From 82985258390e85289940d3663344197344e071f2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 7 Apr 2017 17:20:01 -0400 Subject: kill strlen_user() no callers, no consistent semantics, no sane way to use it... Signed-off-by: Al Viro --- lib/strnlen_user.c | 34 ---------------------------------- 1 file changed, 34 deletions(-) (limited to 'lib') diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 8e105ed4df12..a5f567747ced 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -121,37 +121,3 @@ long strnlen_user(const char __user *str, long count) return 0; } EXPORT_SYMBOL(strnlen_user); - -/** - * strlen_user: - Get the size of a user string INCLUDING final NUL. - * @str: The string to measure. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * Get the size of a NUL-terminated string in user space. - * - * Returns the size of the string INCLUDING the terminating NUL. - * On exception, returns 0. - * - * If there is a limit on the length of a valid string, you may wish to - * consider using strnlen_user() instead. - */ -long strlen_user(const char __user *str) -{ - unsigned long max_addr, src_addr; - - max_addr = user_addr_max(); - src_addr = (unsigned long)str; - if (likely(src_addr < max_addr)) { - unsigned long max = max_addr - src_addr; - long retval; - - user_access_begin(); - retval = do_strnlen_user(str, ~0ul, max); - user_access_end(); - return retval; - } - return 0; -} -EXPORT_SYMBOL(strlen_user); -- cgit v1.2.3 From b5dceda1f7ef66cba6f8d766502f242a27f96e6d Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 15 May 2017 10:34:52 +0530 Subject: lib/raid6: Add log-of-2 table for RAID6 HW requiring disk position The raid6_gfexp table represents {2}^n values for 0 <= n < 256. The Linux async_tx framework pass values from raid6_gfexp as coefficients for each source to prep_dma_pq() callback of DMA channel with PQ capability. This creates problem for RAID6 offload engines (such as Broadcom SBA) which take disk position (i.e. log of {2}) instead of multiplicative cofficients from raid6_gfexp table. This patch adds raid6_gflog table having log-of-2 value for any given x such that 0 <= x < 256. For any given disk coefficient x, the corresponding disk position is given by raid6_gflog[x]. The RAID6 offload engine driver can use this newly added raid6_gflog table to get disk position from multiplicative coefficient. Signed-off-by: Anup Patel Reviewed-by: Scott Branden Reviewed-by: Ray Jui Acked-by: Shaohua Li Signed-off-by: Vinod Koul --- lib/raid6/mktables.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'lib') diff --git a/lib/raid6/mktables.c b/lib/raid6/mktables.c index 39787db588b0..e824d088f72c 100644 --- a/lib/raid6/mktables.c +++ b/lib/raid6/mktables.c @@ -125,6 +125,26 @@ int main(int argc, char *argv[]) printf("EXPORT_SYMBOL(raid6_gfexp);\n"); printf("#endif\n"); + /* Compute log-of-2 table */ + printf("\nconst u8 __attribute__((aligned(256)))\n" + "raid6_gflog[256] =\n" "{\n"); + for (i = 0; i < 256; i += 8) { + printf("\t"); + for (j = 0; j < 8; j++) { + v = 255; + for (k = 0; k < 256; k++) + if (exptbl[k] == (i + j)) { + v = k; + break; + } + printf("0x%02x,%c", v, (j == 7) ? '\n' : ' '); + } + } + printf("};\n"); + printf("#ifdef __KERNEL__\n"); + printf("EXPORT_SYMBOL(raid6_gflog);\n"); + printf("#endif\n"); + /* Compute inverse table x^-1 == x^254 */ printf("\nconst u8 __attribute__((aligned(256)))\n" "raid6_gfinv[256] =\n" "{\n"); -- cgit v1.2.3 From e1b4fc7add72f565d9c35066d85108346e01d3e9 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 14 May 2017 12:04:55 -0300 Subject: fs: update location of filesystems documentation The filesystem documentation was moved from DocBook to Documentation/filesystems/. Update it at the sources. Signed-off-by: Mauro Carvalho Chehab --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e4587ebe52c7..b7882d45f48e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -286,7 +286,7 @@ config DEBUG_FS write to these files. For detailed documentation on the debugfs API, see - Documentation/DocBook/filesystems. + Documentation/filesystems/. If unsure, say N. -- cgit v1.2.3 From 08c76a2f432974de34343a1a323cbeab48321c41 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 14 May 2017 12:06:29 -0300 Subject: lib: update location of kgdb documentation The documentation was moved from DocBook directory. Update its location. Signed-off-by: Mauro Carvalho Chehab --- lib/Kconfig.kgdb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index 533f912638ed..ab4ff0eea776 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -13,7 +13,7 @@ menuconfig KGDB CONFIG_FRAME_POINTER to aid in producing more reliable stack backtraces in the external debugger. Documentation of kernel debugger is available at http://kgdb.sourceforge.net - as well as in DocBook form in Documentation/DocBook/. If + as well as in Documentation/dev-tools/kgdb.rst. If unsure, say N. if KGDB -- cgit v1.2.3 From 719f6a7040f1bdaf96fcc709d272548facb88e90 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 20 Apr 2017 10:52:31 +0200 Subject: printk: Use the main logbuf in NMI when logbuf_lock is available The commit 42a0bb3f71383b457a7d ("printk/nmi: generic solution for safe printk in NMI") caused that printk stores messages into a temporary buffer in NMI context. The buffer is per-CPU and therefore the size is rather limited. It works quite well for NMI backtraces. But there are longer logs that might get printed in NMI context, for example, lockdep warnings, ftrace_dump_on_oops. The temporary buffer is used to avoid deadlocks caused by logbuf_lock. Also it is needed to avoid races with the other temporary buffer that is used when PRINTK_SAFE_CONTEXT is entered. But the main buffer can be used in NMI if the lock is available and we did not interrupt PRINTK_SAFE_CONTEXT. The lock is checked using raw_spin_is_locked(). It might cause false negatives when the lock is taken on another CPU and this CPU is in the safe context from other reasons. Note that the safe context is used also to get console semaphore or when calling console drivers. For this reason, we do the check in printk_nmi_enter(). It makes the handling consistent for the entire NMI handler and avoids reshuffling of the messages. The patch also defines special printk context that allows to use printk_deferred() in NMI. Note that we could not flush the messages to the consoles because console drivers might use many other internal locks. The newly created vprintk_deferred() disables the preemption only around the irq work handling. It is needed there to keep the consistency between the two per-CPU variables. But there is no reason to disable preemption around vprintk_emit(). Finally, the patch puts back explicit serialization of the NMI backtraces from different CPUs. It was removed by the commit a9edc88093287183ac934b ("x86/nmi: Perform a safe NMI stack trace on all CPUs"). It was not needed because the flushing of the temporary per-CPU buffers was serialized. Link: http://lkml.kernel.org/r/1493912763-24873-1-git-send-email-pmladek@suse.com Cc: Steven Rostedt Cc: Andrew Morton Cc: Peter Zijlstra Cc: Russell King Cc: Daniel Thompson Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Chris Metcalf Cc: x86@kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Suggested-by: Sergey Senozhatsky Acked-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- lib/nmi_backtrace.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 4e8a30d1c22f..0bc0a3535a8a 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -86,9 +86,11 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, bool nmi_cpu_backtrace(struct pt_regs *regs) { + static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; int cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { + arch_spin_lock(&lock); if (regs && cpu_in_idle(instruction_pointer(regs))) { pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n", cpu, instruction_pointer(regs)); @@ -99,6 +101,7 @@ bool nmi_cpu_backtrace(struct pt_regs *regs) else dump_stack(); } + arch_spin_unlock(&lock); cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); return true; } -- cgit v1.2.3 From f36776fafbaa0094390dd4e7e3e29805e0b82730 Mon Sep 17 00:00:00 2001 From: Peter Rajnoha Date: Tue, 9 May 2017 15:22:30 +0200 Subject: kobject: support passing in variables for synthetic uevents This patch makes it possible to pass additional arguments in addition to uevent action name when writing /sys/.../uevent attribute. These additional arguments are then inserted into generated synthetic uevent as additional environment variables. Before, we were not able to pass any additional uevent environment variables for synthetic uevents. This made it hard to identify such uevents properly in userspace to make proper distinction between genuine uevents originating from kernel and synthetic uevents triggered from userspace. Also, it was not possible to pass any additional information which would make it possible to optimize and change the way the synthetic uevents are processed back in userspace based on the originating environment of the triggering action in userspace. With the extra additional variables, we are able to pass through this extra information needed and also it makes it possible to synchronize with such synthetic uevents as they can be clearly identified back in userspace. The format for writing the uevent attribute is following: ACTION [UUID [KEY=VALUE ...] There's no change in how "ACTION" is recognized - it stays the same ("add", "change", "remove"). The "ACTION" is the only argument required to generate synthetic uevent, the rest of arguments, that this patch adds support for, are optional. The "UUID" is considered as transaction identifier so it's possible to use the same UUID value for one or more synthetic uevents in which case we logically group these uevents together for any userspace listeners. The "UUID" is expected to be in "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" format where "x" is a hex digit. The value appears in uevent as "SYNTH_UUID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" environment variable. The "KEY=VALUE" pairs can contain alphanumeric characters only. It's possible to define zero or more more pairs - each pair is then delimited by a space character " ". Each pair appears in synthetic uevents as "SYNTH_ARG_KEY=VALUE" environment variable. That means the KEY name gains "SYNTH_ARG_" prefix to avoid possible collisions with existing variables. To pass the "KEY=VALUE" pairs, it's also required to pass in the "UUID" part for the synthetic uevent first. If "UUID" is not passed in, the generated synthetic uevent gains "SYNTH_UUID=0" environment variable automatically so it's possible to identify this situation in userspace when reading generated uevent and so we can still make a difference between genuine and synthetic uevents. Signed-off-by: Peter Rajnoha Signed-off-by: Greg Kroah-Hartman --- lib/kobject_uevent.c | 167 +++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 154 insertions(+), 13 deletions(-) (limited to 'lib') diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 9a2b811966eb..719c155fce20 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -23,6 +23,8 @@ #include #include #include +#include +#include #include #include @@ -52,19 +54,13 @@ static const char *kobject_actions[] = { [KOBJ_OFFLINE] = "offline", }; -/** - * kobject_action_type - translate action string to numeric type - * - * @buf: buffer containing the action string, newline is ignored - * @count: length of buffer - * @type: pointer to the location to store the action type - * - * Returns 0 if the action string was recognized. - */ -int kobject_action_type(const char *buf, size_t count, - enum kobject_action *type) +static int kobject_action_type(const char *buf, size_t count, + enum kobject_action *type, + const char **args) { enum kobject_action action; + size_t count_first; + const char *args_start; int ret = -EINVAL; if (count && (buf[count-1] == '\n' || buf[count-1] == '\0')) @@ -73,11 +69,20 @@ int kobject_action_type(const char *buf, size_t count, if (!count) goto out; + args_start = strnchr(buf, count, ' '); + if (args_start) { + count_first = args_start - buf; + args_start = args_start + 1; + } else + count_first = count; + for (action = 0; action < ARRAY_SIZE(kobject_actions); action++) { - if (strncmp(kobject_actions[action], buf, count) != 0) + if (strncmp(kobject_actions[action], buf, count_first) != 0) continue; - if (kobject_actions[action][count] != '\0') + if (kobject_actions[action][count_first] != '\0') continue; + if (args) + *args = args_start; *type = action; ret = 0; break; @@ -86,6 +91,142 @@ out: return ret; } +static const char *action_arg_word_end(const char *buf, const char *buf_end, + char delim) +{ + const char *next = buf; + + while (next <= buf_end && *next != delim) + if (!isalnum(*next++)) + return NULL; + + if (next == buf) + return NULL; + + return next; +} + +static int kobject_action_args(const char *buf, size_t count, + struct kobj_uevent_env **ret_env) +{ + struct kobj_uevent_env *env = NULL; + const char *next, *buf_end, *key; + int key_len; + int r = -EINVAL; + + if (count && (buf[count - 1] == '\n' || buf[count - 1] == '\0')) + count--; + + if (!count) + return -EINVAL; + + env = kzalloc(sizeof(*env), GFP_KERNEL); + if (!env) + return -ENOMEM; + + /* first arg is UUID */ + if (count < UUID_STRING_LEN || !uuid_is_valid(buf) || + add_uevent_var(env, "SYNTH_UUID=%.*s", UUID_STRING_LEN, buf)) + goto out; + + /* + * the rest are custom environment variables in KEY=VALUE + * format with ' ' delimiter between each KEY=VALUE pair + */ + next = buf + UUID_STRING_LEN; + buf_end = buf + count - 1; + + while (next <= buf_end) { + if (*next != ' ') + goto out; + + /* skip the ' ', key must follow */ + key = ++next; + if (key > buf_end) + goto out; + + buf = next; + next = action_arg_word_end(buf, buf_end, '='); + if (!next || next > buf_end || *next != '=') + goto out; + key_len = next - buf; + + /* skip the '=', value must follow */ + if (++next > buf_end) + goto out; + + buf = next; + next = action_arg_word_end(buf, buf_end, ' '); + if (!next) + goto out; + + if (add_uevent_var(env, "SYNTH_ARG_%.*s=%.*s", + key_len, key, (int) (next - buf), buf)) + goto out; + } + + r = 0; +out: + if (r) + kfree(env); + else + *ret_env = env; + return r; +} + +/** + * kobject_synth_uevent - send synthetic uevent with arguments + * + * @kobj: struct kobject for which synthetic uevent is to be generated + * @buf: buffer containing action type and action args, newline is ignored + * @count: length of buffer + * + * Returns 0 if kobject_synthetic_uevent() is completed with success or the + * corresponding error when it fails. + */ +int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) +{ + char *no_uuid_envp[] = { "SYNTH_UUID=0", NULL }; + enum kobject_action action; + const char *action_args; + struct kobj_uevent_env *env; + const char *msg = NULL, *devpath; + int r; + + r = kobject_action_type(buf, count, &action, &action_args); + if (r) { + msg = "unknown uevent action string\n"; + goto out; + } + + if (!action_args) { + r = kobject_uevent_env(kobj, action, no_uuid_envp); + goto out; + } + + r = kobject_action_args(action_args, + count - (action_args - buf), &env); + if (r == -EINVAL) { + msg = "incorrect uevent action arguments\n"; + goto out; + } + + if (r) + goto out; + + r = kobject_uevent_env(kobj, action, env->envp); + kfree(env); +out: + if (r) { + devpath = kobject_get_path(kobj, GFP_KERNEL); + printk(KERN_WARNING "synth uevent: %s: %s", + devpath ?: "unknown device", + msg ?: "failed to send uevent"); + kfree(devpath); + } + return r; +} + #ifdef CONFIG_NET static int kobj_bcast_filter(struct sock *dsk, struct sk_buff *skb, void *data) { -- cgit v1.2.3 From 105c03614bff2de60adf338e3ee90652b65c2d05 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 30 May 2017 13:31:32 -0700 Subject: bpf: fix stack_depth usage by test_bpf.ko test_bpf.ko doesn't call verifier before selecting interpreter or JITing, hence the tests need to manually specify the amount of stack they consume. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- lib/test_bpf.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index be88cbaadde3..070bde56474c 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -84,6 +84,7 @@ struct bpf_test { } test[MAX_SUBTESTS]; int (*fill_helper)(struct bpf_test *self); __u8 frag_data[MAX_DATA]; + int stack_depth; /* for eBPF only, since tests don't call verifier */ }; /* Large test cases need separate allocation and fill handler. */ @@ -455,6 +456,7 @@ static int __bpf_fill_stxdw(struct bpf_test *self, int size) self->u.ptr.insns = insn; self->u.ptr.len = len; + self->stack_depth = 40; return 0; } @@ -2317,7 +2319,8 @@ static struct bpf_test tests[] = { { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6}, - { { 38, 256 } } + { { 38, 256 } }, + .stack_depth = 64, }, /* BPF_ALU | BPF_MOV | BPF_X */ { @@ -4169,6 +4172,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xff } }, + .stack_depth = 40, }, { "ST_MEM_B: Store/Load byte: max positive", @@ -4181,6 +4185,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x7f } }, + .stack_depth = 40, }, { "STX_MEM_B: Store/Load byte: max negative", @@ -4194,6 +4199,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xff } }, + .stack_depth = 40, }, { "ST_MEM_H: Store/Load half word: max negative", @@ -4206,6 +4212,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xffff } }, + .stack_depth = 40, }, { "ST_MEM_H: Store/Load half word: max positive", @@ -4218,6 +4225,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x7fff } }, + .stack_depth = 40, }, { "STX_MEM_H: Store/Load half word: max negative", @@ -4231,6 +4239,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xffff } }, + .stack_depth = 40, }, { "ST_MEM_W: Store/Load word: max negative", @@ -4243,6 +4252,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xffffffff } }, + .stack_depth = 40, }, { "ST_MEM_W: Store/Load word: max positive", @@ -4255,6 +4265,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x7fffffff } }, + .stack_depth = 40, }, { "STX_MEM_W: Store/Load word: max negative", @@ -4268,6 +4279,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xffffffff } }, + .stack_depth = 40, }, { "ST_MEM_DW: Store/Load double word: max negative", @@ -4280,6 +4292,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xffffffff } }, + .stack_depth = 40, }, { "ST_MEM_DW: Store/Load double word: max negative 2", @@ -4297,6 +4310,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x1 } }, + .stack_depth = 40, }, { "ST_MEM_DW: Store/Load double word: max positive", @@ -4309,6 +4323,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x7fffffff } }, + .stack_depth = 40, }, { "STX_MEM_DW: Store/Load double word: max negative", @@ -4322,6 +4337,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0xffffffff } }, + .stack_depth = 40, }, /* BPF_STX | BPF_XADD | BPF_W/DW */ { @@ -4336,6 +4352,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x22 } }, + .stack_depth = 40, }, { "STX_XADD_W: Test side-effects, r10: 0x12 + 0x10 = 0x22", @@ -4351,6 +4368,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0 } }, + .stack_depth = 40, }, { "STX_XADD_W: Test side-effects, r0: 0x12 + 0x10 = 0x22", @@ -4363,6 +4381,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x12 } }, + .stack_depth = 40, }, { "STX_XADD_W: X + 1 + 1 + 1 + ...", @@ -4384,6 +4403,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x22 } }, + .stack_depth = 40, }, { "STX_XADD_DW: Test side-effects, r10: 0x12 + 0x10 = 0x22", @@ -4399,6 +4419,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0 } }, + .stack_depth = 40, }, { "STX_XADD_DW: Test side-effects, r0: 0x12 + 0x10 = 0x22", @@ -4411,6 +4432,7 @@ static struct bpf_test tests[] = { INTERNAL, { }, { { 0, 0x12 } }, + .stack_depth = 40, }, { "STX_XADD_DW: X + 1 + 1 + 1 + ...", @@ -5809,6 +5831,7 @@ static struct bpf_prog *generate_filter(int which, int *err) /* Type doesn't really matter here as long as it's not unspec. */ fp->type = BPF_PROG_TYPE_SOCKET_FILTER; memcpy(fp->insnsi, fptr, fp->len * sizeof(struct bpf_insn)); + fp->aux->stack_depth = tests[which].stack_depth; /* We cannot error here as we don't need type compatibility * checks. -- cgit v1.2.3 From 0cbaa44841db3d06d2a21ae4ab679882033f3dbe Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Tue, 6 Jun 2017 16:08:39 -0500 Subject: lib: Add crc4 module Add a little helper for crc4 calculations. This works 4-bits-at-a-time, using a simple table approach. We will need this in the FSI core code, as well as any master implementations that need to calculate CRCs in software. Signed-off-by: Jeremy Kerr Signed-off-by: Chris Bostic Signed-off-by: Joel Stanley Signed-off-by: Greg Kroah-Hartman --- lib/Kconfig | 8 ++++++++ lib/Makefile | 1 + lib/crc4.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+) create mode 100644 lib/crc4.c (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 0c8b78a9ae2e..d2fd2623721e 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -158,6 +158,14 @@ config CRC32_BIT endchoice +config CRC4 + tristate "CRC4 functions" + help + This option is provided for the case where no in-kernel-tree + modules require CRC4 functions, but a module built outside + the kernel tree does. Such modules that use library CRC4 + functions require M here. + config CRC7 tristate "CRC7 functions" help diff --git a/lib/Makefile b/lib/Makefile index 0166fbc0fa81..90cf124e5feb 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -99,6 +99,7 @@ obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o obj-$(CONFIG_CRC32) += crc32.o obj-$(CONFIG_CRC32_SELFTEST) += crc32test.o +obj-$(CONFIG_CRC4) += crc4.o obj-$(CONFIG_CRC7) += crc7.o obj-$(CONFIG_LIBCRC32C) += libcrc32c.o obj-$(CONFIG_CRC8) += crc8.o diff --git a/lib/crc4.c b/lib/crc4.c new file mode 100644 index 000000000000..cf6db46661be --- /dev/null +++ b/lib/crc4.c @@ -0,0 +1,46 @@ +/* + * crc4.c - simple crc-4 calculations. + * + * This source code is licensed under the GNU General Public License, Version + * 2. See the file COPYING for more details. + */ + +#include +#include + +static const uint8_t crc4_tab[] = { + 0x0, 0x7, 0xe, 0x9, 0xb, 0xc, 0x5, 0x2, + 0x1, 0x6, 0xf, 0x8, 0xa, 0xd, 0x4, 0x3, +}; + +/** + * crc4 - calculate the 4-bit crc of a value. + * @crc: starting crc4 + * @x: value to checksum + * @bits: number of bits in @x to checksum + * + * Returns the crc4 value of @x, using polynomial 0b10111. + * + * The @x value is treated as left-aligned, and bits above @bits are ignored + * in the crc calculations. + */ +uint8_t crc4(uint8_t c, uint64_t x, int bits) +{ + int i; + + /* mask off anything above the top bit */ + x &= (1ull << bits) - 1; + + /* Align to 4-bits */ + bits = (bits + 3) & ~0x3; + + /* Calculate crc4 over four-bit nibbles, starting at the MSbit */ + for (i = bits - 4; i >= 0; i -= 4) + c = crc4_tab[c ^ ((x >> i) & 0xf)]; + + return c; +} +EXPORT_SYMBOL_GPL(crc4); + +MODULE_DESCRIPTION("CRC4 calculations"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 0aed55af88345b5d673240f90e671d79662fb01e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 29 May 2017 12:22:50 -0700 Subject: x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations The pmem driver has a need to transfer data with a persistent memory destination and be able to rely on the fact that the destination writes are not cached. It is sufficient for the writes to be flushed to a cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync() to ensure data-writes have reached a power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn around and fence previous writes with an "sfence". Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and memcpy_flushcache, that guarantee that the destination buffer is not dirty in the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines will be used to replace the "pmem api" (include/linux/pmem.h + arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache() and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE config symbol, and fallback to copy_from_iter_nocache() and plain memcpy() otherwise. This is meant to satisfy the concern from Linus that if a driver wants to do something beyond the normal nocache semantics it should be something private to that driver [1], and Al's concern that anything uaccess related belongs with the rest of the uaccess code [2]. The first consumer of this interface is a new 'copy_from_iter' dax operation so that pmem can inject cache maintenance operations without imposing this overhead on other dax-capable drivers. [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html Cc: Cc: Jan Kara Cc: Jeff Moyer Cc: Ingo Molnar Cc: Christoph Hellwig Cc: Toshi Kani Cc: "H. Peter Anvin" Cc: Al Viro Cc: Thomas Gleixner Cc: Matthew Wilcox Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams --- lib/Kconfig | 3 +++ lib/iov_iter.c | 22 ++++++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 0c8b78a9ae2e..2d1c4b3a085c 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -548,6 +548,9 @@ config ARCH_HAS_SG_CHAIN config ARCH_HAS_PMEM_API bool +config ARCH_HAS_UACCESS_FLUSHCACHE + bool + config ARCH_HAS_MMIO_FLUSH bool diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f835964c9485..c9a69064462f 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -615,6 +615,28 @@ size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) } EXPORT_SYMBOL(copy_from_iter_nocache); +#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) +{ + char *to = addr; + if (unlikely(i->type & ITER_PIPE)) { + WARN_ON(1); + return 0; + } + iterate_and_advance(i, bytes, v, + __copy_from_user_flushcache((to += v.iov_len) - v.iov_len, + v.iov_base, v.iov_len), + memcpy_page_flushcache((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len), + memcpy_flushcache((to += v.iov_len) - v.iov_len, v.iov_base, + v.iov_len) + ) + + return bytes; +} +EXPORT_SYMBOL_GPL(copy_from_iter_flushcache); +#endif + bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; -- cgit v1.2.3 From aa9f979c41043d9fcf7957c99948e20bbddefc7f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 13 Jun 2017 14:28:18 +0200 Subject: networking: use skb_put_zero() Use the recently introduced helper to replace the pattern of skb_put() && memset(), this transformation was done with the following spatch: @@ identifier p; expression len; expression skb; @@ -p = skb_put(skb, len); -memset(p, 0, len); +p = skb_put_zero(skb, len); Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- lib/nlattr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/nlattr.c b/lib/nlattr.c index a7e0b16078df..d09d9746fc5d 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -400,8 +400,7 @@ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { void *start; - start = skb_put(skb, NLA_ALIGN(attrlen)); - memset(start, 0, NLA_ALIGN(attrlen)); + start = skb_put_zero(skb, NLA_ALIGN(attrlen)); return start; } -- cgit v1.2.3 From b7127cfea050a3b371d6da7a3ce9e69942f945f0 Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 13 Jun 2017 16:49:36 -0700 Subject: test_bpf: Add test to make conditional jump cross a large number of insns. On MIPS, conditional branches can only span 32k instructions. To exceed this limit in the JIT with the BPF maximum of 4k insns, we need to choose eBPF insns that expand to more than 8 machine instructions. Use BPF_LD_ABS as it is quite complex. This forces the JIT to invert the sense of the branch to branch around a long jump to the end. This (somewhat) verifies that the branch inversion logic and target address calculation of the long jumps are done correctly. Signed-off-by: David Daney Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- lib/test_bpf.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 070bde56474c..c871e0e76c2a 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -435,6 +435,30 @@ loop: return 0; } +static int bpf_fill_jump_around_ld_abs(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct bpf_insn *insn; + int i = 0; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[i++] = BPF_MOV64_REG(R6, R1); + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JEQ, R0, 10, len - i - 2); + i++; + while (i < len - 1) + insn[i++] = BPF_LD_ABS(BPF_B, 1); + insn[i] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + static int __bpf_fill_stxdw(struct bpf_test *self, int size) { unsigned int len = BPF_MAXINSNS; @@ -5044,6 +5068,14 @@ static struct bpf_test tests[] = { { { ETH_HLEN, 0xbef } }, .fill_helper = bpf_fill_ld_abs_vlan_push_pop, }, + { + "BPF_MAXINSNS: jump around ld_abs", + { }, + INTERNAL, + { 10, 11 }, + { { 2, 10 } }, + .fill_helper = bpf_fill_jump_around_ld_abs, + }, /* * LD_IND / LD_ABS on fragmented SKBs */ -- cgit v1.2.3 From 59ae1d127ac0ae404baf414c434ba2651b793f46 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jun 2017 14:29:20 +0200 Subject: networking: introduce and use skb_put_data() A common pattern with skb_put() is to just want to memcpy() some data into the new space, introduce skb_put_data() for this. An spatch similar to the one for skb_put_zero() converts many of the places using it: @@ identifier p, p2; expression len, skb, data; type t, t2; @@ ( -p = skb_put(skb, len); +p = skb_put_data(skb, data, len); | -p = (t)skb_put(skb, len); +p = skb_put_data(skb, data, len); ) ( p2 = (t2)p; -memcpy(p2, data, len); | -memcpy(p, data, len); ) @@ type t, t2; identifier p, p2; expression skb, data; @@ t *p; ... ( -p = skb_put(skb, sizeof(t)); +p = skb_put_data(skb, data, sizeof(t)); | -p = (t *)skb_put(skb, sizeof(t)); +p = skb_put_data(skb, data, sizeof(t)); ) ( p2 = (t2)p; -memcpy(p2, data, sizeof(*p)); | -memcpy(p, data, sizeof(*p)); ) @@ expression skb, len, data; @@ -memcpy(skb_put(skb, len), data, len); +skb_put_data(skb, data, len); (again, manually post-processed to retain some comments) Reviewed-by: Stephen Hemminger Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- lib/nlattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/nlattr.c b/lib/nlattr.c index d09d9746fc5d..ab15a6c095d3 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -616,7 +616,7 @@ int nla_append(struct sk_buff *skb, int attrlen, const void *data) if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; - memcpy(skb_put(skb, attrlen), data, attrlen); + skb_put_data(skb, data, attrlen); return 0; } EXPORT_SYMBOL(nla_append); -- cgit v1.2.3 From 4df864c1d9afb46e2461a9f808d9f11a42d31bad Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jun 2017 14:29:21 +0200 Subject: networking: make skb_put & friends return void pointers It seems like a historic accident that these return unsigned char *, and in many places that means casts are required, more often than not. Make these functions (skb_put, __skb_put and pskb_put) return void * and remove all the casts across the tree, adding a (u8 *) cast only where the unsigned char pointer was used directly, all done with the following spatch: @@ expression SKB, LEN; typedef u8; identifier fn = { skb_put, __skb_put }; @@ - *(fn(SKB, LEN)) + *(u8 *)fn(SKB, LEN) @@ expression E, SKB, LEN; identifier fn = { skb_put, __skb_put }; type T; @@ - E = ((T *)(fn(SKB, LEN))) + E = fn(SKB, LEN) which actually doesn't cover pskb_put since there are only three users overall. A handful of stragglers were converted manually, notably a macro in drivers/isdn/i4l/isdn_bsdcomp.c and, oddly enough, one of the many instances in net/bluetooth/hci_sock.c. In the former file, I also had to fix one whitespace problem spatch introduced. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- lib/nlattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/nlattr.c b/lib/nlattr.c index ab15a6c095d3..a0c738aa6a79 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -352,7 +352,7 @@ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { struct nlattr *nla; - nla = (struct nlattr *) skb_put(skb, nla_total_size(attrlen)); + nla = skb_put(skb, nla_total_size(attrlen)); nla->nla_type = attrtype; nla->nla_len = nla_attr_size(attrlen); -- cgit v1.2.3 From d48ad080ec0101c2cca92926bed64993ab565c3d Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 22:47:13 -0400 Subject: rhashtable: use get_random_u32 for hash_rnd This is much faster and just as secure. It also has the added benefit of probably returning better randomness at early-boot on systems with architectural RNGs. Signed-off-by: Jason A. Donenfeld Cc: Thomas Graf Cc: Herbert Xu Signed-off-by: Theodore Ts'o --- lib/rhashtable.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/rhashtable.c b/lib/rhashtable.c index d9e7274a04cd..a1eb7c947f46 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -235,7 +235,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, INIT_LIST_HEAD(&tbl->walkers); - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); + tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i); -- cgit v1.2.3 From d06bfd1989fe97623b32d6df4ffa6e4338c99dc8 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 23:06:55 -0400 Subject: random: warn when kernel uses unseeded randomness This enables an important dmesg notification about when drivers have used the crng without it being seeded first. Prior, these errors would occur silently, and so there hasn't been a great way of diagnosing these types of bugs for obscure setups. By adding this as a config option, we can leave it on by default, so that we learn where these issues happen, in the field, will still allowing some people to turn it off, if they really know what they're doing and do not want the log entries. However, we don't leave it _completely_ by default. An earlier version of this patch simply had `default y`. I'd really love that, but it turns out, this problem with unseeded randomness being used is really quite present and is going to take a long time to fix. Thus, as a compromise between log-messages-for-all and nobody-knows, this is `default y`, except it is also `depends on DEBUG_KERNEL`. This will ensure that the curious see the messages while others don't have to. Signed-off-by: Jason A. Donenfeld Signed-off-by: Theodore Ts'o --- lib/Kconfig.debug | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e4587ebe52c7..c4159605bfbf 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1209,6 +1209,22 @@ config STACKTRACE It is also used by various kernel debugging features that require stack trace generation. +config WARN_UNSEEDED_RANDOM + bool "Warn when kernel uses unseeded randomness" + default y + depends on DEBUG_KERNEL + help + Some parts of the kernel contain bugs relating to their use of + cryptographically secure random numbers before it's actually possible + to generate those numbers securely. This setting ensures that these + flaws don't go unnoticed, by enabling a message, should this ever + occur. This will allow people with obscure setups to know when things + are going wrong, so that they might contact developers about fixing + it. + + Say Y here, unless you simply do not care about using unseeded + randomness and do not want a potential warning message in your logs. + config DEBUG_KOBJECT bool "kobject debugging" depends on DEBUG_KERNEL -- cgit v1.2.3 From de77b966ce8adcb4c58d50e2f087320d5479812a Mon Sep 17 00:00:00 2001 From: yuan linyu Date: Sun, 18 Jun 2017 22:48:17 +0800 Subject: net: introduce __skb_put_[zero, data, u8] follow Johannes Berg, semantic patch file as below, @@ identifier p, p2; expression len; expression skb; type t, t2; @@ ( -p = __skb_put(skb, len); +p = __skb_put_zero(skb, len); | -p = (t)__skb_put(skb, len); +p = __skb_put_zero(skb, len); ) ... when != p ( p2 = (t2)p; -memset(p2, 0, len); | -memset(p, 0, len); ) @@ identifier p; expression len; expression skb; type t; @@ ( -t p = __skb_put(skb, len); +t p = __skb_put_zero(skb, len); ) ... when != p ( -memset(p, 0, len); ) @@ type t, t2; identifier p, p2; expression skb; @@ t *p; ... ( -p = __skb_put(skb, sizeof(t)); +p = __skb_put_zero(skb, sizeof(t)); | -p = (t *)__skb_put(skb, sizeof(t)); +p = __skb_put_zero(skb, sizeof(t)); ) ... when != p ( p2 = (t2)p; -memset(p2, 0, sizeof(*p)); | -memset(p, 0, sizeof(*p)); ) @@ expression skb, len; @@ -memset(__skb_put(skb, len), 0, len); +__skb_put_zero(skb, len); @@ expression skb, len, data; @@ -memcpy(__skb_put(skb, len), data, len); +__skb_put_data(skb, data, len); @@ expression SKB, C, S; typedef u8; identifier fn = {__skb_put}; fresh identifier fn2 = fn ## "_u8"; @@ - *(u8 *)fn(SKB, S) = C; + fn2(SKB, C); Signed-off-by: yuan linyu Signed-off-by: David S. Miller --- lib/test_bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_bpf.c b/lib/test_bpf.c index c871e0e76c2a..d9d5a410955c 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -5717,7 +5717,7 @@ static struct sk_buff *populate_skb(char *buf, int size) if (!skb) return NULL; - memcpy(__skb_put(skb, size), buf, size); + __skb_put_data(skb, buf, size); /* Initialize a fake skb with test pattern. */ skb_reset_mac_header(skb); -- cgit v1.2.3 From b952f4dff2751252db073c27c0f8a16a416a2ddc Mon Sep 17 00:00:00 2001 From: yuan linyu Date: Sun, 18 Jun 2017 22:52:04 +0800 Subject: net: manual clean code which call skb_put_[data:zero] Signed-off-by: yuan linyu Signed-off-by: David S. Miller --- lib/nlattr.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/nlattr.c b/lib/nlattr.c index a0c738aa6a79..fb52435be42d 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -398,11 +398,7 @@ EXPORT_SYMBOL(__nla_reserve_64bit); */ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { - void *start; - - start = skb_put_zero(skb, NLA_ALIGN(attrlen)); - - return start; + return skb_put_zero(skb, NLA_ALIGN(attrlen)); } EXPORT_SYMBOL(__nla_reserve_nohdr); -- cgit v1.2.3 From 104b4e5139fe384431ac11c3b8a6cf4a529edf4a Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Tue, 20 Jun 2017 21:01:20 +0300 Subject: percpu_counter: Rename __percpu_counter_add to percpu_counter_add_batch Currently, percpu_counter_add is a wrapper around __percpu_counter_add which is preempt safe due to explicit calls to preempt_disable. Given how __ prefix is used in percpu related interfaces, the naming unfortunately creates the false sense that __percpu_counter_add is less safe than percpu_counter_add. In terms of context-safety, they're equivalent. The only difference is that the __ version takes a batch parameter. Make this a bit more explicit by just renaming __percpu_counter_add to percpu_counter_add_batch. This patch doesn't cause any functional changes. tj: Minor updates to patch description for clarity. Cosmetic indentation updates. Signed-off-by: Nikolay Borisov Signed-off-by: Tejun Heo Cc: Chris Mason Cc: Josef Bacik Cc: David Sterba Cc: Darrick J. Wong Cc: Jan Kara Cc: Jens Axboe Cc: linux-mm@kvack.org Cc: "David S. Miller" --- lib/flex_proportions.c | 6 +++--- lib/percpu_counter.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index a71cf1bdd4c9..2cc1f94e03a1 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -207,7 +207,7 @@ static void fprop_reflect_period_percpu(struct fprop_global *p, if (val < (nr_cpu_ids * PROP_BATCH)) val = percpu_counter_sum(&pl->events); - __percpu_counter_add(&pl->events, + percpu_counter_add_batch(&pl->events, -val + (val >> (period-pl->period)), PROP_BATCH); } else percpu_counter_set(&pl->events, 0); @@ -219,7 +219,7 @@ static void fprop_reflect_period_percpu(struct fprop_global *p, void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) { fprop_reflect_period_percpu(p, pl); - __percpu_counter_add(&pl->events, 1, PROP_BATCH); + percpu_counter_add_batch(&pl->events, 1, PROP_BATCH); percpu_counter_add(&p->events, 1); } @@ -267,6 +267,6 @@ void __fprop_inc_percpu_max(struct fprop_global *p, return; } else fprop_reflect_period_percpu(p, pl); - __percpu_counter_add(&pl->events, 1, PROP_BATCH); + percpu_counter_add_batch(&pl->events, 1, PROP_BATCH); percpu_counter_add(&p->events, 1); } diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 9c21000df0b5..8ee7e5ec21be 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -72,7 +72,7 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) } EXPORT_SYMBOL(percpu_counter_set); -void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; @@ -89,7 +89,7 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) } preempt_enable(); } -EXPORT_SYMBOL(__percpu_counter_add); +EXPORT_SYMBOL(percpu_counter_add_batch); /* * Add up all the per-cpu counts, return the result. This is a more accurate -- cgit v1.2.3 From ce4fecf1fe1518131ff80eebf412de0080fea049 Mon Sep 17 00:00:00 2001 From: Pantelis Antoniou Date: Wed, 21 Jan 2015 19:06:14 +0200 Subject: vsprintf: Add %p extension "%pOF" for device tree 90% of the usage of device node's full_name is printing it out in a kernel message. However, storing the full path for every node is wasteful and redundant. With a custom format specifier, we can generate the full path at run-time and eventually remove the full path from every node. For instance typical use is: pr_info("Frobbing node %s\n", node->full_name); Which can be written now as: pr_info("Frobbing node %pOF\n", node); '%pO' is the base specifier to represent kobjects with '%pOF' representing struct device_node. Currently, struct device_node is the only supported type of kobject. More fine-grained control of formatting includes printing the name, flags, path-spec name and others, explained in the documentation entry. Originally written by Pantelis, but pretty much rewrote the core function using existing string/number functions. The 2 passes were unnecessary and have been removed. Also, updated the checkpatch.pl check. The unittest code was written by Grant Likely. Signed-off-by: Pantelis Antoniou Acked-by: Joe Perches Signed-off-by: Rob Herring --- lib/vsprintf.c | 136 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 136 insertions(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 2d41de3f98a1..ff8f1269f301 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #ifdef CONFIG_BLOCK #include @@ -1470,6 +1471,126 @@ char *flags_string(char *buf, char *end, void *flags_ptr, const char *fmt) return format_flags(buf, end, flags, names); } +static const char *device_node_name_for_depth(const struct device_node *np, int depth) +{ + for ( ; np && depth; depth--) + np = np->parent; + + return kbasename(np->full_name); +} + +static noinline_for_stack +char *device_node_gen_full_name(const struct device_node *np, char *buf, char *end) +{ + int depth; + const struct device_node *parent = np->parent; + static const struct printf_spec strspec = { + .field_width = -1, + .precision = -1, + }; + + /* special case for root node */ + if (!parent) + return string(buf, end, "/", strspec); + + for (depth = 0; parent->parent; depth++) + parent = parent->parent; + + for ( ; depth >= 0; depth--) { + buf = string(buf, end, "/", strspec); + buf = string(buf, end, device_node_name_for_depth(np, depth), + strspec); + } + return buf; +} + +static noinline_for_stack +char *device_node_string(char *buf, char *end, struct device_node *dn, + struct printf_spec spec, const char *fmt) +{ + char tbuf[sizeof("xxxx") + 1]; + const char *p; + int ret; + char *buf_start = buf; + struct property *prop; + bool has_mult, pass; + static const struct printf_spec num_spec = { + .flags = SMALL, + .field_width = -1, + .precision = -1, + .base = 10, + }; + + struct printf_spec str_spec = spec; + str_spec.field_width = -1; + + if (!IS_ENABLED(CONFIG_OF)) + return string(buf, end, "(!OF)", spec); + + if ((unsigned long)dn < PAGE_SIZE) + return string(buf, end, "(null)", spec); + + /* simple case without anything any more format specifiers */ + fmt++; + if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) + fmt = "f"; + + for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { + if (pass) { + if (buf < end) + *buf = ':'; + buf++; + } + + switch (*fmt) { + case 'f': /* full_name */ + buf = device_node_gen_full_name(dn, buf, end); + break; + case 'n': /* name */ + buf = string(buf, end, dn->name, str_spec); + break; + case 'p': /* phandle */ + buf = number(buf, end, (unsigned int)dn->phandle, num_spec); + break; + case 'P': /* path-spec */ + p = kbasename(of_node_full_name(dn)); + if (!p[1]) + p = "/"; + buf = string(buf, end, p, str_spec); + break; + case 'F': /* flags */ + tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; + tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; + tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; + tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; + tbuf[4] = 0; + buf = string(buf, end, tbuf, str_spec); + break; + case 'c': /* major compatible string */ + ret = of_property_read_string(dn, "compatible", &p); + if (!ret) + buf = string(buf, end, p, str_spec); + break; + case 'C': /* full compatible string */ + has_mult = false; + of_property_for_each_string(dn, "compatible", prop, p) { + if (has_mult) + buf = string(buf, end, ",", str_spec); + buf = string(buf, end, "\"", str_spec); + buf = string(buf, end, p, str_spec); + buf = string(buf, end, "\"", str_spec); + + has_mult = true; + } + break; + default: + break; + } + } + + return widen_string(buf, buf - buf_start, end, spec); +} + int kptr_restrict __read_mostly; /* @@ -1566,6 +1687,16 @@ int kptr_restrict __read_mostly; * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long + * - 'O' For a kobject based struct. Must be one of the following: + * - 'OF[fnpPcCF]' For a device tree object + * Without any optional arguments prints the full_name + * f device node full_name + * n device node name + * p device node phandle + * P device node path spec (name + @unit) + * F device node flags + * c major compatible string + * C full compatible string * * ** Please update also Documentation/printk-formats.txt when making changes ** * @@ -1721,6 +1852,11 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, case 'G': return flags_string(buf, end, ptr, fmt); + case 'O': + switch (fmt[1]) { + case 'F': + return device_node_string(buf, end, ptr, spec, fmt + 1); + } } spec.flags |= SMALL; if (spec.field_width == -1) { -- cgit v1.2.3 From 050d228a740a2e4d988801e64b2aee0159542f59 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 May 2017 11:03:30 +0200 Subject: dma-noop: remove dma_supported and mapping_error methods These just duplicate the default behavior if no method is provided. Signed-off-by: Christoph Hellwig --- lib/dma-noop.c | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'lib') diff --git a/lib/dma-noop.c b/lib/dma-noop.c index de26c8b68f34..643a074f139d 100644 --- a/lib/dma-noop.c +++ b/lib/dma-noop.c @@ -54,23 +54,11 @@ static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nent return nents; } -static int dma_noop_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return 0; -} - -static int dma_noop_supported(struct device *dev, u64 mask) -{ - return 1; -} - const struct dma_map_ops dma_noop_ops = { .alloc = dma_noop_alloc, .free = dma_noop_free, .map_page = dma_noop_map_page, .map_sg = dma_noop_map_sg, - .mapping_error = dma_noop_mapping_error, - .dma_supported = dma_noop_supported, }; EXPORT_SYMBOL(dma_noop_ops); -- cgit v1.2.3 From 3be6d9b6da2ca62a4fd73a401b26f4a1dac2a47d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 May 2017 11:04:17 +0200 Subject: dma-virt: remove dma_supported and mapping_error methods These just duplicate the default behavior if no method is provided. Signed-off-by: Christoph Hellwig --- lib/dma-virt.c | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'lib') diff --git a/lib/dma-virt.c b/lib/dma-virt.c index dcd4df1f7174..5c4f11329721 100644 --- a/lib/dma-virt.c +++ b/lib/dma-virt.c @@ -51,22 +51,10 @@ static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl, return nents; } -static int dma_virt_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return false; -} - -static int dma_virt_supported(struct device *dev, u64 mask) -{ - return true; -} - const struct dma_map_ops dma_virt_ops = { .alloc = dma_virt_alloc, .free = dma_virt_free, .map_page = dma_virt_map_page, .map_sg = dma_virt_map_sg, - .mapping_error = dma_virt_mapping_error, - .dma_supported = dma_virt_supported, }; EXPORT_SYMBOL(dma_virt_ops); -- cgit v1.2.3 From 25f1e18870881f3366a5abec27b651983ce9032c Mon Sep 17 00:00:00 2001 From: Vladimir Murzin Date: Mon, 26 Jun 2017 10:18:55 +0100 Subject: dma: Take into account dma_pfn_offset Even though dma-noop-ops assumes 1:1 memory mapping DMA memory range can be different to RAM. For example, ARM STM32F4 MCU offers the possibility to remap SDRAM from 0xc000_0000 to 0x0 to get CPU performance boost, but DMA continue to see SDRAM at 0xc000_0000. This difference in mapping is handled via device-tree "dma-range" property which leads to dev->dma_pfn_offset is set nonzero. To handle such cases take dma_pfn_offset into account. Cc: Joerg Roedel Cc: Christian Borntraeger Reported-by: Benjamin Gaignard Tested-by: Benjamin Gaignard Tested-by: Andras Szemzo Tested-by: Alexandre TORGUE Reviewed-by: Robin Murphy Signed-off-by: Vladimir Murzin Signed-off-by: Christoph Hellwig --- lib/dma-noop.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/dma-noop.c b/lib/dma-noop.c index 643a074f139d..acc4190e2731 100644 --- a/lib/dma-noop.c +++ b/lib/dma-noop.c @@ -7,6 +7,7 @@ #include #include #include +#include static void *dma_noop_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, @@ -16,7 +17,8 @@ static void *dma_noop_alloc(struct device *dev, size_t size, ret = (void *)__get_free_pages(gfp, get_order(size)); if (ret) - *dma_handle = virt_to_phys(ret); + *dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset); + return ret; } @@ -32,7 +34,7 @@ static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - return page_to_phys(page) + offset; + return page_to_phys(page) + offset - PFN_PHYS(dev->dma_pfn_offset); } static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents, @@ -43,11 +45,12 @@ static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nent struct scatterlist *sg; for_each_sg(sgl, sg, nents, i) { + dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset); void *va; BUG_ON(!sg_page(sg)); va = sg_virt(sg); - sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va); + sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va) - offset; sg_dma_len(sg) = sg->length; } -- cgit v1.2.3 From 9c5f6908de03a4f52ba7364b11fcd6116225480c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 29 Jun 2017 21:39:54 -0400 Subject: copy_{from,to}_user(): move kasan checks and might_fault() out-of-line Signed-off-by: Al Viro --- lib/usercopy.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/usercopy.c b/lib/usercopy.c index 1b6010a3beb8..f5d9f08ee032 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -6,8 +6,11 @@ unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; - if (likely(access_ok(VERIFY_READ, from, n))) + might_fault(); + if (likely(access_ok(VERIFY_READ, from, n))) { + kasan_check_write(to, n); res = raw_copy_from_user(to, from, n); + } if (unlikely(res)) memset(to + (n - res), 0, res); return res; @@ -18,8 +21,11 @@ EXPORT_SYMBOL(_copy_from_user); #ifndef INLINE_COPY_TO_USER unsigned long _copy_to_user(void *to, const void __user *from, unsigned long n) { - if (likely(access_ok(VERIFY_WRITE, to, n))) + might_fault(); + if (likely(access_ok(VERIFY_WRITE, to, n))) { + kasan_check_read(from, n); n = raw_copy_to_user(to, from, n); + } return n; } EXPORT_SYMBOL(_copy_to_user); -- cgit v1.2.3 From aa28de275a248879f9828cb9f7ee7e119c72ff96 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 29 Jun 2017 21:45:10 -0400 Subject: iov_iter/hardening: move object size checks to inlined part There we actually have useful information about object sizes. Note: this patch has them done for all iov_iter flavours. Right now we do them twice in iovec case, but that'll change very shortly. Signed-off-by: Al Viro --- lib/iov_iter.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f835964c9485..bc4a63ebe91a 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -535,7 +535,7 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes, return bytes; } -size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) +size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; if (unlikely(i->type & ITER_PIPE)) @@ -550,9 +550,9 @@ size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) return bytes; } -EXPORT_SYMBOL(copy_to_iter); +EXPORT_SYMBOL(_copy_to_iter); -size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) +size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(i->type & ITER_PIPE)) { @@ -569,9 +569,9 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) return bytes; } -EXPORT_SYMBOL(copy_from_iter); +EXPORT_SYMBOL(_copy_from_iter); -bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) +bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(i->type & ITER_PIPE)) { @@ -594,9 +594,9 @@ bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) iov_iter_advance(i, bytes); return true; } -EXPORT_SYMBOL(copy_from_iter_full); +EXPORT_SYMBOL(_copy_from_iter_full); -size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) +size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(i->type & ITER_PIPE)) { @@ -613,9 +613,9 @@ size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) return bytes; } -EXPORT_SYMBOL(copy_from_iter_nocache); +EXPORT_SYMBOL(_copy_from_iter_nocache); -bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) +bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(i->type & ITER_PIPE)) { @@ -637,7 +637,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) iov_iter_advance(i, bytes); return true; } -EXPORT_SYMBOL(copy_from_iter_full_nocache); +EXPORT_SYMBOL(_copy_from_iter_full_nocache); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) @@ -663,7 +663,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, } if (i->type & (ITER_BVEC|ITER_KVEC)) { void *kaddr = kmap_atomic(page); - size_t wanted = copy_from_iter(kaddr + offset, bytes, i); + size_t wanted = _copy_from_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; } else -- cgit v1.2.3 From 72e809ed81edf81b93d3a36b7238ba50d67f043d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 29 Jun 2017 21:52:57 -0400 Subject: iov_iter: sanity checks for copy to/from page primitives for now - just that we don't attempt to cross out of compound page Signed-off-by: Al Viro --- lib/iov_iter.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'lib') diff --git a/lib/iov_iter.c b/lib/iov_iter.c index bc4a63ebe91a..b50a478f9d34 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -639,9 +639,20 @@ bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) } EXPORT_SYMBOL(_copy_from_iter_full_nocache); +static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) +{ + size_t v = n + offset; + if (likely(n <= v && v <= (PAGE_SIZE << compound_order(page)))) + return true; + WARN_ON(1); + return false; +} + size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { + if (unlikely(!page_copy_sane(page, offset, bytes))) + return 0; if (i->type & (ITER_BVEC|ITER_KVEC)) { void *kaddr = kmap_atomic(page); size_t wanted = copy_to_iter(kaddr + offset, bytes, i); @@ -657,6 +668,8 @@ EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { + if (unlikely(!page_copy_sane(page, offset, bytes))) + return 0; if (unlikely(i->type & ITER_PIPE)) { WARN_ON(1); return 0; @@ -713,6 +726,10 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { char *kaddr = kmap_atomic(page), *p = kaddr + offset; + if (unlikely(!page_copy_sane(page, offset, bytes))) { + kunmap_atomic(kaddr); + return 0; + } if (unlikely(i->type & ITER_PIPE)) { kunmap_atomic(kaddr); WARN_ON(1); -- cgit v1.2.3 From 84cbadadc6eafc4798513773a2c8fce37dcd2fb8 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 6 Jul 2017 07:02:24 -0400 Subject: lib: add errseq_t type and infrastructure for handling it An errseq_t is a way of recording errors in one place, and allowing any number of "subscribers" to tell whether an error has been set again since a previous time. It's implemented as an unsigned 32-bit value that is managed with atomic operations. The low order bits are designated to hold an error code (max size of MAX_ERRNO). The upper bits are used as a counter. The API works with consumers sampling an errseq_t value at a particular point in time. Later, that value can be used to tell whether new errors have been set since that time. Note that there is a 1 in 512k risk of collisions here if new errors are being recorded frequently, since we have so few bits to use as a counter. To mitigate this, one bit is used as a flag to tell whether the va