diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/auditsc.c | 6 | ||||
| -rw-r--r-- | kernel/capability.c | 104 | ||||
| -rw-r--r-- | kernel/dma/swiotlb.c | 11 | ||||
| -rwxr-xr-x | kernel/gen_kheaders.sh | 2 | ||||
| -rw-r--r-- | kernel/irq/irqdomain.c | 39 | ||||
| -rw-r--r-- | kernel/irq/msi.c | 27 | ||||
| -rw-r--r-- | kernel/resource.c | 14 | ||||
| -rw-r--r-- | kernel/trace/trace.h | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_eprobe.c | 83 | ||||
| -rw-r--r-- | kernel/trace/trace_events_synth.c | 6 | ||||
| -rw-r--r-- | kernel/trace/trace_kprobe.c | 72 | ||||
| -rw-r--r-- | kernel/trace/trace_probe.c | 27 | ||||
| -rw-r--r-- | kernel/trace/trace_probe.h | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_probe_kernel.h | 30 | ||||
| -rw-r--r-- | kernel/trace/trace_probe_tmpl.h | 48 | ||||
| -rw-r--r-- | kernel/trace/trace_uprobe.c | 13 | ||||
| -rw-r--r-- | kernel/umh.c | 41 |
17 files changed, 191 insertions, 336 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 93d0b87f3283..addeed3df15d 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1295,15 +1295,11 @@ out: static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) { - int i; - if (cap_isclear(*cap)) { audit_log_format(ab, " %s=0", prefix); return; } - audit_log_format(ab, " %s=", prefix); - CAP_FOR_EACH_U32(i) - audit_log_format(ab, "%08x", cap->cap[CAP_LAST_U32 - i]); + audit_log_format(ab, " %s=%016llx", prefix, cap->val); } static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) diff --git a/kernel/capability.c b/kernel/capability.c index 339a44dfe2f4..3e058f41df32 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -20,13 +20,6 @@ #include <linux/user_namespace.h> #include <linux/uaccess.h> -/* - * Leveraged for setting/resetting capabilities - */ - -const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; -EXPORT_SYMBOL(__cap_empty_set); - int file_caps_enabled = 1; static int __init file_caps_disable(char *str) @@ -151,6 +144,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; + struct __user_cap_data_struct kdata[2]; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) @@ -163,42 +157,46 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); - if (!ret) { - struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; - unsigned i; - - for (i = 0; i < tocopy; i++) { - kdata[i].effective = pE.cap[i]; - kdata[i].permitted = pP.cap[i]; - kdata[i].inheritable = pI.cap[i]; - } - - /* - * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, - * we silently drop the upper capabilities here. This - * has the effect of making older libcap - * implementations implicitly drop upper capability - * bits when they perform a: capget/modify/capset - * sequence. - * - * This behavior is considered fail-safe - * behavior. Upgrading the application to a newer - * version of libcap will enable access to the newer - * capabilities. - * - * An alternative would be to return an error here - * (-ERANGE), but that causes legacy applications to - * unexpectedly fail; the capget/modify/capset aborts - * before modification is attempted and the application - * fails. - */ - if (copy_to_user(dataptr, kdata, tocopy - * sizeof(struct __user_cap_data_struct))) { - return -EFAULT; - } - } + if (ret) + return ret; - return ret; + /* + * Annoying legacy format with 64-bit capabilities exposed + * as two sets of 32-bit fields, so we need to split the + * capability values up. + */ + kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32; + kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32; + kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32; + + /* + * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, + * we silently drop the upper capabilities here. This + * has the effect of making older libcap + * implementations implicitly drop upper capability + * bits when they perform a: capget/modify/capset + * sequence. + * + * This behavior is considered fail-safe + * behavior. Upgrading the application to a newer + * version of libcap will enable access to the newer + * capabilities. + * + * An alternative would be to return an error here + * (-ERANGE), but that causes legacy applications to + * unexpectedly fail; the capget/modify/capset aborts + * before modification is attempted and the application + * fails. + */ + if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0]))) + return -EFAULT; + + return 0; +} + +static kernel_cap_t mk_kernel_cap(u32 low, u32 high) +{ + return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK }; } /** @@ -221,8 +219,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { - struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; - unsigned i, tocopy, copybytes; + struct __user_cap_data_struct kdata[2] = { { 0, }, }; + unsigned tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; @@ -246,21 +244,9 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; - for (i = 0; i < tocopy; i++) { - effective.cap[i] = kdata[i].effective; - permitted.cap[i] = kdata[i].permitted; - inheritable.cap[i] = kdata[i].inheritable; - } - while (i < _KERNEL_CAPABILITY_U32S) { - effective.cap[i] = 0; - permitted.cap[i] = 0; - inheritable.cap[i] = 0; - i++; - } - - effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; - permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; - inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective); + permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted); + inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable); new = prepare_creds(); if (!new) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a34c38bbe28f..03e3251cd9d2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -156,14 +156,6 @@ setup_io_tlb_npages(char *str) } early_param("swiotlb", setup_io_tlb_npages); -unsigned int swiotlb_max_segment(void) -{ - if (!io_tlb_default_mem.nslabs) - return 0; - return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE); -} -EXPORT_SYMBOL_GPL(swiotlb_max_segment); - unsigned long swiotlb_size_or_default(void) { return default_nslabs << IO_TLB_SHIFT; @@ -300,7 +292,8 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, return; } -static void *swiotlb_memblock_alloc(unsigned long nslabs, unsigned int flags, +static void __init *swiotlb_memblock_alloc(unsigned long nslabs, + unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)) { size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT); diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 81b97f0f6556..1ef9a87511f5 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -7,7 +7,7 @@ set -e sfile="$(readlink -f "$0")" outdir="$(pwd)" tarfile=$1 -cpio_dir=$outdir/$tarfile.tmp +cpio_dir=$outdir/${tarfile%/*}/.tmp_cpio_dir dir_list=" include/ diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index aa5b7eeeceb8..7d4fc6479062 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -470,31 +470,6 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, EXPORT_SYMBOL_GPL(irq_find_matching_fwspec); /** - * irq_domain_check_msi_remap - Check whether all MSI irq domains implement - * IRQ remapping - * - * Return: false if any MSI irq domain does not support IRQ remapping, - * true otherwise (including if there is no MSI irq domain) - */ -bool irq_domain_check_msi_remap(void) -{ - struct irq_domain *h; - bool ret = true; - - mutex_lock(&irq_domain_mutex); - list_for_each_entry(h, &irq_domain_list, link) { - if (irq_domain_is_msi(h) && - !irq_domain_hierarchical_is_msi_remap(h)) { - ret = false; - break; - } - } - mutex_unlock(&irq_domain_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(irq_domain_check_msi_remap); - -/** * irq_set_default_host() - Set a "default" irq domain * @domain: default domain pointer * @@ -1890,20 +1865,6 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain) if (domain->ops->alloc) domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY; } - -/** - * irq_domain_hierarchical_is_msi_remap - Check if the domain or any - * parent has MSI remapping support - * @domain: domain pointer - */ -bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain) -{ - for (; domain; domain = domain->parent) { - if (irq_domain_is_msi_remap(domain)) - return true; - } - return false; -} #else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ /** * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 783a3e6a0b10..d0f0389920c1 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1627,3 +1627,30 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain) { return (struct msi_domain_info *)domain->host_data; } + +/** + * msi_device_has_isolated_msi - True if the device has isolated MSI + * @dev: The device to check + * + * Isolated MSI means that HW modeled by an irq_domain on the path from the + * initiating device to the CPU will validate that the MSI message specifies an + * interrupt number that the device is authorized to trigger. This must block + * devices from triggering interrupts they are not authorized to trigger. + * Currently authorization means the MSI vector is one assigned to the device. + * + * This is interesting for securing VFIO use cases where a rouge MSI (eg created + * by abusing a normal PCI MemWr DMA) must not allow the VFIO userspace to + * impact outside its security domain, eg userspace triggering interrupts on + * kernel drivers, a VM triggering interrupts on the hypervisor, or a VM + * triggering interrupts on another VM. + */ +bool msi_device_has_isolated_msi(struct device *dev) +{ + struct irq_domain *domain = dev_get_msi_domain(dev); + + for (; domain; domain = domain->parent) + if (domain->flags & IRQ_DOMAIN_FLAG_ISOLATED_MSI) + return true; + return arch_is_isolated_msi(); +} +EXPORT_SYMBOL_GPL(msi_device_has_isolated_msi); diff --git a/kernel/resource.c b/kernel/resource.c index ddbbacb9fb50..b1763b2fd7ef 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1343,20 +1343,6 @@ retry: continue; } - /* - * All memory regions added from memory-hotplug path have the - * flag IORESOURCE_SYSTEM_RAM. If the resource does not have - * this flag, we know that we are dealing with a resource coming - * from HMM/devm. HMM/devm use another mechanism to add/release - * a resource. This goes via devm_request_mem_region and - * devm_release_mem_region. - * HMM/devm take care to release their resources when they want, - * so if we are dealing with them, let us just back off here. - */ - if (!(res->flags & IORESOURCE_SYSRAM)) { - break; - } - if (!(res->flags & IORESOURCE_MEM)) break; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f3aae2be1d53..616e1aa1c4da 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -25,7 +25,7 @@ #include "pid_list.h" #ifdef CONFIG_FTRACE_SYSCALLS -#include <asm/unistd.h> /* For NR_SYSCALLS */ +#include <asm/unistd.h> /* For NR_syscalls */ #include <asm/syscall.h> /* some archs define it here */ #endif diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 594ac1d086aa..67e854979d53 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -311,7 +311,7 @@ print_eprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - if (print_probe_args(s, tp->args, tp->nr_args, + if (trace_probe_print_args(s, tp->args, tp->nr_args, (u8 *)&field[1], field) < 0) goto out; @@ -320,7 +320,8 @@ print_eprobe_event(struct trace_iterator *iter, int flags, return trace_handle_return(s); } -static unsigned long get_event_field(struct fetch_insn *code, void *rec) +static nokprobe_inline unsigned long +get_event_field(struct fetch_insn *code, void *rec) { struct ftrace_event_field *field = code->data; unsigned long val; @@ -395,20 +396,12 @@ static int get_eprobe_size(struct trace_probe *tp, void *rec) case FETCH_OP_TP_ARG: val = get_event_field(code, rec); break; - case FETCH_OP_IMM: - val = code->immediate; - break; - case FETCH_OP_COMM: - val = (unsigned long)current->comm; - break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; goto retry; default: - continue; + if (process_common_fetch_insn(code, &val) < 0) + continue; } code++; len = process_fetch_insn_bottom(code, val, NULL, NULL); @@ -428,84 +421,26 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, void *base) { unsigned long val; + int ret; retry: switch (code->op) { case FETCH_OP_TP_ARG: val = get_event_field(code, rec); break; - case FETCH_OP_IMM: - val = code->immediate; - break; - case FETCH_OP_COMM: - val = (unsigned long)current->comm; - break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; goto retry; default: - return -EILSEQ; + ret = process_common_fetch_insn(code, &val); + if (ret < 0) + return ret; } code++; return process_fetch_insn_bottom(code, val, dest, base); } NOKPROBE_SYMBOL(process_fetch_insn) -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen_user(unsigned long addr) -{ - return kern_fetch_store_strlen_user(addr); -} - -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen(unsigned long addr) -{ - return kern_fetch_store_strlen(addr); -} - -/* - * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf - * with max length and relative data location. - */ -static nokprobe_inline int -fetch_store_string_user(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string_user(addr, dest, base); -} - -/* - * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max - * length and relative data location. - */ -static nokprobe_inline int -fetch_store_string(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string(addr, dest, base); -} - -static nokprobe_inline int -probe_mem_read_user(void *dest, void *src, size_t size) -{ - const void __user *uaddr = (__force const void __user *)src; - - return copy_from_user_nofault(dest, uaddr, size); -} - -static nokprobe_inline int -probe_mem_read(void *dest, void *src, size_t size) -{ -#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE - if ((unsigned long)src < TASK_SIZE) - return probe_mem_read_user(dest, src, size); -#endif - return copy_from_kernel_nofault(dest, src, size); -} - /* eprobe handler */ static inline void __eprobe_trace_func(struct eprobe_data *edata, void *rec) diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 70bddb25d9c0..46d0abb32d0f 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -448,12 +448,12 @@ static unsigned int trace_string(struct synth_trace_event *entry, data_offset = struct_size(entry, fields, event->n_u64); data_offset += data_size; - len = kern_fetch_store_strlen((unsigned long)str_val); + len = fetch_store_strlen((unsigned long)str_val); data_offset |= len << 16; *(u32 *)&entry->fields[*n_u64] = data_offset; - ret = kern_fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); + ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); (*n_u64)++; } else { @@ -542,7 +542,7 @@ static notrace void trace_event_raw_event_synth(void *__data, len = *((unsigned long *)str_val); len *= sizeof(unsigned long); } else { - len = kern_fetch_store_strlen((unsigned long)str_val); + len = fetch_store_strlen((unsigned long)str_val); } fields_size += len; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ee77c8203bd5..59cda19a9033 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1218,60 +1218,6 @@ static const struct file_operations kprobe_profile_ops = { .release = seq_release, }; -/* Kprobe specific fetch functions */ - -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen_user(unsigned long addr) -{ - return kern_fetch_store_strlen_user(addr); -} - -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen(unsigned long addr) -{ - return kern_fetch_store_strlen(addr); -} - -/* - * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf - * with max length and relative data location. - */ -static nokprobe_inline int -fetch_store_string_user(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string_user(addr, dest, base); -} - -/* - * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max - * length and relative data location. - */ -static nokprobe_inline int -fetch_store_string(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string(addr, dest, base); -} - -static nokprobe_inline int -probe_mem_read_user(void *dest, void *src, size_t size) -{ - const void __user *uaddr = (__force const void __user *)src; - - return copy_from_user_nofault(dest, uaddr, size); -} - -static nokprobe_inline int -probe_mem_read(void *dest, void *src, size_t size) -{ -#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE - if ((unsigned long)src < TASK_SIZE) - return probe_mem_read_user(dest, src, size); -#endif - return copy_from_kernel_nofault(dest, src, size); -} - /* Note that we don't verify it, since the code does not come from user space */ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, @@ -1279,6 +1225,7 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, { struct pt_regs *regs = rec; unsigned long val; + int ret; retry: /* 1st stage: get value from context */ @@ -1295,15 +1242,6 @@ retry: case FETCH_OP_RETVAL: val = regs_return_value(regs); break; - case FETCH_OP_IMM: - val = code->immediate; - break; - case FETCH_OP_COMM: - val = (unsigned long)current->comm; - break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API case FETCH_OP_ARG: val = regs_get_kernel_argument(regs, code->param); @@ -1313,7 +1251,9 @@ retry: code++; goto retry; default: - return -EILSEQ; + ret = process_common_fetch_insn(code, &val); + if (ret < 0) + return ret; } code++; @@ -1424,7 +1364,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - if (print_probe_args(s, tp->args, tp->nr_args, + if (trace_probe_print_args(s, tp->args, tp->nr_args, (u8 *)&field[1], field) < 0) goto out; @@ -1459,7 +1399,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - if (print_probe_args(s, tp->args, tp->nr_args, + if (trace_probe_print_args(s, tp->args, tp->nr_args, (u8 *)&field[1], field) < 0) goto out; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 11008c098727..20d0c4a97633 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1239,3 +1239,30 @@ int trace_probe_create(const char *raw_command, int (*createfn)(int, const char return ret; } + +int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_args, + u8 *data, void *field) +{ + void *p; + int i, j; + + for (i = 0; i < nr_args; i++) { + struct probe_arg *a = args + i; + + trace_seq_printf(s, " %s=", a->name); + if (likely(!a->count)) { + if (!a->type->print(s, data + a->offset, field)) + return -ENOMEM; + continue; + } + trace_seq_putc(s, '{'); + p = data + a->offset; + for (j = 0; j < a->count; j++) { + if (!a->type->print(s, p, field)) + return -ENOMEM; + trace_seq_putc(s, j == a->count - 1 ? '}' : ','); + p += a->type->size; + } + } + return 0; +} diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index b4f99553411e..ef8ed3b65d05 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -349,6 +349,8 @@ int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b); bool trace_probe_match_command_args(struct trace_probe *tp, int argc, const char **argv); int trace_probe_create(const char *raw_command, int (*createfn)(int, const char **)); +int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_args, + u8 *data, void *field); #define trace_probe_for_each_link(pos, tp) \ list_for_each_entry(pos, &(tp)->event->files, list) diff --git a/kernel/trace/trace_probe_kernel.h b/kernel/trace/trace_probe_kernel.h index 77dbd9ff9782..c4e1d4c03a85 100644 --- a/kernel/trace/trace_probe_kernel.h +++ b/kernel/trace/trace_probe_kernel.h @@ -12,7 +12,7 @@ */ /* Return the length of string -- including null terminal byte */ static nokprobe_inline int -kern_fetch_store_strlen_user(unsigned long addr) +fetch_store_strlen_user(unsigned long addr) { const void __user *uaddr = (__force const void __user *)addr; int ret; @@ -29,14 +29,14 @@ kern_fetch_store_strlen_user(unsigned long addr) /* Return the length of string -- including null terminal byte */ static nokprobe_inline int -kern_fetch_store_strlen(unsigned long addr) +fetch_store_strlen(unsigned long addr) { int ret, len = 0; u8 c; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if (addr < TASK_SIZE) - return kern_fetch_store_strlen_user(addr); + return fetch_store_strlen_user(addr); #endif do { @@ -63,7 +63,7 @@ static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void * with max length and relative data location. */ static nokprobe_inline int -kern_fetch_store_string_user(unsigned long addr, void *dest, void *base) +fetch_store_string_user(unsigned long addr, void *dest, void *base) { const void __user *uaddr = (__force const void __user *)addr; int maxlen = get_loc_len(*(u32 *)dest); @@ -86,7 +86,7 @@ kern_fetch_store_string_user(unsigned long addr, void *dest, void *base) * length and relative data location. */ static nokprobe_inline int -kern_fetch_store_string(unsigned long addr, void *dest, void *base) +fetch_store_string(unsigned long addr, void *dest, void *base) { int maxlen = get_loc_len(*(u32 *)dest); void *__dest; @@ -94,7 +94,7 @@ kern_fetch_store_string(unsigned long addr, void *dest, void *base) #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if ((unsigned long)addr < TASK_SIZE) - return kern_fetch_store_string_user(addr, dest, base); + return fetch_store_string_user(addr, dest, base); #endif if (unlikely(!maxlen)) @@ -112,4 +112,22 @@ kern_fetch_store_string(unsigned long addr, void *dest, void *base) return ret; } +static nokprobe_inline int +probe_mem_read_user(void *dest, void *src, size_t size) +{ + const void __user *uaddr = (__force const void __user *)src; + + return copy_from_user_nofault(dest, uaddr, size); +} + +static nokprobe_inline int +probe_mem_read(void *dest, void *src, size_t size) +{ +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + if ((unsigned long)src < TASK_SIZE) + return probe_mem_read_user(dest, src, size); +#endif + return copy_from_kernel_nofault(dest, src, size); +} + #endif /* __TRACE_PROBE_KERNEL_H_ */ diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 5cea672243f6..00707630788d 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -98,6 +98,26 @@ fetch_store_symstring(unsigned long addr, void *dest, void *base) return sprint_symbol(__dest, addr); } +/* common part of process_fetch_insn*/ +static nokprobe_inline int +process_common_fetch_insn(struct fetch_insn *code, unsigned long *val) +{ + switch (code->op) { + case FETCH_OP_IMM: + *val = code->immediate; + break; + case FETCH_OP_COMM: + *val = (unsigned long)current->comm; + break; + case FETCH_OP_DATA: + *val = (unsigned long)code->data; + break; + default: + return -EILSEQ; + } + return 0; +} + /* From the 2nd stage, routine is same */ static nokprobe_inline int process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val, @@ -253,31 +273,3 @@ store_trace_args(void *data, struct trace_probe *tp, void *rec, } } } - -static inline int -print_probe_args(struct trace_seq *s, struct probe_arg *args, int nr_args, - u8 *data, void *field) -{ - void *p; - int i, j; - - for (i = 0; i < nr_args; i++) { - struct probe_arg *a = args + i; - - trace_seq_printf(s, " %s=", a->name); - if (likely(!a->count)) { - if (!a->type->print(s, data + a->offset, field)) - return -ENOMEM; - continue; - } - trace_seq_putc(s, '{'); - p = data + a->offset; - for (j = 0; j < a->count; j++) { - if (!a->type->print(s, p, field)) - return -ENOMEM; - trace_seq_putc(s, j == a->count - 1 ? '}' : ','); - p += a->type->size; - } - } - return 0; -} diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8d64b6553aed..8b92e34ff0c8 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -220,6 +220,7 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, { struct pt_regs *regs = rec; unsigned long val; + int ret; /* 1st stage: get value from context */ switch (code->op) { @@ -235,20 +236,16 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, case FETCH_OP_RETVAL: val = regs_return_value(regs); break; - case FETCH_OP_IMM: - val = code->immediate; - break; case FETCH_OP_COMM: val = FETCH_TOKEN_COMM; break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; case FETCH_OP_FOFFS: val = translate_user_vaddr(code->immediate); break; default: - return -EILSEQ; + ret = process_common_fetch_insn(code, &val); + if (ret < 0) + return ret; } code++; @@ -1042,7 +1039,7 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e data = DATAOF_TRACE_ENTRY(entry, false); } - if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) + if (trace_probe_print_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) goto out; trace_seq_putc(s, '\n'); diff --git a/kernel/umh.c b/kernel/umh.c index fbf872c624cb..2a4708277335 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -501,9 +501,9 @@ static int proc_cap_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; - unsigned long cap_array[_KERNEL_CAPABILITY_U32S]; - kernel_cap_t new_cap; - int err, i; + unsigned long cap_array[2]; + kernel_cap_t new_cap, *cap; + int err; if (write && (!capable(CAP_SETPCAP) || !capable(CAP_SYS_MODULE))) @@ -514,14 +514,16 @@ static int proc_cap_handler(struct ctl_table *table, int write, * userspace if this is a read. */ spin_lock(&umh_sysctl_lock); - for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) { - if (table->data == CAP_BSET) - cap_array[i] = usermodehelper_bset.cap[i]; - else if (table->data == CAP_PI) - cap_array[i] = usermodehelper_inheritable.cap[i]; - else - BUG(); - } + if (table->data == CAP_BSET) + cap = &usermodehelper_bset; + else if (table->data == CAP_PI) + cap = &usermodehelper_inheritable; + else + BUG(); + + /* Legacy format: capabilities are exposed as two 32-bit values */ + cap_array[0] = (u32) cap->val; + cap_array[1] = cap->val >> 32; spin_unlock(&umh_sysctl_lock); t = *table; @@ -535,22 +537,15 @@ static int proc_cap_handler(struct ctl_table *table, int write, if (err < 0) return err; - /* - * convert from the sysctl array of ulongs to the kernel_cap_t - * internal representation - */ - for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) - new_cap.cap[i] = cap_array[i]; + new_cap.val = (u32)cap_array[0]; + new_cap.val += (u64)cap_array[1] << 32; /* * Drop everything not in the new_cap (but don't add things) */ if (write) { spin_lock(&umh_sysctl_lock); - if (table->data == CAP_BSET) - usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap); - if (table->data == CAP_PI) - usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap); + *cap = cap_intersect(*cap, new_cap); spin_unlock(&umh_sysctl_lock); } @@ -561,14 +556,14 @@ struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = CAP_BSET, - .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, { .procname = "inheritable", .data = CAP_PI, - .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, |