clocksource.max_cswd_read_retries= [KNL]
Number of clocksource_watchdog() retries due to
external delays before the clock will be marked
- unstable. Defaults to three retries, that is,
- four attempts to read the clock under test.
+ unstable. Defaults to two retries, that is,
+ three attempts to read the clock under test.
clocksource.verify_n_cpus= [KNL]
Limit the number of CPUs checked for clocksources
hvc<n> Use the hypervisor console device <n>. This is for
both Xen and PowerPC hypervisors.
+ { null | "" }
+ Use to disable console output, i.e., to have kernel
+ console messages discarded.
+ This must be the only console= parameter used on the
+ kernel command line.
+
If the device connected to the port is not a TTY but a braille
device, prepend "brl," before the device type, for instance
console=brl,ttyS0
dump out devices still on the deferred probe list after
retrying.
+ dell_smm_hwmon.ignore_dmi=
+ [HW] Continue probing hardware even if DMI data
+ indicates that the driver is running on unsupported
+ hardware.
+
+ dell_smm_hwmon.force=
+ [HW] Activate driver even if SMM BIOS signature does
+ not match list of supported models and enable otherwise
+ blacklisted features.
+
+ dell_smm_hwmon.power_status=
+ [HW] Report power status in /proc/i8k
+ (disabled by default).
+
+ dell_smm_hwmon.restricted=
+ [HW] Allow controlling fans only if SYS_ADMIN
+ capability is set.
+
+ dell_smm_hwmon.fan_mult=
+ [HW] Factor to multiply fan speed with.
+
+ dell_smm_hwmon.fan_max=
+ [HW] Maximum configurable fan speed.
+
dfltcc= [HW,S390]
Format: { on | off | def_only | inf_only | always }
on: s390 zlib hardware support for compression on
[KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
enabled.
Allows heavy hugetlb users to free up some more
- memory (6 * PAGE_SIZE for each 2MB hugetlb page).
+ memory (7 * PAGE_SIZE for each 2MB hugetlb page).
Format: { on | off (default) }
on: enable the feature
i810= [HW,DRM]
- i8k.ignore_dmi [HW] Continue probing hardware even if DMI data
- indicates that the driver is running on unsupported
- hardware.
- i8k.force [HW] Activate i8k driver even if SMM BIOS signature
- does not match list of supported models.
- i8k.power_status
- [HW] Report power status in /proc/i8k
- (disabled by default)
- i8k.restricted [HW] Allow controlling fans only if SYS_ADMIN
- capability is set.
-
i915.invert_brightness=
[DRM] Invert the sense of the variable that is used to
set the brightness of the panel backlight. Normally a
For details see: Documentation/admin-guide/hw-vuln/mds.rst
+ mem=nn[KMG] [HEXAGON] Set the memory size.
+ Must be specified, otherwise memory size will be 0.
+
mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
Amount of memory to be used in cases as follows:
2 when the kernel is not able to see the whole system memory;
3 memory that lies after 'mem=' boundary is excluded from
the hypervisor, then assigned to KVM guests.
+ 4 to limit the memory available for kdump kernel.
+
+ [ARC,MICROBLAZE] - the limit applies only to low memory,
+ high memory is not affected.
+
+ [ARM64] - only limits memory covered by the linear
+ mapping. The NOMAP regions are not affected.
[X86] Work as limiting max address. Use together
with memmap= to avoid physical address space collisions.
in above case 3, memory may need be hot added after boot
if system memory of hypervisor is not sufficient.
+ mem=nn[KMG]@ss[KMG]
+ [ARM,MIPS] - override the memory layout reported by
+ firmware.
+ Define a memory region of size nn[KMG] starting at
+ ss[KMG].
+ Multiple different regions can be specified with
+ multiple mem= parameters on the command line.
+
mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
memory.
Disable SMAP (Supervisor Mode Access Prevention)
even if it is supported by processor.
- nosmep [X86,PPC]
+ nosmep [X86,PPC64s]
Disable SMEP (Supervisor Mode Execution Prevention)
even if it is supported by processor.
difficult since unequal pointers can no longer be
compared. However, if this command-line option is
specified, then all normal pointers will have their true
- value printed. Pointers printed via %pK may still be
- hashed. This option should only be specified when
+ value printed. This option should only be specified when
debugging the kernel. Please do not use on production
kernels.
Override pmtimer IOPort with a hex value.
e.g. pmtmr=0x508
+ pmu_override= [PPC] Override the PMU.
+ This option takes over the PMU facility, so it is no
+ longer usable by perf. Setting this option starts the
+ PMU counters by setting MMCR0 to 0 (the FC bit is
+ cleared). If a number is given, then MMCR1 is set to
+ that number, otherwise (e.g., 'pmu_override=on'), MMCR1
+ remains 0.
+
pm_debug_messages [SUSPEND,KNL]
Enable suspend/resume debug messages during boot up.
Disable the Correctable Errors Collector,
see CONFIG_RAS_CEC help text.
- rcu_nocbs= [KNL]
- The argument is a cpu list, as described above.
-
- In kernels built with CONFIG_RCU_NOCB_CPU=y, set
- the specified list of CPUs to be no-callback CPUs.
- Invocation of these CPUs' RCU callbacks will be
- offloaded to "rcuox/N" kthreads created for that
- purpose, where "x" is "p" for RCU-preempt, and
- "s" for RCU-sched, and "N" is the CPU number.
- This reduces OS jitter on the offloaded CPUs,
- which can be useful for HPC and real-time
- workloads. It can also improve energy efficiency
- for asymmetric multiprocessors.
+ rcu_nocbs[=cpu-list]
+ [KNL] The optional argument is a cpu list,
+ as described above.
+
+ In kernels built with CONFIG_RCU_NOCB_CPU=y,
+ enable the no-callback CPU mode, which prevents
+ such CPUs' callbacks from being invoked in
+ softirq context. Invocation of such CPUs' RCU
+ callbacks will instead be offloaded to "rcuox/N"
+ kthreads created for that purpose, where "x" is
+ "p" for RCU-preempt, "s" for RCU-sched, and "g"
+ for the kthreads that mediate grace periods; and
+ "N" is the CPU number. This reduces OS jitter on
+ the offloaded CPUs, which can be useful for HPC
+ and real-time workloads. It can also improve
+ energy efficiency for asymmetric multiprocessors.
+
+ If a cpulist is passed as an argument, the specified
+ list of CPUs is set to no-callback mode from boot.
+
+ Otherwise, if the '=' sign and the cpulist
+ arguments are omitted, no CPU will be set to
+ no-callback mode from boot but the mode may be
+ toggled at runtime via cpusets.
rcu_nocb_poll [KNL]
Rather than requiring that offloaded CPUs
(the least-favored priority). Otherwise, when
RCU_BOOST is not set, valid values are 0-99 and
the default is zero (non-realtime operation).
+ When RCU_NOCB_CPU is set, also adjust the
+ priority of NOCB callback kthreads.
rcutree.rcu_nocb_gp_stride= [KNL]
Set the number of NOCB callback kthreads in
on rcutree.qhimark at boot time and to zero to
disable more aggressive help enlistment.
- rcutree.rcu_idle_gp_delay= [KNL]
- Set wakeup interval for idle CPUs that have
- RCU callbacks (RCU_FAST_NO_HZ=y).
-
rcutree.rcu_kick_kthreads= [KNL]
Cause the grace-period kthread to get an extra
wake_up() if it sleeps three times longer than
in seconds.
rcutorture.fwd_progress= [KNL]
- Enable RCU grace-period forward-progress testing
+ Specifies the number of kthreads to be used
+ for RCU grace-period forward-progress testing
for the types of RCU supporting this notion.
+ Defaults to 1 kthread, values less than zero or
+ greater than the number of CPUs cause the number
+ of CPUs to be used.
rcutorture.fwd_progress_div= [KNL]
Specify the fraction of a CPU-stall-warning
period to instead use normal non-expedited
grace-period processing.
+ rcupdate.rcu_task_collapse_lim= [KNL]
+ Set the maximum number of callbacks present
+ at the beginning of a grace period that allows
+ the RCU Tasks flavors to collapse back to using
+ a single callback queue. This switching only
+ occurs when rcupdate.rcu_task_enqueue_lim is
+ set to the default value of -1.
+
+ rcupdate.rcu_task_contend_lim= [KNL]
+ Set the minimum number of callback-queuing-time
+ lock-contention events per jiffy required to
+ cause the RCU Tasks flavors to switch to per-CPU
+ callback queuing. This switching only occurs
+ when rcupdate.rcu_task_enqueue_lim is set to
+ the default value of -1.
+
+ rcupdate.rcu_task_enqueue_lim= [KNL]
+ Set the number of callback queues to use for the
+ RCU Tasks family of RCU flavors. The default
+ of -1 allows this to be automatically (and
+ dynamically) adjusted. This parameter is intended
+ for use in testing.
+
rcupdate.rcu_task_ipi_delay= [KNL]
Set time in jiffies during which RCU tasks will
avoid sending IPIs, starting with the beginning
Specific mitigations can also be selected manually:
retpoline - replace indirect branches
- retpoline,generic - google's original retpoline
- retpoline,amd - AMD-specific minimal thunk
+ retpoline,generic - Retpolines
+ retpoline,lfence - LFENCE; indirect branch
+ retpoline,amd - alias for retpoline,lfence
+ eibrs - enhanced IBRS
+ eibrs,retpoline - enhanced IBRS + Retpolines
+ eibrs,lfence - enhanced IBRS + LFENCE
Not specifying this option is equivalent to
spectre_v2=auto.
controller on both pseries and powernv
platforms. Only useful on POWER9 and above.
+ xive.store-eoi=off [PPC]
+ By default on POWER10 and above, the kernel will use
+ stores for EOI handling when the XIVE interrupt mode
+ is active. This option allows the XIVE driver to use
+ loads instead, as on POWER9.
+
xhci-hcd.quirks [USB,KNL]
A hex value specifying bitmask with supplemental xhci
host controller quirks. Meaning of each bit can be
*/
int __read_mostly suppress_printk;
+ /*
+ * During panic, heavy printk by other CPUs can delay the
+ * panic and risk deadlock on console resources.
+ */
+ static int __read_mostly suppress_panic_printk;
+
#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_lock_dep_map = {
.name = "console_lock"
static int __init control_devkmsg(char *str)
{
- if (__control_devkmsg(str) < 0)
+ if (__control_devkmsg(str) < 0) {
+ pr_warn("printk.devkmsg: bad option string '%s'\n", str);
return 1;
+ }
/*
* Set sysctl string accordingly:
*/
devkmsg_log |= DEVKMSG_LOG_MASK_LOCK;
- return 0;
+ return 1;
}
__setup("printk.devkmsg=", control_devkmsg);
char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
-
+#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
return 0;
}
+#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */
/* Number of registered extended console drivers. */
static int nr_ext_console_drivers;
}
#define up_console_sem() __up_console_sem(_RET_IP_)
+ static bool panic_in_progress(void)
+ {
+ return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID);
+ }
+
/*
* This is used for debugging the mess that is the VT code by
* keeping track if we have the console semaphore held. It's
if (console_trylock())
return 1;
+ /*
+ * It's unsafe to spin once a panic has begun. If we are the
+ * panic CPU, we may have already halted the owner of the
+ * console_sem. If we are not the panic CPU, then we should
+ * avoid taking console_sem, so the panic CPU has a better
+ * chance of cleanly acquiring it later.
+ */
+ if (panic_in_progress())
+ return 0;
+
printk_safe_enter_irqsave(flags);
raw_spin_lock(&console_owner_lock);
if (unlikely(suppress_printk))
return 0;
+ if (unlikely(suppress_panic_printk) &&
+ atomic_read(&panic_cpu) != raw_smp_processor_id())
+ return 0;
+
if (level == LOGLEVEL_SCHED) {
level = LOGLEVEL_DEFAULT;
in_sched = true;
}
#endif
+ static void set_user_specified(struct console_cmdline *c, bool user_specified)
+ {
+ if (!user_specified)
+ return;
+
+ /*
+ * @c console was defined by the user on the command line.
+ * Do not clear when added twice also by SPCR or the device tree.
+ */
+ c->user_specified = true;
+ /* At least one console defined by the user on the command line. */
+ console_set_on_cmdline = 1;
+ }
+
static int __add_preferred_console(char *name, int idx, char *options,
char *brl_options, bool user_specified)
{
if (strcmp(c->name, name) == 0 && c->index == idx) {
if (!brl_options)
preferred_console = i;
- if (user_specified)
- c->user_specified = true;
+ set_user_specified(c, user_specified);
return 0;
}
}
preferred_console = i;
strlcpy(c->name, name, sizeof(c->name));
c->options = options;
- c->user_specified = user_specified;
+ set_user_specified(c, user_specified);
braille_set_options(c, brl_options);
c->index = idx;
*s = 0;
__add_preferred_console(buf, idx, options, brl_options, true);
- console_set_on_cmdline = 1;
return 1;
}
__setup("console=", console_setup);
return 0;
}
+ /*
+ * Return true when this CPU should unlock console_sem without pushing all
+ * messages to the console. This reduces the chance that the console is
+ * locked when the panic CPU tries to use it.
+ */
+ static bool abandon_console_lock_in_panic(void)
+ {
+ if (!panic_in_progress())
+ return false;
+
+ /*
+ * We can use raw_smp_processor_id() here because it is impossible for
+ * the task to be migrated to the panic_cpu, or away from it. If
+ * panic_cpu has already been set, and we're not currently executing on
+ * that CPU, then we never will be.
+ */
+ return atomic_read(&panic_cpu) != raw_smp_processor_id();
+ }
+
/*
* Can we actually use the console at this time on this cpu?
*
{
static char ext_text[CONSOLE_EXT_LOG_MAX];
static char text[CONSOLE_LOG_MAX];
+ static int panic_console_dropped;
unsigned long flags;
bool do_cond_resched, retry;
struct printk_info info;
if (console_seq != r.info->seq) {
console_dropped += r.info->seq - console_seq;
console_seq = r.info->seq;
+ if (panic_in_progress() && panic_console_dropped++ > 10) {
+ suppress_panic_printk = 1;
+ pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n");
+ }
}
if (suppress_message_printing(r.info->level)) {
if (handover)
return;
+ /* Allow panic_cpu to take over the consoles safely */
+ if (abandon_console_lock_in_panic())
+ break;
+
if (do_cond_resched)
cond_resched();
}
* flush, no worries.
*/
retry = prb_read_valid(prb, next_seq, NULL);
- if (retry && console_trylock())
+ if (retry && !abandon_console_lock_in_panic() && console_trylock())
goto again;
}
EXPORT_SYMBOL(console_unlock);
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online",
console_cpu_notify, NULL);
WARN_ON(ret < 0);
+ printk_sysctl_init();
return 0;
}
late_initcall(printk_late_init);
static void wake_up_klogd_work_func(struct irq_work *irq_work)
{
- int pending = __this_cpu_xchg(printk_pending, 0);
+ int pending = this_cpu_xchg(printk_pending, 0);
if (pending & PRINTK_PENDING_OUTPUT) {
/* If trylock fails, someone else is doing the printing */
return;
preempt_disable();
- __this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
+ this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
preempt_enable();
}
#include <asm/page.h> /* for PAGE_SIZE */
#include <asm/byteorder.h> /* cpu_to_le16 */
+ #include <asm/unaligned.h>
#include <linux/string_helpers.h>
#include "kstrtox.h"
+ /* Disable pointer hashing if requested */
+ bool no_hash_pointers __ro_after_init;
+ EXPORT_SYMBOL_GPL(no_hash_pointers);
+
static noinline unsigned long long simple_strntoull(const char *startp, size_t max_chars, char **endp, unsigned int base)
{
const char *cp;
static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
-static void fill_random_ptr_key(struct random_ready_callback *unused)
+static int fill_random_ptr_key(struct notifier_block *nb,
+ unsigned long action, void *data)
{
/* This may be in an interrupt handler. */
queue_work(system_unbound_wq, &enable_ptr_key_work);
+ return 0;
}
-static struct random_ready_callback random_ready = {
- .func = fill_random_ptr_key
+static struct notifier_block random_ready = {
+ .notifier_call = fill_random_ptr_key
};
static int __init initialize_ptr_random(void)
return 0;
}
- ret = add_random_ready_callback(&random_ready);
+ ret = register_random_ready_notifier(&random_ready);
if (!ret) {
return 0;
} else if (ret == -EALREADY) {
return pointer_string(buf, end, (const void *)hashval, spec);
}
+ static char *default_pointer(char *buf, char *end, const void *ptr,
+ struct printf_spec spec)
+ {
+ /*
+ * default is to _not_ leak addresses, so hash before printing,
+ * unless no_hash_pointers is specified on the command line.
+ */
+ if (unlikely(no_hash_pointers))
+ return pointer_string(buf, end, ptr, spec);
+
+ return ptr_to_id(buf, end, ptr, spec);
+ }
+
int kptr_restrict __read_mostly;
static noinline_for_stack
switch (kptr_restrict) {
case 0:
/* Handle as %p, hash and do _not_ leak addresses. */
- return ptr_to_id(buf, end, ptr, spec);
+ return default_pointer(buf, end, ptr, spec);
case 1: {
const struct cred *cred;
struct printf_spec spec, const char *fmt)
{
int nr_bits = max_t(int, spec.field_width, 0);
- /* current bit is 'cur', most recently seen range is [rbot, rtop] */
- int cur, rbot, rtop;
bool first = true;
+ int rbot, rtop;
if (check_pointer(&buf, end, bitmap, spec))
return buf;
- rbot = cur = find_first_bit(bitmap, nr_bits);
- while (cur < nr_bits) {
- rtop = cur;
- cur = find_next_bit(bitmap, nr_bits, cur + 1);
- if (cur < nr_bits && cur <= rtop + 1)
- continue;
-
+ for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) {
if (!first) {
if (buf < end)
*buf = ',';
first = false;
buf = number(buf, end, rbot, default_dec_spec);
- if (rbot < rtop) {
- if (buf < end)
- *buf = '-';
- buf++;
-
- buf = number(buf, end, rtop, default_dec_spec);
- }
+ if (rtop == rbot + 1)
+ continue;
- rbot = cur;
+ if (buf < end)
+ *buf = '-';
+ buf = number(++buf, end, rtop - 1, default_dec_spec);
}
return buf;
}
char output[sizeof("0123 little-endian (0x01234567)")];
char *p = output;
unsigned int i;
- u32 val;
+ u32 orig, val;
if (fmt[1] != 'c' || fmt[2] != 'c')
return error_string(buf, end, "(%p4?)", spec);
if (check_pointer(&buf, end, fourcc, spec))
return buf;
- val = *fourcc & ~BIT(31);
+ orig = get_unaligned(fourcc);
+ val = orig & ~BIT(31);
- for (i = 0; i < sizeof(*fourcc); i++) {
+ for (i = 0; i < sizeof(u32); i++) {
unsigned char c = val >> (i * 8);
/* Print non-control ASCII characters as-is, dot otherwise */
*p++ = isascii(c) && isprint(c) ? c : '.';
}
- strcpy(p, *fourcc & BIT(31) ? " big-endian" : " little-endian");
+ *p++ = ' ';
+ strcpy(p, orig & BIT(31) ? "big-endian" : "little-endian");
p += strlen(p);
*p++ = ' ';
*p++ = '(';
- p = special_hex_number(p, output + sizeof(output) - 2, *fourcc, sizeof(u32));
+ p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32));
*p++ = ')';
*p = '\0';
return widen_string(buf, buf - buf_start, end, spec);
}
- /* Disable pointer hashing if requested */
- bool no_hash_pointers __ro_after_init;
- EXPORT_SYMBOL_GPL(no_hash_pointers);
-
int __init no_hash_pointers_enable(char *str)
{
if (no_hash_pointers)
case 'e':
/* %pe with a non-ERR_PTR gets treated as plain %p */
if (!IS_ERR(ptr))
- break;
+ return default_pointer(buf, end, ptr, spec);
return err_ptr(buf, end, ptr, spec);
case 'u':
case 'k':
default:
return error_string(buf, end, "(einval)", spec);
}
+ default:
+ return default_pointer(buf, end, ptr, spec);
}
-
- /*
- * default is to _not_ leak addresses, so hash before printing,
- * unless no_hash_pointers is specified on the command line.
- */
- if (unlikely(no_hash_pointers))
- return pointer_string(buf, end, ptr, spec);
- else
- return ptr_to_id(buf, end, ptr, spec);
}
/*