diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2018-04-13 12:19:30 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2018-04-13 12:19:30 +1000 |
commit | 41d08c47b95dbdf15ba9030092042c8adda96ab1 (patch) | |
tree | 29c414c151c23544cdb5e2ef61f0ee9d54e5fadd | |
parent | c0a3c4ac336f5d9009b1569982c6b02c72dc729a (diff) | |
parent | 2f74fd9f6655229b70f488fdab65ec3df14d863a (diff) |
Merge branch 'akpm/master'
33 files changed, 832 insertions, 673 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 73ce5dd07642..c32a181a7cbb 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -552,6 +552,9 @@ config KEXEC_FILE for kernel and initramfs as opposed to a list of segments as is the case for the older kexec call. +config ARCH_HAS_KEXEC_PURGATORY + def_bool KEXEC_FILE + config RELOCATABLE bool "Build a relocatable kernel" depends on PPC64 || (FLATMEM && (44x || FSL_BOOKE)) diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index d8b1e8e7e035..4a585cba1787 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -95,7 +95,7 @@ static inline bool kdump_in_progress(void) } #ifdef CONFIG_KEXEC_FILE -extern struct kexec_file_ops kexec_elf64_ops; +extern const struct kexec_file_ops kexec_elf64_ops; #ifdef CONFIG_IMA_KEXEC #define ARCH_HAS_KIMAGE_ARCH diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c index 9a42309b091a..ba4f18a43ee8 100644 --- a/arch/powerpc/kernel/kexec_elf_64.c +++ b/arch/powerpc/kernel/kexec_elf_64.c @@ -572,7 +572,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, { int ret; unsigned int fdt_size; - unsigned long kernel_load_addr, purgatory_load_addr; + unsigned long kernel_load_addr; unsigned long initrd_load_addr = 0, fdt_load_addr; void *fdt; const void *slave_code; @@ -580,6 +580,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, struct elf_info elf_info; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ppc64_rma_size }; + struct kexec_buf pbuf = { .image = image, .buf_min = 0, + .buf_max = ppc64_rma_size, .top_down = true }; ret = build_elf_exec_info(kernel_buf, kernel_len, &ehdr, &elf_info); if (ret) @@ -591,14 +593,13 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr); - ret = kexec_load_purgatory(image, 0, ppc64_rma_size, true, - &purgatory_load_addr); + ret = kexec_load_purgatory(image, &pbuf); if (ret) { pr_err("Loading purgatory failed.\n"); goto out; } - pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr); + pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); if (initrd != NULL) { kbuf.buffer = initrd; @@ -657,7 +658,7 @@ out: return ret ? ERR_PTR(ret) : fdt; } -struct kexec_file_ops kexec_elf64_ops = { +const struct kexec_file_ops kexec_elf64_ops = { .probe = elf64_probe, .load = elf64_load, }; diff --git a/arch/powerpc/kernel/machine_kexec_file_64.c b/arch/powerpc/kernel/machine_kexec_file_64.c index 45e0b7d5f200..0bd23dc789a4 100644 --- a/arch/powerpc/kernel/machine_kexec_file_64.c +++ b/arch/powerpc/kernel/machine_kexec_file_64.c @@ -31,52 +31,19 @@ #define SLAVE_CODE_SIZE 256 -static struct kexec_file_ops *kexec_file_loaders[] = { +const struct kexec_file_ops * const kexec_file_loaders[] = { &kexec_elf64_ops, + NULL }; int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len) { - int i, ret = -ENOEXEC; - struct kexec_file_ops *fops; - /* We don't support crash kernels yet. */ if (image->type == KEXEC_TYPE_CRASH) return -EOPNOTSUPP; - for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { - fops = kexec_file_loaders[i]; - if (!fops || !fops->probe) - continue; - - ret = fops->probe(buf, buf_len); - if (!ret) { - image->fops = fops; - return ret; - } - } - - return ret; -} - -void *arch_kexec_kernel_image_load(struct kimage *image) -{ - if (!image->fops || !image->fops->load) - return ERR_PTR(-ENOEXEC); - - return image->fops->load(image, image->kernel_buf, - image->kernel_buf_len, image->initrd_buf, - image->initrd_buf_len, image->cmdline_buf, - image->cmdline_buf_len); -} - -int arch_kimage_file_post_load_cleanup(struct kimage *image) -{ - if (!image->fops || !image->fops->cleanup) - return 0; - - return image->fops->cleanup(image->image_loader_data); + return kexec_image_probe_default(image, buf, buf_len); } /** diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S index f81ee5419e2c..d0c4d195fd40 100644 --- a/arch/sparc/lib/NG4memset.S +++ b/arch/sparc/lib/NG4memset.S @@ -14,14 +14,14 @@ .globl NG4memset NG4memset: andcc %o1, 0xff, %o4 - be,pt %icc, 1f + be,pt %xcc, 1f mov %o2, %o1 sllx %o4, 8, %g1 or %g1, %o4, %o2 sllx %o2, 16, %g1 or %g1, %o2, %o2 sllx %o2, 32, %g1 - ba,pt %icc, 1f + ba,pt %xcc, 1f or %g1, %o2, %o4 .size NG4memset,.-NG4memset @@ -30,7 +30,7 @@ NG4memset: NG4bzero: clr %o4 1: cmp %o1, 16 - ble %icc, .Ltiny + ble %xcc, .Ltiny mov %o0, %o3 sub %g0, %o0, %g1 and %g1, 0x7, %g1 @@ -38,7 +38,7 @@ NG4bzero: sub %o1, %g1, %o1 1: stb %o4, [%o0 + 0x00] subcc %g1, 1, %g1 - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 1, %o0 .Laligned8: cmp %o1, 64 + (64 - 8) @@ -49,7 +49,7 @@ NG4bzero: sub %o1, %g1, %o1 1: stx %o4, [%o0 + 0x00] subcc %g1, 8, %g1 - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x8, %o0 .Laligned64: andn %o1, 64 - 1, %g1 @@ -59,30 +59,30 @@ NG4bzero: 1: stxa %o4, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P subcc %g1, 0x40, %g1 stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x40, %o0 .Lpostloop: cmp %o1, 8 - bl,pn %icc, .Ltiny + bl,pn %xcc, .Ltiny membar #StoreStore|#StoreLoad .Lmedium: andn %o1, 0x7, %g1 sub %o1, %g1, %o1 1: stx %o4, [%o0 + 0x00] subcc %g1, 0x8, %g1 - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x08, %o0 andcc %o1, 0x4, %g1 - be,pt %icc, .Ltiny + be,pt %xcc, .Ltiny sub %o1, %g1, %o1 stw %o4, [%o0 + 0x00] add %o0, 0x4, %o0 .Ltiny: cmp %o1, 0 - be,pn %icc, .Lexit + be,pn %xcc, .Lexit 1: subcc %o1, 1, %o1 stb %o4, [%o0 + 0x00] - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 1, %o0 .Lexit: retl @@ -100,8 +100,8 @@ NG4bzero: stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P stxa %o4, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P stxa %o4, [%o0 + %o5] ASI_BLK_INIT_QUAD_LDD_P - bne,pt %icc, 1b + bne,pt %xcc, 1b add %o0, 0x30, %o0 - ba,a,pt %icc, .Lpostloop + ba,a,pt %xcc, .Lpostloop nop .size NG4bzero,.-NG4bzero diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5e9593d542b0..d8983df5a2bc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2009,6 +2009,9 @@ config KEXEC_FILE for kernel and initramfs as opposed to list of segments as accepted by previous system call. +config ARCH_HAS_KEXEC_PURGATORY + def_bool KEXEC_FILE + config KEXEC_SIG bool "Verify kernel signature during kexec_file_load() syscall" depends on KEXEC_FILE diff --git a/arch/x86/include/asm/kexec-bzimage64.h b/arch/x86/include/asm/kexec-bzimage64.h index 9f07cff43705..df89ee7d3e9e 100644 --- a/arch/x86/include/asm/kexec-bzimage64.h +++ b/arch/x86/include/asm/kexec-bzimage64.h @@ -2,6 +2,6 @@ #ifndef _ASM_KEXEC_BZIMAGE64_H #define _ASM_KEXEC_BZIMAGE64_H -extern struct kexec_file_ops kexec_bzImage64_ops; +extern const struct kexec_file_ops kexec_bzImage64_ops; #endif /* _ASM_KEXE_BZIMAGE64_H */ diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 1f6680427ff0..f631a3f15587 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -38,37 +38,6 @@ #include <asm/virtext.h> #include <asm/intel_pt.h> -/* Alignment required for elf header segment */ -#define ELF_CORE_HEADER_ALIGN 4096 - -/* This primarily represents number of split ranges due to exclusion */ -#define CRASH_MAX_RANGES 16 - -struct crash_mem_range { - u64 start, end; -}; - -struct crash_mem { - unsigned int nr_ranges; - struct crash_mem_range ranges[CRASH_MAX_RANGES]; -}; - -/* Misc data about ram ranges needed to prepare elf headers */ -struct crash_elf_data { - struct kimage *image; - /* - * Total number of ram ranges we have after various adjustments for - * crash reserved region, etc. - */ - unsigned int max_nr_ranges; - - /* Pointer to elf header */ - void *ehdr; - /* Pointer to next phdr */ - void *bufp; - struct crash_mem mem; -}; - /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { struct boot_params *params; @@ -218,124 +187,49 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg) return 0; } - /* Gather all the required information to prepare elf headers for ram regions */ -static void fill_up_crash_elf_data(struct crash_elf_data *ced, - struct kimage *image) +static struct crash_mem *fill_up_crash_elf_data(void) { unsigned int nr_ranges = 0; - - ced->image = image; + struct crash_mem *cmem; walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + if (!nr_ranges) + return NULL; - ced->max_nr_ranges = nr_ranges; - - /* Exclusion of crash region could split memory ranges */ - ced->max_nr_ranges++; - - /* If crashk_low_res is not 0, another range split possible */ - if (crashk_low_res.end) - ced->max_nr_ranges++; -} - -static int exclude_mem_range(struct crash_mem *mem, - unsigned long long mstart, unsigned long long mend) -{ - int i, j; - unsigned long long start, end; - struct crash_mem_range temp_range = {0, 0}; - - for (i = 0; i < mem->nr_ranges; i++) { - start = mem->ranges[i].start; - end = mem->ranges[i].end; - - if (mstart > end || mend < start) - continue; - - /* Truncate any area outside of range */ - if (mstart < start) - mstart = start; - if (mend > end) - mend = end; - - /* Found completely overlapping range */ - if (mstart == start && mend == end) { - mem->ranges[i].start = 0; - mem->ranges[i].end = 0; - if (i < mem->nr_ranges - 1) { - /* Shift rest of the ranges to left */ - for (j = i; j < mem->nr_ranges - 1; j++) { - mem->ranges[j].start = - mem->ranges[j+1].start; - mem->ranges[j].end = - mem->ranges[j+1].end; - } - } - mem->nr_ranges--; - return 0; - } - - if (mstart > start && mend < end) { - /* Split original range */ - mem->ranges[i].end = mstart - 1; - temp_range.start = mend + 1; - temp_range.end = end; - } else if (mstart != start) - mem->ranges[i].end = mstart - 1; - else - mem->ranges[i].start = mend + 1; - break; - } + /* + * Exclusion of crash region and/or crashk_low_res may cause + * another range split. So add extra two slots here. + */ + nr_ranges += 2; + cmem = vzalloc(sizeof(struct crash_mem) + + sizeof(struct crash_mem_range) * nr_ranges); + if (!cmem) + return NULL; - /* If a split happend, add the split to array */ - if (!temp_range.end) - return 0; + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; - /* Split happened */ - if (i == CRASH_MAX_RANGES - 1) { - pr_err("Too many crash ranges after split\n"); - return -ENOMEM; - } - - /* Location where new range should go */ - j = i + 1; - if (j < mem->nr_ranges) { - /* Move over all ranges one slot towards the end */ - for (i = mem->nr_ranges - 1; i >= j; i--) - mem->ranges[i + 1] = mem->ranges[i]; - } - - mem->ranges[j].start = temp_range.start; - mem->ranges[j].end = temp_range.end; - mem->nr_ranges++; - return 0; + return cmem; } /* * Look for any unwanted ranges between mstart, mend and remove them. This - * might lead to split and split ranges are put in ced->mem.ranges[] array + * might lead to split and split ranges are put in cmem->ranges[] array */ -static int elf_header_exclude_ranges(struct crash_elf_data *ced, - unsigned long long mstart, unsigned long long mend) +static int elf_header_exclude_ranges(struct crash_mem *cmem) { - struct crash_mem *cmem = &ced->mem; int ret = 0; - memset(cmem->ranges, 0, sizeof(cmem->ranges)); - - cmem->ranges[0].start = mstart; - cmem->ranges[0].end = mend; - cmem->nr_ranges = 1; - /* Exclude crashkernel region */ - ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) { - ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + ret = crash_exclude_mem_range(cmem, crashk_low_res.start, + crashk_low_res.end); if (ret) return ret; } @@ -345,144 +239,12 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { - struct crash_elf_data *ced = arg; - Elf64_Ehdr *ehdr; - Elf64_Phdr *phdr; - unsigned long mstart, mend; - struct kimage *image = ced->image; - struct crash_mem *cmem; - int ret, i; - - ehdr = ced->ehdr; - - /* Exclude unwanted mem ranges */ - ret = elf_header_exclude_ranges(ced, res->start, res->end); - if (ret) - return ret; - - /* Go through all the ranges in ced->mem.ranges[] and prepare phdr */ - cmem = &ced->mem; - - for (i = 0; i < cmem->nr_ranges; i++) { - mstart = cmem->ranges[i].start; - mend = cmem->ranges[i].end; - - phdr = ced->bufp; - ced->bufp += sizeof(Elf64_Phdr); - - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_offset = mstart; - - /* - * If a range matches backup region, adjust offset to backup - * segment. - */ - if (mstart == image->arch.backup_src_start && - (mend - mstart + 1) == image->arch.backup_src_sz) - phdr->p_offset = image->arch.backup_load_addr; - - phdr->p_paddr = mstart; - phdr->p_vaddr = (unsigned long long) __va(mstart); - phdr->p_filesz = phdr->p_memsz = mend - mstart + 1; - phdr->p_align = 0; - ehdr->e_phnum++; - pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n", - phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz, - ehdr->e_phnum, phdr->p_offset); - } - - return ret; -} - -static int prepare_elf64_headers(struct crash_elf_data *ced, - void **addr, unsigned long *sz) -{ - Elf64_Ehdr *ehdr; - Elf64_Phdr *phdr; - unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz; - unsigned char *buf, *bufp; - unsigned int cpu; - unsigned long long notes_addr; - int ret; + struct crash_mem *cmem = arg; - /* extra phdr for vmcoreinfo elf note */ - nr_phdr = nr_cpus + 1; - nr_phdr += ced->max_nr_ranges; - - /* - * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping - * area on x86_64 (ffffffff80000000 - ffffffffa0000000). - * I think this is required by tools like gdb. So same physical - * memory will be mapped in two elf headers. One will contain kernel - * text virtual addresses and other will have __va(physical) addresses. - */ + cmem->ranges[cmem->nr_ranges].start = res->start; + cmem->ranges[cmem->nr_ranges].end = res->end; + cmem->nr_ranges++; - nr_phdr++; - elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr); - elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN); - - buf = vzalloc(elf_sz); - if (!buf) - return -ENOMEM; - - bufp = buf; - ehdr = (Elf64_Ehdr *)bufp; - bufp += sizeof(Elf64_Ehdr); - memcpy(ehdr->e_ident, ELFMAG, SELFMAG); - ehdr->e_ident[EI_CLASS] = ELFCLASS64; - ehdr->e_ident[EI_DATA] = ELFDATA2LSB; - ehdr->e_ident[EI_VERSION] = EV_CURRENT; - ehdr->e_ident[EI_OSABI] = ELF_OSABI; - memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD); - ehdr->e_type = ET_CORE; - ehdr->e_machine = ELF_ARCH; - ehdr->e_version = EV_CURRENT; - ehdr->e_phoff = sizeof(Elf64_Ehdr); - ehdr->e_ehsize = sizeof(Elf64_Ehdr); - ehdr->e_phentsize = sizeof(Elf64_Phdr); - - /* Prepare one phdr of type PT_NOTE for each present cpu */ - for_each_present_cpu(cpu) { - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_NOTE; - notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu)); - phdr->p_offset = phdr->p_paddr = notes_addr; - phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t); - (ehdr->e_phnum)++; - } - - /* Prepare one PT_NOTE header for vmcoreinfo */ - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_NOTE; - phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note(); - phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE; - (ehdr->e_phnum)++; - -#ifdef CONFIG_X86_64 - /* Prepare PT_LOAD type program header for kernel text region */ - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_vaddr = (Elf64_Addr)_text; - phdr->p_filesz = phdr->p_memsz = _end - _text; - phdr->p_offset = phdr->p_paddr = __pa_symbol(_text); - (ehdr->e_phnum)++; -#endif - - /* Prepare PT_LOAD headers for system ram chunks. */ - ced->ehdr = ehdr; - ced->bufp = bufp; - ret = walk_system_ram_res(0, -1, ced, - prepare_elf64_ram_headers_callback); - if (ret < 0) - return ret; - - *addr = buf; - *sz = elf_sz; return 0; } @@ -490,18 +252,46 @@ static int prepare_elf64_headers(struct crash_elf_data *ced, static int prepare_elf_headers(struct kimage *image, void **addr, unsigned long *sz) { - struct crash_elf_data *ced; - int ret; + struct crash_mem *cmem; + Elf64_Ehdr *ehdr; + Elf64_Phdr *phdr; + int ret, i; - ced = kzalloc(sizeof(*ced), GFP_KERNEL); - if (!ced) + cmem = fill_up_crash_elf_data(); + if (!cmem) return -ENOMEM; - fill_up_crash_elf_data(ced, image); + ret = walk_system_ram_res(0, -1, cmem, + prepare_elf64_ram_headers_callback); + if (ret) + goto out; + + /* Exclude unwanted mem ranges */ + ret = elf_header_exclude_ranges(cmem); + if (ret) + goto out; /* By default prepare 64bit headers */ - ret = prepare_elf64_headers(ced, addr, sz); - kfree(ced); + ret = crash_prepare_elf64_headers(cmem, + IS_ENABLED(CONFIG_X86_64), addr, sz); + if (ret) + goto out; + + /* + * If a range matches backup region, adjust offset to backup + * segment. + */ + ehdr = (Elf64_Ehdr *)*addr; + phdr = (Elf64_Phdr *)(ehdr + 1); + for (i = 0; i < ehdr->e_phnum; phdr++, i++) + if (phdr->p_type == PT_LOAD && + phdr->p_paddr == image->arch.backup_src_start && + phdr->p_memsz == image->arch.backup_src_sz) { + phdr->p_offset = image->arch.backup_load_addr; + break; + } +out: + vfree(cmem); return ret; } @@ -547,14 +337,14 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, /* Exclude Backup region */ start = image->arch.backup_load_addr; end = start + image->arch.backup_src_sz - 1; - ret = exclude_mem_range(cmem, start, end); + ret = crash_exclude_mem_range(cmem, start, end); if (ret) return ret; /* Exclude elf header region */ start = image->arch.elf_load_addr; end = start + image->arch.elf_headers_sz - 1; - return exclude_mem_range(cmem, start, end); + return crash_exclude_mem_range(cmem, start, end); } /* Prepare memory map for crash dump kernel */ diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 7d0fac5bcbbe..8a89189236e3 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -335,7 +335,6 @@ static void *bzImage64_load(struct kimage *image, char *kernel, unsigned long setup_header_size, params_cmdline_sz; struct boot_params *params; unsigned long bootparam_load_addr, kernel_load_addr, initrd_load_addr; - unsigned long purgatory_load_addr; struct bzimage64_data *ldata; struct kexec_entry64_regs regs64; void *stack; @@ -343,6 +342,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, unsigned int efi_map_offset, efi_map_sz, efi_setup_data_offset; struct kexec_buf kbuf = { .image = image, .buf_max = ULONG_MAX, .top_down = true }; + struct kexec_buf pbuf = { .image = image, .buf_min = MIN_PURGATORY_ADDR, + .buf_max = ULONG_MAX, .top_down = true }; header = (struct setup_header *)(kernel + setup_hdr_offset); setup_sects = header->setup_sects; @@ -380,14 +381,13 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * Load purgatory. For 64bit entry point, purgatory code can be * anywhere. */ - ret = kexec_load_purgatory(image, MIN_PURGATORY_ADDR, ULONG_MAX, 1, - &purgatory_load_addr); + ret = kexec_load_purgatory(image, &pbuf); if (ret) { pr_err("Loading purgatory failed\n"); return ERR_PTR(ret); } - pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr); + pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); /* @@ -539,7 +539,7 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) } #endif -struct kexec_file_ops kexec_bzImage64_ops = { +const struct kexec_file_ops kexec_bzImage64_ops = { .probe = bzImage64_probe, .load = bzImage64_load, .cleanup = bzImage64_cleanup, diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 4b86353c1ebf..a5e55d832d0a 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -30,8 +30,9 @@ #include <asm/set_memory.h> #ifdef CONFIG_KEXEC_FILE -static struct kexec_file_ops *kexec_file_loaders[] = { +const struct kexec_file_ops * const kexec_file_loaders[] = { &kexec_bzImage64_ops, + NULL }; #endif @@ -364,27 +365,6 @@ void arch_crash_save_vmcoreinfo(void) /* arch-dependent functionality related to kexec file-based syscall */ #ifdef CONFIG_KEXEC_FILE -int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len) -{ - int i, ret = -ENOEXEC; - struct kexec_file_ops *fops; - - for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { - fops = kexec_file_loaders[i]; - if (!fops || !fops->probe) - continue; - - ret = fops->probe(buf, buf_len); - if (!ret) { - image->fops = fops; - return ret; - } - } - - return ret; -} - void *arch_kexec_kernel_image_load(struct kimage *image) { vfree(image->arch.elf_headers); @@ -399,88 +379,53 @@ void *arch_kexec_kernel_image_load(struct kimage *image) image->cmdline_buf_len); } -int arch_kimage_file_post_load_cleanup(struct kimage *image) -{ - if (!image->fops || !image->fops->cleanup) - return 0; - - return image->fops->cleanup(image->image_loader_data); -} - -#ifdef CONFIG_KEXEC_SIG -int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel, - unsigned long kernel_len) -{ - if (!image->fops || !image->fops->verify_sig) { - pr_debug("kernel loader does not support signature verification."); - return -EKEYREJECTED; - } - - return image->fops->verify_sig(kernel, kernel_len); -} -#endif - /* * Apply purgatory relocations. * - * ehdr: Pointer to elf headers - * sechdrs: Pointer to section headers. - * relsec: section index of SHT_RELA section. + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELAs. + * @symtabsec: Corresponding symtab. * * TODO: Some of the code belongs to generic code. Move that in kexec.c. */ -int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, - Elf64_Shdr *sechdrs, unsigned int relsec) +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, const Elf_Shdr *relsec, + const Elf_Shdr *symtabsec) { unsigned int i; Elf64_Rela *rel; Elf64_Sym *sym; void *location; - Elf64_Shdr *section, *symtabsec; unsigned long address, sec_base, value; const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; - /* - * ->sh_offset has been modified to keep the pointer to section - * contents in memory - */ - rel = (void *)sechdrs[relsec].sh_offset; - - /* Section to which relocations apply */ - section = &sechdrs[sechdrs[relsec].sh_info]; - - pr_debug("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); - - /* Associated symbol table */ - symtabsec = &sechdrs[sechdrs[relsec].sh_link]; - - /* String table */ - if (symtabsec->sh_link >= ehdr->e_shnum) { - /* Invalid strtab section number */ - pr_err("Invalid string table section index %d\n", - symtabsec->sh_link); - return -ENOEXEC; - } + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtabsec->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; - strtab = (char *)sechdrs[symtabsec->sh_link].sh_offset; + rel = (void *)pi->ehdr + relsec->sh_offset; - /* section header string table */ - shstrtab = (char *)sechdrs[ehdr->e_shstrndx].sh_offset; + pr_debug("Applying relocate section %s to %u\n", + shstrtab + relsec->sh_name, relsec->sh_info); - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + for (i = 0; i < relsec->sh_size / sizeof(*rel); i++) { /* * rel[i].r_offset contains byte offset from beginning * of section to the storage unit affected. * - * This is location to update (->sh_offset). This is temporary - * buffer where section is currently loaded. This will finally - * be loaded to a different address later, pointed to by + * This is location to update. This is temporary buffer + * where section is currently loaded. This will finally be + * loaded to a different address later, pointed to by * ->sh_addr. kexec takes care of moving it * (kexec_load_segment()). */ - location = (void *)(section->sh_offset + rel[i].r_offset); + location = pi->purgatory_buf; + location += section->sh_offset; + location += rel[i].r_offset; /* Final address of the location */ address = section->sh_addr + rel[i].r_offset; @@ -491,8 +436,8 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, * to apply. ELF64_R_SYM() and ELF64_R_TYPE() macros get * these respectively. */ - sym = (Elf64_Sym *)symtabsec->sh_offset + - ELF64_R_SYM(rel[i].r_info); + sym = (void *)pi->ehdr + symtabsec->sh_offset; + sym += ELF64_R_SYM(rel[i].r_info); if (sym->st_name) name = strtab + sym->st_name; @@ -515,12 +460,12 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, if (sym->st_shndx == SHN_ABS) sec_base = 0; - else if (sym->st_shndx >= ehdr->e_shnum) { + else if (sym->st_shndx >= pi->ehdr->e_shnum) { pr_err("Invalid section %d for symbol %s\n", sym->st_shndx, name); return -ENOEXEC; } else - sec_base = sechdrs[sym->st_shndx].sh_addr; + sec_base = pi->sechdrs[sym->st_shndx].sh_addr; value = sym->st_value; value += sec_base; diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index d70c15de417b..2e9ee023e6bc 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -6,6 +6,9 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string targets += $(purgatory-y) PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) +$(obj)/sha256.o: $(srctree)/lib/sha256.c + $(call if_changed_rule,cc_o_c) + LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib targets += purgatory.ro diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index 470edad96bb9..025c34ac0d84 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -11,9 +11,9 @@ */ #include <linux/bug.h> +#include <linux/sha256.h> #include <asm/purgatory.h> -#include "sha256.h" #include "../boot/string.h" unsigned long purgatory_backup_dest __section(.kexec-purgatory); diff --git a/arch/x86/purgatory/string.c b/arch/x86/purgatory/string.c index d886b1fa36f0..795ca4f2cb3c 100644 --- a/arch/x86/purgatory/string.c +++ b/arch/x86/purgatory/string.c @@ -10,4 +10,16 @@ * Version 2. See the file COPYING for more details. */ +#include <linux/types.h> + #include "../boot/string.c" + +void *memcpy(void *dst, const void *src, size_t len) +{ + return __builtin_memcpy(dst, src, len); +} + +void *memset(void *dst, int c, size_t len) +{ + return __builtin_memset(dst, c, len); +} diff --git a/drivers/media/platform/sti/delta/delta-ipc.c b/drivers/media/platform/sti/delta/delta-ipc.c index a4603d573c34..bd1bbbeedec3 100644 --- a/drivers/media/platform/sti/delta/delta-ipc.c +++ b/drivers/media/platform/sti/delta/delta-ipc.c @@ -175,8 +175,8 @@ int delta_ipc_open(struct delta_ctx *pctx, const char *name, msg.ipc_buf_size = ipc_buf_size; msg.ipc_buf_paddr = ctx->ipc_buf->paddr; - memcpy(msg.name, name, sizeof(msg.name)); - msg.name[sizeof(msg.name) - 1] = 0; + memset(msg.name, 0, sizeof(msg.name)); + strcpy(msg.name, name); msg.param_size = param->size; memcpy(ctx->ipc_buf->vaddr, param->data, msg.param_size); diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 63a1ca4b9dee..eb5c41284649 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -384,8 +384,9 @@ out_err: static int __init dnotify_init(void) { - dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC); - dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC); + dnotify_struct_cache = KMEM_CACHE(dnotify_struct, + SLAB_PANIC|SLAB_ACCOUNT); + dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops); if (IS_ERR(dnotify_group)) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d94e8031fe5f..78cfdcfd9f8e 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -153,14 +153,16 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group, if (fanotify_is_perm_event(mask)) { struct fanotify_perm_event_info *pevent; - pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp); + pevent = kmem_cache_alloc_memcg(fanotify_perm_event_cachep, gfp, + group->memcg); if (!pevent) return NULL; event = &pevent->fae; pevent->response = 0; goto init; } - event = kmem_cache_alloc(fanotify_event_cachep, gfp); + event = kmem_cache_alloc_memcg(fanotify_event_cachep, gfp, + group->memcg); if (!event) return NULL; init: __maybe_unused diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index ec4d8c59d0e3..0cf45041dc32 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -16,6 +16,7 @@ #include <linux/uaccess.h> #include <linux/compat.h> #include <linux/sched/signal.h> +#include <linux/memcontrol.h> #include <asm/ioctls.h> @@ -756,6 +757,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user; atomic_inc(&user->fanotify_listeners); + group->memcg = get_mem_cgroup_from_mm(current->mm); oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL); if (unlikely(!oevent)) { @@ -957,7 +959,8 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark, */ static int __init fanotify_user_setup(void) { - fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC); + fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, + SLAB_PANIC|SLAB_ACCOUNT); fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC); if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) { fanotify_perm_event_cachep = diff --git a/fs/notify/group.c b/fs/notify/group.c index b7a4b6a69efa..3e56459f4773 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -22,6 +22,7 @@ #include <linux/srcu.h> #include <linux/rculist.h> #include <linux/wait.h> +#include <linux/memcontrol.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" @@ -36,6 +37,9 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) if (group->ops->free_group_priv) group->ops->free_group_priv(group); + if (group->memcg) + mem_cgroup_put(group->memcg); + kfree(group); } diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 40dedb37a1f3..b184bff93d02 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -98,7 +98,7 @@ int inotify_handle_event(struct fsnotify_group *group, i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); - event = kmalloc(alloc_len, GFP_KERNEL); + event = kmalloc_memcg(alloc_len, GFP_KERNEL, group->memcg); if (unlikely(!event)) { /* * Treat lost event due to ENOMEM the same way as queue diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index ef32f3657958..3c152e350805 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -38,6 +38,7 @@ #include <linux/uaccess.h> #include <linux/poll.h> #include <linux/wait.h> +#include <linux/memcontrol.h> #include "inotify.h" #include "../fdinfo.h" @@ -632,6 +633,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) oevent->name_len = 0; group->max_events = max_events; + group->memcg = get_mem_cgroup_from_mm(current->mm); spin_lock_init(&group->inotify_data.idr_lock); idr_init(&group->inotify_data.idr); @@ -804,7 +806,8 @@ static int __init inotify_user_setup(void) BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21); - inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC); + inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, + SLAB_PANIC|SLAB_ACCOUNT); inotify_max_queued_events = 16384; init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 9f1edb92c97e..81bd86dfa2cd 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -84,6 +84,8 @@ struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; +struct mem_cgroup; + /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. @@ -129,6 +131,8 @@ struct fsnotify_event { * everything will be cleaned up. */ struct fsnotify_group { + const struct fsnotify_ops *ops; /* how this group handles things */ + /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. @@ -139,8 +143,6 @@ struct fsnotify_group { */ refcount_t refcnt; /* things with interest in this group */ - const struct fsnotify_ops *ops; /* how this group handles things */ - /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ @@ -162,6 +164,8 @@ struct fsnotify_group { atomic_t num_marks; /* 1 for each mark and 1 for not being * past the point of no return when freeing * a group */ + atomic_t user_waits; /* Number of tasks waiting for user + * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ @@ -169,8 +173,8 @@ struct fsnotify_group { struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ - atomic_t user_waits; /* Number of tasks waiting for user - * response */ + + struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 466d7be046eb..74a0e4f21087 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -280,6 +280,9 @@ extern int walk_system_ram_res(u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)); extern int +walk_system_ram_res_rev(u64 start, u64 end, void *arg, + int (*func)(struct resource *, void *)); +extern int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)); diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 4ecfb7ca8e66..7404aa14ba33 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -99,21 +99,25 @@ struct compat_kexec_segment { #ifdef CONFIG_KEXEC_FILE struct purgatory_info { - /* Pointer to elf header of read only purgatory */ - Elf_Ehdr *ehdr; - - /* Pointer to purgatory sechdrs which are modifiable */ + /* + * Pointer to elf header at the beginning of kexec_purgatory. + * Note: kexec_purgatory is read only + */ + const Elf_Ehdr *ehdr; + /* + * Temporary, modifiable buffer for sechdrs used for relocation. + * This memory can be freed post image load. + */ Elf_Shdr *sechdrs; /* - * Temporary buffer location where purgatory is loaded and relocated - * This memory can be freed post image load + * Temporary, modifiable buffer for stripped purgatory used for + * relocation. This memory can be freed post image load. */ void *purgatory_buf; - - /* Address where purgatory is finally loaded and is executed from */ - unsigned long purgatory_load_addr; }; +struct kimage; + typedef int (kexec_probe_t)(const char *kernel_buf, unsigned long kernel_size); typedef void *(kexec_load_t)(struct kimage *image, char *kernel_buf, unsigned long kernel_len, char *initrd, @@ -135,6 +139,11 @@ struct kexec_file_ops { #endif }; +extern const struct kexec_file_ops * const kexec_file_loaders[]; + +int kexec_image_probe_default(struct kimage *image, void *buf, + unsigned long buf_len); + /** * struct kexec_buf - parameters for finding a place for a buffer in memory * @image: kexec image in which memory to search. @@ -159,10 +168,44 @@ struct kexec_buf { bool top_down; }; +int kexec_load_purgatory(struct kimage *image, struct kexec_buf *kbuf); +int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, + void *buf, unsigned int size, + bool get_value); +void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); + +int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab); +int __weak arch_kexec_apply_relocations(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab); + int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(struct resource *, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); + +/* Alignment required for elf header segment */ +#define ELF_CORE_HEADER_ALIGN 4096 + +struct crash_mem_range { + u64 start, end; +}; + +struct crash_mem { + unsigned int max_nr_ranges; + unsigned int nr_ranges; + struct crash_mem_range ranges[0]; +}; + +extern int crash_exclude_mem_range(struct crash_mem *mem, + unsigned long long mstart, + unsigned long long mend); +extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, + void **addr, unsigned long *sz); #endif /* CONFIG_KEXEC_FILE */ struct kimage { @@ -209,7 +252,7 @@ struct kimage { unsigned long cmdline_buf_len; /* File operations provided by image loader */ - struct kexec_file_ops *fops; + const struct kexec_file_ops *fops; /* Image loader handling the kernel can store a pointer here */ void *image_loader_data; @@ -226,14 +269,6 @@ extern void machine_kexec_cleanup(struct kimage *image); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); -extern int kexec_load_purgatory(struct kimage *image, unsigned long min, - unsigned long max, int top_down, - unsigned long *load_addr); -extern int kexec_purgatory_get_set_symbol(struct kimage *image, - const char *name, void *buf, - unsigned int size, bool get_value); -extern void *kexec_purgatory_get_symbol_addr(struct kimage *image, - const char *name); extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); @@ -273,16 +308,6 @@ int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); -int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len); -void * __weak arch_kexec_kernel_image_load(struct kimage *image); -int __weak arch_kimage_file_post_load_cleanup(struct kimage *image); -int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, - unsigned long buf_len); -int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, - Elf_Shdr *sechdrs, unsigned int relsec); -int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, - unsigned int relsec); void arch_kexec_protect_crashkres(void); void arch_kexec_unprotect_crashkres(void); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2da009958798..af9eed2e3e04 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -356,6 +356,8 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } +struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { css_put(&memcg->css); @@ -813,6 +815,11 @@ static inline bool task_in_mem_cgroup(struct task_struct *task, return true; } +static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) +{ + return NULL; +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index b3d697f3b573..d0b8c3ee717b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1097,6 +1097,9 @@ struct task_struct { /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; + + /* Used by memcontrol for targeted memcg charge: */ + struct mem_cgroup *target_memcg; #endif #ifdef CONFIG_UPROBES diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2c570cd934af..333f620a4634 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -206,6 +206,30 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } +#ifdef CONFIG_MEMCG +static inline struct mem_cgroup *memalloc_memcg_save(struct mem_cgroup *memcg) +{ + struct mem_cgroup *old_memcg = current->target_memcg; + + current->target_memcg = memcg; + return old_memcg; +} + +static inline void memalloc_memcg_restore(struct mem_cgroup *memcg) +{ + current->target_memcg = memcg; +} +#else +static inline struct mem_cgroup *memalloc_memcg_save(struct mem_cgroup *memcg) +{ + return NULL; +} + +static inline void memalloc_memcg_restore(struct mem_cgroup *memcg) +{ +} +#endif /* CONFIG_MEMCG */ + #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), diff --git a/arch/x86/purgatory/sha256.h b/include/linux/sha256.h index 2867d9825a57..244fe01a65fb 100644 --- a/arch/x86/purgatory/sha256.h +++ b/include/linux/sha256.h @@ -13,9 +13,18 @@ #include <linux/types.h> #include <crypto/sha.h> +/* + * Stand-alone implementation of the SHA256 algorithm. It is designed to + * have as little dependencies as possible so it can be used in the + * kexec_file purgatory. In other cases you should use the implementation in + * crypto/. + * + * For details see lib/sha256.c + */ + extern int sha256_init(struct sha256_state *sctx); extern int sha256_update(struct sha256_state *sctx, const u8 *input, - unsigned int length); + unsigned int length); extern int sha256_final(struct sha256_state *sctx, u8 *hash); #endif /* SHA256_H */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 81ebd71f8c03..9ebe659bd4a5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -15,6 +15,7 @@ #include <linux/gfp.h> #include <linux/types.h> #include <linux/workqueue.h> +#include <linux/sched/mm.h> /* @@ -374,6 +375,21 @@ static __always_inline void kfree_bulk(size_t size, void **p) kmem_cache_free_bulk(NULL, size, p); } +/* + * Calling kmem_cache_alloc_memcg implicitly assumes that the caller + * wants a __GFP_ACCOUNT allocation. + */ +static __always_inline void *kmem_cache_alloc_memcg(struct kmem_cache *cachep, + gfp_t flags, + struct mem_cgroup *memcg) +{ + struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg); + void *ptr = kmem_cache_alloc(cachep, flags | __GFP_ACCOUNT); + + memalloc_memcg_restore(old_memcg); + return ptr; +} + #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; @@ -389,6 +405,21 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f } #endif +/* + * Calling kmem_cache_alloc_node_memcg implicitly assumes that the caller + * wants a __GFP_ACCOUNT allocation. + */ +static __always_inline void * +kmem_cache_alloc_node_memcg(struct kmem_cache *cachep, gfp_t flags, int node, + struct mem_cgroup *memcg) +{ + struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg); + void *ptr = kmem_cache_alloc_node(cachep, flags | __GFP_ACCOUNT, node); + + memalloc_memcg_restore(old_memcg); + return ptr; +} + #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; @@ -518,6 +549,20 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) } /* + * Calling kmalloc_memcg implicitly assumes that the caller wants a + * __GFP_ACCOUNT allocation. + */ +static __always_inline void *kmalloc_memcg(size_t size, gfp_t flags, + struct mem_cgroup *memcg) +{ + struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg); + void *ptr = kmalloc(size, flags | __GFP_ACCOUNT); + + memalloc_memcg_restore(old_memcg); + return ptr; +} + +/* * Determine size used for the nth kmalloc cache. * return size or 0 if a kmalloc cache for that * size does not exist @@ -554,6 +599,20 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) return __kmalloc_node(size, flags, node); } +/* + * Calling kmalloc_node_memcg implicitly assumes that the caller wants a + * __GFP_ACCOUNT allocation. + */ +static __always_inline void * +kmalloc_node_memcg(size_t size, gfp_t flags, int node, struct mem_cgroup *memcg) +{ + struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg); + void *ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); + + memalloc_memcg_restore(old_memcg); + return ptr; +} + struct memcg_cache_array { struct rcu_head rcu; struct kmem_cache *entries[0]; diff --git a/kernel/fork.c b/kernel/fork.c index 3398037de1cb..1e8c9a7d1ada 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -835,6 +835,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->fail_nth = 0; #endif +#ifdef CONFIG_MEMCG + tsk->target_memcg = NULL; +#endif return tsk; free_stack: diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index c47c4de604cd..2d16c5a3a8ee 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -22,50 +22,123 @@ #include <linux/ima.h> #include <crypto/hash.h> #include <crypto/sha.h> +#include <linux/elf.h> +#include <linux/elfcore.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/slab.h> #include <linux/syscalls.h> #include <linux/vmalloc.h> #include "kexec_internal.h" static int kexec_calculate_store_digests(struct kimage *image); +/* + * Currently this is the only default function that is exported as some + * architectures need it to do additional handlings. + * In the future, other default functions may be exported too if required. + */ +int kexec_image_probe_default(struct kimage *image, void *buf, + unsigned long buf_len) +{ + const struct kexec_file_ops * const *fops; + int ret = -ENOEXEC; + + for (fops = &kexec_file_loaders[0]; *fops && (*fops)->probe; ++fops) { + ret = (*fops)->probe(buf, buf_len); + if (!ret) { + image->fops = *fops; + return ret; + } + } + + return ret; +} + /* Architectures can provide this probe function */ int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len) { - return -ENOEXEC; + return kexec_image_probe_default(image, buf, buf_len); +} + +static void *kexec_image_load_default(struct kimage *image) +{ + if (!image->fops || !image->fops->load) + return ERR_PTR(-ENOEXEC); + + return image->fops->load(image, image->kernel_buf, + image->kernel_buf_len, image->initrd_buf, + image->initrd_buf_len, image->cmdline_buf, + image->cmdline_buf_len); } void * __weak arch_kexec_kernel_image_load(struct kimage *image) { - return ERR_PTR(-ENOEXEC); + return kexec_image_load_default(image); +} + +static int kexec_image_post_load_cleanup_default(struct kimage *image) +{ + if (!image->fops || !image->fops->cleanup) + return 0; + + return image->fops->cleanup(image->image_loader_data); } int __weak arch_kimage_file_post_load_cleanup(struct kimage *image) { - return -EINVAL; + return kexec_image_post_load_cleanup_default(image); } #ifdef CONFIG_KEXEC_SIG +static int kexec_image_verify_sig_default(struct kimage *image, void *buf, + unsigned long buf_len) +{ + if (!image->fops || !image->fops->verify_sig) { + pr_debug("kernel loader does not support signature verification.\n"); + return -EKEYREJECTED; + } + + return image->fops->verify_sig(buf, buf_len); +} + int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, unsigned long buf_len) { - return -EKEYREJECTED; + return kexec_image_verify_sig_default(image, buf, buf_len); } #endif -/* Apply relocations of type RELA */ +/* + * arch_kexec_apply_relocations_add - apply relocations of type RELA + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELAs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ int __weak -arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, - unsigned int relsec) +arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) { pr_err("RELA relocation unsupported.\n"); return -ENOEXEC; } -/* Apply relocations of type REL */ +/* + * arch_kexec_apply_relocations - apply relocations of type REL + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ int __weak -arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, - unsigned int relsec) +arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) { pr_err("REL relocation unsupported.\n"); return -ENOEXEC; @@ -487,6 +560,8 @@ int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, crashk_res.start, crashk_res.end, kbuf, func); + else if (kbuf->top_down) + return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func); else return walk_system_ram_res(0, ULONG_MAX, kbuf, func); } @@ -574,6 +649,9 @@ static int kexec_calculate_store_digests(struct kimage *image) struct kexec_sha_region *sha_regions; struct purgatory_info *pi = &image->purgatory_info; + if (!IS_ENABLED(CONFIG_ARCH_HAS_KEXEC_PURGATORY)) + return 0; + zero_buf = __va(page_to_pfn(ZERO_PAGE(0)) << PAGE_SHIFT); zero_buf_sz = PAGE_SIZE; @@ -675,87 +753,29 @@ out: return ret; } -/* Actually load purgatory. Lot of code taken from kexec-tools */ -static int __kexec_load_purgatory(struct kimage *image, unsigned long min, - unsigned long max, int top_down) +#ifdef CONFIG_ARCH_HAS_KEXEC_PURGATORY +/* + * kexec_purgatory_setup_kbuf - prepare buffer to load purgatory. + * @pi: Purgatory to be loaded. + * @kbuf: Buffer to setup. + * + * Allocates the memory needed for the buffer. Caller is responsible to free + * the memory after use. + * + * Return: 0 on success, negative errno on error. + */ +static int kexec_purgatory_setup_kbuf(struct purgatory_info *pi, + struct kexec_buf *kbuf) { - struct purgatory_info *pi = &image->purgatory_info; - unsigned long align, bss_align, bss_sz, bss_pad; - unsigned long entry, load_addr, curr_load_addr, bss_addr, offset; - unsigned char *buf_addr, *src; - int i, ret = 0, entry_sidx = -1; - const Elf_Shdr *sechdrs_c; - Elf_Shdr *sechdrs = NULL; - struct kexec_buf kbuf = { .image = image, .bufsz = 0, .buf_align = 1, - .buf_min = min, .buf_max = max, - .top_down = top_down }; - - /* - * sechdrs_c points to section headers in purgatory and are read - * only. No modifications allowed. - */ - sechdrs_c = (void *)pi->ehdr + pi->ehdr->e_shoff; - - /* - * We can not modify sechdrs_c[] and its fields. It is read only. - * Copy it over to a local copy where one can store some temporary - * data and free it at the end. We need to modify ->sh_addr and - * ->sh_offset fields to keep track of permanent and temporary - * locations of sections. - */ - sechdrs = vzalloc(pi->ehdr->e_shnum * sizeof(Elf_Shdr)); - if (!sechdrs) - return -ENOMEM; - - memcpy(sechdrs, sechdrs_c, pi->ehdr->e_shnum * sizeof(Elf_Shdr)); - - /* - * We seem to have multiple copies of sections. First copy is which - * is embedded in kernel in read only section. Some of these sections - * will be copied to a temporary buffer and relocated. And these - * sections will finally be copied to their final destination at - * segment load time. - * - * Use ->sh_offset to reflect section address in memory. It will - * point to original read only copy if section is not allocatable. - * Otherwise it will point to temporary copy which will be relocated. - * - * Use ->sh_addr to contain final address of the section where it - * will go during execution time. - */ - for (i = 0; i < pi->ehdr->e_shnum; i++) { - if (sechdrs[i].sh_type == SHT_NOBITS) - continue; - - sechdrs[i].sh_offset = (unsigned long)pi->ehdr + - sechdrs[i].sh_offset; - } - - /* - * Identify entry point section and make entry relative to section - * start. - */ - entry = pi->ehdr->e_entry; - for (i = 0; i < pi->ehdr->e_shnum; i++) { - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) - continue; - - if (!(sechdrs[i].sh_flags & SHF_EXECINSTR)) - continue; - - /* Make entry section relative */ - if (sechdrs[i].sh_addr <= pi->ehdr->e_entry && - ((sechdrs[i].sh_addr + sechdrs[i].sh_size) > - pi->ehdr->e_entry)) { - entry_sidx = i; - entry -= sechdrs[i].sh_addr; - break; - } - } + const Elf_Shdr *sechdrs; + unsigned long bss_align; + unsigned long bss_sz; + unsigned long align; + int i, ret; - /* Determine how much memory is needed to load relocatable object. */ - bss_align = 1; - bss_sz = 0; + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + kbuf->buf_align = bss_align = 1; + kbuf->bufsz = bss_sz = 0; for (i = 0; i < pi->ehdr->e_shnum; i++) { if (!(sechdrs[i].sh_flags & SHF_ALLOC)) @@ -763,111 +783,124 @@ static int __kexec_load_purgatory(struct kimage *image, unsigned long min, align = sechdrs[i].sh_addralign; if (sechdrs[i].sh_type != SHT_NOBITS) { - if (kbuf.buf_align < align) - kbuf.buf_align = align; - kbuf.bufsz = ALIGN(kbuf.bufsz, align); - kbuf.bufsz += sechdrs[i].sh_size; + if (kbuf->buf_align < align) + kbuf->buf_align = align; + kbuf->bufsz = ALIGN(kbuf->bufsz, align); + kbuf->bufsz += sechdrs[i].sh_size; } else { - /* bss section */ if (bss_align < align) bss_align = align; bss_sz = ALIGN(bss_sz, align); bss_sz += sechdrs[i].sh_size; } } + kbuf->bufsz = ALIGN(kbuf->bufsz, bss_align); + kbuf->memsz = kbuf->bufsz + bss_sz; + if (kbuf->buf_align < bss_align) + kbuf->buf_align = bss_align; - /* Determine the bss padding required to align bss properly */ - bss_pad = 0; - if (kbuf.bufsz & (bss_align - 1)) - bss_pad = bss_align - (kbuf.bufsz & (bss_align - 1)); - - kbuf.memsz = kbuf.bufsz + bss_pad + bss_sz; + kbuf->buffer = vzalloc(kbuf->bufsz); + if (!kbuf->buffer) + return -ENOMEM; + pi->purgatory_buf = kbuf->buffer; - /* Allocate buffer for purgatory */ - kbuf.buffer = vzalloc(kbuf.bufsz); - if (!kbuf.buffer) { - ret = -ENOMEM; + ret = kexec_add_buffer(kbuf); + if (ret) goto out; - } - if (kbuf.buf_align < bss_align) - kbuf.buf_align = bss_align; + return 0; +out: + vfree(pi->purgatory_buf); + pi->purgatory_buf = NULL; + return ret; +} - /* Add buffer to segment list */ - ret = kexec_add_buffer(&kbuf); - if (ret) - goto out; - pi->purgatory_load_addr = kbuf.mem; +/* + * kexec_purgatory_setup_sechdrs - prepares the pi->sechdrs buffer. + * @pi: Purgatory to be loaded. + * @kbuf: Buffer prepared to store purgatory. + * + * Allocates the memory needed for the buffer. Caller is responsible to free + * the memory after use. + * + * Return: 0 on success, negative errno on error. + */ +static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi, + struct kexec_buf *kbuf) +{ + unsigned long bss_addr; + unsigned long offset; + Elf_Shdr *sechdrs; + int i; + + /* + * The section headers in kexec_purgatory are read-only. In order to + * have them modifiable make a temporary copy. + */ + sechdrs = vzalloc(pi->ehdr->e_shnum * sizeof(Elf_Shdr)); + if (!sechdrs) + return -ENOMEM; + memcpy(sechdrs, (void *)pi->ehdr + pi->ehdr->e_shoff, + pi->ehdr->e_shnum * sizeof(Elf_Shdr)); + pi->sechdrs = sechdrs; - /* Load SHF_ALLOC sections */ - buf_addr = kbuf.buffer; - load_addr = curr_load_addr = pi->purgatory_load_addr; - bss_addr = load_addr + kbuf.bufsz + bss_pad; + offset = 0; + bss_addr = kbuf->mem + kbuf->bufsz; + kbuf->image->start = pi->ehdr->e_entry; for (i = 0; i < pi->ehdr->e_shnum; i++) { + unsigned long align; + void *src, *dst; + if (!(sechdrs[i].sh_flags & SHF_ALLOC)) continue; align = sechdrs[i].sh_addralign; - if (sechdrs[i].sh_type != SHT_NOBITS) { - curr_load_addr = ALIGN(curr_load_addr, align); - offset = curr_load_addr - load_addr; - /* We already modifed ->sh_offset to keep src addr */ - src = (char *) sechdrs[i].sh_offset; - memcpy(buf_addr + offset, src, sechdrs[i].sh_size); - - /* Store load address and source address of section */ - sechdrs[i].sh_addr = curr_load_addr; - - /* - * This section got copied to temporary buffer. Update - * ->sh_offset accordingly. - */ - sechdrs[i].sh_offset = (unsigned long)(buf_addr + offset); - - /* Advance to the next address */ - curr_load_addr += sechdrs[i].sh_size; - } else { + if (sechdrs[i].sh_type == SHT_NOBITS) { bss_addr = ALIGN(bss_addr, align); sechdrs[i].sh_addr = bss_addr; bss_addr += sechdrs[i].sh_size; + continue; } - } - /* Update entry point based on load address of text section */ - if (entry_sidx >= 0) - entry += sechdrs[entry_sidx].sh_addr; + offset = ALIGN(offset, align); + if (sechdrs[i].sh_flags & SHF_EXECINSTR && + pi->ehdr->e_entry >= sechdrs[i].sh_addr && + pi->ehdr->e_entry < (sechdrs[i].sh_addr + + sechdrs[i].sh_size)) { + kbuf->image->start -= sechdrs[i].sh_addr; + kbuf->image->start += kbuf->mem + offset; + } - /* Make kernel jump to purgatory after shutdown */ - image->start = entry; + src = (void *)pi->ehdr + sechdrs[i].sh_offset; + dst = pi->purgatory_buf + offset; + memcpy(dst, src, sechdrs[i].sh_size); - /* Used later to get/set symbol values */ - pi->sechdrs = sechdrs; + sechdrs[i].sh_addr = kbuf->mem + offset; + sechdrs[i].sh_offset = offset; + offset += sechdrs[i].sh_size; + } - /* - * Used later to identify which section is purgatory and skip it - * from checksumming. - */ - pi->purgatory_buf = kbuf.buffer; - return ret; -out: - vfree(sechdrs); - vfree(kbuf.buffer); - return ret; + return 0; } static int kexec_apply_relocations(struct kimage *image) { int i, ret; struct purgatory_info *pi = &image->purgatory_info; - Elf_Shdr *sechdrs = pi->sechdrs; + const Elf_Shdr *sechdrs; + + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; - /* Apply relocations */ for (i = 0; i < pi->ehdr->e_shnum; i++) { - Elf_Shdr *section, *symtab; + const Elf_Shdr *relsec; + const Elf_Shdr *symtab; + Elf_Shdr *section; + + relsec = sechdrs + i; - if (sechdrs[i].sh_type != SHT_RELA && - sechdrs[i].sh_type != SHT_REL) + if (relsec->sh_type != SHT_RELA && + relsec->sh_type != SHT_REL) continue; /* @@ -876,12 +909,12 @@ static int kexec_apply_relocations(struct kimage *image) * symbol table. And ->sh_info contains section header * index of section to which relocations apply. */ - if (sechdrs[i].sh_info >= pi->ehdr->e_shnum || - sechdrs[i].sh_link >= pi->ehdr->e_shnum) + if (relsec->sh_info >= pi->ehdr->e_shnum || + relsec->sh_link >= pi->ehdr->e_shnum) return -ENOEXEC; - section = &sechdrs[sechdrs[i].sh_info]; - symtab = &sechdrs[sechdrs[i].sh_link]; + section = pi->sechdrs + relsec->sh_info; + symtab = sechdrs + relsec->sh_link; if (!(section->sh_flags & SHF_ALLOC)) continue; @@ -898,12 +931,12 @@ static int kexec_apply_relocations(struct kimage *image) * Respective architecture needs to provide support for applying * relocations of type SHT_RELA/SHT_REL. */ - if (sechdrs[i].sh_type == SHT_RELA) - ret = arch_kexec_apply_relocations_add(pi->ehdr, - sechdrs, i); - else if (sechdrs[i].sh_type == SHT_REL) - ret = arch_kexec_apply_relocations(pi->ehdr, - sechdrs, i); + if (relsec->sh_type == SHT_RELA) + ret = arch_kexec_apply_relocations_add(pi, section, + relsec, symtab); + else if (relsec->sh_type == SHT_REL) + ret = arch_kexec_apply_relocations(pi, section, + relsec, symtab); if (ret) return ret; } @@ -911,10 +944,18 @@ static int kexec_apply_relocations(struct kimage *image) return 0; } -/* Load relocatable purgatory object and relocate it appropriately */ -int kexec_load_purgatory(struct kimage *image, unsigned long min, - unsigned long max, int top_down, - unsigned long *load_addr) +/* + * kexec_load_purgatory - Load and relocate the purgatory object. + * @image: Image to add the purgatory to. + * @kbuf: Memory parameters to use. + * + * Allocates the memory needed for image->purgatory_info.sechdrs and + * image->purgatory_info.purgatory_buf/kbuf->buffer. Caller is responsible + * to free the memory after use. + * + * Return: 0 on success, negative errno on error. + */ +int kexec_load_purgatory(struct kimage *image, struct kexec_buf *kbuf) { struct purgatory_info *pi = &image->purgatory_info; int ret; @@ -922,55 +963,51 @@ int kexec_load_purgatory(struct kimage *image, unsigned long min, if (kexec_purgatory_size <= 0) return -EINVAL; - if (kexec_purgatory_size < sizeof(Elf_Ehdr)) - return -ENOEXEC; - - pi->ehdr = (Elf_Ehdr *)kexec_purgatory; - - if (memcmp(pi->ehdr->e_ident, ELFMAG, SELFMAG) != 0 - || pi->ehdr->e_type != ET_REL - || !elf_check_arch(pi->ehdr) - || pi->ehdr->e_shentsize != sizeof(Elf_Shdr)) - return -ENOEXEC; - - if (pi->ehdr->e_shoff >= kexec_purgatory_size - || (pi->ehdr->e_shnum * sizeof(Elf_Shdr) > - kexec_purgatory_size - pi->ehdr->e_shoff)) - return -ENOEXEC; + pi->ehdr = (const Elf_Ehdr *)kexec_purgatory; - ret = __kexec_load_purgatory(image, min, max, top_down); + ret = kexec_purgatory_setup_kbuf(pi, kbuf); if (ret) return ret; + ret = kexec_purgatory_setup_sechdrs(pi, kbuf); + if (ret) + goto out_free_kbuf; + ret = kexec_apply_relocations(image); if (ret) goto out; - *load_addr = pi->purgatory_load_addr; return 0; out: vfree(pi->sechdrs); pi->sechdrs = NULL; - +out_free_kbuf: vfree(pi->purgatory_buf); pi->purgatory_buf = NULL; return ret; } -static Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi, - const char *name) +/* + * kexec_purgatory_find_symbol - find a symbol in the purgatory + * @pi: Purgatory to search in. + * @name: Name of the symbol. + * + * Return: pointer to symbol in read-only symtab on success, NULL on error. + */ +static const Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi, + const char *name) { - Elf_Sym *syms; - Elf_Shdr *sechdrs; - Elf_Ehdr *ehdr; - int i, k; + const Elf_Shdr *sechdrs; + const Elf_Ehdr *ehdr; + const Elf_Sym *syms; const char *strtab; + int i, k; - if (!pi->sechdrs || !pi->ehdr) + if (!pi->ehdr) return NULL; - sechdrs = pi->sechdrs; ehdr = pi->ehdr; + sechdrs = (void *)ehdr + ehdr->e_shoff; for (i = 0; i < ehdr->e_shnum; i++) { if (sechdrs[i].sh_type != SHT_SYMTAB) @@ -979,8 +1016,8 @@ static Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi, if (sechdrs[i].sh_link >= ehdr->e_shnum) /* Invalid strtab section number */ continue; - strtab = (char *)sechdrs[sechdrs[i].sh_link].sh_offset; - syms = (Elf_Sym *)sechdrs[i].sh_offset; + strtab = (void *)ehdr + sechdrs[sechdrs[i].sh_link].sh_offset; + syms = (void *)ehdr + sechdrs[i].sh_offset; /* Go through symbols for a match */ for (k = 0; k < sechdrs[i].sh_size/sizeof(Elf_Sym); k++) { @@ -1008,7 +1045,7 @@ static Elf_Sym *kexec_purgatory_find_symbol(struct purgatory_info *pi, void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name) { struct purgatory_info *pi = &image->purgatory_info; - Elf_Sym *sym; + const Elf_Sym *sym; Elf_Shdr *sechdr; sym = kexec_purgatory_find_symbol(pi, name); @@ -1031,9 +1068,9 @@ void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name) int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, void *buf, unsigned int size, bool get_value) { - Elf_Sym *sym; - Elf_Shdr *sechdrs; struct purgatory_info *pi = &image->purgatory_info; + const Elf_Sym *sym; + Elf_Shdr *sec; char *sym_buf; sym = kexec_purgatory_find_symbol(pi, name); @@ -1046,16 +1083,15 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, return -EINVAL; } - sechdrs = pi->sechdrs; + sec = pi->sechdrs + sym->st_shndx; - if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { + if (sec->sh_type == SHT_NOBITS) { pr_err("symbol %s is in a bss section. Cannot %s\n", name, get_value ? "get" : "set"); return -EINVAL; } - sym_buf = (unsigned char *)sechdrs[sym->st_shndx].sh_offset + - sym->st_value; + sym_buf = (char *)pi->purgatory_buf + sec->sh_offset + sym->st_value; if (get_value) memcpy((void *)buf, sym_buf, size); @@ -1064,3 +1100,174 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, return 0; } +#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */ + +int crash_exclude_mem_range(struct crash_mem *mem, + unsigned long long mstart, unsigned long long mend) +{ + int i, j; + unsigned long long start, end; + struct crash_mem_range temp_range = {0, 0}; + + for (i = 0; i < mem->nr_ranges; i++) { + start = mem->ranges[i].start; + end = mem->ranges[i].end; + + if (mstart > end || mend < start) + continue; + + /* Truncate any area outside of range */ + if (mstart < start) + mstart = start; + if (mend > end) + mend = end; + + /* Found completely overlapping range */ + if (mstart == start && mend == end) { + mem->ranges[i].start = 0; + mem->ranges[i].end = 0; + if (i < mem->nr_ranges - 1) { + /* Shift rest of the ranges to left */ + for (j = i; j < mem->nr_ranges - 1; j++) { + mem->ranges[j].start = + mem->ranges[j+1].start; + mem->ranges[j].end = + mem->ranges[j+1].end; + } + } + mem->nr_ranges--; + return 0; + } + + if (mstart > start && mend < end) { + /* Split original range */ + mem->ranges[i].end = mstart - 1; + temp_range.start = mend + 1; + temp_range.end = end; + } else if (mstart != start) + mem->ranges[i].end = mstart - 1; + else + mem->ranges[i].start = mend + 1; + break; + } + + /* If a split happened, add the split to array */ + if (!temp_range.end) + return 0; + + /* Split happened */ + if (i == mem->max_nr_ranges - 1) + return -ENOMEM; + + /* Location where new range should go */ + j = i + 1; + if (j < mem->nr_ranges) { + /* Move over all ranges one slot towards the end */ + for (i = mem->nr_ranges - 1; i >= j; i--) + mem->ranges[i + 1] = mem->ranges[i]; + } + + mem->ranges[j].start = temp_range.start; + mem->ranges[j].end = temp_range.end; + mem->nr_ranges++; + return 0; +} + +int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, + void **addr, unsigned long *sz) +{ + Elf64_Ehdr *ehdr; + Elf64_Phdr *phdr; + unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz; + unsigned char *buf; + unsigned int cpu, i; + unsigned long long notes_addr; + unsigned long mstart, mend; + + /* extra phdr for vmcoreinfo elf note */ + nr_phdr = nr_cpus + 1; + nr_phdr += mem->nr_ranges; + + /* + * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping + * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64). + * I think this is required by tools like gdb. So same physical + * memory will be mapped in two elf headers. One will contain kernel + * text virtual addresses and other will have __va(physical) addresses. + */ + + nr_phdr++; + elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr); + elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN); + + buf = vzalloc(elf_sz); + if (!buf) + return -ENOMEM; + + ehdr = (Elf64_Ehdr *)buf; + phdr = (Elf64_Phdr *)(ehdr + 1); + memcpy(ehdr->e_ident, ELFMAG, SELFMAG); + ehdr->e_ident[EI_CLASS] = ELFCLASS64; + ehdr->e_ident[EI_DATA] = ELFDATA2LSB; + ehdr->e_ident[EI_VERSION] = EV_CURRENT; + ehdr->e_ident[EI_OSABI] = ELF_OSABI; + memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD); + ehdr->e_type = ET_CORE; + ehdr->e_machine = ELF_ARCH; + ehdr->e_version = EV_CURRENT; + ehdr->e_phoff = sizeof(Elf64_Ehdr); + ehdr->e_ehsize = sizeof(Elf64_Ehdr); + ehdr->e_phentsize = sizeof(Elf64_Phdr); + + /* Prepare one phdr of type PT_NOTE for each present cpu */ + for_each_present_cpu(cpu) { + phdr->p_type = PT_NOTE; + notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu)); + phdr->p_offset = phdr->p_paddr = notes_addr; + phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t); + (ehdr->e_phnum)++; + phdr++; + } + + /* Prepare one PT_NOTE header for vmcoreinfo */ + phdr->p_type = PT_NOTE; + phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note(); + phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE; + (ehdr->e_phnum)++; + phdr++; + + /* Prepare PT_LOAD type program header for kernel text region */ + if (kernel_map) { + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R|PF_W|PF_X; + phdr->p_vaddr = (Elf64_Addr)_text; + phdr->p_filesz = phdr->p_memsz = _end - _text; + phdr->p_offset = phdr->p_paddr = __pa_symbol(_text); + ehdr->e_phnum++; + phdr++; + } + + /* Go through all the ranges in mem->ranges[] and prepare phdr */ + for (i = 0; i < mem->nr_ranges; i++) { + mstart = mem->ranges[i].start; + mend = mem->ranges[i].end; + + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R|PF_W|PF_X; + phdr->p_offset = mstart; + + phdr->p_paddr = mstart; + phdr->p_vaddr = (unsigned long long) __va(mstart); + phdr->p_filesz = phdr->p_memsz = mend - mstart + 1; + phdr->p_align = 0; + ehdr->e_phnum++; + phdr++; + pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n", + phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz, + ehdr->e_phnum, phdr->p_offset); + } + + *addr = buf; + *sz = elf_sz; + return 0; +} diff --git a/kernel/resource.c b/kernel/resource.c index 2af6c03858b9..7d1e38d96735 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -23,6 +23,8 @@ #include <linux/pfn.h> #include <linux/mm.h> #include <linux/resource_ext.h> +#include <linux/string.h> +#include <linux/vmalloc.h> #include <asm/io.h> @@ -470,6 +472,67 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, } /* + * This function, being a variant of walk_system_ram_res(), calls the @func + * callback against all memory ranges of type System RAM which are marked as + * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from + * higher to lower. + */ +int walk_system_ram_res_rev(u64 start, u64 end, void *arg, + int (*func)(struct resource *, void *)) +{ + struct resource res, *rams; + int rams_size = 16, i; + int ret = -1; + + /* create a list */ + rams = vmalloc(sizeof(struct resource) * rams_size); + if (!rams) + return ret; + + res.start = start; + res.end = end; + res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + i = 0; + while ((res.start < res.end) && + (!find_next_iomem_res(&res, IORES_DESC_NONE, true))) { + if (i >= rams_size) { + /* re-alloc */ + struct resource *rams_new; + int rams_new_size; + + rams_new_size = rams_size + 16; + rams_new = vmalloc(sizeof(struct resource) + * rams_new_size); + if (!rams_new) + goto out; + + memcpy(rams_new, rams, + sizeof(struct resource) * rams_size); + vfree(rams); + rams = rams_new; + rams_size = rams_new_size; + } + + rams[i].start = res.start; + rams[i++].end = res.end; + + res.start = res.end + 1; + res.end = end; + } + + /* go reverse */ + for (i--; i >= 0; i--) { + ret = (*func)(&rams[i], arg); + if (ret) + break; + } + +out: + vfree(rams); + return ret; +} + +/* * This function calls the @func callback against all memory ranges, which * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY. */ diff --git a/arch/x86/purgatory/sha256.c b/lib/sha256.c index 548ca675a14a..4400c832e2aa 100644 --- a/arch/x86/purgatory/sha256.c +++ b/lib/sha256.c @@ -16,9 +16,9 @@ */ #include <linux/bitops.h> +#include <linux/sha256.h> +#include <linux/string.h> #include <asm/byteorder.h> -#include "sha256.h" -#include "../boot/string.h" static inline u32 Ch(u32 x, u32 y, u32 z) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0e1bb16b8c3f..3e7942c301a8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -678,7 +678,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) } EXPORT_SYMBOL(mem_cgroup_from_task); -static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) +struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { struct mem_cgroup *memcg = NULL; @@ -2119,6 +2119,15 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, } #ifndef CONFIG_SLOB +static struct mem_cgroup *get_mem_cgroup(struct mem_cgroup *memcg) +{ + rcu_read_lock(); + if (!css_tryget_online(&memcg->css)) + memcg = NULL; + rcu_read_unlock(); + return memcg; +} + static int memcg_alloc_cache_id(void) { int id, size; @@ -2248,7 +2257,7 @@ static inline bool memcg_kmem_bypass(void) */ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg = NULL; struct kmem_cache *memcg_cachep; int kmemcg_id; @@ -2260,7 +2269,10 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) if (current->memcg_kmem_skip_account) return cachep; - memcg = get_mem_cgroup_from_mm(current->mm); + if (current->target_memcg) + memcg = get_mem_cgroup(current->target_memcg); + if (!memcg) + memcg = get_mem_cgroup_from_mm(current->mm); kmemcg_id = READ_ONCE(memcg->kmemcg_id); if (kmemcg_id < 0) goto out; @@ -2338,13 +2350,16 @@ int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, */ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg = NULL; int ret = 0; if (memcg_kmem_bypass()) return 0; - memcg = get_mem_cgroup_from_mm(current->mm); + if (current->target_memcg) + memcg = get_mem_cgroup(current->target_memcg); + if (!memcg) + memcg = get_mem_cgroup_from_mm(current->mm); if (!mem_cgroup_is_root(memcg)) { ret = memcg_kmem_charge_memcg(page, gfp, order, memcg); if (!ret) |