diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2023-03-09 22:18:59 -0800 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2023-03-09 22:22:11 -0800 |
| commit | d0ddf5065ffef45f8fce4001abe0206081c7ff10 (patch) | |
| tree | ea83817cbe9fc25261eae87b85afd9fe086f479e /arch | |
| parent | db47fa2e4cbf180a39d8e6d6170962bd7d82e52d (diff) | |
| parent | 44889ba56cbb3d51154660ccd15818bc77276696 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Documentation/bpf/bpf_devel_QA.rst
b7abcd9c656b ("bpf, doc: Link to submitting-patches.rst for general patch submission info")
d56b0c461d19 ("bpf, docs: Fix link to netdev-FAQ target")
https://lore.kernel.org/all/20230307095812.236eb1be@canb.auug.org.au/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'arch')
131 files changed, 3216 insertions, 641 deletions
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ef427a6bdd1a..7b01ae4f3bc6 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -152,8 +152,11 @@ retry: the fault. */ 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 no_context; return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 27b2592698b0..1023e896d46b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -100,7 +100,6 @@ config ARM64 select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) - select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_NO_INSTR select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES @@ -187,7 +186,8 @@ config ARM64 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ - if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG) + if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \ + !CC_OPTIMIZE_FOR_SIZE) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 9dd08cd339c3..78e5163836a0 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -180,6 +180,7 @@ #include <linux/compiler.h> #include <linux/mmdebug.h> #include <linux/types.h> +#include <asm/boot.h> #include <asm/bug.h> #if VA_BITS > 48 @@ -203,6 +204,16 @@ static inline unsigned long kaslr_offset(void) return kimage_vaddr - KIMAGE_VADDR; } +static inline bool kaslr_enabled(void) +{ + /* + * The KASLR offset modulo MIN_KIMG_ALIGN is taken from the physical + * placement of the image rather than from the seed, so a displacement + * of less than MIN_KIMG_ALIGN means that no seed was provided. + */ + return kaslr_offset() >= MIN_KIMG_ALIGN; +} + /* * Allow all memory at the discovery stage. We will clip it later. */ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 378453faa87e..dba8fcec7f33 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -435,10 +435,6 @@ int acpi_ffh_address_space_arch_setup(void *handler_ctxt, void **region_ctxt) enum arm_smccc_conduit conduit; struct acpi_ffh_data *ffh_ctxt; - ffh_ctxt = kzalloc(sizeof(*ffh_ctxt), GFP_KERNEL); - if (!ffh_ctxt) - return -ENOMEM; - if (arm_smccc_get_version() < ARM_SMCCC_VERSION_1_2) return -EOPNOTSUPP; @@ -448,6 +444,10 @@ int acpi_ffh_address_space_arch_setup(void *handler_ctxt, void **region_ctxt) return -EOPNOTSUPP; } + ffh_ctxt = kzalloc(sizeof(*ffh_ctxt), GFP_KERNEL); + if (!ffh_ctxt) + return -ENOMEM; + if (conduit == SMCCC_CONDUIT_SMC) { ffh_ctxt->invoke_ffh_fn = __arm_smccc_smc; ffh_ctxt->invoke_ffh64_fn = arm_smccc_1_2_smc; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 87687e99fee3..2e3e55139777 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1633,7 +1633,7 @@ bool kaslr_requires_kpti(void) return false; } - return kaslr_offset() > 0; + return kaslr_enabled(); } static bool __meltdown_safe = true; diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 692dfefbe0ed..9e7e50a0fd76 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -2122,9 +2122,6 @@ static int __init fpsimd_init(void) pr_notice("Advanced SIMD is not implemented\n"); - if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE)) - pr_notice("SME is implemented but not SVE\n"); - sve_sysctl_init(); sme_sysctl_init(); diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 325455d16dbc..e7477f21a4c9 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -41,7 +41,7 @@ static int __init kaslr_init(void) return 0; } - if (!kaslr_offset()) { + if (!kaslr_enabled()) { pr_warn("KASLR disabled due to lack of seed\n"); return 0; } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 901dfd9bf04c..4a79ba100799 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -997,7 +997,7 @@ static int cfi_handler(struct pt_regs *regs, unsigned long esr) switch (report_cfi_failure(regs, regs->pc, &target, type)) { case BUG_TRAP_TYPE_BUG: - die("Oops - CFI", regs, 0); + die("Oops - CFI", regs, esr); break; case BUG_TRAP_TYPE_WARN: diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 8dd5a8fe64b4..4aadcfb01754 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -22,7 +22,8 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); if (system_supports_mte() && page_mte_tagged(from)) { - page_kasan_tag_reset(to); + if (kasan_hw_tags_enabled()) + page_kasan_tag_reset(to); /* It's a new page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index f73c7cbfe326..4b578d02fd01 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -93,8 +93,11 @@ 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 no_context; return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index ca2e02685343..259ae57570bf 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -15,11 +15,7 @@ #include <linux/types.h> /* include compiler specific intrinsics */ #include <asm/ia64regs.h> -#ifdef __INTEL_COMPILER -# include <asm/intel_intrin.h> -#else -# include <asm/gcc_intrin.h> -#endif +#include <asm/gcc_intrin.h> /* * This function doesn't exist, so you'll get a linker error if diff --git a/arch/ia64/include/uapi/asm/intel_intrin.h b/arch/ia64/include/uapi/asm/intel_intrin.h deleted file mode 100644 index dc1884dc54b5..000000000000 --- a/arch/ia64/include/uapi/asm/intel_intrin.h +++ /dev/null @@ -1,162 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _ASM_IA64_INTEL_INTRIN_H -#define _ASM_IA64_INTEL_INTRIN_H -/* - * Intel Compiler Intrinsics - * - * Copyright (C) 2002,2003 Jun Nakajima <jun.nakajima@intel.com> - * Copyright (C) 2002,2003 Suresh Siddha <suresh.b.siddha@intel.com> - * Copyright (C) 2005,2006 Hongjiu Lu <hongjiu.lu@intel.com> - * - */ -#include <ia64intrin.h> - -#define ia64_barrier() __memory_barrier() - -#define ia64_stop() /* Nothing: As of now stop bit is generated for each - * intrinsic - */ - -#define ia64_getreg __getReg -#define ia64_setreg __setReg - -#define ia64_hint __hint -#define ia64_hint_pause __hint_pause - -#define ia64_mux1_brcst _m64_mux1_brcst -#define ia64_mux1_mix _m64_mux1_mix -#define ia64_mux1_shuf _m64_mux1_shuf -#define ia64_mux1_alt _m64_mux1_alt -#define ia64_mux1_rev _m64_mux1_rev - -#define ia64_mux1(x,v) _m_to_int64(_m64_mux1(_m_from_int64(x), (v))) -#define ia64_popcnt _m64_popcnt -#define ia64_getf_exp __getf_exp -#define ia64_shrp _m64_shrp - -#define ia64_tpa __tpa -#define ia64_invala __invala -#define ia64_invala_gr __invala_gr -#define ia64_invala_fr __invala_fr -#define ia64_nop __nop -#define ia64_sum __sum -#define ia64_ssm __ssm -#define ia64_rum __rum -#define ia64_rsm __rsm -#define ia64_fc __fc - -#define ia64_ldfs __ldfs -#define ia64_ldfd __ldfd -#define ia64_ldfe __ldfe -#define ia64_ldf8 __ldf8 -#define ia64_ldf_fill __ldf_fill - -#define ia64_stfs __stfs -#define ia64_stfd __stfd -#define ia64_stfe __stfe -#define ia64_stf8 __stf8 -#define ia64_stf_spill __stf_spill - -#define ia64_mf __mf -#define ia64_mfa __mfa - -#define ia64_fetchadd4_acq __fetchadd4_acq -#define ia64_fetchadd4_rel __fetchadd4_rel -#define ia64_fetchadd8_acq __fetchadd8_acq -#define ia64_fetchadd8_rel __fetchadd8_rel - -#define ia64_xchg1 _InterlockedExchange8 -#define ia64_xchg2 _InterlockedExchange16 -#define ia64_xchg4 _InterlockedExchange -#define ia64_xchg8 _InterlockedExchange64 - -#define ia64_cmpxchg1_rel _InterlockedCompareExchange8_rel -#define ia64_cmpxchg1_acq _InterlockedCompareExchange8_acq -#define ia64_cmpxchg2_rel _InterlockedCompareExchange16_rel -#define ia64_cmpxchg2_acq _InterlockedCompareExchange16_acq -#define ia64_cmpxchg4_rel _InterlockedCompareExchange_rel -#define ia64_cmpxchg4_acq _InterlockedCompareExchange_acq -#define ia64_cmpxchg8_rel _InterlockedCompareExchange64_rel -#define ia64_cmpxchg8_acq _InterlockedCompareExchange64_acq - -#define __ia64_set_dbr(index, val) \ - __setIndReg(_IA64_REG_INDR_DBR, index, val) -#define ia64_set_ibr(index, val) \ - __setIndReg(_IA64_REG_INDR_IBR, index, val) -#define ia64_set_pkr(index, val) \ - __setIndReg(_IA64_REG_INDR_PKR, index, val) -#define ia64_set_pmc(index, val) \ - __setIndReg(_IA64_REG_INDR_PMC, index, val) -#define ia64_set_pmd(index, val) \ - __setIndReg(_IA64_REG_INDR_PMD, index, val) -#define ia64_set_rr(index, val) \ - __setIndReg(_IA64_REG_INDR_RR, index, val) - -#define ia64_get_cpuid(index) \ - __getIndReg(_IA64_REG_INDR_CPUID, index) -#define __ia64_get_dbr(index) __getIndReg(_IA64_REG_INDR_DBR, index) -#define ia64_get_ibr(index) __getIndReg(_IA64_REG_INDR_IBR, index) -#define ia64_get_pkr(index) __getIndReg(_IA64_REG_INDR_PKR, index) -#define ia64_get_pmc(index) __getIndReg(_IA64_REG_INDR_PMC, index) -#define ia64_get_pmd(index) __getIndReg(_IA64_REG_INDR_PMD, index) -#define ia64_get_rr(index) __getIndReg(_IA64_REG_INDR_RR, index) - -#define ia64_srlz_d __dsrlz -#define ia64_srlz_i __isrlz - -#define ia64_dv_serialize_data() -#define ia64_dv_serialize_instruction() - -#define ia64_st1_rel __st1_rel -#define ia64_st2_rel __st2_rel -#define ia64_st4_rel __st4_rel -#define ia64_st8_rel __st8_rel - -/* FIXME: need st4.rel.nta intrinsic */ -#define ia64_st4_rel_nta __st4_rel - -#define ia64_ld1_acq __ld1_acq -#define ia64_ld2_acq __ld2_acq -#define ia64_ld4_acq __ld4_acq -#define ia64_ld8_acq __ld8_acq - -#define ia64_sync_i __synci -#define ia64_thash __thash -#define ia64_ttag __ttag -#define ia64_itcd __itcd -#define ia64_itci __itci -#define ia64_itrd __itrd -#define ia64_itri __itri -#define ia64_ptce __ptce -#define ia64_ptcl __ptcl -#define ia64_ptcg __ptcg -#define ia64_ptcga __ptcga -#define ia64_ptri __ptri -#define ia64_ptrd __ptrd -#define ia64_dep_mi _m64_dep_mi - -/* Values for lfhint in __lfetch and __lfetch_fault */ - -#define ia64_lfhint_none __lfhint_none -#define ia64_lfhint_nt1 __lfhint_nt1 -#define ia64_lfhint_nt2 __lfhint_nt2 -#define ia64_lfhint_nta __lfhint_nta - -#define ia64_lfetch __lfetch -#define ia64_lfetch_excl __lfetch_excl -#define ia64_lfetch_fault __lfetch_fault -#define ia64_lfetch_fault_excl __lfetch_fault_excl - -#define ia64_intrin_local_irq_restore(x) \ -do { \ - if ((x) != 0) { \ - ia64_ssm(IA64_PSR_I); \ - ia64_srlz_d(); \ - } else { \ - ia64_rsm(IA64_PSR_I); \ - } \ -} while (0) - -#define __builtin_trap() __break(0); - -#endif /* _ASM_IA64_INTEL_INTRIN_H */ diff --git a/arch/ia64/include/uapi/asm/intrinsics.h b/arch/ia64/include/uapi/asm/intrinsics.h index a0e0a064f5b1..63f27c4ec739 100644 --- a/arch/ia64/include/uapi/asm/intrinsics.h +++ b/arch/ia64/include/uapi/asm/intrinsics.h @@ -14,11 +14,7 @@ #include <linux/types.h> /* include compiler specific intrinsics */ #include <asm/ia64regs.h> -#ifdef __INTEL_COMPILER -# include <asm/intel_intrin.h> -#else -# include <asm/gcc_intrin.h> -#endif +#include <asm/gcc_intrin.h> #include <asm/cmpxchg.h> #define ia64_set_rr0_to_rr4(val0, val1, val2, val3, val4) \ diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 96d13cb7c19f..15f6cfddcc08 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -783,11 +783,9 @@ __init void prefill_possible_map(void) static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) { - cpumask_t tmp_map; int cpu; - cpumask_complement(&tmp_map, cpu_present_mask); - cpu = cpumask_first(&tmp_map); + cpu = cpumask_first_zero(cpu_present_mask); if (cpu >= nr_cpu_ids) return -EINVAL; diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index ef78c2d66cdd..85c4d9ac8686 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -136,8 +136,11 @@ retry: */ 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 no_context; return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 9cc8b84f7eb0..7fd51257e0ed 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -94,15 +94,21 @@ config LOONGARCH select HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT + select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GENERIC_VDSO + select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_KPROBES + select HAVE_KPROBES_ON_FTRACE + select HAVE_KRETPROBES select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_PCI @@ -441,6 +447,24 @@ config ARCH_IOREMAP protection support. However, you can enable LoongArch DMW-based ioremap() for better performance. +config ARCH_STRICT_ALIGN + bool "Enable -mstrict-align to prevent unaligned accesses" if EXPERT + default y + help + Not all LoongArch cores support h/w unaligned access, we can use + -mstrict-align build parameter to prevent unaligned accesses. + + CPUs with h/w unaligned access support: + Loongson-2K2000/2K3000/3A5000/3C5000/3D5000. + + CPUs without h/w unaligned access support: + Loongson-2K500/2K1000. + + This option is enabled by default to make the kernel be able to run + on all LoongArch systems. But you can disable it manually if you want + to run kernel only on systems with h/w unaligned access support in + order to optimise for performance. + config KEXEC bool "Kexec system call" select KEXEC_CORE @@ -454,6 +478,7 @@ config KEXEC config CRASH_DUMP bool "Build kdump crash kernel" + select RELOCATABLE help Generate crash dump after being started by kexec. This should be normally only set in special crash dump kernels which are @@ -463,16 +488,38 @@ config CRASH_DUMP For more details see Documentation/admin-guide/kdump/kdump.rst -config PHYSICAL_START - hex "Physical address where the kernel is loaded" - default "0x90000000a0000000" - depends on CRASH_DUMP +config RELOCATABLE + bool "Relocatable kernel" help - This gives the XKPRANGE address where the kernel is loaded. - If you plan to use kernel for capturing the crash dump change - this value to start of the reserved region (the "X" value as - specified in the "crashkernel=YM@XM" command line boot parameter - passed to the panic-ed kernel). + This builds the kernel as a Position Independent Executable (PIE), + which retains all relocation metadata required, so as to relocate + the kernel binary at runtime to a different virtual address from + its link address. + +config RANDOMIZE_BASE + bool "Randomize the address of the kernel (KASLR)" + depends on RELOCATABLE + help + Randomizes the physical and virtual address at which the + kernel image is loaded, as a security feature that + deters exploit attempts relying on knowledge of the location + of kernel internals. + + The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET. + + If unsure, say N. + +config RANDOMIZE_BASE_MAX_OFFSET + hex "Maximum KASLR offset" if EXPERT + depends on RANDOMIZE_BASE + range 0x0 0x10000000 + default "0x01000000" + help + When KASLR is active, this provides the maximum offset that will + be applied to the kernel image. It should be set according to the + amount of physical RAM available in the target system. + + This is limited by the size of the lower address memory, 256MB. config SECCOMP bool "Enable seccomp to safely compute untrusted bytecode" diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 4402387d2755..f71edf574101 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -71,14 +71,15 @@ KBUILD_AFLAGS_MODULE += -Wa,-mla-global-with-abs KBUILD_CFLAGS_MODULE += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs endif +ifeq ($(CONFIG_RELOCATABLE),y) +KBUILD_CFLAGS_KERNEL += -fPIE +LDFLAGS_vmlinux += -static -pie --no-dynamic-linker -z notext +endif + cflags-y += -ffreestanding cflags-y += $(call cc-option, -mno-check-zero-division) -ifndef CONFIG_PHYSICAL_START load-y = 0x9000000000200000 -else -load-y = $(CONFIG_PHYSICAL_START) -endif bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) drivers-$(CONFIG_PCI) += arch/loongarch/pci/ @@ -91,10 +92,15 @@ KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y) # instead of .eh_frame so we don't discard them. KBUILD_CFLAGS += -fno-asynchronous-unwind-tables +ifdef CONFIG_ARCH_STRICT_ALIGN # Don't emit unaligned accesses. # Not all LoongArch cores support unaligned access, and as kernel we can't # rely on others to provide emulation for these accesses. KBUILD_CFLAGS += $(call cc-option,-mstrict-align) +else +# Optimise for performance on hardware supports unaligned access. +KBUILD_CFLAGS += $(call cc-option,-mno-strict-align) +endif KBUILD_CFLAGS += -isystem $(shell $(CC) -print-file-name=include) diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index eb84cae642e5..e18213f01cc4 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -48,6 +48,7 @@ CONFIG_HOTPLUG_CPU=y CONFIG_NR_CPUS=64 CONFIG_NUMA=y CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y CONFIG_SUSPEND=y CONFIG_HIBERNATION=y CONFIG_ACPI=y diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index d342935e5a72..8fb699b4d40a 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -125,4 +125,6 @@ extern unsigned long vm_map_base; #define ISA_IOSIZE SZ_16K #define IO_SPACE_LIMIT (PCI_IOSIZE - 1) +#define PHYS_LINK_KADDR PHYSADDR(VMLINUX_LOAD_ADDRESS) + #endif /* _ASM_ADDRSPACE_H */ diff --git a/arch/loongarch/include/asm/asm.h b/arch/loongarch/include/asm/asm.h index 40eea6aa469e..f591b3245def 100644 --- a/arch/loongarch/include/asm/asm.h +++ b/arch/loongarch/include/asm/asm.h @@ -188,4 +188,14 @@ #define PTRLOG 3 #endif +/* Annotate a function as being unsuitable for kprobes. */ +#ifdef CONFIG_KPROBES +#define _ASM_NOKPROBE(name) \ + .pushsection "_kprobe_blacklist", "aw"; \ + .quad name; \ + .popsection +#else +#define _ASM_NOKPROBE(name) +#endif + #endif /* __ASM_ASM_H */ diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index be037a40580d..c51a1b43acb4 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -274,4 +274,21 @@ nor \dst, \src, zero .endm +.macro la_abs reg, sym +#ifndef CONFIG_RELOCATABLE + la.abs \reg, \sym +#else + 766: + lu12i.w \reg, 0 + ori \reg, \reg, 0 + lu32i.d \reg, 0 + lu52i.d \reg, \reg, 0 + .pushsection ".la_abs", "aw", %progbits + 768: + .dword 768b-766b + .dword \sym + .popsection +#endif +.endm + #endif /* _ASM_ASMMACRO_H */ diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index 754f28506791..c3da91759472 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -36,7 +36,7 @@ #define PRID_SERIES_LA132 0x8000 /* Loongson 32bit */ #define PRID_SERIES_LA264 0xa000 /* Loongson 64bit, 2-issue */ -#define PRID_SERIES_LA364 0xb000 /* Loongson 64bit，3-issue */ +#define PRID_SERIES_LA364 0xb000 /* Loongson 64bit, 3-issue */ #define PRID_SERIES_LA464 0xc000 /* Loongson 64bit, 4-issue */ #define PRID_SERIES_LA664 0xd000 /* Loongson 64bit, 6-issue */ diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h new file mode 100644 index 000000000000..21447fb1efc7 --- /dev/null +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2023 Loongson Technology Corporation Limited + */ +#ifndef __ASM_HW_BREAKPOINT_H +#define __ASM_HW_BREAKPOINT_H + +#include <asm/loongarch.h> + +#ifdef __KERNEL__ + +/* Breakpoint */ +#define LOONGARCH_BREAKPOINT_EXECUTE (0 << 0) + +/* Watchpoints */ +#define LOONGARCH_BREAKPOINT_LOAD (1 << 0) +#define LOONGARCH_BREAKPOINT_STORE (1 << 1) + +struct arch_hw_breakpoint_ctrl { + u32 __reserved : 28, + len : 2, + type : 2; +}; + +struct arch_hw_breakpoint { + u64 address; + u64 mask; + struct arch_hw_breakpoint_ctrl ctrl; +}; + +/* Lengths */ +#define LOONGARCH_BREAKPOINT_LEN_1 0b11 +#define LOONGARCH_BREAKPOINT_LEN_2 0b10 +#define LOONGARCH_BREAKPOINT_LEN_4 0b01 +#define LOONGARCH_BREAKPOINT_LEN_8 0b00 + +/* + * Limits. + * Changing these will require modifications to the register accessors. + */ +#define LOONGARCH_MAX_BRP 8 +#define LOONGARCH_MAX_WRP 8 + +/* Virtual debug register bases. */ +#define CSR_CFG_ADDR 0 +#define CSR_CFG_MASK (CSR_CFG_ADDR + LOONGARCH_MAX_BRP) +#define CSR_CFG_CTRL (CSR_CFG_MASK + LOONGARCH_MAX_BRP) +#define CSR_CFG_ASID (CSR_CFG_CTRL + LOONGARCH_MAX_WRP) + +/* Debug register names. */ +#define LOONGARCH_CSR_NAME_ADDR ADDR +#define LOONGARCH_CSR_NAME_MASK MASK +#define LOONGARCH_CSR_NAME_CTRL CTRL +#define LOONGARCH_CSR_NAME_ASID ASID + +/* Accessor macros for the debug registers. */ +#define LOONGARCH_CSR_WATCH_READ(N, REG, T, VAL) \ +do { \ + if (T == 0) \ + VAL = csr_read64(LOONGARCH_CSR_##IB##N##REG); \ + else \ + VAL = csr_read64(LOONGARCH_CSR_##DB##N##REG); \ +} while (0) + +#define LOONGARCH_CSR_WATCH_WRITE(N, REG, T, VAL) \ +do { \ + if (T == 0) \ + csr_write64(VAL, LOONGARCH_CSR_##IB##N##REG); \ + else \ + csr_write64(VAL, LOONGARCH_CSR_##DB##N##REG); \ +} while (0) + +/* Exact number */ +#define CSR_FWPC_NUM 0x3f +#define CSR_MWPC_NUM 0x3f + +#define CTRL_PLV_ENABLE 0x1e + +#define MWPnCFG3_LoadEn 8 +#define MWPnCFG3_StoreEn 9 + +#define MWPnCFG3_Type_mask 0x3 +#define MWPnCFG3_Size_mask 0x3 + +static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl) +{ + return (ctrl.len << 10) | (ctrl.type << 8); +} + +static inline void decode_ctrl_reg(u32 reg, struct arch_hw_breakpoint_ctrl *ctrl) +{ + reg >>= 8; + ctrl->type = reg & MWPnCFG3_Type_mask; + reg >>= 2; + ctrl->len = reg & MWPnCFG3_Size_mask; +} + +struct task_struct; +struct notifier_block; +struct perf_event; +struct perf_event_attr; + +extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, + int *gen_len, int *gen_type, int *offset); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data); + +extern int arch_install_hw_breakpoint(struct perf_event *bp); +extern void arch_uninstall_hw_breakpoint(struct perf_event *bp); +extern int hw_breakpoint_slots(int type); +extern void hw_breakpoint_pmu_read(struct perf_event *bp); + +void breakpoint_handler(struct pt_regs *regs); +void watchpoint_handler(struct pt_regs *regs); + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +extern void ptrace_hw_copy_thread(struct task_struct *task); +extern void hw_breakpoint_thread_switch(struct task_struct *next); +#else +static inline void ptrace_hw_copy_thread(struct task_struct *task) +{ +} +static inline void hw_breakpoint_thread_switch(struct task_struct *next) +{ +} +#endif + +/* Determine number of BRP registers available. */ +static inline int get_num_brps(void) +{ + return csr_read64(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; +} + +/* Determine number of WRP registers available. */ +static inline int get_num_wrps(void) +{ + return csr_read64(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; +} + +#endif /* __KERNEL__ */ +#endif /* __ASM_BREAKPOINT_H */ diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index 7eedd83fd0d7..a04fe755d719 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -7,6 +7,7 @@ #include <linux/types.h> #include <asm/asm.h> +#include <asm/ptrace.h> #define INSN_NOP 0x03400000 #define INSN_BREAK 0x002a0000 @@ -23,6 +24,10 @@ #define ADDR_IMM(addr, INSN) ((addr & ADDR_IMMMASK_##INSN) >> ADDR_IMMSHIFT_##INSN) +enum reg0i15_op { + break_op = 0x54, +}; + enum reg0i26_op { b_op = 0x14, bl_op = 0x15, @@ -32,6 +37,7 @@ enum reg1i20_op { lu12iw_op = 0x0a, lu32id_op = 0x0b, pcaddi_op = 0x0c, + pcalau12i_op = 0x0d, pcaddu12i_op = 0x0e, pcaddu18i_op = 0x0f, }; @@ -178,6 +184,11 @@ enum reg3sa2_op { alsld_op = 0x16, }; +struct reg0i15_format { + unsigned int immediate : 15; + unsigned int opcode : 17; +}; + struct reg0i26_format { unsigned int immediate_h : 10; unsigned int immediate_l : 16; @@ -263,6 +274,7 @@ struct reg3sa2_format { union loongarch_instruction { unsigned int word; + struct reg0i15_format reg0i15_format; struct reg0i26_format reg0i26_format; struct reg1i20_format reg1i20_format; struct reg1i21_format reg1i21_format; @@ -321,6 +333,11 @@ static inline bool is_imm_negative(unsigned long val, unsigned int bit) return val & (1UL << (bit - 1)); } +static inline bool is_break_ins(union loongarch_instruction *ip) +{ + return ip->reg0i15_format.opcode == break_op; +} + static inline bool is_pc_ins(union loongarch_instruction *ip) { return ip->reg1i20_format.opcode >= pcaddi_op && @@ -351,6 +368,47 @@ static inline bool is_stack_alloc_ins(union loongarch_instruction *ip) is_imm12_negative(ip->reg2i12_format.immediate); } +static inline bool is_self_loop_ins(union loongarch_instruction *ip, struct pt_regs *regs) +{ + switch (ip->reg0i26_format.opcode) { + case b_op: + case bl_op: + if (ip->reg0i26_format.immediate_l == 0 + && ip->reg0i26_format.immediate_h == 0) + return true; + } + + switch (ip->reg1i21_format.opcode) { + case beqz_op: + case bnez_op: + case bceqz_op: + if (ip->reg1i21_format.immediate_l == 0 + && ip->reg1i21_format.immediate_h == 0) + return true; + } + + switch (ip->reg2i16_format.opcode) { + case beq_op: + case bne_op: + case blt_op: + case bge_op: + case bltu_op: + case bgeu_op: + if (ip->reg2i16_format.immediate == 0) + return true; + break; + case jirl_op: + if (regs->regs[ip->reg2i16_format.rj] + + ((unsigned long)ip->reg2i16_format.immediate << 2) == (unsigned long)ip) + return true; + } + + return false; +} + +void simu_pc(struct pt_regs *regs, union loongarch_instruction insn); +void simu_branch(struct pt_regs *regs, union loongarch_instruction insn); + int larch_insn_read(void *addr, u32 *insnp); int larch_insn_write(void *addr, u32 insn); int larch_insn_patch_text(void *addr, u32 insn); diff --git a/arch/loongarch/include/asm/kprobes.h b/arch/loongarch/include/asm/kprobes.h new file mode 100644 index 000000000000..798020ae02c6 --- /dev/null +++ b/arch/loongarch/include/asm/kprobes.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_LOONGARCH_KPROBES_H +#define __ASM_LOONGARCH_KPROBES_H + +#include <asm-generic/kprobes.h> + +#ifdef CONFIG_KPROBES + +#include <asm/inst.h> +#include <asm/cacheflush.h> + +#define __ARCH_WANT_KPROBES_INSN_SLOT +#define MAX_INSN_SIZE 2 + +#define flush_insn_slot(p) \ +do { \ + if (p->addr) \ + flush_icache_range((unsigned long)p->addr, \ + (unsigned long)p->addr + \ + (MAX_INSN_SIZE * sizeof(kprobe_opcode_t))); \ +} while (0) + +#define kretprobe_blacklist_size 0 + +typedef union loongarch_instruction kprobe_opcode_t; + +/* Architecture specific copy of original instruction */ +struct arch_specific_insn { + /* copy of the original instruction */ + kprobe_opcode_t *insn; + /* restore address after simulation */ + unsigned long restore; +}; + +struct prev_kprobe { + struct kprobe *kp; + unsigned int status; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned int kprobe_status; + unsigned long saved_status; + struct prev_kprobe prev_kprobe; +}; + +void arch_remove_kprobe(struct kprobe *p); +bool kprobe_fault_handler(struct pt_regs *regs, int trapnr); +bool kprobe_breakpoint_handler(struct pt_regs *regs); +bool kprobe_singlestep_handler(struct pt_regs *regs); + +void __kretprobe_trampoline(void); +void *trampoline_probe_handler(struct pt_regs *regs); + +#else /* !CONFIG_KPROBES */ + +static inline bool kprobe_breakpoint_handler(struct pt_regs *regs) { return false; } +static inline bool kprobe_singlestep_handler(struct pt_regs *regs) { return false; } + +#endif /* CONFIG_KPROBES */ +#endif /* __ASM_LOONGARCH_KPROBES_H */ diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 7f8d57a61c8b..65b7dcdea16d 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -970,42 +970,42 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define LOONGARCH_CSR_DB0ADDR 0x310 /* data breakpoint 0 address */ #define LOONGARCH_CSR_DB0MASK 0x311 /* data breakpoint 0 mask */ -#define LOONGARCH_CSR_DB0CTL 0x312 /* data breakpoint 0 control */ +#define LOONGARCH_CSR_DB0CTRL 0x312 /* data breakpoint 0 control */ #define LOONGARCH_CSR_DB0ASID 0x313 /* data breakpoint 0 asid */ #define LOONGARCH_CSR_DB1ADDR 0x318 /* data breakpoint 1 address */ #define LOONGARCH_CSR_DB1MASK 0x319 /* data breakpoint 1 mask */ -#define LOONGARCH_CSR_DB1CTL 0x31a /* data breakpoint 1 control */ +#define LOONGARCH_CSR_DB1CTRL 0x31a /* data breakpoint 1 control */ #define LOONGARCH_CSR_DB1ASID 0x31b /* data breakpoint 1 asid */ #define LOONGARCH_CSR_DB2ADDR 0x320 /* data breakpoint 2 address */ #define LOONGARCH_CSR_DB2MASK 0x321 /* data breakpoint 2 mask */ -#define LOONGARCH_CSR_DB2CTL 0x322 /* data breakpoint 2 control */ +#define LOONGARCH_CSR_DB2CTRL 0x322 /* data breakpoint 2 control */ #define LOONGARCH_CSR_DB2ASID 0x323 /* data breakpoint 2 asid */ #define LOONGARCH_CSR_DB3ADDR 0x328 /* data breakpoint 3 address */ #define LOONGARCH_CSR_DB3MASK 0x329 /* data breakpoint 3 mask */ -#define LOONGARCH_CSR_DB3CTL 0x32a /* data breakpoint 3 control */ +#define LOONGARCH_CSR_DB3CTRL 0x32a /* data breakpoint 3 control */ #define LOONGARCH_CSR_DB3ASID 0x32b /* data breakpoint 3 asid */ #define LOONGARCH_CSR_DB4ADDR 0x330 /* data breakpoint 4 address */ #define LOONGARCH_CSR_DB4MASK 0x331 /* data breakpoint 4 maks */ -#define LOONGARCH_CSR_DB4CTL 0x332 /* data breakpoint 4 control */ +#define LOONGARCH_CSR_DB4CTRL 0x332 /* data breakpoint 4 control */ #define LOONGARCH_CSR_DB4ASID 0x333 /* data breakpoint 4 asid */ #define LOONGARCH_CSR_DB5ADDR 0x338 /* data breakpoint 5 address */ #define LOONGARCH_CSR_DB5MASK 0x339 /* data breakpoint 5 mask */ -#define LOONGARCH_CSR_DB5CTL 0x33a /* data breakpoint 5 control */ +#define LOONGARCH_CSR_DB5CTRL 0x33a /* data breakpoint 5 control */ #define LOONGARCH_CSR_DB5ASID 0x33b /* data breakpoint 5 asid */ #define LOONGARCH_CSR_DB6ADDR 0x340 /* data breakpoint 6 address */ #define LOONGARCH_CSR_DB6MASK 0x341 /* data breakpoint 6 mask */ -#define LOONGARCH_CSR_DB6CTL 0x342 /* data breakpoint 6 control */ +#define LOONGARCH_CSR_DB6CTRL 0x342 /* data breakpoint 6 control */ #define LOONGARCH_CSR_DB6ASID 0x343 /* data breakpoint 6 asid */ #define LOONGARCH_CSR_DB7ADDR 0x348 /* data breakpoint 7 address */ #define LOONGARCH_CSR_DB7MASK 0x349 /* data breakpoint 7 mask */ -#define LOONGARCH_CSR_DB7CTL 0x34a /* data breakpoint 7 control */ +#define LOONGARCH_CSR_DB7CTRL 0x34a /* data breakpoint 7 control */ #define LOONGARCH_CSR_DB7ASID 0x34b /* data breakpoint 7 asid */ #define LOONGARCH_CSR_FWPC 0x380 /* instruction breakpoint config */ @@ -1013,48 +1013,51 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define LOONGARCH_CSR_IB0ADDR 0x390 /* inst breakpoint 0 address */ #define LOONGARCH_CSR_IB0MASK 0x391 /* inst breakpoint 0 mask */ -#define LOONGARCH_CSR_IB0CTL 0x392 /* inst breakpoint 0 control */ +#define LOONGARCH_CSR_IB0CTRL 0x392 /* inst breakpoint 0 control */ #define LOONGARCH_CSR_IB0ASID 0x393 /* inst breakpoint 0 asid */ #define LOONGARCH_CSR_IB1ADDR 0x398 /* inst breakpoint 1 address */ #define LOONGARCH_CSR_IB1MASK 0x399 /* inst breakpoint 1 mask */ -#define LOONGARCH_CSR_IB1CTL 0x39a /* inst breakpoint 1 control */ +#define LOONGARCH_CSR_IB1CTRL 0x39a /* inst breakpoint 1 control */ #define LOONGARCH_CSR_IB1ASID 0x39b /* inst breakpoint 1 asid */ #define LOONGARCH_CSR_IB2ADDR 0x3a0 /* inst breakpoint 2 address */ #define LOONGARCH_CSR_IB2MASK 0x3a1 /* inst breakpoint 2 mask */ -#define LOONGARCH_CSR_IB2CTL 0x3a2 /* inst breakpoint 2 control */ +#define LOONGARCH_CSR_IB2CTRL 0x3a2 /* inst breakpoint 2 control */ #define LOONGARCH_CSR_IB2ASID 0x3a3 /* inst breakpoint 2 asid */ #define LOONGARCH_CSR_IB3ADDR 0x3a8 /* inst breakpoint 3 address */ #define LOONGARCH_CSR_IB3MASK 0x3a9 /* breakpoint 3 mask */ -#define LOONGARCH_CSR_IB3CTL 0x3aa /* inst breakpoint 3 control */ +#define LOONGARCH_CSR_IB3CTRL 0x3aa /* inst breakpoint 3 control */ #define LOONGARCH_CSR_IB3ASID 0x3ab /* inst breakpoint 3 asid */ #define LOONGARCH_CSR_IB4ADDR 0x3b0 /* inst breakpoint 4 address */ #define LOONGARCH_CSR_IB4MASK 0x3b1 /* inst breakpoint 4 mask */ -#define LOONGARCH_CSR_IB4CTL 0x3b2 /* inst breakpoint 4 control */ +#define LOONGARCH_CSR_IB4CTRL 0x3b2 /* inst breakpoint 4 control */ #define LOONGARCH_CSR_IB4ASID 0x3b3 /* inst breakpoint 4 asid */ #define LOONGARCH_CSR_IB5ADDR 0x3b8 /* inst breakpoint 5 address */ #define LOONGARCH_CSR_IB5MASK 0x3b9 /* inst breakpoint 5 mask */ -#define LOONGARCH_CSR_IB5CTL 0x3ba /* inst breakpoint 5 control */ +#define LOONGARCH_CSR_IB5CTRL 0x3ba /* inst breakpoint 5 control */ #define LOONGARCH_CSR_IB5ASID 0x3bb /* inst breakpoint 5 asid */ #define LOONGARCH_CSR_IB6ADDR 0x3c0 /* inst breakpoint 6 address */ #define LOONGARCH_CSR_IB6MASK 0x3c1 /* inst breakpoint 6 mask */ -#define LOONGARCH_CSR_IB6CTL 0x3c2 /* inst breakpoint 6 control */ +#define LOONGARCH_CSR_IB6CTRL 0x3c2 /* inst breakpoint 6 control */ #define LOONGARCH_CSR_IB6ASID 0x3c3 /* inst breakpoint 6 asid */ #define LOONGARCH_CSR_IB7ADDR 0x3c8 /* inst breakpoint 7 address */ #define LOONGARCH_CSR_IB7MASK 0x3c9 /* inst breakpoint 7 mask */ -#define LOONGARCH_CSR_IB7CTL 0x3ca /* inst breakpoint 7 control */ +#define LOONGARCH_CSR_IB7CTRL 0x3ca /* inst breakpoint 7 control */ #define LOONGARCH_CSR_IB7ASID 0x3cb /* inst breakpoint 7 asid */ #define LOONGARCH_CSR_DEBUG 0x500 /* debug config */ #define LOONGARCH_CSR_DERA 0x501 /* debug era */ #define LOONGARCH_CSR_DESAVE 0x502 /* debug save */ +#define CSR_FWPC_SKIP_SHIFT 16 +#define CSR_FWPC_SKIP (_ULCAST_(1) << CSR_FWPC_SKIP_SHIFT) + /* * CSR_ECFG IM */ diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h index 7184f1dc61f2..636e1c66398c 100644 --- a/arch/loongarch/include/asm/processor.h +++ b/arch/loongarch/include/asm/processor.h @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/cpu-info.h> +#include <asm/hw_breakpoint.h> #include <asm/loongarch.h> #include <asm/vdso/processor.h> #include <uapi/asm/ptrace.h> @@ -124,13 +125,18 @@ struct thread_struct { /* Other stuff associated with the thread. */ unsigned long trap_nr; unsigned long error_code; + unsigned long single_step; /* Used by PTRACE_SINGLESTEP */ struct loongarch_vdso_info *vdso; /* - * FPU & vector registers, must be at last because - * they are conditionally copied at fork(). + * FPU & vector registers, must be at the last of inherited + * context because they are conditionally copied at fork(). */ struct loongarch_fpu fpu FPU_ALIGN; + + /* Hardware breakpoints pinned to this task. */ + struct perf_event *hbp_break[LOONGARCH_MAX_BRP]; + struct perf_event *hbp_watch[LOONGARCH_MAX_WRP]; }; #define thread_saved_ra(tsk) (tsk->thread.sched_ra) @@ -172,6 +178,8 @@ struct thread_struct { .fcc = 0, \ .fpr = {{{0,},},}, \ }, \ + .hbp_break = {0}, \ + .hbp_watch = {0}, \ } struct task_struct; @@ -184,10 +192,6 @@ extern unsigned long boot_option_idle_override; */ extern void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp); -static inline void flush_thread(void) -{ -} - unsigned long __get_wchan(struct task_struct *p); #define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \ diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index 59c4608de91d..d761db943335 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -6,6 +6,7 @@ #define _ASM_PTRACE_H #include <asm/page.h> +#include <asm/irqflags.h> #include <asm/thread_info.h> #include <uapi/asm/ptrace.h> @@ -109,6 +110,40 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsi struct task_struct; +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * regs_get_argument() returns @n th argument of the function call. + * Note that this chooses most probably assignment, in some case + * it can be incorrect. + * This is expected to be called from kprobes or ftrace with regs + * where the top of stack is the return address. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, + unsigned int n) +{ +#define NR_REG_ARGUMENTS 8 + static const unsigned int args[] = { + offsetof(struct pt_regs, regs[4]), + offsetof(struct pt_regs, regs[5]), + offsetof(struct pt_regs, regs[6]), + offsetof(struct pt_regs, regs[7]), + offsetof(struct pt_regs, regs[8]), + offsetof(struct pt_regs, regs[9]), + offsetof(struct pt_regs, regs[10]), + offsetof(struct pt_regs, regs[11]), + }; + + if (n < NR_REG_ARGUMENTS) + return regs_get_register(regs, args[n]); + else { + n -= NR_REG_ARGUMENTS; + return regs_get_kernel_stack_nth(regs, n); + } +} + /* * Does the process account for user or for system time? */ @@ -149,4 +184,8 @@ static inline void user_stack_pointer_set(struct pt_regs *regs, regs->regs[3] = val; } +#ifdef CONFIG_HAVE_HW_BREAKPOINT +#define arch_has_single_step() (1) +#endif + #endif /* _ASM_PTRACE_H */ diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index 72ead58039f3..be05c0e706a2 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -21,4 +21,20 @@ extern void per_cpu_trap_init(int cpu); extern void set_handler(unsigned long offset, void *addr, unsigned long len); extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len); +#ifdef CONFIG_RELOCATABLE + +struct rela_la_abs { + long offset; + long symvalue; +}; + +extern long __la_abs_begin; +extern long __la_abs_end; +extern long __rela_dyn_begin; +extern long __rela_dyn_end; + +extern void * __init relocate_kernel(void); + +#endif + #endif /* __SETUP_H */ diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 4ca953062b5b..7df80e6ae9d2 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -7,6 +7,7 @@ #include <linux/threads.h> +#include <asm/addrspace.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/asm-offsets.h> @@ -36,6 +37,14 @@ cfi_restore \reg \offset \docfi .endm +/* Jump to the runtime virtual address. */ + .macro JUMP_VIRT_ADDR temp1 temp2 + li.d \temp1, CACHE_BASE + pcaddi \temp2, 0 + or \temp1, \temp1, \temp2 + jirl zero, \temp1, 0xc + .endm + .macro BACKUP_T0T1 csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 @@ -77,7 +86,7 @@ * new value in sp. */ .macro get_saved_sp docfi=0 - la.abs t1, kernelsp + la_abs t1, kernelsp #ifdef CONFIG_SMP csrrd t0, PERCPU_BASE_KS LONG_ADD t1, t1, t0 @@ -90,7 +99,7 @@ .endm .macro set_saved_sp stackp temp temp2 - la.abs \temp, kernelsp + la.pcrel \temp, kernelsp #ifdef CONFIG_SMP LONG_ADD \temp, \temp, u0 #endif diff --git a/arch/loongarch/include/asm/switch_to.h b/arch/loongarch/include/asm/switch_to.h index 43a5ab162d38..24e3094bebab 100644 --- a/arch/loongarch/include/asm/switch_to.h +++ b/arch/loongarch/include/asm/switch_to.h @@ -34,6 +34,7 @@ extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev, #define switch_to(prev, next, last) \ do { \ lose_fpu_inatomic(1, prev); \ + hw_breakpoint_thread_switch(next); \ (last) = __switch_to(prev, next, task_thread_info(next), \ __builtin_return_address(0), __builtin_frame_address(0)); \ } while (0) diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index 255899d4a7c3..0d22991ae430 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -22,7 +22,6 @@ extern u64 __ua_limit; #define __UA_ADDR ".dword" -#define __UA_LA "la.abs" #define __UA_LIMIT __ua_limit /* diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index 083193f4a5d5..cc48ed262021 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -46,6 +46,15 @@ struct user_fp_state { uint32_t fcsr; }; +struct user_watch_state { + uint16_t dbg_info; + struct { + uint64_t addr; + uint64_t mask; + uint32_t ctrl; + } dbg_regs[8]; +}; + #define PTRACE_SYSEMU 0x1f #define PTRACE_SYSEMU_SINGLESTEP 0x20 diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index c8cfbd562921..78d4e3384305 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -8,13 +8,15 @@ extra-y := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \ elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ - alternative.o unaligned.o unwind.o + alternative.o unwind.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o obj-$(CONFIG_CPU_HAS_FPU) += fpu.o +obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o + ifdef CONFIG_FUNCTION_TRACER ifndef CONFIG_DYNAMIC_FTRACE obj-y += mcount.o ftrace.o @@ -39,6 +41,8 @@ obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o +obj-$(CONFIG_RELOCATABLE) += relocate.o + obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o @@ -46,5 +50,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_regs.o +obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o + +obj-$(CONFIG_KPROBES) += kprobes.o kprobes_trampoline.o CPPFLAGS_vmlinux.lds := $(KBUILD_CFLAGS) diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index d53b631c9022..d737e3cf42d3 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -19,70 +19,71 @@ .cfi_sections .debug_frame .align 5 SYM_FUNC_START(handle_syscall) - csrrd t0, PERCPU_BASE_KS - la.abs t1, kernelsp - add.d t1, t1, t0 - move t2, sp - ld.d sp, t1, 0 + csrrd t0, PERCPU_BASE_KS + la.pcrel t1, kernelsp + add.d t1, t1, t0 + move t2, sp + ld.d sp, t1, 0 - addi.d sp, sp, -PT_SIZE - cfi_st t2, PT_R3 + addi.d sp, sp, -PT_SIZE + cfi_st t2, PT_R3 cfi_rel_offset sp, PT_R3 - st.d zero, sp, PT_R0 - csrrd t2, LOONGARCH_CSR_PRMD - st.d t2, sp, PT_PRMD - csrrd t2, LOONGARCH_CSR_CRMD - st.d t2, sp, PT_CRMD - csrrd t2, LOONGARCH_CSR_EUEN - st.d t2, sp, PT_EUEN - csrrd t2, LOONGARCH_CSR_ECFG - st.d t2, sp, PT_ECFG - csrrd t2, LOONGARCH_CSR_ESTAT - st.d t2, sp, PT_ESTAT - cfi_st ra, PT_R1 - cfi_st a0, PT_R4 - cfi_st a1, PT_R5 - cfi_st a2, PT_R6 - cfi_st a3, PT_R7 - cfi_st a4, PT_R8 - cfi_st a5, PT_R9 - cfi_st a6, PT_R10 - cfi_st a7, PT_R11 - csrrd ra, LOONGARCH_CSR_ERA - st.d ra, sp, PT_ERA + st.d zero, sp, PT_R0 + csrrd t2, LOONGARCH_CSR_PRMD + st.d t2, sp, PT_PRMD + csrrd t2, LOONGARCH_CSR_CRMD + st.d t2, sp, PT_CRMD + csrrd t2, LOONGARCH_CSR_EUEN + st.d t2, sp, PT_EUEN + csrrd t2, LOONGARCH_CSR_ECFG + st.d t2, sp, PT_ECFG + csrrd t2, LOONGARCH_CSR_ESTAT + st.d t2, sp, PT_ESTAT + cfi_st ra, PT_R1 + cfi_st a0, PT_R4 + cfi_st a1, PT_R5 + cfi_st a2, PT_R6 + cfi_st a3, PT_R7 + cfi_st a4, PT_R8 + cfi_st a5, PT_R9 + cfi_st a6, PT_R10 + cfi_st a7, PT_R11 + csrrd ra, LOONGARCH_CSR_ERA + st.d ra, sp, PT_ERA cfi_rel_offset ra, PT_ERA - cfi_st tp, PT_R2 - cfi_st u0, PT_R21 - cfi_st fp, PT_R22 + cfi_st tp, PT_R2 + cfi_st u0, PT_R21 + cfi_st fp, PT_R22 SAVE_STATIC - move u0, t0 - li.d tp, ~_THREAD_MASK - and tp, tp, sp + move u0, t0 + li.d tp, ~_THREAD_MASK + and tp, tp, sp - move a0, sp - bl do_syscall + move a0, sp + bl do_syscall RESTORE_ALL_AND_RET SYM_FUNC_END(handle_syscall) +_ASM_NOKPROBE(handle_syscall) SYM_CODE_START(ret_from_fork) - bl schedule_tail # a0 = struct task_struct *prev - move a0, sp - bl syscall_exit_to_user_mode + bl schedule_tail # a0 = struct task_struct *prev + move a0, sp + bl syscall_exit_to_user_mode RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET SYM_CODE_END(ret_from_fork) SYM_CODE_START(ret_from_kernel_thread) - bl schedule_tail # a0 = struct task_struct *prev - move a0, s1 - jirl ra, s0, 0 - move a0, sp - bl syscall_exit_to_user_mode + bl schedule_tail # a0 = struct task_struct *prev + move a0, s1 + jirl ra, s0, 0 + move a0, sp + bl syscall_exit_to_user_mode RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 0f07591cab30..4a3ef8516ccc 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -6,6 +6,7 @@ */ #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <linux/uaccess.h> #include <asm/inst.h> @@ -271,3 +272,66 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_KPROBES_ON_FTRACE +/* 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) +{ + int bit; + struct pt_regs *regs; + struct kprobe *p; + struct kprobe_ctlblk *kcb; + + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto out; + + regs = ftrace_get_regs(fregs); + if (!regs) + goto out; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + unsigned long orig_ip = instruction_pointer(regs); + + 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)) { + /* + * Emulate singlestep (and also recover regs->csr_era) + * as if there is a nop + */ + 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, 0); + } + instruction_pointer_set(regs, orig_ip); + } + + /* + * If pre_handler returns !0, it changes regs->csr_era. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); + } +out: + ftrace_test_recursion_unlock(bit); +} +NOKPROBE_SYMBOL(kprobe_ftrace_handler); + +int arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + return 0; +} +#endif /* CONFIG_KPROBES_ON_FTRACE */ diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 7e5c293ed89f..44ff1ff64260 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -34,7 +34,7 @@ SYM_FUNC_END(__arch_cpu_idle) SYM_FUNC_START(handle_vint) BACKUP_T0T1 SAVE_ALL - la.abs t1, __arch_cpu_idle + la_abs t1, __arch_cpu_idle LONG_L t0, sp, PT_ERA /* 32 byte rollback region */ ori t0, t0, 0x1f @@ -43,7 +43,7 @@ SYM_FUNC_START(handle_vint) LONG_S t0, sp, PT_ERA 1: move a0, sp move a1, sp - la.abs t0, do_vint + la_abs t0, do_vint jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_vint) @@ -72,7 +72,7 @@ SYM_FUNC_END(except_vec_cex) SAVE_ALL build_prep_\prep move a0, sp - la.abs t0, do_\handler + la_abs t0, do_\handler jirl ra, t0, 0 668: RESTORE_ALL_AND_RET @@ -93,6 +93,6 @@ SYM_FUNC_END(except_vec_cex) BUILD_HANDLER reserved reserved none /* others */ SYM_FUNC_START(handle_sys) - la.abs t0, handle_syscall + la_abs t0, handle_syscall jr t0 SYM_FUNC_END(handle_sys) diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 57bada6b4e93..aa64b179744f 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -24,7 +24,7 @@ _head: .org 0x8 .dword kernel_entry /* Kernel entry point */ .dword _end - _text /* Kernel image effective size */ - .quad 0 /* Kernel image load offset from start of RAM */ + .quad PHYS_LINK_KADDR /* Kernel image load offset from start of RAM */ .org 0x38 /* 0x20 ~ 0x37 reserved */ .long LINUX_PE_MAGIC .long pe_header - _head /* Offset to the PE header */ @@ -50,11 +50,8 @@ SYM_CODE_START(kernel_entry) # kernel entry point li.d t0, CSR_DMW1_INIT # CA, PLV0, 0x9000 xxxx xxxx xxxx csrwr t0, LOONGARCH_CSR_DMWIN1 - /* We might not get launched at the address the kernel is linked to, - so we jump there. */ - la.abs t0, 0f - jr t0 -0: + JUMP_VIRT_ADDR t0, t1 + /* Enable PG */ li.w t0, 0xb0 # PLV=0, IE=0, PG=1 csrwr t0, LOONGARCH_CSR_CRMD @@ -89,6 +86,23 @@ SYM_CODE_START(kernel_entry) # kernel entry point PTR_ADD sp, sp, tp set_saved_sp sp, t0, t1 +#ifdef CONFIG_RELOCATABLE + + bl relocate_kernel + +#ifdef CONFIG_RANDOMIZE_BASE + /* Repoint the sp into the new kernel */ + PTR_LI sp, (_THREAD_SIZE - PT_SIZE) + PTR_ADD sp, sp, tp + set_saved_sp sp, t0, t1 +#endif + + /* relocate_kernel() returns the new kernel entry point */ + jr a0 + ASM_BUG() + +#endif + bl start_kernel ASM_BUG() @@ -106,9 +120,8 @@ SYM_CODE_START(smpboot_entry) li.d t0, CSR_DMW1_INIT # CA, PLV0 csrwr t0, LOONGARCH_CSR_DMWIN1 - la.abs t0, 0f - jr t0 -0: + JUMP_VIRT_ADDR t0, t1 + /* Enable PG */ li.w t0, 0xb0 # PLV=0, IE=0, PG=1 csrwr t0, LOONGARCH_CSR_CRMD @@ -117,7 +130,7 @@ SYM_CODE_START(smpboot_entry) li.w t0, 0x00 # FPE=0, SXE=0, ASXE=0, BTE=0 csrwr t0, LOONGARCH_CSR_EUEN - la.abs t0, cpuboot_data + la.pcrel t0, cpuboot_data ld.d sp, t0, CPU_BOOT_STACK ld.d tp, t0, CPU_BOOT_TINFO diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c new file mode 100644 index 000000000000..2406c95b34cc --- /dev/null +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -0,0 +1,548 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2023 Loongson Technology Corporation Limited + */ +#define pr_fmt(fmt) "hw-breakpoint: " fmt + +#include <linux/hw_breakpoint.h> +#include <linux/kprobes.h> +#include <linux/perf_event.h> + +#include <asm/hw_breakpoint.h> + +/* Breakpoint currently in use for each BRP. */ +static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[LOONGARCH_MAX_BRP]); + +/* Watchpoint currently in use for each WRP. */ +static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[LOONGARCH_MAX_WRP]); + +int hw_breakpoint_slots(int type) +{ + /* + * We can be called early, so don't rely on + * our static variables being initialised. + */ + switch (type) { + case TYPE_INST: + return get_num_brps(); + case TYPE_DATA: + return get_num_wrps(); + default: + pr_warn("unknown slot type: %d\n", type); + return 0; + } +} + +#define READ_WB_REG_CASE(OFF, N, REG, T, VAL) \ + case (OFF + N): \ + LOONGARCH_CSR_WATCH_READ(N, REG, T, VAL); \ + break + +#define WRITE_WB_REG_CASE(OFF, N, REG, T, VAL) \ + case (OFF + N): \ + LOONGARCH_CSR_WATCH_WRITE(N, REG, T, VAL); \ + break + +#define GEN_READ_WB_REG_CASES(OFF, REG, T, VAL) \ + READ_WB_REG_CASE(OFF, 0, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 1, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 2, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 3, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 4, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 5, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 6, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 7, REG, T, VAL); + +#define GEN_WRITE_WB_REG_CASES(OFF, REG, T, VAL) \ + WRITE_WB_REG_CASE(OFF, 0, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 1, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 2, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 3, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 4, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 5, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 6, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); + +static u64 read_wb_reg(int reg, int n, int t) +{ + u64 val = 0; + + switch (reg + n) { + GEN_READ_WB_REG_CASES(CSR_CFG_ADDR, ADDR, t, val); + GEN_READ_WB_REG_CASES(CSR_CFG_MASK, MASK, t, val); + GEN_READ_WB_REG_CASES(CSR_CFG_CTRL, CTRL, t, val); + GEN_READ_WB_REG_CASES(CSR_CFG_ASID, ASID, t, val); + default: + pr_warn("Attempt to read from unknown breakpoint register %d\n", n); + } + + return val; +} +NOKPROBE_SYMBOL(read_wb_reg); + +static void write_wb_reg(int reg, int n, int t, u64 val) +{ + switch (reg + n) { + GEN_WRITE_WB_REG_CASES(CSR_CFG_ADDR, ADDR, t, val); + GEN_WRITE_WB_REG_CASES(CSR_CFG_MASK, MASK, t, val); + GEN_WRITE_WB_REG_CASES(CSR_CFG_CTRL, CTRL, t, val); + GEN_WRITE_WB_REG_CASES(CSR_CFG_ASID, ASID, t, val); + default: + pr_warn("Attempt to write to unknown breakpoint register %d\n", n); + } +} +NOKPROBE_SYMBOL(write_wb_reg); + +enum hw_breakpoint_ops { + HW_BREAKPOINT_INSTALL, + HW_BREAKPOINT_UNINSTALL, +}; + +/* + * hw_breakpoint_slot_setup - Find and setup a perf slot according to operations + * + * @slots: pointer to array of slots + * @max_slots: max number of slots + * @bp: perf_event to setup + * @ops: operation to be carried out on the slot + * + * Return: + * slot index on success + * -ENOSPC if no slot is available/matches + * -EINVAL on wrong operations parameter + */ + +static int hw_breakpoint_slot_setup(struct perf_event **slots, int max_slots, + struct perf_event *bp, enum hw_breakpoint_ops ops) +{ + int i; + struct perf_event **slot; + + for (i = 0; i < max_slots; ++i) { + slot = &slots[i]; + switch (ops) { + case HW_BREAKPOINT_INSTALL: + if (!*slot) { + *slot = bp; + return i; + } + break; + case HW_BREAKPOINT_UNINSTALL: + if (*slot == bp) { + *slot = NULL; + return i; + } + break; + default: + pr_warn_once("Unhandled hw breakpoint ops %d\n", ops); + return -EINVAL; + } + } + + return -ENOSPC; +} + +void ptrace_hw_copy_thread(struct task_struct *tsk) +{ + memset(tsk->thread.hbp_break, 0, sizeof(tsk->thread.hbp_break)); + memset(tsk->thread.hbp_watch, 0, sizeof(tsk->thread.hbp_watch)); +} + +/* + * Unregister breakpoints from this task and reset the pointers in the thread_struct. + */ +void flush_ptrace_hw_breakpoint(struct task_struct *tsk) +{ + int i; + struct thread_struct *t = &tsk->thread; + + for (i = 0; i < LOONGARCH_MAX_BRP; i++) { + if (t->hbp_break[i]) { + unregister_hw_breakpoint(t->hbp_break[i]); + t->hbp_break[i] = NULL; + } + } + + for (i = 0; i < LOONGARCH_MAX_WRP; i++) { + if (t->hbp_watch[i]) { + unregister_hw_breakpoint(t->hbp_watch[i]); + t->hbp_watch[i] = NULL; + } + } +} + +static int hw_breakpoint_control(struct perf_event *bp, + enum hw_breakpoint_ops ops) +{ + u32 ctrl; + int i, max_slots, enable; + struct perf_event **slots; + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + /* Breakpoint */ + slots = this_cpu_ptr(bp_on_reg); + max_slots = boot_cpu_data.watch_ireg_count; + } else { + /* Watchpoint */ + slots = this_cpu_ptr(wp_on_reg); + max_slots = boot_cpu_data.watch_dreg_count; + } + + i = hw_breakpoint_slot_setup(slots, max_slots, bp, ops); + + if (WARN_ONCE(i < 0, "Can't find any breakpoint slot")) + return i; + + switch (ops) { + case HW_BREAKPOINT_INSTALL: + /* Set the FWPnCFG/MWPnCFG 1~4 register. */ + write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); + write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); + write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); + write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + } else { + ctrl = encode_ctrl_reg(info->ctrl); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE | + 1 << MWPnCFG3_LoadEn | 1 << MWPnCFG3_StoreEn); + } + enable = csr_read64(LOONGARCH_CSR_CRMD); + csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); + break; + case HW_BREAKPOINT_UNINSTALL: + /* Reset the FWPnCFG/MWPnCFG 1~4 register. */ + write_wb_reg(CSR_CFG_ADDR, i, 0, 0); + write_wb_reg(CSR_CFG_ADDR, i, 1, 0); + write_wb_reg(CSR_CFG_MASK, i, 0, 0); + write_wb_reg(CSR_CFG_MASK, i, 1, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 1, 0); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + break; + } + + return 0; +} + +/* + * Install a perf counter breakpoint. + */ +int arch_install_hw_breakpoint(struct perf_event *bp) +{ + return hw_breakpoint_control(bp, HW_BREAKPOINT_INSTALL); +} + +void arch_uninstall_hw_breakpoint(struct perf_event *bp) +{ + hw_breakpoint_control(bp, HW_BREAKPOINT_UNINSTALL); +} + +static int get_hbp_len(u8 hbp_len) +{ + unsigned int len_in_bytes = 0; + + switch (hbp_len) { + case LOONGARCH_BREAKPOINT_LEN_1: + len_in_bytes = 1; + break; + case LOONGARCH_BREAKPOINT_LEN_2: + len_in_bytes = 2; + break; + case LOONGARCH_BREAKPOINT_LEN_4: + len_in_bytes = 4; + break; + case LOONGARCH_BREAKPOINT_LEN_8: + len_in_bytes = 8; + break; + } + + return len_in_bytes; +} + +/* + * Check whether bp virtual address is in kernel space. + */ +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) +{ + unsigned int len; + unsigned long va; + + va = hw->address; + len = get_hbp_len(hw->ctrl.len); + + return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); +} + +/* + * Extract generic type and length encodings from an arch_hw_breakpoint_ctrl. + * Hopefully this will disappear when ptrace can bypass the conversion + * to generic breakpoint descriptions. + */ +int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, + int *gen_len, int *gen_type, int *offset) +{ + /* Type */ + switch (ctrl.type) { + case LOONGARCH_BREAKPOINT_EXECUTE: + *gen_type = HW_BREAKPOINT_X; + break; + case LOONGARCH_BREAKPOINT_LOAD: + *gen_type = HW_BREAKPOINT_R; + break; + case LOONGARCH_BREAKPOINT_STORE: + *gen_type = HW_BREAKPOINT_W; + break; + case LOONGARCH_BREAKPOINT_LOAD | LOONGARCH_BREAKPOINT_STORE: + *gen_type = HW_BREAKPOINT_RW; + break; + default: + return -EINVAL; + } + + if (!ctrl.len) + return -EINVAL; + + *offset = __ffs(ctrl.len); + + /* Len */ + switch (ctrl.len) { + case LOONGARCH_BREAKPOINT_LEN_1: + *gen_len = HW_BREAKPOINT_LEN_1; + break; + case LOONGARCH_BREAKPOINT_LEN_2: + *gen_len = HW_BREAKPOINT_LEN_2; + break; + case LOONGARCH_BREAKPOINT_LEN_4: + *gen_len = HW_BREAKPOINT_LEN_4; + break; + case LOONGARCH_BREAKPOINT_LEN_8: + *gen_len = HW_BREAKPOINT_LEN_8; + break; + default: + return -EINVAL; + } + + return 0; +} + +/* + * Construct an arch_hw_breakpoint from a perf_event. + */ +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + /* Type */ + switch (attr->bp_type) { + case HW_BREAKPOINT_X: + hw->ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE; + break; + case HW_BREAKPOINT_R: + hw->ctrl.type = LOONGARCH_BREAKPOINT_LOAD; + break; + case HW_BREAKPOINT_W: + hw->ctrl.type = LOONGARCH_BREAKPOINT_STORE; + break; + case HW_BREAKPOINT_RW: + hw->ctrl.type = LOONGARCH_BREAKPOINT_LOAD | LOONGARCH_BREAKPOINT_STORE; + break; + default: + return -EINVAL; + } + + /* Len */ + switch (attr->bp_len) { + case HW_BREAKPOINT_LEN_1: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_1; + break; + case HW_BREAKPOINT_LEN_2: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_2; + break; + case HW_BREAKPOINT_LEN_4: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_4; + break; + case HW_BREAKPOINT_LEN_8: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_8; + break; + default: + return -EINVAL; + } + + /* Address */ + hw->address = attr->bp_addr; + + return 0; +} + +/* + * Validate the arch-specific HW Breakpoint register settings. + */ +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + int ret; + u64 alignment_mask, offset; + + /* Build the arch_hw_breakpoint. */ + ret = arch_build_bp_info(bp, attr, hw); + if (ret) + return ret; + + if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) + alignment_mask = 0x7; + offset = hw->address & alignment_mask; + + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; + + return 0; +} + +static void update_bp_registers(struct pt_regs *regs, int enable, int type) +{ + u32 ctrl; + int i, max_slots; + struct perf_event **slots; + struct arch_hw_breakpoint *info; + + switch (type) { + case 0: + slots = this_cpu_ptr(bp_on_reg); + max_slots = boot_cpu_data.watch_ireg_count; + break; + case 1: + slots = this_cpu_ptr(wp_on_reg); + max_slots = boot_cpu_data.watch_dreg_count; + break; + default: + return; + } + + for (i = 0; i < max_slots; ++i) { + if (!slots[i]) + continue; + + info = counter_arch_bp(slots[i]); + if (enable) { + if ((info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) && (type == 0)) { + write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + } else { + ctrl = read_wb_reg(CSR_CFG_CTRL, i, 1); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_LOAD) + ctrl |= 0x1 << MWPnCFG3_LoadEn; + if (info->ctrl.type == LOONGARCH_BREAKPOINT_STORE) + ctrl |= 0x1 << MWPnCFG3_StoreEn; + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl); + } + regs->csr_prmd |= CSR_PRMD_PWE; + } else { + if ((info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) && (type == 0)) { + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + } else { + ctrl = read_wb_reg(CSR_CFG_CTRL, i, 1); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_LOAD) + ctrl &= ~0x1 << MWPnCFG3_LoadEn; + if (info->ctrl.type == LOONGARCH_BREAKPOINT_STORE) + ctrl &= ~0x1 << MWPnCFG3_StoreEn; + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl); + } + regs->csr_prmd &= ~CSR_PRMD_PWE; + } + } +} +NOKPROBE_SYMBOL(update_bp_registers); + +/* + * Debug exception handlers. + */ +void breakpoint_handler(struct pt_regs *regs) +{ + int i; + struct perf_event *bp, **slots; + + slots = this_cpu_ptr(bp_on_reg); + + for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) { + bp = slots[i]; + if (bp == NULL) + continue; + perf_bp_event(bp, regs); + } + update_bp_registers(regs, 0, 0); +} +NOKPROBE_SYMBOL(breakpoint_handler); + +void watchpoint_handler(struct pt_regs *regs) +{ + int i; + struct perf_event *wp, **slots; + + slots = this_cpu_ptr(wp_on_reg); + + for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) { + wp = slots[i]; + if (wp == NULL) + continue; + perf_bp_event(wp, regs); + } + update_bp_registers(regs, 0, 1); +} +NOKPROBE_SYMBOL(watchpoint_handler); + +static int __init arch_hw_breakpoint_init(void) +{ + int cpu; + + boot_cpu_data.watch_ireg_count = get_num_brps(); + boot_cpu_data.watch_dreg_count = get_num_wrps(); + + pr_info("Found %d breakpoint and %d watchpoint registers.\n", + boot_cpu_data.watch_ireg_count, boot_cpu_data.watch_dreg_count); + + for (cpu = 1; cpu < NR_CPUS; cpu++) { + cpu_data[cpu].watch_ireg_count = boot_cpu_data.watch_ireg_count; + cpu_data[cpu].watch_dreg_count = boot_cpu_data.watch_dreg_count; + } + + return 0; +} +arch_initcall(arch_hw_breakpoint_init); + +void hw_breakpoint_thread_switch(struct task_struct *next) +{ + u64 addr, mask; + struct pt_regs *regs = task_pt_regs(next); + + if (test_tsk_thread_flag(next, TIF_SINGLESTEP)) { + addr = read_wb_reg(CSR_CFG_ADDR, 0, 0); + mask = read_wb_reg(CSR_CFG_MASK, 0, 0); + if (!((regs->csr_era ^ addr) & ~mask)) + csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS); + regs->csr_prmd |= CSR_PRMD_PWE; + } else { + /* Update breakpoints */ + update_bp_registers(regs, 1, 0); + /* Update watchpoints */ + update_bp_registers(regs, 1, 1); + } +} + +void hw_breakpoint_pmu_read(struct perf_event *bp) +{ +} + +/* + * Dummy function to register with die_notifier. + */ +int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index badc59087042..258ef267cd30 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -10,6 +10,129 @@ static DEFINE_RAW_SPINLOCK(patch_lock); +void simu_pc(struct pt_regs *regs, union loongarch_instruction insn) +{ + unsigned long pc = regs->csr_era; + unsigned int rd = insn.reg1i20_format.rd; + unsigned int imm = insn.reg1i20_format.immediate; + + if (pc & 3) { + pr_warn("%s: invalid pc 0x%lx\n", __func__, pc); + return; + } + + switch (insn.reg1i20_format.opcode) { + case pcaddi_op: + regs->regs[rd] = pc + sign_extend64(imm << 2, 21); + break; + case pcaddu12i_op: + regs->regs[rd] = pc + sign_extend64(imm << 12, 31); + break; + case pcaddu18i_op: + regs->regs[rd] = pc + sign_extend64(imm << 18, 37); + break; + case pcalau12i_op: + regs->regs[rd] = pc + sign_extend64(imm << 12, 31); + regs->regs[rd] &= ~((1 << 12) - 1); + break; + default: + pr_info("%s: unknown opcode\n", __func__); + return; + } + + regs->csr_era += LOONGARCH_INSN_SIZE; +} + +void simu_branch(struct pt_regs *regs, union loongarch_instruction insn) +{ + unsigned int imm, imm_l, imm_h, rd, rj; + unsigned long pc = regs->csr_era; + + if (pc & 3) { + pr_warn("%s: invalid pc 0x%lx\n", __func__, pc); + return; + } + + imm_l = insn.reg0i26_format.immediate_l; + imm_h = insn.reg0i26_format.immediate_h; + switch (insn.reg0i26_format.opcode) { + case b_op: + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 27); + return; + case bl_op: + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 27); + regs->regs[1] = pc + LOONGARCH_INSN_SIZE; + return; + } + + imm_l = insn.reg1i21_format.immediate_l; + imm_h = insn.reg1i21_format.immediate_h; + rj = insn.reg1i21_format.rj; + switch (insn.reg1i21_format.opcode) { + case beqz_op: + if (regs->regs[rj] == 0) + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 22); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + return; + case bnez_op: + if (regs->regs[rj] != 0) + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 22); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + return; + } + + imm = insn.reg2i16_format.immediate; + rj = insn.reg2i16_format.rj; + rd = insn.reg2i16_format.rd; + switch (insn.reg2i16_format.opcode) { + case beq_op: + if (regs->regs[rj] == regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bne_op: + if (regs->regs[rj] != regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case blt_op: + if ((long)regs->regs[rj] < (long)regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bge_op: + if ((long)regs->regs[rj] >= (long)regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bltu_op: + if (regs->regs[rj] < regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bgeu_op: + if (regs->regs[rj] >= regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case jirl_op: + regs->csr_era = regs->regs[rj] + sign_extend64(imm << 2, 17); + regs->regs[rd] = pc + LOONGARCH_INSN_SIZE; + break; + default: + pr_info("%s: unknown opcode\n", __func__); + return; + } +} + int larch_insn_read(void *addr, u32 *insnp) { int ret; diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c new file mode 100644 index 000000000000..56c8c4b09a42 --- /dev/null +++ b/arch/loongarch/kernel/kprobes.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/kdebug.h> +#include <linux/kprobes.h> +#include <linux/preempt.h> +#include <asm/break.h> + +static const union loongarch_instruction breakpoint_insn = { + .reg0i15_format = { + .opcode = break_op, + .immediate = BRK_KPROBE_BP, + } +}; + +static const union loongarch_instruction singlestep_insn = { + .reg0i15_format = { + .opcode = break_op, + .immediate = BRK_KPROBE_SSTEPBP, + } +}; + +DEFINE_PER_CPU(struct kprobe *, current_kprobe); +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static bool insns_not_supported(union loongarch_instruction insn) +{ + switch (insn.reg2i14_format.opcode) { + case llw_op: + case lld_op: + case scw_op: + case scd_op: + pr_notice("kprobe: ll and sc instructions are not supported\n"); + return true; + } + + switch (insn.reg1i21_format.opcode) { + case bceqz_op: + pr_notice("kprobe: bceqz and bcnez instructions are not supported\n"); + return true; + } + + return false; +} +NOKPROBE_SYMBOL(insns_not_supported); + +static bool insns_need_simulation(struct kprobe *p) +{ + if (is_pc_ins(&p->opcode)) + return true; + + if (is_branch_ins(&p->opcode)) + return true; + + return false; +} +NOKPROBE_SYMBOL(insns_need_simulation); + +static void arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) +{ + if (is_pc_ins(&p->opcode)) + simu_pc(regs, p->opcode); + else if (is_branch_ins(&p->opcode)) + simu_branch(regs, p->opcode); +} +NOKPROBE_SYMBOL(arch_simulate_insn); + +static void arch_prepare_ss_slot(struct kprobe *p) +{ + p->ainsn.insn[0] = *p->addr; + p->ainsn.insn[1] = singlestep_insn; + p->ainsn.restore = (unsigned long)p->addr + LOONGARCH_INSN_SIZE; +} +NOKPROBE_SYMBOL(arch_prepare_ss_slot); + +static void arch_prepare_simulate(struct kprobe *p) +{ + p->ainsn.restore = 0; +} +NOKPROBE_SYMBOL(arch_prepare_simulate); + +int arch_prepare_kprobe(struct kprobe *p) +{ + if ((unsigned long)p->addr & 0x3) + return -EILSEQ; + + /* copy instruction */ + p->opcode = *p->addr; + + /* decode instruction */ + if (insns_not_supported(p->opcode)) + return -EINVAL; + + if (insns_need_simulation(p)) { + p->ainsn.insn = NULL; + } else { + p->ainsn.insn = get_insn_slot(); + if (!p->ainsn.insn) + return -ENOMEM; + } + + /* prepare the instruction */ + if (p->ainsn.insn) + arch_prepare_ss_slot(p); + else + arch_prepare_simulate(p); + + return 0; +} +NOKPROBE_SYMBOL(arch_prepare_kprobe); + +/* Install breakpoint in text */ +void arch_arm_kprobe(struct kprobe *p) +{ + *p->addr = breakpoint_insn; + flush_insn_slot(p); +} +NOKPROBE_SYMBOL(arch_arm_kprobe); + +/* Remove breakpoint from text */ +void arch_disarm_kprobe(struct kprobe *p) +{ + *p->addr = p->opcode; + flush_insn_slot(p); +} +NOKPROBE_SYMBOL(arch_disarm_kprobe); + +void arch_remove_kprobe(struct kprobe *p) +{ + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } +} +NOKPROBE_SYMBOL(arch_remove_kprobe); + +static void save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} +NOKPROBE_SYMBOL(save_previous_kprobe); + +static void restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; +} +NOKPROBE_SYMBOL(restore_previous_kprobe); + +static void set_current_kprobe(struct kprobe *p) +{ + __this_cpu_write(current_kprobe, p); +} +NOKPROBE_SYMBOL(set_current_kprobe); + +/* + * Interrupts need to be disabled before single-step mode is set, + * and not reenabled until after single-step mode ends. + * Without disabling interrupt on local CPU, there is a chance of + * interrupt occurrence in the period of exception return and start + * of out-of-line single-step, that result in wrongly single stepping + * into the interrupt handler. + */ +static void save_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + kcb->saved_status = regs->csr_prmd; + regs->csr_prmd &= ~CSR_PRMD_PIE; +} +NOKPROBE_SYMBOL(save_local_irqflag); + +static void restore_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + regs->csr_prmd = kcb->saved_status; +} +NOKPROBE_SYMBOL(restore_local_irqflag); + +static void post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + /* return addr restore if non-branching insn */ + if (cur->ainsn.restore != 0) + instruction_pointer_set(regs, cur->ainsn.restore); + + /* restore back original saved kprobe variables and continue */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + preempt_enable_no_resched(); + return; + } + + /* + * update the kcb status even if the cur->post_handler is + * not set because reset_curent_kprobe() doesn't update kcb. + */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) + cur->post_handler(cur, regs, 0); + + reset_current_kprobe(); + preempt_enable_no_resched(); +} +NOKPROBE_SYMBOL(post_kprobe_handler); + +static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + kcb->kprobe_status = KPROBE_HIT_SS; + } + + if (p->ainsn.insn) { + /* IRQs and single stepping do not mix well */ + save_local_irqflag(kcb, regs); + /* set ip register to prepare for single stepping */ + regs->csr_era = (unsigned long)p->ainsn.insn; + } else { + /* simulate single steping */ + arch_simulate_insn(p, regs); + /* now go for post processing */ + post_kprobe_handler(p, kcb, regs); + } +} +NOKPROBE_SYMBOL(setup_singlestep); + +static bool reenter_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_REENTER: + pr_warn("Failed to recover from reentered kprobes.\n"); + dump_kprobe(p); + WARN_ON_ONCE(1); + break; + default: + WARN_ON(1); + return false; + } + + return true; +} +NOKPROBE_SYMBOL(reenter_kprobe); + +bool kprobe_breakpoint_handler(struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb; + struct kprobe *p, *cur_kprobe; + kprobe_opcode_t *addr = (kprobe_opcode_t *)regs->csr_era; + + /* + * We don't want to be preempted for the entire + * duration of kprobe processing. + */ + preempt_disable(); + kcb = get_kprobe_ctlblk(); + cur_kprobe = kprobe_running(); + + p = get_kprobe(addr); + if (p) { + if (cur_kprobe) { + if (reenter_kprobe(p, regs, kcb)) + return true; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. + * + * pre_handler can hit a breakpoint and can step thru + * before return. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) { + setup_singlestep(p, regs, kcb, 0); + } else { + reset_current_kprobe(); + preempt_enable_no_resched(); + } + return true; + } + } + + if (addr->word != breakpoint_insn.word) { + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Return back to original instruction, and continue. + */ + regs->csr_era = (unsigned long)addr; + preempt_enable_no_resched(); + return true; + } + + preempt_enable_no_resched(); + return false; +} +NOKPROBE_SYMBOL(kprobe_breakpoint_handler); + +bool kprobe_singlestep_handler(struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long addr = instruction_pointer(regs); + + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.insn[1] == addr)) { + restore_local_irqflag(kcb, regs); + post_kprobe_handler(cur, kcb, regs); + return true; + } + + preempt_enable_no_resched(); + return false; +} +NOKPROBE_SYMBOL(kprobe_singlestep_handler); + +bool kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->csr_era = (unsigned long)cur->addr; + WARN_ON_ONCE(!instruction_pointer(regs)); + + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + } else { + restore_local_irqflag(kcb, regs); + reset_current_kprobe(); + } + preempt_enable_no_resched(); + break; + } + return false; +} +NOKPROBE_SYMBOL(kprobe_fault_handler); + +/* + * Provide a blacklist of symbols identifying ranges which cannot be kprobed. + * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). + */ +int __init arch_populate_kprobe_blacklist(void) +{ + return kprobe_add_area_blacklist((unsigned long)__irqentry_text_start, + (unsigned long)__irqentry_text_end); +} + +int __init arch_init_kprobes(void) +{ + return 0; +} + +/* ASM function that handles the kretprobes must not be probed */ +NOKPROBE_SYMBOL(__kretprobe_trampoline); + +/* Called from __kretprobe_trampoline */ +void __used *trampoline_probe_handler(struct pt_regs *regs) +{ + return (void *)kretprobe_trampoline_handler(regs, NULL); +} +NOKPROBE_SYMBOL(trampoline_probe_handler); + +void arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + ri->ret_addr = (kprobe_opcode_t *)regs->regs[1]; + ri->fp = NULL; + + /* Replace the return addr with trampoline addr */ + regs->regs[1] = (unsigned long)&__kretprobe_trampoline; +} +NOKPROBE_SYMBOL(arch_prepare_kretprobe); + +int arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} +NOKPROBE_SYMBOL(arch_trampoline_kprobe); diff --git a/arch/loongarch/kernel/kprobes_trampoline.S b/arch/loongarch/kernel/kprobes_trampoline.S new file mode 100644 index 000000000000..af94b0d213fa --- /dev/null +++ b/arch/loongarch/kernel/kprobes_trampoline.S @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#include <linux/linkage.h> +#include <asm/stackframe.h> + + .text + + .macro save_all_base_regs + cfi_st ra, PT_R1 + cfi_st tp, PT_R2 + cfi_st a0, PT_R4 + cfi_st a1, PT_R5 + cfi_st a2, PT_R6 + cfi_st a3, PT_R7 + cfi_st a4, PT_R8 + cfi_st a5, PT_R9 + cfi_st a6, PT_R10 + cfi_st a7, PT_R11 + cfi_st t0, PT_R12 + cfi_st t1, PT_R13 + cfi_st t2, PT_R14 + cfi_st t3, PT_R15 + cfi_st t4, PT_R16 + cfi_st t5, PT_R17 + cfi_st t6, PT_R18 + cfi_st t7, PT_R19 + cfi_st t8, PT_R20 + cfi_st u0, PT_R21 + cfi_st fp, PT_R22 + cfi_st s0, PT_R23 + cfi_st s1, PT_R24 + cfi_st s2, PT_R25 + cfi_st s3, PT_R26 + cfi_st s4, PT_R27 + cfi_st s5, PT_R28 + cfi_st s6, PT_R29 + cfi_st s7, PT_R30 + cfi_st s8, PT_R31 + csrrd t0, LOONGARCH_CSR_CRMD + andi t0, t0, 0x7 /* extract bit[1:0] PLV, bit[2] IE */ + LONG_S t0, sp, PT_CRMD + .endm + + .macro restore_all_base_regs + cfi_ld tp, PT_R2 + cfi_ld a0, PT_R4 + cfi_ld a1, PT_R5 + cfi_ld a2, PT_R6 + cfi_ld a3, PT_R7 + cfi_ld a4, PT_R8 + cfi_ld a5, PT_R9 + cfi_ld a6, PT_R10 + cfi_ld a7, PT_R11 + cfi_ld t0, PT_R12 + cfi_ld t1, PT_R13 + cfi_ld t2, PT_R14 + cfi_ld t3, PT_R15 + cfi_ld t4, PT_R16 + cfi_ld t5, PT_R17 + cfi_ld t6, PT_R18 + cfi_ld t7, PT_R19 + cfi_ld t8, PT_R20 + cfi_ld u0, PT_R21 + cfi_ld fp, PT_R22 + cfi_ld s0, PT_R23 + cfi_ld s1, PT_R24 + cfi_ld s2, PT_R25 + cfi_ld s3, PT_R26 + cfi_ld s4, PT_R27 + cfi_ld s5, PT_R28 + cfi_ld s6, PT_R29 + cfi_ld s7, PT_R30 + cfi_ld s8, PT_R31 + LONG_L t0, sp, PT_CRMD + li.d t1, 0x7 /* mask bit[1:0] PLV, bit[2] IE */ + csrxchg t0, t1, LOONGARCH_CSR_CRMD + .endm + +SYM_CODE_START(__kretprobe_trampoline) + addi.d sp, sp, -PT_SIZE + save_all_base_regs + + addi.d t0, sp, PT_SIZE + LONG_S t0, sp, PT_R3 + + move a0, sp /* pt_regs */ + + bl trampoline_probe_handler + + /* use the result as the return-address */ + move ra, a0 + + restore_all_base_regs + addi.d sp, sp, PT_SIZE + + jr ra +SYM_CODE_END(__kretprobe_trampoline) diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index edfd220a3737..fa2443c7afb2 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -18,6 +18,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> +#include <linux/hw_breakpoint.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/unistd.h> @@ -96,6 +97,11 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->regs[3] = sp; } +void flush_thread(void) +{ + flush_ptrace_hw_breakpoint(current); +} + void exit_thread(struct task_struct *tsk) { } @@ -181,6 +187,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs->regs[2] = tls; out: + ptrace_hw_copy_thread(p); clear_tsk_thread_flag(p, TIF_USEDFPU); clear_tsk_thread_flag(p, TIF_USEDSIMD); clear_tsk_thread_flag(p, TIF_LSX_CTX_LIVE); diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index dc2b82ea894c..06bceae7d104 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -20,7 +20,9 @@ #include <linux/context_tracking.h> #include <linux/elf.h> #include <linux/errno.h> +#include <linux/hw_breakpoint.h> #include <linux/mm.h> +#include <linux/nospec.h> #include <linux/ptrace.h> #include <linux/regset.h> #include <linux/sched.h> @@ -29,6 +31,7 @@ #include <linux/smp.h> #include <linux/stddef.h> #include <linux/seccomp.h> +#include <linux/thread_info.h> #include <linux/uaccess.h> #include <asm/byteorder.h> @@ -39,6 +42,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/processor.h> +#include <asm/ptrace.h> #include <asm/reg.h> #include <asm/syscall.h> @@ -246,6 +250,384 @@ static int cfg_set(struct task_struct *target, return 0; } +#ifdef CONFIG_HAVE_HW_BREAKPOINT + +/* + * Handle hitting a HW-breakpoint. + */ +static void ptrace_hbptriggered(struct perf_event *bp, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + int i; + struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); + + for (i = 0; i < LOONGARCH_MAX_BRP; ++i) + if (current->thread.hbp_break[i] == bp) + break; + + for (i = 0; i < LOONGARCH_MAX_WRP; ++i) + if (current->thread.hbp_watch[i] == bp) + break; + + force_sig_ptrace_errno_trap(i, (void __user *)bkpt->address); +} + +static struct perf_event *ptrace_hbp_get_event(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + struct perf_event *bp; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if (idx >= LOONGARCH_MAX_BRP) + return ERR_PTR(-EINVAL); + idx = array_index_nospec(idx, LOONGARCH_MAX_BRP); + bp = tsk->thread.hbp_break[idx]; + break; + case NT_LOONGARCH_HW_WATCH: + if (idx >= LOONGARCH_MAX_WRP) + return ERR_PTR(-EINVAL); + idx = array_index_nospec(idx, LOONGARCH_MAX_WRP); + bp = tsk->thread.hbp_watch[idx]; + break; + } + + return bp; +} + +static int ptrace_hbp_set_event(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, + struct perf_event *bp) +{ + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if (idx >= LOONGARCH_MAX_BRP) + return -EINVAL; + idx = array_index_nospec(idx, LOONGARCH_MAX_BRP); + tsk->thread.hbp_break[idx] = bp; + break; + case NT_LOONGARCH_HW_WATCH: + if (idx >= LOONGARCH_MAX_WRP) + return -EINVAL; + idx = array_index_nospec(idx, LOONGARCH_MAX_WRP); + tsk->thread.hbp_watch[idx] = bp; + break; + } + + return 0; +} + +static struct perf_event *ptrace_hbp_create(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + int err, type; + struct perf_event *bp; + struct perf_event_attr attr; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + type = HW_BREAKPOINT_X; + break; + case NT_LOONGARCH_HW_WATCH: + type = HW_BREAKPOINT_RW; + break; + default: + return ERR_PTR(-EINVAL); + } + + ptrace_breakpoint_init(&attr); + + /* + * Initialise fields to sane defaults + * (i.e. values that will pass validation). + */ + attr.bp_addr = 0; + attr.bp_len = HW_BREAKPOINT_LEN_4; + attr.bp_type = type; + attr.disabled = 1; + + bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk); + if (IS_ERR(bp)) + return bp; + + err = ptrace_hbp_set_event(note_type, tsk, idx, bp); + if (err) + return ERR_PTR(err); + + return bp; +} + +static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, + struct arch_hw_breakpoint_ctrl ctrl, + struct perf_event_attr *attr) +{ + int err, len, type, offset; + + err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + if (err) + return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if ((type & HW_BREAKPOINT_X) != type) + return -EINVAL; + break; + case NT_LOONGARCH_HW_WATCH: + if ((type & HW_BREAKPOINT_RW) != type) + return -EINVAL; + break; + default: + return -EINVAL; + } + + attr->bp_len = len; + attr->bp_type = type; + attr->bp_addr += offset; + + return 0; +} + +static int ptrace_hbp_get_resource_info(unsigned int note_type, u16 *info) +{ + u8 num; + u16 reg = 0; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + num = hw_breakpoint_slots(TYPE_INST); + break; + case NT_LOONGARCH_HW_WATCH: + num = hw_breakpoint_slots(TYPE_DATA); + break; + default: + return -EINVAL; + } + + *info = reg | num; + + return 0; +} + +static struct perf_event *ptrace_hbp_get_initialised_bp(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (!bp) + bp = ptrace_hbp_create(note_type, tsk, idx); + + return bp; +} + +static int ptrace_hbp_get_ctrl(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u32 *ctrl) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *ctrl = bp ? encode_ctrl_reg(counter_arch_bp(bp)->ctrl) : 0; + + return 0; +} + +static int ptrace_hbp_get_mask(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 *mask) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *mask = bp ? counter_arch_bp(bp)->mask : 0; + + return 0; +} + +static int ptrace_hbp_get_addr(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 *addr) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *addr = bp ? counter_arch_bp(bp)->address : 0; + + return 0; +} + +static int ptrace_hbp_set_ctrl(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u32 uctrl) +{ + int err; + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint_ctrl ctrl; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + decode_ctrl_reg(uctrl, &ctrl); + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + + return modify_user_hw_breakpoint(bp, &attr); +} + +static int ptrace_hbp_set_mask(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 mask) +{ + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint *info; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + info = counter_arch_bp(bp); + info->mask = mask; + + return modify_user_hw_breakpoint(bp, &attr); +} + +static int ptrace_hbp_set_addr(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 addr) +{ + struct perf_event *bp; + struct perf_event_attr attr; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + attr.bp_addr = addr; + + return modify_user_hw_breakpoint(bp, &attr); +} + +#define PTRACE_HBP_CTRL_SZ sizeof(u32) +#define PTRACE_HBP_ADDR_SZ sizeof(u64) +#define PTRACE_HBP_MASK_SZ sizeof(u64) + +static int hw_break_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + u16 info; + u32 ctrl; + u64 addr, mask; + int ret, idx = 0; + unsigned int note_type = regset->core_note_type; + + /* Resource info */ + ret = ptrace_hbp_get_resource_info(note_type, &info); + if (ret) + return ret; + + membuf_write(&to, &info, sizeof(info)); + + /* (address, ctrl) registers */ + while (to.left) { + ret = ptrace_hbp_get_addr(note_type, target, idx, &addr); + if (ret) + return ret; + + ret = ptrace_hbp_get_mask(note_type, target, idx, &mask); + if (ret) + return ret; + + ret = ptrace_hbp_get_ctrl(note_type, target, idx, &ctrl); + if (ret) + return ret; + + membuf_store(&to, addr); + membuf_store(&to, mask); + membuf_store(&to, ctrl); + idx++; + } + + return 0; +} + +static int hw_break_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u32 ctrl; + u64 addr, mask; + int ret, idx = 0, offset, limit; + unsigned int note_type = regset->core_note_type; + + /* Resource info */ + offset = offsetof(struct user_watch_state, dbg_regs); + user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); + + /* (address, ctrl) registers */ + limit = regset->n * regset->size; + while (count && offset < limit) { + if (count < PTRACE_HBP_ADDR_SZ) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr, + offset, offset + PTRACE_HBP_ADDR_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_addr(note_type, target, idx, addr); + if (ret) + return ret; + offset += PTRACE_HBP_ADDR_SZ; + + if (!count) + break; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, + offset, offset + PTRACE_HBP_ADDR_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_mask(note_type, target, idx, mask); + if (ret) + return ret; + offset += PTRACE_HBP_MASK_SZ; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, + offset, offset + PTRACE_HBP_MASK_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_ctrl(note_type, target, idx, ctrl); + if (ret) + return ret; + offset += PTRACE_HBP_CTRL_SZ; + idx++; + } + + return 0; +} + +#endif + struct pt_regs_offset { const char *name; int offset; @@ -319,6 +701,10 @@ enum loongarch_regset { REGSET_GPR, REGSET_FPR, REGSET_CPUCFG, +#ifdef CONFIG_HAVE_HW_BREAKPOINT + REGSET_HW_BREAK, + REGSET_HW_WATCH, +#endif }; static const struct user_regset loongarch64_regsets[] = { @@ -346,6 +732,24 @@ static const struct user_regset loongarch64_regsets[] = { .regset_get = cfg_get, .set = cfg_set, }, +#ifdef CONFIG_HAVE_HW_BREAKPOINT + [REGSET_HW_BREAK] = { + .core_note_type = NT_LOONGARCH_HW_BREAK, + .n = sizeof(struct user_watch_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = hw_break_get, + .set = hw_break_set, + }, + [REGSET_HW_WATCH] = { + .core_note_type = NT_LOONGARCH_HW_WATCH, + .n = sizeof(struct user_watch_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = hw_break_get, + .set = hw_break_set, + }, +#endif }; static const struct user_regset_view user_loongarch64_view = { @@ -431,3 +835,71 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +static void ptrace_triggered(struct perf_event *bp, + struct perf_sample_data *data, struct pt_regs *regs) +{ + struct perf_event_attr attr; + + attr = bp->attr; + attr.disabled = true; + modify_user_hw_breakpoint(bp, &attr); +} + +static int set_single_step(struct task_struct *tsk, unsigned long addr) +{ + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint *info; + struct thread_struct *thread = &tsk->thread; + + bp = thread->hbp_break[0]; + if (!bp) { + ptrace_breakpoint_init(&attr); + + attr.bp_addr = addr; + attr.bp_len = HW_BREAKPOINT_LEN_8; + attr.bp_type = HW_BREAKPOINT_X; + + bp = register_user_hw_breakpoint(&attr, ptrace_triggered, + NULL, tsk); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + thread->hbp_break[0] = bp; + } else { + int err; + + attr = bp->attr; + attr.bp_addr = addr; + + /* Reenable breakpoint */ + attr.disabled = false; + err = modify_user_hw_breakpoint(bp, &attr); + if (unlikely(err)) + return err; + + csr_write64(attr.bp_addr, LOONGARCH_CSR_IB0ADDR); + } + info = counter_arch_bp(bp); + info->mask = TASK_SIZE - 1; + + return 0; +} + +/* ptrace API */ +void user_enable_single_step(struct task_struct *task) +{ + struct thread_info *ti = task_thread_info(task); + + set_single_step(task, task_pt_regs(task)->csr_era); + task->thread.single_step = task_pt_regs(task)->csr_era; + set_ti_thread_flag(ti, TIF_SINGLESTEP); +} + +void user_disable_single_step(struct task_struct *task) +{ + clear_tsk_thread_flag(task, TIF_SINGLESTEP); +} +#endif diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c new file mode 100644 index 000000000000..01f94d1e3edf --- /dev/null +++ b/arch/loongarch/kernel/relocate.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for Kernel relocation at boot time + * + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +#include <linux/elf.h> +#include <linux/kernel.h> +#include <linux/printk.h> +#include <linux/panic_notifier.h> +#include <linux/start_kernel.h> +#include <asm/bootinfo.h> +#include <asm/early_ioremap.h> +#include <asm/inst.h> +#include <asm/sections.h> +#include <asm/setup.h> + +#define RELOCATED(x) ((void *)((long)x + reloc_offset)) +#define RELOCATED_KASLR(x) ((void *)((long)x + random_offset)) + +static unsigned long reloc_offset; + +static inline void __init relocate_relative(void) +{ + Elf64_Rela *rela, *rela_end; + rela = (Elf64_Rela *)&__rela_dyn_begin; + rela_end = (Elf64_Rela *)&__rela_dyn_end; + + for ( ; rela < rela_end; rela++) { + Elf64_Addr addr = rela->r_offset; + Elf64_Addr relocated_addr = rela->r_addend; + + if (rela->r_info != R_LARCH_RELATIVE) + continue; + + if (relocated_addr >= VMLINUX_LOAD_ADDRESS) + relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr); + + *(Elf64_Addr *)RELOCATED(addr) = relocated_addr; + } +} + +static inline void __init relocate_absolute(long random_offset) +{ + void *begin, *end; + struct rela_la_abs *p; + + begin = RELOCATED_KASLR(&__la_abs_begin); + end = RELOCATED_KASLR(&__la_abs_end); + + for (p = begin; (void *)p < end; p++) { + long v = p->symvalue; + uint32_t lu12iw, ori, lu32id, lu52id; + union loongarch_instruction *insn = (void *)p - p->offset; + + lu12iw = (v >> 12) & 0xfffff; + ori = v & 0xfff; + lu32id = (v >> 32) & 0xfffff; + lu52id = v >> 52; + + insn[0].reg1i20_format.immediate = lu12iw; + insn[1].reg2i12_format.immediate = ori; + insn[2].reg1i20_format.immediate = lu32id; + insn[3].reg2i12_format.immediate = lu52id; + } +} + +#ifdef CONFIG_RANDOMIZE_BASE +static inline __init unsigned long rotate_xor(unsigned long hash, + const void *area, size_t size) +{ + size_t i, diff; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + + diff = (void *)ptr - area; + if (size < diff + sizeof(hash)) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); + + for (i = 0; i < size / sizeof(hash); i++) { + /* Rotate by odd number of bits and XOR. */ + hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7); + hash ^= ptr[i]; + } + + return hash; +} + +static inline __init unsigned long get_random_boot(void) +{ + unsigned long hash = 0; + unsigned long entropy = random_get_entropy(); + + /* Attempt to create a simple but unpredictable starting entropy. */ + hash = rotate_xor(hash, linux_banner, strlen(linux_banner)); + + /* Add in any runtime entropy we can get */ + hash = rotate_xor(hash, &entropy, sizeof(entropy)); + + return hash; +} + +static inline __init bool kaslr_disabled(void) +{ + char *str; + const char *builtin_cmdline = CONFIG_CMDLINE; + + str = strstr(builtin_cmdline, "nokaslr"); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return true; + + str = strstr(boot_command_line, "nokaslr"); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return true; + + return false; +} + +/* Choose a new address for the kernel */ +static inline void __init *determine_relocation_address(void) +{ + unsigned long kernel_length; + unsigned long random_offset; + void *destination = _text; + + if (kaslr_disabled()) + return destination; + + kernel_length = (long)_end - (long)_text; + + random_offset = get_random_boot() << 16; + random_offset &= (CONFIG_RANDOMIZE_BASE_MAX_OFFSET - 1); + if (random_offset < kernel_length) + random_offset += ALIGN(kernel_length, 0xffff); + + return RELOCATED_KASLR(destination); +} + +static inline int __init relocation_addr_valid(void *location_new) +{ + if ((unsigned long)location_new & 0x00000ffff) + return 0; /* Inappropriately aligned new location */ + + if ((unsigned long)location_new < (unsigned long)_end) + return 0; /* New location overlaps original kernel */ + + return 1; +} +#endif + +static inline void __init update_reloc_offset(unsigned long *addr, long random_offset) +{ + unsigned long *new_addr = (unsigned long *)RELOCATED_KASLR(addr); + + *new_addr = (unsigned long)reloc_offset; +} + +void * __init relocate_kernel(void) +{ + unsigned long kernel_length; + unsigned long random_offset = 0; + void *location_new = _text; /* Default to original kernel start */ + void *kernel_entry = start_kernel; /* Default to original kernel entry point */ + char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ + + strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE); + +#ifdef CONFIG_RANDOMIZE_BASE + location_new = determine_relocation_address(); + + /* Sanity check relocation address */ + if (relocation_addr_valid(location_new)) + random_offset = (unsigned long)location_new - (unsigned long)(_text); +#endif + reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS; + + if (random_offset) { + kernel_length = (long)(_end) - (long)(_text); + + /* Copy the kernel to it's new location */ + memcpy(location_new, _text, kernel_length); + + /* Sync the caches ready for execution of new kernel */ + __asm__ __volatile__ ( + "ibar 0 \t\n" + "dbar 0 \t\n" + ::: "memory"); + + reloc_offset += random_offset; + + /* Return the new kernel's entry point */ + kernel_entry = RELOCATED_KASLR(start_kernel); + + /* The current thread is now within the relocated kernel */ + __current_thread_info = RELOCATED_KASLR(__current_thread_info); + + update_reloc_offset(&reloc_offset, random_offset); + } + + if (reloc_offset) + relocate_relative(); + + relocate_absolute(random_offset); + + return kernel_entry; +} + +/* + * Show relocation information on panic. + */ +static void show_kernel_relocation(const char *level) +{ + if (reloc_offset > 0) { + printk(level); + pr_cont("Kernel relocated by 0x%lx\n", reloc_offset); + pr_cont(" .text @ 0x%px\n", _text); + pr_cont(" .data @ 0x%px\n", _sdata); + pr_cont(" .bss @ 0x%px\n", __bss_start); + } +} + +static int kernel_location_notifier_fn(struct notifier_block *self, + unsigned long v, void *p) +{ + show_kernel_relocation(KERN_EMERG); + return NOTIFY_DONE; +} + +static struct notifier_block kernel_location_notifier = { + .notifier_call = kernel_location_notifier_fn +}; + +static int __init register_kernel_offset_dumper(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_location_notifier); + return 0; +} + +arch_initcall(register_kernel_offset_dumper); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 4344502c0b31..bae84ccf6d36 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -234,11 +234,14 @@ static void __init arch_reserve_vmcore(void) #endif } +/* 2MB alignment for crash kernel regions */ +#define CRASH_ALIGN SZ_2M +#define CRASH_ADDR_MAX SZ_4G + static void __init arch_parse_crashkernel(void) { #ifdef CONFIG_KEXEC int ret; - unsigned long long start; unsigned long long total_mem; unsigned long long crash_base, crash_size; @@ -247,8 +250,13 @@ static void __init arch_parse_crashkernel(void) if (ret < 0 || crash_size <= 0) return; - start = memblock_phys_alloc_range(crash_size, 1, crash_base, crash_base + crash_size); - if (start != crash_base) { + if (crash_base <= 0) { + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, CRASH_ALIGN, CRASH_ADDR_MAX); + if (!crash_base) { + pr_warn("crashkernel reservation failed - No suitable area found.\n"); + return; + } + } else if (!memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_base + crash_size)) { pr_warn("Invalid memory region reserved for crash kernel\n"); return; } diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index a6576dea590c..4351f69d9950 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -140,16 +140,17 @@ static int get_timer_irq(void) int constant_clockevent_init(void) { - int irq; unsigned int cpu = smp_processor_id(); unsigned long min_delta = 0x600; unsigned long max_delta = (1UL << 48) - 1; struct clock_event_device *cd; - static int timer_irq_installed = 0; + static int irq = 0, timer_irq_installed = 0; - irq = get_timer_irq(); - if (irq < 0) - pr_err("Failed to map irq %d (timer)\n", irq); + if (!timer_irq_installed) { + irq = get_timer_irq(); + if (irq < 0) + pr_err("Failed to map irq %d (timer)\n", irq); + } cd = &per_cpu(constant_clockevent_device, cpu); diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index c38a146a973b..de8ebe20b666 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -371,9 +371,14 @@ int no_unaligned_warning __read_mostly = 1; /* Only 1 warning by default */ asmlinkage void noinstr do_ale(struct pt_regs *regs) { - unsigned int *pc; irqentry_state_t state = irqentry_enter(regs); +#ifndef CONFIG_ARCH_STRICT_ALIGN + die_if_kernel("Kernel ale access", regs); + force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); +#else + unsigned int *pc; + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr); /* @@ -397,8 +402,8 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs) sigbus: die_if_kernel("Kernel ale access", regs); force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); - out: +#endif irqentry_exit(regs, state); } @@ -432,7 +437,9 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs) unsigned long era = exception_era(regs); irqentry_state_t state = irqentry_enter(regs); - local_irq_enable(); + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_enable(); + current->thread.trap_nr = read_csr_excode(); if (__get_inst(&opcode, (u32 *)era, user)) goto out_sigsegv; @@ -445,14 +452,12 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs) */ switch (bcode) { case BRK_KPROBE_BP: - if (notify_die(DIE_BREAK, "Kprobe", regs, bcode, - current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP) + if (kprobe_breakpoint_handler(regs)) goto out; else break; case BRK_KPROBE_SSTEPBP: - if (notify_die(DIE_SSTEPBP, "Kprobe_SingleStep", regs, bcode, - current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP) + if (kprobe_singlestep_handler(regs)) goto out; else break; @@ -495,7 +500,9 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs) } out: - local_irq_disable(); + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_disable(); + irqentry_exit(regs, state); return; @@ -506,7 +513,52 @@ out_sigsegv: asmlinkage void noinstr do_watch(struct pt_regs *regs) { + irqentry_state_t state = irqentry_enter(regs); + +#ifndef CONFIG_HAVE_HW_BREAKPOINT pr_warn("Hardware watch point handler not implemented!\n"); +#else + if (test_tsk_thread_flag(current, TIF_SINGLESTEP)) { + int llbit = (csr_read32(LOONGARCH_CSR_LLBCTL) & 0x1); + unsigned long pc = instruction_pointer(regs); + union loongarch_instruction *ip = (union loongarch_instruction *)pc; + + if (llbit) { + /* + * When the ll-sc combo is encountered, it is regarded as an single + * instruction. So don't clear llbit and reset CSR.FWPS.Skip until + * the llsc execution is completed. + */ + csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS); + csr_write32(CSR_LLBCTL_KLO, LOONGARCH_CSR_LLBCTL); + goto out; + } + + if (pc == current->thread.single_step) { + /* + * Certain insns are occasionally not skipped when CSR.FWPS.Skip is + * set, such as fld.d/fst.d. So singlestep needs to compare whether + * the csr_era is equal to the value of singlestep which last time set. + */ + if (!is_self_loop_ins(ip, regs)) { + /* + * Check if the given instruction the target pc is equal to the + * current pc, If yes, then we should not set the CSR.FWPS.SKIP + * bit to break the original instruction stream. + */ + csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS); + goto out; + } + } + } else { + breakpoint_handler(regs); + watchpoint_handler(regs); + } + + force_sig(SIGTRAP); +out: +#endif + irqentry_exit(regs, state); } asmlinkage void noinstr do_ri(struct pt_regs *regs) diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index 78506b31ba61..0c7b041be9d8 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -65,10 +65,21 @@ SECTIONS __alt_instructions_end = .; } +#ifdef CONFIG_RELOCATABLE + . = ALIGN(8); + .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) { + __la_abs_begin = .; + *(.la_abs) + __la_abs_end = .; + } +#endif + .got : ALIGN(16) { *(.got) } .plt : ALIGN(16) { *(.plt) } .got.plt : ALIGN(16) { *(.got.plt) } + .data.rel : { *(.data.rel*) } + . = ALIGN(PECOFF_SEGMENT_ALIGN); __init_begin = .; __inittext_begin = .; @@ -92,8 +103,6 @@ SECTIONS PERCPU_SECTION(1 << CONFIG_L1_CACHE_SHIFT) #endif - .rela.dyn : ALIGN(8) { *(.rela.dyn) *(.rela*) } - .init.bss : { *(.init.bss) } @@ -106,6 +115,12 @@ SECTIONS RO_DATA(4096) RW_DATA(1 << CONFIG_L1_CACHE_SHIFT, PAGE_SIZE, THREAD_SIZE) + .rela.dyn : ALIGN(8) { + __rela_dyn_begin = .; + *(.rela.dyn) *(.rela*) + __rela_dyn_end = .; + } + .sdata : { *(.sdata) } @@ -132,6 +147,7 @@ SECTIONS DISCARDS /DISCARD/ : { + *(.dynamic .dynsym .dynstr .hash .gnu.hash) *(.gnu.attributes) *(.options) *(.eh_frame) diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index 7c07d595ee89..3b7e1dec7109 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -17,6 +17,7 @@ SYM_FUNC_START(memcpy) ALTERNATIVE "b __memcpy_generic", \ "b __memcpy_fast", CPU_FEATURE_UAL SYM_FUNC_END(memcpy) +_ASM_NOKPROBE(memcpy) EXPORT_SYMBOL(memcpy) @@ -41,6 +42,7 @@ SYM_FUNC_START(__memcpy_generic) 2: move a0, a3 jr ra SYM_FUNC_END(__memcpy_generic) +_ASM_NOKPROBE(__memcpy_generic) /* * void *__memcpy_fast(void *dst, const void *src, size_t n) @@ -93,3 +95,4 @@ SYM_FUNC_START(__memcpy_fast) 3: move a0, a3 jr ra SYM_FUNC_END(__memcpy_fast) +_ASM_NOKPROBE(__memcpy_fast) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S index 6ffdb46da78f..b796c3d6da05 100644 --- a/arch/loongarch/lib/memmove.S +++ b/arch/loongarch/lib/memmove.S @@ -29,6 +29,7 @@ SYM_FUNC_START(memmove) b rmemcpy 4: b __rmemcpy_generic SYM_FUNC_END(memmove) +_ASM_NOKPROBE(memmove) EXPORT_SYMBOL(memmove) @@ -39,6 +40,7 @@ SYM_FUNC_START(rmemcpy) ALTERNATIVE "b __rmemcpy_generic", \ "b __rmemcpy_fast", CPU_FEATURE_UAL SYM_FUNC_END(rmemcpy) +_ASM_NOKPROBE(rmemcpy) /* * void *__rmemcpy_generic(void *dst, const void *src, size_t n) @@ -64,6 +66,7 @@ SYM_FUNC_START(__rmemcpy_generic) 2: move a0, a3 jr ra SYM_FUNC_END(__rmemcpy_generic) +_ASM_NOKPROBE(__rmemcpy_generic) /* * void *__rmemcpy_fast(void *dst, const void *src, size_t n) @@ -119,3 +122,4 @@ SYM_FUNC_START(__rmemcpy_fast) 3: move a0, a3 jr ra SYM_FUNC_END(__rmemcpy_fast) +_ASM_NOKPROBE(__rmemcpy_fast) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index e7cb4ea3747d..a9eb732ab2ad 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -23,6 +23,7 @@ SYM_FUNC_START(memset) ALTERNATIVE "b __memset_generic", \ "b __memset_fast", CPU_FEATURE_UAL SYM_FUNC_END(memset) +_ASM_NOKPROBE(memset) EXPORT_SYMBOL(memset) @@ -45,6 +46,7 @@ SYM_FUNC_START(__memset_generic) 2: move a0, a3 jr ra SYM_FUNC_END(__memset_generic) +_ASM_NOKPROBE(__memset_generic) /* * void *__memset_fast(void *s, int c, size_t n) @@ -89,3 +91,4 @@ SYM_FUNC_START(__memset_fast) 3: move a0, a3 jr ra SYM_FUNC_END(__memset_fast) +_ASM_NOKPROBE(__memset_fast) diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 1ccd53655cab..449087bd589d 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -135,6 +135,9 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, struct vm_area_struct *vma = NULL; vm_fault_t fault; + if (kprobe_page_fault(regs, current->thread.trap_nr)) + return; + /* * We fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index 58781c6e4191..244e2f5aeee5 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -24,8 +24,7 @@ move a0, sp REG_S a2, sp, PT_BVADDR li.w a1, \write - la.abs t0, do_page_fault - jirl ra, t0, 0 + bl do_page_fault RESTORE_ALL_AND_RET SYM_FUNC_END(tlb_do_page_fault_\write) .endm @@ -40,7 +39,7 @@ SYM_FUNC_START(handle_tlb_protect) move a1, zero csrrd a2, LOONGARCH_CSR_BADV REG_S a2, sp, PT_BVADDR - la.abs t0, do_page_fault + la_abs t0, do_page_fault jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_tlb_protect) @@ -116,7 +115,7 @@ smp_pgtable_change_load: #ifdef CONFIG_64BIT vmalloc_load: - la.abs t1, swapper_pg_dir + la_abs t1, swapper_pg_dir b vmalloc_done_load #endif @@ -187,7 +186,7 @@ tlb_huge_update_load: nopage_tlb_load: dbar 0 csrrd ra, EXCEPTION_KS2 - la.abs t0, tlb_do_page_fault_0 + la_abs t0, tlb_do_page_fault_0 jr t0 SYM_FUNC_END(handle_tlb_load) @@ -263,7 +262,7 @@ smp_pgtable_change_store: #ifdef CONFIG_64BIT vmalloc_store: - la.abs t1, swapper_pg_dir + la_abs t1, swapper_pg_dir b vmalloc_done_store #endif @@ -336,7 +335,7 @@ tlb_huge_update_store: nopage_tlb_store: dbar 0 csrrd ra, EXCEPTION_KS2 - la.abs t0, tlb_do_page_fault_1 + la_abs t0, tlb_do_page_fault_1 jr t0 SYM_FUNC_END(handle_tlb_store) @@ -411,7 +410,7 @@ smp_pgtable_change_modify: #ifdef CONFIG_64BIT vmalloc_modify: - la.abs t1, swapper_pg_dir + la_abs t1, swapper_pg_dir b vmalloc_done_modify #endif @@ -483,7 +482,7 @@ tlb_huge_update_modify: nopage_tlb_modify: dbar 0 csrrd ra, EXCEPTION_KS2 - la.abs t0, tlb_do_page_fault_1 + la_abs t0, tlb_do_page_fault_1 jr t0 SYM_FUNC_END(handle_tlb_modify) diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S index eb2675642f9f..90da899c06a1 100644 --- a/arch/loongarch/power/suspend_asm.S +++ b/arch/loongarch/power/suspend_asm.S @@ -78,9 +78,8 @@ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL) li.d t0, CSR_DMW1_INIT # CA, PLV0 csrwr t0, LOONGARCH_CSR_DMWIN1 - la.abs t0, 0f - jr t0 -0: + JUMP_VIRT_ADDR t0, t1 + la.pcrel t0, acpi_saved_sp ld.d sp, t0, 0 SETUP_WAKEUP diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index 3a2bb2e8fdad..fbff1cea62ca 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -326,16 +326,16 @@ void __init setup_arch(char **cmdline_p) panic("No configuration setup"); } -#ifdef CONFIG_BLK_DEV_INITRD - if (m68k_ramdisk.size) { + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && m68k_ramdisk.size) memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size); + + paging_init(); + + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && m68k_ramdisk.size) { initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr); initrd_end = initrd_start + m68k_ramdisk.size; pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end); } -#endif - - paging_init(); #ifdef CONFIG_NATFEAT nf_init(); diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 5c8cba0efc63..a700807c9b6d 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -30,6 +30,7 @@ #include <linux/init.h> #include <linux/ptrace.h> #include <linux/kallsyms.h> +#include <linux/extable.h> #include <asm/setup.h> #include <asm/fpu.h> @@ -545,7 +546,8 @@ static inline void bus_error030 (struct frame *fp) errorcode |= 2; if (mmusr & (MMU_I | MMU_WP)) { - if (ssw & 4) { + /* We might have an exception table for this PC */ + if (ssw & 4 && !search_exception_tables(fp->ptregs.pc)) { pr_err("Data %s fault at %#010lx in %s (pc=%#lx)\n", ssw & RW ? "read" : "write", fp->un.fmtb.daddr, diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 4d2837eb3e2a..228128e45c67 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -138,8 +138,11 @@ good_area: fault = handle_mm_fault(vma, address, flags, regs); pr_debug("handle_mm_fault returns %x\n", fault); - if (fault_signal_pending(fault, regs)) + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + goto no_context; return 0; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 2a375637e007..911301224078 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -437,7 +437,7 @@ void __init paging_init(void) } min_addr = m68k_memory[0].addr; - max_addr = min_addr + m68k_memory[0].size; + max_addr = min_addr + m68k_memory[0].size - 1; memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, MEMBLOCK_NONE); for (i = 1; i < m68k_num_memory;) { @@ -452,21 +452,21 @@ void __init paging_init(void) } memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i, MEMBLOCK_NONE); - addr = m68k_memory[i].addr + m68k_memory[i].size; + addr = m68k_memory[i].addr + m68k_memory[i].size - 1; if (addr > max_addr) max_addr = addr; i++; } m68k_memoffset = min_addr - PAGE_OFFSET; - m68k_virt_to_node_shift = fls(max_addr - min_addr - 1) - 6; + m68k_virt_to_node_shift = fls(max_addr - min_addr) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); flush_icache(); - high_memory = phys_to_virt(max_addr); + high_memory = phys_to_virt(max_addr) + 1; min_low_pfn = availmem >> PAGE_SHIFT; - max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT; + max_pfn = max_low_pfn = (max_addr >> PAGE_SHIFT) + 1; /* Reserve kernel text/data/bss and the memory allocated in head.S */ memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr); diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index 5c40c3ebe52f..687714db6f4d 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -219,8 +219,11 @@ 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)) + bad_page_fault(regs, address, SIGBUS); return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 5ea07c833c5b..459dc6023cf8 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -607,7 +607,6 @@ config RALINK select DMA_NONCOHERENT select IRQ_MIPS_CPU select USE_OF - select SYS_HAS_CPU_MIPS32_R1 select SYS_HAS_CPU_MIPS32_R2 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN @@ -1077,11 +1076,6 @@ config FW_CFE config ARCH_SUPPORTS_UPROBES bool -config DMA_PERDEV_COHERENT - bool - select ARCH_HAS_SETUP_DMA_OPS - select DMA_NONCOHERENT - config DMA_NONCOHERENT bool # @@ -3203,6 +3197,10 @@ config CC_HAS_MNO_BRANCH_LIKELY def_bool y depends on $(cc-option,-mno-branch-likely) +# https://github.com/llvm/llvm-project/issues/61045 +config CC_HAS_BROKEN_INLINE_COMPAT_BRANCH + def_bool y if CC_IS_CLANG + menu "Power management options" config ARCH_HIBERNATION_POSSIBLE diff --git a/arch/mips/boot/dts/ralink/mt7621.dtsi b/arch/mips/boot/dts/ralink/mt7621.dtsi index 290d47fbcfbb..7caed0d14f11 100644 --- a/arch/mips/boot/dts/ralink/mt7621.dtsi +++ b/arch/mips/boot/dts/ralink/mt7621.dtsi @@ -70,9 +70,10 @@ "250m", "270m"; }; - wdt: wdt@100 { + wdt: watchdog@100 { compatible = "mediatek,mt7621-wdt"; reg = <0x100 0x100>; + mediatek,sysctl = <&sysc>; }; gpio: gpio@600 { diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 89a1511d2ee4..edf9634aa8ee 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -284,6 +284,7 @@ CONFIG_IXGB=m CONFIG_SKGE=m CONFIG_SKY2=m CONFIG_MYRI10GE=m +CONFIG_FEALNX=m CONFIG_NATSEMI=m CONFIG_NS83820=m CONFIG_S2IO=m diff --git a/arch/mips/include/asm/asm.h b/arch/mips/include/asm/asm.h index 336ac9b65235..2e99450f4228 100644 --- a/arch/mips/include/asm/asm.h +++ b/arch/mips/include/asm/asm.h @@ -336,7 +336,7 @@ symbol = value */ #ifdef CONFIG_WAR_R10000_LLSC # define SC_BEQZ beqzl -#elif MIPS_ISA_REV >= 6 +#elif !defined(CONFIG_CC_HAS_BROKEN_INLINE_COMPAT_BRANCH) && MIPS_ISA_REV >= 6 # define SC_BEQZ beqzc #else # define SC_BEQZ beqz diff --git a/arch/mips/include/asm/smp-cps.h b/arch/mips/include/asm/smp-cps.h index 7e5b9411faee..22a572b70fe3 100644 --- a/arch/mips/include/asm/smp-cps.h +++ b/arch/mips/include/asm/smp-cps.h @@ -7,6 +7,8 @@ #ifndef __MIPS_ASM_SMP_CPS_H__ #define __MIPS_ASM_SMP_CPS_H__ +#define CPS_ENTRY_PATCH_INSNS 6 + #ifndef __ASSEMBLY__ struct vpe_boot_config { @@ -30,6 +32,8 @@ extern void mips_cps_boot_vpes(struct core_boot_config *cfg, unsigned vpe); extern void mips_cps_pm_save(void); extern void mips_cps_pm_restore(void); +extern void *mips_cps_core_entry_patch_end; + #ifdef CONFIG_MIPS_CPS extern bool mips_cps_smp_in_use(void); diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 32ec67c9ab67..368e8475870f 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -200,7 +200,7 @@ int c0_compare_int_usable(void) */ if (c0_compare_int_pending()) { cnt = read_c0_count(); - write_c0_compare(cnt); + write_c0_compare(cnt - 1); back_to_back_c0_hazard(); while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS)) if (!c0_compare_int_pending()) @@ -228,7 +228,7 @@ int c0_compare_int_usable(void) if (!c0_compare_int_pending()) return 0; cnt = read_c0_count(); - write_c0_compare(cnt); + write_c0_compare(cnt - 1); back_to_back_c0_hazard(); while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS)) if (!c0_compare_int_pending()) diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 975343240148..8ef492da827f 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -13,6 +13,7 @@ #include <asm/mipsregs.h> #include <asm/mipsmtregs.h> #include <asm/pm.h> +#include <asm/smp-cps.h> #define GCR_CPC_BASE_OFS 0x0088 #define GCR_CL_COHERENCE_OFS 0x2008 @@ -80,25 +81,20 @@ nop .endm - /* Calculate an uncached address for the CM GCRs */ - .macro cmgcrb dest - .set push - .set noat - MFC0 $1, CP0_CMGCRBASE - PTR_SLL $1, $1, 4 - PTR_LI \dest, UNCAC_BASE - PTR_ADDU \dest, \dest, $1 - .set pop - .endm .balign 0x1000 LEAF(mips_cps_core_entry) /* - * These first 4 bytes will be patched by cps_smp_setup to load the - * CCA to use into register s0. + * These first several instructions will be patched by cps_smp_setup to load the + * CCA to use into register s0 and GCR base address to register s1. */ - .word 0 + .rept CPS_ENTRY_PATCH_INSNS + nop + .endr + + .global mips_cps_core_entry_patch_end +mips_cps_core_entry_patch_end: /* Check whether we're here due to an NMI */ mfc0 k0, CP0_STATUS @@ -121,8 +117,7 @@ not_nmi: mtc0 t0, CP0_STATUS /* Skip cache & coherence setup if we're already coherent */ - cmgcrb v1 - lw s7, GCR_CL_COHERENCE_OFS(v1) + lw s7, GCR_CL_COHERENCE_OFS(s1) bnez s7, 1f nop @@ -132,7 +127,7 @@ not_nmi: /* Enter the coherent domain */ li t0, 0xff - sw t0, GCR_CL_COHERENCE_OFS(v1) + sw t0, GCR_CL_COHERENCE_OFS(s1) ehb /* Set Kseg0 CCA to that in s0 */ @@ -305,8 +300,7 @@ LEAF(mips_cps_core_init) */ LEAF(mips_cps_get_bootcfg) /* Calculate a pointer to this cores struct core_boot_config */ - cmgcrb t0 - lw t0, GCR_CL_ID_OFS(t0) + lw t0, GCR_CL_ID_OFS(s1) li t1, COREBOOTCFG_SIZE mul t0, t0, t1 PTR_LA t1, mips_cps_core_bootcfg @@ -366,8 +360,9 @@ LEAF(mips_cps_boot_vpes) has_vp t0, 5f /* Find base address of CPC */ - cmgcrb t3 - PTR_L t1, GCR_CPC_BASE_OFS(t3) + PTR_LA t1, mips_gcr_base + PTR_L t1, 0(t1) + PTR_L t1, GCR_CPC_BASE_OFS(t1) PTR_LI t2, ~0x7fff and t1, t1, t2 PTR_LI t2, UNCAC_BASE diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index f2df0cae1b4d..4fc288bb85b9 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -162,6 +162,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) */ entry_code = (u32 *)&mips_cps_core_entry; uasm_i_addiu(&entry_code, 16, 0, cca); + UASM_i_LA(&entry_code, 17, (long)mips_gcr_base); + BUG_ON((void *)entry_code > (void *)&mips_cps_core_entry_patch_end); blast_dcache_range((unsigned long)&mips_cps_core_entry, (unsigned long)entry_code); bc_wback_inv((unsigned long)&mips_cps_core_entry, diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 06031796c87b..83e61e147b90 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -54,7 +54,7 @@ choice select HAVE_PCI select PCI_DRIVERS_GENERIC select SOC_BUS - select PINCTRL_MT7621 + select PINCTRL help The MT7621 system-on-a-chip includes an 880 MHz MIPS1004Kc diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index edaca0a6c1c1..ca64eccea551 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -136,8 +136,11 @@ 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 no_context; return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index b4762d66e9ef..6734fee3134f 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -162,8 +162,11 @@ 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 no_context; return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 869204e97ec9..6941fdbf2517 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -308,8 +308,13 @@ 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)) { + msg = "Page fault: fault signal on kernel memory"; + goto no_context; + } return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2c9cdf1d8761..a6c4407d3ec8 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -236,7 +236,7 @@ config PPC select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES - select HAVE_LD_DEAD_CODE_DATA_ELIMINATION + select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts index 73f8c998c64d..d4f5f159d6f2 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts @@ -10,7 +10,6 @@ / { model = "fsl,T1040RDB-REV-A"; - compatible = "fsl,T1040RDB-REV-A"; }; &seville_port0 { diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts index b6733e7e6580..dd3aab81e9de 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts @@ -180,6 +180,9 @@ }; &seville_port8 { - ethernet = <&enet0>; + status = "okay"; +}; + +&seville_port9 { status = "okay"; }; diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi index f58eb820eb5e..ad0ab33336b8 100644 --- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -686,6 +686,7 @@ seville_port8: port@8 { reg = <8>; phy-mode = "internal"; + ethernet = <&enet0>; status = "disabled"; fixed-link { @@ -697,6 +698,7 @@ seville_port9: port@9 { reg = <9>; phy-mode = "internal"; + ethernet = <&enet1>; status = "disabled"; fixed-link { diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 110258277959..f73c98be56c8 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -461,6 +461,7 @@ CONFIG_MV643XX_ETH=m CONFIG_SKGE=m CONFIG_SKY2=m CONFIG_MYRI10GE=m +CONFIG_FEALNX=m CONFIG_NATSEMI=m CONFIG_NS83820=m CONFIG_PCMCIA_AXNET=m diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index f128c7cf9c1d..ee86753e444e 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -124,6 +124,7 @@ SECTIONS * included with the main text sections, so put it by itself. */ *(.sfpr); + *(.text.asan.* .text.tsan.*) MEM_KEEP(init.text) MEM_KEEP(exit.text) } :text diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 73c620c2a3a1..e753a6bd4888 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1275,7 +1275,7 @@ static int xmon_batch_next_cpu(void) while (!cpumask_empty(&xmon_batch_cpus)) { cpu = cpumask_next_wrap(smp_processor_id(), &xmon_batch_cpus, xmon_batch_start_cpu, true); - if (cpu == nr_cpumask_bits) + if (cpu >= nr_cpu_ids) break; if (xmon_batch_start_cpu == -1) xmon_batch_start_cpu = cpu; diff --git a/arch/riscv/include/uapi/asm/setup.h b/arch/riscv/include/uapi/asm/setup.h new file mode 100644 index 000000000000..66b13a522880 --- /dev/null +++ b/arch/riscv/include/uapi/asm/setup.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ + +#ifndef _UAPI_ASM_RISCV_SETUP_H +#define _UAPI_ASM_RISCV_SETUP_H + +#define COMMAND_LINE_SIZE 1024 + +#endif /* _UAPI_ASM_RISCV_SETUP_H */ diff --git a/arch/riscv/lib/strcmp.S b/arch/riscv/lib/strcmp.S index 986ab23fe787..c42a8412547f 100644 --- a/arch/riscv/lib/strcmp.S +++ b/arch/riscv/lib/strcmp.S @@ -40,7 +40,9 @@ SYM_FUNC_START(strcmp) ret /* - * Variant of strcmp using the ZBB extension if available + * Variant of strcmp using the ZBB extension if available. + * The code was published as part of the bitmanip manual + * in Appendix A. */ #ifdef CONFIG_RISCV_ISA_ZBB strcmp_zbb: @@ -57,7 +59,7 @@ strcmp_zbb: * a1 - string2 * * Clobbers - * t0, t1, t2, t3, t4, t5 + * t0, t1, t2, t3, t4 */ or t2, a0, a1 diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S index 8345ceeee3f6..15bb8f3aa959 100644 --- a/arch/riscv/lib/strlen.S +++ b/arch/riscv/lib/strlen.S @@ -96,7 +96,7 @@ strlen_zbb: * of valid bytes in this chunk. */ srli a0, t1, 3 - bgtu t3, a0, 3f + bgtu t3, a0, 2f /* Prepare for the word comparison loop. */ addi t2, t0, SZREG @@ -112,20 +112,20 @@ strlen_zbb: addi t0, t0, SZREG orc.b t1, t1 beq t1, t3, 1b -2: + not t1, t1 CZ t1, t1 + srli t1, t1, 3 - /* Get number of processed words. */ + /* Get number of processed bytes. */ sub t2, t0, t2 /* Add number of characters in the first word. */ add a0, a0, t2 - srli t1, t1, 3 /* Add number of characters in the last word. */ add a0, a0, t1 -3: +2: ret .option pop diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S index ee49595075be..7ac2f667285a 100644 --- a/arch/riscv/lib/strncmp.S +++ b/arch/riscv/lib/strncmp.S @@ -70,7 +70,7 @@ strncmp_zbb: li t5, -1 and t2, t2, SZREG-1 add t4, a0, a2 - bnez t2, 4f + bnez t2, 3f /* Adjust limit for fast-path. */ andi t6, t4, -SZREG @@ -78,11 +78,13 @@ strncmp_zbb: /* Main loop for aligned string. */ .p2align 3 1: - bgt a0, t6, 3f + bge a0, t6, 3f REG_L t0, 0(a0) REG_L t1, 0(a1) orc.b t3, t0 bne t3, t5, 2f + orc.b t3, t1 + bne t3, t5, 2f addi a0, a0, SZREG addi a1, a1, SZREG beq t0, t1, 1b @@ -114,23 +116,21 @@ strncmp_zbb: ret /* Simple loop for misaligned strings. */ -3: - /* Restore limit for slow-path. */ .p2align 3 -4: - bge a0, t4, 6f +3: + bge a0, t4, 5f lbu t0, 0(a0) lbu t1, 0(a1) addi a0, a0, 1 addi a1, a1, 1 - bne t0, t1, 5f - bnez t0, 4b + bne t0, t1, 4f + bnez t0, 3b -5: +4: sub a0, t0, t1 ret -6: +5: li a0, 0 ret diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index eb0774d9c03b..460f785f6e09 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -326,8 +326,11 @@ good_area: * signal first. We do not need to release the mmap_lock because it * would already be released in __lock_page_or_retry in mm/filemap.c. */ - if (fault_signal_pending(fault, regs)) + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + no_context(regs, addr); return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index a9270366dc57..c648864c8cd1 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -10,6 +10,7 @@ #include <linux/filter.h> #include <linux/memory.h> #include <linux/stop_machine.h> +#include <asm/patch.h> #include "bpf_jit.h" #define RV_REG_TCC RV_REG_A6 diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 078cd1a773a3..9809c74e1240 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -125,8 +125,8 @@ config S390 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_DEFAULT_BPF_JIT - select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP + select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 select DMA_OPS if PCI @@ -187,7 +187,6 @@ config S390 select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES - select HAVE_RETHOOK select HAVE_KVM select HAVE_LIVEPATCH select HAVE_MEMBLOCK_PHYS_MAP @@ -200,6 +199,7 @@ config S390 select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE + select HAVE_RETHOOK select HAVE_RSEQ select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI @@ -210,9 +210,9 @@ config S390 select HAVE_VIRT_CPU_ACCOUNTING_IDLE select IOMMU_HELPER if PCI select IOMMU_SUPPORT if PCI + select MMU_GATHER_MERGE_VMAS select MMU_GATHER_NO_GATHER select MMU_GATHER_RCU_TABLE_FREE - select MMU_GATHER_MERGE_VMAS select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PCI select NEED_PER_CPU_EMBED_FIRST_CHUNK diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 47a397da0498..cebd4ca16916 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -52,6 +52,8 @@ targets += vmlinux.bin.zst info.bin syms.bin vmlinux.syms $(obj-all) OBJECTS := $(addprefix $(obj)/,$(obj-y)) OBJECTS_ALL := $(addprefix $(obj)/,$(obj-all)) +clean-files += vmlinux.map + quiet_cmd_section_cmp = SECTCMP $* define cmd_section_cmp s1=`$(OBJDUMP) -t -j "$*" "$<" | sort | \ @@ -71,7 +73,7 @@ $(obj)/bzImage: $(obj)/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.b $(obj)/section_cmp%: vmlinux $(obj)/vmlinux FORCE $(call if_changed,section_cmp) -LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup --build-id=sha1 -T +LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup $(if $(CONFIG_VMLINUX_MAP),-Map=$(obj)/vmlinux.map) --build-id=sha1 -T $(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS_ALL) FORCE $(call if_changed,ld) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 57a2d6518d27..c699f251a464 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -49,6 +49,19 @@ struct ap_queue_status { unsigned int _pad2 : 16; }; +/* + * AP queue status reg union to access the reg1 + * register with the lower 32 bits comprising the + * ap queue status. + */ +union ap_queue_status_reg { + unsigned long value; + struct { + u32 _pad; + struct ap_queue_status status; + }; +}; + /** * ap_intructions_available() - Test if AP instructions are available. * @@ -82,7 +95,7 @@ static inline bool ap_instructions_available(void) */ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) { - struct ap_queue_status reg1; + union ap_queue_status_reg reg1; unsigned long reg2; asm volatile( @@ -91,12 +104,12 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) " .insn rre,0xb2af0000,0,0\n" /* PQAP(TAPQ) */ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ " lgr %[reg2],2\n" /* gr2 into reg2 */ - : [reg1] "=&d" (reg1), [reg2] "=&d" (reg2) + : [reg1] "=&d" (reg1.value), [reg2] "=&d" (reg2) : [qid] "d" (qid) : "cc", "0", "1", "2"); if (info) *info = reg2; - return reg1; + return reg1.status; } /** @@ -125,16 +138,16 @@ static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, static inline struct ap_queue_status ap_rapq(ap_qid_t qid) { unsigned long reg0 = qid | (1UL << 24); /* fc 1UL is RAPQ */ - struct ap_queue_status reg1; + union ap_queue_status_reg reg1; asm volatile( " lgr 0,%[reg0]\n" /* qid arg into gr0 */ " .insn rre,0xb2af0000,0,0\n" /* PQAP(RAPQ) */ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - : [reg1] "=&d" (reg1) + : [reg1] "=&d" (reg1.value) : [reg0] "d" (reg0) : "cc", "0", "1"); - return reg1; + return reg1.status; } /** @@ -146,16 +159,16 @@ static inline struct ap_queue_status ap_rapq(ap_qid_t qid) static inline struct ap_queue_status ap_zapq(ap_qid_t qid) { unsigned long reg0 = qid | (2UL << 24); /* fc 2UL is ZAPQ */ - struct ap_queue_status reg1; + union ap_queue_status_reg reg1; asm volatile( " lgr 0,%[reg0]\n" /* qid arg into gr0 */ " .insn rre,0xb2af0000,0,0\n" /* PQAP(ZAPQ) */ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - : [reg1] "=&d" (reg1) + : [reg1] "=&d" (reg1.value) : [reg0] "d" (reg0) : "cc", "0", "1"); - return reg1; + return reg1.status; } /** @@ -209,18 +222,21 @@ static inline int ap_qci(struct ap_config_info *config) * parameter to the PQAP(AQIC) instruction. For details please * see the AR documentation. */ -struct ap_qirq_ctrl { - unsigned int _res1 : 8; - unsigned int zone : 8; /* zone info */ - unsigned int ir : 1; /* ir flag: enable (1) or disable (0) irq */ - unsigned int _res2 : 4; - unsigned int gisc : 3; /* guest isc field */ - unsigned int _res3 : 6; - unsigned int gf : 2; /* gisa format */ - unsigned int _res4 : 1; - unsigned int gisa : 27; /* gisa origin */ - unsigned int _res5 : 1; - unsigned int isc : 3; /* irq sub class */ +union ap_qirq_ctrl { + unsigned long value; + struct { + unsigned int : 8; + unsigned int zone : 8; /* zone info */ + unsigned int ir : 1; /* ir flag: enable (1) or disable (0) irq */ + unsigned int : 4; + unsigned int gisc : 3; /* guest isc field */ + unsigned int : 6; + unsigned int gf : 2; /* gisa format */ + unsigned int : 1; + unsigned int gisa : 27; /* gisa origin */ + unsigned int : 1; + unsigned int isc : 3; /* irq sub class */ + }; }; /** @@ -232,21 +248,14 @@ struct ap_qirq_ctrl { * Returns AP queue status. */ static inline struct ap_queue_status ap_aqic(ap_qid_t qid, - struct ap_qirq_ctrl qirqctrl, + union ap_qirq_ctrl qirqctrl, phys_addr_t pa_ind) { unsigned long reg0 = qid | (3UL << 24); /* fc 3UL is AQIC */ - union { - unsigned long value; - struct ap_qirq_ctrl qirqctrl; - struct { - u32 _pad; - struct ap_queue_status status; - }; - } reg1; + union ap_queue_status_reg reg1; unsigned long reg2 = pa_ind; - reg1.qirqctrl = qirqctrl; + reg1.value = qirqctrl.value; asm volatile( " lgr 0,%[reg0]\n" /* qid param into gr0 */ @@ -254,7 +263,7 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid, " lgr 2,%[reg2]\n" /* ni addr into gr2 */ " .insn rre,0xb2af0000,0,0\n" /* PQAP(AQIC) */ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - : [reg1] "+&d" (reg1) + : [reg1] "+&d" (reg1.value) : [reg0] "d" (reg0), [reg2] "d" (reg2) : "cc", "memory", "0", "1", "2"); @@ -291,13 +300,7 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit, union ap_qact_ap_info *apinfo) { unsigned long reg0 = qid | (5UL << 24) | ((ifbit & 0x01) << 22); - union { - unsigned long value; - struct { - u32 _pad; - struct ap_queue_status status; - }; - } reg1; + union ap_queue_status_reg reg1; unsigned long reg2; reg1.value = apinfo->val; @@ -308,7 +311,7 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit, " .insn rre,0xb2af0000,0,0\n" /* PQAP(QACT) */ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ " lgr %[reg2],2\n" /* qact out info into reg2 */ - : [reg1] "+&d" (reg1), [reg2] "=&d" (reg2) + : [reg1] "+&d" (reg1.value), [reg2] "=&d" (reg2) : [reg0] "d" (reg0) : "cc", "0", "1", "2"); apinfo->val = reg2; @@ -333,7 +336,7 @@ static inline struct ap_queue_status ap_nqap(ap_qid_t qid, { unsigned long reg0 = qid | 0x40000000UL; /* 0x4... is last msg part */ union register_pair nqap_r1, nqap_r2; - struct ap_queue_status reg1; + union ap_queue_status_reg reg1; nqap_r1.even = (unsigned int)(psmid >> 32); nqap_r1.odd = psmid & 0xffffffff; @@ -345,11 +348,11 @@ static inline struct ap_queue_status ap_nqap(ap_qid_t qid, "0: .insn rre,0xb2ad0000,%[nqap_r1],%[nqap_r2]\n" " brc 2,0b\n" /* handle partial completion */ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - : [reg0] "+&d" (reg0), [reg1] "=&d" (reg1), + : [reg0] "+&d" (reg0), [reg1] "=&d" (reg1.value), [nqap_r2] "+&d" (nqap_r2.pair) : [nqap_r1] "d" (nqap_r1.pair) : "cc", "memory", "0", "1"); - return reg1; + return reg1.status; } /** @@ -389,7 +392,7 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, unsigned long *resgr0) { unsigned long reg0 = resgr0 && *resgr0 ? *resgr0 : qid | 0x80000000UL; - struct ap_queue_status reg1; + union ap_queue_status_reg reg1; unsigned long reg2; union register_pair rp1, rp2; @@ -408,8 +411,9 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, "2: lgr %[reg0],0\n" /* gr0 (qid + info) into reg0 */ " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ " lgr %[reg2],2\n" /* gr2 (res length) into reg2 */ - : [reg0] "+&d" (reg0), [reg1] "=&d" (reg1), [reg2] "=&d" (reg2), - [rp1] "+&d" (rp1.pair), [rp2] "+&d" (rp2.pair) + : [reg0] "+&d" (reg0), [reg1] "=&d" (reg1.value), + [reg2] "=&d" (reg2), [rp1] "+&d" (rp1.pair), + [rp2] "+&d" (rp2.pair) : : "cc", "memory", "0", "1", "2"); @@ -421,7 +425,7 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, * Signal the caller that this dqap is only partially received * with a special status response code 0xFF and *resgr0 updated */ - reg1.response_code = 0xFF; + reg1.status.response_code = 0xFF; if (resgr0) *resgr0 = reg0; } else { @@ -430,7 +434,7 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, *resgr0 = 0; } - return reg1; + return reg1.status; } /* diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h index af1cd3a6f406..227466ce9e41 100644 --- a/arch/s390/include/asm/nmi.h +++ b/arch/s390/include/asm/nmi.h @@ -101,9 +101,8 @@ void nmi_alloc_mcesa_early(u64 *mcesad); int nmi_alloc_mcesa(u64 *mcesad); void nmi_free_mcesa(u64 *mcesad); -void s390_handle_mcck(struct pt_regs *regs); -void __s390_handle_mcck(void); -int s390_do_machine_check(struct pt_regs *regs); +void s390_handle_mcck(void); +void s390_do_machine_check(struct pt_regs *regs); #endif /* __ASSEMBLY__ */ #endif /* _ASM_S390_NMI_H */ diff --git a/arch/s390/include/asm/rwonce.h b/arch/s390/include/asm/rwonce.h new file mode 100644 index 000000000000..91fc24520e82 --- /dev/null +++ b/arch/s390/include/asm/rwonce.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_S390_RWONCE_H +#define __ASM_S390_RWONCE_H + +#include <linux/compiler_types.h> + +/* + * Use READ_ONCE_ALIGNED_128() for 128-bit block concurrent (atomic) read + * accesses. Note that x must be 128-bit aligned, otherwise a specification + * exception is generated. + */ +#define READ_ONCE_ALIGNED_128(x) \ +({ \ + union { \ + typeof(x) __x; \ + __uint128_t val; \ + } __u; \ + \ + BUILD_BUG_ON(sizeof(x) != 16); \ + asm volatile( \ + " lpq %[val],%[_x]\n" \ + : [val] "=d" (__u.val) \ + : [_x] "QS" (x) \ + : "memory"); \ + __u.__x; \ +}) + +#include <asm-generic/rwonce.h> + +#endif /* __ASM_S390_RWONCE_H */ diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 59eba19ae0f2..d26f02495636 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -36,6 +36,23 @@ int __bootdata(is_full_image); +#define decompressor_handled_param(param) \ +static int __init ignore_decompressor_param_##param(char *s) \ +{ \ + return 0; \ +} \ +early_param(#param, ignore_decompressor_param_##param) + +decompressor_handled_param(mem); +decompressor_handled_param(vmalloc); +decompressor_handled_param(dfltcc); +decompressor_handled_param(noexec); +decompressor_handled_param(facilities); +decompressor_handled_param(nokaslr); +#if IS_ENABLED(CONFIG_KVM) +decompressor_handled_param(prot_virt); +#endif + static void __init reset_tod_clock(void) { union tod_clock clk; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index c8d8c9960936..76a06f3d3671 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -562,16 +562,6 @@ ENTRY(mcck_int_handler) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,s390_do_machine_check - cghi %r2,0 - je .Lmcck_return - lg %r1,__LC_KERNEL_STACK # switch to kernel stack - mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) - xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) - la %r11,STACK_FRAME_OVERHEAD(%r1) - lgr %r2,%r11 - lgr %r15,%r1 - brasl %r14,s390_handle_mcck -.Lmcck_return: lctlg %c1,%c1,__PT_CR1(%r11) lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 5e713f318de3..7b41ceecbb25 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -278,6 +278,7 @@ static void pop_kprobe(struct kprobe_ctlblk *kcb) { __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; + kcb->prev_kprobe.kp = NULL; } NOKPROBE_SYMBOL(pop_kprobe); @@ -402,12 +403,11 @@ static int post_kprobe_handler(struct pt_regs *regs) if (!p) return 0; + resume_execution(p, regs); if (kcb->kprobe_status != KPROBE_REENTER && p->post_handler) { kcb->kprobe_status = KPROBE_HIT_SSDONE; p->post_handler(p, regs, 0); } - - resume_execution(p, regs); pop_kprobe(kcb); preempt_enable_no_resched(); diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 5dbf274719a9..38ec0487521c 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -156,7 +156,7 @@ NOKPROBE_SYMBOL(s390_handle_damage); * Main machine check handler function. Will be called with interrupts disabled * and machine checks enabled. */ -void __s390_handle_mcck(void) +void s390_handle_mcck(void) { struct mcck_struct mcck; @@ -192,23 +192,16 @@ void __s390_handle_mcck(void) if (mcck.stp_queue) stp_queue_work(); if (mcck.kill_task) { - local_irq_enable(); printk(KERN_EMERG "mcck: Terminating task because of machine " "malfunction (code 0x%016lx).\n", mcck.mcck_code); printk(KERN_EMERG "mcck: task: %s, pid: %d.\n", current->comm, current->pid); - make_task_dead(SIGSEGV); + if (is_global_init(current)) + panic("mcck: Attempting to kill init!\n"); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, current, PIDTYPE_PID); } } -void noinstr s390_handle_mcck(struct pt_regs *regs) -{ - trace_hardirqs_off(); - pai_kernel_enter(regs); - __s390_handle_mcck(); - pai_kernel_exit(regs); - trace_hardirqs_on(); -} /* * returns 0 if register contents could be validated * returns 1 otherwise @@ -346,8 +339,7 @@ static void notrace s390_backup_mcck_info(struct pt_regs *regs) struct sie_page *sie_page; /* r14 contains the sie block, which was set in sie64a */ - struct kvm_s390_sie_block *sie_block = - (struct kvm_s390_sie_block *) regs->gprs[14]; + struct kvm_s390_sie_block *sie_block = phys_to_virt(regs->gprs[14]); if (sie_block == NULL) /* Something's seriously wrong, stop system. */ @@ -374,7 +366,7 @@ NOKPROBE_SYMBOL(s390_backup_mcck_info); /* * machine check handler. */ -int notrace s390_do_machine_check(struct pt_regs *regs) +void notrace s390_do_machine_check(struct pt_regs *regs) { static int ipd_count; static DEFINE_SPINLOCK(ipd_lock); @@ -504,16 +496,10 @@ int notrace s390_do_machine_check(struct pt_regs *regs) } clear_cpu_flag(CIF_MCCK_GUEST); - if (user_mode(regs) && mcck_pending) { - irqentry_nmi_exit(regs, irq_state); - return 1; - } - if (mcck_pending) schedule_mcck_handler(); irqentry_nmi_exit(regs, irq_state); - return 0; } NOKPROBE_SYMBOL(s390_do_machine_check); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 79904a839fb9..e7b867e2f73f 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1355,8 +1355,7 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) num_sdb++; /* Reset trailer (using compare-double-and-swap) */ - /* READ_ONCE() 16 byte header */ - prev.val = __cdsg(&te->header.val, 0, 0); + prev.val = READ_ONCE_ALIGNED_128(te->header.val); do { old.val = prev.val; new.val = prev.val; @@ -1558,8 +1557,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, struct hws_trailer_entry *te; te = aux_sdb_trailer(aux, alert_index); - /* READ_ONCE() 16 byte header */ - prev.val = __cdsg(&te->header.val, 0, 0); + prev.val = READ_ONCE_ALIGNED_128(te->header.val); do { old.val = prev.val; new.val = prev.val; @@ -1637,8 +1635,7 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - /* READ_ONCE() 16 byte header */ - prev.val = __cdsg(&te->header.val, 0, 0); + prev.val = READ_ONCE_ALIGNED_128(te->header.val); do { old.val = prev.val; new.val = prev.val; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 23c427284773..d4888453bbf8 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -333,6 +333,7 @@ static void pcpu_delegate(struct pcpu *pcpu, } /* Stop target cpu (if func returns this stops the current cpu). */ pcpu_sigp_retry(pcpu, SIGP_STOP, 0); + pcpu_sigp_retry(pcpu, SIGP_CPU_RESET, 0); /* Restart func on the target cpu and stop the current cpu. */ if (lc) { lc->restart_stack = stack; @@ -522,7 +523,7 @@ static void smp_handle_ext_call(void) if (test_bit(ec_call_function_single, &bits)) generic_smp_call_function_single_interrupt(); if (test_bit(ec_mcck_pending, &bits)) - __s390_handle_mcck(); + s390_handle_mcck(); if (test_bit(ec_irq_work, &bits)) irq_work_run(); } diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 5060956b8e7d..1bc42ce26599 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -289,15 +289,17 @@ segment_overlaps_others (struct dcss_segment *seg) /* * real segment loading function, called from segment_load + * Must return either an error code < 0, or the segment type code >= 0 */ static int __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long *end) { unsigned long start_addr, end_addr, dummy; struct dcss_segment *seg; - int rc, diag_cc; + int rc, diag_cc, segtype; start_addr = end_addr = 0; + segtype = -1; seg = kmalloc(sizeof(*seg), GFP_KERNEL | GFP_DMA); if (seg == NULL) { rc = -ENOMEM; @@ -326,9 +328,9 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long seg->res_name[8] = '\0'; strlcat(seg->res_name, " (DCSS)", sizeof(seg->res_name)); seg->res->name = seg->res_name; - rc = seg->vm_segtype; - if (rc == SEG_TYPE_SC || - ((rc == SEG_TYPE_SR || rc == SEG_TYPE_ER) && !do_nonshared)) + segtype = seg->vm_segtype; + if (segtype == SEG_TYPE_SC || + ((segtype == SEG_TYPE_SR || segtype == SEG_TYPE_ER) && !do_nonshared)) seg->res->flags |= IORESOURCE_READONLY; /* Check for overlapping resources before adding the mapping. */ @@ -386,7 +388,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long out_free: kfree(seg); out: - return rc; + return rc < 0 ? rc : segtype; } /* diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 27aebf1e75a2..3ef7adf739c8 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -50,6 +50,7 @@ #define SR_FD 0x00008000 #define SR_MD 0x40000000 +#define SR_USER_MASK 0x00000303 // M, Q, S, T bits /* * DSP structure and data */ diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index 90f495d35db2..a6bfc6f37491 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -115,6 +115,7 @@ static int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p) { unsigned int err = 0; + unsigned int sr = regs->sr & ~SR_USER_MASK; #define COPY(x) err |= __get_user(regs->x, &sc->sc_##x) COPY(regs[1]); @@ -130,6 +131,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *r0_p COPY(sr); COPY(pc); #undef COPY + regs->sr = (regs->sr & SR_USER_MASK) | sr; + #ifdef CONFIG_SH_FPU if (boot_cpu_data.flags & CPU_HAS_FPU) { int owned_fp; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 91259f291c54..179295b14664 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -187,8 +187,11 @@ good_area: */ fault = handle_mm_fault(vma, address, flags, regs); - if (fault_signal_pending(fault, regs)) + if (fault_signal_pending(fault, regs)) { + if (!from_user) + goto no_context; return; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 4acc12eafbf5..d91305de694c 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -424,8 +424,13 @@ good_area: fault = handle_mm_fault(vma, address, flags, regs); - if (fault_signal_pending(fault, regs)) + if (fault_signal_pending(fault, regs)) { + if (regs->tstate & TSTATE_PRIV) { + insn = get_fault_insn(regs, insn); + goto handle_kernel_fault; + } goto exit_exception; + } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) diff --git a/arch/um/Kconfig b/arch/um/Kconfig index ad4ff3b0e91e..541a9b18e343 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -25,9 +25,12 @@ config UML select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select HAVE_GCC_PLUGINS + select ARCH_SUPPORTS_LTO_CLANG + select ARCH_SUPPORTS_LTO_CLANG_THIN select TRACE_IRQFLAGS_SUPPORT select TTY # Needed for line.c select HAVE_ARCH_VMAP_STACK + select HAVE_RUST if X86_64 config MMU bool @@ -242,4 +245,8 @@ source "arch/um/drivers/Kconfig" config ARCH_SUSPEND_POSSIBLE def_bool y +menu "Power management options" + source "kernel/power/Kconfig" + +endmenu diff --git a/arch/um/Makefile b/arch/um/Makefile index f1d4d67157be..8186d4761bda 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -68,6 +68,8 @@ KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \ -Din6addr_loopback=kernel_in6addr_loopback \ -Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr +KBUILD_RUSTFLAGS += -Crelocation-model=pie + KBUILD_AFLAGS += $(ARCH_INCLUDE) USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -I%,,$(KBUILD_CFLAGS))) \ @@ -139,11 +141,10 @@ ifeq ($(CONFIG_LD_IS_BFD),y) LDFLAGS_EXECSTACK += $(call ld-option,--no-warn-rwx-segments) endif -LD_FLAGS_CMDLINE = $(foreach opt,$(KBUILD_LDFLAGS),-Wl,$(opt)) +LD_FLAGS_CMDLINE = $(foreach opt,$(KBUILD_LDFLAGS) $(LDFLAGS_EXECSTACK),-Wl,$(opt)) # Used by link-vmlinux.sh which has special support for um link -export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE) -export LDFLAGS_vmlinux := $(LDFLAGS_EXECSTACK) +export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE) $(CC_FLAGS_LTO) # When cleaning we don't include .config, so we don't include # TT or skas makefiles and don't clean skas_ptregs.h. diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig index a4f0a19fbe14..36911b1fddcf 100644 --- a/arch/um/drivers/Kconfig +++ b/arch/um/drivers/Kconfig @@ -261,6 +261,7 @@ config UML_NET_VECTOR config UML_NET_VDE bool "VDE transport (obsolete)" depends on UML_NET + depends on !MODVERSIONS select MAY_HAVE_RUNTIME_DEPS help This User-Mode Linux network transport allows one or more running @@ -309,6 +310,7 @@ config UML_NET_MCAST config UML_NET_PCAP bool "pcap transport (obsolete)" depends on UML_NET + depends on !MODVERSIONS select MAY_HAVE_RUNTIME_DEPS help The pcap transport makes a pcap packet stream on the host look diff --git a/arch/um/drivers/pcap_kern.c b/arch/um/drivers/pcap_kern.c index cfe4cb17694c..25ee2c97ca21 100644 --- a/arch/um/drivers/pcap_kern.c +++ b/arch/um/drivers/pcap_kern.c @@ -15,7 +15,7 @@ struct pcap_init { char *filter; }; -void pcap_init(struct net_device *dev, void *data) +void pcap_init_kern(struct net_device *dev, void *data) { struct uml_net_private *pri; struct pcap_data *ppri; @@ -44,7 +44,7 @@ static int pcap_write(int fd, struct sk_buff *skb, struct uml_net_private *lp) } static const struct net_kern_info pcap_kern_info = { - .init = pcap_init, + .init = pcap_init_kern, .protocol = eth_protocol, .read = pcap_read, .write = pcap_write, diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index ded7c47d2fbe..131b7cb29576 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -767,6 +767,7 @@ static int vector_config(char *str, char **error_out) if (parsed == NULL) { *error_out = "vector_config failed to parse parameters"; + kfree(params); return -EINVAL; } diff --git a/arch/um/drivers/vector_user.h b/arch/um/drivers/vector_user.h index 3a73d17a0161..59ed5f9e6e41 100644 --- a/arch/um/drivers/vector_user.h +++ b/arch/um/drivers/vector_user.h @@ -68,8 +68,6 @@ struct vector_fds { }; #define VECTOR_READ 1 -#define VECTOR_WRITE (1 < 1) -#define VECTOR_HEADERS (1 < 2) extern struct arglist *uml_parse_vector_ifspec(char *arg); diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 3ac220dafec4..7699ca5f35d4 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -8,6 +8,7 @@ #include <linux/virtio.h> #include <linux/virtio_config.h> #include <linux/logic_iomem.h> +#include <linux/of_platform.h> #include <linux/irqdomain.h> #include <linux/virtio_pcidev.h> #include <linux/virtio-uml.h> @@ -39,6 +40,8 @@ struct um_pci_device { unsigned long status; int irq; + + bool platform; }; struct um_pci_device_reg { @@ -48,13 +51,15 @@ struct um_pci_device_reg { static struct pci_host_bridge *bridge; static DEFINE_MUTEX(um_pci_mtx); +static struct um_pci_device *um_pci_platform_device; static struct um_pci_device_reg um_pci_devices[MAX_DEVICES]; static struct fwnode_handle *um_pci_fwnode; static struct irq_domain *um_pci_inner_domain; static struct irq_domain *um_pci_msi_domain; static unsigned long um_pci_msi_used[BITS_TO_LONGS(MAX_MSI_VECTORS)]; -#define UM_VIRT_PCI_MAXDELAY 40000 +static unsigned int um_pci_max_delay_us = 40000; +module_param_named(max_delay_us, um_pci_max_delay_us, uint, 0644); struct um_pci_message_buffer { struct virtio_pcidev_msg hdr; @@ -132,8 +137,11 @@ static int um_pci_send_cmd(struct um_pci_device *dev, out ? 1 : 0, posted ? cmd : HANDLE_NO_FREE(cmd), GFP_ATOMIC); - if (ret) + if (ret) { + if (posted) + kfree(cmd); goto out; + } if (posted) { virtqueue_kick(dev->cmd_vq); @@ -155,7 +163,7 @@ static int um_pci_send_cmd(struct um_pci_device *dev, kfree(completed); if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) || - ++delay_count > UM_VIRT_PCI_MAXDELAY, + ++delay_count > um_pci_max_delay_us, "um virt-pci delay: %d", delay_count)) { ret = -EIO; break; @@ -480,6 +488,9 @@ static void um_pci_handle_irq_message(struct virtqueue *vq, struct virtio_device *vdev = vq->vdev; struct um_pci_device *dev = vdev->priv; + if (!dev->irq) + return; + /* we should properly chain interrupts, but on ARCH=um we don't care */ switch (msg->op) { @@ -533,6 +544,25 @@ static void um_pci_irq_vq_cb(struct virtqueue *vq) } } +/* Copied from arch/x86/kernel/devicetree.c */ +struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) +{ + struct device_node *np; + + for_each_node_by_type(np, "pci") { + const void *prop; + unsigned int bus_min; + + prop = of_get_property(np, "bus-range", NULL); + if (!prop) + continue; + bus_min = be32_to_cpup(prop); + if (bus->number == bus_min) + return np; + } + return NULL; +} + static int um_pci_init_vqs(struct um_pci_device *dev) { struct virtqueue *vqs[2]; @@ -561,6 +591,55 @@ static int um_pci_init_vqs(struct um_pci_device *dev) return 0; } +static void __um_pci_virtio_platform_remove(struct virtio_device *vdev, + struct um_pci_device *dev) +{ + virtio_reset_device(vdev); + vdev->config->del_vqs(vdev); + + mutex_lock(&um_pci_mtx); + um_pci_platform_device = NULL; + mutex_unlock(&um_pci_mtx); + + kfree(dev); +} + +static int um_pci_virtio_platform_probe(struct virtio_device *vdev, + struct um_pci_device *dev) +{ + int ret; + + dev->platform = true; + + mutex_lock(&um_pci_mtx); + + if (um_pci_platform_device) { + mutex_unlock(&um_pci_mtx); + ret = -EBUSY; + goto out_free; + } + + ret = um_pci_init_vqs(dev); + if (ret) { + mutex_unlock(&um_pci_mtx); + goto out_free; + } + + um_pci_platform_device = dev; + + mutex_unlock(&um_pci_mtx); + + ret = of_platform_default_populate(vdev->dev.of_node, NULL, &vdev->dev); + if (ret) + __um_pci_virtio_platform_remove(vdev, dev); + + return ret; + +out_free: + kfree(dev); + return ret; +} + static int um_pci_virtio_probe(struct virtio_device *vdev) { struct um_pci_device *dev; @@ -574,6 +653,9 @@ static int um_pci_virtio_probe(struct virtio_device *vdev) dev->vdev = vdev; vdev->priv = dev; + if (of_device_is_compatible(vdev->dev.of_node, "simple-bus")) + return um_pci_virtio_platform_probe(vdev, dev); + mutex_lock(&um_pci_mtx); for (i = 0; i < MAX_DEVICES; i++) { if (um_pci_devices[i].dev) @@ -623,9 +705,11 @@ static void um_pci_virtio_remove(struct virtio_device *vdev) struct um_pci_device *dev = vdev->priv; int i; - /* Stop all virtqueues */ - virtio_reset_device(vdev); - vdev->config->del_vqs(vdev); + if (dev->platform) { + of_platform_depopulate(&vdev->dev); + __um_pci_virtio_platform_remove(vdev, dev); + return; + } device_set_wakeup_enable(&vdev->dev, false); @@ -633,12 +717,27 @@ static void um_pci_virtio_remove(struct virtio_device *vdev) for (i = 0; i < MAX_DEVICES; i++) { if (um_pci_devices[i].dev != dev) continue; + um_pci_devices[i].dev = NULL; irq_free_desc(dev->irq); + + break; } mutex_unlock(&um_pci_mtx); - um_pci_rescan(); + if (i < MAX_DEVICES) { + struct pci_dev *pci_dev; + + pci_dev = pci_get_slot(bridge->bus, i); + if (pci_dev) + pci_stop_and_remove_bus_device_locked(pci_dev); + } + + /* Stop all virtqueues */ + virtio_reset_device(vdev); + dev->cmd_vq = NULL; + dev->irq_vq = NULL; + vdev->config->del_vqs(vdev); kfree(dev); } @@ -860,6 +959,30 @@ void *pci_root_bus_fwnode(struct pci_bus *bus) return um_pci_fwnode; } +static long um_pci_map_platform(unsigned long offset, size_t size, + const struct logic_iomem_ops **ops, + void **priv) +{ + if (!um_pci_platform_device) + return -ENOENT; + + *ops = &um_pci_device_bar_ops; + *priv = &um_pci_platform_device->resptr[0]; + + return 0; +} + +static const struct logic_iomem_region_ops um_pci_platform_ops = { + .map = um_pci_map_platform, +}; + +static struct resource virt_platform_resource = { + .name = "platform", + .start = 0x10000000, + .end = 0x1fffffff, + .flags = IORESOURCE_MEM, +}; + static int __init um_pci_init(void) { int err, i; @@ -868,6 +991,8 @@ static int __init um_pci_init(void) &um_pci_cfgspace_ops)); WARN_ON(logic_iomem_add_region(&virt_iomem_resource, &um_pci_iomem_ops)); + WARN_ON(logic_iomem_add_region(&virt_platform_resource, + &um_pci_platform_ops)); if (WARN(CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID < 0, "No virtio device ID configured for PCI - no PCI support\n")) diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 588930a0ced1..8adca2000e51 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -168,7 +168,8 @@ static void vhost_user_check_reset(struct virtio_uml_device *vu_dev, if (!vu_dev->registered) return; - virtio_break_device(&vu_dev->vdev); + vu_dev->registered = 0; + schedule_work(&pdata->conn_broken_wk); } @@ -412,7 +413,7 @@ static irqreturn_t vu_req_read_message(struct virtio_uml_device *vu_dev, if (msg.msg.header.flags & VHOST_USER_FLAG_NEED_REPLY) vhost_user_reply(vu_dev, &msg.msg, response); irq_rc = IRQ_HANDLED; - }; + } /* mask EAGAIN as we try non-blocking read until socket is empty */ vu_dev->recv_rc = (rc == -EAGAIN) ? 0 : rc; return irq_rc; @@ -1136,6 +1137,15 @@ void virtio_uml_set_no_vq_suspend(struct virtio_device *vdev, static void vu_of_conn_broken(struct work_struct *wk) { + struct virtio_uml_platform_data *pdata; + struct virtio_uml_device *vu_dev; + + pdata = container_of(wk, struct virtio_uml_platform_data, conn_broken_wk); + + vu_dev = platform_get_drvdata(pdata->pdev); + + virtio_break_device(&vu_dev->vdev); + /* * We can't remove the device from the devicetree so the only thing we * can do is warn. @@ -1266,8 +1276,14 @@ static int vu_unregister_cmdline_device(struct device *dev, void *data) static void vu_conn_broken(struct work_struct *wk) { struct virtio_uml_platform_data *pdata; + struct virtio_uml_device *vu_dev; pdata = container_of(wk, struct virtio_uml_platform_data, conn_broken_wk); + + vu_dev = platform_get_drvdata(pdata->pdev); + + virtio_break_device(&vu_dev->vdev); + vu_unregister_cmdline_device(&pdata->pdev->dev, NULL); } diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index bb5f06480da9..7414154b8e9a 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -91,7 +91,7 @@ struct cpuinfo_um { extern struct cpuinfo_um boot_cpu_data; -#define cpu_data (&boot_cpu_data) +#define cpu_data(cpu) boot_cpu_data #define current_cpu_data boot_cpu_data #define cache_line_size() (boot_cpu_data.cache_alignment) diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 58938d75871a..827a0d3fa589 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -29,8 +29,8 @@ void flush_thread(void) ret = unmap(¤t->mm->context.id, 0, TASK_SIZE, 1, &data); if (ret) { - printk(KERN_ERR "flush_thread - clearing address space failed, " - "err = %d\n", ret); + printk(KERN_ERR "%s - clearing address space failed, err = %d\n", + __func__, ret); force_sig(SIGKILL); } get_safe_registers(current_pt_regs()->regs.gp, diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index ad449173a1a1..7d050ab0f78a 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -314,8 +314,8 @@ static inline int update_p4d_range(pgd_t *pgd, unsigned long addr, return ret; } -void fix_range_common(struct mm_struct *mm, unsigned long start_addr, - unsigned long end_addr, int force) +static void fix_range_common(struct mm_struct *mm, unsigned long start_addr, + unsigned long end_addr, int force) { pgd_t *pgd; struct host_vm_change hvc; @@ -597,6 +597,8 @@ void force_flush_all(void) struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); + mmap_read_lock(mm); for_each_vma(vmi, vma) fix_range(mm, vma->vm_start, vma->vm_end, 1); + mmap_read_unlock(mm); } diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 786b44dc20c9..8dcda617b8bf 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -96,7 +96,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < nr_cpu_ids ? cpu_data + *pos : NULL; + return *pos < nr_cpu_ids ? &boot_cpu_data + *pos : NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) diff --git a/arch/um/kernel/vmlinux.lds.S b/arch/um/kernel/vmlinux.lds.S index 16e49bfa2b42..53d719c04ba9 100644 --- a/arch/um/kernel/vmlinux.lds.S +++ b/arch/um/kernel/vmlinux.lds.S @@ -1,4 +1,4 @@ - +#define RUNTIME_DISCARD_EXIT KERNEL_STACK_SIZE = 4096 * (1 << CONFIG_KERNEL_STACK_ORDER); #ifdef CONFIG_LD_SCRIPT_STATIC diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c index 98ea910ef87c..cf7e49c08b21 100644 --- a/arch/um/os-Linux/irq.c +++ b/arch/um/os-Linux/irq.c @@ -127,12 +127,10 @@ int os_mod_epoll_fd(int events, int fd, void *data) int os_del_epoll_fd(int fd) { struct epoll_event event; - int result; /* This is quiet as we use this as IO ON/OFF - so it is often * invoked on a non-existent fd */ - result = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, &event); - return result; + return epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, &event); } void os_set_ioignore(void) diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index 3b4975ee67e2..953fb10f3f93 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -60,8 +60,8 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr) printk(UM_KERN_ERR "Registers - \n"); for (i = 0; i < MAX_REG_NR; i++) printk(UM_KERN_ERR "\t%d\t0x%lx\n", i, syscall_regs[i]); - panic("do_syscall_stub : PTRACE_SETREGS failed, errno = %d\n", - -n); + panic("%s : PTRACE_SETREGS failed, errno = %d\n", + __func__, -n); } err = ptrace(PTRACE_CONT, pid, 0, 0); @@ -81,20 +81,17 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr) offset = *((unsigned long *) mm_idp->stack + 1); if (offset) { data = (unsigned long *)(mm_idp->stack + offset - STUB_DATA); - printk(UM_KERN_ERR "do_syscall_stub : ret = %ld, offset = %ld, " - "data = %p\n", ret, offset, data); + printk(UM_KERN_ERR "%s : ret = %ld, offset = %ld, data = %p\n", + __func__, ret, offset, data); syscall = (unsigned long *)((unsigned long)data + data[0]); - printk(UM_KERN_ERR "do_syscall_stub: syscall %ld failed, " - "return value = 0x%lx, expected return value = 0x%lx\n", - syscall[0], ret, syscall[7]); - printk(UM_KERN_ERR " syscall parameters: " - "0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", + printk(UM_KERN_ERR "%s: syscall %ld failed, return value = 0x%lx, expected return value = 0x%lx\n", + __func__, syscall[0], ret, syscall[7]); + printk(UM_KERN_ERR " syscall parameters: 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", syscall[1], syscall[2], syscall[3], syscall[4], syscall[5], syscall[6]); for (n = 1; n < data[0]/sizeof(long); n++) { if (n == 1) - printk(UM_KERN_ERR " additional syscall " - "data:"); + printk(UM_KERN_ERR " additional syscall data:"); if (n % 4 == 1) printk("\n" UM_KERN_ERR " "); printk(" 0x%lx", data[n]); diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index b24db6017ded..b1ea53285af1 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -118,8 +118,8 @@ void wait_stub_done(int pid) err = ptrace(PTRACE_CONT, pid, 0, 0); if (err) { - printk(UM_KERN_ERR "wait_stub_done : continue failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s : continue failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } } @@ -130,11 +130,10 @@ void wait_stub_done(int pid) bad_wait: err = ptrace_dump_regs(pid); if (err) - printk(UM_KERN_ERR "Failed to get registers from stub, " - "errno = %d\n", -err); - printk(UM_KERN_ERR "wait_stub_done : failed to wait for SIGTRAP, " - "pid = %d, n = %d, errno = %d, status = 0x%x\n", pid, n, errno, - status); + printk(UM_KERN_ERR "Failed to get registers from stub, errno = %d\n", + -err); + printk(UM_KERN_ERR "%s : failed to wait for SIGTRAP, pid = %d, n = %d, errno = %d, status = 0x%x\n", + __func__, pid, n, errno, status); fatal_sigsegv(); } @@ -195,15 +194,15 @@ static void handle_trap(int pid, struct uml_pt_regs *regs, err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET, __NR_getpid); if (err < 0) { - printk(UM_KERN_ERR "handle_trap - nullifying syscall " - "failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s - nullifying syscall failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } err = ptrace(PTRACE_SYSCALL, pid, 0, 0); if (err < 0) { - printk(UM_KERN_ERR "handle_trap - continuing to end of " - "syscall failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s - continuing to end of syscall failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } @@ -212,11 +211,10 @@ static void handle_trap(int pid, struct uml_pt_regs *regs, (WSTOPSIG(status) != SIGTRAP + 0x80)) { err = ptrace_dump_regs(pid); if (err) - printk(UM_KERN_ERR "Failed to get registers " - "from process, errno = %d\n", -err); - printk(UM_KERN_ERR "handle_trap - failed to wait at " - "end of syscall, errno = %d, status = %d\n", - errno, status); + printk(UM_KERN_ERR "Failed to get registers from process, errno = %d\n", + -err); + printk(UM_KERN_ERR "%s - failed to wait at end of syscall, errno = %d, status = %d\n", + __func__, errno, status); fatal_sigsegv(); } } @@ -256,8 +254,8 @@ static int userspace_tramp(void *stack) addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE, PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset); if (addr == MAP_FAILED) { - printk(UM_KERN_ERR "mapping mmap stub at 0x%lx failed, " - "errno = %d\n", STUB_CODE, errno); + printk(UM_KERN_ERR "mapping mmap stub at 0x%lx failed, errno = %d\n", + STUB_CODE, errno); exit(1); } @@ -267,8 +265,7 @@ static int userspace_tramp(void *stack) UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE, MAP_FIXED | MAP_SHARED, fd, offset); if (addr == MAP_FAILED) { - printk(UM_KERN_ERR "mapping segfault stack " - "at 0x%lx failed, errno = %d\n", + printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n", STUB_DATA, errno); exit(1); } @@ -286,8 +283,8 @@ static int userspace_tramp(void *stack) sa.sa_sigaction = (void *) v; sa.sa_restorer = NULL; if (sigaction(SIGSEGV, &sa, NULL) < 0) { - printk(UM_KERN_ERR "userspace_tramp - setting SIGSEGV " - "handler failed - errno = %d\n", errno); + printk(UM_KERN_ERR "%s - setting SIGSEGV handler failed - errno = %d\n", + __func__, errno); exit(1); } } @@ -322,8 +319,8 @@ int start_userspace(unsigned long stub_stack) MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (stack == MAP_FAILED) { err = -errno; - printk(UM_KERN_ERR "start_userspace : mmap failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s : mmap failed, errno = %d\n", + __func__, errno); return err; } @@ -336,8 +333,8 @@ int start_userspace(unsigned long stub_stack) pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack); if (pid < 0) { err = -errno; - printk(UM_KERN_ERR "start_userspace : clone failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s : clone failed, errno = %d\n", + __func__, errno); return err; } @@ -345,31 +342,31 @@ int start_userspace(unsigned long stub_stack) CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL)); if (n < 0) { err = -errno; - printk(UM_KERN_ERR "start_userspace : wait failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s : wait failed, errno = %d\n", + __func__, errno); goto out_kill; } } while (WIFSTOPPED(status) && (WSTOPSIG(status) == SIGALRM)); if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGSTOP)) { err = -EINVAL; - printk(UM_KERN_ERR "start_userspace : expected SIGSTOP, got " - "status = %d\n", status); + printk(UM_KERN_ERR "%s : expected SIGSTOP, got status = %d\n", + __func__, status); goto out_kill; } if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL, (void *) PTRACE_O_TRACESYSGOOD) < 0) { err = -errno; - printk(UM_KERN_ERR "start_userspace : PTRACE_OLDSETOPTIONS " - "failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n", + __func__, errno); goto out_kill; } if (munmap(stack, UM_KERN_PAGE_SIZE) < 0) { err = -errno; - printk(UM_KERN_ERR "start_userspace : munmap failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s : munmap failed, errno = %d\n", + __func__, errno); goto out_kill; } @@ -403,14 +400,14 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) * just kill the process. */ if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) { - printk(UM_KERN_ERR "userspace - ptrace set regs " - "failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s - ptrace set regs failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } if (put_fp_registers(pid, regs->fp)) { - printk(UM_KERN_ERR "userspace - ptrace set fp regs " - "failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s - ptrace set fp regs failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } @@ -421,28 +418,28 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) singlestepping(NULL)); if (ptrace(op, pid, 0, 0)) { - printk(UM_KERN_ERR "userspace - ptrace continue " - "failed, op = %d, errno = %d\n", op, errno); + printk(UM_KERN_ERR "%s - ptrace continue failed, op = %d, errno = %d\n", + __func__, op, errno); fatal_sigsegv(); } CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL)); if (err < 0) { - printk(UM_KERN_ERR "userspace - wait failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s - wait failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } regs->is_user = 1; if (ptrace(PTRACE_GETREGS, pid, 0, regs->gp)) { - printk(UM_KERN_ERR "userspace - PTRACE_GETREGS failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s - PTRACE_GETREGS failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } if (get_fp_registers(pid, regs->fp)) { - printk(UM_KERN_ERR "userspace - get_fp_registers failed, " - "errno = %d\n", errno); + printk(UM_KERN_ERR "%s - get_fp_registers failed, errno = %d\n", + __func__, errno); fatal_sigsegv(); } @@ -494,8 +491,8 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) unblock_signals_trace(); break; default: - printk(UM_KERN_ERR "userspace - child stopped " - "with signal %d\n", sig); + printk(UM_KERN_ERR "%s - child stopped with signal %d\n", + __func__, sig); fatal_sigsegv(); } pid = userspace_pid[0]; @@ -555,15 +552,15 @@ int copy_context_skas0(unsigned long new_stack, int pid) err = ptrace_setregs(pid, thread_regs); if (err < 0) { err = -errno; - printk(UM_KERN_ERR "copy_context_skas0 : PTRACE_SETREGS " - "failed, pid = %d, errno = %d\n", pid, -err); + printk(UM_KERN_ERR "%s : PTRACE_SETREGS failed, pid = %d, errno = %d\n", + __func__, pid, -err); return err; } err = put_fp_registers(pid, thread_fp_regs); if (err < 0) { - printk(UM_KERN_ERR "copy_context_skas0 : put_fp_registers " - "failed, pid = %d, err = %d\n", pid, err); + printk(UM_KERN_ERR "%s : put_fp_registers failed, pid = %d, err = %d\n", + __func__, pid, err); return err; } @@ -574,8 +571,8 @@ int copy_context_skas0(unsigned long new_stack, int pid) err = ptrace(PTRACE_CONT, pid, 0, 0); if (err) { err = -errno; - printk(UM_KERN_ERR "Failed to continue new process, pid = %d, " - "errno = %d\n", pid, errno); + printk(UM_KERN_ERR "Failed to continue new process, pid = %d, errno = %d\n", + pid, errno); return err; } @@ -583,8 +580,8 @@ int copy_context_skas0(unsigned long new_stack, int pid) pid = data->parent_err; if (pid < 0) { - printk(UM_KERN_ERR "copy_context_skas0 - stub-parent reports " - "error %d\n", -pid); + printk(UM_KERN_ERR "%s - stub-parent reports error %d\n", + __func__, -pid); return pid; } @@ -594,8 +591,8 @@ int copy_context_skas0(unsigned long new_stack, int pid) */ wait_stub_done(pid); if (child_data->child_err != STUB_DATA) { - printk(UM_KERN_ERR "copy_context_skas0 - stub-child %d reports " - "error %ld\n", pid, data->child_err); + printk(UM_KERN_ERR "%s - stub-child %d reports error %ld\n", + __func__, pid, data->child_err); err = data->child_err; goto out_kill; } @@ -603,8 +600,8 @@ int copy_context_skas0(unsigned long new_stack, int pid) if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL, (void *)PTRACE_O_TRACESYSGOOD) < 0) { err = -errno; - printk(UM_KERN_ERR "copy_context_skas0 : PTRACE_OLDSETOPTIONS " - "failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n", + __func__, errno); goto out_kill; } @@ -672,8 +669,8 @@ int start_idle_thread(void *stack, jmp_buf *switch_buf) kmalloc_ok = 0; return 1; default: - printk(UM_KERN_ERR "Bad sigsetjmp return in " - "start_idle_thread - %d\n", n); + printk(UM_KERN_ERR "Bad sigsetjmp return in %s - %d\n", + __func__, n); fatal_sigsegv(); } longjmp(*switch_buf, 1); diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index b89e2e0024c5..b70559b821df 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -1,6 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 core-y += arch/x86/crypto/ +# +# Disable SSE and other FP/SIMD instructions to match normal x86 +# +KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 + ifeq ($(CONFIG_X86_32),y) START := 0x8048000 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 7ecd2aeeeffc..eccc3431e515 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -385,7 +385,14 @@ SYM_CODE_END(xen_error_entry) */ .macro idtentry vector asmsym cfunc has_error_code:req SYM_CODE_START(\asmsym) - UNWIND_HINT_IRET_REGS offset=\has_error_code*8 + + .if \vector == X86_TRAP_BP + /* #BP advances %rip to the next instruction */ + UNWIND_HINT_IRET_REGS offset=\has_error_code*8 signal=0 + .else + UNWIND_HINT_IRET_REGS offset=\has_error_code*8 + .endif + ENDBR ASM_CLAC cld diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e04313e89f4f..3ef70e54a858 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -261,7 +261,7 @@ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ - __stringify(__FILL_ONE_RETURN), \ftr2 + __stringify(nop;nop;__FILL_ONE_RETURN), \ftr2 .Lskip_rsb_\@: .endm diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index 5a2baf28a1dc..1343a62106de 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -57,12 +57,14 @@ struct orc_entry { unsigned sp_reg:4; unsigned bp_reg:4; unsigned type:2; + unsigned signal:1; unsigned end:1; #elif defined(__BIG_ENDIAN_BITFIELD) unsigned bp_reg:4; unsigned sp_reg:4; - unsigned unused:5; + unsigned unused:4; unsigned end:1; + unsigned signal:1; unsigned type:2; #endif } __packed; diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 52788f79786f..255a78d9d906 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -49,7 +49,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); * simple as possible. * Must be called with preemption disabled. */ -static void __resctrl_sched_in(void) +static inline void __resctrl_sched_in(struct task_struct *tsk) { struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); u32 closid = state->default_closid; @@ -61,13 +61,13 @@ static void __resctrl_sched_in(void) * Else use the closid/rmid assigned to this cpu. */ if (static_branch_likely(&rdt_alloc_enable_key)) { - tmp = READ_ONCE(current->closid); + tmp = READ_ONCE(tsk->closid); if (tmp) closid = tmp; } if (static_branch_likely(&rdt_mon_enable_key)) { - tmp = READ_ONCE(current->rmid); + tmp = READ_ONCE(tsk->rmid); if (tmp) rmid = tmp; } @@ -88,17 +88,17 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) return val * scale; } -static inline void resctrl_sched_in(void) +static inline void resctrl_sched_in(struct task_struct *tsk) { if (static_branch_likely(&rdt_enable_key)) - __resctrl_sched_in(); + __resctrl_sched_in(tsk); } void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else -static inline void resctrl_sched_in(void) {} +static inline void resctrl_sched_in(struct task_struct *tsk) {} static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {} #endif /* CONFIG_X86_CPU_RESCTRL */ diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 888731ccf1f6..c1e14cee0722 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -85,25 +85,6 @@ char *strcpy(char *dest, const char *src); char *strcat(char *dest, const char *src); int strcmp(const char *cs, const char *ct); -#if (defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)) -/* - * For files that not instrumented (e.g. mm/slub.c) we - * should use not instrumented version of mem* functions. - */ - -#undef memcpy -#define memcpy(dst, src, len) __memcpy(dst, src, len) -#undef memmove -#define memmove(dst, src, len) __memmove(dst, src, len) -#undef memset -#define memset(s, c, n) __memset(s, c, n) - -#ifndef __NO_FORTIFY -#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ -#endif - -#endif - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1 void __memcpy_flushcache(void *dst, const void *src, size_t cnt); diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index f66fbe6537dd..e7c71750b309 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -15,7 +15,7 @@ UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1 .endm -.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 +.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 signal=1 .if \base == %rsp .if \indirect .set sp_reg, ORC_REG_SP_INDIRECT @@ -45,11 +45,11 @@ .set type, UNWIND_HINT_TYPE_REGS .endif - UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type + UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type signal=\signal .endm -.macro UNWIND_HINT_IRET_REGS base=%rsp offset=0 - UNWIND_HINT_REGS base=\base offset=\offset partial=1 +.macro UNWIND_HINT_IRET_REGS base=%rsp offset=0 signal=1 + UNWIND_HINT_REGS base=\base offset=\offset partial=1 signal=\signal .endm .macro UNWIND_HINT_FUNC @@ -67,7 +67,7 @@ #else #define UNWIND_HINT_FUNC \ - UNWIND_HINT(ORC_REG_SP, 8, UNWIND_HINT_TYPE_FUNC, 0) + UNWIND_HINT(ORC_REG_SP, 8, UNWIND_HINT_TYPE_FUNC, 0, 0) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index cf81848b72f4..f9d060e71c3e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1133,14 +1133,18 @@ spectre_v2_parse_user_cmdline(void) return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) { - return mode == SPECTRE_V2_IBRS || - mode == SPECTRE_V2_EIBRS || + return mode == SPECTRE_V2_EIBRS || mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_EIBRS_LFENCE; } +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +{ + return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS; +} + static void __init spectre_v2_user_select_mitigation(void) { @@ -1203,12 +1207,19 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, - * STIBP is not required. + * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * is not required. + * + * Enhanced IBRS also protects against cross-thread branch target + * injection in user-mode as the IBRS bit remains always set which + * implicitly enables cross-thread protections. However, in legacy IBRS + * mode, the IBRS bit is set only on kernel entry and cleared on return + * to userspace. This disables the implicit cross-thread protection, + * so allow for STIBP to be selected in that case. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return; /* @@ -2340,7 +2351,7 @@ static ssize_t mmio_stale_data_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index e2c1599d1b37..884b6e9a7e31 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -314,7 +314,7 @@ static void update_cpu_closid_rmid(void *info) * executing task might have its own closid selected. Just reuse * the context switch code. */ - resctrl_sched_in(); + resctrl_sched_in(current); } /* @@ -530,7 +530,7 @@ static void _update_task_closid_rmid(void *task) * Otherwise, the MSR is updated when the task is scheduled in. */ if (task == current) - resctrl_sched_in(); + resctrl_sched_in(task); } static void update_task_closid_rmid(struct task_struct *t) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 470c128759ea..708c87b88cc1 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -212,7 +212,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) switch_fpu_finish(); /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(); + resctrl_sched_in(next_p); return prev_p; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4e34b3b68ebd..bb65a68b4b49 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -656,7 +656,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) } /* Load the Intel cache allocation PQR MSR. */ - resctrl_sched_in(); + resctrl_sched_in(next_p); return prev_p; } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index cdf6c6060170..37307b40f8da 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -484,6 +484,8 @@ bool unwind_next_frame(struct unwind_state *state) goto the_end; } + state->signal = orc->signal; + /* Find the previous frame's stack: */ switch (orc->sp_reg) { case ORC_REG_SP: @@ -563,7 +565,6 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; state->prev_regs = NULL; - state->signal = false; break; case UNWIND_HINT_TYPE_REGS: @@ -587,7 +588,6 @@ bool unwind_next_frame(struct unwind_state *state) state->regs = (struct pt_regs *)sp; state->prev_regs = NULL; state->full_regs = true; - state->signal = true; break; case UNWIND_HINT_TYPE_REGS_PARTIAL: @@ -604,7 +604,6 @@ bool unwind_next_frame(struct unwind_state *state) state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; - state->signal = true; break; default: diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 6fbe97c52c99..6825e146a62f 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -61,7 +61,7 @@ CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage # quiet_cmd_vdso = VDSO $@ cmd_vdso = $(CC) -nostdlib -o $@ \ - $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ + $(CC_FLAGS_LTO) $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c index 2112b8d14668..ff0f3b4b6c45 100644 --- a/arch/x86/um/vdso/um_vdso.c +++ b/arch/x86/um/vdso/um_vdso.c @@ -17,8 +17,10 @@ int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm("syscall" + : "=a" (ret) + : "0" (__NR_clock_gettime), "D" (clock), "S" (ts) + : "rcx", "r11", "memory"); return ret; } @@ -29,8 +31,10 @@ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm("syscall" + : "=a" (ret) + : "0" (__NR_gettimeofday), "D" (tv), "S" (tz) + : "rcx", "r11", "memory"); return ret; } |