diff options
Diffstat (limited to 'arch')
285 files changed, 3444 insertions, 1761 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 84bc1de02720..29b0167c088b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -164,7 +164,13 @@ config ARCH_USE_BUILTIN_BSWAP config KRETPROBES def_bool y - depends on KPROBES && HAVE_KRETPROBES + depends on KPROBES && (HAVE_KRETPROBES || HAVE_RETHOOK) + +config KRETPROBE_ON_RETHOOK + def_bool y + depends on HAVE_RETHOOK + depends on KRETPROBES + select RETHOOK config USER_RETURN_NOTIFIER bool @@ -217,9 +223,8 @@ config TRACE_IRQFLAGS_SUPPORT # asm/syscall.h supplying asm-generic/syscall.h interface # linux/regset.h user_regset interfaces # CORE_DUMP_USE_REGSET #define'd in linux/elf.h -# TIF_SYSCALL_TRACE calls tracehook_report_syscall_{entry,exit} -# TIF_NOTIFY_RESUME calls tracehook_notify_resume() -# signal delivery calls tracehook_signal_handler() +# TIF_SYSCALL_TRACE calls ptrace_report_syscall_{entry,exit} +# TIF_NOTIFY_RESUME calls resume_user_mode_work() # config HAVE_ARCH_TRACEHOOK bool diff --git a/arch/alpha/include/asm/floppy.h b/arch/alpha/include/asm/floppy.h index 8dfdb3aa1d96..588758685439 100644 --- a/arch/alpha/include/asm/floppy.h +++ b/arch/alpha/include/asm/floppy.h @@ -43,17 +43,18 @@ alpha_fd_dma_setup(char *addr, unsigned long size, int mode, int io) static int prev_dir; int dir; - dir = (mode != DMA_MODE_READ) ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE; + dir = (mode != DMA_MODE_READ) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; if (bus_addr && (addr != prev_addr || size != prev_size || dir != prev_dir)) { /* different from last time -- unmap prev */ - pci_unmap_single(isa_bridge, bus_addr, prev_size, prev_dir); + dma_unmap_single(&isa_bridge->dev, bus_addr, prev_size, + prev_dir); bus_addr = 0; } if (!bus_addr) /* need to map it */ - bus_addr = pci_map_single(isa_bridge, addr, size, dir); + bus_addr = dma_map_single(&isa_bridge->dev, addr, size, dir); /* remember this one as prev */ prev_addr = addr; diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 56b4ee5a6c9e..4aa996423b0d 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -74,6 +74,8 @@ #define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ #define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ +#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 21f9ac101324..e83a02ed5267 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -333,7 +333,7 @@ static dma_addr_t alpha_pci_map_page(struct device *dev, struct page *page, struct pci_dev *pdev = alpha_gendev_to_pci(dev); int dac_allowed; - BUG_ON(dir == PCI_DMA_NONE); + BUG_ON(dir == DMA_NONE); dac_allowed = pdev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0; return pci_map_single_1(pdev, (char *)page_address(page) + offset, @@ -356,7 +356,7 @@ static void alpha_pci_unmap_page(struct device *dev, dma_addr_t dma_addr, struct pci_iommu_arena *arena; long dma_ofs, npages; - BUG_ON(dir == PCI_DMA_NONE); + BUG_ON(dir == DMA_NONE); if (dma_addr >= __direct_map_base && dma_addr < __direct_map_base + __direct_map_size) { @@ -460,7 +460,7 @@ static void alpha_pci_free_coherent(struct device *dev, size_t size, unsigned long attrs) { struct pci_dev *pdev = alpha_gendev_to_pci(dev); - pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL); + dma_unmap_single(&pdev->dev, dma_addr, size, DMA_BIDIRECTIONAL); free_pages((unsigned long)cpu_addr, get_order(size)); DBGA2("pci_free_consistent: [%llx,%zx] from %ps\n", @@ -639,7 +639,7 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg, dma_addr_t max_dma; int dac_allowed; - BUG_ON(dir == PCI_DMA_NONE); + BUG_ON(dir == DMA_NONE); dac_allowed = dev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0; @@ -702,7 +702,7 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg, /* Some allocation failed while mapping the scatterlist entries. Unmap them now. */ if (out > start) - pci_unmap_sg(pdev, start, out - start, dir); + dma_unmap_sg(&pdev->dev, start, out - start, dir); return -ENOMEM; } @@ -722,7 +722,7 @@ static void alpha_pci_unmap_sg(struct device *dev, struct scatterlist *sg, dma_addr_t max_dma; dma_addr_t fbeg, fend; - BUG_ON(dir == PCI_DMA_NONE); + BUG_ON(dir == DMA_NONE); if (! alpha_mv.mv_pci_tbi) return; diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c index 8c43212ae38e..a1a239ea002d 100644 --- a/arch/alpha/kernel/ptrace.c +++ b/arch/alpha/kernel/ptrace.c @@ -15,7 +15,6 @@ #include <linux/user.h> #include <linux/security.h> #include <linux/signal.h> -#include <linux/tracehook.h> #include <linux/audit.h> #include <linux/uaccess.h> @@ -323,7 +322,7 @@ asmlinkage unsigned long syscall_trace_enter(void) unsigned long ret = 0; struct pt_regs *regs = current_pt_regs(); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(current_pt_regs())) + ptrace_report_syscall_entry(current_pt_regs())) ret = -1UL; audit_syscall_entry(regs->r0, regs->r16, regs->r17, regs->r18, regs->r19); return ret ?: current_pt_regs()->r0; @@ -334,5 +333,5 @@ syscall_trace_leave(void) { audit_syscall_exit(current_pt_regs()); if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(current_pt_regs(), 0); + ptrace_report_syscall_exit(current_pt_regs(), 0); } diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index d8ed71d5bed3..6f47f256fe80 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -22,7 +22,7 @@ #include <linux/binfmts.h> #include <linux/bitops.h> #include <linux/syscalls.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/uaccess.h> #include <asm/sigcontext.h> @@ -531,7 +531,7 @@ do_work_pending(struct pt_regs *regs, unsigned long thread_flags, do_signal(regs, r0, r19); r0 = 0; } else { - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } } local_irq_disable(); diff --git a/arch/alpha/kernel/syscalls/Makefile b/arch/alpha/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/alpha/kernel/syscalls/Makefile +++ b/arch/alpha/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c index 883391977fdf..54b419ac8bda 100644 --- a/arch/arc/kernel/ptrace.c +++ b/arch/arc/kernel/ptrace.c @@ -4,7 +4,6 @@ */ #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/sched/task_stack.h> #include <linux/regset.h> #include <linux/unistd.h> @@ -258,7 +257,7 @@ long arch_ptrace(struct task_struct *child, long request, asmlinkage int syscall_trace_entry(struct pt_regs *regs) { - if (tracehook_report_syscall_entry(regs)) + if (ptrace_report_syscall_entry(regs)) return ULONG_MAX; return regs->r8; @@ -266,5 +265,5 @@ asmlinkage int syscall_trace_entry(struct pt_regs *regs) asmlinkage void syscall_trace_exit(struct pt_regs *regs) { - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); } diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index cb2f88502baf..f748483628f2 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -49,7 +49,7 @@ #include <linux/personality.h> #include <linux/uaccess.h> #include <linux/syscalls.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/sched/task_stack.h> #include <asm/ucontext.h> @@ -438,5 +438,5 @@ void do_notify_resume(struct pt_regs *regs) * user mode */ if (test_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c1251856ef77..2e8091e2d8a8 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -49,7 +49,7 @@ config ARM select DMA_DECLARE_COHERENT select DMA_GLOBAL_POOL if !MMU select DMA_OPS - select DMA_REMAP if MMU + select DMA_NONCOHERENT_MMAP if MMU select EDAC_SUPPORT select EDAC_ATOMIC_SCRUB select GENERIC_ALLOCATOR diff --git a/arch/arm/boot/dts/aspeed-g4.dtsi b/arch/arm/boot/dts/aspeed-g4.dtsi index f14dace34c5a..fa8b581c3d6c 100644 --- a/arch/arm/boot/dts/aspeed-g4.dtsi +++ b/arch/arm/boot/dts/aspeed-g4.dtsi @@ -392,6 +392,17 @@ }; }; + peci0: peci-controller@1e78b000 { + compatible = "aspeed,ast2400-peci"; + reg = <0x1e78b000 0x60>; + interrupts = <15>; + clocks = <&syscon ASPEED_CLK_GATE_REFCLK>; + resets = <&syscon ASPEED_RESET_PECI>; + cmd-timeout-ms = <1000>; + clock-frequency = <1000000>; + status = "disabled"; + }; + uart2: serial@1e78d000 { compatible = "ns16550a"; reg = <0x1e78d000 0x20>; diff --git a/arch/arm/boot/dts/aspeed-g5.dtsi b/arch/arm/boot/dts/aspeed-g5.dtsi index 7495f93c5069..4147b397c883 100644 --- a/arch/arm/boot/dts/aspeed-g5.dtsi +++ b/arch/arm/boot/dts/aspeed-g5.dtsi @@ -516,6 +516,17 @@ }; }; + peci0: peci-controller@1e78b000 { + compatible = "aspeed,ast2500-peci"; + reg = <0x1e78b000 0x60>; + interrupts = <15>; + clocks = <&syscon ASPEED_CLK_GATE_REFCLK>; + resets = <&syscon ASPEED_RESET_PECI>; + cmd-timeout-ms = <1000>; + clock-frequency = <1000000>; + status = "disabled"; + }; + uart2: serial@1e78d000 { compatible = "ns16550a"; reg = <0x1e78d000 0x20>; diff --git a/arch/arm/boot/dts/aspeed-g6.dtsi b/arch/arm/boot/dts/aspeed-g6.dtsi index c32e87fad4dc..3d5ce9da42c3 100644 --- a/arch/arm/boot/dts/aspeed-g6.dtsi +++ b/arch/arm/boot/dts/aspeed-g6.dtsi @@ -512,6 +512,17 @@ status = "disabled"; }; + peci0: peci-controller@1e78b000 { + compatible = "aspeed,ast2600-peci"; + reg = <0x1e78b000 0x100>; + interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon ASPEED_CLK_GATE_REF0CLK>; + resets = <&syscon ASPEED_RESET_PECI>; + cmd-timeout-ms = <1000>; + clock-frequency = <1000000>; + status = "disabled"; + }; + lpc: lpc@1e789000 { compatible = "aspeed,ast2600-lpc-v2", "simple-mfd", "syscon"; reg = <0x1e789000 0x1000>; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 52a9aeecdbb2..5af6d58666f4 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -76,6 +76,22 @@ clock-latency = <61036>; /* two CLK32 periods */ clocks = <&clks IMX7D_CLK_ARM>; cpu-idle-states = <&cpu_sleep_wait>; + operating-points-v2 = <&cpu0_opp_table>; + #cooling-cells = <2>; + nvmem-cells = <&fuse_grade>; + nvmem-cell-names = "speed_grade"; + }; + }; + + cpu0_opp_table: opp-table { + compatible = "operating-points-v2"; + opp-shared; + + opp-792000000 { + opp-hz = /bits/ 64 <792000000>; + opp-microvolt = <1000000>; + clock-latency-ns = <150000>; + opp-supported-hw = <0xf>, <0xf>; }; }; diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi index 827e887afbda..13e1bdb3ddbf 100644 --- a/arch/arm/boot/dts/spear1340.dtsi +++ b/arch/arm/boot/dts/spear1340.dtsi @@ -134,9 +134,9 @@ reg = <0xb4100000 0x1000>; interrupts = <0 105 0x4>; status = "disabled"; - dmas = <&dwdma0 12 0 1>, - <&dwdma0 13 1 0>; - dma-names = "tx", "rx"; + dmas = <&dwdma0 13 0 1>, + <&dwdma0 12 1 0>; + dma-names = "rx", "tx"; }; thermal@e07008c4 { diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi index c87b881b2c8b..913553367687 100644 --- a/arch/arm/boot/dts/spear13xx.dtsi +++ b/arch/arm/boot/dts/spear13xx.dtsi @@ -284,9 +284,9 @@ #size-cells = <0>; interrupts = <0 31 0x4>; status = "disabled"; - dmas = <&dwdma0 4 0 0>, - <&dwdma0 5 0 0>; - dma-names = "tx", "rx"; + dmas = <&dwdma0 5 0 0>, + <&dwdma0 4 0 0>; + dma-names = "rx", "tx"; }; rtc@e0580000 { diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index 2b575792363e..e4dba5461cb3 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -102,6 +102,8 @@ config CRYPTO_AES_ARM_BS depends on KERNEL_MODE_NEON select CRYPTO_SKCIPHER select CRYPTO_LIB_AES + select CRYPTO_AES + select CRYPTO_CBC select CRYPTO_SIMD help Use a faster and more secure NEON based implementation of AES in CBC, diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 43b963ea4a0e..bfe88c6e60d5 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -22,7 +22,6 @@ #include <linux/hw_breakpoint.h> #include <linux/regset.h> #include <linux/audit.h> -#include <linux/tracehook.h> #include <linux/unistd.h> #include <asm/syscall.h> @@ -831,8 +830,7 @@ enum ptrace_syscall_dir { PTRACE_SYSCALL_EXIT, }; -static void tracehook_report_syscall(struct pt_regs *regs, - enum ptrace_syscall_dir dir) +static void report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) { unsigned long ip; @@ -844,8 +842,8 @@ static void tracehook_report_syscall(struct pt_regs *regs, regs->ARM_ip = dir; if (dir == PTRACE_SYSCALL_EXIT) - tracehook_report_syscall_exit(regs, 0); - else if (tracehook_report_syscall_entry(regs)) + ptrace_report_syscall_exit(regs, 0); + else if (ptrace_report_syscall_entry(regs)) current_thread_info()->abi_syscall = -1; regs->ARM_ip = ip; @@ -856,7 +854,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs) int scno; if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); + report_syscall(regs, PTRACE_SYSCALL_ENTER); /* Do seccomp after ptrace; syscall may have changed. */ #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER @@ -897,5 +895,5 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs) trace_sys_exit(regs, regs_return_value(regs)); if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); + report_syscall(regs, PTRACE_SYSCALL_EXIT); } diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index c532a6041066..459abc5d1819 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -9,7 +9,7 @@ #include <linux/signal.h> #include <linux/personality.h> #include <linux/uaccess.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/uprobes.h> #include <linux/syscalls.h> @@ -627,7 +627,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) } else if (thread_flags & _TIF_UPROBE) { uprobe_notify_resume(regs); } else { - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } } local_irq_disable(); diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c index 0659ab4cb0af..11677fc2968f 100644 --- a/arch/arm/mach-omap2/omap-secure.c +++ b/arch/arm/mach-omap2/omap-secure.c @@ -59,8 +59,13 @@ static void __init omap_optee_init_check(void) u32 omap_secure_dispatcher(u32 idx, u32 flag, u32 nargs, u32 arg1, u32 arg2, u32 arg3, u32 arg4) { + static u32 buf[NR_CPUS][5]; + u32 *param; + int cpu; u32 ret; - u32 param[5]; + + cpu = get_cpu(); + param = buf[cpu]; param[0] = nargs; param[1] = arg1; @@ -76,6 +81,8 @@ u32 omap_secure_dispatcher(u32 idx, u32 flag, u32 nargs, u32 arg1, u32 arg2, outer_clean_range(__pa(param), __pa(param + 5)); ret = omap_smc2(idx, flag, __pa(param)); + put_cpu(); + return ret; } @@ -119,8 +126,8 @@ phys_addr_t omap_secure_ram_mempool_base(void) #if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM) u32 omap3_save_secure_ram(void __iomem *addr, int size) { + static u32 param[5]; u32 ret; - u32 param[5]; if (size != OMAP3_SAVE_SECURE_RAM_SZ) return OMAP3_SAVE_SECURE_RAM_SZ; @@ -153,8 +160,8 @@ u32 omap3_save_secure_ram(void __iomem *addr, int size) u32 rx51_secure_dispatcher(u32 idx, u32 process, u32 flag, u32 nargs, u32 arg1, u32 arg2, u32 arg3, u32 arg4) { + static u32 param[5]; u32 ret; - u32 param[5]; param[0] = nargs+1; /* RX-51 needs number of arguments + 1 */ param[1] = arg1; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4b61541853ea..82ffac621854 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -381,6 +381,7 @@ out: */ postcore_initcall(atomic_pool_init); +#ifdef CONFIG_CMA_AREAS struct dma_contig_early_reserve { phys_addr_t base; unsigned long size; @@ -435,6 +436,7 @@ void __init dma_contiguous_remap(void) iotable_init(&map, 1); } } +#endif static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data) { diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 9ff683612f2a..d7ffccb7fea7 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -88,6 +88,10 @@ extern phys_addr_t arm_lowmem_limit; void __init bootmem_init(void); void arm_mm_memblock_reserve(void); +#ifdef CONFIG_CMA_AREAS void dma_contiguous_remap(void); +#else +static inline void dma_contiguous_remap(void) { } +#endif unsigned long __clear_cr(unsigned long mask); diff --git a/arch/arm/tools/Makefile b/arch/arm/tools/Makefile index 4a5c50f67ced..81f13bdf32f2 100644 --- a/arch/arm/tools/Makefile +++ b/arch/arm/tools/Makefile @@ -29,8 +29,7 @@ kapi: $(kapi-hdrs-y) $(gen-y) uapi: $(uapi-hdrs-y) # Create output directory if not already present -_dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') \ - $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') +$(shell mkdir -p $(kapi) $(uapi)) quiet_cmd_gen_mach = GEN $@ cmd_gen_mach = $(AWK) -f $(real-prereqs) > $@ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f8680892401b..57c4c995965f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -208,7 +208,7 @@ config ARM64 select IOMMU_DMA if IOMMU_SUPPORT select IRQ_DOMAIN select IRQ_FORCED_THREADING - select KASAN_VMALLOC if KASAN_GENERIC + select KASAN_VMALLOC if KASAN select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH @@ -811,7 +811,7 @@ config ARM64_ERRATUM_2224489 config ARM64_ERRATUM_2064142 bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled" - depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + depends on CORESIGHT_TRBE default y help This option adds the workaround for ARM Cortex-A510 erratum 2064142. @@ -829,7 +829,7 @@ config ARM64_ERRATUM_2064142 config ARM64_ERRATUM_2038923 bool "Cortex-A510: 2038923: workaround TRBE corruption with enable" - depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + depends on CORESIGHT_TRBE default y help This option adds the workaround for ARM Cortex-A510 erratum 2038923. @@ -852,7 +852,7 @@ config ARM64_ERRATUM_2038923 config ARM64_ERRATUM_1902691 bool "Cortex-A510: 1902691: workaround TRBE trace corruption" - depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + depends on CORESIGHT_TRBE default y help This option adds the workaround for ARM Cortex-A510 erratum 1902691. diff --git a/arch/arm64/boot/dts/amd/Makefile b/arch/arm64/boot/dts/amd/Makefile index 6a6093064a32..68103a8b0ef5 100644 --- a/arch/arm64/boot/dts/amd/Makefile +++ b/arch/arm64/boot/dts/amd/Makefile @@ -1,4 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -dtb-$(CONFIG_ARCH_SEATTLE) += amd-overdrive.dtb \ - amd-overdrive-rev-b0.dtb amd-overdrive-rev-b1.dtb \ - husky.dtb +dtb-$(CONFIG_ARCH_SEATTLE) += amd-overdrive-rev-b0.dtb amd-overdrive-rev-b1.dtb diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts index 8e341be9a399..c290d1ce2b03 100644 --- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts +++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b0.dts @@ -9,6 +9,7 @@ /dts-v1/; /include/ "amd-seattle-soc.dtsi" +/include/ "amd-seattle-cpus.dtsi" / { model = "AMD Seattle (Rev.B0) Development Board (Overdrive)"; @@ -36,14 +37,6 @@ status = "ok"; }; -&gpio2 { - status = "ok"; -}; - -&gpio3 { - status = "ok"; -}; - &gpio4 { status = "ok"; }; @@ -79,10 +72,6 @@ }; }; -&ipmi_kcs { - status = "ok"; -}; - &smb0 { /include/ "amd-seattle-xgbe-b.dtsi" }; diff --git a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts index 92cef05c6b74..e0926f6bb7c3 100644 --- a/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts +++ b/arch/arm64/boot/dts/amd/amd-overdrive-rev-b1.dts @@ -9,6 +9,7 @@ /dts-v1/; /include/ "amd-seattle-soc.dtsi" +/include/ "amd-seattle-cpus.dtsi" / { model = "AMD Seattle (Rev.B1) Development Board (Overdrive)"; diff --git a/arch/arm64/boot/dts/amd/amd-overdrive.dts b/arch/arm64/boot/dts/amd/amd-overdrive.dts deleted file mode 100644 index 41b3a6c0993d..000000000000 --- a/arch/arm64/boot/dts/amd/amd-overdrive.dts +++ /dev/null @@ -1,66 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DTS file for AMD Seattle Overdrive Development Board - * - * Copyright (C) 2014 Advanced Micro Devices, Inc. - */ - -/dts-v1/; - -/include/ "amd-seattle-soc.dtsi" - -/ { - model = "AMD Seattle Development Board (Overdrive)"; - compatible = "amd,seattle-overdrive", "amd,seattle"; - - chosen { - stdout-path = &serial0; - }; -}; - -&ccp0 { - status = "ok"; -}; - -&gpio0 { - status = "ok"; -}; - -&gpio1 { - status = "ok"; -}; - -&i2c0 { - status = "ok"; -}; - -&pcie0 { - status = "ok"; -}; - -&spi0 { - status = "ok"; -}; - -&spi1 { - status = "ok"; - sdcard0: sdcard@0 { - compatible = "mmc-spi-slot"; - reg = <0>; - spi-max-frequency = <20000000>; - voltage-ranges = <3200 3400>; - gpios = <&gpio0 7 0>; - interrupt-parent = <&gpio0>; - interrupts = <7 3>; - pl022,hierarchy = <0>; - pl022,interface = <0>; - pl022,com-mode = <0x0>; - pl022,rx-level-trig = <0>; - pl022,tx-level-trig = <0>; - }; -}; - -&v2m0 { - arm,msi-base-spi = <64>; - arm,msi-num-spis = <256>; -}; diff --git a/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi new file mode 100644 index 000000000000..93688a0b6820 --- /dev/null +++ b/arch/arm64/boot/dts/amd/amd-seattle-cpus.dtsi @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 + +/ { + cpus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&CPU0>; + }; + core1 { + cpu = <&CPU1>; + }; + }; + cluster1 { + core0 { + cpu = <&CPU2>; + }; + core1 { + cpu = <&CPU3>; + }; + }; + cluster2 { + core0 { + cpu = <&CPU4>; + }; + core1 { + cpu = <&CPU5>; + }; + }; + cluster3 { + core0 { + cpu = <&CPU6>; + }; + core1 { + cpu = <&CPU7>; + }; + }; + }; + + CPU0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_0>; + + }; + + CPU1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x1>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_0>; + }; + + CPU2: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x100>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_1>; + }; + + CPU3: cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x101>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_1>; + }; + + CPU4: cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x200>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_2>; + }; + + CPU5: cpu@201 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x201>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_2>; + }; + + CPU6: cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x300>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_3>; + }; + + CPU7: cpu@301 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x301>; + enable-method = "psci"; + + i-cache-size = <0xC000>; + i-cache-line-size = <64>; + i-cache-sets = <256>; + d-cache-size = <0x8000>; + d-cache-line-size = <64>; + d-cache-sets = <256>; + l2-cache = <&L2_3>; + }; + }; + + L2_0: l2-cache0 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L2_1: l2-cache1 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L2_2: l2-cache2 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L2_3: l2-cache3 { + cache-size = <0x100000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + next-level-cache = <&L3>; + }; + + L3: l3-cache { + cache-level = <3>; + cache-size = <0x800000>; + cache-line-size = <64>; + cache-sets = <8192>; + cache-unified; + }; + + pmu { + compatible = "arm,cortex-a57-pmu"; + interrupts = <0x0 0x7 0x4>, + <0x0 0x8 0x4>, + <0x0 0x9 0x4>, + <0x0 0xa 0x4>, + <0x0 0xb 0x4>, + <0x0 0xc 0x4>, + <0x0 0xd 0x4>, + <0x0 0xe 0x4>; + interrupt-affinity = <&CPU0>, + <&CPU1>, + <&CPU2>, + <&CPU3>, + <&CPU4>, + <&CPU5>, + <&CPU6>, + <&CPU7>; + }; +}; diff --git a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi index b664e7af74eb..690020589d41 100644 --- a/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi +++ b/arch/arm64/boot/dts/amd/amd-seattle-soc.dtsi @@ -38,18 +38,6 @@ <1 10 0xff04>; }; - pmu { - compatible = "arm,armv8-pmuv3"; - interrupts = <0 7 4>, - <0 8 4>, - <0 9 4>, - <0 10 4>, - <0 11 4>, - <0 12 4>, - <0 13 4>, - <0 14 4>; - }; - smb0: smb { compatible = "simple-bus"; #address-cells = <2>; @@ -70,6 +58,7 @@ reg = <0 0xe0300000 0 0xf0000>; interrupts = <0 355 4>; clocks = <&sataclk_333mhz>; + iommus = <&sata0_smmu 0x0 0x1f>; dma-coherent; }; @@ -80,6 +69,27 @@ reg = <0 0xe0d00000 0 0xf0000>; interrupts = <0 354 4>; clocks = <&sataclk_333mhz>; + iommus = <&sata1_smmu 0x0e>, + <&sata1_smmu 0x0f>, + <&sata1_smmu 0x1e>; + dma-coherent; + }; + + sata0_smmu: iommu@e0200000 { + compatible = "arm,mmu-401"; + reg = <0 0xe0200000 0 0x10000>; + #global-interrupts = <1>; + interrupts = <0 332 4>, <0 332 4>; + #iommu-cells = <2>; + dma-coherent; + }; + + sata1_smmu: iommu@e0c00000 { + compatible = "arm,mmu-401"; + reg = <0 0xe0c00000 0 0x10000>; + #global-interrupts = <1>; + interrupts = <0 331 4>, <0 331 4>; + #iommu-cells = <1>; dma-coherent; }; @@ -201,6 +211,10 @@ reg = <0 0xe0100000 0 0x10000>; interrupts = <0 3 4>; dma-coherent; + iommus = <&sata1_smmu 0x00>, + <&sata1_smmu 0x02>, + <&sata1_smmu 0x40>, + <&sata1_smmu 0x42>; }; pcie0: pcie@f0000000 { @@ -213,12 +227,22 @@ msi-parent = <&v2m0>; reg = <0 0xf0000000 0 0x10000000>; - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; + interrupt-map-mask = <0xff00 0x0 0x0 0x7>; interrupt-map = - <0x1000 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x120 0x1>, - <0x1000 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x121 0x1>, - <0x1000 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x122 0x1>, - <0x1000 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x123 0x1>; + <0x1100 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x120 0x1>, + <0x1100 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x121 0x1>, + <0x1100 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x122 0x1>, + <0x1100 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x123 0x1>, + + <0x1200 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x124 0x1>, + <0x1200 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x125 0x1>, + <0x1200 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x126 0x1>, + <0x1200 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x127 0x1>, + + <0x1300 0x0 0x0 0x1 &gic0 0x0 0x0 0x0 0x128 0x1>, + <0x1300 0x0 0x0 0x2 &gic0 0x0 0x0 0x0 0x129 0x1>, + <0x1300 0x0 0x0 0x3 &gic0 0x0 0x0 0x0 0x12a 0x1>, + <0x1300 0x0 0x0 0x4 &gic0 0x0 0x0 0x0 0x12b 0x1>; dma-coherent; dma-ranges = <0x43000000 0x0 0x0 0x0 0x0 0x100 0x0>; @@ -227,8 +251,18 @@ <0x01000000 0x00 0x00000000 0x00 0xefff0000 0x00 0x00010000>, /* 32-bit MMIO (size=2G) */ <0x02000000 0x00 0x40000000 0x00 0x40000000 0x00 0x80000000>, - /* 64-bit MMIO (size= 124G) */ + /* 64-bit MMIO (size= 508G) */ <0x03000000 0x01 0x00000000 0x01 0x00000000 0x7f 0x00000000>; + iommu-map = <0x0 &pcie_smmu 0x0 0x10000>; + }; + + pcie_smmu: iommu@e0a00000 { + compatible = "arm,mmu-401"; + reg = <0 0xe0a00000 0 0x10000>; + #global-interrupts = <1>; + interrupts = <0 333 4>, <0 333 4>; + #iommu-cells = <1>; + dma-coherent; }; /* Perf CCN504 PMU */ diff --git a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi index d97498361ce3..9259e547e2e8 100644 --- a/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi +++ b/arch/arm64/boot/dts/amd/amd-seattle-xgbe-b.dtsi @@ -55,7 +55,7 @@ clocks = <&xgmacclk0_dma_250mhz>, <&xgmacclk0_ptp_250mhz>; clock-names = "dma_clk", "ptp_clk"; phy-mode = "xgmii"; - #stream-id-cells = <16>; + iommus = <&xgmac0_smmu 0x00 0x17>; /* 0-7, 16-23 */ dma-coherent; }; @@ -81,11 +81,11 @@ clocks = <&xgmacclk1_dma_250mhz>, <&xgmacclk1_ptp_250mhz>; clock-names = "dma_clk", "ptp_clk"; phy-mode = "xgmii"; - #stream-id-cells = <16>; + iommus = <&xgmac1_smmu 0x00 0x17>; /* 0-7, 16-23 */ dma-coherent; }; - xgmac0_smmu: smmu@e0600000 { + xgmac0_smmu: iommu@e0600000 { compatible = "arm,mmu-401"; reg = <0 0xe0600000 0 0x10000>; #global-interrupts = <1>; @@ -94,14 +94,11 @@ */ <0 336 4>, <0 336 4>; - - mmu-masters = <&xgmac0 - 0 1 2 3 4 5 6 7 - 16 17 18 19 20 21 22 23 - >; + #iommu-cells = <2>; + dma-coherent; }; - xgmac1_smmu: smmu@e0800000 { + xgmac1_smmu: iommu@e0800000 { compatible = "arm,mmu-401"; reg = <0 0xe0800000 0 0x10000>; #global-interrupts = <1>; @@ -110,9 +107,6 @@ */ <0 335 4>, <0 335 4>; - - mmu-masters = <&xgmac1 - 0 1 2 3 4 5 6 7 - 16 17 18 19 20 21 22 23 - >; + #iommu-cells = <2>; + dma-coherent; }; diff --git a/arch/arm64/boot/dts/amd/husky.dts b/arch/arm64/boot/dts/amd/husky.dts deleted file mode 100644 index 7acde34772cb..000000000000 --- a/arch/arm64/boot/dts/amd/husky.dts +++ /dev/null @@ -1,84 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DTS file for AMD/Linaro 96Boards Enterprise Edition Server (Husky) Board - * Note: Based-on AMD Seattle Rev.B0 - * - * Copyright (C) 2015 Advanced Micro Devices, Inc. - */ - -/dts-v1/; - -/include/ "amd-seattle-soc.dtsi" - -/ { - model = "Linaro 96Boards Enterprise Edition Server (Husky) Board"; - compatible = "amd,seattle-overdrive", "amd,seattle"; - - chosen { - stdout-path = &serial0; - }; - - psci { - compatible = "arm,psci-0.2"; - method = "smc"; - }; -}; - -&ccp0 { - status = "ok"; - amd,zlib-support = <1>; -}; - -/** - * NOTE: In Rev.B, gpio0 is reserved. - */ -&gpio1 { - status = "ok"; -}; - -&gpio2 { - status = "ok"; -}; - -&gpio3 { - status = "ok"; -}; - -&gpio4 { - status = "ok"; -}; - -&i2c0 { - status = "ok"; -}; - -&i2c1 { - status = "ok"; -}; - -&pcie0 { - status = "ok"; -}; - -&spi0 { - status = "ok"; -}; - -&spi1 { - status = "ok"; - sdcard0: sdcard@0 { - compatible = "mmc-spi-slot"; - reg = <0>; - spi-max-frequency = <20000000>; - voltage-ranges = <3200 3400>; - pl022,hierarchy = <0>; - pl022,interface = <0>; - pl022,com-mode = <0x0>; - pl022,rx-level-trig = <0>; - pl022,tx-level-trig = <0>; - }; -}; - -&smb0 { - /include/ "amd-seattle-xgbe-b.dtsi" -}; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index 01b01e320411..35d1939e690b 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -536,9 +536,9 @@ clock-names = "i2c"; clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(1)>; - dmas = <&edma0 1 39>, - <&edma0 1 38>; - dma-names = "tx", "rx"; + dmas = <&edma0 1 38>, + <&edma0 1 39>; + dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 687fea6d8afa..4e7bd04d9798 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -499,9 +499,9 @@ interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(2)>; - dmas = <&edma0 1 39>, - <&edma0 1 38>; - dma-names = "tx", "rx"; + dmas = <&edma0 1 38>, + <&edma0 1 39>; + dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 3f8703f3ba5b..794d75173cf5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -921,7 +921,8 @@ usb3_0: usb@32f10100 { compatible = "fsl,imx8mp-dwc3"; - reg = <0x32f10100 0x8>; + reg = <0x32f10100 0x8>, + <0x381f0000 0x20>; clocks = <&clk IMX8MP_CLK_HSIO_ROOT>, <&clk IMX8MP_CLK_USB_ROOT>; clock-names = "hsio", "suspend"; @@ -963,7 +964,8 @@ usb3_1: usb@32f10108 { compatible = "fsl,imx8mp-dwc3"; - reg = <0x32f10108 0x8>; + reg = <0x32f10108 0x8>, + <0x382f0000 0x20>; clocks = <&clk IMX8MP_CLK_HSIO_ROOT>, <&clk IMX8MP_CLK_USB_ROOT>; clock-names = "hsio", "suspend"; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index 30233de58bb3..8c8bb97c9d30 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -132,10 +132,20 @@ reg = <0x11500 0x40>; }; + uartclk: clock-controller@12010 { + compatible = "marvell,armada-3700-uart-clock"; + reg = <0x12010 0x4>, <0x12210 0x4>; + clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>, + <&tbg 3>, <&xtalclk>; + clock-names = "TBG-A-P", "TBG-B-P", "TBG-A-S", + "TBG-B-S", "xtal"; + #clock-cells = <1>; + }; + uart0: serial@12000 { compatible = "marvell,armada-3700-uart"; reg = <0x12000 0x18>; - clocks = <&xtalclk>; + clocks = <&uartclk 0>; interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, @@ -147,7 +157,7 @@ uart1: serial@12200 { compatible = "marvell,armada-3700-uart-ext"; reg = <0x12200 0x30>; - clocks = <&xtalclk>; + clocks = <&uartclk 1>; interrupts = <GIC_SPI 30 IRQ_TYPE_EDGE_RISING>, <GIC_SPI 31 IRQ_TYPE_EDGE_RISING>; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index 4e7efa97724b..aac56575e30d 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -752,12 +752,13 @@ interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>; phys = <&qusb_phy_0>, <&usb0_ssphy>; phy-names = "usb2-phy", "usb3-phy"; + clocks = <&xo>; + clock-names = "ref"; tx-fifo-resize; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; snps,dis_u3_susphy_quirk; - snps,ref-clock-period-ns = <0x29>; dr_mode = "host"; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 0a0be43529f6..e34963505e07 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -1370,6 +1370,7 @@ compatible = "qcom,fastrpc"; qcom,smd-channels = "fastrpcsmd-apps-dsp"; label = "adsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 41f4e46e1f85..b31bf62e8680 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -839,6 +839,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "adsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -889,6 +890,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "cdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index d15fee495238..15f3bf2e7ea0 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -1871,6 +1871,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "sdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -3113,6 +3114,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "cdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -3558,6 +3560,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "adsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index fdaf303ba047..af8f22636436 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2682,6 +2682,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "sdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -2747,6 +2748,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "cdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -4480,6 +4482,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "adsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index d242bab69c2e..20f850b94158 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -2016,6 +2016,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "sdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -2085,6 +2086,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "cdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -2387,6 +2389,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "adsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi index 1e0b1bca7c94..8493dd7d5f1f 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp-clk-ccf.dtsi @@ -223,11 +223,11 @@ clocks = <&zynqmp_clk UART1_REF>, <&zynqmp_clk LPD_LSBUS>; }; -&usb0 { +&dwc3_0 { clocks = <&zynqmp_clk USB0_BUS_REF>, <&zynqmp_clk USB3_DUAL_REF>; }; -&usb1 { +&dwc3_1 { clocks = <&zynqmp_clk USB1_BUS_REF>, <&zynqmp_clk USB3_DUAL_REF>; }; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 056761c974fd..c715a18368c2 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -809,7 +809,6 @@ status = "disabled"; compatible = "xlnx,zynqmp-dwc3"; reg = <0x0 0xff9d0000 0x0 0x100>; - clock-names = "bus_clk", "ref_clk"; power-domains = <&zynqmp_firmware PD_USB_0>; resets = <&zynqmp_reset ZYNQMP_RESET_USB0_CORERESET>, <&zynqmp_reset ZYNQMP_RESET_USB0_HIBERRESET>, @@ -823,6 +822,7 @@ interrupt-parent = <&gic>; interrupt-names = "dwc_usb3", "otg"; interrupts = <0 65 4>, <0 69 4>; + clock-names = "bus_early", "ref"; iommus = <&smmu 0x860>; snps,quirk-frame-length-adjustment = <0x20>; /* dma-coherent; */ @@ -835,7 +835,6 @@ status = "disabled"; compatible = "xlnx,zynqmp-dwc3"; reg = <0x0 0xff9e0000 0x0 0x100>; - clock-names = "bus_clk", "ref_clk"; power-domains = <&zynqmp_firmware PD_USB_1>; resets = <&zynqmp_reset ZYNQMP_RESET_USB1_CORERESET>, <&zynqmp_reset ZYNQMP_RESET_USB1_HIBERRESET>, @@ -849,6 +848,7 @@ interrupt-parent = <&gic>; interrupt-names = "dwc_usb3", "otg"; interrupts = <0 70 4>, <0 74 4>; + clock-names = "bus_early", "ref"; iommus = <&smmu 0x861>; snps,quirk-frame-length-adjustment = <0x20>; /* dma-coherent; */ diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 64202010b700..345fe98605ba 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += early_ioremap.h generic-y += mcs_spinlock.h generic-y += qrwlock.h generic-y += qspinlock.h +generic-y += parport.h generic-y += user.h generated-y += cpucaps.h diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h index b9185503feae..38fafffe699f 100644 --- a/arch/arm64/include/asm/vmalloc.h +++ b/arch/arm64/include/asm/vmalloc.h @@ -25,4 +25,10 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) #endif +#define arch_vmap_pgprot_tagged arch_vmap_pgprot_tagged +static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) +{ + return pgprot_tagged(prot); +} + #endif /* _ASM_ARM64_VMALLOC_H */ diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h index 894e031b28d2..20873099c035 100644 --- a/arch/arm64/include/asm/vmap_stack.h +++ b/arch/arm64/include/asm/vmap_stack.h @@ -17,10 +17,13 @@ */ static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node) { + void *p; + BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK)); - return __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node, + p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node, __builtin_return_address(0)); + return kasan_reset_tag(p); } #endif /* __ASM_VMAP_STACK_H */ diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 309a27553c87..f2d4bb14bfab 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -58,12 +58,13 @@ void *module_alloc(unsigned long size) PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { + if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } - return p; + /* Memory is intended to be executable, reset the pointer tag. */ + return kasan_reset_tag(p); } enum aarch64_reloc_op { diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 39dbdfdc38d3..230a47b9189e 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -27,7 +27,6 @@ #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/regset.h> -#include <linux/tracehook.h> #include <linux/elf.h> #include <asm/compat.h> @@ -1792,8 +1791,7 @@ enum ptrace_syscall_dir { PTRACE_SYSCALL_EXIT, }; -static void tracehook_report_syscall(struct pt_regs *regs, - enum ptrace_syscall_dir dir) +static void report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) { int regno; unsigned long saved_reg; @@ -1819,11 +1817,11 @@ static void tracehook_report_syscall(struct pt_regs *regs, regs->regs[regno] = dir; if (dir == PTRACE_SYSCALL_ENTER) { - if (tracehook_report_syscall_entry(regs)) + if (ptrace_report_syscall_entry(regs)) forget_syscall(regs); regs->regs[regno] = saved_reg; } else if (!test_thread_flag(TIF_SINGLESTEP)) { - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); regs->regs[regno] = saved_reg; } else { regs->regs[regno] = saved_reg; @@ -1833,7 +1831,7 @@ static void tracehook_report_syscall(struct pt_regs *regs, * tracer modifications to the registers may have rewound the * state machine. */ - tracehook_report_syscall_exit(regs, 1); + ptrace_report_syscall_exit(regs, 1); } } @@ -1842,7 +1840,7 @@ int syscall_trace_enter(struct pt_regs *regs) unsigned long flags = read_thread_flags(); if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { - tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); + report_syscall(regs, PTRACE_SYSCALL_ENTER); if (flags & _TIF_SYSCALL_EMU) return NO_SYSCALL; } @@ -1870,7 +1868,7 @@ void syscall_trace_exit(struct pt_regs *regs) trace_sys_exit(regs, syscall_get_return_value(current, regs)); if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) - tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); + report_syscall(regs, PTRACE_SYSCALL_EXIT); rseq_syscall(regs); } diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 50fe8eaf7df0..4a4122ef6f39 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -16,7 +16,7 @@ #include <linux/uaccess.h> #include <linux/sizes.h> #include <linux/string.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/ratelimit.h> #include <linux/syscalls.h> @@ -942,7 +942,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) do_signal(regs); if (thread_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); if (thread_flags & _TIF_FOREIGN_FPSTATE) fpsimd_restore_current_state(); diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 6c01b63ff56d..ed181bedbffc 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -68,7 +68,8 @@ VDSO_CFLAGS += -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common \ -Werror-implicit-function-declaration \ -Wno-format-security \ - -std=gnu89 + -Wdeclaration-after-statement \ + -std=gnu11 VDSO_CFLAGS += -O2 # Some useful compiler-dependent flags from top-level Makefile VDSO_CFLAGS += $(call cc32-option,-Wdeclaration-after-statement,) diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index a3bacd79507a..64e985eaa52d 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -85,7 +85,7 @@ static int change_memory_common(unsigned long addr, int numpages, */ area = find_vm_area((void *)addr); if (!area || - end > (unsigned long)area->addr + area->size || + end > (unsigned long)kasan_reset_tag(area->addr) + area->size || !(area->flags & VM_ALLOC)) return -EINVAL; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index e850c69e128c..fcc675aa1670 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1304,7 +1304,8 @@ u64 bpf_jit_alloc_exec_limit(void) void *bpf_jit_alloc_exec(unsigned long size) { - return vmalloc(size); + /* Memory is intended to be executable, reset the pointer tag. */ + return kasan_reset_tag(vmalloc(size)); } void bpf_jit_free_exec(void *addr) diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index 904a18a818be..888248235c23 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -4,5 +4,6 @@ generic-y += extable.h generic-y += gpio.h generic-y += kvm_para.h generic-y += qrwlock.h +generic-y += parport.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c index 1a5f54e0d272..0f7e7b653c72 100644 --- a/arch/csky/kernel/ptrace.c +++ b/arch/csky/kernel/ptrace.c @@ -12,7 +12,6 @@ #include <linux/sched/task_stack.h> #include <linux/signal.h> #include <linux/smp.h> -#include <linux/tracehook.h> #include <linux/uaccess.h> #include <linux/user.h> @@ -321,7 +320,7 @@ long arch_ptrace(struct task_struct *child, long request, asmlinkage int syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) - if (tracehook_report_syscall_entry(regs)) + if (ptrace_report_syscall_entry(regs)) return -1; if (secure_computing() == -1) @@ -339,7 +338,7 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs) audit_syscall_exit(regs); if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_exit(regs, syscall_get_return_value(current, regs)); diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 8867ddf3e6c7..b7b3685283d7 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -3,7 +3,7 @@ #include <linux/signal.h> #include <linux/uaccess.h> #include <linux/syscalls.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/traps.h> #include <asm/ucontext.h> @@ -265,5 +265,5 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c index a11db009d0ea..a9898b27b756 100644 --- a/arch/h8300/kernel/ptrace.c +++ b/arch/h8300/kernel/ptrace.c @@ -12,7 +12,6 @@ #include <linux/errno.h> #include <linux/ptrace.h> #include <linux/audit.h> -#include <linux/tracehook.h> #include <linux/regset.h> #include <linux/elf.h> @@ -174,7 +173,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) long ret = 0; if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) + ptrace_report_syscall_entry(regs)) /* * Tracing decided this syscall should not happen. * We'll return a bogus call number to get an ENOSYS @@ -196,5 +195,5 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index 75a1c36b105a..0716fc8a8ce2 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -39,7 +39,7 @@ #include <linux/personality.h> #include <linux/tty.h> #include <linux/binfmts.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/setup.h> #include <linux/uaccess.h> @@ -283,5 +283,5 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags) do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index dfa6b2757c05..eab03c691f53 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -14,7 +14,7 @@ #include <linux/tick.h> #include <linux/uaccess.h> #include <linux/slab.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> /* * Program thread launch. Often defined as a macro in processor.h, @@ -177,7 +177,7 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags) } if (thread_info_flags & _TIF_NOTIFY_RESUME) { - tracehook_notify_resume(regs); + resume_user_mode_work(regs); return 1; } diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c index 94cc7ff52dce..bcba31e9e0ae 100644 --- a/arch/hexagon/kernel/signal.c +++ b/arch/hexagon/kernel/signal.c @@ -7,7 +7,6 @@ #include <linux/linkage.h> #include <linux/syscalls.h> -#include <linux/tracehook.h> #include <linux/sched/task_stack.h> #include <asm/registers.h> diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index 1240f038cce0..6447763ce5a9 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -14,7 +14,7 @@ #include <linux/kdebug.h> #include <linux/syscalls.h> #include <linux/signal.h> -#include <linux/tracehook.h> +#include <linux/ptrace.h> #include <asm/traps.h> #include <asm/vm_fault.h> #include <asm/syscall.h> @@ -348,7 +348,7 @@ void do_trap0(struct pt_regs *regs) /* allow strace to catch syscall args */ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs))) + ptrace_report_syscall_entry(regs))) return; /* return -ENOSYS somewhere? */ /* Interrupts should be re-enabled for syscall processing */ @@ -386,7 +386,7 @@ void do_trap0(struct pt_regs *regs) /* allow strace to get the syscall return state */ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACE))) - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); break; case TRAP_DEBUG: diff --git a/arch/ia64/include/uapi/asm/termbits.h b/arch/ia64/include/uapi/asm/termbits.h deleted file mode 100644 index 000a1a297c75..000000000000 --- a/arch/ia64/include/uapi/asm/termbits.h +++ /dev/null @@ -1,209 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _ASM_IA64_TERMBITS_H -#define _ASM_IA64_TERMBITS_H - -/* - * Based on <asm-i386/termbits.h>. - * - * Modified 1999 - * David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co - * - * 99/01/28 Added new baudrates - */ - -#include <linux/posix_types.h> - -typedef unsigned char cc_t; -typedef unsigned int speed_t; -typedef unsigned int tcflag_t; - -#define NCCS 19 -struct termios { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ -}; - -struct termios2 { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ - speed_t c_ispeed; /* input speed */ - speed_t c_ospeed; /* output speed */ -}; - -struct ktermios { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ - speed_t c_ispeed; /* input speed */ - speed_t c_ospeed; /* output speed */ -}; - -/* c_cc characters */ -#define VINTR 0 -#define VQUIT 1 -#define VERASE 2 -#define VKILL 3 -#define VEOF 4 -#define VTIME 5 -#define VMIN 6 -#define VSWTC 7 -#define VSTART 8 -#define VSTOP 9 -#define VSUSP 10 -#define VEOL 11 -#define VREPRINT 12 -#define VDISCARD 13 -#define VWERASE 14 -#define VLNEXT 15 -#define VEOL2 16 - -/* c_iflag bits */ -#define IGNBRK 0000001 -#define BRKINT 0000002 -#define IGNPAR 0000004 -#define PARMRK 0000010 -#define INPCK 0000020 -#define ISTRIP 0000040 -#define INLCR 0000100 -#define IGNCR 0000200 -#define ICRNL 0000400 -#define IUCLC 0001000 -#define IXON 0002000 -#define IXANY 0004000 -#define IXOFF 0010000 -#define IMAXBEL 0020000 -#define IUTF8 0040000 - -/* c_oflag bits */ -#define OPOST 0000001 -#define OLCUC 0000002 -#define ONLCR 0000004 -#define OCRNL 0000010 -#define ONOCR 0000020 -#define ONLRET 0000040 -#define OFILL 0000100 -#define OFDEL 0000200 -#define NLDLY 0000400 -#define NL0 0000000 -#define NL1 0000400 -#define CRDLY 0003000 -#define CR0 0000000 -#define CR1 0001000 -#define CR2 0002000 -#define CR3 0003000 -#define TABDLY 0014000 -#define TAB0 0000000 -#define TAB1 0004000 -#define TAB2 0010000 -#define TAB3 0014000 -#define XTABS 0014000 -#define BSDLY 0020000 -#define BS0 0000000 -#define BS1 0020000 -#define VTDLY 0040000 -#define VT0 0000000 -#define VT1 0040000 -#define FFDLY 0100000 -#define FF0 0000000 -#define FF1 0100000 - -/* c_cflag bit meaning */ -#define CBAUD 0010017 -#define B0 0000000 /* hang up */ -#define B50 0000001 -#define B75 0000002 -#define B110 0000003 -#define B134 0000004 -#define B150 0000005 -#define B200 0000006 -#define B300 0000007 -#define B600 0000010 -#define B1200 0000011 -#define B1800 0000012 -#define B2400 0000013 -#define B4800 0000014 -#define B9600 0000015 -#define B19200 0000016 -#define B38400 0000017 -#define EXTA B19200 -#define EXTB B38400 -#define CSIZE 0000060 -#define CS5 0000000 -#define CS6 0000020 -#define CS7 0000040 -#define CS8 0000060 -#define CSTOPB 0000100 -#define CREAD 0000200 -#define PARENB 0000400 -#define PARODD 0001000 -#define HUPCL 0002000 -#define CLOCAL 0004000 -#define CBAUDEX 0010000 -#define BOTHER 0010000 -#define B57600 0010001 -#define B115200 0010002 -#define B230400 0010003 -#define B460800 0010004 -#define B500000 0010005 -#define B576000 0010006 -#define B921600 0010007 -#define B1000000 0010010 -#define B1152000 0010011 -#define B1500000 0010012 -#define B2000000 0010013 -#define B2500000 0010014 -#define B3000000 0010015 -#define B3500000 0010016 -#define B4000000 0010017 -#define CIBAUD 002003600000 /* input baud rate */ -#define CMSPAR 010000000000 /* mark or space (stick) parity */ -#define CRTSCTS 020000000000 /* flow control */ - -#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ - -/* c_lflag bits */ -#define ISIG 0000001 -#define ICANON 0000002 -#define XCASE 0000004 -#define ECHO 0000010 -#define ECHOE 0000020 -#define ECHOK 0000040 -#define ECHONL 0000100 -#define NOFLSH 0000200 -#define TOSTOP 0000400 -#define ECHOCTL 0001000 -#define ECHOPRT 0002000 -#define ECHOKE 0004000 -#define FLUSHO 0010000 -#define PENDIN 0040000 -#define IEXTEN 0100000 -#define EXTPROC 0200000 - -/* tcflow() and TCXONC use these */ -#define TCOOFF 0 -#define TCOON 1 -#define TCIOFF 2 -#define TCION 3 - -/* tcflush() and TCFLSH use these */ -#define TCIFLUSH 0 -#define TCOFLUSH 1 -#define TCIOFLUSH 2 - -/* tcsetattr uses these */ -#define TCSANOW 0 -#define TCSADRAIN 1 -#define TCSAFLUSH 2 - -#endif /* _ASM_IA64_TERMBITS_H */ diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 834df24a88f1..d7a256bd9d6b 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -32,7 +32,7 @@ #include <linux/delay.h> #include <linux/kdebug.h> #include <linux/utsname.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/rcupdate.h> #include <asm/cpu.h> @@ -179,7 +179,7 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall) if (test_thread_flag(TIF_NOTIFY_RESUME)) { local_irq_enable(); /* force interrupt enable */ - tracehook_notify_resume(&scr->pt); + resume_user_mode_work(&scr->pt); } /* copy user rbs to kernel rbs */ diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index 6a1439eaa050..a19acd9f5e1f 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -23,7 +23,7 @@ #include <linux/signal.h> #include <linux/regset.h> #include <linux/elf.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/processor.h> #include <asm/ptrace_offsets.h> @@ -1217,7 +1217,7 @@ syscall_trace_enter (long arg0, long arg1, long arg2, long arg3, struct pt_regs regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) - if (tracehook_report_syscall_entry(®s)) + if (ptrace_report_syscall_entry(®s)) return -ENOSYS; /* copy user rbs to kernel rbs */ @@ -1243,7 +1243,7 @@ syscall_trace_leave (long arg0, long arg1, long arg2, long arg3, step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(®s, step); + ptrace_report_syscall_exit(®s, step); /* copy user rbs to kernel rbs */ if (test_thread_flag(TIF_RESTORE_RSE)) diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index c1b299760bf7..51cf6a7ec158 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -12,7 +12,6 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/sched.h> #include <linux/signal.h> #include <linux/smp.h> diff --git a/arch/ia64/kernel/syscalls/Makefile b/arch/ia64/kernel/syscalls/Makefile index 14f40ecf8b65..d009f927a048 100644 --- a/arch/ia64/kernel/syscalls/Makefile +++ b/arch/ia64/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c index aa3a0b8d07e9..6342ff4d2073 100644 --- a/arch/m68k/kernel/ptrace.c +++ b/arch/m68k/kernel/ptrace.c @@ -19,7 +19,6 @@ #include <linux/ptrace.h> #include <linux/user.h> #include <linux/signal.h> -#include <linux/tracehook.h> #include <linux/uaccess.h> #include <asm/page.h> @@ -282,13 +281,13 @@ asmlinkage int syscall_trace_enter(void) int ret = 0; if (test_thread_flag(TIF_SYSCALL_TRACE)) - ret = tracehook_report_syscall_entry(task_pt_regs(current)); + ret = ptrace_report_syscall_entry(task_pt_regs(current)); return ret; } asmlinkage void syscall_trace_leave(void) { if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(task_pt_regs(current), 0); + ptrace_report_syscall_exit(task_pt_regs(current), 0); } #endif /* CONFIG_COLDFIRE */ diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 338817d0cb3f..49533f65958a 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -43,7 +43,7 @@ #include <linux/tty.h> #include <linux/binfmts.h> #include <linux/extable.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/setup.h> #include <linux/uaccess.h> @@ -1109,5 +1109,5 @@ void do_notify_resume(struct pt_regs *regs) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/m68k/kernel/syscalls/Makefile b/arch/m68k/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/m68k/kernel/syscalls/Makefile +++ b/arch/m68k/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile index cff570a71946..2b42c370d574 100644 --- a/arch/microblaze/boot/Makefile +++ b/arch/microblaze/boot/Makefile @@ -29,7 +29,7 @@ $(obj)/simpleImage.$(DTB).ub: $(obj)/simpleImage.$(DTB) FORCE $(call if_changed,uimage) $(obj)/simpleImage.$(DTB).unstrip: vmlinux FORCE - $(call if_changed,shipped) + $(call if_changed,copy) $(obj)/simpleImage.$(DTB).strip: vmlinux FORCE $(call if_changed,strip) diff --git a/arch/microblaze/boot/dts/Makefile b/arch/microblaze/boot/dts/Makefile index ef00dd30d19a..b84e2cbb20ee 100644 --- a/arch/microblaze/boot/dts/Makefile +++ b/arch/microblaze/boot/dts/Makefile @@ -12,7 +12,7 @@ $(obj)/linked_dtb.o: $(obj)/system.dtb # Generate system.dtb from $(DTB).dtb ifneq ($(DTB),system) $(obj)/system.dtb: $(obj)/$(DTB).dtb - $(call if_changed,shipped) + $(call if_changed,copy) endif endif diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h index 7c4dc5d85f53..d90528064604 100644 --- a/arch/microblaze/include/asm/pci.h +++ b/arch/microblaze/include/asm/pci.h @@ -61,10 +61,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus, extern void pcibios_resource_survey(void); struct file; -extern pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, - unsigned long size, - pgprot_t prot); /* This part of code was originally in xilinx-pci.h */ #ifdef CONFIG_PCI_XILINX diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c index badd286882ae..5234d0c1dcaa 100644 --- a/arch/microblaze/kernel/ptrace.c +++ b/arch/microblaze/kernel/ptrace.c @@ -33,7 +33,6 @@ #include <linux/elf.h> #include <linux/audit.h> #include <linux/seccomp.h> -#include <linux/tracehook.h> #include <linux/errno.h> #include <asm/processor.h> @@ -140,7 +139,7 @@ asmlinkage unsigned long do_syscall_trace_enter(struct pt_regs *regs) secure_computing_strict(regs->r12); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) + ptrace_report_syscall_entry(regs)) /* * Tracing decided this syscall should not happen. * We'll return a bogus call number to get an ENOSYS @@ -161,7 +160,7 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } void ptrace_disable(struct task_struct *child) diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index 23e8a9336a29..c3aebec71c0c 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -11,7 +11,7 @@ * * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson * - * This file was was derived from the sh version, arch/sh/kernel/signal.c + * This file was derived from the sh version, arch/sh/kernel/signal.c * * This file is subject to the terms and conditions of the GNU General * Public License. See the file COPYING in the main directory of this @@ -31,7 +31,7 @@ #include <linux/personality.h> #include <linux/percpu.h> #include <linux/linkage.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/entry.h> #include <asm/ucontext.h> #include <linux/uaccess.h> @@ -311,5 +311,5 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, int in_syscall) do_signal(regs, in_syscall); if (test_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/microblaze/kernel/syscalls/Makefile b/arch/microblaze/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/microblaze/kernel/syscalls/Makefile +++ b/arch/microblaze/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index 622a4867f9e9..33bab7eec731 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -165,55 +165,6 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma) return 0; } -/* - * This one is used by /dev/mem and fbdev who have no clue about the - * PCI device, it tries to find the PCI device first and calls the - * above routine - */ -pgprot_t pci_phys_mem_access_prot(struct file *file, - unsigned long pfn, - unsigned long size, - pgprot_t prot) -{ - struct pci_dev *pdev = NULL; - struct resource *found = NULL; - resource_size_t offset = ((resource_size_t)pfn) << PAGE_SHIFT; - int i; - - if (page_is_ram(pfn)) - return prot; - - prot = pgprot_noncached(prot); - for_each_pci_dev(pdev) { - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &pdev->resource[i]; - int flags = rp->flags; - - /* Active and same type? */ - if ((flags & IORESOURCE_MEM) == 0) - continue; - /* In the range of this resource? */ - if (offset < (rp->start & PAGE_MASK) || - offset > rp->end) - continue; - found = rp; - break; - } - if (found) - break; - } - if (found) { - if (found->flags & IORESOURCE_PREFETCH) - prot = pgprot_noncached_wc(prot); - pci_dev_put(pdev); - } - - pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n", - (unsigned long long)offset, pgprot_val(prot)); - - return prot; -} - /* This provides legacy IO read access on a bus */ int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size) { diff --git a/arch/microblaze/pci/xilinx_pci.c b/arch/microblaze/pci/xilinx_pci.c index b800909ddccf..f4cb86fffcee 100644 --- a/arch/microblaze/pci/xilinx_pci.c +++ b/arch/microblaze/pci/xilinx_pci.c @@ -27,7 +27,7 @@ #define PCI_HOST_ENABLE_CMD (PCI_COMMAND_SERR | PCI_COMMAND_PARITY | \ PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY) -static struct of_device_id xilinx_pci_match[] = { +static const struct of_device_id xilinx_pci_match[] = { { .compatible = "xlnx,plbv46-pci-1.03.a", }, {} }; diff --git a/arch/mips/boot/dts/ralink/Makefile b/arch/mips/boot/dts/ralink/Makefile index 6c26dfa0a903..11732b8c8163 100644 --- a/arch/mips/boot/dts/ralink/Makefile +++ b/arch/mips/boot/dts/ralink/Makefile @@ -6,4 +6,8 @@ dtb-$(CONFIG_DTB_MT7620A_EVAL) += mt7620a_eval.dtb dtb-$(CONFIG_DTB_OMEGA2P) += omega2p.dtb dtb-$(CONFIG_DTB_VOCORE2) += vocore2.dtb +dtb-$(CONFIG_SOC_MT7621) += \ + mt7621-gnubee-gb-pc1.dtb \ + mt7621-gnubee-gb-pc2.dtb + obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc1.dts b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc1.dts new file mode 100644 index 000000000000..5892bcf71595 --- /dev/null +++ b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc1.dts @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/dts-v1/; + +#include "mt7621.dtsi" + +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/input/input.h> + +/ { + compatible = "gnubee,gb-pc1", "mediatek,mt7621-soc"; + model = "GB-PC1"; + + memory@0 { + device_type = "memory"; + reg = <0x00000000 0x1c000000>, + <0x20000000 0x04000000>; + }; + + chosen { + bootargs = "console=ttyS0,57600"; + }; + + palmbus: palmbus@1e000000 { + i2c@900 { + status = "okay"; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + reset { + label = "reset"; + gpios = <&gpio 18 GPIO_ACTIVE_HIGH>; + linux,code = <KEY_RESTART>; + }; + }; + + gpio-leds { + compatible = "gpio-leds"; + + power { + label = "green:power"; + gpios = <&gpio 6 GPIO_ACTIVE_LOW>; + linux,default-trigger = "default-on"; + }; + + system { + label = "green:system"; + gpios = <&gpio 8 GPIO_ACTIVE_LOW>; + linux,default-trigger = "disk-activity"; + }; + }; +}; + +&sdhci { + status = "okay"; +}; + +&spi0 { + status = "okay"; + + m25p80@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + broken-flash-reset; + + partition@0 { + label = "u-boot"; + reg = <0x0 0x30000>; + read-only; + }; + + partition@30000 { + label = "u-boot-env"; + reg = <0x30000 0x10000>; + read-only; + }; + + factory: partition@40000 { + label = "factory"; + reg = <0x40000 0x10000>; + read-only; + }; + + partition@50000 { + label = "firmware"; + reg = <0x50000 0x1fb0000>; + }; + }; +}; + +&pcie { + status = "okay"; +}; + +&pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&state_default>; + + state_default: state-default { + gpio-pinmux { + groups = "rgmii2", "uart3", "wdt"; + function = "gpio"; + }; + }; +}; + +ðernet { + pinctrl-0 = <&mdio_pins>, <&rgmii1_pins>; +}; + +&switch0 { + ports { + port@0 { + status = "okay"; + label = "ethblack"; + }; + + port@4 { + status = "okay"; + label = "ethblue"; + }; + }; +}; diff --git a/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc2.dts b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc2.dts new file mode 100644 index 000000000000..a7fce8de6147 --- /dev/null +++ b/arch/mips/boot/dts/ralink/mt7621-gnubee-gb-pc2.dts @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/dts-v1/; + +#include "mt7621.dtsi" + +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/input/input.h> + +/ { + compatible = "gnubee,gb-pc2", "mediatek,mt7621-soc"; + model = "GB-PC2"; + + memory@0 { + device_type = "memory"; + reg = <0x00000000 0x1c000000>, + <0x20000000 0x04000000>; + }; + + chosen { + bootargs = "console=ttyS0,57600"; + }; + + palmbus: palmbus@1e000000 { + i2c@900 { + status = "okay"; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + reset { + label = "reset"; + gpios = <&gpio 18 GPIO_ACTIVE_HIGH>; + linux,code = <KEY_RESTART>; + }; + }; +}; + +&sdhci { + status = "okay"; +}; + +&spi0 { + status = "okay"; + + m25p80@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + broken-flash-reset; + + partition@0 { + label = "u-boot"; + reg = <0x0 0x30000>; + read-only; + }; + + partition@30000 { + label = "u-boot-env"; + reg = <0x30000 0x10000>; + read-only; + }; + + factory: partition@40000 { + label = "factory"; + reg = <0x40000 0x10000>; + read-only; + }; + + partition@50000 { + label = "firmware"; + reg = <0x50000 0x1fb0000>; + }; + }; +}; + +&pcie { + status = "okay"; +}; + +&pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&state_default>; + + state_default: state-default { + gpio-pinmux { + groups = "wdt"; + function = "gpio"; + }; + }; +}; + +ðernet { + gmac1: mac@1 { + status = "okay"; + phy-handle = <ðphy7>; + }; + + mdio-bus { + ethphy7: ethernet-phy@7 { + reg = <7>; + phy-mode = "rgmii-rxid"; + }; + }; +}; + +&switch0 { + ports { + port@0 { + status = "okay"; + label = "ethblack"; + }; + + port@4 { + status = "okay"; + label = "ethblue"; + }; + }; +}; diff --git a/arch/mips/boot/dts/ralink/mt7621.dtsi b/arch/mips/boot/dts/ralink/mt7621.dtsi new file mode 100644 index 000000000000..3222684915ac --- /dev/null +++ b/arch/mips/boot/dts/ralink/mt7621.dtsi @@ -0,0 +1,497 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +#include <dt-bindings/interrupt-controller/mips-gic.h> +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/clock/mt7621-clk.h> +#include <dt-bindings/reset/mt7621-reset.h> + +/ { + #address-cells = <1>; + #size-cells = <1>; + compatible = "mediatek,mt7621-soc"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "mips,mips1004Kc"; + reg = <0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "mips,mips1004Kc"; + reg = <1>; + }; + }; + + cpuintc: cpuintc { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + compatible = "mti,cpu-interrupt-controller"; + }; + + aliases { + serial0 = &uartlite; + }; + + + mmc_fixed_3v3: regulator-3v3 { + compatible = "regulator-fixed"; + regulator-name = "mmc_power"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + enable-active-high; + regulator-always-on; + }; + + mmc_fixed_1v8_io: regulator-1v8 { + compatible = "regulator-fixed"; + regulator-name = "mmc_io"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + enable-active-high; + regulator-always-on; + }; + + palmbus: palmbus@1e000000 { + compatible = "palmbus"; + reg = <0x1e000000 0x100000>; + ranges = <0x0 0x1e000000 0x0fffff>; + + #address-cells = <1>; + #size-cells = <1>; + + sysc: syscon@0 { + compatible = "mediatek,mt7621-sysc", "syscon"; + reg = <0x0 0x100>; + #clock-cells = <1>; + #reset-cells = <1>; + ralink,memctl = <&memc>; + clock-output-names = "xtal", "cpu", "bus", + "50m", "125m", "150m", + "250m", "270m"; + }; + + wdt: wdt@100 { + compatible = "mediatek,mt7621-wdt"; + reg = <0x100 0x100>; + }; + + gpio: gpio@600 { + #gpio-cells = <2>; + #interrupt-cells = <2>; + compatible = "mediatek,mt7621-gpio"; + gpio-controller; + gpio-ranges = <&pinctrl 0 0 95>; + interrupt-controller; + reg = <0x600 0x100>; + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 12 IRQ_TYPE_LEVEL_HIGH>; + }; + + i2c: i2c@900 { + compatible = "mediatek,mt7621-i2c"; + reg = <0x900 0x100>; + + clocks = <&sysc MT7621_CLK_I2C>; + clock-names = "i2c"; + resets = <&sysc MT7621_RST_I2C>; + reset-names = "i2c"; + + #address-cells = <1>; + #size-cells = <0>; + + status = "disabled"; + + pinctrl-names = "default"; + pinctrl-0 = <&i2c_pins>; + }; + + memc: syscon@5000 { + compatible = "mediatek,mt7621-memc", "syscon"; + reg = <0x5000 0x1000>; + }; + + uartlite: uartlite@c00 { + compatible = "ns16550a"; + reg = <0xc00 0x100>; + + clocks = <&sysc MT7621_CLK_UART1>; + clock-names = "uart1"; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 26 IRQ_TYPE_LEVEL_HIGH>; + + reg-shift = <2>; + reg-io-width = <4>; + no-loopback-test; + }; + + spi0: spi@b00 { + status = "disabled"; + + compatible = "ralink,mt7621-spi"; + reg = <0xb00 0x100>; + + clocks = <&sysc MT7621_CLK_SPI>; + clock-names = "spi"; + + resets = <&sysc MT7621_RST_SPI>; + reset-names = "spi"; + + #address-cells = <1>; + #size-cells = <0>; + + pinctrl-names = "default"; + pinctrl-0 = <&spi_pins>; + }; + }; + + pinctrl: pinctrl { + compatible = "ralink,rt2880-pinmux"; + + i2c_pins: i2c0-pins { + pinmux { + groups = "i2c"; + function = "i2c"; + }; + }; + + spi_pins: spi0-pins { + pinmux { + groups = "spi"; + function = "spi"; + }; + }; + + uart1_pins: uart1-pins { + pinmux { + groups = "uart1"; + function = "uart1"; + }; + }; + + uart2_pins: uart2-pins { + pinmux { + groups = "uart2"; + function = "uart2"; + }; + }; + + uart3_pins: uart3-pins { + pinmux { + groups = "uart3"; + function = "uart3"; + }; + }; + + rgmii1_pins: rgmii1-pins { + pinmux { + groups = "rgmii1"; + function = "rgmii1"; + }; + }; + + rgmii2_pins: rgmii2-pins { + pinmux { + groups = "rgmii2"; + function = "rgmii2"; + }; + }; + + mdio_pins: mdio0-pins { + pinmux { + groups = "mdio"; + function = "mdio"; + }; + }; + + pcie_pins: pcie0-pins { + pinmux { + groups = "pcie"; + function = "gpio"; + }; + }; + + nand_pins: nand0-pins { + spi-pinmux { + groups = "spi"; + function = "nand1"; + }; + + sdhci-pinmux { + groups = "sdhci"; + function = "nand2"; + }; + }; + + sdhci_pins: sdhci0-pins { + pinmux { + groups = "sdhci"; + function = "sdhci"; + }; + }; + }; + + sdhci: sdhci@1e130000 { + status = "disabled"; + + compatible = "mediatek,mt7620-mmc"; + reg = <0x1e130000 0x4000>; + + bus-width = <4>; + max-frequency = <48000000>; + cap-sd-highspeed; + cap-mmc-highspeed; + vmmc-supply = <&mmc_fixed_3v3>; + vqmmc-supply = <&mmc_fixed_1v8_io>; + disable-wp; + + pinctrl-names = "default", "state_uhs"; + pinctrl-0 = <&sdhci_pins>; + pinctrl-1 = <&sdhci_pins>; + + clocks = <&sysc MT7621_CLK_SHXC>, + <&sysc MT7621_CLK_50M>; + clock-names = "source", "hclk"; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 20 IRQ_TYPE_LEVEL_HIGH>; + }; + + xhci: xhci@1e1c0000 { + compatible = "mediatek,mt8173-xhci"; + reg = <0x1e1c0000 0x1000 + 0x1e1d0700 0x0100>; + reg-names = "mac", "ippc"; + + clocks = <&sysc MT7621_CLK_XTAL>; + clock-names = "sys_ck"; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 22 IRQ_TYPE_LEVEL_HIGH>; + }; + + gic: interrupt-controller@1fbc0000 { + compatible = "mti,gic"; + reg = <0x1fbc0000 0x2000>; + + interrupt-controller; + #interrupt-cells = <3>; + + mti,reserved-cpu-vectors = <7>; + + timer { + compatible = "mti,gic-timer"; + interrupts = <GIC_LOCAL 1 IRQ_TYPE_NONE>; + clocks = <&sysc MT7621_CLK_CPU>; + }; + }; + + cpc: cpc@1fbf0000 { + compatible = "mti,mips-cpc"; + reg = <0x1fbf0000 0x8000>; + }; + + cdmm: cdmm@1fbf8000 { + compatible = "mti,mips-cdmm"; + reg = <0x1fbf8000 0x8000>; + }; + + ethernet: ethernet@1e100000 { + compatible = "mediatek,mt7621-eth"; + reg = <0x1e100000 0x10000>; + + clocks = <&sysc MT7621_CLK_FE>, + <&sysc MT7621_CLK_ETH>; + clock-names = "fe", "ethif"; + + #address-cells = <1>; + #size-cells = <0>; + + resets = <&sysc MT7621_RST_FE &sysc MT7621_RST_ETH>; + reset-names = "fe", "eth"; + + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 3 IRQ_TYPE_LEVEL_HIGH>; + + mediatek,ethsys = <&sysc>; + + pinctrl-names = "default"; + pinctrl-0 = <&mdio_pins>, <&rgmii1_pins>, <&rgmii2_pins>; + + gmac0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "trgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + + gmac1: mac@1 { + compatible = "mediatek,eth-mac"; + reg = <1>; + status = "off"; + phy-mode = "rgmii-rxid"; + }; + + mdio-bus { + #address-cells = <1>; + #size-cells = <0>; + + switch0: switch0@0 { + compatible = "mediatek,mt7621"; + reg = <0>; + mediatek,mcm; + resets = <&sysc MT7621_RST_MCM>; + reset-names = "mcm"; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&gic>; + interrupts = <GIC_SHARED 23 IRQ_TYPE_LEVEL_HIGH>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + status = "off"; + reg = <0>; + label = "lan0"; + }; + + port@1 { + status = "off"; + reg = <1>; + label = "lan1"; + }; + + port@2 { + status = "off"; + reg = <2>; + label = "lan2"; + }; + + port@3 { + status = "off"; + reg = <3>; + label = "lan3"; + }; + + port@4 { + status = "off"; + reg = <4>; + label = "lan4"; + }; + + port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "trgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + }; + }; + }; + + pcie: pcie@1e140000 { + compatible = "mediatek,mt7621-pci"; + reg = <0x1e140000 0x100>, /* host-pci bridge registers */ + <0x1e142000 0x100>, /* pcie port 0 RC control registers */ + <0x1e143000 0x100>, /* pcie port 1 RC control registers */ + <0x1e144000 0x100>; /* pcie port 2 RC control registers */ + #address-cells = <3>; + #size-cells = <2>; + + pinctrl-names = "default"; + pinctrl-0 = <&pcie_pins>; + + device_type = "pci"; + + ranges = <0x02000000 0 0x60000000 0x60000000 0 0x10000000>, /* pci memory */ + <0x01000000 0 0x00000000 0x1e160000 0 0x00010000>; /* io space */ + + #interrupt-cells = <1>; + interrupt-map-mask = <0xF800 0 0 0>; + interrupt-map = <0x0000 0 0 0 &gic GIC_SHARED 4 IRQ_TYPE_LEVEL_HIGH>, + <0x0800 0 0 0 &gic GIC_SHARED 24 IRQ_TYPE_LEVEL_HIGH>, + <0x1000 0 0 0 &gic GIC_SHARED 25 IRQ_TYPE_LEVEL_HIGH>; + + status = "disabled"; + + reset-gpios = <&gpio 19 GPIO_ACTIVE_LOW>; + + pcie@0,0 { + reg = <0x0000 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SHARED 4 IRQ_TYPE_LEVEL_HIGH>; + resets = <&sysc MT7621_RST_PCIE0>; + clocks = <&sysc MT7621_CLK_PCIE0>; + phys = <&pcie0_phy 1>; + phy-names = "pcie-phy0"; + ranges; + }; + + pcie@1,0 { + reg = <0x0800 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SHARED 24 IRQ_TYPE_LEVEL_HIGH>; + resets = <&sysc MT7621_RST_PCIE1>; + clocks = <&sysc MT7621_CLK_PCIE1>; + phys = <&pcie0_phy 1>; + phy-names = "pcie-phy1"; + ranges; + }; + + pcie@2,0 { + reg = <0x1000 0 0 0 0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SHARED 25 IRQ_TYPE_LEVEL_HIGH>; + resets = <&sysc MT7621_RST_PCIE2>; + clocks = <&sysc MT7621_CLK_PCIE2>; + phys = <&pcie2_phy 0>; + phy-names = "pcie-phy2"; + ranges; + }; + }; + + pcie0_phy: pcie-phy@1e149000 { + compatible = "mediatek,mt7621-pci-phy"; + reg = <0x1e149000 0x0700>; + clocks = <&sysc MT7621_CLK_XTAL>; + #phy-cells = <1>; + }; + + pcie2_phy: pcie-phy@1e14a000 { + compatible = "mediatek,mt7621-pci-phy"; + reg = <0x1e14a000 0x0700>; + clocks = <&sysc MT7621_CLK_XTAL>; + #phy-cells = <1>; + }; +}; diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h index 9ceb5e72889f..d3f397dcab6e 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h @@ -1380,8 +1380,6 @@ #define PCIE_IDVAL3_REG 0x43c #define IDVAL3_CLASS_CODE_MASK 0xffffff -#define IDVAL3_SUBCLASS_SHIFT 8 -#define IDVAL3_CLASS_SHIFT 16 #define PCIE_DLSTATUS_REG 0x1048 #define DLSTATUS_PHYLINKUP (1 << 13) diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 40b210c65a5a..1be428663c10 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -101,6 +101,8 @@ #define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ #define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ +#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index db7c5be1d4a3..567aec4abac0 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -27,7 +27,6 @@ #include <linux/smp.h> #include <linux/security.h> #include <linux/stddef.h> -#include <linux/tracehook.h> #include <linux/audit.h> #include <linux/seccomp.h> #include <linux/ftrace.h> @@ -1317,7 +1316,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) current_thread_info()->syscall = syscall; if (test_thread_flag(TIF_SYSCALL_TRACE)) { - if (tracehook_report_syscall_entry(regs)) + if (ptrace_report_syscall_entry(regs)) return -1; syscall = current_thread_info()->syscall; } @@ -1376,7 +1375,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) trace_sys_exit(regs, regs_return_value(regs)); if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); user_enter(); } diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 71e309be86a2..479999b7f2de 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -25,7 +25,7 @@ #include <linux/compiler.h> #include <linux/syscalls.h> #include <linux/uaccess.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/abi.h> #include <asm/asm.h> @@ -915,7 +915,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); user_enter(); } diff --git a/arch/mips/kernel/syscalls/Makefile b/arch/mips/kernel/syscalls/Makefile index 10bf90dc02c0..e6b21de65cca 100644 --- a/arch/mips/kernel/syscalls/Makefile +++ b/arch/mips/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syshdr := $(srctree)/scripts/syscallhdr.sh sysnr := $(srctree)/$(src)/syscallnr.sh diff --git a/arch/mips/pci/fixup-sb1250.c b/arch/mips/pci/fixup-sb1250.c index 40efc990cdce..3f914c33b7de 100644 --- a/arch/mips/pci/fixup-sb1250.c +++ b/arch/mips/pci/fixup-sb1250.c @@ -75,7 +75,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI, */ static void quirk_sb1250_ht(struct pci_dev *dev) { - dev->class = PCI_CLASS_BRIDGE_PCI << 8; + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_HT, quirk_sb1250_ht); diff --git a/arch/mips/pci/pci-bcm63xx.c b/arch/mips/pci/pci-bcm63xx.c index 5548365605c0..ac83243772d2 100644 --- a/arch/mips/pci/pci-bcm63xx.c +++ b/arch/mips/pci/pci-bcm63xx.c @@ -186,7 +186,7 @@ static int __init bcm63xx_register_pcie(void) /* setup class code as bridge */ val = bcm_pcie_readl(PCIE_IDVAL3_REG); val &= ~IDVAL3_CLASS_CODE_MASK; - val |= (PCI_CLASS_BRIDGE_PCI << IDVAL3_SUBCLASS_SHIFT); + val |= PCI_CLASS_BRIDGE_PCI_NORMAL; bcm_pcie_writel(val, PCIE_IDVAL3_REG); /* disable bar1 size */ diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 120adad51d6a..f9fe15630abb 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -54,10 +54,15 @@ choice select HAVE_PCI select PCI_DRIVERS_GENERIC select SOC_BUS + + help + The MT7621 system-on-a-chip includes an 880 MHz MIPS1004Kc dual-core CPU, + a 5-port 10/100/1000 switch/PHY and one RGMII. endchoice choice prompt "Devicetree selection" + depends on !SOC_MT7621 default DTB_RT_NONE help Select the devicetree. diff --git a/arch/nios2/kernel/ptrace.c b/arch/nios2/kernel/ptrace.c index a6ea9e1b4f61..cd62f310778b 100644 --- a/arch/nios2/kernel/ptrace.c +++ b/arch/nios2/kernel/ptrace.c @@ -15,7 +15,6 @@ #include <linux/regset.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> -#include <linux/tracehook.h> #include <linux/uaccess.h> #include <linux/user.h> @@ -134,7 +133,7 @@ asmlinkage int do_syscall_trace_enter(void) int ret = 0; if (test_thread_flag(TIF_SYSCALL_TRACE)) - ret = tracehook_report_syscall_entry(task_pt_regs(current)); + ret = ptrace_report_syscall_entry(task_pt_regs(current)); return ret; } @@ -142,5 +141,5 @@ asmlinkage int do_syscall_trace_enter(void) asmlinkage void do_syscall_trace_exit(void) { if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(task_pt_regs(current), 0); + ptrace_report_syscall_exit(task_pt_regs(current), 0); } diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c index 386e46443b60..cb0b91589cf2 100644 --- a/arch/nios2/kernel/signal.c +++ b/arch/nios2/kernel/signal.c @@ -15,7 +15,7 @@ #include <linux/uaccess.h> #include <linux/unistd.h> #include <linux/personality.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/ucontext.h> #include <asm/cacheflush.h> @@ -321,7 +321,7 @@ asmlinkage int do_notify_resume(struct pt_regs *regs) return restart; } } else if (test_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); return 0; } diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c index 4d60ae2a12fa..b971740fc2aa 100644 --- a/arch/openrisc/kernel/ptrace.c +++ b/arch/openrisc/kernel/ptrace.c @@ -22,7 +22,6 @@ #include <linux/ptrace.h> #include <linux/audit.h> #include <linux/regset.h> -#include <linux/tracehook.h> #include <linux/elf.h> #include <asm/thread_info.h> @@ -159,7 +158,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) long ret = 0; if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) + ptrace_report_syscall_entry(regs)) /* * Tracing decided this syscall should not happen. * We'll return a bogus call number to get an ENOSYS @@ -181,5 +180,5 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index 92c5b70740f5..80f69740c731 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -21,7 +21,7 @@ #include <linux/ptrace.h> #include <linux/unistd.h> #include <linux/stddef.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/processor.h> #include <asm/syscall.h> @@ -309,7 +309,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) } syscall = 0; } else { - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } } local_irq_disable(); diff --git a/arch/openrisc/lib/memcpy.c b/arch/openrisc/lib/memcpy.c index fe2177628fd9..e2af9b510804 100644 --- a/arch/openrisc/lib/memcpy.c +++ b/arch/openrisc/lib/memcpy.c @@ -101,7 +101,7 @@ void *memcpy(void *dest, __const void *src, __kernel_size_t n) */ void *memcpy(void *dest, __const void *src, __kernel_size_t n) { - unsigned char *d = (unsigned char *)dest, *s = (unsigned char *)src; + unsigned char *d, *s; uint32_t *dest_w = (uint32_t *)dest, *src_w = (uint32_t *)src; /* If both source and dest are word aligned copy words */ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 90fc95bd55ca..52e550b45692 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -37,7 +37,7 @@ config PARISC select GENERIC_PCI_IOMAP select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD - select GENERIC_CPU_DEVICES + select GENERIC_ARCH_TOPOLOGY if SMP select GENERIC_LIB_DEVMEM_IS_ALLOWED select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_EXCEPTION_TRACE @@ -56,6 +56,7 @@ config PARISC select HAVE_ARCH_TRACEHOOK select HAVE_REGS_AND_STACK_ACCESS_API select GENERIC_SCHED_CLOCK + select GENERIC_IRQ_MIGRATION if SMP select HAVE_UNSTABLE_SCHED_CLOCK if SMP select LEGACY_TIMER_TICK select CPU_NO_EFFICIENT_FFS @@ -279,16 +280,9 @@ config SMP If you don't know what to do here, say N. -config PARISC_CPU_TOPOLOGY - bool "Support cpu topology definition" - depends on SMP - default y - help - Support PARISC cpu topology definition. - config SCHED_MC bool "Multi-core scheduler support" - depends on PARISC_CPU_TOPOLOGY && PA8X00 + depends on GENERIC_ARCH_TOPOLOGY && PA8X00 help Multi-core scheduler support improves the CPU scheduler's decision making when dealing with multi-core CPU chips at a cost of slightly diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 2a9387a93592..7583fc39ab2d 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -42,7 +42,7 @@ export LD_BFD # Set default 32 bits cross compilers for vdso CC_ARCHES_32 = hppa hppa2.0 hppa1.1 -CC_SUFFIXES = linux linux-gnu unknown-linux-gnu +CC_SUFFIXES = linux linux-gnu unknown-linux-gnu suse-linux CROSS32_COMPILE := $(call cc-cross-prefix, \ $(foreach a,$(CC_ARCHES_32), \ $(foreach s,$(CC_SUFFIXES),$(a)-$(s)-))) @@ -52,7 +52,7 @@ export CROSS32CC # Set default cross compiler for kernel build ifdef cross_compiling ifeq ($(CROSS_COMPILE),) - CC_SUFFIXES = linux linux-gnu unknown-linux-gnu + CC_SUFFIXES = linux linux-gnu unknown-linux-gnu suse-linux CROSS_COMPILE := $(call cc-cross-prefix, \ $(foreach a,$(CC_ARCHES), \ $(foreach s,$(CC_SUFFIXES),$(a)-$(s)-))) diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index 18b957a8630d..b643092d4b98 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -94,6 +94,9 @@ int pdc_sti_call(unsigned long func, unsigned long flags, unsigned long glob_cfg); int __pdc_cpu_rendezvous(void); +void pdc_cpu_rendezvous_lock(void); +void pdc_cpu_rendezvous_unlock(void); + static inline char * os_id_to_string(u16 os_id) { switch(os_id) { case OS_ID_NONE: return "No OS"; diff --git a/arch/parisc/include/asm/pdcpat.h b/arch/parisc/include/asm/pdcpat.h index 24355ed1453a..8f160375b865 100644 --- a/arch/parisc/include/asm/pdcpat.h +++ b/arch/parisc/include/asm/pdcpat.h @@ -83,6 +83,7 @@ #define PDC_PAT_CPU_RENDEZVOUS 6L /* Rendezvous CPU */ #define PDC_PAT_CPU_GET_CLOCK_INFO 7L /* Return CPU Clock info */ #define PDC_PAT_CPU_GET_RENDEZVOUS_STATE 8L /* Return Rendezvous State */ +#define PDC_PAT_CPU_GET_PDC_ENTRYPOINT 11L /* Return PDC Entry point */ #define PDC_PAT_CPU_PLUNGE_FABRIC 128L /* Plunge Fabric */ #define PDC_PAT_CPU_UPDATE_CACHE_CLEANSING 129L /* Manipulate Cache * Cleansing Mode */ @@ -356,7 +357,7 @@ struct pdc_pat_cell_mod_maddr_block { /* PDC_PAT_CELL_MODULE */ typedef struct pdc_pat_cell_mod_maddr_block pdc_pat_cell_mod_maddr_block_t; - +extern int pdc_pat_get_PDC_entrypoint(unsigned long *pdc_entry); extern int pdc_pat_chassis_send_log(unsigned long status, unsigned long data); extern int pdc_pat_cell_get_number(struct pdc_pat_cell_num *cell_info); extern int pdc_pat_cell_info(struct pdc_pat_cell_info_rtn_block *info, diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 006364212795..4621ceb51314 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -95,6 +95,7 @@ struct cpuinfo_parisc { extern struct system_cpuinfo_parisc boot_cpu_data; DECLARE_PER_CPU(struct cpuinfo_parisc, cpu_data); +extern int time_keeper_id; /* CPU used for timekeeping */ #define CPU_HVERSION ((boot_cpu_data.hversion >> 4) & 0x0FFF) diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h index 2279ebe5e2da..94d1f21ce99a 100644 --- a/arch/parisc/include/asm/smp.h +++ b/arch/parisc/include/asm/smp.h @@ -44,12 +44,7 @@ static inline void smp_send_all_nop(void) { return; } #define NO_PROC_ID 0xFF /* No processor magic marker */ #define ANY_PROC_ID 0xFF /* Any processor magic marker */ -static inline int __cpu_disable (void) { - return 0; -} -static inline void __cpu_die (unsigned int cpu) { - while(1) - ; -} +int __cpu_disable(void); +void __cpu_die(unsigned int cpu); #endif /* __ASM_SMP_H */ diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h index 41b3ddbd344c..c822bd0c0e3c 100644 --- a/arch/parisc/include/asm/special_insns.h +++ b/arch/parisc/include/asm/special_insns.h @@ -30,11 +30,15 @@ pa; \ }) +#define CR_EIEM 15 /* External Interrupt Enable Mask */ +#define CR_CR16 16 /* CR16 Interval Timer */ +#define CR_EIRR 23 /* External Interrupt Request Register */ + #define mfctl(reg) ({ \ unsigned long cr; \ __asm__ __volatile__( \ - "mfctl " #reg ",%0" : \ - "=r" (cr) \ + "mfctl %1,%0" : \ + "=r" (cr) : "i" (reg) \ ); \ cr; \ }) @@ -44,13 +48,8 @@ : /* no outputs */ \ : "r" (gr), "i" (cr) : "memory") -/* these are here to de-mystefy the calling code, and to provide hooks */ -/* which I needed for debugging EIEM problems -PB */ -#define get_eiem() mfctl(15) -static inline void set_eiem(unsigned long val) -{ - mtctl(val, 15); -} +#define get_eiem() mfctl(CR_EIEM) +#define set_eiem(val) mtctl(val, CR_EIEM) #define mfsp(reg) ({ \ unsigned long cr; \ diff --git a/arch/parisc/include/asm/topology.h b/arch/parisc/include/asm/topology.h index 6f0750c74e47..406afb356f1a 100644 --- a/arch/parisc/include/asm/topology.h +++ b/arch/parisc/include/asm/topology.h @@ -1,33 +1,16 @@ #ifndef _ASM_PARISC_TOPOLOGY_H #define _ASM_PARISC_TOPOLOGY_H -#ifdef CONFIG_PARISC_CPU_TOPOLOGY +#ifdef CONFIG_GENERIC_ARCH_TOPOLOGY #include <linux/cpumask.h> - -struct cputopo_parisc { - int thread_id; - int core_id; - int socket_id; - cpumask_t thread_sibling; - cpumask_t core_sibling; -}; - -extern struct cputopo_parisc cpu_topology[NR_CPUS]; - -#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) -#define topology_core_id(cpu) (cpu_topology[cpu].core_id) -#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) - -void init_cpu_topology(void); -void store_cpu_topology(unsigned int cpuid); -const struct cpumask *cpu_coregroup_mask(int cpu); +#include <linux/arch_topology.h> #else static inline void init_cpu_topology(void) { } static inline void store_cpu_topology(unsigned int cpuid) { } +static inline void reset_cpu_topology(void) { } #endif diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 9e3c010c0f61..a7ea3204a5fa 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -55,6 +55,8 @@ #define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ #define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ +#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ + #define MADV_MERGEABLE 65 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index d579243edc2f..d0bfac89a842 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -31,7 +31,7 @@ obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o # only supported for PCX-W/U in 64-bit mode at the moment obj-$(CONFIG_64BIT) += perf.o perf_asm.o $(obj64-y) -obj-$(CONFIG_PARISC_CPU_TOPOLOGY) += topology.o +obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += topology.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 456e879d34a8..23348199f3f8 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -273,7 +273,7 @@ parisc_cache_init(void) } } -void __init disable_sr_hashing(void) +void disable_sr_hashing(void) { int srhash_type, retval; unsigned long space_bits; @@ -611,8 +611,8 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { if (pfn_valid(pfn)) { - flush_tlb_page(vma, vmaddr); if (likely(vma->vm_mm->context.space_id)) { + flush_tlb_page(vma, vmaddr); __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } else { __purge_cache_page(vma, vmaddr, PFN_PHYS(pfn)); @@ -624,7 +624,6 @@ void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - unsigned long flags, physaddr; if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && (unsigned long)size >= parisc_cache_flush_threshold) { @@ -633,14 +632,8 @@ void flush_kernel_vmap_range(void *vaddr, int size) return; } - while (start < end) { - physaddr = lpa(start); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, start); - purge_tlb_end(flags); - flush_dcache_page_asm(physaddr, start); - start += PAGE_SIZE; - } + flush_kernel_dcache_range_asm(start, end); + flush_tlb_kernel_range(start, end); } EXPORT_SYMBOL(flush_kernel_vmap_range); @@ -648,7 +641,6 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - unsigned long flags, physaddr; if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && (unsigned long)size >= parisc_cache_flush_threshold) { @@ -657,13 +649,7 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) return; } - while (start < end) { - physaddr = lpa(start); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, start); - purge_tlb_end(flags); - purge_dcache_page_asm(physaddr, start); - start += PAGE_SIZE; - } + purge_kernel_dcache_range_asm(start, end); + flush_tlb_kernel_range(start, end); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 3370e347dde3..6a7e315bcc2e 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -83,7 +83,7 @@ extern unsigned long pdc_result2[NUM_PDC_RESULT]; /* Firmware needs to be initially set to narrow to determine the * actual firmware width. */ -int parisc_narrow_firmware __ro_after_init = 1; +int parisc_narrow_firmware __ro_after_init = 2; #endif /* On most currently-supported platforms, IODC I/O calls are 32-bit calls @@ -174,6 +174,11 @@ void set_firmware_width_unlocked(void) void set_firmware_width(void) { unsigned long flags; + + /* already initialized? */ + if (parisc_narrow_firmware != 2) + return; + spin_lock_irqsave(&pdc_lock, flags); set_firmware_width_unlocked(); spin_unlock_irqrestore(&pdc_lock, flags); @@ -324,7 +329,44 @@ int __pdc_cpu_rendezvous(void) return mem_pdc_call(PDC_PROC, 1, 0); } +/** + * pdc_cpu_rendezvous_lock - Lock PDC while transitioning to rendezvous state + */ +void pdc_cpu_rendezvous_lock(void) +{ + spin_lock(&pdc_lock); +} + +/** + * pdc_cpu_rendezvous_unlock - Unlock PDC after reaching rendezvous state + */ +void pdc_cpu_rendezvous_unlock(void) +{ + spin_unlock(&pdc_lock); +} + +/** + * pdc_pat_get_PDC_entrypoint - Get PDC entry point for current CPU + * @retval: -1 on error, 0 on success + */ +int pdc_pat_get_PDC_entrypoint(unsigned long *pdc_entry) +{ + int retval = 0; + unsigned long flags; + + if (!IS_ENABLED(CONFIG_SMP) || !is_pdc_pat()) { + *pdc_entry = MEM_PDC; + return 0; + } + + spin_lock_irqsave(&pdc_lock, flags); + retval = mem_pdc_call(PDC_PAT_CPU, PDC_PAT_CPU_GET_PDC_ENTRYPOINT, + __pa(pdc_result)); + *pdc_entry = pdc_result[0]; + spin_unlock_irqrestore(&pdc_lock, flags); + return retval; +} /** * pdc_chassis_warn - Fetches chassis warnings * @retval: -1 on error, 0 on success diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index b24f77748c22..e0a9e9657622 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -162,6 +162,15 @@ $pgt_fill_loop: /* FALLTHROUGH */ .procend +#ifdef CONFIG_HOTPLUG_CPU + /* common_stext is far away in another section... jump there */ + load32 PA(common_stext), %rp + bv,n (%rp) + + /* common_stext and smp_slave_stext needs to be in text section */ + .text +#endif + /* ** Code Common to both Monarch and Slave processors. ** Entry: @@ -371,8 +380,6 @@ smp_slave_stext: .procend #endif /* CONFIG_SMP */ -ENDPROC(parisc_kernel_start) - #ifndef CONFIG_64BIT .section .data..ro_after_init diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index eb18e16362f6..0fe2d79fb123 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -105,28 +105,12 @@ int cpu_check_affinity(struct irq_data *d, const struct cpumask *dest) if (irqd_is_per_cpu(d)) return -EINVAL; - /* whatever mask they set, we just allow one CPU */ - cpu_dest = cpumask_next_and(d->irq & (num_online_cpus()-1), - dest, cpu_online_mask); + cpu_dest = cpumask_first_and(dest, cpu_online_mask); if (cpu_dest >= nr_cpu_ids) - cpu_dest = cpumask_first_and(dest, cpu_online_mask); + cpu_dest = cpumask_first(cpu_online_mask); return cpu_dest; } - -static int cpu_set_affinity_irq(struct irq_data *d, const struct cpumask *dest, - bool force) -{ - int cpu_dest; - - cpu_dest = cpu_check_affinity(d, dest); - if (cpu_dest < 0) - return -1; - - cpumask_copy(irq_data_get_affinity_mask(d), dest); - - return 0; -} #endif static struct irq_chip cpu_interrupt_type = { @@ -135,9 +119,6 @@ static struct irq_chip cpu_interrupt_type = { .irq_unmask = cpu_unmask_irq, .irq_ack = cpu_ack_irq, .irq_eoi = cpu_eoi_irq, -#ifdef CONFIG_SMP - .irq_set_affinity = cpu_set_affinity_irq, -#endif /* XXX: Needs to be written. We managed without it so far, but * we really ought to write it. */ @@ -582,7 +563,7 @@ static void claim_cpu_irqs(void) #endif } -void __init init_IRQ(void) +void init_IRQ(void) { local_irq_disable(); /* PARANOID - should already be disabled */ mtctl(~0UL, 23); /* EIRR : clear all pending external intr */ diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index b2ba6d633065..b4c3f01e2399 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -1264,7 +1264,7 @@ ENTRY_CFI(flush_kernel_icache_range_asm) nop ENDPROC_CFI(flush_kernel_icache_range_asm) - __INIT + .text /* align should cover use of rfi in disable_sr_hashing_asm and * srdis_done. diff --git a/arch/parisc/kernel/patch.c b/arch/parisc/kernel/patch.c index 80a0ab372802..e59574f65e64 100644 --- a/arch/parisc/kernel/patch.c +++ b/arch/parisc/kernel/patch.c @@ -40,10 +40,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags, *need_unmap = 1; set_fixmap(fixmap, page_to_phys(page)); - if (flags) - raw_spin_lock_irqsave(&patch_lock, *flags); - else - __acquire(&patch_lock); + raw_spin_lock_irqsave(&patch_lock, *flags); return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK)); } @@ -52,10 +49,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { clear_fixmap(fixmap); - if (flags) - raw_spin_unlock_irqrestore(&patch_lock, *flags); - else - __release(&patch_lock); + raw_spin_unlock_irqrestore(&patch_lock, *flags); } void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) @@ -67,8 +61,9 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) int mapped; /* Make sure we don't have any aliases in cache */ - flush_kernel_vmap_range(addr, len); - flush_icache_range(start, end); + flush_kernel_dcache_range_asm(start, end); + flush_kernel_icache_range_asm(start, end); + flush_tlb_kernel_range(start, end); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, &mapped); @@ -81,8 +76,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) * We're crossing a page boundary, so * need to remap */ - flush_kernel_vmap_range((void *)fixmap, - (p-fixmap) * sizeof(*p)); + flush_kernel_dcache_range_asm((unsigned long)fixmap, + (unsigned long)p); + flush_tlb_kernel_range((unsigned long)fixmap, + (unsigned long)p); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, @@ -90,10 +87,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) } } - flush_kernel_vmap_range((void *)fixmap, (p-fixmap) * sizeof(*p)); + flush_kernel_dcache_range_asm((unsigned long)fixmap, (unsigned long)p); + flush_tlb_kernel_range((unsigned long)fixmap, (unsigned long)p); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); - flush_icache_range(start, end); } void __kprobes __patch_text(void *addr, u32 insn) diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 2030c77592d3..28b6a2a5574c 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -38,6 +38,7 @@ #include <linux/rcupdate.h> #include <linux/random.h> #include <linux/nmi.h> +#include <linux/sched/hotplug.h> #include <asm/io.h> #include <asm/asm-offsets.h> @@ -46,6 +47,7 @@ #include <asm/pdc_chassis.h> #include <asm/unwind.h> #include <asm/sections.h> +#include <asm/cacheflush.h> #define COMMAND_GLOBAL F_EXTEND(0xfffe0030) #define CMD_RESET 5 /* reset any module */ @@ -158,10 +160,29 @@ void release_thread(struct task_struct *dead_task) int running_on_qemu __ro_after_init; EXPORT_SYMBOL(running_on_qemu); -void __cpuidle arch_cpu_idle_dead(void) +/* + * Called from the idle thread for the CPU which has been shutdown. + */ +void arch_cpu_idle_dead(void) { - /* nop on real hardware, qemu will offline CPU. */ - asm volatile("or %%r31,%%r31,%%r31\n":::); +#ifdef CONFIG_HOTPLUG_CPU + idle_task_exit(); + + local_irq_disable(); + + /* Tell __cpu_die() that this CPU is now safe to dispose of. */ + (void)cpu_report_death(); + + /* Ensure that the cache lines are written out. */ + flush_cache_all_local(); + flush_tlb_all_local(NULL); + + /* Let PDC firmware put CPU into firmware idle loop. */ + __pdc_cpu_rendezvous(); + + pr_warn("PDC does not provide rendezvous function.\n"); +#endif + while (1); } void __cpuidle arch_cpu_idle(void) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 1b6129e7d776..d98692115221 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -19,6 +19,7 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/cpu.h> +#include <asm/topology.h> #include <asm/param.h> #include <asm/cache.h> #include <asm/hardware.h> /* for register_parisc_driver() stuff */ @@ -317,7 +318,7 @@ void __init collect_boot_cpu_data(void) * * o Enable CPU profiling hooks. */ -int __init init_per_cpu(int cpunum) +int init_per_cpu(int cpunum) { int ret; struct pdc_coproc_cfg coproc_cfg; @@ -390,7 +391,7 @@ show_cpuinfo (struct seq_file *m, void *v) boot_cpu_data.cpu_hz / 1000000, boot_cpu_data.cpu_hz % 1000000 ); -#ifdef CONFIG_PARISC_CPU_TOPOLOGY +#ifdef CONFIG_GENERIC_ARCH_TOPOLOGY seq_printf(m, "physical id\t: %d\n", topology_physical_package_id(cpu)); seq_printf(m, "siblings\t: %d\n", @@ -460,5 +461,6 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { + reset_cpu_topology(); register_parisc_driver(&cpu_driver); } diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 65de6c4c9354..96ef6a6b66e5 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -15,7 +15,6 @@ #include <linux/elf.h> #include <linux/errno.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/user.h> #include <linux/personality.h> #include <linux/regset.h> @@ -316,7 +315,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) { - int rc = tracehook_report_syscall_entry(regs); + int rc = ptrace_report_syscall_entry(regs); /* * As tracesys_next does not set %r28 to -ENOSYS @@ -327,7 +326,7 @@ long do_syscall_trace_enter(struct pt_regs *regs) if (rc) { /* * A nonzero return code from - * tracehook_report_syscall_entry() tells us + * ptrace_report_syscall_entry() tells us * to prevent the syscall execution. Skip * the syscall call and the syscall restart handling. * @@ -381,7 +380,7 @@ void do_syscall_trace_exit(struct pt_regs *regs) #endif if (stepping || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, stepping); + ptrace_report_syscall_exit(regs, stepping); } diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 3dd672e2e301..8bc0ddaa6219 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -19,7 +19,7 @@ #include <linux/errno.h> #include <linux/wait.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/compat.h> @@ -585,5 +585,5 @@ void do_notify_resume(struct pt_regs *regs, long in_syscall) do_signal(regs, in_syscall); if (test_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index a32a882a2d58..24d0744c3b3a 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -30,6 +30,7 @@ #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/kgdb.h> +#include <linux/sched/hotplug.h> #include <linux/atomic.h> #include <asm/current.h> @@ -60,8 +61,6 @@ volatile struct task_struct *smp_init_current_idle_task; /* track which CPU is booting */ static volatile int cpu_now_booting; -static int parisc_max_cpus = 1; - static DEFINE_PER_CPU(spinlock_t, ipi_lock); enum ipi_message_type { @@ -269,7 +268,7 @@ void arch_send_call_function_single_ipi(int cpu) /* * Called by secondaries to update state and initialize CPU registers. */ -static void __init +static void smp_cpu_init(int cpunum) { extern void init_IRQ(void); /* arch/parisc/kernel/irq.c */ @@ -309,7 +308,7 @@ smp_cpu_init(int cpunum) * Slaves start using C here. Indirectly called from smp_slave_stext. * Do what start_kernel() and main() do for boot strap processor (aka monarch) */ -void __init smp_callin(unsigned long pdce_proc) +void smp_callin(unsigned long pdce_proc) { int slave_id = cpu_now_booting; @@ -334,11 +333,28 @@ void __init smp_callin(unsigned long pdce_proc) /* * Bring one cpu online. */ -int smp_boot_one_cpu(int cpuid, struct task_struct *idle) +static int smp_boot_one_cpu(int cpuid, struct task_struct *idle) { const struct cpuinfo_parisc *p = &per_cpu(cpu_data, cpuid); long timeout; +#ifdef CONFIG_HOTPLUG_CPU + int i; + + /* reset irq statistics for this CPU */ + memset(&per_cpu(irq_stat, cpuid), 0, sizeof(irq_cpustat_t)); + for (i = 0; i < NR_IRQS; i++) { + struct irq_desc *desc = irq_to_desc(i); + + if (desc && desc->kstat_irqs) + *per_cpu_ptr(desc->kstat_irqs, cpuid) = 0; + } +#endif + + /* wait until last booting CPU has started. */ + while (cpu_now_booting) + ; + /* Let _start know what logical CPU we're booting ** (offset into init_tasks[],cpu_data[]) */ @@ -374,7 +390,6 @@ int smp_boot_one_cpu(int cpuid, struct task_struct *idle) if(cpu_online(cpuid)) { /* Which implies Slave has started up */ cpu_now_booting = 0; - smp_init_current_idle_task = NULL; goto alive ; } udelay(100); @@ -415,25 +430,88 @@ void __init smp_prepare_cpus(unsigned int max_cpus) spin_lock_init(&per_cpu(ipi_lock, cpu)); init_cpu_present(cpumask_of(0)); - - parisc_max_cpus = max_cpus; - if (!max_cpus) - printk(KERN_INFO "SMP mode deactivated.\n"); } -void smp_cpus_done(unsigned int cpu_max) +void __init smp_cpus_done(unsigned int cpu_max) { - return; } int __cpu_up(unsigned int cpu, struct task_struct *tidle) { - if (cpu != 0 && cpu < parisc_max_cpus && smp_boot_one_cpu(cpu, tidle)) - return -ENOSYS; + if (cpu_online(cpu)) + return 0; + + if (num_online_cpus() < setup_max_cpus && smp_boot_one_cpu(cpu, tidle)) + return -EIO; + + return cpu_online(cpu) ? 0 : -EIO; +} + +/* + * __cpu_disable runs on the processor to be shutdown. + */ +int __cpu_disable(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + unsigned int cpu = smp_processor_id(); + + remove_cpu_topology(cpu); + + /* + * Take this CPU offline. Once we clear this, we can't return, + * and we must not schedule until we're ready to give up the cpu. + */ + set_cpu_online(cpu, false); + + /* Find a new timesync master */ + if (cpu == time_keeper_id) { + time_keeper_id = cpumask_first(cpu_online_mask); + pr_info("CPU %d is now promoted to time-keeper master\n", time_keeper_id); + } + + disable_percpu_irq(IPI_IRQ); + + irq_migrate_all_off_this_cpu(); + + flush_cache_all_local(); + flush_tlb_all_local(NULL); + + /* disable all irqs, including timer irq */ + local_irq_disable(); + + /* wait for next timer irq ... */ + mdelay(1000/HZ+100); + + /* ... and then clear all pending external irqs */ + set_eiem(0); + mtctl(~0UL, CR_EIRR); + mfctl(CR_EIRR); + mtctl(0, CR_EIRR); +#endif + return 0; +} + +/* + * called on the thread which is asking for a CPU to be shutdown - + * waits until shutdown has completed, or it is timed out. + */ +void __cpu_die(unsigned int cpu) +{ + pdc_cpu_rendezvous_lock(); + + if (!cpu_wait_death(cpu, 5)) { + pr_crit("CPU%u: cpu didn't die\n", cpu); + return; + } + pr_info("CPU%u: is shutting down\n", cpu); + + /* set task's state to interruptible sleep */ + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout((IS_ENABLED(CONFIG_64BIT) ? 8:2) * HZ); - return cpu_online(cpu) ? 0 : -ENOSYS; + pdc_cpu_rendezvous_unlock(); } #ifdef CONFIG_PROC_FS diff --git a/arch/parisc/kernel/syscalls/Makefile b/arch/parisc/kernel/syscalls/Makefile index d63f18dd058d..8440c16dfb22 100644 --- a/arch/parisc/kernel/syscalls/Makefile +++ b/arch/parisc/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 061119a56fbe..bb27dfeeddfc 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -40,6 +40,8 @@ #include <linux/timex.h> +int time_keeper_id __read_mostly; /* CPU used for timekeeping. */ + static unsigned long clocktick __ro_after_init; /* timer cycles per tick */ /* @@ -84,7 +86,7 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) cpuinfo->it_value = next_tick; /* Go do system house keeping. */ - if (cpu != 0) + if (IS_ENABLED(CONFIG_SMP) && (cpu != time_keeper_id)) ticks_elapsed = 0; legacy_timer_tick(ticks_elapsed); @@ -150,7 +152,7 @@ static struct clocksource clocksource_cr16 = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -void __init start_cpu_itimer(void) +void start_cpu_itimer(void) { unsigned int cpu = smp_processor_id(); unsigned long next_tick = mfctl(16) + clocktick; diff --git a/arch/parisc/kernel/topology.c b/arch/parisc/kernel/topology.c index e88a6ce7c96d..9696e3cb6a2a 100644 --- a/arch/parisc/kernel/topology.c +++ b/arch/parisc/kernel/topology.c @@ -13,56 +13,23 @@ #include <linux/percpu.h> #include <linux/sched.h> #include <linux/sched/topology.h> +#include <linux/cpu.h> #include <asm/topology.h> +#include <asm/sections.h> - /* - * cpu topology table - */ -struct cputopo_parisc cpu_topology[NR_CPUS] __read_mostly; -EXPORT_SYMBOL_GPL(cpu_topology); +static DEFINE_PER_CPU(struct cpu, cpu_devices); -const struct cpumask *cpu_coregroup_mask(int cpu) -{ - return &cpu_topology[cpu].core_sibling; -} - -static void update_siblings_masks(unsigned int cpuid) -{ - struct cputopo_parisc *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; - int cpu; - - /* update core and thread sibling masks */ - for_each_possible_cpu(cpu) { - cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->socket_id != cpu_topo->socket_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); - - if (cpuid_topo->core_id != cpu_topo->core_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); - } - smp_wmb(); -} - -static int dualcores_found __initdata; +static int dualcores_found; /* * store_cpu_topology is called at boot when only one cpu is running * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, * which prevents simultaneous write access to cpu_topology array */ -void __init store_cpu_topology(unsigned int cpuid) +void store_cpu_topology(unsigned int cpuid) { - struct cputopo_parisc *cpuid_topo = &cpu_topology[cpuid]; + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; struct cpuinfo_parisc *p; int max_socket = -1; unsigned long cpu; @@ -71,6 +38,12 @@ void __init store_cpu_topology(unsigned int cpuid) if (cpuid_topo->core_id != -1) return; +#ifdef CONFIG_HOTPLUG_CPU + per_cpu(cpu_devices, cpuid).hotpluggable = 1; +#endif + if (register_cpu(&per_cpu(cpu_devices, cpuid), cpuid)) + pr_warn("Failed to register CPU%d device", cpuid); + /* create cpu topology mapping */ cpuid_topo->thread_id = -1; cpuid_topo->core_id = 0; @@ -86,25 +59,25 @@ void __init store_cpu_topology(unsigned int cpuid) cpuid_topo->core_id = cpu_topology[cpu].core_id; if (p->cpu_loc) { cpuid_topo->core_id++; - cpuid_topo->socket_id = cpu_topology[cpu].socket_id; + cpuid_topo->package_id = cpu_topology[cpu].package_id; dualcores_found = 1; continue; } } - if (cpuid_topo->socket_id == -1) - max_socket = max(max_socket, cpu_topology[cpu].socket_id); + if (cpuid_topo->package_id == -1) + max_socket = max(max_socket, cpu_topology[cpu].package_id); } - if (cpuid_topo->socket_id == -1) - cpuid_topo->socket_id = max_socket + 1; + if (cpuid_topo->package_id == -1) + cpuid_topo->package_id = max_socket + 1; update_siblings_masks(cpuid); pr_info("CPU%u: cpu core %d of socket %d\n", cpuid, cpu_topology[cpuid].core_id, - cpu_topology[cpuid].socket_id); + cpu_topology[cpuid].package_id); } static struct sched_domain_topology_level parisc_mc_topology[] = { @@ -122,20 +95,6 @@ static struct sched_domain_topology_level parisc_mc_topology[] = { */ void __init init_cpu_topology(void) { - unsigned int cpu; - - /* init core mask and capacity */ - for_each_possible_cpu(cpu) { - struct cputopo_parisc *cpu_topo = &(cpu_topology[cpu]); - - cpu_topo->thread_id = -1; - cpu_topo->core_id = -1; - cpu_topo->socket_id = -1; - cpumask_clear(&cpu_topo->core_sibling); - cpumask_clear(&cpu_topo->thread_sibling); - } - smp_wmb(); - /* Set scheduler topology descriptor */ if (dualcores_found) set_sched_topology(parisc_mc_topology); diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 219559d65864..47ed639f3b8f 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -48,6 +48,11 @@ struct dev_archdata { struct pdev_archdata { u64 dma_mask; + /* + * Pointer to nvdimm_pmu structure, to handle the unregistering + * of pmu device + */ + void *priv; }; #endif /* _ASM_POWERPC_DEVICE_H */ diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h index 6f10de6af6e3..1c60094ea0cd 100644 --- a/arch/powerpc/include/asm/livepatch.h +++ b/arch/powerpc/include/asm/livepatch.h @@ -16,16 +16,6 @@ static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip) { ftrace_instruction_pointer_set(fregs, ip); } - -#define klp_get_ftrace_location klp_get_ftrace_location -static inline unsigned long klp_get_ftrace_location(unsigned long faddr) -{ - /* - * Live patch works on PPC32 and only with -mprofile-kernel on PPC64. In - * both cases, the ftrace location is always within the first 16 bytes. - */ - return ftrace_location_range(faddr, faddr + 16); -} #endif /* CONFIG_LIVEPATCH */ #ifdef CONFIG_LIVEPATCH_64 diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 9a492fdec1df..7dae0b01abfb 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -105,6 +105,27 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset) return addr; } +static bool arch_kprobe_on_func_entry(unsigned long offset) +{ +#ifdef PPC64_ELF_ABI_v2 +#ifdef CONFIG_KPROBES_ON_FTRACE + return offset <= 16; +#else + return offset <= 8; +#endif +#else + return !offset; +#endif +} + +/* XXX try and fold the magic of kprobe_lookup_name() in this */ +kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, + bool *on_func_entry) +{ + *on_func_entry = arch_kprobe_on_func_entry(offset); + return (kprobe_opcode_t *)(addr + offset); +} + void *alloc_insn_page(void) { void *page; @@ -218,19 +239,6 @@ static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs kcb->kprobe_saved_msr = regs->msr; } -bool arch_kprobe_on_func_entry(unsigned long offset) -{ -#ifdef PPC64_ELF_ABI_v2 -#ifdef CONFIG_KPROBES_ON_FTRACE - return offset <= 16; -#else - return offset <= 8; -#endif -#else - return !offset; -#endif -} - void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { ri->ret_addr = (kprobe_opcode_t *)regs->link; diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c index 55742ef1f991..6d5026a9db4f 100644 --- a/arch/powerpc/kernel/ptrace/ptrace.c +++ b/arch/powerpc/kernel/ptrace/ptrace.c @@ -16,7 +16,7 @@ */ #include <linux/regset.h> -#include <linux/tracehook.h> +#include <linux/ptrace.h> #include <linux/audit.h> #include <linux/context_tracking.h> #include <linux/syscalls.h> @@ -262,12 +262,12 @@ long do_syscall_trace_enter(struct pt_regs *regs) flags = read_thread_flags() & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE); if (flags) { - int rc = tracehook_report_syscall_entry(regs); + int rc = ptrace_report_syscall_entry(regs); if (unlikely(flags & _TIF_SYSCALL_EMU)) { /* * A nonzero return code from - * tracehook_report_syscall_entry() tells us to prevent + * ptrace_report_syscall_entry() tells us to prevent * the syscall execution, but we are not going to * execute it anyway. * @@ -333,7 +333,7 @@ void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } void __init pt_regs_check(void); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index b93b87df499d..f7f8620663c7 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -9,7 +9,7 @@ * this archive for more details. */ -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/signal.h> #include <linux/uprobes.h> #include <linux/key.h> @@ -294,7 +294,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) } if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } static unsigned long get_tm_stackpointer(struct task_struct *tsk) diff --git a/arch/powerpc/kernel/syscalls/Makefile b/arch/powerpc/kernel/syscalls/Makefile index 5476f62eb80f..9d7bd81510b8 100644 --- a/arch/powerpc/kernel/syscalls/Makefile +++ b/arch/powerpc/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/powerpc/mm/book3s64/trace.c b/arch/powerpc/mm/book3s64/trace.c index b86e7b906257..ccd64b5e6cac 100644 --- a/arch/powerpc/mm/book3s64/trace.c +++ b/arch/powerpc/mm/book3s64/trace.c @@ -3,6 +3,5 @@ * This file is for defining trace points and trace related helpers. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define CREATE_TRACE_POINTS #include <trace/events/thp.h> #endif diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 9a8391b983d1..f7054879ecd4 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -815,7 +815,7 @@ void pnv_pci_shutdown(void) /* Fixup wrong class code in p7ioc and p8 root complex */ static void pnv_p7ioc_rc_quirk(struct pci_dev *dev) { - dev->class = PCI_CLASS_BRIDGE_PCI << 8; + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk); diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 1238b94b3cc1..f58728d5f10d 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -19,6 +19,7 @@ #include <asm/papr_pdsm.h> #include <asm/mce.h> #include <asm/unaligned.h> +#include <linux/perf_event.h> #define BIND_ANY_ADDR (~0ul) @@ -124,6 +125,8 @@ struct papr_scm_priv { /* The bits which needs to be overridden */ u64 health_bitmap_inject_mask; + /* array to have event_code and stat_id mappings */ + char **nvdimm_events_map; }; static int papr_scm_pmem_flush(struct nd_region *nd_region, @@ -344,6 +347,225 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p, return 0; } +#ifdef CONFIG_PERF_EVENTS +#define to_nvdimm_pmu(_pmu) container_of(_pmu, struct nvdimm_pmu, pmu) + +static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, u64 *count) +{ + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + struct papr_scm_priv *p = (struct papr_scm_priv *)dev->driver_data; + int rc, size; + + /* Allocate request buffer enough to hold single performance stat */ + size = sizeof(struct papr_scm_perf_stats) + + sizeof(struct papr_scm_perf_stat); + + if (!p || !p->nvdimm_events_map) + return -EINVAL; + + stats = kzalloc(size, GFP_KERNEL); + if (!stats) + return -ENOMEM; + + stat = &stats->scm_statistic[0]; + memcpy(&stat->stat_id, + p->nvdimm_events_map[event->attr.config], + sizeof(stat->stat_id)); + stat->stat_val = 0; + + rc = drc_pmem_query_stats(p, stats, 1); + if (rc < 0) { + kfree(stats); + return rc; + } + + *count = be64_to_cpu(stat->stat_val); + kfree(stats); + return 0; +} + +static int papr_scm_pmu_event_init(struct perf_event *event) +{ + struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); + struct papr_scm_priv *p; + + if (!nd_pmu) + return -EINVAL; + + /* test the event attr type for PMU enumeration */ + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* it does not support event sampling mode */ + if (is_sampling_event(event)) + return -EOPNOTSUPP; + + /* no branch sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + p = (struct papr_scm_priv *)nd_pmu->dev->driver_data; + if (!p) + return -EINVAL; + + /* Invalid eventcode */ + if (event->attr.config == 0 || event->attr.config > 16) + return -EINVAL; + + return 0; +} + +static int papr_scm_pmu_add(struct perf_event *event, int flags) +{ + u64 count; + int rc; + struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); + + if (!nd_pmu) + return -EINVAL; + + if (flags & PERF_EF_START) { + rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &count); + if (rc) + return rc; + + local64_set(&event->hw.prev_count, count); + } + + return 0; +} + +static void papr_scm_pmu_read(struct perf_event *event) +{ + u64 prev, now; + int rc; + struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu); + + if (!nd_pmu) + return; + + rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &now); + if (rc) + return; + + prev = local64_xchg(&event->hw.prev_count, now); + local64_add(now - prev, &event->count); +} + +static void papr_scm_pmu_del(struct perf_event *event, int flags) +{ + papr_scm_pmu_read(event); +} + +static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu *nd_pmu) +{ + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + char *statid; + int index, rc, count; + u32 available_events; + + if (!p->stat_buffer_len) + return -ENOENT; + + available_events = (p->stat_buffer_len - sizeof(struct papr_scm_perf_stats)) + / sizeof(struct papr_scm_perf_stat); + + /* Allocate the buffer for phyp where stats are written */ + stats = kzalloc(p->stat_buffer_len, GFP_KERNEL); + if (!stats) { + rc = -ENOMEM; + return rc; + } + + /* Allocate memory to nvdimm_event_map */ + p->nvdimm_events_map = kcalloc(available_events, sizeof(char *), GFP_KERNEL); + if (!p->nvdimm_events_map) { + rc = -ENOMEM; + goto out_stats; + } + + /* Called to get list of events supported */ + rc = drc_pmem_query_stats(p, stats, 0); + if (rc) + goto out_nvdimm_events_map; + + for (index = 0, stat = stats->scm_statistic, count = 0; + index < available_events; index++, ++stat) { + statid = kzalloc(strlen(stat->stat_id) + 1, GFP_KERNEL); + if (!statid) { + rc = -ENOMEM; + goto out_nvdimm_events_map; + } + + strcpy(statid, stat->stat_id); + p->nvdimm_events_map[count] = statid; + count++; + } + p->nvdimm_events_map[count] = NULL; + kfree(stats); + return 0; + +out_nvdimm_events_map: + kfree(p->nvdimm_events_map); +out_stats: + kfree(stats); + return rc; +} + +static void papr_scm_pmu_register(struct papr_scm_priv *p) +{ + struct nvdimm_pmu *nd_pmu; + int rc, nodeid; + + nd_pmu = kzalloc(sizeof(*nd_pmu), GFP_KERNEL); + if (!nd_pmu) { + rc = -ENOMEM; + goto pmu_err_print; + } + + rc = papr_scm_pmu_check_events(p, nd_pmu); + if (rc) + goto pmu_check_events_err; + + nd_pmu->pmu.task_ctx_nr = perf_invalid_context; + nd_pmu->pmu.name = nvdimm_name(p->nvdimm); + nd_pmu->pmu.event_init = papr_scm_pmu_event_init; + nd_pmu->pmu.read = papr_scm_pmu_read; + nd_pmu->pmu.add = papr_scm_pmu_add; + nd_pmu->pmu.del = papr_scm_pmu_del; + + nd_pmu->pmu.capabilities = PERF_PMU_CAP_NO_INTERRUPT | + PERF_PMU_CAP_NO_EXCLUDE; + + /*updating the cpumask variable */ + nodeid = numa_map_to_online_node(dev_to_node(&p->pdev->dev)); + nd_pmu->arch_cpumask = *cpumask_of_node(nodeid); + + rc = register_nvdimm_pmu(nd_pmu, p->pdev); + if (rc) + goto pmu_register_err; + + /* + * Set archdata.priv value to nvdimm_pmu structure, to handle the + * unregistering of pmu device. + */ + p->pdev->archdata.priv = nd_pmu; + return; + +pmu_register_err: + kfree(p->nvdimm_events_map); +pmu_check_events_err: + kfree(nd_pmu); +pmu_err_print: + dev_info(&p->pdev->dev, "nvdimm pmu didn't register rc=%d\n", rc); +} + +#else +static void papr_scm_pmu_register(struct papr_scm_priv *p) { } +#endif + /* * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the * health information. @@ -1320,6 +1542,7 @@ static int papr_scm_probe(struct platform_device *pdev) goto err2; platform_set_drvdata(pdev, p); + papr_scm_pmu_register(p); return 0; @@ -1338,6 +1561,12 @@ static int papr_scm_remove(struct platform_device *pdev) nvdimm_bus_unregister(p->bus); drc_pmem_unbind(p); + + if (pdev->archdata.priv) + unregister_nvdimm_pmu(pdev->archdata.priv); + + pdev->archdata.priv = NULL; + kfree(p->nvdimm_events_map); kfree(p->bus_desc.provider_name); kfree(p); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 674f047b7820..a97ce602394e 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -55,7 +55,7 @@ static void quirk_fsl_pcie_early(struct pci_dev *dev) if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE) return; - dev->class = PCI_CLASS_BRIDGE_PCI << 8; + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; fsl_pcie_bus_fixup = 1; return; } diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 3eef52b1a59b..aad45d7f498f 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -164,7 +164,7 @@ reg = <0x0 0x10010000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <4>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; status = "disabled"; }; dma: dma@3000000 { @@ -180,7 +180,7 @@ reg = <0x0 0x10011000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <5>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; status = "disabled"; }; i2c0: i2c@10030000 { @@ -188,7 +188,7 @@ reg = <0x0 0x10030000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <50>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; reg-shift = <2>; reg-io-width = <1>; #address-cells = <1>; @@ -201,7 +201,7 @@ <0x0 0x20000000 0x0 0x10000000>; interrupt-parent = <&plic0>; interrupts = <51>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -212,7 +212,7 @@ <0x0 0x30000000 0x0 0x10000000>; interrupt-parent = <&plic0>; interrupts = <52>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -222,7 +222,7 @@ reg = <0x0 0x10050000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <6>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -235,8 +235,8 @@ <0x0 0x100a0000 0x0 0x1000>; local-mac-address = [00 00 00 00 00 00]; clock-names = "pclk", "hclk"; - clocks = <&prci PRCI_CLK_GEMGXLPLL>, - <&prci PRCI_CLK_GEMGXLPLL>; + clocks = <&prci FU540_PRCI_CLK_GEMGXLPLL>, + <&prci FU540_PRCI_CLK_GEMGXLPLL>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -246,7 +246,7 @@ reg = <0x0 0x10020000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <42>, <43>, <44>, <45>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; #pwm-cells = <3>; status = "disabled"; }; @@ -255,7 +255,7 @@ reg = <0x0 0x10021000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <46>, <47>, <48>, <49>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; #pwm-cells = <3>; status = "disabled"; }; @@ -281,7 +281,7 @@ #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; - clocks = <&prci PRCI_CLK_TLCLK>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; status = "disabled"; }; }; diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi index 8464b0e3c887..7b77c13496d8 100644 --- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -166,7 +166,7 @@ reg = <0x0 0x10010000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <39>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; status = "disabled"; }; uart1: serial@10011000 { @@ -174,7 +174,7 @@ reg = <0x0 0x10011000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <40>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; status = "disabled"; }; i2c0: i2c@10030000 { @@ -182,7 +182,7 @@ reg = <0x0 0x10030000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <52>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; reg-shift = <2>; reg-io-width = <1>; #address-cells = <1>; @@ -194,7 +194,7 @@ reg = <0x0 0x10031000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <53>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; reg-shift = <2>; reg-io-width = <1>; #address-cells = <1>; @@ -207,7 +207,7 @@ <0x0 0x20000000 0x0 0x10000000>; interrupt-parent = <&plic0>; interrupts = <41>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -218,7 +218,7 @@ <0x0 0x30000000 0x0 0x10000000>; interrupt-parent = <&plic0>; interrupts = <42>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -228,7 +228,7 @@ reg = <0x0 0x10050000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <43>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -241,8 +241,8 @@ <0x0 0x100a0000 0x0 0x1000>; local-mac-address = [00 00 00 00 00 00]; clock-names = "pclk", "hclk"; - clocks = <&prci PRCI_CLK_GEMGXLPLL>, - <&prci PRCI_CLK_GEMGXLPLL>; + clocks = <&prci FU740_PRCI_CLK_GEMGXLPLL>, + <&prci FU740_PRCI_CLK_GEMGXLPLL>; #address-cells = <1>; #size-cells = <0>; status = "disabled"; @@ -252,7 +252,7 @@ reg = <0x0 0x10020000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <44>, <45>, <46>, <47>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; #pwm-cells = <3>; status = "disabled"; }; @@ -261,7 +261,7 @@ reg = <0x0 0x10021000 0x0 0x1000>; interrupt-parent = <&plic0>; interrupts = <48>, <49>, <50>, <51>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; #pwm-cells = <3>; status = "disabled"; }; @@ -287,7 +287,7 @@ #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; - clocks = <&prci PRCI_CLK_PCLK>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; status = "disabled"; }; pcie@e00000000 { @@ -316,7 +316,7 @@ <0x0 0x0 0x0 0x3 &plic0 59>, <0x0 0x0 0x0 0x4 &plic0 60>; clock-names = "pcie_aux"; - clocks = <&prci PRCI_CLK_PCIE_AUX>; + clocks = <&prci FU740_PRCI_CLK_PCIE_AUX>; pwren-gpios = <&gpio 5 0>; reset-gpios = <&gpio 8 0>; resets = <&prci 4>; diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 57b86fd9916c..5edf5b8587e7 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -2,5 +2,6 @@ generic-y += early_ioremap.h generic-y += flat.h generic-y += kvm_para.h +generic-y += parport.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index a89243730153..793c7da0554b 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -17,7 +17,6 @@ #include <linux/regset.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> -#include <linux/tracehook.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -241,7 +240,7 @@ long arch_ptrace(struct task_struct *child, long request, __visible int do_syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) - if (tracehook_report_syscall_entry(regs)) + if (ptrace_report_syscall_entry(regs)) return -1; /* @@ -266,7 +265,7 @@ __visible void do_syscall_trace_exit(struct pt_regs *regs) audit_syscall_exit(regs); if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 16da3c3b53a1..9f4e59f80551 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -9,7 +9,7 @@ #include <linux/signal.h> #include <linux/uaccess.h> #include <linux/syscalls.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/linkage.h> #include <asm/ucontext.h> @@ -319,5 +319,5 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs, do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9b80e8bed3f6..77b5a03de13a 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -58,6 +58,7 @@ config S390 select ALTERNATE_USER_ADDRESS_SPACE select ARCH_32BIT_USTAT_F_TINODE select ARCH_BINFMT_ELF_STATE + select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 diff --git a/arch/s390/include/asm/alternative-asm.h b/arch/s390/include/asm/alternative-asm.h index 955d620db23e..bb3837d7387c 100644 --- a/arch/s390/include/asm/alternative-asm.h +++ b/arch/s390/include/asm/alternative-asm.h @@ -37,9 +37,15 @@ * a 2-byte nop if the size of the area is not divisible by 6. */ .macro alt_pad_fill bytes - .fill ( \bytes ) / 6, 6, 0xc0040000 - .fill ( \bytes ) % 6 / 4, 4, 0x47000000 - .fill ( \bytes ) % 6 % 4 / 2, 2, 0x0700 + .rept ( \bytes ) / 6 + brcl 0,0 + .endr + .rept ( \bytes ) % 6 / 4 + nop + .endr + .rept ( \bytes ) % 6 % 4 / 2 + nopr + .endr .endm /* diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h index d3880ca764ee..3f2856ed6808 100644 --- a/arch/s390/include/asm/alternative.h +++ b/arch/s390/include/asm/alternative.h @@ -71,11 +71,18 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end); ".if " oldinstr_pad_len(num) " > 6\n" \ "\tjg " e_oldinstr_pad_end "f\n" \ "6620:\n" \ - "\t.fill (" oldinstr_pad_len(num) " - (6620b-662b)) / 2, 2, 0x0700\n" \ + "\t.rept (" oldinstr_pad_len(num) " - (6620b-662b)) / 2\n" \ + "\tnopr\n" \ ".else\n" \ - "\t.fill " oldinstr_pad_len(num) " / 6, 6, 0xc0040000\n" \ - "\t.fill " oldinstr_pad_len(num) " %% 6 / 4, 4, 0x47000000\n" \ - "\t.fill " oldinstr_pad_len(num) " %% 6 %% 4 / 2, 2, 0x0700\n" \ + "\t.rept " oldinstr_pad_len(num) " / 6\n" \ + "\t.brcl 0,0\n" \ + "\t.endr\n" \ + "\t.rept " oldinstr_pad_len(num) " %% 6 / 4\n" \ + "\tnop\n" \ + "\t.endr\n" \ + "\t.rept " oldinstr_pad_len(num) " %% 6 %% 4 / 2\n" \ + "\tnopr\n" \ + ".endr\n" \ ".endif\n" #define OLDINSTR(oldinstr, num) \ diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index ae75da592ccb..b515cfa62bd9 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -60,11 +60,11 @@ static inline bool ap_instructions_available(void) unsigned long reg1 = 0; asm volatile( - " lgr 0,%[reg0]\n" /* qid into gr0 */ - " lghi 1,0\n" /* 0 into gr1 */ - " lghi 2,0\n" /* 0 into gr2 */ - " .long 0xb2af0000\n" /* PQAP(TAPQ) */ - "0: la %[reg1],1\n" /* 1 into reg1 */ + " lgr 0,%[reg0]\n" /* qid into gr0 */ + " lghi 1,0\n" /* 0 into gr1 */ + " lghi 2,0\n" /* 0 into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(TAPQ) */ + "0: la %[reg1],1\n" /* 1 into reg1 */ "1:\n" EX_TABLE(0b, 1b) : [reg1] "+&d" (reg1) @@ -86,11 +86,11 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) unsigned long reg2; asm volatile( - " lgr 0,%[qid]\n" /* qid into gr0 */ - " lghi 2,0\n" /* 0 into gr2 */ - " .long 0xb2af0000\n" /* PQAP(TAPQ) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - " lgr %[reg2],2\n" /* gr2 into reg2 */ + " lgr 0,%[qid]\n" /* qid into gr0 */ + " lghi 2,0\n" /* 0 into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(TAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr %[reg2],2\n" /* gr2 into reg2 */ : [reg1] "=&d" (reg1), [reg2] "=&d" (reg2) : [qid] "d" (qid) : "cc", "0", "1", "2"); @@ -128,9 +128,9 @@ static inline struct ap_queue_status ap_rapq(ap_qid_t qid) struct ap_queue_status reg1; asm volatile( - " lgr 0,%[reg0]\n" /* qid arg into gr0 */ - " .long 0xb2af0000\n" /* PQAP(RAPQ) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr 0,%[reg0]\n" /* qid arg into gr0 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(RAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ : [reg1] "=&d" (reg1) : [reg0] "d" (reg0) : "cc", "0", "1"); @@ -149,9 +149,9 @@ static inline struct ap_queue_status ap_zapq(ap_qid_t qid) struct ap_queue_status reg1; asm volatile( - " lgr 0,%[reg0]\n" /* qid arg into gr0 */ - " .long 0xb2af0000\n" /* PQAP(ZAPQ) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr 0,%[reg0]\n" /* qid arg into gr0 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(ZAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ : [reg1] "=&d" (reg1) : [reg0] "d" (reg0) : "cc", "0", "1"); @@ -190,10 +190,10 @@ static inline int ap_qci(struct ap_config_info *config) struct ap_config_info *reg2 = config; asm volatile( - " lgr 0,%[reg0]\n" /* QCI fc into gr0 */ - " lgr 2,%[reg2]\n" /* ptr to config into gr2 */ - " .long 0xb2af0000\n" /* PQAP(QCI) */ - "0: la %[reg1],0\n" /* good case, QCI fc available */ + " lgr 0,%[reg0]\n" /* QCI fc into gr0 */ + " lgr 2,%[reg2]\n" /* ptr to config into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(QCI) */ + "0: la %[reg1],0\n" /* good case, QCI fc available */ "1:\n" EX_TABLE(0b, 1b) : [reg1] "+&d" (reg1) @@ -246,11 +246,11 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid, reg1.qirqctrl = qirqctrl; asm volatile( - " lgr 0,%[reg0]\n" /* qid param into gr0 */ - " lgr 1,%[reg1]\n" /* irq ctrl into gr1 */ - " lgr 2,%[reg2]\n" /* ni addr into gr2 */ - " .long 0xb2af0000\n" /* PQAP(AQIC) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr 0,%[reg0]\n" /* qid param into gr0 */ + " lgr 1,%[reg1]\n" /* irq ctrl into gr1 */ + " lgr 2,%[reg2]\n" /* ni addr into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(AQIC) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ : [reg1] "+&d" (reg1) : [reg0] "d" (reg0), [reg2] "d" (reg2) : "cc", "0", "1", "2"); @@ -297,11 +297,11 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit, reg1.value = apinfo->val; asm volatile( - " lgr 0,%[reg0]\n" /* qid param into gr0 */ - " lgr 1,%[reg1]\n" /* qact in info into gr1 */ - " .long 0xb2af0000\n" /* PQAP(QACT) */ - " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ - " lgr %[reg2],2\n" /* qact out info into reg2 */ + " lgr 0,%[reg0]\n" /* qid param into gr0 */ + " lgr 1,%[reg1]\n" /* qact in info into gr1 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(QACT) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + " lgr %[reg2],2\n" /* qact out info into reg2 */ : [reg1] "+&d" (reg1), [reg2] "=&d" (reg2) : [reg0] "d" (reg0) : "cc", "0", "1", "2"); diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index c800199a376b..82388da3f95f 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -74,8 +74,17 @@ static __always_inline void __ctl_clear_bit(unsigned int cr, unsigned int bit) __ctl_load(reg, cr, cr); } -void smp_ctl_set_bit(int cr, int bit); -void smp_ctl_clear_bit(int cr, int bit); +void smp_ctl_set_clear_bit(int cr, int bit, bool set); + +static inline void ctl_set_bit(int cr, int bit) +{ + smp_ctl_set_clear_bit(cr, bit, true); +} + +static inline void ctl_clear_bit(int cr, int bit) +{ + smp_ctl_set_clear_bit(cr, bit, false); +} union ctlreg0 { unsigned long val; @@ -130,8 +139,5 @@ union ctlreg15 { }; }; -#define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit) -#define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit) - #endif /* __ASSEMBLY__ */ #endif /* __ASM_CTL_REG_H */ diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index 17aead80aadb..eabab24b71dd 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -5,7 +5,6 @@ #include <linux/sched.h> #include <linux/audit.h> #include <linux/randomize_kstack.h> -#include <linux/tracehook.h> #include <linux/processor.h> #include <linux/uaccess.h> #include <asm/timex.h> diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 84ec63145325..eee8d96fb38e 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -319,11 +319,18 @@ extern void (*s390_base_pgm_handler_fn)(struct pt_regs *regs); extern int memcpy_real(void *, unsigned long, size_t); extern void memcpy_absolute(void *, void *, size_t); -#define mem_assign_absolute(dest, val) do { \ - __typeof__(dest) __tmp = (val); \ - \ - BUILD_BUG_ON(sizeof(__tmp) != sizeof(val)); \ - memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ +#define put_abs_lowcore(member, x) do { \ + unsigned long __abs_address = offsetof(struct lowcore, member); \ + __typeof__(((struct lowcore *)0)->member) __tmp = (x); \ + \ + memcpy_absolute(__va(__abs_address), &__tmp, sizeof(__tmp)); \ +} while (0) + +#define get_abs_lowcore(x, member) do { \ + unsigned long __abs_address = offsetof(struct lowcore, member); \ + __typeof__(((struct lowcore *)0)->member) *__ptr = &(x); \ + \ + memcpy_absolute(__ptr, __va(__abs_address), sizeof(*__ptr)); \ } while (0) extern int s390_isolate_bp(void); diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 888a2f1c9ee3..24a54443c865 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -78,7 +78,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lp) { typecheck(int, lp->lock); asm_inline volatile( - ALTERNATIVE("", ".long 0xb2fa0070", 49) /* NIAI 7 */ + ALTERNATIVE("", ".insn rre,0xb2fa0000,7,0", 49) /* NIAI 7 */ " sth %1,%0\n" : "=R" (((unsigned short *) &lp->lock)[1]) : "d" (0) : "cc", "memory"); diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h index ad2c996e7e93..fde7e6b1df48 100644 --- a/arch/s390/include/asm/syscall_wrapper.h +++ b/arch/s390/include/asm/syscall_wrapper.h @@ -162,4 +162,4 @@ __diag_pop(); \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#endif /* _ASM_X86_SYSCALL_WRAPPER_H */ +#endif /* _ASM_S390_SYSCALL_WRAPPER_H */ diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h index 5ebf534ef753..0bf06f1682d8 100644 --- a/arch/s390/include/asm/unwind.h +++ b/arch/s390/include/asm/unwind.h @@ -4,6 +4,8 @@ #include <linux/sched.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> +#include <linux/llist.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> @@ -36,10 +38,21 @@ struct unwind_state { struct pt_regs *regs; unsigned long sp, ip; int graph_idx; + struct llist_node *kr_cur; bool reliable; bool error; }; +/* Recover the return address modified by kretprobe and ftrace_graph. */ +static inline unsigned long unwind_recover_ret_addr(struct unwind_state *state, + unsigned long ip) +{ + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL); + if (is_kretprobe_trampoline(ip)) + ip = kretprobe_find_ret_addr(state->task, (void *)state->sp, &state->kr_cur); + return ip; +} + void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long first_frame); bool unwind_next_frame(struct unwind_state *state); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index a601a518b569..59b69c8ab5e1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -121,22 +121,22 @@ _LPP_OFFSET = __LC_LPP .endm .macro BPOFF - ALTERNATIVE "", ".long 0xb2e8c000", 82 + ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,12,0", 82 .endm .macro BPON - ALTERNATIVE "", ".long 0xb2e8d000", 82 + ALTERNATIVE "", ".insn rrf,0xb2e80000,0,0,13,0", 82 .endm .macro BPENTER tif_ptr,tif_mask - ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .long 0xb2e8d000", \ + ALTERNATIVE "TSTMSK \tif_ptr,\tif_mask; jz .+8; .insn rrf,0xb2e80000,0,0,13,0", \ "", 82 .endm .macro BPEXIT tif_ptr,tif_mask TSTMSK \tif_ptr,\tif_mask - ALTERNATIVE "jz .+8; .long 0xb2e8c000", \ - "jnz .+8; .long 0xb2e8d000", 82 + ALTERNATIVE "jz .+8; .insn rrf,0xb2e80000,0,0,12,0", \ + "jnz .+8; .insn rrf,0xb2e80000,0,0,13,0", 82 .endm /* diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 28ae7df26c4a..1cc85b8ff42e 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1646,8 +1646,8 @@ static void dump_reipl_run(struct shutdown_trigger *trigger) csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); - mem_assign_absolute(S390_lowcore.ipib, ipib); - mem_assign_absolute(S390_lowcore.ipib_checksum, csum); + put_abs_lowcore(ipib, ipib); + put_abs_lowcore(ipib_checksum, csum); dump_run(trigger); } diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index e32c14fd1282..0032bdbe8e3f 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -284,11 +284,11 @@ NOKPROBE_SYMBOL(pop_kprobe); void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { - ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14]; - ri->fp = NULL; + ri->ret_addr = (kprobe_opcode_t *)regs->gprs[14]; + ri->fp = (void *)regs->gprs[15]; /* Replace the return addr with trampoline addr */ - regs->gprs[14] = (unsigned long) &__kretprobe_trampoline; + regs->gprs[14] = (unsigned long)&__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -385,7 +385,7 @@ NOKPROBE_SYMBOL(arch_kretprobe_fixup_return); */ void trampoline_probe_handler(struct pt_regs *regs) { - kretprobe_trampoline_handler(regs, NULL); + kretprobe_trampoline_handler(regs, (void *)regs->gprs[15]); } NOKPROBE_SYMBOL(trampoline_probe_handler); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 088d57a3083f..b2ef014a9287 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -226,7 +226,7 @@ void arch_crash_save_vmcoreinfo(void) vmcoreinfo_append_str("SAMODE31=%lx\n", __samode31); vmcoreinfo_append_str("EAMODE31=%lx\n", __eamode31); vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); - mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); + put_abs_lowcore(vmcore_info, paddr_vmcoreinfo_note()); } void machine_shutdown(void) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index c0dd72db77b8..26125a9c436d 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -45,7 +45,7 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END, gfp_mask, PAGE_KERNEL_EXEC, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { + if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 6b5b64e67eee..1acc2e05d70f 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -63,7 +63,7 @@ void __init os_info_init(void) os_info.version_minor = OS_INFO_VERSION_MINOR; os_info.magic = OS_INFO_MAGIC; os_info.csum = os_info_csum(&os_info); - mem_assign_absolute(S390_lowcore.os_info, __pa(ptr)); + put_abs_lowcore(os_info, __pa(ptr)); } #ifdef CONFIG_CRASH_DUMP diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ed3439515bb2..53e0209229f8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -21,7 +21,6 @@ #include <linux/signal.h> #include <linux/elf.h> #include <linux/regset.h> -#include <linux/tracehook.h> #include <linux/seccomp.h> #include <linux/compat.h> #include <trace/syscall.h> diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 84e23fcc1106..d860ac300919 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -481,11 +481,11 @@ static void __init setup_lowcore_dat_off(void) lc->mcck_stack = mcck_stack + STACK_INIT_OFFSET; /* Setup absolute zero lowcore */ - mem_assign_absolute(S390_lowcore.restart_stack, lc->restart_stack); - mem_assign_absolute(S390_lowcore.restart_fn, lc->restart_fn); - mem_assign_absolute(S390_lowcore.restart_data, lc->restart_data); - mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source); - mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw); + put_abs_lowcore(restart_stack, lc->restart_stack); + put_abs_lowcore(restart_fn, lc->restart_fn); + put_abs_lowcore(restart_data, lc->restart_data); + put_abs_lowcore(restart_source, lc->restart_source); + put_abs_lowcore(restart_psw, lc->restart_psw); lc->spinlock_lockval = arch_spin_lockval(0); lc->spinlock_index = 0; @@ -501,6 +501,7 @@ static void __init setup_lowcore_dat_off(void) static void __init setup_lowcore_dat_on(void) { struct lowcore *lc = lowcore_ptr[0]; + int cr; __ctl_clear_bit(0, 28); S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT; @@ -509,10 +510,10 @@ static void __init setup_lowcore_dat_on(void) S390_lowcore.io_new_psw.mask |= PSW_MASK_DAT; __ctl_store(S390_lowcore.cregs_save_area, 0, 15); __ctl_set_bit(0, 28); - mem_assign_absolute(S390_lowcore.restart_flags, RESTART_FLAG_CTLREGS); - mem_assign_absolute(S390_lowcore.program_new_psw, lc->program_new_psw); - memcpy_absolute(&S390_lowcore.cregs_save_area, lc->cregs_save_area, - sizeof(S390_lowcore.cregs_save_area)); + put_abs_lowcore(restart_flags, RESTART_FLAG_CTLREGS); + put_abs_lowcore(program_new_psw, lc->program_new_psw); + for (cr = 0; cr < ARRAY_SIZE(lc->cregs_save_area); cr++) + put_abs_lowcore(cregs_save_area[cr], lc->cregs_save_area[cr]); } static struct resource code_resource = { diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 5ff8d915ec7a..38258f817048 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -25,7 +25,6 @@ #include <linux/tty.h> #include <linux/personality.h> #include <linux/binfmts.h> -#include <linux/tracehook.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <asm/ucontext.h> @@ -453,7 +452,7 @@ static void handle_signal(struct ksignal *ksig, sigset_t *oldset, * stack-frames in one go after that. */ -void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) +void arch_do_signal_or_restart(struct pt_regs *regs) { struct ksignal ksig; sigset_t *oldset = sigmask_to_save(); @@ -466,7 +465,7 @@ void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) current->thread.system_call = test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0; - if (has_signal && get_signal(&ksig)) { + if (get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ if (current->thread.system_call) { regs->int_code = current->thread.system_call; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 127da1850b06..30c91d565933 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -213,7 +213,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) if (nmi_alloc_mcesa(&lc->mcesad)) goto out; lowcore_ptr[cpu] = lc; - pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc); + pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, __pa(lc)); return 0; out: @@ -326,10 +326,17 @@ static void pcpu_delegate(struct pcpu *pcpu, /* Stop target cpu (if func returns this stops the current cpu). */ pcpu_sigp_retry(pcpu, SIGP_STOP, 0); /* Restart func on the target cpu and stop the current cpu. */ - mem_assign_absolute(lc->restart_stack, stack); - mem_assign_absolute(lc->restart_fn, (unsigned long) func); - mem_assign_absolute(lc->restart_data, (unsigned long) data); - mem_assign_absolute(lc->restart_source, source_cpu); + if (lc) { + lc->restart_stack = stack; + lc->restart_fn = (unsigned long)func; + lc->restart_data = (unsigned long)data; + lc->restart_source = source_cpu; + } else { + put_abs_lowcore(restart_stack, stack); + put_abs_lowcore(restart_fn, (unsigned long)func); + put_abs_lowcore(restart_data, (unsigned long)data); + put_abs_lowcore(restart_source, source_cpu); + } __bpon(); asm volatile( "0: sigp 0,%0,%2 # sigp restart to target cpu\n" @@ -570,39 +577,27 @@ static void smp_ctl_bit_callback(void *info) } static DEFINE_SPINLOCK(ctl_lock); -static unsigned long ctlreg; -/* - * Set a bit in a control register of all cpus - */ -void smp_ctl_set_bit(int cr, int bit) +void smp_ctl_set_clear_bit(int cr, int bit, bool set) { - struct ec_creg_mask_parms parms = { 1UL << bit, -1UL, cr }; - - spin_lock(&ctl_lock); - memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg)); - __set_bit(bit, &ctlreg); - memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg)); - spin_unlock(&ctl_lock); - on_each_cpu(smp_ctl_bit_callback, &parms, 1); -} -EXPORT_SYMBOL(smp_ctl_set_bit); - -/* - * Clear a bit in a control register of all cpus - */ -void smp_ctl_clear_bit(int cr, int bit) -{ - struct ec_creg_mask_parms parms = { 0, ~(1UL << bit), cr }; + struct ec_creg_mask_parms parms = { .cr = cr, }; + u64 ctlreg; + if (set) { + parms.orval = 1UL << bit; + parms.andval = -1UL; + } else { + parms.orval = 0; + parms.andval = ~(1UL << bit); + } spin_lock(&ctl_lock); - memcpy_absolute(&ctlreg, &S390_lowcore.cregs_save_area[cr], sizeof(ctlreg)); - __clear_bit(bit, &ctlreg); - memcpy_absolute(&S390_lowcore.cregs_save_area[cr], &ctlreg, sizeof(ctlreg)); + get_abs_lowcore(ctlreg, cregs_save_area[cr]); + ctlreg = (ctlreg & parms.andval) | parms.orval; + put_abs_lowcore(cregs_save_area[cr], ctlreg); spin_unlock(&ctl_lock); on_each_cpu(smp_ctl_bit_callback, &parms, 1); } -EXPORT_SYMBOL(smp_ctl_clear_bit); +EXPORT_SYMBOL(smp_ctl_set_clear_bit); #ifdef CONFIG_CRASH_DUMP diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile index b98f25029b8e..fb85e797946d 100644 --- a/arch/s390/kernel/syscalls/Makefile +++ b/arch/s390/kernel/syscalls/Makefile @@ -21,8 +21,7 @@ uapi: $(uapi-hdrs-y) # Create output directory if not already present -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) filechk_syshdr = $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" < $< diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 674c65019434..1d2aa448d103 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -141,10 +141,10 @@ static inline void do_fp_trap(struct pt_regs *regs, __u32 fpc) do_trap(regs, SIGFPE, si_code, "floating point exception"); } -static void translation_exception(struct pt_regs *regs) +static void translation_specification_exception(struct pt_regs *regs) { /* May never happen. */ - panic("Translation exception"); + panic("Translation-Specification Exception"); } static void illegal_op(struct pt_regs *regs) @@ -368,7 +368,7 @@ static void (*pgm_check_table[128])(struct pt_regs *regs) = { [0x0f] = hfp_divide_exception, [0x10] = do_dat_exception, [0x11] = do_dat_exception, - [0x12] = translation_exception, + [0x12] = translation_specification_exception, [0x13] = special_op_exception, [0x14] = default_trap_handler, [0x15] = operand_exception, diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index 707fd99f6734..0ece156fdd7c 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -64,8 +64,8 @@ bool unwind_next_frame(struct unwind_state *state) ip = READ_ONCE_NOCHECK(sf->gprs[8]); reliable = false; regs = NULL; - if (!__kernel_text_address(ip)) { - /* skip bogus %r14 */ + /* skip bogus %r14 or if is the same as regs->psw.addr */ + if (!__kernel_text_address(ip) || state->ip == unwind_recover_ret_addr(state, ip)) { state->regs = NULL; return unwind_next_frame(state); } @@ -103,13 +103,11 @@ bool unwind_next_frame(struct unwind_state *state) if (sp & 0x7) goto out_err; - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp); - /* Update unwind state */ state->sp = sp; - state->ip = ip; state->regs = regs; state->reliable = reliable; + state->ip = unwind_recover_ret_addr(state, ip); return true; out_err: @@ -161,12 +159,10 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, ip = READ_ONCE_NOCHECK(sf->gprs[8]); } - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL); - /* Update unwind state */ state->sp = sp; - state->ip = ip; state->reliable = true; + state->ip = unwind_recover_ret_addr(state, ip); if (!first_frame) return; diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 692dc84cd19c..5e7ea8b111e8 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -75,7 +75,7 @@ static inline int arch_load_niai4(int *lock) int owner; asm_inline volatile( - ALTERNATIVE("", ".long 0xb2fa0040", 49) /* NIAI 4 */ + ALTERNATIVE("", ".insn rre,0xb2fa0000,4,0", 49) /* NIAI 4 */ " l %0,%1\n" : "=d" (owner) : "Q" (*lock) : "memory"); return owner; @@ -86,7 +86,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new) int expected = old; asm_inline volatile( - ALTERNATIVE("", ".long 0xb2fa0080", 49) /* NIAI 8 */ + ALTERNATIVE("", ".insn rre,0xb2fa0000,8,0", 49) /* NIAI 8 */ " cs %0,%3,%1\n" : "=d" (old), "=Q" (*lock) : "0" (old), "d" (new), "Q" (*lock) diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index c01f02887de4..9bb067321ab4 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -47,7 +47,7 @@ static void print_backtrace(char *bt) static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, unsigned long sp) { - int frame_count, prev_is_func2, seen_func2_func1; + int frame_count, prev_is_func2, seen_func2_func1, seen_kretprobe_trampoline; const int max_frames = 128; struct unwind_state state; size_t bt_pos = 0; @@ -63,6 +63,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, frame_count = 0; prev_is_func2 = 0; seen_func2_func1 = 0; + seen_kretprobe_trampoline = 0; unwind_for_each_frame(&state, task, regs, sp) { unsigned long addr = unwind_get_return_address(&state); char sym[KSYM_SYMBOL_LEN]; @@ -88,6 +89,8 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, if (prev_is_func2 && str_has_prefix(sym, "unwindme_func1")) seen_func2_func1 = 1; prev_is_func2 = str_has_prefix(sym, "unwindme_func2"); + if (str_has_prefix(sym, "__kretprobe_trampoline+0x0/")) + seen_kretprobe_trampoline = 1; } /* Check the results. */ @@ -103,6 +106,10 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, kunit_err(current_test, "Maximum number of frames exceeded\n"); ret = -EINVAL; } + if (seen_kretprobe_trampoline) { + kunit_err(current_test, "__kretprobe_trampoline+0x0 in unwinding results\n"); + ret = -EINVAL; + } if (ret || force_bt) print_backtrace(bt); kfree(bt); @@ -132,36 +139,50 @@ static struct unwindme *unwindme; #define UWM_PGM 0x40 /* Unwind from program check handler */ #define UWM_KPROBE_ON_FTRACE 0x80 /* Unwind from kprobe handler called via ftrace. */ #define UWM_FTRACE 0x100 /* Unwind from ftrace handler. */ -#define UWM_KRETPROBE 0x200 /* Unwind kretprobe handlers. */ +#define UWM_KRETPROBE 0x200 /* Unwind through kretprobed function. */ +#define UWM_KRETPROBE_HANDLER 0x400 /* Unwind from kretprobe handler. */ -static __always_inline unsigned long get_psw_addr(void) +static __always_inline struct pt_regs fake_pt_regs(void) { - unsigned long psw_addr; + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + regs.gprs[15] = current_stack_pointer(); asm volatile( "basr %[psw_addr],0\n" - : [psw_addr] "=d" (psw_addr)); - return psw_addr; + : [psw_addr] "=d" (regs.psw.addr)); + return regs; } static int kretprobe_ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs) { struct unwindme *u = unwindme; + if (!(u->flags & UWM_KRETPROBE_HANDLER)) + return 0; + u->ret = test_unwind(NULL, (u->flags & UWM_REGS) ? regs : NULL, (u->flags & UWM_SP) ? u->sp : 0); return 0; } -static noinline notrace void test_unwind_kretprobed_func(void) +static noinline notrace int test_unwind_kretprobed_func(struct unwindme *u) { - asm volatile(" nop\n"); + struct pt_regs regs; + + if (!(u->flags & UWM_KRETPROBE)) + return 0; + + regs = fake_pt_regs(); + return test_unwind(NULL, (u->flags & UWM_REGS) ? ®s : NULL, + (u->flags & UWM_SP) ? u->sp : 0); } -static noinline void test_unwind_kretprobed_func_caller(void) +static noinline int test_unwind_kretprobed_func_caller(struct unwindme *u) { - test_unwind_kretprobed_func(); + return test_unwind_kretprobed_func(u); } static int test_unwind_kretprobe(struct unwindme *u) @@ -187,10 +208,12 @@ static int test_unwind_kretprobe(struct unwindme *u) return -EINVAL; } - test_unwind_kretprobed_func_caller(); + ret = test_unwind_kretprobed_func_caller(u); unregister_kretprobe(&my_kretprobe); unwindme = NULL; - return u->ret; + if (u->flags & UWM_KRETPROBE_HANDLER) + ret = u->ret; + return ret; } static int kprobe_pre_handler(struct kprobe *p, struct pt_regs *regs) @@ -304,16 +327,13 @@ static noinline int unwindme_func4(struct unwindme *u) return 0; } else if (u->flags & (UWM_PGM | UWM_KPROBE_ON_FTRACE)) { return test_unwind_kprobe(u); - } else if (u->flags & (UWM_KRETPROBE)) { + } else if (u->flags & (UWM_KRETPROBE | UWM_KRETPROBE_HANDLER)) { return test_unwind_kretprobe(u); } else if (u->flags & UWM_FTRACE) { return test_unwind_ftrace(u); } else { - struct pt_regs regs; + struct pt_regs regs = fake_pt_regs(); - memset(®s, 0, sizeof(regs)); - regs.psw.addr = get_psw_addr(); - regs.gprs[15] = current_stack_pointer(); return test_unwind(NULL, (u->flags & UWM_REGS) ? ®s : NULL, (u->flags & UWM_SP) ? u->sp : 0); @@ -452,6 +472,10 @@ static const struct test_params param_list[] = { TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_SP), TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_REGS), TEST_WITH_FLAGS(UWM_KRETPROBE | UWM_SP | UWM_REGS), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_SP), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_REGS), + TEST_WITH_FLAGS(UWM_KRETPROBE_HANDLER | UWM_SP | UWM_REGS), }; /* diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 792f8e0f2178..e563cb65c0c4 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -69,6 +69,7 @@ struct zpci_dev *get_zdev_by_fid(u32 fid) list_for_each_entry(tmp, &zpci_list, entry) { if (tmp->fid == fid) { zdev = tmp; + zpci_zdev_get(zdev); break; } } @@ -399,7 +400,7 @@ EXPORT_SYMBOL(pci_iounmap); static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct zpci_dev *zdev = get_zdev_by_bus(bus, devfn); + struct zpci_dev *zdev = zdev_from_bus(bus, devfn); return (zdev) ? zpci_cfg_load(zdev, where, val, size) : -ENODEV; } @@ -407,7 +408,7 @@ static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - struct zpci_dev *zdev = get_zdev_by_bus(bus, devfn); + struct zpci_dev *zdev = zdev_from_bus(bus, devfn); return (zdev) ? zpci_cfg_store(zdev, where, val, size) : -ENODEV; } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e359d2686178..e96c9860e064 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -19,7 +19,8 @@ void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error); void zpci_release_device(struct kref *kref); static inline void zpci_zdev_put(struct zpci_dev *zdev) { - kref_put(&zdev->kref, zpci_release_device); + if (zdev) + kref_put(&zdev->kref, zpci_release_device); } static inline void zpci_zdev_get(struct zpci_dev *zdev) @@ -32,8 +33,8 @@ void zpci_free_domain(int domain); int zpci_setup_bus_resources(struct zpci_dev *zdev, struct list_head *resources); -static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, - unsigned int devfn) +static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, + unsigned int devfn) { struct zpci_bus *zbus = bus->sysdata; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 63f3e057c168..1057d7af4a55 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -23,6 +23,8 @@ #include <asm/clp.h> #include <uapi/asm/clp.h> +#include "pci_bus.h" + bool zpci_unique_uid; void update_uid_checking(bool new) @@ -404,8 +406,11 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data) return; zdev = get_zdev_by_fid(entry->fid); - if (!zdev) - zpci_create_device(entry->fid, entry->fh, entry->config_state); + if (zdev) { + zpci_zdev_put(zdev); + return; + } + zpci_create_device(entry->fid, entry->fh, entry->config_state); } int clp_scan_pci_devices(void) diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 2e3e5b278925..ea9db5cea64e 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -269,7 +269,7 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); if (!pdev) - return; + goto no_pdev; switch (ccdf->pec) { case 0x003a: /* Service Action or Error Recovery Successful */ @@ -286,6 +286,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) break; } pci_dev_put(pdev); +no_pdev: + zpci_zdev_put(zdev); } void zpci_event_error(void *data) @@ -314,6 +316,7 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); + bool existing_zdev = !!zdev; enum zpci_state state; zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n", @@ -378,6 +381,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) default: break; } + if (existing_zdev) + zpci_zdev_put(zdev); } void zpci_event_availability(void *data) diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c index 4d499476c33a..b0c2a5238d04 100644 --- a/arch/sh/drivers/pci/pcie-sh7786.c +++ b/arch/sh/drivers/pci/pcie-sh7786.c @@ -314,7 +314,7 @@ static int __init pcie_init(struct sh7786_pcie_port *port) * class to match. Hardware takes care of propagating the IDSETR * settings, so there is no need to bother with a quirk. */ - pci_write_reg(chan, PCI_CLASS_BRIDGE_PCI << 16, SH4A_PCIEIDSETR1); + pci_write_reg(chan, PCI_CLASS_BRIDGE_PCI_NORMAL << 8, SH4A_PCIEIDSETR1); /* Initialize default capabilities. */ data = pci_read_reg(chan, SH4A_PCIEEXPCAP0); diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 5281685f6ad1..d417988d9770 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -20,7 +20,6 @@ #include <linux/io.h> #include <linux/audit.h> #include <linux/seccomp.h> -#include <linux/tracehook.h> #include <linux/elf.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> @@ -456,7 +455,7 @@ long arch_ptrace(struct task_struct *child, long request, asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) { + ptrace_report_syscall_entry(regs)) { regs->regs[0] = -ENOSYS; return -1; } @@ -484,5 +483,5 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index dd3092911efa..90f495d35db2 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -25,7 +25,7 @@ #include <linux/personality.h> #include <linux/binfmts.h> #include <linux/io.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/ucontext.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -503,5 +503,5 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0, do_signal(regs, save_r0); if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/sh/kernel/syscalls/Makefile b/arch/sh/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/sh/kernel/syscalls/Makefile +++ b/arch/sh/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 57a72c46eddb..4e4f3d3263e4 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -309,7 +309,7 @@ arch_initcall(sparc_register_ioport); void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - if (dir != PCI_DMA_TODEVICE && + if (dir != DMA_TO_DEVICE && sparc_cpu_model == sparc_leon && !sparc_leon3_snooping_enabled()) leon_flush_dcache_all(); diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c index 5318174a0268..e7db48acb838 100644 --- a/arch/sparc/kernel/ptrace_32.c +++ b/arch/sparc/kernel/ptrace_32.c @@ -21,7 +21,6 @@ #include <linux/signal.h> #include <linux/regset.h> #include <linux/elf.h> -#include <linux/tracehook.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -439,9 +438,9 @@ asmlinkage int syscall_trace(struct pt_regs *regs, int syscall_exit_p) if (test_thread_flag(TIF_SYSCALL_TRACE)) { if (syscall_exit_p) - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); else - ret = tracehook_report_syscall_entry(regs); + ret = ptrace_report_syscall_entry(regs); } return ret; diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index 2b92155db8a5..86a7eb5c27ba 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -25,7 +25,6 @@ #include <linux/audit.h> #include <linux/signal.h> #include <linux/regset.h> -#include <linux/tracehook.h> #include <trace/syscall.h> #include <linux/compat.h> #include <linux/elf.h> @@ -1095,7 +1094,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs) user_exit(); if (test_thread_flag(TIF_SYSCALL_TRACE)) - ret = tracehook_report_syscall_entry(regs); + ret = ptrace_report_syscall_entry(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->u_regs[UREG_G1]); @@ -1118,7 +1117,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) trace_sys_exit(regs, regs->u_regs[UREG_I0]); if (test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); if (test_thread_flag(TIF_NOHZ)) user_enter(); diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 6cc124a3bb98..f9fe502b81c6 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -20,7 +20,6 @@ #include <linux/binfmts.h> #include <linux/compat.h> #include <linux/bitops.h> -#include <linux/tracehook.h> #include <linux/uaccess.h> #include <asm/ptrace.h> diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 74f80443b195..89b93c7136e7 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -19,7 +19,7 @@ #include <linux/smp.h> #include <linux/binfmts.h> /* do_coredum */ #include <linux/bitops.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/uaccess.h> #include <asm/ptrace.h> @@ -524,7 +524,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, orig_i0); if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr, diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 2a78d2af1265..8b9fc76cd3e0 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -15,7 +15,7 @@ #include <linux/errno.h> #include <linux/wait.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/unistd.h> #include <linux/mm.h> #include <linux/tty.h> @@ -552,7 +552,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs, orig_i0); if (thread_info_flags & _TIF_NOTIFY_RESUME) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); user_enter(); } diff --git a/arch/sparc/kernel/syscalls/Makefile b/arch/sparc/kernel/syscalls/Makefile index d63f18dd058d..8440c16dfb22 100644 --- a/arch/sparc/kernel/syscalls/Makefile +++ b/arch/sparc/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh diff --git a/arch/um/Makefile b/arch/um/Makefile index f2fe63bfd819..320b09cd513c 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -75,6 +75,10 @@ USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -I%,,$(KBUILD_CFLAGS))) \ -D_FILE_OFFSET_BITS=64 -idirafter $(srctree)/include \ -idirafter $(objtree)/include -D__KERNEL__ -D__UM_HOST__ +ifdef CONFIG_CC_IS_CLANG +USER_CFLAGS := $(patsubst -mno-global-merge,,$(USER_CFLAGS)) +endif + #This will adjust *FLAGS accordingly to the platform. include $(srctree)/$(ARCH_DIR)/Makefile-os-$(OS) diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 6ead1e240457..8ca67a692683 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -224,7 +224,7 @@ void mconsole_go(struct mc_request *req) void mconsole_stop(struct mc_request *req) { - deactivate_fd(req->originating_fd, MCONSOLE_IRQ); + block_signals(); os_set_fd_block(req->originating_fd, 1); mconsole_reply(req, "stopped", 0, 0); for (;;) { @@ -247,6 +247,7 @@ void mconsole_stop(struct mc_request *req) } os_set_fd_block(req->originating_fd, 0); mconsole_reply(req, "", 0, 0); + unblock_signals(); } static DEFINE_SPINLOCK(mc_devices_lock); diff --git a/arch/um/drivers/port_user.c b/arch/um/drivers/port_user.c index 5b5b64cb1071..3c62ae81df62 100644 --- a/arch/um/drivers/port_user.c +++ b/arch/um/drivers/port_user.c @@ -5,6 +5,7 @@ #include <stdio.h> #include <stdlib.h> +#include <string.h> #include <errno.h> #include <termios.h> #include <unistd.h> @@ -167,14 +168,29 @@ static void port_pre_exec(void *arg) int port_connection(int fd, int *socket, int *pid_out) { int new, err; - char *argv[] = { "/usr/sbin/in.telnetd", "-L", + char *env; + char *argv[] = { "in.telnetd", "-L", OS_LIB_PATH "/uml/port-helper", NULL }; struct port_pre_exec_data data; + if ((env = getenv("UML_PORT_HELPER"))) + argv[2] = env; + new = accept(fd, NULL, 0); if (new < 0) return -errno; + err = os_access(argv[2], X_OK); + if (err < 0) { + printk(UM_KERN_ERR "port_connection : error accessing port-helper " + "executable at %s: %s\n", argv[2], strerror(-err)); + if (env == NULL) + printk(UM_KERN_ERR "Set UML_PORT_HELPER environment " + "variable to path to uml-utilities port-helper " + "binary\n"); + goto out_close; + } + err = os_pipe(socket, 0, 0); if (err < 0) goto out_close; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 69d2d0049a61..b03269faef71 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1526,13 +1526,19 @@ static void do_io(struct io_thread_req *req, struct io_desc *desc) } break; case REQ_OP_DISCARD: - case REQ_OP_WRITE_ZEROES: n = os_falloc_punch(req->fds[bit], off, len); if (n) { req->error = map_error(-n); return; } break; + case REQ_OP_WRITE_ZEROES: + n = os_falloc_zeroes(req->fds[bit], off, len); + if (n) { + req->error = map_error(-n); + return; + } + break; default: WARN_ON_ONCE(1); req->error = BLK_STS_NOTSUPP; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 4fc1a5d70dcf..1d6f6a66766c 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -67,6 +67,7 @@ static LIST_HEAD(vector_devices); static int driver_registered; static void vector_eth_configure(int n, struct arglist *def); +static int vector_mmsg_rx(struct vector_private *vp, int budget); /* Argument accessors to set variables (and/or set default values) * mtu, buffer sizing, default headroom, etc @@ -77,7 +78,6 @@ static void vector_eth_configure(int n, struct arglist *def); #define DEFAULT_VECTOR_SIZE 64 #define TX_SMALL_PACKET 128 #define MAX_IOV_SIZE (MAX_SKB_FRAGS + 1) -#define MAX_ITERATIONS 64 static const struct { const char string[ETH_GSTRING_LEN]; @@ -458,7 +458,6 @@ static int vector_send(struct vector_queue *qi) vp->estats.tx_queue_running_average = (vp->estats.tx_queue_running_average + result) >> 1; } - netif_trans_update(qi->dev); netif_wake_queue(qi->dev); /* if TX is busy, break out of the send loop, * poll write IRQ will reschedule xmit for us @@ -470,8 +469,6 @@ static int vector_send(struct vector_queue *qi) } } spin_unlock(&qi->head_lock); - } else { - tasklet_schedule(&vp->tx_poll); } return queue_depth; } @@ -608,7 +605,7 @@ out_fail: /* * We do not use the RX queue as a proper wraparound queue for now - * This is not necessary because the consumption via netif_rx() + * This is not necessary because the consumption via napi_gro_receive() * happens in-line. While we can try using the return code of * netif_rx() for flow control there are no drivers doing this today. * For this RX specific use we ignore the tail/head locks and @@ -896,7 +893,7 @@ static int vector_legacy_rx(struct vector_private *vp) skb->protocol = eth_type_trans(skb, skb->dev); vp->dev->stats.rx_bytes += skb->len; vp->dev->stats.rx_packets++; - netif_rx(skb); + napi_gro_receive(&vp->napi, skb); } else { dev_kfree_skb_irq(skb); } @@ -955,7 +952,7 @@ drop: * mmsg vector matched to an skb vector which we prepared earlier. */ -static int vector_mmsg_rx(struct vector_private *vp) +static int vector_mmsg_rx(struct vector_private *vp, int budget) { int packet_count, i; struct vector_queue *qi = vp->rx_queue; @@ -972,6 +969,9 @@ static int vector_mmsg_rx(struct vector_private *vp) /* Fire the Lazy Gun - get as many packets as we can in one go. */ + if (budget > qi->max_depth) + budget = qi->max_depth; + packet_count = uml_vector_recvmmsg( vp->fds->rx_fd, qi->mmsg_vector, qi->max_depth, 0); @@ -1021,7 +1021,7 @@ static int vector_mmsg_rx(struct vector_private *vp) */ vp->dev->stats.rx_bytes += skb->len; vp->dev->stats.rx_packets++; - netif_rx(skb); + napi_gro_receive(&vp->napi, skb); } else { /* Overlay header too short to do anything - discard. * We can actually keep this skb and reuse it, @@ -1044,23 +1044,6 @@ static int vector_mmsg_rx(struct vector_private *vp) return packet_count; } -static void vector_rx(struct vector_private *vp) -{ - int err; - int iter = 0; - - if ((vp->options & VECTOR_RX) > 0) - while (((err = vector_mmsg_rx(vp)) > 0) && (iter < MAX_ITERATIONS)) - iter++; - else - while (((err = vector_legacy_rx(vp)) > 0) && (iter < MAX_ITERATIONS)) - iter++; - if ((err != 0) && net_ratelimit()) - netdev_err(vp->dev, "vector_rx: error(%d)\n", err); - if (iter == MAX_ITERATIONS) - netdev_err(vp->dev, "vector_rx: device stuck, remote end may have closed the connection\n"); -} - static int vector_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct vector_private *vp = netdev_priv(dev); @@ -1085,25 +1068,15 @@ static int vector_net_start_xmit(struct sk_buff *skb, struct net_device *dev) netdev_sent_queue(vp->dev, skb->len); queue_depth = vector_enqueue(vp->tx_queue, skb); - /* if the device queue is full, stop the upper layers and - * flush it. - */ - - if (queue_depth >= vp->tx_queue->max_depth - 1) { - vp->estats.tx_kicks++; - netif_stop_queue(dev); - vector_send(vp->tx_queue); - return NETDEV_TX_OK; - } - if (netdev_xmit_more()) { + if (queue_depth < vp->tx_queue->max_depth && netdev_xmit_more()) { mod_timer(&vp->tl, vp->coalesce); return NETDEV_TX_OK; + } else { + queue_depth = vector_send(vp->tx_queue); + if (queue_depth > 0) + napi_schedule(&vp->napi); } - if (skb->len < TX_SMALL_PACKET) { - vp->estats.tx_kicks++; - vector_send(vp->tx_queue); - } else - tasklet_schedule(&vp->tx_poll); + return NETDEV_TX_OK; } @@ -1114,7 +1087,7 @@ static irqreturn_t vector_rx_interrupt(int irq, void *dev_id) if (!netif_running(dev)) return IRQ_NONE; - vector_rx(vp); + napi_schedule(&vp->napi); return IRQ_HANDLED; } @@ -1133,8 +1106,7 @@ static irqreturn_t vector_tx_interrupt(int irq, void *dev_id) * tweaking the IRQ mask less costly */ - if (vp->in_write_poll) - tasklet_schedule(&vp->tx_poll); + napi_schedule(&vp->napi); return IRQ_HANDLED; } @@ -1161,7 +1133,8 @@ static int vector_net_close(struct net_device *dev) um_free_irq(vp->tx_irq, dev); vp->tx_irq = 0; } - tasklet_kill(&vp->tx_poll); + napi_disable(&vp->napi); + netif_napi_del(&vp->napi); if (vp->fds->rx_fd > 0) { if (vp->bpf) uml_vector_detach_bpf(vp->fds->rx_fd, vp->bpf); @@ -1193,15 +1166,32 @@ static int vector_net_close(struct net_device *dev) return 0; } -/* TX tasklet */ - -static void vector_tx_poll(struct tasklet_struct *t) +static int vector_poll(struct napi_struct *napi, int budget) { - struct vector_private *vp = from_tasklet(vp, t, tx_poll); + struct vector_private *vp = container_of(napi, struct vector_private, napi); + int work_done = 0; + int err; + bool tx_enqueued = false; - vp->estats.tx_kicks++; - vector_send(vp->tx_queue); + if ((vp->options & VECTOR_TX) != 0) + tx_enqueued = (vector_send(vp->tx_queue) > 0); + if ((vp->options & VECTOR_RX) > 0) + err = vector_mmsg_rx(vp, budget); + else { + err = vector_legacy_rx(vp); + if (err > 0) + err = 1; + } + if (err > 0) + work_done += err; + + if (tx_enqueued || err > 0) + napi_schedule(napi); + if (work_done < budget) + napi_complete_done(napi, work_done); + return work_done; } + static void vector_reset_tx(struct work_struct *work) { struct vector_private *vp = @@ -1265,6 +1255,9 @@ static int vector_net_open(struct net_device *dev) goto out_close; } + netif_napi_add(vp->dev, &vp->napi, vector_poll, get_depth(vp->parsed)); + napi_enable(&vp->napi); + /* READ IRQ */ err = um_request_irq( irq_rr + VECTOR_BASE_IRQ, vp->fds->rx_fd, @@ -1306,15 +1299,15 @@ static int vector_net_open(struct net_device *dev) uml_vector_attach_bpf(vp->fds->rx_fd, vp->bpf); netif_start_queue(dev); + vector_reset_stats(vp); /* clear buffer - it can happen that the host side of the interface * is full when we get here. In this case, new data is never queued, * SIGIOs never arrive, and the net never works. */ - vector_rx(vp); + napi_schedule(&vp->napi); - vector_reset_stats(vp); vdevice = find_device(vp->unit); vdevice->opened = 1; @@ -1543,15 +1536,16 @@ static const struct net_device_ops vector_netdev_ops = { #endif }; - static void vector_timer_expire(struct timer_list *t) { struct vector_private *vp = from_timer(vp, t, tl); vp->estats.tx_kicks++; - vector_send(vp->tx_queue); + napi_schedule(&vp->napi); } + + static void vector_eth_configure( int n, struct arglist *def @@ -1634,7 +1628,6 @@ static void vector_eth_configure( }); dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST); - tasklet_setup(&vp->tx_poll, vector_tx_poll); INIT_WORK(&vp->reset_tx, vector_reset_tx); timer_setup(&vp->tl, vector_timer_expire, 0); diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h index 8fff93a75a92..2a1fa8e0f3e1 100644 --- a/arch/um/drivers/vector_kern.h +++ b/arch/um/drivers/vector_kern.h @@ -14,6 +14,7 @@ #include <linux/ctype.h> #include <linux/workqueue.h> #include <linux/interrupt.h> + #include "vector_user.h" /* Queue structure specially adapted for multiple enqueue/dequeue @@ -72,6 +73,7 @@ struct vector_private { struct list_head list; spinlock_t lock; struct net_device *dev; + struct napi_struct napi ____cacheline_aligned; int unit; @@ -115,7 +117,6 @@ struct vector_private { spinlock_t stats_lock; - struct tasklet_struct tx_poll; bool rexmit_scheduled; bool opened; bool in_write_poll; diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c index e4ffeb9a1fa4..c650e428432b 100644 --- a/arch/um/drivers/vector_user.c +++ b/arch/um/drivers/vector_user.c @@ -771,7 +771,7 @@ int uml_vector_detach_bpf(int fd, void *bpf) printk(KERN_ERR BPF_DETACH_FAIL, prog->len, prog->filter, fd, -errno); return err; } -void *uml_vector_default_bpf(void *mac) +void *uml_vector_default_bpf(const void *mac) { struct sock_filter *bpf; uint32_t *mac1 = (uint32_t *)(mac + 2); diff --git a/arch/um/drivers/vector_user.h b/arch/um/drivers/vector_user.h index d29d5fdd98fa..3a73d17a0161 100644 --- a/arch/um/drivers/vector_user.h +++ b/arch/um/drivers/vector_user.h @@ -97,7 +97,7 @@ extern int uml_vector_recvmmsg( unsigned int vlen, unsigned int flags ); -extern void *uml_vector_default_bpf(void *mac); +extern void *uml_vector_default_bpf(const void *mac); extern void *uml_vector_user_bpf(char *filename); extern int uml_vector_attach_bpf(int fd, void *bpf); extern int uml_vector_detach_bpf(int fd, void *bpf); diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index e5a7b552bb38..b08bd2966253 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -17,6 +17,7 @@ generic-y += mcs_spinlock.h generic-y += mmiowb.h generic-y += module.lds.h generic-y += param.h +generic-y += parport.h generic-y += percpu.h generic-y += preempt.h generic-y += softirq_stack.h diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h index f512704a9ec7..22b39de73c24 100644 --- a/arch/um/include/asm/xor.h +++ b/arch/um/include/asm/xor.h @@ -4,8 +4,10 @@ #ifdef CONFIG_64BIT #undef CONFIG_X86_32 +#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_sse_pf64)) #else #define CONFIG_X86_32 1 +#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_8regs)) #endif #include <asm/cpufeature.h> @@ -16,7 +18,7 @@ #undef XOR_SELECT_TEMPLATE /* pick an arbitrary one - measuring isn't possible with inf-cpu */ #define XOR_SELECT_TEMPLATE(x) \ - (time_travel_mode == TT_MODE_INFCPU ? &xor_block_8regs : NULL) + (time_travel_mode == TT_MODE_INFCPU ? TT_CPU_INF_XOR_DEFAULT : x)) #endif #endif diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 00214059d9ec..fafde1d5416e 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -168,6 +168,7 @@ extern unsigned os_major(unsigned long long dev); extern unsigned os_minor(unsigned long long dev); extern unsigned long long os_makedev(unsigned major, unsigned minor); extern int os_falloc_punch(int fd, unsigned long long offset, int count); +extern int os_falloc_zeroes(int fd, unsigned long long offset, int count); extern int os_eventfd(unsigned int initval, int flags); extern int os_sendmsg_fds(int fd, const void *buf, unsigned int len, const int *fds, unsigned int fds_num); diff --git a/arch/um/kernel/dtb.c b/arch/um/kernel/dtb.c index ca69d72025f3..484141b06938 100644 --- a/arch/um/kernel/dtb.c +++ b/arch/um/kernel/dtb.c @@ -25,8 +25,8 @@ void uml_dtb_init(void) return; } - unflatten_device_tree(); early_init_fdt_scan_reserved_mem(); + unflatten_device_tree(); } static int __init uml_dtb_setup(char *line, int *add) diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 4a420778ed87..80504680be08 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -23,7 +23,7 @@ #include <linux/seq_file.h> #include <linux/tick.h> #include <linux/threads.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <asm/current.h> #include <asm/mmu_context.h> #include <linux/uaccess.h> @@ -104,7 +104,7 @@ void interrupt_end(void) test_thread_flag(TIF_NOTIFY_SIGNAL)) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } int get_current_pid(void) diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c index b425f47bddbb..bfaf6ab1ac03 100644 --- a/arch/um/kernel/ptrace.c +++ b/arch/um/kernel/ptrace.c @@ -6,7 +6,6 @@ #include <linux/audit.h> #include <linux/ptrace.h> #include <linux/sched.h> -#include <linux/tracehook.h> #include <linux/uaccess.h> #include <asm/ptrace-abi.h> @@ -135,7 +134,7 @@ int syscall_trace_enter(struct pt_regs *regs) if (!test_thread_flag(TIF_SYSCALL_TRACE)) return 0; - return tracehook_report_syscall_entry(regs); + return ptrace_report_syscall_entry(regs); } void syscall_trace_leave(struct pt_regs *regs) @@ -151,7 +150,7 @@ void syscall_trace_leave(struct pt_regs *regs) if (!test_thread_flag(TIF_SYSCALL_TRACE)) return; - tracehook_report_syscall_exit(regs, 0); + ptrace_report_syscall_exit(regs, 0); /* force do_signal() --> is_syscall() */ if (ptraced & PT_PTRACED) set_thread_flag(TIF_SIGPENDING); diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index abceeabe29b9..0760e24f2eba 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -424,6 +424,10 @@ void __init check_bugs(void) os_check_bugs(); } +void apply_ibt_endbr(s32 *start, s32 *end) +{ +} + void apply_retpolines(s32 *start, s32 *end) { } diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index e4421dbc4c36..fc4450db59bd 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -625,6 +625,15 @@ int os_falloc_punch(int fd, unsigned long long offset, int len) return n; } +int os_falloc_zeroes(int fd, unsigned long long offset, int len) +{ + int n = fallocate(fd, FALLOC_FL_ZERO_RANGE|FALLOC_FL_KEEP_SIZE, offset, len); + + if (n < 0) + return -errno; + return n; +} + int os_eventfd(unsigned int initval, int flags) { int fd = eventfd(initval, flags); diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index 32e88baf18dd..b459745f52e2 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -4,6 +4,7 @@ */ #include <stdlib.h> +#include <string.h> #include <unistd.h> #include <errno.h> #include <sched.h> @@ -99,6 +100,10 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) CATCH_EINTR(waitpid(pid, NULL, __WALL)); } + if (ret < 0) + printk(UM_KERN_ERR "run_helper : failed to exec %s on host: %s\n", + argv[0], strerror(-ret)); + out_free2: kfree(data.buf); out_close: diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c index 6c5041c5560b..4d5591d96d8c 100644 --- a/arch/um/os-Linux/time.c +++ b/arch/um/os-Linux/time.c @@ -18,12 +18,6 @@ static timer_t event_high_res_timer = 0; -static inline long long timeval_to_ns(const struct timeval *tv) -{ - return ((long long) tv->tv_sec * UM_NSEC_PER_SEC) + - tv->tv_usec * UM_NSEC_PER_USEC; -} - static inline long long timespec_to_ns(const struct timespec *ts) { return ((long long) ts->tv_sec * UM_NSEC_PER_SEC) + ts->tv_nsec; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b037fe7be374..ff45a27fc29c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -224,6 +224,7 @@ config X86 select HAVE_KPROBES_ON_FTRACE select HAVE_FUNCTION_ERROR_INJECTION select HAVE_KRETPROBES + select HAVE_RETHOOK select HAVE_KVM select HAVE_LIVEPATCH if X86_64 select HAVE_MIXED_BREAKPOINTS_REGS @@ -337,9 +338,6 @@ config GENERIC_CALIBRATE_DELAY config ARCH_HAS_CPU_RELAX def_bool y -config ARCH_HAS_FILTER_PGPROT - def_bool y - config ARCH_HIBERNATION_POSSIBLE def_bool y @@ -1845,6 +1843,36 @@ config X86_UMIP specific cases in protected and virtual-8086 modes. Emulated results are dummy. +config CC_HAS_IBT + # GCC >= 9 and binutils >= 2.29 + # Retpoline check to work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93654 + # Clang/LLVM >= 14 + # https://github.com/llvm/llvm-project/commit/e0b89df2e0f0130881bf6c39bf31d7f6aac00e0f + # https://github.com/llvm/llvm-project/commit/dfcf69770bc522b9e411c66454934a37c1f35332 + def_bool ((CC_IS_GCC && $(cc-option, -fcf-protection=branch -mindirect-branch-register)) || \ + (CC_IS_CLANG && CLANG_VERSION >= 140000)) && \ + $(as-instr,endbr64) + +config X86_KERNEL_IBT + prompt "Indirect Branch Tracking" + bool + depends on X86_64 && CC_HAS_IBT && STACK_VALIDATION + # https://github.com/llvm/llvm-project/commit/9d7001eba9c4cb311e03cd8cdc231f9e579f2d0f + depends on !LD_IS_LLD || LLD_VERSION >= 140000 + help + Build the kernel with support for Indirect Branch Tracking, a + hardware support course-grain forward-edge Control Flow Integrity + protection. It enforces that all indirect calls must land on + an ENDBR instruction, as such, the compiler will instrument the + code with them to make this happen. + + In addition to building the kernel with IBT, seal all functions that + are not indirect call targets, avoiding them ever becomming one. + + This requires LTO like objtool runs and will slow down the build. It + does significantly reduce the number of ENDBR instructions in the + kernel image. + config X86_INTEL_MEMORY_PROTECTION_KEYS prompt "Memory Protection Keys" def_bool y @@ -2818,19 +2846,20 @@ config IA32_AOUT help Support old a.out binaries in the 32bit emulation. -config X86_X32 +config X86_X32_ABI bool "x32 ABI for 64-bit mode" depends on X86_64 + # llvm-objcopy does not convert x86_64 .note.gnu.property or + # compressed debug sections to x86_x32 properly: + # https://github.com/ClangBuiltLinux/linux/issues/514 + # https://github.com/ClangBuiltLinux/linux/issues/1141 + depends on $(success,$(OBJCOPY) --version | head -n1 | grep -qv llvm) help Include code to run binaries for the x32 native 32-bit ABI for 64-bit processors. An x32 process gets access to the full 64-bit register file and wide data path while leaving pointers at 32 bits for smaller memory footprint. - You will need a recent binutils (2.22 or later) with - elf32_x86_64 support enabled to compile a kernel with this - option set. - config COMPAT_32 def_bool y depends on IA32_EMULATION || X86_32 @@ -2839,7 +2868,7 @@ config COMPAT_32 config COMPAT def_bool y - depends on IA32_EMULATION || X86_X32 + depends on IA32_EMULATION || X86_X32_ABI if COMPAT config COMPAT_FOR_U64_ALIGNMENT diff --git a/arch/x86/Makefile b/arch/x86/Makefile index e84cdd409b64..63d50f65b828 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -36,7 +36,7 @@ endif # How to compile the 16-bit code. Note we always compile for -march=i386; # that way we can complain to the user if the CPU is insufficient. -REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING \ +REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none) @@ -62,8 +62,20 @@ export BITS # KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx -# Intel CET isn't enabled in the kernel +ifeq ($(CONFIG_X86_KERNEL_IBT),y) +# +# Kernel IBT has S_CET.NOTRACK_EN=0, as such the compilers must not generate +# NOTRACK prefixes. Current generation compilers unconditionally employ NOTRACK +# for jump-tables, as such, disable jump-tables for now. +# +# (jump-tables are implicitly disabled by RETPOLINE) +# +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104816 +# +KBUILD_CFLAGS += $(call cc-option,-fcf-protection=branch -fno-jump-tables) +else KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) +endif ifeq ($(CONFIG_X86_32),y) BITS := 32 @@ -140,22 +152,6 @@ else KBUILD_CFLAGS += -mcmodel=kernel endif -ifdef CONFIG_X86_X32 - x32_ld_ok := $(call try-run,\ - /bin/echo -e '1: .quad 1b' | \ - $(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" - && \ - $(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMP.o" && \ - $(LD) -m elf32_x86_64 "$$TMP.o" -o "$$TMP",y,n) - ifeq ($(x32_ld_ok),y) - CONFIG_X86_X32_ABI := y - KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI - KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI - else - $(warning CONFIG_X86_X32 enabled but no binutils support) - endif -endif -export CONFIG_X86_X32_ABI - # # If the function graph tracer is used with mcount instead of fentry, # '-maccumulate-outgoing-args' is needed to prevent a GCC bug diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index a4339cb2d247..1cdcaf34ee36 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -37,10 +37,11 @@ * try to define their own functions if these are not defined as macros. */ #define memzero(s, n) memset((s), 0, (n)) +#ifndef memmove #define memmove memmove - /* Functions used by the included decompressor code below. */ void *memmove(void *dest, const void *src, size_t n); +#endif /* * This is set up by the setup-routine at boot-time diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S index 946f74dd6fba..259383e1ad44 100644 --- a/arch/x86/crypto/chacha-avx512vl-x86_64.S +++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S @@ -172,7 +172,7 @@ SYM_FUNC_START(chacha_2block_xor_avx512vl) # xor remaining bytes from partial register into output mov %rcx,%rax and $0xf,%rcx - jz .Ldone8 + jz .Ldone2 mov %rax,%r9 and $~0xf,%r9 @@ -438,7 +438,7 @@ SYM_FUNC_START(chacha_4block_xor_avx512vl) # xor remaining bytes from partial register into output mov %rcx,%rax and $0xf,%rcx - jz .Ldone8 + jz .Ldone4 mov %rax,%r9 and $~0xf,%r9 diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 80c0d22fc42c..ec35915f0901 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -195,6 +195,7 @@ crc_array: .altmacro LABEL crc_ %i .noaltmacro + ENDBR crc32q -i*8(block_0), crc_init crc32q -i*8(block_1), crc1 crc32q -i*8(block_2), crc2 @@ -204,6 +205,7 @@ LABEL crc_ %i .altmacro LABEL crc_ %i .noaltmacro + ENDBR crc32q -i*8(block_0), crc_init crc32q -i*8(block_1), crc1 # SKIP crc32 -i*8(block_2), crc2 ; Don't do this one yet @@ -237,6 +239,7 @@ LABEL crc_ %i ################################################################ LABEL crc_ 0 + ENDBR mov tmp, len cmp $128*24, tmp jae full_block diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl index 71fae5a09e56..2077ce7a5647 100644 --- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl @@ -297,7 +297,7 @@ ___ $code.=<<___; mov \$1,%eax .Lno_key: - ret + RET ___ &end_function("poly1305_init_x86_64"); @@ -373,7 +373,7 @@ $code.=<<___; .cfi_adjust_cfa_offset -48 .Lno_data: .Lblocks_epilogue: - ret + RET .cfi_endproc ___ &end_function("poly1305_blocks_x86_64"); @@ -399,7 +399,7 @@ $code.=<<___; mov %rax,0($mac) # write result mov %rcx,8($mac) - ret + RET ___ &end_function("poly1305_emit_x86_64"); if ($avx) { @@ -429,7 +429,7 @@ ___ &poly1305_iteration(); $code.=<<___; pop $ctx - ret + RET .size __poly1305_block,.-__poly1305_block .type __poly1305_init_avx,\@abi-omnipotent @@ -594,7 +594,7 @@ __poly1305_init_avx: lea -48-64($ctx),$ctx # size [de-]optimization pop %rbp - ret + RET .size __poly1305_init_avx,.-__poly1305_init_avx ___ @@ -747,7 +747,7 @@ $code.=<<___; .cfi_restore %rbp .Lno_data_avx: .Lblocks_avx_epilogue: - ret + RET .cfi_endproc .align 32 @@ -1452,7 +1452,7 @@ $code.=<<___ if (!$win64); ___ $code.=<<___; vzeroupper - ret + RET .cfi_endproc ___ &end_function("poly1305_blocks_avx"); @@ -1508,7 +1508,7 @@ $code.=<<___; mov %rax,0($mac) # write result mov %rcx,8($mac) - ret + RET ___ &end_function("poly1305_emit_avx"); @@ -1675,7 +1675,7 @@ $code.=<<___; .cfi_restore %rbp .Lno_data_avx2$suffix: .Lblocks_avx2_epilogue$suffix: - ret + RET .cfi_endproc .align 32 @@ -2201,7 +2201,7 @@ $code.=<<___ if (!$win64); ___ $code.=<<___; vzeroupper - ret + RET .cfi_endproc ___ if($avx > 2 && $avx512) { @@ -2792,7 +2792,7 @@ $code.=<<___ if (!$win64); .cfi_def_cfa_register %rsp ___ $code.=<<___; - ret + RET .cfi_endproc ___ @@ -2893,7 +2893,7 @@ $code.=<<___ if ($flavour =~ /elf32/); ___ $code.=<<___; mov \$1,%eax - ret + RET .size poly1305_init_base2_44,.-poly1305_init_base2_44 ___ { @@ -3010,7 +3010,7 @@ poly1305_blocks_vpmadd52: jnz .Lblocks_vpmadd52_4x .Lno_data_vpmadd52: - ret + RET .size poly1305_blocks_vpmadd52,.-poly1305_blocks_vpmadd52 ___ } @@ -3451,7 +3451,7 @@ poly1305_blocks_vpmadd52_4x: vzeroall .Lno_data_vpmadd52_4x: - ret + RET .size poly1305_blocks_vpmadd52_4x,.-poly1305_blocks_vpmadd52_4x ___ } @@ -3824,7 +3824,7 @@ $code.=<<___; vzeroall .Lno_data_vpmadd52_8x: - ret + RET .size poly1305_blocks_vpmadd52_8x,.-poly1305_blocks_vpmadd52_8x ___ } @@ -3861,7 +3861,7 @@ poly1305_emit_base2_44: mov %rax,0($mac) # write result mov %rcx,8($mac) - ret + RET .size poly1305_emit_base2_44,.-poly1305_emit_base2_44 ___ } } } @@ -3916,7 +3916,7 @@ xor128_encrypt_n_pad: .Ldone_enc: mov $otp,%rax - ret + RET .size xor128_encrypt_n_pad,.-xor128_encrypt_n_pad .globl xor128_decrypt_n_pad @@ -3967,7 +3967,7 @@ xor128_decrypt_n_pad: .Ldone_dec: mov $otp,%rax - ret + RET .size xor128_decrypt_n_pad,.-xor128_decrypt_n_pad ___ } @@ -4109,7 +4109,7 @@ avx_handler: pop %rbx pop %rdi pop %rsi - ret + RET .size avx_handler,.-avx_handler .section .pdata diff --git a/arch/x86/crypto/sm3-avx-asm_64.S b/arch/x86/crypto/sm3-avx-asm_64.S index 71e6aae23e17..b12b9efb5ec5 100644 --- a/arch/x86/crypto/sm3-avx-asm_64.S +++ b/arch/x86/crypto/sm3-avx-asm_64.S @@ -513,5 +513,5 @@ SYM_FUNC_START(sm3_transform_avx) movq %rbp, %rsp; popq %rbp; - ret; + RET; SYM_FUNC_END(sm3_transform_avx) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 466df3e50276..4faac48ebec5 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -86,6 +86,7 @@ SYM_CODE_START(entry_SYSCALL_64) UNWIND_HINT_EMPTY + ENDBR swapgs /* tss.sp2 is scratch space. */ @@ -94,6 +95,7 @@ SYM_CODE_START(entry_SYSCALL_64) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR /* Construct struct pt_regs on stack */ pushq $__USER_DS /* pt_regs->ss */ @@ -276,6 +278,7 @@ SYM_FUNC_END(__switch_to_asm) .pushsection .text, "ax" SYM_CODE_START(ret_from_fork) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR // copy_thread movq %rax, %rdi call schedule_tail /* rdi: 'prev' task parameter */ @@ -350,6 +353,7 @@ SYM_CODE_END(ret_from_fork) .macro idtentry vector asmsym cfunc has_error_code:req SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 + ENDBR ASM_CLAC .if \has_error_code == 0 @@ -417,6 +421,7 @@ SYM_CODE_END(\asmsym) .macro idtentry_mce_db vector asmsym cfunc SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS + ENDBR ASM_CLAC pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -472,6 +477,7 @@ SYM_CODE_END(\asmsym) .macro idtentry_vc vector asmsym cfunc SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS + ENDBR ASM_CLAC /* @@ -533,6 +539,7 @@ SYM_CODE_END(\asmsym) .macro idtentry_df vector asmsym cfunc SYM_CODE_START(\asmsym) UNWIND_HINT_IRET_REGS offset=8 + ENDBR ASM_CLAC /* paranoid_entry returns GS information for paranoid_exit in EBX. */ @@ -544,6 +551,9 @@ SYM_CODE_START(\asmsym) movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ call \cfunc + /* For some configurations \cfunc ends up being a noreturn. */ + REACHABLE + jmp paranoid_exit _ASM_NOKPROBE(\asmsym) @@ -564,6 +574,7 @@ __irqentry_text_start: .align 16 .globl __irqentry_text_end __irqentry_text_end: + ANNOTATE_NOENDBR SYM_CODE_START_LOCAL(common_interrupt_return) SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) @@ -608,8 +619,8 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi - SWAPGS - INTERRUPT_RETURN + swapgs + jmp .Lnative_iret SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL) @@ -626,9 +637,14 @@ SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL) * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization * when returning from IPI handler. */ - INTERRUPT_RETURN +#ifdef CONFIG_XEN_PV +SYM_INNER_LABEL(early_xen_iret_patch, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + .byte 0xe9 + .long .Lnative_iret - (. + 4) +#endif -SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL) +.Lnative_iret: UNWIND_HINT_IRET_REGS /* * Are we returning to a stack segment from the LDT? Note: in @@ -640,6 +656,7 @@ SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL) #endif SYM_INNER_LABEL(native_irq_return_iret, SYM_L_GLOBAL) + ANNOTATE_NOENDBR // exc_double_fault /* * This may fault. Non-paranoid faults on return to userspace are * handled by fixup_bad_iret. These include #SS, #GP, and #NP. @@ -734,6 +751,7 @@ SYM_FUNC_START(asm_load_gs_index) FRAME_BEGIN swapgs .Lgs_change: + ANNOTATE_NOENDBR // error_entry movl %edi, %gs 2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE swapgs @@ -804,6 +822,7 @@ SYM_CODE_END(exc_xen_hypervisor_callback) */ SYM_CODE_START(xen_failsafe_callback) UNWIND_HINT_EMPTY + ENDBR movl %ds, %ecx cmpw %cx, 0x10(%rsp) jne 1f @@ -1063,6 +1082,7 @@ SYM_CODE_END(error_return) */ SYM_CODE_START(asm_exc_nmi) UNWIND_HINT_IRET_REGS + ENDBR /* * We allow breakpoints in NMIs. If a breakpoint occurs, then @@ -1310,6 +1330,7 @@ first_nmi: #endif repeat_nmi: + ANNOTATE_NOENDBR // this code /* * If there was a nested NMI, the first NMI's iret will return * here. But NMIs are still enabled and we can take another @@ -1338,6 +1359,7 @@ repeat_nmi: .endr subq $(5*8), %rsp end_repeat_nmi: + ANNOTATE_NOENDBR // this code /* * Everything below this point can be preempted by a nested NMI. @@ -1421,6 +1443,7 @@ SYM_CODE_END(asm_exc_nmi) */ SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY + ENDBR mov $-ENOSYS, %eax sysretl SYM_CODE_END(ignore_sysret) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 0051cf5c792d..4fdb007cddbd 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -48,6 +48,7 @@ */ SYM_CODE_START(entry_SYSENTER_compat) UNWIND_HINT_EMPTY + ENDBR /* Interrupts are off on entry. */ SWAPGS @@ -147,6 +148,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) popfq jmp .Lsysenter_flags_fixed SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL) + ANNOTATE_NOENDBR // is_sysenter_singlestep SYM_CODE_END(entry_SYSENTER_compat) /* @@ -198,6 +200,7 @@ SYM_CODE_END(entry_SYSENTER_compat) */ SYM_CODE_START(entry_SYSCALL_compat) UNWIND_HINT_EMPTY + ENDBR /* Interrupts are off on entry. */ swapgs @@ -211,6 +214,7 @@ SYM_CODE_START(entry_SYSCALL_compat) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) + ANNOTATE_NOENDBR /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ @@ -340,6 +344,7 @@ SYM_CODE_END(entry_SYSCALL_compat) */ SYM_CODE_START(entry_INT80_compat) UNWIND_HINT_EMPTY + ENDBR /* * Interrupts are off on entry. */ diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile index 5b3efed0e4e8..eca5d6eff132 100644 --- a/arch/x86/entry/syscalls/Makefile +++ b/arch/x86/entry/syscalls/Makefile @@ -3,8 +3,7 @@ out := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm # Create output directory if not already present -_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ - $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') +$(shell mkdir -p $(out) $(uapi)) syscall32 := $(src)/syscall_32.tbl syscall64 := $(src)/syscall_64.tbl @@ -67,7 +66,7 @@ uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h syshdr-y += syscalls_32.h syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h syshdr-$(CONFIG_X86_64) += syscalls_64.h -syshdr-$(CONFIG_X86_X32) += syscalls_x32.h +syshdr-$(CONFIG_X86_X32_ABI) += syscalls_x32.h syshdr-$(CONFIG_XEN) += xen-hypercalls.h uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 58eee6402832..9b10c8c76087 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -76,6 +76,7 @@ extern int alternatives_patched; extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); extern void apply_retpolines(s32 *start, s32 *end); +extern void apply_ibt_endbr(s32 *start, s32 *end); struct module; diff --git a/arch/x86/include/asm/amd_hsmp.h b/arch/x86/include/asm/amd_hsmp.h new file mode 100644 index 000000000000..03c2ce3edaf5 --- /dev/null +++ b/arch/x86/include/asm/amd_hsmp.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _ASM_X86_AMD_HSMP_H_ +#define _ASM_X86_AMD_HSMP_H_ + +#include <uapi/asm/amd_hsmp.h> + +#if IS_ENABLED(CONFIG_AMD_HSMP) +int hsmp_send_message(struct hsmp_message *msg); +#else +static inline int hsmp_send_message(struct hsmp_message *msg) +{ + return -ENODEV; +} +#endif +#endif /*_ASM_X86_AMD_HSMP_H_*/ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index bab883c0b6fe..4d20a293c6fd 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -4,6 +4,7 @@ #include <linux/stringify.h> #include <linux/instrumentation.h> +#include <linux/objtool.h> /* * Despite that some emulators terminate on UD2, we use it for WARN(). diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 33d41e350c79..86e5e4e26fcb 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -7,6 +7,7 @@ #include <linux/topology.h> #include <linux/nodemask.h> #include <linux/percpu.h> +#include <asm/ibt.h> #ifdef CONFIG_SMP @@ -72,4 +73,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c); #else static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} #endif + +extern __noendbr void cet_disable(void); + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 3edf05e98e58..73e643ae94b6 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -388,6 +388,7 @@ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */ #define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ #define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ #define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 03cb12775043..98938a68251c 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -7,6 +7,7 @@ #include <asm/tlb.h> #include <asm/nospec-branch.h> #include <asm/mmu_context.h> +#include <asm/ibt.h> #include <linux/build_bug.h> #include <linux/kernel.h> #include <linux/pgtable.h> @@ -120,8 +121,12 @@ extern asmlinkage u64 __efi_call(void *fp, ...); efi_enter_mm(); \ }) -#define arch_efi_call_virt(p, f, args...) \ - efi_call((void *)p->f, args) \ +#define arch_efi_call_virt(p, f, args...) ({ \ + u64 ret, ibt = ibt_save(); \ + ret = efi_call((void *)p->f, args); \ + ibt_restore(ibt); \ + ret; \ +}) #define arch_efi_call_virt_teardown() \ ({ \ diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h new file mode 100644 index 000000000000..689880eca9ba --- /dev/null +++ b/arch/x86/include/asm/ibt.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IBT_H +#define _ASM_X86_IBT_H + +#include <linux/types.h> + +/* + * The rules for enabling IBT are: + * + * - CC_HAS_IBT: the toolchain supports it + * - X86_KERNEL_IBT: it is selected in Kconfig + * - !__DISABLE_EXPORTS: this is regular kernel code + * + * Esp. that latter one is a bit non-obvious, but some code like compressed, + * purgatory, realmode etc.. is built with custom CFLAGS that do not include + * -fcf-protection=branch and things will go *bang*. + * + * When all the above are satisfied, HAS_KERNEL_IBT will be 1, otherwise 0. + */ +#if defined(CONFIG_X86_KERNEL_IBT) && !defined(__DISABLE_EXPORTS) + +#define HAS_KERNEL_IBT 1 + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_X86_64 +#define ASM_ENDBR "endbr64\n\t" +#else +#define ASM_ENDBR "endbr32\n\t" +#endif + +#define __noendbr __attribute__((nocf_check)) + +static inline __attribute_const__ u32 gen_endbr(void) +{ + u32 endbr; + + /* + * Generate ENDBR64 in a way that is sure to not result in + * an ENDBR64 instruction as immediate. + */ + asm ( "mov $~0xfa1e0ff3, %[endbr]\n\t" + "not %[endbr]\n\t" + : [endbr] "=&r" (endbr) ); + + return endbr; +} + +static inline __attribute_const__ u32 gen_endbr_poison(void) +{ + /* + * 4 byte NOP that isn't NOP4 (in fact it is OSP NOP3), such that it + * will be unique to (former) ENDBR sites. + */ + return 0x001f0f66; /* osp nopl (%rax) */ +} + +static inline bool is_endbr(u32 val) +{ + if (val == gen_endbr_poison()) + return true; + + val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */ + return val == gen_endbr(); +} + +extern __noendbr u64 ibt_save(void); +extern __noendbr void ibt_restore(u64 save); + +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_X86_64 +#define ENDBR endbr64 +#else +#define ENDBR endbr32 +#endif + +#endif /* __ASSEMBLY__ */ + +#else /* !IBT */ + +#define HAS_KERNEL_IBT 0 + +#ifndef __ASSEMBLY__ + +#define ASM_ENDBR + +#define __noendbr + +static inline bool is_endbr(u32 val) { return false; } + +static inline u64 ibt_save(void) { return 0; } +static inline void ibt_restore(u64 save) { } + +#else /* __ASSEMBLY__ */ + +#define ENDBR + +#endif /* __ASSEMBLY__ */ + +#endif /* CONFIG_X86_KERNEL_IBT */ + +#define ENDBR_INSN_SIZE (4*HAS_KERNEL_IBT) + +#endif /* _ASM_X86_IBT_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 1345088e9902..7924f27f5c8b 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -5,6 +5,8 @@ /* Interrupts/Exceptions */ #include <asm/trapnr.h> +#define IDT_ALIGN (8 * (1 + HAS_KERNEL_IBT)) + #ifndef __ASSEMBLY__ #include <linux/entry-common.h> #include <linux/hardirq.h> @@ -480,7 +482,7 @@ __visible noinstr void func(struct pt_regs *regs, \ /* * ASM code to emit the common vector entry stubs where each stub is - * packed into 8 bytes. + * packed into IDT_ALIGN bytes. * * Note, that the 'pushq imm8' is emitted via '.byte 0x6a, vector' because * GCC treats the local vector variable as unsigned int and would expand @@ -492,33 +494,33 @@ __visible noinstr void func(struct pt_regs *regs, \ * point is to mask off the bits above bit 7 because the push is sign * extending. */ - .align 8 + .align IDT_ALIGN SYM_CODE_START(irq_entries_start) vector=FIRST_EXTERNAL_VECTOR .rept NR_EXTERNAL_VECTORS UNWIND_HINT_IRET_REGS 0 : + ENDBR .byte 0x6a, vector jmp asm_common_interrupt - nop - /* Ensure that the above is 8 bytes max */ - . = 0b + 8 + /* Ensure that the above is IDT_ALIGN bytes max */ + .fill 0b + IDT_ALIGN - ., 1, 0xcc vector = vector+1 .endr SYM_CODE_END(irq_entries_start) #ifdef CONFIG_X86_LOCAL_APIC - .align 8 + .align IDT_ALIGN SYM_CODE_START(spurious_entries_start) vector=FIRST_SYSTEM_VECTOR .rept NR_SYSTEM_VECTORS UNWIND_HINT_IRET_REGS 0 : + ENDBR .byte 0x6a, vector jmp asm_spurious_interrupt - nop - /* Ensure that the above is 8 bytes max */ - . = 0b + 8 + /* Ensure that the above is IDT_ALIGN bytes max */ + .fill 0b + IDT_ALIGN - ., 1, 0xcc vector = vector+1 .endr SYM_CODE_END(spurious_entries_start) @@ -615,6 +617,11 @@ DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault); DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_DF, xenpv_exc_double_fault); #endif +/* #CP */ +#ifdef CONFIG_X86_KERNEL_IBT +DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_CP, exc_control_protection); +#endif + /* #VC */ #ifdef CONFIG_AMD_MEM_ENCRYPT DECLARE_IDTENTRY_VC(X86_TRAP_VC, exc_vmm_communication); diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index ae9d40f6c706..63f818aedf77 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -3,6 +3,7 @@ #define _ASM_X86_IRQ_STACK_H #include <linux/ptrace.h> +#include <linux/objtool.h> #include <asm/processor.h> @@ -99,7 +100,8 @@ } #define ASM_CALL_ARG0 \ - "call %P[__func] \n" + "call %P[__func] \n" \ + ASM_REACHABLE #define ASM_CALL_ARG1 \ "movq %[arg1], %%rdi \n" \ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 87761396e8cc..111104d1c2cd 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -141,13 +141,8 @@ static __always_inline void arch_local_irq_restore(unsigned long flags) #ifdef CONFIG_X86_64 #ifdef CONFIG_XEN_PV #define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV -#define INTERRUPT_RETURN \ - ANNOTATE_RETPOLINE_SAFE; \ - ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);", \ - X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;") #else #define SWAPGS swapgs -#define INTERRUPT_RETURN jmp native_iret #endif #endif #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 030907922bd0..85865f1645bd 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -3,6 +3,7 @@ #define _ASM_X86_LINKAGE_H #include <linux/stringify.h> +#include <asm/ibt.h> #undef notrace #define notrace __attribute__((no_instrument_function)) @@ -34,5 +35,35 @@ #endif /* __ASSEMBLY__ */ +/* SYM_FUNC_START -- use for global functions */ +#define SYM_FUNC_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + ENDBR + +/* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */ +#define SYM_FUNC_START_NOALIGN(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE) \ + ENDBR + +/* SYM_FUNC_START_LOCAL -- use for local functions */ +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) \ + ENDBR + +/* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */ +#define SYM_FUNC_START_LOCAL_NOALIGN(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_NONE) \ + ENDBR + +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) \ + ENDBR + +/* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */ +#define SYM_FUNC_START_WEAK_NOALIGN(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \ + ENDBR + #endif /* _ASM_X86_LINKAGE_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9f1741ac4769..0eb90d21049e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -362,11 +362,29 @@ #define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c #define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d - #define MSR_CORE_PERF_LIMIT_REASONS 0x00000690 #define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 #define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 +/* Control-flow Enforcement Technology MSRs */ +#define MSR_IA32_U_CET 0x000006a0 /* user mode cet */ +#define MSR_IA32_S_CET 0x000006a2 /* kernel mode cet */ +#define CET_SHSTK_EN BIT_ULL(0) +#define CET_WRSS_EN BIT_ULL(1) +#define CET_ENDBR_EN BIT_ULL(2) +#define CET_LEG_IW_EN BIT_ULL(3) +#define CET_NO_TRACK_EN BIT_ULL(4) +#define CET_SUPPRESS_DISABLE BIT_ULL(5) +#define CET_RESERVED (BIT_ULL(6) | BIT_ULL(7) | BIT_ULL(8) | BIT_ULL(9)) +#define CET_SUPPRESS BIT_ULL(10) +#define CET_WAIT_ENDBR BIT_ULL(11) + +#define MSR_IA32_PL0_SSP 0x000006a4 /* ring-0 shadow stack pointer */ +#define MSR_IA32_PL1_SSP 0x000006a5 /* ring-1 shadow stack pointer */ +#define MSR_IA32_PL2_SSP 0x000006a6 /* ring-2 shadow stack pointer */ +#define MSR_IA32_PL3_SSP 0x000006a7 /* ring-3 shadow stack pointer */ +#define MSR_IA32_INT_SSP_TAB 0x000006a8 /* exception shadow stack table */ + /* Hardware P state interface */ #define MSR_PPERF 0x0000064e #define MSR_PERF_LIMIT_REASONS 0x0000064f diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 0d76502cc6f5..964442b99245 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -666,6 +666,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); ".globl " PV_THUNK_NAME(func) ";" \ ".type " PV_THUNK_NAME(func) ", @function;" \ PV_THUNK_NAME(func) ":" \ + ASM_ENDBR \ FRAME_BEGIN \ PV_SAVE_ALL_CALLER_REGS \ "call " #func ";" \ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index e1591467668e..89df6c6617f5 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -272,7 +272,6 @@ struct paravirt_patch_template { extern struct pv_info pv_info; extern struct paravirt_patch_template pv_ops; -extern void (*paravirt_iret)(void); #define PARAVIRT_PATCH(x) \ (offsetof(struct paravirt_patch_template, x) / sizeof(void *)) diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 3fb6fc596095..a0627dfae541 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -5,7 +5,10 @@ * (c) 1999 Martin Mares <mj@ucw.cz> */ +#include <linux/errno.h> +#include <linux/init.h> #include <linux/ioport.h> +#include <linux/spinlock.h> #undef DEBUG diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a87e7c33d5ac..91d0f93a00c7 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -837,7 +837,7 @@ bool xen_set_default_idle(void); #define xen_set_default_idle 0 #endif -void stop_this_cpu(void *dummy); +void __noreturn stop_this_cpu(void *dummy); void microcode_check(void); enum l1tf_mitigations { diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 1474cf96251d..892fd8c3a6f7 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -2,6 +2,8 @@ #ifndef __ASM_QSPINLOCK_PARAVIRT_H #define __ASM_QSPINLOCK_PARAVIRT_H +#include <asm/ibt.h> + /* * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit * registers. For i386, however, only 1 32-bit register needs to be saved @@ -39,6 +41,7 @@ asm (".pushsection .text;" ".type " PV_UNLOCK ", @function;" ".align 4,0x90;" PV_UNLOCK ": " + ASM_ENDBR FRAME_BEGIN "push %rdx;" "mov $0x1,%eax;" diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index b228c9d44ee7..656ed6531d03 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -4,6 +4,7 @@ #include <linux/const.h> #include <asm/alternative.h> +#include <asm/ibt.h> /* * Constructor for a conventional segment GDT (or LDT) entry. @@ -275,7 +276,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node) * vector has no error code (two bytes), a 'push $vector_number' (two * bytes), and a jump to the common entry code (up to five bytes). */ -#define EARLY_IDT_HANDLER_SIZE 9 +#define EARLY_IDT_HANDLER_SIZE (9 + ENDBR_INSN_SIZE) /* * xen_early_idt_handler_array is for Xen pv guests: for each entry in @@ -283,7 +284,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node) * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to * max 8 bytes. */ -#define XEN_EARLY_IDT_HANDLER_SIZE 8 +#define XEN_EARLY_IDT_HANDLER_SIZE (8 + ENDBR_INSN_SIZE) #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index a12458a7a8d4..896e48d45828 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -8,6 +8,7 @@ #include <linux/linkage.h> #include <asm/page_types.h> +#include <asm/ibt.h> #ifdef __i386__ @@ -119,7 +120,7 @@ void *extend_brk(size_t size, size_t align); * executable.) */ #define RESERVE_BRK(name,sz) \ - static void __section(".discard.text") __used notrace \ + static void __section(".discard.text") __noendbr __used notrace \ __brk_reservation_fn_##name##__(void) { \ asm volatile ( \ ".pushsection .brk_reservation,\"aw\",@nobits;" \ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 6a2827d0681f..59358d1bf880 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -159,7 +159,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #endif /* CONFIG_IA32_EMULATION */ -#ifdef CONFIG_X86_X32 +#ifdef CONFIG_X86_X32_ABI /* * For the x32 ABI, we need to create a stub for compat_sys_*() which is aware * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common @@ -177,12 +177,12 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __X32_COMPAT_SYS_NI(name) \ __SYS_NI(x64, compat_sys_##name) -#else /* CONFIG_X86_X32 */ +#else /* CONFIG_X86_X32_ABI */ #define __X32_COMPAT_SYS_STUB0(name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #define __X32_COMPAT_COND_SYSCALL(name) #define __X32_COMPAT_SYS_NI(name) -#endif /* CONFIG_X86_X32 */ +#endif /* CONFIG_X86_X32_ABI */ #ifdef CONFIG_COMPAT diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 4cc18ba1b75e..d20ab0921480 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -97,24 +97,40 @@ union text_poke_insn { }; static __always_inline -void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +void __text_gen_insn(void *buf, u8 opcode, const void *addr, const void *dest, int size) { - static union text_poke_insn insn; /* per instance */ - int size = text_opcode_size(opcode); + union text_poke_insn *insn = buf; + + BUG_ON(size < text_opcode_size(opcode)); + + /* + * Hide the addresses to avoid the compiler folding in constants when + * referencing code, these can mess up annotations like + * ANNOTATE_NOENDBR. + */ + OPTIMIZER_HIDE_VAR(insn); + OPTIMIZER_HIDE_VAR(addr); + OPTIMIZER_HIDE_VAR(dest); - insn.opcode = opcode; + insn->opcode = opcode; if (size > 1) { - insn.disp = (long)dest - (long)(addr + size); + insn->disp = (long)dest - (long)(addr + size); if (size == 2) { /* - * Ensure that for JMP9 the displacement + * Ensure that for JMP8 the displacement * actually fits the signed byte. */ - BUG_ON((insn.disp >> 31) != (insn.disp >> 7)); + BUG_ON((insn->disp >> 31) != (insn->disp >> 7)); } } +} +static __always_inline +void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +{ + static union text_poke_insn insn; /* per instance */ + __text_gen_insn(&insn, opcode, addr, dest, text_opcode_size(opcode)); return &insn.text; } diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 6221be7cafc3..35317c5c551d 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -18,6 +18,8 @@ void __init trap_init(void); asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif +extern bool ibt_selftest(void); + #ifdef CONFIG_X86_F00F_BUG /* For handling the FOOF bug */ void handle_invalid_op(struct pt_regs *regs); diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 2a1f8734416d..7cede4dc21f0 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -4,7 +4,7 @@ #include <linux/sched.h> #include <linux/ftrace.h> -#include <linux/kprobes.h> +#include <linux/rethook.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> @@ -16,7 +16,7 @@ struct unwind_state { unsigned long stack_mask; struct task_struct *task; int graph_idx; -#ifdef CONFIG_KRETPROBES +#if defined(CONFIG_RETHOOK) struct llist_node *kr_cur; #endif bool error; @@ -104,19 +104,18 @@ void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, #endif static inline -unsigned long unwind_recover_kretprobe(struct unwind_state *state, - unsigned long addr, unsigned long *addr_p) +unsigned long unwind_recover_rethook(struct unwind_state *state, + unsigned long addr, unsigned long *addr_p) { -#ifdef CONFIG_KRETPROBES - return is_kretprobe_trampoline(addr) ? - kretprobe_find_ret_addr(state->task, addr_p, &state->kr_cur) : - addr; -#else - return addr; +#ifdef CONFIG_RETHOOK + if (is_rethook_trampoline(addr)) + return rethook_find_ret_addr(state->task, (unsigned long)addr_p, + &state->kr_cur); #endif + return addr; } -/* Recover the return address modified by kretprobe and ftrace_graph. */ +/* Recover the return address modified by rethook and ftrace_graph. */ static inline unsigned long unwind_recover_ret_addr(struct unwind_state *state, unsigned long addr, unsigned long *addr_p) @@ -125,7 +124,7 @@ unsigned long unwind_recover_ret_addr(struct unwind_state *state, ret = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, addr_p); - return unwind_recover_kretprobe(state, ret, addr_p); + return unwind_recover_rethook(state, ret, addr_p); } /* diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 98aa103eb4ab..2963a2f5dbc4 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -37,7 +37,7 @@ struct vdso_image { extern const struct vdso_image vdso_image_64; #endif -#ifdef CONFIG_X86_X32 +#ifdef CONFIG_X86_X32_ABI extern const struct vdso_image vdso_image_x32; #endif diff --git a/arch/x86/include/uapi/asm/amd_hsmp.h b/arch/x86/include/uapi/asm/amd_hsmp.h new file mode 100644 index 000000000000..7ee7ba0d63a3 --- /dev/null +++ b/arch/x86/include/uapi/asm/amd_hsmp.h @@ -0,0 +1,203 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_ASM_X86_AMD_HSMP_H_ +#define _UAPI_ASM_X86_AMD_HSMP_H_ + +#include <linux/types.h> + +#pragma pack(4) + +#define HSMP_MAX_MSG_LEN 8 + +/* + * HSMP Messages supported + */ +enum hsmp_message_ids { + HSMP_TEST = 1, /* 01h Increments input value by 1 */ + HSMP_GET_SMU_VER, /* 02h SMU FW version */ + HSMP_GET_PROTO_VER, /* 03h HSMP interface version */ + HSMP_GET_SOCKET_POWER, /* 04h average package power consumption */ + HSMP_SET_SOCKET_POWER_LIMIT, /* 05h Set the socket power limit */ + HSMP_GET_SOCKET_POWER_LIMIT, /* 06h Get current socket power limit */ + HSMP_GET_SOCKET_POWER_LIMIT_MAX,/* 07h Get maximum socket power value */ + HSMP_SET_BOOST_LIMIT, /* 08h Set a core maximum frequency limit */ + HSMP_SET_BOOST_LIMIT_SOCKET, /* 09h Set socket maximum frequency level */ + HSMP_GET_BOOST_LIMIT, /* 0Ah Get current frequency limit */ + HSMP_GET_PROC_HOT, /* 0Bh Get PROCHOT status */ + HSMP_SET_XGMI_LINK_WIDTH, /* 0Ch Set max and min width of xGMI Link */ + HSMP_SET_DF_PSTATE, /* 0Dh Alter APEnable/Disable messages behavior */ + HSMP_SET_AUTO_DF_PSTATE, /* 0Eh Enable DF P-State Performance Boost algorithm */ + HSMP_GET_FCLK_MCLK, /* 0Fh Get FCLK and MEMCLK for current socket */ + HSMP_GET_CCLK_THROTTLE_LIMIT, /* 10h Get CCLK frequency limit in socket */ + HSMP_GET_C0_PERCENT, /* 11h Get average C0 residency in socket */ + HSMP_SET_NBIO_DPM_LEVEL, /* 12h Set max/min LCLK DPM Level for a given NBIO */ + /* 13h Reserved */ + HSMP_GET_DDR_BANDWIDTH = 0x14, /* 14h Get theoretical maximum and current DDR Bandwidth */ + HSMP_GET_TEMP_MONITOR, /* 15h Get per-DIMM temperature and refresh rates */ + HSMP_MSG_ID_MAX, +}; + +struct hsmp_message { + __u32 msg_id; /* Message ID */ + __u16 num_args; /* Number of input argument words in message */ + __u16 response_sz; /* Number of expected output/response words */ + __u32 args[HSMP_MAX_MSG_LEN]; /* argument/response buffer */ + __u16 sock_ind; /* socket number */ +}; + +enum hsmp_msg_type { + HSMP_RSVD = -1, + HSMP_SET = 0, + HSMP_GET = 1, +}; + +struct hsmp_msg_desc { + int num_args; + int response_sz; + enum hsmp_msg_type type; +}; + +/* + * User may use these comments as reference, please find the + * supported list of messages and message definition in the + * HSMP chapter of respective family/model PPR. + * + * Not supported messages would return -ENOMSG. + */ +static const struct hsmp_msg_desc hsmp_msg_desc_table[] = { + /* RESERVED */ + {0, 0, HSMP_RSVD}, + + /* + * HSMP_TEST, num_args = 1, response_sz = 1 + * input: args[0] = xx + * output: args[0] = xx + 1 + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_GET_SMU_VER, num_args = 0, response_sz = 1 + * output: args[0] = smu fw ver + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_PROTO_VER, num_args = 0, response_sz = 1 + * output: args[0] = proto version + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_SOCKET_POWER, num_args = 0, response_sz = 1 + * output: args[0] = socket power in mWatts + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_SET_SOCKET_POWER_LIMIT, num_args = 1, response_sz = 0 + * input: args[0] = power limit value in mWatts + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_GET_SOCKET_POWER_LIMIT, num_args = 0, response_sz = 1 + * output: args[0] = socket power limit value in mWatts + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_SOCKET_POWER_LIMIT_MAX, num_args = 0, response_sz = 1 + * output: args[0] = maximuam socket power limit in mWatts + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_SET_BOOST_LIMIT, num_args = 1, response_sz = 0 + * input: args[0] = apic id[31:16] + boost limit value in MHz[15:0] + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_SET_BOOST_LIMIT_SOCKET, num_args = 1, response_sz = 0 + * input: args[0] = boost limit value in MHz + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_GET_BOOST_LIMIT, num_args = 1, response_sz = 1 + * input: args[0] = apic id + * output: args[0] = boost limit value in MHz + */ + {1, 1, HSMP_GET}, + + /* + * HSMP_GET_PROC_HOT, num_args = 0, response_sz = 1 + * output: args[0] = proc hot status + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_SET_XGMI_LINK_WIDTH, num_args = 1, response_sz = 0 + * input: args[0] = min link width[15:8] + max link width[7:0] + */ + {1, 0, HSMP_SET}, + + /* + * HSMP_SET_DF_PSTATE, num_args = 1, response_sz = 0 + * input: args[0] = df pstate[7:0] + */ + {1, 0, HSMP_SET}, + + /* HSMP_SET_AUTO_DF_PSTATE, num_args = 0, response_sz = 0 */ + {0, 0, HSMP_SET}, + + /* + * HSMP_GET_FCLK_MCLK, num_args = 0, response_sz = 2 + * output: args[0] = fclk in MHz, args[1] = mclk in MHz + */ + {0, 2, HSMP_GET}, + + /* + * HSMP_GET_CCLK_THROTTLE_LIMIT, num_args = 0, response_sz = 1 + * output: args[0] = core clock in MHz + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_C0_PERCENT, num_args = 0, response_sz = 1 + * output: args[0] = average c0 residency + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_SET_NBIO_DPM_LEVEL, num_args = 1, response_sz = 0 + * input: args[0] = nbioid[23:16] + max dpm level[15:8] + min dpm level[7:0] + */ + {1, 0, HSMP_SET}, + + /* RESERVED message */ + {0, 0, HSMP_RSVD}, + + /* + * HSMP_GET_DDR_BANDWIDTH, num_args = 0, response_sz = 1 + * output: args[0] = max bw in Gbps[31:20] + utilised bw in Gbps[19:8] + + * bw in percentage[7:0] + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_TEMP_MONITOR, num_args = 0, response_sz = 1 + * output: args[0] = temperature in degree celsius. [15:8] integer part + + * [7:5] fractional part + */ + {0, 1, HSMP_GET}, +}; + +/* Reset to default packing */ +#pragma pack() + +/* Define unique ioctl command for hsmp msgs using generic _IOWR */ +#define HSMP_BASE_IOCTL_NR 0xF8 +#define HSMP_IOCTL_CMD _IOWR(HSMP_BASE_IOCTL_NR, 0, struct hsmp_message) + +#endif /*_ASM_X86_AMD_HSMP_H_*/ diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index bcba3c643e63..c47cc7f2feeb 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -130,6 +130,8 @@ #define X86_CR4_SMAP _BITUL(X86_CR4_SMAP_BIT) #define X86_CR4_PKE_BIT 22 /* enable Protection Keys support */ #define X86_CR4_PKE _BITUL(X86_CR4_PKE_BIT) +#define X86_CR4_CET_BIT 23 /* enable Control-flow Enforcement Technology */ +#define X86_CR4_CET _BITUL(X86_CR4_CET_BIT) /* * x86-64 Task Priority Register, CR8 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 6462e3dd98f4..c41ef42adbe8 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -103,6 +103,7 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_TRACING) += trace.o +obj-$(CONFIG_RETHOOK) += rethook.o obj-$(CONFIG_CRASH_CORE) += crash_core_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b4e576600969..d374cb3cf024 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -115,6 +115,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) } extern s32 __retpoline_sites[], __retpoline_sites_end[]; +extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); @@ -512,6 +513,42 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } #endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */ +#ifdef CONFIG_X86_KERNEL_IBT + +/* + * Generated by: objtool --ibt + */ +void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + u32 endbr, poison = gen_endbr_poison(); + void *addr = (void *)s + *s; + + if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr))) + continue; + + if (WARN_ON_ONCE(!is_endbr(endbr))) + continue; + + DPRINTK("ENDBR at: %pS (%px)", addr, addr); + + /* + * When we have IBT, the lack of ENDBR will trigger #CP + */ + DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr); + DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr); + text_poke_early(addr, &poison, 4); + } +} + +#else + +void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) { } + +#endif /* CONFIG_X86_KERNEL_IBT */ + #ifdef CONFIG_SMP static void alternatives_smp_lock(const s32 *start, const s32 *end, u8 *text, u8 *text_end) @@ -713,34 +750,39 @@ asm ( " .pushsection .init.text, \"ax\", @progbits\n" " .type int3_magic, @function\n" "int3_magic:\n" + ANNOTATE_NOENDBR " movl $1, (%" _ASM_ARG1 ")\n" ASM_RET " .size int3_magic, .-int3_magic\n" " .popsection\n" ); -extern __initdata unsigned long int3_selftest_ip; /* defined in asm below */ +extern void int3_selftest_ip(void); /* defined in asm below */ static int __init int3_exception_notify(struct notifier_block *self, unsigned long val, void *data) { + unsigned long selftest = (unsigned long)&int3_selftest_ip; struct die_args *args = data; struct pt_regs *regs = args->regs; + OPTIMIZER_HIDE_VAR(selftest); + if (!regs || user_mode(regs)) return NOTIFY_DONE; if (val != DIE_INT3) return NOTIFY_DONE; - if (regs->ip - INT3_INSN_SIZE != int3_selftest_ip) + if (regs->ip - INT3_INSN_SIZE != selftest) return NOTIFY_DONE; int3_emulate_call(regs, (unsigned long)&int3_magic); return NOTIFY_STOP; } -static void __init int3_selftest(void) +/* Must be noinline to ensure uniqueness of int3_selftest_ip. */ +static noinline void __init int3_selftest(void) { static __initdata struct notifier_block int3_exception_nb = { .notifier_call = int3_exception_notify, @@ -753,18 +795,12 @@ static void __init int3_selftest(void) /* * Basically: int3_magic(&val); but really complicated :-) * - * Stick the address of the INT3 instruction into int3_selftest_ip, - * then trigger the INT3, padded with NOPs to match a CALL instruction - * length. + * INT3 padded with NOP to CALL_INSN_SIZE. The int3_exception_nb + * notifier above will emulate CALL for us. */ - asm volatile ("1: int3; nop; nop; nop; nop\n\t" - ".pushsection .init.data,\"aw\"\n\t" - ".align " __ASM_SEL(4, 8) "\n\t" - ".type int3_selftest_ip, @object\n\t" - ".size int3_selftest_ip, " __ASM_SEL(4, 8) "\n\t" - "int3_selftest_ip:\n\t" - __ASM_SEL(.long, .quad) " 1b\n\t" - ".popsection\n\t" + asm volatile ("int3_selftest_ip:\n\t" + ANNOTATE_NOENDBR + " int3; nop; nop; nop; nop\n\t" : ASM_CALL_CONSTRAINT : __ASM_SEL_RAW(a, D) (&val) : "memory"); @@ -831,6 +867,8 @@ void __init alternative_instructions(void) */ apply_alternatives(__alt_instructions, __alt_instructions_end); + apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 241dda687eb9..60e330cdbd17 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -232,6 +232,7 @@ #include <asm/paravirt.h> #include <asm/reboot.h> #include <asm/nospec-branch.h> +#include <asm/ibt.h> #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) extern int (*console_blank_hook)(int); @@ -598,6 +599,7 @@ static long __apm_bios_call(void *_call) struct desc_struct save_desc_40; struct desc_struct *gdt; struct apm_bios_call *call = _call; + u64 ibt; cpu = get_cpu(); BUG_ON(cpu != 0); @@ -607,11 +609,13 @@ static long __apm_bios_call(void *_call) apm_irq_save(flags); firmware_restrict_branch_speculation_start(); + ibt = ibt_save(); APM_DO_SAVE_SEGS; apm_bios_call_asm(call->func, call->ebx, call->ecx, &call->eax, &call->ebx, &call->ecx, &call->edx, &call->esi); APM_DO_RESTORE_SEGS; + ibt_restore(ibt); firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; @@ -676,6 +680,7 @@ static long __apm_bios_call_simple(void *_call) struct desc_struct save_desc_40; struct desc_struct *gdt; struct apm_bios_call *call = _call; + u64 ibt; cpu = get_cpu(); BUG_ON(cpu != 0); @@ -685,10 +690,12 @@ static long __apm_bios_call_simple(void *_call) apm_irq_save(flags); firmware_restrict_branch_speculation_start(); + ibt = ibt_save(); APM_DO_SAVE_SEGS; error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, &call->eax); APM_DO_RESTORE_SEGS; + ibt_restore(ibt); firmware_restrict_branch_speculation_end(); apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 64deb7727d00..ed4417500700 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -59,6 +59,7 @@ #include <asm/cpu_device_id.h> #include <asm/uv/uv.h> #include <asm/sigframe.h> +#include <asm/traps.h> #include "cpu.h" @@ -438,7 +439,8 @@ out: /* These bits should not change their value after CPU init is finished. */ static const unsigned long cr4_pinned_mask = - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE; + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | + X86_CR4_FSGSBASE | X86_CR4_CET; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -592,6 +594,58 @@ static __init int setup_disable_pku(char *arg) __setup("nopku", setup_disable_pku); #endif /* CONFIG_X86_64 */ +#ifdef CONFIG_X86_KERNEL_IBT + +__noendbr u64 ibt_save(void) +{ + u64 msr = 0; + + if (cpu_feature_enabled(X86_FEATURE_IBT)) { + rdmsrl(MSR_IA32_S_CET, msr); + wrmsrl(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN); + } + + return msr; +} + +__noendbr void ibt_restore(u64 save) +{ + u64 msr; + + if (cpu_feature_enabled(X86_FEATURE_IBT)) { + rdmsrl(MSR_IA32_S_CET, msr); + msr &= ~CET_ENDBR_EN; + msr |= (save & CET_ENDBR_EN); + wrmsrl(MSR_IA32_S_CET, msr); + } +} + +#endif + +static __always_inline void setup_cet(struct cpuinfo_x86 *c) +{ + u64 msr = CET_ENDBR_EN; + + if (!HAS_KERNEL_IBT || + !cpu_feature_enabled(X86_FEATURE_IBT)) + return; + + wrmsrl(MSR_IA32_S_CET, msr); + cr4_set_bits(X86_CR4_CET); + + if (!ibt_selftest()) { + pr_err("IBT selftest: Failed!\n"); + setup_clear_cpu_cap(X86_FEATURE_IBT); + return; + } +} + +__noendbr void cet_disable(void) +{ + if (cpu_feature_enabled(X86_FEATURE_IBT)) + wrmsrl(MSR_IA32_S_CET, 0); +} + /* * Some CPU features depend on higher CPUID levels, which may not always * be available due to CPUID level capping or broken virtualization @@ -1709,6 +1763,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) x86_init_rdrand(c); setup_pku(c); + setup_cet(c); /* * Clear/Set all flags overridden by options, need do it @@ -1777,6 +1832,8 @@ void enable_sep_cpu(void) void __init identify_boot_cpu(void) { identify_cpu(&boot_cpu_data); + if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) + pr_info("CET detected: Indirect Branch Tracking enabled\n"); #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index e53d3e6096fb..981496e6bc0e 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -86,14 +86,6 @@ struct mce_vendor_flags mce_flags __read_mostly; struct mca_config mca_cfg __read_mostly = { .bootlog = -1, - /* - * Tolerant levels: - * 0: always panic on uncorrected errors, log corrected errors - * 1: panic or SIGBUS on uncorrected errors, log corrected errors - * 2: SIGBUS or log uncorrected errors (if possible), log corr. errors - * 3: never panic or SIGBUS, log all errors (for testing only) - */ - .tolerant = 1, .monarch_timeout = -1 }; @@ -168,27 +160,6 @@ void mce_unregister_decode_chain(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); -u32 mca_msr_reg(int bank, enum mca_msr reg) -{ - if (mce_flags.smca) { - switch (reg) { - case MCA_CTL: return MSR_AMD64_SMCA_MCx_CTL(bank); - case MCA_ADDR: return MSR_AMD64_SMCA_MCx_ADDR(bank); - case MCA_MISC: return MSR_AMD64_SMCA_MCx_MISC(bank); - case MCA_STATUS: return MSR_AMD64_SMCA_MCx_STATUS(bank); - } - } - - switch (reg) { - case MCA_CTL: return MSR_IA32_MCx_CTL(bank); - case MCA_ADDR: return MSR_IA32_MCx_ADDR(bank); - case MCA_MISC: return MSR_IA32_MCx_MISC(bank); - case MCA_STATUS: return MSR_IA32_MCx_STATUS(bank); - } - - return 0; -} - static void __print_mce(struct mce *m) { pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n", @@ -769,7 +740,7 @@ log_it: goto clear_it; mce_read_aux(&m, i); - m.severity = mce_severity(&m, NULL, mca_cfg.tolerant, NULL, false); + m.severity = mce_severity(&m, NULL, NULL, false); /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. @@ -809,7 +780,8 @@ EXPORT_SYMBOL_GPL(machine_check_poll); * the severity assessment code. Pretend that EIPV was set, and take the * ip/cs values from the pt_regs that mce_gather_info() ignored earlier. */ -static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) +static __always_inline void +quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) { if (bank != 0) return; @@ -830,11 +802,64 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) } /* + * Disable fast string copy and return from the MCE handler upon the first SRAR + * MCE on bank 1 due to a CPU erratum on Intel Skylake/Cascade Lake/Cooper Lake + * CPUs. + * The fast string copy instructions ("REP; MOVS*") could consume an + * uncorrectable memory error in the cache line _right after_ the desired region + * to copy and raise an MCE with RIP pointing to the instruction _after_ the + * "REP; MOVS*". + * This mitigation addresses the issue completely with the caveat of performance + * degradation on the CPU affected. This is still better than the OS crashing on + * MCEs raised on an irrelevant process due to "REP; MOVS*" accesses from a + * kernel context (e.g., copy_page). + * + * Returns true when fast string copy on CPU has been disabled. + */ +static noinstr bool quirk_skylake_repmov(void) +{ + u64 mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + u64 misc_enable = mce_rdmsrl(MSR_IA32_MISC_ENABLE); + u64 mc1_status; + + /* + * Apply the quirk only to local machine checks, i.e., no broadcast + * sync is needed. + */ + if (!(mcgstatus & MCG_STATUS_LMCES) || + !(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) + return false; + + mc1_status = mce_rdmsrl(MSR_IA32_MCx_STATUS(1)); + + /* Check for a software-recoverable data fetch error. */ + if ((mc1_status & + (MCI_STATUS_VAL | MCI_STATUS_OVER | MCI_STATUS_UC | MCI_STATUS_EN | + MCI_STATUS_ADDRV | MCI_STATUS_MISCV | MCI_STATUS_PCC | + MCI_STATUS_AR | MCI_STATUS_S)) == + (MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN | + MCI_STATUS_ADDRV | MCI_STATUS_MISCV | + MCI_STATUS_AR | MCI_STATUS_S)) { + misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING; + mce_wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); + mce_wrmsrl(MSR_IA32_MCx_STATUS(1), 0); + + instrumentation_begin(); + pr_err_once("Erratum detected, disable fast string copy instructions.\n"); + instrumentation_end(); + + return true; + } + + return false; +} + +/* * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. */ -static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, - struct pt_regs *regs) +static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, + struct pt_regs *regs) { char *tmp = *msg; int i; @@ -844,12 +869,12 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (!(m->status & MCI_STATUS_VAL)) continue; - __set_bit(i, validp); + arch___set_bit(i, validp); if (mce_flags.snb_ifu_quirk) quirk_sandybridge_ifu(i, m, regs); m->bank = i; - if (mce_severity(m, regs, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) { mce_read_aux(m, i); *msg = tmp; return 1; @@ -897,12 +922,11 @@ static noinstr int mce_timed_out(u64 *t, const char *msg) if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { - if (mca_cfg.tolerant <= 1) { - if (cpumask_and(&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) - pr_emerg("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n", - cpumask_pr_args(&mce_missing_cpus)); - mce_panic(msg, NULL, NULL); - } + if (cpumask_and(&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) + pr_emerg("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n", + cpumask_pr_args(&mce_missing_cpus)); + mce_panic(msg, NULL, NULL); + ret = 1; goto out; } @@ -966,9 +990,9 @@ static void mce_reign(void) * This dumps all the mces in the log buffer and stops the * other CPUs. */ - if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { + if (m && global_worst >= MCE_PANIC_SEVERITY) { /* call mce_severity() to get "msg" for panic */ - mce_severity(m, NULL, mca_cfg.tolerant, &msg, true); + mce_severity(m, NULL, &msg, true); mce_panic("Fatal machine check", m, msg); } @@ -982,7 +1006,7 @@ static void mce_reign(void) * No machine check event found. Must be some external * source or one CPU is hung. Panic. */ - if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3) + if (global_worst <= MCE_KEEP_SEVERITY) mce_panic("Fatal machine check from unknown source", NULL, NULL); /* @@ -1010,13 +1034,13 @@ static noinstr int mce_start(int *no_way_out) if (!timeout) return ret; - atomic_add(*no_way_out, &global_nwo); + arch_atomic_add(*no_way_out, &global_nwo); /* * Rely on the implied barrier below, such that global_nwo * is updated before mce_callin. */ - order = atomic_inc_return(&mce_callin); - cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); + order = arch_atomic_inc_return(&mce_callin); + arch_cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); /* Enable instrumentation around calls to external facilities */ instrumentation_begin(); @@ -1024,10 +1048,10 @@ static noinstr int mce_start(int *no_way_out) /* * Wait for everyone. */ - while (atomic_read(&mce_callin) != num_online_cpus()) { + while (arch_atomic_read(&mce_callin) != num_online_cpus()) { if (mce_timed_out(&timeout, "Timeout: Not all CPUs entered broadcast exception handler")) { - atomic_set(&global_nwo, 0); + arch_atomic_set(&global_nwo, 0); goto out; } ndelay(SPINUNIT); @@ -1042,7 +1066,7 @@ static noinstr int mce_start(int *no_way_out) /* * Monarch: Starts executing now, the others wait. */ - atomic_set(&mce_executing, 1); + arch_atomic_set(&mce_executing, 1); } else { /* * Subject: Now start the scanning loop one by one in @@ -1050,10 +1074,10 @@ static noinstr int mce_start(int *no_way_out) * This way when there are any shared banks it will be * only seen by one CPU before cleared, avoiding duplicates. */ - while (atomic_read(&mce_executing) < order) { + while (arch_atomic_read(&mce_executing) < order) { if (mce_timed_out(&timeout, "Timeout: Subject CPUs unable to finish machine check processing")) { - atomic_set(&global_nwo, 0); + arch_atomic_set(&global_nwo, 0); goto out; } ndelay(SPINUNIT); @@ -1063,7 +1087,7 @@ static noinstr int mce_start(int *no_way_out) /* * Cache the global no_way_out state. */ - *no_way_out = atomic_read(&global_nwo); + *no_way_out = arch_atomic_read(&global_nwo); ret = order; @@ -1148,12 +1172,12 @@ out: return ret; } -static void mce_clear_state(unsigned long *toclear) +static __always_inline void mce_clear_state(unsigned long *toclear) { int i; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { - if (test_bit(i, toclear)) + if (arch_test_bit(i, toclear)) mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); } } @@ -1203,8 +1227,8 @@ __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, int severity, i, taint = 0; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { - __clear_bit(i, toclear); - if (!test_bit(i, valid_banks)) + arch___clear_bit(i, toclear); + if (!arch_test_bit(i, valid_banks)) continue; if (!mce_banks[i].ctl) @@ -1229,7 +1253,7 @@ __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, /* Set taint even when machine check was not enabled. */ taint++; - severity = mce_severity(m, regs, cfg->tolerant, NULL, true); + severity = mce_severity(m, regs, NULL, true); /* * When machine check was for corrected/deferred handler don't @@ -1239,7 +1263,7 @@ __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, severity == MCE_UCNA_SEVERITY) && !no_way_out) continue; - __set_bit(i, toclear); + arch___set_bit(i, toclear); /* Machine check event was not enabled. Clear, but ignore. */ if (severity == MCE_NO_SEVERITY) @@ -1389,7 +1413,6 @@ noinstr void do_machine_check(struct pt_regs *regs) int worst = 0, order, no_way_out, kill_current_task, lmce, taint = 0; DECLARE_BITMAP(valid_banks, MAX_NR_BANKS) = { 0 }; DECLARE_BITMAP(toclear, MAX_NR_BANKS) = { 0 }; - struct mca_config *cfg = &mca_cfg; struct mce m, *final; char *msg = NULL; @@ -1400,6 +1423,9 @@ noinstr void do_machine_check(struct pt_regs *regs) else if (unlikely(!mca_cfg.initialized)) return unexpected_machine_check(regs); + if (mce_flags.skx_repmov_quirk && quirk_skylake_repmov()) + goto clear; + /* * Establish sequential order between the CPUs entering the machine * check handler. @@ -1408,7 +1434,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* * If no_way_out gets set, there is no safe way to recover from this - * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. + * MCE. */ no_way_out = 0; @@ -1442,7 +1468,7 @@ noinstr void do_machine_check(struct pt_regs *regs) * severity is MCE_AR_SEVERITY we have other options. */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) - kill_current_task = (cfg->tolerant == 3) ? 0 : 1; + kill_current_task = 1; /* * Check if this MCE is signaled to only this logical processor, * on Intel, Zhaoxin only. @@ -1459,7 +1485,7 @@ noinstr void do_machine_check(struct pt_regs *regs) * to see it will clear it. */ if (lmce) { - if (no_way_out && cfg->tolerant < 3) + if (no_way_out) mce_panic("Fatal local machine check", &m, msg); } else { order = mce_start(&no_way_out); @@ -1479,7 +1505,7 @@ noinstr void do_machine_check(struct pt_regs *regs) if (!no_way_out) no_way_out = worst >= MCE_PANIC_SEVERITY; - if (no_way_out && cfg->tolerant < 3) + if (no_way_out) mce_panic("Fatal machine check on current CPU", &m, msg); } } else { @@ -1491,8 +1517,8 @@ noinstr void do_machine_check(struct pt_regs *regs) * fatal error. We call "mce_severity()" again to * make sure we have the right "msg". */ - if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { - mce_severity(&m, regs, cfg->tolerant, &msg, true); + if (worst >= MCE_PANIC_SEVERITY) { + mce_severity(&m, regs, &msg, true); mce_panic("Local fatal machine check!", &m, msg); } } @@ -1542,6 +1568,7 @@ noinstr void do_machine_check(struct pt_regs *regs) out: instrumentation_end(); +clear: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -1855,6 +1882,13 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model == 45) mce_flags.snb_ifu_quirk = 1; + + /* + * Skylake, Cascacde Lake and Cooper Lake require a quirk on + * rep movs. + */ + if (c->x86 == 6 && c->x86_model == INTEL_FAM6_SKYLAKE_X) + mce_flags.skx_repmov_quirk = 1; } if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { @@ -2220,10 +2254,9 @@ static int __init mcheck_enable(char *str) cfg->bios_cmci_threshold = 1; else if (!strcmp(str, "recovery")) cfg->recovery = 1; - else if (isdigit(str[0])) { - if (get_option(&str, &cfg->tolerant) == 2) - get_option(&str, &(cfg->monarch_timeout)); - } else { + else if (isdigit(str[0])) + get_option(&str, &(cfg->monarch_timeout)); + else { pr_info("mce argument %s ignored. Please use /sys\n", str); return 0; } @@ -2473,7 +2506,6 @@ static ssize_t store_int_with_restart(struct device *s, return ret; } -static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); static DEVICE_BOOL_ATTR(print_all, 0644, mca_cfg.print_all); @@ -2494,7 +2526,6 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = { }; static struct device_attribute *mce_device_attrs[] = { - &dev_attr_tolerant.attr, &dev_attr_check_interval.attr, #ifdef CONFIG_X86_MCELOG_LEGACY &dev_attr_trigger, diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 52c633950b38..4ae0e603f7fa 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -35,7 +35,7 @@ int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); struct llist_node *mce_gen_pool_prepare_records(void); -int mce_severity(struct mce *a, struct pt_regs *regs, int tolerant, char **msg, bool is_excp); +int mce_severity(struct mce *a, struct pt_regs *regs, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern mce_banks_t mce_banks_ce_disabled; @@ -127,7 +127,6 @@ struct mca_config { bool ignore_ce; bool print_all; - int tolerant; int monarch_timeout; int panic_timeout; u32 rip_msr; @@ -170,7 +169,10 @@ struct mce_vendor_flags { /* SandyBridge IFU quirk */ snb_ifu_quirk : 1, - __reserved_0 : 57; + /* Skylake, Cascade Lake, Cooper Lake REP;MOVS* quirk */ + skx_repmov_quirk : 1, + + __reserved_0 : 56; }; extern struct mce_vendor_flags mce_flags; @@ -182,8 +184,6 @@ enum mca_msr { MCA_MISC, }; -u32 mca_msr_reg(int bank, enum mca_msr reg); - /* Decide whether to add MCE record to MCE event pool or filter it out. */ extern bool filter_mce(struct mce *m); @@ -209,4 +209,25 @@ static inline void winchip_machine_check(struct pt_regs *regs) {} noinstr u64 mce_rdmsrl(u32 msr); +static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg) +{ + if (mce_flags.smca) { + switch (reg) { + case MCA_CTL: return MSR_AMD64_SMCA_MCx_CTL(bank); + case MCA_ADDR: return MSR_AMD64_SMCA_MCx_ADDR(bank); + case MCA_MISC: return MSR_AMD64_SMCA_MCx_MISC(bank); + case MCA_STATUS: return MSR_AMD64_SMCA_MCx_STATUS(bank); + } + } + + switch (reg) { + case MCA_CTL: return MSR_IA32_MCx_CTL(bank); + case MCA_ADDR: return MSR_IA32_MCx_ADDR(bank); + case MCA_MISC: return MSR_IA32_MCx_MISC(bank); + case MCA_STATUS: return MSR_IA32_MCx_STATUS(bank); + } + + return 0; +} + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 7aa2bda93cbb..1add86935349 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -301,7 +301,7 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) } } -static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) +static __always_inline int mce_severity_amd_smca(struct mce *m, enum context err_ctx) { u64 mcx_cfg; @@ -330,8 +330,7 @@ static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) * See AMD Error Scope Hierarchy table in a newer BKDG. For example * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" */ -static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant, - char **msg, bool is_excp) +static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { enum context ctx = error_context(m, regs); @@ -383,8 +382,7 @@ static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tol return MCE_KEEP_SEVERITY; } -static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, - int tolerant, char **msg, bool is_excp) +static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m, regs); @@ -412,22 +410,21 @@ static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, if (msg) *msg = s->msg; s->covered = 1; - if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) { - if (tolerant < 1) - return MCE_PANIC_SEVERITY; - } + + if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) + return MCE_PANIC_SEVERITY; + return s->sev; } } -int noinstr mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, - bool is_excp) +int noinstr mce_severity(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) { if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - return mce_severity_amd(m, regs, tolerant, msg, is_excp); + return mce_severity_amd(m, regs, msg, is_excp); else - return mce_severity_intel(m, regs, tolerant, msg, is_excp); + return mce_severity_intel(m, regs, msg, is_excp); } #ifdef CONFIG_DEBUG_FS diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index b57b3db9a6a7..83f901e2c2df 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3221,13 +3221,13 @@ static int __init rdtgroup_setup_root(void) list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - ret = rdtgroup_add_files(rdt_root->kn, RF_CTRL_BASE); + ret = rdtgroup_add_files(kernfs_root_to_node(rdt_root), RF_CTRL_BASE); if (ret) { kernfs_destroy_root(rdt_root); goto out; } - rdtgroup_default.kn = rdt_root->kn; + rdtgroup_default.kn = kernfs_root_to_node(rdt_root); kernfs_activate(rdtgroup_default.kn); out: diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index d3c531d3b244..68b38925a74f 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -387,7 +387,7 @@ static int __init setup_early_printk(char *buf) #endif #ifdef CONFIG_EARLY_PRINTK_USB_XDBC if (!strncmp(buf, "xdbc", 4)) - early_xdbc_parse_parameter(buf + 4); + early_xdbc_parse_parameter(buf + 4, keep); #endif buf++; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 7cc540e6de0c..1e31c7d21597 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -316,12 +316,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned long offset; unsigned long npages; unsigned long size; - unsigned long retq; unsigned long *ptr; void *trampoline; void *ip; /* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */ unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 }; + unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE }; union ftrace_op_code_union op_ptr; int ret; @@ -359,12 +359,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - - /* The trampoline ends with ret(q) */ - retq = (unsigned long)ftrace_stub; - ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); - if (WARN_ON(ret < 0)) - goto fail; + memcpy(ip, retq, RET_SIZE); /* No need to test direct calls on created trampolines */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 11ac028e30e4..4ec13608d3c6 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -145,6 +145,7 @@ SYM_FUNC_START(ftrace_caller) movq %rcx, RSP(%rsp) SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL) + ANNOTATE_NOENDBR /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx @@ -155,6 +156,7 @@ SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL) movq $0, CS(%rsp) SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) + ANNOTATE_NOENDBR call ftrace_stub /* Handlers can change the RIP */ @@ -169,6 +171,7 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) * layout here. */ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR jmp ftrace_epilogue SYM_FUNC_END(ftrace_caller); @@ -176,10 +179,10 @@ SYM_FUNC_END(ftrace_caller); SYM_FUNC_START(ftrace_epilogue) /* * This is weak to keep gas from relaxing the jumps. - * It is also used to copy the RET for trampolines. */ SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) UNWIND_HINT_FUNC + ENDBR RET SYM_FUNC_END(ftrace_epilogue) @@ -192,6 +195,7 @@ SYM_FUNC_START(ftrace_regs_caller) /* save_mcount_regs fills in first two parameters */ SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL) + ANNOTATE_NOENDBR /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx @@ -221,6 +225,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL) leaq (%rsp), %rcx SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) + ANNOTATE_NOENDBR call ftrace_stub /* Copy flags back to SS, to restore them */ @@ -248,6 +253,7 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) */ testq %rax, %rax SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL) + ANNOTATE_NOENDBR jnz 1f restore_mcount_regs @@ -261,6 +267,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL) * to the return. */ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR jmp ftrace_epilogue /* Swap the flags with orig_rax */ @@ -284,6 +291,7 @@ SYM_FUNC_START(__fentry__) jnz trace SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) + ENDBR RET trace: @@ -307,7 +315,7 @@ EXPORT_SYMBOL(__fentry__) #ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_FUNC_START(return_to_handler) - subq $24, %rsp + subq $16, %rsp /* Save the return values */ movq %rax, (%rsp) @@ -319,7 +327,19 @@ SYM_FUNC_START(return_to_handler) movq %rax, %rdi movq 8(%rsp), %rdx movq (%rsp), %rax - addq $24, %rsp - JMP_NOSPEC rdi + + addq $16, %rsp + /* + * Jump back to the old return address. This cannot be JMP_NOSPEC rdi + * since IBT would demand that contain ENDBR, which simply isn't so for + * return addresses. Use a retpoline here to keep the RSB balanced. + */ + ANNOTATE_INTRA_FUNCTION_CALL + call .Ldo_rop + int3 +.Ldo_rop: + mov %rdi, (%rsp) + UNWIND_HINT_FUNC + RET SYM_FUNC_END(return_to_handler) #endif diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 9c63fc5988cd..b8e3019547a5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -99,6 +99,7 @@ SYM_CODE_END(startup_64) SYM_CODE_START(secondary_startup_64) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. @@ -127,6 +128,7 @@ SYM_CODE_START(secondary_startup_64) */ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR /* * Retrieve the modifier (SME encryption mask if SME is active) to be @@ -192,6 +194,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) jmp *%rax 1: UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR // above /* * We must switch to a new descriptor in kernel space for the GDT @@ -299,6 +302,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) pushq %rax # target address in negative space lretq .Lafter_lret: + ANNOTATE_NOENDBR SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" @@ -328,6 +332,7 @@ SYM_CODE_END(start_cpu0) */ SYM_CODE_START_NOALIGN(vc_boot_ghcb) UNWIND_HINT_IRET_REGS offset=8 + ENDBR /* Build pt_regs */ PUSH_AND_CLEAR_REGS @@ -345,7 +350,6 @@ SYM_CODE_START_NOALIGN(vc_boot_ghcb) /* Remove Error Code */ addq $8, %rsp - /* Pure iret required here - don't use INTERRUPT_RETURN */ iretq SYM_CODE_END(vc_boot_ghcb) #endif @@ -372,9 +376,11 @@ SYM_CODE_START(early_idt_handler_array) .rept NUM_EXCEPTION_VECTORS .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 UNWIND_HINT_IRET_REGS + ENDBR pushq $0 # Dummy error code, to make stack frame uniform .else UNWIND_HINT_IRET_REGS offset=8 + ENDBR .endif pushq $i # 72(%rsp) Vector number jmp early_idt_handler_common @@ -382,10 +388,11 @@ SYM_CODE_START(early_idt_handler_array) i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr - UNWIND_HINT_IRET_REGS offset=16 SYM_CODE_END(early_idt_handler_array) + ANNOTATE_NOENDBR // early_idt_handler_array[NUM_EXCEPTION_VECTORS] SYM_CODE_START_LOCAL(early_idt_handler_common) + UNWIND_HINT_IRET_REGS offset=16 /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -426,11 +433,14 @@ SYM_CODE_END(early_idt_handler_common) * early_idt_handler_array can't be used because it returns via the * paravirtualized INTERRUPT_RETURN and pv-ops don't work that early. * + * XXX it does, fix this. + * * This handler will end up in the .init.text section and not be * available to boot secondary CPUs. */ SYM_CODE_START_NOALIGN(vc_no_ghcb) UNWIND_HINT_IRET_REGS offset=8 + ENDBR /* Build pt_regs */ PUSH_AND_CLEAR_REGS diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index df0fa695bb09..608eb63bf044 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -10,6 +10,7 @@ #include <asm/proto.h> #include <asm/desc.h> #include <asm/hw_irq.h> +#include <asm/idtentry.h> #define DPL0 0x0 #define DPL3 0x3 @@ -103,6 +104,10 @@ static const __initconst struct idt_data def_idts[] = { ISTG(X86_TRAP_MC, asm_exc_machine_check, IST_INDEX_MCE), #endif +#ifdef CONFIG_X86_KERNEL_IBT + INTG(X86_TRAP_CP, asm_exc_control_protection), +#endif + #ifdef CONFIG_AMD_MEM_ENCRYPT ISTG(X86_TRAP_VC, asm_exc_vmm_communication, IST_INDEX_VC), #endif @@ -272,7 +277,7 @@ void __init idt_setup_apic_and_irq_gates(void) idt_setup_from_table(idt_table, apic_idts, ARRAY_SIZE(apic_idts), true); for_each_clear_bit_from(i, system_vectors, FIRST_SYSTEM_VECTOR) { - entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); + entry = irq_entries_start + IDT_ALIGN * (i - FIRST_EXTERNAL_VECTOR); set_intr_gate(i, entry); } @@ -283,7 +288,7 @@ void __init idt_setup_apic_and_irq_gates(void) * system_vectors bitmap. Otherwise they show up in * /proc/interrupts. */ - entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR); + entry = spurious_entries_start + IDT_ALIGN * (i - FIRST_SYSTEM_VECTOR); set_intr_gate(i, entry); } #endif diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index 7d3a2e2daf01..c993521d4933 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -6,6 +6,7 @@ #include <asm/asm.h> #include <asm/frame.h> +#include <asm/insn.h> #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6290712cb36d..7c4ab8870da4 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -52,6 +52,7 @@ #include <asm/insn.h> #include <asm/debugreg.h> #include <asm/set_memory.h> +#include <asm/ibt.h> #include "common.h" @@ -193,17 +194,10 @@ static unsigned long __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) { struct kprobe *kp; - unsigned long faddr; + bool faddr; kp = get_kprobe((void *)addr); - faddr = ftrace_location(addr); - /* - * Addresses inside the ftrace location are refused by - * arch_check_ftrace_location(). Something went terribly wrong - * if such an address is checked here. - */ - if (WARN_ON(faddr && faddr != addr)) - return 0UL; + faddr = ftrace_location(addr) == addr; /* * Use the current code if it is not modified by Kprobe * and it cannot be modified by ftrace. @@ -301,6 +295,22 @@ static int can_probe(unsigned long paddr) return (addr == paddr); } +/* If x86 supports IBT (ENDBR) it must be skipped. */ +kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, + bool *on_func_entry) +{ + if (is_endbr(*(u32 *)addr)) { + *on_func_entry = !offset || offset == 4; + if (*on_func_entry) + offset = 4; + + } else { + *on_func_entry = !offset; + } + + return (kprobe_opcode_t *)(addr + offset); +} + /* * Copy an instruction with recovering modified instruction by kprobes * and adjust the displacement if the instruction uses the %rip-relative @@ -801,18 +811,6 @@ set_current_kprobe(struct kprobe *p, struct pt_regs *regs, = (regs->flags & X86_EFLAGS_IF); } -void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) -{ - unsigned long *sara = stack_addr(regs); - - ri->ret_addr = (kprobe_opcode_t *) *sara; - ri->fp = sara; - - /* Replace the return addr with trampoline addr */ - *sara = (unsigned long) &__kretprobe_trampoline; -} -NOKPROBE_SYMBOL(arch_prepare_kretprobe); - static void kprobe_post_process(struct kprobe *cur, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { @@ -1013,100 +1011,6 @@ int kprobe_int3_handler(struct pt_regs *regs) } NOKPROBE_SYMBOL(kprobe_int3_handler); -/* - * When a retprobed function returns, this code saves registers and - * calls trampoline_handler() runs, which calls the kretprobe's handler. - */ -asm( - ".text\n" - ".global __kretprobe_trampoline\n" - ".type __kretprobe_trampoline, @function\n" - "__kretprobe_trampoline:\n" -#ifdef CONFIG_X86_64 - /* Push a fake return address to tell the unwinder it's a kretprobe. */ - " pushq $__kretprobe_trampoline\n" - UNWIND_HINT_FUNC - /* Save the 'sp - 8', this will be fixed later. */ - " pushq %rsp\n" - " pushfq\n" - SAVE_REGS_STRING - " movq %rsp, %rdi\n" - " call trampoline_handler\n" - RESTORE_REGS_STRING - /* In trampoline_handler(), 'regs->flags' is copied to 'regs->sp'. */ - " addq $8, %rsp\n" - " popfq\n" -#else - /* Push a fake return address to tell the unwinder it's a kretprobe. */ - " pushl $__kretprobe_trampoline\n" - UNWIND_HINT_FUNC - /* Save the 'sp - 4', this will be fixed later. */ - " pushl %esp\n" - " pushfl\n" - SAVE_REGS_STRING - " movl %esp, %eax\n" - " call trampoline_handler\n" - RESTORE_REGS_STRING - /* In trampoline_handler(), 'regs->flags' is copied to 'regs->sp'. */ - " addl $4, %esp\n" - " popfl\n" -#endif - ASM_RET - ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n" -); -NOKPROBE_SYMBOL(__kretprobe_trampoline); -/* - * __kretprobe_trampoline() skips updating frame pointer. The frame pointer - * saved in trampoline_handler() points to the real caller function's - * frame pointer. Thus the __kretprobe_trampoline() doesn't have a - * standard stack frame with CONFIG_FRAME_POINTER=y. - * Let's mark it non-standard function. Anyway, FP unwinder can correctly - * unwind without the hint. - */ -STACK_FRAME_NON_STANDARD_FP(__kretprobe_trampoline); - -/* This is called from kretprobe_trampoline_handler(). */ -void arch_kretprobe_fixup_return(struct pt_regs *regs, - kprobe_opcode_t *correct_ret_addr) -{ - unsigned long *frame_pointer = ®s->sp + 1; - - /* Replace fake return address with real one. */ - *frame_pointer = (unsigned long)correct_ret_addr; -} - -/* - * Called from __kretprobe_trampoline - */ -__used __visible void trampoline_handler(struct pt_regs *regs) -{ - unsigned long *frame_pointer; - - /* fixup registers */ - regs->cs = __KERNEL_CS; -#ifdef CONFIG_X86_32 - regs->gs = 0; -#endif - regs->ip = (unsigned long)&__kretprobe_trampoline; - regs->orig_ax = ~0UL; - regs->sp += sizeof(long); - frame_pointer = ®s->sp + 1; - - /* - * The return address at 'frame_pointer' is recovered by the - * arch_kretprobe_fixup_return() which called from the - * kretprobe_trampoline_handler(). - */ - kretprobe_trampoline_handler(regs, frame_pointer); - - /* - * Copy FLAGS to 'pt_regs::sp' so that __kretprobe_trapmoline() - * can do RET right after POPF. - */ - regs->sp = regs->flags; -} -NOKPROBE_SYMBOL(trampoline_handler); - int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index b4a54a52aa59..e6b8c5362b94 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -106,7 +106,8 @@ asm ( ".global optprobe_template_entry\n" "optprobe_template_entry:\n" #ifdef CONFIG_X86_64 - /* We don't bother saving the ss register */ + " pushq $" __stringify(__KERNEL_DS) "\n" + /* Save the 'sp - 8', this will be fixed later. */ " pushq %rsp\n" " pushfq\n" ".global optprobe_template_clac\n" @@ -121,14 +122,17 @@ asm ( ".global optprobe_template_call\n" "optprobe_template_call:\n" ASM_NOP5 - /* Move flags to rsp */ + /* Copy 'regs->flags' into 'regs->ss'. */ " movq 18*8(%rsp), %rdx\n" - " movq %rdx, 19*8(%rsp)\n" + " movq %rdx, 20*8(%rsp)\n" RESTORE_REGS_STRING - /* Skip flags entry */ - " addq $8, %rsp\n" + /* Skip 'regs->flags' and 'regs->sp'. */ + " addq $16, %rsp\n" + /* And pop flags register from 'regs->ss'. */ " popfq\n" #else /* CONFIG_X86_32 */ + " pushl %ss\n" + /* Save the 'sp - 4', this will be fixed later. */ " pushl %esp\n" " pushfl\n" ".global optprobe_template_clac\n" @@ -142,12 +146,13 @@ asm ( ".global optprobe_template_call\n" "optprobe_template_call:\n" ASM_NOP5 - /* Move flags into esp */ + /* Copy 'regs->flags' into 'regs->ss'. */ " movl 14*4(%esp), %edx\n" - " movl %edx, 15*4(%esp)\n" + " movl %edx, 16*4(%esp)\n" RESTORE_REGS_STRING - /* Skip flags entry */ - " addl $4, %esp\n" + /* Skip 'regs->flags' and 'regs->sp'. */ + " addl $8, %esp\n" + /* And pop flags register from 'regs->ss'. */ " popfl\n" #endif ".global optprobe_template_end\n" @@ -179,6 +184,8 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) kprobes_inc_nmissed_count(&op->kp); } else { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + /* Adjust stack pointer */ + regs->sp += sizeof(long); /* Save skipped registers */ regs->cs = __KERNEL_CS; #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d77481ecb0d5..79e0b8d63ffa 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -1029,10 +1029,11 @@ asm( ".global __raw_callee_save___kvm_vcpu_is_preempted;" ".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" "__raw_callee_save___kvm_vcpu_is_preempted:" +ASM_ENDBR "movq __per_cpu_offset(,%rdi,8), %rax;" "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" "setne %al;" -"ret;" +ASM_RET ".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;" ".popsection"); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index f5da4a18070a..566bb8e17149 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -27,6 +27,7 @@ #include <asm/kexec-bzimage64.h> #include <asm/setup.h> #include <asm/set_memory.h> +#include <asm/cpu.h> #ifdef CONFIG_ACPI /* @@ -310,6 +311,7 @@ void machine_kexec(struct kimage *image) /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); hw_breakpoint_disable(); + cet_disable(); if (image->preserve_context) { #ifdef CONFIG_X86_IO_APIC @@ -325,7 +327,7 @@ void machine_kexec(struct kimage *image) } control_page = page_address(image->control_code_page) + PAGE_SIZE; - memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); + __memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page); page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 96d7c27b7093..b98ffcf4d250 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -78,7 +78,7 @@ void *module_alloc(unsigned long size) MODULES_END, gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { + if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } @@ -253,7 +253,7 @@ int module_finalize(const Elf_Ehdr *hdr, { const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, *para = NULL, *orc = NULL, *orc_ip = NULL, - *retpolines = NULL; + *retpolines = NULL, *ibt_endbr = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { @@ -271,6 +271,8 @@ int module_finalize(const Elf_Ehdr *hdr, orc_ip = s; if (!strcmp(".retpoline_sites", secstrings + s->sh_name)) retpolines = s; + if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name)) + ibt_endbr = s; } /* @@ -290,6 +292,10 @@ int module_finalize(const Elf_Ehdr *hdr, void *aseg = (void *)alt->sh_addr; apply_alternatives(aseg, aseg + alt->sh_size); } + if (ibt_endbr) { + void *iseg = (void *)ibt_endbr->sh_addr; + apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size); + } if (locks && text) { void *lseg = (void *)locks->sh_addr; void *tseg = (void *)text->sh_addr; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 4420499f7bb4..7ca2d46c08cc 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -41,6 +41,7 @@ extern void _paravirt_nop(void); asm (".pushsection .entry.text, \"ax\"\n" ".global _paravirt_nop\n" "_paravirt_nop:\n\t" + ASM_ENDBR ASM_RET ".size _paravirt_nop, . - _paravirt_nop\n\t" ".type _paravirt_nop, @function\n\t" @@ -50,6 +51,7 @@ asm (".pushsection .entry.text, \"ax\"\n" asm (".pushsection .entry.text, \"ax\"\n" ".global paravirt_ret0\n" "paravirt_ret0:\n\t" + ASM_ENDBR "xor %" _ASM_AX ", %" _ASM_AX ";\n\t" ASM_RET ".size paravirt_ret0, . - paravirt_ret0\n\t" @@ -69,29 +71,12 @@ noinstr void paravirt_BUG(void) BUG(); } -struct branch { - unsigned char opcode; - u32 delta; -} __attribute__((packed)); - static unsigned paravirt_patch_call(void *insn_buff, const void *target, unsigned long addr, unsigned len) { - const int call_len = 5; - struct branch *b = insn_buff; - unsigned long delta = (unsigned long)target - (addr+call_len); - - if (len < call_len) { - pr_warn("paravirt: Failed to patch indirect CALL at %ps\n", (void *)addr); - /* Kernel might not be viable if patching fails, bail out: */ - BUG_ON(1); - } - - b->opcode = 0xe8; /* call */ - b->delta = delta; - BUILD_BUG_ON(sizeof(*b) != call_len); - - return call_len; + __text_gen_insn(insn_buff, CALL_INSN_OPCODE, + (void *)addr, target, CALL_INSN_SIZE); + return CALL_INSN_SIZE; } #ifdef CONFIG_PARAVIRT_XXL @@ -149,8 +134,6 @@ void paravirt_set_sched_clock(u64 (*func)(void)) } /* These are in entry.S */ -extern void native_iret(void); - static struct resource reserve_ioports = { .start = 0, .end = IO_SPACE_LIMIT, @@ -414,8 +397,6 @@ struct paravirt_patch_template pv_ops = { #ifdef CONFIG_PARAVIRT_XXL NOKPROBE_SYMBOL(native_load_idt); - -void (*paravirt_iret)(void) = native_iret; #endif EXPORT_SYMBOL(pv_ops); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e131d71b3cae..b370767f5b19 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -747,7 +747,7 @@ bool xen_set_default_idle(void) } #endif -void stop_this_cpu(void *dummy) +void __noreturn stop_this_cpu(void *dummy) { local_irq_disable(); /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3402edec236c..e459253649be 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -681,7 +681,7 @@ void set_personality_64bit(void) static void __set_personality_x32(void) { -#ifdef CONFIG_X86_X32 +#ifdef CONFIG_X86_X32_ABI if (current->mm) current->mm->context.flags = 0; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 8d2f2f995539..98d10ef60571 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -13,7 +13,6 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/ptrace.h> -#include <linux/tracehook.h> #include <linux/user.h> #include <linux/elf.h> #include <linux/security.h> diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 399f075ccdc4..c1d8626c53b6 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -42,6 +42,7 @@ .code64 SYM_CODE_START_NOALIGN(relocate_kernel) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR /* * %rdi indirection_page * %rsi page_list @@ -115,6 +116,14 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) pushq %rdx /* + * Clear X86_CR4_CET (if it was set) such that we can clear CR0_WP + * below. + */ + movq %cr4, %rax + andq $~(X86_CR4_CET), %rax + movq %rax, %cr4 + + /* * Set cr0 to a known state: * - Paging enabled * - Alignment check disabled @@ -215,6 +224,7 @@ SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR // RET target, above movq RSP(%r8), %rsp movq CR4(%r8), %rax movq %rax, %cr4 diff --git a/arch/x86/kernel/rethook.c b/arch/x86/kernel/rethook.c new file mode 100644 index 000000000000..8a1c0111ae79 --- /dev/null +++ b/arch/x86/kernel/rethook.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * x86 implementation of rethook. Mostly copied from arch/x86/kernel/kprobes/core.c. + */ +#include <linux/bug.h> +#include <linux/rethook.h> +#include <linux/kprobes.h> +#include <linux/objtool.h> + +#include "kprobes/common.h" + +__visible void arch_rethook_trampoline_callback(struct pt_regs *regs); + +#ifndef ANNOTATE_NOENDBR +#define ANNOTATE_NOENDBR +#endif + +/* + * When a target function returns, this code saves registers and calls + * arch_rethook_trampoline_callback(), which calls the rethook handler. + */ +asm( + ".text\n" + ".global arch_rethook_trampoline\n" + ".type arch_rethook_trampoline, @function\n" + "arch_rethook_trampoline:\n" +#ifdef CONFIG_X86_64 + ANNOTATE_NOENDBR /* This is only jumped from ret instruction */ + /* Push a fake return address to tell the unwinder it's a rethook. */ + " pushq $arch_rethook_trampoline\n" + UNWIND_HINT_FUNC + " pushq $" __stringify(__KERNEL_DS) "\n" + /* Save the 'sp - 16', this will be fixed later. */ + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rdi\n" + " call arch_rethook_trampoline_callback\n" + RESTORE_REGS_STRING + /* In the callback function, 'regs->flags' is copied to 'regs->ss'. */ + " addq $16, %rsp\n" + " popfq\n" +#else + /* Push a fake return address to tell the unwinder it's a rethook. */ + " pushl $arch_rethook_trampoline\n" + UNWIND_HINT_FUNC + " pushl %ss\n" + /* Save the 'sp - 8', this will be fixed later. */ + " pushl %esp\n" + " pushfl\n" + SAVE_REGS_STRING + " movl %esp, %eax\n" + " call arch_rethook_trampoline_callback\n" + RESTORE_REGS_STRING + /* In the callback function, 'regs->flags' is copied to 'regs->ss'. */ + " addl $8, %esp\n" + " popfl\n" +#endif + ASM_RET + ".size arch_rethook_trampoline, .-arch_rethook_trampoline\n" +); +NOKPROBE_SYMBOL(arch_rethook_trampoline); + +/* + * Called from arch_rethook_trampoline + */ +__used __visible void arch_rethook_trampoline_callback(struct pt_regs *regs) +{ + unsigned long *frame_pointer; + + /* fixup registers */ + regs->cs = __KERNEL_CS; +#ifdef CONFIG_X86_32 + regs->gs = 0; +#endif + regs->ip = (unsigned long)&arch_rethook_trampoline; + regs->orig_ax = ~0UL; + regs->sp += 2*sizeof(long); + frame_pointer = (long *)(regs + 1); + + /* + * The return address at 'frame_pointer' is recovered by the + * arch_rethook_fixup_return() which called from this + * rethook_trampoline_handler(). + */ + rethook_trampoline_handler(regs, (unsigned long)frame_pointer); + + /* + * Copy FLAGS to 'pt_regs::ss' so that arch_rethook_trapmoline() + * can do RET right after POPF. + */ + *(unsigned long *)®s->ss = regs->flags; +} +NOKPROBE_SYMBOL(arch_rethook_trampoline_callback); + +/* + * arch_rethook_trampoline() skips updating frame pointer. The frame pointer + * saved in arch_rethook_trampoline_callback() points to the real caller + * function's frame pointer. Thus the arch_rethook_trampoline() doesn't have + * a standard stack frame with CONFIG_FRAME_POINTER=y. + * Let's mark it non-standard function. Anyway, FP unwinder can correctly + * unwind without the hint. + */ +STACK_FRAME_NON_STANDARD_FP(arch_rethook_trampoline); + +/* This is called from rethook_trampoline_handler(). */ +void arch_rethook_fixup_return(struct pt_regs *regs, + unsigned long correct_ret_addr) +{ + unsigned long *frame_pointer = (void *)(regs + 1); + + /* Replace fake return address with real one. */ + *frame_pointer = correct_ret_addr; +} +NOKPROBE_SYMBOL(arch_rethook_fixup_return); + +void arch_rethook_prepare(struct rethook_node *rh, struct pt_regs *regs, bool mcount) +{ + unsigned long *stack = (unsigned long *)regs->sp; + + rh->ret_addr = stack[0]; + rh->frame = regs->sp; + + /* Replace the return addr with trampoline addr */ + stack[0] = (unsigned long) arch_rethook_trampoline; +} +NOKPROBE_SYMBOL(arch_rethook_prepare); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index ec71e06ae364..e439eb14325f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -18,7 +18,6 @@ #include <linux/kstrtox.h> #include <linux/errno.h> #include <linux/wait.h> -#include <linux/tracehook.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/personality.h> @@ -861,11 +860,11 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) +void arch_do_signal_or_restart(struct pt_regs *regs) { struct ksignal ksig; - if (has_signal && get_signal(&ksig)) { + if (get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 2e37862e3a8c..1563fb995005 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -210,6 +210,81 @@ DEFINE_IDTENTRY(exc_overflow) do_error_trap(regs, 0, "overflow", X86_TRAP_OF, SIGSEGV, 0, NULL); } +#ifdef CONFIG_X86_KERNEL_IBT + +static __ro_after_init bool ibt_fatal = true; + +extern void ibt_selftest_ip(void); /* code label defined in asm below */ + +enum cp_error_code { + CP_EC = (1 << 15) - 1, + + CP_RET = 1, + CP_IRET = 2, + CP_ENDBR = 3, + CP_RSTRORSSP = 4, + CP_SETSSBSY = 5, + + CP_ENCL = 1 << 15, +}; + +DEFINE_IDTENTRY_ERRORCODE(exc_control_protection) +{ + if (!cpu_feature_enabled(X86_FEATURE_IBT)) { + pr_err("Unexpected #CP\n"); + BUG(); + } + + if (WARN_ON_ONCE(user_mode(regs) || (error_code & CP_EC) != CP_ENDBR)) + return; + + if (unlikely(regs->ip == (unsigned long)&ibt_selftest_ip)) { + regs->ax = 0; + return; + } + + pr_err("Missing ENDBR: %pS\n", (void *)instruction_pointer(regs)); + if (!ibt_fatal) { + printk(KERN_DEFAULT CUT_HERE); + __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + return; + } + BUG(); +} + +/* Must be noinline to ensure uniqueness of ibt_selftest_ip. */ +noinline bool ibt_selftest(void) +{ + unsigned long ret; + + asm (" lea ibt_selftest_ip(%%rip), %%rax\n\t" + ANNOTATE_RETPOLINE_SAFE + " jmp *%%rax\n\t" + "ibt_selftest_ip:\n\t" + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + " nop\n\t" + + : "=a" (ret) : : "memory"); + + return !ret; +} + +static int __init ibt_setup(char *str) +{ + if (!strcmp(str, "off")) + setup_clear_cpu_cap(X86_FEATURE_IBT); + + if (!strcmp(str, "warn")) + ibt_fatal = false; + + return 1; +} + +__setup("ibt=", ibt_setup); + +#endif /* CONFIG_X86_KERNEL_IBT */ + #ifdef CONFIG_X86_F00F_BUG void handle_invalid_op(struct pt_regs *regs) #else diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a698196377be..cafacb2e58cc 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1487,6 +1487,9 @@ static unsigned long __init get_loops_per_jiffy(void) static void __init tsc_enable_sched_clock(void) { + loops_per_jiffy = get_loops_per_jiffy(); + use_tsc_delay(); + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); cyc2ns_init_boot_cpu(); @@ -1502,8 +1505,6 @@ void __init tsc_early_init(void) return; if (!determine_cpu_tsc_frequencies(true)) return; - loops_per_jiffy = get_loops_per_jiffy(); - tsc_enable_sched_clock(); } @@ -1537,7 +1538,6 @@ void __init tsc_init(void) enable_sched_clock_irqtime(); lpj_fine = get_loops_per_jiffy(); - use_tsc_delay(); check_system_tsc_reliable(); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 2de3c8c5eba9..794fdef2501a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -550,15 +550,15 @@ bool unwind_next_frame(struct unwind_state *state) } /* * There is a small chance to interrupt at the entry of - * __kretprobe_trampoline() where the ORC info doesn't exist. - * That point is right after the RET to __kretprobe_trampoline() + * arch_rethook_trampoline() where the ORC info doesn't exist. + * That point is right after the RET to arch_rethook_trampoline() * which was modified return address. - * At that point, the @addr_p of the unwind_recover_kretprobe() + * At that point, the @addr_p of the unwind_recover_rethook() * (this has to point the address of the stack entry storing * the modified return address) must be "SP - (a stack entry)" * because SP is incremented by the RET. */ - state->ip = unwind_recover_kretprobe(state, state->ip, + state->ip = unwind_recover_rethook(state, state->ip, (unsigned long *)(state->sp - sizeof(long))); state->regs = (struct pt_regs *)sp; state->prev_regs = NULL; @@ -573,7 +573,7 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } /* See UNWIND_HINT_TYPE_REGS case comment. */ - state->ip = unwind_recover_kretprobe(state, state->ip, + state->ip = unwind_recover_rethook(state, state->ip, (unsigned long *)(state->sp - sizeof(long))); if (state->full_regs) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 27f830345b6f..7fda7f27e762 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -285,6 +285,15 @@ SECTIONS } #endif +#ifdef CONFIG_X86_KERNEL_IBT + . = ALIGN(8); + .ibt_endbr_seal : AT(ADDR(.ibt_endbr_seal) - LOAD_OFFSET) { + __ibt_endbr_seal = .; + *(.ibt_endbr_seal) + __ibt_endbr_seal_end = .; + } +#endif + /* * struct alt_inst entries. From the header (alternative.h): * "Alternative instructions for different CPU types or capabilities" diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 7ba4ec77feeb..f9c00c89829b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -24,6 +24,7 @@ #include <linux/stringify.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> +#include <asm/ibt.h> #include "x86.h" #include "tss.h" @@ -189,7 +190,7 @@ #define X16(x...) X8(x), X8(x) #define NR_FASTOP (ilog2(sizeof(ulong)) + 1) -#define FASTOP_SIZE 8 +#define FASTOP_SIZE (8 * (1 + HAS_KERNEL_IBT)) struct opcode { u64 flags; @@ -311,7 +312,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ ".align " __stringify(FASTOP_SIZE) " \n\t" \ ".type " name ", @function \n\t" \ - name ":\n\t" + name ":\n\t" \ + ASM_ENDBR #define FOP_FUNC(name) \ __FOP_FUNC(#name) @@ -433,21 +435,23 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); /* * Depending on .config the SETcc functions look like: * + * ENDBR [4 bytes; CONFIG_X86_KERNEL_IBT] * SETcc %al [3 bytes] * RET [1 byte] * INT3 [1 byte; CONFIG_SLS] * - * Which gives possible sizes 4 or 5. When rounded up to the - * next power-of-two alignment they become 4 or 8. + * Which gives possible sizes 4, 5, 8 or 9. When rounded up to the + * next power-of-two alignment they become 4, 8 or 16 resp. */ -#define SETCC_LENGTH (4 + IS_ENABLED(CONFIG_SLS)) -#define SETCC_ALIGN (4 << IS_ENABLED(CONFIG_SLS)) +#define SETCC_LENGTH (ENDBR_INSN_SIZE + 4 + IS_ENABLED(CONFIG_SLS)) +#define SETCC_ALIGN (4 << IS_ENABLED(CONFIG_SLS) << HAS_KERNEL_IBT) static_assert(SETCC_LENGTH <= SETCC_ALIGN); #define FOP_SETCC(op) \ ".align " __stringify(SETCC_ALIGN) " \n\t" \ ".type " #op ", @function \n\t" \ #op ": \n\t" \ + ASM_ENDBR \ #op " %al \n\t" \ __FOP_RET(#op) diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index 520897061ee0..1e3de0769b81 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -3,6 +3,7 @@ #include <linux/linkage.h> #include <linux/error-injection.h> #include <linux/kprobes.h> +#include <linux/objtool.h> asmlinkage void just_return_func(void); @@ -11,6 +12,7 @@ asm( ".type just_return_func, @function\n" ".globl just_return_func\n" "just_return_func:\n" + ANNOTATE_NOENDBR ASM_RET ".size just_return_func, .-just_return_func\n" ); diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index 3a6e6cfe8c35..ef3af7ff2c8a 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -4,6 +4,7 @@ #undef memcpy #undef memset +#undef memmove __visible void *memcpy(void *to, const void *from, size_t n) { diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index afbdda539b80..5f87bab4fb8d 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -55,6 +55,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) .align RETPOLINE_THUNK_SIZE SYM_CODE_START(__x86_indirect_thunk_array) + ANNOTATE_NOENDBR // apply_retpolines #define GEN(reg) THUNK reg #include <asm/GEN-for-each-reg.h> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 4ba024d5b63a..d8cfce221275 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -31,7 +31,6 @@ * We need to define the tracepoints somewhere, and tlb.c * is only compiled when SMP=y. */ -#define CREATE_TRACE_POINTS #include <trace/events/tlb.h> #include "mm_internal.h" diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a6cf56a14939..6eb4d91d5365 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -9,6 +9,7 @@ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/sched/smt.h> +#include <linux/task_work.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 6efbb87f65ed..8fe35ed11fd6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -46,6 +46,12 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT4_off32(b1, b2, b3, b4, off) \ do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) +#ifdef CONFIG_X86_KERNEL_IBT +#define EMIT_ENDBR() EMIT(gen_endbr(), 4) +#else +#define EMIT_ENDBR() +#endif + static bool is_imm8(int value) { return value <= 127 && value >= -128; @@ -241,7 +247,7 @@ struct jit_context { /* Number of bytes emit_patch() needs to generate instructions */ #define X86_PATCH_SIZE 5 /* Number of bytes that will be skipped on tailcall */ -#define X86_TAIL_CALL_OFFSET 11 +#define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE) static void push_callee_regs(u8 **pprog, bool *callee_regs_used) { @@ -286,6 +292,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, /* BPF trampoline can be made to work without these nops, * but let's waste 5 bytes for now and optimize later */ + EMIT_ENDBR(); memcpy(prog, x86_nops[5], X86_PATCH_SIZE); prog += X86_PATCH_SIZE; if (!ebpf_from_cbpf) { @@ -296,6 +303,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + + /* X86_TAIL_CALL_OFFSET is here */ + EMIT_ENDBR(); + /* sub rsp, rounded_stack_depth */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8)); @@ -380,6 +391,13 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, /* BPF poking in modules is not supported */ return -EINVAL; + /* + * See emit_prologue(), for IBT builds the trampoline hook is preceded + * with an ENDBR instruction. + */ + if (is_endbr(*(u32 *)ip)) + ip += ENDBR_INSN_SIZE; + return __bpf_arch_text_poke(ip, t, old_addr, new_addr); } @@ -2013,14 +2031,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ip_off = stack_size; - if (flags & BPF_TRAMP_F_SKIP_FRAME) + if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* skip patched call instruction and point orig_call to actual * body of the kernel function. */ + if (is_endbr(*(u32 *)orig_call)) + orig_call += ENDBR_INSN_SIZE; orig_call += X86_PATCH_SIZE; + } prog = image; + EMIT_ENDBR(); EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index 84b09c230cbd..a50245157685 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y KASAN_SANITIZE := n GCOV_PROFILE := n diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 25799d768624..854dd81804b7 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -20,12 +20,14 @@ */ #include <linux/linkage.h> +#include <linux/objtool.h> #include <asm/page_types.h> #include <asm/segment.h> .text .code64 -SYM_CODE_START(__efi64_thunk) +SYM_FUNC_START(__efi64_thunk) +STACK_FRAME_NON_STANDARD __efi64_thunk push %rbp push %rbx @@ -79,7 +81,7 @@ SYM_CODE_START(__efi64_thunk) 2: pushl $__KERNEL_CS pushl %ebp lret -SYM_CODE_END(__efi64_thunk) +SYM_FUNC_END(__efi64_thunk) .bss .balign 8 diff --git a/arch/x86/um/shared/sysdep/syscalls_64.h b/arch/x86/um/shared/sysdep/syscalls_64.h index 48d6cd12f8a5..b6b997225841 100644 --- a/arch/x86/um/shared/sysdep/syscalls_64.h +++ b/arch/x86/um/shared/sysdep/syscalls_64.h @@ -10,13 +10,12 @@ #include <linux/msg.h> #include <linux/shm.h> -typedef long syscall_handler_t(void); +typedef long syscall_handler_t(long, long, long, long, long, long); extern syscall_handler_t *sys_call_table[]; #define EXECUTE_SYSCALL(syscall, regs) \ - (((long (*)(long, long, long, long, long, long)) \ - (*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(®s->regs), \ + (((*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(®s->regs), \ UPT_SYSCALL_ARG2(®s->regs), \ UPT_SYSCALL_ARG3(®s->regs), \ UPT_SYSCALL_ARG4(®s->regs), \ diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index fe5323f0c42d..27b29ae6c471 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -12,7 +12,6 @@ #include <asm/prctl.h> /* XXX This should get the constants from libc */ #include <registers.h> #include <os.h> -#include <registers.h> long arch_prctl(struct task_struct *task, int option, unsigned long __user *arg2) diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 0d46cc283cf5..62d34b6611c5 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -51,7 +51,7 @@ static u32 xen_apic_read(u32 reg) .interface_version = XENPF_INTERFACE_VERSION, .u.pcpu_info.xen_cpuid = 0, }; - int ret = 0; + int ret; /* Shouldn't need this as APIC is turned off for PV, and we only * get called on the bootup processor. But just in case. */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d47c3d176ae4..5038edb79ad5 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -624,6 +624,9 @@ static struct trap_array_entry trap_array[] = { TRAP_ENTRY(exc_coprocessor_error, false ), TRAP_ENTRY(exc_alignment_check, false ), TRAP_ENTRY(exc_simd_coprocessor_error, false ), +#ifdef CONFIG_X86_KERNEL_IBT + TRAP_ENTRY(exc_control_protection, false ), +#endif }; static bool __ref get_trap_addr(void **addr, unsigned int ist) @@ -1177,6 +1180,8 @@ static void __init xen_domu_set_legacy_features(void) x86_platform.legacy.rtc = 0; } +extern void early_xen_iret_patch(void); + /* First C function to be called on Xen boot */ asmlinkage __visible void __init xen_start_kernel(void) { @@ -1187,6 +1192,10 @@ asmlinkage __visible void __init xen_start_kernel(void) if (!xen_start_info) return; + __text_gen_insn(&early_xen_iret_patch, + JMP32_INSN_OPCODE, &early_xen_iret_patch, &xen_iret, + JMP32_INSN_SIZE); + xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; @@ -1195,7 +1204,6 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; pv_ops.cpu = xen_cpu_ops.cpu; - paravirt_iret = xen_iret; xen_init_irq_ops(); /* diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 89dd6b1708b0..21ecbe754cb2 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -506,10 +506,7 @@ irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) return ret; } -bool is_xen_pmu(int cpu) -{ - return (get_xenpmu_data() != NULL); -} +bool is_xen_pmu; void xen_pmu_init(int cpu) { @@ -520,7 +517,7 @@ void xen_pmu_init(int cpu) BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE); - if (xen_hvm_domain()) + if (xen_hvm_domain() || (cpu != 0 && !is_xen_pmu)) return; xenpmu_data = (struct xen_pmu_data *)get_zeroed_page(GFP_KERNEL); @@ -541,7 +538,8 @@ void xen_pmu_init(int cpu) per_cpu(xenpmu_shared, cpu).xenpmu_data = xenpmu_data; per_cpu(xenpmu_shared, cpu).flags = 0; - if (cpu == 0) { + if (!is_xen_pmu) { + is_xen_pmu = true; perf_register_guest_info_callbacks(&xen_guest_cbs); xen_pmu_arch_init(); } diff --git a/arch/x86/xen/pmu.h b/arch/x86/xen/pmu.h index 0e83a160589b..65c58894fc79 100644 --- a/arch/x86/xen/pmu.h +++ b/arch/x86/xen/pmu.h @@ -4,6 +4,8 @@ #include <xen/interface/xenpmu.h> +extern bool is_xen_pmu; + irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id); #ifdef CONFIG_XEN_HAVE_VPMU void xen_pmu_init(int cpu); @@ -12,7 +14,6 @@ void xen_pmu_finish(int cpu); static inline void xen_pmu_init(int cpu) {} static inline void xen_pmu_finish(int cpu) {} #endif -bool is_xen_pmu(int cpu); bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err); bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err); int pmu_apic_update(uint32_t reg); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index af216feb63d9..81aa46f770c5 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -719,7 +719,7 @@ static void __init xen_reserve_xen_mfnlist(void) } /** - * machine_specific_memory_setup - Hook for machine specific memory setup. + * xen_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index 6ff3c887e0b9..b70afdff419c 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -20,6 +20,12 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void) xen_vcpu_setup(0); /* + * Called again in case the kernel boots on vcpu >= MAX_VIRT_CPUS. + * Refer to comments in xen_hvm_init_time_ops(). + */ + xen_hvm_init_time_ops(); + + /* * The alternative logic (which patches the unlock/lock) runs before * the smp bootup up code is activated. Hence we need to set this up * the core kernel is being patched. Otherwise we will have only diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 4a6019238ee7..688aa8b6ae29 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -129,7 +129,7 @@ int xen_smp_intr_init_pv(unsigned int cpu) per_cpu(xen_irq_work, cpu).irq = rc; per_cpu(xen_irq_work, cpu).name = callfunc_name; - if (is_xen_pmu(cpu)) { + if (is_xen_pmu) { pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu); rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu, xen_pmu_irq_handler, diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index d9c945ee1100..9ef0a5cca96e 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -558,6 +558,11 @@ static void xen_hvm_setup_cpu_clockevents(void) void __init xen_hvm_init_time_ops(void) { + static bool hvm_time_initialized; + + if (hvm_time_initialized) + return; + /* * vector callback is needed otherwise we cannot receive interrupts * on cpu > 0 and at this point we don't know how many cpus are @@ -567,7 +572,22 @@ void __init xen_hvm_init_time_ops(void) return; if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { - pr_info("Xen doesn't support pvclock on HVM, disable pv timer"); + pr_info_once("Xen doesn't support pvclock on HVM, disable pv timer"); + return; + } + + /* + * Only MAX_VIRT_CPUS 'vcpu_info' are embedded inside 'shared_info'. + * The __this_cpu_read(xen_vcpu) is still NULL when Xen HVM guest + * boots on vcpu >= MAX_VIRT_CPUS (e.g., kexec), To access + * __this_cpu_read(xen_vcpu) via xen_clocksource_read() will panic. + * + * The xen_hvm_init_time_ops() should be called again later after + * __this_cpu_read(xen_vcpu) is available. + */ + if (!__this_cpu_read(xen_vcpu)) { + pr_info("Delay xen_init_time_common() as kernel is running on vcpu=%d\n", + xen_vcpu_nr(0)); return; } @@ -577,6 +597,8 @@ void __init xen_hvm_init_time_ops(void) x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents; x86_platform.set_wallclock = xen_set_wallclock; + + hvm_time_initialized = true; } #endif diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index e730e6200e64..caa9bc2fa100 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -122,6 +122,7 @@ SYM_FUNC_END(xen_read_cr2_direct); .macro xen_pv_trap name SYM_CODE_START(xen_\name) UNWIND_HINT_EMPTY + ENDBR pop %rcx pop %r11 jmp \name @@ -147,6 +148,9 @@ xen_pv_trap asm_exc_page_fault xen_pv_trap asm_exc_spurious_interrupt_bug xen_pv_trap asm_exc_coprocessor_error xen_pv_trap asm_exc_alignment_check +#ifdef CONFIG_X86_KERNEL_IBT +xen_pv_trap asm_exc_control_protection +#endif #ifdef CONFIG_X86_MCE xen_pv_trap asm_xenpv_exc_machine_check #endif /* CONFIG_X86_MCE */ @@ -162,6 +166,7 @@ SYM_CODE_START(xen_early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS UNWIND_HINT_EMPTY + ENDBR pop %rcx pop %r11 jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE @@ -189,6 +194,7 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 */ SYM_CODE_START(xen_iret) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR pushq $0 jmp hypercall_iret SYM_CODE_END(xen_iret) @@ -230,6 +236,7 @@ SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) /* Normal 64-bit system call target */ SYM_CODE_START(xen_syscall_target) UNWIND_HINT_EMPTY + ENDBR popq %rcx popq %r11 @@ -249,6 +256,7 @@ SYM_CODE_END(xen_syscall_target) /* 32-bit compat syscall target */ SYM_CODE_START(xen_syscall32_target) UNWIND_HINT_EMPTY + ENDBR popq %rcx popq %r11 @@ -266,6 +274,7 @@ SYM_CODE_END(xen_syscall32_target) /* 32-bit compat sysenter target */ SYM_CODE_START(xen_sysenter_target) UNWIND_HINT_EMPTY + ENDBR /* * NB: Xen is polite and clears TF from EFLAGS for us. This means * that we don't need to guard against single step exceptions here. @@ -289,6 +298,7 @@ SYM_CODE_END(xen_sysenter_target) SYM_CODE_START(xen_syscall32_target) SYM_CODE_START(xen_sysenter_target) UNWIND_HINT_EMPTY + ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 11d286529fe5..ac17196e2518 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -25,8 +25,12 @@ SYM_CODE_START(hypercall_page) .rept (PAGE_SIZE / 32) UNWIND_HINT_FUNC - .skip 31, 0x90 - RET + ANNOTATE_NOENDBR + ret + /* + * Xen will write the hypercall page, and sort out ENDBR. + */ + .skip 31, 0xcc .endr #define HYPERCALL(n) \ @@ -74,6 +78,7 @@ SYM_CODE_END(startup_xen) .pushsection .text SYM_CODE_START(asm_cpu_bringup_and_idle) UNWIND_HINT_EMPTY + ENDBR call cpu_bringup_and_idle SYM_CODE_END(asm_cpu_bringup_and_idle) diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index f46c7d2d439c..bd113bc6e192 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -18,7 +18,7 @@ config XTENSA select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS select COMMON_CLK - select DMA_REMAP if MMU + select DMA_NONCOHERENT_MMAP if MMU select GENERIC_ATOMIC64 select GENERIC_IRQ_SHOW select GENERIC_LIB_CMPDI2 diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 854c5e07e867..fa07c686cbcc 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -4,6 +4,7 @@ generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += param.h +generic-y += parport.h generic-y += qrwlock.h generic-y += qspinlock.h generic-y += user.h diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index b3a22095371b..7966a58af472 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -109,6 +109,8 @@ #define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ #define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ +#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/xtensa/include/uapi/asm/termbits.h b/arch/xtensa/include/uapi/asm/termbits.h deleted file mode 100644 index d4206a7c5138..000000000000 --- a/arch/xtensa/include/uapi/asm/termbits.h +++ /dev/null @@ -1,221 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * include/asm-xtensa/termbits.h - * - * Copied from SH. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2001 - 2005 Tensilica Inc. - */ - -#ifndef _XTENSA_TERMBITS_H -#define _XTENSA_TERMBITS_H - - -#include <linux/posix_types.h> - -typedef unsigned char cc_t; -typedef unsigned int speed_t; -typedef unsigned int tcflag_t; - -#define NCCS 19 -struct termios { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ -}; - -struct termios2 { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ - speed_t c_ispeed; /* input speed */ - speed_t c_ospeed; /* output speed */ -}; - -struct ktermios { - tcflag_t c_iflag; /* input mode flags */ - tcflag_t c_oflag; /* output mode flags */ - tcflag_t c_cflag; /* control mode flags */ - tcflag_t c_lflag; /* local mode flags */ - cc_t c_line; /* line discipline */ - cc_t c_cc[NCCS]; /* control characters */ - speed_t c_ispeed; /* input speed */ - speed_t c_ospeed; /* output speed */ -}; - -/* c_cc characters */ - -#define VINTR 0 -#define VQUIT 1 -#define VERASE 2 -#define VKILL 3 -#define VEOF 4 -#define VTIME 5 -#define VMIN 6 -#define VSWTC 7 -#define VSTART 8 -#define VSTOP 9 -#define VSUSP 10 -#define VEOL 11 -#define VREPRINT 12 -#define VDISCARD 13 -#define VWERASE 14 -#define VLNEXT 15 -#define VEOL2 16 - -/* c_iflag bits */ - -#define IGNBRK 0000001 -#define BRKINT 0000002 -#define IGNPAR 0000004 -#define PARMRK 0000010 -#define INPCK 0000020 -#define ISTRIP 0000040 -#define INLCR 0000100 -#define IGNCR 0000200 -#define ICRNL 0000400 -#define IUCLC 0001000 -#define IXON 0002000 -#define IXANY 0004000 -#define IXOFF 0010000 -#define IMAXBEL 0020000 -#define IUTF8 0040000 - -/* c_oflag bits */ - -#define OPOST 0000001 -#define OLCUC 0000002 -#define ONLCR 0000004 -#define OCRNL 0000010 -#define ONOCR 0000020 -#define ONLRET 0000040 -#define OFILL 0000100 -#define OFDEL 0000200 -#define NLDLY 0000400 -#define NL0 0000000 -#define NL1 0000400 -#define CRDLY 0003000 -#define CR0 0000000 -#define CR1 0001000 -#define CR2 0002000 -#define CR3 0003000 -#define TABDLY 0014000 -#define TAB0 0000000 -#define TAB1 0004000 -#define TAB2 0010000 -#define TAB3 0014000 -#define XTABS 0014000 -#define BSDLY 0020000 -#define BS0 0000000 -#define BS1 0020000 -#define VTDLY 0040000 -#define VT0 0000000 -#define VT1 0040000 -#define FFDLY 0100000 -#define FF0 0000000 -#define FF1 0100000 - -/* c_cflag bit meaning */ - -#define CBAUD 0010017 -#define B0 0000000 /* hang up */ -#define B50 0000001 -#define B75 0000002 -#define B110 0000003 -#define B134 0000004 -#define B150 0000005 -#define B200 0000006 -#define B300 0000007 -#define B600 0000010 -#define B1200 0000011 -#define B1800 0000012 -#define B2400 0000013 -#define B4800 0000014 -#define B9600 0000015 -#define B19200 0000016 -#define B38400 0000017 -#define EXTA B19200 -#define EXTB B38400 -#define CSIZE 0000060 -#define CS5 0000000 -#define CS6 0000020 -#define CS7 0000040 -#define CS8 0000060 -#define CSTOPB 0000100 -#define CREAD 0000200 -#define PARENB 0000400 -#define PARODD 0001000 -#define HUPCL 0002000 -#define CLOCAL 0004000 -#define CBAUDEX 0010000 -#define BOTHER 0010000 -#define B57600 0010001 -#define B115200 0010002 -#define B230400 0010003 -#define B460800 0010004 -#define B500000 0010005 -#define B576000 0010006 -#define B921600 0010007 -#define B1000000 0010010 -#define B1152000 0010011 -#define B1500000 0010012 -#define B2000000 0010013 -#define B2500000 0010014 -#define B3000000 0010015 -#define B3500000 0010016 -#define B4000000 0010017 -#define CIBAUD 002003600000 /* input baud rate */ -#define CMSPAR 010000000000 /* mark or space (stick) parity */ -#define CRTSCTS 020000000000 /* flow control */ - -#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ - -/* c_lflag bits */ - -#define ISIG 0000001 -#define ICANON 0000002 -#define XCASE 0000004 -#define ECHO 0000010 -#define ECHOE 0000020 -#define ECHOK 0000040 -#define ECHONL 0000100 -#define NOFLSH 0000200 -#define TOSTOP 0000400 -#define ECHOCTL 0001000 -#define ECHOPRT 0002000 -#define ECHOKE 0004000 -#define FLUSHO 0010000 -#define PENDIN 0040000 -#define IEXTEN 0100000 -#define EXTPROC 0200000 - -/* tcflow() and TCXONC use these */ - -#define TCOOFF 0 -#define TCOON 1 -#define TCIOFF 2 -#define TCION 3 - -/* tcflush() and TCFLSH use these */ - -#define TCIFLUSH 0 -#define TCOFLUSH 1 -#define TCIOFLUSH 2 - -/* tcsetattr uses these */ - -#define TCSANOW 0 -#define TCSADRAIN 1 -#define TCSAFLUSH 2 - -#endif /* _XTENSA_TERMBITS_H */ diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c index bb3f4797d212..323c678a691f 100644 --- a/arch/xtensa/kernel/ptrace.c +++ b/arch/xtensa/kernel/ptrace.c @@ -26,7 +26,6 @@ #include <linux/security.h> #include <linux/signal.h> #include <linux/smp.h> -#include <linux/tracehook.h> #include <linux/uaccess.h> #define CREATE_TRACE_POINTS @@ -550,7 +549,7 @@ int do_syscall_trace_enter(struct pt_regs *regs) regs->areg[2] = -ENOSYS; if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) { + ptrace_report_syscall_entry(regs)) { regs->areg[2] = -ENOSYS; regs->syscall = NO_SYSCALL; return 0; @@ -583,5 +582,5 @@ void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index f6c949895b3e..6f68649e86ba 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -19,7 +19,7 @@ #include <linux/errno.h> #include <linux/ptrace.h> #include <linux/personality.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/sched/task_stack.h> #include <asm/ucontext.h> @@ -511,5 +511,5 @@ void do_notify_resume(struct pt_regs *regs) do_signal(regs); if (test_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(regs); + resume_user_mode_work(regs); } diff --git a/arch/xtensa/kernel/syscalls/Makefile b/arch/xtensa/kernel/syscalls/Makefile index 6713c65a25e1..b265e4bc16c2 100644 --- a/arch/xtensa/kernel/syscalls/Makefile +++ b/arch/xtensa/kernel/syscalls/Makefile @@ -2,8 +2,7 @@ kapi := arch/$(SRCARCH)/include/generated/asm uapi := arch/$(SRCARCH)/include/generated/uapi/asm -_dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \ - $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') +$(shell mkdir -p $(uapi) $(kapi)) syscall := $(src)/syscall.tbl syshdr := $(srctree)/scripts/syscallhdr.sh |