (kprobes_built_in() && !user_mode(regs)) {
- preempt_disable();
- if (kprobe_running() && kprobe_fault_handler(regs, 14))
- ret = 1;
- preempt_enable();
- }
-
- return ret;
+ if (!kprobes_built_in())
+ return 0;
+ if (user_mode(regs))
+ return 0;
+ /*
+ * To be potentially processing a kprobe fault and to be allowed to call
+ * kprobe_running(), we have to be non-preemptible.
+ */
+ if (preemptible())
+ return 0;
+ if (!kprobe_running())
+ return 0;
+ return kprobe_fault_handler(regs, X86_TRAP_PF);
}
/*
@@ -709,7 +711,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
int sig;
/* Are we prepared to handle this kernel fault? */
- if (fixup_exception(regs, X86_TRAP_PF)) {
+ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
/*
* Any interrupt that takes a fault gets the fixup. This makes
* the below recursive fault logic only apply to a faults from
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 7a8fc26c1115..faca978ebf9d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end)
set_memory_np_noalias(begin_ul, len_pages);
}
+void __weak mem_encrypt_free_decrypted_mem(void) { }
+
void __ref free_initmem(void)
{
e820__reallocate_tables();
+ mem_encrypt_free_decrypted_mem();
+
free_kernel_image_pages(&__init_begin, &__init_end);
}
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index b2de398d1fd3..006f373f54ab 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -348,6 +348,30 @@ bool sev_active(void)
EXPORT_SYMBOL(sev_active);
/* Architecture __weak replacement functions */
+void __init mem_encrypt_free_decrypted_mem(void)
+{
+ unsigned long vaddr, vaddr_end, npages;
+ int r;
+
+ vaddr = (unsigned long)__start_bss_decrypted_unused;
+ vaddr_end = (unsigned long)__end_bss_decrypted;
+ npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
+
+ /*
+ * The unused memory range was mapped decrypted, change the encryption
+ * attribute from decrypted to encrypted before freeing it.
+ */
+ if (mem_encrypt_active()) {
+ r = set_memory_encrypted(vaddr, npages);
+ if (r) {
+ pr_warn("failed to free unused decrypted pages\n");
+ return;
+ }
+ }
+
+ free_init_pages("unused decrypted", vaddr, vaddr_end);
+}
+
void __init mem_encrypt_init(void)
{
if (!sme_me_mask)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ae394552fb94..089e78c4effd 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
{
unsigned long address = __fix_to_virt(idx);
+#ifdef CONFIG_X86_64
+ /*
+ * Ensure that the static initial page tables are covering the
+ * fixmap completely.
+ */
+ BUILD_BUG_ON(__end_of_permanent_fixed_addresses >
+ (FIXMAP_PMD_NUM * PTRS_PER_PTE));
+#endif
+
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 05ca14222463..9959657127f4 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -85,10 +85,9 @@ pgd_t * __init efi_call_phys_prolog(void)
void __init efi_call_phys_epilog(pgd_t *save_pgd)
{
+ load_fixmap_gdt(0);
load_cr3(save_pgd);
__flush_tlb_all();
-
- load_fixmap_gdt(0);
}
void __init efi_runtime_update_mappings(void)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 3a6c8ebc8032..0b08067c45f3 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -196,6 +196,7 @@ static const char *rel_type(unsigned type)
#if ELF_BITS == 64
REL_TYPE(R_X86_64_NONE),
REL_TYPE(R_X86_64_64),
+ REL_TYPE(R_X86_64_PC64),
REL_TYPE(R_X86_64_PC32),
REL_TYPE(R_X86_64_GOT32),
REL_TYPE(R_X86_64_PLT32),
@@ -782,6 +783,15 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
add_reloc(&relocs32neg, offset);
break;
+ case R_X86_64_PC64:
+ /*
+ * Only used by jump labels
+ */
+ if (is_percpu_sym(sym, symname))
+ die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n",
+ symname);
+ break;
+
case R_X86_64_32:
case R_X86_64_32S:
case R_X86_64_64:
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
index 548197212a45..413f3519d9a1 100644
--- a/arch/x86/um/asm/elf.h
+++ b/arch/x86/um/asm/elf.h
@@ -116,8 +116,7 @@ do { \
#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
#define R_X86_64_8 14 /* Direct 8 bit sign extended */
#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM 16
+#define R_X86_64_PC64 24 /* Place relative 64-bit signed */
/*
* This is used to ensure we don't load something for the wrong architecture.
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2fe5c9b1816b..dd461c0167ef 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1907,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
/* L3_k[511] -> level2_fixmap_pgt */
convert_pfn_mfn(level3_kernel_pgt);
- /* L3_k[511][506] -> level1_fixmap_pgt */
+ /* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */
convert_pfn_mfn(level2_fixmap_pgt);
/* We get [511][511] and have Xen's version of level2_kernel_pgt */
@@ -1952,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
- set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+ for (i = 0; i < FIXMAP_PMD_NUM; i++) {
+ set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE,
+ PAGE_KERNEL_RO);
+ }
/* Pin down new L4 */
pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 7d00d4ad44d4..95997e6c0696 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -478,7 +478,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs,
irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
{
int err, ret = IRQ_NONE;
- struct pt_regs regs;
+ struct pt_regs regs = {0};
const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
uint8_t xenpmu_flags = get_xenpmu_flags();
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 04d038f3b6fa..b9ad83a0ee5d 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -4,6 +4,7 @@ config ZONE_DMA
config XTENSA
def_bool y
+ select ARCH_HAS_SG_CHAIN
select ARCH_HAS_SYNC_DMA_FOR_CPU
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_NO_COHERENT_DMA_MMAP if !MMU
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 295c120ed099..d67e30faff9c 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -64,11 +64,7 @@ endif
vardirs := $(patsubst %,arch/xtensa/variants/%/,$(variant-y))
plfdirs := $(patsubst %,arch/xtensa/platforms/%/,$(platform-y))
-ifeq ($(KBUILD_SRC),)
-KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(vardirs) $(plfdirs))
-else
KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(vardirs) $(plfdirs))
-endif
KBUILD_DEFCONFIG := iss_defconfig
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index 91907590d183..8dff506caf07 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -35,8 +35,8 @@ sed-y = -e ':a; s/\*(\([^)]*\)\.text\.unlikely/*(\1.literal.unlikely .{text}.unl
-e 's/\.{text}/.text/g'
quiet_cmd__cpp_lds_S = LDS $@
-cmd__cpp_lds_S = $(CPP) $(cpp_flags) -P -C -Uxtensa -D__ASSEMBLY__ $< \
- | sed $(sed-y) >$@
+cmd__cpp_lds_S = $(CPP) $(cpp_flags) -P -C -Uxtensa -D__ASSEMBLY__ \
+ -DLINKER_SCRIPT $< | sed $(sed-y) >$@
$(obj)/vmlinux.lds: $(src)/vmlinux.lds.S FORCE
$(call if_changed_dep,_cpp_lds_S)
diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c
index f4bbb28026f8..58709e89a8ed 100644
--- a/arch/xtensa/platforms/iss/setup.c
+++ b/arch/xtensa/platforms/iss/setup.c
@@ -78,23 +78,28 @@ static struct notifier_block iss_panic_block = {
void __init platform_setup(char **p_cmdline)
{
+ static void *argv[COMMAND_LINE_SIZE / sizeof(void *)] __initdata;
+ static char cmdline[COMMAND_LINE_SIZE] __initdata;
int argc = simc_argc();
int argv_size = simc_argv_size();
if (argc > 1) {
- void **argv = alloc_bootmem(argv_size);
- char *cmdline = alloc_bootmem(argv_size);
- int i;
+ if (argv_size > sizeof(argv)) {
+ pr_err("%s: command line too long: argv_size = %d\n",
+ __func__, argv_size);
+ } else {
+ int i;
- cmdline[0] = 0;
- simc_argv((void *)argv);
+ cmdline[0] = 0;
+ simc_argv((void *)argv);
- for (i = 1; i < argc; ++i) {
- if (i > 1)
- strcat(cmdline, " ");
- strcat(cmdline, argv[i]);
+ for (i = 1; i < argc; ++i) {
+ if (i > 1)
+ strcat(cmdline, " ");
+ strcat(cmdline, argv[i]);
+ }
+ *p_cmdline = cmdline;
}
- *p_cmdline = cmdline;
}
atomic_notifier_chain_register(&panic_notifier_list, &iss_panic_block);