intel_idle.max_cstate= [KNL,HW,ACPI,X86]
0 disables intel_idle and fall back on acpi_idle.
- 1 to 6 specify maximum depth of C-state.
+ 1 to 9 specify maximum depth of C-state.
intel_pstate= [X86]
disable
than or equal to this physical address is ignored.
maxcpus= [SMP] Maximum number of processors that an SMP kernel
- should make use of. maxcpus=n : n >= 0 limits the
- kernel to using 'n' processors. n=0 is a special case,
- it is equivalent to "nosmp", which also disables
- the IO APIC.
+ will bring up during bootup. maxcpus=n : n >= 0 limits
+ the kernel to bring up 'n' processors. Surely after
+ bootup you can bring up the other plugged cpu by executing
+ "echo 1 > /sys/devices/system/cpu/cpuX/online". So maxcpus
+ only takes effect during system bootup.
+ While n=0 is a special case, it is equivalent to "nosmp",
+ which also disables the IO APIC.
max_loop= [LOOP] The number of loop block devices that get
(loop.max_loop) unconditionally pre-created at init time. The default
nr_cpus= [SMP] Maximum number of processors that an SMP kernel
could support. nr_cpus=n : n >= 1 limits the kernel to
- supporting 'n' processors. Later in runtime you can not
- use hotplug cpu feature to put more cpu back to online.
- just like you compile the kernel NR_CPUS=n
+ support 'n' processors. It could be larger than the
+ number of already plugged CPU during bootup, later in
+ runtime you can physically add extra cpu until it reaches
+ n. So during boot up some boot time memory for per-cpu
+ variables need be pre-allocated for later physical cpu
+ hot plugging.
nr_uarts= [SERIAL] maximum number of UARTs to be registered.
PAGE_SIZE is used as alignment.
PCI-PCI bridge can be specified, if resource
windows need to be expanded.
+ To specify the alignment for several
+ instances of a device, the PCI vendor,
+ device, subvendor, and subdevice may be
+ specified, e.g., 4096@pci:8086:9c22:103c:198f
ecrc= Enable/disable PCIe ECRC (transaction layer
end-to-end CRC checking).
bios: Use BIOS/firmware settings. This is the
raid= [HW,RAID]
See Documentation/md.txt.
+ ram_latent_entropy
+ Enable a very simple form of latent entropy extraction
+ from the first 4GB of memory as the bootmem allocator
+ passes the memory pages to the buddy allocator.
+
ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
See Documentation/blockdev/ramdisk.txt.
results in the system call being skipped immediately.
- seccomp syscall wired up
- For best performance, an arch should use seccomp_phase1 and
- seccomp_phase2 directly. It should call seccomp_phase1 for all
- syscalls if TIF_SECCOMP is set, but seccomp_phase1 does not
- need to be called from a ptrace-safe context. It must then
- call seccomp_phase2 if seccomp_phase1 returns anything other
- than SECCOMP_PHASE1_OK or SECCOMP_PHASE1_SKIP.
-
- As an additional optimization, an arch may provide seccomp_data
- directly to seccomp_phase1; this avoids multiple calls
- to the syscall_xyz helpers for every syscall.
-
config SECCOMP_FILTER
def_bool y
depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
gcc-4.5 on). It is based on the commit "Add fuzzing coverage support"
by Dmitry Vyukov <dvyukov@google.com>.
+ config GCC_PLUGIN_LATENT_ENTROPY
+ bool "Generate some entropy during boot and runtime"
+ depends on GCC_PLUGINS
+ help
+ By saying Y here the kernel will instrument some kernel code to
+ extract some entropy from both original and artificially created
+ program state. This will help especially embedded systems where
+ there is little 'natural' source of entropy normally. The cost
+ is some slowdown of the boot process (about 0.5%) and fork and
+ irq processing.
+
+ Note that entropy extracted this way is not cryptographically
+ secure!
+
+ This plugin was ported from grsecurity/PaX. More information at:
+ * https://grsecurity.net/
+ * https://pax.grsecurity.net/
+
config HAVE_CC_STACKPROTECTOR
bool
help
and similar) by implementing an inline arch_within_stack_frames(),
which is used by CONFIG_HARDENED_USERCOPY.
+config THIN_ARCHIVES
+ bool
+ help
+ Select this if the architecture wants to use thin archives
+ instead of ld -r to create the built-in.o files.
+
+config LD_DEAD_CODE_DATA_ELIMINATION
+ bool
+ help
+ Select this if the architecture wants to do dead code and
+ data elimination with the linker by compiling with
+ -ffunction-sections -fdata-sections and linking with
+ --gc-sections.
+
+ This requires that the arch annotates or otherwise protects
+ its external entry points from being discarded. Linker scripts
+ must also merge .text.*, .data.*, and .bss.* correctly into
+ output sections.
+
config HAVE_CONTEXT_TRACKING
bool
help
CFLAGS_btext.o += -fPIC
endif
+ CFLAGS_cputable.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+
ifdef CONFIG_FUNCTION_TRACER
# Do not trace early boot code
CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o hmi.o
+obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
obj-$(CONFIG_PPC64) += vdso64/
obj-$(CONFIG_ALTIVEC) += vecemu.o
flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
- MS_STRICTATIME);
+ MS_STRICTATIME | MS_NOREMOTELOCK);
if (flags & MS_REMOUNT)
retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
return new_ns;
}
+ __latent_entropy
struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
struct user_namespace *user_ns, struct fs_struct *new_fs)
{
#define __compiler_offsetof(a, b) \
__builtin_offsetof(a, b)
-#if GCC_VERSION >= 40100 && GCC_VERSION < 40600
+#if GCC_VERSION >= 40100
# define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
#endif
#endif /* GCC_VERSION >= 40300 */
#if GCC_VERSION >= 40500
+
+ #ifndef __CHECKER__
+ #ifdef LATENT_ENTROPY_PLUGIN
+ #define __latent_entropy __attribute__((latent_entropy))
+ #endif
+ #endif
+
/*
* Mark a position in code as unreachable. This can be used to
* suppress control flow warnings after asm blocks that transfer
*/
#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
-#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+/*
+ * sparse (__CHECKER__) pretends to be gcc, but can't do constant
+ * folding in __builtin_bswap*() (yet), so don't set these for it.
+ */
+#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__)
#if GCC_VERSION >= 40400
#define __HAVE_BUILTIN_BSWAP32__
#define __HAVE_BUILTIN_BSWAP64__
#if GCC_VERSION >= 40800
#define __HAVE_BUILTIN_BSWAP16__
#endif
-#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */
#if GCC_VERSION >= 50000
#define KASAN_ABI_VERSION 4
# define unreachable() do { } while (1)
#endif
+/*
+ * KENTRY - kernel entry point
+ * This can be used to annotate symbols (functions or data) that are used
+ * without their linker symbol being referenced explicitly. For example,
+ * interrupt vector handlers, or functions in the kernel image that are found
+ * programatically.
+ *
+ * Not required for symbols exported with EXPORT_SYMBOL, or initcalls. Those
+ * are handled in their own way (with KEEP() in linker scripts).
+ *
+ * KENTRY can be avoided if the symbols in question are marked as KEEP() in the
+ * linker script. For example an architecture could KEEP() its entire
+ * boot/exception vector code rather than annotate each function and data.
+ */
+#ifndef KENTRY
+# define KENTRY(sym) \
+ extern typeof(sym) sym; \
+ static const unsigned long __kentry_##sym \
+ __used \
+ __attribute__((section("___kentry" "+" #sym ), used)) \
+ = (unsigned long)&sym;
+#endif
+
#ifndef RELOC_HIDE
# define RELOC_HIDE(ptr, off) \
({ unsigned long __ptr; \
# define __attribute_const__ /* unimplemented */
#endif
+ #ifndef __latent_entropy
+ # define __latent_entropy
+ #endif
+
/*
* Tell gcc if a function is cold. The compiler will assume any path
* directly leading to the call is unlikely.
* object's lifetime is managed by something other than RCU. That
* "something other" might be reference counting or simple immortality.
*
- * The seemingly unused void * variable is to validate @p is indeed a pointer
- * type. All pointer types silently cast to void *.
+ * The seemingly unused size_t variable is to validate @p is indeed a pointer
+ * type by making sure it can be dereferenced.
*/
#define lockless_dereference(p) \
({ \
typeof(p) _________p1 = READ_ONCE(p); \
- __maybe_unused const void * const _________p2 = _________p1; \
+ size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
(_________p1); \
})
/* These are for everybody (although not all archs will actually
discard it in modules) */
- #define __init __section(.init.text) __cold notrace
+ #define __init __section(.init.text) __cold notrace __latent_entropy
#define __initdata __section(.init.data)
#define __initconst __constsection(.init.rodata)
#define __exitdata __section(.exit.data)
#define __exit __section(.exit.text) __exitused __cold notrace
/* Used for MEMORY_HOTPLUG */
- #define __meminit __section(.meminit.text) __cold notrace
+ #define __meminit __section(.meminit.text) __cold notrace \
+ __latent_entropy
#define __meminitdata __section(.meminit.data)
#define __meminitconst __constsection(.meminit.rodata)
#define __memexit __section(.memexit.text) __exitused __cold notrace
#ifndef __ASSEMBLY__
-#ifdef CONFIG_LTO
-/* Work around a LTO gcc problem: when there is no reference to a variable
- * in a module it will be moved to the end of the program. This causes
- * reordering of initcalls which the kernel does not like.
- * Add a dummy reference function to avoid this. The function is
- * deleted by the linker.
- */
-#define LTO_REFERENCE_INITCALL(x) \
- ; /* yes this is needed */ \
- static __used __exit void *reference_##x(void) \
- { \
- return &x; \
- }
-#else
-#define LTO_REFERENCE_INITCALL(x)
-#endif
-
-/* initcalls are now grouped by functionality into separate
+/*
+ * initcalls are now grouped by functionality into separate
* subsections. Ordering inside the subsections is determined
* by link order.
* For backwards compatibility, initcall() puts the call in
*
* The `id' arg to __define_initcall() is needed so that multiple initcalls
* can point at the same handler without causing duplicate-symbol build errors.
+ *
+ * Initcalls are run by placing pointers in initcall sections that the
+ * kernel iterates at runtime. The linker can do dead code / data elimination
+ * and remove that completely, so the initcall sections have to be marked
+ * as KEEP() in the linker script.
*/
#define __define_initcall(fn, id) \
static initcall_t __initcall_##fn##id __used \
- __attribute__((__section__(".initcall" #id ".init"))) = fn; \
- LTO_REFERENCE_INITCALL(__initcall_##fn##id)
+ __attribute__((__section__(".initcall" #id ".init"))) = fn;
/*
* Early initcalls run before initializing SMP.
#define __initcall(fn) device_initcall(fn)
-#define __exitcall(fn) \
+#define __exitcall(fn) \
static exitcall_t __exitcall_##fn __exit_call = fn
-#define console_initcall(fn) \
- static initcall_t __initcall_##fn \
+#define console_initcall(fn) \
+ static initcall_t __initcall_##fn \
__used __section(.con_initcall.init) = fn
-#define security_initcall(fn) \
- static initcall_t __initcall_##fn \
+#define security_initcall(fn) \
+ static initcall_t __initcall_##fn \
__used __section(.security_initcall.init) = fn
struct obs_kernel_param {
}
#ifdef CONFIG_MMU
- static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+ static __latent_entropy int dup_mmap(struct mm_struct *mm,
+ struct mm_struct *oldmm)
{
struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
struct rb_node **rb_link, *rb_parent;
}
EXPORT_SYMBOL(get_mm_exe_file);
+/**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+struct file *get_task_exe_file(struct task_struct *task)
+{
+ struct file *exe_file = NULL;
+ struct mm_struct *mm;
+
+ task_lock(task);
+ mm = task->mm;
+ if (mm) {
+ if (!(task->flags & PF_KTHREAD))
+ exe_file = get_mm_exe_file(mm);
+ }
+ task_unlock(task);
+ return exe_file;
+}
+EXPORT_SYMBOL(get_task_exe_file);
+
/**
* get_task_mm - acquire a reference to the task's mm
*
deactivate_mm(tsk, mm);
/*
- * If we're exiting normally, clear a user-space tid field if
- * requested. We leave this alone when dying by signal, to leave
- * the value intact in a core dump, and to save the unnecessary
- * trouble, say, a killed vfork parent shouldn't touch this mm.
- * Userland only wants this done for a sys_exit.
+ * Signal userspace if we're not exiting with a core dump
+ * because we want to leave the value intact for debugging
+ * purposes.
*/
if (tsk->clear_child_tid) {
- if (!(tsk->flags & PF_SIGNALED) &&
+ if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
atomic_read(&mm->mm_users) > 1) {
/*
* We don't check the error code - if userspace has
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
- static struct task_struct *copy_process(unsigned long clone_flags,
+ static __latent_entropy struct task_struct *copy_process(
+ unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *child_tidptr,
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
- threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p);
bad_fork_free_pid:
+ threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
- threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
+ add_latent_entropy();
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
{
- struct rq *rq = rq_of(cfs_rq);
- int cpu = cpu_of(rq);
-
- if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
- unsigned long max = rq->cpu_capacity_orig;
-
+ if (&this_rq()->cfs == cfs_rq) {
/*
* There are a few boundary cases this might miss but it should
* get called often enough that that should (hopefully) not be
*
* See cpu_util().
*/
- cpufreq_update_util(rq_clock(rq),
- min(cfs_rq->avg.util_avg, max), max);
+ cpufreq_update_util(rq_of(cfs_rq), 0);
}
}
static inline void update_load_avg(struct sched_entity *se, int not_used)
{
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- struct rq *rq = rq_of(cfs_rq);
-
- cpufreq_trigger_update(rq_clock(rq));
+ cpufreq_update_util(rq_of(cfs_rq_of(se)), 0);
}
static inline void
pcfs_rq = tg->parent->cfs_rq[cpu];
cfs_rq->throttle_count = pcfs_rq->throttle_count;
- pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+ cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
}
/* conditionally throttle active cfs_rq's from put_prev_entity() */
* run_rebalance_domains is triggered when needed from the scheduler tick.
* Also triggered for nohz idle balancing (with nohz_balancing_kick set).
*/
- static void run_rebalance_domains(struct softirq_action *h)
+ static __latent_entropy void run_rebalance_domains(struct softirq_action *h)
{
struct rq *this_rq = this_rq();
enum cpu_idle_type idle = this_rq->idle_balance ?
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
u64 expires = KTIME_MAX;
unsigned long nextevt;
+ bool is_max_delta;
/*
* Pretend that there is no timer pending if the cpu is offline.
spin_lock(&base->lock);
nextevt = __next_timer_interrupt(base);
+ is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
base->next_expiry = nextevt;
/*
* We have a fresh next event. Check whether we can forward the base:
expires = basem;
base->is_idle = false;
} else {
- expires = basem + (nextevt - basej) * TICK_NSEC;
+ if (!is_max_delta)
+ expires = basem + (nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle:
*/
/*
* This function runs timers and the timer-tq in bottom half context.
*/
- static void run_timer_softirq(struct softirq_action *h)
+ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
{
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
#include <linux/page_owner.h>
#include <linux/kthread.h>
#include <linux/memcontrol.h>
+ #include <linux/random.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
int _node_numa_mem_[MAX_NUMNODES];
#endif
+ #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
+ volatile u64 latent_entropy __latent_entropy;
+ EXPORT_SYMBOL(latent_entropy);
+ #endif
+
/*
* Array of node states.
*/
}
if (PageMappingFlags(page))
page->mapping = NULL;
- if (memcg_kmem_enabled() && PageKmemcg(page)) {
+ if (memcg_kmem_enabled() && PageKmemcg(page))
memcg_kmem_uncharge(page, order);
- __ClearPageKmemcg(page);
- }
if (check_free)
bad += free_pages_check(page);
if (bad)
local_irq_restore(flags);
}
+ bool __meminitdata ram_latent_entropy;
+
+ static int __init setup_ram_latent_entropy(char *str)
+ {
+ ram_latent_entropy = true;
+ return 0;
+ }
+ early_param("ram_latent_entropy", setup_ram_latent_entropy);
+
static void __init __free_pages_boot_core(struct page *page, unsigned int order)
{
unsigned int nr_pages = 1 << order;
__ClearPageReserved(p);
set_page_count(p, 0);
+ if (ram_latent_entropy && !PageHighMem(page) &&
+ page_to_pfn(page) < 0x100000) {
+ u64 hash = 0;
+ size_t index, end = PAGE_SIZE * nr_pages / sizeof(hash);
+ const u64 *data = lowmem_page_address(page);
+
+ for (index = 0; index < end; index++)
+ hash ^= hash + data[index];
+ add_device_randomness((const void *)&hash, sizeof(hash));
+ }
+
page_zone(page)->managed_pages += nr_pages;
set_page_refcounted(page);
__free_pages(page, order);
return NULL;
}
-static inline bool
-should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
- enum compact_result compact_result,
- enum compact_priority *compact_priority,
- int compaction_retries)
-{
- int max_retries = MAX_COMPACT_RETRIES;
-
- if (!order)
- return false;
-
- /*
- * compaction considers all the zone as desperately out of memory
- * so it doesn't really make much sense to retry except when the
- * failure could be caused by insufficient priority
- */
- if (compaction_failed(compact_result)) {
- if (*compact_priority > MIN_COMPACT_PRIORITY) {
- (*compact_priority)--;
- return true;
- }
- return false;
- }
-
- /*
- * make sure the compaction wasn't deferred or didn't bail out early
- * due to locks contention before we declare that we should give up.
- * But do not retry if the given zonelist is not suitable for
- * compaction.
- */
- if (compaction_withdrawn(compact_result))
- return compaction_zonelist_suitable(ac, order, alloc_flags);
-
- /*
- * !costly requests are much more important than __GFP_REPEAT
- * costly ones because they are de facto nofail and invoke OOM
- * killer to move on while costly can fail and users are ready
- * to cope with that. 1/4 retries is rather arbitrary but we
- * would need much more detailed feedback from compaction to
- * make a better decision.
- */
- if (order > PAGE_ALLOC_COSTLY_ORDER)
- max_retries /= 4;
- if (compaction_retries <= max_retries)
- return true;
-
- return false;
-}
#else
static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
return NULL;
}
+#endif /* CONFIG_COMPACTION */
+
static inline bool
should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
enum compact_result compact_result,
}
return false;
}
-#endif /* CONFIG_COMPACTION */
/* Perform direct synchronous page reclaim */
static int
}
out:
- if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) {
- if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) {
- __free_pages(page, order);
- page = NULL;
- } else
- __SetPageKmemcg(page);
+ if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
+ unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+ __free_pages(page, order);
+ page = NULL;
}
if (kmemcheck_enabled && page)
int lru;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
- pages[lru] = global_page_state(NR_LRU_BASE + lru);
+ pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
wmark_low += zone->watermark[WMARK_LOW];
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
- if (populated_zone(zone)) {
+ if (managed_zone(zone)) {
zoneref_set_zone(zone,
&zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
for (j = 0; j < nr_nodes; j++) {
node = node_order[j];
z = &NODE_DATA(node)->node_zones[zone_type];
- if (populated_zone(z)) {
+ if (managed_zone(z)) {
zoneref_set_zone(z,
&zonelist->_zonerefs[pos++]);
check_highest_zone(zone_type);
}
#endif
+static void setup_min_unmapped_ratio(void);
+static void setup_min_slab_ratio(void);
#else /* CONFIG_NUMA */
static void set_zonelist_order(void)
zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
#ifdef CONFIG_NUMA
zone->node = nid;
- pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio)
- / 100;
- pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100;
#endif
zone->name = zone_names[j];
zone->zone_pgdat = pgdat;
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
+
+#ifdef CONFIG_NUMA
+ setup_min_unmapped_ratio();
+ setup_min_slab_ratio();
+#endif
+
return 0;
}
core_initcall(init_per_zone_wmark_min)
}
#ifdef CONFIG_NUMA
+static void setup_min_unmapped_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
+ for_each_online_pgdat(pgdat)
+ pgdat->min_unmapped_pages = 0;
+
+ for_each_zone(zone)
+ zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
+ sysctl_min_unmapped_ratio) / 100;
+}
+
+
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
+ setup_min_unmapped_ratio();
+
+ return 0;
+}
+
+static void setup_min_slab_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
for_each_online_pgdat(pgdat)
pgdat->min_slab_pages = 0;
for_each_zone(zone)
- zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
- sysctl_min_unmapped_ratio) / 100;
- return 0;
+ zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
+ sysctl_min_slab_ratio) / 100;
}
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
- for_each_online_pgdat(pgdat)
- pgdat->min_slab_pages = 0;
+ setup_min_slab_ratio();
- for_each_zone(zone)
- zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
- sysctl_min_slab_ratio) / 100;
return 0;
}
#endif
else
skb_dst_force(skb);
-#ifdef CONFIG_NET_SWITCHDEV
- /* Don't forward if offload device already forwarded */
- if (skb->offload_fwd_mark &&
- skb->offload_fwd_mark == dev->offload_fwd_mark) {
- consume_skb(skb);
- rc = NET_XMIT_SUCCESS;
- goto out;
- }
-#endif
-
txq = netdev_pick_tx(dev, skb, accel_priv);
q = rcu_dereference_bh(txq->qdisc);
}
EXPORT_SYMBOL(netif_rx_ni);
- static void net_tx_action(struct softirq_action *h)
+ static __latent_entropy void net_tx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
}
}
-#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \
- (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE))
+#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE)
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
unsigned char *addr) __read_mostly;
return skb;
}
+/**
+ * netdev_is_rx_handler_busy - check if receive handler is registered
+ * @dev: device to check
+ *
+ * Check if a receive handler is already registered for a given device.
+ * Return true if there one.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+bool netdev_is_rx_handler_busy(struct net_device *dev)
+{
+ ASSERT_RTNL();
+ return dev && rtnl_dereference(dev->rx_handler);
+}
+EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy);
+
/**
* netdev_rx_handler_register - register receive handler
* @dev: device to register a handler for
}
EXPORT_SYMBOL(netif_receive_skb);
-/* Network device is going away, flush any packets still pending
- * Called with irqs disabled.
- */
-static void flush_backlog(void *arg)
+DEFINE_PER_CPU(struct work_struct, flush_works);
+
+/* Network device is going away, flush any packets still pending */
+static void flush_backlog(struct work_struct *work)
{
- struct net_device *dev = arg;
- struct softnet_data *sd = this_cpu_ptr(&softnet_data);
struct sk_buff *skb, *tmp;
+ struct softnet_data *sd;
+
+ local_bh_disable();
+ sd = this_cpu_ptr(&softnet_data);
+ local_irq_disable();
rps_lock(sd);
skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
- if (skb->dev == dev) {
+ if (skb->dev->reg_state == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->input_pkt_queue);
kfree_skb(skb);
input_queue_head_incr(sd);
}
}
rps_unlock(sd);
+ local_irq_enable();
skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
- if (skb->dev == dev) {
+ if (skb->dev->reg_state == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->process_queue);
kfree_skb(skb);
input_queue_head_incr(sd);
}
}
+ local_bh_enable();
+}
+
+static void flush_all_backlogs(void)
+{
+ unsigned int cpu;
+
+ get_online_cpus();
+
+ for_each_online_cpu(cpu)
+ queue_work_on(cpu, system_highpri_wq,
+ per_cpu_ptr(&flush_works, cpu));
+
+ for_each_online_cpu(cpu)
+ flush_work(per_cpu_ptr(&flush_works, cpu));
+
+ put_online_cpus();
}
static int napi_gro_complete(struct sk_buff *skb)
static int process_backlog(struct napi_struct *napi, int quota)
{
- int work = 0;
struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
+ bool again = true;
+ int work = 0;
/* Check if we have pending ipi, its better to send them now,
* not waiting net_rx_action() end.
}
napi->weight = weight_p;
- local_irq_disable();
- while (1) {
+ while (again) {
struct sk_buff *skb;
while ((skb = __skb_dequeue(&sd->process_queue))) {
rcu_read_lock();
- local_irq_enable();
__netif_receive_skb(skb);
rcu_read_unlock();
- local_irq_disable();
input_queue_head_incr(sd);
- if (++work >= quota) {
- local_irq_enable();
+ if (++work >= quota)
return work;
- }
+
}
+ local_irq_disable();
rps_lock(sd);
if (skb_queue_empty(&sd->input_pkt_queue)) {
/*
* and we dont need an smp_mb() memory barrier.
*/
napi->state = 0;
- rps_unlock(sd);
-
- break;
+ again = false;
+ } else {
+ skb_queue_splice_tail_init(&sd->input_pkt_queue,
+ &sd->process_queue);
}
-
- skb_queue_splice_tail_init(&sd->input_pkt_queue,
- &sd->process_queue);
rps_unlock(sd);
+ local_irq_enable();
}
- local_irq_enable();
return work;
}
return work;
}
- static void net_rx_action(struct softirq_action *h)
+ static __latent_entropy void net_rx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies + 2;
EXPORT_SYMBOL(netdev_lower_dev_get_private);
-int dev_get_nest_level(struct net_device *dev,
- bool (*type_check)(const struct net_device *dev))
+int dev_get_nest_level(struct net_device *dev)
{
struct net_device *lower = NULL;
struct list_head *iter;
ASSERT_RTNL();
netdev_for_each_lower_dev(dev, lower, iter) {
- nest = dev_get_nest_level(lower, type_check);
+ nest = dev_get_nest_level(lower);
if (max_nest < nest)
max_nest = nest;
}
- if (type_check(dev))
- max_nest++;
-
- return max_nest;
+ return max_nest + 1;
}
EXPORT_SYMBOL(dev_get_nest_level);
unlist_netdevice(dev);
dev->reg_state = NETREG_UNREGISTERING;
- on_each_cpu(flush_backlog, dev, 1);
}
+ flush_all_backlogs();
synchronize_net();
INIT_LIST_HEAD(&dev->all_adj_list.lower);
INIT_LIST_HEAD(&dev->ptype_all);
INIT_LIST_HEAD(&dev->ptype_specific);
+#ifdef CONFIG_NET_SCHED
+ hash_init(dev->qdisc_hash);
+#endif
dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
setup(dev);
*/
for_each_possible_cpu(i) {
+ struct work_struct *flush = per_cpu_ptr(&flush_works, i);
struct softnet_data *sd = &per_cpu(softnet_data, i);
+ INIT_WORK(flush, flush_backlog);
+
skb_queue_head_init(&sd->input_pkt_queue);
skb_queue_head_init(&sd->process_queue);
INIT_LIST_HEAD(&sd->poll_list);