summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig3
-rw-r--r--arch/arc/boot/dts/haps_hs.dts2
-rw-r--r--arch/arc/kernel/signal.c4
-rw-r--r--arch/arc/kernel/unwind.c27
-rw-r--r--arch/arm/Kconfig1
-rw-r--r--arch/arm/boot/dts/am33xx.dtsi3
-rw-r--r--arch/arm/boot/dts/armada-385-turris-omnia.dts4
-rw-r--r--arch/arm/boot/dts/at91-sam9x60ek.dts8
-rw-r--r--arch/arm/boot/dts/at91-sama5d27_som1.dtsi4
-rw-r--r--arch/arm/boot/dts/bcm2711.dtsi12
-rw-r--r--arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi2
-rw-r--r--arch/arm/boot/dts/imx6ul-14x14-evk.dtsi22
-rw-r--r--arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts1
-rw-r--r--arch/arm/boot/dts/omap4.dtsi5
-rw-r--r--arch/arm/boot/dts/omap44xx-clocks.dtsi8
-rw-r--r--arch/arm/boot/dts/omap5.dtsi5
-rw-r--r--arch/arm/boot/dts/sam9x60.dtsi9
-rw-r--r--arch/arm/mach-imx/avic.c16
-rw-r--r--arch/arm/mach-imx/common.h1
-rw-r--r--arch/arm/mach-imx/mach-imx1.c11
-rw-r--r--arch/arm/mach-imx/mach-imx25.c12
-rw-r--r--arch/arm/mach-imx/mach-imx27.c12
-rw-r--r--arch/arm/mach-imx/mach-imx31.c1
-rw-r--r--arch/arm/mach-imx/mach-imx35.c1
-rw-r--r--arch/arm/mach-imx/mm-imx3.c24
-rw-r--r--arch/arm/mach-keystone/keystone.c4
-rw-r--r--arch/arm/mach-omap1/ams-delta-fiq-handler.S1
-rw-r--r--arch/arm/mach-omap2/omap-secure.c39
-rw-r--r--arch/arm/mach-omap2/omap-secure.h1
-rw-r--r--arch/arm/mach-omap2/pmic-cpcap.c4
-rw-r--r--arch/arm/mach-omap2/sr_device.c75
-rw-r--r--arch/arm/mach-pxa/mainstone.c8
-rw-r--r--arch/arm/xen/p2m.c5
-rw-r--r--arch/arm64/Kconfig28
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi1
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi1
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi1
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h2
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts2
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi2
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h2
-rw-r--r--arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts2
-rw-r--r--arch/arm64/boot/dts/marvell/armada-cp11x.dtsi6
-rw-r--r--arch/arm64/include/asm/alternative-macros.h8
-rw-r--r--arch/arm64/include/asm/checksum.h2
-rw-r--r--arch/arm64/include/asm/cpucaps.h3
-rw-r--r--arch/arm64/include/asm/kvm_arm.h1
-rw-r--r--arch/arm64/include/asm/kvm_asm.h8
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h8
-rw-r--r--arch/arm64/include/asm/memory.h5
-rw-r--r--arch/arm64/include/asm/mmu_context.h17
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h1
-rw-r--r--arch/arm64/include/asm/pgtable.h3
-rw-r--r--arch/arm64/include/asm/processor.h2
-rw-r--r--arch/arm64/include/asm/sysreg.h20
-rw-r--r--arch/arm64/include/asm/thread_info.h2
-rw-r--r--arch/arm64/include/asm/word-at-a-time.h10
-rw-r--r--arch/arm64/kernel/cpu_errata.c8
-rw-r--r--arch/arm64/kernel/cpufeature.c6
-rw-r--r--arch/arm64/kernel/cpuinfo.c2
-rw-r--r--arch/arm64/kernel/crash_dump.c2
-rw-r--r--arch/arm64/kernel/entry.S10
-rw-r--r--arch/arm64/kernel/head.S8
-rw-r--r--arch/arm64/kernel/idreg-override.c43
-rw-r--r--arch/arm64/kernel/image-vars.h3
-rw-r--r--arch/arm64/kernel/perf_event.c2
-rw-r--r--arch/arm64/kernel/probes/kprobes.c6
-rw-r--r--arch/arm64/kernel/process.c2
-rw-r--r--arch/arm64/kernel/sleep.S2
-rw-r--r--arch/arm64/kernel/stacktrace.c9
-rw-r--r--arch/arm64/kvm/arm.c7
-rw-r--r--arch/arm64/kvm/debug.c2
-rw-r--r--arch/arm64/kvm/hyp/entry.S8
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h9
-rw-r--r--arch/arm64/kvm/hyp/nvhe/debug-sr.c12
-rw-r--r--arch/arm64/kvm/hyp/nvhe/host.S15
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-main.c12
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c14
-rw-r--r--arch/arm64/kvm/hyp/nvhe/tlb.c3
-rw-r--r--arch/arm64/kvm/hyp/pgtable.c1
-rw-r--r--arch/arm64/kvm/hyp/vgic-v3-sr.c49
-rw-r--r--arch/arm64/kvm/hyp/vhe/tlb.c3
-rw-r--r--arch/arm64/kvm/mmu.c3
-rw-r--r--arch/arm64/kvm/perf.c10
-rw-r--r--arch/arm64/kvm/pmu-emul.c10
-rw-r--r--arch/arm64/kvm/reset.c22
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3.c12
-rw-r--r--arch/arm64/mm/init.c29
-rw-r--r--arch/arm64/mm/mmu.c26
-rw-r--r--arch/csky/Kconfig2
-rw-r--r--arch/csky/include/asm/page.h2
-rw-r--r--arch/csky/kernel/probes/ftrace.c2
-rw-r--r--arch/ia64/configs/generic_defconfig2
-rw-r--r--arch/ia64/include/asm/ptrace.h8
-rw-r--r--arch/ia64/include/asm/syscall.h2
-rw-r--r--arch/ia64/kernel/err_inject.c22
-rw-r--r--arch/ia64/kernel/mca.c2
-rw-r--r--arch/ia64/kernel/ptrace.c24
-rw-r--r--arch/ia64/mm/discontig.c6
-rw-r--r--arch/m68k/include/asm/page_mm.h4
-rw-r--r--arch/m68k/include/asm/page_no.h4
-rw-r--r--arch/mips/boot/compressed/decompress.c8
-rw-r--r--arch/mips/crypto/Makefile4
-rw-r--r--arch/mips/include/asm/traps.h3
-rw-r--r--arch/mips/kernel/cpu-probe.c6
-rw-r--r--arch/mips/kernel/cpu-r3k-probe.c3
-rw-r--r--arch/mips/kernel/setup.c2
-rw-r--r--arch/mips/kernel/traps.c10
-rw-r--r--arch/mips/kernel/vmlinux.lds.S6
-rw-r--r--arch/nds32/mm/cacheflush.c2
-rw-r--r--arch/parisc/Kconfig7
-rw-r--r--arch/parisc/include/asm/cmpxchg.h2
-rw-r--r--arch/parisc/include/asm/processor.h1
-rw-r--r--arch/parisc/kernel/ptrace.c2
-rw-r--r--arch/parisc/math-emu/fpu.h32
-rw-r--r--arch/powerpc/include/asm/code-patching.h7
-rw-r--r--arch/powerpc/include/asm/cpu_has_feature.h4
-rw-r--r--arch/powerpc/include/asm/dcr-native.h8
-rw-r--r--arch/powerpc/include/asm/interrupt.h3
-rw-r--r--arch/powerpc/include/asm/mmu.h4
-rw-r--r--arch/powerpc/include/asm/ptrace.h4
-rw-r--r--arch/powerpc/include/asm/switch_to.h10
-rw-r--r--arch/powerpc/include/asm/vio.h2
-rw-r--r--arch/powerpc/kernel/Makefile4
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S2
-rw-r--r--arch/powerpc/kernel/head_book3s_32.S9
-rw-r--r--arch/powerpc/kernel/interrupt.c3
-rw-r--r--arch/powerpc/kernel/ptrace/Makefile4
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-decl.h14
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-fpu.c10
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-novsx.c8
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-view.c2
-rw-r--r--arch/powerpc/kernel/signal_32.c20
-rw-r--r--arch/powerpc/kernel/traps.c2
-rw-r--r--arch/powerpc/kernel/vdso32/gettimeofday.S11
-rw-r--r--arch/powerpc/lib/sstep.c4
-rw-r--r--arch/powerpc/perf/core-book3s.c4
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c3
-rw-r--r--arch/powerpc/platforms/pseries/mobility.c48
-rw-r--r--arch/powerpc/platforms/pseries/msi.c25
-rw-r--r--arch/powerpc/platforms/pseries/vio.c7
-rw-r--r--arch/riscv/Kconfig6
-rw-r--r--arch/riscv/Kconfig.socs2
-rw-r--r--arch/riscv/include/asm/asm-prototypes.h16
-rw-r--r--arch/riscv/include/asm/irq.h2
-rw-r--r--arch/riscv/include/asm/processor.h1
-rw-r--r--arch/riscv/include/asm/ptrace.h5
-rw-r--r--arch/riscv/include/asm/sbi.h4
-rw-r--r--arch/riscv/include/asm/timex.h2
-rw-r--r--arch/riscv/include/asm/uaccess.h7
-rw-r--r--arch/riscv/kernel/Makefile1
-rw-r--r--arch/riscv/kernel/entry.S4
-rw-r--r--arch/riscv/kernel/probes/ftrace.c29
-rw-r--r--arch/riscv/kernel/probes/kprobes.c3
-rw-r--r--arch/riscv/kernel/process.c1
-rw-r--r--arch/riscv/kernel/sbi.c2
-rw-r--r--arch/riscv/kernel/setup.c3
-rw-r--r--arch/riscv/kernel/stacktrace.c2
-rw-r--r--arch/riscv/kernel/time.c1
-rw-r--r--arch/riscv/kernel/traps.c2
-rw-r--r--arch/riscv/mm/fault.c1
-rw-r--r--arch/riscv/mm/kasan_init.c6
-rw-r--r--arch/s390/configs/debug_defconfig16
-rw-r--r--arch/s390/configs/defconfig11
-rw-r--r--arch/s390/configs/zfcpdump_defconfig3
-rw-r--r--arch/s390/include/asm/idle.h12
-rw-r--r--arch/s390/include/asm/pci.h2
-rw-r--r--arch/s390/include/asm/stacktrace.h1
-rw-r--r--arch/s390/include/asm/timex.h36
-rw-r--r--arch/s390/include/asm/vdso/data.h2
-rw-r--r--arch/s390/include/uapi/asm/hwctrset.h (renamed from arch/s390/include/uapi/asm/perf_cpum_cf_diag.h)0
-rw-r--r--arch/s390/kernel/cpcmd.c6
-rw-r--r--arch/s390/kernel/dumpstack.c12
-rw-r--r--arch/s390/kernel/entry.S7
-rw-r--r--arch/s390/kernel/idle.c12
-rw-r--r--arch/s390/kernel/irq.c2
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c2
-rw-r--r--arch/s390/kernel/perf_cpum_cf_diag.c23
-rw-r--r--arch/s390/kernel/setup.c2
-rw-r--r--arch/s390/kernel/time.c38
-rw-r--r--arch/s390/kernel/topology.c2
-rw-r--r--arch/s390/kernel/vtime.c2
-rw-r--r--arch/s390/kvm/interrupt.c2
-rw-r--r--arch/s390/pci/pci.c28
-rw-r--r--arch/s390/pci/pci_event.c18
-rw-r--r--arch/sparc/configs/sparc64_defconfig4
-rw-r--r--arch/sparc/include/asm/elf_64.h1
-rw-r--r--arch/sparc/include/asm/extable.h (renamed from arch/sparc/include/asm/extable_64.h)4
-rw-r--r--arch/sparc/include/asm/processor_32.h6
-rw-r--r--arch/sparc/include/asm/thread_info_64.h1
-rw-r--r--arch/sparc/include/asm/uaccess.h3
-rw-r--r--arch/sparc/include/asm/uaccess_32.h38
-rw-r--r--arch/sparc/include/asm/uaccess_64.h1
-rw-r--r--arch/sparc/kernel/head_32.S2
-rw-r--r--arch/sparc/kernel/head_64.S2
-rw-r--r--arch/sparc/kernel/process_32.c12
-rw-r--r--arch/sparc/kernel/setup_32.c3
-rw-r--r--arch/sparc/kernel/setup_64.c4
-rw-r--r--arch/sparc/kernel/traps_64.c13
-rw-r--r--arch/sparc/kernel/unaligned_32.c106
-rw-r--r--arch/sparc/lib/checksum_32.S64
-rw-r--r--arch/sparc/lib/copy_user.S315
-rw-r--r--arch/sparc/lib/memset.S87
-rw-r--r--arch/sparc/mm/Makefile2
-rw-r--r--arch/sparc/mm/extable.c107
-rw-r--r--arch/sparc/mm/fault_32.c80
-rw-r--r--arch/sparc/mm/mm_32.h2
-rw-r--r--arch/x86/Makefile2
-rw-r--r--arch/x86/entry/common.c3
-rw-r--r--arch/x86/entry/entry_64_compat.S2
-rw-r--r--arch/x86/events/core.c15
-rw-r--r--arch/x86/events/intel/core.c8
-rw-r--r--arch/x86/events/intel/ds.c2
-rw-r--r--arch/x86/include/asm/insn-eval.h2
-rw-r--r--arch/x86/include/asm/kfence.h7
-rw-r--r--arch/x86/include/asm/kvm_host.h38
-rw-r--r--arch/x86/include/asm/processor.h9
-rw-r--r--arch/x86/include/asm/proto.h1
-rw-r--r--arch/x86/include/asm/ptrace.h15
-rw-r--r--arch/x86/include/asm/smap.h10
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/thread_info.h15
-rw-r--r--arch/x86/include/asm/xen/page.h12
-rw-r--r--arch/x86/kernel/acpi/boot.c25
-rw-r--r--arch/x86/kernel/acpi/wakeup_64.S2
-rw-r--r--arch/x86/kernel/apic/apic.c5
-rw-r--r--arch/x86/kernel/apic/io_apic.c10
-rw-r--r--arch/x86/kernel/kprobes/ftrace.c2
-rw-r--r--arch/x86/kernel/kvm.c23
-rw-r--r--arch/x86/kernel/kvmclock.c19
-rw-r--r--arch/x86/kernel/setup.c7
-rw-r--r--arch/x86/kernel/sev-es.c22
-rw-r--r--arch/x86/kernel/signal.c24
-rw-r--r--arch/x86/kernel/smpboot.c26
-rw-r--r--arch/x86/kernel/traps.c7
-rw-r--r--arch/x86/kernel/unwind_orc.c14
-rw-r--r--arch/x86/kvm/Makefile2
-rw-r--r--arch/x86/kvm/hyperv.c91
-rw-r--r--arch/x86/kvm/hyperv.h1
-rw-r--r--arch/x86/kvm/lapic.c12
-rw-r--r--arch/x86/kvm/mmu/mmu.c9
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h5
-rw-r--r--arch/x86/kvm/mmu/tdp_iter.c30
-rw-r--r--arch/x86/kvm/mmu/tdp_iter.h4
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c77
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h24
-rw-r--r--arch/x86/kvm/svm/nested.c28
-rw-r--r--arch/x86/kvm/svm/pmu.c8
-rw-r--r--arch/x86/kvm/svm/svm.c25
-rw-r--r--arch/x86/kvm/vmx/vmx.c12
-rw-r--r--arch/x86/kvm/x86.c172
-rw-r--r--arch/x86/kvm/x86.h1
-rw-r--r--arch/x86/lib/insn-eval.c66
-rw-r--r--arch/x86/mm/mem_encrypt.c2
-rw-r--r--arch/x86/net/bpf_jit_comp.c52
-rw-r--r--arch/x86/net/bpf_jit_comp32.c11
-rw-r--r--arch/x86/platform/iris/iris.c1
-rw-r--r--arch/x86/xen/p2m.c13
-rw-r--r--arch/x86/xen/setup.c16
-rw-r--r--arch/xtensa/kernel/coprocessor.S64
-rw-r--r--arch/xtensa/mm/fault.c5
261 files changed, 1846 insertions, 1621 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 2bb30673d8e6..ecfd3520b676 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -632,13 +632,12 @@ config HAS_LTO_CLANG
def_bool y
# Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510
depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD
- depends on $(success,test $(LLVM) -eq 1)
depends on $(success,test $(LLVM_IAS) -eq 1)
depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm)
depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm)
depends on ARCH_SUPPORTS_LTO_CLANG
depends on !FTRACE_MCOUNT_USE_RECORDMCOUNT
- depends on !KASAN
+ depends on !KASAN || KASAN_HW_TAGS
depends on !GCOV_KERNEL
help
The compiler and Kconfig options support building with Clang's
diff --git a/arch/arc/boot/dts/haps_hs.dts b/arch/arc/boot/dts/haps_hs.dts
index 60d578e2781f..76ad527a0847 100644
--- a/arch/arc/boot/dts/haps_hs.dts
+++ b/arch/arc/boot/dts/haps_hs.dts
@@ -16,7 +16,7 @@
memory {
device_type = "memory";
/* CONFIG_LINUX_RAM_BASE needs to match low mem start */
- reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */
+ reg = <0x0 0x80000000 0x0 0x40000000 /* 1 GB low mem */
0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */
};
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index a78d8f745a67..fdbe06c98895 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -96,7 +96,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
sizeof(sf->uc.uc_mcontext.regs.scratch));
err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
- return err;
+ return err ? -EFAULT : 0;
}
static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
@@ -110,7 +110,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
&(sf->uc.uc_mcontext.regs.scratch),
sizeof(sf->uc.uc_mcontext.regs.scratch));
if (err)
- return err;
+ return -EFAULT;
set_current_blocked(&set);
regs->bta = uregs.scratch.bta;
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 74ad4256022e..47bab67f8649 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -187,25 +187,26 @@ static void init_unwind_table(struct unwind_table *table, const char *name,
const void *table_start, unsigned long table_size,
const u8 *header_start, unsigned long header_size)
{
- const u8 *ptr = header_start + 4;
- const u8 *end = header_start + header_size;
-
table->core.pc = (unsigned long)core_start;
table->core.range = core_size;
table->init.pc = (unsigned long)init_start;
table->init.range = init_size;
table->address = table_start;
table->size = table_size;
-
- /* See if the linker provided table looks valid. */
- if (header_size <= 4
- || header_start[0] != 1
- || (void *)read_pointer(&ptr, end, header_start[1]) != table_start
- || header_start[2] == DW_EH_PE_omit
- || read_pointer(&ptr, end, header_start[2]) <= 0
- || header_start[3] == DW_EH_PE_omit)
- header_start = NULL;
-
+ /* To avoid the pointer addition with NULL pointer.*/
+ if (header_start != NULL) {
+ const u8 *ptr = header_start + 4;
+ const u8 *end = header_start + header_size;
+ /* See if the linker provided table looks valid. */
+ if (header_size <= 4
+ || header_start[0] != 1
+ || (void *)read_pointer(&ptr, end, header_start[1])
+ != table_start
+ || header_start[2] == DW_EH_PE_omit
+ || read_pointer(&ptr, end, header_start[2]) <= 0
+ || header_start[3] == DW_EH_PE_omit)
+ header_start = NULL;
+ }
table->hdrsz = header_size;
smp_wmb();
table->header = header_start;
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index becc6d684051..2fae14857dcf 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -348,6 +348,7 @@ config ARCH_EP93XX
select ARM_AMBA
imply ARM_PATCH_PHYS_VIRT
select ARM_VIC
+ select GENERIC_IRQ_MULTI_HANDLER
select AUTO_ZRELADDR
select CLKDEV_LOOKUP
select CLKSRC_MMIO
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 5b213a1e68bb..5e33d0e88f5b 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -40,6 +40,9 @@
ethernet1 = &cpsw_emac1;
spi0 = &spi0;
spi1 = &spi1;
+ mmc0 = &mmc1;
+ mmc1 = &mmc2;
+ mmc2 = &mmc3;
};
cpus {
diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts
index 646a06420c77..5bd6a66d2c2b 100644
--- a/arch/arm/boot/dts/armada-385-turris-omnia.dts
+++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts
@@ -32,7 +32,8 @@
ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000
MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000
MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000
- MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>;
+ MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000
+ MBUS_ID(0x0c, 0x04) 0 0xf1200000 0x100000>;
internal-regs {
@@ -389,6 +390,7 @@
phy1: ethernet-phy@1 {
compatible = "ethernet-phy-ieee802.3-c22";
reg = <1>;
+ marvell,reg-init = <3 18 0 0x4985>;
/* irq is connected to &pcawan pin 7 */
};
diff --git a/arch/arm/boot/dts/at91-sam9x60ek.dts b/arch/arm/boot/dts/at91-sam9x60ek.dts
index 73b6b1f89de9..775ceb3acb6c 100644
--- a/arch/arm/boot/dts/at91-sam9x60ek.dts
+++ b/arch/arm/boot/dts/at91-sam9x60ek.dts
@@ -334,14 +334,6 @@
};
&pinctrl {
- atmel,mux-mask = <
- /* A B C */
- 0xFFFFFE7F 0xC0E0397F 0xEF00019D /* pioA */
- 0x03FFFFFF 0x02FC7E68 0x00780000 /* pioB */
- 0xffffffff 0xF83FFFFF 0xB800F3FC /* pioC */
- 0x003FFFFF 0x003F8000 0x00000000 /* pioD */
- >;
-
adc {
pinctrl_adc_default: adc_default {
atmel,pins = <AT91_PIOB 15 AT91_PERIPH_A AT91_PINCTRL_NONE>;
diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
index 1b1163858b1d..e3251f3e3eaa 100644
--- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
+++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi
@@ -84,8 +84,8 @@
pinctrl-0 = <&pinctrl_macb0_default>;
phy-mode = "rmii";
- ethernet-phy@0 {
- reg = <0x0>;
+ ethernet-phy@7 {
+ reg = <0x7>;
interrupt-parent = <&pioA>;
interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>;
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi
index 462b1dfb0385..720beec54d61 100644
--- a/arch/arm/boot/dts/bcm2711.dtsi
+++ b/arch/arm/boot/dts/bcm2711.dtsi
@@ -308,14 +308,6 @@
#reset-cells = <1>;
};
- bsc_intr: interrupt-controller@7ef00040 {
- compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc";
- reg = <0x7ef00040 0x30>;
- interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-controller;
- #interrupt-cells = <1>;
- };
-
aon_intr: interrupt-controller@7ef00100 {
compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc";
reg = <0x7ef00100 0x30>;
@@ -362,8 +354,6 @@
reg = <0x7ef04500 0x100>, <0x7ef00b00 0x300>;
reg-names = "bsc", "auto-i2c";
clock-frequency = <97500>;
- interrupt-parent = <&bsc_intr>;
- interrupts = <0>;
status = "disabled";
};
@@ -405,8 +395,6 @@
reg = <0x7ef09500 0x100>, <0x7ef05b00 0x300>;
reg-names = "bsc", "auto-i2c";
clock-frequency = <97500>;
- interrupt-parent = <&bsc_intr>;
- interrupts = <1>;
status = "disabled";
};
};
diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
index 7a1e53195785..f28a96fcf23e 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
@@ -433,6 +433,7 @@
pinctrl-0 = <&pinctrl_usdhc2>;
cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+ vmmc-supply = <&vdd_sd1_reg>;
status = "disabled";
};
@@ -442,5 +443,6 @@
&pinctrl_usdhc3_cdwp>;
cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;
wp-gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>;
+ vmmc-supply = <&vdd_sd0_reg>;
status = "disabled";
};
diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
index c593597b2119..5a1e10def6ef 100644
--- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
+++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi
@@ -210,9 +210,6 @@
micrel,led-mode = <1>;
clocks = <&clks IMX6UL_CLK_ENET_REF>;
clock-names = "rmii-ref";
- reset-gpios = <&gpio_spi 1 GPIO_ACTIVE_LOW>;
- reset-assert-us = <10000>;
- reset-deassert-us = <100>;
};
@@ -222,9 +219,6 @@
micrel,led-mode = <1>;
clocks = <&clks IMX6UL_CLK_ENET2_REF>;
clock-names = "rmii-ref";
- reset-gpios = <&gpio_spi 2 GPIO_ACTIVE_LOW>;
- reset-assert-us = <10000>;
- reset-deassert-us = <100>;
};
};
};
@@ -243,6 +237,22 @@
status = "okay";
};
+&gpio_spi {
+ eth0-phy-hog {
+ gpio-hog;
+ gpios = <1 GPIO_ACTIVE_HIGH>;
+ output-high;
+ line-name = "eth0-phy";
+ };
+
+ eth1-phy-hog {
+ gpio-hog;
+ gpios = <2 GPIO_ACTIVE_HIGH>;
+ output-high;
+ line-name = "eth1-phy";
+ };
+};
+
&i2c1 {
clock-frequency = <100000>;
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts
index ecbb2cc5b9ab..79cc45728cd2 100644
--- a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts
+++ b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts
@@ -14,5 +14,6 @@
};
&gpmi {
+ fsl,use-minimum-ecc;
status = "okay";
};
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 72e4f6481776..4a9f9496a867 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -22,6 +22,11 @@
i2c1 = &i2c2;
i2c2 = &i2c3;
i2c3 = &i2c4;
+ mmc0 = &mmc1;
+ mmc1 = &mmc2;
+ mmc2 = &mmc3;
+ mmc3 = &mmc4;
+ mmc4 = &mmc5;
serial0 = &uart1;
serial1 = &uart2;
serial2 = &uart3;
diff --git a/arch/arm/boot/dts/omap44xx-clocks.dtsi b/arch/arm/boot/dts/omap44xx-clocks.dtsi
index 532868591107..1f1c04d8f472 100644
--- a/arch/arm/boot/dts/omap44xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap44xx-clocks.dtsi
@@ -770,14 +770,6 @@
ti,max-div = <2>;
};
- sha2md5_fck: sha2md5_fck@15c8 {
- #clock-cells = <0>;
- compatible = "ti,gate-clock";
- clocks = <&l3_div_ck>;
- ti,bit-shift = <1>;
- reg = <0x15c8>;
- };
-
usb_phy_cm_clk32k: usb_phy_cm_clk32k@640 {
#clock-cells = <0>;
compatible = "ti,gate-clock";
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index e025b7c9a357..ee821d0ab364 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -25,6 +25,11 @@
i2c2 = &i2c3;
i2c3 = &i2c4;
i2c4 = &i2c5;
+ mmc0 = &mmc1;
+ mmc1 = &mmc2;
+ mmc2 = &mmc3;
+ mmc3 = &mmc4;
+ mmc4 = &mmc5;
serial0 = &uart1;
serial1 = &uart2;
serial2 = &uart3;
diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi
index 84066c1298df..ec45ced3cde6 100644
--- a/arch/arm/boot/dts/sam9x60.dtsi
+++ b/arch/arm/boot/dts/sam9x60.dtsi
@@ -606,6 +606,15 @@
compatible = "microchip,sam9x60-pinctrl", "atmel,at91sam9x5-pinctrl", "atmel,at91rm9200-pinctrl", "simple-bus";
ranges = <0xfffff400 0xfffff400 0x800>;
+ /* mux-mask corresponding to sam9x60 SoC in TFBGA228L package */
+ atmel,mux-mask = <
+ /* A B C */
+ 0xffffffff 0xffe03fff 0xef00019d /* pioA */
+ 0x03ffffff 0x02fc7e7f 0x00780000 /* pioB */
+ 0xffffffff 0xffffffff 0xf83fffff /* pioC */
+ 0x003fffff 0x003f8000 0x00000000 /* pioD */
+ >;
+
pioA: gpio@fffff400 {
compatible = "microchip,sam9x60-gpio", "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio";
reg = <0xfffff400 0x200>;
diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c
index 322caa21bcb3..21bce4049cec 100644
--- a/arch/arm/mach-imx/avic.c
+++ b/arch/arm/mach-imx/avic.c
@@ -7,6 +7,7 @@
#include <linux/module.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
+#include <linux/irqchip.h>
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_address.h>
@@ -162,7 +163,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs)
* interrupts. It registers the interrupt enable and disable functions
* to the kernel for each interrupt source.
*/
-void __init mxc_init_irq(void __iomem *irqbase)
+static void __init mxc_init_irq(void __iomem *irqbase)
{
struct device_node *np;
int irq_base;
@@ -220,3 +221,16 @@ void __init mxc_init_irq(void __iomem *irqbase)
printk(KERN_INFO "MXC IRQ initialized\n");
}
+
+static int __init imx_avic_init(struct device_node *node,
+ struct device_node *parent)
+{
+ void __iomem *avic_base;
+
+ avic_base = of_iomap(node, 0);
+ BUG_ON(!avic_base);
+ mxc_init_irq(avic_base);
+ return 0;
+}
+
+IRQCHIP_DECLARE(imx_avic, "fsl,avic", imx_avic_init);
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 2b004cc4f95e..474dedb73bc7 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -22,7 +22,6 @@ void mx35_map_io(void);
void imx21_init_early(void);
void imx31_init_early(void);
void imx35_init_early(void);
-void mxc_init_irq(void __iomem *);
void mx31_init_irq(void);
void mx35_init_irq(void);
void mxc_set_cpu_type(unsigned int type);
diff --git a/arch/arm/mach-imx/mach-imx1.c b/arch/arm/mach-imx/mach-imx1.c
index 32df3b8012f9..8eca92d66a2e 100644
--- a/arch/arm/mach-imx/mach-imx1.c
+++ b/arch/arm/mach-imx/mach-imx1.c
@@ -17,16 +17,6 @@ static void __init imx1_init_early(void)
mxc_set_cpu_type(MXC_CPU_MX1);
}
-static void __init imx1_init_irq(void)
-{
- void __iomem *avic_addr;
-
- avic_addr = ioremap(MX1_AVIC_ADDR, SZ_4K);
- WARN_ON(!avic_addr);
-
- mxc_init_irq(avic_addr);
-}
-
static const char * const imx1_dt_board_compat[] __initconst = {
"fsl,imx1",
NULL
@@ -34,7 +24,6 @@ static const char * const imx1_dt_board_compat[] __initconst = {
DT_MACHINE_START(IMX1_DT, "Freescale i.MX1 (Device Tree Support)")
.init_early = imx1_init_early,
- .init_irq = imx1_init_irq,
.dt_compat = imx1_dt_board_compat,
.restart = mxc_restart,
MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx25.c b/arch/arm/mach-imx/mach-imx25.c
index 95de48a1aa7d..51927bd08aef 100644
--- a/arch/arm/mach-imx/mach-imx25.c
+++ b/arch/arm/mach-imx/mach-imx25.c
@@ -22,17 +22,6 @@ static void __init imx25_dt_init(void)
imx_aips_allow_unprivileged_access("fsl,imx25-aips");
}
-static void __init mx25_init_irq(void)
-{
- struct device_node *np;
- void __iomem *avic_base;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
- mxc_init_irq(avic_base);
-}
-
static const char * const imx25_dt_board_compat[] __initconst = {
"fsl,imx25",
NULL
@@ -42,6 +31,5 @@ DT_MACHINE_START(IMX25_DT, "Freescale i.MX25 (Device Tree Support)")
.init_early = imx25_init_early,
.init_machine = imx25_dt_init,
.init_late = imx25_pm_init,
- .init_irq = mx25_init_irq,
.dt_compat = imx25_dt_board_compat,
MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx27.c b/arch/arm/mach-imx/mach-imx27.c
index 262422a9c196..e325c9468105 100644
--- a/arch/arm/mach-imx/mach-imx27.c
+++ b/arch/arm/mach-imx/mach-imx27.c
@@ -56,17 +56,6 @@ static void __init imx27_init_early(void)
mxc_set_cpu_type(MXC_CPU_MX27);
}
-static void __init mx27_init_irq(void)
-{
- void __iomem *avic_base;
- struct device_node *np;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
- mxc_init_irq(avic_base);
-}
-
static const char * const imx27_dt_board_compat[] __initconst = {
"fsl,imx27",
NULL
@@ -75,7 +64,6 @@ static const char * const imx27_dt_board_compat[] __initconst = {
DT_MACHINE_START(IMX27_DT, "Freescale i.MX27 (Device Tree Support)")
.map_io = mx27_map_io,
.init_early = imx27_init_early,
- .init_irq = mx27_init_irq,
.init_late = imx27_pm_init,
.dt_compat = imx27_dt_board_compat,
MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx31.c b/arch/arm/mach-imx/mach-imx31.c
index dc69dfe600df..e9a1092b6093 100644
--- a/arch/arm/mach-imx/mach-imx31.c
+++ b/arch/arm/mach-imx/mach-imx31.c
@@ -14,6 +14,5 @@ static const char * const imx31_dt_board_compat[] __initconst = {
DT_MACHINE_START(IMX31_DT, "Freescale i.MX31 (Device Tree Support)")
.map_io = mx31_map_io,
.init_early = imx31_init_early,
- .init_irq = mx31_init_irq,
.dt_compat = imx31_dt_board_compat,
MACHINE_END
diff --git a/arch/arm/mach-imx/mach-imx35.c b/arch/arm/mach-imx/mach-imx35.c
index ec5c3068715c..0fc08218b77d 100644
--- a/arch/arm/mach-imx/mach-imx35.c
+++ b/arch/arm/mach-imx/mach-imx35.c
@@ -27,6 +27,5 @@ DT_MACHINE_START(IMX35_DT, "Freescale i.MX35 (Device Tree Support)")
.l2c_aux_mask = ~0,
.map_io = mx35_map_io,
.init_early = imx35_init_early,
- .init_irq = mx35_init_irq,
.dt_compat = imx35_dt_board_compat,
MACHINE_END
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index 5056438e5b42..28db97289ee8 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -109,18 +109,6 @@ void __init imx31_init_early(void)
mx3_ccm_base = of_iomap(np, 0);
BUG_ON(!mx3_ccm_base);
}
-
-void __init mx31_init_irq(void)
-{
- void __iomem *avic_base;
- struct device_node *np;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,imx31-avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
-
- mxc_init_irq(avic_base);
-}
#endif /* ifdef CONFIG_SOC_IMX31 */
#ifdef CONFIG_SOC_IMX35
@@ -158,16 +146,4 @@ void __init imx35_init_early(void)
mx3_ccm_base = of_iomap(np, 0);
BUG_ON(!mx3_ccm_base);
}
-
-void __init mx35_init_irq(void)
-{
- void __iomem *avic_base;
- struct device_node *np;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,imx35-avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
-
- mxc_init_irq(avic_base);
-}
#endif /* ifdef CONFIG_SOC_IMX35 */
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index cd711bfc591f..2c647bdf8d25 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -65,7 +65,7 @@ static void __init keystone_init(void)
static long long __init keystone_pv_fixup(void)
{
long long offset;
- phys_addr_t mem_start, mem_end;
+ u64 mem_start, mem_end;
mem_start = memblock_start_of_DRAM();
mem_end = memblock_end_of_DRAM();
@@ -78,7 +78,7 @@ static long long __init keystone_pv_fixup(void)
if (mem_start < KEYSTONE_HIGH_PHYS_START ||
mem_end > KEYSTONE_HIGH_PHYS_END) {
pr_crit("Invalid address space for memory (%08llx-%08llx)\n",
- (u64)mem_start, (u64)mem_end);
+ mem_start, mem_end);
return 0;
}
diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
index 14a6c3eb3298..f745a65d3bd7 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S
+++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S
@@ -15,6 +15,7 @@
#include <linux/platform_data/gpio-omap.h>
#include <asm/assembler.h>
+#include <asm/irq.h>
#include "ams-delta-fiq.h"
#include "board-ams-delta.h"
diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index f70d561f37f7..0659ab4cb0af 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -9,6 +9,7 @@
*/
#include <linux/arm-smccc.h>
+#include <linux/cpu_pm.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/io.h>
@@ -20,6 +21,7 @@
#include "common.h"
#include "omap-secure.h"
+#include "soc.h"
static phys_addr_t omap_secure_memblock_base;
@@ -213,3 +215,40 @@ void __init omap_secure_init(void)
{
omap_optee_init_check();
}
+
+/*
+ * Dummy dispatcher call after core OSWR and MPU off. Updates the ROM return
+ * address after MMU has been re-enabled after CPU1 has been woken up again.
+ * Otherwise the ROM code will attempt to use the earlier physical return
+ * address that got set with MMU off when waking up CPU1. Only used on secure
+ * devices.
+ */
+static int cpu_notifier(struct notifier_block *nb, unsigned long cmd, void *v)
+{
+ switch (cmd) {
+ case CPU_CLUSTER_PM_EXIT:
+ omap_secure_dispatcher(OMAP4_PPA_SERVICE_0,
+ FLAG_START_CRITICAL,
+ 0, 0, 0, 0, 0);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block secure_notifier_block = {
+ .notifier_call = cpu_notifier,
+};
+
+static int __init secure_pm_init(void)
+{
+ if (omap_type() == OMAP2_DEVICE_TYPE_GP || !soc_is_omap44xx())
+ return 0;
+
+ cpu_pm_register_notifier(&secure_notifier_block);
+
+ return 0;
+}
+omap_arch_initcall(secure_pm_init);
diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h
index 4aaa95706d39..172069f31616 100644
--- a/arch/arm/mach-omap2/omap-secure.h
+++ b/arch/arm/mach-omap2/omap-secure.h
@@ -50,6 +50,7 @@
#define OMAP5_DRA7_MON_SET_ACR_INDEX 0x107
/* Secure PPA(Primary Protected Application) APIs */
+#define OMAP4_PPA_SERVICE_0 0x21
#define OMAP4_PPA_L2_POR_INDEX 0x23
#define OMAP4_PPA_CPU_ACTRL_SMP_INDEX 0x25
diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c
index 09076ad0576d..668dc84fd31e 100644
--- a/arch/arm/mach-omap2/pmic-cpcap.c
+++ b/arch/arm/mach-omap2/pmic-cpcap.c
@@ -246,10 +246,10 @@ int __init omap4_cpcap_init(void)
omap_voltage_register_pmic(voltdm, &omap443x_max8952_mpu);
if (of_machine_is_compatible("motorola,droid-bionic")) {
- voltdm = voltdm_lookup("mpu");
+ voltdm = voltdm_lookup("core");
omap_voltage_register_pmic(voltdm, &omap_cpcap_core);
- voltdm = voltdm_lookup("mpu");
+ voltdm = voltdm_lookup("iva");
omap_voltage_register_pmic(voltdm, &omap_cpcap_iva);
} else {
voltdm = voltdm_lookup("core");
diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c
index 62df666c2bd0..17b66f0d0dee 100644
--- a/arch/arm/mach-omap2/sr_device.c
+++ b/arch/arm/mach-omap2/sr_device.c
@@ -88,34 +88,26 @@ static void __init sr_set_nvalues(struct omap_volt_data *volt_data,
extern struct omap_sr_data omap_sr_pdata[];
-static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
+static int __init sr_init_by_name(const char *name, const char *voltdm)
{
struct omap_sr_data *sr_data = NULL;
struct omap_volt_data *volt_data;
- struct omap_smartreflex_dev_attr *sr_dev_attr;
static int i;
- if (!strncmp(oh->name, "smartreflex_mpu_iva", 20) ||
- !strncmp(oh->name, "smartreflex_mpu", 16))
+ if (!strncmp(name, "smartreflex_mpu_iva", 20) ||
+ !strncmp(name, "smartreflex_mpu", 16))
sr_data = &omap_sr_pdata[OMAP_SR_MPU];
- else if (!strncmp(oh->name, "smartreflex_core", 17))
+ else if (!strncmp(name, "smartreflex_core", 17))
sr_data = &omap_sr_pdata[OMAP_SR_CORE];
- else if (!strncmp(oh->name, "smartreflex_iva", 16))
+ else if (!strncmp(name, "smartreflex_iva", 16))
sr_data = &omap_sr_pdata[OMAP_SR_IVA];
if (!sr_data) {
- pr_err("%s: Unknown instance %s\n", __func__, oh->name);
+ pr_err("%s: Unknown instance %s\n", __func__, name);
return -EINVAL;
}
- sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr;
- if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) {
- pr_err("%s: No voltage domain specified for %s. Cannot initialize\n",
- __func__, oh->name);
- goto exit;
- }
-
- sr_data->name = oh->name;
+ sr_data->name = name;
if (cpu_is_omap343x())
sr_data->ip_type = 1;
else
@@ -136,10 +128,10 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
}
}
- sr_data->voltdm = voltdm_lookup(sr_dev_attr->sensor_voltdm_name);
+ sr_data->voltdm = voltdm_lookup(voltdm);
if (!sr_data->voltdm) {
pr_err("%s: Unable to get voltage domain pointer for VDD %s\n",
- __func__, sr_dev_attr->sensor_voltdm_name);
+ __func__, voltdm);
goto exit;
}
@@ -160,6 +152,20 @@ exit:
return 0;
}
+static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
+{
+ struct omap_smartreflex_dev_attr *sr_dev_attr;
+
+ sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr;
+ if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) {
+ pr_err("%s: No voltage domain specified for %s. Cannot initialize\n",
+ __func__, oh->name);
+ return 0;
+ }
+
+ return sr_init_by_name(oh->name, sr_dev_attr->sensor_voltdm_name);
+}
+
/*
* API to be called from board files to enable smartreflex
* autocompensation at init.
@@ -169,7 +175,42 @@ void __init omap_enable_smartreflex_on_init(void)
sr_enable_on_init = true;
}
+static const char * const omap4_sr_instances[] = {
+ "mpu",
+ "iva",
+ "core",
+};
+
+static const char * const dra7_sr_instances[] = {
+ "mpu",
+ "core",
+};
+
int __init omap_devinit_smartreflex(void)
{
+ const char * const *sr_inst;
+ int i, nr_sr = 0;
+
+ if (soc_is_omap44xx()) {
+ sr_inst = omap4_sr_instances;
+ nr_sr = ARRAY_SIZE(omap4_sr_instances);
+
+ } else if (soc_is_dra7xx()) {
+ sr_inst = dra7_sr_instances;
+ nr_sr = ARRAY_SIZE(dra7_sr_instances);
+ }
+
+ if (nr_sr) {
+ const char *name, *voltdm;
+
+ for (i = 0; i < nr_sr; i++) {
+ name = kasprintf(GFP_KERNEL, "smartreflex_%s", sr_inst[i]);
+ voltdm = sr_inst[i];
+ sr_init_by_name(name, voltdm);
+ }
+
+ return 0;
+ }
+
return omap_hwmod_for_each_by_class("smartreflex", sr_dev_init, NULL);
}
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index d1010ec26e9f..d237bd030238 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -502,16 +502,20 @@ static inline void mainstone_init_keypad(void) {}
#endif
static int mst_pcmcia0_irqs[11] = {
- [0 ... 10] = -1,
+ [0 ... 4] = -1,
[5] = MAINSTONE_S0_CD_IRQ,
+ [6 ... 7] = -1,
[8] = MAINSTONE_S0_STSCHG_IRQ,
+ [9] = -1,
[10] = MAINSTONE_S0_IRQ,
};
static int mst_pcmcia1_irqs[11] = {
- [0 ... 10] = -1,
+ [0 ... 4] = -1,
[5] = MAINSTONE_S1_CD_IRQ,
+ [6 ... 7] = -1,
[8] = MAINSTONE_S1_STSCHG_IRQ,
+ [9] = -1,
[10] = MAINSTONE_S1_IRQ,
};
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index acb464547a54..84a1cea1f43b 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -11,6 +11,7 @@
#include <xen/xen.h>
#include <xen/interface/memory.h>
+#include <xen/grant_table.h>
#include <xen/page.h>
#include <xen/swiotlb-xen.h>
@@ -109,7 +110,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
map_ops[i].status = GNTST_general_error;
unmap.host_addr = map_ops[i].host_addr,
unmap.handle = map_ops[i].handle;
- map_ops[i].handle = ~0;
+ map_ops[i].handle = INVALID_GRANT_HANDLE;
if (map_ops[i].flags & GNTMAP_device_map)
unmap.dev_bus_addr = map_ops[i].dev_bus_addr;
else
@@ -130,7 +131,6 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
return 0;
}
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_unmap_grant_ref *kunmap_ops,
@@ -145,7 +145,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
return 0;
}
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
bool __set_phys_to_machine_multi(unsigned long pfn,
unsigned long mfn, unsigned long nr_pages)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1f212b47a48a..dfdc3e0af5e1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -810,6 +810,16 @@ config QCOM_FALKOR_ERRATUM_E1041
If unsure, say Y.
+config NVIDIA_CARMEL_CNP_ERRATUM
+ bool "NVIDIA Carmel CNP: CNP on Carmel semantically different than ARM cores"
+ default y
+ help
+ If CNP is enabled on Carmel cores, non-sharable TLBIs on a core will not
+ invalidate shared TLB entries installed by a different core, as it would
+ on standard ARM cores.
+
+ If unsure, say Y.
+
config SOCIONEXT_SYNQUACER_PREITS
bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
default y
@@ -1055,8 +1065,6 @@ config HW_PERF_EVENTS
config SYS_SUPPORTS_HUGETLBFS
def_bool y
-config ARCH_WANT_HUGE_PMD_SHARE
-
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
@@ -1157,8 +1165,8 @@ config XEN
config FORCE_MAX_ZONEORDER
int
- default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
- default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE)
+ default "14" if ARM64_64K_PAGES
+ default "12" if ARM64_16K_PAGES
default "11"
help
The kernel memory allocator divides physically contiguous memory
@@ -1398,10 +1406,13 @@ config ARM64_PAN
config AS_HAS_LDAPR
def_bool $(as-instr,.arch_extension rcpc)
+config AS_HAS_LSE_ATOMICS
+ def_bool $(as-instr,.arch_extension lse)
+
config ARM64_LSE_ATOMICS
bool
default ARM64_USE_LSE_ATOMICS
- depends on $(as-instr,.arch_extension lse)
+ depends on AS_HAS_LSE_ATOMICS
config ARM64_USE_LSE_ATOMICS
bool "Atomic instructions"
@@ -1658,6 +1669,7 @@ config ARM64_MTE
default y
depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI
depends on AS_HAS_ARMV8_5
+ depends on AS_HAS_LSE_ATOMICS
# Required for tag checking in the uaccess routines
depends on ARM64_PAN
select ARCH_USES_HIGH_VMA_FLAGS
@@ -1855,12 +1867,6 @@ config CMDLINE_FROM_BOOTLOADER
the boot loader doesn't provide any, the default kernel command
string provided in CMDLINE will be used.
-config CMDLINE_EXTEND
- bool "Extend bootloader kernel arguments"
- help
- The command-line arguments provided by the boot loader will be
- appended to the default kernel command string.
-
config CMDLINE_FORCE
bool "Always use the default kernel command string"
help
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
index 7de6b376d792..9058cfa4980f 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi
@@ -198,6 +198,7 @@
ranges = <0x0 0x00 0x1700000 0x100000>;
reg = <0x00 0x1700000 0x0 0x100000>;
interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
sec_jr0: jr@10000 {
compatible = "fsl,sec-v5.4-job-ring",
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 5a8a1dc4262d..28c51e521cb2 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -348,6 +348,7 @@
ranges = <0x0 0x00 0x1700000 0x100000>;
reg = <0x00 0x1700000 0x0 0x100000>;
interrupts = <0 75 0x4>;
+ dma-coherent;
sec_jr0: jr@10000 {
compatible = "fsl,sec-v5.4-job-ring",
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 1d6dfd189c7f..39458305e333 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -354,6 +354,7 @@
ranges = <0x0 0x00 0x1700000 0x100000>;
reg = <0x00 0x1700000 0x0 0x100000>;
interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
sec_jr0: jr@10000 {
compatible = "fsl,sec-v5.4-job-ring",
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h
index 5ccc4cc91959..a003e6af3353 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h
+++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h
@@ -124,7 +124,7 @@
#define MX8MM_IOMUXC_SD1_CMD_USDHC1_CMD 0x0A4 0x30C 0x000 0x0 0x0
#define MX8MM_IOMUXC_SD1_CMD_GPIO2_IO1 0x0A4 0x30C 0x000 0x5 0x0
#define MX8MM_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x0A8 0x310 0x000 0x0 0x0
-#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x31 0x000 0x5 0x0
+#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x310 0x000 0x5 0x0
#define MX8MM_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x0AC 0x314 0x000 0x0 0x0
#define MX8MM_IOMUXC_SD1_DATA1_GPIO2_IO3 0x0AC 0x314 0x000 0x5 0x0
#define MX8MM_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x0B0 0x318 0x000 0x0 0x0
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
index 0e1a6d953389..122c95ddad30 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
@@ -35,7 +35,7 @@
&i2c2 {
clock-frequency = <400000>;
- pinctrl-names = "default";
+ pinctrl-names = "default", "gpio";
pinctrl-0 = <&pinctrl_i2c2>;
pinctrl-1 = <&pinctrl_i2c2_gpio>;
sda-gpios = <&gpio5 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
index 44a8c2337cee..f3965ec5b31d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
@@ -67,7 +67,7 @@
&i2c1 {
clock-frequency = <400000>;
- pinctrl-names = "default";
+ pinctrl-names = "default", "gpio";
pinctrl-0 = <&pinctrl_i2c1>;
pinctrl-1 = <&pinctrl_i2c1_gpio>;
sda-gpios = <&gpio5 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h
index b94b02080a34..68e8fa172974 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h
+++ b/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h
@@ -130,7 +130,7 @@
#define MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0x0A4 0x30C 0x000 0x0 0x0
#define MX8MQ_IOMUXC_SD1_CMD_GPIO2_IO1 0x0A4 0x30C 0x000 0x5 0x0
#define MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x0A8 0x310 0x000 0x0 0x0
-#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x31 0x000 0x5 0x0
+#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x310 0x000 0x5 0x0
#define MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x0AC 0x314 0x000 0x0 0x0
#define MX8MQ_IOMUXC_SD1_DATA1_GPIO2_IO3 0x0AC 0x314 0x000 0x5 0x0
#define MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x0B0 0x318 0x000 0x0 0x0
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index d239ab70ed99..53e817c5f6f3 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
/*
* Device Tree file for CZ.NIC Turris Mox Board
- * 2019 by Marek Behun <marek.behun@nic.cz>
+ * 2019 by Marek Behún <kabel@kernel.org>
*/
/dts-v1/;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
index 64179a372ecf..c6f5df2deccf 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi
@@ -310,9 +310,11 @@
};
CP11X_LABEL(sata0): sata@540000 {
- compatible = "marvell,armada-8k-ahci";
+ compatible = "marvell,armada-8k-ahci",
+ "generic-ahci";
reg = <0x540000 0x30000>;
dma-coherent;
+ interrupts = <107 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&CP11X_LABEL(clk) 1 15>,
<&CP11X_LABEL(clk) 1 16>;
#address-cells = <1>;
@@ -320,12 +322,10 @@
status = "disabled";
sata-port@0 {
- interrupts = <109 IRQ_TYPE_LEVEL_HIGH>;
reg = <0>;
};
sata-port@1 {
- interrupts = <107 IRQ_TYPE_LEVEL_HIGH>;
reg = <1>;
};
};
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 5df500dcc627..8a078fc662ac 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -97,9 +97,9 @@
.popsection
.subsection 1
663: \insn2
-664: .previous
- .org . - (664b-663b) + (662b-661b)
+664: .org . - (664b-663b) + (662b-661b)
.org . - (662b-661b) + (664b-663b)
+ .previous
.endif
.endm
@@ -169,11 +169,11 @@
*/
.macro alternative_endif
664:
+ .org . - (664b-663b) + (662b-661b)
+ .org . - (662b-661b) + (664b-663b)
.if .Lasm_alt_mode==0
.previous
.endif
- .org . - (664b-663b) + (662b-661b)
- .org . - (662b-661b) + (664b-663b)
.endm
/*
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 93a161b3bf3f..dc52b733675d 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -37,7 +37,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
} while (--n > 0);
sum += ((sum >> 32) | (sum << 32));
- return csum_fold((__force u32)(sum >> 32));
+ return csum_fold((__force __wsum)(sum >> 32));
}
#define ip_fast_csum ip_fast_csum
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index b77d997b173b..c40f2490cd7b 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -66,7 +66,8 @@
#define ARM64_WORKAROUND_1508412 58
#define ARM64_HAS_LDAPR 59
#define ARM64_KVM_PROTECTED_MODE 60
+#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP 61
-#define ARM64_NCAPS 61
+#define ARM64_NCAPS 62
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 4e90c2debf70..94d4025acc0b 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -278,6 +278,7 @@
#define CPTR_EL2_DEFAULT CPTR_EL2_RES1
/* Hyp Debug Configuration Register bits */
+#define MDCR_EL2_TTRF (1 << 19)
#define MDCR_EL2_TPMS (1 << 14)
#define MDCR_EL2_E2PB_MASK (UL(0x3))
#define MDCR_EL2_E2PB_SHIFT (UL(12))
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 22d933e9b59e..a7ab84f781f7 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -47,10 +47,10 @@
#define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context 2
#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa 3
#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid 4
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid 5
+#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context 5
#define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff 6
#define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs 7
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_ich_vtr_el2 8
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config 8
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr 9
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr 10
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs 11
@@ -183,16 +183,16 @@ DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
#define __bp_harden_hyp_vecs CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
int level);
extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
extern void __kvm_timer_set_cntvoff(u64 cntvoff);
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
-extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_get_gic_config(void);
extern u64 __vgic_v3_read_vmcr(void);
extern void __vgic_v3_write_vmcr(u32 vmcr);
extern void __vgic_v3_init_lrs(void);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index c0450828378b..32ae676236b6 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -83,6 +83,11 @@ void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
void __debug_switch_to_host(struct kvm_vcpu *vcpu);
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+#endif
+
void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
@@ -97,7 +102,8 @@ bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
void __noreturn hyp_panic(void);
#ifdef __KVM_NVHE_HYPERVISOR__
-void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+ u64 elr, u64 par);
#endif
#endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index c759faf7a1ff..0aabc3be9a75 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -328,6 +328,11 @@ static inline void *phys_to_virt(phys_addr_t x)
#define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET)
#if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
+#define page_to_virt(x) ({ \
+ __typeof__(x) __page = x; \
+ void *__addr = __va(page_to_phys(__page)); \
+ (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
+})
#define virt_to_page(x) pfn_to_page(virt_to_pfn(x))
#else
#define page_to_virt(x) ({ \
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 70ce8c1d2b07..bd02e99b1a4c 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -63,23 +63,6 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
extern u64 idmap_t0sz;
extern u64 idmap_ptrs_per_pgd;
-static inline bool __cpu_uses_extended_idmap(void)
-{
- if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52))
- return false;
-
- return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
-}
-
-/*
- * True if the extended ID map requires an extra level of translation table
- * to be configured.
- */
-static inline bool __cpu_uses_extended_idmap_level(void)
-{
- return ARM64_HW_PGTABLE_LEVELS(64 - idmap_t0sz) > CONFIG_PGTABLE_LEVELS;
-}
-
/*
* Ensure TCR.T0SZ is set to the provided value.
*/
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 046be789fbb4..9a65fb528110 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -66,7 +66,6 @@ extern bool arm64_use_ng_mappings;
#define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
#define PAGE_KERNEL __pgprot(PROT_NORMAL)
-#define PAGE_KERNEL_TAGGED __pgprot(PROT_NORMAL_TAGGED)
#define PAGE_KERNEL_RO __pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
#define PAGE_KERNEL_ROX __pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
#define PAGE_KERNEL_EXEC __pgprot(PROT_NORMAL & ~PTE_PXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e17b96d0e4b5..47027796c2f9 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -486,6 +486,9 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
#define pgprot_device(prot) \
__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
+#define pgprot_tagged(prot) \
+ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED))
+#define pgprot_mhp pgprot_tagged
/*
* DMA allocations for non-coherent devices use what the Arm architecture calls
* "Normal non-cacheable" memory, which permits speculation, unaligned accesses
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ca2cd75d3286..efc10e9041a0 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -251,6 +251,8 @@ unsigned long get_wchan(struct task_struct *p);
extern struct task_struct *cpu_switch_to(struct task_struct *prev,
struct task_struct *next);
+asmlinkage void arm64_preempt_schedule_irq(void);
+
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index dfd4edbfe360..d4a5fca984c3 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -796,6 +796,11 @@
#define ID_AA64MMFR0_PARANGE_48 0x5
#define ID_AA64MMFR0_PARANGE_52 0x6
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT 0x0
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE 0x1
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN 0x2
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX 0x7
+
#ifdef CONFIG_ARM64_PA_BITS_52
#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_52
#else
@@ -961,14 +966,17 @@
#define ID_PFR1_PROGMOD_SHIFT 0
#if defined(CONFIG_ARM64_4K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7
#elif defined(CONFIG_ARM64_16K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0xF
#elif defined(CONFIG_ARM64_64K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7
#endif
#define MVFR2_FPMISC_SHIFT 4
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 9f4e3b266f21..6623c99f0984 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -55,6 +55,8 @@ void arch_setup_new_exec(void);
#define arch_setup_new_exec arch_setup_new_exec
void arch_release_task_struct(struct task_struct *tsk);
+int arch_dup_task_struct(struct task_struct *dst,
+ struct task_struct *src);
#endif
diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
index 3333950b5909..ea487218db79 100644
--- a/arch/arm64/include/asm/word-at-a-time.h
+++ b/arch/arm64/include/asm/word-at-a-time.h
@@ -53,7 +53,7 @@ static inline unsigned long find_zero(unsigned long mask)
*/
static inline unsigned long load_unaligned_zeropad(const void *addr)
{
- unsigned long ret, offset;
+ unsigned long ret, tmp;
/* Load word from unaligned pointer addr */
asm(
@@ -61,9 +61,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
"2:\n"
" .pushsection .fixup,\"ax\"\n"
" .align 2\n"
- "3: and %1, %2, #0x7\n"
- " bic %2, %2, #0x7\n"
- " ldr %0, [%2]\n"
+ "3: bic %1, %2, #0x7\n"
+ " ldr %0, [%1]\n"
+ " and %1, %2, #0x7\n"
" lsl %1, %1, #0x3\n"
#ifndef __AARCH64EB__
" lsr %0, %0, %1\n"
@@ -73,7 +73,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr)
" b 2b\n"
" .popsection\n"
_ASM_EXTABLE(1b, 3b)
- : "=&r" (ret), "=&r" (offset)
+ : "=&r" (ret), "=&r" (tmp)
: "r" (addr), "Q" (*(unsigned long *)addr));
return ret;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 506a1cd37973..e2c20c036442 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -526,6 +526,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
1, 0),
},
#endif
+#ifdef CONFIG_NVIDIA_CARMEL_CNP_ERRATUM
+ {
+ /* NVIDIA Carmel */
+ .desc = "NVIDIA Carmel CNP erratum",
+ .capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP,
+ ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+ },
+#endif
{
}
};
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 066030717a4c..e5281e1c8f1d 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -383,7 +383,6 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
* of support.
*/
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
ARM64_FTR_END,
};
@@ -1321,7 +1320,10 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
* may share TLB entries with a CPU stuck in the crashed
* kernel.
*/
- if (is_kdump_kernel())
+ if (is_kdump_kernel())
+ return false;
+
+ if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP))
return false;
return has_cpuid_feature(entry, scope);
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 77605aec25fe..51fcf99d5351 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -353,7 +353,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
* with the CLIDR_EL1 fields to avoid triggering false warnings
* when there is a mismatch across the CPUs. Keep track of the
* effective value of the CTR_EL0 in our internal records for
- * acurate sanity check and feature enablement.
+ * accurate sanity check and feature enablement.
*/
info->reg_ctr = read_cpuid_effective_cachetype();
info->reg_dczid = read_cpuid(DCZID_EL0);
diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c
index e6e284265f19..58303a9ec32c 100644
--- a/arch/arm64/kernel/crash_dump.c
+++ b/arch/arm64/kernel/crash_dump.c
@@ -64,5 +64,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
{
memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count);
+ *ppos += count;
+
return count;
}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a31a0a713c85..6acfc5e6b5e0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -148,16 +148,18 @@ alternative_cb_end
.endm
/* Check for MTE asynchronous tag check faults */
- .macro check_mte_async_tcf, flgs, tmp
+ .macro check_mte_async_tcf, tmp, ti_flags
#ifdef CONFIG_ARM64_MTE
+ .arch_extension lse
alternative_if_not ARM64_MTE
b 1f
alternative_else_nop_endif
mrs_s \tmp, SYS_TFSRE0_EL1
tbz \tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f
/* Asynchronous TCF occurred for TTBR0 access, set the TI flag */
- orr \flgs, \flgs, #_TIF_MTE_ASYNC_FAULT
- str \flgs, [tsk, #TSK_TI_FLAGS]
+ mov \tmp, #_TIF_MTE_ASYNC_FAULT
+ add \ti_flags, tsk, #TSK_TI_FLAGS
+ stset \tmp, [\ti_flags]
msr_s SYS_TFSRE0_EL1, xzr
1:
#endif
@@ -244,7 +246,7 @@ alternative_else_nop_endif
disable_step_tsk x19, x20
/* Check for asynchronous tag check faults in user space */
- check_mte_async_tcf x19, x22
+ check_mte_async_tcf x22, x23
apply_ssbd 1, x22, x23
ptrauth_keys_install_kernel tsk, x20, x22, x23
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 66b0e0b66e31..840bda1869e9 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -319,7 +319,7 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
*/
adrp x5, __idmap_text_end
clz x5, x5
- cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough?
+ cmp x5, TCR_T0SZ(VA_BITS_MIN) // default T0SZ small enough?
b.ge 1f // .. then skip VA range extension
adr_l x6, idmap_t0sz
@@ -655,8 +655,10 @@ SYM_FUNC_END(__secondary_too_slow)
SYM_FUNC_START(__enable_mmu)
mrs x2, ID_AA64MMFR0_EL1
ubfx x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
- cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
- b.ne __no_granule_support
+ cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MIN
+ b.lt __no_granule_support
+ cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MAX
+ b.gt __no_granule_support
update_early_cpu_boot_status 0, x2, x3
adrp x2, idmap_pg_dir
phys_to_ttbr x1, x1
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index dffb16682330..83f1c4b92095 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -163,33 +163,36 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases)
} while (1);
}
-static __init void parse_cmdline(void)
+static __init const u8 *get_bootargs_cmdline(void)
{
- if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) {
- const u8 *prop;
- void *fdt;
- int node;
+ const u8 *prop;
+ void *fdt;
+ int node;
- fdt = get_early_fdt_ptr();
- if (!fdt)
- goto out;
+ fdt = get_early_fdt_ptr();
+ if (!fdt)
+ return NULL;
- node = fdt_path_offset(fdt, "/chosen");
- if (node < 0)
- goto out;
+ node = fdt_path_offset(fdt, "/chosen");
+ if (node < 0)
+ return NULL;
- prop = fdt_getprop(fdt, node, "bootargs", NULL);
- if (!prop)
- goto out;
+ prop = fdt_getprop(fdt, node, "bootargs", NULL);
+ if (!prop)
+ return NULL;
- __parse_cmdline(prop, true);
+ return strlen(prop) ? prop : NULL;
+}
- if (!IS_ENABLED(CONFIG_CMDLINE_EXTEND))
- return;
- }
+static __init void parse_cmdline(void)
+{
+ const u8 *prop = get_bootargs_cmdline();
-out:
- __parse_cmdline(CONFIG_CMDLINE, true);
+ if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop)
+ __parse_cmdline(CONFIG_CMDLINE, true);
+
+ if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop)
+ __parse_cmdline(prop, true);
}
/* Keep checkers quiet */
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 23f1a557bd9f..5aa9ed1e9ec6 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -101,6 +101,9 @@ KVM_NVHE_ALIAS(__stop___kvm_ex_table);
/* Array containing bases of nVHE per-CPU memory regions. */
KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base);
+/* PMU available static key */
+KVM_NVHE_ALIAS(kvm_arm_pmu_available);
+
#endif /* CONFIG_KVM */
#endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 7d2318f80955..4658fcf88c2b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -460,7 +460,7 @@ static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
}
-static inline u32 armv8pmu_read_evcntr(int idx)
+static inline u64 armv8pmu_read_evcntr(int idx)
{
u32 counter = ARMV8_IDX_TO_COUNTER(idx);
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 66aac2881ba8..85645b2b0c7a 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -267,10 +267,12 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
if (!instruction_pointer(regs))
BUG();
- if (kcb->kprobe_status == KPROBE_REENTER)
+ if (kcb->kprobe_status == KPROBE_REENTER) {
restore_previous_kprobe(kcb);
- else
+ } else {
+ kprobes_restore_local_irqflag(kcb, regs);
reset_current_kprobe();
+ }
break;
case KPROBE_HIT_ACTIVE:
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 325c83b1a24d..6e60aa3b5ea9 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -57,6 +57,8 @@
#include <asm/processor.h>
#include <asm/pointer_auth.h>
#include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+#include <asm/system_misc.h>
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 5bfd9b87f85d..4ea9392f86e0 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -134,7 +134,7 @@ SYM_FUNC_START(_cpu_resume)
*/
bl cpu_do_resume
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
mov x0, sp
bl kasan_unpoison_task_stack_below
#endif
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index ad20981dfda4..d55bdfb7789c 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -194,8 +194,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
#ifdef CONFIG_STACKTRACE
-void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
- struct task_struct *task, struct pt_regs *regs)
+noinline void arch_stack_walk(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task,
+ struct pt_regs *regs)
{
struct stackframe frame;
@@ -203,8 +204,8 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
start_backtrace(&frame, regs->regs[29], regs->pc);
else if (task == current)
start_backtrace(&frame,
- (unsigned long)__builtin_frame_address(0),
- (unsigned long)arch_stack_walk);
+ (unsigned long)__builtin_frame_address(1),
+ (unsigned long)__builtin_return_address(0));
else
start_backtrace(&frame, thread_saved_fp(task),
thread_saved_pc(task));
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index fc4c95dd2d26..7f06ba76698d 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -385,11 +385,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
/*
+ * We guarantee that both TLBs and I-cache are private to each
+ * vcpu. If detecting that a vcpu from the same VM has
+ * previously run on the same physical CPU, call into the
+ * hypervisor code to nuke the relevant contexts.
+ *
* We might get preempted before the vCPU actually runs, but
* over-invalidation doesn't affect correctness.
*/
if (*last_ran != vcpu->vcpu_id) {
- kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
+ kvm_call_hyp(__kvm_flush_cpu_context, mmu);
*last_ran = vcpu->vcpu_id;
}
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 7a7e425616b5..dbc890511631 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -89,6 +89,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
* - Debug ROM Address (MDCR_EL2_TDRA)
* - OS related registers (MDCR_EL2_TDOSA)
* - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB)
+ * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF)
*
* Additionally, KVM only traps guest accesses to the debug registers if
* the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY
@@ -112,6 +113,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
MDCR_EL2_TPMS |
+ MDCR_EL2_TTRF |
MDCR_EL2_TPMCR |
MDCR_EL2_TDRA |
MDCR_EL2_TDOSA);
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index b0afad7a99c6..e831d3dfd50d 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -85,8 +85,10 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
// If the hyp context is loaded, go straight to hyp_panic
get_loaded_vcpu x0, x1
- cbz x0, hyp_panic
+ cbnz x0, 1f
+ b hyp_panic
+1:
// The hyp context is saved so make sure it is restored to allow
// hyp_panic to run at hyp and, subsequently, panic to run in the host.
// This makes use of __guest_exit to avoid duplication but sets the
@@ -94,7 +96,7 @@ SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
// current state is saved to the guest context but it will only be
// accurate if the guest had been completely restored.
adr_this_cpu x0, kvm_hyp_ctxt, x1
- adr x1, hyp_panic
+ adr_l x1, hyp_panic
str x1, [x0, #CPU_XREG_OFFSET(30)]
get_vcpu_ptr x1, x0
@@ -146,7 +148,7 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
// Now restore the hyp regs
restore_callee_saved_regs x2
- set_loaded_vcpu xzr, x1, x2
+ set_loaded_vcpu xzr, x2, x3
alternative_if ARM64_HAS_RAS_EXTN
// If we have the RAS extensions we can consume a pending error
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 54f4860cd87c..6c1f51f25eb3 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -90,15 +90,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
* counter, which could make a PMXEVCNTR_EL0 access UNDEF at
* EL1 instead of being trapped to EL2.
*/
- write_sysreg(0, pmselr_el0);
- write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+ if (kvm_arm_support_pmu_v3()) {
+ write_sysreg(0, pmselr_el0);
+ write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+ }
write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
}
static inline void __deactivate_traps_common(void)
{
write_sysreg(0, hstr_el2);
- write_sysreg(0, pmuserenr_el0);
+ if (kvm_arm_support_pmu_v3())
+ write_sysreg(0, pmuserenr_el0);
}
static inline void ___activate_traps(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 91a711aa8382..f401724f12ef 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -58,16 +58,24 @@ static void __debug_restore_spe(u64 pmscr_el1)
write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
}
-void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
{
/* Disable and flush SPE data generation */
__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
__debug_switch_to_guest_common(vcpu);
}
-void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
{
__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
__debug_switch_to_host_common(vcpu);
}
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 6585a7cbbc56..5d94584840cc 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -71,7 +71,8 @@ SYM_FUNC_START(__host_enter)
SYM_FUNC_END(__host_enter)
/*
- * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+ * void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+ * u64 elr, u64 par);
*/
SYM_FUNC_START(__hyp_do_panic)
/* Prepare and exit to the host's panic funciton. */
@@ -82,9 +83,11 @@ SYM_FUNC_START(__hyp_do_panic)
hyp_kimg_va lr, x6
msr elr_el2, lr
- /* Set the panic format string. Use the, now free, LR as scratch. */
- ldr lr, =__hyp_panic_string
- hyp_kimg_va lr, x6
+ mov x29, x0
+
+ /* Load the format string into x0 and arguments into x1-7 */
+ ldr x0, =__hyp_panic_string
+ hyp_kimg_va x0, x6
/* Load the format arguments into x1-7. */
mov x6, x3
@@ -94,9 +97,7 @@ SYM_FUNC_START(__hyp_do_panic)
mrs x5, hpfar_el2
/* Enter the host, conditionally restoring the host context. */
- cmp x0, xzr
- mov x0, lr
- b.eq __host_enter_without_restoring
+ cbz x29, __host_enter_without_restoring
b __host_enter_for_panic
SYM_FUNC_END(__hyp_do_panic)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index f012f8665ecc..936328207bde 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -46,11 +46,11 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
}
-static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt)
+static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
{
DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
- __kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
+ __kvm_flush_cpu_context(kern_hyp_va(mmu));
}
static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
@@ -67,9 +67,9 @@ static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt)
write_sysreg_el2(tmp, SYS_SCTLR);
}
-static void handle___vgic_v3_get_ich_vtr_el2(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
{
- cpu_reg(host_ctxt, 1) = __vgic_v3_get_ich_vtr_el2();
+ cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
}
static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
@@ -115,10 +115,10 @@ static const hcall_t host_hcall[] = {
HANDLE_FUNC(__kvm_flush_vm_context),
HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
HANDLE_FUNC(__kvm_tlb_flush_vmid),
- HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
+ HANDLE_FUNC(__kvm_flush_cpu_context),
HANDLE_FUNC(__kvm_timer_set_cntvoff),
HANDLE_FUNC(__kvm_enable_ssbs),
- HANDLE_FUNC(__vgic_v3_get_ich_vtr_el2),
+ HANDLE_FUNC(__vgic_v3_get_gic_config),
HANDLE_FUNC(__vgic_v3_read_vmcr),
HANDLE_FUNC(__vgic_v3_write_vmcr),
HANDLE_FUNC(__vgic_v3_init_lrs),
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index f3d0e9eca56c..68ab6b4d5141 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -192,6 +192,14 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
__sysreg_save_state_nvhe(host_ctxt);
+ /*
+ * We must flush and disable the SPE buffer for nVHE, as
+ * the translation regime(EL1&0) is going to be loaded with
+ * that of the guest. And we must do this before we change the
+ * translation regime to EL2 (via MDCR_EL2_E2PB == 0) and
+ * before we load guest Stage1.
+ */
+ __debug_save_host_buffers_nvhe(vcpu);
__adjust_pc(vcpu);
@@ -234,11 +242,12 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
__fpsimd_save_fpexc32(vcpu);
+ __debug_switch_to_host(vcpu);
/*
* This must come after restoring the host sysregs, since a non-VHE
* system may enable SPE here and make use of the TTBRs.
*/
- __debug_switch_to_host(vcpu);
+ __debug_restore_host_buffers_nvhe(vcpu);
if (pmu_switch_needed)
__pmu_switch_to_host(host_ctxt);
@@ -257,7 +266,6 @@ void __noreturn hyp_panic(void)
u64 spsr = read_sysreg_el2(SYS_SPSR);
u64 elr = read_sysreg_el2(SYS_ELR);
u64 par = read_sysreg_par();
- bool restore_host = true;
struct kvm_cpu_context *host_ctxt;
struct kvm_vcpu *vcpu;
@@ -271,7 +279,7 @@ void __noreturn hyp_panic(void)
__sysreg_restore_state_nvhe(host_ctxt);
}
- __hyp_do_panic(restore_host, spsr, elr, par);
+ __hyp_do_panic(host_ctxt, spsr, elr, par);
unreachable();
}
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index fbde89a2c6e8..229b06748c20 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -123,7 +123,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
__tlb_switch_to_host(&cxt);
}
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
{
struct tlb_inv_context cxt;
@@ -131,6 +131,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
__tlb_switch_to_guest(mmu, &cxt);
__tlbi(vmalle1);
+ asm volatile("ic iallu");
dsb(nsh);
isb();
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 4d177ce1d536..926fc07074f5 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -223,6 +223,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
goto out;
if (!table) {
+ data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
data->addr += kvm_granule_size(level);
goto out;
}
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 80406f463c28..39f8f7f9227c 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -405,9 +405,54 @@ void __vgic_v3_init_lrs(void)
__gic_v3_set_lr(0, i);
}
-u64 __vgic_v3_get_ich_vtr_el2(void)
+/*
+ * Return the GIC CPU configuration:
+ * - [31:0] ICH_VTR_EL2
+ * - [62:32] RES0
+ * - [63] MMIO (GICv2) capable
+ */
+u64 __vgic_v3_get_gic_config(void)
{
- return read_gicreg(ICH_VTR_EL2);
+ u64 val, sre = read_gicreg(ICC_SRE_EL1);
+ unsigned long flags = 0;
+
+ /*
+ * To check whether we have a MMIO-based (GICv2 compatible)
+ * CPU interface, we need to disable the system register
+ * view. To do that safely, we have to prevent any interrupt
+ * from firing (which would be deadly).
+ *
+ * Note that this only makes sense on VHE, as interrupts are
+ * already masked for nVHE as part of the exception entry to
+ * EL2.
+ */
+ if (has_vhe())
+ flags = local_daif_save();
+
+ /*
+ * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
+ * that to be able to set ICC_SRE_EL1.SRE to 0, all the
+ * interrupt overrides must be set. You've got to love this.
+ */
+ sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+ isb();
+ write_gicreg(0, ICC_SRE_EL1);
+ isb();
+
+ val = read_gicreg(ICC_SRE_EL1);
+
+ write_gicreg(sre, ICC_SRE_EL1);
+ isb();
+ sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+ isb();
+
+ if (has_vhe())
+ local_daif_restore(flags);
+
+ val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
+ val |= read_gicreg(ICH_VTR_EL2);
+
+ return val;
}
u64 __vgic_v3_read_vmcr(void)
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index fd7895945bbc..66f17349f0c3 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -127,7 +127,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
__tlb_switch_to_host(&cxt);
}
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
{
struct tlb_inv_context cxt;
@@ -135,6 +135,7 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
__tlb_switch_to_guest(mmu, &cxt);
__tlbi(vmalle1);
+ asm volatile("ic iallu");
dsb(nsh);
isb();
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 77cb2d28f2a4..8711894db8c2 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1312,8 +1312,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
* Prevent userspace from creating a memory region outside of the IPA
* space addressable by the KVM guest IPA space.
*/
- if (memslot->base_gfn + memslot->npages >=
- (kvm_phys_size(kvm) >> PAGE_SHIFT))
+ if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
return -EFAULT;
mmap_read_lock(current->mm);
diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c
index d45b8b9a4415..739164324afe 100644
--- a/arch/arm64/kvm/perf.c
+++ b/arch/arm64/kvm/perf.c
@@ -11,6 +11,8 @@
#include <asm/kvm_emulate.h>
+DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
static int kvm_is_in_guest(void)
{
return kvm_get_running_vcpu() != NULL;
@@ -48,6 +50,14 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
int kvm_perf_init(void)
{
+ /*
+ * Check if HW_PERF_EVENTS are supported by checking the number of
+ * hardware performance counters. This could ensure the presence of
+ * a physical PMU and CONFIG_PERF_EVENT is selected.
+ */
+ if (IS_ENABLED(CONFIG_ARM_PMU) && perf_num_counters() > 0)
+ static_branch_enable(&kvm_arm_pmu_available);
+
return perf_register_guest_info_callbacks(&kvm_guest_cbs);
}
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index e9ec08b0b070..e32c6e139a09 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -823,16 +823,6 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
return val & mask;
}
-bool kvm_arm_support_pmu_v3(void)
-{
- /*
- * Check if HW_PERF_EVENTS are supported by checking the number of
- * hardware performance counters. This could ensure the presence of
- * a physical PMU and CONFIG_PERF_EVENT is selected.
- */
- return (perf_num_counters() > 0);
-}
-
int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
{
if (!kvm_vcpu_has_pmu(vcpu))
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 47f3f035f3ea..bd354cd45d28 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -311,23 +311,24 @@ int kvm_set_ipa_limit(void)
}
switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
- default:
- case 1:
+ case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE:
kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
return -EINVAL;
- case 0:
+ case ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT:
kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
break;
- case 2:
+ case ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX:
kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
break;
+ default:
+ kvm_err("Unsupported value for TGRAN_2, giving up\n");
+ return -EINVAL;
}
kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
- WARN(kvm_ipa_limit < KVM_PHYS_SHIFT,
- "KVM IPA Size Limit (%d bits) is smaller than default size\n",
- kvm_ipa_limit);
- kvm_info("IPA Size Limit: %d bits\n", kvm_ipa_limit);
+ kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
+ ((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
+ " (Reduced IPA size, limited VM/VMM compatibility)" : ""));
return 0;
}
@@ -356,6 +357,11 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
return -EINVAL;
} else {
phys_shift = KVM_PHYS_SHIFT;
+ if (phys_shift > kvm_ipa_limit) {
+ pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
+ current->comm);
+ return -EINVAL;
+ }
}
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 52915b342351..6f530925a231 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -574,9 +574,13 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
*/
int vgic_v3_probe(const struct gic_kvm_info *info)
{
- u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2);
+ u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+ bool has_v2;
int ret;
+ has_v2 = ich_vtr_el2 >> 63;
+ ich_vtr_el2 = (u32)ich_vtr_el2;
+
/*
* The ListRegs field is 5 bits, but there is an architectural
* maximum of 16 list registers. Just ignore bit 4...
@@ -594,13 +598,15 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
gicv4_enable ? "en" : "dis");
}
+ kvm_vgic_global_state.vcpu_base = 0;
+
if (!info->vcpu.start) {
kvm_info("GICv3: no GICV resource entry\n");
- kvm_vgic_global_state.vcpu_base = 0;
+ } else if (!has_v2) {
+ pr_warn(FW_BUG "CPU interface incapable of MMIO access\n");
} else if (!PAGE_ALIGNED(info->vcpu.start)) {
pr_warn("GICV physical address 0x%llx not page aligned\n",
(unsigned long long)info->vcpu.start);
- kvm_vgic_global_state.vcpu_base = 0;
} else {
kvm_vgic_global_state.vcpu_base = info->vcpu.start;
kvm_vgic_global_state.can_emulate_gicv2 = true;
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 0ace5e68efba..3685e12aba9b 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -219,17 +219,40 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
int pfn_valid(unsigned long pfn)
{
- phys_addr_t addr = pfn << PAGE_SHIFT;
+ phys_addr_t addr = PFN_PHYS(pfn);
- if ((addr >> PAGE_SHIFT) != pfn)
+ /*
+ * Ensure the upper PAGE_SHIFT bits are clear in the
+ * pfn. Else it might lead to false positives when
+ * some of the upper bits are set, but the lower bits
+ * match a valid pfn.
+ */
+ if (PHYS_PFN(addr) != pfn)
return 0;
#ifdef CONFIG_SPARSEMEM
+{
+ struct mem_section *ms;
+
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
- if (!valid_section(__pfn_to_section(pfn)))
+ ms = __pfn_to_section(pfn);
+ if (!valid_section(ms))
return 0;
+
+ /*
+ * ZONE_DEVICE memory does not have the memblock entries.
+ * memblock_is_map_memory() check for ZONE_DEVICE based
+ * addresses will always fail. Even the normal hotplugged
+ * memory will never have MEMBLOCK_NOMAP flag set in their
+ * memblock entries. Skip memblock search for all non early
+ * memory sections covering all of hotplug memory including
+ * both normal and ZONE_DEVICE based.
+ */
+ if (!early_section(ms))
+ return pfn_section_valid(ms, pfn);
+}
#endif
return memblock_is_map_memory(addr);
}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 3802cfbdd20d..5d9550fdb9cf 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -40,7 +40,7 @@
#define NO_BLOCK_MAPPINGS BIT(0)
#define NO_CONT_MAPPINGS BIT(1)
-u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN);
u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
u64 __section(".mmuoff.data.write") vabits_actual;
@@ -512,7 +512,8 @@ static void __init map_mem(pgd_t *pgdp)
* if MTE is present. Otherwise, it has the same attributes as
* PAGE_KERNEL.
*/
- __map_memblock(pgdp, start, end, PAGE_KERNEL_TAGGED, flags);
+ __map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL),
+ flags);
}
/*
@@ -1447,6 +1448,22 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
struct range arch_get_mappable_range(void)
{
struct range mhp_range;
+ u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
+ u64 end_linear_pa = __pa(PAGE_END - 1);
+
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ /*
+ * Check for a wrap, it is possible because of randomized linear
+ * mapping the start physical address is actually bigger than
+ * the end physical address. In this case set start to zero
+ * because [0, end_linear_pa] range must still be able to cover
+ * all addressable physical addresses.
+ */
+ if (start_linear_pa > end_linear_pa)
+ start_linear_pa = 0;
+ }
+
+ WARN_ON(start_linear_pa > end_linear_pa);
/*
* Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
@@ -1454,8 +1471,9 @@ struct range arch_get_mappable_range(void)
* range which can be mapped inside this linear mapping range, must
* also be derived from its end points.
*/
- mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual));
- mhp_range.end = __pa(PAGE_END - 1);
+ mhp_range.start = start_linear_pa;
+ mhp_range.end = end_linear_pa;
+
return mhp_range;
}
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 34e91224adc3..8de5b987edb9 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -314,7 +314,7 @@ config FORCE_MAX_ZONEORDER
int "Maximum zone order"
default "11"
-config RAM_BASE
+config DRAM_BASE
hex "DRAM start addr (the same with memory-section in dts)"
default 0x0
diff --git a/arch/csky/include/asm/page.h b/arch/csky/include/asm/page.h
index 3b91fc3cf36f..ed7451478b1b 100644
--- a/arch/csky/include/asm/page.h
+++ b/arch/csky/include/asm/page.h
@@ -28,7 +28,7 @@
#define SSEG_SIZE 0x20000000
#define LOWMEM_LIMIT (SSEG_SIZE * 2)
-#define PHYS_OFFSET_OFFSET (CONFIG_RAM_BASE & (SSEG_SIZE - 1))
+#define PHYS_OFFSET_OFFSET (CONFIG_DRAM_BASE & (SSEG_SIZE - 1))
#ifndef __ASSEMBLY__
diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
index ae2b1c7b3b5c..ef2bb9bd9605 100644
--- a/arch/csky/kernel/probes/ftrace.c
+++ b/arch/csky/kernel/probes/ftrace.c
@@ -9,7 +9,7 @@ int arch_check_ftrace_location(struct kprobe *p)
return 0;
}
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index ca0d596c800d..8916a2850c48 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -55,8 +55,6 @@ CONFIG_CHR_DEV_SG=m
CONFIG_SCSI_FC_ATTRS=y
CONFIG_SCSI_SYM53C8XX_2=y
CONFIG_SCSI_QLOGIC_1280=y
-CONFIG_ATA=y
-CONFIG_ATA_PIIX=y
CONFIG_SATA_VITESSE=y
CONFIG_MD=y
CONFIG_BLK_DEV_MD=m
diff --git a/arch/ia64/include/asm/ptrace.h b/arch/ia64/include/asm/ptrace.h
index b3aa46090101..08179135905c 100644
--- a/arch/ia64/include/asm/ptrace.h
+++ b/arch/ia64/include/asm/ptrace.h
@@ -54,8 +54,7 @@
static inline unsigned long user_stack_pointer(struct pt_regs *regs)
{
- /* FIXME: should this be bspstore + nr_dirty regs? */
- return regs->ar_bspstore;
+ return regs->r12;
}
static inline int is_syscall_success(struct pt_regs *regs)
@@ -79,11 +78,6 @@ static inline long regs_return_value(struct pt_regs *regs)
unsigned long __ip = instruction_pointer(regs); \
(__ip & ~3UL) + ((__ip & 3UL) << 2); \
})
-/*
- * Why not default? Because user_stack_pointer() on ia64 gives register
- * stack backing store instead...
- */
-#define current_user_stack_pointer() (current_pt_regs()->r12)
/* given a pointer to a task_struct, return the user's pt_regs */
# define task_pt_regs(t) (((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1)
diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index 6c6f16e409a8..0d23c0049301 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -32,7 +32,7 @@ static inline void syscall_rollback(struct task_struct *task,
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
- return regs->r10 == -1 ? regs->r8:0;
+ return regs->r10 == -1 ? -regs->r8:0;
}
static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
index 8b5b8e6bc9d9..dd5bfed52031 100644
--- a/arch/ia64/kernel/err_inject.c
+++ b/arch/ia64/kernel/err_inject.c
@@ -59,7 +59,7 @@ show_##name(struct device *dev, struct device_attribute *attr, \
char *buf) \
{ \
u32 cpu=dev->id; \
- return sprintf(buf, "%lx\n", name[cpu]); \
+ return sprintf(buf, "%llx\n", name[cpu]); \
}
#define store(name) \
@@ -86,9 +86,9 @@ store_call_start(struct device *dev, struct device_attribute *attr,
#ifdef ERR_INJ_DEBUG
printk(KERN_DEBUG "pal_mc_err_inject for cpu%d:\n", cpu);
- printk(KERN_DEBUG "err_type_info=%lx,\n", err_type_info[cpu]);
- printk(KERN_DEBUG "err_struct_info=%lx,\n", err_struct_info[cpu]);
- printk(KERN_DEBUG "err_data_buffer=%lx, %lx, %lx.\n",
+ printk(KERN_DEBUG "err_type_info=%llx,\n", err_type_info[cpu]);
+ printk(KERN_DEBUG "err_struct_info=%llx,\n", err_struct_info[cpu]);
+ printk(KERN_DEBUG "err_data_buffer=%llx, %llx, %llx.\n",
err_data_buffer[cpu].data1,
err_data_buffer[cpu].data2,
err_data_buffer[cpu].data3);
@@ -117,8 +117,8 @@ store_call_start(struct device *dev, struct device_attribute *attr,
#ifdef ERR_INJ_DEBUG
printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]);
- printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]);
- printk(KERN_DEBUG "resources=%lx\n", resources[cpu]);
+ printk(KERN_DEBUG "capabilities=%llx,\n", capabilities[cpu]);
+ printk(KERN_DEBUG "resources=%llx\n", resources[cpu]);
#endif
return size;
}
@@ -131,7 +131,7 @@ show_virtual_to_phys(struct device *dev, struct device_attribute *attr,
char *buf)
{
unsigned int cpu=dev->id;
- return sprintf(buf, "%lx\n", phys_addr[cpu]);
+ return sprintf(buf, "%llx\n", phys_addr[cpu]);
}
static ssize_t
@@ -145,7 +145,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL);
if (ret<=0) {
#ifdef ERR_INJ_DEBUG
- printk("Virtual address %lx is not existing.\n",virt_addr);
+ printk("Virtual address %llx is not existing.\n", virt_addr);
#endif
return -EINVAL;
}
@@ -163,7 +163,7 @@ show_err_data_buffer(struct device *dev,
{
unsigned int cpu=dev->id;
- return sprintf(buf, "%lx, %lx, %lx\n",
+ return sprintf(buf, "%llx, %llx, %llx\n",
err_data_buffer[cpu].data1,
err_data_buffer[cpu].data2,
err_data_buffer[cpu].data3);
@@ -178,13 +178,13 @@ store_err_data_buffer(struct device *dev,
int ret;
#ifdef ERR_INJ_DEBUG
- printk("write err_data_buffer=[%lx,%lx,%lx] on cpu%d\n",
+ printk("write err_data_buffer=[%llx,%llx,%llx] on cpu%d\n",
err_data_buffer[cpu].data1,
err_data_buffer[cpu].data2,
err_data_buffer[cpu].data3,
cpu);
#endif
- ret=sscanf(buf, "%lx, %lx, %lx",
+ ret = sscanf(buf, "%llx, %llx, %llx",
&err_data_buffer[cpu].data1,
&err_data_buffer[cpu].data2,
&err_data_buffer[cpu].data3);
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index d4cae2fc69ca..adf6521525f4 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1824,7 +1824,7 @@ ia64_mca_cpu_init(void *cpu_data)
data = mca_bootmem();
first_time = 0;
} else
- data = (void *)__get_free_pages(GFP_KERNEL,
+ data = (void *)__get_free_pages(GFP_ATOMIC,
get_order(sz));
if (!data)
panic("Could not allocate MCA memory for cpu %d\n",
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index c3490ee2daa5..e14f5653393a 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -2013,27 +2013,39 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
{
struct syscall_get_set_args *args = data;
struct pt_regs *pt = args->regs;
- unsigned long *krbs, cfm, ndirty;
+ unsigned long *krbs, cfm, ndirty, nlocals, nouts;
int i, count;
if (unw_unwind_to_user(info) < 0)
return;
+ /*
+ * We get here via a few paths:
+ * - break instruction: cfm is shared with caller.
+ * syscall args are in out= regs, locals are non-empty.
+ * - epsinstruction: cfm is set by br.call
+ * locals don't exist.
+ *
+ * For both cases argguments are reachable in cfm.sof - cfm.sol.
+ * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ]
+ */
cfm = pt->cr_ifs;
+ nlocals = (cfm >> 7) & 0x7f; /* aka sol */
+ nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */
krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8;
ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));
count = 0;
if (in_syscall(pt))
- count = min_t(int, args->n, cfm & 0x7f);
+ count = min_t(int, args->n, nouts);
+ /* Iterate over outs. */
for (i = 0; i < count; i++) {
+ int j = ndirty + nlocals + i + args->i;
if (args->rw)
- *ia64_rse_skip_regs(krbs, ndirty + i + args->i) =
- args->args[i];
+ *ia64_rse_skip_regs(krbs, j) = args->args[i];
else
- args->args[i] = *ia64_rse_skip_regs(krbs,
- ndirty + i + args->i);
+ args->args[i] = *ia64_rse_skip_regs(krbs, j);
}
if (!args->rw) {
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 03b3a02375ff..c310b4c99fb3 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -95,7 +95,7 @@ static int __init build_node_maps(unsigned long start, unsigned long len,
* acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
* called yet. Note that node 0 will also count all non-existent cpus.
*/
-static int __meminit early_nr_cpus_node(int node)
+static int early_nr_cpus_node(int node)
{
int cpu, n = 0;
@@ -110,7 +110,7 @@ static int __meminit early_nr_cpus_node(int node)
* compute_pernodesize - compute size of pernode data
* @node: the node id.
*/
-static unsigned long __meminit compute_pernodesize(int node)
+static unsigned long compute_pernodesize(int node)
{
unsigned long pernodesize = 0, cpus;
@@ -367,7 +367,7 @@ static void __init reserve_pernode_space(void)
}
}
-static void __meminit scatter_node_data(void)
+static void scatter_node_data(void)
{
pg_data_t **dst;
int node;
diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h
index 7f5912af2a52..2411ea9ef578 100644
--- a/arch/m68k/include/asm/page_mm.h
+++ b/arch/m68k/include/asm/page_mm.h
@@ -167,11 +167,11 @@ static inline __attribute_const__ int __virt_to_node_shift(void)
((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn; \
})
#else
-#define ARCH_PFN_OFFSET (m68k_memory[0].addr)
+#define ARCH_PFN_OFFSET (m68k_memory[0].addr >> PAGE_SHIFT)
#include <asm-generic/memory_model.h>
#endif
-#define virt_addr_valid(kaddr) ((void *)(kaddr) >= (void *)PAGE_OFFSET && (void *)(kaddr) < high_memory)
+#define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
#define pfn_valid(pfn) virt_addr_valid(pfn_to_virt(pfn))
#endif /* __ASSEMBLY__ */
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index 6bbe52025de3..8d0f862ee9d7 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -30,8 +30,8 @@ extern unsigned long memory_end;
#define page_to_pfn(page) virt_to_pfn(page_to_virt(page))
#define pfn_valid(pfn) ((pfn) < max_mapnr)
-#define virt_addr_valid(kaddr) (((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
- ((void *)(kaddr) < (void *)memory_end))
+#define virt_addr_valid(kaddr) (((unsigned long)(kaddr) >= PAGE_OFFSET) && \
+ ((unsigned long)(kaddr) < memory_end))
#endif /* __ASSEMBLY__ */
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index e3946b06e840..3d70d15ada28 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -14,6 +14,7 @@
#include <asm/addrspace.h>
#include <asm/unaligned.h>
+#include <asm-generic/vmlinux.lds.h>
/*
* These two variables specify the free mem region
@@ -120,6 +121,13 @@ void decompress_kernel(unsigned long boot_heap_start)
/* last four bytes is always image size in little endian */
image_size = get_unaligned_le32((void *)&__image_end - 4);
+ /* The device tree's address must be properly aligned */
+ image_size = ALIGN(image_size, STRUCT_ALIGNMENT);
+
+ puts("Copy device tree to address ");
+ puthex(VMLINUX_LOAD_ADDRESS_ULL + image_size);
+ puts("\n");
+
/* copy dtb to where the booted kernel will expect it */
memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
__appended_dtb, dtb_size);
diff --git a/arch/mips/crypto/Makefile b/arch/mips/crypto/Makefile
index 8e1deaf00e0c..5e4105cccf9f 100644
--- a/arch/mips/crypto/Makefile
+++ b/arch/mips/crypto/Makefile
@@ -12,8 +12,8 @@ AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots
obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
poly1305-mips-y := poly1305-core.o poly1305-glue.o
-perlasm-flavour-$(CONFIG_CPU_MIPS32) := o32
-perlasm-flavour-$(CONFIG_CPU_MIPS64) := 64
+perlasm-flavour-$(CONFIG_32BIT) := o32
+perlasm-flavour-$(CONFIG_64BIT) := 64
quiet_cmd_perlasm = PERLASM $@
cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)
diff --git a/arch/mips/include/asm/traps.h b/arch/mips/include/asm/traps.h
index 6aa8f126a43d..b710e76c9c65 100644
--- a/arch/mips/include/asm/traps.h
+++ b/arch/mips/include/asm/traps.h
@@ -24,8 +24,11 @@ extern void (*board_ebase_setup)(void);
extern void (*board_cache_error_setup)(void);
extern int register_nmi_notifier(struct notifier_block *nb);
+extern void reserve_exception_space(phys_addr_t addr, unsigned long size);
extern char except_vec_nmi[];
+#define VECTORSPACING 0x100 /* for EI/VI mode */
+
#define nmi_notifier(fn, pri) \
({ \
static struct notifier_block fn##_nb = { \
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 9a89637b4ecf..b71892064f27 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -26,6 +26,7 @@
#include <asm/elf.h>
#include <asm/pgtable-bits.h>
#include <asm/spram.h>
+#include <asm/traps.h>
#include <linux/uaccess.h>
#include "fpu-probe.h"
@@ -1628,6 +1629,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
c->cputype = CPU_BMIPS3300;
__cpu_name[cpu] = "Broadcom BMIPS3300";
set_elf_platform(cpu, "bmips3300");
+ reserve_exception_space(0x400, VECTORSPACING * 64);
break;
case PRID_IMP_BMIPS43XX: {
int rev = c->processor_id & PRID_REV_MASK;
@@ -1638,6 +1640,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
__cpu_name[cpu] = "Broadcom BMIPS4380";
set_elf_platform(cpu, "bmips4380");
c->options |= MIPS_CPU_RIXI;
+ reserve_exception_space(0x400, VECTORSPACING * 64);
} else {
c->cputype = CPU_BMIPS4350;
__cpu_name[cpu] = "Broadcom BMIPS4350";
@@ -1654,6 +1657,7 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
__cpu_name[cpu] = "Broadcom BMIPS5000";
set_elf_platform(cpu, "bmips5000");
c->options |= MIPS_CPU_ULRI | MIPS_CPU_RIXI;
+ reserve_exception_space(0x1000, VECTORSPACING * 64);
break;
}
}
@@ -2133,6 +2137,8 @@ void cpu_probe(void)
if (cpu == 0)
__ua_limit = ~((1ull << cpu_vmbits) - 1);
#endif
+
+ reserve_exception_space(0, 0x1000);
}
void cpu_report(void)
diff --git a/arch/mips/kernel/cpu-r3k-probe.c b/arch/mips/kernel/cpu-r3k-probe.c
index abdbbe8c5a43..af654771918c 100644
--- a/arch/mips/kernel/cpu-r3k-probe.c
+++ b/arch/mips/kernel/cpu-r3k-probe.c
@@ -21,6 +21,7 @@
#include <asm/fpu.h>
#include <asm/mipsregs.h>
#include <asm/elf.h>
+#include <asm/traps.h>
#include "fpu-probe.h"
@@ -158,6 +159,8 @@ void cpu_probe(void)
cpu_set_fpu_opts(c);
else
cpu_set_nofpu_opts(c);
+
+ reserve_exception_space(0, 0x400);
}
void cpu_report(void)
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 279be0153f8b..23a140327a0b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -43,7 +43,7 @@
#include <asm/prom.h>
#ifdef CONFIG_MIPS_ELF_APPENDED_DTB
-const char __section(".appended_dtb") __appended_dtb[0x100000];
+char __section(".appended_dtb") __appended_dtb[0x100000];
#endif /* CONFIG_MIPS_ELF_APPENDED_DTB */
struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index e0352958e2f7..808b8b61ded1 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2009,13 +2009,16 @@ void __noreturn nmi_exception_handler(struct pt_regs *regs)
nmi_exit();
}
-#define VECTORSPACING 0x100 /* for EI/VI mode */
-
unsigned long ebase;
EXPORT_SYMBOL_GPL(ebase);
unsigned long exception_handlers[32];
unsigned long vi_handlers[64];
+void reserve_exception_space(phys_addr_t addr, unsigned long size)
+{
+ memblock_reserve(addr, size);
+}
+
void __init *set_except_vector(int n, void *addr)
{
unsigned long handler = (unsigned long) addr;
@@ -2367,10 +2370,7 @@ void __init trap_init(void)
if (!cpu_has_mips_r2_r6) {
ebase = CAC_BASE;
- ebase_pa = virt_to_phys((void *)ebase);
vec_size = 0x400;
-
- memblock_reserve(ebase_pa, vec_size);
} else {
if (cpu_has_veic || cpu_has_vint)
vec_size = 0x200 + VECTORSPACING*64;
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index c1c345be04ff..1f98947fe715 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -145,6 +145,7 @@ SECTIONS
}
#ifdef CONFIG_MIPS_ELF_APPENDED_DTB
+ STRUCT_ALIGN();
.appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
*(.appended_dtb)
KEEP(*(.appended_dtb))
@@ -172,6 +173,11 @@ SECTIONS
#endif
#ifdef CONFIG_MIPS_RAW_APPENDED_DTB
+ .fill : {
+ FILL(0);
+ BYTE(0);
+ STRUCT_ALIGN();
+ }
__appended_dtb = .;
/* leave space for appended DTB */
. += 0x100000;
diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index 6eb98a7ad27d..ad5344ef5d33 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -238,7 +238,7 @@ void flush_dcache_page(struct page *page)
{
struct address_space *mapping;
- mapping = page_mapping(page);
+ mapping = page_mapping_file(page);
if (mapping && !mapping_mapped(mapping))
set_bit(PG_dcache_dirty, &page->flags);
else {
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 4e53ac46e857..afc3b8d03572 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -203,9 +203,12 @@ config PREFETCH
def_bool y
depends on PA8X00 || PA7200
+config PARISC_HUGE_KERNEL
+ def_bool y if !MODULES || UBSAN || FTRACE || COMPILE_TEST
+
config MLONGCALLS
- def_bool y if !MODULES || UBSAN || FTRACE
- bool "Enable the -mlong-calls compiler option for big kernels" if MODULES && !UBSAN && !FTRACE
+ def_bool y if PARISC_HUGE_KERNEL
+ bool "Enable the -mlong-calls compiler option for big kernels" if !PARISC_HUGE_KERNEL
depends on PA8X00
help
If you configure the kernel to include many drivers built-in instead
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index cf5ee9b0b393..84ee232278a6 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -72,7 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
#endif
case 4: return __cmpxchg_u32((unsigned int *)ptr,
(unsigned int)old, (unsigned int)new_);
- case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
+ case 1: return __cmpxchg_u8((u8 *)ptr, old & 0xff, new_ & 0xff);
}
__cmpxchg_called_with_bad_pointer();
return old;
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 11ece0d07374..b5fbcd2c1780 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -272,7 +272,6 @@ on downward growing arches, it looks like this:
regs->gr[23] = 0; \
} while(0)
-struct task_struct;
struct mm_struct;
/* Free all resources held by a thread. */
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 2127974982df..65de6c4c9354 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -567,8 +567,6 @@ static const struct user_regset_view user_parisc_native_view = {
};
#ifdef CONFIG_64BIT
-#include <linux/compat.h>
-
static int gpr32_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
diff --git a/arch/parisc/math-emu/fpu.h b/arch/parisc/math-emu/fpu.h
index 853c19c03828..dec951d40286 100644
--- a/arch/parisc/math-emu/fpu.h
+++ b/arch/parisc/math-emu/fpu.h
@@ -5,34 +5,10 @@
* Floating-point emulation code
* Copyright (C) 2001 Hewlett-Packard (Paul Bame) <bame@debian.org>
*/
-/*
- * BEGIN_DESC
- *
- * File:
- * @(#) pa/fp/fpu.h $Revision: 1.1 $
- *
- * Purpose:
- * <<please update with a synopis of the functionality provided by this file>>
- *
- *
- * END_DESC
-*/
-
-#ifdef __NO_PA_HDRS
- PA header file -- do not include this header file for non-PA builds.
-#endif
-
#ifndef _MACHINE_FPU_INCLUDED /* allows multiple inclusion */
#define _MACHINE_FPU_INCLUDED
-#if 0
-#ifndef _SYS_STDSYMS_INCLUDED
-# include <sys/stdsyms.h>
-#endif /* _SYS_STDSYMS_INCLUDED */
-#include <machine/pdc/pdc_rqsts.h>
-#endif
-
#define PA83_FPU_FLAG 0x00000001
#define PA89_FPU_FLAG 0x00000002
#define PA2_0_FPU_FLAG 0x00000010
@@ -43,21 +19,19 @@
#define COPR_FP 0x00000080 /* Floating point -- Coprocessor 0 */
#define SFU_MPY_DIVIDE 0x00008000 /* Multiply/Divide __ SFU 0 */
-
#define EM_FPU_TYPE_OFFSET 272
/* version of EMULATION software for COPR,0,0 instruction */
#define EMULATION_VERSION 4
/*
- * The only was to differeniate between TIMEX and ROLEX (or PCX-S and PCX-T)
- * is thorough the potential type field from the PDC_MODEL call. The
- * following flags are used at assist this differeniation.
+ * The only way to differentiate between TIMEX and ROLEX (or PCX-S and PCX-T)
+ * is through the potential type field from the PDC_MODEL call.
+ * The following flags are used to assist this differentiation.
*/
#define ROLEX_POTENTIAL_KEY_FLAGS PDC_MODEL_CPU_KEY_WORD_TO_IO
#define TIMEX_POTENTIAL_KEY_FLAGS (PDC_MODEL_CPU_KEY_QUAD_STORE | \
PDC_MODEL_CPU_KEY_RECIP_SQRT)
-
#endif /* ! _MACHINE_FPU_INCLUDED */
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index eacc9102c251..f1d029bf906e 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -73,9 +73,10 @@ void __patch_exception(int exc, unsigned long addr);
#endif
#define OP_RT_RA_MASK 0xffff0000UL
-#define LIS_R2 0x3c020000UL
-#define ADDIS_R2_R12 0x3c4c0000UL
-#define ADDI_R2_R2 0x38420000UL
+#define LIS_R2 (PPC_INST_ADDIS | __PPC_RT(R2))
+#define ADDIS_R2_R12 (PPC_INST_ADDIS | __PPC_RT(R2) | __PPC_RA(R12))
+#define ADDI_R2_R2 (PPC_INST_ADDI | __PPC_RT(R2) | __PPC_RA(R2))
+
static inline unsigned long ppc_function_entry(void *func)
{
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 7897d16e0990..727d4b321937 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -7,7 +7,7 @@
#include <linux/bug.h>
#include <asm/cputable.h>
-static inline bool early_cpu_has_feature(unsigned long feature)
+static __always_inline bool early_cpu_has_feature(unsigned long feature)
{
return !!((CPU_FTRS_ALWAYS & feature) ||
(CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature));
@@ -46,7 +46,7 @@ static __always_inline bool cpu_has_feature(unsigned long feature)
return static_branch_likely(&cpu_feature_keys[i]);
}
#else
-static inline bool cpu_has_feature(unsigned long feature)
+static __always_inline bool cpu_has_feature(unsigned long feature)
{
return early_cpu_has_feature(feature);
}
diff --git a/arch/powerpc/include/asm/dcr-native.h b/arch/powerpc/include/asm/dcr-native.h
index 7141ccea8c94..a92059964579 100644
--- a/arch/powerpc/include/asm/dcr-native.h
+++ b/arch/powerpc/include/asm/dcr-native.h
@@ -53,8 +53,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
#define mfdcr(rn) \
({unsigned int rval; \
if (__builtin_constant_p(rn) && rn < 1024) \
- asm volatile("mfdcr %0," __stringify(rn) \
- : "=r" (rval)); \
+ asm volatile("mfdcr %0, %1" : "=r" (rval) \
+ : "n" (rn)); \
else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \
rval = mfdcrx(rn); \
else \
@@ -64,8 +64,8 @@ static inline void mtdcrx(unsigned int reg, unsigned int val)
#define mtdcr(rn, v) \
do { \
if (__builtin_constant_p(rn) && rn < 1024) \
- asm volatile("mtdcr " __stringify(rn) ",%0" \
- : : "r" (v)); \
+ asm volatile("mtdcr %0, %1" \
+ : : "n" (rn), "r" (v)); \
else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \
mtdcrx(rn, v); \
else \
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index aedfba29e43a..e8d09a841373 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -410,7 +410,6 @@ DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
DECLARE_INTERRUPT_HANDLER(CacheLockingException);
DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
-DECLARE_INTERRUPT_HANDLER(unrecoverable_exception);
DECLARE_INTERRUPT_HANDLER(WatchdogException);
DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
@@ -437,6 +436,8 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
+void unrecoverable_exception(struct pt_regs *regs);
+
void replay_system_reset(void);
void replay_soft_interrupts(void);
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 80b27f5d9648..607168b1aef4 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -228,7 +228,7 @@ enum {
#define MMU_FTRS_ALWAYS 0
#endif
-static inline bool early_mmu_has_feature(unsigned long feature)
+static __always_inline bool early_mmu_has_feature(unsigned long feature)
{
if (MMU_FTRS_ALWAYS & feature)
return true;
@@ -286,7 +286,7 @@ static inline void mmu_feature_keys_init(void)
}
-static inline bool mmu_has_feature(unsigned long feature)
+static __always_inline bool mmu_has_feature(unsigned long feature)
{
return early_mmu_has_feature(feature);
}
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 975ba260006a..1499e928ea6a 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -195,7 +195,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
#define TRAP_FLAGS_MASK 0x11
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) (((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs) ((regs)->trap |= 1)
+#define SET_FULL_REGS(regs) ((regs)->trap &= ~1)
#endif
#define CHECK_FULL_REGS(regs) BUG_ON(!FULL_REGS(regs))
#define NV_REG_POISON 0xdeadbeefdeadbeefUL
@@ -210,7 +210,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
#define TRAP_FLAGS_MASK 0x1F
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) (((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs) ((regs)->trap |= 1)
+#define SET_FULL_REGS(regs) ((regs)->trap &= ~1)
#define IS_CRITICAL_EXC(regs) (((regs)->trap & 2) != 0)
#define IS_MCHECK_EXC(regs) (((regs)->trap & 4) != 0)
#define IS_DEBUG_EXC(regs) (((regs)->trap & 8) != 0)
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index fdab93428372..9d1fbd8be1c7 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -71,6 +71,16 @@ static inline void disable_kernel_vsx(void)
{
msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
}
+#else
+static inline void enable_kernel_vsx(void)
+{
+ BUILD_BUG();
+}
+
+static inline void disable_kernel_vsx(void)
+{
+ BUILD_BUG();
+}
#endif
#ifdef CONFIG_SPE
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index 0cf52746531b..721c0d6715ac 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -113,7 +113,7 @@ struct vio_driver {
const char *name;
const struct vio_device_id *id_table;
int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
- int (*remove)(struct vio_dev *dev);
+ void (*remove)(struct vio_dev *dev);
/* A driver must have a get_desired_dma() function to
* be loaded in a CMO environment if it uses DMA.
*/
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 6084fa499aa3..f66b63e81c3b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -191,3 +191,7 @@ $(obj)/prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o FORCE
targets += prom_init_check
clean-files := vmlinux.lds
+
+# Force dependency (incbin is bad)
+$(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg
+$(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 60d3051a8bc8..8082b690e874 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -466,7 +466,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
ld r10,PACAKMSR(r13) /* get MSR value for kernel */
/* MSR[RI] is clear iff using SRR regs */
- .if IHSRR == EXC_HV_OR_STD
+ .if IHSRR_IF_HVMODE
BEGIN_FTR_SECTION
xori r10,r10,MSR_RI
END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 727fdab557c9..565e84e20a72 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -457,11 +457,12 @@ InstructionTLBMiss:
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SDR1
- li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
rlwinm r2, r2, 28, 0xfffff000
#ifdef CONFIG_MODULES
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
#endif
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
@@ -520,10 +521,11 @@ DataLoadTLBMiss:
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SDR1
- li r1, _PAGE_PRESENT | _PAGE_ACCESSED
+ li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
rlwinm r2, r2, 28, 0xfffff000
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1, _PAGE_PRESENT | _PAGE_ACCESSED
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
lwz r2,0(r2) /* get pmd entry */
@@ -597,10 +599,11 @@ DataStoreTLBMiss:
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SDR1
- li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+ li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
rlwinm r2, r2, 28, 0xfffff000
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
lwz r2,0(r2) /* get pmd entry */
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 398cd86b6ada..c475a229a42a 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -149,7 +149,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
* enabled when the interrupt handler returns (indicating a process-context /
* synchronous interrupt) then irqs_enabled should be true.
*/
-static notrace inline bool __prep_irq_for_enabled_exit(bool clear_ri)
+static notrace __always_inline bool __prep_irq_for_enabled_exit(bool clear_ri)
{
/* This must be done with RI=1 because tracing may touch vmaps */
trace_hardirqs_on();
@@ -436,7 +436,6 @@ again:
return ret;
}
-void unrecoverable_exception(struct pt_regs *regs);
void preempt_schedule_irq(void);
notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)
diff --git a/arch/powerpc/kernel/ptrace/Makefile b/arch/powerpc/kernel/ptrace/Makefile
index 8ebc11d1168d..77abd1a5a508 100644
--- a/arch/powerpc/kernel/ptrace/Makefile
+++ b/arch/powerpc/kernel/ptrace/Makefile
@@ -6,11 +6,11 @@
CFLAGS_ptrace-view.o += -DUTS_MACHINE='"$(UTS_MACHINE)"'
obj-y += ptrace.o ptrace-view.o
-obj-$(CONFIG_PPC_FPU_REGS) += ptrace-fpu.o
+obj-y += ptrace-fpu.o
obj-$(CONFIG_COMPAT) += ptrace32.o
obj-$(CONFIG_VSX) += ptrace-vsx.o
ifneq ($(CONFIG_VSX),y)
-obj-$(CONFIG_PPC_FPU_REGS) += ptrace-novsx.o
+obj-y += ptrace-novsx.o
endif
obj-$(CONFIG_ALTIVEC) += ptrace-altivec.o
obj-$(CONFIG_SPE) += ptrace-spe.o
diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h
index 3487f2c9735c..eafe5f0f6289 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-decl.h
+++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h
@@ -165,22 +165,8 @@ int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data);
extern const struct user_regset_view user_ppc_native_view;
/* ptrace-fpu */
-#ifdef CONFIG_PPC_FPU_REGS
int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data);
int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data);
-#else
-static inline int
-ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
-{
- return -EIO;
-}
-
-static inline int
-ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
-{
- return -EIO;
-}
-#endif
/* ptrace-(no)adv */
void ppc_gethwdinfo(struct ppc_debug_info *dbginfo);
diff --git a/arch/powerpc/kernel/ptrace/ptrace-fpu.c b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
index 8301cb52dd99..5dca19361316 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-fpu.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
@@ -8,32 +8,42 @@
int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
{
+#ifdef CONFIG_PPC_FPU_REGS
unsigned int fpidx = index - PT_FPR0;
+#endif
if (index > PT_FPSCR)
return -EIO;
+#ifdef CONFIG_PPC_FPU_REGS
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long));
else
*data = child->thread.fp_state.fpscr;
+#else
+ *data = 0;
+#endif
return 0;
}
int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
{
+#ifdef CONFIG_PPC_FPU_REGS
unsigned int fpidx = index - PT_FPR0;
+#endif
if (index > PT_FPSCR)
return -EIO;
+#ifdef CONFIG_PPC_FPU_REGS
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long));
else
child->thread.fp_state.fpscr = data;
+#endif
return 0;
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-novsx.c b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
index b3b36835658a..7433f3db979a 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-novsx.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
@@ -21,12 +21,16 @@
int fpr_get(struct task_struct *target, const struct user_regset *regset,
struct membuf to)
{
+#ifdef CONFIG_PPC_FPU_REGS
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
offsetof(struct thread_fp_state, fpr[32]));
flush_fp_to_thread(target);
return membuf_write(&to, &target->thread.fp_state, 33 * sizeof(u64));
+#else
+ return membuf_write(&to, &empty_zero_page, 33 * sizeof(u64));
+#endif
}
/*
@@ -46,6 +50,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
+#ifdef CONFIG_PPC_FPU_REGS
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
offsetof(struct thread_fp_state, fpr[32]));
@@ -53,4 +58,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset,
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&target->thread.fp_state, 0, -1);
+#else
+ return 0;
+#endif
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index 2bad8068f598..6ccffc65ac97 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -522,13 +522,11 @@ static const struct user_regset native_regsets[] = {
.size = sizeof(long), .align = sizeof(long),
.regset_get = gpr_get, .set = gpr_set
},
-#ifdef CONFIG_PPC_FPU_REGS
[REGSET_FPR] = {
.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
.size = sizeof(double), .align = sizeof(double),
.regset_get = fpr_get, .set = fpr_set
},
-#endif
#ifdef CONFIG_ALTIVEC
[REGSET_VMX] = {
.core_note_type = NT_PPC_VMX, .n = 34,
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 75ee918a120a..f651b992fe01 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -775,7 +775,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
else
prepare_save_user_regs(1);
- if (!user_write_access_begin(frame, sizeof(*frame)))
+ if (!user_access_begin(frame, sizeof(*frame)))
goto badframe;
/* Put the siginfo & fill in most of the ucontext */
@@ -809,17 +809,15 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
unsafe_put_user(PPC_INST_ADDI + __NR_rt_sigreturn, &mctx->mc_pad[0],
failed);
unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed);
+ asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
}
unsafe_put_sigset_t(&frame->uc.uc_sigmask, oldset, failed);
- user_write_access_end();
+ user_access_end();
if (copy_siginfo_to_user(&frame->info, &ksig->info))
goto badframe;
- if (tramp == (unsigned long)mctx->mc_pad)
- flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long));
-
regs->link = tramp;
#ifdef CONFIG_PPC_FPU_REGS
@@ -844,7 +842,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
return 0;
failed:
- user_write_access_end();
+ user_access_end();
badframe:
signal_fault(tsk, regs, "handle_rt_signal32", frame);
@@ -879,7 +877,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
else
prepare_save_user_regs(1);
- if (!user_write_access_begin(frame, sizeof(*frame)))
+ if (!user_access_begin(frame, sizeof(*frame)))
goto badframe;
sc = (struct sigcontext __user *) &frame->sctx;
@@ -908,11 +906,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
/* Set up the sigreturn trampoline: li r0,sigret; sc */
unsafe_put_user(PPC_INST_ADDI + __NR_sigreturn, &mctx->mc_pad[0], failed);
unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed);
+ asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
}
- user_write_access_end();
-
- if (tramp == (unsigned long)mctx->mc_pad)
- flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long));
+ user_access_end();
regs->link = tramp;
@@ -935,7 +931,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
return 0;
failed:
- user_write_access_end();
+ user_access_end();
badframe:
signal_fault(tsk, regs, "handle_signal32", frame);
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1583fd1c6010..a44a30b0688c 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -2170,7 +2170,7 @@ DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
* in the MSR is 0. This indicates that SRR0/1 are live, and that
* we therefore lost state by taking this exception.
*/
-DEFINE_INTERRUPT_HANDLER(unrecoverable_exception)
+void unrecoverable_exception(struct pt_regs *regs)
{
pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
regs->trap, regs->nip, regs->msr);
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index a6e29f880e0e..d21d08140a5e 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -65,3 +65,14 @@ V_FUNCTION_END(__kernel_clock_getres)
V_FUNCTION_BEGIN(__kernel_time)
cvdso_call_time __c_kernel_time
V_FUNCTION_END(__kernel_time)
+
+/* Routines for restoring integer registers, called by the compiler. */
+/* Called with r11 pointing to the stack header word of the caller of the */
+/* function, just beyond the end of the integer restore area. */
+_GLOBAL(_restgpr_31_x)
+_GLOBAL(_rest32gpr_31_x)
+ lwz r0,4(r11)
+ lwz r31,-4(r11)
+ mtlr r0
+ mr r1,r11
+ blr
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index bb5c20d4ca91..c6aebc149d14 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -904,7 +904,7 @@ static nokprobe_inline int do_vsx_load(struct instruction_op *op,
if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs))
return -EFAULT;
- nr_vsx_regs = size / sizeof(__vector128);
+ nr_vsx_regs = max(1ul, size / sizeof(__vector128));
emulate_vsx_load(op, buf, mem, cross_endian);
preempt_disable();
if (reg < 32) {
@@ -951,7 +951,7 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op,
if (!address_ok(regs, ea, size))
return -EFAULT;
- nr_vsx_regs = size / sizeof(__vector128);
+ nr_vsx_regs = max(1ul, size / sizeof(__vector128));
preempt_disable();
if (reg < 32) {
/* FP regs + extensions */
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6817331e22ff..766f064f00fb 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -222,7 +222,7 @@ static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *
if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
*addrp = mfspr(SPRN_SDAR);
- if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0)
+ if (is_kernel_addr(mfspr(SPRN_SDAR)) && event->attr.exclude_kernel)
*addrp = 0;
}
@@ -507,7 +507,7 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *
* addresses, hence include a check before filtering code
*/
if (!(ppmu->flags & PPMU_ARCH_31) &&
- is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
+ is_kernel_addr(addr) && event->attr.exclude_kernel)
continue;
/* Branches are read most recent first (ie. mfbhrb 0 is
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 764170fdb0f7..3805519a6469 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -887,7 +887,8 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot,
want_v = hpte_encode_avpn(vpn, psize, ssize);
- flags = (newpp & 7) | H_AVPN;
+ flags = (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO)) | H_AVPN;
+ flags |= (newpp & HPTE_R_KEY_HI) >> 48;
if (mmu_has_feature(MMU_FTR_KERNEL_RO))
/* Move pp0 into bit 8 (IBM 55) */
flags |= (newpp & HPTE_R_PP0) >> 55;
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index ea4d6a660e0d..e83e0891272d 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -452,12 +452,28 @@ static int do_suspend(void)
return ret;
}
+/**
+ * struct pseries_suspend_info - State shared between CPUs for join/suspend.
+ * @counter: Threads are to increment this upon resuming from suspend
+ * or if an error is received from H_JOIN. The thread which performs
+ * the first increment (i.e. sets it to 1) is responsible for
+ * waking the other threads.
+ * @done: False if join/suspend is in progress. True if the operation is
+ * complete (successful or not).
+ */
+struct pseries_suspend_info {
+ atomic_t counter;
+ bool done;
+};
+
static int do_join(void *arg)
{
- atomic_t *counter = arg;
+ struct pseries_suspend_info *info = arg;
+ atomic_t *counter = &info->counter;
long hvrc;
int ret;
+retry:
/* Must ensure MSR.EE off for H_JOIN. */
hard_irq_disable();
hvrc = plpar_hcall_norets(H_JOIN);
@@ -473,8 +489,20 @@ static int do_join(void *arg)
case H_SUCCESS:
/*
* The suspend is complete and this cpu has received a
- * prod.
+ * prod, or we've received a stray prod from unrelated
+ * code (e.g. paravirt spinlocks) and we need to join
+ * again.
+ *
+ * This barrier orders the return from H_JOIN above vs
+ * the load of info->done. It pairs with the barrier
+ * in the wakeup/prod path below.
*/
+ smp_mb();
+ if (READ_ONCE(info->done) == false) {
+ pr_info_ratelimited("premature return from H_JOIN on CPU %i, retrying",
+ smp_processor_id());
+ goto retry;
+ }
ret = 0;
break;
case H_BAD_MODE:
@@ -488,6 +516,13 @@ static int do_join(void *arg)
if (atomic_inc_return(counter) == 1) {
pr_info("CPU %u waking all threads\n", smp_processor_id());
+ WRITE_ONCE(info->done, true);
+ /*
+ * This barrier orders the store to info->done vs subsequent
+ * H_PRODs to wake the other CPUs. It pairs with the barrier
+ * in the H_SUCCESS case above.
+ */
+ smp_mb();
prod_others();
}
/*
@@ -535,11 +570,16 @@ static int pseries_suspend(u64 handle)
int ret;
while (true) {
- atomic_t counter = ATOMIC_INIT(0);
+ struct pseries_suspend_info info;
unsigned long vasi_state;
int vasi_err;
- ret = stop_machine(do_join, &counter, cpu_online_mask);
+ info = (struct pseries_suspend_info) {
+ .counter = ATOMIC_INIT(0),
+ .done = false,
+ };
+
+ ret = stop_machine(do_join, &info, cpu_online_mask);
if (ret == 0)
break;
/*
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index b3ac2455faad..637300330507 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -4,6 +4,7 @@
* Copyright 2006-2007 Michael Ellerman, IBM Corp.
*/
+#include <linux/crash_dump.h>
#include <linux/device.h>
#include <linux/irq.h>
#include <linux/msi.h>
@@ -458,8 +459,28 @@ again:
return hwirq;
}
- virq = irq_create_mapping_affinity(NULL, hwirq,
- entry->affinity);
+ /*
+ * Depending on the number of online CPUs in the original
+ * kernel, it is likely for CPU #0 to be offline in a kdump
+ * kernel. The associated IRQs in the affinity mappings
+ * provided by irq_create_affinity_masks() are thus not
+ * started by irq_startup(), as per-design for managed IRQs.
+ * This can be a problem with multi-queue block devices driven
+ * by blk-mq : such a non-started IRQ is very likely paired
+ * with the single queue enforced by blk-mq during kdump (see
+ * blk_mq_alloc_tag_set()). This causes the device to remain
+ * silent and likely hangs the guest at some point.
+ *
+ * We don't really care for fine-grained affinity when doing
+ * kdump actually : simply ignore the pre-computed affinity
+ * masks in this case and let the default mask with all CPUs
+ * be used when creating the IRQ mappings.
+ */
+ if (is_kdump_kernel())
+ virq = irq_create_mapping(NULL, hwirq);
+ else
+ virq = irq_create_mapping_affinity(NULL, hwirq,
+ entry->affinity);
if (!virq) {
pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index b2797cfe4e2b..9cb4fc839fd5 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1261,7 +1261,6 @@ static int vio_bus_remove(struct device *dev)
struct vio_dev *viodev = to_vio_dev(dev);
struct vio_driver *viodrv = to_vio_driver(dev->driver);
struct device *devptr;
- int ret = 1;
/*
* Hold a reference to the device after the remove function is called
@@ -1270,13 +1269,13 @@ static int vio_bus_remove(struct device *dev)
devptr = get_device(dev);
if (viodrv->remove)
- ret = viodrv->remove(viodev);
+ viodrv->remove(viodev);
- if (!ret && firmware_has_feature(FW_FEATURE_CMO))
+ if (firmware_has_feature(FW_FEATURE_CMO))
vio_cmo_bus_remove(viodev);
put_device(devptr);
- return ret;
+ return 0;
}
/**
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 85d626b8ce5e..4515a10c5d22 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -93,7 +93,6 @@ config RISCV
select PCI_MSI if PCI
select RISCV_INTC
select RISCV_TIMER if RISCV_SBI
- select SPARSEMEM_STATIC if 32BIT
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
@@ -154,7 +153,8 @@ config ARCH_FLATMEM_ENABLE
config ARCH_SPARSEMEM_ENABLE
def_bool y
depends on MMU
- select SPARSEMEM_VMEMMAP_ENABLE
+ select SPARSEMEM_STATIC if 32BIT && SPARSEMEM
+ select SPARSEMEM_VMEMMAP_ENABLE if 64BIT
config ARCH_SELECT_MEMORY_MODEL
def_bool ARCH_SPARSEMEM_ENABLE
@@ -314,7 +314,7 @@ endchoice
# Common NUMA Features
config NUMA
bool "NUMA Memory Allocation and Scheduler Support"
- depends on SMP
+ depends on SMP && MMU
select GENERIC_ARCH_NUMA
select OF_NUMA
select ARCH_SUPPORTS_NUMA_BALANCING
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 7efcece8896c..e1b2690b6e45 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -31,6 +31,8 @@ config SOC_CANAAN
select SIFIVE_PLIC
select ARCH_HAS_RESET_CONTROLLER
select PINCTRL
+ select COMMON_CLK
+ select COMMON_CLK_K210
help
This enables support for Canaan Kendryte K210 SoC platform hardware.
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 27e005fca584..2a652b0c987d 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -9,4 +9,20 @@ long long __lshrti3(long long a, int b);
long long __ashrti3(long long a, int b);
long long __ashlti3(long long a, int b);
+
+#define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs)
+
+DECLARE_DO_ERROR_INFO(do_trap_unknown);
+DECLARE_DO_ERROR_INFO(do_trap_insn_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_insn_fault);
+DECLARE_DO_ERROR_INFO(do_trap_insn_illegal);
+DECLARE_DO_ERROR_INFO(do_trap_load_fault);
+DECLARE_DO_ERROR_INFO(do_trap_load_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_fault);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_u);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
+DECLARE_DO_ERROR_INFO(do_trap_break);
+
#endif /* _ASM_RISCV_PROTOTYPES_H */
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
index 9807ad164015..e4c435509983 100644
--- a/arch/riscv/include/asm/irq.h
+++ b/arch/riscv/include/asm/irq.h
@@ -12,4 +12,6 @@
#include <asm-generic/irq.h>
+extern void __init init_IRQ(void);
+
#endif /* _ASM_RISCV_IRQ_H */
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 3a240037bde2..021ed64ee608 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -71,6 +71,7 @@ int riscv_of_processor_hartid(struct device_node *node);
int riscv_of_parent_hartid(struct device_node *node);
extern void riscv_fill_hwcap(void);
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index cb4abb639e8d..09ad4e923510 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -119,6 +119,11 @@ extern int regs_query_register_offset(const char *name);
extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
unsigned int n);
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+ unsigned long frame_pointer);
+int do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_exit(struct pt_regs *regs);
+
/**
* regs_get_register() - get register value from its offset
* @regs: pt_regs from which register value is gotten
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index 99895d9c3bdd..d7027411dde8 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -51,10 +51,10 @@ enum sbi_ext_rfence_fid {
SBI_EXT_RFENCE_REMOTE_FENCE_I = 0,
SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
- SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
- SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+ SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+ SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
};
enum sbi_ext_hsm_fid {
diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h
index 81de51e6aa32..507cae273bc6 100644
--- a/arch/riscv/include/asm/timex.h
+++ b/arch/riscv/include/asm/timex.h
@@ -88,4 +88,6 @@ static inline int read_current_timer(unsigned long *timer_val)
return 0;
}
+extern void time_init(void);
+
#endif /* _ASM_RISCV_TIMEX_H */
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 824b2c9da75b..f944062c9d99 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -306,7 +306,9 @@ do { \
* data types like structures or arrays.
*
* @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
+ * to the result of dereferencing @ptr. The value of @x is copied to avoid
+ * re-ordering where @x is evaluated inside the block that enables user-space
+ * access (thus bypassing user space protection if @x is a function).
*
* Caller must check the pointer with access_ok() before calling this
* function.
@@ -316,12 +318,13 @@ do { \
#define __put_user(x, ptr) \
({ \
__typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ __typeof__(*__gu_ptr) __val = (x); \
long __pu_err = 0; \
\
__chk_user_ptr(__gu_ptr); \
\
__enable_user_access(); \
- __put_user_nocheck(x, __gu_ptr, __pu_err); \
+ __put_user_nocheck(__val, __gu_ptr, __pu_err); \
__disable_user_access(); \
\
__pu_err; \
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 3dc0abde988a..647a47f5484a 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -8,6 +8,7 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE)
endif
+CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,)
extra-y += head.o
extra-y += vmlinux.lds
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 744f3209c48d..83095faa680e 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -130,6 +130,9 @@ skip_context_tracking:
*/
andi t0, s1, SR_PIE
beqz t0, 1f
+ /* kprobes, entered via ebreak, must have interrupts disabled. */
+ li t0, EXC_BREAKPOINT
+ beq s4, t0, 1f
#ifdef CONFIG_TRACE_IRQFLAGS
call trace_hardirqs_on
#endif
@@ -447,6 +450,7 @@ ENDPROC(__switch_to)
#endif
.section ".rodata"
+ .align LGREG
/* Exception vector table */
ENTRY(excp_vect_table)
RISCV_PTR do_trap_insn_misaligned
diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c
index e6372490aa0b..aab85a82f419 100644
--- a/arch/riscv/kernel/probes/ftrace.c
+++ b/arch/riscv/kernel/probes/ftrace.c
@@ -2,39 +2,47 @@
#include <linux/kprobes.h>
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *ops, struct ftrace_regs *regs)
+ struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
struct kprobe *p;
+ struct pt_regs *regs;
struct kprobe_ctlblk *kcb;
+ int bit;
+ bit = ftrace_test_recursion_trylock(ip, parent_ip);
+ if (bit < 0)
+ return;
+
+ preempt_disable_notrace();
p = get_kprobe((kprobe_opcode_t *)ip);
if (unlikely(!p) || kprobe_disabled(p))
- return;
+ goto out;
+ regs = ftrace_get_regs(fregs);
kcb = get_kprobe_ctlblk();
if (kprobe_running()) {
kprobes_inc_nmissed_count(p);
} else {
- unsigned long orig_ip = instruction_pointer(&(regs->regs));
+ unsigned long orig_ip = instruction_pointer(regs);
- instruction_pointer_set(&(regs->regs), ip);
+ instruction_pointer_set(regs, ip);
__this_cpu_write(current_kprobe, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
- if (!p->pre_handler || !p->pre_handler(p, &(regs->regs))) {
+ if (!p->pre_handler || !p->pre_handler(p, regs)) {
/*
* Emulate singlestep (and also recover regs->pc)
* as if there is a nop
*/
- instruction_pointer_set(&(regs->regs),
+ instruction_pointer_set(regs,
(unsigned long)p->addr + MCOUNT_INSN_SIZE);
if (unlikely(p->post_handler)) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
- p->post_handler(p, &(regs->regs), 0);
+ p->post_handler(p, regs, 0);
}
- instruction_pointer_set(&(regs->regs), orig_ip);
+ instruction_pointer_set(regs, orig_ip);
}
/*
@@ -43,6 +51,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
*/
__this_cpu_write(current_kprobe, NULL);
}
+out:
+ preempt_enable_notrace();
+ ftrace_test_recursion_unlock(bit);
}
NOKPROBE_SYMBOL(kprobe_ftrace_handler);
diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
index a2ec18662fee..7e2c78e2ca6b 100644
--- a/arch/riscv/kernel/probes/kprobes.c
+++ b/arch/riscv/kernel/probes/kprobes.c
@@ -256,8 +256,7 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr)
* normal page fault.
*/
regs->epc = (unsigned long) cur->addr;
- if (!instruction_pointer(regs))
- BUG();
+ BUG_ON(!instruction_pointer(regs));
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 6f728e731bed..f9cd57c9c67d 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -10,6 +10,7 @@
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/sched.h>
+#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/tick.h>
#include <linux/ptrace.h>
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index f4a7db3d309e..d3bf756321a5 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -116,7 +116,7 @@ void sbi_clear_ipi(void)
EXPORT_SYMBOL(sbi_clear_ipi);
/**
- * sbi_set_timer_v01() - Program the timer for next timer event.
+ * __sbi_set_timer_v01() - Program the timer for next timer event.
* @stime_value: The value after which next timer event should fire.
*
* Return: None
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index e85bacff1b50..f8f15332caa2 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -147,7 +147,8 @@ static void __init init_resources(void)
bss_res.end = __pa_symbol(__bss_stop) - 1;
bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
- mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res);
+ /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
+ mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt + 1) * sizeof(*mem_res);
mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
if (!mem_res)
panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 3f893c9d9d85..2b3e0cb90d78 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -14,7 +14,7 @@
#include <asm/stacktrace.h>
-register const unsigned long sp_in_global __asm__("sp");
+register unsigned long sp_in_global __asm__("sp");
#ifdef CONFIG_FRAME_POINTER
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 8a5cf99c0776..1b432264f7ef 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -9,6 +9,7 @@
#include <linux/delay.h>
#include <asm/sbi.h>
#include <asm/processor.h>
+#include <asm/timex.h>
unsigned long riscv_timebase;
EXPORT_SYMBOL_GPL(riscv_timebase);
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 3ed2c23601a0..1357abf79570 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -17,6 +17,7 @@
#include <linux/module.h>
#include <linux/irq.h>
+#include <asm/asm-prototypes.h>
#include <asm/bug.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
@@ -177,6 +178,7 @@ asmlinkage __visible void do_trap_break(struct pt_regs *regs)
else
die(regs, "Kernel BUG");
}
+NOKPROBE_SYMBOL(do_trap_break);
#ifdef CONFIG_GENERIC_BUG
int is_valid_bugaddr(unsigned long pc)
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 8f17519208c7..c5dbd55cbf7c 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -328,3 +328,4 @@ good_area:
}
return;
}
+NOKPROBE_SYMBOL(do_page_fault);
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 3fc18f469efb..937d13ce9ab8 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -155,7 +155,7 @@ static void __init kasan_populate(void *start, void *end)
memset(start, KASAN_SHADOW_INIT, end - start);
}
-void __init kasan_shallow_populate(void *start, void *end)
+static void __init kasan_shallow_populate(void *start, void *end)
{
unsigned long vaddr = (unsigned long)start & PAGE_MASK;
unsigned long vend = PAGE_ALIGN((unsigned long)end);
@@ -187,6 +187,8 @@ void __init kasan_shallow_populate(void *start, void *end)
}
vaddr += PAGE_SIZE;
}
+
+ local_flush_tlb_all();
}
void __init kasan_init(void)
@@ -214,7 +216,7 @@ void __init kasan_init(void)
break;
kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
- };
+ }
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(&kasan_early_shadow_pte[i],
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 02056b024091..dc0b69058ac4 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -275,9 +275,9 @@ CONFIG_IP_VS_DH=m
CONFIG_IP_VS_SH=m
CONFIG_IP_VS_SED=m
CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
CONFIG_IP_NF_IPTABLES=m
@@ -298,7 +298,6 @@ CONFIG_IP_NF_SECURITY=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_FIB_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
@@ -481,7 +480,6 @@ CONFIG_NLMON=m
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_BROCADE is not set
# CONFIG_NET_VENDOR_CADENCE is not set
@@ -581,7 +579,6 @@ CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
CONFIG_S390_CCW_IOMMU=y
CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
@@ -635,6 +632,7 @@ CONFIG_NTFS_RW=y
CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
CONFIG_HUGETLBFS=y
CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
@@ -714,12 +712,8 @@ CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
@@ -731,7 +725,6 @@ CONFIG_CRYPTO_CAST6=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
@@ -796,12 +789,9 @@ CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
CONFIG_SLUB_DEBUG_ON=y
CONFIG_SLUB_STATS=y
-CONFIG_DEBUG_KMEMLEAK=y
-CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y
CONFIG_DEBUG_STACK_USAGE=y
CONFIG_DEBUG_VM=y
CONFIG_DEBUG_VM_VMACACHE=y
-CONFIG_DEBUG_VM_RB=y
CONFIG_DEBUG_VM_PGFLAGS=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
@@ -838,6 +828,7 @@ CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
CONFIG_FTRACE_STARTUP_TEST=y
# CONFIG_EVENT_TRACE_STARTUP_TEST is not set
+CONFIG_DEBUG_ENTRY=y
CONFIG_NOTIFIER_ERROR_INJECTION=m
CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
@@ -861,4 +852,3 @@ CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BITOPS=m
CONFIG_TEST_BPF=m
-CONFIG_DEBUG_ENTRY=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index bac721a501da..320379da96d9 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -266,9 +266,9 @@ CONFIG_IP_VS_DH=m
CONFIG_IP_VS_SH=m
CONFIG_IP_VS_SED=m
CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
CONFIG_IP_NF_IPTABLES=m
@@ -289,7 +289,6 @@ CONFIG_IP_NF_SECURITY=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_FIB_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
@@ -473,7 +472,6 @@ CONFIG_NLMON=m
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_BROCADE is not set
# CONFIG_NET_VENDOR_CADENCE is not set
@@ -573,7 +571,6 @@ CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
CONFIG_S390_CCW_IOMMU=y
CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
@@ -623,6 +620,7 @@ CONFIG_NTFS_RW=y
CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
CONFIG_HUGETLBFS=y
CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
@@ -703,12 +701,8 @@ CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
@@ -720,7 +714,6 @@ CONFIG_CRYPTO_CAST6=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index acf982a2ae4c..76123a4b26ab 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -26,7 +26,6 @@ CONFIG_CRASH_DUMP=y
# CONFIG_SECCOMP is not set
# CONFIG_GCC_PLUGINS is not set
CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_COMPACTION is not set
# CONFIG_MIGRATION is not set
@@ -61,11 +60,9 @@ CONFIG_RAW_DRIVER=y
# CONFIG_HID is not set
# CONFIG_VIRTIO_MENU is not set
# CONFIG_VHOST_MENU is not set
-# CONFIG_SURFACE_PLATFORMS is not set
# CONFIG_IOMMU_SUPPORT is not set
# CONFIG_DNOTIFY is not set
# CONFIG_INOTIFY_USER is not set
-CONFIG_CONFIGFS_FS=y
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_LSM="yama,loadpin,safesetid,integrity"
diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index b04f6a794cdf..5cea629c548e 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -14,12 +14,12 @@
struct s390_idle_data {
seqcount_t seqcount;
- unsigned long long idle_count;
- unsigned long long idle_time;
- unsigned long long clock_idle_enter;
- unsigned long long clock_idle_exit;
- unsigned long long timer_idle_enter;
- unsigned long long timer_idle_exit;
+ unsigned long idle_count;
+ unsigned long idle_time;
+ unsigned long clock_idle_enter;
+ unsigned long clock_idle_exit;
+ unsigned long timer_idle_enter;
+ unsigned long timer_idle_exit;
unsigned long mt_cycles_enter[8];
};
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 053fe8b8dec7..a75d94a9bcb2 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -202,7 +202,7 @@ extern unsigned int s390_pci_no_rid;
----------------------------------------------------------------------------- */
/* Base stuff */
int zpci_create_device(u32 fid, u32 fh, enum zpci_state state);
-void zpci_remove_device(struct zpci_dev *zdev);
+void zpci_remove_device(struct zpci_dev *zdev, bool set_error);
int zpci_enable_device(struct zpci_dev *);
int zpci_disable_device(struct zpci_dev *);
int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index ee056f4a4fa3..2b543163d90a 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -12,6 +12,7 @@ enum stack_type {
STACK_TYPE_IRQ,
STACK_TYPE_NODAT,
STACK_TYPE_RESTART,
+ STACK_TYPE_MCCK,
};
struct stack_info {
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index c4e23e925665..f6326c6d2abe 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -98,10 +98,10 @@ extern unsigned char ptff_function_mask[16];
/* Query TOD offset result */
struct ptff_qto {
- unsigned long long physical_clock;
- unsigned long long tod_offset;
- unsigned long long logical_tod_offset;
- unsigned long long tod_epoch_difference;
+ unsigned long physical_clock;
+ unsigned long tod_offset;
+ unsigned long logical_tod_offset;
+ unsigned long tod_epoch_difference;
} __packed;
static inline int ptff_query(unsigned int nr)
@@ -151,9 +151,9 @@ struct ptff_qui {
rc; \
})
-static inline unsigned long long local_tick_disable(void)
+static inline unsigned long local_tick_disable(void)
{
- unsigned long long old;
+ unsigned long old;
old = S390_lowcore.clock_comparator;
S390_lowcore.clock_comparator = clock_comparator_max;
@@ -161,7 +161,7 @@ static inline unsigned long long local_tick_disable(void)
return old;
}
-static inline void local_tick_enable(unsigned long long comp)
+static inline void local_tick_enable(unsigned long comp)
{
S390_lowcore.clock_comparator = comp;
set_clock_comparator(S390_lowcore.clock_comparator);
@@ -169,9 +169,9 @@ static inline void local_tick_enable(unsigned long long comp)
#define CLOCK_TICK_RATE 1193180 /* Underlying HZ */
-typedef unsigned long long cycles_t;
+typedef unsigned long cycles_t;
-static inline unsigned long long get_tod_clock(void)
+static inline unsigned long get_tod_clock(void)
{
union tod_clock clk;
@@ -179,10 +179,10 @@ static inline unsigned long long get_tod_clock(void)
return clk.tod;
}
-static inline unsigned long long get_tod_clock_fast(void)
+static inline unsigned long get_tod_clock_fast(void)
{
#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
- unsigned long long clk;
+ unsigned long clk;
asm volatile("stckf %0" : "=Q" (clk) : : "cc");
return clk;
@@ -208,9 +208,9 @@ extern union tod_clock tod_clock_base;
* Therefore preemption must be disabled, otherwise the returned
* value is not guaranteed to be monotonic.
*/
-static inline unsigned long long get_tod_clock_monotonic(void)
+static inline unsigned long get_tod_clock_monotonic(void)
{
- unsigned long long tod;
+ unsigned long tod;
preempt_disable_notrace();
tod = get_tod_clock() - tod_clock_base.tod;
@@ -237,7 +237,7 @@ static inline unsigned long long get_tod_clock_monotonic(void)
* -> ns = (th * 125) + ((tl * 125) >> 9);
*
*/
-static inline unsigned long long tod_to_ns(unsigned long long todval)
+static inline unsigned long tod_to_ns(unsigned long todval)
{
return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
}
@@ -249,10 +249,10 @@ static inline unsigned long long tod_to_ns(unsigned long long todval)
*
* Returns: true if a is later than b
*/
-static inline int tod_after(unsigned long long a, unsigned long long b)
+static inline int tod_after(unsigned long a, unsigned long b)
{
if (MACHINE_HAS_SCC)
- return (long long) a > (long long) b;
+ return (long) a > (long) b;
return a > b;
}
@@ -263,10 +263,10 @@ static inline int tod_after(unsigned long long a, unsigned long long b)
*
* Returns: true if a is later than b
*/
-static inline int tod_after_eq(unsigned long long a, unsigned long long b)
+static inline int tod_after_eq(unsigned long a, unsigned long b)
{
if (MACHINE_HAS_SCC)
- return (long long) a >= (long long) b;
+ return (long) a >= (long) b;
return a >= b;
}
diff --git a/arch/s390/include/asm/vdso/data.h b/arch/s390/include/asm/vdso/data.h
index 7b3cdb4a5f48..73ee89142666 100644
--- a/arch/s390/include/asm/vdso/data.h
+++ b/arch/s390/include/asm/vdso/data.h
@@ -6,7 +6,7 @@
#include <vdso/datapage.h>
struct arch_vdso_data {
- __u64 tod_steering_delta;
+ __s64 tod_steering_delta;
__u64 tod_steering_end;
};
diff --git a/arch/s390/include/uapi/asm/perf_cpum_cf_diag.h b/arch/s390/include/uapi/asm/hwctrset.h
index 3d8284b95f87..3d8284b95f87 100644
--- a/arch/s390/include/uapi/asm/perf_cpum_cf_diag.h
+++ b/arch/s390/include/uapi/asm/hwctrset.h
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index af013b4244d3..2da027359798 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -37,10 +37,12 @@ static int diag8_noresponse(int cmdlen)
static int diag8_response(int cmdlen, char *response, int *rlen)
{
+ unsigned long _cmdlen = cmdlen | 0x40000000L;
+ unsigned long _rlen = *rlen;
register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
register unsigned long reg3 asm ("3") = (addr_t) response;
- register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
- register unsigned long reg5 asm ("5") = *rlen;
+ register unsigned long reg4 asm ("4") = _cmdlen;
+ register unsigned long reg5 asm ("5") = _rlen;
asm volatile(
" diag %2,%0,0x8\n"
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 0dc4b258b98d..db1bc00229ca 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -79,6 +79,15 @@ static bool in_nodat_stack(unsigned long sp, struct stack_info *info)
return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top);
}
+static bool in_mcck_stack(unsigned long sp, struct stack_info *info)
+{
+ unsigned long frame_size, top;
+
+ frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+ top = S390_lowcore.mcck_stack + frame_size;
+ return in_stack(sp, info, STACK_TYPE_MCCK, top - THREAD_SIZE, top);
+}
+
static bool in_restart_stack(unsigned long sp, struct stack_info *info)
{
unsigned long frame_size, top;
@@ -108,7 +117,8 @@ int get_stack_info(unsigned long sp, struct task_struct *task,
/* Check per-cpu stacks */
if (!in_irq_stack(sp, info) &&
!in_nodat_stack(sp, info) &&
- !in_restart_stack(sp, info))
+ !in_restart_stack(sp, info) &&
+ !in_mcck_stack(sp, info))
goto unknown;
recursion_check:
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index c10b9f31eef7..12de7a9c85b3 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -401,15 +401,13 @@ ENTRY(\name)
brasl %r14,.Lcleanup_sie_int
#endif
0: CHECK_STACK __LC_SAVE_AREA_ASYNC
- lgr %r11,%r15
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- stg %r11,__SF_BACKCHAIN(%r15)
j 2f
1: BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
lctlg %c1,%c1,__LC_KERNEL_ASCE
lg %r15,__LC_KERNEL_STACK
- xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-2: la %r11,STACK_FRAME_OVERHEAD(%r15)
+2: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+ la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
# clear user controlled registers to prevent speculative use
xgr %r0,%r0
@@ -445,6 +443,7 @@ INT_HANDLER io_int_handler,__LC_IO_OLD_PSW,do_io_irq
* Load idle PSW.
*/
ENTRY(psw_idle)
+ stg %r14,(__SF_GPRS+8*8)(%r15)
stg %r3,__SF_EMPTY(%r15)
larl %r1,psw_idle_exit
stg %r1,__SF_EMPTY+8(%r15)
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 812073ea073e..4bf1ee293f2b 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -47,7 +47,7 @@ void account_idle_time_irq(void)
void arch_cpu_idle(void)
{
struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
- unsigned long long idle_time;
+ unsigned long idle_time;
unsigned long psw_mask;
/* Wait for external, I/O or machine check interrupt. */
@@ -73,7 +73,7 @@ static ssize_t show_idle_count(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
- unsigned long long idle_count;
+ unsigned long idle_count;
unsigned int seq;
do {
@@ -82,14 +82,14 @@ static ssize_t show_idle_count(struct device *dev,
if (READ_ONCE(idle->clock_idle_enter))
idle_count++;
} while (read_seqcount_retry(&idle->seqcount, seq));
- return sprintf(buf, "%llu\n", idle_count);
+ return sprintf(buf, "%lu\n", idle_count);
}
DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
static ssize_t show_idle_time(struct device *dev,
struct device_attribute *attr, char *buf)
{
- unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
+ unsigned long now, idle_time, idle_enter, idle_exit, in_idle;
struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
unsigned int seq;
@@ -109,14 +109,14 @@ static ssize_t show_idle_time(struct device *dev,
}
}
idle_time += in_idle;
- return sprintf(buf, "%llu\n", idle_time >> 12);
+ return sprintf(buf, "%lu\n", idle_time >> 12);
}
DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
u64 arch_cpu_idle_time(int cpu)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
- unsigned long long now, idle_enter, idle_exit, in_idle;
+ unsigned long now, idle_enter, idle_exit, in_idle;
unsigned int seq;
do {
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 601c21791338..714269e10eec 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -174,7 +174,7 @@ void noinstr do_ext_irq(struct pt_regs *regs)
memcpy(&regs->int_code, &S390_lowcore.ext_cpu_addr, 4);
regs->int_parm = S390_lowcore.ext_params;
- regs->int_parm_long = *(unsigned long *)S390_lowcore.ext_params2;
+ regs->int_parm_long = S390_lowcore.ext_params2;
from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit;
if (from_idle)
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 0eb1d1cc53a8..b3beef64d3d4 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -269,7 +269,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
case CPUMF_CTR_SET_MAX:
/* The counter could not be associated to a counter set */
return -EINVAL;
- };
+ }
/* Initialize for using the CPU-measurement counter facility */
if (!atomic_inc_not_zero(&num_events)) {
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index db4877bbb9aa..2e3e7edbe3a0 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -26,12 +26,10 @@
#include <asm/timex.h>
#include <asm/debug.h>
-#include <asm/perf_cpum_cf_diag.h>
+#include <asm/hwctrset.h>
#define CF_DIAG_CTRSET_DEF 0xfeef /* Counter set header mark */
-#define CF_DIAG_MIN_INTERVAL 60 /* Minimum counter set read */
/* interval in seconds */
-static unsigned long cf_diag_interval = CF_DIAG_MIN_INTERVAL;
static unsigned int cf_diag_cpu_speed;
static debug_info_t *cf_diag_dbg;
@@ -729,7 +727,6 @@ static DEFINE_MUTEX(cf_diag_ctrset_mutex);
static struct cf_diag_ctrset {
unsigned long ctrset; /* Bit mask of counter set to read */
cpumask_t mask; /* CPU mask to read from */
- time64_t lastread; /* Epoch counter set last read */
} cf_diag_ctrset;
static void cf_diag_ctrset_clear(void)
@@ -866,27 +863,16 @@ static int cf_diag_all_read(unsigned long arg)
{
struct cf_diag_call_on_cpu_parm p;
cpumask_var_t mask;
- time64_t now;
- int rc = 0;
+ int rc;
debug_sprintf_event(cf_diag_dbg, 5, "%s\n", __func__);
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
- now = ktime_get_seconds();
- if (cf_diag_ctrset.lastread + cf_diag_interval > now) {
- debug_sprintf_event(cf_diag_dbg, 5, "%s now %lld "
- " lastread %lld\n", __func__, now,
- cf_diag_ctrset.lastread);
- rc = -EAGAIN;
- goto out;
- } else {
- cf_diag_ctrset.lastread = now;
- }
+
p.sets = cf_diag_ctrset.ctrset;
cpumask_and(mask, &cf_diag_ctrset.mask, cpu_online_mask);
on_each_cpu_mask(mask, cf_diag_cpu_read, &p, 1);
rc = cf_diag_all_copy(arg, mask);
-out:
free_cpumask_var(mask);
debug_sprintf_event(cf_diag_dbg, 5, "%s rc %d\n", __func__, rc);
return rc;
@@ -982,7 +968,7 @@ static int cf_diag_all_start(void)
*/
static size_t cf_diag_needspace(unsigned int sets)
{
- struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ struct cpu_cf_events *cpuhw = get_cpu_ptr(&cpu_cf_events);
size_t bytes = 0;
int i;
@@ -998,6 +984,7 @@ static size_t cf_diag_needspace(unsigned int sets)
sizeof(((struct s390_ctrset_cpudata *)0)->no_sets));
debug_sprintf_event(cf_diag_dbg, 5, "%s bytes %ld\n", __func__,
bytes);
+ put_cpu_ptr(&cpu_cf_events);
return bytes;
}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 60da976eee6f..72134f9f6ff5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -354,7 +354,7 @@ static int __init stack_realloc(void)
if (!new)
panic("Couldn't allocate machine check stack");
WRITE_ONCE(S390_lowcore.mcck_stack, new + STACK_INIT_OFFSET);
- memblock_free(old, THREAD_SIZE);
+ memblock_free_late(old, THREAD_SIZE);
return 0;
}
early_initcall(stack_realloc);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 06bcfa636638..326cb8f75f58 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -68,10 +68,10 @@ EXPORT_SYMBOL(s390_epoch_delta_notifier);
unsigned char ptff_function_mask[16];
-static unsigned long long lpar_offset;
-static unsigned long long initial_leap_seconds;
-static unsigned long long tod_steering_end;
-static long long tod_steering_delta;
+static unsigned long lpar_offset;
+static unsigned long initial_leap_seconds;
+static unsigned long tod_steering_end;
+static long tod_steering_delta;
/*
* Get time offsets with PTFF
@@ -80,10 +80,12 @@ void __init time_early_init(void)
{
struct ptff_qto qto;
struct ptff_qui qui;
+ int cs;
/* Initialize TOD steering parameters */
tod_steering_end = tod_clock_base.tod;
- vdso_data->arch_data.tod_steering_end = tod_steering_end;
+ for (cs = 0; cs < CS_BASES; cs++)
+ vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
if (!test_facility(28))
return;
@@ -96,7 +98,7 @@ void __init time_early_init(void)
/* get initial leap seconds */
if (ptff_query(PTFF_QUI) && ptff(&qui, sizeof(qui), PTFF_QUI) == 0)
- initial_leap_seconds = (unsigned long long)
+ initial_leap_seconds = (unsigned long)
((long) qui.old_leap * 4096000000L);
}
@@ -222,7 +224,7 @@ void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
static u64 read_tod_clock(struct clocksource *cs)
{
- unsigned long long now, adj;
+ unsigned long now, adj;
preempt_disable(); /* protect from changes to steering parameters */
now = get_tod_clock();
@@ -362,10 +364,11 @@ static inline int check_sync_clock(void)
* Apply clock delta to the global data structures.
* This is called once on the CPU that performed the clock sync.
*/
-static void clock_sync_global(unsigned long long delta)
+static void clock_sync_global(unsigned long delta)
{
unsigned long now, adj;
struct ptff_qto qto;
+ int cs;
/* Fixup the monotonic sched clock. */
tod_clock_base.eitod += delta;
@@ -378,10 +381,13 @@ static void clock_sync_global(unsigned long long delta)
-(adj >> 15) : (adj >> 15);
tod_steering_delta += delta;
if ((abs(tod_steering_delta) >> 48) != 0)
- panic("TOD clock sync offset %lli is too large to drift\n",
+ panic("TOD clock sync offset %li is too large to drift\n",
tod_steering_delta);
tod_steering_end = now + (abs(tod_steering_delta) << 15);
- vdso_data->arch_data.tod_steering_end = tod_steering_end;
+ for (cs = 0; cs < CS_BASES; cs++) {
+ vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
+ vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
+ }
/* Update LPAR offset. */
if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
@@ -394,7 +400,7 @@ static void clock_sync_global(unsigned long long delta)
* Apply clock delta to the per-CPU data structures of this CPU.
* This is called for each online CPU after the call to clock_sync_global.
*/
-static void clock_sync_local(unsigned long long delta)
+static void clock_sync_local(unsigned long delta)
{
/* Add the delta to the clock comparator. */
if (S390_lowcore.clock_comparator != clock_comparator_max) {
@@ -418,7 +424,7 @@ static void __init time_init_wq(void)
struct clock_sync_data {
atomic_t cpus;
int in_sync;
- unsigned long long clock_delta;
+ unsigned long clock_delta;
};
/*
@@ -538,7 +544,7 @@ static int stpinfo_valid(void)
static int stp_sync_clock(void *data)
{
struct clock_sync_data *sync = data;
- unsigned long long clock_delta, flags;
+ u64 clock_delta, flags;
static int first;
int rc;
@@ -720,8 +726,8 @@ static ssize_t ctn_id_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid())
- ret = sprintf(buf, "%016llx\n",
- *(unsigned long long *) stp_info.ctnid);
+ ret = sprintf(buf, "%016lx\n",
+ *(unsigned long *) stp_info.ctnid);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -794,7 +800,7 @@ static ssize_t leap_seconds_scheduled_show(struct device *dev,
if (!stzi.lsoib.p)
return sprintf(buf, "0,0\n");
- return sprintf(buf, "%llu,%d\n",
+ return sprintf(buf, "%lu,%d\n",
tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC,
stzi.lsoib.nlso - stzi.lsoib.also);
}
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index e7ce447651b9..bfcc327acc6b 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -76,8 +76,6 @@ static void cpu_group_map(cpumask_t *dst, struct mask_info *info, unsigned int c
}
info = info->next;
}
- if (cpumask_empty(&mask))
- cpumask_copy(&mask, cpumask_of(cpu));
break;
case TOPOLOGY_MODE_PACKAGE:
cpumask_copy(&mask, cpu_present_mask);
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 73c7afcc0527..f216a1b2f825 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -214,7 +214,7 @@ void vtime_flush(struct task_struct *tsk)
avg_steal = S390_lowcore.avg_steal_timer / 2;
if ((s64) steal > 0) {
S390_lowcore.steal_timer = 0;
- account_steal_time(steal);
+ account_steal_time(cputime_to_nsecs(steal));
avg_steal += steal;
}
S390_lowcore.avg_steal_timer = avg_steal;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index e3183bd05910..d548d60caed2 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1287,7 +1287,7 @@ static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
/* already expired? */
if (cputm >> 63)
return 0;
- return min(sltime, tod_to_ns(cputm));
+ return min_t(u64, sltime, tod_to_ns(cputm));
}
} else if (cpu_timer_interrupts_enabled(vcpu)) {
sltime = kvm_s390_get_cpu_timer(vcpu);
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 600881d894dd..91064077526d 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -682,16 +682,36 @@ int zpci_disable_device(struct zpci_dev *zdev)
}
EXPORT_SYMBOL_GPL(zpci_disable_device);
-void zpci_remove_device(struct zpci_dev *zdev)
+/* zpci_remove_device - Removes the given zdev from the PCI core
+ * @zdev: the zdev to be removed from the PCI core
+ * @set_error: if true the device's error state is set to permanent failure
+ *
+ * Sets a zPCI device to a configured but offline state; the zPCI
+ * device is still accessible through its hotplug slot and the zPCI
+ * API but is removed from the common code PCI bus, making it
+ * no longer available to drivers.
+ */
+void zpci_remove_device(struct zpci_dev *zdev, bool set_error)
{
struct zpci_bus *zbus = zdev->zbus;
struct pci_dev *pdev;
+ if (!zdev->zbus->bus)
+ return;
+
pdev = pci_get_slot(zbus->bus, zdev->devfn);
if (pdev) {
- if (pdev->is_virtfn)
- return zpci_iov_remove_virtfn(pdev, zdev->vfn);
+ if (set_error)
+ pdev->error_state = pci_channel_io_perm_failure;
+ if (pdev->is_virtfn) {
+ zpci_iov_remove_virtfn(pdev, zdev->vfn);
+ /* balance pci_get_slot */
+ pci_dev_put(pdev);
+ return;
+ }
pci_stop_and_remove_bus_device_locked(pdev);
+ /* balance pci_get_slot */
+ pci_dev_put(pdev);
}
}
@@ -765,7 +785,7 @@ void zpci_release_device(struct kref *kref)
struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
if (zdev->zbus->bus)
- zpci_remove_device(zdev);
+ zpci_remove_device(zdev, false);
switch (zdev->state) {
case ZPCI_FN_STATE_ONLINE:
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index b4162da4e8a2..ac0c65cdd69d 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -76,13 +76,10 @@ void zpci_event_error(void *data)
static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
{
struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
- struct pci_dev *pdev = NULL;
enum zpci_state state;
+ struct pci_dev *pdev;
int ret;
- if (zdev && zdev->zbus->bus)
- pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
-
zpci_err("avail CCDF:\n");
zpci_err_hex(ccdf, sizeof(*ccdf));
@@ -124,8 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
case 0x0303: /* Deconfiguration requested */
if (!zdev)
break;
- if (pdev)
- zpci_remove_device(zdev);
+ zpci_remove_device(zdev, false);
ret = zpci_disable_device(zdev);
if (ret)
@@ -140,12 +136,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
case 0x0304: /* Configured -> Standby|Reserved */
if (!zdev)
break;
- if (pdev) {
- /* Give the driver a hint that the function is
- * already unusable. */
- pdev->error_state = pci_channel_io_perm_failure;
- zpci_remove_device(zdev);
- }
+ /* Give the driver a hint that the function is
+ * already unusable.
+ */
+ zpci_remove_device(zdev, true);
zdev->fh = ccdf->fh;
zpci_disable_device(zdev);
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index 148f44b33890..12a4fb0bd52a 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -93,7 +93,7 @@ CONFIG_NETDEVICES=y
CONFIG_NET_ETHERNET=y
CONFIG_MII=m
CONFIG_SUNLANCE=m
-CONFIG_HAPPYMEAL=m
+CONFIG_HAPPYMEAL=y
CONFIG_SUNGEM=m
CONFIG_SUNVNET=m
CONFIG_LDMVSW=m
@@ -234,9 +234,7 @@ CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRC16=m
CONFIG_LIBCRC32C=m
CONFIG_VCC=m
-CONFIG_ATA=y
CONFIG_PATA_CMD64X=y
-CONFIG_HAPPYMEAL=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_DEVTMPFS=y
diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h
index 7e078bc73ef5..8fb09eec8c3e 100644
--- a/arch/sparc/include/asm/elf_64.h
+++ b/arch/sparc/include/asm/elf_64.h
@@ -8,7 +8,6 @@
#include <asm/ptrace.h>
#include <asm/processor.h>
-#include <asm/extable_64.h>
#include <asm/spitfire.h>
#include <asm/adi.h>
diff --git a/arch/sparc/include/asm/extable_64.h b/arch/sparc/include/asm/extable.h
index 5a0171907b7e..554a9dc376fc 100644
--- a/arch/sparc/include/asm/extable_64.h
+++ b/arch/sparc/include/asm/extable.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_EXTABLE64_H
-#define __ASM_EXTABLE64_H
+#ifndef __ASM_EXTABLE_H
+#define __ASM_EXTABLE_H
/*
* The exception table consists of pairs of addresses: the first is the
* address of an instruction that is allowed to fault, and the second is
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index 3c4bc2189092..b6242f7771e9 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -50,16 +50,12 @@ struct thread_struct {
unsigned long fsr;
unsigned long fpqdepth;
struct fpq fpqueue[16];
- unsigned long flags;
mm_segment_t current_ds;
};
-#define SPARC_FLAG_KTHREAD 0x1 /* task is a kernel thread */
-#define SPARC_FLAG_UNALIGNED 0x2 /* is allowed to do unaligned accesses */
-
#define INIT_THREAD { \
- .flags = SPARC_FLAG_KTHREAD, \
.current_ds = KERNEL_DS, \
+ .kregs = (struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
}
/* Do necessary setup to start up a newly executed thread. */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 42cd4cd3892e..8047a9caab2f 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -118,6 +118,7 @@ struct thread_info {
.task = &tsk, \
.current_ds = ASI_P, \
.preempt_count = INIT_PREEMPT_COUNT, \
+ .kregs = (struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
}
/* how to get the thread information struct from C */
diff --git a/arch/sparc/include/asm/uaccess.h b/arch/sparc/include/asm/uaccess.h
index dd85bc2c2cad..390094200fc4 100644
--- a/arch/sparc/include/asm/uaccess.h
+++ b/arch/sparc/include/asm/uaccess.h
@@ -1,6 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ___ASM_SPARC_UACCESS_H
#define ___ASM_SPARC_UACCESS_H
+
+#include <asm/extable.h>
+
#if defined(__sparc__) && defined(__arch64__)
#include <asm/uaccess_64.h>
#else
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 0a2d3ebc4bb8..4a12346bb69c 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -13,9 +13,6 @@
#include <asm/processor.h>
-#define ARCH_HAS_SORT_EXTABLE
-#define ARCH_HAS_SEARCH_EXTABLE
-
/* Sparc is not segmented, however we need to be able to fool access_ok()
* when doing system calls from kernel mode legitimately.
*
@@ -40,36 +37,6 @@
#define __access_ok(addr, size) (__user_ok((addr) & get_fs().seg, (size)))
#define access_ok(addr, size) __access_ok((unsigned long)(addr), size)
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- *
- * There is a special way how to put a range of potentially faulting
- * insns (like twenty ldd/std's with now intervening other instructions)
- * You specify address of first in insn and 0 in fixup and in the next
- * exception_table_entry you specify last potentially faulting insn + 1
- * and in fixup the routine which should handle the fault.
- * That fixup code will get
- * (faulting_insn_address - first_insn_in_the_range_address)/4
- * in %g2 (ie. index of the faulting instruction in the range).
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise. */
-unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
-
/* Uh, these should become the main single-value transfer routines..
* They automatically use the right size if we just have the right
* pointer type..
@@ -252,12 +219,7 @@ static inline unsigned long __clear_user(void __user *addr, unsigned long size)
unsigned long ret;
__asm__ __volatile__ (
- ".section __ex_table,#alloc\n\t"
- ".align 4\n\t"
- ".word 1f,3\n\t"
- ".previous\n\t"
"mov %2, %%o1\n"
- "1:\n\t"
"call __bzero\n\t"
" mov %1, %%o0\n\t"
"mov %%o0, %0\n"
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index 698cf69f74e9..30eb4c6414d1 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -10,7 +10,6 @@
#include <linux/string.h>
#include <asm/asi.h>
#include <asm/spitfire.h>
-#include <asm/extable_64.h>
#include <asm/processor.h>
diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S
index be30c8d4cc73..6044b82b9767 100644
--- a/arch/sparc/kernel/head_32.S
+++ b/arch/sparc/kernel/head_32.S
@@ -515,7 +515,7 @@ continue_boot:
/* I want a kernel stack NOW! */
set init_thread_union, %g1
- set (THREAD_SIZE - STACKFRAME_SZ), %g2
+ set (THREAD_SIZE - STACKFRAME_SZ - TRACEREG_SZ), %g2
add %g1, %g2, %sp
mov 0, %fp /* And for good luck */
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index c5ff2472b3d9..72a5bdc833ea 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -706,7 +706,7 @@ tlb_fixup_done:
wr %g0, ASI_P, %asi
mov 1, %g1
sllx %g1, THREAD_SHIFT, %g1
- sub %g1, (STACKFRAME_SZ + STACK_BIAS), %g1
+ sub %g1, (STACKFRAME_SZ + STACK_BIAS + TRACEREG_SZ), %g1
add %g6, %g1, %sp
/* Set per-cpu pointer initially to zero, this makes
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index b91e88058e0c..3b9794978e5b 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -216,16 +216,6 @@ void flush_thread(void)
clear_thread_flag(TIF_USEDFPU);
#endif
}
-
- /* This task is no longer a kernel thread. */
- if (current->thread.flags & SPARC_FLAG_KTHREAD) {
- current->thread.flags &= ~SPARC_FLAG_KTHREAD;
-
- /* We must fixup kregs as well. */
- /* XXX This was not fixed for ti for a while, worked. Unused? */
- current->thread.kregs = (struct pt_regs *)
- (task_stack_page(current) + (THREAD_SIZE - TRACEREG_SZ));
- }
}
static inline struct sparc_stackf __user *
@@ -313,7 +303,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
extern int nwindows;
unsigned long psr;
memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ);
- p->thread.flags |= SPARC_FLAG_KTHREAD;
p->thread.current_ds = KERNEL_DS;
ti->kpc = (((unsigned long) ret_from_kernel_thread) - 0x8);
childregs->u_regs[UREG_G1] = sp; /* function */
@@ -325,7 +314,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
}
memcpy(new_stack, (char *)regs - STACKFRAME_SZ, STACKFRAME_SZ + TRACEREG_SZ);
childregs->u_regs[UREG_FP] = sp;
- p->thread.flags &= ~SPARC_FLAG_KTHREAD;
p->thread.current_ds = USER_DS;
ti->kpc = (((unsigned long) ret_from_fork) - 0x8);
ti->kpsr = current->thread.fork_kpsr | PSR_PIL;
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index eea43a1aef1b..c8e0dd99f370 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -266,7 +266,6 @@ static __init void leon_patch(void)
}
struct tt_entry *sparc_ttable;
-static struct pt_regs fake_swapper_regs;
/* Called from head_32.S - before we have setup anything
* in the kernel. Be very careful with what you do here.
@@ -363,8 +362,6 @@ void __init setup_arch(char **cmdline_p)
(*(linux_dbvec->teach_debugger))();
}
- init_task.thread.kregs = &fake_swapper_regs;
-
/* Run-time patch instructions to match the cpu model */
per_cpu_patch();
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index d87244197d5c..48abee4eee29 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -165,8 +165,6 @@ extern int root_mountflags;
char reboot_command[COMMAND_LINE_SIZE];
-static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 };
-
static void __init per_cpu_patch(void)
{
struct cpuid_patch_entry *p;
@@ -661,8 +659,6 @@ void __init setup_arch(char **cmdline_p)
rd_image_start = ram_flags & RAMDISK_IMAGE_START_MASK;
#endif
- task_thread_info(&init_task)->kregs = &fake_swapper_regs;
-
#ifdef CONFIG_IP_PNP
if (!ic_set_manually) {
phandle chosen = prom_finddevice("/chosen");
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index d92e5eaa4c1d..a850dccd78ea 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -275,14 +275,13 @@ bool is_no_fault_exception(struct pt_regs *regs)
asi = (regs->tstate >> 24); /* saved %asi */
else
asi = (insn >> 5); /* immediate asi */
- if ((asi & 0xf2) == ASI_PNF) {
- if (insn & 0x1000000) { /* op3[5:4]=3 */
- handle_ldf_stq(insn, regs);
- return true;
- } else if (insn & 0x200000) { /* op3[2], stores */
+ if ((asi & 0xf6) == ASI_PNF) {
+ if (insn & 0x200000) /* op3[2], stores */
return false;
- }
- handle_ld_nf(insn, regs);
+ if (insn & 0x1000000) /* op3[5:4]=3 (fp) */
+ handle_ldf_stq(insn, regs);
+ else
+ handle_ld_nf(insn, regs);
return true;
}
}
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index 83db94c0b431..ef5c5207c9ff 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -16,6 +16,7 @@
#include <linux/uaccess.h>
#include <linux/smp.h>
#include <linux/perf_event.h>
+#include <linux/extable.h>
#include <asm/setup.h>
@@ -213,10 +214,10 @@ static inline int ok_for_kernel(unsigned int insn)
static void kernel_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
{
- unsigned long g2 = regs->u_regs [UREG_G2];
- unsigned long fixup = search_extables_range(regs->pc, &g2);
+ const struct exception_table_entry *entry;
- if (!fixup) {
+ entry = search_exception_tables(regs->pc);
+ if (!entry) {
unsigned long address = compute_effective_address(regs, insn);
if(address < PAGE_SIZE) {
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference in mna handler");
@@ -232,9 +233,8 @@ static void kernel_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
die_if_kernel("Oops", regs);
/* Not reached */
}
- regs->pc = fixup;
+ regs->pc = entry->fixup;
regs->npc = regs->pc + 4;
- regs->u_regs [UREG_G2] = g2;
}
asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
@@ -274,103 +274,9 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
}
}
-static inline int ok_for_user(struct pt_regs *regs, unsigned int insn,
- enum direction dir)
-{
- unsigned int reg;
- int size = ((insn >> 19) & 3) == 3 ? 8 : 4;
-
- if ((regs->pc | regs->npc) & 3)
- return 0;
-
- /* Must access_ok() in all the necessary places. */
-#define WINREG_ADDR(regnum) \
- ((void __user *)(((unsigned long *)regs->u_regs[UREG_FP])+(regnum)))
-
- reg = (insn >> 25) & 0x1f;
- if (reg >= 16) {
- if (!access_ok(WINREG_ADDR(reg - 16), size))
- return -EFAULT;
- }
- reg = (insn >> 14) & 0x1f;
- if (reg >= 16) {
- if (!access_ok(WINREG_ADDR(reg - 16), size))
- return -EFAULT;
- }
- if (!(insn & 0x2000)) {
- reg = (insn & 0x1f);
- if (reg >= 16) {
- if (!access_ok(WINREG_ADDR(reg - 16), size))
- return -EFAULT;
- }
- }
-#undef WINREG_ADDR
- return 0;
-}
-
-static void user_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
+asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
{
send_sig_fault(SIGBUS, BUS_ADRALN,
(void __user *)safe_compute_effective_address(regs, insn),
0, current);
}
-
-asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
-{
- enum direction dir;
-
- if(!(current->thread.flags & SPARC_FLAG_UNALIGNED) ||
- (((insn >> 30) & 3) != 3))
- goto kill_user;
- dir = decode_direction(insn);
- if(!ok_for_user(regs, insn, dir)) {
- goto kill_user;
- } else {
- int err, size = decode_access_size(insn);
- unsigned long addr;
-
- if(floating_point_load_or_store_p(insn)) {
- printk("User FPU load/store unaligned unsupported.\n");
- goto kill_user;
- }
-
- addr = compute_effective_address(regs, insn);
- perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
- switch(dir) {
- case load:
- err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
- regs),
- size, (unsigned long *) addr,
- decode_signedness(insn));
- break;
-
- case store:
- err = do_int_store(((insn>>25)&0x1f), size,
- (unsigned long *) addr, regs);
- break;
-
- case both:
- /*
- * This was supported in 2.4. However, we question
- * the value of SWAP instruction across word boundaries.
- */
- printk("Unaligned SWAP unsupported.\n");
- err = -EFAULT;
- break;
-
- default:
- unaligned_panic("Impossible user unaligned trap.");
- goto out;
- }
- if (err)
- goto kill_user;
- else
- advance(regs);
- goto out;
- }
-
-kill_user:
- user_mna_trap_fault(regs, insn);
-out:
- ;
-}
diff --git a/arch/sparc/lib/checksum_32.S b/arch/sparc/lib/checksum_32.S
index 7488d130faf7..781e39b3c009 100644
--- a/arch/sparc/lib/checksum_32.S
+++ b/arch/sparc/lib/checksum_32.S
@@ -155,13 +155,6 @@ cpout: retl ! get outta here
.text; \
.align 4
-#define EXT(start,end) \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word start, 0, end, cc_fault; \
- .text; \
- .align 4
-
/* This aligned version executes typically in 8.5 superscalar cycles, this
* is the best I can do. I say 8.5 because the final add will pair with
* the next ldd in the main unrolled loop. Thus the pipe is always full.
@@ -169,20 +162,20 @@ cpout: retl ! get outta here
* please check the fixup code below as well.
*/
#define CSUMCOPY_BIGCHUNK_ALIGNED(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [src + off + 0x00], t0; \
- ldd [src + off + 0x08], t2; \
+ EX(ldd [src + off + 0x00], t0); \
+ EX(ldd [src + off + 0x08], t2); \
addxcc t0, sum, sum; \
- ldd [src + off + 0x10], t4; \
+ EX(ldd [src + off + 0x10], t4); \
addxcc t1, sum, sum; \
- ldd [src + off + 0x18], t6; \
+ EX(ldd [src + off + 0x18], t6); \
addxcc t2, sum, sum; \
- std t0, [dst + off + 0x00]; \
+ EX(std t0, [dst + off + 0x00]); \
addxcc t3, sum, sum; \
- std t2, [dst + off + 0x08]; \
+ EX(std t2, [dst + off + 0x08]); \
addxcc t4, sum, sum; \
- std t4, [dst + off + 0x10]; \
+ EX(std t4, [dst + off + 0x10]); \
addxcc t5, sum, sum; \
- std t6, [dst + off + 0x18]; \
+ EX(std t6, [dst + off + 0x18]); \
addxcc t6, sum, sum; \
addxcc t7, sum, sum;
@@ -191,39 +184,39 @@ cpout: retl ! get outta here
* Viking MXCC into streaming mode. Ho hum...
*/
#define CSUMCOPY_BIGCHUNK(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [src + off + 0x00], t0; \
- ldd [src + off + 0x08], t2; \
- ldd [src + off + 0x10], t4; \
- ldd [src + off + 0x18], t6; \
- st t0, [dst + off + 0x00]; \
+ EX(ldd [src + off + 0x00], t0); \
+ EX(ldd [src + off + 0x08], t2); \
+ EX(ldd [src + off + 0x10], t4); \
+ EX(ldd [src + off + 0x18], t6); \
+ EX(st t0, [dst + off + 0x00]); \
addxcc t0, sum, sum; \
- st t1, [dst + off + 0x04]; \
+ EX(st t1, [dst + off + 0x04]); \
addxcc t1, sum, sum; \
- st t2, [dst + off + 0x08]; \
+ EX(st t2, [dst + off + 0x08]); \
addxcc t2, sum, sum; \
- st t3, [dst + off + 0x0c]; \
+ EX(st t3, [dst + off + 0x0c]); \
addxcc t3, sum, sum; \
- st t4, [dst + off + 0x10]; \
+ EX(st t4, [dst + off + 0x10]); \
addxcc t4, sum, sum; \
- st t5, [dst + off + 0x14]; \
+ EX(st t5, [dst + off + 0x14]); \
addxcc t5, sum, sum; \
- st t6, [dst + off + 0x18]; \
+ EX(st t6, [dst + off + 0x18]); \
addxcc t6, sum, sum; \
- st t7, [dst + off + 0x1c]; \
+ EX(st t7, [dst + off + 0x1c]); \
addxcc t7, sum, sum;
/* Yuck, 6 superscalar cycles... */
#define CSUMCOPY_LASTCHUNK(src, dst, sum, off, t0, t1, t2, t3) \
- ldd [src - off - 0x08], t0; \
- ldd [src - off - 0x00], t2; \
+ EX(ldd [src - off - 0x08], t0); \
+ EX(ldd [src - off - 0x00], t2); \
addxcc t0, sum, sum; \
- st t0, [dst - off - 0x08]; \
+ EX(st t0, [dst - off - 0x08]); \
addxcc t1, sum, sum; \
- st t1, [dst - off - 0x04]; \
+ EX(st t1, [dst - off - 0x04]); \
addxcc t2, sum, sum; \
- st t2, [dst - off - 0x00]; \
+ EX(st t2, [dst - off - 0x00]); \
addxcc t3, sum, sum; \
- st t3, [dst - off + 0x04];
+ EX(st t3, [dst - off + 0x04]);
/* Handle the end cruft code out of band for better cache patterns. */
cc_end_cruft:
@@ -331,7 +324,6 @@ __csum_partial_copy_sparc_generic:
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-10: EXT(5b, 10b) ! note for exception handling
sub %g1, 128, %g1 ! detract from length
addx %g0, %g7, %g7 ! add in last carry bit
andcc %g1, 0xffffff80, %g0 ! more to csum?
@@ -356,8 +348,7 @@ cctbl: CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x68,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x28,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x18,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x08,%g2,%g3,%g4,%g5)
-12: EXT(cctbl, 12b) ! note for exception table handling
- addx %g0, %g7, %g7
+12: addx %g0, %g7, %g7
andcc %o3, 0xf, %g0 ! check for low bits set
ccte: bne cc_end_cruft ! something left, handle it out of band
andcc %o3, 8, %g0 ! begin checks for that code
@@ -367,7 +358,6 @@ ccdbl: CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x00,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-11: EXT(ccdbl, 11b) ! note for exception table handling
sub %g1, 128, %g1 ! detract from length
addx %g0, %g7, %g7 ! add in last carry bit
andcc %g1, 0xffffff80, %g0 ! more to csum?
diff --git a/arch/sparc/lib/copy_user.S b/arch/sparc/lib/copy_user.S
index dc72f2b970b7..954572c78539 100644
--- a/arch/sparc/lib/copy_user.S
+++ b/arch/sparc/lib/copy_user.S
@@ -21,98 +21,134 @@
/* Work around cpp -rob */
#define ALLOC #alloc
#define EXECINSTR #execinstr
+
+#define EX_ENTRY(l1, l2) \
+ .section __ex_table,ALLOC; \
+ .align 4; \
+ .word l1, l2; \
+ .text;
+
#define EX(x,y,a,b) \
98: x,y; \
.section .fixup,ALLOC,EXECINSTR; \
.align 4; \
-99: ba fixupretl; \
- a, b, %g3; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 99b; \
- .text; \
- .align 4
+99: retl; \
+ a, b, %o0; \
+ EX_ENTRY(98b, 99b)
#define EX2(x,y,c,d,e,a,b) \
98: x,y; \
.section .fixup,ALLOC,EXECINSTR; \
.align 4; \
99: c, d, e; \
- ba fixupretl; \
- a, b, %g3; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 99b; \
- .text; \
- .align 4
+ retl; \
+ a, b, %o0; \
+ EX_ENTRY(98b, 99b)
#define EXO2(x,y) \
98: x, y; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 97f; \
- .text; \
- .align 4
+ EX_ENTRY(98b, 97f)
-#define EXT(start,end,handler) \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word start, 0, end, handler; \
- .text; \
- .align 4
+#define LD(insn, src, offset, reg, label) \
+98: insn [%src + (offset)], %reg; \
+ .section .fixup,ALLOC,EXECINSTR; \
+99: ba label; \
+ mov offset, %g5; \
+ EX_ENTRY(98b, 99b)
-/* Please do not change following macros unless you change logic used
- * in .fixup at the end of this file as well
- */
+#define ST(insn, dst, offset, reg, label) \
+98: insn %reg, [%dst + (offset)]; \
+ .section .fixup,ALLOC,EXECINSTR; \
+99: ba label; \
+ mov offset, %g5; \
+ EX_ENTRY(98b, 99b)
/* Both these macros have to start with exactly the same insn */
+/* left: g7 + (g1 % 128) - offset */
#define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [%src + (offset) + 0x00], %t0; \
- ldd [%src + (offset) + 0x08], %t2; \
- ldd [%src + (offset) + 0x10], %t4; \
- ldd [%src + (offset) + 0x18], %t6; \
- st %t0, [%dst + (offset) + 0x00]; \
- st %t1, [%dst + (offset) + 0x04]; \
- st %t2, [%dst + (offset) + 0x08]; \
- st %t3, [%dst + (offset) + 0x0c]; \
- st %t4, [%dst + (offset) + 0x10]; \
- st %t5, [%dst + (offset) + 0x14]; \
- st %t6, [%dst + (offset) + 0x18]; \
- st %t7, [%dst + (offset) + 0x1c];
-
+ LD(ldd, src, offset + 0x00, t0, bigchunk_fault) \
+ LD(ldd, src, offset + 0x08, t2, bigchunk_fault) \
+ LD(ldd, src, offset + 0x10, t4, bigchunk_fault) \
+ LD(ldd, src, offset + 0x18, t6, bigchunk_fault) \
+ ST(st, dst, offset + 0x00, t0, bigchunk_fault) \
+ ST(st, dst, offset + 0x04, t1, bigchunk_fault) \
+ ST(st, dst, offset + 0x08, t2, bigchunk_fault) \
+ ST(st, dst, offset + 0x0c, t3, bigchunk_fault) \
+ ST(st, dst, offset + 0x10, t4, bigchunk_fault) \
+ ST(st, dst, offset + 0x14, t5, bigchunk_fault) \
+ ST(st, dst, offset + 0x18, t6, bigchunk_fault) \
+ ST(st, dst, offset + 0x1c, t7, bigchunk_fault)
+
+/* left: g7 + (g1 % 128) - offset */
#define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [%src + (offset) + 0x00], %t0; \
- ldd [%src + (offset) + 0x08], %t2; \
- ldd [%src + (offset) + 0x10], %t4; \
- ldd [%src + (offset) + 0x18], %t6; \
- std %t0, [%dst + (offset) + 0x00]; \
- std %t2, [%dst + (offset) + 0x08]; \
- std %t4, [%dst + (offset) + 0x10]; \
- std %t6, [%dst + (offset) + 0x18];
+ LD(ldd, src, offset + 0x00, t0, bigchunk_fault) \
+ LD(ldd, src, offset + 0x08, t2, bigchunk_fault) \
+ LD(ldd, src, offset + 0x10, t4, bigchunk_fault) \
+ LD(ldd, src, offset + 0x18, t6, bigchunk_fault) \
+ ST(std, dst, offset + 0x00, t0, bigchunk_fault) \
+ ST(std, dst, offset + 0x08, t2, bigchunk_fault) \
+ ST(std, dst, offset + 0x10, t4, bigchunk_fault) \
+ ST(std, dst, offset + 0x18, t6, bigchunk_fault)
+ .section .fixup,#alloc,#execinstr
+bigchunk_fault:
+ sub %g7, %g5, %o0
+ and %g1, 127, %g1
+ retl
+ add %o0, %g1, %o0
+
+/* left: offset + 16 + (g1 % 16) */
#define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
- ldd [%src - (offset) - 0x10], %t0; \
- ldd [%src - (offset) - 0x08], %t2; \
- st %t0, [%dst - (offset) - 0x10]; \
- st %t1, [%dst - (offset) - 0x0c]; \
- st %t2, [%dst - (offset) - 0x08]; \
- st %t3, [%dst - (offset) - 0x04];
+ LD(ldd, src, -(offset + 0x10), t0, lastchunk_fault) \
+ LD(ldd, src, -(offset + 0x08), t2, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x10), t0, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x0c), t1, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x08), t2, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x04), t3, lastchunk_fault)
-#define MOVE_HALFCHUNK(src, dst, offset, t0, t1, t2, t3) \
- lduh [%src + (offset) + 0x00], %t0; \
- lduh [%src + (offset) + 0x02], %t1; \
- lduh [%src + (offset) + 0x04], %t2; \
- lduh [%src + (offset) + 0x06], %t3; \
- sth %t0, [%dst + (offset) + 0x00]; \
- sth %t1, [%dst + (offset) + 0x02]; \
- sth %t2, [%dst + (offset) + 0x04]; \
- sth %t3, [%dst + (offset) + 0x06];
+ .section .fixup,#alloc,#execinstr
+lastchunk_fault:
+ and %g1, 15, %g1
+ retl
+ sub %g1, %g5, %o0
+/* left: o3 + (o2 % 16) - offset */
+#define MOVE_HALFCHUNK(src, dst, offset, t0, t1, t2, t3) \
+ LD(lduh, src, offset + 0x00, t0, halfchunk_fault) \
+ LD(lduh, src, offset + 0x02, t1, halfchunk_fault) \
+ LD(lduh, src, offset + 0x04, t2, halfchunk_fault) \
+ LD(lduh, src, offset + 0x06, t3, halfchunk_fault) \
+ ST(sth, dst, offset + 0x00, t0, halfchunk_fault) \
+ ST(sth, dst, offset + 0x02, t1, halfchunk_fault) \
+ ST(sth, dst, offset + 0x04, t2, halfchunk_fault) \
+ ST(sth, dst, offset + 0x06, t3, halfchunk_fault)
+
+/* left: o3 + (o2 % 16) + offset + 2 */
#define MOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
- ldub [%src - (offset) - 0x02], %t0; \
- ldub [%src - (offset) - 0x01], %t1; \
- stb %t0, [%dst - (offset) - 0x02]; \
- stb %t1, [%dst - (offset) - 0x01];
+ LD(ldub, src, -(offset + 0x02), t0, halfchunk_fault) \
+ LD(ldub, src, -(offset + 0x01), t1, halfchunk_fault) \
+ ST(stb, dst, -(offset + 0x02), t0, halfchunk_fault) \
+ ST(stb, dst, -(offset + 0x01), t1, halfchunk_fault)
+
+ .section .fixup,#alloc,#execinstr
+halfchunk_fault:
+ and %o2, 15, %o2
+ sub %o3, %g5, %o3
+ retl
+ add %o2, %o3, %o0
+
+/* left: offset + 2 + (o2 % 2) */
+#define MOVE_LAST_SHORTCHUNK(src, dst, offset, t0, t1) \
+ LD(ldub, src, -(offset + 0x02), t0, last_shortchunk_fault) \
+ LD(ldub, src, -(offset + 0x01), t1, last_shortchunk_fault) \
+ ST(stb, dst, -(offset + 0x02), t0, last_shortchunk_fault) \
+ ST(stb, dst, -(offset + 0x01), t1, last_shortchunk_fault)
+
+ .section .fixup,#alloc,#execinstr
+last_shortchunk_fault:
+ and %o2, 1, %o2
+ retl
+ sub %o2, %g5, %o0
.text
.align 4
@@ -182,8 +218,6 @@ __copy_user: /* %o0=dst %o1=src %o2=len */
MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-80:
- EXT(5b, 80b, 50f)
subcc %g7, 128, %g7
add %o1, 128, %o1
bne 5b
@@ -201,7 +235,6 @@ __copy_user: /* %o0=dst %o1=src %o2=len */
jmpl %o5 + %lo(copy_user_table_end), %g0
add %o0, %g7, %o0
-copy_user_table:
MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
@@ -210,7 +243,6 @@ copy_user_table:
MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
copy_user_table_end:
- EXT(copy_user_table, copy_user_table_end, 51f)
be copy_user_last7
andcc %g1, 4, %g0
@@ -250,8 +282,6 @@ ldd_std:
MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-81:
- EXT(ldd_std, 81b, 52f)
subcc %g7, 128, %g7
add %o1, 128, %o1
bne ldd_std
@@ -290,8 +320,6 @@ cannot_optimize:
10:
MOVE_HALFCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
MOVE_HALFCHUNK(o1, o0, 0x08, g2, g3, g4, g5)
-82:
- EXT(10b, 82b, 53f)
subcc %o3, 0x10, %o3
add %o1, 0x10, %o1
bne 10b
@@ -308,8 +336,6 @@ byte_chunk:
MOVE_SHORTCHUNK(o1, o0, -0x0c, g2, g3)
MOVE_SHORTCHUNK(o1, o0, -0x0e, g2, g3)
MOVE_SHORTCHUNK(o1, o0, -0x10, g2, g3)
-83:
- EXT(byte_chunk, 83b, 54f)
subcc %o3, 0x10, %o3
add %o1, 0x10, %o1
bne byte_chunk
@@ -325,16 +351,14 @@ short_end:
add %o1, %o3, %o1
jmpl %o5 + %lo(short_table_end), %g0
andcc %o2, 1, %g0
-84:
- MOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x08, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x06, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x04, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x02, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x00, g2, g3)
short_table_end:
- EXT(84b, short_table_end, 55f)
be 1f
nop
EX(ldub [%o1], %g2, add %g0, 1)
@@ -363,123 +387,8 @@ short_aligned_end:
.section .fixup,#alloc,#execinstr
.align 4
97:
- mov %o2, %g3
-fixupretl:
retl
- mov %g3, %o0
-
-/* exception routine sets %g2 to (broken_insn - first_insn)>>2 */
-50:
-/* This magic counts how many bytes are left when crash in MOVE_BIGCHUNK
- * happens. This is derived from the amount ldd reads, st stores, etc.
- * x = g2 % 12;
- * g3 = g1 + g7 - ((g2 / 12) * 32 + (x < 4) ? 0 : (x - 4) * 4);
- * o0 += (g2 / 12) * 32;
- */
- cmp %g2, 12
- add %o0, %g7, %o0
- bcs 1f
- cmp %g2, 24
- bcs 2f
- cmp %g2, 36
- bcs 3f
- nop
- sub %g2, 12, %g2
- sub %g7, 32, %g7
-3: sub %g2, 12, %g2
- sub %g7, 32, %g7
-2: sub %g2, 12, %g2
- sub %g7, 32, %g7
-1: cmp %g2, 4
- bcs,a 60f
- clr %g2
- sub %g2, 4, %g2
- sll %g2, 2, %g2
-60: and %g1, 0x7f, %g3
- sub %o0, %g7, %o0
- add %g3, %g7, %g3
- ba fixupretl
- sub %g3, %g2, %g3
-51:
-/* i = 41 - g2; j = i % 6;
- * g3 = (g1 & 15) + (i / 6) * 16 + (j < 4) ? (j + 1) * 4 : 16;
- * o0 -= (i / 6) * 16 + 16;
- */
- neg %g2
- and %g1, 0xf, %g1
- add %g2, 41, %g2
- add %o0, %g1, %o0
-1: cmp %g2, 6
- bcs,a 2f
- cmp %g2, 4
- add %g1, 16, %g1
- b 1b
- sub %g2, 6, %g2
-2: bcc,a 2f
- mov 16, %g2
- inc %g2
- sll %g2, 2, %g2
-2: add %g1, %g2, %g3
- ba fixupretl
- sub %o0, %g3, %o0
-52:
-/* g3 = g1 + g7 - (g2 / 8) * 32 + (g2 & 4) ? (g2 & 3) * 8 : 0;
- o0 += (g2 / 8) * 32 */
- andn %g2, 7, %g4
- add %o0, %g7, %o0
- andcc %g2, 4, %g0
- and %g2, 3, %g2
- sll %g4, 2, %g4
- sll %g2, 3, %g2
- bne 60b
- sub %g7, %g4, %g7
- ba 60b
- clr %g2
-53:
-/* g3 = o3 + (o2 & 15) - (g2 & 8) - (g2 & 4) ? (g2 & 3) * 2 : 0;
- o0 += (g2 & 8) */
- and %g2, 3, %g4
- andcc %g2, 4, %g0
- and %g2, 8, %g2
- sll %g4, 1, %g4
- be 1f
- add %o0, %g2, %o0
- add %g2, %g4, %g2
-1: and %o2, 0xf, %g3
- add %g3, %o3, %g3
- ba fixupretl
- sub %g3, %g2, %g3
-54:
-/* g3 = o3 + (o2 & 15) - (g2 / 4) * 2 - (g2 & 2) ? (g2 & 1) : 0;
- o0 += (g2 / 4) * 2 */
- srl %g2, 2, %o4
- and %g2, 1, %o5
- srl %g2, 1, %g2
- add %o4, %o4, %o4
- and %o5, %g2, %o5
- and %o2, 0xf, %o2
- add %o0, %o4, %o0
- sub %o3, %o5, %o3
- sub %o2, %o4, %o2
- ba fixupretl
- add %o2, %o3, %g3
-55:
-/* i = 27 - g2;
- g3 = (o2 & 1) + i / 4 * 2 + !(i & 3);
- o0 -= i / 4 * 2 + 1 */
- neg %g2
- and %o2, 1, %o2
- add %g2, 27, %g2
- srl %g2, 2, %o5
- andcc %g2, 3, %g0
- mov 1, %g2
- add %o5, %o5, %o5
- be,a 1f
- clr %g2
-1: add %g2, %o5, %g3
- sub %o0, %g3, %o0
- ba fixupretl
- add %g3, %o2, %g3
+ mov %o2, %o0
.globl __copy_user_end
__copy_user_end:
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index f427f34b8b79..eaff68213fdf 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -19,7 +19,7 @@
98: x,y; \
.section .fixup,ALLOC,EXECINSTR; \
.align 4; \
-99: ba 30f; \
+99: retl; \
a, b, %o0; \
.section __ex_table,ALLOC; \
.align 4; \
@@ -27,35 +27,44 @@
.text; \
.align 4
-#define EXT(start,end,handler) \
+#define STORE(source, base, offset, n) \
+98: std source, [base + offset + n]; \
+ .section .fixup,ALLOC,EXECINSTR; \
+ .align 4; \
+99: ba 30f; \
+ sub %o3, n - offset, %o3; \
.section __ex_table,ALLOC; \
.align 4; \
- .word start, 0, end, handler; \
+ .word 98b, 99b; \
.text; \
- .align 4
+ .align 4;
+
+#define STORE_LAST(source, base, offset, n) \
+ EX(std source, [base - offset - n], \
+ add %o1, offset + n);
/* Please don't change these macros, unless you change the logic
* in the .fixup section below as well.
* Store 64 bytes at (BASE + OFFSET) using value SOURCE. */
-#define ZERO_BIG_BLOCK(base, offset, source) \
- std source, [base + offset + 0x00]; \
- std source, [base + offset + 0x08]; \
- std source, [base + offset + 0x10]; \
- std source, [base + offset + 0x18]; \
- std source, [base + offset + 0x20]; \
- std source, [base + offset + 0x28]; \
- std source, [base + offset + 0x30]; \
- std source, [base + offset + 0x38];
+#define ZERO_BIG_BLOCK(base, offset, source) \
+ STORE(source, base, offset, 0x00); \
+ STORE(source, base, offset, 0x08); \
+ STORE(source, base, offset, 0x10); \
+ STORE(source, base, offset, 0x18); \
+ STORE(source, base, offset, 0x20); \
+ STORE(source, base, offset, 0x28); \
+ STORE(source, base, offset, 0x30); \
+ STORE(source, base, offset, 0x38);
#define ZERO_LAST_BLOCKS(base, offset, source) \
- std source, [base - offset - 0x38]; \
- std source, [base - offset - 0x30]; \
- std source, [base - offset - 0x28]; \
- std source, [base - offset - 0x20]; \
- std source, [base - offset - 0x18]; \
- std source, [base - offset - 0x10]; \
- std source, [base - offset - 0x08]; \
- std source, [base - offset - 0x00];
+ STORE_LAST(source, base, offset, 0x38); \
+ STORE_LAST(source, base, offset, 0x30); \
+ STORE_LAST(source, base, offset, 0x28); \
+ STORE_LAST(source, base, offset, 0x20); \
+ STORE_LAST(source, base, offset, 0x18); \
+ STORE_LAST(source, base, offset, 0x10); \
+ STORE_LAST(source, base, offset, 0x08); \
+ STORE_LAST(source, base, offset, 0x00);
.text
.align 4
@@ -68,8 +77,6 @@ __bzero_begin:
.globl memset
EXPORT_SYMBOL(__bzero)
EXPORT_SYMBOL(memset)
- .globl __memset_start, __memset_end
-__memset_start:
memset:
mov %o0, %g1
mov 1, %g4
@@ -122,8 +129,6 @@ __bzero:
ZERO_BIG_BLOCK(%o0, 0x00, %g2)
subcc %o3, 128, %o3
ZERO_BIG_BLOCK(%o0, 0x40, %g2)
-11:
- EXT(10b, 11b, 20f)
bne 10b
add %o0, 128, %o0
@@ -138,11 +143,9 @@ __bzero:
jmp %o4
add %o0, %o2, %o0
-12:
ZERO_LAST_BLOCKS(%o0, 0x48, %g2)
ZERO_LAST_BLOCKS(%o0, 0x08, %g2)
13:
- EXT(12b, 13b, 21f)
be 8f
andcc %o1, 4, %g0
@@ -182,37 +185,13 @@ __bzero:
5:
retl
clr %o0
-__memset_end:
.section .fixup,#alloc,#execinstr
.align 4
-20:
- cmp %g2, 8
- bleu 1f
- and %o1, 0x7f, %o1
- sub %g2, 9, %g2
- add %o3, 64, %o3
-1:
- sll %g2, 3, %g2
- add %o3, %o1, %o0
- b 30f
- sub %o0, %g2, %o0
-21:
- mov 8, %o0
- and %o1, 7, %o1
- sub %o0, %g2, %o0
- sll %o0, 3, %o0
- b 30f
- add %o0, %o1, %o0
30:
-/* %o4 is faulting address, %o5 is %pc where fault occurred */
- save %sp, -104, %sp
- mov %i5, %o0
- mov %i7, %o1
- call lookup_fault
- mov %i4, %o2
- ret
- restore
+ and %o1, 0x7f, %o1
+ retl
+ add %o3, %o1, %o0
.globl __bzero_end
__bzero_end:
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 68db1f859b02..871354aa3c00 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -8,7 +8,7 @@ ccflags-y := -Werror
obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o
obj-y += fault_$(BITS).o
obj-y += init_$(BITS).o
-obj-$(CONFIG_SPARC32) += extable.o srmmu.o iommu.o io-unit.o
+obj-$(CONFIG_SPARC32) += srmmu.o iommu.o io-unit.o
obj-$(CONFIG_SPARC32) += srmmu_access.o
obj-$(CONFIG_SPARC32) += hypersparc.o viking.o tsunami.o swift.o
obj-$(CONFIG_SPARC32) += leon_mm.o
diff --git a/arch/sparc/mm/extable.c b/arch/sparc/mm/extable.c
deleted file mode 100644
index 241b40641873..000000000000
--- a/arch/sparc/mm/extable.c
+++ /dev/null
@@ -1,107 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * linux/arch/sparc/mm/extable.c
- */
-
-#include <linux/module.h>
-#include <linux/extable.h>
-#include <linux/uaccess.h>
-
-void sort_extable(struct exception_table_entry *start,
- struct exception_table_entry *finish)
-{
-}
-
-/* Caller knows they are in a range if ret->fixup == 0 */
-const struct exception_table_entry *
-search_extable(const struct exception_table_entry *base,
- const size_t num,
- unsigned long value)
-{
- int i;
-
- /* Single insn entries are encoded as:
- * word 1: insn address
- * word 2: fixup code address
- *
- * Range entries are encoded as:
- * word 1: first insn address
- * word 2: 0
- * word 3: last insn address + 4 bytes
- * word 4: fixup code address
- *
- * Deleted entries are encoded as:
- * word 1: unused
- * word 2: -1
- *
- * See asm/uaccess.h for more details.
- */
-
- /* 1. Try to find an exact match. */
- for (i = 0; i < num; i++) {
- if (base[i].fixup == 0) {
- /* A range entry, skip both parts. */
- i++;
- continue;
- }
-
- /* A deleted entry; see trim_init_extable */
- if (base[i].fixup == -1)
- continue;
-
- if (base[i].insn == value)
- return &base[i];
- }
-
- /* 2. Try to find a range match. */
- for (i = 0; i < (num - 1); i++) {
- if (base[i].fixup)
- continue;
-
- if (base[i].insn <= value && base[i + 1].insn > value)
- return &base[i];
-
- i++;
- }
-
- return NULL;
-}
-
-#ifdef CONFIG_MODULES
-/* We could memmove them around; easier to mark the trimmed ones. */
-void trim_init_extable(struct module *m)
-{
- unsigned int i;
- bool range;
-
- for (i = 0; i < m->num_exentries; i += range ? 2 : 1) {
- range = m->extable[i].fixup == 0;
-
- if (within_module_init(m->extable[i].insn, m)) {
- m->extable[i].fixup = -1;
- if (range)
- m->extable[i+1].fixup = -1;
- }
- if (range)
- i++;
- }
-}
-#endif /* CONFIG_MODULES */
-
-/* Special extable search, which handles ranges. Returns fixup */
-unsigned long search_extables_range(unsigned long addr, unsigned long *g2)
-{
- const struct exception_table_entry *entry;
-
- entry = search_exception_tables(addr);
- if (!entry)
- return 0;
-
- /* Inside range? Fix g2 and return correct fixup */
- if (!entry->fixup) {
- *g2 = (addr - entry->insn) / 4;
- return (entry + 1)->fixup;
- }
-
- return entry->fixup;
-}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 40ce087dfecf..de2031c2b2d7 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -23,6 +23,7 @@
#include <linux/interrupt.h>
#include <linux/kdebug.h>
#include <linux/uaccess.h>
+#include <linux/extable.h>
#include <asm/page.h>
#include <asm/openprom.h>
@@ -54,54 +55,6 @@ static void __noreturn unhandled_fault(unsigned long address,
die_if_kernel("Oops", regs);
}
-asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
- unsigned long address)
-{
- struct pt_regs regs;
- unsigned long g2;
- unsigned int insn;
- int i;
-
- i = search_extables_range(ret_pc, &g2);
- switch (i) {
- case 3:
- /* load & store will be handled by fixup */
- return 3;
-
- case 1:
- /* store will be handled by fixup, load will bump out */
- /* for _to_ macros */
- insn = *((unsigned int *) pc);
- if ((insn >> 21) & 1)
- return 1;
- break;
-
- case 2:
- /* load will be handled by fixup, store will bump out */
- /* for _from_ macros */
- insn = *((unsigned int *) pc);
- if (!((insn >> 21) & 1) || ((insn>>19)&0x3f) == 15)
- return 2;
- break;
-
- default:
- break;
- }
-
- memset(&regs, 0, sizeof(regs));
- regs.pc = pc;
- regs.npc = pc + 4;
- __asm__ __volatile__(
- "rd %%psr, %0\n\t"
- "nop\n\t"
- "nop\n\t"
- "nop\n" : "=r" (regs.psr));
- unhandled_fault(address, current, &regs);
-
- /* Not reached */
- return 0;
-}
-
static inline void
show_signal_msg(struct pt_regs *regs, int sig, int code,
unsigned long address, struct task_struct *tsk)
@@ -162,8 +115,6 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
struct vm_area_struct *vma;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
- unsigned int fixup;
- unsigned long g2;
int from_user = !(regs->psr & PSR_PS);
int code;
vm_fault_t fault;
@@ -281,30 +232,19 @@ bad_area_nosemaphore:
/* Is this in ex_table? */
no_context:
- g2 = regs->u_regs[UREG_G2];
if (!from_user) {
- fixup = search_extables_range(regs->pc, &g2);
- /* Values below 10 are reserved for other things */
- if (fixup > 10) {
- extern const unsigned int __memset_start[];
- extern const unsigned int __memset_end[];
+ const struct exception_table_entry *entry;
+ entry = search_exception_tables(regs->pc);
#ifdef DEBUG_EXCEPTIONS
- printk("Exception: PC<%08lx> faddr<%08lx>\n",
- regs->pc, address);
- printk("EX_TABLE: insn<%08lx> fixup<%08x> g2<%08lx>\n",
- regs->pc, fixup, g2);
+ printk("Exception: PC<%08lx> faddr<%08lx>\n",
+ regs->pc, address);
+ printk("EX_TABLE: insn<%08lx> fixup<%08x>\n",
+ regs->pc, entry->fixup);
#endif
- if ((regs->pc >= (unsigned long)__memset_start &&
- regs->pc < (unsigned long)__memset_end)) {
- regs->u_regs[UREG_I4] = address;
- regs->u_regs[UREG_I5] = regs->pc;
- }
- regs->u_regs[UREG_G2] = g2;
- regs->pc = fixup;
- regs->npc = regs->pc + 4;
- return;
- }
+ regs->pc = entry->fixup;
+ regs->npc = regs->pc + 4;
+ return;
}
unhandled_fault(address, tsk, regs);
diff --git a/arch/sparc/mm/mm_32.h b/arch/sparc/mm/mm_32.h
index ce750a99eea9..ee55f1080634 100644
--- a/arch/sparc/mm/mm_32.h
+++ b/arch/sparc/mm/mm_32.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* fault_32.c - visible as they are called from assembler */
-asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
- unsigned long address);
asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
unsigned long address);
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d6d5a28c3bf..9a85eae37b17 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -27,7 +27,7 @@ endif
REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
-Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
- -mno-mmx -mno-sse
+ -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
REALMODE_CFLAGS += -ffreestanding
REALMODE_CFLAGS += -fno-stack-protector
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index a2433ae8a65e..4efd39aacb9f 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -128,7 +128,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
regs->ax = -EFAULT;
instrumentation_end();
- syscall_exit_to_user_mode(regs);
+ local_irq_disable();
+ irqentry_exit_to_user_mode(regs);
return false;
}
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 541fdaf64045..0051cf5c792d 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -210,6 +210,8 @@ SYM_CODE_START(entry_SYSCALL_compat)
/* Switch to the kernel stack */
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
+
/* Construct struct pt_regs on stack */
pushq $__USER32_DS /* pt_regs->ss */
pushq %r8 /* pt_regs->sp */
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6ddeed3cd2ac..18df17129695 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -81,7 +81,11 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx);
DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs);
DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
-DEFINE_STATIC_CALL_NULL(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs);
+/*
+ * This one is magic, it will get called even when PMU init fails (because
+ * there is no PMU), in which case it should simply return NULL.
+ */
+DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs);
u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
@@ -1944,13 +1948,6 @@ static void _x86_pmu_read(struct perf_event *event)
x86_perf_event_update(event);
}
-static inline struct perf_guest_switch_msr *
-perf_guest_get_msrs_nop(int *nr)
-{
- *nr = 0;
- return NULL;
-}
-
static int __init init_hw_perf_events(void)
{
struct x86_pmu_quirk *quirk;
@@ -2025,7 +2022,7 @@ static int __init init_hw_perf_events(void)
x86_pmu.read = _x86_pmu_read;
if (!x86_pmu.guest_get_msrs)
- x86_pmu.guest_get_msrs = perf_guest_get_msrs_nop;
+ x86_pmu.guest_get_msrs = (void *)&__static_call_return0;
x86_pmu_static_call_update();
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 5bac48d5c18e..37ce38403cb8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3659,11 +3659,16 @@ static int intel_pmu_hw_config(struct perf_event *event)
return ret;
if (event->attr.precise_ip) {
+ if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
+ return -EINVAL;
+
if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
- ~intel_pmu_large_pebs_flags(event)))
+ ~intel_pmu_large_pebs_flags(event))) {
event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
+ event->attach_state |= PERF_ATTACH_SCHED_CB;
+ }
}
if (x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event);
@@ -3676,6 +3681,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
ret = intel_pmu_setup_lbr_filter(event);
if (ret)
return ret;
+ event->attach_state |= PERF_ATTACH_SCHED_CB;
/*
* BTS is set up earlier in this path, so don't account twice
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ebae1826403..d32b302719fe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2010,7 +2010,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
*/
if (!pebs_status && cpuc->pebs_enabled &&
!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
- pebs_status = cpuc->pebs_enabled;
+ pebs_status = p->status = cpuc->pebs_enabled;
bit = find_first_bit((unsigned long *)&pebs_status,
x86_pmu.max_pebs_events);
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index a0f839aa144d..98b4dae5e8bc 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -23,6 +23,8 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
int insn_get_code_seg_params(struct pt_regs *regs);
int insn_fetch_from_user(struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE]);
+int insn_fetch_from_user_inatomic(struct pt_regs *regs,
+ unsigned char buf[MAX_INSN_SIZE]);
bool insn_decode(struct insn *insn, struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE], int buf_size);
diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h
index 97bbb4a9083a..05b48b33baf0 100644
--- a/arch/x86/include/asm/kfence.h
+++ b/arch/x86/include/asm/kfence.h
@@ -56,8 +56,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
else
set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
- /* Flush this CPU's TLB. */
+ /*
+ * Flush this CPU's TLB, assuming whoever did the allocation/free is
+ * likely to continue running on this CPU.
+ */
+ preempt_disable();
flush_tlb_one_kernel(addr);
+ preempt_enable();
return true;
}
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 877a4025d8da..3768819693e5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -884,12 +884,29 @@ struct kvm_hv_syndbg {
u64 options;
};
+/* Current state of Hyper-V TSC page clocksource */
+enum hv_tsc_page_status {
+ /* TSC page was not set up or disabled */
+ HV_TSC_PAGE_UNSET = 0,
+ /* TSC page MSR was written by the guest, update pending */
+ HV_TSC_PAGE_GUEST_CHANGED,
+ /* TSC page MSR was written by KVM userspace, update pending */
+ HV_TSC_PAGE_HOST_CHANGED,
+ /* TSC page was properly set up and is currently active */
+ HV_TSC_PAGE_SET,
+ /* TSC page is currently being updated and therefore is inactive */
+ HV_TSC_PAGE_UPDATING,
+ /* TSC page was set up with an inaccessible GPA */
+ HV_TSC_PAGE_BROKEN,
+};
+
/* Hyper-V emulation context */
struct kvm_hv {
struct mutex hv_lock;
u64 hv_guest_os_id;
u64 hv_hypercall;
u64 hv_tsc_page;
+ enum hv_tsc_page_status hv_tsc_page_status;
/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
@@ -931,6 +948,12 @@ enum kvm_irqchip_mode {
KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */
};
+struct kvm_x86_msr_filter {
+ u8 count;
+ bool default_allow:1;
+ struct msr_bitmap_range ranges[16];
+};
+
#define APICV_INHIBIT_REASON_DISABLE 0
#define APICV_INHIBIT_REASON_HYPERV 1
#define APICV_INHIBIT_REASON_NESTED 2
@@ -963,7 +986,7 @@ struct kvm_arch {
struct kvm_pit *vpit;
atomic_t vapics_in_nmi_mode;
struct mutex apic_map_lock;
- struct kvm_apic_map *apic_map;
+ struct kvm_apic_map __rcu *apic_map;
atomic_t apic_map_dirty;
bool apic_access_page_done;
@@ -1025,18 +1048,13 @@ struct kvm_arch {
bool guest_can_read_msr_platform_info;
bool exception_payload_enabled;
+ bool bus_lock_detection_enabled;
+
/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
u32 user_space_msr_mask;
+ struct kvm_x86_msr_filter __rcu *msr_filter;
- struct {
- u8 count;
- bool default_allow:1;
- struct msr_bitmap_range ranges[16];
- } msr_filter;
-
- bool bus_lock_detection_enabled;
-
- struct kvm_pmu_event_filter *pmu_event_filter;
+ struct kvm_pmu_event_filter __rcu *pmu_event_filter;
struct task_struct *nx_lpage_recovery_thread;
#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index dc6d149bf851..f1b9ed5efaa9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -551,15 +551,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
*size = fpu_kernel_xstate_size;
}
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
-
static inline void
native_load_sp0(unsigned long sp0)
{
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 2c35f1c01a2d..b6a9d51d1d79 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -25,6 +25,7 @@ void __end_SYSENTER_singlestep_region(void);
void entry_SYSENTER_compat(void);
void __end_entry_SYSENTER_compat(void);
void entry_SYSCALL_compat(void);
+void entry_SYSCALL_compat_safe_stack(void);
void entry_INT80_compat(void);
#ifdef CONFIG_XEN_PV
void xen_entry_INT80_compat(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index d8324a236696..409f661481e1 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -94,6 +94,8 @@ struct pt_regs {
#include <asm/paravirt_types.h>
#endif
+#include <asm/proto.h>
+
struct cpuinfo_x86;
struct task_struct;
@@ -175,6 +177,19 @@ static inline bool any_64bit_mode(struct pt_regs *regs)
#ifdef CONFIG_X86_64
#define current_user_stack_pointer() current_pt_regs()->sp
#define compat_user_stack_pointer() current_pt_regs()->sp
+
+static inline bool ip_within_syscall_gap(struct pt_regs *regs)
+{
+ bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
+ regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack);
+
+#ifdef CONFIG_IA32_EMULATION
+ ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat &&
+ regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack);
+#endif
+
+ return ret;
+}
#endif
static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 8b58d6975d5d..0bc9b0895f33 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -58,9 +58,8 @@ static __always_inline unsigned long smap_save(void)
unsigned long flags;
asm volatile ("# smap_save\n\t"
- ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
- "pushf; pop %0; " __ASM_CLAC "\n\t"
- "1:"
+ ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC "\n\t",
+ X86_FEATURE_SMAP)
: "=rm" (flags) : : "memory", "cc");
return flags;
@@ -69,9 +68,8 @@ static __always_inline unsigned long smap_save(void)
static __always_inline void smap_restore(unsigned long flags)
{
asm volatile ("# smap_restore\n\t"
- ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
- "push %0; popf\n\t"
- "1:"
+ ALTERNATIVE("", "push %0; popf\n\t",
+ X86_FEATURE_SMAP)
: : "g" (flags) : "memory", "cc");
}
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index c0538f82c9a2..630ff08532be 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,6 +132,7 @@ void native_play_dead(void);
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
int wbinvd_on_all_cpus(void);
+void cond_wakeup_cpu0(void);
void native_smp_send_reschedule(int cpu);
void native_send_call_func_ipi(const struct cpumask *mask);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 0d751d5da702..06b740bae431 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -205,10 +205,23 @@ static inline int arch_within_stack_frames(const void * const stack,
#endif
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
+
+#ifndef __ASSEMBLY__
#ifdef CONFIG_COMPAT
#define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */
+
+#define arch_set_restart_data(restart) \
+ do { restart->arch_data = current_thread_info()->status; } while (0)
+
#endif
-#ifndef __ASSEMBLY__
#ifdef CONFIG_X86_32
#define in_ia32_syscall() true
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 7068e4bb057d..1a162e559753 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -87,18 +87,6 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
#endif
/*
- * The maximum amount of extra memory compared to the base size. The
- * main scaling factor is the size of struct page. At extreme ratios
- * of base:extra, all the base memory can be filled with page
- * structures for the extra memory, leaving no space for anything
- * else.
- *
- * 10x seems like a reasonable balance between scaling flexibility and
- * leaving a practically usable system.
- */
-#define XEN_EXTRA_MEM_RATIO (10)
-
-/*
* Helper functions to write or read unsigned long values to/from
* memory, when the access may fault.
*/
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7bdc0239a943..14cd3186dc77 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1554,10 +1554,18 @@ void __init acpi_boot_table_init(void)
/*
* Initialize the ACPI boot-time table parser.
*/
- if (acpi_table_init()) {
+ if (acpi_locate_initial_tables())
disable_acpi();
- return;
- }
+ else
+ acpi_reserve_initial_tables();
+}
+
+int __init early_acpi_boot_init(void)
+{
+ if (acpi_disabled)
+ return 1;
+
+ acpi_table_init_complete();
acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
@@ -1570,18 +1578,9 @@ void __init acpi_boot_table_init(void)
} else {
printk(KERN_WARNING PREFIX "Disabling ACPI support\n");
disable_acpi();
- return;
+ return 1;
}
}
-}
-
-int __init early_acpi_boot_init(void)
-{
- /*
- * If acpi_disabled, bail out
- */
- if (acpi_disabled)
- return 1;
/*
* Process the Multiple APIC Description Table (MADT), if present
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 56b6865afb2a..d5d8a352eafa 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -115,7 +115,7 @@ SYM_FUNC_START(do_suspend_lowlevel)
movq pt_regs_r14(%rax), %r14
movq pt_regs_r15(%rax), %r15
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
/*
* The suspend path may have poisoned some areas deeper in the stack,
* which we now need to unpoison.
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index bda4f2a36868..4f26700f314d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2342,6 +2342,11 @@ static int cpuid_to_apicid[] = {
[0 ... NR_CPUS - 1] = -1,
};
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+ return phys_id == cpuid_to_apicid[cpu];
+}
+
#ifdef CONFIG_SMP
/**
* apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c3b60c37c728..73ff4dd426a8 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1032,6 +1032,16 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
irq = mp_irqs[idx].srcbusirq;
legacy = mp_is_legacy_irq(irq);
+ /*
+ * IRQ2 is unusable for historical reasons on systems which
+ * have a legacy PIC. See the comment vs. IRQ2 further down.
+ *
+ * If this gets removed at some point then the related code
+ * in lapic_assign_system_vectors() needs to be adjusted as
+ * well.
+ */
+ if (legacy && irq == PIC_CASCADE_IR)
+ return -EINVAL;
}
mutex_lock(&ioapic_mutex);
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 373e5fa3ce1f..51c7f5271aee 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -12,7 +12,7 @@
#include "common.h"
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5e78e01ca3b4..78bb0fae3982 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -836,28 +836,25 @@ static void kvm_kick_cpu(int cpu)
static void kvm_wait(u8 *ptr, u8 val)
{
- unsigned long flags;
-
if (in_nmi())
return;
- local_irq_save(flags);
-
- if (READ_ONCE(*ptr) != val)
- goto out;
-
/*
* halt until it's our turn and kicked. Note that we do safe halt
* for irq enabled case to avoid hang when lock info is overwritten
* in irq spinlock slowpath and no spurious interrupt occur to save us.
*/
- if (arch_irqs_disabled_flags(flags))
- halt();
- else
- safe_halt();
+ if (irqs_disabled()) {
+ if (READ_ONCE(*ptr) == val)
+ halt();
+ } else {
+ local_irq_disable();
-out:
- local_irq_restore(flags);
+ if (READ_ONCE(*ptr) == val)
+ safe_halt();
+
+ local_irq_enable();
+ }
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index aa593743acf6..1fc0962c89c0 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -268,21 +268,20 @@ static void __init kvmclock_init_mem(void)
static int __init kvm_setup_vsyscall_timeinfo(void)
{
-#ifdef CONFIG_X86_64
- u8 flags;
+ kvmclock_init_mem();
- if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
- return 0;
+#ifdef CONFIG_X86_64
+ if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) {
+ u8 flags;
- flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
- if (!(flags & PVCLOCK_TSC_STABLE_BIT))
- return 0;
+ flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+ if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+ return 0;
- kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+ kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+ }
#endif
- kvmclock_init_mem();
-
return 0;
}
early_initcall(kvm_setup_vsyscall_timeinfo);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d883176ef2ce..ccab6cf91283 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1129,6 +1129,8 @@ void __init setup_arch(char **cmdline_p)
reserve_initrd();
acpi_table_upgrade();
+ /* Look for ACPI tables and reserve memory occupied by them. */
+ acpi_boot_table_init();
vsmp_init();
@@ -1136,11 +1138,6 @@ void __init setup_arch(char **cmdline_p)
early_platform_quirks();
- /*
- * Parse the ACPI tables for possible boot-time SMP configuration.
- */
- acpi_boot_table_init();
-
early_acpi_boot_init();
initmem_init();
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 84c1821819af..04a780abb512 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -121,8 +121,18 @@ static void __init setup_vc_stacks(int cpu)
cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
}
-static __always_inline bool on_vc_stack(unsigned long sp)
+static __always_inline bool on_vc_stack(struct pt_regs *regs)
{
+ unsigned long sp = regs->sp;
+
+ /* User-mode RSP is not trusted */
+ if (user_mode(regs))
+ return false;
+
+ /* SYSCALL gap still has user-mode RSP */
+ if (ip_within_syscall_gap(regs))
+ return false;
+
return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
}
@@ -144,7 +154,7 @@ void noinstr __sev_es_ist_enter(struct pt_regs *regs)
old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
/* Make room on the IST stack */
- if (on_vc_stack(regs->sp))
+ if (on_vc_stack(regs))
new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist);
else
new_ist = old_ist - sizeof(old_ist);
@@ -248,7 +258,7 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
int res;
if (user_mode(ctxt->regs)) {
- res = insn_fetch_from_user(ctxt->regs, buffer);
+ res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
if (!res) {
ctxt->fi.vector = X86_TRAP_PF;
ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
@@ -1248,13 +1258,12 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs)
DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
{
struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+ irqentry_state_t irq_state;
struct ghcb_state state;
struct es_em_ctxt ctxt;
enum es_result result;
struct ghcb *ghcb;
- lockdep_assert_irqs_disabled();
-
/*
* Handle #DB before calling into !noinstr code to avoid recursive #DB.
*/
@@ -1263,6 +1272,8 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
return;
}
+ irq_state = irqentry_nmi_enter(regs);
+ lockdep_assert_irqs_disabled();
instrumentation_begin();
/*
@@ -1325,6 +1336,7 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
out:
instrumentation_end();
+ irqentry_nmi_exit(regs, irq_state);
return;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index ea794a083c44..f306e85a08a6 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -766,30 +766,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
{
- /*
- * This function is fundamentally broken as currently
- * implemented.
- *
- * The idea is that we want to trigger a call to the
- * restart_block() syscall and that we want in_ia32_syscall(),
- * in_x32_syscall(), etc. to match whatever they were in the
- * syscall being restarted. We assume that the syscall
- * instruction at (regs->ip - 2) matches whatever syscall
- * instruction we used to enter in the first place.
- *
- * The problem is that we can get here when ptrace pokes
- * syscall-like values into regs even if we're not in a syscall
- * at all.
- *
- * For now, we maintain historical behavior and guess based on
- * stored state. We could do better by saving the actual
- * syscall arch in restart_block or (with caveats on x32) by
- * checking if regs->ip points to 'int $0x80'. The current
- * behavior is incorrect if a tracer has a different bitness
- * than the tracee.
- */
#ifdef CONFIG_IA32_EMULATION
- if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
+ if (current->restart_block.arch_data & TS_COMPAT)
return __NR_ia32_restart_syscall;
#endif
#ifdef CONFIG_X86_X32_ABI
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 02813a7f3a7c..16703c35a944 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1659,13 +1659,17 @@ void play_dead_common(void)
local_irq_disable();
}
-static bool wakeup_cpu0(void)
+/**
+ * cond_wakeup_cpu0 - Wake up CPU0 if needed.
+ *
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+void cond_wakeup_cpu0(void)
{
if (smp_processor_id() == 0 && enable_start_cpu0)
- return true;
-
- return false;
+ start_cpu0();
}
+EXPORT_SYMBOL_GPL(cond_wakeup_cpu0);
/*
* We need to flush the caches before going to sleep, lest we have
@@ -1734,11 +1738,8 @@ static inline void mwait_play_dead(void)
__monitor(mwait_ptr, 0, 0);
mb();
__mwait(eax, 0);
- /*
- * If NMI wants to wake up CPU0, start CPU0.
- */
- if (wakeup_cpu0())
- start_cpu0();
+
+ cond_wakeup_cpu0();
}
}
@@ -1749,11 +1750,8 @@ void hlt_play_dead(void)
while (1) {
native_halt();
- /*
- * If NMI wants to wake up CPU0, start CPU0.
- */
- if (wakeup_cpu0())
- start_cpu0();
+
+ cond_wakeup_cpu0();
}
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7f5aec758f0e..651e3e508959 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -556,7 +556,7 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
tsk->thread.trap_nr = X86_TRAP_GP;
if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0))
- return;
+ goto exit;
show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
force_sig(SIGSEGV);
@@ -694,8 +694,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
* In the SYSCALL entry path the RSP value comes from user-space - don't
* trust it and switch to the current kernel stack
*/
- if (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
- regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack) {
+ if (ip_within_syscall_gap(regs)) {
sp = this_cpu_read(cpu_current_top_of_stack);
goto sync;
}
@@ -1058,7 +1057,7 @@ static void math_error(struct pt_regs *regs, int trapnr)
goto exit;
if (fixup_vdso_exception(regs, trapnr, 0, 0))
- return;
+ goto exit;
force_sig_fault(SIGFPE, si_code,
(void __user *)uprobe_get_trap_addr(regs));
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 2a1d47f47eee..a1202536fc57 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -13,7 +13,7 @@
#define orc_warn_current(args...) \
({ \
- if (state->task == current) \
+ if (state->task == current && !state->error) \
orc_warn(args); \
})
@@ -367,8 +367,8 @@ static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
return false;
- *ip = regs->ip;
- *sp = regs->sp;
+ *ip = READ_ONCE_NOCHECK(regs->ip);
+ *sp = READ_ONCE_NOCHECK(regs->sp);
return true;
}
@@ -380,8 +380,8 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
return false;
- *ip = regs->ip;
- *sp = regs->sp;
+ *ip = READ_ONCE_NOCHECK(regs->ip);
+ *sp = READ_ONCE_NOCHECK(regs->sp);
return true;
}
@@ -402,12 +402,12 @@ static bool get_reg(struct unwind_state *state, unsigned int reg_off,
return false;
if (state->full_regs) {
- *val = ((unsigned long *)state->regs)[reg];
+ *val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]);
return true;
}
if (state->prev_regs) {
- *val = ((unsigned long *)state->prev_regs)[reg];
+ *val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]);
return true;
}
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 1b4766fe1de2..eafc4d601f25 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-ccflags-y += -Iarch/x86/kvm
+ccflags-y += -I $(srctree)/arch/x86/kvm
ccflags-$(CONFIG_KVM_WERROR) += -Werror
ifeq ($(CONFIG_FRAME_POINTER),y)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 58fa8c029867..f98370a39936 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -520,10 +520,10 @@ static u64 get_time_ref_counter(struct kvm *kvm)
u64 tsc;
/*
- * The guest has not set up the TSC page or the clock isn't
- * stable, fall back to get_kvmclock_ns.
+ * Fall back to get_kvmclock_ns() when TSC page hasn't been set up,
+ * is broken, disabled or being updated.
*/
- if (!hv->tsc_ref.tsc_sequence)
+ if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET)
return div_u64(get_kvmclock_ns(kvm), 100);
vcpu = kvm_get_vcpu(kvm, 0);
@@ -1077,6 +1077,21 @@ static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock,
return true;
}
+/*
+ * Don't touch TSC page values if the guest has opted for TSC emulation after
+ * migration. KVM doesn't fully support reenlightenment notifications and TSC
+ * access emulation and Hyper-V is known to expect the values in TSC page to
+ * stay constant before TSC access emulation is disabled from guest side
+ * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC
+ * frequency and guest visible TSC value across migration (and prevent it when
+ * TSC scaling is unsupported).
+ */
+static inline bool tsc_page_update_unsafe(struct kvm_hv *hv)
+{
+ return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) &&
+ hv->hv_tsc_emulation_control;
+}
+
void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock)
{
@@ -1087,7 +1102,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence));
BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0);
- if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+ hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
return;
mutex_lock(&hv->hv_lock);
@@ -1101,7 +1117,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
*/
if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn),
&tsc_seq, sizeof(tsc_seq))))
+ goto out_err;
+
+ if (tsc_seq && tsc_page_update_unsafe(hv)) {
+ if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
+ goto out_err;
+
+ hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
goto out_unlock;
+ }
/*
* While we're computing and writing the parameters, force the
@@ -1110,15 +1134,15 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
hv->tsc_ref.tsc_sequence = 0;
if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
- goto out_unlock;
+ goto out_err;
if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref))
- goto out_unlock;
+ goto out_err;
/* Ensure sequence is zero before writing the rest of the struct. */
smp_wmb();
if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
- goto out_unlock;
+ goto out_err;
/*
* Now switch to the TSC page mechanism by writing the sequence.
@@ -1131,8 +1155,45 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
smp_wmb();
hv->tsc_ref.tsc_sequence = tsc_seq;
- kvm_write_guest(kvm, gfn_to_gpa(gfn),
- &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
+ if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+ &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+ goto out_err;
+
+ hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
+ goto out_unlock;
+
+out_err:
+ hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+out_unlock:
+ mutex_unlock(&hv->hv_lock);
+}
+
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
+{
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+ u64 gfn;
+
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+ hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET ||
+ tsc_page_update_unsafe(hv))
+ return;
+
+ mutex_lock(&hv->hv_lock);
+
+ if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+ goto out_unlock;
+
+ /* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET)
+ hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING;
+
+ gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+
+ hv->tsc_ref.tsc_sequence = 0;
+ if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+ &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+ hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+
out_unlock:
mutex_unlock(&hv->hv_lock);
}
@@ -1193,8 +1254,15 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
}
case HV_X64_MSR_REFERENCE_TSC:
hv->hv_tsc_page = data;
- if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)
+ if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) {
+ if (!host)
+ hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED;
+ else
+ hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED;
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
+ } else {
+ hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET;
+ }
break;
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
return kvm_hv_msr_set_crash_data(kvm,
@@ -1229,6 +1297,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
hv->hv_tsc_emulation_control = data;
break;
case HV_X64_MSR_TSC_EMULATION_STATUS:
+ if (data && !host)
+ return 1;
+
hv->hv_tsc_emulation_status = data;
break;
case HV_X64_MSR_TIME_REF_COUNT:
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index e951af1fcb2c..60547d5cb6d7 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -133,6 +133,7 @@ void kvm_hv_process_stimers(struct kvm_vcpu *vcpu);
void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock);
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm);
void kvm_hv_init_vm(struct kvm *kvm);
void kvm_hv_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 45d40bfacb7c..cc369b9ad8f1 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1642,7 +1642,16 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
}
if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
- kvm_wait_lapic_expire(vcpu);
+ /*
+ * Ensure the guest's timer has truly expired before posting an
+ * interrupt. Open code the relevant checks to avoid querying
+ * lapic_timer_int_injected(), which will be false since the
+ * interrupt isn't yet injected. Waiting until after injecting
+ * is not an option since that won't help a posted interrupt.
+ */
+ if (vcpu->arch.apic->lapic_timer.expired_tscdeadline &&
+ vcpu->arch.apic->lapic_timer.timer_advance_ns)
+ __kvm_wait_lapic_expire(vcpu);
kvm_apic_inject_pending_timer_irqs(apic);
return;
}
@@ -2595,6 +2604,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
apic_update_ppr(apic);
hrtimer_cancel(&apic->lapic_timer.timer);
+ apic->lapic_timer.expired_tscdeadline = 0;
apic_update_lvtt(apic);
apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
update_divide_count(apic);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d75524bc8423..951dae4e7175 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5884,6 +5884,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
struct kvm_mmu_page *sp;
unsigned int ratio;
LIST_HEAD(invalid_list);
+ bool flush = false;
ulong to_zap;
rcu_idx = srcu_read_lock(&kvm->srcu);
@@ -5905,19 +5906,19 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
lpage_disallowed_link);
WARN_ON_ONCE(!sp->lpage_disallowed);
if (is_tdp_mmu_page(sp)) {
- kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
- sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+ flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
} else {
kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
WARN_ON_ONCE(sp->lpage_disallowed);
}
if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
- kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
cond_resched_rwlock_write(&kvm->mmu_lock);
+ flush = false;
}
}
- kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
write_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, rcu_idx);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index ec4fc28b325a..1f6f98c76bdf 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -78,6 +78,11 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
return to_shadow_page(__pa(sptep));
}
+static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
+{
+ return sp->role.smm ? 1 : 0;
+}
+
static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
{
/*
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index e5f148106e20..b3ed302c1a35 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -21,6 +21,21 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
}
/*
+ * Return the TDP iterator to the root PT and allow it to continue its
+ * traversal over the paging structure from there.
+ */
+void tdp_iter_restart(struct tdp_iter *iter)
+{
+ iter->yielded_gfn = iter->next_last_level_gfn;
+ iter->level = iter->root_level;
+
+ iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+ tdp_iter_refresh_sptep(iter);
+
+ iter->valid = true;
+}
+
+/*
* Sets a TDP iterator to walk a pre-order traversal of the paging structure
* rooted at root_pt, starting with the walk to translate next_last_level_gfn.
*/
@@ -31,16 +46,12 @@ void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
iter->next_last_level_gfn = next_last_level_gfn;
- iter->yielded_gfn = iter->next_last_level_gfn;
iter->root_level = root_level;
iter->min_level = min_level;
- iter->level = root_level;
- iter->pt_path[iter->level - 1] = (tdp_ptep_t)root_pt;
-
- iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
- tdp_iter_refresh_sptep(iter);
+ iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt;
+ iter->as_id = kvm_mmu_page_as_id(sptep_to_sp(root_pt));
- iter->valid = true;
+ tdp_iter_restart(iter);
}
/*
@@ -159,8 +170,3 @@ void tdp_iter_next(struct tdp_iter *iter)
iter->valid = false;
}
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter)
-{
- return iter->pt_path[iter->root_level - 1];
-}
-
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index 4cc177d75c4a..b1748b988d3a 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -36,6 +36,8 @@ struct tdp_iter {
int min_level;
/* The iterator's current level within the paging structure */
int level;
+ /* The address space ID, i.e. SMM vs. regular. */
+ int as_id;
/* A snapshot of the value at sptep */
u64 old_spte;
/*
@@ -62,6 +64,6 @@ tdp_ptep_t spte_to_child_pt(u64 pte, int level);
void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
int min_level, gfn_t next_last_level_gfn);
void tdp_iter_next(struct tdp_iter *iter);
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter);
+void tdp_iter_restart(struct tdp_iter *iter);
#endif /* __KVM_X86_MMU_TDP_ITER_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index c926c6b899a1..018d82e73e31 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
- gfn_t start, gfn_t end, bool can_yield);
+ gfn_t start, gfn_t end, bool can_yield, bool flush);
void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
{
@@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
list_del(&root->link);
- zap_gfn_range(kvm, root, 0, max_gfn, false);
+ zap_gfn_range(kvm, root, 0, max_gfn, false, false);
free_page((unsigned long)root->spt);
kmem_cache_free(mmu_page_header_cache, root);
@@ -203,11 +203,6 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
u64 old_spte, u64 new_spte, int level,
bool shared);
-static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
-{
- return sp->role.smm ? 1 : 0;
-}
-
static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level)
{
bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
@@ -301,11 +296,16 @@ static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp,
*
* Given a page table that has been removed from the TDP paging structure,
* iterates through the page table to clear SPTEs and free child page tables.
+ *
+ * Note that pt is passed in as a tdp_ptep_t, but it does not need RCU
+ * protection. Since this thread removed it from the paging structure,
+ * this thread will be responsible for ensuring the page is freed. Hence the
+ * early rcu_dereferences in the function.
*/
-static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
+static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
bool shared)
{
- struct kvm_mmu_page *sp = sptep_to_sp(pt);
+ struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
int level = sp->role.level;
gfn_t base_gfn = sp->gfn;
u64 old_child_spte;
@@ -318,7 +318,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
tdp_mmu_unlink_page(kvm, sp, shared);
for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
- sptep = pt + i;
+ sptep = rcu_dereference(pt) + i;
gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1));
if (shared) {
@@ -337,7 +337,18 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
cpu_relax();
}
} else {
+ /*
+ * If the SPTE is not MMU-present, there is no backing
+ * page associated with the SPTE and so no side effects
+ * that need to be recorded, and exclusive ownership of
+ * mmu_lock ensures the SPTE can't be made present.
+ * Note, zapping MMIO SPTEs is also unnecessary as they
+ * are guarded by the memslots generation, not by being
+ * unreachable.
+ */
old_child_spte = READ_ONCE(*sptep);
+ if (!is_shadow_present_pte(old_child_spte))
+ continue;
/*
* Marking the SPTE as a removed SPTE is not
@@ -481,10 +492,6 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
struct tdp_iter *iter,
u64 new_spte)
{
- u64 *root_pt = tdp_iter_root_pt(iter);
- struct kvm_mmu_page *root = sptep_to_sp(root_pt);
- int as_id = kvm_mmu_page_as_id(root);
-
lockdep_assert_held_read(&kvm->mmu_lock);
/*
@@ -498,8 +505,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
new_spte) != iter->old_spte)
return false;
- handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
- iter->level, true);
+ handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+ new_spte, iter->level, true);
return true;
}
@@ -527,7 +534,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm,
* here since the SPTE is going from non-present
* to non-present.
*/
- WRITE_ONCE(*iter->sptep, 0);
+ WRITE_ONCE(*rcu_dereference(iter->sptep), 0);
return true;
}
@@ -553,10 +560,6 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
u64 new_spte, bool record_acc_track,
bool record_dirty_log)
{
- tdp_ptep_t root_pt = tdp_iter_root_pt(iter);
- struct kvm_mmu_page *root = sptep_to_sp(root_pt);
- int as_id = kvm_mmu_page_as_id(root);
-
lockdep_assert_held_write(&kvm->mmu_lock);
/*
@@ -570,13 +573,13 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
- __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
- iter->level, false);
+ __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+ new_spte, iter->level, false);
if (record_acc_track)
handle_changed_spte_acc_track(iter->old_spte, new_spte,
iter->level);
if (record_dirty_log)
- handle_changed_spte_dirty_log(kvm, as_id, iter->gfn,
+ handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn,
iter->old_spte, new_spte,
iter->level);
}
@@ -648,9 +651,7 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
WARN_ON(iter->gfn > iter->next_last_level_gfn);
- tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
- iter->root_level, iter->min_level,
- iter->next_last_level_gfn);
+ tdp_iter_restart(iter);
return true;
}
@@ -667,20 +668,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
* scheduler needs the CPU or there is contention on the MMU lock. If this
* function cannot yield, it will not release the MMU lock or reschedule and
* the caller must ensure it does not supply too large a GFN range, or the
- * operation can cause a soft lockup.
+ * operation can cause a soft lockup. Note, in some use cases a flush may be
+ * required by prior actions. Ensure the pending flush is performed prior to
+ * yielding.
*/
static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
- gfn_t start, gfn_t end, bool can_yield)
+ gfn_t start, gfn_t end, bool can_yield, bool flush)
{
struct tdp_iter iter;
- bool flush_needed = false;
rcu_read_lock();
tdp_root_for_each_pte(iter, root, start, end) {
if (can_yield &&
- tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
- flush_needed = false;
+ tdp_mmu_iter_cond_resched(kvm, &iter, flush)) {
+ flush = false;
continue;
}
@@ -698,11 +700,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
continue;
tdp_mmu_set_spte(kvm, &iter, 0);
- flush_needed = true;
+ flush = true;
}
rcu_read_unlock();
- return flush_needed;
+ return flush;
}
/*
@@ -711,13 +713,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
* SPTEs have been cleared and a TLB flush is needed before releasing the
* MMU lock.
*/
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+ bool can_yield)
{
struct kvm_mmu_page *root;
bool flush = false;
for_each_tdp_mmu_root_yield_safe(kvm, root)
- flush |= zap_gfn_range(kvm, root, start, end, true);
+ flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
return flush;
}
@@ -929,7 +932,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm,
struct kvm_mmu_page *root, gfn_t start,
gfn_t end, unsigned long unused)
{
- return zap_gfn_range(kvm, root, start, end, false);
+ return zap_gfn_range(kvm, root, start, end, false, false);
}
int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 3b761c111bff..31096ece9b14 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -8,7 +8,29 @@
hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root);
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end);
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+ bool can_yield);
+static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start,
+ gfn_t end)
+{
+ return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true);
+}
+static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
+
+ /*
+ * Don't allow yielding, as the caller may have a flush pending. Note,
+ * if mmu_lock is held for write, zapping will never yield in this case,
+ * but explicitly disallow it for safety. The TDP MMU does not yield
+ * until it has made forward progress (steps sideways), and when zapping
+ * a single shadow page that it's guaranteed to see (thus the mmu_lock
+ * requirement), its "step sideways" will always step beyond the bounds
+ * of the shadow page's gfn range and stop iterating before yielding.
+ */
+ lockdep_assert_held_write(&kvm->mmu_lock);
+ return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false);
+}
void kvm_tdp_mmu_zap_all(struct kvm *kvm);
int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 35891d9a1099..fb204eaa8bb3 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -246,11 +246,18 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
return true;
}
-static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
+static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
bool vmcb12_lma;
+ /*
+ * FIXME: these should be done after copying the fields,
+ * to avoid TOC/TOU races. For these save area checks
+ * the possible damage is limited since kvm_set_cr0 and
+ * kvm_set_cr4 handle failure; EFER_SVME is an exception
+ * so it is force-set later in nested_prepare_vmcb_save.
+ */
if ((vmcb12->save.efer & EFER_SVME) == 0)
return false;
@@ -271,7 +278,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
return false;
- return nested_vmcb_check_controls(&vmcb12->control);
+ return true;
}
static void load_nested_vmcb_control(struct vcpu_svm *svm,
@@ -396,7 +403,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
svm->vmcb->save.gdtr = vmcb12->save.gdtr;
svm->vmcb->save.idtr = vmcb12->save.idtr;
kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
- svm_set_efer(&svm->vcpu, vmcb12->save.efer);
+
+ /*
+ * Force-set EFER_SVME even though it is checked earlier on the
+ * VMCB12, because the guest can flip the bit between the check
+ * and now. Clearing EFER_SVME would call svm_free_nested.
+ */
+ svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);
+
svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2;
@@ -468,7 +482,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa,
svm->nested.vmcb12_gpa = vmcb12_gpa;
- load_nested_vmcb_control(svm, &vmcb12->control);
nested_prepare_vmcb_control(svm);
nested_prepare_vmcb_save(svm, vmcb12);
@@ -515,7 +528,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
if (WARN_ON_ONCE(!svm->nested.initialized))
return -EINVAL;
- if (!nested_vmcb_checks(svm, vmcb12)) {
+ load_nested_vmcb_control(svm, &vmcb12->control);
+
+ if (!nested_vmcb_check_save(svm, vmcb12) ||
+ !nested_vmcb_check_controls(&svm->nested.ctl)) {
vmcb12->control.exit_code = SVM_EXIT_ERR;
vmcb12->control.exit_code_hi = 0;
vmcb12->control.exit_info_1 = 0;
@@ -1209,6 +1225,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
*/
if (!(save->cr0 & X86_CR0_PG))
goto out_free;
+ if (!(save->efer & EFER_SVME))
+ goto out_free;
/*
* All checks done, we can enter guest mode. L1 control fields
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 035da07500e8..fdf587f19c5f 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -98,6 +98,8 @@ static enum index msr_to_index(u32 msr)
static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
enum pmu_type type)
{
+ struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+
switch (msr) {
case MSR_F15H_PERF_CTL0:
case MSR_F15H_PERF_CTL1:
@@ -105,6 +107,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
case MSR_F15H_PERF_CTL3:
case MSR_F15H_PERF_CTL4:
case MSR_F15H_PERF_CTL5:
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+ return NULL;
+ fallthrough;
case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
if (type != PMU_TYPE_EVNTSEL)
return NULL;
@@ -115,6 +120,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
case MSR_F15H_PERF_CTR3:
case MSR_F15H_PERF_CTR4:
case MSR_F15H_PERF_CTR5:
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+ return NULL;
+ fallthrough;
case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
if (type != PMU_TYPE_COUNTER)
return NULL;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index baee91c1e936..58a45bb139f8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -115,13 +115,6 @@ static const struct svm_direct_access_msrs {
{ .index = MSR_INVALID, .always = false },
};
-/* enable NPT for AMD64 and X86 with PAE */
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-bool npt_enabled = true;
-#else
-bool npt_enabled;
-#endif
-
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* pause_filter_count: On processors that support Pause filtering(indicated
@@ -170,9 +163,12 @@ module_param(pause_filter_count_shrink, ushort, 0444);
static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
module_param(pause_filter_count_max, ushort, 0444);
-/* allow nested paging (virtualized MMU) for all guests */
-static int npt = true;
-module_param(npt, int, S_IRUGO);
+/*
+ * Use nested page tables by default. Note, NPT may get forced off by
+ * svm_hardware_setup() if it's unsupported by hardware or the host kernel.
+ */
+bool npt_enabled = true;
+module_param_named(npt, npt_enabled, bool, 0444);
/* allow nested virtualization in KVM/SVM */
static int nested = true;
@@ -988,10 +984,15 @@ static __init int svm_hardware_setup(void)
goto err;
}
- if (!boot_cpu_has(X86_FEATURE_NPT))
+ /*
+ * KVM's MMU doesn't support using 2-level paging for itself, and thus
+ * NPT isn't supported if the host is using 2-level paging since host
+ * CR4 is unchanged on VMRUN.
+ */
+ if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
npt_enabled = false;
- if (npt_enabled && !npt)
+ if (!boot_cpu_has(X86_FEATURE_NPT))
npt_enabled = false;
kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 50810d471462..29b40e092d13 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6027,19 +6027,19 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
exit_reason.basic != EXIT_REASON_PML_FULL &&
exit_reason.basic != EXIT_REASON_APIC_ACCESS &&
exit_reason.basic != EXIT_REASON_TASK_SWITCH)) {
+ int ndata = 3;
+
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
- vcpu->run->internal.ndata = 3;
vcpu->run->internal.data[0] = vectoring_info;
vcpu->run->internal.data[1] = exit_reason.full;
vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) {
- vcpu->run->internal.ndata++;
- vcpu->run->internal.data[3] =
+ vcpu->run->internal.data[ndata++] =
vmcs_read64(GUEST_PHYSICAL_ADDRESS);
}
- vcpu->run->internal.data[vcpu->run->internal.ndata++] =
- vcpu->arch.last_vmentry_cpu;
+ vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu;
+ vcpu->run->internal.ndata = ndata;
return 0;
}
@@ -6580,8 +6580,8 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
int i, nr_msrs;
struct perf_guest_switch_msr *msrs;
+ /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */
msrs = perf_guest_get_msrs(&nr_msrs);
-
if (!msrs)
return;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2a20ce60152e..eca63625aee4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -271,8 +271,7 @@ static struct kmem_cache *x86_emulator_cache;
* When called, it means the previous get/set msr reached an invalid msr.
* Return true if we want to ignore/silent this failed msr access.
*/
-static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
- u64 data, bool write)
+static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write)
{
const char *op = write ? "wrmsr" : "rdmsr";
@@ -1445,7 +1444,7 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
if (r == KVM_MSR_RET_INVALID) {
/* Unconditionally clear the output for simplicity */
*data = 0;
- if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ if (kvm_msr_ignored_check(index, 0, false))
r = 0;
}
@@ -1526,35 +1525,44 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
{
+ struct kvm_x86_msr_filter *msr_filter;
+ struct msr_bitmap_range *ranges;
struct kvm *kvm = vcpu->kvm;
- struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
- u32 count = kvm->arch.msr_filter.count;
- u32 i;
- bool r = kvm->arch.msr_filter.default_allow;
+ bool allowed;
int idx;
+ u32 i;
- /* MSR filtering not set up or x2APIC enabled, allow everything */
- if (!count || (index >= 0x800 && index <= 0x8ff))
+ /* x2APIC MSRs do not support filtering. */
+ if (index >= 0x800 && index <= 0x8ff)
return true;
- /* Prevent collision with set_msr_filter */
idx = srcu_read_lock(&kvm->srcu);
- for (i = 0; i < count; i++) {
+ msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu);
+ if (!msr_filter) {
+ allowed = true;
+ goto out;
+ }
+
+ allowed = msr_filter->default_allow;
+ ranges = msr_filter->ranges;
+
+ for (i = 0; i < msr_filter->count; i++) {
u32 start = ranges[i].base;
u32 end = start + ranges[i].nmsrs;
u32 flags = ranges[i].flags;
unsigned long *bitmap = ranges[i].bitmap;
if ((index >= start) && (index < end) && (flags & type)) {
- r = !!test_bit(index - start, bitmap);
+ allowed = !!test_bit(index - start, bitmap);
break;
}
}
+out:
srcu_read_unlock(&kvm->srcu, idx);
- return r;
+ return allowed;
}
EXPORT_SYMBOL_GPL(kvm_msr_allowed);
@@ -1611,7 +1619,7 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
if (ret == KVM_MSR_RET_INVALID)
- if (kvm_msr_ignored_check(vcpu, index, data, true))
+ if (kvm_msr_ignored_check(index, data, true))
ret = 0;
return ret;
@@ -1649,7 +1657,7 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
if (ret == KVM_MSR_RET_INVALID) {
/* Unconditionally clear *data for simplicity */
*data = 0;
- if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ if (kvm_msr_ignored_check(index, 0, false))
ret = 0;
}
@@ -2320,7 +2328,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
- spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
+ spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
if (!matched) {
kvm->arch.nr_vcpus_matched_tsc = 0;
} else if (!already_matched) {
@@ -2328,7 +2336,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
}
kvm_track_tsc_matching(vcpu);
- spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
}
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2550,11 +2558,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
int i;
struct kvm_vcpu *vcpu;
struct kvm_arch *ka = &kvm->arch;
+ unsigned long flags;
+
+ kvm_hv_invalidate_tsc_page(kvm);
- spin_lock(&ka->pvclock_gtod_sync_lock);
kvm_make_mclock_inprogress_request(kvm);
+
/* no guest entries from this point */
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2562,8 +2575,6 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
/* guest entries allowed */
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
- spin_unlock(&ka->pvclock_gtod_sync_lock);
#endif
}
@@ -2571,17 +2582,18 @@ u64 get_kvmclock_ns(struct kvm *kvm)
{
struct kvm_arch *ka = &kvm->arch;
struct pvclock_vcpu_time_info hv_clock;
+ unsigned long flags;
u64 ret;
- spin_lock(&ka->pvclock_gtod_sync_lock);
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
if (!ka->use_master_clock) {
- spin_unlock(&ka->pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
return get_kvmclock_base_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
- spin_unlock(&ka->pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
@@ -2675,13 +2687,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
*/
- spin_lock(&ka->pvclock_gtod_sync_lock);
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
use_master_clock = ka->use_master_clock;
if (use_master_clock) {
host_tsc = ka->master_cycle_now;
kernel_ns = ka->master_kernel_ns;
}
- spin_unlock(&ka->pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
@@ -5352,25 +5364,34 @@ split_irqchip_unlock:
return r;
}
-static void kvm_clear_msr_filter(struct kvm *kvm)
+static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow)
+{
+ struct kvm_x86_msr_filter *msr_filter;
+
+ msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT);
+ if (!msr_filter)
+ return NULL;
+
+ msr_filter->default_allow = default_allow;
+ return msr_filter;
+}
+
+static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter)
{
u32 i;
- u32 count = kvm->arch.msr_filter.count;
- struct msr_bitmap_range ranges[16];
- mutex_lock(&kvm->lock);
- kvm->arch.msr_filter.count = 0;
- memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0]));
- mutex_unlock(&kvm->lock);
- synchronize_srcu(&kvm->srcu);
+ if (!msr_filter)
+ return;
+
+ for (i = 0; i < msr_filter->count; i++)
+ kfree(msr_filter->ranges[i].bitmap);
- for (i = 0; i < count; i++)
- kfree(ranges[i].bitmap);
+ kfree(msr_filter);
}
-static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range)
+static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
+ struct kvm_msr_filter_range *user_range)
{
- struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
struct msr_bitmap_range range;
unsigned long *bitmap = NULL;
size_t bitmap_size;
@@ -5404,11 +5425,9 @@ static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user
goto err;
}
- /* Everything ok, add this range identifier to our global pool */
- ranges[kvm->arch.msr_filter.count] = range;
- /* Make sure we filled the array before we tell anyone to walk it */
- smp_wmb();
- kvm->arch.msr_filter.count++;
+ /* Everything ok, add this range identifier. */
+ msr_filter->ranges[msr_filter->count] = range;
+ msr_filter->count++;
return 0;
err:
@@ -5419,10 +5438,11 @@ err:
static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
{
struct kvm_msr_filter __user *user_msr_filter = argp;
+ struct kvm_x86_msr_filter *new_filter, *old_filter;
struct kvm_msr_filter filter;
bool default_allow;
- int r = 0;
bool empty = true;
+ int r = 0;
u32 i;
if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
@@ -5435,25 +5455,32 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
if (empty && !default_allow)
return -EINVAL;
- kvm_clear_msr_filter(kvm);
-
- kvm->arch.msr_filter.default_allow = default_allow;
+ new_filter = kvm_alloc_msr_filter(default_allow);
+ if (!new_filter)
+ return -ENOMEM;
- /*
- * Protect from concurrent calls to this function that could trigger
- * a TOCTOU violation on kvm->arch.msr_filter.count.
- */
- mutex_lock(&kvm->lock);
for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
- r = kvm_add_msr_filter(kvm, &filter.ranges[i]);
- if (r)
- break;
+ r = kvm_add_msr_filter(new_filter, &filter.ranges[i]);
+ if (r) {
+ kvm_free_msr_filter(new_filter);
+ return r;
+ }
}
+ mutex_lock(&kvm->lock);
+
+ /* The per-VM filter is protected by kvm->lock... */
+ old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1);
+
+ rcu_assign_pointer(kvm->arch.msr_filter, new_filter);
+ synchronize_srcu(&kvm->srcu);
+
+ kvm_free_msr_filter(old_filter);
+
kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
mutex_unlock(&kvm->lock);
- return r;
+ return 0;
}
long kvm_arch_vm_ioctl(struct file *filp,
@@ -5700,6 +5727,7 @@ set_pit2_out:
}
#endif
case KVM_SET_CLOCK: {
+ struct kvm_arch *ka = &kvm->arch;
struct kvm_clock_data user_ns;
u64 now_ns;
@@ -5718,8 +5746,22 @@ set_pit2_out:
* pvclock_update_vm_gtod_copy().
*/
kvm_gen_update_masterclock(kvm);
- now_ns = get_kvmclock_ns(kvm);
- kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
+
+ /*
+ * This pairs with kvm_guest_time_update(): when masterclock is
+ * in use, we use master_kernel_ns + kvmclock_offset to set
+ * unsigned 'system_time' so if we use get_kvmclock_ns() (which
+ * is slightly ahead) here we risk going negative on unsigned
+ * 'system_time' when 'user_ns.clock' is very small.
+ */
+ spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+ if (kvm->arch.use_master_clock)
+ now_ns = ka->master_kernel_ns;
+ else
+ now_ns = get_kvmclock_base_ns();
+ ka->kvmclock_offset = user_ns.clock - now_ns;
+ spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+
kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
break;
}
@@ -6603,7 +6645,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
int cpu = get_cpu();
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
- smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
+ on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
wbinvd_ipi, NULL, 1);
put_cpu();
cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
@@ -7698,6 +7740,7 @@ static void kvm_hyperv_tsc_notifier(void)
struct kvm *kvm;
struct kvm_vcpu *vcpu;
int cpu;
+ unsigned long flags;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
@@ -7713,17 +7756,15 @@ static void kvm_hyperv_tsc_notifier(void)
list_for_each_entry(kvm, &vm_list, vm_list) {
struct kvm_arch *ka = &kvm->arch;
- spin_lock(&ka->pvclock_gtod_sync_lock);
-
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
- spin_unlock(&ka->pvclock_gtod_sync_lock);
}
mutex_unlock(&kvm_lock);
}
@@ -10601,7 +10642,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
return (void __user *)hva;
} else {
if (!slot || !slot->npages)
- return 0;
+ return NULL;
old_npages = slot->npages;
hva = slot->userspace_addr;
@@ -10634,8 +10675,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
void kvm_arch_destroy_vm(struct kvm *kvm)
{
- u32 i;
-
if (current->mm == kvm->mm) {
/*
* Free memory regions allocated on behalf of userspace,
@@ -10651,8 +10690,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
mutex_unlock(&kvm->slots_lock);
}
static_call_cond(kvm_x86_vm_destroy)(kvm);
- for (i = 0; i < kvm->arch.msr_filter.count; i++)
- kfree(kvm->arch.msr_filter.ranges[i].bitmap);
+ kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
kvm_pic_destroy(kvm);
kvm_ioapic_destroy(kvm);
kvm_free_vcpus(kvm);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 39eb04887141..9035e34aa156 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -250,7 +250,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs);
void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
-void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
u64 get_kvmclock_ns(struct kvm *kvm);
int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 4229950a5d78..bb0b3fe1e0a0 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -1415,6 +1415,25 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
}
}
+static unsigned long insn_get_effective_ip(struct pt_regs *regs)
+{
+ unsigned long seg_base = 0;
+
+ /*
+ * If not in user-space long mode, a custom code segment could be in
+ * use. This is true in protected mode (if the process defined a local
+ * descriptor table), or virtual-8086 mode. In most of the cases
+ * seg_base will be zero as in USER_CS.
+ */
+ if (!user_64bit_mode(regs)) {
+ seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
+ if (seg_base == -1L)
+ return 0;
+ }
+
+ return seg_base + regs->ip;
+}
+
/**
* insn_fetch_from_user() - Copy instruction bytes from user-space memory
* @regs: Structure with register values as seen when entering kernel mode
@@ -1431,24 +1450,43 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
*/
int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
{
- unsigned long seg_base = 0;
+ unsigned long ip;
int not_copied;
- /*
- * If not in user-space long mode, a custom code segment could be in
- * use. This is true in protected mode (if the process defined a local
- * descriptor table), or virtual-8086 mode. In most of the cases
- * seg_base will be zero as in USER_CS.
- */
- if (!user_64bit_mode(regs)) {
- seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
- if (seg_base == -1L)
- return 0;
- }
+ ip = insn_get_effective_ip(regs);
+ if (!ip)
+ return 0;
+
+ not_copied = copy_from_user(buf, (void __user *)ip, MAX_INSN_SIZE);
+ return MAX_INSN_SIZE - not_copied;
+}
+
+/**
+ * insn_fetch_from_user_inatomic() - Copy instruction bytes from user-space memory
+ * while in atomic code
+ * @regs: Structure with register values as seen when entering kernel mode
+ * @buf: Array to store the fetched instruction
+ *
+ * Gets the linear address of the instruction and copies the instruction bytes
+ * to the buf. This function must be used in atomic context.
+ *
+ * Returns:
+ *
+ * Number of instruction bytes copied.
+ *
+ * 0 if nothing was copied.
+ */
+int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
+{
+ unsigned long ip;
+ int not_copied;
+
+ ip = insn_get_effective_ip(regs);
+ if (!ip)
+ return 0;
- not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip),
- MAX_INSN_SIZE);
+ not_copied = __copy_from_user_inatomic(buf, (void __user *)ip, MAX_INSN_SIZE);
return MAX_INSN_SIZE - not_copied;
}
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 4b01f7dbaf30..ae78cef79980 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -262,7 +262,7 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
if (pgprot_val(old_prot) == pgprot_val(new_prot))
return;
- pa = pfn << page_level_shift(level);
+ pa = pfn << PAGE_SHIFT;
size = page_level_size(level);
/*
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 79e7a0ec1da5..7f1b3a862e14 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1349,6 +1349,7 @@ st: if (is_imm8(insn->off))
insn->imm == (BPF_XOR | BPF_FETCH)) {
u8 *branch_target;
bool is64 = BPF_SIZE(insn->code) == BPF_DW;
+ u32 real_src_reg = src_reg;
/*
* Can't be implemented with a single x86 insn.
@@ -1357,6 +1358,9 @@ st: if (is_imm8(insn->off))
/* Will need RAX as a CMPXCHG operand so save R0 */
emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
+ if (src_reg == BPF_REG_0)
+ real_src_reg = BPF_REG_AX;
+
branch_target = prog;
/* Load old value */
emit_ldx(&prog, BPF_SIZE(insn->code),
@@ -1366,9 +1370,9 @@ st: if (is_imm8(insn->off))
* put the result in the AUX_REG.
*/
emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
- maybe_emit_mod(&prog, AUX_REG, src_reg, is64);
+ maybe_emit_mod(&prog, AUX_REG, real_src_reg, is64);
EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
- add_2reg(0xC0, AUX_REG, src_reg));
+ add_2reg(0xC0, AUX_REG, real_src_reg));
/* Attempt to swap in new value */
err = emit_atomic(&prog, BPF_CMPXCHG,
dst_reg, AUX_REG, insn->off,
@@ -1381,7 +1385,7 @@ st: if (is_imm8(insn->off))
*/
EMIT2(X86_JNE, -(prog - branch_target) - 2);
/* Return the pre-modification value */
- emit_mov_reg(&prog, is64, src_reg, BPF_REG_0);
+ emit_mov_reg(&prog, is64, real_src_reg, BPF_REG_0);
/* Restore R0 after clobbering RAX */
emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
break;
@@ -1685,7 +1689,16 @@ emit_jmp:
}
if (image) {
- if (unlikely(proglen + ilen > oldproglen)) {
+ /*
+ * When populating the image, assert that:
+ *
+ * i) We do not write beyond the allocated space, and
+ * ii) addrs[i] did not change from the prior run, in order
+ * to validate assumptions made for computing branch
+ * displacements.
+ */
+ if (unlikely(proglen + ilen > oldproglen ||
+ proglen + ilen != addrs[i])) {
pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
@@ -1932,7 +1945,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
* add rsp, 8 // skip eth_type_trans's frame
* ret // return to its caller
*/
-int arch_prepare_bpf_trampoline(void *image, void *image_end,
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_progs *tprogs,
void *orig_call)
@@ -1971,6 +1984,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
save_regs(m, &prog, nr_args, stack_size);
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ /* arg1: mov rdi, im */
+ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+ if (emit_call(&prog, __bpf_tramp_enter, prog)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
+ }
+
if (fentry->nr_progs)
if (invoke_bpf(m, &prog, fentry, stack_size))
return -EINVAL;
@@ -1989,8 +2011,7 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
}
if (flags & BPF_TRAMP_F_CALL_ORIG) {
- if (fentry->nr_progs || fmod_ret->nr_progs)
- restore_regs(m, &prog, nr_args, stack_size);
+ restore_regs(m, &prog, nr_args, stack_size);
/* call original function */
if (emit_call(&prog, orig_call, prog)) {
@@ -1999,6 +2020,9 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
}
/* remember return value in a stack for bpf prog to access */
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+ im->ip_after_call = prog;
+ memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+ prog += X86_PATCH_SIZE;
}
if (fmod_ret->nr_progs) {
@@ -2029,9 +2053,17 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
* the return value is only updated on the stack and still needs to be
* restored to R0.
*/
- if (flags & BPF_TRAMP_F_CALL_ORIG)
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ im->ip_epilogue = prog;
+ /* arg1: mov rdi, im */
+ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+ if (emit_call(&prog, __bpf_tramp_exit, prog)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
/* restore original return value back into RAX */
emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
+ }
EMIT1(0x5B); /* pop rbx */
EMIT1(0xC9); /* leave */
@@ -2221,7 +2253,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
padding = true;
goto skip_init_addrs;
}
- addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
+ addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
if (!addrs) {
prog = orig_prog;
goto out_addrs;
@@ -2313,7 +2345,7 @@ out_image:
if (image)
bpf_prog_fill_jited_linfo(prog, addrs + 1);
out_addrs:
- kfree(addrs);
+ kvfree(addrs);
kfree(jit_data);
prog->aux->jit_data = NULL;
}
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index d17b67c69f89..6a99def7d315 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -2276,7 +2276,16 @@ notyet:
}
if (image) {
- if (unlikely(proglen + ilen > oldproglen)) {
+ /*
+ * When populating the image, assert that:
+ *
+ * i) We do not write beyond the allocated space, and
+ * ii) addrs[i] did not change from the prior run, in order
+ * to validate assumptions made for computing branch
+ * displacements.
+ */
+ if (unlikely(proglen + ilen > oldproglen ||
+ proglen + ilen != addrs[i])) {
pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c
index 1ac8578258af..b42bfdab01a9 100644
--- a/arch/x86/platform/iris/iris.c
+++ b/arch/x86/platform/iris/iris.c
@@ -27,7 +27,6 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Sébastien Hinderer <Sebastien.Hinderer@ens-lyon.org>");
MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille");
-MODULE_SUPPORTED_DEVICE("Eurobraille/Iris");
static bool force;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index a3cc33091f46..ac06ca32e9ef 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -98,8 +98,8 @@ EXPORT_SYMBOL_GPL(xen_p2m_size);
unsigned long xen_max_p2m_pfn __read_mostly;
EXPORT_SYMBOL_GPL(xen_max_p2m_pfn);
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
-#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+#ifdef CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
+#define P2M_LIMIT CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
#else
#define P2M_LIMIT 0
#endif
@@ -416,9 +416,6 @@ void __init xen_vmalloc_p2m_tree(void)
xen_p2m_last_pfn = xen_max_p2m_pfn;
p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
- if (!p2m_limit && IS_ENABLED(CONFIG_XEN_UNPOPULATED_ALLOC))
- p2m_limit = xen_start_info->nr_pages * XEN_EXTRA_MEM_RATIO;
-
vm.flags = VM_ALLOC;
vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
PMD_SIZE * PMDS_PER_MID_PAGE);
@@ -741,7 +738,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
map_ops[i].status = GNTST_general_error;
unmap[0].host_addr = map_ops[i].host_addr,
unmap[0].handle = map_ops[i].handle;
- map_ops[i].handle = ~0;
+ map_ops[i].handle = INVALID_GRANT_HANDLE;
if (map_ops[i].flags & GNTMAP_device_map)
unmap[0].dev_bus_addr = map_ops[i].dev_bus_addr;
else
@@ -751,7 +748,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
kmap_ops[i].status = GNTST_general_error;
unmap[1].host_addr = kmap_ops[i].host_addr,
unmap[1].handle = kmap_ops[i].handle;
- kmap_ops[i].handle = ~0;
+ kmap_ops[i].handle = INVALID_GRANT_HANDLE;
if (kmap_ops[i].flags & GNTMAP_device_map)
unmap[1].dev_bus_addr = kmap_ops[i].dev_bus_addr;
else
@@ -776,7 +773,6 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
out:
return ret;
}
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_unmap_grant_ref *kunmap_ops,
@@ -802,7 +798,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
return ret;
}
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
#ifdef CONFIG_XEN_DEBUG_FS
#include <linux/debugfs.h>
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1a3b75652fa4..8bfc10330107 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -59,6 +59,18 @@ static struct {
} xen_remap_buf __initdata __aligned(PAGE_SIZE);
static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
+/*
+ * The maximum amount of extra memory compared to the base size. The
+ * main scaling factor is the size of struct page. At extreme ratios
+ * of base:extra, all the base memory can be filled with page
+ * structures for the extra memory, leaving no space for anything
+ * else.
+ *
+ * 10x seems like a reasonable balance between scaling flexibility and
+ * leaving a practically usable system.
+ */
+#define EXTRA_MEM_RATIO (10)
+
static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
static void __init xen_parse_512gb(void)
@@ -778,13 +790,13 @@ char * __init xen_memory_setup(void)
extra_pages += max_pages - max_pfn;
/*
- * Clamp the amount of extra memory to a XEN_EXTRA_MEM_RATIO
+ * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size.
*
* Make sure we have no memory above max_pages, as this area
* isn't handled by the p2m management.
*/
- extra_pages = min3(XEN_EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+ extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages, max_pages - max_pfn);
i = 0;
addr = xen_e820_table.entries[0].addr;
diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S
index c426b846beef..45cc0ae0af6f 100644
--- a/arch/xtensa/kernel/coprocessor.S
+++ b/arch/xtensa/kernel/coprocessor.S
@@ -100,37 +100,6 @@
LOAD_CP_REGS_TAB(7)
/*
- * coprocessor_flush(struct thread_info*, index)
- * a2 a3
- *
- * Save coprocessor registers for coprocessor 'index'.
- * The register values are saved to or loaded from the coprocessor area
- * inside the task_info structure.
- *
- * Note that this function doesn't update the coprocessor_owner information!
- *
- */
-
-ENTRY(coprocessor_flush)
-
- /* reserve 4 bytes on stack to save a0 */
- abi_entry(4)
-
- s32i a0, a1, 0
- movi a0, .Lsave_cp_regs_jump_table
- addx8 a3, a3, a0
- l32i a4, a3, 4
- l32i a3, a3, 0
- add a2, a2, a4
- beqz a3, 1f
- callx0 a3
-1: l32i a0, a1, 0
-
- abi_ret(4)
-
-ENDPROC(coprocessor_flush)
-
-/*
* Entry condition:
*
* a0: trashed, original value saved on stack (PT_AREG0)
@@ -245,6 +214,39 @@ ENTRY(fast_coprocessor)
ENDPROC(fast_coprocessor)
+ .text
+
+/*
+ * coprocessor_flush(struct thread_info*, index)
+ * a2 a3
+ *
+ * Save coprocessor registers for coprocessor 'index'.
+ * The register values are saved to or loaded from the coprocessor area
+ * inside the task_info structure.
+ *
+ * Note that this function doesn't update the coprocessor_owner information!
+ *
+ */
+
+ENTRY(coprocessor_flush)
+
+ /* reserve 4 bytes on stack to save a0 */
+ abi_entry(4)
+
+ s32i a0, a1, 0
+ movi a0, .Lsave_cp_regs_jump_table
+ addx8 a3, a3, a0
+ l32i a4, a3, 4
+ l32i a3, a3, 0
+ add a2, a2, a4
+ beqz a3, 1f
+ callx0 a3
+1: l32i a0, a1, 0
+
+ abi_ret(4)
+
+ENDPROC(coprocessor_flush)
+
.data
ENTRY(coprocessor_owner)
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 7666408ce12a..95a74890c7e9 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -112,8 +112,11 @@ good_area:
*/
fault = handle_mm_fault(vma, address, flags, regs);
- if (fault_signal_pending(fault, regs))
+ if (fault_signal_pending(fault, regs)) {
+ if (!user_mode(regs))
+ goto bad_page_fault;
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)