F: drivers/net/hamradio/baycom*
BCACHE (BLOCK LAYER CACHE)
-M: Michael Lyle <mlyle@lyle.org>
+M: Coly Li <colyli@suse.de>
M: Kent Overstreet <kent.overstreet@gmail.com>
L: linux-bcache@vger.kernel.org
W: http://bcache.evilpiepirate.org
select ARCH_WANT_FRAME_POINTERS
select CLONE_BACKWARDS
select COMMON_CLK
+ select DMA_DIRECT_OPS
select GENERIC_CLOCKEVENTS
select GENERIC_CPU_DEVICES
select GENERIC_IRQ_SHOW
config HAVE_KPROBES
def_bool n
-config DMA_DIRECT_OPS
- def_bool y
-
menu "Platform type"
choice
generic-y += futex.h
generic-y += hardirq.h
generic-y += hash.h
-generic-y += handle_irq.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
# Add -lgcc so rv32 gets static muldi3 and lshrdi3 definitions.
# Make sure only to export the intended __vdso_xxx symbol offsets.
quiet_cmd_vdsold = VDSOLD $@
- cmd_vdsold = $(CC) $(KCFLAGS) -nostdlib $(SYSCFLAGS_$(@F)) \
+ cmd_vdsold = $(CC) $(KCFLAGS) $(call cc-option, -no-pie) -nostdlib $(SYSCFLAGS_$(@F)) \
-Wl,-T,$(filter-out FORCE,$^) -o $@.tmp -lgcc && \
$(CROSS_COMPILE)objcopy \
$(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@
void arch_release_task_struct(struct task_struct *tsk);
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
+
#endif
/*
apply_alternatives(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strcmp(".nospec_call_table", secname)))
+ (!strncmp(".s390_indirect", secname, 14)))
nospec_revert(aseg, aseg + s->sh_size);
if (IS_ENABLED(CONFIG_EXPOLINE) &&
- (!strcmp(".nospec_return_table", secname)))
+ (!strncmp(".s390_return", secname, 12)))
nospec_revert(aseg, aseg + s->sh_size);
}
CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
-CPUMF_EVENT_ATTR(cf_z13, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z13, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_MISSES, 0x0082);
CPUMF_EVENT_ATTR(cf_z13, DTLB1_HPAGE_WRITES, 0x0083);
CPUMF_EVENT_ATTR(cf_z13, TX_C_TABORT_SPECIAL, 0x00dc);
CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z13, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-CPUMF_EVENT_ATTR(cf_z14, L1D_WRITES_RO_EXCL, 0x0080);
+CPUMF_EVENT_ATTR(cf_z14, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_MISSES, 0x0082);
CPUMF_EVENT_ATTR(cf_z14, DTLB2_HPAGE_WRITES, 0x0083);
};
static struct attribute *cpumcf_z13_pmu_event_attr[] __initdata = {
- CPUMF_EVENT_PTR(cf_z13, L1D_WRITES_RO_EXCL),
+ CPUMF_EVENT_PTR(cf_z13, L1D_RO_EXCL_WRITES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_WRITES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_MISSES),
CPUMF_EVENT_PTR(cf_z13, DTLB1_HPAGE_WRITES),
};
static struct attribute *cpumcf_z14_pmu_event_attr[] __initdata = {
- CPUMF_EVENT_PTR(cf_z14, L1D_WRITES_RO_EXCL),
+ CPUMF_EVENT_PTR(cf_z14, L1D_RO_EXCL_WRITES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_WRITES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_MISSES),
CPUMF_EVENT_PTR(cf_z14, DTLB2_HPAGE_WRITES),
#include <linux/random.h>
#include <linux/export.h>
#include <linux/init_task.h>
+#include <asm/cpu_mf.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/vtimer.h>
{
}
+void arch_setup_new_exec(void)
+{
+ if (S390_lowcore.current_pid != current->pid) {
+ S390_lowcore.current_pid = current->pid;
+ if (test_facility(40))
+ lpp(&S390_lowcore.lpp);
+ }
+}
+
void arch_release_task_struct(struct task_struct *tsk)
{
runtime_instr_release(tsk);
return orig;
}
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+ struct pt_regs *regs)
+{
+ if (ctx == RP_CHECK_CHAIN_CALL)
+ return user_stack_pointer(regs) <= ret->stack;
+ else
+ return user_stack_pointer(regs) < ret->stack;
+}
+
/* Instruction Emulation */
static void adjust_psw_addr(psw_t *psw, unsigned long len)
bool new_queue = false;
bool bfqq_already_existing = false, split = false;
- if (!rq->elv.icq)
+ /*
+ * Even if we don't have an icq attached, we should still clear
+ * the scheduler pointers, as they might point to previously
+ * allocated bic/bfqq structs.
+ */
+ if (!rq->elv.icq) {
+ rq->elv.priv[0] = rq->elv.priv[1] = NULL;
return;
+ }
+
bic = icq_to_bic(rq->elv.icq);
spin_lock_irq(&bfqd->lock);
preloaded = !radix_tree_preload(GFP_KERNEL);
- /*
- * Make sure the root blkg exists and count the existing blkgs. As
- * @q is bypassing at this point, blkg_lookup_create() can't be
- * used. Open code insertion.
- */
+ /* Make sure the root blkg exists. */
rcu_read_lock();
spin_lock_irq(q->queue_lock);
blkg = blkg_create(&blkcg_root, q, new_blkg);
+ if (IS_ERR(blkg))
+ goto err_unlock;
+ q->root_blkg = blkg;
+ q->root_rl.blkg = blkg;
spin_unlock_irq(q->queue_lock);
rcu_read_unlock();
if (preloaded)
radix_tree_preload_end();
- if (IS_ERR(blkg))
- return PTR_ERR(blkg);
-
- q->root_blkg = blkg;
- q->root_rl.blkg = blkg;
-
ret = blk_throtl_init(q);
if (ret) {
spin_lock_irq(q->queue_lock);
spin_unlock_irq(q->queue_lock);
}
return ret;
+
+err_unlock:
+ spin_unlock_irq(q->queue_lock);
+ rcu_read_unlock();
+ if (preloaded)
+ radix_tree_preload_end();
+ return PTR_ERR(blkg);
}
/**
__clear_bit(pol->plid, q->blkcg_pols);
list_for_each_entry(blkg, &q->blkg_list, q_node) {
- /* grab blkcg lock too while removing @pd from @blkg */
- spin_lock(&blkg->blkcg->lock);
-
if (blkg->pd[pol->plid]) {
if (!blkg->pd[pol->plid]->offline &&
pol->pd_offline_fn) {
pol->pd_free_fn(blkg->pd[pol->plid]);
blkg->pd[pol->plid] = NULL;
}
-
- spin_unlock(&blkg->blkcg->lock);
}
spin_unlock_irq(q->queue_lock);
rq->part = NULL;
seqcount_init(&rq->gstate_seq);
u64_stats_init(&rq->aborted_gstate_sync);
+ /*
+ * See comment of blk_mq_init_request
+ */
+ WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC);
}
EXPORT_SYMBOL(blk_rq_init);
while (true) {
bool success = false;
- int ret;
rcu_read_lock();
if (percpu_ref_tryget_live(&q->q_usage_counter)) {
*/
smp_rmb();
- ret = wait_event_interruptible(q->mq_freeze_wq,
- (atomic_read(&q->mq_freeze_depth) == 0 &&
- (preempt || !blk_queue_preempt_only(q))) ||
- blk_queue_dying(q));
+ wait_event(q->mq_freeze_wq,
+ (atomic_read(&q->mq_freeze_depth) == 0 &&
+ (preempt || !blk_queue_preempt_only(q))) ||
+ blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
- if (ret)
- return ret;
}
}
seqcount_init(&rq->gstate_seq);
u64_stats_init(&rq->aborted_gstate_sync);
+ /*
+ * start gstate with gen 1 instead of 0, otherwise it will be equal
+ * to aborted_gstate, and be identified timed out by
+ * blk_mq_terminate_expired.
+ */
+ WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC);
+
return 0;
}
static void blk_mq_map_swqueue(struct request_queue *q)
{
- unsigned int i;
+ unsigned int i, hctx_idx;
struct blk_mq_hw_ctx *hctx;
struct blk_mq_ctx *ctx;
struct blk_mq_tag_set *set = q->tag_set;
/*
* Map software to hardware queues.
+ *
+ * If the cpu isn't present, the cpu is mapped to first hctx.
*/
for_each_possible_cpu(i) {
+ hctx_idx = q->mq_map[i];
+ /* unmapped hw queue can be remapped after CPU topo changed */
+ if (!set->tags[hctx_idx] &&
+ !__blk_mq_alloc_rq_map(set, hctx_idx)) {
+ /*
+ * If tags initialization fail for some hctx,
+ * that hctx won't be brought online. In this
+ * case, remap the current ctx to hctx[0] which
+ * is guaranteed to always have tags allocated
+ */
+ q->mq_map[i] = 0;
+ }
+
ctx = per_cpu_ptr(q->queue_ctx, i);
hctx = blk_mq_map_queue(q, i);
mutex_unlock(&q->sysfs_lock);
queue_for_each_hw_ctx(q, hctx, i) {
- /* every hctx should get mapped by at least one CPU */
- WARN_ON(!hctx->nr_ctx);
+ /*
+ * If no software queues are mapped to this hardware queue,
+ * disable it and free the request entries.
+ */
+ if (!hctx->nr_ctx) {
+ /* Never unmap queue 0. We need it as a
+ * fallback in case of a new remap fails
+ * allocation
+ */
+ if (i && set->tags[i])
+ blk_mq_free_map_and_requests(set, i);
+
+ hctx->tags = NULL;
+ continue;
+ }
hctx->tags = set->tags[i];
WARN_ON(!hctx->tags);
struct blk_mq_tag_set;
+/**
+ * struct blk_mq_ctx - State for a software queue facing the submitting CPUs
+ */
struct blk_mq_ctx {
struct {
spinlock_t lock;
DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
},
},
+ /*
+ * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
+ * the Low Power S0 Idle firmware interface (see
+ * https://bugzilla.kernel.org/show_bug.cgi?id=199057).
+ */
+ {
+ .callback = init_no_lps0,
+ .ident = "ThinkPad X1 Tablet(2016)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"),
+ },
+ },
{},
};
* This checks whether the memory was allocated from the per-device
* coherent memory pool and if so, maps that memory to the provided vma.
*
- * Returns 1 if we correctly mapped the memory, or 0 if the caller should
- * proceed with mapping memory from generic pools.
+ * Returns 1 if @vaddr belongs to the device coherent pool and the caller
+ * should return @ret, or 0 if they should proceed with mapping memory from
+ * generic areas.
*/
int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
void *vaddr, size_t size, int *ret)
#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
unsigned long off = vma->vm_pgoff;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
- if (off < count && user_count <= (count - off)) {
+ if (off < count && user_count <= (count - off))
ret = remap_pfn_range(vma, vma->vm_start,
- pfn + off,
+ page_to_pfn(virt_to_page(cpu_addr)) + off,
user_count << PAGE_SHIFT,
vma->vm_page_prot);
- }
#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
return ret;
static void lo_complete_rq(struct request *rq)
{
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ blk_status_t ret = BLK_STS_OK;
- if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
- cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
- struct bio *bio = cmd->rq->bio;
-
- bio_advance(bio, cmd->ret);
- zero_fill_bio(bio);
+ if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
+ req_op(rq) != REQ_OP_READ) {
+ if (cmd->ret < 0)
+ ret = BLK_STS_IOERR;
+ goto end_io;
}
- blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
+ /*
+ * Short READ - if we got some data, advance our request and
+ * retry it. If we got no data, end the rest with EIO.
+ */
+ if (cmd->ret) {
+ blk_update_request(rq, BLK_STS_OK, cmd->ret);
+ cmd->ret = 0;
+ blk_mq_requeue_request(rq, true);
+ } else {
+ if (cmd->use_aio) {
+ struct bio *bio = rq->bio;
+
+ while (bio) {
+ zero_fill_bio(bio);
+ bio = bio->bi_next;
+ }
+ }
+ ret = BLK_STS_IOERR;
+end_io:
+ blk_mq_end_request(rq, ret);
+ }
}
static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
{
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
+
if (!atomic_dec_and_test(&cmd->ref))
return;
kfree(cmd->bvec);
cmd->bvec = NULL;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(rq);
}
static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
{
struct iov_iter iter;
struct bio_vec *bvec;
- struct request *rq = cmd->rq;
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
struct bio *bio = rq->bio;
struct file *file = lo->lo_backing_file;
unsigned int offset;
static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
- struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
- struct loop_device *lo = cmd->rq->q->queuedata;
+ struct request *rq = bd->rq;
+ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ struct loop_device *lo = rq->q->queuedata;
- blk_mq_start_request(bd->rq);
+ blk_mq_start_request(rq);
if (lo->lo_state != Lo_bound)
return BLK_STS_IOERR;
- switch (req_op(cmd->rq)) {
+ switch (req_op(rq)) {
case REQ_OP_FLUSH:
case REQ_OP_DISCARD:
case REQ_OP_WRITE_ZEROES:
/* always use the first bio's css */
#ifdef CONFIG_BLK_CGROUP
- if (cmd->use_aio && cmd->rq->bio && cmd->rq->bio->bi_css) {
- cmd->css = cmd->rq->bio->bi_css;
+ if (cmd->use_aio && rq->bio && rq->bio->bi_css) {
+ cmd->css = rq->bio->bi_css;
css_get(cmd->css);
} else
#endif
static void loop_handle_cmd(struct loop_cmd *cmd)
{
- const bool write = op_is_write(req_op(cmd->rq));
- struct loop_device *lo = cmd->rq->q->queuedata;
+ struct request *rq = blk_mq_rq_from_pdu(cmd);
+ const bool write = op_is_write(req_op(rq));
+ struct loop_device *lo = rq->q->queuedata;
int ret = 0;
if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
goto failed;
}
- ret = do_req_filebacked(lo, cmd->rq);
+ ret = do_req_filebacked(lo, rq);
failed:
/* complete non-aio request */
if (!cmd->use_aio || ret) {
cmd->ret = ret ? -EIO : 0;
- blk_mq_complete_request(cmd->rq);
+ blk_mq_complete_request(rq);
}
}
{
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
- cmd->rq = rq;
kthread_init_work(&cmd->work, loop_queue_work);
-
return 0;
}
struct loop_cmd {
struct kthread_work work;
- struct request *rq;
bool use_aio; /* use AIO interface to handle I/O */
atomic_t ref; /* only for aio */
long ret;
/* Select values for swim_select and swim_readbit */
#define READ_DATA_0 0x074
-#define TWOMEG_DRIVE 0x075
+#define ONEMEG_DRIVE 0x075
#define SINGLE_SIDED 0x076
#define DRIVE_PRESENT 0x077
#define DISK_IN 0x170
#define TRACK_ZERO 0x172
#define TACHO 0x173
#define READ_DATA_1 0x174
-#define MFM_MODE 0x175
+#define GCR_MODE 0x175
#define SEEK_COMPLETE 0x176
-#define ONEMEG_MEDIA 0x177
+#define TWOMEG_MEDIA 0x177
/* Bits in handshake register */
struct floppy_struct *g;
fs->disk_in = 1;
fs->write_protected = swim_readbit(base, WRITE_PROT);
- fs->type = swim_readbit(base, ONEMEG_MEDIA);
if (swim_track00(base))
printk(KERN_ERR
swim_track00(base);
+ fs->type = swim_readbit(base, TWOMEG_MEDIA) ?
+ HD_MEDIA : DD_MEDIA;
+ fs->head_number = swim_readbit(base, SINGLE_SIDED) ? 1 : 2;
get_floppy_geometry(fs, 0, &g);
fs->total_secs = g->size;
fs->secpercyl = g->head * g->sect;
swim_write(base, setup, S_IBM_DRIVE | S_FCLK_DIV2);
udelay(10);
- swim_drive(base, INTERNAL_DRIVE);
+ swim_drive(base, fs->location);
swim_motor(base, ON);
swim_action(base, SETMFM);
if (fs->ejected)
goto out;
}
+ set_capacity(fs->disk, fs->total_secs);
+
if (mode & FMODE_NDELAY)
return 0;
if (copy_to_user((void __user *) param, (void *) &floppy_type,
sizeof(struct floppy_struct)))
return -EFAULT;
- break;
-
- default:
- printk(KERN_DEBUG "SWIM floppy_ioctl: unknown cmd %d\n",
- cmd);
- return -ENOSYS;
+ return 0;
}
- return 0;
+ return -ENOTTY;
}
static int floppy_getgeo(struct block_device *bdev, struct hd_geometry *geo)
struct swim_priv *swd = data;
int drive = (*part & 3);
- if (drive > swd->floppy_count)
+ if (drive >= swd->floppy_count)
return NULL;
*part = 0;
swim_motor(base, OFF);
- if (swim_readbit(base, SINGLE_SIDED))
- fs->head_number = 1;
- else
- fs->head_number = 2;
+ fs->type = HD_MEDIA;
+ fs->head_number = 2;
+
fs->ref_count = 0;
fs->ejected = 1;
/* scan floppy drives */
swim_drive(base, INTERNAL_DRIVE);
- if (swim_readbit(base, DRIVE_PRESENT))
+ if (swim_readbit(base, DRIVE_PRESENT) &&
+ !swim_readbit(base, ONEMEG_DRIVE))
swim_add_floppy(swd, INTERNAL_DRIVE);
swim_drive(base, EXTERNAL_DRIVE);
- if (swim_readbit(base, DRIVE_PRESENT))
+ if (swim_readbit(base, DRIVE_PRESENT) &&
+ !swim_readbit(base, ONEMEG_DRIVE))
swim_add_floppy(swd, EXTERNAL_DRIVE);
/* register floppy drives */
&swd->lock);
if (!swd->unit[drive].disk->queue) {
err = -ENOMEM;
- put_disk(swd->unit[drive].disk);
goto exit_put_disks;
}
blk_queue_bounce_limit(swd->unit[drive].disk->queue,
goto out;
}
- swim_base = ioremap(res->start, resource_size(res));
+ swim_base = (struct swim __iomem *)res->start;
if (!swim_base) {
ret = -ENOMEM;
goto out_release_io;
if (!get_swim_mode(swim_base)) {
printk(KERN_INFO "SWIM device not found !\n");
ret = -ENODEV;
- goto out_iounmap;
+ goto out_release_io;
}
/* set platform driver data */
swd = kzalloc(sizeof(struct swim_priv), GFP_KERNEL);
if (!swd) {
ret = -ENOMEM;
- goto out_iounmap;
+ goto out_release_io;
}
platform_set_drvdata(dev, swd);
out_kfree:
kfree(swd);
-out_iounmap:
- iounmap(swim_base);
out_release_io:
release_mem_region(res->start, resource_size(res));
out:
for (drive = 0; drive < swd->floppy_count; drive++)
floppy_eject(&swd->unit[drive]);
- iounmap(swd->base);
-
res = platform_get_resource(dev, IORESOURCE_MEM, 0);
if (res)
release_mem_region(res->start, resource_size(res));
#define MOTOR_ON 2
#define RELAX 3 /* also eject in progress */
#define READ_DATA_0 4
-#define TWOMEG_DRIVE 5
+#define ONEMEG_DRIVE 5
#define SINGLE_SIDED 6 /* drive or diskette is 4MB type? */
#define DRIVE_PRESENT 7
#define DISK_IN 8
#define TRACK_ZERO 10
#define TACHO 11
#define READ_DATA_1 12
-#define MFM_MODE 13
+#define GCR_MODE 13
#define SEEK_COMPLETE 14
-#define ONEMEG_MEDIA 15
+#define TWOMEG_MEDIA 15
/* Definitions of values used in writing and formatting */
#define DATA_ESCAPE 0x99
if (!CDROM_CAN(CDC_SELECT_DISC) || arg == CDSL_CURRENT)
return media_changed(cdi, 1);
- if ((unsigned int)arg >= cdi->capacity)
+ if (arg >= cdi->capacity)
return -EINVAL;
info = kmalloc(sizeof(*info), GFP_KERNEL);
#include <linux/ptrace.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
+#include <linux/ratelimit.h>
#include <linux/syscalls.h>
#include <linux/completion.h>
#include <linux/uuid.h>
static void process_random_ready_list(void);
static void _get_random_bytes(void *buf, int nbytes);
+static struct ratelimit_state unseeded_warning =
+ RATELIMIT_STATE_INIT("warn_unseeded_randomness", HZ, 3);
+static struct ratelimit_state urandom_warning =
+ RATELIMIT_STATE_INIT("warn_urandom_randomness", HZ, 3);
+
+static int ratelimit_disable __read_mostly;
+
+module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
+MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
+
/**********************************************************************
*
* OS independent entropy store. Here are the functions which handle
}
#ifdef CONFIG_NUMA
-static void numa_crng_init(void)
+static void do_numa_crng_init(struct work_struct *work)
{
int i;
struct crng_state *crng;
kfree(pool);
}
}
+
+static DECLARE_WORK(numa_crng_init_work, do_numa_crng_init);
+
+static void numa_crng_init(void)
+{
+ schedule_work(&numa_crng_init_work);
+}
#else
static void numa_crng_init(void) {}
#endif
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
pr_notice("random: crng init done\n");
+ if (unseeded_warning.missed) {
+ pr_notice("random: %d get_random_xx warning(s) missed "
+ "due to ratelimiting\n",
+ unseeded_warning.missed);
+ unseeded_warning.missed = 0;
+ }
+ if (urandom_warning.missed) {
+ pr_notice("random: %d urandom warning(s) missed "
+ "due to ratelimiting\n",
+ urandom_warning.missed);
+ urandom_warning.missed = 0;
+ }
}
}
#ifndef CONFIG_WARN_ALL_UNSEEDED_RANDOM
print_once = true;
#endif
- pr_notice("random: %s called from %pS with crng_init=%d\n",
- func_name, caller, crng_init);
+ if (__ratelimit(&unseeded_warning))
+ pr_notice("random: %s called from %pS with crng_init=%d\n",
+ func_name, caller, crng_init);
}
/*
init_std_data(&blocking_pool);
crng_initialize(&primary_crng);
crng_global_init_time = jiffies;
+ if (ratelimit_disable) {
+ urandom_warning.interval = 0;
+ unseeded_warning.interval = 0;
+ }
return 0;
}
early_initcall(rand_initialize);
if (!crng_ready() && maxwarn > 0) {
maxwarn--;
- printk(KERN_NOTICE "random: %s: uninitialized urandom read "
- "(%zd bytes read)\n",
- current->comm, nbytes);
+ if (__ratelimit(&urandom_warning))
+ printk(KERN_NOTICE "random: %s: uninitialized "
+ "urandom read (%zd bytes read)\n",
+ current->comm, nbytes);
spin_lock_irqsave(&primary_crng.lock, flags);
crng_init_cnt = 0;
spin_unlock_irqrestore(&primary_crng.lock, flags);
Say Y, if you have a Broadcom SoC with AVS support for DFS or DVFS.
-config ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
- bool "Broadcom STB AVS CPUfreq driver sysfs debug capability"
- depends on ARM_BRCMSTB_AVS_CPUFREQ
- help
- Enabling this option turns on debug support via sysfs under
- /sys/kernel/debug/brcmstb-avs-cpufreq. It is possible to read all and
- write some AVS mailbox registers through sysfs entries.
-
- If in doubt, say N.
-
config ARM_EXYNOS5440_CPUFREQ
tristate "SAMSUNG EXYNOS5440"
depends on SOC_EXYNOS5440
#include <linux/platform_device.h>
#include <linux/semaphore.h>
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-#include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#endif
-
/* Max number of arguments AVS calls take */
#define AVS_MAX_CMD_ARGS 4
/*
void __iomem *base;
void __iomem *avs_intr_base;
struct device *dev;
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
- struct dentry *debugfs;
-#endif
struct completion done;
struct semaphore sem;
struct pmap pmap;
};
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-enum debugfs_format {
- DEBUGFS_NORMAL,
- DEBUGFS_FLOAT,
- DEBUGFS_REV,
-};
-
-struct debugfs_data {
- struct debugfs_entry *entry;
- struct private_data *priv;
-};
-
-struct debugfs_entry {
- char *name;
- u32 offset;
- fmode_t mode;
- enum debugfs_format format;
-};
-
-#define DEBUGFS_ENTRY(name, mode, format) { \
- #name, AVS_MBOX_##name, mode, format \
-}
-
-/*
- * These are used for debugfs only. Otherwise we use AVS_MBOX_PARAM() directly.
- */
-#define AVS_MBOX_PARAM1 AVS_MBOX_PARAM(0)
-#define AVS_MBOX_PARAM2 AVS_MBOX_PARAM(1)
-#define AVS_MBOX_PARAM3 AVS_MBOX_PARAM(2)
-#define AVS_MBOX_PARAM4 AVS_MBOX_PARAM(3)
-
-/*
- * This table stores the name, access permissions and offset for each hardware
- * register and is used to generate debugfs entries.
- */
-static struct debugfs_entry debugfs_entries[] = {
- DEBUGFS_ENTRY(COMMAND, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(STATUS, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(VOLTAGE0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(TEMP0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PV0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(MV0, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PARAM1, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM2, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM3, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(PARAM4, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(REVISION, 0, DEBUGFS_REV),
- DEBUGFS_ENTRY(PSTATE, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(HEARTBEAT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(MAGIC, S_IWUSR, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(SIGMA_HVT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(SIGMA_SVT, 0, DEBUGFS_NORMAL),
- DEBUGFS_ENTRY(VOLTAGE1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(TEMP1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(PV1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(MV1, 0, DEBUGFS_FLOAT),
- DEBUGFS_ENTRY(FREQUENCY, 0, DEBUGFS_NORMAL),
-};
-
-static int brcm_avs_target_index(struct cpufreq_policy *, unsigned int);
-
-static char *__strtolower(char *s)
-{
- char *p;
-
- for (p = s; *p; p++)
- *p = tolower(*p);
-
- return s;
-}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
static void __iomem *__map_region(const char *name)
{
struct device_node *np;
return table;
}
-#ifdef CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG
-
-#define MANT(x) (unsigned int)(abs((x)) / 1000)
-#define FRAC(x) (unsigned int)(abs((x)) - abs((x)) / 1000 * 1000)
-
-static int brcm_avs_debug_show(struct seq_file *s, void *data)
-{
- struct debugfs_data *dbgfs = s->private;
- void __iomem *base;
- u32 val, offset;
-
- if (!dbgfs) {
- seq_puts(s, "No device pointer\n");
- return 0;
- }
-
- base = dbgfs->priv->base;
- offset = dbgfs->entry->offset;
- val = readl(base + offset);
- switch (dbgfs->entry->format) {
- case DEBUGFS_NORMAL:
- seq_printf(s, "%u\n", val);
- break;
- case DEBUGFS_FLOAT:
- seq_printf(s, "%d.%03d\n", MANT(val), FRAC(val));
- break;
- case DEBUGFS_REV:
- seq_printf(s, "%c.%c.%c.%c\n", (val >> 24 & 0xff),
- (val >> 16 & 0xff), (val >> 8 & 0xff),
- val & 0xff);
- break;
- }
- seq_printf(s, "0x%08x\n", val);
-
- return 0;
-}
-
-#undef MANT
-#undef FRAC
-
-static ssize_t brcm_avs_seq_write(struct file *file, const char __user *buf,
- size_t size, loff_t *ppos)
-{
- struct seq_file *s = file->private_data;
- struct debugfs_data *dbgfs = s->private;
- struct private_data *priv = dbgfs->priv;
- void __iomem *base, *avs_intr_base;
- bool use_issue_command = false;
- unsigned long val, offset;
- char str[128];
- int ret;
- char *str_ptr = str;
-
- if (size >= sizeof(str))
- return -E2BIG;
-
- memset(str, 0, sizeof(str));
- ret = copy_from_user(str, buf, size);
- if (ret)
- return ret;
-
- base = priv->base;
- avs_intr_base = priv->avs_intr_base;
- offset = dbgfs->entry->offset;
- /*
- * Special case writing to "command" entry only: if the string starts
- * with a 'c', we use the driver's __issue_avs_command() function.
- * Otherwise, we perform a raw write. This should allow testing of raw
- * access as well as using the higher level function. (Raw access
- * doesn't clear the firmware return status after issuing the command.)
- */
- if (str_ptr[0] == 'c' && offset == AVS_MBOX_COMMAND) {
- use_issue_command = true;
- str_ptr++;
- }
- if (kstrtoul(str_ptr, 0, &val) != 0)
- return -EINVAL;
-
- /*
- * Setting the P-state is a special case. We need to update the CPU
- * frequency we report.
- */
- if (val == AVS_CMD_SET_PSTATE) {
- struct cpufreq_policy *policy;
- unsigned int pstate;
-
- policy = cpufreq_cpu_get(smp_processor_id());
- /* Read back the P-state we are about to set */
- pstate = readl(base + AVS_MBOX_PARAM(0));
- if (use_issue_command) {
- ret = brcm_avs_target_index(policy, pstate);
- return ret ? ret : size;
- }
- policy->cur = policy->freq_table[pstate].frequency;
- }
-
- if (use_issue_command) {
- ret = __issue_avs_command(priv, val, false, NULL);
- } else {
- /* Locking here is not perfect, but is only for debug. */
- ret = down_interruptible(&priv->sem);
- if (ret)
- return ret;
-
- writel(val, base + offset);
- /* We have to wake up the firmware to process a command. */
- if (offset == AVS_MBOX_COMMAND)
- writel(AVS_CPU_L2_INT_MASK,
- avs_intr_base + AVS_CPU_L2_SET0);
- up(&priv->sem);
- }
-
- return ret ? ret : size;
-}
-
-static struct debugfs_entry *__find_debugfs_entry(const char *name)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++)
- if (strcasecmp(debugfs_entries[i].name, name) == 0)
- return &debugfs_entries[i];
-
- return NULL;
-}
-
-static int brcm_avs_debug_open(struct inode *inode, struct file *file)
-{
- struct debugfs_data *data;
- fmode_t fmode;
- int ret;
-
- /*
- * seq_open(), which is called by single_open(), clears "write" access.
- * We need write access to some files, so we preserve our access mode
- * and restore it.
- */
- fmode = file->f_mode;
- /*
- * Check access permissions even for root. We don't want to be writing
- * to read-only registers. Access for regular users has already been
- * checked by the VFS layer.
- */
- if ((fmode & FMODE_WRITER) && !(inode->i_mode & S_IWUSR))
- return -EACCES;
-
- data = kmalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
- /*
- * We use the same file system operations for all our debug files. To
- * produce specific output, we look up the file name upon opening a
- * debugfs entry and map it to a memory offset. This offset is then used
- * in the generic "show" function to read a specific register.
- */
- data->entry = __find_debugfs_entry(file->f_path.dentry->d_iname);
- data->priv = inode->i_private;
-
- ret = single_open(file, brcm_avs_debug_show, data);
- if (ret)
- kfree(data);
- file->f_mode = fmode;
-
- return ret;
-}
-
-static int brcm_avs_debug_release(struct inode *inode, struct file *file)
-{
- struct seq_file *seq_priv = file->private_data;
- struct debugfs_data *data = seq_priv->private;
-
- kfree(data);
- return single_release(inode, file);
-}
-
-static const struct file_operations brcm_avs_debug_ops = {
- .open = brcm_avs_debug_open,
- .read = seq_read,
- .write = brcm_avs_seq_write,
- .llseek = seq_lseek,
- .release = brcm_avs_debug_release,
-};
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev)
-{
- struct private_data *priv = platform_get_drvdata(pdev);
- struct dentry *dir;
- int i;
-
- if (!priv)
- return;
-
- dir = debugfs_create_dir(BRCM_AVS_CPUFREQ_NAME, NULL);
- if (IS_ERR_OR_NULL(dir))
- return;
- priv->debugfs = dir;
-
- for (i = 0; i < ARRAY_SIZE(debugfs_entries); i++) {
- /*
- * The DEBUGFS_ENTRY macro generates uppercase strings. We
- * convert them to lowercase before creating the debugfs
- * entries.
- */
- char *entry = __strtolower(debugfs_entries[i].name);
- fmode_t mode = debugfs_entries[i].mode;
-
- if (!debugfs_create_file(entry, S_IFREG | S_IRUGO | mode,
- dir, priv, &brcm_avs_debug_ops)) {
- priv->debugfs = NULL;
- debugfs_remove_recursive(dir);
- break;
- }
- }
-}
-
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev)
-{
- struct private_data *priv = platform_get_drvdata(pdev);
-
- if (priv && priv->debugfs) {
- debugfs_remove_recursive(priv->debugfs);
- priv->debugfs = NULL;
- }
-}
-
-#else
-
-static void brcm_avs_cpufreq_debug_init(struct platform_device *pdev) {}
-static void brcm_avs_cpufreq_debug_exit(struct platform_device *pdev) {}
-
-#endif /* CONFIG_ARM_BRCMSTB_AVS_CPUFREQ_DEBUG */
-
/*
* To ensure the right firmware is running we need to
* - check the MAGIC matches what we expect
return ret;
brcm_avs_driver.driver_data = pdev;
- ret = cpufreq_register_driver(&brcm_avs_driver);
- if (!ret)
- brcm_avs_cpufreq_debug_init(pdev);
- return ret;
+ return cpufreq_register_driver(&brcm_avs_driver);
}
static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
if (ret)
return ret;
- brcm_avs_cpufreq_debug_exit(pdev);
-
priv = platform_get_drvdata(pdev);
iounmap(priv->base);
iounmap(priv->avs_intr_base);
.cmd_per_lun = 7,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = mptscsih_host_attrs,
+ .no_write_same = 1,
};
static int mptsas_get_linkerrors(struct sas_phy *phy)
} /* switch(bond_mode) */
#ifdef CONFIG_NET_POLL_CONTROLLER
- slave_dev->npinfo = bond->dev->npinfo;
- if (slave_dev->npinfo) {
+ if (bond->dev->npinfo) {
if (slave_enable_netpoll(new_slave)) {
netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n");
res = -EBUSY;
#define MDIO_VEND2_AN_STAT 0x8002
#endif
+#ifndef MDIO_VEND2_PMA_CDR_CONTROL
+#define MDIO_VEND2_PMA_CDR_CONTROL 0x8056
+#endif
+
#ifndef MDIO_CTRL1_SPEED1G
#define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
#endif
#define XGBE_AN_CL37_TX_CONFIG_MASK 0x08
#define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100
+#define XGBE_PMA_CDR_TRACK_EN_MASK 0x01
+#define XGBE_PMA_CDR_TRACK_EN_OFF 0x00
+#define XGBE_PMA_CDR_TRACK_EN_ON 0x01
+
/* Bit setting and getting macros
* The get macro will extract the current bit field value from within
* the variable
"debugfs_create_file failed\n");
}
+ if (pdata->vdata->an_cdr_workaround) {
+ pfile = debugfs_create_bool("an_cdr_workaround", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_workaround);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+
+ pfile = debugfs_create_bool("an_cdr_track_early", 0600,
+ pdata->xgbe_debugfs,
+ &pdata->debugfs_an_cdr_track_early);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_bool failed\n");
+ }
+
kfree(buf);
}
XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
/* Call MDIO/PHY initialization routine */
+ pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround;
ret = pdata->phy_if.phy_init(pdata);
if (ret)
return ret;
xgbe_an73_set(pdata, false, false);
xgbe_an73_disable_interrupts(pdata);
+ pdata->an_start = 0;
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
}
static void xgbe_an_restart(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_pre)
+ pdata->phy_if.phy_impl.an_pre(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
static void xgbe_an_disable(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
switch (pdata->an_mode) {
case XGBE_AN_MODE_CL73:
case XGBE_AN_MODE_CL73_REDRV:
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
reg);
- if (pdata->phy_if.phy_impl.kr_training_post)
- pdata->phy_if.phy_impl.kr_training_post(pdata);
-
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
+
+ if (pdata->phy_if.phy_impl.kr_training_post)
+ pdata->phy_if.phy_impl.kr_training_post(pdata);
}
return XGBE_AN_PAGE_RECEIVED;
return XGBE_AN_NO_LINK;
}
- xgbe_an73_disable(pdata);
+ xgbe_an_disable(pdata);
xgbe_switch_mode(pdata);
- xgbe_an73_restart(pdata);
+ xgbe_an_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
}
pdata->an_result = pdata->an_state;
pdata->an_state = XGBE_AN_READY;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
pdata->kx_state = XGBE_RX_BPA;
pdata->an_start = 0;
+ if (pdata->phy_if.phy_impl.an_post)
+ pdata->phy_if.phy_impl.an_post(pdata);
+
netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct xgbe_version_data xgbe_v2b = {
.irq_reissue_support = 1,
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
+ .an_cdr_workaround = 1,
};
static const struct pci_device_id xgbe_pci_table[] = {
/* Rate-change complete wait/retry count */
#define XGBE_RATECHANGE_COUNT 500
+/* CDR delay values for KR support (in usec) */
+#define XGBE_CDR_DELAY_INIT 10000
+#define XGBE_CDR_DELAY_INC 10000
+#define XGBE_CDR_DELAY_MAX 100000
+
+/* RRC frequency during link status check */
+#define XGBE_RRC_FREQUENCY 10
+
enum xgbe_port_mode {
XGBE_PORT_MODE_RSVD = 0,
XGBE_PORT_MODE_BACKPLANE,
#define XGBE_SFP_BASE_VENDOR_SN 4
#define XGBE_SFP_BASE_VENDOR_SN_LEN 16
+#define XGBE_SFP_EXTD_OPT1 1
+#define XGBE_SFP_EXTD_OPT1_RX_LOS BIT(1)
+#define XGBE_SFP_EXTD_OPT1_TX_FAULT BIT(3)
+
#define XGBE_SFP_EXTD_DIAG 28
#define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2)
unsigned int sfp_gpio_address;
unsigned int sfp_gpio_mask;
+ unsigned int sfp_gpio_inputs;
unsigned int sfp_gpio_rx_los;
unsigned int sfp_gpio_tx_fault;
unsigned int sfp_gpio_mod_absent;
unsigned int redrv_addr;
unsigned int redrv_lane;
unsigned int redrv_model;
+
+ /* KR AN support */
+ unsigned int phy_cdr_notrack;
+ unsigned int phy_cdr_delay;
};
/* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
phy_data->sfp_phy_avail = 1;
}
+static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data)
+{
+ u8 *sfp_extd = phy_data->sfp_eeprom.extd;
+
+ if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT))
+ return false;
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault))
+ return true;
+
+ return false;
+}
+
+static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data)
+{
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT)
+ return false;
+
+ if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent))
+ return true;
+
+ return false;
+}
+
static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
return;
+ /* Update transceiver signals (eeprom extd/options) */
+ phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data);
+ phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data);
+
if (xgbe_phy_sfp_parse_quirks(pdata))
return;
static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
- unsigned int gpio_input;
u8 gpio_reg, gpio_ports[2];
int ret;
return;
}
- gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
-
- if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
- /* No GPIO, just assume the module is present for now */
- phy_data->sfp_mod_absent = 0;
- } else {
- if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
- phy_data->sfp_mod_absent = 0;
- }
-
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
- (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
- phy_data->sfp_rx_los = 1;
+ phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0];
- if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
- (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
- phy_data->sfp_tx_fault = 1;
+ phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data);
}
static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
return 1;
/* No link, attempt a receiver reset cycle */
- if (phy_data->rrc_count++) {
+ if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
phy_data->rrc_count = 0;
xgbe_phy_rrc(pdata);
}
return true;
}
+static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (!phy_data->phy_cdr_notrack)
+ return;
+
+ usleep_range(phy_data->phy_cdr_delay,
+ phy_data->phy_cdr_delay + 500);
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_ON);
+
+ phy_data->phy_cdr_notrack = 0;
+}
+
+static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (!pdata->debugfs_an_cdr_workaround)
+ return;
+
+ if (phy_data->phy_cdr_notrack)
+ return;
+
+ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL,
+ XGBE_PMA_CDR_TRACK_EN_MASK,
+ XGBE_PMA_CDR_TRACK_EN_OFF);
+
+ xgbe_phy_rrc(pdata);
+
+ phy_data->phy_cdr_notrack = 1;
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+ if (!pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+ if (pdata->debugfs_an_cdr_track_early)
+ xgbe_phy_cdr_track(pdata);
+}
+
+static void xgbe_phy_an_post(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_track(pdata);
+
+ switch (pdata->an_result) {
+ case XGBE_AN_READY:
+ case XGBE_AN_COMPLETE:
+ break;
+ default:
+ if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX)
+ phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC;
+ else
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ if (phy_data->cur_mode != XGBE_MODE_KR)
+ break;
+
+ xgbe_phy_cdr_notrack(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
{
struct xgbe_phy_data *phy_data = pdata->phy_data;
xgbe_phy_sfp_reset(phy_data);
xgbe_phy_sfp_mod_absent(pdata);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* Power off the PHY */
xgbe_phy_power_off(pdata);
/* Start in highest supported mode */
xgbe_phy_set_mode(pdata, phy_data->start_mode);
+ /* Reset CDR support */
+ xgbe_phy_cdr_track(pdata);
+
/* After starting the I2C controller, we can check for an SFP */
switch (phy_data->port_mode) {
case XGBE_PORT_MODE_SFP:
}
}
+ phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT;
+
/* Register for driving external PHYs */
mii = devm_mdiobus_alloc(pdata->dev);
if (!mii) {
phy_impl->an_advertising = xgbe_phy_an_advertising;
phy_impl->an_outcome = xgbe_phy_an_outcome;
+
+ phy_impl->an_pre = xgbe_phy_an_pre;
+ phy_impl->an_post = xgbe_phy_an_post;
+
+ phy_impl->kr_training_pre = xgbe_phy_kr_training_pre;
+ phy_impl->kr_training_post = xgbe_phy_kr_training_post;
}
/* This structure represents implementation specific routines for an
* implementation of a PHY. All routines are required unless noted below.
* Optional routines:
+ * an_pre, an_post
* kr_training_pre, kr_training_post
*/
struct xgbe_phy_impl_if {
/* Process results of auto-negotiation */
enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
+ /* Pre/Post auto-negotiation support */
+ void (*an_pre)(struct xgbe_prv_data *);
+ void (*an_post)(struct xgbe_prv_data *);
+
/* Pre/Post KR training enablement support */
void (*kr_training_pre)(struct xgbe_prv_data *);
void (*kr_training_post)(struct xgbe_prv_data *);
unsigned int irq_reissue_support;
unsigned int tx_desc_prefetch;
unsigned int rx_desc_prefetch;
+ unsigned int an_cdr_workaround;
};
struct xgbe_vxlan_data {
unsigned int debugfs_xprop_reg;
unsigned int debugfs_xi2c_reg;
+
+ bool debugfs_an_cdr_workaround;
+ bool debugfs_an_cdr_track_early;
};
/* Function prototypes*/
if (!adapter->rx_pool)
return;
- rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
+ rx_scrqs = adapter->num_active_rx_pools;
rx_entries = adapter->req_rx_add_entries_per_subcrq;
/* Free any remaining skbs in the rx buffer pools */
if (!adapter->tx_pool || !adapter->tso_pool)
return;
- tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
+ tx_scrqs = adapter->num_active_tx_pools;
/* Free any remaining skbs in the tx buffer pools */
for (i = 0; i < tx_scrqs; i++) {
#define ICE_LG_ACT_MIRROR_VSI_ID_S 3
#define ICE_LG_ACT_MIRROR_VSI_ID_M (0x3FF << ICE_LG_ACT_MIRROR_VSI_ID_S)
- /* Action type = 5 - Large Action */
+ /* Action type = 5 - Generic Value */
#define ICE_LG_ACT_GENERIC 0x5
#define ICE_LG_ACT_GENERIC_VALUE_S 3
#define ICE_LG_ACT_GENERIC_VALUE_M (0xFFFF << ICE_LG_ACT_GENERIC_VALUE_S)
struct ice_aq_desc desc;
enum ice_status status;
u16 flags;
+ u8 i;
cmd = &desc.params.mac_read;
return ICE_ERR_CFG;
}
- ether_addr_copy(hw->port_info->mac.lan_addr, resp->mac_addr);
- ether_addr_copy(hw->port_info->mac.perm_addr, resp->mac_addr);
+ /* A single port can report up to two (LAN and WoL) addresses */
+ for (i = 0; i < cmd->num_addr; i++)
+ if (resp[i].addr_type == ICE_AQC_MAN_MAC_ADDR_TYPE_LAN) {
+ ether_addr_copy(hw->port_info->mac.lan_addr,
+ resp[i].mac_addr);
+ ether_addr_copy(hw->port_info->mac.perm_addr,
+ resp[i].mac_addr);
+ break;
+ }
+
return 0;
}
if (status)
goto err_unroll_sched;
- /* Get port MAC information */
- mac_buf_len = sizeof(struct ice_aqc_manage_mac_read_resp);
- mac_buf = devm_kzalloc(ice_hw_to_dev(hw), mac_buf_len, GFP_KERNEL);
+ /* Get MAC information */
+ /* A single port can report up to two (LAN and WoL) addresses */
+ mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2,
+ sizeof(struct ice_aqc_manage_mac_read_resp),
+ GFP_KERNEL);
+ mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp);
if (!mac_buf) {
status = ICE_ERR_NO_MEMORY;
#define PFINT_FW_CTL_CAUSE_ENA_S 30
#define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S)
#define PFINT_OICR 0x0016CA00
-#define PFINT_OICR_INTEVENT_S 0
-#define PFINT_OICR_INTEVENT_M BIT(PFINT_OICR_INTEVENT_S)
#define PFINT_OICR_HLP_RDY_S 14
#define PFINT_OICR_HLP_RDY_M BIT(PFINT_OICR_HLP_RDY_S)
#define PFINT_OICR_CPM_RDY_S 15
oicr = rd32(hw, PFINT_OICR);
ena_mask = rd32(hw, PFINT_OICR_ENA);
- if (!(oicr & PFINT_OICR_INTEVENT_M))
- goto ena_intr;
-
if (oicr & PFINT_OICR_GRST_M) {
u32 reset;
/* we have a reset warning */
}
ret = IRQ_HANDLED;
-ena_intr:
/* re-enable interrupt causes that are not handled during this pass */
wr32(hw, PFINT_OICR_ENA, ena_mask);
if (!test_bit(__ICE_DOWN, pf->state)) {
u16 num_added = 0;
u32 temp;
+ *num_nodes_added = 0;
+
if (!num_nodes)
return status;
if (!parent || layer < hw->sw_entry_point_layer)
return ICE_ERR_PARAM;
- *num_nodes_added = 0;
-
/* max children per node per layer */
max_child_nodes =
le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children);
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
- if (enable) {
+ if (enable || queue == 0) {
+ /* i210 does not allow the queue 0 to be in the Strict
+ * Priority mode while the Qav mode is enabled, so,
+ * instead of disabling strict priority mode, we give
+ * queue 0 the maximum of credits possible.
+ *
+ * See section 8.12.19 of the i210 datasheet, "Note:
+ * Queue0 QueueMode must be set to 1b when
+ * TransmitMode is set to Qav."
+ */
+ if (queue == 0 && !enable) {
+ /* max "linkspeed" idleslope in kbps */
+ idleslope = 1000000;
+ hicredit = ETH_FRAME_LEN;
+ }
+
set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
if (!err)
continue;
hw_dbg(&adapter->hw, "Allocation for XDP Queue %u failed\n", j);
- break;
+ goto err_setup_tx;
}
return 0;
atomic_set(&efx->active_queues, 0);
}
-static bool efx_ef10_filter_equal(const struct efx_filter_spec *left,
- const struct efx_filter_spec *right)
-{
- if ((left->match_flags ^ right->match_flags) |
- ((left->flags ^ right->flags) &
- (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
- return false;
-
- return memcmp(&left->outer_vid, &right->outer_vid,
- sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) == 0;
-}
-
-static unsigned int efx_ef10_filter_hash(const struct efx_filter_spec *spec)
-{
- BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
- return jhash2((const u32 *)&spec->outer_vid,
- (sizeof(struct efx_filter_spec) -
- offsetof(struct efx_filter_spec, outer_vid)) / 4,
- 0);
- /* XXX should we randomise the initval? */
-}
-
/* Decide whether a filter should be exclusive or else should allow
* delivery to additional recipients. Currently we decide that
* filters for specific local unicast MAC and IP addresses are
goto out_unlock;
match_pri = rc;
- hash = efx_ef10_filter_hash(spec);
+ hash = efx_filter_spec_hash(spec);
is_mc_recip = efx_filter_is_mc_recipient(spec);
if (is_mc_recip)
bitmap_zero(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
if (!saved_spec) {
if (ins_index < 0)
ins_index = i;
- } else if (efx_ef10_filter_equal(spec, saved_spec)) {
+ } else if (efx_filter_spec_equal(spec, saved_spec)) {
if (spec->priority < saved_spec->priority &&
spec->priority != EFX_FILTER_PRI_AUTO) {
rc = -EPERM;
static bool efx_ef10_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
unsigned int filter_idx)
{
+ struct efx_filter_spec *spec, saved_spec;
struct efx_ef10_filter_table *table;
- struct efx_filter_spec *spec;
- bool ret;
+ struct efx_arfs_rule *rule = NULL;
+ bool ret = true, force = false;
+ u16 arfs_id;
down_read(&efx->filter_sem);
table = efx->filter_state;
down_write(&table->lock);
spec = efx_ef10_filter_entry_spec(table, filter_idx);
- if (!spec || spec->priority != EFX_FILTER_PRI_HINT) {
- ret = true;
+ if (!spec || spec->priority != EFX_FILTER_PRI_HINT)
goto out_unlock;
- }
- if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, 0)) {
- ret = false;
- goto out_unlock;
+ spin_lock_bh(&efx->rps_hash_lock);
+ if (!efx->rps_hash_table) {
+ /* In the absence of the table, we always return 0 to ARFS. */
+ arfs_id = 0;
+ } else {
+ rule = efx_rps_hash_find(efx, spec);
+ if (!rule)
+ /* ARFS table doesn't know of this filter, so remove it */
+ goto expire;
+ arfs_id = rule->arfs_id;
+ ret = efx_rps_check_rule(rule, filter_idx, &force);
+ if (force)
+ goto expire;
+ if (!ret) {
+ spin_unlock_bh(&efx->rps_hash_lock);
+ goto out_unlock;
+ }
}
-
+ if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, arfs_id))
+ ret = false;
+ else if (rule)
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+expire:
+ saved_spec = *spec; /* remove operation will kfree spec */
+ spin_unlock_bh(&efx->rps_hash_lock);
+ /* At this point (since we dropped the lock), another thread might queue
+ * up a fresh insertion request (but the actual insertion will be held
+ * up by our possession of the filter table lock). In that case, it
+ * will set rule->filter_id to EFX_ARFS_FILTER_ID_PENDING, meaning that
+ * the rule is not removed by efx_rps_hash_del() below.
+ */
ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority,
filter_idx, true) == 0;
+ /* While we can't safely dereference rule (we dropped the lock), we can
+ * still test it for NULL.
+ */
+ if (ret && rule) {
+ /* Expiring, so remove entry from ARFS table */
+ spin_lock_bh(&efx->rps_hash_lock);
+ efx_rps_hash_del(efx, &saved_spec);
+ spin_unlock_bh(&efx->rps_hash_lock);
+ }
out_unlock:
up_write(&table->lock);
up_read(&efx->filter_sem);
mutex_init(&efx->mac_lock);
#ifdef CONFIG_RFS_ACCEL
mutex_init(&efx->rps_mutex);
+ spin_lock_init(&efx->rps_hash_lock);
+ /* Failure to allocate is not fatal, but may degrade ARFS performance */
+ efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE,
+ sizeof(*efx->rps_hash_table), GFP_KERNEL);
#endif
efx->phy_op = &efx_dummy_phy_operations;
efx->mdio.dev = net_dev;
{
int i;
+#ifdef CONFIG_RFS_ACCEL
+ kfree(efx->rps_hash_table);
+#endif
+
for (i = 0; i < EFX_MAX_CHANNELS; i++)
kfree(efx->channel[i]);
stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops);
}
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right)
+{
+ if ((left->match_flags ^ right->match_flags) |
+ ((left->flags ^ right->flags) &
+ (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
+ return false;
+
+ return memcmp(&left->outer_vid, &right->outer_vid,
+ sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) == 0;
+}
+
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec)
+{
+ BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
+ return jhash2((const u32 *)&spec->outer_vid,
+ (sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) / 4,
+ 0);
+}
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force)
+{
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) {
+ /* ARFS is currently updating this entry, leave it */
+ return false;
+ }
+ if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) {
+ /* ARFS tried and failed to update this, so it's probably out
+ * of date. Remove the filter and the ARFS rule entry.
+ */
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+ *force = true;
+ return true;
+ } else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */
+ /* ARFS has moved on, so old filter is not needed. Since we did
+ * not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will
+ * not be removed by efx_rps_hash_del() subsequently.
+ */
+ *force = true;
+ return true;
+ }
+ /* Remove it iff ARFS wants to. */
+ return true;
+}
+
+struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ u32 hash = efx_filter_spec_hash(spec);
+
+ WARN_ON(!spin_is_locked(&efx->rps_hash_lock));
+ if (!efx->rps_hash_table)
+ return NULL;
+ return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
+}
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec))
+ return rule;
+ }
+ return NULL;
+}
+
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (!head)
+ return NULL;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ *new = false;
+ return rule;
+ }
+ }
+ rule = kmalloc(sizeof(*rule), GFP_ATOMIC);
+ *new = true;
+ if (rule) {
+ memcpy(&rule->spec, spec, sizeof(rule->spec));
+ hlist_add_head(&rule->node, head);
+ }
+ return rule;
+}
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec)
+{
+ struct efx_arfs_rule *rule;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ head = efx_rps_hash_bucket(efx, spec);
+ if (WARN_ON(!head))
+ return;
+ hlist_for_each(node, head) {
+ rule = container_of(node, struct efx_arfs_rule, node);
+ if (efx_filter_spec_equal(spec, &rule->spec)) {
+ /* Someone already reused the entry. We know that if
+ * this check doesn't fire (i.e. filter_id == REMOVING)
+ * then the REMOVING mark was put there by our caller,
+ * because caller is holding a lock on filter table and
+ * only holders of that lock set REMOVING.
+ */
+ if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING)
+ return;
+ hlist_del(node);
+ kfree(rule);
+ return;
+ }
+ }
+ /* We didn't find it. */
+ WARN_ON(1);
+}
+#endif
+
/* RSS contexts. We're using linked lists and crappy O(n) algorithms, because
* (a) this is an infrequent control-plane operation and (b) n is small (max 64)
*/
#endif
bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
+bool efx_filter_spec_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right);
+u32 efx_filter_spec_hash(const struct efx_filter_spec *spec);
+
+#ifdef CONFIG_RFS_ACCEL
+bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx,
+ bool *force);
+
+struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx,
+ const struct efx_filter_spec *spec);
+
+/* @new is written to indicate if entry was newly added (true) or if an old
+ * entry was found and returned (false).
+ */
+struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ bool *new);
+
+void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec);
+#endif
+
/* RSS contexts */
struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx);
struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id);
{
struct efx_farch_filter_state *state = efx->filter_state;
struct efx_farch_filter_table *table;
- bool ret = false;
+ bool ret = false, force = false;
+ u16 arfs_id;
down_write(&state->lock);
+ spin_lock_bh(&efx->rps_hash_lock);
table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
if (test_bit(index, table->used_bitmap) &&
- table->spec[index].priority == EFX_FILTER_PRI_HINT &&
- rps_may_expire_flow(efx->net_dev, table->spec[index].dmaq_id,
- flow_id, 0)) {
- efx_farch_filter_table_clear_entry(efx, table, index);
- ret = true;
+ table->spec[index].priority == EFX_FILTER_PRI_HINT) {
+ struct efx_arfs_rule *rule = NULL;
+ struct efx_filter_spec spec;
+
+ efx_farch_filter_to_gen_spec(&spec, &table->spec[index]);
+ if (!efx->rps_hash_table) {
+ /* In the absence of the table, we always returned 0 to
+ * ARFS, so use the same to query it.
+ */
+ arfs_id = 0;
+ } else {
+ rule = efx_rps_hash_find(efx, &spec);
+ if (!rule) {
+ /* ARFS table doesn't know of this filter, remove it */
+ force = true;
+ } else {
+ arfs_id = rule->arfs_id;
+ if (!efx_rps_check_rule(rule, index, &force))
+ goto out_unlock;
+ }
+ }
+ if (force || rps_may_expire_flow(efx->net_dev, spec.dmaq_id,
+ flow_id, arfs_id)) {
+ if (rule)
+ rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING;
+ efx_rps_hash_del(efx, &spec);
+ efx_farch_filter_table_clear_entry(efx, table, index);
+ ret = true;
+ }
}
-
+out_unlock:
+ spin_unlock_bh(&efx->rps_hash_lock);
up_write(&state->lock);
return ret;
}
};
#ifdef CONFIG_RFS_ACCEL
+/* Order of these is important, since filter_id >= %EFX_ARFS_FILTER_ID_PENDING
+ * is used to test if filter does or will exist.
+ */
+#define EFX_ARFS_FILTER_ID_PENDING -1
+#define EFX_ARFS_FILTER_ID_ERROR -2
+#define EFX_ARFS_FILTER_ID_REMOVING -3
+/**
+ * struct efx_arfs_rule - record of an ARFS filter and its IDs
+ * @node: linkage into hash table
+ * @spec: details of the filter (used as key for hash table). Use efx->type to
+ * determine which member to use.
+ * @rxq_index: channel to which the filter will steer traffic.
+ * @arfs_id: filter ID which was returned to ARFS
+ * @filter_id: index in software filter table. May be
+ * %EFX_ARFS_FILTER_ID_PENDING if filter was not inserted yet,
+ * %EFX_ARFS_FILTER_ID_ERROR if filter insertion failed, or
+ * %EFX_ARFS_FILTER_ID_REMOVING if expiry is currently removing the filter.
+ */
+struct efx_arfs_rule {
+ struct hlist_node node;
+ struct efx_filter_spec spec;
+ u16 rxq_index;
+ u16 arfs_id;
+ s32 filter_id;
+};
+
+/* Size chosen so that the table is one page (4kB) */
+#define EFX_ARFS_HASH_TABLE_SIZE 512
+
/**
* struct efx_async_filter_insertion - Request to asynchronously insert a filter
* @net_dev: Reference to the netdevice
* @rps_expire_channel's @rps_flow_id
* @rps_slot_map: bitmap of in-flight entries in @rps_slot
* @rps_slot: array of ARFS insertion requests for efx_filter_rfs_work()
+ * @rps_hash_lock: Protects ARFS filter mapping state (@rps_hash_table and
+ * @rps_next_id).
+ * @rps_hash_table: Mapping between ARFS filters and their various IDs
+ * @rps_next_id: next arfs_id for an ARFS filter
* @active_queues: Count of RX and TX queues that haven't been flushed and drained.
* @rxq_flush_pending: Count of number of receive queues that need to be flushed.
* Decremented when the efx_flush_rx_queue() is called.
unsigned int rps_expire_index;
unsigned long rps_slot_map;
struct efx_async_filter_insertion rps_slot[EFX_RPS_MAX_IN_FLIGHT];
+ spinlock_t rps_hash_lock;
+ struct hlist_head *rps_hash_table;
+ u32 rps_next_id;
#endif
atomic_t active_queues;
struct efx_nic *efx = netdev_priv(req->net_dev);
struct efx_channel *channel = efx_get_channel(efx, req->rxq_index);
int slot_idx = req - efx->rps_slot;
+ struct efx_arfs_rule *rule;
+ u16 arfs_id = 0;
int rc;
rc = efx->type->filter_insert(efx, &req->spec, true);
+ if (efx->rps_hash_table) {
+ spin_lock_bh(&efx->rps_hash_lock);
+ rule = efx_rps_hash_find(efx, &req->spec);
+ /* The rule might have already gone, if someone else's request
+ * for the same spec was already worked and then expired before
+ * we got around to our work. In that case we have nothing
+ * tying us to an arfs_id, meaning that as soon as the filter
+ * is considered for expiry it will be removed.
+ */
+ if (rule) {
+ if (rc < 0)
+ rule->filter_id = EFX_ARFS_FILTER_ID_ERROR;
+ else
+ rule->filter_id = rc;
+ arfs_id = rule->arfs_id;
+ }
+ spin_unlock_bh(&efx->rps_hash_lock);
+ }
if (rc >= 0) {
/* Remember this so we can check whether to expire the filter
* later.
if (req->spec.ether_type == htons(ETH_P_IP))
netif_info(efx, rx_status, efx->net_dev,
- "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
+ "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d id %u]\n",
(req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
req->spec.rem_host, ntohs(req->spec.rem_port),
req->spec.loc_host, ntohs(req->spec.loc_port),
- req->rxq_index, req->flow_id, rc);
+ req->rxq_index, req->flow_id, rc, arfs_id);
else
netif_info(efx, rx_status, efx->net_dev,
- "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n",
+ "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d id %u]\n",
(req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
req->spec.rem_host, ntohs(req->spec.rem_port),
req->spec.loc_host, ntohs(req->spec.loc_port),
- req->rxq_index, req->flow_id, rc);
+ req->rxq_index, req->flow_id, rc, arfs_id);
}
/* Release references */
{
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_async_filter_insertion *req;
+ struct efx_arfs_rule *rule;
struct flow_keys fk;
int slot_idx;
+ bool new;
int rc;
/* find a free slot */
req->spec.rem_port = fk.ports.src;
req->spec.loc_port = fk.ports.dst;
+ if (efx->rps_hash_table) {
+ /* Add it to ARFS hash table */
+ spin_lock(&efx->rps_hash_lock);
+ rule = efx_rps_hash_add(efx, &req->spec, &new);
+ if (!rule) {
+ rc = -ENOMEM;
+ goto out_unlock;
+ }
+ if (new)
+ rule->arfs_id = efx->rps_next_id++ % RPS_NO_FILTER;
+ rc = rule->arfs_id;
+ /* Skip if existing or pending filter already does the right thing */
+ if (!new && rule->rxq_index == rxq_index &&
+ rule->filter_id >= EFX_ARFS_FILTER_ID_PENDING)
+ goto out_unlock;
+ rule->rxq_index = rxq_index;
+ rule->filter_id = EFX_ARFS_FILTER_ID_PENDING;
+ spin_unlock(&efx->rps_hash_lock);
+ } else {
+ /* Without an ARFS hash table, we just use arfs_id 0 for all
+ * filters. This means if multiple flows hash to the same
+ * flow_id, all but the most recently touched will be eligible
+ * for expiry.
+ */
+ rc = 0;
+ }
+
+ /* Queue the request */
dev_hold(req->net_dev = net_dev);
INIT_WORK(&req->work, efx_filter_rfs_work);
req->rxq_index = rxq_index;
req->flow_id = flow_id;
schedule_work(&req->work);
- return 0;
+ return rc;
+out_unlock:
+ spin_unlock(&efx->rps_hash_lock);
out_clear:
clear_bit(slot_idx, &efx->rps_slot_map);
return rc;
#define RX_PRIORITY_MAPPING 0x76543210
#define TX_PRIORITY_MAPPING 0x33221100
-#define CPDMA_TX_PRIORITY_MAP 0x01234567
+#define CPDMA_TX_PRIORITY_MAP 0x76543210
#define CPSW_VLAN_AWARE BIT(1)
#define CPSW_RX_VLAN_ENCAP BIT(2)
if (err < 0)
goto error;
+ /* If WOL event happened once, the LED[2] interrupt pin
+ * will not be cleared unless we reading the interrupt status
+ * register. If interrupts are in use, the normal interrupt
+ * handling will clear the WOL event. Clear the WOL event
+ * before enabling it if !phy_interrupt_is_valid()
+ */
+ if (!phy_interrupt_is_valid(phydev))
+ phy_read(phydev, MII_M1011_IEVENT);
+
/* Enable the WOL interrupt */
err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0,
MII_88E1318S_PHY_CSIER_WOL_EIE);
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppox))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OE)
goto end;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int __team_port_enable_netpoll(struct team_port *port)
{
struct netpoll *np;
int err;
- if (!team->dev->npinfo)
- return 0;
-
np = kzalloc(sizeof(*np), GFP_KERNEL);
if (!np)
return -ENOMEM;
return err;
}
+static int team_port_enable_netpoll(struct team_port *port)
+{
+ if (!port->team->dev->npinfo)
+ return 0;
+
+ return __team_port_enable_netpoll(port);
+}
+
static void team_port_disable_netpoll(struct team_port *port)
{
struct netpoll *np = port->np;
kfree(np);
}
#else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port)
+static int team_port_enable_netpoll(struct team_port *port)
{
return 0;
}
goto err_vids_add;
}
- err = team_port_enable_netpoll(team, port);
+ err = team_port_enable_netpoll(port);
if (err) {
netdev_err(dev, "Failed to enable netpoll on device %s\n",
portname);
mutex_lock(&team->lock);
list_for_each_entry(port, &team->port_list, list) {
- err = team_port_enable_netpoll(team, port);
+ err = __team_port_enable_netpoll(port);
if (err) {
__team_netpoll_cleanup(team);
break;
* devices should not be touched during freeze/thaw transitions,
* however.
*/
- if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
+ if (!dev_pm_smart_suspend_and_suspended(dev)) {
pm_runtime_resume(dev);
+ pci_dev->state_saved = false;
+ }
- pci_dev->state_saved = false;
if (pm->freeze) {
int error;
int dasd_alias_add_device(struct dasd_device *device)
{
struct dasd_eckd_private *private = device->private;
- struct alias_lcu *lcu;
+ __u8 uaddr = private->uid.real_unit_addr;
+ struct alias_lcu *lcu = private->lcu;
unsigned long flags;
int rc;
- lcu = private->lcu;
rc = 0;
spin_lock_irqsave(&lcu->lock, flags);
+ /*
+ * Check if device and lcu type differ. If so, the uac data may be
+ * outdated and needs to be updated.
+ */
+ if (private->uid.type != lcu->uac->unit[uaddr].ua_type) {
+ lcu->flags |= UPDATE_PENDING;
+ DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+ "uid type mismatch - trigger rescan");
+ }
if (!(lcu->flags & UPDATE_PENDING)) {
rc = _add_device_to_lcu(lcu, device, device);
if (rc)
static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area)
{
+ struct channel_path *chp;
struct chp_link link;
struct chp_id chpid;
int status;
chpid.id = sei_area->rsid;
/* allocate a new channel path structure, if needed */
status = chp_get_status(chpid);
- if (status < 0)
- chp_new(chpid);
- else if (!status)
+ if (!status)
return;
+
+ if (status < 0) {
+ chp_new(chpid);
+ } else {
+ chp = chpid_to_chp(chpid);
+ mutex_lock(&chp->lock);
+ chp_update_desc(chp);
+ mutex_unlock(&chp->lock);
+ }
memset(&link, 0, sizeof(struct chp_link));
link.chpid = chpid;
if ((sei_area->vf & 0xc0) != 0) {
int ccode;
__u8 lpm;
unsigned long flags;
+ int ret;
sch = private->sch;
spin_lock_irqsave(sch->lock, flags);
private->state = VFIO_CCW_STATE_BUSY;
- spin_unlock_irqrestore(sch->lock, flags);
orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
* Initialize device status information
*/
sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
- return 0;
+ ret = 0;
+ break;
case 1: /* Status pending */
case 2: /* Busy */
- return -EBUSY;
+ ret = -EBUSY;
+ break;
case 3: /* Device/path not operational */
{
lpm = orb->cmd.lpm;
sch->lpm = 0;
if (cio_update_schib(sch))
- return -ENODEV;
-
- return sch->lpm ? -EACCES : -ENODEV;
+ ret = -ENODEV;
+ else
+ ret = sch->lpm ? -EACCES : -ENODEV;
+ break;
}
default:
- return ccode;
+ ret = ccode;
}
+ spin_unlock_irqrestore(sch->lock, flags);
+ return ret;
}
static void fsm_notoper(struct vfio_ccw_private *private,
enum qeth_cmd_buffer_state {
BUF_STATE_FREE,
BUF_STATE_LOCKED,
- BUF_STATE_PROCESSED,
};
enum qeth_cq {
struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO];
atomic_t irq_pending;
int io_buf_no;
- int buf_no;
};
/**
qeth_put_reply(reply);
}
spin_unlock_irqrestore(&card->lock, flags);
- atomic_set(&card->write.irq_pending, 0);
}
EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list);
for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
qeth_release_buffer(channel, &channel->iob[cnt]);
- channel->buf_no = 0;
channel->io_buf_no = 0;
}
EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers);
kfree(channel->iob[cnt].data);
return -ENOMEM;
}
- channel->buf_no = 0;
channel->io_buf_no = 0;
atomic_set(&channel->irq_pending, 0);
spin_lock_init(&channel->iob_lock);
{
int rc;
int cstat, dstat;
- struct qeth_cmd_buffer *buffer;
+ struct qeth_cmd_buffer *iob = NULL;
struct qeth_channel *channel;
struct qeth_card *card;
- struct qeth_cmd_buffer *iob;
- __u8 index;
-
- if (__qeth_check_irb_error(cdev, intparm, irb))
- return;
- cstat = irb->scsw.cmd.cstat;
- dstat = irb->scsw.cmd.dstat;
card = CARD_FROM_CDEV(cdev);
if (!card)
channel = &card->data;
QETH_CARD_TEXT(card, 5, "data");
}
+
+ if (qeth_intparm_is_iob(intparm))
+ iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
+
+ if (__qeth_check_irb_error(cdev, intparm, irb)) {
+ /* IO was terminated, free its resources. */
+ if (iob)
+ qeth_release_buffer(iob->channel, iob);
+ atomic_set(&channel->irq_pending, 0);
+ wake_up(&card->wait_q);
+ return;
+ }
+
atomic_set(&channel->irq_pending, 0);
if (irb->scsw.cmd.fctl & (SCSW_FCTL_CLEAR_FUNC))
/* we don't have to handle this further */
intparm = 0;
}
+
+ cstat = irb->scsw.cmd.cstat;
+ dstat = irb->scsw.cmd.dstat;
+
if ((dstat & DEV_STAT_UNIT_EXCEP) ||
(dstat & DEV_STAT_UNIT_CHECK) ||
(cstat)) {
channel->state = CH_STATE_RCD_DONE;
goto out;
}
- if (intparm) {
- buffer = (struct qeth_cmd_buffer *) __va((addr_t)intparm);
- buffer->state = BUF_STATE_PROCESSED;
- }
if (channel == &card->data)
return;
if (channel == &card->read &&
channel->state == CH_STATE_UP)
__qeth_issue_next_read(card);
- iob = channel->iob;
- index = channel->buf_no;
- while (iob[index].state == BUF_STATE_PROCESSED) {
- if (iob[index].callback != NULL)
- iob[index].callback(channel, iob + index);
+ if (iob && iob->callback)
+ iob->callback(iob->channel, iob);
- index = (index + 1) % QETH_CMD_BUFFER_NO;
- }
- channel->buf_no = index;
out:
wake_up(&card->wait_q);
return;
atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
- rc = ccw_device_start(channel->ccwdev,
- &channel->ccw, (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+ (addr_t) iob, 0, 0, QETH_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
if (rc) {
if (channel->state != CH_STATE_UP) {
rc = -ETIME;
QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc);
- qeth_clear_cmd_buffers(channel);
} else
rc = 0;
return rc;
atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
- rc = ccw_device_start(channel->ccwdev,
- &channel->ccw, (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+ (addr_t) iob, 0, 0, QETH_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n",
dev_name(&channel->ccwdev->dev));
QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME);
- qeth_clear_cmd_buffers(channel);
return -ETIME;
}
return qeth_idx_activate_get_answer(channel, idx_reply_cb);
QETH_CARD_TEXT(card, 6, "noirqpnd");
spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
- rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
- (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+ (addr_t) iob, 0, 0, event_timeout);
spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: "
}
}
- if (reply->rc == -EIO)
- goto error;
rc = reply->rc;
qeth_put_reply(reply);
return rc;
list_del_init(&reply->list);
spin_unlock_irqrestore(&reply->card->lock, flags);
atomic_inc(&reply->received);
-error:
- atomic_set(&card->write.irq_pending, 0);
- qeth_release_buffer(iob->channel, iob);
- card->write.buf_no = (card->write.buf_no + 1) % QETH_CMD_BUFFER_NO;
rc = reply->rc;
qeth_put_reply(reply);
return rc;
return rc;
}
-static int qeth_default_setadapterparms_cb(struct qeth_card *card,
- struct qeth_reply *reply, unsigned long data)
+static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd)
{
- struct qeth_ipa_cmd *cmd;
-
- QETH_CARD_TEXT(card, 4, "defadpcb");
-
- cmd = (struct qeth_ipa_cmd *) data;
- if (cmd->hdr.return_code == 0)
+ if (!cmd->hdr.return_code)
cmd->hdr.return_code =
cmd->data.setadapterparms.hdr.return_code;
- return 0;
+ return cmd->hdr.return_code;
}
static int qeth_query_setadapterparms_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 3, "quyadpcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) {
card->info.link_type =
cmd->data.setadapterparms.data.query_cmds_supp.lan_type;
}
card->options.adp.supported_funcs =
cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds;
- return qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
+ return 0;
}
static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
static int qeth_query_switch_attributes_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
- struct qeth_switch_info *sw_info;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_query_switch_attributes *attrs;
+ struct qeth_switch_info *sw_info;
QETH_CARD_TEXT(card, 2, "qswiatcb");
- cmd = (struct qeth_ipa_cmd *) data;
- sw_info = (struct qeth_switch_info *)reply->param;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
- sw_info->capabilities = attrs->capabilities;
- sw_info->settings = attrs->settings;
- QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
- sw_info->settings);
- }
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
+ sw_info = (struct qeth_switch_info *)reply->param;
+ attrs = &cmd->data.setadapterparms.data.query_switch_attributes;
+ sw_info->capabilities = attrs->capabilities;
+ sw_info->settings = attrs->settings;
+ QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities,
+ sw_info->settings);
return 0;
}
static int qeth_setadp_promisc_mode_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_ipacmd_setadpparms *setparms;
QETH_CARD_TEXT(card, 4, "prmadpcb");
- cmd = (struct qeth_ipa_cmd *) data;
setparms = &(cmd->data.setadapterparms);
-
- qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd);
- if (cmd->hdr.return_code) {
+ if (qeth_setadpparms_inspect_rc(cmd)) {
QETH_CARD_TEXT_(card, 4, "prmrc%x", cmd->hdr.return_code);
setparms->data.mode = SET_PROMISC_MODE_OFF;
}
static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
QETH_CARD_TEXT(card, 4, "chgmaccb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *) data;
if (!card->options.layer2 ||
!(card->info.mac_bits & QETH_LAYER2_MAC_READ)) {
ether_addr_copy(card->dev->dev_addr,
cmd->data.setadapterparms.data.change_addr.addr);
card->info.mac_bits |= QETH_LAYER2_MAC_READ;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data;
struct qeth_set_access_ctrl *access_ctrl_req;
int fallback = *(int *)reply->param;
QETH_CARD_TEXT(card, 4, "setaccb");
+ if (cmd->hdr.return_code)
+ return 0;
+ qeth_setadpparms_inspect_rc(cmd);
- cmd = (struct qeth_ipa_cmd *) data;
access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
QETH_DBF_TEXT_(SETUP, 2, "setaccb");
QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name);
card->options.isolation = card->options.prev_isolation;
break;
}
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
return 0;
}
static int qeth_setadpparms_query_oat_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_qoat_priv *priv;
char *resdata;
int resdatalen;
QETH_CARD_TEXT(card, 3, "qoatcb");
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- cmd = (struct qeth_ipa_cmd *)data;
priv = (struct qeth_qoat_priv *)reply->param;
resdatalen = cmd->data.setadapterparms.hdr.cmdlength;
resdata = (char *)data + 28;
static int qeth_query_card_info_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
- struct qeth_ipa_cmd *cmd;
+ struct carrier_info *carrier_info = (struct carrier_info *)reply->param;
+ struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
struct qeth_query_card_info *card_info;
- struct carrier_info *carrier_info;
QETH_CARD_TEXT(card, 2, "qcrdincb");
- carrier_info = (struct carrier_info *)reply->param;
- cmd = (struct qeth_ipa_cmd *)data;
- card_info = &cmd->data.setadapterparms.data.card_info;
- if (cmd->data.setadapterparms.hdr.return_code == 0) {
- carrier_info->card_type = card_info->card_type;
- carrier_info->port_mode = card_info->port_mode;
- carrier_info->port_speed = card_info->port_speed;
- }
+ if (qeth_setadpparms_inspect_rc(cmd))
+ return 0;
- qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd);
+ card_info = &cmd->data.setadapterparms.data.card_info;
+ carrier_info->card_type = card_info->card_type;
+ carrier_info->port_mode = card_info->port_mode;
+ carrier_info->port_speed = card_info->port_speed;
return 0;
}
goto out;
}
- ccw_device_get_id(CARD_DDEV(card), &id);
+ ccw_device_get_id(CARD_RDEV(card), &id);
request->resp_buf_len = sizeof(*response);
request->resp_version = DIAG26C_VERSION2;
request->op_code = DIAG26C_GET_MAC;
mutex_init(&qeth_mod_mutex);
qeth_wq = create_singlethread_workqueue("qeth_wq");
+ if (!qeth_wq) {
+ rc = -ENOMEM;
+ goto out_err;
+ }
rc = qeth_register_dbf_views();
if (rc)
- goto out_err;
+ goto dbf_err;
qeth_core_root_dev = root_device_register("qeth");
rc = PTR_ERR_OR_ZERO(qeth_core_root_dev);
if (rc)
root_device_unregister(qeth_core_root_dev);
register_err:
qeth_unregister_dbf_views();
+dbf_err:
+ destroy_workqueue(qeth_wq);
out_err:
pr_err("Initializing the qeth device driver failed\n");
return rc;
#define QETH_HALT_CHANNEL_PARM -11
#define QETH_RCD_PARM -12
+static inline bool qeth_intparm_is_iob(unsigned long intparm)
+{
+ switch (intparm) {
+ case QETH_CLEAR_CHANNEL_PARM:
+ case QETH_HALT_CHANNEL_PARM:
+ case QETH_RCD_PARM:
+ case 0:
+ return false;
+ }
+ return true;
+}
+
/*****************************************************************************/
/* IP Assist related definitions */
/*****************************************************************************/
QETH_CARD_TEXT(card, 2, "L2Setmac");
rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC);
if (rc == 0) {
- card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
- ether_addr_copy(card->dev->dev_addr, mac);
dev_info(&card->gdev->dev,
- "MAC address %pM successfully registered on device %s\n",
- card->dev->dev_addr, card->dev->name);
+ "MAC address %pM successfully registered on device %s\n",
+ mac, card->dev->name);
} else {
- card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
switch (rc) {
case -EEXIST:
dev_warn(&card->gdev->dev,
return rc;
}
-static int qeth_l2_send_delmac(struct qeth_card *card, __u8 *mac)
-{
- int rc;
-
- QETH_CARD_TEXT(card, 2, "L2Delmac");
- if (!(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
- return 0;
- rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_DELVMAC);
- if (rc == 0)
- card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
- return rc;
-}
-
static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
{
enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
{
struct sockaddr *addr = p;
struct qeth_card *card = dev->ml_priv;
+ u8 old_addr[ETH_ALEN];
int rc = 0;
QETH_CARD_TEXT(card, 3, "setmac");
return -EOPNOTSUPP;
}
QETH_CARD_HEX(card, 3, addr->sa_data, ETH_ALEN);
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
QETH_CARD_TEXT(card, 3, "setmcREC");
return -ERESTARTSYS;
}
- rc = qeth_l2_send_delmac(card, &card->dev->dev_addr[0]);
- if (!rc || (rc == -ENOENT))
- rc = qeth_l2_send_setmac(card, addr->sa_data);
- return rc ? -EINVAL : 0;
+
+ if (!qeth_card_hw_is_reachable(card)) {
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+ return 0;
+ }
+
+ /* don't register the same address twice */
+ if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
+ (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
+ return 0;
+
+ /* add the new address, switch over, drop the old */
+ rc = qeth_l2_send_setmac(card, addr->sa_data);
+ if (rc)
+ return rc;
+ ether_addr_copy(old_addr, dev->dev_addr);
+ ether_addr_copy(dev->dev_addr, addr->sa_data);
+
+ if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
+ qeth_l2_remove_mac(card, old_addr);
+ card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
+ return 0;
}
static void qeth_promisc_to_bridge(struct qeth_card *card)
goto out_remove;
}
- if (card->info.type != QETH_CARD_TYPE_OSN)
- qeth_l2_send_setmac(card, &card->dev->dev_addr[0]);
+ if (card->info.type != QETH_CARD_TYPE_OSN &&
+ !qeth_l2_send_setmac(card, card->dev->dev_addr))
+ card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) {
if (card->info.hwtrap &&
qeth_prepare_control_data(card, len, iob);
QETH_CARD_TEXT(card, 6, "osnoirqp");
spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
- rc = ccw_device_start(card->write.ccwdev, &card->write.ccw,
- (addr_t) iob, 0, 0);
+ rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+ (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT);
spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
if (rc) {
QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: "
"Number of Abort FW Timeouts: %lld\n"
"Number of Abort IO NOT Found: %lld\n"
- "Abord issued times: \n"
+ "Abort issued times: \n"
" < 6 sec : %lld\n"
" 6 sec - 20 sec : %lld\n"
" 20 sec - 30 sec : %lld\n"
goto fail_fw_init;
}
- ret = 0;
+ return 0;
fail_fw_init:
dev_err(&instance->pdev->dev,
- "Init cmd return status %s for SCSI host %d\n",
- ret ? "FAILED" : "SUCCESS", instance->host->host_no);
+ "Init cmd return status FAILED for SCSI host %d\n",
+ instance->host->host_no);
return ret;
}
#define F_INV_OP 0x200
#define F_FAKE_RW 0x400
#define F_M_ACCESS 0x800 /* media access */
-#define F_LONG_DELAY 0x1000
+#define F_SSU_DELAY 0x1000
+#define F_SYNC_DELAY 0x2000
#define FF_RESPOND (F_RL_WLUN_OK | F_SKIP_UA | F_DELAY_OVERR)
#define FF_MEDIA_IO (F_M_ACCESS | F_FAKE_RW)
#define FF_SA (F_SA_HIGH | F_SA_LOW)
+#define F_LONG_DELAY (F_SSU_DELAY | F_SYNC_DELAY)
#define SDEBUG_MAX_PARTS 4
};
static const struct opcode_info_t sync_cache_iarr[] = {
- {0, 0x91, 0, F_LONG_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
+ {0, 0x91, 0, F_SYNC_DELAY | F_M_ACCESS, resp_sync_cache, NULL,
{16, 0x6, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
0xff, 0xff, 0xff, 0xff, 0x3f, 0xc7} }, /* SYNC_CACHE (16) */
};
resp_write_dt0, write_iarr, /* WRITE(16) */
{16, 0xfa, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
0xff, 0xff, 0xff, 0xff, 0xff, 0xc7} },
- {0, 0x1b, 0, F_LONG_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
+ {0, 0x1b, 0, F_SSU_DELAY, resp_start_stop, NULL,/* START STOP UNIT */
{6, 0x1, 0, 0xf, 0xf7, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
{ARRAY_SIZE(sa_in_16_iarr), 0x9e, 0x10, F_SA_LOW | F_D_IN,
resp_readcap16, sa_in_16_iarr, /* SA_IN(16), READ CAPACITY(16) */
resp_write_same_10, write_same_iarr, /* WRITE SAME(10) */
{10, 0xff, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0,
0, 0, 0, 0, 0} },
- {ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_LONG_DELAY | F_M_ACCESS,
+ {ARRAY_SIZE(sync_cache_iarr), 0x35, 0, F_SYNC_DELAY | F_M_ACCESS,
resp_sync_cache, sync_cache_iarr,
{10, 0x7, 0xff, 0xff, 0xff, 0xff, 0x3f, 0xff, 0xff, 0xc7, 0, 0,
0, 0, 0, 0} }, /* SYNC_CACHE (10) */
static bool sdebug_any_injecting_opt;
static bool sdebug_verbose;
static bool have_dif_prot;
+static bool write_since_sync;
static bool sdebug_statistics = DEF_STATISTICS;
static unsigned int sdebug_store_sectors;
{
unsigned char *cmd = scp->cmnd;
int power_cond, stop;
+ bool changing;
power_cond = (cmd[4] & 0xf0) >> 4;
if (power_cond) {
return check_condition_result;
}
stop = !(cmd[4] & 1);
+ changing = atomic_read(&devip->stopped) == !stop;
atomic_xchg(&devip->stopped, stop);
- return (cmd[1] & 0x1) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+ if (!changing || cmd[1] & 0x1) /* state unchanged or IMMED set */
+ return SDEG_RES_IMMED_MASK;
+ else
+ return 0;
}
static sector_t get_sdebug_capacity(void)
if (do_write) {
sdb = scsi_out(scmd);
dir = DMA_TO_DEVICE;
+ write_since_sync = true;
} else {
sdb = scsi_in(scmd);
dir = DMA_FROM_DEVICE;
static int resp_sync_cache(struct scsi_cmnd *scp,
struct sdebug_dev_info *devip)
{
+ int res = 0;
u64 lba;
u32 num_blocks;
u8 *cmd = scp->cmnd;
mk_sense_buffer(scp, ILLEGAL_REQUEST, LBA_OUT_OF_RANGE, 0);
return check_condition_result;
}
- return (cmd[1] & 0x2) ? SDEG_RES_IMMED_MASK : 0; /* check IMMED bit */
+ if (!write_since_sync || cmd[1] & 0x2)
+ res = SDEG_RES_IMMED_MASK;
+ else /* delay if write_since_sync and IMMED clear */
+ write_since_sync = false;
+ return res;
}
#define RL_BUCKET_ELEMS 8
return schedule_resp(scp, devip, errsts, pfp, 0, 0);
else if ((sdebug_jdelay || sdebug_ndelay) && (flags & F_LONG_DELAY)) {
/*
- * If any delay is active, want F_LONG_DELAY to be at least 1
+ * If any delay is active, for F_SSU_DELAY want at least 1
* second and if sdebug_jdelay>0 want a long delay of that
- * many seconds.
+ * many seconds; for F_SYNC_DELAY want 1/20 of that.
*/
int jdelay = (sdebug_jdelay < 2) ? 1 : sdebug_jdelay;
+ int denom = (flags & F_SYNC_DELAY) ? 20 : 1;
- jdelay = mult_frac(USER_HZ * jdelay, HZ, USER_HZ);
+ jdelay = mult_frac(USER_HZ * jdelay, HZ, denom * USER_HZ);
return schedule_resp(scp, devip, errsts, pfp, jdelay, 0);
} else
return schedule_resp(scp, devip, errsts, pfp, sdebug_jdelay,
return nlmsg_multicast(nls, skb, 0, group, gfp);
}
+static int
+iscsi_unicast_skb(struct sk_buff *skb, u32 portid)
+{
+ return nlmsg_unicast(nls, skb, portid);
+}
+
int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
char *data, uint32_t data_size)
{
EXPORT_SYMBOL_GPL(iscsi_ping_comp_event);
static int
-iscsi_if_send_reply(uint32_t group, int seq, int type, int done, int multi,
- void *payload, int size)
+iscsi_if_send_reply(u32 portid, int type, void *payload, int size)
{
struct sk_buff *skb;
struct nlmsghdr *nlh;
int len = nlmsg_total_size(size);
- int flags = multi ? NLM_F_MULTI : 0;
- int t = done ? NLMSG_DONE : type;
skb = alloc_skb(len, GFP_ATOMIC);
if (!skb) {
return -ENOMEM;
}
- nlh = __nlmsg_put(skb, 0, 0, t, (len - sizeof(*nlh)), 0);
- nlh->nlmsg_flags = flags;
+ nlh = __nlmsg_put(skb, 0, 0, type, (len - sizeof(*nlh)), 0);
memcpy(nlmsg_data(nlh), payload, size);
- return iscsi_multicast_skb(skb, group, GFP_ATOMIC);
+ return iscsi_unicast_skb(skb, portid);
}
static int
iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
{
int err = 0;
+ u32 portid;
struct iscsi_uevent *ev = nlmsg_data(nlh);
struct iscsi_transport *transport = NULL;
struct iscsi_internal *priv;
if (!try_module_get(transport->owner))
return -EINVAL;
+ portid = NETLINK_CB(skb).portid;
+
switch (nlh->nlmsg_type) {
case ISCSI_UEVENT_CREATE_SESSION:
err = iscsi_if_create_session(priv, ep, ev,
- NETLINK_CB(skb).portid,
+ portid,
ev->u.c_session.initial_cmdsn,
ev->u.c_session.cmds_max,
ev->u.c_session.queue_depth);
}
err = iscsi_if_create_session(priv, ep, ev,
- NETLINK_CB(skb).portid,
+ portid,
ev->u.c_bound_session.initial_cmdsn,
ev->u.c_bound_session.cmds_max,
ev->u.c_bound_session.queue_depth);
static void
iscsi_if_rx(struct sk_buff *skb)
{
+ u32 portid = NETLINK_CB(skb).portid;
+
mutex_lock(&rx_queue_mutex);
while (skb->len >= NLMSG_HDRLEN) {
int err;
break;
if (ev->type == ISCSI_UEVENT_GET_CHAP && !err)
break;
- err = iscsi_if_send_reply(group, nlh->nlmsg_seq,
- nlh->nlmsg_type, 0, 0, ev, sizeof(*ev));
+ err = iscsi_if_send_reply(portid, nlh->nlmsg_type,
+ ev, sizeof(*ev));
} while (err < 0 && err != -ECONNREFUSED && err != -ESRCH);
skb_pull(skb, rlen);
}
break; /* standby */
if (sshdr.asc == 4 && sshdr.ascq == 0xc)
break; /* unavailable */
+ if (sshdr.asc == 4 && sshdr.ascq == 0x1b)
+ break; /* sanitize in progress */
/*
* Issue command to spin up drive when not ready
*/
*
* Check that all zones of the device are equal. The last zone can however
* be smaller. The zone size must also be a power of two number of LBAs.
+ *
+ * Returns the zone size in bytes upon success or an error code upon failure.
*/
-static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
+static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
{
u64 zone_blocks = 0;
sector_t block = 0;
int ret;
u8 same;
- sdkp->zone_blocks = 0;
-
/* Get a buffer */
buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
if (!buf)
/* Parse zone descriptors */
while (rec < buf + buf_len) {
- zone_blocks = get_unaligned_be64(&rec[8]);
- if (sdkp->zone_blocks == 0) {
- sdkp->zone_blocks = zone_blocks;
- } else if (zone_blocks != sdkp->zone_blocks &&
- (block + zone_blocks < sdkp->capacity
- || zone_blocks > sdkp->zone_blocks)) {
- zone_blocks = 0;
+ u64 this_zone_blocks = get_unaligned_be64(&rec[8]);
+
+ if (zone_blocks == 0) {
+ zone_blocks = this_zone_blocks;
+ } else if (this_zone_blocks != zone_blocks &&
+ (block + this_zone_blocks < sdkp->capacity
+ || this_zone_blocks > zone_blocks)) {
+ this_zone_blocks = 0;
goto out;
}
- block += zone_blocks;
+ block += this_zone_blocks;
rec += 64;
}
} while (block < sdkp->capacity);
- zone_blocks = sdkp->zone_blocks;
-
out:
if (!zone_blocks) {
if (sdkp->first_scan)
"Zone size too large\n");
ret = -ENODEV;
} else {
- sdkp->zone_blocks = zone_blocks;
- sdkp->zone_shift = ilog2(zone_blocks);
+ ret = zone_blocks;
}
out_free:
/**
* sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone).
- * @sdkp: The disk of the bitmap
+ * @nr_zones: Number of zones to allocate space for.
+ * @numa_node: NUMA node to allocate the memory from.
*/
-static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
+static inline unsigned long *
+sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node)
{
- struct request_queue *q = sdkp->disk->queue;
-
- return kzalloc_node(BITS_TO_LONGS(sdkp->nr_zones)
- * sizeof(unsigned long),
- GFP_KERNEL, q->node);
+ return kzalloc_node(BITS_TO_LONGS(nr_zones) * sizeof(unsigned long),
+ GFP_KERNEL, numa_node);
}
/**
* @sdkp: disk used
* @buf: report reply buffer
* @buflen: length of @buf
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
* @seq_zones_bitmap: bitmap of sequential zones to set
*
* Parse reported zone descriptors in @buf to identify sequential zones and
* Return the LBA after the last zone reported.
*/
static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
- unsigned int buflen,
+ unsigned int buflen, u32 zone_shift,
unsigned long *seq_zones_bitmap)
{
sector_t lba, next_lba = sdkp->capacity;
if (type != ZBC_ZONE_TYPE_CONV &&
cond != ZBC_ZONE_COND_READONLY &&
cond != ZBC_ZONE_COND_OFFLINE)
- set_bit(lba >> sdkp->zone_shift, seq_zones_bitmap);
+ set_bit(lba >> zone_shift, seq_zones_bitmap);
next_lba = lba + get_unaligned_be64(&rec[8]);
rec += 64;
}
}
/**
- * sd_zbc_setup_seq_zones_bitmap - Initialize the disk seq zone bitmap.
+ * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap.
* @sdkp: target disk
+ * @zone_shift: logarithm base 2 of the number of blocks in a zone
+ * @nr_zones: number of zones to set up a seq zone bitmap for
*
* Allocate a zone bitmap and initialize it by identifying sequential zones.
*/
-static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
+static unsigned long *
+sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift,
+ u32 nr_zones)
{
struct request_queue *q = sdkp->disk->queue;
unsigned long *seq_zones_bitmap;
unsigned char *buf;
int ret = -ENOMEM;
- seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(sdkp);
+ seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node);
if (!seq_zones_bitmap)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
if (!buf)
if (ret)
goto out;
lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
- seq_zones_bitmap);
+ zone_shift, seq_zones_bitmap);
}
if (lba != sdkp->capacity) {
kfree(buf);
if (ret) {
kfree(seq_zones_bitmap);
- return ret;
+ return ERR_PTR(ret);
}
-
- q->seq_zones_bitmap = seq_zones_bitmap;
-
- return 0;
+ return seq_zones_bitmap;
}
static void sd_zbc_cleanup(struct scsi_disk *sdkp)
q->nr_zones = 0;
}
-static int sd_zbc_setup(struct scsi_disk *sdkp)
+static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks)
{
struct request_queue *q = sdkp->disk->queue;
+ u32 zone_shift = ilog2(zone_blocks);
+ u32 nr_zones;
int ret;
- /* READ16/WRITE16 is mandatory for ZBC disks */
- sdkp->device->use_16_for_rw = 1;
- sdkp->device->use_10_for_rw = 0;
-
/* chunk_sectors indicates the zone size */
- blk_queue_chunk_sectors(sdkp->disk->queue,
- logical_to_sectors(sdkp->device, sdkp->zone_blocks));
- sdkp->nr_zones =
- round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift;
+ blk_queue_chunk_sectors(q,
+ logical_to_sectors(sdkp->device, zone_blocks));
+ nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift;
/*
* Initialize the device request queue information if the number
* of zones changed.
*/
- if (sdkp->nr_zones != q->nr_zones) {
-
- sd_zbc_cleanup(sdkp);
-
- q->nr_zones = sdkp->nr_zones;
- if (sdkp->nr_zones) {
- q->seq_zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp);
- if (!q->seq_zones_wlock) {
+ if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) {
+ unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
+ size_t zone_bitmap_size;
+
+ if (nr_zones) {
+ seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones,
+ q->node);
+ if (!seq_zones_wlock) {
ret = -ENOMEM;
goto err;
}
- ret = sd_zbc_setup_seq_zones_bitmap(sdkp);
- if (ret) {
- sd_zbc_cleanup(sdkp);
+ seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp,
+ zone_shift, nr_zones);
+ if (IS_ERR(seq_zones_bitmap)) {
+ ret = PTR_ERR(seq_zones_bitmap);
+ kfree(seq_zones_wlock);
goto err;
}
}
-
+ zone_bitmap_size = BITS_TO_LONGS(nr_zones) *
+ sizeof(unsigned long);
+ blk_mq_freeze_queue(q);
+ if (q->nr_zones != nr_zones) {
+ /* READ16/WRITE16 is mandatory for ZBC disks */
+ sdkp->device->use_16_for_rw = 1;
+ sdkp->device->use_10_for_rw = 0;
+
+ sdkp->zone_blocks = zone_blocks;
+ sdkp->zone_shift = zone_shift;
+ sdkp->nr_zones = nr_zones;
+ q->nr_zones = nr_zones;
+ swap(q->seq_zones_wlock, seq_zones_wlock);
+ swap(q->seq_zones_bitmap, seq_zones_bitmap);
+ } else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap,
+ zone_bitmap_size) != 0) {
+ memcpy(q->seq_zones_bitmap, seq_zones_bitmap,
+ zone_bitmap_size);
+ }
+ blk_mq_unfreeze_queue(q);
+ kfree(seq_zones_wlock);
+ kfree(seq_zones_bitmap);
}
return 0;
int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
{
+ int64_t zone_blocks;
int ret;
if (!sd_is_zoned(sdkp))
* Check zone size: only devices with a constant zone size (except
* an eventual last runt zone) that is a power of 2 are supported.
*/
- ret = sd_zbc_check_zone_size(sdkp);
- if (ret)
+ zone_blocks = sd_zbc_check_zone_size(sdkp);
+ ret = -EFBIG;
+ if (zone_blocks != (u32)zone_blocks)
+ goto err;
+ ret = zone_blocks;
+ if (ret < 0)
goto err;
/* The drive satisfies the kernel restrictions: set it up */
- ret = sd_zbc_setup(sdkp);
+ ret = sd_zbc_setup(sdkp, zone_blocks);
if (ret)
goto err;
*val = ' ';
}
+static void ufshcd_add_cmd_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->sc.cdb);
+}
+
+static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_upiu_req *rq = hba->lrb[tag].ucd_req_ptr;
+
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &rq->header, &rq->qr);
+}
+
+static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag,
+ const char *str)
+{
+ struct utp_task_req_desc *descp;
+ struct utp_upiu_task_req *task_req;
+ int off = (int)tag - hba->nutrs;
+
+ descp = &hba->utmrdl_base_addr[off];
+ task_req = (struct utp_upiu_task_req *)descp->task_req_upiu;
+ trace_ufshcd_upiu(dev_name(hba->dev), str, &task_req->header,
+ &task_req->input_param1);
+}
+
static void ufshcd_add_command_trace(struct ufs_hba *hba,
unsigned int tag, const char *str)
{
struct ufshcd_lrb *lrbp;
int transfer_len = -1;
+ /* trace UPIU also */
+ ufshcd_add_cmd_upiu_trace(hba, tag, str);
+
if (!trace_ufshcd_command_enabled())
return;
hba->dev_cmd.complete = &wait;
+ ufshcd_add_query_upiu_trace(hba, tag, "query_send");
/* Make sure descriptors are ready before ringing the doorbell */
wmb();
spin_lock_irqsave(hba->host->host_lock, flags);
err = ufshcd_wait_for_dev_cmd(hba, lrbp, timeout);
+ ufshcd_add_query_upiu_trace(hba, tag,
+ err ? "query_complete_err" : "query_complete");
+
out_put_tag:
ufshcd_put_dev_cmd_tag(hba, tag);
wake_up(&hba->dev_cmd.tag_wq);
spin_unlock_irqrestore(host->host_lock, flags);
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_send");
+
/* wait until the task management command is completed */
err = wait_event_timeout(hba->tm_wq,
test_bit(free_slot, &hba->tm_condition),
msecs_to_jiffies(TM_CMD_TIMEOUT));
if (!err) {
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete_err");
dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
__func__, tm_function);
if (ufshcd_clear_tm_cmd(hba, free_slot))
err = -ETIMEDOUT;
} else {
err = ufshcd_task_req_compl(hba, free_slot, tm_response);
+ ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete");
}
clear_bit(free_slot, &hba->tm_condition);
bytes = min(bytes, data_len);
if (!bio) {
+new_bio:
nr_vecs = min_t(int, BIO_MAX_PAGES, nr_pages);
nr_pages -= nr_vecs;
/*
* be allocated with pscsi_get_bio() above.
*/
bio = NULL;
+ goto new_bio;
}
data_len -= bytes;
struct blk_mq_tags;
struct blk_flush_queue;
+/**
+ * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device
+ */
struct blk_mq_hw_ctx {
struct {
spinlock_t lock;
* initialized by the low level device driver (e.g. scsi/sd.c).
* Stacking drivers (device mappers) may or may not initialize
* these fields.
+ *
+ * Reads of this information must be protected with blk_queue_enter() /
+ * blk_queue_exit(). Modifying this information is only allowed while
+ * no requests are being processed. See also blk_mq_freeze_queue() and
+ * blk_mq_unfreeze_queue().
*/
unsigned int nr_zones;
unsigned long *seq_zones_bitmap;
#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
#define blk_queue_preempt_only(q) \
test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags)
+#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
extern int blk_set_preempt_only(struct request_queue *q);
extern void blk_clear_preempt_only(struct request_queue *q);
void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
struct bpf_prog *old_prog);
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
- __u32 __user *prog_ids, u32 request_cnt,
- __u32 __user *prog_cnt);
+ u32 *prog_ids, u32 request_cnt,
+ u32 *prog_cnt);
int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog *exclude_prog,
struct bpf_prog *include_prog,
* fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS
* instead of the latter), any change to them will be overwritten
* by kernel. Returns a negative error code or zero.
+ * @get_fecparam: Get the network device Forward Error Correction parameters.
+ * @set_fecparam: Set the network device Forward Error Correction parameters.
*
* All operations are optional (i.e. the function pointer may be set
* to %NULL) and callers must take this into account. Callers must
union { /* Object pointer [lock] */
struct inode *inode;
struct vfsmount *mnt;
- };
- union {
- struct hlist_head list;
/* Used listing heads to free after srcu period expires */
struct fsnotify_mark_connector *destroy_next;
};
+ struct hlist_head list;
};
/*
void *ife_encode(struct sk_buff *skb, u16 metalen);
void *ife_decode(struct sk_buff *skb, u16 *metalen);
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen);
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen);
int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen,
const void *dval);
struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern);
+void llc_sk_stop_all_timers(struct sock *sk, bool sync);
void llc_sk_free(struct sock *sk);
void llc_sk_reset(struct sock *sk);
extern void scsi_print_command(struct scsi_cmnd *);
extern size_t __scsi_format_command(char *, size_t,
const unsigned char *, size_t);
-extern void scsi_show_extd_sense(const struct scsi_device *, const char *,
- unsigned char, unsigned char);
extern void scsi_print_sense_hdr(const struct scsi_device *, const char *,
const struct scsi_sense_hdr *);
extern void scsi_print_sense(const struct scsi_cmnd *);
)
);
+TRACE_EVENT(ufshcd_upiu,
+ TP_PROTO(const char *dev_name, const char *str, void *hdr, void *tsf),
+
+ TP_ARGS(dev_name, str, hdr, tsf),
+
+ TP_STRUCT__entry(
+ __string(dev_name, dev_name)
+ __string(str, str)
+ __array(unsigned char, hdr, 12)
+ __array(unsigned char, tsf, 16)
+ ),
+
+ TP_fast_assign(
+ __assign_str(dev_name, dev_name);
+ __assign_str(str, str);
+ memcpy(__entry->hdr, hdr, sizeof(__entry->hdr));
+ memcpy(__entry->tsf, tsf, sizeof(__entry->tsf));
+ ),
+
+ TP_printk(
+ "%s: %s: HDR:%s, CDB:%s",
+ __get_str(str), __get_str(dev_name),
+ __print_hex(__entry->hdr, sizeof(__entry->hdr)),
+ __print_hex(__entry->tsf, sizeof(__entry->tsf))
+ )
+);
+
#endif /* if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ) */
/* This part must be outside protection */
return cnt;
}
+static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+ u32 *prog_ids,
+ u32 request_cnt)
+{
+ int i = 0;
+
+ for (; *prog; prog++) {
+ if (*prog == &dummy_bpf_prog.prog)
+ continue;
+ prog_ids[i] = (*prog)->aux->id;
+ if (++i == request_cnt) {
+ prog++;
+ break;
+ }
+ }
+
+ return !!(*prog);
+}
+
int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
__u32 __user *prog_ids, u32 cnt)
{
struct bpf_prog **prog;
unsigned long err = 0;
- u32 i = 0, *ids;
bool nospc;
+ u32 *ids;
/* users of this function are doing:
* cnt = bpf_prog_array_length();
return -ENOMEM;
rcu_read_lock();
prog = rcu_dereference(progs)->progs;
- for (; *prog; prog++) {
- if (*prog == &dummy_bpf_prog.prog)
- continue;
- ids[i] = (*prog)->aux->id;
- if (++i == cnt) {
- prog++;
- break;
- }
- }
- nospc = !!(*prog);
+ nospc = bpf_prog_array_copy_core(prog, ids, cnt);
rcu_read_unlock();
err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
kfree(ids);
}
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
- __u32 __user *prog_ids, u32 request_cnt,
- __u32 __user *prog_cnt)
+ u32 *prog_ids, u32 request_cnt,
+ u32 *prog_cnt)
{
+ struct bpf_prog **prog;
u32 cnt = 0;
if (array)
cnt = bpf_prog_array_length(array);
- if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
- return -EFAULT;
+ *prog_cnt = cnt;
/* return early if user requested only program count or nothing to copy */
if (!request_cnt || !cnt)
return 0;
- return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+ /* this function is called under trace/bpf_trace.c: bpf_event_mutex */
+ prog = rcu_dereference_check(array, 1)->progs;
+ return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+ : 0;
}
static void bpf_prog_free_deferred(struct work_struct *work)
attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
- if (attr->value_size > KMALLOC_MAX_SIZE)
- return ERR_PTR(-E2BIG);
-
err = bpf_tcp_ulp_register();
if (err && err != -EEXIST)
return ERR_PTR(err);
{
struct perf_event_query_bpf __user *uquery = info;
struct perf_event_query_bpf query = {};
+ u32 *ids, prog_cnt, ids_len;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EINVAL;
if (copy_from_user(&query, uquery, sizeof(query)))
return -EFAULT;
- if (query.ids_len > BPF_TRACE_MAX_PROGS)
+
+ ids_len = query.ids_len;
+ if (ids_len > BPF_TRACE_MAX_PROGS)
return -E2BIG;
+ ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN);
+ if (!ids)
+ return -ENOMEM;
+ /*
+ * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which
+ * is required when user only wants to check for uquery->prog_cnt.
+ * There is no need to check for it since the case is handled
+ * gracefully in bpf_prog_array_copy_info.
+ */
mutex_lock(&bpf_event_mutex);
ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
- uquery->ids,
- query.ids_len,
- &uquery->prog_cnt);
+ ids,
+ ids_len,
+ &prog_cnt);
mutex_unlock(&bpf_event_mutex);
+ if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
+ copy_to_user(uquery->ids, ids, ids_len * sizeof(u32)))
+ ret = -EFAULT;
+
+ kfree(ids);
return ret;
}
__free_pages(page, page_order);
page = NULL;
- if (dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+ if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
!(gfp & GFP_DMA)) {
gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
goto again;
{
unsigned int size = info->entries_size;
const void *entries = info->entries;
- int ret;
newinfo->entries_size = size;
-
- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries);
- if (ret)
- return ret;
+ if (info->nentries) {
+ int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
+ info->nentries);
+ if (ret)
+ return ret;
+ }
return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
entries, newinfo);
int total_pull;
u16 ifehdrln;
+ if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN))
+ return NULL;
+
ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len);
ifehdrln = ntohs(ifehdr->metalen);
total_pull = skb->dev->hard_header_len + ifehdrln;
__be16 len;
};
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+ const unsigned char *ifehdr_end)
+{
+ const struct meta_tlvhdr *tlv;
+ u16 tlvlen;
+
+ if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+ return false;
+
+ tlv = (const struct meta_tlvhdr *)skbdata;
+ tlvlen = ntohs(tlv->len);
+
+ /* tlv length field is inc header, check on minimum */
+ if (tlvlen < NLA_HDRLEN)
+ return false;
+
+ /* overflow by NLA_ALIGN check */
+ if (NLA_ALIGN(tlvlen) < tlvlen)
+ return false;
+
+ if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+ return false;
+
+ return true;
+}
+
/* Caller takes care of presenting data in network order
*/
-void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen)
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+ u16 *dlen, u16 *totlen)
{
- struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+ struct meta_tlvhdr *tlv;
+
+ if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+ return NULL;
+ tlv = (struct meta_tlvhdr *)skbdata;
*dlen = ntohs(tlv->len) - NLA_HDRLEN;
*attrtype = ntohs(tlv->type);
int length = (th->doff << 2) - sizeof(*th);
const u8 *ptr = (const u8 *)(th + 1);
- /* If the TCP option is too short, we can short cut */
- if (length < TCPOLEN_MD5SIG)
- return NULL;
-
- while (length > 0) {
+ /* If not enough data remaining, we can short cut */
+ while (length >= TCPOLEN_MD5SIG) {
int opcode = *ptr++;
int opsize;
fields such as the source, destination, flowlabel, hop-limit and
the packet mark.
+if NF_NAT_IPV6
+
+config NFT_CHAIN_NAT_IPV6
+ tristate "IPv6 nf_tables nat chain support"
+ help
+ This option enables the "nat" chain for IPv6 in nf_tables. This
+ chain type is used to perform Network Address Translation (NAT)
+ packet transformations such as the source, destination address and
+ source and destination ports.
+
+config NFT_MASQ_IPV6
+ tristate "IPv6 masquerade support for nf_tables"
+ depends on NFT_MASQ
+ select NF_NAT_MASQUERADE_IPV6
+ help
+ This is the expression that provides IPv4 masquerading support for
+ nf_tables.
+
+config NFT_REDIR_IPV6
+ tristate "IPv6 redirect support for nf_tables"
+ depends on NFT_REDIR
+ select NF_NAT_REDIRECT
+ help
+ This is the expression that provides IPv4 redirect support for
+ nf_tables.
+
+endif # NF_NAT_IPV6
+
config NFT_REJECT_IPV6
select NF_REJECT_IPV6
default NFT_REJECT
if NF_NAT_IPV6
-config NFT_CHAIN_NAT_IPV6
- depends on NF_TABLES_IPV6
- tristate "IPv6 nf_tables nat chain support"
- help
- This option enables the "nat" chain for IPv6 in nf_tables. This
- chain type is used to perform Network Address Translation (NAT)
- packet transformations such as the source, destination address and
- source and destination ports.
-
config NF_NAT_MASQUERADE_IPV6
tristate "IPv6 masquerade support"
help
This is the kernel functionality to provide NAT in the masquerade
flavour (automatic source address selection) for IPv6.
-config NFT_MASQ_IPV6
- tristate "IPv6 masquerade support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_MASQ
- select NF_NAT_MASQUERADE_IPV6
- help
- This is the expression that provides IPv4 masquerading support for
- nf_tables.
-
-config NFT_REDIR_IPV6
- tristate "IPv6 redirect support for nf_tables"
- depends on NF_TABLES_IPV6
- depends on NFT_REDIR
- select NF_NAT_REDIRECT
- help
- This is the expression that provides IPv4 redirect support for
- nf_tables.
-
endif # NF_NAT_IPV6
config IP6_NF_IPTABLES
static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_GATEWAY] = { .len = sizeof(struct in6_addr) },
+ [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_EXPIRES] = { .type = NLA_U32 },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
+ [RTA_TABLE] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
isrh->nexthdr = proto;
hdr->daddr = isrh->segments[isrh->first_segment];
- set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
+ set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
#ifdef CONFIG_IPV6_SEG6_HMAC
if (sr_has_hmac(isrh)) {
return;
/* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */
- if (pd->tunnel)
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
lock_sock(sk);
error = -EINVAL;
+
+ if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
+ sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
+ goto end;
+
if (sp->sa_protocol != PX_PROTO_OL2TP)
goto end;
return;
/* Drop reference taken by last invocation of pppol2tp_next_tunnel() */
- if (pd->tunnel)
+ if (pd->tunnel) {
l2tp_tunnel_dec_refcount(pd->tunnel);
+ pd->tunnel = NULL;
+ pd->session = NULL;
+ }
}
static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
{
struct sock *sk = sock->sk;
struct llc_sock *llc;
- struct llc_sap *sap;
if (unlikely(sk == NULL))
goto out;
llc->laddr.lsap, llc->daddr.lsap);
if (!llc_send_disc(sk))
llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo);
- sap = llc->sap;
- /* Hold this for release_sock(), so that llc_backlog_rcv() could still
- * use it.
- */
- llc_sap_hold(sap);
- if (!sock_flag(sk, SOCK_ZAPPED))
+ if (!sock_flag(sk, SOCK_ZAPPED)) {
+ struct llc_sap *sap = llc->sap;
+
+ /* Hold this for release_sock(), so that llc_backlog_rcv()
+ * could still use it.
+ */
+ llc_sap_hold(sap);
llc_sap_remove_socket(llc->sap, sk);
- release_sock(sk);
- llc_sap_put(sap);
+ release_sock(sk);
+ llc_sap_put(sap);
+ } else {
+ release_sock(sk);
+ }
if (llc->dev)
dev_put(llc->dev);
sock_put(sk);
int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb)
{
- struct llc_sock *llc = llc_sk(sk);
-
- del_timer(&llc->pf_cycle_timer.timer);
- del_timer(&llc->ack_timer.timer);
- del_timer(&llc->rej_sent_timer.timer);
- del_timer(&llc->busy_state_timer.timer);
- llc->ack_must_be_send = 0;
- llc->ack_pf = 0;
+ llc_sk_stop_all_timers(sk, false);
return 0;
}
return sk;
}
+void llc_sk_stop_all_timers(struct sock *sk, bool sync)
+{
+ struct llc_sock *llc = llc_sk(sk);
+
+ if (sync) {
+ del_timer_sync(&llc->pf_cycle_timer.timer);
+ del_timer_sync(&llc->ack_timer.timer);
+ del_timer_sync(&llc->rej_sent_timer.timer);
+ del_timer_sync(&llc->busy_state_timer.timer);
+ } else {
+ del_timer(&llc->pf_cycle_timer.timer);
+ del_timer(&llc->ack_timer.timer);
+ del_timer(&llc->rej_sent_timer.timer);
+ del_timer(&llc->busy_state_timer.timer);
+ }
+
+ llc->ack_must_be_send = 0;
+ llc->ack_pf = 0;
+}
+
/**
* llc_sk_free - Frees a LLC socket
* @sk - socket to free
llc->state = LLC_CONN_OUT_OF_SVC;
/* Stop all (possibly) running timers */
- llc_conn_ac_stop_all_timers(sk, NULL);
+ llc_sk_stop_all_timers(sk, true);
#ifdef DEBUG_LLC_CONN_ALLOC
printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__,
skb_queue_len(&llc->pdu_unack_q),
config NFT_REJECT
default m if NETFILTER_ADVANCED=n
tristate "Netfilter nf_tables reject support"
+ depends on !NF_TABLES_INET || (IPV6!=m || m)
help
This option adds the "reject" expression that you can use to
explicitly deny and notify via TCP reset/ICMP informational errors
strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
sizeof(cfg.mcast_ifn));
cfg.syncid = dm->syncid;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &cfg, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
if (ipvs->mixed_address_family_dests > 0)
return -EINVAL;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
return ret;
}
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/kernel.h>
+#include <linux/sched/signal.h>
#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */
/*
* Specifiy default interface for outgoing multicasts
*/
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
{
- struct net_device *dev;
struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
-
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
* in the in_addr structure passed in as a parameter.
*/
static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
{
- struct net *net = sock_net(sk);
struct ip_mreqn mreq;
- struct net_device *dev;
int ret;
memset(&mreq, 0, sizeof(mreq));
memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
#ifdef CONFIG_IP_VS_IPV6
static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
- char *ifname)
+ struct net_device *dev)
{
- struct net *net = sock_net(sk);
- struct net_device *dev;
int ret;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
}
#endif
-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
{
- struct net *net = sock_net(sock->sk);
- struct net_device *dev;
__be32 addr;
struct sockaddr_in sin;
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
-
addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
if (!addr)
pr_err("You probably need to specify IP address on "
"multicast interface.\n");
IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
- ifname, &addr);
+ dev->name, &addr);
/* Now bind the socket with the address of multicast interface */
sin.sin_family = AF_INET;
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
- result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+ *sock_ret = sock;
+ result = set_mcast_if(sock->sk, dev);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
goto error;
set_sock_size(sock->sk, 1, result);
if (AF_INET == ipvs->mcfg.mcast_af)
- result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+ result = bind_mcastif_addr(sock, dev);
else
result = 0;
if (result < 0) {
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
- int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
+ *sock_ret = sock;
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = SK_CAN_REUSE;
result = sysctl_sync_sock_size(ipvs);
set_sock_size(sock->sk, 0, result);
get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
- sock->sk->sk_bound_dev_if = ifindex;
+ sock->sk->sk_bound_dev_if = dev->ifindex;
result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
#ifdef CONFIG_IP_VS_IPV6
if (ipvs->bcfg.mcast_af == AF_INET6)
result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
else
#endif
result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
if (result < 0) {
pr_err("Error joining to the multicast group\n");
goto error;
}
- return sock;
+ return 0;
error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo;
+ struct ip_vs_sync_thread_data *tinfo = NULL;
struct task_struct **array = NULL, *task;
- struct socket *sock;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
- int id, count, hlen;
+ int id = 0, count, hlen;
int result = -ENOMEM;
u16 mtu, min_mtu;
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));
+ /* Do not hold one mutex and then to block on another */
+ for (;;) {
+ rtnl_lock();
+ if (mutex_trylock(&ipvs->sync_mutex))
+ break;
+ rtnl_unlock();
+ mutex_lock(&ipvs->sync_mutex);
+ if (rtnl_trylock())
+ break;
+ mutex_unlock(&ipvs->sync_mutex);
+ }
+
if (!ipvs->sync_state) {
count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
ipvs->threads_mask = count - 1;
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
- return -ENODEV;
+ result = -ENODEV;
+ goto out_early;
}
hlen = (AF_INET6 == c->mcast_af) ?
sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
c->sync_maxlen = mtu - hlen;
if (state == IP_VS_STATE_MASTER) {
+ result = -EEXIST;
if (ipvs->ms)
- return -EEXIST;
+ goto out_early;
ipvs->mcfg = *c;
name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
+ result = -EEXIST;
if (ipvs->backup_threads)
- return -EEXIST;
+ goto out_early;
ipvs->bcfg = *c;
name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
} else {
- return -EINVAL;
+ result = -EINVAL;
+ goto out_early;
}
if (state == IP_VS_STATE_MASTER) {
struct ipvs_master_sync_state *ms;
+ result = -ENOMEM;
ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL);
if (!ipvs->ms)
goto out;
} else {
array = kcalloc(count, sizeof(struct task_struct *),
GFP_KERNEL);
+ result = -ENOMEM;
if (!array)
goto out;
}
- tinfo = NULL;
for (id = 0; id < count; id++) {
- if (state == IP_VS_STATE_MASTER)
- sock = make_send_sock(ipvs, id);
- else
- sock = make_receive_sock(ipvs, id, dev->ifindex);
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto outtinfo;
- }
+ result = -ENOMEM;
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
- goto outsocket;
+ goto out;
tinfo->ipvs = ipvs;
- tinfo->sock = sock;
+ tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
- goto outtinfo;
+ goto out;
} else {
tinfo->buf = NULL;
}
tinfo->id = id;
+ if (state == IP_VS_STATE_MASTER)
+ result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+ else
+ result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+ if (result < 0)
+ goto out;
task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
if (IS_ERR(task)) {
result = PTR_ERR(task);
- goto outtinfo;
+ goto out;
}
tinfo = NULL;
if (state == IP_VS_STATE_MASTER)
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
+
/* increase the module use count */
ip_vs_use_count_inc();
return 0;
-outsocket:
- sock_release(sock);
-
-outtinfo:
- if (tinfo) {
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
- }
+out:
+ /* We do not need RTNL lock anymore, release it here so that
+ * sock_release below and in the kthreads can use rtnl_lock
+ * to leave the mcast group.
+ */
+ rtnl_unlock();
count = id;
while (count-- > 0) {
if (state == IP_VS_STATE_MASTER)
else
kthread_stop(array[count]);
}
- kfree(array);
-
-out:
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
+ mutex_unlock(&ipvs->sync_mutex);
+ if (tinfo) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ kfree(array);
+ return result;
+
+out_early:
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
return result;
}
static inline int expect_matches(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b)
{
- return a->master == b->master && a->class == b->class &&
+ return a->master == b->master &&
nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
h = nf_ct_expect_dst_hash(net, &expect->tuple);
hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
+ if (i->class != expect->class)
+ return -EALREADY;
+
if (nf_ct_remove_expect(i))
break;
} else if (expect_clash(i, expect)) {
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
+#include <linux/kmemleak.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
rcu_read_unlock();
alloc = max(newlen, NF_CT_EXT_PREALLOC);
+ kmemleak_not_leak(old);
new = __krealloc(old, alloc, gfp);
if (!new)
return NULL;
datalen, rtp_exp, rtcp_exp,
mediaoff, medialen, daddr);
else {
- if (nf_ct_expect_related(rtp_exp) == 0) {
- if (nf_ct_expect_related(rtcp_exp) != 0)
- nf_ct_unexpect_related(rtp_exp);
- else
+ /* -EALREADY handling works around end-points that send
+ * SDP messages with identical port but different media type,
+ * we pretend expectation was set up.
+ */
+ int errp = nf_ct_expect_related(rtp_exp);
+
+ if (errp == 0 || errp == -EALREADY) {
+ int errcp = nf_ct_expect_related(rtcp_exp);
+
+ if (errcp == 0 || errcp == -EALREADY)
ret = NF_ACCEPT;
+ else if (errp == 0)
+ nf_ct_unexpect_related(rtp_exp);
}
}
nf_ct_expect_put(rtcp_exp);
}
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
- if (nft_is_active_next(net, old_rule)) {
- trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
- old_rule);
- if (trans == NULL) {
- err = -ENOMEM;
- goto err2;
- }
- nft_deactivate_next(net, old_rule);
- chain->use--;
- list_add_tail_rcu(&rule->list, &old_rule->list);
- } else {
+ if (!nft_is_active_next(net, old_rule)) {
err = -ENOENT;
goto err2;
}
- } else if (nlh->nlmsg_flags & NLM_F_APPEND)
- if (old_rule)
- list_add_rcu(&rule->list, &old_rule->list);
- else
- list_add_tail_rcu(&rule->list, &chain->rules);
- else {
- if (old_rule)
- list_add_tail_rcu(&rule->list, &old_rule->list);
- else
- list_add_rcu(&rule->list, &chain->rules);
- }
+ trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+ old_rule);
+ if (trans == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+ nft_deactivate_next(net, old_rule);
+ chain->use--;
- if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
- err = -ENOMEM;
- goto err3;
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ } else {
+ if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+ err = -ENOMEM;
+ goto err2;
+ }
+
+ if (nlh->nlmsg_flags & NLM_F_APPEND) {
+ if (old_rule)
+ list_add_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_tail_rcu(&rule->list, &chain->rules);
+ } else {
+ if (old_rule)
+ list_add_tail_rcu(&rule->list, &old_rule->list);
+ else
+ list_add_rcu(&rule->list, &chain->rules);
+ }
}
chain->use++;
return 0;
-err3:
- list_del_rcu(&rule->list);
err2:
nf_tables_rule_destroy(&ctx, rule);
err1:
err = ops->init(set, &desc, nla);
if (err < 0)
- goto err2;
+ goto err3;
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err3;
+ goto err4;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
-err3:
+err4:
ops->destroy(set);
+err3:
+ kfree(set->name);
err2:
kvfree(set);
err1:
struct nft_base_chain *basechain;
if (nft_trans_chain_name(trans))
- strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+ swap(trans->ctx.chain->name, nft_trans_chain_name(trans));
if (!nft_is_base_chain(trans->ctx.chain))
return;
MODULE_ALIAS("ip6t_connmark");
static unsigned int
-connmark_tg_shift(struct sk_buff *skb,
- const struct xt_connmark_tginfo1 *info,
- u8 shift_bits, u8 shift_dir)
+connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info)
{
enum ip_conntrack_info ctinfo;
+ u_int32_t new_targetmark;
struct nf_conn *ct;
u_int32_t newmark;
switch (info->mode) {
case XT_CONNMARK_SET:
newmark = (ct->mark & ~info->ctmask) ^ info->ctmark;
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ newmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ newmark <<= info->shift_bits;
+
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_SAVE:
- newmark = (ct->mark & ~info->ctmask) ^
- (skb->mark & info->nfmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (skb->mark & info->nfmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (ct->mark & ~info->ctmask) ^
+ new_targetmark;
if (ct->mark != newmark) {
ct->mark = newmark;
nf_conntrack_event_cache(IPCT_MARK, ct);
}
break;
case XT_CONNMARK_RESTORE:
- newmark = (skb->mark & ~info->nfmask) ^
- (ct->mark & info->ctmask);
- if (shift_dir == D_SHIFT_RIGHT)
- newmark >>= shift_bits;
+ new_targetmark = (ct->mark & info->ctmask);
+ if (info->shift_dir == D_SHIFT_RIGHT)
+ new_targetmark >>= info->shift_bits;
else
- newmark <<= shift_bits;
+ new_targetmark <<= info->shift_bits;
+
+ newmark = (skb->mark & ~info->nfmask) ^
+ new_targetmark;
skb->mark = newmark;
break;
}
connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_connmark_tginfo1 *info = par->targinfo;
-
- return connmark_tg_shift(skb, info, 0, 0);
+ const struct xt_connmark_tginfo2 info2 = {
+ .ctmark = info->ctmark,
+ .ctmask = info->ctmask,
+ .nfmask = info->nfmask,
+ .mode = info->mode,
+ };
+
+ return connmark_tg_shift(skb, &info2);
}
static unsigned int
{
const struct xt_connmark_tginfo2 *info = par->targinfo;
- return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info,
- info->shift_bits, info->shift_dir);
+ return connmark_tg_shift(skb, info);
}
static int connmark_tg_check(const struct xt_tgchk_param *par)
skb_set_queue_mapping(skb, queue_index);
}
-/* register_prot_hook must be invoked with the po->bind_lock held,
+/* __register_prot_hook must be invoked through register_prot_hook
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
*/
-static void register_prot_hook(struct sock *sk)
+static void __register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
}
}
-/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock
- * held. If the sync parameter is true, we will temporarily drop
+static void register_prot_hook(struct sock *sk)
+{
+ lockdep_assert_held_once(&pkt_sk(sk)->bind_lock);
+ __register_prot_hook(sk);
+}
+
+/* If the sync parameter is true, we will temporarily drop
* the po->bind_lock and do a synchronize_net to make sure no
* asynchronous packet processing paths still refer to the elements
* of po->prot_hook. If the sync parameter is false, it is the
{
struct packet_sock *po = pkt_sk(sk);
+ lockdep_assert_held_once(&po->bind_lock);
+
po->running = 0;
if (po->fanout)
if (proto) {
po->prot_hook.type = proto;
- register_prot_hook(sk);
+ __register_prot_hook(sk);
}
mutex_lock(&net->packet.sklist_lock);
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_loss = !!val;
- return 0;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_loss = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_AUXDATA:
{
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->auxdata = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_ORIGDEV:
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ lock_sock(sk);
po->origdev = !!val;
+ release_sock(sk);
return 0;
}
case PACKET_VNET_HDR:
if (sock->type != SOCK_RAW)
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (optlen < sizeof(val))
return -EINVAL;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->has_vnet_hdr = !!val;
- return 0;
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->has_vnet_hdr = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
+ return ret;
}
case PACKET_TIMESTAMP:
{
if (optlen != sizeof(val))
return -EINVAL;
- if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
- return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
- po->tp_tx_has_off = !!val;
+
+ lock_sock(sk);
+ if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) {
+ ret = -EBUSY;
+ } else {
+ po->tp_tx_has_off = !!val;
+ ret = 0;
+ }
+ release_sock(sk);
return 0;
}
case PACKET_QDISC_BYPASS:
int copy_thresh;
spinlock_t bind_lock;
struct mutex pg_vec_lock;
- unsigned int running:1, /* prot_hook is attached*/
- auxdata:1,
+ unsigned int running; /* bind_lock must be held */
+ unsigned int auxdata:1, /* writer must hold sock lock */
origdev:1,
- has_vnet_hdr:1;
+ has_vnet_hdr:1,
+ tp_loss:1,
+ tp_tx_has_off:1;
int pressure;
int ifindex; /* bound device */
__be16 num;
enum tpacket_versions tp_version;
unsigned int tp_hdrlen;
unsigned int tp_reserve;
- unsigned int tp_loss:1;
- unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
struct net_device __rcu *cached_dev;
int (*xmit)(struct sk_buff *skb);
}
}
- return 0;
+ return -ENOENT;
}
static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
u16 mtype;
u16 dlen;
- curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL);
+ curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype,
+ &dlen, NULL);
+ if (!curr_data) {
+ qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats));
+ return TC_ACT_SHOT;
+ }
if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
/* abuse overlimits to count when we receive metadata
static void strp_start_timer(struct strparser *strp, long timeo)
{
- if (timeo)
+ if (timeo && timeo != LONG_MAX)
mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo);
}
magic |= VFS_CAP_FLAGS_EFFECTIVE;
memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
cap->magic_etc = cpu_to_le32(magic);
+ } else {
+ size = -ENOMEM;
}
}
kfree(tmpbuf);
test_verifier_log
feature
test_libbpf_open
+test_sock
+test_sock_addr
+urandom_read
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#include <bpf/libbpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
#define CG_PATH "/foo"
#define CONNECT4_PROG_PATH "./connect4_prog.o"
ping_once()
{
- ping -q -c 1 -W 1 ${1%%/*} >/dev/null 2>&1
+ ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
}
wait_for_ip()
echo -n "Wait for testing IPv4/IPv6 to become available "
for _i in $(seq ${MAX_PING_TRIES}); do
echo -n "."
- if ping_once ${TEST_IPv4} && ping_once ${TEST_IPv6}; then
+ if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then
echo " OK"
return
fi