diff options
Diffstat (limited to 'arch/powerpc/kernel')
28 files changed, 592 insertions, 327 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index d3282fbea4f2..8585d03c02d3 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -3,9 +3,6 @@ # Makefile for the linux kernel. # -ifdef CONFIG_PPC64 -CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) -endif ifdef CONFIG_PPC32 CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC @@ -87,6 +84,7 @@ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_DAWR) += dawr.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o +obj-$(CONFIG_PPC_BOOK3S_64) += dexcr.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_64e.o obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o @@ -190,9 +188,6 @@ GCOV_PROFILE_kprobes-ftrace.o := n KCOV_INSTRUMENT_kprobes-ftrace.o := n KCSAN_SANITIZE_kprobes-ftrace.o := n UBSAN_SANITIZE_kprobes-ftrace.o := n -GCOV_PROFILE_syscall_64.o := n -KCOV_INSTRUMENT_syscall_64.o := n -UBSAN_SANITIZE_syscall_64.o := n UBSAN_SANITIZE_vdso.o := n # Necessary for booting with kcov enabled on book3e machines diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index bfd3f442e5eb..ab3ca74e6730 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -401,7 +401,7 @@ _GLOBAL(__save_cpu_setup) andi. r3,r3,0xff00 cmpwi cr0,r3,0x0200 bne 1f - mfspr r4,SPRN_HID2 + mfspr r4,SPRN_HID2_750FX stw r4,CS_HID2(r5) 1: mtcr r7 @@ -496,7 +496,7 @@ _GLOBAL(__restore_cpu_setup) bne 4f lwz r4,CS_HID2(r5) rlwinm r4,r4,0,19,17 - mtspr SPRN_HID2,r4 + mtspr SPRN_HID2_750FX,r4 sync 4: lwz r4,CS_HID1(r5) diff --git a/arch/powerpc/kernel/dexcr.c b/arch/powerpc/kernel/dexcr.c new file mode 100644 index 000000000000..3a0358e91c60 --- /dev/null +++ b/arch/powerpc/kernel/dexcr.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/capability.h> +#include <linux/cpu.h> +#include <linux/init.h> +#include <linux/prctl.h> +#include <linux/sched.h> + +#include <asm/cpu_has_feature.h> +#include <asm/cputable.h> +#include <asm/processor.h> +#include <asm/reg.h> + +static int __init init_task_dexcr(void) +{ + if (!early_cpu_has_feature(CPU_FTR_ARCH_31)) + return 0; + + current->thread.dexcr_onexec = mfspr(SPRN_DEXCR); + + return 0; +} +early_initcall(init_task_dexcr) + +/* Allow thread local configuration of these by default */ +#define DEXCR_PRCTL_EDITABLE ( \ + DEXCR_PR_IBRTPD | \ + DEXCR_PR_SRAPD | \ + DEXCR_PR_NPHIE) + +static int prctl_to_aspect(unsigned long which, unsigned int *aspect) +{ + switch (which) { + case PR_PPC_DEXCR_SBHE: + *aspect = DEXCR_PR_SBHE; + break; + case PR_PPC_DEXCR_IBRTPD: + *aspect = DEXCR_PR_IBRTPD; + break; + case PR_PPC_DEXCR_SRAPD: + *aspect = DEXCR_PR_SRAPD; + break; + case PR_PPC_DEXCR_NPHIE: + *aspect = DEXCR_PR_NPHIE; + break; + default: + return -ENODEV; + } + + return 0; +} + +int get_dexcr_prctl(struct task_struct *task, unsigned long which) +{ + unsigned int aspect; + int ret; + + ret = prctl_to_aspect(which, &aspect); + if (ret) + return ret; + + if (aspect & DEXCR_PRCTL_EDITABLE) + ret |= PR_PPC_DEXCR_CTRL_EDITABLE; + + if (aspect & mfspr(SPRN_DEXCR)) + ret |= PR_PPC_DEXCR_CTRL_SET; + else + ret |= PR_PPC_DEXCR_CTRL_CLEAR; + + if (aspect & task->thread.dexcr_onexec) + ret |= PR_PPC_DEXCR_CTRL_SET_ONEXEC; + else + ret |= PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC; + + return ret; +} + +int set_dexcr_prctl(struct task_struct *task, unsigned long which, unsigned long ctrl) +{ + unsigned long dexcr; + unsigned int aspect; + int err = 0; + + err = prctl_to_aspect(which, &aspect); + if (err) + return err; + + if (!(aspect & DEXCR_PRCTL_EDITABLE)) + return -EPERM; + + if (ctrl & ~PR_PPC_DEXCR_CTRL_MASK) + return -EINVAL; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET && ctrl & PR_PPC_DEXCR_CTRL_CLEAR) + return -EINVAL; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC && ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC) + return -EINVAL; + + /* + * We do not want an unprivileged process being able to disable + * a setuid process's hash check instructions + */ + if (aspect == DEXCR_PR_NPHIE && + ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + + dexcr = mfspr(SPRN_DEXCR); + + if (ctrl & PR_PPC_DEXCR_CTRL_SET) + dexcr |= aspect; + else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR) + dexcr &= ~aspect; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC) + task->thread.dexcr_onexec |= aspect; + else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC) + task->thread.dexcr_onexec &= ~aspect; + + mtspr(SPRN_DEXCR, dexcr); + + return 0; +} diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 8920862ffd79..f0ae39e77e37 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -216,6 +216,6 @@ const struct dma_map_ops dma_iommu_ops = { .get_required_mask = dma_iommu_get_required_mask, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index ab316e155ea9..6670063a7a6c 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -506,9 +506,18 @@ int eeh_dev_check_failure(struct eeh_dev *edev) * We will punt with the following conditions: Failure to get * PE's state, EEH not support and Permanently unavailable * state, PE is in good state. + * + * On the pSeries, after reaching the threshold, get_state might + * return EEH_STATE_NOT_SUPPORT. However, it's possible that the + * device state remains uncleared if the device is not marked + * pci_channel_io_perm_failure. Therefore, consider logging the + * event to let device removal happen. + * */ if ((ret < 0) || - (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) { + (ret == EEH_STATE_NOT_SUPPORT && + dev->error_state == pci_channel_io_perm_failure) || + eeh_state_active(ret)) { eeh_stats.false_positives++; pe->false_positives++; rc = 0; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 48773d2d9be3..7efe04c68f0f 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -865,9 +865,18 @@ void eeh_handle_normal_event(struct eeh_pe *pe) devices++; if (!devices) { - pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n", + pr_warn("EEH: Frozen PHB#%x-PE#%x is empty!\n", pe->phb->global_number, pe->addr); - goto out; /* nothing to recover */ + /* + * The device is removed, tear down its state, on powernv + * hotplug driver would take care of it but not on pseries, + * permanently disable the card as it is hot removed. + * + * In the case of powernv, note that the removal of device + * is covered by pci rescan lock, so no problem even if hotplug + * driver attempts to remove the device. + */ + goto recover_failed; } /* Log the event */ diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index e0ce81279624..d1030bc52564 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -24,10 +24,10 @@ static int eeh_pe_aux_size = 0; static LIST_HEAD(eeh_phb_pe); /** - * eeh_set_pe_aux_size - Set PE auxillary data size - * @size: PE auxillary data size + * eeh_set_pe_aux_size - Set PE auxiliary data size + * @size: PE auxiliary data size in bytes * - * Set PE auxillary data size + * Set PE auxiliary data size. */ void eeh_set_pe_aux_size(int size) { @@ -527,7 +527,7 @@ EXPORT_SYMBOL_GPL(eeh_pe_state_mark); * eeh_pe_mark_isolated * @pe: EEH PE * - * Record that a PE has been isolated by marking the PE and it's children as + * Record that a PE has been isolated by marking the PE and its children as * EEH_PE_ISOLATED (and EEH_PE_CFG_BLOCKED, if required) and their PCI devices * as pci_channel_io_frozen. */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index d14eda1e8589..a612e7513a4f 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -53,8 +53,6 @@ static struct kobject *fadump_kobj; static atomic_t cpus_in_fadump; static DEFINE_MUTEX(fadump_mutex); -static struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false }; - #define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */ #define RESERVED_RNGS_CNT (RESERVED_RNGS_SZ / \ sizeof(struct fadump_memory_range)) @@ -133,6 +131,41 @@ static int __init fadump_cma_init(void) static int __init fadump_cma_init(void) { return 1; } #endif /* CONFIG_CMA */ +/* + * Additional parameters meant for capture kernel are placed in a dedicated area. + * If this is capture kernel boot, append these parameters to bootargs. + */ +void __init fadump_append_bootargs(void) +{ + char *append_args; + size_t len; + + if (!fw_dump.dump_active || !fw_dump.param_area_supported || !fw_dump.param_area) + return; + + if (fw_dump.param_area >= fw_dump.boot_mem_top) { + if (memblock_reserve(fw_dump.param_area, COMMAND_LINE_SIZE)) { + pr_warn("WARNING: Can't use additional parameters area!\n"); + fw_dump.param_area = 0; + return; + } + } + + append_args = (char *)fw_dump.param_area; + len = strlen(boot_command_line); + + /* + * Too late to fail even if cmdline size exceeds. Truncate additional parameters + * to cmdline size and proceed anyway. + */ + if (len + strlen(append_args) >= COMMAND_LINE_SIZE - 1) + pr_warn("WARNING: Appending parameters exceeds cmdline size. Truncating!\n"); + + pr_debug("Cmdline: %s\n", boot_command_line); + snprintf(boot_command_line + len, COMMAND_LINE_SIZE - len, " %s", append_args); + pr_info("Updated cmdline: %s\n", boot_command_line); +} + /* Scan the Firmware Assisted dump configuration details. */ int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data) @@ -223,28 +256,6 @@ static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end) } /* - * Returns true, if there are no holes in boot memory area, - * false otherwise. - */ -bool is_fadump_boot_mem_contiguous(void) -{ - unsigned long d_start, d_end; - bool ret = false; - int i; - - for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { - d_start = fw_dump.boot_mem_addr[i]; - d_end = d_start + fw_dump.boot_mem_sz[i]; - - ret = is_fadump_mem_area_contiguous(d_start, d_end); - if (!ret) - break; - } - - return ret; -} - -/* * Returns true, if there are no holes in reserved memory area, * false otherwise. */ @@ -373,12 +384,6 @@ static unsigned long __init get_fadump_area_size(void) size = PAGE_ALIGN(size); size += fw_dump.boot_memory_size; size += sizeof(struct fadump_crash_info_header); - size += sizeof(struct elfhdr); /* ELF core header.*/ - size += sizeof(struct elf_phdr); /* place holder for cpu notes */ - /* Program headers for crash memory regions. */ - size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2); - - size = PAGE_ALIGN(size); /* This is to hold kernel metadata on platforms that support it */ size += (fw_dump.ops->fadump_get_metadata_size ? @@ -389,10 +394,11 @@ static unsigned long __init get_fadump_area_size(void) static int __init add_boot_mem_region(unsigned long rstart, unsigned long rsize) { + int max_boot_mem_rgns = fw_dump.ops->fadump_max_boot_mem_rgns(); int i = fw_dump.boot_mem_regs_cnt++; - if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) { - fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS; + if (fw_dump.boot_mem_regs_cnt > max_boot_mem_rgns) { + fw_dump.boot_mem_regs_cnt = max_boot_mem_rgns; return 0; } @@ -573,22 +579,6 @@ int __init fadump_reserve_mem(void) } } - /* - * Calculate the memory boundary. - * If memory_limit is less than actual memory boundary then reserve - * the memory for fadump beyond the memory_limit and adjust the - * memory_limit accordingly, so that the running kernel can run with - * specified memory_limit. - */ - if (memory_limit && memory_limit < memblock_end_of_DRAM()) { - size = get_fadump_area_size(); - if ((memory_limit + size) < memblock_end_of_DRAM()) - memory_limit += size; - else - memory_limit = memblock_end_of_DRAM(); - printk(KERN_INFO "Adjusted memory_limit for firmware-assisted" - " dump, now %#016llx\n", memory_limit); - } if (memory_limit) mem_boundary = memory_limit; else @@ -705,7 +695,7 @@ void crash_fadump(struct pt_regs *regs, const char *str) * old_cpu == -1 means this is the first CPU which has come here, * go ahead and trigger fadump. * - * old_cpu != -1 means some other CPU has already on it's way + * old_cpu != -1 means some other CPU has already on its way * to trigger fadump, just keep looping here. */ this_cpu = smp_processor_id(); @@ -931,36 +921,6 @@ static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info, return 0; } -static int fadump_exclude_reserved_area(u64 start, u64 end) -{ - u64 ra_start, ra_end; - int ret = 0; - - ra_start = fw_dump.reserve_dump_area_start; - ra_end = ra_start + fw_dump.reserve_dump_area_size; - - if ((ra_start < end) && (ra_end > start)) { - if ((start < ra_start) && (end > ra_end)) { - ret = fadump_add_mem_range(&crash_mrange_info, - start, ra_start); - if (ret) - return ret; - - ret = fadump_add_mem_range(&crash_mrange_info, - ra_end, end); - } else if (start < ra_start) { - ret = fadump_add_mem_range(&crash_mrange_info, - start, ra_start); - } else if (ra_end < end) { - ret = fadump_add_mem_range(&crash_mrange_info, - ra_end, end); - } - } else - ret = fadump_add_mem_range(&crash_mrange_info, start, end); - - return ret; -} - static int fadump_init_elfcore_header(char *bufp) { struct elfhdr *elf; @@ -998,52 +958,6 @@ static int fadump_init_elfcore_header(char *bufp) } /* - * Traverse through memblock structure and setup crash memory ranges. These - * ranges will be used create PT_LOAD program headers in elfcore header. - */ -static int fadump_setup_crash_memory_ranges(void) -{ - u64 i, start, end; - int ret; - - pr_debug("Setup crash memory ranges.\n"); - crash_mrange_info.mem_range_cnt = 0; - - /* - * Boot memory region(s) registered with firmware are moved to - * different location at the time of crash. Create separate program - * header(s) for this memory chunk(s) with the correct offset. - */ - for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { - start = fw_dump.boot_mem_addr[i]; - end = start + fw_dump.boot_mem_sz[i]; - ret = fadump_add_mem_range(&crash_mrange_info, start, end); - if (ret) - return ret; - } - - for_each_mem_range(i, &start, &end) { - /* - * skip the memory chunk that is already added - * (0 through boot_memory_top). - */ - if (start < fw_dump.boot_mem_top) { - if (end > fw_dump.boot_mem_top) - start = fw_dump.boot_mem_top; - else - continue; - } - - /* add this range excluding the reserved dump area. */ - ret = fadump_exclude_reserved_area(start, end); - if (ret) - return ret; - } - - return 0; -} - -/* * If the given physical address falls within the boot memory region then * return the relocated address that points to the dump region reserved * for saving initial boot memory contents. @@ -1073,36 +987,50 @@ static inline unsigned long fadump_relocate(unsigned long paddr) return raddr; } -static int fadump_create_elfcore_headers(char *bufp) +static void __init populate_elf_pt_load(struct elf_phdr *phdr, u64 start, + u64 size, unsigned long long offset) { - unsigned long long raddr, offset; - struct elf_phdr *phdr; + phdr->p_align = 0; + phdr->p_memsz = size; + phdr->p_filesz = size; + phdr->p_paddr = start; + phdr->p_offset = offset; + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R|PF_W|PF_X; + phdr->p_vaddr = (unsigned long)__va(start); +} + +static void __init fadump_populate_elfcorehdr(struct fadump_crash_info_header *fdh) +{ + char *bufp; struct elfhdr *elf; - int i, j; + struct elf_phdr *phdr; + u64 boot_mem_dest_offset; + unsigned long long i, ra_start, ra_end, ra_size, mstart, mend; + bufp = (char *) fw_dump.elfcorehdr_addr; fadump_init_elfcore_header(bufp); elf = (struct elfhdr *)bufp; bufp += sizeof(struct elfhdr); /* - * setup ELF PT_NOTE, place holder for cpu notes info. The notes info - * will be populated during second kernel boot after crash. Hence - * this PT_NOTE will always be the first elf note. + * Set up ELF PT_NOTE, a placeholder for CPU notes information. + * The notes info will be populated later by platform-specific code. + * Hence, this PT_NOTE will always be the first ELF note. * * NOTE: Any new ELF note addition should be placed after this note. */ phdr = (struct elf_phdr *)bufp; bufp += sizeof(struct elf_phdr); phdr->p_type = PT_NOTE; - phdr->p_flags = 0; - phdr->p_vaddr = 0; - phdr->p_align = 0; - - phdr->p_offset = 0; - phdr->p_paddr = 0; - phdr->p_filesz = 0; - phdr->p_memsz = 0; - + phdr->p_flags = 0; + phdr->p_vaddr = 0; + phdr->p_align = 0; + phdr->p_offset = 0; + phdr->p_paddr = 0; + phdr->p_filesz = 0; + phdr->p_memsz = 0; + /* Increment number of program headers. */ (elf->e_phnum)++; /* setup ELF PT_NOTE for vmcoreinfo */ @@ -1112,55 +1040,66 @@ static int fadump_create_elfcore_headers(char *bufp) phdr->p_flags = 0; phdr->p_vaddr = 0; phdr->p_align = 0; - - phdr->p_paddr = fadump_relocate(paddr_vmcoreinfo_note()); - phdr->p_offset = phdr->p_paddr; - phdr->p_memsz = phdr->p_filesz = VMCOREINFO_NOTE_SIZE; - + phdr->p_paddr = phdr->p_offset = fdh->vmcoreinfo_raddr; + phdr->p_memsz = phdr->p_filesz = fdh->vmcoreinfo_size; /* Increment number of program headers. */ (elf->e_phnum)++; - /* setup PT_LOAD sections. */ - j = 0; - offset = 0; - raddr = fw_dump.boot_mem_addr[0]; - for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) { - u64 mbase, msize; - - mbase = crash_mrange_info.mem_ranges[i].base; - msize = crash_mrange_info.mem_ranges[i].size; - if (!msize) - continue; - + /* + * Setup PT_LOAD sections. first include boot memory regions + * and then add rest of the memory regions. + */ + boot_mem_dest_offset = fw_dump.boot_mem_dest_addr; + for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { phdr = (struct elf_phdr *)bufp; bufp += sizeof(struct elf_phdr); - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_offset = mbase; - - if (mbase == raddr) { - /* - * The entire real memory region will be moved by - * firmware to the specified destination_address. - * Hence set the correct offset. - */ - phdr->p_offset = fw_dump.boot_mem_dest_addr + offset; - if (j < (fw_dump.boot_mem_regs_cnt - 1)) { - offset += fw_dump.boot_mem_sz[j]; - raddr = fw_dump.boot_mem_addr[++j]; - } + populate_elf_pt_load(phdr, fw_dump.boot_mem_addr[i], + fw_dump.boot_mem_sz[i], + boot_mem_dest_offset); + /* Increment number of program headers. */ + (elf->e_phnum)++; + boot_mem_dest_offset += fw_dump.boot_mem_sz[i]; + } + + /* Memory reserved for fadump in first kernel */ + ra_start = fw_dump.reserve_dump_area_start; + ra_size = get_fadump_area_size(); + ra_end = ra_start + ra_size; + + phdr = (struct elf_phdr *)bufp; + for_each_mem_range(i, &mstart, &mend) { + /* Boot memory regions already added, skip them now */ + if (mstart < fw_dump.boot_mem_top) { + if (mend > fw_dump.boot_mem_top) + mstart = fw_dump.boot_mem_top; + else + continue; } - phdr->p_paddr = mbase; - phdr->p_vaddr = (unsigned long)__va(mbase); - phdr->p_filesz = msize; - phdr->p_memsz = msize; - phdr->p_align = 0; + /* Handle memblock regions overlaps with fadump reserved area */ + if ((ra_start < mend) && (ra_end > mstart)) { + if ((mstart < ra_start) && (mend > ra_end)) { + populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart); + /* Increment number of program headers. */ + (elf->e_phnum)++; + bufp += sizeof(struct elf_phdr); + phdr = (struct elf_phdr *)bufp; + populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end); + } else if (mstart < ra_start) { + populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart); + } else if (ra_end < mend) { + populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end); + } + } else { + /* No overlap with fadump reserved memory region */ + populate_elf_pt_load(phdr, mstart, mend - mstart, mstart); + } /* Increment number of program headers. */ (elf->e_phnum)++; + bufp += sizeof(struct elf_phdr); + phdr = (struct elf_phdr *) bufp; } - return 0; } static unsigned long init_fadump_header(unsigned long addr) @@ -1175,14 +1114,25 @@ static unsigned long init_fadump_header(unsigned long addr) memset(fdh, 0, sizeof(struct fadump_crash_info_header)); fdh->magic_number = FADUMP_CRASH_INFO_MAGIC; - fdh->elfcorehdr_addr = addr; + fdh->version = FADUMP_HEADER_VERSION; /* We will set the crashing cpu id in crash_fadump() during crash. */ fdh->crashing_cpu = FADUMP_CPU_UNKNOWN; + + /* + * The physical address and size of vmcoreinfo are required in the + * second kernel to prepare elfcorehdr. + */ + fdh->vmcoreinfo_raddr = fadump_relocate(paddr_vmcoreinfo_note()); + fdh->vmcoreinfo_size = VMCOREINFO_NOTE_SIZE; + + + fdh->pt_regs_sz = sizeof(struct pt_regs); /* * When LPAR is terminated by PYHP, ensure all possible CPUs' * register data is processed while exporting the vmcore. */ fdh->cpu_mask = *cpu_possible_mask; + fdh->cpu_mask_sz = sizeof(struct cpumask); return addr; } @@ -1190,8 +1140,6 @@ static unsigned long init_fadump_header(unsigned long addr) static int register_fadump(void) { unsigned long addr; - void *vaddr; - int ret; /* * If no memory is reserved then we can not register for firmware- @@ -1200,18 +1148,10 @@ static int register_fadump(void) if (!fw_dump.reserve_dump_area_size) return -ENODEV; - ret = fadump_setup_crash_memory_ranges(); - if (ret) - return ret; - addr = fw_dump.fadumphdr_addr; /* Initialize fadump crash info header. */ addr = init_fadump_header(addr); - vaddr = __va(addr); - - pr_debug("Creating ELF core headers at %#016lx\n", addr); - fadump_create_elfcore_headers(vaddr); /* register the future kernel dump with firmware. */ pr_debug("Registering for firmware-assisted kernel dump...\n"); @@ -1230,7 +1170,6 @@ void fadump_cleanup(void) } else if (fw_dump.dump_registered) { /* Un-register Firmware-assisted dump if it was registered. */ fw_dump.ops->fadump_unregister(&fw_dump); - fadump_free_mem_ranges(&crash_mrange_info); } if (fw_dump.ops->fadump_cleanup) @@ -1416,6 +1355,22 @@ static void fadump_release_memory(u64 begin, u64 end) fadump_release_reserved_area(tstart, end); } +static void fadump_free_elfcorehdr_buf(void) +{ + if (fw_dump.elfcorehdr_addr == 0 || fw_dump.elfcorehdr_size == 0) + return; + + /* + * Before freeing the memory of `elfcorehdr`, reset the global + * `elfcorehdr_addr` to prevent modules like `vmcore` from accessing + * invalid memory. + */ + elfcorehdr_addr = ELFCORE_ADDR_ERR; + fadump_free_buffer(fw_dump.elfcorehdr_addr, fw_dump.elfcorehdr_size); + fw_dump.elfcorehdr_addr = 0; + fw_dump.elfcorehdr_size = 0; +} + static void fadump_invalidate_release_mem(void) { mutex_lock(&fadump_mutex); @@ -1427,6 +1382,7 @@ static void fadump_invalidate_release_mem(void) fadump_cleanup(); mutex_unlock(&fadump_mutex); + fadump_free_elfcorehdr_buf(); fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM()); fadump_free_cpu_notes_buf(); @@ -1484,6 +1440,18 @@ static ssize_t enabled_show(struct kobject *kobj, return sprintf(buf, "%d\n", fw_dump.fadump_enabled); } +/* + * /sys/kernel/fadump/hotplug_ready sysfs node returns 1, which inidcates + * to usersapce that fadump re-registration is not required on memory + * hotplug events. + */ +static ssize_t hotplug_ready_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", 1); +} + static ssize_t mem_reserved_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -1498,6 +1466,43 @@ static ssize_t registered_show(struct kobject *kobj, return sprintf(buf, "%d\n", fw_dump.dump_registered); } +static ssize_t bootargs_append_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%s\n", (char *)__va(fw_dump.param_area)); +} + +static ssize_t bootargs_append_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + char *params; + + if (!fw_dump.fadump_enabled || fw_dump.dump_active) + return -EPERM; + + if (count >= COMMAND_LINE_SIZE) + return -EINVAL; + + /* + * Fail here instead of handling this scenario with + * some silly workaround in capture kernel. + */ + if (saved_command_line_len + count >= COMMAND_LINE_SIZE) { + pr_err("Appending parameters exceeds cmdline size!\n"); + return -ENOSPC; + } + + params = __va(fw_dump.param_area); + strscpy_pad(params, buf, COMMAND_LINE_SIZE); + /* Remove newline character at the end. */ + if (params[count-1] == '\n') + params[count-1] = '\0'; + + return count; +} + static ssize_t registered_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) @@ -1556,11 +1561,14 @@ static struct kobj_attribute release_attr = __ATTR_WO(release_mem); static struct kobj_attribute enable_attr = __ATTR_RO(enabled); static struct kobj_attribute register_attr = __ATTR_RW(registered); static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved); +static struct kobj_attribute hotplug_ready_attr = __ATTR_RO(hotplug_ready); +static struct kobj_attribute bootargs_append_attr = __ATTR_RW(bootargs_append); static struct attribute *fadump_attrs[] = { &enable_attr.attr, ®ister_attr.attr, &mem_reserved_attr.attr, + &hotplug_ready_attr.attr, NULL, }; @@ -1632,6 +1640,150 @@ static void __init fadump_init_files(void) return; } +static int __init fadump_setup_elfcorehdr_buf(void) +{ + int elf_phdr_cnt; + unsigned long elfcorehdr_size; + + /* + * Program header for CPU notes comes first, followed by one for + * vmcoreinfo, and the remaining program headers correspond to + * memory regions. + */ + elf_phdr_cnt = 2 + fw_dump.boot_mem_regs_cnt + memblock_num_regions(memory); + elfcorehdr_size = sizeof(struct elfhdr) + (elf_phdr_cnt * sizeof(struct elf_phdr)); + elfcorehdr_size = PAGE_ALIGN(elfcorehdr_size); + + fw_dump.elfcorehdr_addr = (u64)fadump_alloc_buffer(elfcorehdr_size); + if (!fw_dump.elfcorehdr_addr) { + pr_err("Failed to allocate %lu bytes for elfcorehdr\n", + elfcorehdr_size); + return -ENOMEM; + } + fw_dump.elfcorehdr_size = elfcorehdr_size; + return 0; +} + +/* + * Check if the fadump header of crashed kernel is compatible with fadump kernel. + * + * It checks the magic number, endianness, and size of non-primitive type + * members of fadump header to ensure safe dump collection. + */ +static bool __init is_fadump_header_compatible(struct fadump_crash_info_header *fdh) +{ + if (fdh->magic_number == FADUMP_CRASH_INFO_MAGIC_OLD) { + pr_err("Old magic number, can't process the dump.\n"); + return false; + } + + if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { + if (fdh->magic_number == swab64(FADUMP_CRASH_INFO_MAGIC)) + pr_err("Endianness mismatch between the crashed and fadump kernels.\n"); + else + pr_err("Fadump header is corrupted.\n"); + + return false; + } + + /* + * Dump collection is not safe if the size of non-primitive type members + * of the fadump header do not match between crashed and fadump kernel. + */ + if (fdh->pt_regs_sz != sizeof(struct pt_regs) || + fdh->cpu_mask_sz != sizeof(struct cpumask)) { + pr_err("Fadump header size mismatch.\n"); + return false; + } + + return true; +} + +static void __init fadump_process(void) +{ + struct fadump_crash_info_header *fdh; + + fdh = (struct fadump_crash_info_header *) __va(fw_dump.fadumphdr_addr); + if (!fdh) { + pr_err("Crash info header is empty.\n"); + goto err_out; + } + + /* Avoid processing the dump if fadump header isn't compatible */ + if (!is_fadump_header_compatible(fdh)) + goto err_out; + + /* Allocate buffer for elfcorehdr */ + if (fadump_setup_elfcorehdr_buf()) + goto err_out; + + fadump_populate_elfcorehdr(fdh); + + /* Let platform update the CPU notes in elfcorehdr */ + if (fw_dump.ops->fadump_process(&fw_dump) < 0) + goto err_out; + + /* + * elfcorehdr is now ready to be exported. + * + * set elfcorehdr_addr so that vmcore module will export the + * elfcorehdr through '/proc/vmcore'. + */ + elfcorehdr_addr = virt_to_phys((void *)fw_dump.elfcorehdr_addr); + return; + +err_out: + fadump_invalidate_release_mem(); +} + +/* + * Reserve memory to store additional parameters to be passed + * for fadump/capture kernel. + */ +static void __init fadump_setup_param_area(void) +{ + phys_addr_t range_start, range_end; + + if (!fw_dump.param_area_supported || fw_dump.dump_active) + return; + + /* This memory can't be used by PFW or bootloader as it is shared across kernels */ + if (radix_enabled()) { + /* + * Anywhere in the upper half should be good enough as all memory + * is accessible in real mode. + */ + range_start = memblock_end_of_DRAM() / 2; + range_end = memblock_end_of_DRAM(); + } else { + /* + * Passing additional parameters is supported for hash MMU only + * if the first memory block size is 768MB or higher. + */ + if (ppc64_rma_size < 0x30000000) + return; + + /* + * 640 MB to 768 MB is not used by PFW/bootloader. So, try reserving + * memory for passing additional parameters in this range to avoid + * being stomped on by PFW/bootloader. + */ + range_start = 0x2A000000; + range_end = range_start + 0x4000000; + } + + fw_dump.param_area = memblock_phys_alloc_range(COMMAND_LINE_SIZE, + COMMAND_LINE_SIZE, + range_start, + range_end); + if (!fw_dump.param_area || sysfs_create_file(fadump_kobj, &bootargs_append_attr.attr)) { + pr_warn("WARNING: Could not setup area to pass additional parameters!\n"); + return; + } + + memset(phys_to_virt(fw_dump.param_area), 0, COMMAND_LINE_SIZE); +} + /* * Prepare for firmware-assisted dump. */ @@ -1651,15 +1803,11 @@ int __init setup_fadump(void) * saving it to the disk. */ if (fw_dump.dump_active) { - /* - * if dump process fails then invalidate the registration - * and release memory before proceeding for re-registration. - */ - if (fw_dump.ops->fadump_process(&fw_dump) < 0) - fadump_invalidate_release_mem(); + fadump_process(); } /* Initialize the kernel dump memory structure and register with f/w */ else if (fw_dump.reserve_dump_area_size) { + fadump_setup_param_area(); fw_dump.ops->fadump_init_mem_struct(&fw_dump); register_fadump(); } @@ -1735,8 +1883,3 @@ static void __init fadump_reserve_crash_area(u64 base) memblock_reserve(mstart, msize); } } - -unsigned long __init arch_reserved_kernel_pages(void) -{ - return memblock_reserved_size() / PAGE_SIZE; -} diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 647b0b445e89..edc479a7c2bc 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -199,12 +199,12 @@ instruction_counter: mfspr r10, SPRN_SRR0 /* Get effective address of fault */ INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11) mtspr SPRN_MD_EPN, r10 -#ifdef CONFIG_MODULES +#ifdef CONFIG_EXECMEM mfcr r11 compare_to_kernel_boundary r10, r10 #endif mfspr r10, SPRN_M_TWB /* Get level 1 table */ -#ifdef CONFIG_MODULES +#ifdef CONFIG_EXECMEM blt+ 3f rlwinm r10, r10, 0, 20, 31 oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index c1d89764dd22..57196883a00e 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -419,14 +419,14 @@ InstructionTLBMiss: */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_IMISS -#ifdef CONFIG_MODULES +#ifdef CONFIG_EXECMEM lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 #endif mfspr r2, SPRN_SDR1 li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC rlwinm r2, r2, 28, 0xfffff000 -#ifdef CONFIG_MODULES +#ifdef CONFIG_EXECMEM li r0, 3 bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ @@ -442,7 +442,7 @@ InstructionTLBMiss: andc. r1,r1,r2 /* check access & ~permission */ bne- InstructionAddressInvalid /* return if access not permitted */ /* Convert linux-style PTE to low word of PPC-style PTE */ -#ifdef CONFIG_MODULES +#ifdef CONFIG_EXECMEM rlwimi r2, r0, 0, 31, 31 /* userspace ? -> PP lsb */ #endif ori r1, r1, 0xe06 /* clear out reserved bits */ diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 1185efebf032..b70b4f93561f 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -26,6 +26,7 @@ #include <linux/iommu.h> #include <linux/sched.h> #include <linux/debugfs.h> +#include <linux/vmalloc.h> #include <asm/io.h> #include <asm/iommu.h> #include <asm/pci-bridge.h> @@ -1285,15 +1286,14 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, struct device *dev) { struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - struct iommu_group *grp = iommu_group_get(dev); struct iommu_table_group *table_group; + struct iommu_group *grp; /* At first attach the ownership is already set */ - if (!domain) { - iommu_group_put(grp); + if (!domain) return 0; - } + grp = iommu_group_get(dev); table_group = iommu_group_get_iommudata(grp); /* * The domain being set to PLATFORM from earlier diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 072ebe7f290b..f8208c027148 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct pt_regs *regs; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(nip, parent_nip); if (bit < 0) return; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index bbca90a5e2ec..14c5ddec3056 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -19,8 +19,8 @@ #include <linux/extable.h> #include <linux/kdebug.h> #include <linux/slab.h> -#include <linux/moduleloader.h> #include <linux/set_memory.h> +#include <linux/execmem.h> #include <asm/code-patching.h> #include <asm/cacheflush.h> #include <asm/sstep.h> @@ -126,26 +126,6 @@ kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offse return (kprobe_opcode_t *)(addr + offset); } -void *alloc_insn_page(void) -{ - void *page; - - page = module_alloc(PAGE_SIZE); - if (!page) - return NULL; - - if (strict_module_rwx_enabled()) { - int err = set_memory_rox((unsigned long)page, 1); - - if (err) - goto error; - } - return page; -error: - module_memfree(page); - return NULL; -} - int arch_prepare_kprobe(struct kprobe *p) { int ret = 0; diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 1a8cdafd68e8..91123e102db4 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -192,7 +192,7 @@ _GLOBAL(scom970_read) xori r0,r0,MSR_EE mtmsrd r0,1 - /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits + /* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits * (including parity). On current CPUs they must be 0'd, * and finally or in RW bit */ @@ -226,7 +226,7 @@ _GLOBAL(scom970_write) xori r0,r0,MSR_EE mtmsrd r0,1 - /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits + /* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits * (including parity). On current CPUs they must be 0'd. */ diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index f6d6ae0a1692..baeb24c102c8 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -7,7 +7,6 @@ #include <linux/elf.h> #include <linux/moduleloader.h> #include <linux/err.h> -#include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/bug.h> #include <asm/module.h> @@ -17,8 +16,6 @@ #include <asm/setup.h> #include <asm/sections.h> -static LIST_HEAD(module_bug_list); - static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, const char *name) @@ -88,40 +85,3 @@ int module_finalize(const Elf_Ehdr *hdr, return 0; } - -static __always_inline void * -__module_alloc(unsigned long size, unsigned long start, unsigned long end, bool nowarn) -{ - pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC; - gfp_t gfp = GFP_KERNEL | (nowarn ? __GFP_NOWARN : 0); - - /* - * Don't do huge page allocations for modules yet until more testing - * is done. STRICT_MODULE_RWX may require extra work to support this - * too. - */ - return __vmalloc_node_range(size, 1, start, end, gfp, prot, - VM_FLUSH_RESET_PERMS, - NUMA_NO_NODE, __builtin_return_address(0)); -} - -void *module_alloc(unsigned long size) -{ -#ifdef MODULES_VADDR - unsigned long limit = (unsigned long)_etext - SZ_32M; - void *ptr = NULL; - - BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR); - - /* First try within 32M limit from _etext to avoid branch trampolines */ - if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) - ptr = __module_alloc(size, limit, MODULES_END, true); - - if (!ptr) - ptr = __module_alloc(size, MODULES_VADDR, MODULES_END, false); - - return ptr; -#else - return __module_alloc(size, VMALLOC_START, VMALLOC_END, false); -#endif -} diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index d95a48eff412..eac84d687b53 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -517,7 +517,7 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma) } /* - * This one is used by /dev/mem and fbdev who have no clue about the + * This one is used by /dev/mem and video who have no clue about the * PCI device, it tries to find the PCI device first and calls the * above routine */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9452a54d356c..a7671786764b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1185,6 +1185,9 @@ static inline void save_sprs(struct thread_struct *t) if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) t->hashkeyr = mfspr(SPRN_HASHKEYR); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + t->dexcr = mfspr(SPRN_DEXCR); #endif } @@ -1267,6 +1270,10 @@ static inline void restore_sprs(struct thread_struct *old_thread, if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && old_thread->hashkeyr != new_thread->hashkeyr) mtspr(SPRN_HASHKEYR, new_thread->hashkeyr); + + if (cpu_has_feature(CPU_FTR_ARCH_31) && + old_thread->dexcr != new_thread->dexcr) + mtspr(SPRN_DEXCR, new_thread->dexcr); #endif } @@ -1634,6 +1641,13 @@ void arch_setup_new_exec(void) current->thread.regs->amr = default_amr; current->thread.regs->iamr = default_iamr; #endif + +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + current->thread.dexcr = current->thread.dexcr_onexec; + mtspr(SPRN_DEXCR, current->thread.dexcr); + } +#endif /* CONFIG_PPC_BOOK3S_64 */ } #ifdef CONFIG_PPC64 @@ -1647,7 +1661,7 @@ void arch_setup_new_exec(void) * cases will happen: * * 1. The correct thread is running, the wrong thread is not - * In this situation, the correct thread is woken and proceeds to pass it's + * In this situation, the correct thread is woken and proceeds to pass its * condition check. * * 2. Neither threads are running @@ -1657,15 +1671,15 @@ void arch_setup_new_exec(void) * for the wrong thread, or they will execute the condition check immediately. * * 3. The wrong thread is running, the correct thread is not - * The wrong thread will be woken, but will fail it's condition check and + * The wrong thread will be woken, but will fail its condition check and * re-execute wait. The correct thread, when scheduled, will execute either - * it's condition check (which will pass), or wait, which returns immediately - * when called the first time after the thread is scheduled, followed by it's + * its condition check (which will pass), or wait, which returns immediately + * when called the first time after the thread is scheduled, followed by its * condition check (which will pass). * * 4. Both threads are running - * Both threads will be woken. The wrong thread will fail it's condition check - * and execute another wait, while the correct thread will pass it's condition + * Both threads will be woken. The wrong thread will fail its condition check + * and execute another wait, while the correct thread will pass its condition * check. * * @t: the task to set the thread ID for @@ -1878,6 +1892,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) #ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) p->thread.hashkeyr = current->thread.hashkeyr; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + p->thread.dexcr = mfspr(SPRN_DEXCR); #endif return 0; } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index cd8d8883de90..60819751e55e 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -779,7 +779,7 @@ static inline void save_fscr_to_task(void) {} void __init early_init_devtree(void *params) { - phys_addr_t limit; + phys_addr_t int_vector_size; DBG(" -> early_init_devtree(%px)\n", params); @@ -813,6 +813,9 @@ void __init early_init_devtree(void *params) */ of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line); + /* Append additional parameters passed for fadump capture kernel */ + fadump_append_bootargs(); + /* Scan memory nodes and rebuild MEMBLOCKs */ early_init_dt_scan_root(); early_init_dt_scan_memory_ppc(); @@ -832,9 +835,16 @@ void __init early_init_devtree(void *params) setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ memblock_reserve(PHYSICAL_START, __pa(_end) - PHYSICAL_START); +#ifdef CONFIG_PPC64 + /* If relocatable, reserve at least 32k for interrupt vectors etc. */ + int_vector_size = __end_interrupts - _stext; + int_vector_size = max_t(phys_addr_t, SZ_32K, int_vector_size); +#else /* If relocatable, reserve first 32k for interrupt vectors etc. */ + int_vector_size = SZ_32K; +#endif if (PHYSICAL_START > MEMORY_START) - memblock_reserve(MEMORY_START, 0x8000); + memblock_reserve(MEMORY_START, int_vector_size); reserve_kdump_trampoline(); #if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) /* @@ -846,9 +856,12 @@ void __init early_init_devtree(void *params) reserve_crashkernel(); early_reserve_mem(); - /* Ensure that total memory size is page-aligned. */ - limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); - memblock_enforce_memory_limit(limit); + if (memory_limit > memblock_phys_mem_size()) + memory_limit = 0; + + /* Align down to 16 MB which is large page size with hash page translation */ + memory_limit = ALIGN_DOWN(memory_limit ?: memblock_phys_mem_size(), SZ_16M); + memblock_enforce_memory_limit(memory_limit); #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES) if (!early_radix_enabled()) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0ef358285337..fbb68fc28ed3 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -817,8 +817,8 @@ static void __init early_cmdline_parse(void) opt += 4; prom_memory_limit = prom_memparse(opt, (const char **)&opt); #ifdef CONFIG_PPC64 - /* Align to 16 MB == size of ppc64 large page */ - prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000); + /* Align down to 16 MB which is large page size with hash page translation */ + prom_memory_limit = ALIGN_DOWN(prom_memory_limit, SZ_16M); #endif } diff --git a/arch/powerpc/kernel/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c index 210ea834e603..447bff87fd21 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-tm.c +++ b/arch/powerpc/kernel/ptrace/ptrace-tm.c @@ -12,7 +12,7 @@ void flush_tmregs_to_thread(struct task_struct *tsk) { /* * If task is not current, it will have been flushed already to - * it's thread_struct during __switch_to(). + * its thread_struct during __switch_to(). * * A reclaim flushes ALL the state or if not in TM save TM SPRs * in the appropriate thread structures from live. diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index 584cf5c3df50..c1819e0a6684 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -469,12 +469,7 @@ static int dexcr_get(struct task_struct *target, const struct user_regset *regse if (!cpu_has_feature(CPU_FTR_ARCH_31)) return -ENODEV; - /* - * The DEXCR is currently static across all CPUs, so we don't - * store the target's value anywhere, but the static value - * will also be correct. - */ - membuf_store(&to, (u64)lower_32_bits(DEXCR_INIT)); + membuf_store(&to, (u64)lower_32_bits(target->thread.dexcr)); /* * Technically the HDEXCR is per-cpu, but a hypervisor can't reasonably diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 01ed1263e1a9..4bd2f87616ba 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -405,7 +405,7 @@ static void __init cpu_init_thread_core_maps(int tpc) cpumask_set_cpu(i, &threads_core_mask); printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n", - tpc, tpc > 1 ? "s" : ""); + tpc, str_plural(tpc)); printk(KERN_DEBUG " (thread shift is %d)\n", threads_shift); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2f19d5e94485..ae36a129789f 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -834,6 +834,7 @@ static __init int pcpu_cpu_to_node(int cpu) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); +DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged); void __init setup_per_cpu_areas(void) { @@ -876,6 +877,7 @@ void __init setup_per_cpu_areas(void) if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); + static_key_enable(&__percpu_first_chunk_is_paged.key); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) { __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 12e53b3d7923..46e6d2cd7a2d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1567,7 +1567,7 @@ static void add_cpu_to_masks(int cpu) /* * This CPU will not be in the online mask yet so we need to manually - * add it to it's own thread sibling mask. + * add it to its own thread sibling mask. */ map_cpu_to_node(cpu, cpu_to_node(cpu)); cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 17173b82ca21..3656f1ca7a21 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -548,3 +548,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 0f39a6b84132..b842c83ab497 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -139,7 +139,7 @@ static unsigned long dscr_default; * @val: Returned cpu specific DSCR default value * * This function returns the per cpu DSCR default value - * for any cpu which is contained in it's PACA structure. + * for any cpu which is contained in its PACA structure. */ static void read_dscr(void *val) { @@ -152,7 +152,7 @@ static void read_dscr(void *val) * @val: New cpu specific DSCR default value to update * * This function updates the per cpu DSCR default value - * for any cpu which is contained in it's PACA structure. + * for any cpu which is contained in its PACA structure. */ static void write_dscr(void *val) { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index df20cf201f74..c0fdc6d94fee 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -354,6 +354,28 @@ void vtime_flush(struct task_struct *tsk) acct->hardirq_time = 0; acct->softirq_time = 0; } + +/* + * Called from the context switch with interrupts disabled, to charge all + * accumulated times to the current process, and to prepare accounting on + * the next process. + */ +void vtime_task_switch(struct task_struct *prev) +{ + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + vtime_account_kernel(prev); + + vtime_flush(prev); + + if (!IS_ENABLED(CONFIG_PPC64)) { + struct cpu_accounting_data *acct = get_accounting(current); + struct cpu_accounting_data *acct0 = get_accounting(prev); + + acct->starttime = acct0->starttime; + } +} #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ void __no_kcsan __delay(unsigned long loops) diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 1b93655c2857..1425b6edc66b 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -47,12 +47,6 @@ obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) -GCOV_PROFILE := n -KCOV_INSTRUMENT := n -UBSAN_SANITIZE := n -KASAN_SANITIZE := n -KCSAN_SANITIZE := n - ccflags-y := -fno-common -fno-builtin ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack $(CLANG_FLAGS) ldflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld) @@ -74,9 +68,9 @@ targets += vdso64.lds CPPFLAGS_vdso64.lds += -P -C # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE +$(obj)/vdso32.so.dbg: $(obj)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE $(call if_changed,vdso32ld_and_check) -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE +$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE $(call if_changed,vdso64ld_and_check) # assembly rules for the .S files @@ -90,10 +84,10 @@ $(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE $(call if_changed_dep,cc_o_c) # Generate VDSO offsets using helper script -gen-vdso32sym := $(srctree)/$(src)/gen_vdso32_offsets.sh +gen-vdso32sym := $(src)/gen_vdso32_offsets.sh quiet_cmd_vdso32sym = VDSO32SYM $@ cmd_vdso32sym = $(NM) $< | $(gen-vdso32sym) | LC_ALL=C sort > $@ -gen-vdso64sym := $(srctree)/$(src)/gen_vdso64_offsets.sh +gen-vdso64sym := $(src)/gen_vdso64_offsets.sh quiet_cmd_vdso64sym = VDSO64SYM $@ cmd_vdso64sym = $(NM) $< | $(gen-vdso64sym) | LC_ALL=C sort > $@ @@ -114,5 +108,3 @@ quiet_cmd_vdso64ld_and_check = VDSO64L $@ cmd_vdso64ld_and_check = $(VDSOCC) $(ldflags-y) $(LD64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check) quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(VDSOCC) $(a_flags) $(AS64FLAGS) -c -o $@ $< - -OBJECT_FILES_NON_STANDARD := y |