aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/auditsc.c8
-rw-r--r--kernel/cred.c2
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/irq/Kconfig2
-rw-r--r--kernel/irq/debug.h38
-rw-r--r--kernel/irq/irqdomain.c47
-rw-r--r--kernel/irq_work.c1
-rw-r--r--kernel/itimer.c8
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/power/swap.c28
-rw-r--r--kernel/rcutree.c1
-rw-r--r--kernel/sched/core.c22
-rw-r--r--kernel/sched/fair.c18
-rw-r--r--kernel/sched/features.h1
-rw-r--r--kernel/seccomp.c458
-rw-r--r--kernel/signal.c9
-rw-r--r--kernel/sys.c12
-rw-r--r--kernel/time/Kconfig4
-rw-r--r--kernel/time/tick-broadcast.c11
-rw-r--r--kernel/time/tick-sched.c4
-rw-r--r--kernel/trace/trace.c8
-rw-r--r--kernel/trace/trace.h4
-rw-r--r--kernel/trace/trace_output.c5
24 files changed, 586 insertions, 112 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index af1de0f34eae..4b96415527b8 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -67,6 +67,7 @@
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/fs_struct.h>
+#include <linux/compat.h>
#include "audit.h"
@@ -2710,13 +2711,16 @@ void audit_core_dumps(long signr)
audit_log_end(ab);
}
-void __audit_seccomp(unsigned long syscall)
+void __audit_seccomp(unsigned long syscall, long signr, int code)
{
struct audit_buffer *ab;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
- audit_log_abend(ab, "seccomp", SIGKILL);
+ audit_log_abend(ab, "seccomp", signr);
audit_log_format(ab, " syscall=%ld", syscall);
+ audit_log_format(ab, " compat=%d", is_compat_task());
+ audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current));
+ audit_log_format(ab, " code=0x%x", code);
audit_log_end(ab);
}
diff --git a/kernel/cred.c b/kernel/cred.c
index 97b36eeca4c9..e70683d9ec32 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -386,6 +386,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
struct cred *new;
int ret;
+ p->replacement_session_keyring = NULL;
+
if (
#ifdef CONFIG_KEYS
!p->cred->thread_keyring &&
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6a9ec4cd8f5..fd126f82b57c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3183,7 +3183,7 @@ static void perf_event_for_each(struct perf_event *event,
perf_event_for_each_child(event, func);
func(event);
list_for_each_entry(sibling, &event->sibling_list, group_entry)
- perf_event_for_each_child(event, func);
+ perf_event_for_each_child(sibling, func);
mutex_unlock(&ctx->mutex);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index b9372a0bff18..f7cf6fb107ec 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -34,6 +34,7 @@
#include <linux/cgroup.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
+#include <linux/seccomp.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
@@ -170,6 +171,7 @@ void free_task(struct task_struct *tsk)
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
+ put_seccomp_filter(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@@ -1162,6 +1164,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto fork_out;
ftrace_graph_init_task(p);
+ get_seccomp_filter(p);
rt_mutex_init_task(p);
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index cf1a4a68ce44..d1a758bc972a 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -62,7 +62,7 @@ config IRQ_DOMAIN_DEBUG
help
This option will show the mapping relationship between hardware irq
numbers and Linux irq numbers. The mapping is exposed via debugfs
- in the file "virq_mapping".
+ in the file "irq_domain_mapping".
If you don't know what this means you don't need it.
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
index 97a8bfadc88a..e75e29e4434a 100644
--- a/kernel/irq/debug.h
+++ b/kernel/irq/debug.h
@@ -4,10 +4,10 @@
#include <linux/kallsyms.h>
-#define P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
-#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
+#define ___P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
+#define ___PS(f) if (desc->istate & f) printk("%14s set\n", #f)
/* FIXME */
-#define PD(f) do { } while (0)
+#define ___PD(f) do { } while (0)
static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
{
@@ -23,23 +23,23 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
print_symbol("%s\n", (unsigned long)desc->action->handler);
}
- P(IRQ_LEVEL);
- P(IRQ_PER_CPU);
- P(IRQ_NOPROBE);
- P(IRQ_NOREQUEST);
- P(IRQ_NOTHREAD);
- P(IRQ_NOAUTOEN);
+ ___P(IRQ_LEVEL);
+ ___P(IRQ_PER_CPU);
+ ___P(IRQ_NOPROBE);
+ ___P(IRQ_NOREQUEST);
+ ___P(IRQ_NOTHREAD);
+ ___P(IRQ_NOAUTOEN);
- PS(IRQS_AUTODETECT);
- PS(IRQS_REPLAY);
- PS(IRQS_WAITING);
- PS(IRQS_PENDING);
+ ___PS(IRQS_AUTODETECT);
+ ___PS(IRQS_REPLAY);
+ ___PS(IRQS_WAITING);
+ ___PS(IRQS_PENDING);
- PD(IRQS_INPROGRESS);
- PD(IRQS_DISABLED);
- PD(IRQS_MASKED);
+ ___PD(IRQS_INPROGRESS);
+ ___PD(IRQS_DISABLED);
+ ___PD(IRQS_MASKED);
}
-#undef P
-#undef PS
-#undef PD
+#undef ___P
+#undef ___PS
+#undef ___PD
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 3601f3fbf67c..0e0ba5f840b2 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -23,7 +23,6 @@ static LIST_HEAD(irq_domain_list);
static DEFINE_MUTEX(irq_domain_mutex);
static DEFINE_MUTEX(revmap_trees_mutex);
-static unsigned int irq_virq_count = NR_IRQS;
static struct irq_domain *irq_default_domain;
/**
@@ -184,13 +183,16 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
}
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
+ unsigned int max_irq,
const struct irq_domain_ops *ops,
void *host_data)
{
struct irq_domain *domain = irq_domain_alloc(of_node,
IRQ_DOMAIN_MAP_NOMAP, ops, host_data);
- if (domain)
+ if (domain) {
+ domain->revmap_data.nomap.max_irq = max_irq ? max_irq : ~0;
irq_domain_add(domain);
+ }
return domain;
}
@@ -262,22 +264,6 @@ void irq_set_default_host(struct irq_domain *domain)
irq_default_domain = domain;
}
-/**
- * irq_set_virq_count() - Set the maximum number of linux irqs
- * @count: number of linux irqs, capped with NR_IRQS
- *
- * This is mainly for use by platforms like iSeries who want to program
- * the virtual irq number in the controller to avoid the reverse mapping
- */
-void irq_set_virq_count(unsigned int count)
-{
- pr_debug("irq: Trying to set virq count to %d\n", count);
-
- BUG_ON(count < NUM_ISA_INTERRUPTS);
- if (count < NR_IRQS)
- irq_virq_count = count;
-}
-
static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
irq_hw_number_t hwirq)
{
@@ -320,13 +306,12 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
pr_debug("irq: create_direct virq allocation failed\n");
return 0;
}
- if (virq >= irq_virq_count) {
+ if (virq >= domain->revmap_data.nomap.max_irq) {
pr_err("ERROR: no free irqs available below %i maximum\n",
- irq_virq_count);
+ domain->revmap_data.nomap.max_irq);
irq_free_desc(virq);
return 0;
}
-
pr_debug("irq: create_direct obtained virq %d\n", virq);
if (irq_setup_virq(domain, virq, virq)) {
@@ -350,7 +335,8 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
unsigned int irq_create_mapping(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
- unsigned int virq, hint;
+ unsigned int hint;
+ int virq;
pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
@@ -377,13 +363,13 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
return irq_domain_legacy_revmap(domain, hwirq);
/* Allocate a virtual interrupt number */
- hint = hwirq % irq_virq_count;
+ hint = hwirq % nr_irqs;
if (hint == 0)
hint++;
virq = irq_alloc_desc_from(hint, 0);
- if (!virq)
+ if (virq <= 0)
virq = irq_alloc_desc_from(1, 0);
- if (!virq) {
+ if (virq <= 0) {
pr_debug("irq: -> virq allocation failed\n");
return 0;
}
@@ -515,7 +501,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
unsigned int i;
- unsigned int hint = hwirq % irq_virq_count;
+ unsigned int hint = hwirq % nr_irqs;
/* Look for default domain if nececssary */
if (domain == NULL)
@@ -536,7 +522,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
if (data && (data->domain == domain) && (data->hwirq == hwirq))
return i;
i++;
- if (i >= irq_virq_count)
+ if (i >= nr_irqs)
i = 1;
} while(i != hint);
return 0;
@@ -642,8 +628,9 @@ static int virq_debug_show(struct seq_file *m, void *private)
void *data;
int i;
- seq_printf(m, "%-5s %-7s %-15s %-18s %s\n", "virq", "hwirq",
- "chip name", "chip data", "domain name");
+ seq_printf(m, "%-5s %-7s %-15s %-*s %s\n", "irq", "hwirq",
+ "chip name", (int)(2 * sizeof(void *) + 2), "chip data",
+ "domain name");
for (i = 1; i < nr_irqs; i++) {
desc = irq_to_desc(i);
@@ -666,7 +653,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
seq_printf(m, "%-15s ", p);
data = irq_desc_get_chip_data(desc);
- seq_printf(m, "0x%16p ", data);
+ seq_printf(m, data ? "0x%p " : " %p ", data);
if (desc->irq_data.domain && desc->irq_data.domain->of_node)
p = desc->irq_data.domain->of_node->full_name;
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 0c56d44b9fd5..1588e3b2871b 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -11,6 +11,7 @@
#include <linux/irq_work.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
+#include <linux/irqflags.h>
#include <asm/processor.h>
/*
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 22000c3db0dd..8d262b467573 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -284,8 +284,12 @@ SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value,
if (value) {
if(copy_from_user(&set_buffer, value, sizeof(set_buffer)))
return -EFAULT;
- } else
- memset((char *) &set_buffer, 0, sizeof(set_buffer));
+ } else {
+ memset(&set_buffer, 0, sizeof(set_buffer));
+ printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer."
+ " Misfeature support will be removed\n",
+ current->comm);
+ }
error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL);
if (error || !ovalue)
diff --git a/kernel/panic.c b/kernel/panic.c
index 80aed44e345a..8ed89a175d79 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -97,7 +97,7 @@ void panic(const char *fmt, ...)
/*
* Avoid nested stack-dumping if a panic occurs during oops processing
*/
- if (!oops_in_progress)
+ if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
dump_stack();
#endif
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8742fd013a94..eef311a58a64 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -51,6 +51,23 @@
#define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1)
+/*
+ * Number of free pages that are not high.
+ */
+static inline unsigned long low_free_pages(void)
+{
+ return nr_free_pages() - nr_free_highpages();
+}
+
+/*
+ * Number of pages required to be kept free while writing the image. Always
+ * half of all available low pages before the writing starts.
+ */
+static inline unsigned long reqd_free_pages(void)
+{
+ return low_free_pages() / 2;
+}
+
struct swap_map_page {
sector_t entries[MAP_PAGE_ENTRIES];
sector_t next_swap;
@@ -72,7 +89,7 @@ struct swap_map_handle {
sector_t cur_swap;
sector_t first_sector;
unsigned int k;
- unsigned long nr_free_pages, written;
+ unsigned long reqd_free_pages;
u32 crc32;
};
@@ -316,8 +333,7 @@ static int get_swap_writer(struct swap_map_handle *handle)
goto err_rel;
}
handle->k = 0;
- handle->nr_free_pages = nr_free_pages() >> 1;
- handle->written = 0;
+ handle->reqd_free_pages = reqd_free_pages();
handle->first_sector = handle->cur_swap;
return 0;
err_rel:
@@ -352,11 +368,11 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
handle->cur_swap = offset;
handle->k = 0;
}
- if (bio_chain && ++handle->written > handle->nr_free_pages) {
+ if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
error = hib_wait_on_bio_chain(bio_chain);
if (error)
goto out;
- handle->written = 0;
+ handle->reqd_free_pages = reqd_free_pages();
}
out:
return error;
@@ -618,7 +634,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
* Adjust number of free pages after all allocations have been done.
* We don't want to run out of pages when writing.
*/
- handle->nr_free_pages = nr_free_pages() >> 1;
+ handle->reqd_free_pages = reqd_free_pages();
/*
* Start the CRC32 thread.
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1050d6d3922c..d0c5baf1ab18 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1820,7 +1820,6 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
* a quiescent state betweentimes.
*/
local_irq_save(flags);
- WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
rdp = this_cpu_ptr(rsp->rda);
/* Add the callback to our list. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4603b9d8f30a..0533a688ce22 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6405,16 +6405,26 @@ static void __sdt_free(const struct cpumask *cpu_map)
struct sd_data *sdd = &tl->data;
for_each_cpu(j, cpu_map) {
- struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
- if (sd && (sd->flags & SD_OVERLAP))
- free_sched_groups(sd->groups, 0);
- kfree(*per_cpu_ptr(sdd->sd, j));
- kfree(*per_cpu_ptr(sdd->sg, j));
- kfree(*per_cpu_ptr(sdd->sgp, j));
+ struct sched_domain *sd;
+
+ if (sdd->sd) {
+ sd = *per_cpu_ptr(sdd->sd, j);
+ if (sd && (sd->flags & SD_OVERLAP))
+ free_sched_groups(sd->groups, 0);
+ kfree(*per_cpu_ptr(sdd->sd, j));
+ }
+
+ if (sdd->sg)
+ kfree(*per_cpu_ptr(sdd->sg, j));
+ if (sdd->sgp)
+ kfree(*per_cpu_ptr(sdd->sgp, j));
}
free_percpu(sdd->sd);
+ sdd->sd = NULL;
free_percpu(sdd->sg);
+ sdd->sg = NULL;
free_percpu(sdd->sgp);
+ sdd->sgp = NULL;
}
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d97ebdc58f0..e9553640c1c3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -784,7 +784,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
#ifdef CONFIG_SMP
if (entity_is_task(se))
- list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+ list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
#endif
cfs_rq->nr_running++;
}
@@ -3215,6 +3215,8 @@ static int move_one_task(struct lb_env *env)
static unsigned long task_h_load(struct task_struct *p);
+static const unsigned int sched_nr_migrate_break = 32;
+
/*
* move_tasks tries to move up to load_move weighted load from busiest to
* this_rq, as part of a balancing operation within domain "sd".
@@ -3242,7 +3244,7 @@ static int move_tasks(struct lb_env *env)
/* take a breather every nr_migrate tasks */
if (env->loop > env->loop_break) {
- env->loop_break += sysctl_sched_nr_migrate;
+ env->loop_break += sched_nr_migrate_break;
env->flags |= LBF_NEED_BREAK;
break;
}
@@ -3252,7 +3254,7 @@ static int move_tasks(struct lb_env *env)
load = task_h_load(p);
- if (load < 16 && !env->sd->nr_balance_failed)
+ if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
goto next;
if ((load / 2) > env->load_move)
@@ -4407,7 +4409,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
.dst_cpu = this_cpu,
.dst_rq = this_rq,
.idle = idle,
- .loop_break = sysctl_sched_nr_migrate,
+ .loop_break = sched_nr_migrate_break,
};
cpumask_copy(cpus, cpu_active_mask);
@@ -4445,10 +4447,10 @@ redo:
* correctly treated as an imbalance.
*/
env.flags |= LBF_ALL_PINNED;
- env.load_move = imbalance;
- env.src_cpu = busiest->cpu;
- env.src_rq = busiest;
- env.loop_max = busiest->nr_running;
+ env.load_move = imbalance;
+ env.src_cpu = busiest->cpu;
+ env.src_rq = busiest;
+ env.loop_max = min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running);
more_balance:
local_irq_save(flags);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index e61fd73913d0..de00a486c5c6 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -68,3 +68,4 @@ SCHED_FEAT(TTWU_QUEUE, true)
SCHED_FEAT(FORCE_SD_OVERLAP, false)
SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(LB_MIN, false)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e8d76c5895ea..ee376beedaf9 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -3,16 +3,357 @@
*
* Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com>
*
- * This defines a simple but solid secure-computing mode.
+ * Copyright (C) 2012 Google, Inc.
+ * Will Drewry <wad@chromium.org>
+ *
+ * This defines a simple but solid secure-computing facility.
+ *
+ * Mode 1 uses a fixed list of allowed system calls.
+ * Mode 2 allows user-defined system call filters in the form
+ * of Berkeley Packet Filters/Linux Socket Filters.
*/
+#include <linux/atomic.h>
#include <linux/audit.h>
-#include <linux/seccomp.h>
-#include <linux/sched.h>
#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/seccomp.h>
/* #define SECCOMP_DEBUG 1 */
-#define NR_SECCOMP_MODES 1
+
+#ifdef CONFIG_SECCOMP_FILTER
+#include <asm/syscall.h>
+#include <linux/filter.h>
+#include <linux/ptrace.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/tracehook.h>
+#include <linux/uaccess.h>
+
+/**
+ * struct seccomp_filter - container for seccomp BPF programs
+ *
+ * @usage: reference count to manage the object lifetime.
+ * get/put helpers should be used when accessing an instance
+ * outside of a lifetime-guarded section. In general, this
+ * is only needed for handling filters shared across tasks.
+ * @prev: points to a previously installed, or inherited, filter
+ * @len: the number of instructions in the program
+ * @insns: the BPF program instructions to evaluate
+ *
+ * seccomp_filter objects are organized in a tree linked via the @prev
+ * pointer. For any task, it appears to be a singly-linked list starting
+ * with current->seccomp.filter, the most recently attached or inherited filter.
+ * However, multiple filters may share a @prev node, by way of fork(), which
+ * results in a unidirectional tree existing in memory. This is similar to
+ * how namespaces work.
+ *
+ * seccomp_filter objects should never be modified after being attached
+ * to a task_struct (other than @usage).
+ */
+struct seccomp_filter {
+ atomic_t usage;
+ struct seccomp_filter *prev;
+ unsigned short len; /* Instruction count */
+ struct sock_filter insns[];
+};
+
+/* Limit any path through the tree to 256KB worth of instructions. */
+#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
+
+/**
+ * get_u32 - returns a u32 offset into data
+ * @data: a unsigned 64 bit value
+ * @index: 0 or 1 to return the first or second 32-bits
+ *
+ * This inline exists to hide the length of unsigned long. If a 32-bit
+ * unsigned long is passed in, it will be extended and the top 32-bits will be
+ * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
+ * properly returned.
+ *
+ * Endianness is explicitly ignored and left for BPF program authors to manage
+ * as per the specific architecture.
+ */
+static inline u32 get_u32(u64 data, int index)
+{
+ return ((u32 *)&data)[index];
+}
+
+/* Helper for bpf_load below. */
+#define BPF_DATA(_name) offsetof(struct seccomp_data, _name)
+/**
+ * bpf_load: checks and returns a pointer to the requested offset
+ * @off: offset into struct seccomp_data to load from
+ *
+ * Returns the requested 32-bits of data.
+ * seccomp_check_filter() should assure that @off is 32-bit aligned
+ * and not out of bounds. Failure to do so is a BUG.
+ */
+u32 seccomp_bpf_load(int off)
+{
+ struct pt_regs *regs = task_pt_regs(current);
+ if (off == BPF_DATA(nr))
+ return syscall_get_nr(current, regs);
+ if (off == BPF_DATA(arch))
+ return syscall_get_arch(current, regs);
+ if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
+ unsigned long value;
+ int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
+ int index = !!(off % sizeof(u64));
+ syscall_get_arguments(current, regs, arg, 1, &value);
+ return get_u32(value, index);
+ }
+ if (off == BPF_DATA(instruction_pointer))
+ return get_u32(KSTK_EIP(current), 0);
+ if (off == BPF_DATA(instruction_pointer) + sizeof(u32))
+ return get_u32(KSTK_EIP(current), 1);
+ /* seccomp_check_filter should make this impossible. */
+ BUG();
+}
+
+/**
+ * seccomp_check_filter - verify seccomp filter code
+ * @filter: filter to verify
+ * @flen: length of filter
+ *
+ * Takes a previously checked filter (by sk_chk_filter) and
+ * redirects all filter code that loads struct sk_buff data
+ * and related data through seccomp_bpf_load. It also
+ * enforces length and alignment checking of those loads.
+ *
+ * Returns 0 if the rule set is legal or -EINVAL if not.
+ */
+static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
+{
+ int pc;
+ for (pc = 0; pc < flen; pc++) {
+ struct sock_filter *ftest = &filter[pc];
+ u16 code = ftest->code;
+ u32 k = ftest->k;
+
+ switch (code) {
+ case BPF_S_LD_W_ABS:
+ ftest->code = BPF_S_ANC_SECCOMP_LD_W;
+ /* 32-bit aligned and not out of bounds. */
+ if (k >= sizeof(struct seccomp_data) || k & 3)
+ return -EINVAL;
+ continue;
+ case BPF_S_LD_W_LEN:
+ ftest->code = BPF_S_LD_IMM;
+ ftest->k = sizeof(struct seccomp_data);
+ continue;
+ case BPF_S_LDX_W_LEN:
+ ftest->code = BPF_S_LDX_IMM;
+ ftest->k = sizeof(struct seccomp_data);
+ continue;
+ /* Explicitly include allowed calls. */
+ case BPF_S_RET_K:
+ case BPF_S_RET_A:
+ case BPF_S_ALU_ADD_K:
+ case BPF_S_ALU_ADD_X:
+ case BPF_S_ALU_SUB_K:
+ case BPF_S_ALU_SUB_X:
+ case BPF_S_ALU_MUL_K:
+ case BPF_S_ALU_MUL_X:
+ case BPF_S_ALU_DIV_X:
+ case BPF_S_ALU_AND_K:
+ case BPF_S_ALU_AND_X:
+ case BPF_S_ALU_OR_K:
+ case BPF_S_ALU_OR_X:
+ case BPF_S_ALU_LSH_K:
+ case BPF_S_ALU_LSH_X:
+ case BPF_S_ALU_RSH_K:
+ case BPF_S_ALU_RSH_X:
+ case BPF_S_ALU_NEG:
+ case BPF_S_LD_IMM:
+ case BPF_S_LDX_IMM:
+ case BPF_S_MISC_TAX:
+ case BPF_S_MISC_TXA:
+ case BPF_S_ALU_DIV_K:
+ case BPF_S_LD_MEM:
+ case BPF_S_LDX_MEM:
+ case BPF_S_ST:
+ case BPF_S_STX:
+ case BPF_S_JMP_JA:
+ case BPF_S_JMP_JEQ_K:
+ case BPF_S_JMP_JEQ_X:
+ case BPF_S_JMP_JGE_K:
+ case BPF_S_JMP_JGE_X:
+ case BPF_S_JMP_JGT_K:
+ case BPF_S_JMP_JGT_X:
+ case BPF_S_JMP_JSET_K:
+ case BPF_S_JMP_JSET_X:
+ continue;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+/**
+ * seccomp_run_filters - evaluates all seccomp filters against @syscall
+ * @syscall: number of the current system call
+ *
+ * Returns valid seccomp BPF response codes.
+ */
+static u32 seccomp_run_filters(int syscall)
+{
+ struct seccomp_filter *f;
+ u32 ret = SECCOMP_RET_ALLOW;
+
+ /* Ensure unexpected behavior doesn't result in failing open. */
+ if (WARN_ON(current->seccomp.filter == NULL))
+ return SECCOMP_RET_KILL;
+
+ /*
+ * All filters in the list are evaluated and the lowest BPF return
+ * value always takes priority (ignoring the DATA).
+ */
+ for (f = current->seccomp.filter; f; f = f->prev) {
+ u32 cur_ret = sk_run_filter(NULL, f->insns);
+ if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+ ret = cur_ret;
+ }
+ return ret;
+}
+
+/**
+ * seccomp_attach_filter: Attaches a seccomp filter to current.
+ * @fprog: BPF program to install
+ *
+ * Returns 0 on success or an errno on failure.
+ */
+static long seccomp_attach_filter(struct sock_fprog *fprog)
+{
+ struct seccomp_filter *filter;
+ unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
+ unsigned long total_insns = fprog->len;
+ long ret;
+
+ if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
+ return -EINVAL;
+
+ for (filter = current->seccomp.filter; filter; filter = filter->prev)
+ total_insns += filter->len + 4; /* include a 4 instr penalty */
+ if (total_insns > MAX_INSNS_PER_PATH)
+ return -ENOMEM;
+
+ /*
+ * Installing a seccomp filter requires that the task have
+ * CAP_SYS_ADMIN in its namespace or be running with no_new_privs.
+ * This avoids scenarios where unprivileged tasks can affect the
+ * behavior of privileged children.
+ */
+ if (!current->no_new_privs &&
+ security_capable_noaudit(current_cred(), current_user_ns(),
+ CAP_SYS_ADMIN) != 0)
+ return -EACCES;
+
+ /* Allocate a new seccomp_filter */
+ filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
+ GFP_KERNEL|__GFP_NOWARN);
+ if (!filter)
+ return -ENOMEM;
+ atomic_set(&filter->usage, 1);
+ filter->len = fprog->len;
+
+ /* Copy the instructions from fprog. */
+ ret = -EFAULT;
+ if (copy_from_user(filter->insns, fprog->filter, fp_size))
+ goto fail;
+
+ /* Check and rewrite the fprog via the skb checker */
+ ret = sk_chk_filter(filter->insns, filter->len);
+ if (ret)
+ goto fail;
+
+ /* Check and rewrite the fprog for seccomp use */
+ ret = seccomp_check_filter(filter->insns, filter->len);
+ if (ret)
+ goto fail;
+
+ /*
+ * If there is an existing filter, make it the prev and don't drop its
+ * task reference.
+ */
+ filter->prev = current->seccomp.filter;
+ current->seccomp.filter = filter;
+ return 0;
+fail:
+ kfree(filter);
+ return ret;
+}
+
+/**
+ * seccomp_attach_user_filter - attaches a user-supplied sock_fprog
+ * @user_filter: pointer to the user data containing a sock_fprog.
+ *
+ * Returns 0 on success and non-zero otherwise.
+ */
+long seccomp_attach_user_filter(char __user *user_filter)
+{
+ struct sock_fprog fprog;
+ long ret = -EFAULT;
+
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ struct compat_sock_fprog fprog32;
+ if (copy_from_user(&fprog32, user_filter, sizeof(fprog32)))
+ goto out;
+ fprog.len = fprog32.len;
+ fprog.filter = compat_ptr(fprog32.filter);
+ } else /* falls through to the if below. */
+#endif
+ if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
+ goto out;
+ ret = seccomp_attach_filter(&fprog);
+out:
+ return ret;
+}
+
+/* get_seccomp_filter - increments the reference count of the filter on @tsk */
+void get_seccomp_filter(struct task_struct *tsk)
+{
+ struct seccomp_filter *orig = tsk->seccomp.filter;
+ if (!orig)
+ return;
+ /* Reference count is bounded by the number of total processes. */
+ atomic_inc(&orig->usage);
+}
+
+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+ struct seccomp_filter *orig = tsk->seccomp.filter;
+ /* Clean up single-reference branches iteratively. */
+ while (orig && atomic_dec_and_test(&orig->usage)) {
+ struct seccomp_filter *freeme = orig;
+ orig = orig->prev;
+ kfree(freeme);
+ }
+}
+
+/**
+ * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
+ * @syscall: syscall number to send to userland
+ * @reason: filter-supplied reason code to send to userland (via si_errno)
+ *
+ * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
+ */
+static void seccomp_send_sigsys(int syscall, int reason)
+{
+ struct siginfo info;
+ memset(&info, 0, sizeof(info));
+ info.si_signo = SIGSYS;
+ info.si_code = SYS_SECCOMP;
+ info.si_call_addr = (void __user *)KSTK_EIP(current);
+ info.si_errno = reason;
+ info.si_arch = syscall_get_arch(current, task_pt_regs(current));
+ info.si_syscall = syscall;
+ force_sig_info(SIGSYS, &info, current);
+}
+#endif /* CONFIG_SECCOMP_FILTER */
/*
* Secure computing mode 1 allows only read/write/exit/sigreturn.
@@ -31,13 +372,15 @@ static int mode1_syscalls_32[] = {
};
#endif
-void __secure_computing(int this_syscall)
+int __secure_computing(int this_syscall)
{
int mode = current->seccomp.mode;
- int * syscall;
+ int exit_sig = 0;
+ int *syscall;
+ u32 ret;
switch (mode) {
- case 1:
+ case SECCOMP_MODE_STRICT:
syscall = mode1_syscalls;
#ifdef CONFIG_COMPAT
if (is_compat_task())
@@ -45,9 +388,54 @@ void __secure_computing(int this_syscall)
#endif
do {
if (*syscall == this_syscall)
- return;
+ return 0;
} while (*++syscall);
+ exit_sig = SIGKILL;
+ ret = SECCOMP_RET_KILL;
+ break;
+#ifdef CONFIG_SECCOMP_FILTER
+ case SECCOMP_MODE_FILTER: {
+ int data;
+ ret = seccomp_run_filters(this_syscall);
+ data = ret & SECCOMP_RET_DATA;
+ ret &= SECCOMP_RET_ACTION;
+ switch (ret) {
+ case SECCOMP_RET_ERRNO:
+ /* Set the low-order 16-bits as a errno. */
+ syscall_set_return_value(current, task_pt_regs(current),
+ -data, 0);
+ goto skip;
+ case SECCOMP_RET_TRAP:
+ /* Show the handler the original registers. */
+ syscall_rollback(current, task_pt_regs(current));
+ /* Let the filter pass back 16 bits of data. */
+ seccomp_send_sigsys(this_syscall, data);
+ goto skip;
+ case SECCOMP_RET_TRACE:
+ /* Skip these calls if there is no tracer. */
+ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP))
+ goto skip;
+ /* Allow the BPF to provide the event message */
+ ptrace_event(PTRACE_EVENT_SECCOMP, data);
+ /*
+ * The delivery of a fatal signal during event
+ * notification may silently skip tracer notification.
+ * Terminating the task now avoids executing a system
+ * call that may not be intended.
+ */
+ if (fatal_signal_pending(current))
+ break;
+ return 0;
+ case SECCOMP_RET_ALLOW:
+ return 0;
+ case SECCOMP_RET_KILL:
+ default:
+ break;
+ }
+ exit_sig = SIGSYS;
break;
+ }
+#endif
default:
BUG();
}
@@ -55,8 +443,13 @@ void __secure_computing(int this_syscall)
#ifdef SECCOMP_DEBUG
dump_stack();
#endif
- audit_seccomp(this_syscall);
- do_exit(SIGKILL);
+ audit_seccomp(this_syscall, exit_sig, ret);
+ do_exit(exit_sig);
+#ifdef CONFIG_SECCOMP_FILTER
+skip:
+ audit_seccomp(this_syscall, exit_sig, ret);
+#endif
+ return -1;
}
long prctl_get_seccomp(void)
@@ -64,25 +457,48 @@ long prctl_get_seccomp(void)
return current->seccomp.mode;
}
-long prctl_set_seccomp(unsigned long seccomp_mode)
+/**
+ * prctl_set_seccomp: configures current->seccomp.mode
+ * @seccomp_mode: requested mode to use
+ * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
+ *
+ * This function may be called repeatedly with a @seccomp_mode of
+ * SECCOMP_MODE_FILTER to install additional filters. Every filter
+ * successfully installed will be evaluated (in reverse order) for each system
+ * call the task makes.
+ *
+ * Once current->seccomp.mode is non-zero, it may not be changed.
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
{
- long ret;
+ long ret = -EINVAL;
- /* can set it only once to be even more secure */
- ret = -EPERM;
- if (unlikely(current->seccomp.mode))
+ if (current->seccomp.mode &&
+ current->seccomp.mode != seccomp_mode)
goto out;
- ret = -EINVAL;
- if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) {
- current->seccomp.mode = seccomp_mode;
- set_thread_flag(TIF_SECCOMP);
+ switch (seccomp_mode) {
+ case SECCOMP_MODE_STRICT:
+ ret = 0;
#ifdef TIF_NOTSC
disable_TSC();
#endif
- ret = 0;
+ break;
+#ifdef CONFIG_SECCOMP_FILTER
+ case SECCOMP_MODE_FILTER:
+ ret = seccomp_attach_user_filter(filter);
+ if (ret)
+ goto out;
+ break;
+#endif
+ default:
+ goto out;
}
- out:
+ current->seccomp.mode = seccomp_mode;
+ set_thread_flag(TIF_SECCOMP);
+out:
return ret;
}
diff --git a/kernel/signal.c b/kernel/signal.c
index 17afcaf582d0..1a006b5d9d9d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -160,7 +160,7 @@ void recalc_sigpending(void)
#define SYNCHRONOUS_MASK \
(sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \
- sigmask(SIGTRAP) | sigmask(SIGFPE))
+ sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS))
int next_signal(struct sigpending *pending, sigset_t *mask)
{
@@ -2706,6 +2706,13 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
err |= __put_user(from->si_uid, &to->si_uid);
err |= __put_user(from->si_ptr, &to->si_ptr);
break;
+#ifdef __ARCH_SIGSYS
+ case __SI_SYS:
+ err |= __put_user(from->si_call_addr, &to->si_call_addr);
+ err |= __put_user(from->si_syscall, &to->si_syscall);
+ err |= __put_user(from->si_arch, &to->si_arch);
+ break;
+#endif
default: /* this is just in case for now ... */
err |= __put_user(from->si_pid, &to->si_pid);
err |= __put_user(from->si_uid, &to->si_uid);
diff --git a/kernel/sys.c b/kernel/sys.c
index e7006eb6c1e4..ba0ae8eea6fb 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1908,7 +1908,7 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = prctl_get_seccomp();
break;
case PR_SET_SECCOMP:
- error = prctl_set_seccomp(arg2);
+ error = prctl_set_seccomp(arg2, (char __user *)arg3);
break;
case PR_GET_TSC:
error = GET_TSC_CTL(arg2);
@@ -1979,6 +1979,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = put_user(me->signal->is_child_subreaper,
(int __user *) arg2);
break;
+ case PR_SET_NO_NEW_PRIVS:
+ if (arg2 != 1 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ current->no_new_privs = 1;
+ break;
+ case PR_GET_NO_NEW_PRIVS:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ return current->no_new_privs ? 1 : 0;
default:
error = -EINVAL;
break;
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 2cf9cc7aa103..a20dc8a3c949 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -1,6 +1,10 @@
#
# Timer subsystem related configuration options
#
+
+# Core internal switch. Selected by NO_HZ / HIGH_RES_TIMERS. This is
+# only related to the tick functionality. Oneshot clockevent devices
+# are supported independ of this.
config TICK_ONESHOT
bool
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index e883f57a3cd3..f113755695e2 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -346,7 +346,8 @@ int tick_resume_broadcast(void)
tick_get_broadcast_mask());
break;
case TICKDEV_MODE_ONESHOT:
- broadcast = tick_resume_broadcast_oneshot(bc);
+ if (!cpumask_empty(tick_get_broadcast_mask()))
+ broadcast = tick_resume_broadcast_oneshot(bc);
break;
}
}
@@ -373,6 +374,9 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
{
struct clock_event_device *bc = tick_broadcast_device.evtdev;
+ if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
+ clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
return clockevents_program_event(bc, expires, force);
}
@@ -531,7 +535,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
bc->event_handler = tick_handle_oneshot_broadcast;
- clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
/* Take the do_timer update */
tick_do_timer_cpu = cpu;
@@ -549,6 +552,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
to_cpumask(tmpmask));
if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
+ clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
tick_broadcast_init_next_event(to_cpumask(tmpmask),
tick_next_period);
tick_broadcast_set_event(tick_next_period, 1);
@@ -575,15 +579,12 @@ void tick_broadcast_switch_to_oneshot(void)
unsigned long flags;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
- if (cpumask_empty(tick_get_broadcast_mask()))
- goto end;
tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
bc = tick_broadcast_device.evtdev;
if (bc)
tick_broadcast_setup_oneshot(bc);
-end:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3526038f2836..6a3a5b9ff561 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -534,9 +534,9 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
hrtimer_get_expires(&ts->sched_timer), 0))
break;
}
- /* Update jiffies and reread time */
- tick_do_update_jiffies64(now);
+ /* Reread time and update jiffies */
now = ktime_get();
+ tick_do_update_jiffies64(now);
}
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed7b5d1e12f4..2a22255c1010 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4629,7 +4629,8 @@ static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct ring_buffer *buffer = filp->private_data;
+ struct trace_array *tr = filp->private_data;
+ struct ring_buffer *buffer = tr->buffer;
char buf[64];
int r;
@@ -4647,7 +4648,8 @@ static ssize_t
rb_simple_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct ring_buffer *buffer = filp->private_data;
+ struct trace_array *tr = filp->private_data;
+ struct ring_buffer *buffer = tr->buffer;
unsigned long val;
int ret;
@@ -4734,7 +4736,7 @@ static __init int tracer_init_debugfs(void)
&trace_clock_fops);
trace_create_file("tracing_on", 0644, d_tracer,
- global_trace.buffer, &rb_simple_fops);
+ &global_trace, &rb_simple_fops);
#ifdef CONFIG_DYNAMIC_FTRACE
trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 95059f091a24..f95d65da6db8 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -836,11 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[];
filter)
#include "trace_entries.h"
-#ifdef CONFIG_FUNCTION_TRACER
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
int perf_ftrace_event_register(struct ftrace_event_call *call,
enum trace_reg type, void *data);
#else
#define perf_ftrace_event_register NULL
-#endif /* CONFIG_FUNCTION_TRACER */
+#endif
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 859fae6b1825..df611a0e76c5 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -652,6 +652,8 @@ int trace_print_lat_context(struct trace_iterator *iter)
{
u64 next_ts;
int ret;
+ /* trace_find_next_entry will reset ent_size */
+ int ent_size = iter->ent_size;
struct trace_seq *s = &iter->seq;
struct trace_entry *entry = iter->ent,
*next_entry = trace_find_next_entry(iter, NULL,
@@ -660,6 +662,9 @@ int trace_print_lat_context(struct trace_iterator *iter)
unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
unsigned long rel_usecs;
+ /* Restore the original ent_size */
+ iter->ent_size = ent_size;
+
if (!next_entry)
next_ts = iter->ts;
rel_usecs = ns2usecs(next_ts - iter->ts);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.