diff options
69 files changed, 5188 insertions, 1846 deletions
diff --git a/Documentation/ABI/obsolete/sysfs-selinux-checkreqprot b/Documentation/ABI/obsolete/sysfs-selinux-checkreqprot index 49ed9c8fd1e5..ed6b52ca210f 100644 --- a/Documentation/ABI/obsolete/sysfs-selinux-checkreqprot +++ b/Documentation/ABI/obsolete/sysfs-selinux-checkreqprot @@ -15,7 +15,7 @@ Description: actual protection), and Android and Linux distributions have been explicitly writing a "0" to /sys/fs/selinux/checkreqprot during initialization for some time. Support for setting checkreqprot to 1 - will be removed in a future kernel release, at which point the kernel + will be removed no sooner than June 2021, at which point the kernel will always cease using checkreqprot internally and will always check the actual protections being applied upon mmap/mprotect calls. The checkreqprot selinuxfs node will remain for backward compatibility diff --git a/Documentation/admin-guide/kdump/gdbmacros.txt b/Documentation/admin-guide/kdump/gdbmacros.txt index 220d0a80ca2c..82aecdcae8a6 100644 --- a/Documentation/admin-guide/kdump/gdbmacros.txt +++ b/Documentation/admin-guide/kdump/gdbmacros.txt @@ -170,57 +170,103 @@ document trapinfo address the kernel panicked. end -define dump_log_idx - set $idx = $arg0 - if ($argc > 1) - set $prev_flags = $arg1 +define dump_record + set var $desc = $arg0 + set var $info = $arg1 + if ($argc > 2) + set var $prev_flags = $arg2 else - set $prev_flags = 0 + set var $prev_flags = 0 end - set $msg = ((struct printk_log *) (log_buf + $idx)) - set $prefix = 1 - set $newline = 1 - set $log = log_buf + $idx + sizeof(*$msg) - - # prev & LOG_CONT && !(msg->flags & LOG_PREIX) - if (($prev_flags & 8) && !($msg->flags & 4)) - set $prefix = 0 + + set var $prefix = 1 + set var $newline = 1 + + set var $begin = $desc->text_blk_lpos.begin % (1U << prb->text_data_ring.size_bits) + set var $next = $desc->text_blk_lpos.next % (1U << prb->text_data_ring.size_bits) + + # handle data-less record + if ($begin & 1) + set var $text_len = 0 + set var $log = "" + else + # handle wrapping data block + if ($begin > $next) + set var $begin = 0 + end + + # skip over descriptor id + set var $begin = $begin + sizeof(long) + + # handle truncated message + if ($next - $begin < $info->text_len) + set var $text_len = $next - $begin + else + set var $text_len = $info->text_len + end + + set var $log = &prb->text_data_ring.data[$begin] + end + + # prev & LOG_CONT && !(info->flags & LOG_PREIX) + if (($prev_flags & 8) && !($info->flags & 4)) + set var $prefix = 0 end - # msg->flags & LOG_CONT - if ($msg->flags & 8) + # info->flags & LOG_CONT + if ($info->flags & 8) # (prev & LOG_CONT && !(prev & LOG_NEWLINE)) if (($prev_flags & 8) && !($prev_flags & 2)) - set $prefix = 0 + set var $prefix = 0 end - # (!(msg->flags & LOG_NEWLINE)) - if (!($msg->flags & 2)) - set $newline = 0 + # (!(info->flags & LOG_NEWLINE)) + if (!($info->flags & 2)) + set var $newline = 0 end end if ($prefix) - printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000 + printf "[%5lu.%06lu] ", $info->ts_nsec / 1000000000, $info->ts_nsec % 1000000000 end - if ($msg->text_len != 0) - eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len + if ($text_len) + eval "printf \"%%%d.%ds\", $log", $text_len, $text_len end if ($newline) printf "\n" end - if ($msg->dict_len > 0) - set $dict = $log + $msg->text_len - set $idx = 0 - set $line = 1 - while ($idx < $msg->dict_len) - if ($line) - printf " " - set $line = 0 + + # handle dictionary data + + set var $dict = &$info->dev_info.subsystem[0] + set var $dict_len = sizeof($info->dev_info.subsystem) + if ($dict[0] != '\0') + printf " SUBSYSTEM=" + set var $idx = 0 + while ($idx < $dict_len) + set var $c = $dict[$idx] + if ($c == '\0') + loop_break + else + if ($c < ' ' || $c >= 127 || $c == '\\') + printf "\\x%02x", $c + else + printf "%c", $c + end end - set $c = $dict[$idx] + set var $idx = $idx + 1 + end + printf "\n" + end + + set var $dict = &$info->dev_info.device[0] + set var $dict_len = sizeof($info->dev_info.device) + if ($dict[0] != '\0') + printf " DEVICE=" + set var $idx = 0 + while ($idx < $dict_len) + set var $c = $dict[$idx] if ($c == '\0') - printf "\n" - set $line = 1 + loop_break else if ($c < ' ' || $c >= 127 || $c == '\\') printf "\\x%02x", $c @@ -228,33 +274,46 @@ define dump_log_idx printf "%c", $c end end - set $idx = $idx + 1 + set var $idx = $idx + 1 end printf "\n" end end -document dump_log_idx - Dump a single log given its index in the log buffer. The first - parameter is the index into log_buf, the second is optional and - specified the previous log buffer's flags, used for properly - formatting continued lines. +document dump_record + Dump a single record. The first parameter is the descriptor, + the second parameter is the info, the third parameter is + optional and specifies the previous record's flags, used for + properly formatting continued lines. end define dmesg - set $i = log_first_idx - set $end_idx = log_first_idx - set $prev_flags = 0 + # definitions from kernel/printk/printk_ringbuffer.h + set var $desc_committed = 1 + set var $desc_finalized = 2 + set var $desc_sv_bits = sizeof(long) * 8 + set var $desc_flags_shift = $desc_sv_bits - 2 + set var $desc_flags_mask = 3 << $desc_flags_shift + set var $id_mask = ~$desc_flags_mask + + set var $desc_count = 1U << prb->desc_ring.count_bits + set var $prev_flags = 0 + + set var $id = prb->desc_ring.tail_id.counter + set var $end_id = prb->desc_ring.head_id.counter while (1) - set $msg = ((struct printk_log *) (log_buf + $i)) - if ($msg->len == 0) - set $i = 0 - else - dump_log_idx $i $prev_flags - set $i = $i + $msg->len - set $prev_flags = $msg->flags + set var $desc = &prb->desc_ring.descs[$id % $desc_count] + set var $info = &prb->desc_ring.infos[$id % $desc_count] + + # skip non-committed record + set var $state = 3 & ($desc->state_var.counter >> $desc_flags_shift) + if ($state == $desc_committed || $state == $desc_finalized) + dump_record $desc $info $prev_flags + set var $prev_flags = $info->flags end - if ($i == $end_idx) + + set var $id = ($id + 1) & $id_mask + if ($id == $end_id) loop_break end end diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst index 2baad0bfb09d..e44a6c01f336 100644 --- a/Documentation/admin-guide/kdump/vmcoreinfo.rst +++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst @@ -189,50 +189,123 @@ from this. Free areas descriptor. User-space tools use this value to iterate the free_area ranges. MAX_ORDER is used by the zone buddy allocator. -log_first_idx +prb +--- + +A pointer to the printk ringbuffer (struct printk_ringbuffer). This +may be pointing to the static boot ringbuffer or the dynamically +allocated ringbuffer, depending on when the the core dump occurred. +Used by user-space tools to read the active kernel log buffer. + +printk_rb_static +---------------- + +A pointer to the static boot printk ringbuffer. If @prb has a +different value, this is useful for viewing the initial boot messages, +which may have been overwritten in the dynamically allocated +ringbuffer. + +clear_seq +--------- + +The sequence number of the printk() record after the last clear +command. It indicates the first record after the last +SYSLOG_ACTION_CLEAR, like issued by 'dmesg -c'. Used by user-space +tools to dump a subset of the dmesg log. + +printk_ringbuffer +----------------- + +The size of a printk_ringbuffer structure. This structure contains all +information required for accessing the various components of the +kernel log buffer. + +(printk_ringbuffer, desc_ring|text_data_ring|dict_data_ring|fail) +----------------------------------------------------------------- + +Offsets for the various components of the printk ringbuffer. Used by +user-space tools to view the kernel log buffer without requiring the +declaration of the structure. + +prb_desc_ring ------------- -Index of the first record stored in the buffer log_buf. Used by -user-space tools to read the strings in the log_buf. +The size of the prb_desc_ring structure. This structure contains +information about the set of record descriptors. -log_buf -------- +(prb_desc_ring, count_bits|descs|head_id|tail_id) +------------------------------------------------- + +Offsets for the fields describing the set of record descriptors. Used +by user-space tools to be able to traverse the descriptors without +requiring the declaration of the structure. + +prb_desc +-------- + +The size of the prb_desc structure. This structure contains +information about a single record descriptor. + +(prb_desc, info|state_var|text_blk_lpos|dict_blk_lpos) +------------------------------------------------------ + +Offsets for the fields describing a record descriptors. Used by +user-space tools to be able to read descriptors without requiring +the declaration of the structure. + +prb_data_blk_lpos +----------------- + +The size of the prb_data_blk_lpos structure. This structure contains +information about where the text or dictionary data (data block) is +located within the respective data ring. + +(prb_data_blk_lpos, begin|next) +------------------------------- -Console output is written to the ring buffer log_buf at index -log_first_idx. Used to get the kernel log. +Offsets for the fields describing the location of a data block. Used +by user-space tools to be able to locate data blocks without +requiring the declaration of the structure. -log_buf_len +printk_info ----------- -log_buf's length. +The size of the printk_info structure. This structure contains all +the meta-data for a record. -clear_idx ---------- +(printk_info, seq|ts_nsec|text_len|dict_len|caller_id) +------------------------------------------------------ -The index that the next printk() record to read after the last clear -command. It indicates the first record after the last SYSLOG_ACTION -_CLEAR, like issued by 'dmesg -c'. Used by user-space tools to dump -the dmesg log. +Offsets for the fields providing the meta-data for a record. Used by +user-space tools to be able to read the information without requiring +the declaration of the structure. -log_next_idx ------------- +prb_data_ring +------------- -The index of the next record to store in the buffer log_buf. Used to -compute the index of the current buffer position. +The size of the prb_data_ring structure. This structure contains +information about a set of data blocks. -printk_log ----------- +(prb_data_ring, size_bits|data|head_lpos|tail_lpos) +--------------------------------------------------- -The size of a structure printk_log. Used to compute the size of -messages, and extract dmesg log. It encapsulates header information for -log_buf, such as timestamp, syslog level, etc. +Offsets for the fields describing a set of data blocks. Used by +user-space tools to be able to access the data blocks without +requiring the declaration of the structure. -(printk_log, ts_nsec|len|text_len|dict_len) -------------------------------------------- +atomic_long_t +------------- + +The size of the atomic_long_t structure. Used by user-space tools to +be able to copy the full structure, regardless of its +architecture-specific implementation. + +(atomic_long_t, counter) +------------------------ -It represents field offsets in struct printk_log. User space tools -parse it and check whether the values of printk_log's members have been -changed. +Offset for the long value of an atomic_long_t variable. Used by +user-space tools to access the long value without requiring the +architecture-specific declaration. (free_area.free_list, MIGRATE_TYPES) ------------------------------------ diff --git a/MAINTAINERS b/MAINTAINERS index 42f1230d1add..7eecfb345806 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13970,6 +13970,7 @@ PRINTK M: Petr Mladek <pmladek@suse.com> M: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> R: Steven Rostedt <rostedt@goodmis.org> +R: John Ogness <john.ogness@linutronix.de> S: Maintained F: include/linux/printk.h F: kernel/printk/ @@ -15620,6 +15621,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git F: Documentation/ABI/obsolete/sysfs-selinux-checkreqprot F: Documentation/ABI/obsolete/sysfs-selinux-disable F: Documentation/admin-guide/LSM/SELinux.rst +F: include/trace/events/avc.h F: include/uapi/linux/selinux_netlink.h F: scripts/selinux/ F: security/selinux/ diff --git a/arch/Kconfig b/arch/Kconfig index 76ec3395b843..8519d9f42e33 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -450,10 +450,23 @@ config ARCH_WANT_OLD_COMPAT_IPC select ARCH_WANT_COMPAT_IPC_PARSE_VERSION bool +config HAVE_ARCH_SECCOMP + bool + help + An arch should select this symbol to support seccomp mode 1 (the fixed + syscall policy), and must provide an overrides for __NR_seccomp_sigreturn, + and compat syscalls if the asm-generic/seccomp.h defaults need adjustment: + - __NR_seccomp_read_32 + - __NR_seccomp_write_32 + - __NR_seccomp_exit_32 + - __NR_seccomp_sigreturn_32 + config HAVE_ARCH_SECCOMP_FILTER bool + select HAVE_ARCH_SECCOMP help An arch should select this symbol if it provides all of these things: + - all the requirements for HAVE_ARCH_SECCOMP - syscall_get_arch() - syscall_get_arguments() - syscall_rollback() @@ -464,6 +477,23 @@ config HAVE_ARCH_SECCOMP_FILTER results in the system call being skipped immediately. - seccomp syscall wired up +config SECCOMP + prompt "Enable seccomp to safely execute untrusted bytecode" + def_bool y + depends on HAVE_ARCH_SECCOMP + help + This kernel feature is useful for number crunching applications + that may need to handle untrusted bytecode during their + execution. By using pipes or other transports made available + to the process as file descriptors supporting the read/write + syscalls, it's possible to isolate those applications in their + own address space using seccomp. Once seccomp is enabled via + prctl(PR_SET_SECCOMP) or the seccomp() syscall, it cannot be + disabled and the task is only allowed to execute a few safe + syscalls defined by each seccomp mode. + + If unsure, say Y. + config SECCOMP_FILTER def_bool y depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 1ed277f2e4fc..3996b6572c3a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -68,6 +68,7 @@ config ARM select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK @@ -1618,20 +1619,6 @@ config UACCESS_WITH_MEMCPY However, if the CPU data cache is using a write-allocate mode, this option is unlikely to provide any performance gain. -config SECCOMP - bool - prompt "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - config PARAVIRT bool "Enable paravirtualization code" help diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 583b6a60b094..893130ce1626 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1041,19 +1041,6 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK config CC_HAVE_SHADOW_CALL_STACK def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18) -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - config PARAVIRT bool "Enable paravirtualization code" help diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 3d5afb5f5685..7f424c85772c 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -309,16 +309,3 @@ endmenu source "arch/csky/Kconfig.platforms" source "kernel/Kconfig.hz" - -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index d262ac0c8714..37bd6a5f38fb 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -26,6 +26,7 @@ config MICROBLAZE select GENERIC_SCHED_CLOCK select HAVE_ARCH_HASH select HAVE_ARCH_KGDB + select HAVE_ARCH_SECCOMP select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE @@ -120,23 +121,6 @@ config CMDLINE_FORCE Set this to have arguments from the default kernel command string override those passed by the boot loader. -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - endmenu menu "Kernel features" diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index cff19225da3d..440614dc9de2 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -3006,23 +3006,6 @@ config PHYSICAL_START specified in the "crashkernel=YM@XM" command line boot parameter passed to the panic-ed kernel). -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - config MIPS_O32_FP64_SUPPORT bool "Support for O32 binaries using 64-bit FP" if !CPU_MIPSR6 depends on 32BIT || MIPS32_O32 diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 3b0f53dd70bc..cd4afe1e7a6c 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -378,19 +378,3 @@ endmenu source "drivers/parisc/Kconfig" - -config SECCOMP - def_bool y - prompt "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 592036103493..1f0bd7e223f5 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -946,23 +946,6 @@ config ARCH_WANTS_FREEZER_CONTROL source "kernel/power/Kconfig" -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - config PPC_MEM_KEYS prompt "PowerPC Memory Protection Keys" def_bool y diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7766e1289468..b7821ac36d28 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -334,19 +334,6 @@ menu "Kernel features" source "kernel/Kconfig.hz" -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - config RISCV_SBI_V01 bool "SBI v0.1 support" default y diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 0a3899386a51..d509bf23ef78 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -792,23 +792,6 @@ config CRASH_DUMP endmenu -config SECCOMP - def_bool y - prompt "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. - config CCW def_bool y diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index d20927128fce..18278152c91c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -600,22 +600,6 @@ config PHYSICAL_START where the fail safe kernel needs to run at a different address than the panic-ed kernel. -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl, it cannot be disabled and the task is only - allowed to execute a few safe syscalls defined by each seccomp - mode. - - If unsure, say N. - config SMP bool "Symmetric multi-processing support" depends on SYS_SUPPORTS_SMP diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 91ed1104b7f4..096530eac8e1 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -23,6 +23,7 @@ config SPARC select HAVE_OPROFILE select HAVE_ARCH_KGDB if !SMP || SPARC64 select HAVE_ARCH_TRACEHOOK + select HAVE_ARCH_SECCOMP if SPARC64 select HAVE_EXIT_THREAD select HAVE_PCI select SYSCTL_EXCEPTION_TRACE @@ -227,23 +228,6 @@ config EARLYFB help Say Y here to enable a faster early framebuffer boot console. -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on SPARC64 && PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" depends on SPARC64 && SMP diff --git a/arch/um/Kconfig b/arch/um/Kconfig index eb51fec75948..d49f471b02e3 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -173,22 +173,6 @@ config PGTABLE_LEVELS default 3 if 3_LEVEL_PGTABLES default 2 -config SECCOMP - def_bool y - prompt "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. - config UML_TIME_TRAVEL_SUPPORT bool prompt "Support time-travel mode (e.g. for test execution)" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 835d93006bd6..255084c65138 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1970,22 +1970,6 @@ config EFI_MIXED If unsure, say N. -config SECCOMP - def_bool y - prompt "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - source "kernel/Kconfig.hz" config KEXEC diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index e997e0119c02..d8a29dc5a284 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -217,20 +217,6 @@ config HOTPLUG_CPU Say N if you want to disable CPU hotplug. -config SECCOMP - bool - prompt "Enable seccomp to safely compute untrusted bytecode" - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via prctl(PR_SET_SECCOMP), it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - config FAST_SYSCALL_XTENSA bool "Enable fast atomic syscalls" default n diff --git a/drivers/base/core.c b/drivers/base/core.c index 8dd753539c06..0bad9e6066c3 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4061,22 +4061,21 @@ void device_shutdown(void) */ #ifdef CONFIG_PRINTK -static int -create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen) +static void +set_dev_info(const struct device *dev, struct dev_printk_info *dev_info) { const char *subsys; - size_t pos = 0; + + memset(dev_info, 0, sizeof(*dev_info)); if (dev->class) subsys = dev->class->name; else if (dev->bus) subsys = dev->bus->name; else - return 0; + return; - pos += snprintf(hdr + pos, hdrlen - pos, "SUBSYSTEM=%s", subsys); - if (pos >= hdrlen) - goto overflow; + strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem)); /* * Add device identifier DEVICE=: @@ -4092,41 +4091,28 @@ create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen) c = 'b'; else c = 'c'; - pos++; - pos += snprintf(hdr + pos, hdrlen - pos, - "DEVICE=%c%u:%u", - c, MAJOR(dev->devt), MINOR(dev->devt)); + + snprintf(dev_info->device, sizeof(dev_info->device), + "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt)); } else if (strcmp(subsys, "net") == 0) { struct net_device *net = to_net_dev(dev); - pos++; - pos += snprintf(hdr + pos, hdrlen - pos, - "DEVICE=n%u", net->ifindex); + snprintf(dev_info->device, sizeof(dev_info->device), + "n%u", net->ifindex); } else { - pos++; - pos += snprintf(hdr + pos, hdrlen - pos, - "DEVICE=+%s:%s", subsys, dev_name(dev)); + snprintf(dev_info->device, sizeof(dev_info->device), + "+%s:%s", subsys, dev_name(dev)); } - - if (pos >= hdrlen) - goto overflow; - - return pos; - -overflow: - dev_WARN(dev, "device/subsystem name too long"); - return 0; } int dev_vprintk_emit(int level, const struct device *dev, const char *fmt, va_list args) { - char hdr[128]; - size_t hdrlen; + struct dev_printk_info dev_info; - hdrlen = create_syslog_header(dev, hdr, sizeof(hdr)); + set_dev_info(dev, &dev_info); - return vprintk_emit(0, level, hdrlen ? hdr : NULL, hdrlen, fmt, args); + return vprintk_emit(0, level, &dev_info, fmt, args); } EXPORT_SYMBOL(dev_vprintk_emit); diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 6594dbc34a37..206bde8308b2 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -55,6 +55,9 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_OFFSET(name, field) \ vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ (unsigned long)offsetof(struct name, field)) +#define VMCOREINFO_TYPE_OFFSET(name, field) \ + vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \ + (unsigned long)offsetof(name, field)) #define VMCOREINFO_LENGTH(name, value) \ vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value) #define VMCOREINFO_NUMBER(name) \ diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index e7e45f0cc7da..2915f56ad421 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -2,9 +2,9 @@ #ifndef __LINUX_DEBUG_LOCKING_H #define __LINUX_DEBUG_LOCKING_H -#include <linux/kernel.h> #include <linux/atomic.h> #include <linux/bug.h> +#include <linux/printk.h> struct task_struct; diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 3028b644b4fb..6f009559ee54 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -21,6 +21,14 @@ struct device; +#define PRINTK_INFO_SUBSYSTEM_LEN 16 +#define PRINTK_INFO_DEVICE_LEN 48 + +struct dev_printk_info { + char subsystem[PRINTK_INFO_SUBSYSTEM_LEN]; + char device[PRINTK_INFO_DEVICE_LEN]; +}; + #ifdef CONFIG_PRINTK __printf(3, 0) __cold diff --git a/include/linux/kernel.h b/include/linux/kernel.h index c25b8e41c0ea..e4aa29b1ad62 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -526,7 +526,6 @@ extern unsigned int sysctl_oops_all_cpu_backtrace; #endif /* CONFIG_SMP */ extern void bust_spinlocks(int yes); -extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 93fcef105061..f1c4e7b56bd9 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -43,6 +43,16 @@ #define is_non_negative(a) ((a) > 0 || (a) == 0) #define is_negative(a) (!(is_non_negative(a))) +/* + * Allows for effectively applying __must_check to a macro so we can have + * both the type-agnostic benefits of the macros while also being able to + * enforce that the return value is, in fact, checked. + */ +static inline bool __must_check __must_check_overflow(bool overflow) +{ + return unlikely(overflow); +} + #ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on @@ -52,32 +62,32 @@ * alias for __builtin_add_overflow, but add type checks similar to * below. */ -#define check_add_overflow(a, b, d) ({ \ +#define check_add_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_add_overflow(__a, __b, __d); \ -}) +})) -#define check_sub_overflow(a, b, d) ({ \ +#define check_sub_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_sub_overflow(__a, __b, __d); \ -}) +})) -#define check_mul_overflow(a, b, d) ({ \ +#define check_mul_overflow(a, b, d) __must_check_overflow(({ \ typeof(a) __a = (a); \ typeof(b) __b = (b); \ typeof(d) __d = (d); \ (void) (&__a == &__b); \ (void) (&__a == __d); \ __builtin_mul_overflow(__a, __b, __d); \ -}) +})) #else @@ -190,21 +200,20 @@ }) -#define check_add_overflow(a, b, d) \ +#define check_add_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d)) + __unsigned_add_overflow(a, b, d))) -#define check_sub_overflow(a, b, d) \ +#define check_sub_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d)) + __unsigned_sub_overflow(a, b, d))) -#define check_mul_overflow(a, b, d) \ +#define check_mul_overflow(a, b, d) __must_check_overflow( \ __builtin_choose_expr(is_signed_type(typeof(a)), \ __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d)) - + __unsigned_mul_overflow(a, b, d))) #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ @@ -227,7 +236,7 @@ * '*d' will hold the results of the attempted shift, but is not * considered "safe for use" if false is returned. */ -#define check_shl_overflow(a, s, d) ({ \ +#define check_shl_overflow(a, s, d) __must_check_overflow(({ \ typeof(a) _a = a; \ typeof(s) _s = s; \ typeof(d) _d = d; \ @@ -237,7 +246,7 @@ *_d = (_a_full << _to_shift); \ (_to_shift != _s || is_negative(*_d) || is_negative(_a) || \ (*_d >> _to_shift) != _a); \ -}) +})) /** * array_size() - Calculate size of 2-dimensional array. diff --git a/include/linux/printk.h b/include/linux/printk.h index 34c1a7be3e01..78479633ccfc 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -12,6 +12,8 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; +extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ + #define PRINTK_MAX_SINGLE_HEADER_LEN 2 static inline int printk_get_level(const char *buffer) @@ -159,10 +161,12 @@ static inline void printk_nmi_direct_enter(void) { } static inline void printk_nmi_direct_exit(void) { } #endif /* PRINTK_NMI */ +struct dev_printk_info; + #ifdef CONFIG_PRINTK -asmlinkage __printf(5, 0) +asmlinkage __printf(4, 0) int vprintk_emit(int facility, int level, - const char *dict, size_t dictlen, + const struct dev_printk_info *dev_info, const char *fmt, va_list args); asmlinkage __printf(1, 0) diff --git a/include/trace/events/avc.h b/include/trace/events/avc.h new file mode 100644 index 000000000000..b55fda2e0773 --- /dev/null +++ b/include/trace/events/avc.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Authors: Thiébaud Weksteen <tweek@google.com> + * Peter Enderborg <Peter.Enderborg@sony.com> + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM avc + +#if !defined(_TRACE_SELINUX_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_SELINUX_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(selinux_audited, + + TP_PROTO(struct selinux_audit_data *sad, + char *scontext, + char *tcontext, + const char *tclass + ), + + TP_ARGS(sad, scontext, tcontext, tclass), + + TP_STRUCT__entry( + __field(u32, requested) + __field(u32, denied) + __field(u32, audited) + __field(int, result) + __string(scontext, scontext) + __string(tcontext, tcontext) + __string(tclass, tclass) + ), + + TP_fast_assign( + __entry->requested = sad->requested; + __entry->denied = sad->denied; + __entry->audited = sad->audited; + __entry->result = sad->result; + __assign_str(tcontext, tcontext); + __assign_str(scontext, scontext); + __assign_str(tclass, tclass); + ), + + TP_printk("requested=0x%x denied=0x%x audited=0x%x result=%d scontext=%s tcontext=%s tclass=%s", + __entry->requested, __entry->denied, __entry->audited, __entry->result, + __get_str(scontext), __get_str(tcontext), __get_str(tclass) + ) +); + +#endif + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/init/Kconfig b/init/Kconfig index c0f56e455dce..2a583ef2ff66 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -682,7 +682,8 @@ config IKHEADERS config LOG_BUF_SHIFT int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" - range 12 25 + range 12 25 if !H8300 + range 12 19 if H8300 default 17 depends on PRINTK help diff --git a/kernel/audit.c b/kernel/audit.c index 7efaece534a9..68cee3bc8cfe 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -123,9 +123,9 @@ static u32 audit_backlog_limit = 64; static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; /* The identity of the user shutting down the audit system. */ -kuid_t audit_sig_uid = INVALID_UID; -pid_t audit_sig_pid = -1; -u32 audit_sig_sid = 0; +static kuid_t audit_sig_uid = INVALID_UID; +static pid_t audit_sig_pid = -1; +static u32 audit_sig_sid; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] @@ -934,8 +934,7 @@ static void audit_free_reply(struct audit_reply *reply) if (!reply) return; - if (reply->skb) - kfree_skb(reply->skb); + kfree_skb(reply->skb); if (reply->net) put_net(reply->net); kfree(reply); diff --git a/kernel/audit.h b/kernel/audit.h index ddc22878433d..3b9c0945225a 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -327,10 +327,6 @@ static inline int audit_signal_info_syscall(struct task_struct *t) extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len); -extern pid_t audit_sig_pid; -extern kuid_t audit_sig_uid; -extern u32 audit_sig_sid; - extern int audit_filter(int msgtype, unsigned int listtype); extern void audit_ctl_lock(void); diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile index 4d052fc6bcde..eee3dc9b60a9 100644 --- a/kernel/printk/Makefile +++ b/kernel/printk/Makefile @@ -2,3 +2,4 @@ obj-y = printk.o obj-$(CONFIG_PRINTK) += printk_safe.o obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o +obj-$(CONFIG_PRINTK) += printk_ringbuffer.o diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 660f9a6bf73a..3a8fd491758c 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -14,9 +14,9 @@ extern raw_spinlock_t logbuf_lock; -__printf(5, 0) +__printf(4, 0) int vprintk_store(int facility, int level, - const char *dict, size_t dictlen, + const struct dev_printk_info *dev_info, const char *fmt, va_list args); __printf(1, 0) int vprintk_default(const char *fmt, va_list args); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 9b75f6bfc333..fe64a49344bf 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -55,6 +55,7 @@ #define CREATE_TRACE_POINTS #include <trace/events/printk.h> +#include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" #include "internal.h" @@ -294,30 +295,22 @@ enum con_msg_format_flags { static int console_msg_format = MSG_FORMAT_DEFAULT; /* - * The printk log buffer consists of a chain of concatenated variable - * length records. Every record starts with a record header, containing - * the overall length of the record. + * The printk log buffer consists of a sequenced collection of records, each + * containing variable length message text. Every record also contains its + * own meta-data (@info). * - * The heads to the first and last entry in the buffer, as well as the - * sequence numbers of these entries are maintained when messages are - * stored. + * Every record meta-data carries the timestamp in microseconds, as well as + * the standard userspace syslog level and syslog facility. The usual kernel + * messages use LOG_KERN; userspace-injected messages always carry a matching + * syslog facility, by default LOG_USER. The origin of every message can be + * reliably determined that way. * - * If the heads indicate available messages, the length in the header - * tells the start next message. A length == 0 for the next message - * indicates a wrap-around to the beginning of the buffer. + * The human readable log message of a record is available in @text, the + * length of the message text in @text_len. The stored message is not + * terminated. * - * Every record carries the monotonic timestamp in microseconds, as well as - * the standard userspace syslog level and syslog facility. The usual - * kernel messages use LOG_KERN; userspace-injected messages always carry - * a matching syslog facility, by default LOG_USER. The origin of every - * message can be reliably determined that way. - * - * The human readable log message directly follows the message header. The - * length of the message text is stored in the header, the stored message - * is not terminated. - * - * Optionally, a message can carry a dictionary of properties (key/value pairs), - * to provide userspace with a machine-readable message context. + * Optionally, a record can carry a dictionary of properties (key/value + * pairs), to provide userspace with a machine-readable message context. * * Examples for well-defined, commonly used property names are: * DEVICE=b12:8 device identifier @@ -327,25 +320,22 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; * +sound:card0 subsystem:devname * SUBSYSTEM=pci driver-core subsystem name * - * Valid characters in property names are [a-zA-Z0-9.-_]. The plain text value - * follows directly after a '=' character. Every property is terminated by - * a '\0' character. The last property is not terminated. - * - * Example of a message structure: - * 0000 ff 8f 00 00 00 00 00 00 monotonic time in nsec - * 0008 34 00 record is 52 bytes long - * 000a 0b 00 text is 11 bytes long - * 000c 1f 00 dictionary is 23 bytes long - * 000e 03 00 LOG_KERN (facility) LOG_ERR (level) - * 0010 69 74 27 73 20 61 20 6c "it's a l" - * 69 6e 65 "ine" - * 001b 44 45 56 49 43 "DEVIC" - * 45 3d 62 38 3a 32 00 44 "E=b8:2\0D" - * 52 49 56 45 52 3d 62 75 "RIVER=bu" - * 67 "g" - * 0032 00 00 00 padding to next message header - * - * The 'struct printk_log' buffer header must never be directly exported to + * Valid characters in property names are [a-zA-Z0-9.-_]. Property names + * and values are terminated by a '\0' character. + * + * Example of record values: + * record.text_buf = "it's a line" (unterminated) + * record.info.seq = 56 + * record.info.ts_nsec = 36863 + * record.info.text_len = 11 + * record.info.facility = 0 (LOG_KERN) + * record.info.flags = 0 + * record.info.level = 3 (LOG_ERR) + * record.info.caller_id = 299 (task 299) + * record.info.dev_info.subsystem = "pci" (terminated) + * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) + * + * The 'struct printk_info' buffer must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * @@ -365,23 +355,6 @@ enum log_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; -struct printk_log { - u64 ts_nsec; /* timestamp in nanoseconds */ - u16 len; /* length of entire record */ - u16 text_len; /* length of text buffer */ - u16 dict_len; /* length of dictionary buffer */ - u8 facility; /* syslog facility */ - u8 flags:5; /* internal record flags */ - u8 level:3; /* syslog level */ -#ifdef CONFIG_PRINTK_CALLER - u32 caller_id; /* thread id or processor id */ -#endif -} -#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS -__packed __aligned(4) -#endif -; - /* * The logbuf_lock protects kmsg buffer, indices, counters. This can be taken * within the scheduler's rq lock. It must be released before calling @@ -421,26 +394,16 @@ DEFINE_RAW_SPINLOCK(logbuf_lock); DECLARE_WAIT_QUEUE_HEAD(log_wait); /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; -static u32 syslog_idx; static size_t syslog_partial; static bool syslog_time; -/* index and sequence number of the first record stored in the buffer */ -static u64 log_first_seq; -static u32 log_first_idx; - -/* index and sequence number of the next record to store in the buffer */ -static u64 log_next_seq; -static u32 log_next_idx; - /* the next printk record to write to the console */ static u64 console_seq; -static u32 console_idx; static u64 exclusive_console_stop_seq; +static unsigned long console_dropped; /* the next printk record to read after the last 'clear' command */ static u64 clear_seq; -static u32 clear_idx; #ifdef CONFIG_PRINTK_CALLER #define PREFIX_MAX 48 @@ -453,7 +416,7 @@ static u32 clear_idx; #define LOG_FACILITY(v) ((v) >> 3 & 0xff) /* record buffer */ -#define LOG_ALIGN __alignof__(struct printk_log) +#define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) #define LOG_BUF_LEN_MAX (u32)(1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); @@ -461,6 +424,23 @@ static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; /* + * Define the average message size. This only affects the number of + * descriptors that will be available. Underestimating is better than + * overestimating (too many available descriptors is better than not enough). + */ +#define PRB_AVGBITS 5 /* 32 character average length */ + +#if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS +#error CONFIG_LOG_BUF_SHIFT value too small. +#endif +_DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, + PRB_AVGBITS, &__log_buf[0]); + +static struct printk_ringbuffer printk_rb_dynamic; + +static struct printk_ringbuffer *prb = &printk_rb_static; + +/* * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before * per_cpu_areas are initialised. This variable is set to true when * it's safe to access per-CPU data. @@ -484,108 +464,6 @@ u32 log_buf_len_get(void) return log_buf_len; } -/* human readable text of the record */ -static char *log_text(const struct printk_log *msg) -{ - return (char *)msg + sizeof(struct printk_log); -} - -/* optional key/value pair dictionary attached to the record */ -static char *log_dict(const struct printk_log *msg) -{ - return (char *)msg + sizeof(struct printk_log) + msg->text_len; -} - -/* get record by index; idx must point to valid msg */ -static struct printk_log *log_from_idx(u32 idx) -{ - struct printk_log *msg = (struct printk_log *)(log_buf + idx); - - /* - * A length == 0 record is the end of buffer marker. Wrap around and - * read the message at the start of the buffer. - */ - if (!msg->len) - return (struct printk_log *)log_buf; - return msg; -} - -/* get next record; idx must point to valid msg */ -static u32 log_next(u32 idx) -{ - struct printk_log *msg = (struct printk_log *)(log_buf + idx); - - /* length == 0 indicates the end of the buffer; wrap */ - /* - * A length == 0 record is the end of buffer marker. Wrap around and - * read the message at the start of the buffer as *this* one, and - * return the one after that. - */ - if (!msg->len) { - msg = (struct printk_log *)log_buf; - return msg->len; - } - return idx + msg->len; -} - -/* - * Check whether there is enough free space for the given message. - * - * The same values of first_idx and next_idx mean that the buffer - * is either empty or full. - * - * If the buffer is empty, we must respect the position of the indexes. - * They cannot be reset to the beginning of the buffer. - */ -static int logbuf_has_space(u32 msg_size, bool empty) -{ - u32 free; - - if (log_next_idx > log_first_idx || empty) - free = max(log_buf_len - log_next_idx, log_first_idx); - else - free = log_first_idx - log_next_idx; - - /* - * We need space also for an empty header that signalizes wrapping - * of the buffer. - */ - return free >= msg_size + sizeof(struct printk_log); -} - -static int log_make_free_space(u32 msg_size) -{ - while (log_first_seq < log_next_seq && - !logbuf_has_space(msg_size, false)) { - /* drop old messages until we have enough contiguous space */ - log_first_idx = log_next(log_first_idx); - log_first_seq++; - } - - if (clear_seq < log_first_seq) { - clear_seq = log_first_seq; - clear_idx = log_first_idx; - } - - /* sequence numbers are equal, so the log buffer is empty */ - if (logbuf_has_space(msg_size, log_first_seq == log_next_seq)) - return 0; - - return -ENOMEM; -} - -/* compute the message size including the padding bytes */ -static u32 msg_used_size(u16 text_len, u16 dict_len, u32 *pad_len) -{ - u32 size; - - size = sizeof(struct printk_log) + text_len + dict_len; - *pad_len = (-size) & (LOG_ALIGN - 1); - size += *pad_len; - - return size; -} - /* * Define how much of the log buffer we could take at maximum. The value * must be greater than two. Note that only half of the buffer is available @@ -594,84 +472,69 @@ static u32 msg_used_size(u16 text_len, u16 dict_len, u32 *pad_len) #define MAX_LOG_TAKE_PART 4 static const char trunc_msg[] = "<truncated>"; -static u32 truncate_msg(u16 *text_len, u16 *trunc_msg_len, - u16 *dict_len, u32 *pad_len) +static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) { /* * The message should not take the whole buffer. Otherwise, it might * get removed too soon. */ u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; + if (*text_len > max_text_len) *text_len = max_text_len; - /* enable the warning message */ + + /* enable the warning message (if there is room) */ *trunc_msg_len = strlen(trunc_msg); - /* disable the "dict" completely */ - *dict_len = 0; - /* compute the size again, count also the warning message */ - return msg_used_size(*text_len + *trunc_msg_len, 0, pad_len); + if (*text_len >= *trunc_msg_len) + *text_len -= *trunc_msg_len; + else + *trunc_msg_len = 0; } /* insert record into the buffer, discard old ones, update heads */ static int log_store(u32 caller_id, int facility, int level, enum log_flags flags, u64 ts_nsec, - const char *dict, u16 dict_len, + const struct dev_printk_info *dev_info, const char *text, u16 text_len) { - struct printk_log *msg; - u32 size, pad_len; + struct prb_reserved_entry e; + struct printk_record r; u16 trunc_msg_len = 0; - /* number of '\0' padding bytes to next message */ - size = msg_used_size(text_len, dict_len, &pad_len); + prb_rec_init_wr(&r, text_len); - if (log_make_free_space(size)) { + if (!prb_reserve(&e, prb, &r)) { /* truncate the message if it is too long for empty buffer */ - size = truncate_msg(&text_len, &trunc_msg_len, - &dict_len, &pad_len); + truncate_msg(&text_len, &trunc_msg_len); + prb_rec_init_wr(&r, text_len + trunc_msg_len); /* survive when the log buffer is too small for trunc_msg */ - if (log_make_free_space(size)) + if (!prb_reserve(&e, prb, &r)) return 0; } - if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) { - /* - * This message + an additional empty header does not fit - * at the end of the buffer. Add an empty header with len == 0 - * to signify a wrap around. - */ - memset(log_buf + log_next_idx, 0, sizeof(struct printk_log)); - log_next_idx = 0; - } - /* fill message */ - msg = (struct printk_log *)(log_buf + log_next_idx); - memcpy(log_text(msg), text, text_len); - msg->text_len = text_len; - if (trunc_msg_len) { - memcpy(log_text(msg) + text_len, trunc_msg, trunc_msg_len); - msg->text_len += trunc_msg_len; - } - memcpy(log_dict(msg), dict, dict_len); - msg->dict_len = dict_len; - msg->facility = facility; - msg->level = level & 7; - msg->flags = flags & 0x1f; + memcpy(&r.text_buf[0], text, text_len); + if (trunc_msg_len) + memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); + r.info->text_len = text_len + trunc_msg_len; + r.info->facility = facility; + r.info->level = level & 7; + r.info->flags = flags & 0x1f; if (ts_nsec > 0) - msg->ts_nsec = ts_nsec; + r.info->ts_nsec = ts_nsec; else - msg->ts_nsec = local_clock(); -#ifdef CONFIG_PRINTK_CALLER - msg->caller_id = caller_id; -#endif - memset(log_dict(msg) + dict_len, 0, pad_len); - msg->len = size; + r.info->ts_nsec = local_clock(); + r.info->caller_id = caller_id; + if (dev_info) + memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); /* insert message */ - log_next_idx += msg->len; - log_next_seq++; + if ((flags & LOG_CONT) || !(flags & LOG_NEWLINE)) + prb_commit(&e); + else + prb_final_commit(&e); - return msg->text_len; + return (text_len + trunc_msg_len); } int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); @@ -723,13 +586,13 @@ static void append_char(char **pp, char *e, char c) *(*pp)++ = c; } -static ssize_t msg_print_ext_header(char *buf, size_t size, - struct printk_log *msg, u64 seq) +static ssize_t info_print_ext_header(char *buf, size_t size, + struct printk_info *info) { - u64 ts_usec = msg->ts_nsec; + u64 ts_usec = info->ts_nsec; char caller[20]; #ifdef CONFIG_PRINTK_CALLER - u32 id = msg->caller_id; + u32 id = info->caller_id; snprintf(caller, sizeof(caller), ",caller=%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); @@ -740,13 +603,13 @@ static ssize_t msg_print_ext_header(char *buf, size_t size, do_div(ts_usec, 1000); return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", - (msg->facility << 3) | msg->level, seq, ts_usec, - msg->flags & LOG_CONT ? 'c' : '-', caller); + (info->facility << 3) | info->level, info->seq, + ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); } -static ssize_t msg_print_ext_body(char *buf, size_t size, - char *dict, size_t dict_len, - char *text, size_t text_len) +static ssize_t msg_add_ext_text(char *buf, size_t size, + const char *text, size_t text_len, + unsigned char endc) { char *p = buf, *e = buf + size; size_t i; @@ -760,45 +623,56 @@ static ssize_t msg_print_ext_body(char *buf, size_t size, else append_char(&p, e, c); } - append_char(&p, e, '\n'); + append_char(&p, e, endc); - if (dict_len) { - bool line = true; + return p - buf; +} - for (i = 0; i < dict_len; i++) { - unsigned char c = dict[i]; +static ssize_t msg_add_dict_text(char *buf, size_t size, + const char *key, const char *val) +{ + size_t val_len = strlen(val); + ssize_t len; - if (line) { - append_char(&p, e, ' '); - line = false; - } + if (!val_len) + return 0; - if (c == '\0') { - append_char(&p, e, '\n'); - line = true; - continue; - } + len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ + len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); + len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); - if (c < ' ' || c >= 127 || c == '\\') { - p += scnprintf(p, e - p, "\\x%02x", c); - continue; - } + return len; +} - append_char(&p, e, c); - } - append_char(&p, e, '\n'); - } +static ssize_t msg_print_ext_body(char *buf, size_t size, + char *text, size_t text_len, + struct dev_printk_info *dev_info) +{ + ssize_t len; - return p - buf; + len = msg_add_ext_text(buf, size, text, text_len, '\n'); + + if (!dev_info) + goto out; + + len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", + dev_info->subsystem); + len += msg_add_dict_text(buf + len, size - len, "DEVICE", + dev_info->device); +out: + return len; } /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { u64 seq; - u32 idx; struct ratelimit_state rs; struct mutex lock; char buf[CONSOLE_EXT_LOG_MAX]; + + struct printk_info info; + char text_buf[CONSOLE_EXT_LOG_MAX]; + struct printk_record record; }; static __printf(3, 4) __cold @@ -808,7 +682,7 @@ int devkmsg_emit(int facility, int level, const char *fmt, ...) int r; va_start(args, fmt); - r = vprintk_emit(facility, level, NULL, 0, fmt, args); + r = vprintk_emit(facility, level, NULL, fmt, args); va_end(args); return r; @@ -881,7 +755,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; - struct printk_log *msg; + struct printk_record *r = &user->record; size_t len; ssize_t ret; @@ -893,7 +767,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, return ret; logbuf_lock_irq(); - while (user->seq == log_next_seq) { + if (!prb_read_valid(prb, user->seq, r)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; logbuf_unlock_irq(); @@ -902,30 +776,26 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, logbuf_unlock_irq(); ret = wait_event_interruptible(log_wait, - user->seq != log_next_seq); + prb_read_valid(prb, user->seq, r)); if (ret) goto out; logbuf_lock_irq(); } - if (user->seq < log_first_seq) { + if (user->seq < prb_first_valid_seq(prb)) { /* our last seen message is gone, return error and reset */ - user->idx = log_first_idx; - user->seq = log_first_seq; + user->seq = prb_first_valid_seq(prb); ret = -EPIPE; logbuf_unlock_irq(); goto out; } - msg = log_from_idx(user->idx); - len = msg_print_ext_header(user->buf, sizeof(user->buf), - msg, user->seq); + len = info_print_ext_header(user->buf, sizeof(user->buf), r->info); len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len, - log_dict(msg), msg->dict_len, - log_text(msg), msg->text_len); + &r->text_buf[0], r->info->text_len, + &r->info->dev_info); - user->idx = log_next(user->idx); - user->seq++; + user->seq = r->info->seq + 1; logbuf_unlock_irq(); if (len > count) { @@ -965,8 +835,7 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) switch (whence) { case SEEK_SET: /* the first record */ - user->idx = log_first_idx; - user->seq = log_first_seq; + user->seq = prb_first_valid_seq(prb); break; case SEEK_DATA: /* @@ -974,13 +843,11 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ - user->idx = clear_idx; user->seq = clear_seq; break; case SEEK_END: /* after the last record */ - user->idx = log_next_idx; - user->seq = log_next_seq; + user->seq = prb_next_seq(prb); break; default: ret = -EINVAL; @@ -1000,9 +867,9 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) poll_wait(file, &log_wait, wait); logbuf_lock_irq(); - if (user->seq < log_next_seq) { + if (prb_read_valid(prb, user->seq, NULL)) { /* return error when data has vanished underneath us */ - if (user->seq < log_first_seq) + if (user->seq < prb_first_valid_seq(prb)) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; @@ -1037,9 +904,11 @@ static int devkmsg_open(struct inode *inode, struct file *file) mutex_init(&user->lock); + prb_rec_init_rd(&user->record, &user->info, + &user->text_buf[0], sizeof(user->text_buf)); + logbuf_lock_irq(); - user->idx = log_first_idx; - user->seq = log_first_seq; + user->seq = prb_first_valid_seq(prb); logbuf_unlock_irq(); file->private_data = user; @@ -1080,23 +949,58 @@ const struct file_operations kmsg_fops = { */ void log_buf_vmcoreinfo_setup(void) { - VMCOREINFO_SYMBOL(log_buf); - VMCOREINFO_SYMBOL(log_buf_len); - VMCOREINFO_SYMBOL(log_first_idx); - VMCOREINFO_SYMBOL(clear_idx); - VMCOREINFO_SYMBOL(log_next_idx); + struct dev_printk_info *dev_info = NULL; + + VMCOREINFO_SYMBOL(prb); + VMCOREINFO_SYMBOL(printk_rb_static); + VMCOREINFO_SYMBOL(clear_seq); + /* - * Export struct printk_log size and field offsets. User space tools can + * Export struct size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ - VMCOREINFO_STRUCT_SIZE(printk_log); - VMCOREINFO_OFFSET(printk_log, ts_nsec); - VMCOREINFO_OFFSET(printk_log, len); - VMCOREINFO_OFFSET(printk_log, text_len); - VMCOREINFO_OFFSET(printk_log, dict_len); -#ifdef CONFIG_PRINTK_CALLER - VMCOREINFO_OFFSET(printk_log, caller_id); -#endif + + VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); + VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); + VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); + VMCOREINFO_OFFSET(printk_ringbuffer, fail); + + VMCOREINFO_STRUCT_SIZE(prb_desc_ring); + VMCOREINFO_OFFSET(prb_desc_ring, count_bits); + VMCOREINFO_OFFSET(prb_desc_ring, descs); + VMCOREINFO_OFFSET(prb_desc_ring, infos); + VMCOREINFO_OFFSET(prb_desc_ring, head_id); + VMCOREINFO_OFFSET(prb_desc_ring, tail_id); + + VMCOREINFO_STRUCT_SIZE(prb_desc); + VMCOREINFO_OFFSET(prb_desc, state_var); + VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); + + VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); + VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); + VMCOREINFO_OFFSET(prb_data_blk_lpos, next); + + VMCOREINFO_STRUCT_SIZE(printk_info); + VMCOREINFO_OFFSET(printk_info, seq); + VMCOREINFO_OFFSET(printk_info, ts_nsec); + VMCOREINFO_OFFSET(printk_info, text_len); + VMCOREINFO_OFFSET(printk_info, caller_id); + VMCOREINFO_OFFSET(printk_info, dev_info); + + VMCOREINFO_STRUCT_SIZE(dev_printk_info); + VMCOREINFO_OFFSET(dev_printk_info, subsystem); + VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); + VMCOREINFO_OFFSET(dev_printk_info, device); + VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); + + VMCOREINFO_STRUCT_SIZE(prb_data_ring); + VMCOREINFO_OFFSET(prb_data_ring, size_bits); + VMCOREINFO_OFFSET(prb_data_ring, data); + VMCOREINFO_OFFSET(prb_data_ring, head_lpos); + VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); + + VMCOREINFO_SIZE(atomic_long_t); + VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); } #endif @@ -1174,11 +1078,46 @@ static void __init set_percpu_data_ready(void) __printk_percpu_data_ready = true; } +static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, + struct printk_record *r) +{ + struct prb_reserved_entry e; + struct printk_record dest_r; + + prb_rec_init_wr(&dest_r, r->info->text_len); + + if (!prb_reserve(&e, rb, &dest_r)) + return 0; + + memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); + dest_r.info->text_len = r->info->text_len; + dest_r.info->facility = r->info->facility; + dest_r.info->level = r->info->level; + dest_r.info->flags = r->info->flags; + dest_r.info->ts_nsec = r->info->ts_nsec; + dest_r.info->caller_id = r->info->caller_id; + memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); + + prb_final_commit(&e); + + return prb_record_text_space(&e); +} + +static char setup_text_buf[LOG_LINE_MAX] __initdata; + void __init setup_log_buf(int early) { + struct printk_info *new_infos; + unsigned int new_descs_count; + struct prb_desc *new_descs; + struct printk_info info; + struct printk_record r; + size_t new_descs_size; + size_t new_infos_size; unsigned long flags; char *new_log_buf; unsigned int free; + u64 seq; /* * Some archs call setup_log_buf() multiple times - first is very @@ -1197,24 +1136,75 @@ void __init setup_log_buf(int early) if (!new_log_buf_len) return; + new_descs_count = new_log_buf_len >> PRB_AVGBITS; + if (new_descs_count == 0) { + pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); + return; + } + new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); if (unlikely(!new_log_buf)) { - pr_err("log_buf_len: %lu bytes not available\n", - new_log_buf_len); + pr_err("log_buf_len: %lu text bytes not available\n", + new_log_buf_len); return; } + new_descs_size = new_descs_count * sizeof(struct prb_desc); + new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); + if (unlikely(!new_descs)) { + pr_err("log_buf_len: %zu desc bytes not available\n", + new_descs_size); + goto err_free_log_buf; + } + + new_infos_size = new_descs_count * sizeof(struct printk_info); + new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); + if (unlikely(!new_infos)) { + pr_err("log_buf_len: %zu info bytes not available\n", + new_infos_size); + goto err_free_descs; + } + + prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); + + prb_init(&printk_rb_dynamic, + new_log_buf, ilog2(new_log_buf_len), + new_descs, ilog2(new_descs_count), + new_infos); + logbuf_lock_irqsave(flags); + log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; - free = __LOG_BUF_LEN - log_next_idx; - memcpy(log_buf, __log_buf, __LOG_BUF_LEN); + + free = __LOG_BUF_LEN; + prb_for_each_record(0, &printk_rb_static, seq, &r) + free -= add_to_rb(&printk_rb_dynamic, &r); + + /* + * This is early enough that everything is still running on the + * boot CPU and interrupts are disabled. So no new messages will + * appear during the transition to the dynamic buffer. + */ + prb = &printk_rb_dynamic; + logbuf_unlock_irqrestore(flags); + if (seq != prb_next_seq(&printk_rb_static)) { + pr_err("dropped %llu messages\n", + prb_next_seq(&printk_rb_static) - seq); + } + pr_info("log_buf_len: %u bytes\n", log_buf_len); pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); + return; + +err_free_descs: + memblock_free(__pa(new_descs), new_descs_size); +err_free_log_buf: + memblock_free(__pa(new_log_buf), new_log_buf_len); } static bool __read_mostly ignore_loglevel; @@ -1321,18 +1311,18 @@ static size_t print_caller(u32 id, char *buf) #define print_caller(id, buf) 0 #endif -static size_t print_prefix(const struct printk_log *msg, bool syslog, - bool time, char *buf) +static size_t info_print_prefix(const struct printk_info *info, bool syslog, + bool time, char *buf) { size_t len = 0; if (syslog) - len = print_syslog((msg->facility << 3) | msg->level, buf); + len = print_syslog((info->facility << 3) | info->level, buf); if (time) - len += print_time(msg->ts_nsec, buf + len); + len += print_time(info->ts_nsec, buf + len); - len += print_caller(msg->caller_id, buf + len); + len += print_caller(info->caller_id, buf + len); if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { buf[len++] = ' '; @@ -1342,72 +1332,150 @@ static size_t print_prefix(const struct printk_log *msg, bool syslog, return len; } -static size_t msg_print_text(const struct printk_log *msg, bool syslog, - bool time, char *buf, size_t size) +/* + * Prepare the record for printing. The text is shifted within the given + * buffer to avoid a need for another one. The following operations are + * done: + * + * - Add prefix for each line. + * - Add the trailing newline that has been removed in vprintk_store(). + * - Drop truncated lines that do not longer fit into the buffer. + * + * Return: The length of the updated/prepared text, including the added + * prefixes and the newline. The dropped line(s) are not counted. + */ +static size_t record_print_text(struct printk_record *r, bool syslog, + bool time) { - const char *text = log_text(msg); - size_t text_size = msg->text_len; - size_t len = 0; + size_t text_len = r->info->text_len; + size_t buf_size = r->text_buf_size; + char *text = r->text_buf; char prefix[PREFIX_MAX]; - const size_t prefix_len = print_prefix(msg, syslog, time, prefix); + bool truncated = false; + size_t prefix_len; + size_t line_len; + size_t len = 0; + char *next; + + /* + * If the message was truncated because the buffer was not large + * enough, treat the available text as if it were the full text. + */ + if (text_len > buf_size) + text_len = buf_size; - do { - const char *next = memchr(text, '\n', text_size); - size_t text_len; + prefix_len = info_print_prefix(r->info, syslog, time, prefix); + /* + * @text_len: bytes of unprocessed text + * @line_len: bytes of current line _without_ newline + * @text: pointer to beginning of current line + * @len: number of bytes prepared in r->text_buf + */ + for (;;) { + next = memchr(text, '\n', text_len); if (next) { - text_len = next - text; - next++; - text_size -= next - text; + line_len = next - text; } else { - text_len = text_size; + /* Drop truncated line(s). */ + if (truncated) + break; + line_len = text_len; } - if (buf) { - if (prefix_len + text_len + 1 >= size - len) + /* + * Truncate the text if there is not enough space to add the + * prefix and a trailing newline. + */ + if (len + prefix_len + text_len + 1 > buf_size) { + /* Drop even the current line if no space. */ + if (len + prefix_len + line_len + 1 > buf_size) break; - memcpy(buf + len, prefix, prefix_len); - len += prefix_len; - memcpy(buf + len, text, text_len); - len += text_len; - buf[len++] = '\n'; - } else { - /* SYSLOG_ACTION_* buffer size only calculation */ - len += prefix_len + text_len + 1; + text_len = buf_size - len - prefix_len - 1; + truncated = true; } - text = next; - } while (text); + memmove(text + prefix_len, text, text_len); + memcpy(text, prefix, prefix_len); + + len += prefix_len + line_len + 1; + + if (text_len == line_len) { + /* + * Add the trailing newline removed in + * vprintk_store(). + */ + text[prefix_len + line_len] = '\n'; + break; + } + + /* + * Advance beyond the added prefix and the related line with + * its newline. + */ + text += prefix_len + line_len + 1; + + /* + * The remaining text has only decreased by the line with its + * newline. + * + * Note that @text_len can become zero. It happens when @text + * ended with a newline (either due to truncation or the + * original string ending with "\n\n"). The loop is correctly + * repeated and (if not truncated) an empty line with a prefix + * will be prepared. + */ + text_len -= line_len + 1; + } return len; } +static size_t get_record_print_text_size(struct printk_info *info, + unsigned int line_count, + bool syslog, bool time) +{ + char prefix[PREFIX_MAX]; + size_t prefix_len; + + prefix_len = info_print_prefix(info, syslog, time, prefix); + + /* + * Each line will be preceded with a prefix. The intermediate + * newlines are already within the text, but a final trailing + * newline will be added. + */ + return ((prefix_len * line_count) + info->text_len + 1); +} + static int syslog_print(char __user *buf, int size) { + struct printk_info info; + struct printk_record r; char *text; - struct printk_log *msg; int len = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) return -ENOMEM; + prb_rec_init_rd(&r, &info, text, LOG_LINE_MAX + PREFIX_MAX); + while (size > 0) { size_t n; size_t skip; logbuf_lock_irq(); - if (syslog_seq < log_first_seq) { - /* messages are gone, move to first one */ - syslog_seq = log_first_seq; - syslog_idx = log_first_idx; - syslog_partial = 0; - } - if (syslog_seq == log_next_seq) { + if (!prb_read_valid(prb, syslog_seq, &r)) { logbuf_unlock_irq(); break; } + if (r.info->seq != syslog_seq) { + /* message is gone, move to next valid one */ + syslog_seq = r.info->seq; + syslog_partial = 0; + } /* * To keep reading/counting partial line consistent, @@ -1417,13 +1485,10 @@ static int syslog_print(char __user *buf, int size) syslog_time = printk_time; skip = syslog_partial; - msg = log_from_idx(syslog_idx); - n = msg_print_text(msg, true, syslog_time, text, - LOG_LINE_MAX + PREFIX_MAX); + n = record_print_text(&r, true, syslog_time); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ - syslog_idx = log_next(syslog_idx); - syslog_seq++; + syslog_seq = r.info->seq + 1; n -= syslog_partial; syslog_partial = 0; } else if (!len){ @@ -1454,11 +1519,12 @@ static int syslog_print(char __user *buf, int size) static int syslog_print_all(char __user *buf, int size, bool clear) { + struct printk_info info; + unsigned int line_count; + struct printk_record r; char *text; int len = 0; - u64 next_seq; u64 seq; - u32 idx; bool time; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); @@ -1471,38 +1537,28 @@ static int syslog_print_all(char __user *buf, int size, bool clear) * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ - seq = clear_seq; - idx = clear_idx; - while (seq < log_next_seq) { - struct printk_log *msg = log_from_idx(idx); - - len += msg_print_text(msg, true, time, NULL, 0); - idx = log_next(idx); - seq++; - } + prb_for_each_info(clear_seq, prb, seq, &info, &line_count) + len += get_record_print_text_size(&info, line_count, true, time); /* move first record forward until length fits into the buffer */ - seq = clear_seq; - idx = clear_idx; - while (len > size && seq < log_next_seq) { - struct printk_log *msg = log_from_idx(idx); - - len -= msg_print_text(msg, true, time, NULL, 0); - idx = log_next(idx); - seq++; + prb_for_each_info(clear_seq, prb, seq, &info, &line_count) { + if (len <= size) + break; + len -= get_record_print_text_size(&info, line_count, true, time); } - /* last message fitting into this dump */ - next_seq = log_next_seq; + prb_rec_init_rd(&r, &info, text, LOG_LINE_MAX + PREFIX_MAX); len = 0; - while (len >= 0 && seq < next_seq) { - struct printk_log *msg = log_from_idx(idx); - int textlen = msg_print_text(msg, true, time, text, - LOG_LINE_MAX + PREFIX_MAX); + prb_for_each_record(seq, prb, seq, &r) { + int textlen; - idx = log_next(idx); - seq++; + textlen = record_print_text(&r, true, time); + + if (len + textlen > size) { + seq--; + break; + } logbuf_unlock_irq(); if (copy_to_user(buf + len, text, textlen)) @@ -1511,17 +1567,12 @@ static int syslog_print_all(char __user *buf, int size, bool clear) len += textlen; logbuf_lock_irq(); - if (seq < log_first_seq) { - /* messages are gone, move to next one */ - seq = log_first_seq; - idx = log_first_idx; - } + if (len < 0) + break; } - if (clear) { - clear_seq = log_next_seq; - clear_idx = log_next_idx; - } + if (clear) + clear_seq = seq; logbuf_unlock_irq(); kfree(text); @@ -1531,8 +1582,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) static void syslog_clear(void) { logbuf_lock_irq(); - clear_seq = log_next_seq; - clear_idx = log_next_idx; + clear_seq = prb_next_seq(prb); logbuf_unlock_irq(); } @@ -1559,7 +1609,7 @@ int do_syslog(int type, char __user *buf, int len, int source) if (!access_ok(buf, len)) return -EFAULT; error = wait_event_interruptible(log_wait, - syslog_seq != log_next_seq); + prb_read_valid(prb, syslog_seq, NULL)); if (error) return error; error = syslog_print(buf, len); @@ -1567,7 +1617,7 @@ int do_syslog(int type, char __user *buf, int len, int source) /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; - /* FALL THRU */ + fallthrough; /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) @@ -1608,10 +1658,9 @@ int do_syslog(int type, char __user *buf, int len, int source) /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: logbuf_lock_irq(); - if (syslog_seq < log_first_seq) { + if (syslog_seq < prb_first_valid_seq(prb)) { /* messages are gone, move to first one */ - syslog_seq = log_first_seq; - syslog_idx = log_first_idx; + syslog_seq = prb_first_valid_seq(prb); syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { @@ -1620,20 +1669,18 @@ int do_syslog(int type, char __user *buf, int len, int source) * for pending data, not the size; return the count of * records, not the length. */ - error = log_next_seq - syslog_seq; + error = prb_next_seq(prb) - syslog_seq; } else { - u64 seq = syslog_seq; - u32 idx = syslog_idx; bool time = syslog_partial ? syslog_time : printk_time; - - while (seq < log_next_seq) { - struct printk_log *msg = log_from_idx(idx); - - error += msg_print_text(msg, true, time, NULL, - 0); + struct printk_info info; + unsigned int line_count; + u64 seq; + + prb_for_each_info(syslog_seq, prb, seq, &info, + &line_count) { + error += get_record_print_text_size(&info, line_count, + true, time); time = printk_time; - idx = log_next(idx); - seq++; } error -= syslog_partial; } @@ -1804,10 +1851,22 @@ static int console_trylock_spinning(void) static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) { + static char dropped_text[64]; + size_t dropped_len = 0; struct console *con; trace_console_rcuidle(text, len); + if (!console_drivers) + return; + + if (console_dropped) { + dropped_len = snprintf(dropped_text, sizeof(dropped_text), + "** %lu printk messages dropped **\n", + console_dropped); + console_dropped = 0; + } + for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -1820,8 +1879,11 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, continue; if (con->flags & CON_EXTENDED) con->write(con, ext_text, ext_len); - else + else { + if (dropped_len) + con->write(con, dropped_text, dropped_len); con->write(con, text, len); + } } } @@ -1845,97 +1907,38 @@ static inline u32 printk_caller_id(void) 0x80000000 + raw_smp_processor_id(); } -/* - * Continuation lines are buffered, and not committed to the record buffer - * until the line is complete, or a race forces it. The line fragments - * though, are printed immediately to the consoles to ensure everything has - * reached the console in case of a kernel crash. - */ -static struct cont { - char buf[LOG_LINE_MAX]; - size_t len; /* length == 0 means unused buffer */ - u32 caller_id; /* printk_caller_id() of first print */ - u64 ts_nsec; /* time of first print */ - u8 level; /* log level of first message */ - u8 facility; /* log facility of first message */ - enum log_flags flags; /* prefix, newline flags */ -} cont; - -static void cont_flush(void) -{ - if (cont.len == 0) - return; - - log_store(cont.caller_id, cont.facility, cont.level, cont.flags, - cont.ts_nsec, NULL, 0, cont.buf, cont.len); - cont.len = 0; -} - -static bool cont_add(u32 caller_id, int facility, int level, - enum log_flags flags, const char *text, size_t len) -{ - /* If the line gets too long, split it up in separate records. */ - if (cont.len + len > sizeof(cont.buf)) { - cont_flush(); - return false; - } - - if (!cont.len) { - cont.facility = facility; - cont.level = level; - cont.caller_id = caller_id; - cont.ts_nsec = local_clock(); - cont.flags = flags; - } - - memcpy(cont.buf + cont.len, text, len); - cont.len += len; - - // The original flags come from the first line, - // but later continuations can add a newline. - if (flags & LOG_NEWLINE) { - cont.flags |= LOG_NEWLINE; - cont_flush(); - } - - return true; -} - -static size_t log_output(int facility, int level, enum log_flags lflags, const char *dict, size_t dictlen, char *text, size_t text_len) +static size_t log_output(int facility, int level, enum log_flags lflags, + const struct dev_printk_info *dev_info, + char *text, size_t text_len) { const u32 caller_id = printk_caller_id(); - /* - * If an earlier line was buffered, and we're a continuation - * write from the same context, try to add it to the buffer. - */ - if (cont.len) { - if (cont.caller_id == caller_id && (lflags & LOG_CONT)) { - if (cont_add(caller_id, facility, level, lflags, text, text_len)) - return text_len; - } - /* Otherwise, make sure it's flushed */ - cont_flush(); - } - - /* Skip empty continuation lines that couldn't be added - they just flush */ - if (!text_len && (lflags & LOG_CONT)) - return 0; - - /* If it doesn't end in a newline, try to buffer the current line */ - if (!(lflags & LOG_NEWLINE)) { - if (cont_add(caller_id, facility, level, lflags, text, text_len)) + if (lflags & LOG_CONT) { + struct prb_reserved_entry e; + struct printk_record r; + + prb_rec_init_wr(&r, text_len); + if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) { + memcpy(&r.text_buf[r.info->text_len], text, text_len); + r.info->text_len += text_len; + if (lflags & LOG_NEWLINE) { + r.info->flags |= LOG_NEWLINE; + prb_final_commit(&e); + } else { + prb_commit(&e); + } return text_len; + } } /* Store it in the record log */ return log_store(caller_id, facility, level, lflags, 0, - dict, dictlen, text, text_len); + dev_info, text, text_len); } /* Must be called under logbuf_lock. */ int vprintk_store(int facility, int level, - const char *dict, size_t dictlen, + const struct dev_printk_info *dev_info, const char *fmt, va_list args) { static char textbuf[LOG_LINE_MAX]; @@ -1977,21 +1980,19 @@ int vprintk_store(int facility, int level, if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; - if (dict) + if (dev_info) lflags |= LOG_NEWLINE; - return log_output(facility, level, lflags, - dict, dictlen, text, text_len); + return log_output(facility, level, lflags, dev_info, text, text_len); } asmlinkage int vprintk_emit(int facility, int level, - const char *dict, size_t dictlen, + const struct dev_printk_info *dev_info, const char *fmt, va_list args) { int printed_len; - bool in_sched = false, pending_output; + bool in_sched = false; unsigned long flags; - u64 curr_log_seq; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) @@ -2007,13 +2008,11 @@ asmlinkage int vprintk_emit(int facility, int level, /* This stops the holder of console_sem just where we want him */ logbuf_lock_irqsave(flags); - curr_log_seq = log_next_seq; - printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args); - pending_output = (curr_log_seq != log_next_seq); + printed_len = vprintk_store(facility, level, dev_info, fmt, args); logbuf_unlock_irqrestore(flags); /* If called from the scheduler, we can not call up(). */ - if (!in_sched && pending_output) { + if (!in_sched) { /* * Disable preemption to avoid being preempted while holding * console_sem which would prevent anyone from printing to @@ -2030,8 +2029,7 @@ asmlinkage int vprintk_emit(int facility, int level, preempt_enable(); } - if (pending_output) - wake_up_klogd(); + wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); @@ -2044,7 +2042,7 @@ EXPORT_SYMBOL(vprintk); int vprintk_default(const char *fmt, va_list args) { - return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args); + return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } EXPORT_SYMBOL_GPL(vprintk_default); @@ -2088,30 +2086,31 @@ EXPORT_SYMBOL(printk); #define PREFIX_MAX 0 #define printk_time false +#define prb_read_valid(rb, seq, r) false +#define prb_first_valid_seq(rb) 0 + static u64 syslog_seq; -static u32 syslog_idx; static u64 console_seq; -static u32 console_idx; static u64 exclusive_console_stop_seq; -static u64 log_first_seq; -static u32 log_first_idx; -static u64 log_next_seq; -static char *log_text(const struct printk_log *msg) { return NULL; } -static char *log_dict(const struct printk_log *msg) { return NULL; } -static struct printk_log *log_from_idx(u32 idx) { return NULL; } -static u32 log_next(u32 idx) { return 0; } -static ssize_t msg_print_ext_header(char *buf, size_t size, - struct printk_log *msg, - u64 seq) { return 0; } +static unsigned long console_dropped; + +static size_t record_print_text(const struct printk_record *r, + bool syslog, bool time) +{ + return 0; +} +static ssize_t info_print_ext_header(char *buf, size_t size, + struct printk_info *info) +{ + return 0; +} static ssize_t msg_print_ext_body(char *buf, size_t size, - char *dict, size_t dict_len, - char *text, size_t text_len) { return 0; } + char *text, size_t text_len, + struct dev_printk_info *dev_info) { return 0; } static void console_lock_spinning_enable(void) { } static int console_lock_spinning_disable_and_check(void) { return 0; } static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) {} -static size_t msg_print_text(const struct printk_log *msg, bool syslog, - bool time, char *buf, size_t size) { return 0; } static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ @@ -2398,12 +2397,16 @@ void console_unlock(void) static char text[LOG_LINE_MAX + PREFIX_MAX]; unsigned long flags; bool do_cond_resched, retry; + struct printk_info info; + struct printk_record r; if (console_suspended) { up_console_sem(); return; } + prb_rec_init_rd(&r, &info, text, sizeof(text)); + /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may @@ -2416,7 +2419,7 @@ void console_unlock(void) * * console_trylock() is not able to detect the preemptive * context reliably. Therefore the value must be stored before - * and cleared after the the "again" goto label. + * and cleared after the "again" goto label. */ do_cond_resched = console_may_schedule; again: @@ -2434,35 +2437,26 @@ again: } for (;;) { - struct printk_log *msg; size_t ext_len = 0; size_t len; printk_safe_enter_irqsave(flags); raw_spin_lock(&logbuf_lock); - if (console_seq < log_first_seq) { - len = snprintf(text, sizeof(text), - "** %llu printk messages dropped **\n", - log_first_seq - console_seq); - - /* messages are gone, move to first one */ - console_seq = log_first_seq; - console_idx = log_first_idx; - } else { - len = 0; - } skip: - if (console_seq == log_next_seq) + if (!prb_read_valid(prb, console_seq, &r)) break; - msg = log_from_idx(console_idx); - if (suppress_message_printing(msg->level)) { + if (console_seq != r.info->seq) { + console_dropped += r.info->seq - console_seq; + console_seq = r.info->seq; + } + + if (suppress_message_printing(r.info->level)) { /* * Skip record we have buffered and already printed * directly to the console when we received it, and * record that has level above the console loglevel. */ - console_idx = log_next(console_idx); console_seq++; goto skip; } @@ -2473,19 +2467,23 @@ skip: exclusive_console = NULL; } - len += msg_print_text(msg, - console_msg_format & MSG_FORMAT_SYSLOG, - printk_time, text + len, sizeof(text) - len); + /* + * Handle extended console text first because later + * record_print_text() will modify the record buffer in-place. + */ if (nr_ext_console_drivers) { - ext_len = msg_print_ext_header(ext_text, + ext_len = info_print_ext_header(ext_text, sizeof(ext_text), - msg, console_seq); + r.info); ext_len += msg_print_ext_body(ext_text + ext_len, sizeof(ext_text) - ext_len, - log_dict(msg), msg->dict_len, - log_text(msg), msg->text_len); + &r.text_buf[0], + r.info->text_len, + &r.info->dev_info); } - console_idx = log_next(console_idx); + len = record_print_text(&r, + console_msg_format & MSG_FORMAT_SYSLOG, + printk_time); console_seq++; raw_spin_unlock(&logbuf_lock); @@ -2525,7 +2523,7 @@ skip: * flush, no worries. */ raw_spin_lock(&logbuf_lock); - retry = console_seq != log_next_seq; + retry = prb_read_valid(prb, console_seq, NULL); raw_spin_unlock(&logbuf_lock); printk_safe_exit_irqrestore(flags); @@ -2594,8 +2592,7 @@ void console_flush_on_panic(enum con_flush_mode mode) unsigned long flags; logbuf_lock_irqsave(flags); - console_seq = log_first_seq; - console_idx = log_first_idx; + console_seq = prb_first_valid_seq(prb); logbuf_unlock_irqrestore(flags); } console_unlock(); @@ -2838,7 +2835,6 @@ void register_console(struct console *newcon) exclusive_console = newcon; exclusive_console_stop_seq = console_seq; console_seq = syslog_seq; - console_idx = syslog_idx; logbuf_unlock_irqrestore(flags); } console_unlock(); @@ -3062,7 +3058,7 @@ int vprintk_deferred(const char *fmt, va_list args) { int r; - r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args); + r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); defer_console_output(); return r; @@ -3227,9 +3223,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) logbuf_lock_irqsave(flags); dumper->cur_seq = clear_seq; - dumper->cur_idx = clear_idx; - dumper->next_seq = log_next_seq; - dumper->next_idx = log_next_idx; + dumper->next_seq = prb_next_seq(prb); logbuf_unlock_irqrestore(flags); /* invoke dumper which will iterate over records */ @@ -3263,28 +3257,33 @@ void kmsg_dump(enum kmsg_dump_reason reason) bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len) { - struct printk_log *msg; + struct printk_info info; + unsigned int line_count; + struct printk_record r; size_t l = 0; bool ret = false; + prb_rec_init_rd(&r, &info, line, size); + if (!dumper->active) goto out; - if (dumper->cur_seq < log_first_seq) { - /* messages are gone, move to first available one */ - dumper->cur_seq = log_first_seq; - dumper->cur_idx = log_first_idx; - } - - /* last entry */ - if (dumper->cur_seq >= log_next_seq) - goto out; + /* Read text or count text lines? */ + if (line) { + if (!prb_read_valid(prb, dumper->cur_seq, &r)) + goto out; + l = record_print_text(&r, syslog, printk_time); + } else { + if (!prb_read_valid_info(prb, dumper->cur_seq, + &info, &line_count)) { + goto out; + } + l = get_record_print_text_size(&info, line_count, syslog, + printk_time); - msg = log_from_idx(dumper->cur_idx); - l = msg_print_text(msg, syslog, printk_time, line, size); + } - dumper->cur_idx = log_next(dumper->cur_idx); - dumper->cur_seq++; + dumper->cur_seq = r.info->seq + 1; ret = true; out: if (len) @@ -3332,7 +3331,7 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_line); * @len: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer - * with as many of the the *youngest* kmsg records that fit into it. + * with as many of the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * @@ -3345,23 +3344,25 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_line); bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, char *buf, size_t size, size_t *len) { + struct printk_info info; + unsigned int line_count; + struct printk_record r; unsigned long flags; u64 seq; - u32 idx; u64 next_seq; - u32 next_idx; size_t l = 0; bool ret = false; bool time = printk_time; - if (!dumper->active) + prb_rec_init_rd(&r, &info, buf, size); + + if (!dumper->active || !buf || !size) goto out; logbuf_lock_irqsave(flags); - if (dumper->cur_seq < log_first_seq) { + if (dumper->cur_seq < prb_first_valid_seq(prb)) { /* messages are gone, move to first available one */ - dumper->cur_seq = log_first_seq; - dumper->cur_idx = log_first_idx; + dumper->cur_seq = prb_first_valid_seq(prb); } /* last entry */ @@ -3372,41 +3373,41 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, /* calculate length of entire buffer */ seq = dumper->cur_seq; - idx = dumper->cur_idx; - while (seq < dumper->next_seq) { - struct printk_log *msg = log_from_idx(idx); - - l += msg_print_text(msg, true, time, NULL, 0); - idx = log_next(idx); - seq++; + while (prb_read_valid_info(prb, seq, &info, &line_count)) { + if (r.info->seq >= dumper->next_seq) + break; + l += get_record_print_text_size(&info, line_count, true, time); + seq = r.info->seq + 1; } /* move first record forward until length fits into the buffer */ seq = dumper->cur_seq; - idx = dumper->cur_idx; - while (l >= size && seq < dumper->next_seq) { - struct printk_log *msg = log_from_idx(idx); - - l -= msg_print_text(msg, true, time, NULL, 0); - idx = log_next(idx); - seq++; + while (l >= size && prb_read_valid_info(prb, seq, + &info, &line_count)) { + if (r.info->seq >= dumper->next_seq) + break; + l -= get_record_print_text_size(&info, line_count, true, time); + seq = r.info->seq + 1; } /* last message in next interation */ next_seq = seq; - next_idx = idx; + /* actually read text into the buffer now */ l = 0; - while (seq < dumper->next_seq) { - struct printk_log *msg = log_from_idx(idx); + while (prb_read_valid(prb, seq, &r)) { + if (r.info->seq >= dumper->next_seq) + break; + + l += record_print_text(&r, syslog, time); + + /* adjust record to store to remaining buffer space */ + prb_rec_init_rd(&r, &info, buf + l, size - l); - l += msg_print_text(msg, syslog, time, buf + l, size - l); - idx = log_next(idx); - seq++; + seq = r.info->seq + 1; } dumper->next_seq = next_seq; - dumper->next_idx = next_idx; ret = true; logbuf_unlock_irqrestore(flags); out: @@ -3429,9 +3430,7 @@ EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) { dumper->cur_seq = clear_seq; - dumper->cur_idx = clear_idx; - dumper->next_seq = log_next_seq; - dumper->next_idx = log_next_idx; + dumper->next_seq = prb_next_seq(prb); } /** diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c new file mode 100644 index 000000000000..2493348a1631 --- /dev/null +++ b/kernel/printk/printk_ringbuffer.c @@ -0,0 +1,2083 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/irqflags.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/bug.h> +#include "printk_ringbuffer.h" + +/** + * DOC: printk_ringbuffer overview + * + * Data Structure + * -------------- + * The printk_ringbuffer is made up of 3 internal ringbuffers: + * + * desc_ring + * A ring of descriptors and their meta data (such as sequence number, + * timestamp, loglevel, etc.) as well as internal state information about + * the record and logical positions specifying where in the other + * ringbuffer the text strings are located. + * + * text_data_ring + * A ring of data blocks. A data block consists of an unsigned long + * integer (ID) that maps to a desc_ring index followed by the text + * string of the record. + * + * The internal state information of a descriptor is the key element to allow + * readers and writers to locklessly synchronize access to the data. + * + * Implementation + * -------------- + * + * Descriptor Ring + * ~~~~~~~~~~~~~~~ + * The descriptor ring is an array of descriptors. A descriptor contains + * essential meta data to track the data of a printk record using + * blk_lpos structs pointing to associated text data blocks (see + * "Data Rings" below). Each descriptor is assigned an ID that maps + * directly to index values of the descriptor array and has a state. The ID + * and the state are bitwise combined into a single descriptor field named + * @state_var, allowing ID and state to be synchronously and atomically + * updated. + * + * Descriptors have four states: + * + * reserved + * A writer is modifying the record. + * + * committed + * The record and all its data are written. A writer can reopen the + * descriptor (transitioning it back to reserved), but in the committed + * state the data is consistent. + * + * finalized + * The record and all its data are complete and available for reading. A + * writer cannot reopen the descriptor. + * + * reusable + * The record exists, but its text and/or meta data may no longer be + * available. + * + * Querying the @state_var of a record requires providing the ID of the + * descriptor to query. This can yield a possible fifth (pseudo) state: + * + * miss + * The descriptor being queried has an unexpected ID. + * + * The descriptor ring has a @tail_id that contains the ID of the oldest + * descriptor and @head_id that contains the ID of the newest descriptor. + * + * When a new descriptor should be created (and the ring is full), the tail + * descriptor is invalidated by first transitioning to the reusable state and + * then invalidating all tail data blocks up to and including the data blocks + * associated with the tail descriptor (for the text ring). Then + * @tail_id is advanced, followed by advancing @head_id. And finally the + * @state_var of the new descriptor is initialized to the new ID and reserved + * state. + * + * The @tail_id can only be advanced if the new @tail_id would be in the + * committed or reusable queried state. This makes it possible that a valid + * sequence number of the tail is always available. + * + * Descriptor Finalization + * ~~~~~~~~~~~~~~~~~~~~~~~ + * When a writer calls the commit function prb_commit(), record data is + * fully stored and is consistent within the ringbuffer. However, a writer can + * reopen that record, claiming exclusive access (as with prb_reserve()), and + * modify that record. When finished, the writer must again commit the record. + * + * In order for a record to be made available to readers (and also become + * recyclable for writers), it must be finalized. A finalized record cannot be + * reopened and can never become "unfinalized". Record finalization can occur + * in three different scenarios: + * + * 1) A writer can simultaneously commit and finalize its record by calling + * prb_final_commit() instead of prb_commit(). + * + * 2) When a new record is reserved and the previous record has been + * committed via prb_commit(), that previous record is automatically + * finalized. + * + * 3) When a record is committed via prb_commit() and a newer record + * already exists, the record being committed is automatically finalized. + * + * Data Ring + * ~~~~~~~~~ + * The text data ring is a byte array composed of data blocks. Data blocks are + * referenced by blk_lpos structs that point to the logical position of the + * beginning of a data block and the beginning of the next adjacent data + * block. Logical positions are mapped directly to index values of the byte + * array ringbuffer. + * + * Each data block consists of an ID followed by the writer data. The ID is + * the identifier of a descriptor that is associated with the data block. A + * given data block is considered valid if all of the following conditions + * are met: + * + * 1) The descriptor associated with the data block is in the committed + * or finalized queried state. + * + * 2) The blk_lpos struct within the descriptor associated with the data + * block references back to the same data block. + * + * 3) The data block is within the head/tail logical position range. + * + * If the writer data of a data block would extend beyond the end of the + * byte array, only the ID of the data block is stored at the logical + * position and the full data block (ID and writer data) is stored at the + * beginning of the byte array. The referencing blk_lpos will point to the + * ID before the wrap and the next data block will be at the logical + * position adjacent the full data block after the wrap. + * + * Data rings have a @tail_lpos that points to the beginning of the oldest + * data block and a @head_lpos that points to the logical position of the + * next (not yet existing) data block. + * + * When a new data block should be created (and the ring is full), tail data + * blocks will first be invalidated by putting their associated descriptors + * into the reusable state and then pushing the @tail_lpos forward beyond + * them. Then the @head_lpos is pushed forward and is associated with a new + * descriptor. If a data block is not valid, the @tail_lpos cannot be + * advanced beyond it. + * + * Info Array + * ~~~~~~~~~~ + * The general meta data of printk records are stored in printk_info structs, + * stored in an array with the same number of elements as the descriptor ring. + * Each info corresponds to the descriptor of the same index in the + * descriptor ring. Info validity is confirmed by evaluating the corresponding + * descriptor before and after loading the info. + * + * Usage + * ----- + * Here are some simple examples demonstrating writers and readers. For the + * examples a global ringbuffer (test_rb) is available (which is not the + * actual ringbuffer used by printk):: + * + * DEFINE_PRINTKRB(test_rb, 15, 5); + * + * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of + * 1 MiB (2 ^ (15 + 5)) for text data. + * + * Sample writer code:: + * + * const char *textstr = "message text"; + * struct prb_reserved_entry e; + * struct printk_record r; + * + * // specify how much to allocate + * prb_rec_init_wr(&r, strlen(textstr) + 1); + * + * if (prb_reserve(&e, &test_rb, &r)) { + * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); + * + * r.info->text_len = strlen(textstr); + * r.info->ts_nsec = local_clock(); + * r.info->caller_id = printk_caller_id(); + * + * // commit and finalize the record + * prb_final_commit(&e); + * } + * + * Note that additional writer functions are available to extend a record + * after it has been committed but not yet finalized. This can be done as + * long as no new records have been reserved and the caller is the same. + * + * Sample writer code (record extending):: + * + * // alternate rest of previous example + * + * r.info->text_len = strlen(textstr); + * r.info->ts_nsec = local_clock(); + * r.info->caller_id = printk_caller_id(); + * + * // commit the record (but do not finalize yet) + * prb_commit(&e); + * } + * + * ... + * + * // specify additional 5 bytes text space to extend + * prb_rec_init_wr(&r, 5); + * + * // try to extend, but only if it does not exceed 32 bytes + * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id()), 32) { + * snprintf(&r.text_buf[r.info->text_len], + * r.text_buf_size - r.info->text_len, "hello"); + * + * r.info->text_len += 5; + * + * // commit and finalize the record + * prb_final_commit(&e); + * } + * + * Sample reader code:: + * + * struct printk_info info; + * struct printk_record r; + * char text_buf[32]; + * u64 seq; + * + * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); + * + * prb_for_each_record(0, &test_rb, &seq, &r) { + * if (info.seq != seq) + * pr_warn("lost %llu records\n", info.seq - seq); + * + * if (info.text_len > r.text_buf_size) { + * pr_warn("record %llu text truncated\n", info.seq); + * text_buf[r.text_buf_size - 1] = 0; + * } + * + * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, + * &text_buf[0]); + * } + * + * Note that additional less convenient reader functions are available to + * allow complex record access. + * + * ABA Issues + * ~~~~~~~~~~ + * To help avoid ABA issues, descriptors are referenced by IDs (array index + * values combined with tagged bits counting array wraps) and data blocks are + * referenced by logical positions (array index values combined with tagged + * bits counting array wraps). However, on 32-bit systems the number of + * tagged bits is relatively small such that an ABA incident is (at least + * theoretically) possible. For example, if 4 million maximally sized (1KiB) + * printk messages were to occur in NMI context on a 32-bit system, the + * interrupted context would not be able to recognize that the 32-bit integer + * completely wrapped and thus represents a different data block than the one + * the interrupted context expects. + * + * To help combat this possibility, additional state checking is performed + * (such as using cmpxchg() even though set() would suffice). These extra + * checks are commented as such and will hopefully catch any ABA issue that + * a 32-bit system might experience. + * + * Memory Barriers + * ~~~~~~~~~~~~~~~ + * Multiple memory barriers are used. To simplify proving correctness and + * generating litmus tests, lines of code related to memory barriers + * (loads, stores, and the associated memory barriers) are labeled:: + * + * LMM(function:letter) + * + * Comments reference the labels using only the "function:letter" part. + * + * The memory barrier pairs and their ordering are: + * + * desc_reserve:D / desc_reserve:B + * push descriptor tail (id), then push descriptor head (id) + * + * desc_reserve:D / data_push_tail:B + * push data tail (lpos), then set new descriptor reserved (state) + * + * desc_reserve:D / desc_push_tail:C + * push descriptor tail (id), then set new descriptor reserved (state) + * + * desc_reserve:D / prb_first_seq:C + * push descriptor tail (id), then set new descriptor reserved (state) + * + * desc_reserve:F / desc_read:D + * set new descriptor id and reserved (state), then allow writer changes + * + * data_alloc:A (or data_realloc:A) / desc_read:D + * set old descriptor reusable (state), then modify new data block area + * + * data_alloc:A (or data_realloc:A) / data_push_tail:B + * push data tail (lpos), then modify new data block area + * + * _prb_commit:B / desc_read:B + * store writer changes, then set new descriptor committed (state) + * + * desc_reopen_last:A / _prb_commit:B + * set descriptor reserved (state), then read descriptor data + * + * _prb_commit:B / desc_reserve:D + * set new descriptor committed (state), then check descriptor head (id) + * + * data_push_tail:D / data_push_tail:A + * set descriptor reusable (state), then push data tail (lpos) + * + * desc_push_tail:B / desc_reserve:D + * set descriptor reusable (state), then push descriptor tail (id) + */ + +#define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) +#define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) + +#define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) +#define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) + +/* Determine the data array index from a logical position. */ +#define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) + +/* Determine the desc array index from an ID or sequence number. */ +#define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) + +/* Determine how many times the data array has wrapped. */ +#define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) + +/* Determine if a logical position refers to a data-less block. */ +#define LPOS_DATALESS(lpos) ((lpos) & 1UL) +#define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ + LPOS_DATALESS((blk)->next)) + +/* Get the logical position at index 0 of the current wrap. */ +#define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ +((lpos) & ~DATA_SIZE_MASK(data_ring)) + +/* Get the ID for the same index of the previous wrap as the given ID. */ +#define DESC_ID_PREV_WRAP(desc_ring, id) \ +DESC_ID((id) - DESCS_COUNT(desc_ring)) + +/* + * A data block: mapped directly to the beginning of the data block area + * specified as a logical position within the data ring. + * + * @id: the ID of the associated descriptor + * @data: the writer data + * + * Note that the size of a data block is only known by its associated + * descriptor. + */ +struct prb_data_block { + unsigned long id; + char data[0]; +}; + +/* + * Return the descriptor associated with @n. @n can be either a + * descriptor ID or a sequence number. + */ +static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) +{ + return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; +} + +/* + * Return the printk_info associated with @n. @n can be either a + * descriptor ID or a sequence number. + */ +static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) +{ + return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; +} + +static struct prb_data_block *to_block(struct prb_data_ring *data_ring, + unsigned long begin_lpos) +{ + return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; +} + +/* + * Increase the data size to account for data block meta data plus any + * padding so that the adjacent data block is aligned on the ID size. + */ +static unsigned int to_blk_size(unsigned int size) +{ + struct prb_data_block *db = NULL; + + size += sizeof(*db); + size = ALIGN(size, sizeof(db->id)); + return size; +} + +/* + * Sanity checker for reserve size. The ringbuffer code assumes that a data + * block does not exceed the maximum possible size that could fit within the + * ringbuffer. This function provides that basic size check so that the + * assumption is safe. + */ +static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) +{ + struct prb_data_block *db = NULL; + + if (size == 0) + return true; + + /* + * Ensure the alignment padded size could possibly fit in the data + * array. The largest possible data block must still leave room for + * at least the ID of the next block. + */ + size = to_blk_size(size); + if (size > DATA_SIZE(data_ring) - sizeof(db->id)) + return false; + + return true; +} + +/* Query the state of a descriptor. */ +static enum desc_state get_desc_state(unsigned long id, + unsigned long state_val) +{ + if (id != DESC_ID(state_val)) + return desc_miss; + + return DESC_STATE(state_val); +} + +/* + * Get a copy of a specified descriptor and return its queried state. If the + * descriptor is in an inconsistent state (miss or reserved), the caller can + * only expect the descriptor's @state_var field to be valid. + * + * The sequence number and caller_id can be optionally retrieved. Like all + * non-state_var data, they are only valid if the descriptor is in a + * consistent state. + */ +static enum desc_state desc_read(struct prb_desc_ring *desc_ring, + unsigned long id, struct prb_desc *desc_out, + u64 *seq_out, u32 *caller_id_out) +{ + struct printk_info *info = to_info(desc_ring, id); + struct prb_desc *desc = to_desc(desc_ring, id); + atomic_long_t *state_var = &desc->state_var; + enum desc_state d_state; + unsigned long state_val; + + /* Check the descriptor state. */ + state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ + d_state = get_desc_state(id, state_val); + if (d_state == desc_miss || d_state == desc_reserved) { + /* + * The descriptor is in an inconsistent state. Set at least + * @state_var so that the caller can see the details of + * the inconsistent state. + */ + goto out; + } + + /* + * Guarantee the state is loaded before copying the descriptor + * content. This avoids copying obsolete descriptor content that might + * not apply to the descriptor state. This pairs with _prb_commit:B. + * + * Memory barrier involvement: + * + * If desc_read:A reads from _prb_commit:B, then desc_read:C reads + * from _prb_commit:A. + * + * Relies on: + * + * WMB from _prb_commit:A to _prb_commit:B + * matching + * RMB from desc_read:A to desc_read:C + */ + smp_rmb(); /* LMM(desc_read:B) */ + + /* + * Copy the descriptor data. The data is not valid until the + * state has been re-checked. A memcpy() for all of @desc + * cannot be used because of the atomic_t @state_var field. + */ + memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, + sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ + if (seq_out) + *seq_out = info->seq; /* also part of desc_read:C */ + if (caller_id_out) + *caller_id_out = info->caller_id; /* also part of desc_read:C */ + + /* + * 1. Guarantee the descriptor content is loaded before re-checking + * the state. This avoids reading an obsolete descriptor state + * that may not apply to the copied content. This pairs with + * desc_reserve:F. + * + * Memory barrier involvement: + * + * If desc_read:C reads from desc_reserve:G, then desc_read:E + * reads from desc_reserve:F. + * + * Relies on: + * + * WMB from desc_reserve:F to desc_reserve:G + * matching + * RMB from desc_read:C to desc_read:E + * + * 2. Guarantee the record data is loaded before re-checking the + * state. This avoids reading an obsolete descriptor state that may + * not apply to the copied data. This pairs with data_alloc:A and + * data_realloc:A. + * + * Memory barrier involvement: + * + * If copy_data:A reads from data_alloc:B, then desc_read:E + * reads from desc_make_reusable:A. + * + * Relies on: + * + * MB from desc_make_reusable:A to data_alloc:B + * matching + * RMB from desc_read:C to desc_read:E + * + * Note: desc_make_reusable:A and data_alloc:B can be different + * CPUs. However, the data_alloc:B CPU (which performs the + * full memory barrier) must have previously seen + * desc_make_reusable:A. + */ + smp_rmb(); /* LMM(desc_read:D) */ + + /* + * The data has been copied. Return the current descriptor state, + * which may have changed since the load above. + */ + state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ + d_state = get_desc_state(id, state_val); +out: + atomic_long_set(&desc_out->state_var, state_val); + return d_state; +} + +/* + * Take a specified descriptor out of the finalized state by attempting + * the transition from finalized to reusable. Either this context or some + * other context will have been successful. + */ +static void desc_make_reusable(struct prb_desc_ring *desc_ring, + unsigned long id) +{ + unsigned long val_finalized = DESC_SV(id, desc_finalized); + unsigned long val_reusable = DESC_SV(id, desc_reusable); + struct prb_desc *desc = to_desc(desc_ring, id); + atomic_long_t *state_var = &desc->state_var; + + atomic_long_cmpxchg_relaxed(state_var, val_finalized, + val_reusable); /* LMM(desc_make_reusable:A) */ +} + +/* + * Given the text data ring, put the associated descriptor of each + * data block from @lpos_begin until @lpos_end into the reusable state. + * + * If there is any problem making the associated descriptor reusable, either + * the descriptor has not yet been finalized or another writer context has + * already pushed the tail lpos past the problematic data block. Regardless, + * on error the caller can re-load the tail lpos to determine the situation. + */ +static bool data_make_reusable(struct printk_ringbuffer *rb, + struct prb_data_ring *data_ring, + unsigned long lpos_begin, + unsigned long lpos_end, + unsigned long *lpos_out) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct prb_data_block *blk; + enum desc_state d_state; + struct prb_desc desc; + struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; + unsigned long id; + + /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ + while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { + blk = to_block(data_ring, lpos_begin); + + /* + * Load the block ID from the data block. This is a data race + * against a writer that may have newly reserved this data + * area. If the loaded value matches a valid descriptor ID, + * the blk_lpos of that descriptor will be checked to make + * sure it points back to this data block. If the check fails, + * the data area has been recycled by another writer. + */ + id = blk->id; /* LMM(data_make_reusable:A) */ + + d_state = desc_read(desc_ring, id, &desc, + NULL, NULL); /* LMM(data_make_reusable:B) */ + + switch (d_state) { + case desc_miss: + case desc_reserved: + case desc_committed: + return false; + case desc_finalized: + /* + * This data block is invalid if the descriptor + * does not point back to it. + */ + if (blk_lpos->begin != lpos_begin) + return false; + desc_make_reusable(desc_ring, id); + break; + case desc_reusable: + /* + * This data block is invalid if the descriptor + * does not point back to it. + */ + if (blk_lpos->begin != lpos_begin) + return false; + break; + } + + /* Advance @lpos_begin to the next data block. */ + lpos_begin = blk_lpos->next; + } + + *lpos_out = lpos_begin; + return true; +} + +/* + * Advance the data ring tail to at least @lpos. This function puts + * descriptors into the reusable state if the tail is pushed beyond + * their associated data block. + */ +static bool data_push_tail(struct printk_ringbuffer *rb, + struct prb_data_ring *data_ring, + unsigned long lpos) +{ + unsigned long tail_lpos_new; + unsigned long tail_lpos; + unsigned long next_lpos; + + /* If @lpos is from a data-less block, there is nothing to do. */ + if (LPOS_DATALESS(lpos)) + return true; + + /* + * Any descriptor states that have transitioned to reusable due to the + * data tail being pushed to this loaded value will be visible to this + * CPU. This pairs with data_push_tail:D. + * + * Memory barrier involvement: + * + * If data_push_tail:A reads from data_push_tail:D, then this CPU can + * see desc_make_reusable:A. + * + * Relies on: + * + * MB from desc_make_reusable:A to data_push_tail:D + * matches + * READFROM from data_push_tail:D to data_push_tail:A + * thus + * READFROM from desc_make_reusable:A to this CPU + */ + tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ + + /* + * Loop until the tail lpos is at or beyond @lpos. This condition + * may already be satisfied, resulting in no full memory barrier + * from data_push_tail:D being performed. However, since this CPU + * sees the new tail lpos, any descriptor states that transitioned to + * the reusable state must already be visible. + */ + while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { + /* + * Make all descriptors reusable that are associated with + * data blocks before @lpos. + */ + if (!data_make_reusable(rb, data_ring, tail_lpos, lpos, + &next_lpos)) { + /* + * 1. Guarantee the block ID loaded in + * data_make_reusable() is performed before + * reloading the tail lpos. The failed + * data_make_reusable() may be due to a newly + * recycled data area causing the tail lpos to + * have been previously pushed. This pairs with + * data_alloc:A and data_realloc:A. + * + * Memory barrier involvement: + * + * If data_make_reusable:A reads from data_alloc:B, + * then data_push_tail:C reads from + * data_push_tail:D. + * + * Relies on: + * + * MB from data_push_tail:D to data_alloc:B + * matching + * RMB from data_make_reusable:A to + * data_push_tail:C + * + * Note: data_push_tail:D and data_alloc:B can be + * different CPUs. However, the data_alloc:B + * CPU (which performs the full memory + * barrier) must have previously seen + * data_push_tail:D. + * + * 2. Guarantee the descriptor state loaded in + * data_make_reusable() is performed before + * reloading the tail lpos. The failed + * data_make_reusable() may be due to a newly + * recycled descriptor causing the tail lpos to + * have been previously pushed. This pairs with + * desc_reserve:D. + * + * Memory barrier involvement: + * + * If data_make_reusable:B reads from + * desc_reserve:F, then data_push_tail:C reads + * from data_push_tail:D. + * + * Relies on: + * + * MB from data_push_tail:D to desc_reserve:F + * matching + * RMB from data_make_reusable:B to + * data_push_tail:C + * + * Note: data_push_tail:D and desc_reserve:F can + * be different CPUs. However, the + * desc_reserve:F CPU (which performs the + * full memory barrier) must have previously + * seen data_push_tail:D. + */ + smp_rmb(); /* LMM(data_push_tail:B) */ + + tail_lpos_new = atomic_long_read(&data_ring->tail_lpos + ); /* LMM(data_push_tail:C) */ + if (tail_lpos_new == tail_lpos) + return false; + + /* Another CPU pushed the tail. Try again. */ + tail_lpos = tail_lpos_new; + continue; + } + + /* + * Guarantee any descriptor states that have transitioned to + * reusable are stored before pushing the tail lpos. A full + * memory barrier is needed since other CPUs may have made + * the descriptor states reusable. This pairs with + * data_push_tail:A. + */ + if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, + next_lpos)) { /* LMM(data_push_tail:D) */ + break; + } + } + + return true; +} + +/* + * Advance the desc ring tail. This function advances the tail by one + * descriptor, thus invalidating the oldest descriptor. Before advancing + * the tail, the tail descriptor is made reusable and all data blocks up to + * and including the descriptor's data block are invalidated (i.e. the data + * ring tail is pushed past the data block of the descriptor being made + * reusable). + */ +static bool desc_push_tail(struct printk_ringbuffer *rb, + unsigned long tail_id) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + enum desc_state d_state; + struct prb_desc desc; + + d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); + + switch (d_state) { + case desc_miss: + /* + * If the ID is exactly 1 wrap behind the expected, it is + * in the process of being reserved by another writer and + * must be considered reserved. + */ + if (DESC_ID(atomic_long_read(&desc.state_var)) == + DESC_ID_PREV_WRAP(desc_ring, tail_id)) { + return false; + } + + /* + * The ID has changed. Another writer must have pushed the + * tail and recycled the descriptor already. Success is + * returned because the caller is only interested in the + * specified tail being pushed, which it was. + */ + return true; + case desc_reserved: + case desc_committed: + return false; + case desc_finalized: + desc_make_reusable(desc_ring, tail_id); + break; + case desc_reusable: + break; + } + + /* + * Data blocks must be invalidated before their associated + * descriptor can be made available for recycling. Invalidating + * them later is not possible because there is no way to trust + * data blocks once their associated descriptor is gone. + */ + + if (!data_push_tail(rb, &rb->text_data_ring, desc.text_blk_lpos.next)) + return false; + + /* + * Check the next descriptor after @tail_id before pushing the tail + * to it because the tail must always be in a finalized or reusable + * state. The implementation of prb_first_seq() relies on this. + * + * A successful read implies that the next descriptor is less than or + * equal to @head_id so there is no risk of pushing the tail past the + * head. + */ + d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, + NULL, NULL); /* LMM(desc_push_tail:A) */ + + if (d_state == desc_finalized || d_state == desc_reusable) { + /* + * Guarantee any descriptor states that have transitioned to + * reusable are stored before pushing the tail ID. This allows + * verifying the recycled descriptor state. A full memory + * barrier is needed since other CPUs may have made the + * descriptor states reusable. This pairs with desc_reserve:D. + */ + atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, + DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ + } else { + /* + * Guarantee the last state load from desc_read() is before + * reloading @tail_id in order to see a new tail ID in the + * case that the descriptor has been recycled. This pairs + * with desc_reserve:D. + * + * Memory barrier involvement: + * + * If desc_push_tail:A reads from desc_reserve:F, then + * desc_push_tail:D reads from desc_push_tail:B. + * + * Relies on: + * + * MB from desc_push_tail:B to desc_reserve:F + * matching + * RMB from desc_push_tail:A to desc_push_tail:D + * + * Note: desc_push_tail:B and desc_reserve:F can be different + * CPUs. However, the desc_reserve:F CPU (which performs + * the full memory barrier) must have previously seen + * desc_push_tail:B. + */ + smp_rmb(); /* LMM(desc_push_tail:C) */ + + /* + * Re-check the tail ID. The descriptor following @tail_id is + * not in an allowed tail state. But if the tail has since + * been moved by another CPU, then it does not matter. + */ + if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ + return false; + } + + return true; +} + +/* Reserve a new descriptor, invalidating the oldest if necessary. */ +static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + unsigned long prev_state_val; + unsigned long id_prev_wrap; + struct prb_desc *desc; + unsigned long head_id; + unsigned long id; + + head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ + + do { + desc = to_desc(desc_ring, head_id); + + id = DESC_ID(head_id + 1); + id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); + + /* + * Guarantee the head ID is read before reading the tail ID. + * Since the tail ID is updated before the head ID, this + * guarantees that @id_prev_wrap is never ahead of the tail + * ID. This pairs with desc_reserve:D. + * + * Memory barrier involvement: + * + * If desc_reserve:A reads from desc_reserve:D, then + * desc_reserve:C reads from desc_push_tail:B. + * + * Relies on: + * + * MB from desc_push_tail:B to desc_reserve:D + * matching + * RMB from desc_reserve:A to desc_reserve:C + * + * Note: desc_push_tail:B and desc_reserve:D can be different + * CPUs. However, the desc_reserve:D CPU (which performs + * the full memory barrier) must have previously seen + * desc_push_tail:B. + */ + smp_rmb(); /* LMM(desc_reserve:B) */ + + if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id + )) { /* LMM(desc_reserve:C) */ + /* + * Make space for the new descriptor by + * advancing the tail. + */ + if (!desc_push_tail(rb, id_prev_wrap)) + return false; + } + + /* + * 1. Guarantee the tail ID is read before validating the + * recycled descriptor state. A read memory barrier is + * sufficient for this. This pairs with desc_push_tail:B. + * + * Memory barrier involvement: + * + * If desc_reserve:C reads from desc_push_tail:B, then + * desc_reserve:E reads from desc_make_reusable:A. + * + * Relies on: + * + * MB from desc_make_reusable:A to desc_push_tail:B + * matching + * RMB from desc_reserve:C to desc_reserve:E + * + * Note: desc_make_reusable:A and desc_push_tail:B can be + * different CPUs. However, the desc_push_tail:B CPU + * (which performs the full memory barrier) must have + * previously seen desc_make_reusable:A. + * + * 2. Guarantee the tail ID is stored before storing the head + * ID. This pairs with desc_reserve:B. + * + * 3. Guarantee any data ring tail changes are stored before + * recycling the descriptor. Data ring tail changes can + * happen via desc_push_tail()->data_push_tail(). A full + * memory barrier is needed since another CPU may have + * pushed the data ring tails. This pairs with + * data_push_tail:B. + * + * 4. Guarantee a new tail ID is stored before recycling the + * descriptor. A full memory barrier is needed since + * another CPU may have pushed the tail ID. This pairs + * with desc_push_tail:C and this also pairs with + * prb_first_seq:C. + * + * 5. Guarantee the head ID is stored before trying to + * finalize the previous descriptor. This pairs with + * _prb_commit:B. + */ + } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, + id)); /* LMM(desc_reserve:D) */ + + desc = to_desc(desc_ring, id); + + /* + * If the descriptor has been recycled, verify the old state val. + * See "ABA Issues" about why this verification is performed. + */ + prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ + if (prev_state_val && + get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { + WARN_ON_ONCE(1); + return false; + } + + /* + * Assign the descriptor a new ID and set its state to reserved. + * See "ABA Issues" about why cmpxchg() instead of set() is used. + * + * Guarantee the new descriptor ID and state is stored before making + * any other changes. A write memory barrier is sufficient for this. + * This pairs with desc_read:D. + */ + if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, + DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ + WARN_ON_ONCE(1); + return false; + } + + /* Now data in @desc can be modified: LMM(desc_reserve:G) */ + + *id_out = id; + return true; +} + +/* Determine the end of a data block. */ +static unsigned long get_next_lpos(struct prb_data_ring *data_ring, + unsigned long lpos, unsigned int size) +{ + unsigned long begin_lpos; + unsigned long next_lpos; + + begin_lpos = lpos; + next_lpos = lpos + size; + + /* First check if the data block does not wrap. */ + if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) + return next_lpos; + + /* Wrapping data blocks store their data at the beginning. */ + return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); +} + +/* + * Allocate a new data block, invalidating the oldest data block(s) + * if necessary. This function also associates the data block with + * a specified descriptor. + */ +static char *data_alloc(struct printk_ringbuffer *rb, + struct prb_data_ring *data_ring, unsigned int size, + struct prb_data_blk_lpos *blk_lpos, unsigned long id) +{ + struct prb_data_block *blk; + unsigned long begin_lpos; + unsigned long next_lpos; + + if (size == 0) { + /* Specify a data-less block. */ + blk_lpos->begin = NO_LPOS; + blk_lpos->next = NO_LPOS; + return NULL; + } + + size = to_blk_size(size); + + begin_lpos = atomic_long_read(&data_ring->head_lpos); + + do { + next_lpos = get_next_lpos(data_ring, begin_lpos, size); + + if (!data_push_tail(rb, data_ring, next_lpos - DATA_SIZE(data_ring))) { + /* Failed to allocate, specify a data-less block. */ + blk_lpos->begin = FAILED_LPOS; + blk_lpos->next = FAILED_LPOS; + return NULL; + } + + /* + * 1. Guarantee any descriptor states that have transitioned + * to reusable are stored before modifying the newly + * allocated data area. A full memory barrier is needed + * since other CPUs may have made the descriptor states + * reusable. See data_push_tail:A about why the reusable + * states are visible. This pairs with desc_read:D. + * + * 2. Guarantee any updated tail lpos is stored before + * modifying the newly allocated data area. Another CPU may + * be in data_make_reusable() and is reading a block ID + * from this area. data_make_reusable() can handle reading + * a garbage block ID value, but then it must be able to + * load a new tail lpos. A full memory barrier is needed + * since other CPUs may have updated the tail lpos. This + * pairs with data_push_tail:B. + */ + } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, + next_lpos)); /* LMM(data_alloc:A) */ + + blk = to_block(data_ring, begin_lpos); + blk->id = id; /* LMM(data_alloc:B) */ + + if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { + /* Wrapping data blocks store their data at the beginning. */ + blk = to_block(data_ring, 0); + + /* + * Store the ID on the wrapped block for consistency. + * The printk_ringbuffer does not actually use it. + */ + blk->id = id; + } + + blk_lpos->begin = begin_lpos; + blk_lpos->next = next_lpos; + + return &blk->data[0]; +} + +/* + * Try to resize an existing data block associated with the descriptor + * specified by @id. If the resized data block should become wrapped, it + * copies the old data to the new data block. If @size yields a data block + * with the same or less size, the data block is left as is. + * + * Fail if this is not the last allocated data block or if there is not + * enough space or it is not possible make enough space. + * + * Return a pointer to the beginning of the entire data buffer or NULL on + * failure. + */ +static char *data_realloc(struct printk_ringbuffer *rb, + struct prb_data_ring *data_ring, unsigned int size, + struct prb_data_blk_lpos *blk_lpos, unsigned long id) +{ + struct prb_data_block *blk; + unsigned long head_lpos; + unsigned long next_lpos; + bool wrapped; + + /* Reallocation only works if @blk_lpos is the newest data block. */ + head_lpos = atomic_long_read(&data_ring->head_lpos); + if (head_lpos != blk_lpos->next) + return NULL; + + /* Keep track if @blk_lpos was a wrapping data block. */ + wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); + + size = to_blk_size(size); + + next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); + + /* If the data block does not increase, there is nothing to do. */ + if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { + blk = to_block(data_ring, blk_lpos->begin); + return &blk->data[0]; + } + + if (!data_push_tail(rb, data_ring, next_lpos - DATA_SIZE(data_ring))) + return NULL; + + /* The memory barrier involvement is the same as data_alloc:A. */ + if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, + next_lpos)) { /* LMM(data_realloc:A) */ + return NULL; + } + + blk = to_block(data_ring, blk_lpos->begin); + + if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { + struct prb_data_block *old_blk = blk; + + /* Wrapping data blocks store their data at the beginning. */ + blk = to_block(data_ring, 0); + + /* + * Store the ID on the wrapped block for consistency. + * The printk_ringbuffer does not actually use it. + */ + blk->id = id; + + if (!wrapped) { + /* + * Since the allocated space is now in the newly + * created wrapping data block, copy the content + * from the old data block. + */ + memcpy(&blk->data[0], &old_blk->data[0], + (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); + } + } + + blk_lpos->next = next_lpos; + + return &blk->data[0]; +} + +/* Return the number of bytes used by a data block. */ +static unsigned int space_used(struct prb_data_ring *data_ring, + struct prb_data_blk_lpos *blk_lpos) +{ + /* Data-less blocks take no space. */ + if (BLK_DATALESS(blk_lpos)) + return 0; + + if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { + /* Data block does not wrap. */ + return (DATA_INDEX(data_ring, blk_lpos->next) - + DATA_INDEX(data_ring, blk_lpos->begin)); + } + + /* + * For wrapping data blocks, the trailing (wasted) space is + * also counted. + */ + return (DATA_INDEX(data_ring, blk_lpos->next) + + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); +} + +/* + * Given @blk_lpos, return a pointer to the writer data from the data block + * and calculate the size of the data part. A NULL pointer is returned if + * @blk_lpos specifies values that could never be legal. + * + * This function (used by readers) performs strict validation on the lpos + * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is + * triggered if an internal error is detected. + */ +static const char *get_data(struct prb_data_ring *data_ring, + struct prb_data_blk_lpos *blk_lpos, + unsigned int *data_size) +{ + struct prb_data_block *db; + + /* Data-less data block description. */ + if (BLK_DATALESS(blk_lpos)) { + if (blk_lpos->begin == NO_LPOS && blk_lpos->next == NO_LPOS) { + *data_size = 0; + return ""; + } + return NULL; + } + + /* Regular data block: @begin less than @next and in same wrap. */ + if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && + blk_lpos->begin < blk_lpos->next) { + db = to_block(data_ring, blk_lpos->begin); + *data_size = blk_lpos->next - blk_lpos->begin; + + /* Wrapping data block: @begin is one wrap behind @next. */ + } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == + DATA_WRAPS(data_ring, blk_lpos->next)) { + db = to_block(data_ring, 0); + *data_size = DATA_INDEX(data_ring, blk_lpos->next); + + /* Illegal block description. */ + } else { + WARN_ON_ONCE(1); + return NULL; + } + + /* A valid data block will always be aligned to the ID size. */ + if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || + WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { + return NULL; + } + + /* A valid data block will always have at least an ID. */ + if (WARN_ON_ONCE(*data_size < sizeof(db->id))) + return NULL; + + /* Subtract block ID space from size to reflect data size. */ + *data_size -= sizeof(db->id); + + return &db->data[0]; +} + +/* + * Attempt to transition the newest descriptor from committed back to reserved + * so that the record can be modified by a writer again. This is only possible + * if the descriptor is not yet finalized and the provided @caller_id matches. + */ +static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, + u32 caller_id, unsigned long *id_out) +{ + unsigned long prev_state_val; + enum desc_state d_state; + struct prb_desc desc; + struct prb_desc *d; + unsigned long id; + u32 cid; + + id = atomic_long_read(&desc_ring->head_id); + + /* + * To reduce unnecessarily reopening, first check if the descriptor + * state and caller ID are correct. + */ + d_state = desc_read(desc_ring, id, &desc, NULL, &cid); + if (d_state != desc_committed || cid != caller_id) + return NULL; + + d = to_desc(desc_ring, id); + + prev_state_val = DESC_SV(id, desc_committed); + + /* + * Guarantee the reserved state is stored before reading any + * record data. A full memory barrier is needed because @state_var + * modification is followed by reading. This pairs with _prb_commit:B. + * + * Memory barrier involvement: + * + * If desc_reopen_last:A reads from _prb_commit:B, then + * prb_reserve_in_last:A reads from _prb_commit:A. + * + * Relies on: + * + * WMB from _prb_commit:A to _prb_commit:B + * matching + * MB If desc_reopen_last:A to prb_reserve_in_last:A + */ + if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, + DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ + return NULL; + } + + *id_out = id; + return d; +} + +/** + * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer + * used by the newest record. + * + * @e: The entry structure to setup. + * @rb: The ringbuffer to re-reserve and extend data in. + * @r: The record structure to allocate buffers for. + * @caller_id: The caller ID of the caller (reserving writer). + * @max_size: Fail if the extended size would be greater than this. + * + * This is the public function available to writers to re-reserve and extend + * data. + * + * The writer specifies the text size to extend (not the new total size) by + * setting the @text_buf_size field of @r. To ensure proper initialization + * of @r, prb_rec_init_wr() should be used. + * + * This function will fail if @caller_id does not match the caller ID of the + * newest record. In that case the caller must reserve new data using + * prb_reserve(). + * + * Context: Any context. Disables local interrupts on success. + * Return: true if text data could be extended, otherwise false. + * + * On success: + * + * - @r->text_buf points to the beginning of the entire text buffer. + * + * - @r->text_buf_size is set to the new total size of the buffer. + * + * - @r->info is not touched so that @r->info->text_len could be used + * to append the text. + * + * - prb_record_text_space() can be used on @e to query the new + * actually used space. + * + * Important: All @r->info fields will already be set with the current values + * for the record. I.e. @r->info->text_len will be less than + * @text_buf_size. Writers can use @r->info->text_len to know + * where concatenation begins and writers should update + * @r->info->text_len after concatenating. + */ +bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r, u32 caller_id, unsigned int max_size) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct printk_info *info; + unsigned int data_size; + struct prb_desc *d; + unsigned long id; + + local_irq_save(e->irqflags); + + /* Transition the newest descriptor back to the reserved state. */ + d = desc_reopen_last(desc_ring, caller_id, &id); + if (!d) { + local_irq_restore(e->irqflags); + goto fail_reopen; + } + + /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ + + info = to_info(desc_ring, id); + + /* + * Set the @e fields here so that prb_commit() can be used if + * anything fails from now on. + */ + e->rb = rb; + e->id = id; + + /* + * desc_reopen_last() checked the caller_id, but there was no + * exclusive access at that point. The descriptor may have + * changed since then. + */ + if (caller_id != info->caller_id) + goto fail; + + if (BLK_DATALESS(&d->text_blk_lpos)) { + if (WARN_ON_ONCE(info->text_len != 0)) { + pr_warn_once("wrong text_len value (%hu, expecting 0)\n", + info->text_len); + info->text_len = 0; + } + + if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) + goto fail; + + if (r->text_buf_size > max_size) + goto fail; + + r->text_buf = data_alloc(rb, &rb->text_data_ring, r->text_buf_size, + &d->text_blk_lpos, id); + } else { + if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) + goto fail; + + /* + * Increase the buffer size to include the original size. If + * the meta data (@text_len) is not sane, use the full data + * block size. + */ + if (WARN_ON_ONCE(info->text_len > data_size)) { + pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", + info->text_len, data_size); + info->text_len = data_size; + } + r->text_buf_size += info->text_len; + + if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) + goto fail; + + if (r->text_buf_size > max_size) + goto fail; + + r->text_buf = data_realloc(rb, &rb->text_data_ring, r->text_buf_size, + &d->text_blk_lpos, id); + } + if (r->text_buf_size && !r->text_buf) + goto fail; + + r->info = info; + + e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); + + return true; +fail: + prb_commit(e); + /* prb_commit() re-enabled interrupts. */ +fail_reopen: + /* Make it clear to the caller that the re-reserve failed. */ + memset(r, 0, sizeof(*r)); + return false; +} + +/* + * Attempt to finalize a specified descriptor. If this fails, the descriptor + * is either already final or it will finalize itself when the writer commits. + */ +static void desc_make_final(struct prb_desc_ring *desc_ring, unsigned long id) +{ + unsigned long prev_state_val = DESC_SV(id, desc_committed); + struct prb_desc *d = to_desc(desc_ring, id); + + atomic_long_cmpxchg_relaxed(&d->state_var, prev_state_val, + DESC_SV(id, desc_finalized)); /* LMM(desc_make_final:A) */ +} + +/** + * prb_reserve() - Reserve space in the ringbuffer. + * + * @e: The entry structure to setup. + * @rb: The ringbuffer to reserve data in. + * @r: The record structure to allocate buffers for. + * + * This is the public function available to writers to reserve data. + * + * The writer specifies the text size to reserve by setting the + * @text_buf_size field of @r. To ensure proper initialization of @r, + * prb_rec_init_wr() should be used. + * + * Context: Any context. Disables local interrupts on success. + * Return: true if at least text data could be allocated, otherwise false. + * + * On success, the fields @info and @text_buf of @r will be set by this + * function and should be filled in by the writer before committing. Also + * on success, prb_record_text_space() can be used on @e to query the actual + * space used for the text data block. + * + * Important: @info->text_len needs to be set correctly by the writer in + * order for data to be readable and/or extended. Its value + * is initialized to 0. + */ +bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct printk_info *info; + struct prb_desc *d; + unsigned long id; + u64 seq; + + if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) + goto fail; + + /* + * Descriptors in the reserved state act as blockers to all further + * reservations once the desc_ring has fully wrapped. Disable + * interrupts during the reserve/commit window in order to minimize + * the likelihood of this happening. + */ + local_irq_save(e->irqflags); + + if (!desc_reserve(rb, &id)) { + /* Descriptor reservation failures are tracked. */ + atomic_long_inc(&rb->fail); + local_irq_restore(e->irqflags); + goto fail; + } + + d = to_desc(desc_ring, id); + info = to_info(desc_ring, id); + + /* + * All @info fields (except @seq) are cleared and must be filled in + * by the writer. Save @seq before clearing because it is used to + * determine the new sequence number. + */ + seq = info->seq; + memset(info, 0, sizeof(*info)); + + /* + * Set the @e fields here so that prb_commit() can be used if + * text data allocation fails. + */ + e->rb = rb; + e->id = id; + + /* + * Initialize the sequence number if it has "never been set". + * Otherwise just increment it by a full wrap. + * + * @seq is considered "never been set" if it has a value of 0, + * _except_ for @infos[0], which was specially setup by the ringbuffer + * initializer and therefore is always considered as set. + * + * See the "Bootstrap" comment block in printk_ringbuffer.h for + * details about how the initializer bootstraps the descriptors. + */ + if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) + info->seq = DESC_INDEX(desc_ring, id); + else + info->seq = seq + DESCS_COUNT(desc_ring); + + /* + * New data is about to be reserved. Once that happens, previous + * descriptors are no longer able to be extended. Finalize the + * previous descriptor now so that it can be made available to + * readers. (For seq==0 there is no previous descriptor.) + */ + if (info->seq > 0) + desc_make_final(desc_ring, DESC_ID(id - 1)); + + r->text_buf = data_alloc(rb, &rb->text_data_ring, r->text_buf_size, + &d->text_blk_lpos, id); + /* If text data allocation fails, a data-less record is committed. */ + if (r->text_buf_size && !r->text_buf) { + prb_commit(e); + /* prb_commit() re-enabled interrupts. */ + goto fail; + } + + r->info = info; + + /* Record full text space used by record. */ + e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); + + return true; +fail: + /* Make it clear to the caller that the reserve failed. */ + memset(r, 0, sizeof(*r)); + return false; +} + +/* Commit the data (possibly finalizing it) and restore interrupts. */ +static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) +{ + struct prb_desc_ring *desc_ring = &e->rb->desc_ring; + struct prb_desc *d = to_desc(desc_ring, e->id); + unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); + + /* Now the writer has finished all writing: LMM(_prb_commit:A) */ + + /* + * Set the descriptor as committed. See "ABA Issues" about why + * cmpxchg() instead of set() is used. + * + * 1 Guarantee all record data is stored before the descriptor state + * is stored as committed. A write memory barrier is sufficient + * for this. This pairs with desc_read:B and desc_reopen_last:A. + * + * 2. Guarantee the descriptor state is stored as committed before + * re-checking the head ID in order to possibly finalize this + * descriptor. This pairs with desc_reserve:D. + * + * Memory barrier involvement: + * + * If prb_commit:A reads from desc_reserve:D, then + * desc_make_final:A reads from _prb_commit:B. + * + * Relies on: + * + * MB _prb_commit:B to prb_commit:A + * matching + * MB desc_reserve:D to desc_make_final:A + */ + if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, + DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ + WARN_ON_ONCE(1); + } + + /* Restore interrupts, the reserve/commit window is finished. */ + local_irq_restore(e->irqflags); +} + +/** + * prb_commit() - Commit (previously reserved) data to the ringbuffer. + * + * @e: The entry containing the reserved data information. + * + * This is the public function available to writers to commit data. + * + * Note that the data is not yet available to readers until it is finalized. + * Finalizing happens automatically when space for the next record is + * reserved. + * + * See prb_final_commit() for a version of this function that finalizes + * immediately. + * + * Context: Any context. Enables local interrupts. + */ +void prb_commit(struct prb_reserved_entry *e) +{ + struct prb_desc_ring *desc_ring = &e->rb->desc_ring; + unsigned long head_id; + + _prb_commit(e, desc_committed); + + /* + * If this descriptor is no longer the head (i.e. a new record has + * been allocated), extending the data for this record is no longer + * allowed and therefore it must be finalized. + */ + head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ + if (head_id != e->id) + desc_make_final(desc_ring, e->id); +} + +/** + * prb_final_commit() - Commit and finalize (previously reserved) data to + * the ringbuffer. + * + * @e: The entry containing the reserved data information. + * + * This is the public function available to writers to commit+finalize data. + * + * By finalizing, the data is made immediately available to readers. + * + * This function should only be used if there are no intentions of extending + * this data using prb_reserve_in_last(). + * + * Context: Any context. Enables local interrupts. + */ +void prb_final_commit(struct prb_reserved_entry *e) +{ + _prb_commit(e, desc_finalized); +} + +/* + * Count the number of lines in provided text. All text has at least 1 line + * (even if @text_size is 0). Each '\n' processed is counted as an additional + * line. + */ +static unsigned int count_lines(const char *text, unsigned int text_size) +{ + unsigned int next_size = text_size; + unsigned int line_count = 1; + const char *next = text; + + while (next_size) { + next = memchr(next, '\n', next_size); + if (!next) + break; + line_count++; + next++; + next_size = text_size - (next - text); + } + + return line_count; +} + +/* + * Given @blk_lpos, copy an expected @len of data into the provided buffer. + * If @line_count is provided, count the number of lines in the data. + * + * This function (used by readers) performs strict validation on the data + * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is + * triggered if an internal error is detected. + */ +static bool copy_data(struct prb_data_ring *data_ring, + struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, + unsigned int buf_size, unsigned int *line_count) +{ + unsigned int data_size; + const char *data; + + /* Caller might not want any data. */ + if ((!buf || !buf_size) && !line_count) + return true; + + data = get_data(data_ring, blk_lpos, &data_size); + if (!data) + return false; + + /* + * Actual cannot be less than expected. It can be more than expected + * because of the trailing alignment padding. + * + * Note that invalid @len values can occur because the caller loads + * the value during an allowed data race. + */ + if (data_size < (unsigned int)len) + return false; + + /* Caller interested in the line count? */ + if (line_count) + *line_count = count_lines(data, data_size); + + /* Caller interested in the data content? */ + if (!buf || !buf_size) + return true; + + data_size = min_t(u16, buf_size, len); + + memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ + return true; +} + +/* + * This is an extended version of desc_read(). It gets a copy of a specified + * descriptor. However, it also verifies that the record is finalized and has + * the sequence number @seq. On success, 0 is returned. + * + * Error return values: + * -EINVAL: A finalized record with sequence number @seq does not exist. + * -ENOENT: A finalized record with sequence number @seq exists, but its data + * is not available. This is a valid record, so readers should + * continue with the next record. + */ +static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, + unsigned long id, u64 seq, + struct prb_desc *desc_out) +{ + struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; + enum desc_state d_state; + u64 s; + + d_state = desc_read(desc_ring, id, desc_out, &s, NULL); + + /* + * An unexpected @id (desc_miss) or @seq mismatch means the record + * does not exist. A descriptor in the reserved or committed state + * means the record does not yet exist for the reader. + */ + if (d_state == desc_miss || + d_state == desc_reserved || + d_state == desc_committed || + s != seq) { + return -EINVAL; + } + + /* + * A descriptor in the reusable state may no longer have its data + * available; report it as existing but with lost data. Or the record + * may actually be a record with lost data. + */ + if (d_state == desc_reusable || + (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { + return -ENOENT; + } + + return 0; +} + +/* + * Copy the ringbuffer data from the record with @seq to the provided + * @r buffer. On success, 0 is returned. + * + * See desc_read_finalized_seq() for error return values. + */ +static int prb_read(struct printk_ringbuffer *rb, u64 seq, + struct printk_record *r, unsigned int *line_count) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + struct printk_info *info = to_info(desc_ring, seq); + struct prb_desc *rdesc = to_desc(desc_ring, seq); + atomic_long_t *state_var = &rdesc->state_var; + struct prb_desc desc; + unsigned long id; + int err; + + /* Extract the ID, used to specify the descriptor to read. */ + id = DESC_ID(atomic_long_read(state_var)); + + /* Get a local copy of the correct descriptor (if available). */ + err = desc_read_finalized_seq(desc_ring, id, seq, &desc); + + /* + * If @r is NULL, the caller is only interested in the availability + * of the record. + */ + if (err || !r) + return err; + + /* If requested, copy meta data. */ + if (r->info) + memcpy(r->info, info, sizeof(*(r->info))); + + /* Copy text data. If it fails, this is a data-less record. */ + if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, + r->text_buf, r->text_buf_size, line_count)) { + return -ENOENT; + } + + /* Ensure the record is still finalized and has the same @seq. */ + return desc_read_finalized_seq(desc_ring, id, seq, &desc); +} + +/* Get the sequence number of the tail descriptor. */ +static u64 prb_first_seq(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + enum desc_state d_state; + struct prb_desc desc; + unsigned long id; + u64 seq; + + for (;;) { + id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ + + d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ + + /* + * This loop will not be infinite because the tail is + * _always_ in the finalized or reusable state. + */ + if (d_state == desc_finalized || d_state == desc_reusable) + break; + + /* + * Guarantee the last state load from desc_read() is before + * reloading @tail_id in order to see a new tail in the case + * that the descriptor has been recycled. This pairs with + * desc_reserve:D. + * + * Memory barrier involvement: + * + * If prb_first_seq:B reads from desc_reserve:F, then + * prb_first_seq:A reads from desc_push_tail:B. + * + * Relies on: + * + * MB from desc_push_tail:B to desc_reserve:F + * matching + * RMB prb_first_seq:B to prb_first_seq:A + */ + smp_rmb(); /* LMM(prb_first_seq:C) */ + } + + return seq; +} + +/* + * Non-blocking read of a record. Updates @seq to the last finalized record + * (which may have no data available). + * + * See the description of prb_read_valid() and prb_read_valid_info() + * for details. + */ +static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, + struct printk_record *r, unsigned int *line_count) +{ + u64 tail_seq; + int err; + + while ((err = prb_read(rb, *seq, r, line_count))) { + tail_seq = prb_first_seq(rb); + + if (*seq < tail_seq) { + /* + * Behind the tail. Catch up and try again. This + * can happen for -ENOENT and -EINVAL cases. + */ + *seq = tail_seq; + + } else if (err == -ENOENT) { + /* Record exists, but no data available. Skip. */ + (*seq)++; + + } else { + /* Non-existent/non-finalized record. Must stop. */ + return false; + } + } + + return true; +} + +/** + * prb_read_valid() - Non-blocking read of a requested record or (if gone) + * the next available record. + * + * @rb: The ringbuffer to read from. + * @seq: The sequence number of the record to read. + * @r: A record data buffer to store the read record to. + * + * This is the public function available to readers to read a record. + * + * The reader provides the @info and @text_buf buffers of @r to be + * filled in. Any of the buffer pointers can be set to NULL if the reader + * is not interested in that data. To ensure proper initialization of @r, + * prb_rec_init_rd() should be used. + * + * Context: Any context. + * Return: true if a record was read, otherwise false. + * + * On success, the reader must check r->info.seq to see which record was + * actually read. This allows the reader to detect dropped records. + * + * Failure means @seq refers to a not yet written record. + */ +bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, + struct printk_record *r) +{ + return _prb_read_valid(rb, &seq, r, NULL); +} + +/** + * prb_read_valid_info() - Non-blocking read of meta data for a requested + * record or (if gone) the next available record. + * + * @rb: The ringbuffer to read from. + * @seq: The sequence number of the record to read. + * @info: A buffer to store the read record meta data to. + * @line_count: A buffer to store the number of lines in the record text. + * + * This is the public function available to readers to read only the + * meta data of a record. + * + * The reader provides the @info, @line_count buffers to be filled in. + * Either of the buffer pointers can be set to NULL if the reader is not + * interested in that data. + * + * Context: Any context. + * Return: true if a record's meta data was read, otherwise false. + * + * On success, the reader must check info->seq to see which record meta data + * was actually read. This allows the reader to detect dropped records. + * + * Failure means @seq refers to a not yet written record. + */ +bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, + struct printk_info *info, unsigned int *line_count) +{ + struct printk_record r; + + prb_rec_init_rd(&r, info, NULL, 0); + + return _prb_read_valid(rb, &seq, &r, line_count); +} + +/** + * prb_first_valid_seq() - Get the sequence number of the oldest available + * record. + * + * @rb: The ringbuffer to get the sequence number from. + * + * This is the public function available to readers to see what the + * first/oldest valid sequence number is. + * + * This provides readers a starting point to begin iterating the ringbuffer. + * + * Context: Any context. + * Return: The sequence number of the first/oldest record or, if the + * ringbuffer is empty, 0 is returned. + */ +u64 prb_first_valid_seq(struct printk_ringbuffer *rb) +{ + u64 seq = 0; + + if (!_prb_read_valid(rb, &seq, NULL, NULL)) + return 0; + + return seq; +} + +/** + * prb_next_seq() - Get the sequence number after the last available record. + * + * @rb: The ringbuffer to get the sequence number from. + * + * This is the public function available to readers to see what the next + * newest sequence number available to readers will be. + * + * This provides readers a sequence number to jump to if all currently + * available records should be skipped. + * + * Context: Any context. + * Return: The sequence number of the next newest (not yet available) record + * for readers. + */ +u64 prb_next_seq(struct printk_ringbuffer *rb) +{ + u64 seq = 0; + + /* Search forward from the oldest descriptor. */ + while (_prb_read_valid(rb, &seq, NULL, NULL)) + seq++; + + return seq; +} + +/** + * prb_init() - Initialize a ringbuffer to use provided external buffers. + * + * @rb: The ringbuffer to initialize. + * @text_buf: The data buffer for text data. + * @textbits: The size of @text_buf as a power-of-2 value. + * @descs: The descriptor buffer for ringbuffer records. + * @descbits: The count of @descs items as a power-of-2 value. + * @infos: The printk_info buffer for ringbuffer records. + * + * This is the public function available to writers to setup a ringbuffer + * during runtime using provided buffers. + * + * This must match the initialization of DEFINE_PRINTKRB(). + * + * Context: Any context. + */ +void prb_init(struct printk_ringbuffer *rb, + char *text_buf, unsigned int textbits, + struct prb_desc *descs, unsigned int descbits, + struct printk_info *infos) +{ + memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); + memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); + + rb->desc_ring.count_bits = descbits; + rb->desc_ring.descs = descs; + rb->desc_ring.infos = infos; + atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); + atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); + + rb->text_data_ring.size_bits = textbits; + rb->text_data_ring.data = text_buf; + atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); + atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); + + atomic_long_set(&rb->fail, 0); + + atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); + descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; + descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; + + infos[0].seq = -(u64)_DESCS_COUNT(descbits); + infos[_DESCS_COUNT(descbits) - 1].seq = 0; +} + +/** + * prb_record_text_space() - Query the full actual used ringbuffer space for + * the text data of a reserved entry. + * + * @e: The successfully reserved entry to query. + * + * This is the public function available to writers to see how much actual + * space is used in the ringbuffer to store the text data of the specified + * entry. + * + * This function is only valid if @e has been successfully reserved using + * prb_reserve(). + * + * Context: Any context. + * Return: The size in bytes used by the text data of the associated record. + */ +unsigned int prb_record_text_space(struct prb_reserved_entry *e) +{ + return e->text_space; +} diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h new file mode 100644 index 000000000000..5dc9d022db07 --- /dev/null +++ b/kernel/printk/printk_ringbuffer.h @@ -0,0 +1,382 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _KERNEL_PRINTK_RINGBUFFER_H +#define _KERNEL_PRINTK_RINGBUFFER_H + +#include <linux/atomic.h> +#include <linux/dev_printk.h> + +/* + * Meta information about each stored message. + * + * All fields are set by the printk code except for @seq, which is + * set by the ringbuffer code. + */ +struct printk_info { + u64 seq; /* sequence number */ + u64 ts_nsec; /* timestamp in nanoseconds */ + u16 text_len; /* length of text message */ + u8 facility; /* syslog facility */ + u8 flags:5; /* internal record flags */ + u8 level:3; /* syslog level */ + u32 caller_id; /* thread id or processor id */ + + struct dev_printk_info dev_info; +}; + +/* + * A structure providing the buffers, used by writers and readers. + * + * Writers: + * Using prb_rec_init_wr(), a writer sets @text_buf_size before calling + * prb_reserve(). On success, prb_reserve() sets @info and @text_buf to + * buffers reserved for that writer. + * + * Readers: + * Using prb_rec_init_rd(), a reader sets all fields before calling + * prb_read_valid(). Note that the reader provides the @info and @text_buf, + * buffers. On success, the struct pointed to by @info will be filled and + * the char array pointed to by @text_buf will be filled with text data. + */ +struct printk_record { + struct printk_info *info; + char *text_buf; + unsigned int text_buf_size; +}; + +/* Specifies the logical position and span of a data block. */ +struct prb_data_blk_lpos { + unsigned long begin; + unsigned long next; +}; + +/* + * A descriptor: the complete meta-data for a record. + * + * @state_var: A bitwise combination of descriptor ID and descriptor state. + */ +struct prb_desc { + atomic_long_t state_var; + struct prb_data_blk_lpos text_blk_lpos; +}; + +/* A ringbuffer of "ID + data" elements. */ +struct prb_data_ring { + unsigned int size_bits; + char *data; + atomic_long_t head_lpos; + atomic_long_t tail_lpos; +}; + +/* A ringbuffer of "struct prb_desc" elements. */ +struct prb_desc_ring { + unsigned int count_bits; + struct prb_desc *descs; + struct printk_info *infos; + atomic_long_t head_id; + atomic_long_t tail_id; +}; + +/* + * The high level structure representing the printk ringbuffer. + * + * @fail: Count of failed prb_reserve() calls where not even a data-less + * record was created. + */ +struct printk_ringbuffer { + struct prb_desc_ring desc_ring; + struct prb_data_ring text_data_ring; + atomic_long_t fail; +}; + +/* + * Used by writers as a reserve/commit handle. + * + * @rb: Ringbuffer where the entry is reserved. + * @irqflags: Saved irq flags to restore on entry commit. + * @id: ID of the reserved descriptor. + * @text_space: Total occupied buffer space in the text data ring, including + * ID, alignment padding, and wrapping data blocks. + * + * This structure is an opaque handle for writers. Its contents are only + * to be used by the ringbuffer implementation. + */ +struct prb_reserved_entry { + struct printk_ringbuffer *rb; + unsigned long irqflags; + unsigned long id; + unsigned int text_space; +}; + +/* The possible responses of a descriptor state-query. */ +enum desc_state { + desc_miss = -1, /* ID mismatch (pseudo state) */ + desc_reserved = 0x0, /* reserved, in use by writer */ + desc_committed = 0x1, /* committed by writer, could get reopened */ + desc_finalized = 0x2, /* committed, no further modification allowed */ + desc_reusable = 0x3, /* free, not yet used by any writer */ +}; + +#define _DATA_SIZE(sz_bits) (1UL << (sz_bits)) +#define _DESCS_COUNT(ct_bits) (1U << (ct_bits)) +#define DESC_SV_BITS (sizeof(unsigned long) * 8) +#define DESC_FLAGS_SHIFT (DESC_SV_BITS - 2) +#define DESC_FLAGS_MASK (3UL << DESC_FLAGS_SHIFT) +#define DESC_STATE(sv) (3UL & (sv >> DESC_FLAGS_SHIFT)) +#define DESC_SV(id, state) (((unsigned long)state << DESC_FLAGS_SHIFT) | id) +#define DESC_ID_MASK (~DESC_FLAGS_MASK) +#define DESC_ID(sv) ((sv) & DESC_ID_MASK) +#define FAILED_LPOS 0x1 +#define NO_LPOS 0x3 + +#define FAILED_BLK_LPOS \ +{ \ + .begin = FAILED_LPOS, \ + .next = FAILED_LPOS, \ +} + +/* + * Descriptor Bootstrap + * + * The descriptor array is minimally initialized to allow immediate usage + * by readers and writers. The requirements that the descriptor array + * initialization must satisfy: + * + * Req1 + * The tail must point to an existing (committed or reusable) descriptor. + * This is required by the implementation of prb_first_seq(). + * + * Req2 + * Readers must see that the ringbuffer is initially empty. + * + * Req3 + * The first record reserved by a writer is assigned sequence number 0. + * + * To satisfy Req1, the tail initially points to a descriptor that is + * minimally initialized (having no data block, i.e. data-less with the + * data block's lpos @begin and @next values set to FAILED_LPOS). + * + * To satisfy Req2, the initial tail descriptor is initialized to the + * reusable state. Readers recognize reusable descriptors as existing + * records, but skip over them. + * + * To satisfy Req3, the last descriptor in the array is used as the initial + * head (and tail) descriptor. This allows the first record reserved by a + * writer (head + 1) to be the first descriptor in the array. (Only the first + * descriptor in the array could have a valid sequence number of 0.) + * + * The first time a descriptor is reserved, it is assigned a sequence number + * with the value of the array index. A "first time reserved" descriptor can + * be recognized because it has a sequence number of 0 but does not have an + * index of 0. (Only the first descriptor in the array could have a valid + * sequence number of 0.) After the first reservation, all future reservations + * (recycling) simply involve incrementing the sequence number by the array + * count. + * + * Hack #1 + * Only the first descriptor in the array is allowed to have the sequence + * number 0. In this case it is not possible to recognize if it is being + * reserved the first time (set to index value) or has been reserved + * previously (increment by the array count). This is handled by _always_ + * incrementing the sequence number by the array count when reserving the + * first descriptor in the array. In order to satisfy Req3, the sequence + * number of the first descriptor in the array is initialized to minus + * the array count. Then, upon the first reservation, it is incremented + * to 0, thus satisfying Req3. + * + * Hack #2 + * prb_first_seq() can be called at any time by readers to retrieve the + * sequence number of the tail descriptor. However, due to Req2 and Req3, + * initially there are no records to report the sequence number of + * (sequence numbers are u64 and there is nothing less than 0). To handle + * this, the sequence number of the initial tail descriptor is initialized + * to 0. Technically this is incorrect, because there is no record with + * sequence number 0 (yet) and the tail descriptor is not the first + * descriptor in the array. But it allows prb_read_valid() to correctly + * report the existence of a record for _any_ given sequence number at all + * times. Bootstrapping is complete when the tail is pushed the first + * time, thus finally pointing to the first descriptor reserved by a + * writer, which has the assigned sequence number 0. + */ + +/* + * Initiating Logical Value Overflows + * + * Both logical position (lpos) and ID values can be mapped to array indexes + * but may experience overflows during the lifetime of the system. To ensure + * that printk_ringbuffer can handle the overflows for these types, initial + * values are chosen that map to the correct initial array indexes, but will + * result in overflows soon. + * + * BLK0_LPOS + * The initial @head_lpos and @tail_lpos for data rings. It is at index + * 0 and the lpos value is such that it will overflow on the first wrap. + * + * DESC0_ID + * The initial @head_id and @tail_id for the desc ring. It is at the last + * index of the descriptor array (see Req3 above) and the ID value is such + * that it will overflow on the second wrap. + */ +#define BLK0_LPOS(sz_bits) (-(_DATA_SIZE(sz_bits))) +#define DESC0_ID(ct_bits) DESC_ID(-(_DESCS_COUNT(ct_bits) + 1)) +#define DESC0_SV(ct_bits) DESC_SV(DESC0_ID(ct_bits), desc_reusable) + +/* + * Define a ringbuffer with an external text data buffer. The same as + * DEFINE_PRINTKRB() but requires specifying an external buffer for the + * text data. + * + * Note: The specified external buffer must be of the size: + * 2 ^ (descbits + avgtextbits) + */ +#define _DEFINE_PRINTKRB(name, descbits, avgtextbits, text_buf) \ +static struct prb_desc _##name##_descs[_DESCS_COUNT(descbits)] = { \ + /* the initial head and tail */ \ + [_DESCS_COUNT(descbits) - 1] = { \ + /* reusable */ \ + .state_var = ATOMIC_INIT(DESC0_SV(descbits)), \ + /* no associated data block */ \ + .text_blk_lpos = FAILED_BLK_LPOS, \ + }, \ +}; \ +static struct printk_info _##name##_infos[_DESCS_COUNT(descbits)] = { \ + /* this will be the first record reserved by a writer */ \ + [0] = { \ + /* will be incremented to 0 on the first reservation */ \ + .seq = -(u64)_DESCS_COUNT(descbits), \ + }, \ + /* the initial head and tail */ \ + [_DESCS_COUNT(descbits) - 1] = { \ + /* reports the first seq value during the bootstrap phase */ \ + .seq = 0, \ + }, \ +}; \ +static struct printk_ringbuffer name = { \ + .desc_ring = { \ + .count_bits = descbits, \ + .descs = &_##name##_descs[0], \ + .infos = &_##name##_infos[0], \ + .head_id = ATOMIC_INIT(DESC0_ID(descbits)), \ + .tail_id = ATOMIC_INIT(DESC0_ID(descbits)), \ + }, \ + .text_data_ring = { \ + .size_bits = (avgtextbits) + (descbits), \ + .data = text_buf, \ + .head_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ + .tail_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ + }, \ + .fail = ATOMIC_LONG_INIT(0), \ +} + +/** + * DEFINE_PRINTKRB() - Define a ringbuffer. + * + * @name: The name of the ringbuffer variable. + * @descbits: The number of descriptors as a power-of-2 value. + * @avgtextbits: The average text data size per record as a power-of-2 value. + * + * This is a macro for defining a ringbuffer and all internal structures + * such that it is ready for immediate use. See _DEFINE_PRINTKRB() for a + * variant where the text data buffer can be specified externally. + */ +#define DEFINE_PRINTKRB(name, descbits, avgtextbits) \ +static char _##name##_text[1U << ((avgtextbits) + (descbits))] \ + __aligned(__alignof__(unsigned long)); \ +_DEFINE_PRINTKRB(name, descbits, avgtextbits, &_##name##_text[0]) + +/* Writer Interface */ + +/** + * prb_rec_init_wd() - Initialize a buffer for writing records. + * + * @r: The record to initialize. + * @text_buf_size: The needed text buffer size. + */ +static inline void prb_rec_init_wr(struct printk_record *r, + unsigned int text_buf_size) +{ + r->info = NULL; + r->text_buf = NULL; + r->text_buf_size = text_buf_size; +} + +bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r); +bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, + struct printk_record *r, u32 caller_id, unsigned int max_size); +void prb_commit(struct prb_reserved_entry *e); +void prb_final_commit(struct prb_reserved_entry *e); + +void prb_init(struct printk_ringbuffer *rb, + char *text_buf, unsigned int text_buf_size, + struct prb_desc *descs, unsigned int descs_count_bits, + struct printk_info *infos); +unsigned int prb_record_text_space(struct prb_reserved_entry *e); + +/* Reader Interface */ + +/** + * prb_rec_init_rd() - Initialize a buffer for reading records. + * + * @r: The record to initialize. + * @info: A buffer to store record meta-data. + * @text_buf: A buffer to store text data. + * @text_buf_size: The size of @text_buf. + * + * Initialize all the fields that a reader is interested in. All arguments + * (except @r) are optional. Only record data for arguments that are + * non-NULL or non-zero will be read. + */ +static inline void prb_rec_init_rd(struct printk_record *r, + struct printk_info *info, + char *text_buf, unsigned int text_buf_size) +{ + r->info = info; + r->text_buf = text_buf; + r->text_buf_size = text_buf_size; +} + +/** + * prb_for_each_record() - Iterate over the records of a ringbuffer. + * + * @from: The sequence number to begin with. + * @rb: The ringbuffer to iterate over. + * @s: A u64 to store the sequence number on each iteration. + * @r: A printk_record to store the record on each iteration. + * + * This is a macro for conveniently iterating over a ringbuffer. + * Note that @s may not be the sequence number of the record on each + * iteration. For the sequence number, @r->info->seq should be checked. + * + * Context: Any context. + */ +#define prb_for_each_record(from, rb, s, r) \ +for ((s) = from; prb_read_valid(rb, s, r); (s) = (r)->info->seq + 1) + +/** + * prb_for_each_info() - Iterate over the meta data of a ringbuffer. + * + * @from: The sequence number to begin with. + * @rb: The ringbuffer to iterate over. + * @s: A u64 to store the sequence number on each iteration. + * @i: A printk_info to store the record meta data on each iteration. + * @lc: An unsigned int to store the text line count of each record. + * + * This is a macro for conveniently iterating over a ringbuffer. + * Note that @s may not be the sequence number of the record on each + * iteration. For the sequence number, @r->info->seq should be checked. + * + * Context: Any context. + */ +#define prb_for_each_info(from, rb, s, i, lc) \ +for ((s) = from; prb_read_valid_info(rb, s, i, lc); (s) = (i)->seq + 1) + +bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, + struct printk_record *r); +bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, + struct printk_info *info, unsigned int *line_count); + +u64 prb_first_valid_seq(struct printk_ringbuffer *rb); +u64 prb_next_seq(struct printk_ringbuffer *rb); + +#endif /* _KERNEL_PRINTK_RINGBUFFER_H */ diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index 50aeae770434..5dbc40160990 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -375,7 +375,7 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args) raw_spin_trylock(&logbuf_lock)) { int len; - len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args); + len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args); raw_spin_unlock(&logbuf_lock); defer_console_output(); return len; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 676d4af62103..8ad7a293255a 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -196,6 +196,10 @@ struct seccomp_filter { */ static void populate_seccomp_data(struct seccomp_data *sd) { + /* + * Instead of using current_pt_reg(), we're already doing the work + * to safely fetch "current", so just use "task" everywhere below. + */ struct task_struct *task = current; struct pt_regs *regs = task_pt_regs(task); unsigned long args[6]; @@ -910,7 +914,7 @@ out: if (flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) return 0; - syscall_set_return_value(current, task_pt_regs(current), + syscall_set_return_value(current, current_pt_regs(), err, ret); return -1; } @@ -943,13 +947,13 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, /* Set low-order bits as an errno, capped at MAX_ERRNO. */ if (data > MAX_ERRNO) data = MAX_ERRNO; - syscall_set_return_value(current, task_pt_regs(current), + syscall_set_return_value(current, current_pt_regs(), -data, 0); goto skip; case SECCOMP_RET_TRAP: /* Show the handler the original registers. */ - syscall_rollback(current, task_pt_regs(current)); + syscall_rollback(current, current_pt_regs()); /* Let the filter pass back 16 bits of data. */ seccomp_send_sigsys(this_syscall, data); goto skip; @@ -962,7 +966,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, /* ENOSYS these calls if there is no tracer attached. */ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { syscall_set_return_value(current, - task_pt_regs(current), + current_pt_regs(), -ENOSYS, 0); goto skip; } @@ -982,7 +986,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, if (fatal_signal_pending(current)) goto skip; /* Check if the tracer forced the syscall to be skipped. */ - this_syscall = syscall_get_nr(current, task_pt_regs(current)); + this_syscall = syscall_get_nr(current, current_pt_regs()); if (this_syscall < 0) goto skip; @@ -1020,20 +1024,20 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, default: seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ - if (action == SECCOMP_RET_KILL_PROCESS || + if (action != SECCOMP_RET_KILL_THREAD || get_nr_threads(current) == 1) { kernel_siginfo_t info; /* Show the original registers in the dump. */ - syscall_rollback(current, task_pt_regs(current)); + syscall_rollback(current, current_pt_regs()); /* Trigger a manual coredump since do_exit skips it. */ seccomp_init_siginfo(&info, this_syscall, data); do_coredump(&info); } - if (action == SECCOMP_RET_KILL_PROCESS) - do_group_exit(SIGSYS); - else + if (action == SECCOMP_RET_KILL_THREAD) do_exit(SIGSYS); + else + do_group_exit(SIGSYS); } unreachable(); @@ -1060,7 +1064,7 @@ int __secure_computing(const struct seccomp_data *sd) return 0; this_syscall = sd ? sd->nr : - syscall_get_nr(current, task_pt_regs(current)); + syscall_get_nr(current, current_pt_regs()); switch (mode) { case SECCOMP_MODE_STRICT: @@ -1472,13 +1476,7 @@ static const struct file_operations seccomp_notify_ops = { static struct file *init_listener(struct seccomp_filter *filter) { - struct file *ret = ERR_PTR(-EBUSY); - struct seccomp_filter *cur; - - for (cur = current->seccomp.filter; cur; cur = cur->prev) { - if (cur->notif) - goto out; - } + struct file *ret; ret = ERR_PTR(-ENOMEM); filter->notif = kzalloc(sizeof(*(filter->notif)), GFP_KERNEL); @@ -1504,6 +1502,31 @@ out: return ret; } +/* + * Does @new_child have a listener while an ancestor also has a listener? + * If so, we'll want to reject this filter. + * This only has to be tested for the current process, even in the TSYNC case, + * because TSYNC installs @child with the same parent on all threads. + * Note that @new_child is not hooked up to its parent at this point yet, so + * we use current->seccomp.filter. + */ +static bool has_duplicate_listener(struct seccomp_filter *new_child) +{ + struct seccomp_filter *cur; + + /* must be protected against concurrent TSYNC */ + lockdep_assert_held(¤t->sighand->siglock); + + if (!new_child->notif) + return false; + for (cur = current->seccomp.filter; cur; cur = cur->prev) { + if (cur->notif) + return true; + } + + return false; +} + /** * seccomp_set_mode_filter: internal function for setting seccomp filter * @flags: flags to change filter behavior @@ -1575,6 +1598,11 @@ static long seccomp_set_mode_filter(unsigned int flags, if (!seccomp_may_assign_mode(seccomp_mode)) goto out; + if (has_duplicate_listener(prepared)) { + ret = -EBUSY; + goto out; + } + ret = seccomp_attach_filter(flags, prepared); if (ret) goto out; diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index 2fa7bb83885f..a92c55bd8de5 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -16,8 +16,13 @@ import sys from linux import utils -printk_log_type = utils.CachedType("struct printk_log") - +printk_info_type = utils.CachedType("struct printk_info") +prb_data_blk_lpos_type = utils.CachedType("struct prb_data_blk_lpos") +prb_desc_type = utils.CachedType("struct prb_desc") +prb_desc_ring_type = utils.CachedType("struct prb_desc_ring") +prb_data_ring_type = utils.CachedType("struct prb_data_ring") +printk_ringbuffer_type = utils.CachedType("struct printk_ringbuffer") +atomic_long_type = utils.CachedType("atomic_long_t") class LxDmesg(gdb.Command): """Print Linux kernel log buffer.""" @@ -26,44 +31,110 @@ class LxDmesg(gdb.Command): super(LxDmesg, self).__init__("lx-dmesg", gdb.COMMAND_DATA) def invoke(self, arg, from_tty): - log_buf_addr = int(str(gdb.parse_and_eval( - "(void *)'printk.c'::log_buf")).split()[0], 16) - log_first_idx = int(gdb.parse_and_eval("'printk.c'::log_first_idx")) - log_next_idx = int(gdb.parse_and_eval("'printk.c'::log_next_idx")) - log_buf_len = int(gdb.parse_and_eval("'printk.c'::log_buf_len")) - inf = gdb.inferiors()[0] - start = log_buf_addr + log_first_idx - if log_first_idx < log_next_idx: - log_buf_2nd_half = -1 - length = log_next_idx - log_first_idx - log_buf = utils.read_memoryview(inf, start, length).tobytes() - else: - log_buf_2nd_half = log_buf_len - log_first_idx - a = utils.read_memoryview(inf, start, log_buf_2nd_half) - b = utils.read_memoryview(inf, log_buf_addr, log_next_idx) - log_buf = a.tobytes() + b.tobytes() - - length_offset = printk_log_type.get_type()['len'].bitpos // 8 - text_len_offset = printk_log_type.get_type()['text_len'].bitpos // 8 - time_stamp_offset = printk_log_type.get_type()['ts_nsec'].bitpos // 8 - text_offset = printk_log_type.get_type().sizeof - - pos = 0 - while pos < log_buf.__len__(): - length = utils.read_u16(log_buf, pos + length_offset) - if length == 0: - if log_buf_2nd_half == -1: - gdb.write("Corrupted log buffer!\n") + + # read in prb structure + prb_addr = int(str(gdb.parse_and_eval("(void *)'printk.c'::prb")).split()[0], 16) + sz = printk_ringbuffer_type.get_type().sizeof + prb = utils.read_memoryview(inf, prb_addr, sz).tobytes() + + # read in descriptor ring structure + off = printk_ringbuffer_type.get_type()['desc_ring'].bitpos // 8 + addr = prb_addr + off + sz = prb_desc_ring_type.get_type().sizeof + desc_ring = utils.read_memoryview(inf, addr, sz).tobytes() + + # read in descriptor array + off = prb_desc_ring_type.get_type()['count_bits'].bitpos // 8 + desc_ring_count = 1 << utils.read_u32(desc_ring, off) + desc_sz = prb_desc_type.get_type().sizeof + off = prb_desc_ring_type.get_type()['descs'].bitpos // 8 + addr = utils.read_ulong(desc_ring, off) + descs = utils.read_memoryview(inf, addr, desc_sz * desc_ring_count).tobytes() + + # read in info array + info_sz = printk_info_type.get_type().sizeof + off = prb_desc_ring_type.get_type()['infos'].bitpos // 8 + addr = utils.read_ulong(desc_ring, off) + infos = utils.read_memoryview(inf, addr, info_sz * desc_ring_count).tobytes() + + # read in text data ring structure + off = printk_ringbuffer_type.get_type()['text_data_ring'].bitpos // 8 + addr = prb_addr + off + sz = prb_data_ring_type.get_type().sizeof + text_data_ring = utils.read_memoryview(inf, addr, sz).tobytes() + + # read in text data + off = prb_data_ring_type.get_type()['size_bits'].bitpos // 8 + text_data_sz = 1 << utils.read_u32(text_data_ring, off) + off = prb_data_ring_type.get_type()['data'].bitpos // 8 + addr = utils.read_ulong(text_data_ring, off) + text_data = utils.read_memoryview(inf, addr, text_data_sz).tobytes() + + counter_off = atomic_long_type.get_type()['counter'].bitpos // 8 + + sv_off = prb_desc_type.get_type()['state_var'].bitpos // 8 + + off = prb_desc_type.get_type()['text_blk_lpos'].bitpos // 8 + begin_off = off + (prb_data_blk_lpos_type.get_type()['begin'].bitpos // 8) + next_off = off + (prb_data_blk_lpos_type.get_type()['next'].bitpos // 8) + + ts_off = printk_info_type.get_type()['ts_nsec'].bitpos // 8 + len_off = printk_info_type.get_type()['text_len'].bitpos // 8 + + # definitions from kernel/printk/printk_ringbuffer.h + desc_committed = 1 + desc_finalized = 2 + desc_sv_bits = utils.get_long_type().sizeof * 8 + desc_flags_shift = desc_sv_bits - 2 + desc_flags_mask = 3 << desc_flags_shift + desc_id_mask = ~desc_flags_mask + + # read in tail and head descriptor ids + off = prb_desc_ring_type.get_type()['tail_id'].bitpos // 8 + tail_id = utils.read_u64(desc_ring, off + counter_off) + off = prb_desc_ring_type.get_type()['head_id'].bitpos // 8 + head_id = utils.read_u64(desc_ring, off + counter_off) + + did = tail_id + while True: + ind = did % desc_ring_count + desc_off = desc_sz * ind + info_off = info_sz * ind + + # skip non-committed record + state = 3 & (utils.read_u64(descs, desc_off + sv_off + + counter_off) >> desc_flags_shift) + if state != desc_committed and state != desc_finalized: + if did == head_id: break - pos = log_buf_2nd_half + did = (did + 1) & desc_id_mask continue - text_len = utils.read_u16(log_buf, pos + text_len_offset) - text_start = pos + text_offset - text = log_buf[text_start:text_start + text_len].decode( - encoding='utf8', errors='replace') - time_stamp = utils.read_u64(log_buf, pos + time_stamp_offset) + begin = utils.read_ulong(descs, desc_off + begin_off) % text_data_sz + end = utils.read_ulong(descs, desc_off + next_off) % text_data_sz + + # handle data-less record + if begin & 1 == 1: + text = "" + else: + # handle wrapping data block + if begin > end: + begin = 0 + + # skip over descriptor id + text_start = begin + utils.get_long_type().sizeof + + text_len = utils.read_u16(infos, info_off + len_off) + + # handle truncated message + if end - text_start < text_len: + text_len = end - text_start + + text = text_data[text_start:text_start + text_len].decode( + encoding='utf8', errors='replace') + + time_stamp = utils.read_u64(infos, info_off + ts_off) for line in text.splitlines(): msg = u"[{time:12.6f}] {line}\n".format( @@ -75,7 +146,9 @@ class LxDmesg(gdb.Command): msg = msg.encode(encoding='utf8', errors='replace') gdb.write(msg) - pos += length + if did == head_id: + break + did = (did + 1) & desc_id_mask LxDmesg() diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index ea94221dbd39..ff7c1799d588 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -123,6 +123,13 @@ def read_u64(buffer, offset): return read_u32(buffer, offset + 4) + (read_u32(buffer, offset) << 32) +def read_ulong(buffer, offset): + if get_long_type().sizeof == 8: + return read_u64(buffer, offset) + else: + return read_u32(buffer, offset) + + target_arch = None diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c index 6ceb88eb9b59..105c1c31a316 100644 --- a/scripts/selinux/mdp/mdp.c +++ b/scripts/selinux/mdp/mdp.c @@ -35,6 +35,9 @@ struct security_class_mapping { #include "classmap.h" #include "initial_sid_to_string.h" +#include "policycap_names.h" + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) int main(int argc, char *argv[]) { @@ -115,6 +118,10 @@ int main(int argc, char *argv[]) } } + /* enable all policy capabilities */ + for (i = 0; i < ARRAY_SIZE(selinux_policycap_names); i++) + fprintf(fout, "policycap %s;\n", selinux_policycap_names[i]); + /* types, roles, and allows */ fprintf(fout, "type base_t;\n"); fprintf(fout, "role base_r;\n"); diff --git a/security/selinux/avc.c b/security/selinux/avc.c index d18cb32a242a..3c05827608b6 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -31,6 +31,9 @@ #include "avc_ss.h" #include "classmap.h" +#define CREATE_TRACE_POINTS +#include <trace/events/avc.h> + #define AVC_CACHE_SLOTS 512 #define AVC_DEF_CACHE_THRESHOLD 512 #define AVC_CACHE_RECLAIM 16 @@ -702,33 +705,37 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; - char *scontext; + char *scontext = NULL; + char *tcontext = NULL; + const char *tclass = NULL; u32 scontext_len; + u32 tcontext_len; int rc; rc = security_sid_to_context(sad->state, sad->ssid, &scontext, &scontext_len); if (rc) audit_log_format(ab, " ssid=%d", sad->ssid); - else { + else audit_log_format(ab, " scontext=%s", scontext); - kfree(scontext); - } - rc = security_sid_to_context(sad->state, sad->tsid, &scontext, - &scontext_len); + rc = security_sid_to_context(sad->state, sad->tsid, &tcontext, + &tcontext_len); if (rc) audit_log_format(ab, " tsid=%d", sad->tsid); - else { - audit_log_format(ab, " tcontext=%s", scontext); - kfree(scontext); - } + else + audit_log_format(ab, " tcontext=%s", tcontext); - audit_log_format(ab, " tclass=%s", secclass_map[sad->tclass-1].name); + tclass = secclass_map[sad->tclass-1].name; + audit_log_format(ab, " tclass=%s", tclass); if (sad->denied) audit_log_format(ab, " permissive=%u", sad->result ? 0 : 1); + trace_selinux_audited(sad, scontext, tcontext, tclass); + kfree(tcontext); + kfree(scontext); + /* in case of invalid context report also the actual context string */ rc = security_sid_to_context_inval(sad->state, sad->ssid, &scontext, &scontext_len); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index a340986aa92e..2dabd58b126a 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1978,7 +1978,7 @@ static inline u32 file_to_av(struct file *file) } /* - * Convert a file to an access vector and include the correct open + * Convert a file to an access vector and include the correct * open permission. */ static inline u32 open_file_to_av(struct file *file) @@ -3271,6 +3271,9 @@ static int selinux_inode_removexattr(struct dentry *dentry, const char *name) return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } + if (!selinux_initialized(&selinux_state)) + return 0; + /* No one is allowed to remove a SELinux security label. You can change the label, but all data must be labeled. */ return -EACCES; @@ -3709,7 +3712,7 @@ static int selinux_mmap_file(struct file *file, unsigned long reqprot, return rc; } - if (selinux_state.checkreqprot) + if (checkreqprot_get(&selinux_state)) prot = reqprot; return file_map_prot_check(file, prot, @@ -3723,7 +3726,7 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); - if (selinux_state.checkreqprot) + if (checkreqprot_get(&selinux_state)) prot = reqprot; if (default_noexec && @@ -4438,7 +4441,7 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) * * If @skb_sid is valid then the user:role:type information from @sk_sid is * combined with the MLS information from @skb_sid in order to create - * @conn_sid. If @skb_sid is not valid then then @conn_sid is simply a copy + * @conn_sid. If @skb_sid is not valid then @conn_sid is simply a copy * of @sk_sid. Returns zero on success, negative values on failure. * */ @@ -5308,7 +5311,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, /* As selinux_sctp_bind_connect() is called by the * SCTP protocol layer, the socket is already locked, - * therefore selinux_netlbl_socket_connect_locked() is + * therefore selinux_netlbl_socket_connect_locked() * is called here. The situations handled are: * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2), * whenever a new IP address is added or when a new @@ -7225,10 +7228,10 @@ static __init int selinux_init(void) memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(&selinux_state, selinux_enforcing_boot); - selinux_state.checkreqprot = selinux_checkreqprot_boot; - selinux_ss_init(&selinux_state.ss); + checkreqprot_set(&selinux_state, selinux_checkreqprot_boot); selinux_avc_init(&selinux_state.avc); mutex_init(&selinux_state.status_lock); + mutex_init(&selinux_state.policy_mutex); /* Set the security state for the initial task. */ cred_init_security(); diff --git a/security/selinux/include/conditional.h b/security/selinux/include/conditional.h index 539ab357707d..b09343346e3f 100644 --- a/security/selinux/include/conditional.h +++ b/security/selinux/include/conditional.h @@ -13,7 +13,7 @@ #include "security.h" -int security_get_bools(struct selinux_state *state, +int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names, int **values); int security_set_bools(struct selinux_state *state, u32 len, int *values); diff --git a/security/selinux/include/policycap.h b/security/selinux/include/policycap.h new file mode 100644 index 000000000000..2ec038efbb03 --- /dev/null +++ b/security/selinux/include/policycap.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SELINUX_POLICYCAP_H_ +#define _SELINUX_POLICYCAP_H_ + +/* Policy capabilities */ +enum { + POLICYDB_CAPABILITY_NETPEER, + POLICYDB_CAPABILITY_OPENPERM, + POLICYDB_CAPABILITY_EXTSOCKCLASS, + POLICYDB_CAPABILITY_ALWAYSNETWORK, + POLICYDB_CAPABILITY_CGROUPSECLABEL, + POLICYDB_CAPABILITY_NNP_NOSUID_TRANSITION, + POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS, + __POLICYDB_CAPABILITY_MAX +}; +#define POLICYDB_CAPABILITY_MAX (__POLICYDB_CAPABILITY_MAX - 1) + +extern const char *selinux_policycap_names[__POLICYDB_CAPABILITY_MAX]; + +#endif /* _SELINUX_POLICYCAP_H_ */ diff --git a/security/selinux/include/policycap_names.h b/security/selinux/include/policycap_names.h new file mode 100644 index 000000000000..b89289f092c9 --- /dev/null +++ b/security/selinux/include/policycap_names.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SELINUX_POLICYCAP_NAMES_H_ +#define _SELINUX_POLICYCAP_NAMES_H_ + +#include "policycap.h" + +/* Policy capability names */ +const char *selinux_policycap_names[__POLICYDB_CAPABILITY_MAX] = { + "network_peer_controls", + "open_perms", + "extended_socket_class", + "always_check_network", + "cgroup_seclabel", + "nnp_nosuid_transition", + "genfs_seclabel_symlinks" +}; + +#endif /* _SELINUX_POLICYCAP_NAMES_H_ */ diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index b0e02cfe3ce1..3cc8bab31ea8 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -13,9 +13,11 @@ #include <linux/dcache.h> #include <linux/magic.h> #include <linux/types.h> +#include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include "flask.h" +#include "policycap.h" #define SECSID_NULL 0x00000000 /* unspecified SID */ #define SECSID_WILD 0xffffffff /* wildcard SID */ @@ -72,21 +74,6 @@ struct netlbl_lsm_secattr; extern int selinux_enabled_boot; -/* Policy capabilities */ -enum { - POLICYDB_CAPABILITY_NETPEER, - POLICYDB_CAPABILITY_OPENPERM, - POLICYDB_CAPABILITY_EXTSOCKCLASS, - POLICYDB_CAPABILITY_ALWAYSNETWORK, - POLICYDB_CAPABILITY_CGROUPSECLABEL, - POLICYDB_CAPABILITY_NNP_NOSUID_TRANSITION, - POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS, - __POLICYDB_CAPABILITY_MAX -}; -#define POLICYDB_CAPABILITY_MAX (__POLICYDB_CAPABILITY_MAX - 1) - -extern const char *selinux_policycap_names[__POLICYDB_CAPABILITY_MAX]; - /* * type_datum properties * available at the kernel policy version >= POLICYDB_VERSION_BOUNDARY @@ -98,7 +85,7 @@ extern const char *selinux_policycap_names[__POLICYDB_CAPABILITY_MAX]; #define POLICYDB_BOUNDS_MAXDEPTH 4 struct selinux_avc; -struct selinux_ss; +struct selinux_policy; struct selinux_state { #ifdef CONFIG_SECURITY_SELINUX_DISABLE @@ -115,10 +102,10 @@ struct selinux_state { struct mutex status_lock; struct selinux_avc *avc; - struct selinux_ss *ss; + struct selinux_policy __rcu *policy; + struct mutex policy_mutex; } __randomize_layout; -void selinux_ss_init(struct selinux_ss **ss); void selinux_avc_init(struct selinux_avc **avc); extern struct selinux_state selinux_state; @@ -156,6 +143,16 @@ static inline void enforcing_set(struct selinux_state *state, bool value) } #endif +static inline bool checkreqprot_get(const struct selinux_state *state) +{ + return READ_ONCE(state->checkreqprot); +} + +static inline void checkreqprot_set(struct selinux_state *state, bool value) +{ + WRITE_ONCE(state->checkreqprot, value); +} + #ifdef CONFIG_SECURITY_SELINUX_DISABLE static inline bool selinux_disabled(struct selinux_state *state) { @@ -177,57 +174,61 @@ static inline bool selinux_policycap_netpeer(void) { struct selinux_state *state = &selinux_state; - return state->policycap[POLICYDB_CAPABILITY_NETPEER]; + return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_NETPEER]); } static inline bool selinux_policycap_openperm(void) { struct selinux_state *state = &selinux_state; - return state->policycap[POLICYDB_CAPABILITY_OPENPERM]; + return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_OPENPERM]); } static inline bool selinux_policycap_extsockclass(void) { struct selinux_state *state = &selinux_state; - return state->policycap[POLICYDB_CAPABILITY_EXTSOCKCLASS]; + return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_EXTSOCKCLASS]); } static inline bool selinux_policycap_alwaysnetwork(void) { struct selinux_state *state = &selinux_state; - return state->policycap[POLICYDB_CAPABILITY_ALWAYSNETWORK]; + return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_ALWAYSNETWORK]); } static inline bool selinux_policycap_cgroupseclabel(void) { struct selinux_state *state = &selinux_state; - return state->policycap[POLICYDB_CAPABILITY_CGROUPSECLABEL]; + return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_CGROUPSECLABEL]); } static inline bool selinux_policycap_nnp_nosuid_transition(void) { struct selinux_state *state = &selinux_state; - return state->policycap[POLICYDB_CAPABILITY_NNP_NOSUID_TRANSITION]; + return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_NNP_NOSUID_TRANSITION]); } static inline bool selinux_policycap_genfs_seclabel_symlinks(void) { struct selinux_state *state = &selinux_state; - return state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]; + return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]); } int security_mls_enabled(struct selinux_state *state); int security_load_policy(struct selinux_state *state, - void *data, size_t len); + void *data, size_t len, + struct selinux_policy **newpolicyp); +void selinux_policy_commit(struct selinux_state *state, + struct selinux_policy *newpolicy); +void selinux_policy_cancel(struct selinux_state *state, + struct selinux_policy *policy); int security_read_policy(struct selinux_state *state, void **data, size_t *len); -size_t security_policydb_len(struct selinux_state *state); int security_policycap_supported(struct selinux_state *state, unsigned int req_cap); @@ -358,9 +359,9 @@ int security_net_peersid_resolve(struct selinux_state *state, u32 xfrm_sid, u32 *peer_sid); -int security_get_classes(struct selinux_state *state, +int security_get_classes(struct selinux_policy *policy, char ***classes, int *nclasses); -int security_get_permissions(struct selinux_state *state, +int security_get_permissions(struct selinux_policy *policy, char *class, char ***perms, int *nperms); int security_get_reject_unknown(struct selinux_state *state); int security_get_allow_unknown(struct selinux_state *state); @@ -380,6 +381,10 @@ int security_genfs_sid(struct selinux_state *state, const char *fstype, char *name, u16 sclass, u32 *sid); +int selinux_policy_genfs_sid(struct selinux_policy *policy, + const char *fstype, char *name, u16 sclass, + u32 *sid); + #ifdef CONFIG_NETLABEL int security_netlbl_secattr_to_sid(struct selinux_state *state, struct netlbl_lsm_secattr *secattr, diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 4781314c2510..4bde570d56a2 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -20,6 +20,7 @@ #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/mutex.h> +#include <linux/namei.h> #include <linux/init.h> #include <linux/string.h> #include <linux/security.h> @@ -74,7 +75,6 @@ struct selinux_fs_info { unsigned long last_class_ino; bool policy_opened; struct dentry *policycap_dir; - struct mutex mutex; unsigned long last_ino; struct selinux_state *state; struct super_block *sb; @@ -88,7 +88,6 @@ static int selinux_fs_info_create(struct super_block *sb) if (!fsi) return -ENOMEM; - mutex_init(&fsi->mutex); fsi->last_ino = SEL_INO_NEXT - 1; fsi->state = &selinux_state; fsi->sb = sb; @@ -117,6 +116,10 @@ static void selinux_fs_info_free(struct super_block *sb) #define SEL_POLICYCAP_INO_OFFSET 0x08000000 #define SEL_INO_MASK 0x00ffffff +#define BOOL_DIR_NAME "booleans" +#define CLASS_DIR_NAME "class" +#define POLICYCAP_DIR_NAME "policy_capabilities" + #define TMPBUFLEN 12 static ssize_t sel_read_enforce(struct file *filp, char __user *buf, size_t count, loff_t *ppos) @@ -346,14 +349,24 @@ static const struct file_operations sel_policyvers_ops = { }; /* declaration for sel_write_load */ -static int sel_make_bools(struct selinux_fs_info *fsi); -static int sel_make_classes(struct selinux_fs_info *fsi); -static int sel_make_policycap(struct selinux_fs_info *fsi); +static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir, + unsigned int *bool_num, char ***bool_pending_names, + unsigned int **bool_pending_values); +static int sel_make_classes(struct selinux_policy *newpolicy, + struct dentry *class_dir, + unsigned long *last_class_ino); /* declaration for sel_make_class_dirs */ static struct dentry *sel_make_dir(struct dentry *dir, const char *name, unsigned long *ino); +/* declaration for sel_make_policy_nodes */ +static struct dentry *sel_make_disconnected_dir(struct super_block *sb, + unsigned long *ino); + +/* declaration for sel_make_policy_nodes */ +static void sel_remove_entries(struct dentry *de); + static ssize_t sel_read_mls(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { @@ -385,7 +398,7 @@ static int sel_open_policy(struct inode *inode, struct file *filp) BUG_ON(filp->private_data); - mutex_lock(&fsi->mutex); + mutex_lock(&fsi->state->policy_mutex); rc = avc_has_perm(&selinux_state, current_sid(), SECINITSID_SECURITY, @@ -402,25 +415,25 @@ static int sel_open_policy(struct inode *inode, struct file *filp) if (!plm) goto err; - if (i_size_read(inode) != security_policydb_len(state)) { - inode_lock(inode); - i_size_write(inode, security_policydb_len(state)); - inode_unlock(inode); - } - rc = security_read_policy(state, &plm->data, &plm->len); if (rc) goto err; + if ((size_t)i_size_read(inode) != plm->len) { + inode_lock(inode); + i_size_write(inode, plm->len); + inode_unlock(inode); + } + fsi->policy_opened = 1; filp->private_data = plm; - mutex_unlock(&fsi->mutex); + mutex_unlock(&fsi->state->policy_mutex); return 0; err: - mutex_unlock(&fsi->mutex); + mutex_unlock(&fsi->state->policy_mutex); if (plm) vfree(plm->data); @@ -508,29 +521,94 @@ static const struct file_operations sel_policy_ops = { .llseek = generic_file_llseek, }; -static int sel_make_policy_nodes(struct selinux_fs_info *fsi) +static void sel_remove_old_bool_data(unsigned int bool_num, char **bool_names, + unsigned int *bool_values) { - int ret; + u32 i; + + /* bool_dir cleanup */ + for (i = 0; i < bool_num; i++) + kfree(bool_names[i]); + kfree(bool_names); + kfree(bool_values); +} - ret = sel_make_bools(fsi); +static int sel_make_policy_nodes(struct selinux_fs_info *fsi, + struct selinux_policy *newpolicy) +{ + int ret = 0; + struct dentry *tmp_parent, *tmp_bool_dir, *tmp_class_dir, *old_dentry; + unsigned int tmp_bool_num, old_bool_num; + char **tmp_bool_names, **old_bool_names; + unsigned int *tmp_bool_values, *old_bool_values; + unsigned long tmp_ino = fsi->last_ino; /* Don't increment last_ino in this function */ + + tmp_parent = sel_make_disconnected_dir(fsi->sb, &tmp_ino); + if (IS_ERR(tmp_parent)) + return PTR_ERR(tmp_parent); + + tmp_ino = fsi->bool_dir->d_inode->i_ino - 1; /* sel_make_dir will increment and set */ + tmp_bool_dir = sel_make_dir(tmp_parent, BOOL_DIR_NAME, &tmp_ino); + if (IS_ERR(tmp_bool_dir)) { + ret = PTR_ERR(tmp_bool_dir); + goto out; + } + + tmp_ino = fsi->class_dir->d_inode->i_ino - 1; /* sel_make_dir will increment and set */ + tmp_class_dir = sel_make_dir(tmp_parent, CLASS_DIR_NAME, &tmp_ino); + if (IS_ERR(tmp_class_dir)) { + ret = PTR_ERR(tmp_class_dir); + goto out; + } + + ret = sel_make_bools(newpolicy, tmp_bool_dir, &tmp_bool_num, + &tmp_bool_names, &tmp_bool_values); if (ret) { pr_err("SELinux: failed to load policy booleans\n"); - return ret; + goto out; } - ret = sel_make_classes(fsi); + ret = sel_make_classes(newpolicy, tmp_class_dir, + &fsi->last_class_ino); if (ret) { pr_err("SELinux: failed to load policy classes\n"); - return ret; + goto out; } - ret = sel_make_policycap(fsi); - if (ret) { - pr_err("SELinux: failed to load policy capabilities\n"); - return ret; - } + /* booleans */ + old_dentry = fsi->bool_dir; + lock_rename(tmp_bool_dir, old_dentry); + d_exchange(tmp_bool_dir, fsi->bool_dir); - return 0; + old_bool_num = fsi->bool_num; + old_bool_names = fsi->bool_pending_names; + old_bool_values = fsi->bool_pending_values; + + fsi->bool_num = tmp_bool_num; + fsi->bool_pending_names = tmp_bool_names; + fsi->bool_pending_values = tmp_bool_values; + + sel_remove_old_bool_data(old_bool_num, old_bool_names, old_bool_values); + + fsi->bool_dir = tmp_bool_dir; + unlock_rename(tmp_bool_dir, old_dentry); + + /* classes */ + old_dentry = fsi->class_dir; + lock_rename(tmp_class_dir, old_dentry); + d_exchange(tmp_class_dir, fsi->class_dir); + fsi->class_dir = tmp_class_dir; + unlock_rename(tmp_class_dir, old_dentry); + +out: + /* Since the other temporary dirs are children of tmp_parent + * this will handle all the cleanup in the case of a failure before + * the swapover + */ + sel_remove_entries(tmp_parent); + dput(tmp_parent); /* d_genocide() only handles the children */ + + return ret; } static ssize_t sel_write_load(struct file *file, const char __user *buf, @@ -538,10 +616,11 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, { struct selinux_fs_info *fsi = file_inode(file)->i_sb->s_fs_info; + struct selinux_policy *newpolicy; ssize_t length; void *data = NULL; - mutex_lock(&fsi->mutex); + mutex_lock(&fsi->state->policy_mutex); length = avc_has_perm(&selinux_state, current_sid(), SECINITSID_SECURITY, @@ -563,15 +642,19 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, if (copy_from_user(data, buf, count) != 0) goto out; - length = security_load_policy(fsi->state, data, count); + length = security_load_policy(fsi->state, data, count, &newpolicy); if (length) { pr_warn_ratelimited("SELinux: failed to load policy\n"); goto out; } - length = sel_make_policy_nodes(fsi); - if (length) + length = sel_make_policy_nodes(fsi, newpolicy); + if (length) { + selinux_policy_cancel(fsi->state, newpolicy); goto out1; + } + + selinux_policy_commit(fsi->state, newpolicy); length = count; @@ -581,7 +664,7 @@ out1: from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); out: - mutex_unlock(&fsi->mutex); + mutex_unlock(&fsi->state->policy_mutex); vfree(data); return length; } @@ -634,7 +717,8 @@ static ssize_t sel_read_checkreqprot(struct file *filp, char __user *buf, char tmpbuf[TMPBUFLEN]; ssize_t length; - length = scnprintf(tmpbuf, TMPBUFLEN, "%u", fsi->state->checkreqprot); + length = scnprintf(tmpbuf, TMPBUFLEN, "%u", + checkreqprot_get(fsi->state)); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } @@ -676,7 +760,7 @@ static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf, comm, current->pid); } - fsi->state->checkreqprot = new_value ? 1 : 0; + checkreqprot_set(fsi->state, (new_value ? 1 : 0)); length = count; out: kfree(page); @@ -1186,7 +1270,7 @@ static ssize_t sel_read_bool(struct file *filep, char __user *buf, unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK; const char *name = filep->f_path.dentry->d_name.name; - mutex_lock(&fsi->mutex); + mutex_lock(&fsi->state->policy_mutex); ret = -EINVAL; if (index >= fsi->bool_num || strcmp(name, @@ -1205,14 +1289,14 @@ static ssize_t sel_read_bool(struct file *filep, char __user *buf, } length = scnprintf(page, PAGE_SIZE, "%d %d", cur_enforcing, fsi->bool_pending_values[index]); - mutex_unlock(&fsi->mutex); + mutex_unlock(&fsi->state->policy_mutex); ret = simple_read_from_buffer(buf, count, ppos, page, length); out_free: free_page((unsigned long)page); return ret; out_unlock: - mutex_unlock(&fsi->mutex); + mutex_unlock(&fsi->state->policy_mutex); goto out_free; } @@ -1237,7 +1321,7 @@ static ssize_t sel_write_bool(struct file *filep, const char __user *buf, if (IS_ERR(page)) return PTR_ERR(page); - mutex_lock(&fsi->mutex); + mutex_lock(&fsi->state->policy_mutex); length = avc_has_perm(&selinux_state, current_sid(), SECINITSID_SECURITY, @@ -1262,7 +1346,7 @@ static ssize_t sel_write_bool(struct file *filep, const char __user *buf, length = count; out: - mutex_unlock(&fsi->mutex); + mutex_unlock(&fsi->state->policy_mutex); kfree(page); return length; } @@ -1293,7 +1377,7 @@ static ssize_t sel_commit_bools_write(struct file *filep, if (IS_ERR(page)) return PTR_ERR(page); - mutex_lock(&fsi->mutex); + mutex_lock(&fsi->state->policy_mutex); length = avc_has_perm(&selinux_state, current_sid(), SECINITSID_SECURITY, @@ -1315,7 +1399,7 @@ static ssize_t sel_commit_bools_write(struct file *filep, length = count; out: - mutex_unlock(&fsi->mutex); + mutex_unlock(&fsi->state->policy_mutex); kfree(page); return length; } @@ -1331,14 +1415,13 @@ static void sel_remove_entries(struct dentry *de) shrink_dcache_parent(de); } -#define BOOL_DIR_NAME "booleans" - -static int sel_make_bools(struct selinux_fs_info *fsi) +static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir, + unsigned int *bool_num, char ***bool_pending_names, + unsigned int **bool_pending_values) { int ret; ssize_t len; struct dentry *dentry = NULL; - struct dentry *dir = fsi->bool_dir; struct inode *inode = NULL; struct inode_security_struct *isec; char **names = NULL, *page; @@ -1346,34 +1429,23 @@ static int sel_make_bools(struct selinux_fs_info *fsi) int *values = NULL; u32 sid; - /* remove any existing files */ - for (i = 0; i < fsi->bool_num; i++) - kfree(fsi->bool_pending_names[i]); - kfree(fsi->bool_pending_names); - kfree(fsi->bool_pending_values); - fsi->bool_num = 0; - fsi->bool_pending_names = NULL; - fsi->bool_pending_values = NULL; - - sel_remove_entries(dir); - ret = -ENOMEM; page = (char *)get_zeroed_page(GFP_KERNEL); if (!page) goto out; - ret = security_get_bools(fsi->state, &num, &names, &values); + ret = security_get_bools(newpolicy, &num, &names, &values); if (ret) goto out; for (i = 0; i < num; i++) { ret = -ENOMEM; - dentry = d_alloc_name(dir, names[i]); + dentry = d_alloc_name(bool_dir, names[i]); if (!dentry) goto out; ret = -ENOMEM; - inode = sel_make_inode(dir->d_sb, S_IFREG | S_IRUGO | S_IWUSR); + inode = sel_make_inode(bool_dir->d_sb, S_IFREG | S_IRUGO | S_IWUSR); if (!inode) { dput(dentry); goto out; @@ -1388,7 +1460,7 @@ static int sel_make_bools(struct selinux_fs_info *fsi) } isec = selinux_inode(inode); - ret = security_genfs_sid(fsi->state, "selinuxfs", page, + ret = selinux_policy_genfs_sid(newpolicy, "selinuxfs", page, SECCLASS_FILE, &sid); if (ret) { pr_warn_ratelimited("SELinux: no sid found, defaulting to security isid for %s\n", @@ -1402,9 +1474,9 @@ static int sel_make_bools(struct selinux_fs_info *fsi) inode->i_ino = i|SEL_BOOL_INO_OFFSET; d_add(dentry, inode); } - fsi->bool_num = num; - fsi->bool_pending_names = names; - fsi->bool_pending_values = values; + *bool_num = num; + *bool_pending_names = names; + *bool_pending_values = values; free_page((unsigned long)page); return 0; @@ -1417,7 +1489,7 @@ out: kfree(names); } kfree(values); - sel_remove_entries(dir); + sel_remove_entries(bool_dir); return ret; } @@ -1791,14 +1863,14 @@ static const struct file_operations sel_policycap_ops = { .llseek = generic_file_llseek, }; -static int sel_make_perm_files(char *objclass, int classvalue, - struct dentry *dir) +static int sel_make_perm_files(struct selinux_policy *newpolicy, + char *objclass, int classvalue, + struct dentry *dir) { - struct selinux_fs_info *fsi = dir->d_sb->s_fs_info; int i, rc, nperms; char **perms; - rc = security_get_permissions(fsi->state, objclass, &perms, &nperms); + rc = security_get_permissions(newpolicy, objclass, &perms, &nperms); if (rc) return rc; @@ -1831,8 +1903,9 @@ out: return rc; } -static int sel_make_class_dir_entries(char *classname, int index, - struct dentry *dir) +static int sel_make_class_dir_entries(struct selinux_policy *newpolicy, + char *classname, int index, + struct dentry *dir) { struct super_block *sb = dir->d_sb; struct selinux_fs_info *fsi = sb->s_fs_info; @@ -1858,39 +1931,38 @@ static int sel_make_class_dir_entries(char *classname, int index, if (IS_ERR(dentry)) return PTR_ERR(dentry); - rc = sel_make_perm_files(classname, index, dentry); + rc = sel_make_perm_files(newpolicy, classname, index, dentry); return rc; } -static int sel_make_classes(struct selinux_fs_info *fsi) +static int sel_make_classes(struct selinux_policy *newpolicy, + struct dentry *class_dir, + unsigned long *last_class_ino) { int rc, nclasses, i; char **classes; - /* delete any existing entries */ - sel_remove_entries(fsi->class_dir); - - rc = security_get_classes(fsi->state, &classes, &nclasses); + rc = security_get_classes(newpolicy, &classes, &nclasses); if (rc) return rc; /* +2 since classes are 1-indexed */ - fsi->last_class_ino = sel_class_to_ino(nclasses + 2); + *last_class_ino = sel_class_to_ino(nclasses + 2); for (i = 0; i < nclasses; i++) { struct dentry *class_name_dir; - class_name_dir = sel_make_dir(fsi->class_dir, classes[i], - &fsi->last_class_ino); + class_name_dir = sel_make_dir(class_dir, classes[i], + last_class_ino); if (IS_ERR(class_name_dir)) { rc = PTR_ERR(class_name_dir); goto out; } /* i+1 since class values are 1-indexed */ - rc = sel_make_class_dir_entries(classes[i], i + 1, + rc = sel_make_class_dir_entries(newpolicy, classes[i], i + 1, class_name_dir); if (rc) goto out; @@ -1909,8 +1981,6 @@ static int sel_make_policycap(struct selinux_fs_info *fsi) struct dentry *dentry = NULL; struct inode *inode = NULL; - sel_remove_entries(fsi->policycap_dir); - for (iter = 0; iter <= POLICYDB_CAPABILITY_MAX; iter++) { if (iter < ARRAY_SIZE(selinux_policycap_names)) dentry = d_alloc_name(fsi->policycap_dir, @@ -1962,6 +2032,22 @@ static struct dentry *sel_make_dir(struct dentry *dir, const char *name, return dentry; } +static struct dentry *sel_make_disconnected_dir(struct super_block *sb, + unsigned long *ino) +{ + struct inode *inode = sel_make_inode(sb, S_IFDIR | S_IRUGO | S_IXUGO); + + if (!inode) + return ERR_PTR(-ENOMEM); + + inode->i_op = &simple_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + inode->i_ino = ++(*ino); + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + return d_obtain_alias(inode); +} + #define NULL_FILE_NAME "null" static int sel_fill_super(struct super_block *sb, struct fs_context *fc) @@ -2060,14 +2146,14 @@ static int sel_fill_super(struct super_block *sb, struct fs_context *fc) if (ret) goto err; - fsi->class_dir = sel_make_dir(sb->s_root, "class", &fsi->last_ino); + fsi->class_dir = sel_make_dir(sb->s_root, CLASS_DIR_NAME, &fsi->last_ino); if (IS_ERR(fsi->class_dir)) { ret = PTR_ERR(fsi->class_dir); fsi->class_dir = NULL; goto err; } - fsi->policycap_dir = sel_make_dir(sb->s_root, "policy_capabilities", + fsi->policycap_dir = sel_make_dir(sb->s_root, POLICYCAP_DIR_NAME, &fsi->last_ino); if (IS_ERR(fsi->policycap_dir)) { ret = PTR_ERR(fsi->policycap_dir); @@ -2075,9 +2161,12 @@ static int sel_fill_super(struct super_block *sb, struct fs_context *fc) goto err; } - ret = sel_make_policy_nodes(fsi); - if (ret) + ret = sel_make_policycap(fsi); + if (ret) { + pr_err("SELinux: failed to load policy capabilities\n"); goto err; + } + return 0; err: pr_err("SELinux: %s: failed while creating inodes\n", diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c index 01b300a4a882..0172d87e2b9a 100644 --- a/security/selinux/ss/avtab.c +++ b/security/selinux/ss/avtab.c @@ -301,7 +301,6 @@ void avtab_destroy(struct avtab *h) void avtab_init(struct avtab *h) { - kvfree(h->htable); h->htable = NULL; h->nel = 0; } @@ -340,6 +339,54 @@ int avtab_alloc(struct avtab *h, u32 nrules) return 0; } +int avtab_duplicate(struct avtab *new, struct avtab *orig) +{ + int i; + struct avtab_node *node, *tmp, *tail; + + memset(new, 0, sizeof(*new)); + + new->htable = kvcalloc(orig->nslot, sizeof(void *), GFP_KERNEL); + if (!new->htable) + return -ENOMEM; + new->nslot = orig->nslot; + new->mask = orig->mask; + + for (i = 0; i < orig->nslot; i++) { + tail = NULL; + for (node = orig->htable[i]; node; node = node->next) { + tmp = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); + if (!tmp) + goto error; + tmp->key = node->key; + if (tmp->key.specified & AVTAB_XPERMS) { + tmp->datum.u.xperms = + kmem_cache_zalloc(avtab_xperms_cachep, + GFP_KERNEL); + if (!tmp->datum.u.xperms) { + kmem_cache_free(avtab_node_cachep, tmp); + goto error; + } + tmp->datum.u.xperms = node->datum.u.xperms; + } else + tmp->datum.u.data = node->datum.u.data; + + if (tail) + tail->next = tmp; + else + new->htable[i] = tmp; + + tail = tmp; + new->nel++; + } + } + + return 0; +error: + avtab_destroy(new); + return -ENOMEM; +} + void avtab_hash_eval(struct avtab *h, char *tag) { int i, chain_len, slots_used, max_chain_len; diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h index 5fdcb6696bcc..4c4445ca9118 100644 --- a/security/selinux/ss/avtab.h +++ b/security/selinux/ss/avtab.h @@ -89,6 +89,7 @@ struct avtab { void avtab_init(struct avtab *h); int avtab_alloc(struct avtab *, u32); +int avtab_duplicate(struct avtab *new, struct avtab *orig); struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *k); void avtab_destroy(struct avtab *h); void avtab_hash_eval(struct avtab *h, char *tag); diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 5a47258c1d77..0b32f3ab025e 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -600,3 +600,158 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key, services_compute_xperms_drivers(xperms, node); } } + +static int cond_dup_av_list(struct cond_av_list *new, + struct cond_av_list *orig, + struct avtab *avtab) +{ + struct avtab_node *avnode; + u32 i; + + memset(new, 0, sizeof(*new)); + + new->nodes = kcalloc(orig->len, sizeof(*new->nodes), GFP_KERNEL); + if (!new->nodes) + return -ENOMEM; + + for (i = 0; i < orig->len; i++) { + avnode = avtab_search_node(avtab, &orig->nodes[i]->key); + if (WARN_ON(!avnode)) + return -EINVAL; + new->nodes[i] = avnode; + new->len++; + } + + return 0; +} + +static int duplicate_policydb_cond_list(struct policydb *newp, + struct policydb *origp) +{ + int rc, i, j; + + rc = avtab_duplicate(&newp->te_cond_avtab, &origp->te_cond_avtab); + if (rc) + return rc; + + newp->cond_list_len = 0; + newp->cond_list = kcalloc(origp->cond_list_len, + sizeof(*newp->cond_list), + GFP_KERNEL); + if (!newp->cond_list) + goto error; + + for (i = 0; i < origp->cond_list_len; i++) { + struct cond_node *newn = &newp->cond_list[i]; + struct cond_node *orign = &origp->cond_list[i]; + + newp->cond_list_len++; + + newn->cur_state = orign->cur_state; + newn->expr.nodes = kcalloc(orign->expr.len, + sizeof(*newn->expr.nodes), GFP_KERNEL); + if (!newn->expr.nodes) + goto error; + for (j = 0; j < orign->expr.len; j++) + newn->expr.nodes[j] = orign->expr.nodes[j]; + newn->expr.len = orign->expr.len; + + rc = cond_dup_av_list(&newn->true_list, &orign->true_list, + &newp->te_cond_avtab); + if (rc) + goto error; + + rc = cond_dup_av_list(&newn->false_list, &orign->false_list, + &newp->te_cond_avtab); + if (rc) + goto error; + } + + return 0; + +error: + avtab_destroy(&newp->te_cond_avtab); + cond_list_destroy(newp); + return -ENOMEM; +} + +static int cond_bools_destroy(void *key, void *datum, void *args) +{ + /* key was not copied so no need to free here */ + kfree(datum); + return 0; +} + +static int cond_bools_copy(struct hashtab_node *new, struct hashtab_node *orig, void *args) +{ + struct cond_bool_datum *datum; + + datum = kmemdup(orig->datum, sizeof(struct cond_bool_datum), + GFP_KERNEL); + if (!datum) + return -ENOMEM; + + new->key = orig->key; /* No need to copy, never modified */ + new->datum = datum; + return 0; +} + +static int cond_bools_index(void *key, void *datum, void *args) +{ + struct cond_bool_datum *booldatum, **cond_bool_array; + + booldatum = datum; + cond_bool_array = args; + cond_bool_array[booldatum->value - 1] = booldatum; + + return 0; +} + +static int duplicate_policydb_bools(struct policydb *newdb, + struct policydb *orig) +{ + struct cond_bool_datum **cond_bool_array; + int rc; + + cond_bool_array = kmalloc_array(orig->p_bools.nprim, + sizeof(*orig->bool_val_to_struct), + GFP_KERNEL); + if (!cond_bool_array) + return -ENOMEM; + + rc = hashtab_duplicate(&newdb->p_bools.table, &orig->p_bools.table, + cond_bools_copy, cond_bools_destroy, NULL); + if (rc) { + kfree(cond_bool_array); + return -ENOMEM; + } + + hashtab_map(&newdb->p_bools.table, cond_bools_index, cond_bool_array); + newdb->bool_val_to_struct = cond_bool_array; + + newdb->p_bools.nprim = orig->p_bools.nprim; + + return 0; +} + +void cond_policydb_destroy_dup(struct policydb *p) +{ + hashtab_map(&p->p_bools.table, cond_bools_destroy, NULL); + hashtab_destroy(&p->p_bools.table); + cond_policydb_destroy(p); +} + +int cond_policydb_dup(struct policydb *new, struct policydb *orig) +{ + cond_policydb_init(new); + + if (duplicate_policydb_bools(new, orig)) + return -ENOMEM; + + if (duplicate_policydb_cond_list(new, orig)) { + cond_policydb_destroy_dup(new); + return -ENOMEM; + } + + return 0; +} diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h index 79e7e03db859..e47ec6ddeaf6 100644 --- a/security/selinux/ss/conditional.h +++ b/security/selinux/ss/conditional.h @@ -79,5 +79,7 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key, void cond_compute_xperms(struct avtab *ctab, struct avtab_key *key, struct extended_perms_decision *xpermd); void evaluate_cond_nodes(struct policydb *p); +void cond_policydb_destroy_dup(struct policydb *p); +int cond_policydb_dup(struct policydb *new, struct policydb *orig); #endif /* _CONDITIONAL_H_ */ diff --git a/security/selinux/ss/hashtab.c b/security/selinux/ss/hashtab.c index d9287bb4bfeb..dab8c25c739b 100644 --- a/security/selinux/ss/hashtab.c +++ b/security/selinux/ss/hashtab.c @@ -122,6 +122,59 @@ void hashtab_stat(struct hashtab *h, struct hashtab_info *info) info->max_chain_len = max_chain_len; } +int hashtab_duplicate(struct hashtab *new, struct hashtab *orig, + int (*copy)(struct hashtab_node *new, + struct hashtab_node *orig, void *args), + int (*destroy)(void *k, void *d, void *args), + void *args) +{ + struct hashtab_node *cur, *tmp, *tail; + int i, rc; + + memset(new, 0, sizeof(*new)); + + new->htable = kcalloc(orig->size, sizeof(*new->htable), GFP_KERNEL); + if (!new->htable) + return -ENOMEM; + + new->size = orig->size; + + for (i = 0; i < orig->size; i++) { + tail = NULL; + for (cur = orig->htable[i]; cur; cur = cur->next) { + tmp = kmem_cache_zalloc(hashtab_node_cachep, + GFP_KERNEL); + if (!tmp) + goto error; + rc = copy(tmp, cur, args); + if (rc) { + kmem_cache_free(hashtab_node_cachep, tmp); + goto error; + } + tmp->next = NULL; + if (!tail) + new->htable[i] = tmp; + else + tail->next = tmp; + tail = tmp; + new->nel++; + } + } + + return 0; + + error: + for (i = 0; i < new->size; i++) { + for (cur = new->htable[i]; cur; cur = tmp) { + tmp = cur->next; + destroy(cur->key, cur->datum, args); + kmem_cache_free(hashtab_node_cachep, cur); + } + } + kmem_cache_free(hashtab_node_cachep, new); + return -ENOMEM; +} + void __init hashtab_cache_init(void) { hashtab_node_cachep = kmem_cache_create("hashtab_node", diff --git a/security/selinux/ss/hashtab.h b/security/selinux/ss/hashtab.h index 3c952f0f01f9..043a773bf0b7 100644 --- a/security/selinux/ss/hashtab.h +++ b/security/selinux/ss/hashtab.h @@ -136,6 +136,12 @@ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); +int hashtab_duplicate(struct hashtab *new, struct hashtab *orig, + int (*copy)(struct hashtab_node *new, + struct hashtab_node *orig, void *args), + int (*destroy)(void *k, void *d, void *args), + void *args); + /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 1caf4e603309..9704c8a32303 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -64,25 +64,7 @@ #include "xfrm.h" #include "ebitmap.h" #include "audit.h" - -/* Policy capability names */ -const char *selinux_policycap_names[__POLICYDB_CAPABILITY_MAX] = { - "network_peer_controls", - "open_perms", - "extended_socket_class", - "always_check_network", - "cgroup_seclabel", - "nnp_nosuid_transition", - "genfs_seclabel_symlinks" -}; - -static struct selinux_ss selinux_ss; - -void selinux_ss_init(struct selinux_ss **ss) -{ - rwlock_init(&selinux_ss.policy_rwlock); - *ss = &selinux_ss; -} +#include "policycap_names.h" /* Forward declaration. */ static int context_struct_to_string(struct policydb *policydb, @@ -248,9 +230,17 @@ static void map_decision(struct selinux_map *map, int security_mls_enabled(struct selinux_state *state) { - struct policydb *p = &state->ss->policydb; + int mls_enabled; + struct selinux_policy *policy; - return p->mls_enabled; + if (!selinux_initialized(state)) + return 0; + + rcu_read_lock(); + policy = rcu_dereference(state->policy); + mls_enabled = policy->policydb.mls_enabled; + rcu_read_unlock(); + return mls_enabled; } /* @@ -721,13 +711,14 @@ static void context_struct_compute_av(struct policydb *policydb, } static int security_validtrans_handle_fail(struct selinux_state *state, - struct sidtab_entry *oentry, - struct sidtab_entry *nentry, - struct sidtab_entry *tentry, - u16 tclass) -{ - struct policydb *p = &state->ss->policydb; - struct sidtab *sidtab = state->ss->sidtab; + struct selinux_policy *policy, + struct sidtab_entry *oentry, + struct sidtab_entry *nentry, + struct sidtab_entry *tentry, + u16 tclass) +{ + struct policydb *p = &policy->policydb; + struct sidtab *sidtab = policy->sidtab; char *o = NULL, *n = NULL, *t = NULL; u32 olen, nlen, tlen; @@ -755,6 +746,7 @@ static int security_compute_validatetrans(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 orig_tclass, bool user) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *oentry; @@ -769,13 +761,14 @@ static int security_compute_validatetrans(struct selinux_state *state, if (!selinux_initialized(state)) return 0; - read_lock(&state->ss->policy_rwlock); + rcu_read_lock(); - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; if (!user) - tclass = unmap_class(&state->ss->map, orig_tclass); + tclass = unmap_class(&policy->map, orig_tclass); else tclass = orig_tclass; @@ -818,17 +811,18 @@ static int security_compute_validatetrans(struct selinux_state *state, rc = -EPERM; else rc = security_validtrans_handle_fail(state, - oentry, - nentry, - tentry, - tclass); + policy, + oentry, + nentry, + tentry, + tclass); goto out; } constraint = constraint->next; } out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -860,6 +854,7 @@ int security_validate_transition(struct selinux_state *state, int security_bounded_transition(struct selinux_state *state, u32 old_sid, u32 new_sid) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *old_entry, *new_entry; @@ -870,10 +865,10 @@ int security_bounded_transition(struct selinux_state *state, if (!selinux_initialized(state)) return 0; - read_lock(&state->ss->policy_rwlock); - - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; rc = -EINVAL; old_entry = sidtab_search_entry(sidtab, old_sid); @@ -934,17 +929,20 @@ int security_bounded_transition(struct selinux_state *state, kfree(old_name); } out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } -static void avd_init(struct selinux_state *state, struct av_decision *avd) +static void avd_init(struct selinux_policy *policy, struct av_decision *avd) { avd->allowed = 0; avd->auditallow = 0; avd->auditdeny = 0xffffffff; - avd->seqno = state->ss->latest_granting; + if (policy) + avd->seqno = policy->latest_granting; + else + avd->seqno = 0; avd->flags = 0; } @@ -1009,6 +1007,7 @@ void security_compute_xperms_decision(struct selinux_state *state, u8 driver, struct extended_perms_decision *xpermd) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; @@ -1025,12 +1024,13 @@ void security_compute_xperms_decision(struct selinux_state *state, memset(xpermd->auditallow->p, 0, sizeof(xpermd->auditallow->p)); memset(xpermd->dontaudit->p, 0, sizeof(xpermd->dontaudit->p)); - read_lock(&state->ss->policy_rwlock); + rcu_read_lock(); if (!selinux_initialized(state)) goto allow; - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { @@ -1046,7 +1046,7 @@ void security_compute_xperms_decision(struct selinux_state *state, goto out; } - tclass = unmap_class(&state->ss->map, orig_tclass); + tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; @@ -1078,7 +1078,7 @@ void security_compute_xperms_decision(struct selinux_state *state, } } out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return; allow: memset(xpermd->allowed->p, 0xff, sizeof(xpermd->allowed->p)); @@ -1103,19 +1103,21 @@ void security_compute_av(struct selinux_state *state, struct av_decision *avd, struct extended_perms *xperms) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; struct context *scontext = NULL, *tcontext = NULL; - read_lock(&state->ss->policy_rwlock); - avd_init(state, avd); + rcu_read_lock(); + policy = rcu_dereference(state->policy); + avd_init(policy, avd); xperms->len = 0; if (!selinux_initialized(state)) goto allow; - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + policydb = &policy->policydb; + sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { @@ -1135,7 +1137,7 @@ void security_compute_av(struct selinux_state *state, goto out; } - tclass = unmap_class(&state->ss->map, orig_tclass); + tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; @@ -1143,10 +1145,10 @@ void security_compute_av(struct selinux_state *state, } context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, xperms); - map_decision(&state->ss->map, orig_tclass, avd, + map_decision(&policy->map, orig_tclass, avd, policydb->allow_unknown); out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return; allow: avd->allowed = 0xffffffff; @@ -1159,17 +1161,19 @@ void security_compute_av_user(struct selinux_state *state, u16 tclass, struct av_decision *avd) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *scontext = NULL, *tcontext = NULL; - read_lock(&state->ss->policy_rwlock); - avd_init(state, avd); + rcu_read_lock(); + policy = rcu_dereference(state->policy); + avd_init(policy, avd); if (!selinux_initialized(state)) goto allow; - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + policydb = &policy->policydb; + sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { @@ -1198,7 +1202,7 @@ void security_compute_av_user(struct selinux_state *state, context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, NULL); out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return; allow: avd->allowed = 0xffffffff; @@ -1283,6 +1287,7 @@ static int sidtab_entry_to_string(struct policydb *p, int security_sidtab_hash_stats(struct selinux_state *state, char *page) { + struct selinux_policy *policy; int rc; if (!selinux_initialized(state)) { @@ -1291,9 +1296,10 @@ int security_sidtab_hash_stats(struct selinux_state *state, char *page) return -EINVAL; } - read_lock(&state->ss->policy_rwlock); - rc = sidtab_hash_stats(state->ss->sidtab, page); - read_unlock(&state->ss->policy_rwlock); + rcu_read_lock(); + policy = rcu_dereference(state->policy); + rc = sidtab_hash_stats(policy->sidtab, page); + rcu_read_unlock(); return rc; } @@ -1310,6 +1316,7 @@ static int security_sid_to_context_core(struct selinux_state *state, u32 *scontext_len, int force, int only_invalid) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *entry; @@ -1339,9 +1346,10 @@ static int security_sid_to_context_core(struct selinux_state *state, "load_policy on unknown SID %d\n", __func__, sid); return -EINVAL; } - read_lock(&state->ss->policy_rwlock); - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; if (force) entry = sidtab_search_entry_force(sidtab, sid); @@ -1360,7 +1368,7 @@ static int security_sid_to_context_core(struct selinux_state *state, scontext_len); out_unlock: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -1495,6 +1503,7 @@ static int security_context_to_sid_core(struct selinux_state *state, u32 *sid, u32 def_sid, gfp_t gfp_flags, int force) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; char *scontext2, *str = NULL; @@ -1533,9 +1542,10 @@ static int security_context_to_sid_core(struct selinux_state *state, if (!str) goto out; } - read_lock(&state->ss->policy_rwlock); - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; rc = string_to_context_struct(policydb, sidtab, scontext2, &context, def_sid); if (rc == -EINVAL && force) { @@ -1547,7 +1557,7 @@ static int security_context_to_sid_core(struct selinux_state *state, rc = sidtab_context_to_sid(sidtab, &context, sid); context_destroy(&context); out_unlock: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); out: kfree(scontext2); kfree(str); @@ -1617,13 +1627,14 @@ int security_context_to_sid_force(struct selinux_state *state, static int compute_sid_handle_invalid_context( struct selinux_state *state, + struct selinux_policy *policy, struct sidtab_entry *sentry, struct sidtab_entry *tentry, u16 tclass, struct context *newcontext) { - struct policydb *policydb = &state->ss->policydb; - struct sidtab *sidtab = state->ss->sidtab; + struct policydb *policydb = &policy->policydb; + struct sidtab *sidtab = policy->sidtab; char *s = NULL, *t = NULL, *n = NULL; u32 slen, tlen, nlen; struct audit_buffer *ab; @@ -1690,6 +1701,7 @@ static int security_compute_sid(struct selinux_state *state, u32 *out_sid, bool kern) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct class_datum *cladatum = NULL; @@ -1716,19 +1728,21 @@ static int security_compute_sid(struct selinux_state *state, context_init(&newcontext); - read_lock(&state->ss->policy_rwlock); + rcu_read_lock(); + + policy = rcu_dereference(state->policy); if (kern) { - tclass = unmap_class(&state->ss->map, orig_tclass); + tclass = unmap_class(&policy->map, orig_tclass); sock = security_is_socket_class(orig_tclass); } else { tclass = orig_tclass; - sock = security_is_socket_class(map_class(&state->ss->map, + sock = security_is_socket_class(map_class(&policy->map, tclass)); } - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + policydb = &policy->policydb; + sidtab = policy->sidtab; sentry = sidtab_search_entry(sidtab, ssid); if (!sentry) { @@ -1848,15 +1862,16 @@ static int security_compute_sid(struct selinux_state *state, /* Check the validity of the context. */ if (!policydb_context_isvalid(policydb, &newcontext)) { - rc = compute_sid_handle_invalid_context(state, sentry, tentry, - tclass, &newcontext); + rc = compute_sid_handle_invalid_context(state, policy, sentry, + tentry, tclass, + &newcontext); if (rc) goto out_unlock; } /* Obtain the sid for the context. */ rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid); out_unlock: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); context_destroy(&newcontext); out: return rc; @@ -1943,9 +1958,9 @@ int security_change_sid(struct selinux_state *state, static inline int convert_context_handle_invalid_context( struct selinux_state *state, + struct policydb *policydb, struct context *context) { - struct policydb *policydb = &state->ss->policydb; char *s; u32 len; @@ -2077,7 +2092,9 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) /* Check the validity of the new context. */ if (!policydb_context_isvalid(args->newp, newc)) { - rc = convert_context_handle_invalid_context(args->state, oldc); + rc = convert_context_handle_invalid_context(args->state, + args->oldp, + oldc); if (rc) goto bad; } @@ -2096,14 +2113,18 @@ bad: return 0; } -static void security_load_policycaps(struct selinux_state *state) +static void security_load_policycaps(struct selinux_state *state, + struct selinux_policy *policy) { - struct policydb *p = &state->ss->policydb; + struct policydb *p; unsigned int i; struct ebitmap_node *node; + p = &policy->policydb; + for (i = 0; i < ARRAY_SIZE(state->policycap); i++) - state->policycap[i] = ebitmap_get_bit(&p->policycaps, i); + WRITE_ONCE(state->policycap[i], + ebitmap_get_bit(&p->policycaps, i)); for (i = 0; i < ARRAY_SIZE(selinux_policycap_names); i++) pr_info("SELinux: policy capability %s=%d\n", @@ -2117,8 +2138,97 @@ static void security_load_policycaps(struct selinux_state *state) } } -static int security_preserve_bools(struct selinux_state *state, - struct policydb *newpolicydb); +static int security_preserve_bools(struct selinux_policy *oldpolicy, + struct selinux_policy *newpolicy); + +static void selinux_policy_free(struct selinux_policy *policy) +{ + if (!policy) + return; + + sidtab_destroy(policy->sidtab); + kfree(policy->map.mapping); + policydb_destroy(&policy->policydb); + kfree(policy->sidtab); + kfree(policy); +} + +static void selinux_policy_cond_free(struct selinux_policy *policy) +{ + cond_policydb_destroy_dup(&policy->policydb); + kfree(policy); +} + +void selinux_policy_cancel(struct selinux_state *state, + struct selinux_policy *policy) +{ + struct selinux_policy *oldpolicy; + + oldpolicy = rcu_dereference_protected(state->policy, + lockdep_is_held(&state->policy_mutex)); + + sidtab_cancel_convert(oldpolicy->sidtab); + selinux_policy_free(policy); +} + +static void selinux_notify_policy_change(struct selinux_state *state, + u32 seqno) +{ + /* Flush external caches and notify userspace of policy load */ + avc_ss_reset(state->avc, seqno); + selnl_notify_policyload(seqno); + selinux_status_update_policyload(state, seqno); + selinux_netlbl_cache_invalidate(); + selinux_xfrm_notify_policyload(); +} + +void selinux_policy_commit(struct selinux_state *state, + struct selinux_policy *newpolicy) +{ + struct selinux_policy *oldpolicy; + u32 seqno; + + oldpolicy = rcu_dereference_protected(state->policy, + lockdep_is_held(&state->policy_mutex)); + + /* If switching between different policy types, log MLS status */ + if (oldpolicy) { + if (oldpolicy->policydb.mls_enabled && !newpolicy->policydb.mls_enabled) + pr_info("SELinux: Disabling MLS support...\n"); + else if (!oldpolicy->policydb.mls_enabled && newpolicy->policydb.mls_enabled) + pr_info("SELinux: Enabling MLS support...\n"); + } + + /* Set latest granting seqno for new policy. */ + if (oldpolicy) + newpolicy->latest_granting = oldpolicy->latest_granting + 1; + else + newpolicy->latest_granting = 1; + seqno = newpolicy->latest_granting; + + /* Install the new policy. */ + rcu_assign_pointer(state->policy, newpolicy); + + /* Load the policycaps from the new policy */ + security_load_policycaps(state, newpolicy); + + if (!selinux_initialized(state)) { + /* + * After first policy load, the security server is + * marked as initialized and ready to handle requests and + * any objects created prior to policy load are then labeled. + */ + selinux_mark_initialized(state); + selinux_complete_init(); + } + + /* Free the old policy */ + synchronize_rcu(); + selinux_policy_free(oldpolicy); + + /* Notify others of the policy change */ + selinux_notify_policy_change(state, seqno); +} /** * security_load_policy - Load a security policy configuration. @@ -2130,173 +2240,95 @@ static int security_preserve_bools(struct selinux_state *state, * This function will flush the access vector cache after * loading the new policy. */ -int security_load_policy(struct selinux_state *state, void *data, size_t len) +int security_load_policy(struct selinux_state *state, void *data, size_t len, + struct selinux_policy **newpolicyp) { - struct policydb *policydb; - struct sidtab *oldsidtab, *newsidtab; - struct policydb *oldpolicydb, *newpolicydb; - struct selinux_mapping *oldmapping; - struct selinux_map newmap; + struct selinux_policy *newpolicy, *oldpolicy; struct sidtab_convert_params convert_params; struct convert_context_args args; - u32 seqno; int rc = 0; struct policy_file file = { data, len }, *fp = &file; - policydb = &state->ss->policydb; - - newsidtab = kmalloc(sizeof(*newsidtab), GFP_KERNEL); - if (!newsidtab) + newpolicy = kzalloc(sizeof(*newpolicy), GFP_KERNEL); + if (!newpolicy) return -ENOMEM; - if (!selinux_initialized(state)) { - rc = policydb_read(policydb, fp); - if (rc) { - kfree(newsidtab); - return rc; - } - - policydb->len = len; - rc = selinux_set_mapping(policydb, secclass_map, - &state->ss->map); - if (rc) { - kfree(newsidtab); - policydb_destroy(policydb); - return rc; - } - - rc = policydb_load_isids(policydb, newsidtab); - if (rc) { - kfree(newsidtab); - policydb_destroy(policydb); - return rc; - } - - state->ss->sidtab = newsidtab; - security_load_policycaps(state); - selinux_mark_initialized(state); - seqno = ++state->ss->latest_granting; - selinux_complete_init(); - avc_ss_reset(state->avc, seqno); - selnl_notify_policyload(seqno); - selinux_status_update_policyload(state, seqno); - selinux_netlbl_cache_invalidate(); - selinux_xfrm_notify_policyload(); - return 0; + newpolicy->sidtab = kzalloc(sizeof(*newpolicy->sidtab), GFP_KERNEL); + if (!newpolicy->sidtab) { + rc = -ENOMEM; + goto err_policy; } - oldpolicydb = kcalloc(2, sizeof(*oldpolicydb), GFP_KERNEL); - if (!oldpolicydb) { - kfree(newsidtab); - return -ENOMEM; - } - newpolicydb = oldpolicydb + 1; + rc = policydb_read(&newpolicy->policydb, fp); + if (rc) + goto err_sidtab; + + newpolicy->policydb.len = len; + rc = selinux_set_mapping(&newpolicy->policydb, secclass_map, + &newpolicy->map); + if (rc) + goto err_policydb; - rc = policydb_read(newpolicydb, fp); + rc = policydb_load_isids(&newpolicy->policydb, newpolicy->sidtab); if (rc) { - kfree(newsidtab); - goto out; + pr_err("SELinux: unable to load the initial SIDs\n"); + goto err_mapping; } - newpolicydb->len = len; - /* If switching between different policy types, log MLS status */ - if (policydb->mls_enabled && !newpolicydb->mls_enabled) - pr_info("SELinux: Disabling MLS support...\n"); - else if (!policydb->mls_enabled && newpolicydb->mls_enabled) - pr_info("SELinux: Enabling MLS support...\n"); - rc = policydb_load_isids(newpolicydb, newsidtab); - if (rc) { - pr_err("SELinux: unable to load the initial SIDs\n"); - policydb_destroy(newpolicydb); - kfree(newsidtab); - goto out; + if (!selinux_initialized(state)) { + /* First policy load, so no need to preserve state from old policy */ + *newpolicyp = newpolicy; + return 0; } - rc = selinux_set_mapping(newpolicydb, secclass_map, &newmap); - if (rc) - goto err; + oldpolicy = rcu_dereference_protected(state->policy, + lockdep_is_held(&state->policy_mutex)); - rc = security_preserve_bools(state, newpolicydb); + /* Preserve active boolean values from the old policy */ + rc = security_preserve_bools(oldpolicy, newpolicy); if (rc) { pr_err("SELinux: unable to preserve booleans\n"); - goto err; + goto err_free_isids; } - oldsidtab = state->ss->sidtab; - /* * Convert the internal representations of contexts * in the new SID table. */ args.state = state; - args.oldp = policydb; - args.newp = newpolicydb; + args.oldp = &oldpolicy->policydb; + args.newp = &newpolicy->policydb; convert_params.func = convert_context; convert_params.args = &args; - convert_params.target = newsidtab; + convert_params.target = newpolicy->sidtab; - rc = sidtab_convert(oldsidtab, &convert_params); + rc = sidtab_convert(oldpolicy->sidtab, &convert_params); if (rc) { pr_err("SELinux: unable to convert the internal" " representation of contexts in the new SID" " table\n"); - goto err; + goto err_free_isids; } - /* Save the old policydb and SID table to free later. */ - memcpy(oldpolicydb, policydb, sizeof(*policydb)); - - /* Install the new policydb and SID table. */ - write_lock_irq(&state->ss->policy_rwlock); - memcpy(policydb, newpolicydb, sizeof(*policydb)); - state->ss->sidtab = newsidtab; - security_load_policycaps(state); - oldmapping = state->ss->map.mapping; - state->ss->map.mapping = newmap.mapping; - state->ss->map.size = newmap.size; - seqno = ++state->ss->latest_granting; - write_unlock_irq(&state->ss->policy_rwlock); - - /* Free the old policydb and SID table. */ - policydb_destroy(oldpolicydb); - sidtab_destroy(oldsidtab); - kfree(oldsidtab); - kfree(oldmapping); - - avc_ss_reset(state->avc, seqno); - selnl_notify_policyload(seqno); - selinux_status_update_policyload(state, seqno); - selinux_netlbl_cache_invalidate(); - selinux_xfrm_notify_policyload(); - - rc = 0; - goto out; + *newpolicyp = newpolicy; + return 0; -err: - kfree(newmap.mapping); - sidtab_destroy(newsidtab); - kfree(newsidtab); - policydb_destroy(newpolicydb); +err_free_isids: + sidtab_destroy(newpolicy->sidtab); +err_mapping: + kfree(newpolicy->map.mapping); +err_policydb: + policydb_destroy(&newpolicy->policydb); +err_sidtab: + kfree(newpolicy->sidtab); +err_policy: + kfree(newpolicy); -out: - kfree(oldpolicydb); return rc; } -size_t security_policydb_len(struct selinux_state *state) -{ - struct policydb *p = &state->ss->policydb; - size_t len; - - read_lock(&state->ss->policy_rwlock); - len = p->len; - read_unlock(&state->ss->policy_rwlock); - - return len; -} - /** * security_port_sid - Obtain the SID for a port. * @protocol: protocol number @@ -2306,15 +2338,21 @@ size_t security_policydb_len(struct selinux_state *state) int security_port_sid(struct selinux_state *state, u8 protocol, u16 port, u32 *out_sid) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc = 0; - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) { + *out_sid = SECINITSID_PORT; + return 0; + } - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; c = policydb->ocontexts[OCON_PORT]; while (c) { @@ -2338,7 +2376,7 @@ int security_port_sid(struct selinux_state *state, } out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -2351,15 +2389,21 @@ out: int security_ib_pkey_sid(struct selinux_state *state, u64 subnet_prefix, u16 pkey_num, u32 *out_sid) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc = 0; - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) { + *out_sid = SECINITSID_UNLABELED; + return 0; + } - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBPKEY]; while (c) { @@ -2384,7 +2428,7 @@ int security_ib_pkey_sid(struct selinux_state *state, *out_sid = SECINITSID_UNLABELED; out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -2397,15 +2441,21 @@ out: int security_ib_endport_sid(struct selinux_state *state, const char *dev_name, u8 port_num, u32 *out_sid) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc = 0; - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) { + *out_sid = SECINITSID_UNLABELED; + return 0; + } - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBENDPORT]; while (c) { @@ -2430,7 +2480,7 @@ int security_ib_endport_sid(struct selinux_state *state, *out_sid = SECINITSID_UNLABELED; out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -2442,15 +2492,21 @@ out: int security_netif_sid(struct selinux_state *state, char *name, u32 *if_sid) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc = 0; struct ocontext *c; - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) { + *if_sid = SECINITSID_NETIF; + return 0; + } - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; c = policydb->ocontexts[OCON_NETIF]; while (c) { @@ -2475,7 +2531,7 @@ int security_netif_sid(struct selinux_state *state, *if_sid = SECINITSID_NETIF; out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -2505,15 +2561,21 @@ int security_node_sid(struct selinux_state *state, u32 addrlen, u32 *out_sid) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) { + *out_sid = SECINITSID_NODE; + return 0; + } - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; switch (domain) { case AF_INET: { @@ -2568,7 +2630,7 @@ int security_node_sid(struct selinux_state *state, rc = 0; out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -2594,6 +2656,7 @@ int security_get_user_sids(struct selinux_state *state, u32 **sids, u32 *nel) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *fromcon, usercon; @@ -2610,10 +2673,10 @@ int security_get_user_sids(struct selinux_state *state, if (!selinux_initialized(state)) goto out; - read_lock(&state->ss->policy_rwlock); - - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; context_init(&usercon); @@ -2664,7 +2727,7 @@ int security_get_user_sids(struct selinux_state *state, } rc = 0; out_unlock: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); if (rc || !mynel) { kfree(mysids); goto out; @@ -2705,17 +2768,15 @@ out: * Obtain a SID to use for a file in a filesystem that * cannot support xattr or use a fixed labeling behavior like * transition SIDs or task SIDs. - * - * The caller must acquire the policy_rwlock before calling this function. */ -static inline int __security_genfs_sid(struct selinux_state *state, +static inline int __security_genfs_sid(struct selinux_policy *policy, const char *fstype, char *path, u16 orig_sclass, u32 *sid) { - struct policydb *policydb = &state->ss->policydb; - struct sidtab *sidtab = state->ss->sidtab; + struct policydb *policydb = &policy->policydb; + struct sidtab *sidtab = policy->sidtab; int len; u16 sclass; struct genfs *genfs; @@ -2725,7 +2786,7 @@ static inline int __security_genfs_sid(struct selinux_state *state, while (path[0] == '/' && path[1] == '/') path++; - sclass = unmap_class(&state->ss->map, orig_sclass); + sclass = unmap_class(&policy->map, orig_sclass); *sid = SECINITSID_UNLABELED; for (genfs = policydb->genfs; genfs; genfs = genfs->next) { @@ -2777,20 +2838,39 @@ int security_genfs_sid(struct selinux_state *state, u16 orig_sclass, u32 *sid) { + struct selinux_policy *policy; int retval; - read_lock(&state->ss->policy_rwlock); - retval = __security_genfs_sid(state, fstype, path, orig_sclass, sid); - read_unlock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) { + *sid = SECINITSID_UNLABELED; + return 0; + } + + rcu_read_lock(); + policy = rcu_dereference(state->policy); + retval = __security_genfs_sid(policy, + fstype, path, orig_sclass, sid); + rcu_read_unlock(); return retval; } +int selinux_policy_genfs_sid(struct selinux_policy *policy, + const char *fstype, + char *path, + u16 orig_sclass, + u32 *sid) +{ + /* no lock required, policy is not yet accessible by other threads */ + return __security_genfs_sid(policy, fstype, path, orig_sclass, sid); +} + /** * security_fs_use - Determine how to handle labeling for a filesystem. * @sb: superblock in question */ int security_fs_use(struct selinux_state *state, struct super_block *sb) { + struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc = 0; @@ -2798,10 +2878,16 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) struct superblock_security_struct *sbsec = sb->s_security; const char *fstype = sb->s_type->name; - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) { + sbsec->behavior = SECURITY_FS_USE_NONE; + sbsec->sid = SECINITSID_UNLABELED; + return 0; + } - policydb = &state->ss->policydb; - sidtab = state->ss->sidtab; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; c = policydb->ocontexts[OCON_FSUSE]; while (c) { @@ -2820,8 +2906,8 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) } sbsec->sid = c->sid[0]; } else { - rc = __security_genfs_sid(state, fstype, "/", SECCLASS_DIR, - &sbsec->sid); + rc = __security_genfs_sid(policy, fstype, "/", + SECCLASS_DIR, &sbsec->sid); if (rc) { sbsec->behavior = SECURITY_FS_USE_NONE; rc = 0; @@ -2831,27 +2917,18 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) } out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } -int security_get_bools(struct selinux_state *state, +int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names, int **values) { struct policydb *policydb; u32 i; int rc; - if (!selinux_initialized(state)) { - *len = 0; - *names = NULL; - *values = NULL; - return 0; - } - - read_lock(&state->ss->policy_rwlock); - - policydb = &state->ss->policydb; + policydb = &policy->policydb; *names = NULL; *values = NULL; @@ -2882,7 +2959,6 @@ int security_get_bools(struct selinux_state *state, } rc = 0; out: - read_unlock(&state->ss->policy_rwlock); return rc; err: if (*names) { @@ -2900,61 +2976,89 @@ err: int security_set_bools(struct selinux_state *state, u32 len, int *values) { - struct policydb *policydb; + struct selinux_policy *newpolicy, *oldpolicy; int rc; - u32 i, lenp, seqno = 0; + u32 i, seqno = 0; - write_lock_irq(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) + return -EINVAL; - policydb = &state->ss->policydb; + oldpolicy = rcu_dereference_protected(state->policy, + lockdep_is_held(&state->policy_mutex)); - rc = -EFAULT; - lenp = policydb->p_bools.nprim; - if (len != lenp) - goto out; + /* Consistency check on number of booleans, should never fail */ + if (WARN_ON(len != oldpolicy->policydb.p_bools.nprim)) + return -EINVAL; + + newpolicy = kmemdup(oldpolicy, sizeof(*newpolicy), GFP_KERNEL); + if (!newpolicy) + return -ENOMEM; + + /* + * Deep copy only the parts of the policydb that might be + * modified as a result of changing booleans. + */ + rc = cond_policydb_dup(&newpolicy->policydb, &oldpolicy->policydb); + if (rc) { + kfree(newpolicy); + return -ENOMEM; + } + /* Update the boolean states in the copy */ for (i = 0; i < len; i++) { - if (!!values[i] != policydb->bool_val_to_struct[i]->state) { + int new_state = !!values[i]; + int old_state = newpolicy->policydb.bool_val_to_struct[i]->state; + + if (new_state != old_state) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_MAC_CONFIG_CHANGE, "bool=%s val=%d old_val=%d auid=%u ses=%u", - sym_name(policydb, SYM_BOOLS, i), - !!values[i], - policydb->bool_val_to_struct[i]->state, + sym_name(&newpolicy->policydb, SYM_BOOLS, i), + new_state, + old_state, from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); + newpolicy->policydb.bool_val_to_struct[i]->state = new_state; } - if (values[i]) - policydb->bool_val_to_struct[i]->state = 1; - else - policydb->bool_val_to_struct[i]->state = 0; } - evaluate_cond_nodes(policydb); + /* Re-evaluate the conditional rules in the copy */ + evaluate_cond_nodes(&newpolicy->policydb); - seqno = ++state->ss->latest_granting; - rc = 0; -out: - write_unlock_irq(&state->ss->policy_rwlock); - if (!rc) { - avc_ss_reset(state->avc, seqno); - selnl_notify_policyload(seqno); - selinux_status_update_policyload(state, seqno); - selinux_xfrm_notify_policyload(); - } - return rc; + /* Set latest granting seqno for new policy */ + newpolicy->latest_granting = oldpolicy->latest_granting + 1; + seqno = newpolicy->latest_granting; + + /* Install the new policy */ + rcu_assign_pointer(state->policy, newpolicy); + + /* + * Free the conditional portions of the old policydb + * that were copied for the new policy, and the oldpolicy + * structure itself but not what it references. + */ + synchronize_rcu(); + selinux_policy_cond_free(oldpolicy); + + /* Notify others of the policy change */ + selinux_notify_policy_change(state, seqno); + return 0; } int security_get_bool_value(struct selinux_state *state, u32 index) { + struct selinux_policy *policy; struct policydb *policydb; int rc; u32 len; - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) + return 0; - policydb = &state->ss->policydb; + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; rc = -EFAULT; len = policydb->p_bools.nprim; @@ -2963,27 +3067,28 @@ int security_get_bool_value(struct selinux_state *state, rc = policydb->bool_val_to_struct[index]->state; out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } -static int security_preserve_bools(struct selinux_state *state, - struct policydb *policydb) +static int security_preserve_bools(struct selinux_policy *oldpolicy, + struct selinux_policy *newpolicy) { int rc, *bvalues = NULL; char **bnames = NULL; struct cond_bool_datum *booldatum; u32 i, nbools = 0; - rc = security_get_bools(state, &nbools, &bnames, &bvalues); + rc = security_get_bools(oldpolicy, &nbools, &bnames, &bvalues); if (rc) goto out; for (i = 0; i < nbools; i++) { - booldatum = symtab_search(&policydb->p_bools, bnames[i]); + booldatum = symtab_search(&newpolicy->policydb.p_bools, + bnames[i]); if (booldatum) booldatum->state = bvalues[i]; } - evaluate_cond_nodes(policydb); + evaluate_cond_nodes(&newpolicy->policydb); out: if (bnames) { @@ -3002,8 +3107,9 @@ out: int security_sid_mls_copy(struct selinux_state *state, u32 sid, u32 mls_sid, u32 *new_sid) { - struct policydb *policydb = &state->ss->policydb; - struct sidtab *sidtab = state->ss->sidtab; + struct selinux_policy *policy; + struct policydb *policydb; + struct sidtab *sidtab; struct context *context1; struct context *context2; struct context newcon; @@ -3012,14 +3118,22 @@ int security_sid_mls_copy(struct selinux_state *state, int rc; rc = 0; - if (!selinux_initialized(state) || !policydb->mls_enabled) { + if (!selinux_initialized(state)) { *new_sid = sid; goto out; } context_init(&newcon); - read_lock(&state->ss->policy_rwlock); + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; + + if (!policydb->mls_enabled) { + *new_sid = sid; + goto out_unlock; + } rc = -EINVAL; context1 = sidtab_search(sidtab, sid); @@ -3046,7 +3160,8 @@ int security_sid_mls_copy(struct selinux_state *state, /* Check the validity of the new context. */ if (!policydb_context_isvalid(policydb, &newcon)) { - rc = convert_context_handle_invalid_context(state, &newcon); + rc = convert_context_handle_invalid_context(state, policydb, + &newcon); if (rc) { if (!context_struct_to_string(policydb, &newcon, &s, &len)) { @@ -3067,7 +3182,7 @@ int security_sid_mls_copy(struct selinux_state *state, } rc = sidtab_context_to_sid(sidtab, &newcon, new_sid); out_unlock: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); context_destroy(&newcon); out: return rc; @@ -3098,8 +3213,9 @@ int security_net_peersid_resolve(struct selinux_state *state, u32 xfrm_sid, u32 *peer_sid) { - struct policydb *policydb = &state->ss->policydb; - struct sidtab *sidtab = state->ss->sidtab; + struct selinux_policy *policy; + struct policydb *policydb; + struct sidtab *sidtab; int rc; struct context *nlbl_ctx; struct context *xfrm_ctx; @@ -3121,15 +3237,23 @@ int security_net_peersid_resolve(struct selinux_state *state, return 0; } + if (!selinux_initialized(state)) + return 0; + + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; + /* * We don't need to check initialized here since the only way both * nlbl_sid and xfrm_sid are not equal to SECSID_NULL would be if the * security server was initialized and state->initialized was true. */ - if (!policydb->mls_enabled) - return 0; - - read_lock(&state->ss->policy_rwlock); + if (!policydb->mls_enabled) { + rc = 0; + goto out; + } rc = -EINVAL; nlbl_ctx = sidtab_search(sidtab, nlbl_sid); @@ -3156,7 +3280,7 @@ int security_net_peersid_resolve(struct selinux_state *state, * expressive */ *peer_sid = xfrm_sid; out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -3173,19 +3297,13 @@ static int get_classes_callback(void *k, void *d, void *args) return 0; } -int security_get_classes(struct selinux_state *state, +int security_get_classes(struct selinux_policy *policy, char ***classes, int *nclasses) { - struct policydb *policydb = &state->ss->policydb; + struct policydb *policydb; int rc; - if (!selinux_initialized(state)) { - *nclasses = 0; - *classes = NULL; - return 0; - } - - read_lock(&state->ss->policy_rwlock); + policydb = &policy->policydb; rc = -ENOMEM; *nclasses = policydb->p_classes.nprim; @@ -3203,7 +3321,6 @@ int security_get_classes(struct selinux_state *state, } out: - read_unlock(&state->ss->policy_rwlock); return rc; } @@ -3220,14 +3337,14 @@ static int get_permissions_callback(void *k, void *d, void *args) return 0; } -int security_get_permissions(struct selinux_state *state, +int security_get_permissions(struct selinux_policy *policy, char *class, char ***perms, int *nperms) { - struct policydb *policydb = &state->ss->policydb; + struct policydb *policydb; int rc, i; struct class_datum *match; - read_lock(&state->ss->policy_rwlock); + policydb = &policy->policydb; rc = -EINVAL; match = symtab_search(&policydb->p_classes, class); @@ -3256,11 +3373,9 @@ int security_get_permissions(struct selinux_state *state, goto err; out: - read_unlock(&state->ss->policy_rwlock); return rc; err: - read_unlock(&state->ss->policy_rwlock); for (i = 0; i < *nperms; i++) kfree((*perms)[i]); kfree(*perms); @@ -3269,12 +3384,32 @@ err: int security_get_reject_unknown(struct selinux_state *state) { - return state->ss->policydb.reject_unknown; + struct selinux_policy *policy; + int value; + + if (!selinux_initialized(state)) + return 0; + + rcu_read_lock(); + policy = rcu_dereference(state->policy); + value = policy->policydb.reject_unknown; + rcu_read_unlock(); + return value; } int security_get_allow_unknown(struct selinux_state *state) { - return state->ss->policydb.allow_unknown; + struct selinux_policy *policy; + int value; + + if (!selinux_initialized(state)) + return 0; + + rcu_read_lock(); + policy = rcu_dereference(state->policy); + value = policy->policydb.allow_unknown; + rcu_read_unlock(); + return value; } /** @@ -3290,12 +3425,16 @@ int security_get_allow_unknown(struct selinux_state *state) int security_policycap_supported(struct selinux_state *state, unsigned int req_cap) { - struct policydb *policydb = &state->ss->policydb; + struct selinux_policy *policy; int rc; - read_lock(&state->ss->policy_rwlock); - rc = ebitmap_get_bit(&policydb->policycaps, req_cap); - read_unlock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) + return 0; + + rcu_read_lock(); + policy = rcu_dereference(state->policy); + rc = ebitmap_get_bit(&policy->policydb.policycaps, req_cap); + rcu_read_unlock(); return rc; } @@ -3318,7 +3457,8 @@ void selinux_audit_rule_free(void *vrule) int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) { struct selinux_state *state = &selinux_state; - struct policydb *policydb = &state->ss->policydb; + struct selinux_policy *policy; + struct policydb *policydb; struct selinux_audit_rule *tmprule; struct role_datum *roledatum; struct type_datum *typedatum; @@ -3361,9 +3501,11 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) context_init(&tmprule->au_ctxt); - read_lock(&state->ss->policy_rwlock); + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; - tmprule->au_seqno = state->ss->latest_granting; + tmprule->au_seqno = policy->latest_granting; switch (field) { case AUDIT_SUBJ_USER: @@ -3402,7 +3544,7 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) } rc = 0; out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); if (rc) { selinux_audit_rule_free(tmprule); @@ -3442,6 +3584,7 @@ int selinux_audit_rule_known(struct audit_krule *rule) int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) { struct selinux_state *state = &selinux_state; + struct selinux_policy *policy; struct context *ctxt; struct mls_level *level; struct selinux_audit_rule *rule = vrule; @@ -3452,14 +3595,19 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) return -ENOENT; } - read_lock(&state->ss->policy_rwlock); + if (!selinux_initialized(state)) + return 0; + + rcu_read_lock(); - if (rule->au_seqno < state->ss->latest_granting) { + policy = rcu_dereference(state->policy); + + if (rule->au_seqno < policy->latest_granting) { match = -ESTALE; goto out; } - ctxt = sidtab_search(state->ss->sidtab, sid); + ctxt = sidtab_search(policy->sidtab, sid); if (unlikely(!ctxt)) { WARN_ONCE(1, "selinux_audit_rule_match: unrecognized SID %d\n", sid); @@ -3543,7 +3691,7 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) } out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return match; } @@ -3621,8 +3769,9 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state, struct netlbl_lsm_secattr *secattr, u32 *sid) { - struct policydb *policydb = &state->ss->policydb; - struct sidtab *sidtab = state->ss->sidtab; + struct selinux_policy *policy; + struct policydb *policydb; + struct sidtab *sidtab; int rc; struct context *ctx; struct context ctx_new; @@ -3632,7 +3781,10 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state, return 0; } - read_lock(&state->ss->policy_rwlock); + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; + sidtab = policy->sidtab; if (secattr->flags & NETLBL_SECATTR_CACHE) *sid = *(u32 *)secattr->cache->data; @@ -3668,12 +3820,12 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state, } else *sid = SECSID_NULL; - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return 0; out_free: ebitmap_destroy(&ctx_new.range.level[0].cat); out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } @@ -3690,17 +3842,20 @@ out: int security_netlbl_sid_to_secattr(struct selinux_state *state, u32 sid, struct netlbl_lsm_secattr *secattr) { - struct policydb *policydb = &state->ss->policydb; + struct selinux_policy *policy; + struct policydb *policydb; int rc; struct context *ctx; if (!selinux_initialized(state)) return 0; - read_lock(&state->ss->policy_rwlock); + rcu_read_lock(); + policy = rcu_dereference(state->policy); + policydb = &policy->policydb; rc = -ENOENT; - ctx = sidtab_search(state->ss->sidtab, sid); + ctx = sidtab_search(policy->sidtab, sid); if (ctx == NULL) goto out; @@ -3715,7 +3870,7 @@ int security_netlbl_sid_to_secattr(struct selinux_state *state, mls_export_netlbl_lvl(policydb, ctx, secattr); rc = mls_export_netlbl_cat(policydb, ctx, secattr); out: - read_unlock(&state->ss->policy_rwlock); + rcu_read_unlock(); return rc; } #endif /* CONFIG_NETLABEL */ @@ -3729,15 +3884,16 @@ out: int security_read_policy(struct selinux_state *state, void **data, size_t *len) { - struct policydb *policydb = &state->ss->policydb; + struct selinux_policy *policy; int rc; struct policy_file fp; - if (!selinux_initialized(state)) + policy = rcu_dereference_protected( + state->policy, lockdep_is_held(&state->policy_mutex)); + if (!policy) return -EINVAL; - *len = security_policydb_len(state); - + *len = policy->policydb.len; *data = vmalloc_user(*len); if (!*data) return -ENOMEM; @@ -3745,10 +3901,7 @@ int security_read_policy(struct selinux_state *state, fp.data = *data; fp.len = *len; - read_lock(&state->ss->policy_rwlock); - rc = policydb_write(policydb, &fp); - read_unlock(&state->ss->policy_rwlock); - + rc = policydb_write(&policy->policydb, &fp); if (rc) return rc; diff --git a/security/selinux/ss/services.h b/security/selinux/ss/services.h index a06f3d835216..9555ad074303 100644 --- a/security/selinux/ss/services.h +++ b/security/selinux/ss/services.h @@ -22,12 +22,11 @@ struct selinux_map { u16 size; /* array size of mapping */ }; -struct selinux_ss { +struct selinux_policy { struct sidtab *sidtab; struct policydb policydb; - rwlock_t policy_rwlock; - u32 latest_granting; struct selinux_map map; + u32 latest_granting; } __randomize_layout; void services_compute_xperms_drivers(struct extended_perms *xperms, diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index eb6d27b5aeb4..5ee190bd30f5 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -464,6 +464,16 @@ int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) return 0; } +void sidtab_cancel_convert(struct sidtab *s) +{ + unsigned long flags; + + /* cancelling policy load - disable live convert of sidtab */ + spin_lock_irqsave(&s->lock, flags); + s->convert = NULL; + spin_unlock_irqrestore(&s->lock, flags); +} + static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); diff --git a/security/selinux/ss/sidtab.h b/security/selinux/ss/sidtab.h index f2a84560b8b3..80c744d07ad6 100644 --- a/security/selinux/ss/sidtab.h +++ b/security/selinux/ss/sidtab.h @@ -123,6 +123,8 @@ static inline struct context *sidtab_search_force(struct sidtab *s, u32 sid) int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params); +void sidtab_cancel_convert(struct sidtab *s); + int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid); void sidtab_destroy(struct sidtab *s); diff --git a/security/smack/smack.h b/security/smack/smack.h index e9e817d09785..a9768b12716b 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -100,7 +100,12 @@ struct socket_smack { struct smack_known *smk_out; /* outbound label */ struct smack_known *smk_in; /* inbound label */ struct smack_known *smk_packet; /* TCP peer label */ + int smk_state; /* netlabel socket states */ }; +#define SMK_NETLBL_UNSET 0 +#define SMK_NETLBL_UNLABELED 1 +#define SMK_NETLBL_LABELED 2 +#define SMK_NETLBL_REQSKB 3 /* * Inode smack data @@ -197,19 +202,6 @@ enum { #define SMACK_CIPSO_OPTION "-CIPSO" /* - * How communications on this socket are treated. - * Usually it's determined by the underlying netlabel code - * but there are certain cases, including single label hosts - * and potentially single label interfaces for which the - * treatment can not be known in advance. - * - * The possibility of additional labeling schemes being - * introduced in the future exists as well. - */ -#define SMACK_UNLABELED_SOCKET 0 -#define SMACK_CIPSO_SOCKET 1 - -/* * CIPSO defaults. */ #define SMACK_CIPSO_DOI_DEFAULT 3 /* Historical */ @@ -305,6 +297,7 @@ struct smack_known *smk_find_entry(const char *); bool smack_privileged(int cap); bool smack_privileged_cred(int cap, const struct cred *cred); void smk_destroy_label_list(struct list_head *list); +int smack_populate_secattr(struct smack_known *skp); /* * Shared data. diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index 38ac3da4e791..efe2406a3960 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -511,6 +511,42 @@ int smk_netlbl_mls(int level, char *catset, struct netlbl_lsm_secattr *sap, } /** + * smack_populate_secattr - fill in the smack_known netlabel information + * @skp: pointer to the structure to fill + * + * Populate the netlabel secattr structure for a Smack label. + * + * Returns 0 unless creating the category mapping fails + */ +int smack_populate_secattr(struct smack_known *skp) +{ + int slen; + + skp->smk_netlabel.attr.secid = skp->smk_secid; + skp->smk_netlabel.domain = skp->smk_known; + skp->smk_netlabel.cache = netlbl_secattr_cache_alloc(GFP_ATOMIC); + if (skp->smk_netlabel.cache != NULL) { + skp->smk_netlabel.flags |= NETLBL_SECATTR_CACHE; + skp->smk_netlabel.cache->free = NULL; + skp->smk_netlabel.cache->data = skp; + } + skp->smk_netlabel.flags |= NETLBL_SECATTR_SECID | + NETLBL_SECATTR_MLS_LVL | + NETLBL_SECATTR_DOMAIN; + /* + * If direct labeling works use it. + * Otherwise use mapped labeling. + */ + slen = strlen(skp->smk_known); + if (slen < SMK_CIPSOLEN) + return smk_netlbl_mls(smack_cipso_direct, skp->smk_known, + &skp->smk_netlabel, slen); + + return smk_netlbl_mls(smack_cipso_mapped, (char *)&skp->smk_secid, + &skp->smk_netlabel, sizeof(skp->smk_secid)); +} + +/** * smk_import_entry - import a label, return the list entry * @string: a text string that might be a Smack label * @len: the maximum size, or zero if it is NULL terminated. @@ -523,7 +559,6 @@ struct smack_known *smk_import_entry(const char *string, int len) { struct smack_known *skp; char *smack; - int slen; int rc; smack = smk_parse_smack(string, len); @@ -544,21 +579,8 @@ struct smack_known *smk_import_entry(const char *string, int len) skp->smk_known = smack; skp->smk_secid = smack_next_secid++; - skp->smk_netlabel.domain = skp->smk_known; - skp->smk_netlabel.flags = - NETLBL_SECATTR_DOMAIN | NETLBL_SECATTR_MLS_LVL; - /* - * If direct labeling works use it. - * Otherwise use mapped labeling. - */ - slen = strlen(smack); - if (slen < SMK_CIPSOLEN) - rc = smk_netlbl_mls(smack_cipso_direct, skp->smk_known, - &skp->smk_netlabel, slen); - else - rc = smk_netlbl_mls(smack_cipso_mapped, (char *)&skp->smk_secid, - &skp->smk_netlabel, sizeof(skp->smk_secid)); + rc = smack_populate_secattr(skp); if (rc >= 0) { INIT_LIST_HEAD(&skp->smk_rules); mutex_init(&skp->smk_rules_lock); @@ -569,9 +591,6 @@ struct smack_known *smk_import_entry(const char *string, int len) smk_insert_entry(skp); goto unlockout; } - /* - * smk_netlbl_mls failed. - */ kfree(skp); skp = ERR_PTR(rc); freeout: diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 8c0893eb5aa8..5c90b9fa4d40 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -2383,38 +2383,31 @@ static struct smack_known *smack_ipv6host_label(struct sockaddr_in6 *sip) } /** - * smack_netlabel - Set the secattr on a socket + * smack_netlbl_add - Set the secattr on a socket * @sk: the socket - * @labeled: socket label scheme * - * Convert the outbound smack value (smk_out) to a - * secattr and attach it to the socket. + * Attach the outbound smack value (smk_out) to the socket. * * Returns 0 on success or an error code */ -static int smack_netlabel(struct sock *sk, int labeled) +static int smack_netlbl_add(struct sock *sk) { - struct smack_known *skp; struct socket_smack *ssp = sk->sk_security; - int rc = 0; + struct smack_known *skp = ssp->smk_out; + int rc; - /* - * Usually the netlabel code will handle changing the - * packet labeling based on the label. - * The case of a single label host is different, because - * a single label host should never get a labeled packet - * even though the label is usually associated with a packet - * label. - */ local_bh_disable(); bh_lock_sock_nested(sk); - if (ssp->smk_out == smack_net_ambient || - labeled == SMACK_UNLABELED_SOCKET) - netlbl_sock_delattr(sk); - else { - skp = ssp->smk_out; - rc = netlbl_sock_setattr(sk, sk->sk_family, &skp->smk_netlabel); + rc = netlbl_sock_setattr(sk, sk->sk_family, &skp->smk_netlabel); + switch (rc) { + case 0: + ssp->smk_state = SMK_NETLBL_LABELED; + break; + case -EDESTADDRREQ: + ssp->smk_state = SMK_NETLBL_REQSKB; + rc = 0; + break; } bh_unlock_sock(sk); @@ -2424,7 +2417,31 @@ static int smack_netlabel(struct sock *sk, int labeled) } /** - * smack_netlbel_send - Set the secattr on a socket and perform access checks + * smack_netlbl_delete - Remove the secattr from a socket + * @sk: the socket + * + * Remove the outbound smack value from a socket + */ +static void smack_netlbl_delete(struct sock *sk) +{ + struct socket_smack *ssp = sk->sk_security; + + /* + * Take the label off the socket if one is set. + */ + if (ssp->smk_state != SMK_NETLBL_LABELED) + return; + + local_bh_disable(); + bh_lock_sock_nested(sk); + netlbl_sock_delattr(sk); + bh_unlock_sock(sk); + local_bh_enable(); + ssp->smk_state = SMK_NETLBL_UNLABELED; +} + +/** + * smk_ipv4_check - Perform IPv4 host access checks * @sk: the socket * @sap: the destination address * @@ -2434,11 +2451,10 @@ static int smack_netlabel(struct sock *sk, int labeled) * Returns 0 on success or an error code. * */ -static int smack_netlabel_send(struct sock *sk, struct sockaddr_in *sap) +static int smk_ipv4_check(struct sock *sk, struct sockaddr_in *sap) { struct smack_known *skp; - int rc; - int sk_lbl; + int rc = 0; struct smack_known *hkp; struct socket_smack *ssp = sk->sk_security; struct smk_audit_info ad; @@ -2454,19 +2470,18 @@ static int smack_netlabel_send(struct sock *sk, struct sockaddr_in *sap) ad.a.u.net->dport = sap->sin_port; ad.a.u.net->v4info.daddr = sap->sin_addr.s_addr; #endif - sk_lbl = SMACK_UNLABELED_SOCKET; skp = ssp->smk_out; rc = smk_access(skp, hkp, MAY_WRITE, &ad); rc = smk_bu_note("IPv4 host check", skp, hkp, MAY_WRITE, rc); - } else { - sk_lbl = SMACK_CIPSO_SOCKET; - rc = 0; + /* + * Clear the socket netlabel if it's set. + */ + if (!rc) + smack_netlbl_delete(sk); } rcu_read_unlock(); - if (rc != 0) - return rc; - return smack_netlabel(sk, sk_lbl); + return rc; } /** @@ -2703,7 +2718,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name, else if (strcmp(name, XATTR_SMACK_IPOUT) == 0) { ssp->smk_out = skp; if (sock->sk->sk_family == PF_INET) { - rc = smack_netlabel(sock->sk, SMACK_CIPSO_SOCKET); + rc = smack_netlbl_add(sock->sk); if (rc != 0) printk(KERN_WARNING "Smack: \"%s\" netlbl error %d.\n", @@ -2754,7 +2769,7 @@ static int smack_socket_post_create(struct socket *sock, int family, /* * Set the outbound netlbl. */ - return smack_netlabel(sock->sk, SMACK_CIPSO_SOCKET); + return smack_netlbl_add(sock->sk); } /** @@ -2845,7 +2860,7 @@ static int smack_socket_connect(struct socket *sock, struct sockaddr *sap, } if (sap->sa_family != AF_INET || addrlen < sizeof(struct sockaddr_in)) return 0; - rc = smack_netlabel_send(sock->sk, (struct sockaddr_in *)sap); + rc = smk_ipv4_check(sock->sk, (struct sockaddr_in *)sap); return rc; } @@ -3663,7 +3678,7 @@ static int smack_socket_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_namelen < sizeof(struct sockaddr_in) || sip->sin_family != AF_INET) return -EINVAL; - rc = smack_netlabel_send(sock->sk, sip); + rc = smk_ipv4_check(sock->sk, sip); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: @@ -3700,6 +3715,18 @@ static struct smack_known *smack_from_secattr(struct netlbl_lsm_secattr *sap, int acat; int kcat; + /* + * Netlabel found it in the cache. + */ + if ((sap->flags & NETLBL_SECATTR_CACHE) != 0) + return (struct smack_known *)sap->cache->data; + + if ((sap->flags & NETLBL_SECATTR_SECID) != 0) + /* + * Looks like a fallback, which gives us a secid. + */ + return smack_from_secid(sap->attr.secid); + if ((sap->flags & NETLBL_SECATTR_MLS_LVL) != 0) { /* * Looks like a CIPSO packet. @@ -3747,11 +3774,6 @@ static struct smack_known *smack_from_secattr(struct netlbl_lsm_secattr *sap, return &smack_known_web; return &smack_known_star; } - if ((sap->flags & NETLBL_SECATTR_SECID) != 0) - /* - * Looks like a fallback, which gives us a secid. - */ - return smack_from_secid(sap->attr.secid); /* * Without guidance regarding the smack value * for the packet fall back on the network @@ -3811,6 +3833,62 @@ static int smk_skb_to_addr_ipv6(struct sk_buff *skb, struct sockaddr_in6 *sip) #endif /* CONFIG_IPV6 */ /** + * smack_from_skb - Smack data from the secmark in an skb + * @skb: packet + * + * Returns smack_known of the secmark or NULL if that won't work. + */ +#ifdef CONFIG_NETWORK_SECMARK +static struct smack_known *smack_from_skb(struct sk_buff *skb) +{ + if (skb == NULL || skb->secmark == 0) + return NULL; + + return smack_from_secid(skb->secmark); +} +#else +static inline struct smack_known *smack_from_skb(struct sk_buff *skb) +{ + return NULL; +} +#endif + +/** + * smack_from_netlbl - Smack data from the IP options in an skb + * @sk: socket data came in on + * @family: address family + * @skb: packet + * + * Find the Smack label in the IP options. If it hasn't been + * added to the netlabel cache, add it here. + * + * Returns smack_known of the IP options or NULL if that won't work. + */ +static struct smack_known *smack_from_netlbl(struct sock *sk, u16 family, + struct sk_buff *skb) +{ + struct netlbl_lsm_secattr secattr; + struct socket_smack *ssp = NULL; + struct smack_known *skp = NULL; + int rc; + + netlbl_secattr_init(&secattr); + + if (sk) + ssp = sk->sk_security; + + if (netlbl_skbuff_getattr(skb, family, &secattr) == 0) { + skp = smack_from_secattr(&secattr, ssp); + if (secattr.flags & NETLBL_SECATTR_CACHEABLE) + rc = netlbl_cache_add(skb, family, &skp->smk_netlabel); + } + + netlbl_secattr_destroy(&secattr); + + return skp; +} + +/** * smack_socket_sock_rcv_skb - Smack packet delivery access check * @sk: socket * @skb: packet @@ -3819,7 +3897,6 @@ static int smk_skb_to_addr_ipv6(struct sk_buff *skb, struct sockaddr_in6 *sip) */ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { - struct netlbl_lsm_secattr secattr; struct socket_smack *ssp = sk->sk_security; struct smack_known *skp = NULL; int rc = 0; @@ -3838,33 +3915,18 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) switch (family) { case PF_INET: -#ifdef CONFIG_SECURITY_SMACK_NETFILTER /* * If there is a secmark use it rather than the CIPSO label. * If there is no secmark fall back to CIPSO. * The secmark is assumed to reflect policy better. */ - if (skb && skb->secmark != 0) { - skp = smack_from_secid(skb->secmark); - goto access_check; + skp = smack_from_skb(skb); + if (skp == NULL) { + skp = smack_from_netlbl(sk, family, skb); + if (skp == NULL) + skp = smack_net_ambient; } -#endif /* CONFIG_SECURITY_SMACK_NETFILTER */ - /* - * Translate what netlabel gave us. - */ - netlbl_secattr_init(&secattr); - rc = netlbl_skbuff_getattr(skb, family, &secattr); - if (rc == 0) - skp = smack_from_secattr(&secattr, ssp); - else - skp = smack_net_ambient; - - netlbl_secattr_destroy(&secattr); - -#ifdef CONFIG_SECURITY_SMACK_NETFILTER -access_check: -#endif #ifdef CONFIG_AUDIT smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net); ad.a.u.net->family = family; @@ -3890,16 +3952,14 @@ access_check: proto != IPPROTO_TCP && proto != IPPROTO_DCCP) break; #ifdef SMACK_IPV6_SECMARK_LABELING - if (skb && skb->secmark != 0) - skp = smack_from_secid(skb->secmark); - else if (smk_ipv6_localhost(&sadd)) - break; - else + skp = smack_from_skb(skb); + if (skp == NULL) { + if (smk_ipv6_localhost(&sadd)) + break; skp = smack_ipv6host_label(&sadd); - if (skp == NULL) - skp = smack_net_ambient; - if (skb == NULL) - break; + if (skp == NULL) + skp = smack_net_ambient; + } #ifdef CONFIG_AUDIT smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net); ad.a.u.net->family = family; @@ -3971,12 +4031,11 @@ static int smack_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { - struct netlbl_lsm_secattr secattr; struct socket_smack *ssp = NULL; struct smack_known *skp; + struct sock *sk = NULL; int family = PF_UNSPEC; u32 s = 0; /* 0 is the invalid secid */ - int rc; if (skb != NULL) { if (skb->protocol == htons(ETH_P_IP)) @@ -3995,27 +4054,25 @@ static int smack_socket_getpeersec_dgram(struct socket *sock, s = ssp->smk_out->smk_secid; break; case PF_INET: -#ifdef CONFIG_SECURITY_SMACK_NETFILTER - s = skb->secmark; - if (s != 0) + skp = smack_from_skb(skb); + if (skp) { + s = skp->smk_secid; break; -#endif + } /* * Translate what netlabel gave us. */ - if (sock != NULL && sock->sk != NULL) - ssp = sock->sk->sk_security; - netlbl_secattr_init(&secattr); - rc = netlbl_skbuff_getattr(skb, family, &secattr); - if (rc == 0) { - skp = smack_from_secattr(&secattr, ssp); + if (sock != NULL) + sk = sock->sk; + skp = smack_from_netlbl(sk, family, skb); + if (skp != NULL) s = skp->smk_secid; - } - netlbl_secattr_destroy(&secattr); break; case PF_INET6: #ifdef SMACK_IPV6_SECMARK_LABELING - s = skb->secmark; + skp = smack_from_skb(skb); + if (skp) + s = skp->smk_secid; #endif break; } @@ -4063,7 +4120,6 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, u16 family = sk->sk_family; struct smack_known *skp; struct socket_smack *ssp = sk->sk_security; - struct netlbl_lsm_secattr secattr; struct sockaddr_in addr; struct iphdr *hdr; struct smack_known *hskp; @@ -4087,29 +4143,17 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, } #endif /* CONFIG_IPV6 */ -#ifdef CONFIG_SECURITY_SMACK_NETFILTER /* * If there is a secmark use it rather than the CIPSO label. * If there is no secmark fall back to CIPSO. * The secmark is assumed to reflect policy better. */ - if (skb && skb->secmark != 0) { - skp = smack_from_secid(skb->secmark); - goto access_check; + skp = smack_from_skb(skb); + if (skp == NULL) { + skp = smack_from_netlbl(sk, family, skb); + if (skp == NULL) + skp = &smack_known_huh; } -#endif /* CONFIG_SECURITY_SMACK_NETFILTER */ - - netlbl_secattr_init(&secattr); - rc = netlbl_skbuff_getattr(skb, family, &secattr); - if (rc == 0) - skp = smack_from_secattr(&secattr, ssp); - else - skp = &smack_known_huh; - netlbl_secattr_destroy(&secattr); - -#ifdef CONFIG_SECURITY_SMACK_NETFILTER -access_check: -#endif #ifdef CONFIG_AUDIT smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net); diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index 9c4308077574..e567b4baf3a0 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -922,6 +922,10 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf, skp->smk_netlabel.attr.mls.cat = ncats.attr.mls.cat; skp->smk_netlabel.attr.mls.lvl = ncats.attr.mls.lvl; rc = count; + /* + * This mapping may have been cached, so clear the cache. + */ + netlbl_cache_invalidate(); } out: @@ -2950,15 +2954,6 @@ static struct file_system_type smk_fs_type = { static struct vfsmount *smackfs_mount; -static int __init smk_preset_netlabel(struct smack_known *skp) -{ - skp->smk_netlabel.domain = skp->smk_known; - skp->smk_netlabel.flags = - NETLBL_SECATTR_DOMAIN | NETLBL_SECATTR_MLS_LVL; - return smk_netlbl_mls(smack_cipso_direct, skp->smk_known, - &skp->smk_netlabel, strlen(skp->smk_known)); -} - /** * init_smk_fs - get the smackfs superblock * @@ -2997,19 +2992,19 @@ static int __init init_smk_fs(void) smk_cipso_doi(); smk_unlbl_ambient(NULL); - rc = smk_preset_netlabel(&smack_known_floor); + rc = smack_populate_secattr(&smack_known_floor); if (err == 0 && rc < 0) err = rc; - rc = smk_preset_netlabel(&smack_known_hat); + rc = smack_populate_secattr(&smack_known_hat); if (err == 0 && rc < 0) err = rc; - rc = smk_preset_netlabel(&smack_known_huh); + rc = smack_populate_secattr(&smack_known_huh); if (err == 0 && rc < 0) err = rc; - rc = smk_preset_netlabel(&smack_known_star); + rc = smack_populate_secattr(&smack_known_star); if (err == 0 && rc < 0) err = rc; - rc = smk_preset_netlabel(&smack_known_web); + rc = smack_populate_secattr(&smack_known_web); if (err == 0 && rc < 0) err = rc; diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c index eba0b3395851..a40abb0b91ee 100644 --- a/security/tomoyo/util.c +++ b/security/tomoyo/util.c @@ -143,6 +143,8 @@ char *tomoyo_read_token(struct tomoyo_acl_param *param) return pos; } +static bool tomoyo_correct_path2(const char *filename, const size_t len); + /** * tomoyo_get_domainname - Read a domainname from a line. * @@ -157,10 +159,10 @@ const struct tomoyo_path_info *tomoyo_get_domainname char *pos = start; while (*pos) { - if (*pos++ != ' ' || *pos++ == '/') + if (*pos++ != ' ' || + tomoyo_correct_path2(pos, strchrnul(pos, ' ') - pos)) continue; - pos -= 2; - *pos++ = '\0'; + *(pos - 1) = '\0'; break; } param->data = pos; @@ -514,6 +516,22 @@ bool tomoyo_correct_word(const char *string) } /** + * tomoyo_correct_path2 - Check whether the given pathname follows the naming rules. + * + * @filename: The pathname to check. + * @len: Length of @filename. + * + * Returns true if @filename follows the naming rules, false otherwise. + */ +static bool tomoyo_correct_path2(const char *filename, const size_t len) +{ + const char *cp1 = memchr(filename, '/', len); + const char *cp2 = memchr(filename, '.', len); + + return cp1 && (!cp2 || (cp1 < cp2)) && tomoyo_correct_word2(filename, len); +} + +/** * tomoyo_correct_path - Validate a pathname. * * @filename: The pathname to check. @@ -523,7 +541,7 @@ bool tomoyo_correct_word(const char *string) */ bool tomoyo_correct_path(const char *filename) { - return *filename == '/' && tomoyo_correct_word(filename); + return tomoyo_correct_path2(filename, strlen(filename)); } /** @@ -545,8 +563,7 @@ bool tomoyo_correct_domain(const unsigned char *domainname) if (!cp) break; - if (*domainname != '/' || - !tomoyo_correct_word2(domainname, cp - domainname)) + if (!tomoyo_correct_path2(domainname, cp - domainname)) return false; domainname = cp + 1; } diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index b7e6dec36173..42be3b925830 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -20,13 +20,6 @@ #include "../kselftest.h" #include "clone3_selftests.h" -/* - * Different sizes of struct clone_args - */ -#ifndef CLONE3_ARGS_SIZE_V0 -#define CLONE3_ARGS_SIZE_V0 64 -#endif - enum test_mode { CLONE3_ARGS_NO_TEST, CLONE3_ARGS_ALL_0, @@ -38,13 +31,13 @@ enum test_mode { static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) { - struct clone_args args = { + struct __clone_args args = { .flags = flags, .exit_signal = SIGCHLD, }; struct clone_args_extended { - struct clone_args args; + struct __clone_args args; __aligned_u64 excess_space[2]; } args_ext; @@ -52,11 +45,11 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) int status; memset(&args_ext, 0, sizeof(args_ext)); - if (size > sizeof(struct clone_args)) + if (size > sizeof(struct __clone_args)) args_ext.excess_space[1] = 1; if (size == 0) - size = sizeof(struct clone_args); + size = sizeof(struct __clone_args); switch (test_mode) { case CLONE3_ARGS_ALL_0: @@ -77,9 +70,9 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode) break; } - memcpy(&args_ext.args, &args, sizeof(struct clone_args)); + memcpy(&args_ext.args, &args, sizeof(struct __clone_args)); - pid = sys_clone3((struct clone_args *)&args_ext, size); + pid = sys_clone3((struct __clone_args *)&args_ext, size); if (pid < 0) { ksft_print_msg("%s - Failed to create new process\n", strerror(errno)); @@ -144,14 +137,14 @@ int main(int argc, char *argv[]) else ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n"); - /* Do a clone3() with CLONE3_ARGS_SIZE_V0. */ - test_clone3(0, CLONE3_ARGS_SIZE_V0, 0, CLONE3_ARGS_NO_TEST); + /* Do a clone3() with CLONE_ARGS_SIZE_VER0. */ + test_clone3(0, CLONE_ARGS_SIZE_VER0, 0, CLONE3_ARGS_NO_TEST); - /* Do a clone3() with CLONE3_ARGS_SIZE_V0 - 8 */ - test_clone3(0, CLONE3_ARGS_SIZE_V0 - 8, -EINVAL, CLONE3_ARGS_NO_TEST); + /* Do a clone3() with CLONE_ARGS_SIZE_VER0 - 8 */ + test_clone3(0, CLONE_ARGS_SIZE_VER0 - 8, -EINVAL, CLONE3_ARGS_NO_TEST); /* Do a clone3() with sizeof(struct clone_args) + 8 */ - test_clone3(0, sizeof(struct clone_args) + 8, 0, CLONE3_ARGS_NO_TEST); + test_clone3(0, sizeof(struct __clone_args) + 8, 0, CLONE3_ARGS_NO_TEST); /* Do a clone3() with exit_signal having highest 32 bits non-zero */ test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG); @@ -165,31 +158,31 @@ int main(int argc, char *argv[]) /* Do a clone3() with NSIG < exit_signal < CSIG */ test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG); - test_clone3(0, sizeof(struct clone_args) + 8, 0, CLONE3_ARGS_ALL_0); + test_clone3(0, sizeof(struct __clone_args) + 8, 0, CLONE3_ARGS_ALL_0); - test_clone3(0, sizeof(struct clone_args) + 16, -E2BIG, + test_clone3(0, sizeof(struct __clone_args) + 16, -E2BIG, CLONE3_ARGS_ALL_0); - test_clone3(0, sizeof(struct clone_args) * 2, -E2BIG, + test_clone3(0, sizeof(struct __clone_args) * 2, -E2BIG, CLONE3_ARGS_ALL_0); /* Do a clone3() with > page size */ test_clone3(0, getpagesize() + 8, -E2BIG, CLONE3_ARGS_NO_TEST); - /* Do a clone3() with CLONE3_ARGS_SIZE_V0 in a new PID NS. */ + /* Do a clone3() with CLONE_ARGS_SIZE_VER0 in a new PID NS. */ if (uid == 0) - test_clone3(CLONE_NEWPID, CLONE3_ARGS_SIZE_V0, 0, + test_clone3(CLONE_NEWPID, CLONE_ARGS_SIZE_VER0, 0, CLONE3_ARGS_NO_TEST); else ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n"); - /* Do a clone3() with CLONE3_ARGS_SIZE_V0 - 8 in a new PID NS */ - test_clone3(CLONE_NEWPID, CLONE3_ARGS_SIZE_V0 - 8, -EINVAL, + /* Do a clone3() with CLONE_ARGS_SIZE_VER0 - 8 in a new PID NS */ + test_clone3(CLONE_NEWPID, CLONE_ARGS_SIZE_VER0 - 8, -EINVAL, CLONE3_ARGS_NO_TEST); /* Do a clone3() with sizeof(struct clone_args) + 8 in a new PID NS */ if (uid == 0) - test_clone3(CLONE_NEWPID, sizeof(struct clone_args) + 8, 0, + test_clone3(CLONE_NEWPID, sizeof(struct __clone_args) + 8, 0, CLONE3_ARGS_NO_TEST); else ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n"); diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c index 9562425aa0a9..55bd387ce7ec 100644 --- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -44,13 +44,13 @@ static int call_clone3_set_tid(struct __test_metadata *_metadata, int status; pid_t pid = -1; - struct clone_args args = { + struct __clone_args args = { .exit_signal = SIGCHLD, .set_tid = ptr_to_u64(set_tid), .set_tid_size = set_tid_size, }; - pid = sys_clone3(&args, sizeof(struct clone_args)); + pid = sys_clone3(&args, sizeof(args)); if (pid < 0) { TH_LOG("%s - Failed to create new process", strerror(errno)); return -errno; diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c index db5fc9c5edcf..47a8c0fc3676 100644 --- a/tools/testing/selftests/clone3/clone3_clear_sighand.c +++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c @@ -47,7 +47,7 @@ static void test_clone3_clear_sighand(void) { int ret; pid_t pid; - struct clone_args args = {}; + struct __clone_args args = {}; struct sigaction act; /* diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h index 91c1a78ddb39..e81ffaaee02b 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -19,13 +19,11 @@ #define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */ #endif -#ifndef CLONE_ARGS_SIZE_VER0 -#define CLONE_ARGS_SIZE_VER0 64 -#endif - #ifndef __NR_clone3 #define __NR_clone3 -1 -struct clone_args { +#endif + +struct __clone_args { __aligned_u64 flags; __aligned_u64 pidfd; __aligned_u64 child_tid; @@ -34,15 +32,21 @@ struct clone_args { __aligned_u64 stack; __aligned_u64 stack_size; __aligned_u64 tls; -#define CLONE_ARGS_SIZE_VER1 80 +#ifndef CLONE_ARGS_SIZE_VER0 +#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ +#endif __aligned_u64 set_tid; __aligned_u64 set_tid_size; -#define CLONE_ARGS_SIZE_VER2 88 +#ifndef CLONE_ARGS_SIZE_VER1 +#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ +#endif __aligned_u64 cgroup; +#ifndef CLONE_ARGS_SIZE_VER2 +#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */ +#endif }; -#endif /* __NR_clone3 */ -static pid_t sys_clone3(struct clone_args *args, size_t size) +static pid_t sys_clone3(struct __clone_args *args, size_t size) { fflush(stdout); fflush(stderr); @@ -52,7 +56,7 @@ static pid_t sys_clone3(struct clone_args *args, size_t size) static inline void test_clone3_supported(void) { pid_t pid; - struct clone_args args = {}; + struct __clone_args args = {}; if (__NR_clone3 < 0) ksft_exit_skip("clone3() syscall is not supported\n"); diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index 5831c1082d6d..0229e9ebb995 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -46,14 +46,14 @@ static int call_clone3_set_tid(pid_t *set_tid, int status; pid_t pid = -1; - struct clone_args args = { + struct __clone_args args = { .flags = flags, .exit_signal = SIGCHLD, .set_tid = ptr_to_u64(set_tid), .set_tid_size = set_tid_size, }; - pid = sys_clone3(&args, sizeof(struct clone_args)); + pid = sys_clone3(&args, sizeof(args)); if (pid < 0) { ksft_print_msg("%s - Failed to create new process\n", strerror(errno)); diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 7dca1aa4672d..1f085b922c6e 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -75,7 +75,7 @@ static int sys_waitid(int which, pid_t pid, int options) pid_t create_child(int *pidfd, unsigned flags) { - struct clone_args args = { + struct __clone_args args = { .flags = CLONE_PIDFD | flags, .exit_signal = SIGCHLD, .pidfd = ptr_to_u64(pidfd), diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 7a6d40286a42..4a180439ee9e 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -774,8 +774,15 @@ void *kill_thread(void *data) return (void *)SIBLING_EXIT_UNKILLED; } +enum kill_t { + KILL_THREAD, + KILL_PROCESS, + RET_UNKNOWN +}; + /* Prepare a thread that will kill itself or both of us. */ -void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process) +void kill_thread_or_group(struct __test_metadata *_metadata, + enum kill_t kill_how) { pthread_t thread; void *status; @@ -791,11 +798,12 @@ void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process) .len = (unsigned short)ARRAY_SIZE(filter_thread), .filter = filter_thread, }; + int kill = kill_how == KILL_PROCESS ? SECCOMP_RET_KILL_PROCESS : 0xAAAAAAAAA; struct sock_filter filter_process[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)), BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_PROCESS), + BPF_STMT(BPF_RET|BPF_K, kill), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; struct sock_fprog prog_process = { @@ -808,13 +816,15 @@ void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process) } ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, - kill_process ? &prog_process : &prog_thread)); + kill_how == KILL_THREAD ? &prog_thread + : &prog_process)); /* * Add the KILL_THREAD rule again to make sure that the KILL_PROCESS * flag cannot be downgraded by a new filter. */ - ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread)); + if (kill_how == KILL_PROCESS) + ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread)); /* Start a thread that will exit immediately. */ ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)false)); @@ -842,7 +852,7 @@ TEST(KILL_thread) child_pid = fork(); ASSERT_LE(0, child_pid); if (child_pid == 0) { - kill_thread_or_group(_metadata, false); + kill_thread_or_group(_metadata, KILL_THREAD); _exit(38); } @@ -861,7 +871,7 @@ TEST(KILL_process) child_pid = fork(); ASSERT_LE(0, child_pid); if (child_pid == 0) { - kill_thread_or_group(_metadata, true); + kill_thread_or_group(_metadata, KILL_PROCESS); _exit(38); } @@ -872,6 +882,27 @@ TEST(KILL_process) ASSERT_EQ(SIGSYS, WTERMSIG(status)); } +TEST(KILL_unknown) +{ + int status; + pid_t child_pid; + + child_pid = fork(); + ASSERT_LE(0, child_pid); + if (child_pid == 0) { + kill_thread_or_group(_metadata, RET_UNKNOWN); + _exit(38); + } + + ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0)); + + /* If the entire process was killed, we'll see SIGSYS. */ + EXPECT_TRUE(WIFSIGNALED(status)) { + TH_LOG("Unknown SECCOMP_RET is only killing the thread?"); + } + ASSERT_EQ(SIGSYS, WTERMSIG(status)); +} + /* TODO(wad) add 64-bit versus 32-bit arg tests. */ TEST(arg_out_of_range) { @@ -1667,70 +1698,148 @@ TEST_F(TRACE_poke, getpid_runs_normally) } #if defined(__x86_64__) -# define ARCH_REGS struct user_regs_struct -# define SYSCALL_NUM orig_rax -# define SYSCALL_RET rax +# define ARCH_REGS struct user_regs_struct +# define SYSCALL_NUM(_regs) (_regs).orig_rax +# define SYSCALL_RET(_regs) (_regs).rax #elif defined(__i386__) -# define ARCH_REGS struct user_regs_struct -# define SYSCALL_NUM orig_eax -# define SYSCALL_RET eax +# define ARCH_REGS struct user_regs_struct +# define SYSCALL_NUM(_regs) (_regs).orig_eax +# define SYSCALL_RET(_regs) (_regs).eax #elif defined(__arm__) -# define ARCH_REGS struct pt_regs -# define SYSCALL_NUM ARM_r7 -# define SYSCALL_RET ARM_r0 +# define ARCH_REGS struct pt_regs +# define SYSCALL_NUM(_regs) (_regs).ARM_r7 +# ifndef PTRACE_SET_SYSCALL +# define PTRACE_SET_SYSCALL 23 +# endif +# define SYSCALL_NUM_SET(_regs, _nr) \ + EXPECT_EQ(0, ptrace(PTRACE_SET_SYSCALL, tracee, NULL, _nr)) +# define SYSCALL_RET(_regs) (_regs).ARM_r0 #elif defined(__aarch64__) -# define ARCH_REGS struct user_pt_regs -# define SYSCALL_NUM regs[8] -# define SYSCALL_RET regs[0] +# define ARCH_REGS struct user_pt_regs +# define SYSCALL_NUM(_regs) (_regs).regs[8] +# ifndef NT_ARM_SYSTEM_CALL +# define NT_ARM_SYSTEM_CALL 0x404 +# endif +# define SYSCALL_NUM_SET(_regs, _nr) \ + do { \ + struct iovec __v; \ + typeof(_nr) __nr = (_nr); \ + __v.iov_base = &__nr; \ + __v.iov_len = sizeof(__nr); \ + EXPECT_EQ(0, ptrace(PTRACE_SETREGSET, tracee, \ + NT_ARM_SYSTEM_CALL, &__v)); \ + } while (0) +# define SYSCALL_RET(_regs) (_regs).regs[0] #elif defined(__riscv) && __riscv_xlen == 64 -# define ARCH_REGS struct user_regs_struct -# define SYSCALL_NUM a7 -# define SYSCALL_RET a0 +# define ARCH_REGS struct user_regs_struct +# define SYSCALL_NUM(_regs) (_regs).a7 +# define SYSCALL_RET(_regs) (_regs).a0 #elif defined(__csky__) -# define ARCH_REGS struct pt_regs -#if defined(__CSKYABIV2__) -# define SYSCALL_NUM regs[3] -#else -# define SYSCALL_NUM regs[9] -#endif -# define SYSCALL_RET a0 +# define ARCH_REGS struct pt_regs +# if defined(__CSKYABIV2__) +# define SYSCALL_NUM(_regs) (_regs).regs[3] +# else +# define SYSCALL_NUM(_regs) (_regs).regs[9] +# endif +# define SYSCALL_RET(_regs) (_regs).a0 #elif defined(__hppa__) -# define ARCH_REGS struct user_regs_struct -# define SYSCALL_NUM gr[20] -# define SYSCALL_RET gr[28] +# define ARCH_REGS struct user_regs_struct +# define SYSCALL_NUM(_regs) (_regs).gr[20] +# define SYSCALL_RET(_regs) (_regs).gr[28] #elif defined(__powerpc__) -# define ARCH_REGS struct pt_regs -# define SYSCALL_NUM gpr[0] -# define SYSCALL_RET gpr[3] +# define ARCH_REGS struct pt_regs +# define SYSCALL_NUM(_regs) (_regs).gpr[0] +# define SYSCALL_RET(_regs) (_regs).gpr[3] +# define SYSCALL_RET_SET(_regs, _val) \ + do { \ + typeof(_val) _result = (_val); \ + /* \ + * A syscall error is signaled by CR0 SO bit \ + * and the code is stored as a positive value. \ + */ \ + if (_result < 0) { \ + SYSCALL_RET(_regs) = -result; \ + (_regs).ccr |= 0x10000000; \ + } else { \ + SYSCALL_RET(_regs) = result; \ + (_regs).ccr &= ~0x10000000; \ + } \ + } while (0) +# define SYSCALL_RET_SET_ON_PTRACE_EXIT #elif defined(__s390__) -# define ARCH_REGS s390_regs -# define SYSCALL_NUM gprs[2] -# define SYSCALL_RET gprs[2] -# define SYSCALL_NUM_RET_SHARE_REG +# define ARCH_REGS s390_regs +# define SYSCALL_NUM(_regs) (_regs).gprs[2] +# define SYSCALL_RET_SET(_regs, _val) \ + TH_LOG("Can't modify syscall return on this architecture") #elif defined(__mips__) -# define ARCH_REGS struct pt_regs -# define SYSCALL_NUM regs[2] -# define SYSCALL_SYSCALL_NUM regs[4] -# define SYSCALL_RET regs[2] -# define SYSCALL_NUM_RET_SHARE_REG +# include <asm/unistd_nr_n32.h> +# include <asm/unistd_nr_n64.h> +# include <asm/unistd_nr_o32.h> +# define ARCH_REGS struct pt_regs +# define SYSCALL_NUM(_regs) \ + ({ \ + typeof((_regs).regs[2]) _nr; \ + if ((_regs).regs[2] == __NR_O32_Linux) \ + _nr = (_regs).regs[4]; \ + else \ + _nr = (_regs).regs[2]; \ + _nr; \ + }) +# define SYSCALL_NUM_SET(_regs, _nr) \ + do { \ + if ((_regs).regs[2] == __NR_O32_Linux) \ + (_regs).regs[4] = _nr; \ + else \ + (_regs).regs[2] = _nr; \ + } while (0) +# define SYSCALL_RET_SET(_regs, _val) \ + TH_LOG("Can't modify syscall return on this architecture") #elif defined(__xtensa__) -# define ARCH_REGS struct user_pt_regs -# define SYSCALL_NUM syscall +# define ARCH_REGS struct user_pt_regs +# define SYSCALL_NUM(_regs) (_regs).syscall /* * On xtensa syscall return value is in the register * a2 of the current window which is not fixed. */ -#define SYSCALL_RET(reg) a[(reg).windowbase * 4 + 2] +#define SYSCALL_RET(_regs) (_regs).a[(_regs).windowbase * 4 + 2] #elif defined(__sh__) -# define ARCH_REGS struct pt_regs -# define SYSCALL_NUM gpr[3] -# define SYSCALL_RET gpr[0] +# define ARCH_REGS struct pt_regs +# define SYSCALL_NUM(_regs) (_regs).gpr[3] +# define SYSCALL_RET(_regs) (_regs).gpr[0] #else # error "Do not know how to find your architecture's registers and syscalls" #endif +/* + * Most architectures can change the syscall by just updating the + * associated register. This is the default if not defined above. + */ +#ifndef SYSCALL_NUM_SET +# define SYSCALL_NUM_SET(_regs, _nr) \ + do { \ + SYSCALL_NUM(_regs) = (_nr); \ + } while (0) +#endif +/* + * Most architectures can change the syscall return value by just + * writing to the SYSCALL_RET register. This is the default if not + * defined above. If an architecture cannot set the return value + * (for example when the syscall and return value register is + * shared), report it with TH_LOG() in an arch-specific definition + * of SYSCALL_RET_SET() above, and leave SYSCALL_RET undefined. + */ +#if !defined(SYSCALL_RET) && !defined(SYSCALL_RET_SET) +# error "One of SYSCALL_RET or SYSCALL_RET_SET is needed for this arch" +#endif +#ifndef SYSCALL_RET_SET +# define SYSCALL_RET_SET(_regs, _val) \ + do { \ + SYSCALL_RET(_regs) = (_val); \ + } while (0) +#endif + /* When the syscall return can't be changed, stub out the tests for it. */ -#ifdef SYSCALL_NUM_RET_SHARE_REG +#ifndef SYSCALL_RET # define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(-1, action) #else # define EXPECT_SYSCALL_RETURN(val, action) \ @@ -1745,116 +1854,92 @@ TEST_F(TRACE_poke, getpid_runs_normally) } while (0) #endif -/* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for +/* + * Some architectures (e.g. powerpc) can only set syscall + * return values on syscall exit during ptrace. + */ +const bool ptrace_entry_set_syscall_nr = true; +const bool ptrace_entry_set_syscall_ret = +#ifndef SYSCALL_RET_SET_ON_PTRACE_EXIT + true; +#else + false; +#endif + +/* + * Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux). */ #if defined(__x86_64__) || defined(__i386__) || defined(__mips__) -#define HAVE_GETREGS +# define ARCH_GETREGS(_regs) ptrace(PTRACE_GETREGS, tracee, 0, &(_regs)) +# define ARCH_SETREGS(_regs) ptrace(PTRACE_SETREGS, tracee, 0, &(_regs)) +#else +# define ARCH_GETREGS(_regs) ({ \ + struct iovec __v; \ + __v.iov_base = &(_regs); \ + __v.iov_len = sizeof(_regs); \ + ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &__v); \ + }) +# define ARCH_SETREGS(_regs) ({ \ + struct iovec __v; \ + __v.iov_base = &(_regs); \ + __v.iov_len = sizeof(_regs); \ + ptrace(PTRACE_SETREGSET, tracee, NT_PRSTATUS, &__v); \ + }) #endif /* Architecture-specific syscall fetching routine. */ int get_syscall(struct __test_metadata *_metadata, pid_t tracee) { ARCH_REGS regs; -#ifdef HAVE_GETREGS - EXPECT_EQ(0, ptrace(PTRACE_GETREGS, tracee, 0, ®s)) { - TH_LOG("PTRACE_GETREGS failed"); - return -1; - } -#else - struct iovec iov; - iov.iov_base = ®s; - iov.iov_len = sizeof(regs); - EXPECT_EQ(0, ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov)) { - TH_LOG("PTRACE_GETREGSET failed"); + EXPECT_EQ(0, ARCH_GETREGS(regs)) { return -1; } -#endif -#if defined(__mips__) - if (regs.SYSCALL_NUM == __NR_O32_Linux) - return regs.SYSCALL_SYSCALL_NUM; -#endif - return regs.SYSCALL_NUM; + return SYSCALL_NUM(regs); } /* Architecture-specific syscall changing routine. */ -void change_syscall(struct __test_metadata *_metadata, - pid_t tracee, int syscall, int result) +void __change_syscall(struct __test_metadata *_metadata, + pid_t tracee, long *syscall, long *ret) { - int ret; - ARCH_REGS regs; -#ifdef HAVE_GETREGS - ret = ptrace(PTRACE_GETREGS, tracee, 0, ®s); -#else - struct iovec iov; - iov.iov_base = ®s; - iov.iov_len = sizeof(regs); - ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov); -#endif - EXPECT_EQ(0, ret) {} + ARCH_REGS orig, regs; -#if defined(__x86_64__) || defined(__i386__) || defined(__powerpc__) || \ - defined(__s390__) || defined(__hppa__) || defined(__riscv) || \ - defined(__xtensa__) || defined(__csky__) || defined(__sh__) - { - regs.SYSCALL_NUM = syscall; - } -#elif defined(__mips__) - { - if (regs.SYSCALL_NUM == __NR_O32_Linux) - regs.SYSCALL_SYSCALL_NUM = syscall; - else - regs.SYSCALL_NUM = syscall; - } + /* Do not get/set registers if we have nothing to do. */ + if (!syscall && !ret) + return; -#elif defined(__arm__) -# ifndef PTRACE_SET_SYSCALL -# define PTRACE_SET_SYSCALL 23 -# endif - { - ret = ptrace(PTRACE_SET_SYSCALL, tracee, NULL, syscall); - EXPECT_EQ(0, ret); + EXPECT_EQ(0, ARCH_GETREGS(regs)) { + return; } + orig = regs; -#elif defined(__aarch64__) -# ifndef NT_ARM_SYSTEM_CALL -# define NT_ARM_SYSTEM_CALL 0x404 -# endif - { - iov.iov_base = &syscall; - iov.iov_len = sizeof(syscall); - ret = ptrace(PTRACE_SETREGSET, tracee, NT_ARM_SYSTEM_CALL, - &iov); - EXPECT_EQ(0, ret); - } + if (syscall) + SYSCALL_NUM_SET(regs, *syscall); -#else - ASSERT_EQ(1, 0) { - TH_LOG("How is the syscall changed on this architecture?"); - } -#endif + if (ret) + SYSCALL_RET_SET(regs, *ret); - /* If syscall is skipped, change return value. */ - if (syscall == -1) -#ifdef SYSCALL_NUM_RET_SHARE_REG - TH_LOG("Can't modify syscall return on this architecture"); + /* Flush any register changes made. */ + if (memcmp(&orig, ®s, sizeof(orig)) != 0) + EXPECT_EQ(0, ARCH_SETREGS(regs)); +} -#elif defined(__xtensa__) - regs.SYSCALL_RET(regs) = result; -#else - regs.SYSCALL_RET = result; -#endif +/* Change only syscall number. */ +void change_syscall_nr(struct __test_metadata *_metadata, + pid_t tracee, long syscall) +{ + __change_syscall(_metadata, tracee, &syscall, NULL); +} -#ifdef HAVE_GETREGS - ret = ptrace(PTRACE_SETREGS, tracee, 0, ®s); -#else - iov.iov_base = ®s; - iov.iov_len = sizeof(regs); - ret = ptrace(PTRACE_SETREGSET, tracee, NT_PRSTATUS, &iov); -#endif - EXPECT_EQ(0, ret); +/* Change syscall return value (and set syscall number to -1). */ +void change_syscall_ret(struct __test_metadata *_metadata, + pid_t tracee, long ret) +{ + long syscall = -1; + + __change_syscall(_metadata, tracee, &syscall, &ret); } void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee, @@ -1872,17 +1957,17 @@ void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee, case 0x1002: /* change getpid to getppid. */ EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee)); - change_syscall(_metadata, tracee, __NR_getppid, 0); + change_syscall_nr(_metadata, tracee, __NR_getppid); break; case 0x1003: /* skip gettid with valid return code. */ EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee)); - change_syscall(_metadata, tracee, -1, 45000); + change_syscall_ret(_metadata, tracee, 45000); break; case 0x1004: /* skip openat with error. */ EXPECT_EQ(__NR_openat, get_syscall(_metadata, tracee)); - change_syscall(_metadata, tracee, -1, -ESRCH); + change_syscall_ret(_metadata, tracee, -ESRCH); break; case 0x1005: /* do nothing (allow getppid) */ @@ -1897,12 +1982,21 @@ void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee, } +FIXTURE(TRACE_syscall) { + struct sock_fprog prog; + pid_t tracer, mytid, mypid, parent; + long syscall_nr; +}; + void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, int status, void *args) { - int ret, nr; + int ret; unsigned long msg; static bool entry; + long syscall_nr_val, syscall_ret_val; + long *syscall_nr = NULL, *syscall_ret = NULL; + FIXTURE_DATA(TRACE_syscall) *self = args; /* * The traditional way to tell PTRACE_SYSCALL entry/exit @@ -1916,24 +2010,48 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, EXPECT_EQ(entry ? PTRACE_EVENTMSG_SYSCALL_ENTRY : PTRACE_EVENTMSG_SYSCALL_EXIT, msg); - if (!entry) - return; + /* + * Some architectures only support setting return values during + * syscall exit under ptrace, and on exit the syscall number may + * no longer be available. Therefore, save the initial sycall + * number here, so it can be examined during both entry and exit + * phases. + */ + if (entry) + self->syscall_nr = get_syscall(_metadata, tracee); - nr = get_syscall(_metadata, tracee); + /* + * Depending on the architecture's syscall setting abilities, we + * pick which things to set during this phase (entry or exit). + */ + if (entry == ptrace_entry_set_syscall_nr) + syscall_nr = &syscall_nr_val; + if (entry == ptrace_entry_set_syscall_ret) + syscall_ret = &syscall_ret_val; + + /* Now handle the actual rewriting cases. */ + switch (self->syscall_nr) { + case __NR_getpid: + syscall_nr_val = __NR_getppid; + /* Never change syscall return for this case. */ + syscall_ret = NULL; + break; + case __NR_gettid: + syscall_nr_val = -1; + syscall_ret_val = 45000; + break; + case __NR_openat: + syscall_nr_val = -1; + syscall_ret_val = -ESRCH; + break; + default: + /* Unhandled, do nothing. */ + return; + } - if (nr == __NR_getpid) - change_syscall(_metadata, tracee, __NR_getppid, 0); - if (nr == __NR_gettid) - change_syscall(_metadata, tracee, -1, 45000); - if (nr == __NR_openat) - change_syscall(_metadata, tracee, -1, -ESRCH); + __change_syscall(_metadata, tracee, syscall_nr, syscall_ret); } -FIXTURE(TRACE_syscall) { - struct sock_fprog prog; - pid_t tracer, mytid, mypid, parent; -}; - FIXTURE_VARIANT(TRACE_syscall) { /* * All of the SECCOMP_RET_TRACE behaviors can be tested with either @@ -1992,7 +2110,7 @@ FIXTURE_SETUP(TRACE_syscall) self->tracer = setup_trace_fixture(_metadata, variant->use_ptrace ? tracer_ptrace : tracer_seccomp, - NULL, variant->use_ptrace); + self, variant->use_ptrace); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); @@ -3142,11 +3260,11 @@ skip: static int user_notif_syscall(int nr, unsigned int flags) { struct sock_filter filter[] = { - BPF_STMT(BPF_LD+BPF_W+BPF_ABS, + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1), - BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF), - BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, nr, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; struct sock_fprog prog = { @@ -3699,7 +3817,7 @@ TEST(user_notification_filter_empty) long ret; int status; struct pollfd pollfd; - struct clone_args args = { + struct __clone_args args = { .flags = CLONE_FILES, .exit_signal = SIGCHLD, }; @@ -3715,7 +3833,7 @@ TEST(user_notification_filter_empty) if (pid == 0) { int listener; - listener = user_notif_syscall(__NR_mknod, SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_mknodat, SECCOMP_FILTER_FLAG_NEW_LISTENER); if (listener < 0) _exit(EXIT_FAILURE); @@ -3753,7 +3871,7 @@ TEST(user_notification_filter_empty_threaded) long ret; int status; struct pollfd pollfd; - struct clone_args args = { + struct __clone_args args = { .flags = CLONE_FILES, .exit_signal = SIGCHLD, }; |