Home Home > GIT Browse > openSUSE-15.0
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKernel Build Daemon <kbuild@suse.de>2019-07-16 07:13:38 +0200
committerKernel Build Daemon <kbuild@suse.de>2019-07-16 07:13:38 +0200
commit2bd144a2916119ffb57e5e76ec395aea7cc7a3a1 (patch)
treebfad83c9a4f43eff8c7ffc5d0dd54d385fbd06bc
parenta601f9176d750241b2cfa4049ae04d3f208217dc (diff)
parent39c1db16882be53e5db2d4ccf562506ac9f59fc5 (diff)
Merge branch 'SLE15' into openSUSE-15.0
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S9
-rw-r--r--arch/s390/include/asm/kvm_host.h5
-rw-r--r--arch/s390/include/asm/lowcore.h8
-rw-r--r--arch/s390/kernel/smp.c3
-rw-r--r--arch/s390/kernel/vtime.c19
-rw-r--r--arch/s390/kvm/Kconfig1
-rw-r--r--arch/s390/kvm/kvm-s390.c17
-rw-r--r--drivers/cpufreq/acpi-cpufreq.c4
-rw-r--r--drivers/cpufreq/brcmstb-avs-cpufreq.c12
-rw-r--r--drivers/cpufreq/cpufreq.c18
-rw-r--r--drivers/cpufreq/intel_pstate.c23
-rw-r--r--drivers/cpufreq/kirkwood-cpufreq.c19
-rw-r--r--drivers/cpufreq/pasemi-cpufreq.c1
-rw-r--r--drivers/cpufreq/pmac32-cpufreq.c2
-rw-r--r--drivers/cpufreq/ppc_cbe_cpufreq.c1
-rw-r--r--drivers/hid/wacom_sys.c13
-rw-r--r--drivers/hid/wacom_wac.c23
-rw-r--r--drivers/hid/wacom_wac.h1
-rw-r--r--drivers/hwtracing/intel_th/msu.c2
-rw-r--r--drivers/md/bcache/alloc.c14
-rw-r--r--drivers/md/bcache/bcache.h6
-rw-r--r--drivers/md/bcache/bset.c77
-rw-r--r--drivers/md/bcache/bset.h34
-rw-r--r--drivers/md/bcache/btree.c55
-rw-r--r--drivers/md/bcache/btree.h2
-rw-r--r--drivers/md/bcache/io.c12
-rw-r--r--drivers/md/bcache/journal.c179
-rw-r--r--drivers/md/bcache/journal.h4
-rw-r--r--drivers/md/bcache/request.c41
-rw-r--r--drivers/md/bcache/request.h2
-rw-r--r--drivers/md/bcache/super.c317
-rw-r--r--drivers/md/bcache/sysfs.c76
-rw-r--r--drivers/md/bcache/util.h28
-rw-r--r--drivers/md/bcache/writeback.c8
-rw-r--r--drivers/media/platform/marvell-ccic/mcam-core.c5
-rw-r--r--drivers/media/platform/s5p-mfc/s5p_mfc_pm.c5
-rw-r--r--drivers/media/platform/vivid/vivid-osd.c2
-rw-r--r--drivers/media/v4l2-core/v4l2-ctrls.c9
-rw-r--r--drivers/memory/tegra/mc.c2
-rw-r--r--drivers/memstick/core/memstick.c13
-rw-r--r--drivers/mmc/host/sdhci-pci-core.c7
-rw-r--r--drivers/net/wireless/ath/ath6kl/wmi.c10
-rw-r--r--drivers/net/wireless/ath/wil6210/txrx.c1
-rw-r--r--drivers/net/wireless/marvell/mwifiex/fw.h16
-rw-r--r--drivers/net/wireless/marvell/mwifiex/scan.c18
-rw-r--r--drivers/net/wireless/marvell/mwifiex/sta_ioctl.c4
-rw-r--r--drivers/net/wireless/marvell/mwifiex/wmm.c2
-rw-r--r--drivers/platform/x86/pmc_atom.c8
-rw-r--r--drivers/staging/comedi/drivers/amplc_pci230.c3
-rw-r--r--drivers/staging/comedi/drivers/dt282x.c3
-rw-r--r--drivers/staging/rtl8712/rtl871x_ioctl_linux.c157
-rw-r--r--fs/btrfs/ctree.c57
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/delayed-inode.c3
-rw-r--r--fs/ocfs2/dlmglue.c82
-rw-r--r--fs/ocfs2/ocfs2.h4
-rw-r--r--include/linux/cgroup.h10
-rw-r--r--include/linux/cpufreq.h12
-rw-r--r--include/linux/kvm_host.h10
-rw-r--r--lib/bitmap.c2
-rw-r--r--lib/scatterlist.c9
-rw-r--r--net/batman-adv/translation-table.c2
-rw-r--r--net/core/ethtool.c12
-rw-r--r--net/core/pktgen.c11
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/netfilter/nf_conntrack_core.c13
-rw-r--r--net/packet/af_packet.c16
-rw-r--r--net/rds/ib_frmr.c1
-rw-r--r--net/unix/af_unix.c10
-rw-r--r--sound/pci/hda/patch_realtek.c2
-rw-r--r--sound/soc/codecs/cs4265.c2
-rw-r--r--sound/soc/codecs/max98090.c16
-rw-r--r--sound/soc/soc-pcm.c3
-rw-r--r--virt/kvm/Kconfig3
-rw-r--r--virt/kvm/kvm_main.c2
75 files changed, 1094 insertions, 495 deletions
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ea21e90ab0dc..220f3e37c4a5 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1688,7 +1688,7 @@ handle_page_fault:
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_page_fault
cmpdi r3,0
- beq+ 12f
+ beq+ ret_from_except_lite
bl save_nvgprs
mr r5,r3
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -1703,7 +1703,12 @@ handle_dabr_fault:
ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_break
-12: b ret_from_except_lite
+ /*
+ * do_break() may have changed the NV GPRS while handling a breakpoint.
+ * If so, we need to restore them with their updated values. Don't use
+ * ret_from_except_lite here.
+ */
+ b ret_from_except
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e287417a9014..d15c7b9a65ba 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -39,7 +39,7 @@
*/
#define KVM_NR_IRQCHIPS 1
#define KVM_IRQCHIP_NUM_PINS 4096
-#define KVM_HALT_POLL_NS_DEFAULT 80000
+#define KVM_HALT_POLL_NS_DEFAULT 50000
/* s390-specific vcpu->requests bit members */
#define KVM_REQ_ENABLE_IBS KVM_ARCH_REQ(0)
@@ -303,6 +303,9 @@ struct kvm_vcpu_stat {
u64 halt_successful_poll;
u64 halt_attempted_poll;
u64 halt_poll_invalid;
+#ifndef __GENKSYMS__
+ u64 halt_no_poll_steal;
+#endif
u64 halt_wakeup;
u64 instruction_lctl;
u64 instruction_lctlg;
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 4b028396e539..069c13c4e9ef 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -98,7 +98,11 @@ struct lowcore {
/* Current process. */
__u64 current_task; /* 0x0328 */
- __u8 pad_0x318[0x320-0x318]; /* 0x0330 */
+#ifndef __GENKSYMS__
+ __u64 avg_steal_timer; /* 0x0330 */
+#else
+ __u8 pad_0x318[0x320-0x318]; /* 0x0330 */
+#endif
__u64 kernel_stack; /* 0x0338 */
/* Interrupt, panic and restart stack. */
@@ -139,7 +143,7 @@ struct lowcore {
/* Per cpu primary space access list */
__u32 paste[16]; /* 0x0400 */
- __u8 pad_0x04c0[0x0500-0x0440]; /* 0x0440 */
+ __u8 pad_0x04c0[0x0500-0x0440]; /* 0x0440 */
/* br %r1 trampoline */
__u16 br_r1_trampoline; /* 0x0500 */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 07383496f1d3..0400a8dfc63d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -274,7 +274,8 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = S390_lowcore.kernel_asce;
lc->machine_flags = S390_lowcore.machine_flags;
- lc->user_timer = lc->system_timer = lc->steal_timer = 0;
+ lc->user_timer = lc->system_timer =
+ lc->steal_timer = lc->avg_steal_timer = 0;
__ctl_store(lc->cregs_save_area, 0, 15);
save_access_regs((unsigned int *) lc->access_regs_save_area);
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 072d84ba42a3..a6f23238c3b0 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -124,7 +124,7 @@ static void account_system_index_scaled(struct task_struct *p,
*/
static int do_account_vtime(struct task_struct *tsk)
{
- u64 timer, clock, user, guest, system, hardirq, softirq, steal;
+ u64 timer, clock, user, guest, system, hardirq, softirq;
timer = S390_lowcore.last_update_timer;
clock = S390_lowcore.last_update_clock;
@@ -185,12 +185,6 @@ static int do_account_vtime(struct task_struct *tsk)
account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
CPUTIME_SOFTIRQ);
- steal = S390_lowcore.steal_timer;
- if ((s64) steal > 0) {
- S390_lowcore.steal_timer = 0;
- account_steal_time(cputime_to_nsecs(steal));
- }
-
return virt_timer_forward(user + guest + system + hardirq + softirq);
}
@@ -216,8 +210,19 @@ void vtime_task_switch(struct task_struct *prev)
*/
void vtime_flush(struct task_struct *tsk)
{
+ u64 steal, avg_steal;
+
if (do_account_vtime(tsk))
virt_timer_expire();
+
+ steal = S390_lowcore.steal_timer;
+ avg_steal = S390_lowcore.avg_steal_timer / 2;
+ if ((s64) steal > 0) {
+ S390_lowcore.steal_timer = 0;
+ account_steal_time(steal);
+ avg_steal += steal;
+ }
+ S390_lowcore.avg_steal_timer = avg_steal;
}
/*
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index b1900239b0ab..b538ca407b9a 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_INVALID_WAKEUPS
+ select HAVE_KVM_NO_POLL
select SRCU
select KVM_VFIO
---help---
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index a8f125aa751f..a1313ab2060e 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -73,6 +73,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
+ { "halt_no_poll_steal", VCPU_STAT(halt_no_poll_steal) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
@@ -160,6 +161,11 @@ MODULE_PARM_DESC(nested, "Nested virtualization support");
*/
#define SIZE_INTERNAL 16
+/* maximum percentage of steal time for polling. >100 is treated like 100 */
+static u8 halt_poll_max_steal = 10;
+module_param(halt_poll_max_steal, byte, 0644);
+MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling");
+
/*
* Base feature mask that defines default mask for facilities. Consists of the
* defines in FACILITIES_KVM and the non-hypervisor managed bits.
@@ -2661,6 +2667,17 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
}
}
+bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
+{
+ /* do not poll with more than halt_poll_max_steal percent of steal time */
+ if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >=
+ halt_poll_max_steal) {
+ vcpu->stat.halt_no_poll_steal++;
+ return true;
+ }
+ return false;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
/* kvm common code refers to this, but never calls it */
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 4796aa11ccc5..c98c22ab4529 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -914,8 +914,10 @@ static void __init acpi_cpufreq_boost_init(void)
{
int ret;
- if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
+ if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) {
+ pr_debug("Boost capabilities not present in the processor\n");
return;
+ }
acpi_cpufreq_driver.set_boost = set_boost;
acpi_cpufreq_driver.boost_enabled = boost_state(0);
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 7281a2c19c36..39c462711eae 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -468,12 +468,12 @@ static int brcm_avs_set_pstate(struct private_data *priv, unsigned int pstate)
return __issue_avs_command(priv, AVS_CMD_SET_PSTATE, true, args);
}
-static unsigned long brcm_avs_get_voltage(void __iomem *base)
+static u32 brcm_avs_get_voltage(void __iomem *base)
{
return readl(base + AVS_MBOX_VOLTAGE1);
}
-static unsigned long brcm_avs_get_frequency(void __iomem *base)
+static u32 brcm_avs_get_frequency(void __iomem *base)
{
return readl(base + AVS_MBOX_FREQUENCY) * 1000; /* in kHz */
}
@@ -762,8 +762,8 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv)
rc = brcm_avs_get_pmap(priv, NULL);
magic = readl(priv->base + AVS_MBOX_MAGIC);
- return (magic == AVS_FIRMWARE_MAGIC) && (rc != -ENOTSUPP) &&
- (rc != -EINVAL);
+ return (magic == AVS_FIRMWARE_MAGIC) && ((rc != -ENOTSUPP) ||
+ (rc != -EINVAL));
}
static unsigned int brcm_avs_cpufreq_get(unsigned int cpu)
@@ -973,14 +973,14 @@ static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf)
{
struct private_data *priv = policy->driver_data;
- return sprintf(buf, "0x%08lx\n", brcm_avs_get_voltage(priv->base));
+ return sprintf(buf, "0x%08x\n", brcm_avs_get_voltage(priv->base));
}
static ssize_t show_brcm_avs_frequency(struct cpufreq_policy *policy, char *buf)
{
struct private_data *priv = policy->driver_data;
- return sprintf(buf, "0x%08lx\n", brcm_avs_get_frequency(priv->base));
+ return sprintf(buf, "0x%08x\n", brcm_avs_get_frequency(priv->base));
}
cpufreq_freq_attr_ro(brcm_avs_pstate);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 2ad6a750520d..e4a26f826d9c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -554,13 +554,13 @@ EXPORT_SYMBOL_GPL(cpufreq_policy_transition_delay_us);
* SYSFS INTERFACE *
*********************************************************************/
static ssize_t show_boost(struct kobject *kobj,
- struct attribute *attr, char *buf)
+ struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", cpufreq_driver->boost_enabled);
}
-static ssize_t store_boost(struct kobject *kobj, struct attribute *attr,
- const char *buf, size_t count)
+static ssize_t store_boost(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t count)
{
int ret, enable;
@@ -1523,17 +1523,16 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
{
unsigned int ret_freq = 0;
- if (!cpufreq_driver->get)
+ if (unlikely(policy_is_inactive(policy)) || !cpufreq_driver->get)
return ret_freq;
ret_freq = cpufreq_driver->get(policy->cpu);
/*
- * Updating inactive policies is invalid, so avoid doing that. Also
- * if fast frequency switching is used with the given policy, the check
+ * If fast frequency switching is used with the given policy, the check
* against policy->cur is pointless, so skip it in that case too.
*/
- if (unlikely(policy_is_inactive(policy)) || policy->fast_switch_enabled)
+ if (policy->fast_switch_enabled)
return ret_freq;
if (ret_freq && policy->cur &&
@@ -1562,10 +1561,7 @@ unsigned int cpufreq_get(unsigned int cpu)
if (policy) {
down_read(&policy->rwsem);
-
- if (!policy_is_inactive(policy))
- ret_freq = __cpufreq_get(policy);
-
+ ret_freq = __cpufreq_get(policy);
up_read(&policy->rwsem);
cpufreq_cpu_put(policy);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 6f8f913f096e..27ce2ae25a62 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1022,7 +1022,7 @@ static void intel_pstate_debug_hide_params(void)
/************************** sysfs begin ************************/
#define show_one(file_name, object) \
static ssize_t show_##file_name \
- (struct kobject *kobj, struct attribute *attr, char *buf) \
+ (struct kobject *kobj, struct kobj_attribute *attr, char *buf) \
{ \
return sprintf(buf, "%u\n", global.object); \
}
@@ -1031,7 +1031,7 @@ static ssize_t intel_pstate_show_status(char *buf);
static int intel_pstate_update_status(const char *buf, size_t size);
static ssize_t show_status(struct kobject *kobj,
- struct attribute *attr, char *buf)
+ struct kobj_attribute *attr, char *buf)
{
ssize_t ret;
@@ -1042,7 +1042,7 @@ static ssize_t show_status(struct kobject *kobj,
return ret;
}
-static ssize_t store_status(struct kobject *a, struct attribute *b,
+static ssize_t store_status(struct kobject *a, struct kobj_attribute *b,
const char *buf, size_t count)
{
char *p = memchr(buf, '\n', count);
@@ -1056,7 +1056,7 @@ static ssize_t store_status(struct kobject *a, struct attribute *b,
}
static ssize_t show_turbo_pct(struct kobject *kobj,
- struct attribute *attr, char *buf)
+ struct kobj_attribute *attr, char *buf)
{
struct cpudata *cpu;
int total, no_turbo, turbo_pct;
@@ -1082,7 +1082,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
}
static ssize_t show_num_pstates(struct kobject *kobj,
- struct attribute *attr, char *buf)
+ struct kobj_attribute *attr, char *buf)
{
struct cpudata *cpu;
int total;
@@ -1103,7 +1103,7 @@ static ssize_t show_num_pstates(struct kobject *kobj,
}
static ssize_t show_no_turbo(struct kobject *kobj,
- struct attribute *attr, char *buf)
+ struct kobj_attribute *attr, char *buf)
{
ssize_t ret;
@@ -1125,7 +1125,7 @@ static ssize_t show_no_turbo(struct kobject *kobj,
return ret;
}
-static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
+static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
const char *buf, size_t count)
{
unsigned int input;
@@ -1172,7 +1172,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
return count;
}
-static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
+static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
const char *buf, size_t count)
{
unsigned int input;
@@ -1202,7 +1202,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
return count;
}
-static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
+static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
const char *buf, size_t count)
{
unsigned int input;
@@ -1234,12 +1234,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
}
static ssize_t show_hwp_dynamic_boost(struct kobject *kobj,
- struct attribute *attr, char *buf)
+ struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%u\n", hwp_boost);
}
-static ssize_t store_hwp_dynamic_boost(struct kobject *a, struct attribute *b,
+static ssize_t store_hwp_dynamic_boost(struct kobject *a,
+ struct kobj_attribute *b,
const char *buf, size_t count)
{
unsigned int input;
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index c2dd43f3f5d8..8d63a6dc8383 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -124,13 +124,14 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
priv.cpu_clk = of_clk_get_by_name(np, "cpu_clk");
if (IS_ERR(priv.cpu_clk)) {
dev_err(priv.dev, "Unable to get cpuclk\n");
- return PTR_ERR(priv.cpu_clk);
+ err = PTR_ERR(priv.cpu_clk);
+ goto out_node;
}
err = clk_prepare_enable(priv.cpu_clk);
if (err) {
dev_err(priv.dev, "Unable to prepare cpuclk\n");
- return err;
+ goto out_node;
}
kirkwood_freq_table[0].frequency = clk_get_rate(priv.cpu_clk) / 1000;
@@ -161,20 +162,22 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
goto out_ddr;
}
- of_node_put(np);
- np = NULL;
-
err = cpufreq_register_driver(&kirkwood_cpufreq_driver);
- if (!err)
- return 0;
+ if (err) {
+ dev_err(priv.dev, "Failed to register cpufreq driver\n");
+ goto out_powersave;
+ }
- dev_err(priv.dev, "Failed to register cpufreq driver\n");
+ of_node_put(np);
+ return 0;
+out_powersave:
clk_disable_unprepare(priv.powersave_clk);
out_ddr:
clk_disable_unprepare(priv.ddr_clk);
out_cpu:
clk_disable_unprepare(priv.cpu_clk);
+out_node:
of_node_put(np);
return err;
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index 35dd4d7ffee0..58c933f48300 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -146,6 +146,7 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
cpu = of_get_cpu_node(policy->cpu, NULL);
+ of_node_put(cpu);
if (!cpu)
goto out;
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index ff44016ea031..641f8021855a 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -551,6 +551,7 @@ static int pmac_cpufreq_init_7447A(struct device_node *cpunode)
volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select");
if (volt_gpio_np)
voltage_gpio = read_gpio(volt_gpio_np);
+ of_node_put(volt_gpio_np);
if (!voltage_gpio){
pr_err("missing cpu-vcore-select gpio\n");
return 1;
@@ -587,6 +588,7 @@ static int pmac_cpufreq_init_750FX(struct device_node *cpunode)
if (volt_gpio_np)
voltage_gpio = read_gpio(volt_gpio_np);
+ of_node_put(volt_gpio_np);
pvr = mfspr(SPRN_PVR);
has_cpu_l2lve = !((pvr & 0xf00) == 0x100);
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index 5a4c5a639f61..2eaeebcc93af 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -86,6 +86,7 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
if (!cbe_get_cpu_pmd_regs(policy->cpu) ||
!cbe_get_cpu_mic_tm_regs(policy->cpu)) {
pr_info("invalid CBE regs pointers for cpufreq\n");
+ of_node_put(cpu);
return -EINVAL;
}
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 71fecc3e7685..0f45a9519516 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -307,18 +307,23 @@ static void wacom_feature_mapping(struct hid_device *hdev,
wacom_hid_usage_quirk(hdev, field, usage);
switch (equivalent_usage) {
+ case WACOM_HID_WD_TOUCH_RING_SETTING:
+ wacom->generic_has_leds = true;
+ break;
case HID_DG_CONTACTMAX:
/* leave touch_max as is if predefined */
if (!features->touch_max) {
/* read manually */
- data = kzalloc(2, GFP_KERNEL);
+ n = hid_report_len(field->report);
+ data = hid_alloc_report_buf(field->report, GFP_KERNEL);
if (!data)
break;
data[0] = field->report->id;
ret = wacom_get_report(hdev, HID_FEATURE_REPORT,
- data, 2, WAC_CMD_RETRIES);
- if (ret == 2) {
- features->touch_max = data[1];
+ data, n, WAC_CMD_RETRIES);
+ if (ret == n) {
+ ret = hid_report_raw_event(hdev,
+ HID_FEATURE_REPORT, data, n, 0);
} else {
features->touch_max = 16;
hid_warn(hdev, "wacom_feature_mapping: "
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 09b8e4aac82f..bde3416cce7e 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -1930,8 +1930,6 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
features->device_type |= WACOM_DEVICETYPE_PAD;
break;
case WACOM_HID_WD_BUTTONCENTER:
- wacom->generic_has_leds = true;
- /* fall through */
case WACOM_HID_WD_BUTTONHOME:
case WACOM_HID_WD_BUTTONUP:
case WACOM_HID_WD_BUTTONDOWN:
@@ -2123,14 +2121,12 @@ static void wacom_wac_pad_report(struct hid_device *hdev,
bool active = wacom_wac->hid_data.inrange_state != 0;
/* report prox for expresskey events */
- if ((wacom_equivalent_usage(field->physical) == HID_DG_TABLETFUNCTIONKEY) &&
- wacom_wac->hid_data.pad_input_event_flag) {
+ if (wacom_wac->hid_data.pad_input_event_flag) {
input_event(input, EV_ABS, ABS_MISC, active ? PAD_DEVICE_ID : 0);
input_sync(input);
if (!active)
wacom_wac->hid_data.pad_input_event_flag = false;
}
-
}
static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
@@ -2516,6 +2512,7 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
struct wacom *wacom = hid_get_drvdata(hdev);
struct wacom_wac *wacom_wac = &wacom->wacom_wac;
unsigned equivalent_usage = wacom_equivalent_usage(usage->hid);
+ struct wacom_features *features = &wacom->wacom_wac.features;
switch (equivalent_usage) {
case HID_GD_X:
@@ -2536,6 +2533,9 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
case HID_DG_TIPSWITCH:
wacom_wac->hid_data.tipswitch = value;
break;
+ case HID_DG_CONTACTMAX:
+ features->touch_max = value;
+ return;
}
@@ -2706,9 +2706,7 @@ static int wacom_wac_collection(struct hid_device *hdev, struct hid_report *repo
if (report->type != HID_INPUT_REPORT)
return -1;
- if (WACOM_PAD_FIELD(field) && wacom->wacom_wac.pad_input)
- wacom_wac_pad_report(hdev, report, field);
- else if (WACOM_PEN_FIELD(field) && wacom->wacom_wac.pen_input)
+ if (WACOM_PEN_FIELD(field) && wacom->wacom_wac.pen_input)
wacom_wac_pen_report(hdev, report);
else if (WACOM_FINGER_FIELD(field) && wacom->wacom_wac.touch_input)
wacom_wac_finger_report(hdev, report);
@@ -2722,7 +2720,7 @@ void wacom_wac_report(struct hid_device *hdev, struct hid_report *report)
struct wacom_wac *wacom_wac = &wacom->wacom_wac;
struct hid_field *field;
bool pad_in_hid_field = false, pen_in_hid_field = false,
- finger_in_hid_field = false;
+ finger_in_hid_field = false, true_pad = false;
int r;
int prev_collection = -1;
@@ -2738,6 +2736,8 @@ void wacom_wac_report(struct hid_device *hdev, struct hid_report *report)
pen_in_hid_field = true;
if (WACOM_FINGER_FIELD(field))
finger_in_hid_field = true;
+ if (wacom_equivalent_usage(field->physical) == HID_DG_TABLETFUNCTIONKEY)
+ true_pad = true;
}
wacom_wac_battery_pre_report(hdev, report);
@@ -2761,6 +2761,9 @@ void wacom_wac_report(struct hid_device *hdev, struct hid_report *report)
}
wacom_wac_battery_report(hdev, report);
+
+ if (true_pad && wacom->wacom_wac.pad_input)
+ wacom_wac_pad_report(hdev, report, field);
}
static int wacom_bpt_touch(struct wacom_wac *wacom)
@@ -3717,7 +3720,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
0, 5920, 4, 0);
}
input_abs_set_res(input_dev, ABS_MT_POSITION_X, 40);
- input_abs_set_res(input_dev, ABS_MT_POSITION_X, 40);
+ input_abs_set_res(input_dev, ABS_MT_POSITION_Y, 40);
/* fall through */
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 295fd3718caa..f67d871841c0 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -145,6 +145,7 @@
#define WACOM_HID_WD_OFFSETBOTTOM (WACOM_HID_UP_WACOMDIGITIZER | 0x0d33)
#define WACOM_HID_WD_DATAMODE (WACOM_HID_UP_WACOMDIGITIZER | 0x1002)
#define WACOM_HID_WD_DIGITIZERINFO (WACOM_HID_UP_WACOMDIGITIZER | 0x1013)
+#define WACOM_HID_WD_TOUCH_RING_SETTING (WACOM_HID_UP_WACOMDIGITIZER | 0x1032)
#define WACOM_HID_UP_G9 0xff090000
#define WACOM_HID_G9_PEN (WACOM_HID_UP_G9 | 0x02)
#define WACOM_HID_G9_TOUCHSCREEN (WACOM_HID_UP_G9 | 0x11)
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 36016c09dd96..6ebf6a2edb33 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -640,7 +640,7 @@ static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size)
goto err_out;
ret = -ENOMEM;
- page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+ page = alloc_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32, order);
if (!page)
goto err_free_sgt;
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 56a06375978e..b7bdb0600852 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -326,10 +326,11 @@ static int bch_allocator_thread(void *arg)
* possibly issue discards to them, then we add the bucket to
* the free list:
*/
- while (!fifo_empty(&ca->free_inc)) {
+ while (1) {
long bucket;
- fifo_pop(&ca->free_inc, bucket);
+ if (!fifo_pop(&ca->free_inc, bucket))
+ break;
if (ca->discard) {
mutex_unlock(&ca->set->bucket_lock);
@@ -391,6 +392,11 @@ long bch_bucket_alloc(struct cache *ca, unsigned int reserve, bool wait)
struct bucket *b;
long r;
+
+ /* No allocation if CACHE_SET_IO_DISABLE bit is set */
+ if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &ca->set->flags)))
+ return -1;
+
/* fastpath */
if (fifo_pop(&ca->free[RESERVE_NONE], r) ||
fifo_pop(&ca->free[reserve], r))
@@ -482,6 +488,10 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
{
int i;
+ /* No allocation if CACHE_SET_IO_DISABLE bit is set */
+ if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
+ return -1;
+
lockdep_assert_held(&c->bucket_lock);
BUG_ON(!n || n > c->caches_loaded || n > MAX_CACHES_PER_SET);
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 2f6c60d140b3..bab49ef2a922 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -704,8 +704,8 @@ struct cache_set {
atomic_long_t writeback_keys_failed;
atomic_long_t reclaim;
+ atomic_long_t reclaimed_journal_buckets;
atomic_long_t flush_write;
- atomic_long_t retry_flush_write;
enum {
ON_ERROR_UNREGISTER,
@@ -725,8 +725,6 @@ struct cache_set {
#define BUCKET_HASH_BITS 12
struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS];
-
- DECLARE_HEAP(struct btree *, flush_btree);
};
struct bbio {
@@ -1005,7 +1003,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size);
int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
uint8_t *set_uuid);
void bch_cached_dev_detach(struct cached_dev *dc);
-void bch_cached_dev_run(struct cached_dev *dc);
+int bch_cached_dev_run(struct cached_dev *dc);
void bcache_device_stop(struct bcache_device *d);
void bch_cache_set_unregister(struct cache_set *c);
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 1b895b4fed60..cd92e6205225 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -346,22 +346,19 @@ EXPORT_SYMBOL(bch_btree_keys_alloc);
void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
bool *expensive_debug_checks)
{
- unsigned int i;
-
b->ops = ops;
b->expensive_debug_checks = expensive_debug_checks;
b->nsets = 0;
b->last_set_unwritten = 0;
- /* XXX: shouldn't be needed */
- for (i = 0; i < MAX_BSETS; i++)
- b->set[i].size = 0;
/*
- * Second loop starts at 1 because b->keys[0]->data is the memory we
- * allocated
+ * struct btree_keys in embedded in struct btree, and struct
+ * bset_tree is embedded into struct btree_keys. They are all
+ * initialized as 0 by kzalloc() in mca_bucket_alloc(), and
+ * b->set[0].data is allocated in bch_btree_keys_alloc(), so we
+ * don't have to initiate b->set[].size and b->set[].data here
+ * any more.
*/
- for (i = 1; i < MAX_BSETS; i++)
- b->set[i].data = NULL;
}
EXPORT_SYMBOL(bch_btree_keys_init);
@@ -886,12 +883,22 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
struct bset *i = bset_tree_last(b)->data;
struct bkey *m, *prev = NULL;
struct btree_iter iter;
+ struct bkey preceding_key_on_stack = ZERO_KEY;
+ struct bkey *preceding_key_p = &preceding_key_on_stack;
BUG_ON(b->ops->is_extents && !KEY_SIZE(k));
- m = bch_btree_iter_init(b, &iter, b->ops->is_extents
- ? PRECEDING_KEY(&START_KEY(k))
- : PRECEDING_KEY(k));
+ /*
+ * If k has preceding key, preceding_key_p will be set to address
+ * of k's preceding key; otherwise preceding_key_p will be set
+ * to NULL inside preceding_key().
+ */
+ if (b->ops->is_extents)
+ preceding_key(&START_KEY(k), &preceding_key_p);
+ else
+ preceding_key(k, &preceding_key_p);
+
+ m = bch_btree_iter_init(b, &iter, preceding_key_p);
if (b->ops->insert_fixup(b, k, &iter, replace_key))
return status;
@@ -959,45 +966,25 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
unsigned int inorder, j, n = 1;
do {
- /*
- * A bit trick here.
- * If p < t->size, (int)(p - t->size) is a minus value and
- * the most significant bit is set, right shifting 31 bits
- * gets 1. If p >= t->size, the most significant bit is
- * not set, right shifting 31 bits gets 0.
- * So the following 2 lines equals to
- * if (p >= t->size)
- * p = 0;
- * but a branch instruction is avoided.
- */
unsigned int p = n << 4;
- p &= ((int) (p - t->size)) >> 31;
-
- prefetch(&t->tree[p]);
+ if (p < t->size)
+ prefetch(&t->tree[p]);
j = n;
f = &t->tree[j];
- /*
- * Similar bit trick, use subtract operation to avoid a branch
- * instruction.
- *
- * n = (f->mantissa > bfloat_mantissa())
- * ? j * 2
- * : j * 2 + 1;
- *
- * We need to subtract 1 from f->mantissa for the sign bit trick
- * to work - that's done in make_bfloat()
- */
- if (likely(f->exponent != 127))
- n = j * 2 + (((unsigned int)
- (f->mantissa -
- bfloat_mantissa(search, f))) >> 31);
- else
- n = (bkey_cmp(tree_to_bkey(t, j), search) > 0)
- ? j * 2
- : j * 2 + 1;
+ if (likely(f->exponent != 127)) {
+ if (f->mantissa >= bfloat_mantissa(search, f))
+ n = j * 2;
+ else
+ n = j * 2 + 1;
+ } else {
+ if (bkey_cmp(tree_to_bkey(t, j), search) > 0)
+ n = j * 2;
+ else
+ n = j * 2 + 1;
+ }
} while (n < t->size);
inorder = to_inorder(j, t);
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index fe584622d8dc..fe331b02ba16 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -433,20 +433,26 @@ static inline bool bch_cut_back(const struct bkey *where, struct bkey *k)
return __bch_cut_back(where, k);
}
-#define PRECEDING_KEY(_k) \
-({ \
- struct bkey *_ret = NULL; \
- \
- if (KEY_INODE(_k) || KEY_OFFSET(_k)) { \
- _ret = &KEY(KEY_INODE(_k), KEY_OFFSET(_k), 0); \
- \
- if (!_ret->low) \
- _ret->high--; \
- _ret->low--; \
- } \
- \
- _ret; \
-})
+/*
+ * Pointer '*preceding_key_p' points to a memory object to store preceding
+ * key of k. If the preceding key does not exist, set '*preceding_key_p' to
+ * NULL. So the caller of preceding_key() needs to take care of memory
+ * which '*preceding_key_p' pointed to before calling preceding_key().
+ * Currently the only caller of preceding_key() is bch_btree_insert_key(),
+ * and it points to an on-stack variable, so the memory release is handled
+ * by stackframe itself.
+ */
+static inline void preceding_key(struct bkey *k, struct bkey **preceding_key_p)
+{
+ if (KEY_INODE(k) || KEY_OFFSET(k)) {
+ (**preceding_key_p) = KEY(KEY_INODE(k), KEY_OFFSET(k), 0);
+ if (!(*preceding_key_p)->low)
+ (*preceding_key_p)->high--;
+ (*preceding_key_p)->low--;
+ } else {
+ (*preceding_key_p) = NULL;
+ }
+}
static inline bool bch_ptr_invalid(struct btree_keys *b, const struct bkey *k)
{
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 4c1b976fc2da..d83479dfdb92 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -34,7 +34,7 @@
#include <linux/rcupdate.h>
#include <linux/sched/clock.h>
#include <linux/rculist.h>
-
+#include <linux/delay.h>
#include <trace/events/bcache.h>
/*
@@ -611,6 +611,10 @@ static void mca_data_alloc(struct btree *b, struct bkey *k, gfp_t gfp)
static struct btree *mca_bucket_alloc(struct cache_set *c,
struct bkey *k, gfp_t gfp)
{
+ /*
+ * kzalloc() is necessary here for initialization,
+ * see code comments in bch_btree_keys_init().
+ */
struct btree *b = kzalloc(sizeof(struct btree), gfp);
if (!b)
@@ -653,7 +657,25 @@ static int mca_reap(struct btree *b, unsigned int min_order, bool flush)
up(&b->io_mutex);
}
+retry:
+ /*
+ * BTREE_NODE_dirty might be cleared in btree_flush_btree() by
+ * __bch_btree_node_write(). To avoid an extra flush, acquire
+ * b->write_lock before checking BTREE_NODE_dirty bit.
+ */
mutex_lock(&b->write_lock);
+ /*
+ * If this btree node is selected in btree_flush_write() by journal
+ * code, delay and retry until the node is flushed by journal code
+ * and BTREE_NODE_journal_flush bit cleared by btree_flush_write().
+ */
+ if (btree_node_journal_flush(b)) {
+ pr_debug("bnode %p is flushing by journal, retry", b);
+ mutex_unlock(&b->write_lock);
+ udelay(1);
+ goto retry;
+ }
+
if (btree_node_dirty(b))
__bch_btree_node_write(b, &cl);
mutex_unlock(&b->write_lock);
@@ -776,10 +798,15 @@ void bch_btree_cache_free(struct cache_set *c)
while (!list_empty(&c->btree_cache)) {
b = list_first_entry(&c->btree_cache, struct btree, list);
- if (btree_node_dirty(b))
+ /*
+ * This function is called by cache_set_free(), no I/O
+ * request on cache now, it is unnecessary to acquire
+ * b->write_lock before clearing BTREE_NODE_dirty anymore.
+ */
+ if (btree_node_dirty(b)) {
btree_complete_write(b, btree_current_write(b));
- clear_bit(BTREE_NODE_dirty, &b->flags);
-
+ clear_bit(BTREE_NODE_dirty, &b->flags);
+ }
mca_data_free(b);
}
@@ -1065,11 +1092,25 @@ static void btree_node_free(struct btree *b)
BUG_ON(b == b->c->root);
+retry:
mutex_lock(&b->write_lock);
+ /*
+ * If the btree node is selected and flushing in btree_flush_write(),
+ * delay and retry until the BTREE_NODE_journal_flush bit cleared,
+ * then it is safe to free the btree node here. Otherwise this btree
+ * node will be in race condition.
+ */
+ if (btree_node_journal_flush(b)) {
+ mutex_unlock(&b->write_lock);
+ pr_debug("bnode %p journal_flush set, retry", b);
+ udelay(1);
+ goto retry;
+ }
- if (btree_node_dirty(b))
+ if (btree_node_dirty(b)) {
btree_complete_write(b, btree_current_write(b));
- clear_bit(BTREE_NODE_dirty, &b->flags);
+ clear_bit(BTREE_NODE_dirty, &b->flags);
+ }
mutex_unlock(&b->write_lock);
@@ -1474,11 +1515,11 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
out_nocoalesce:
closure_sync(&cl);
- bch_keylist_free(&keylist);
while ((k = bch_keylist_pop(&keylist)))
if (!bkey_cmp(k, &ZERO_KEY))
atomic_dec(&b->c->prio_blocked);
+ bch_keylist_free(&keylist);
for (i = 0; i < nodes; i++)
if (!IS_ERR_OR_NULL(new_nodes[i])) {
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index e9432b4d33a8..15c1c6cd826e 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -157,11 +157,13 @@ enum btree_flags {
BTREE_NODE_io_error,
BTREE_NODE_dirty,
BTREE_NODE_write_idx,
+ BTREE_NODE_journal_flush,
};
BTREE_FLAG(io_error);
BTREE_FLAG(dirty);
BTREE_FLAG(write_idx);
+BTREE_FLAG(journal_flush);
static inline struct btree_write *btree_current_write(struct btree *b)
{
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 47b7e54180ed..71b5a3cda04d 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -57,6 +57,18 @@ void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
WARN_ONCE(!dc, "NULL pointer of struct cached_dev");
+ /*
+ * Read-ahead requests on a degrading and recovering md raid
+ * (e.g. raid6) device might be failured immediately by md
+ * raid code, which is not a real hardware media failure. So
+ * we shouldn't count failed REQ_RAHEAD bio to dc->io_errors.
+ */
+ if (bio->bi_opf & REQ_RAHEAD) {
+ pr_warn_ratelimited("%s: Read-ahead I/O failed on backing device, ignore",
+ dc->backing_dev_name);
+ return;
+ }
+
errors = atomic_add_return(1, &dc->io_errors);
if (errors < dc->error_limit)
pr_err("%s: IO error on backing device, unrecoverable",
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 5cf9df00eefc..986cc59b3843 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -99,6 +99,20 @@ reread: left = ca->sb.bucket_size - offset;
blocks = set_blocks(j, block_bytes(ca->set));
+ /*
+ * Nodes in 'list' are in linear increasing order of
+ * i->j.seq, the node on head has the smallest (oldest)
+ * journal seq, the node on tail has the biggest
+ * (latest) journal seq.
+ */
+
+ /*
+ * Check from the oldest jset for last_seq. If
+ * i->j.seq < j->last_seq, it means the oldest jset
+ * in list is expired and useless, remove it from
+ * this list. Otherwise, j is a condidate jset for
+ * further following checks.
+ */
while (!list_empty(list)) {
i = list_first_entry(list,
struct journal_replay, list);
@@ -108,13 +122,22 @@ reread: left = ca->sb.bucket_size - offset;
kfree(i);
}
+ /* iterate list in reverse order (from latest jset) */
list_for_each_entry_reverse(i, list, list) {
if (j->seq == i->j.seq)
goto next_set;
+ /*
+ * if j->seq is less than any i->j.last_seq
+ * in list, j is an expired and useless jset.
+ */
if (j->seq < i->j.last_seq)
goto next_set;
+ /*
+ * 'where' points to first jset in list which
+ * is elder then j.
+ */
if (j->seq > i->j.seq) {
where = &i->list;
goto add;
@@ -128,10 +151,12 @@ add:
if (!i)
return -ENOMEM;
memcpy(&i->j, j, bytes);
+ /* Add to the location after 'where' points to */
list_add(&i->list, where);
ret = 1;
- ja->seq[bucket_index] = j->seq;
+ if (j->seq > ja->seq[bucket_index])
+ ja->seq[bucket_index] = j->seq;
next_set:
offset += blocks * ca->sb.block_size;
len -= blocks * ca->sb.block_size;
@@ -146,7 +171,7 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
{
#define read_bucket(b) \
({ \
- int ret = journal_read_bucket(ca, list, b); \
+ ret = journal_read_bucket(ca, list, b); \
__set_bit(b, bitmap); \
if (ret < 0) \
return ret; \
@@ -155,6 +180,7 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
struct cache *ca;
unsigned int iter;
+ int ret = 0;
for_each_cache(ca, c, iter) {
struct journal_device *ja = &ca->journal;
@@ -316,6 +342,18 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list)
}
}
+static bool is_discard_enabled(struct cache_set *s)
+{
+ struct cache *ca;
+ unsigned int i;
+
+ for_each_cache(ca, s, i)
+ if (ca->discard)
+ return true;
+
+ return false;
+}
+
int bch_journal_replay(struct cache_set *s, struct list_head *list)
{
int ret = 0, keys = 0, entries = 0;
@@ -329,9 +367,17 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list)
list_for_each_entry(i, list, list) {
BUG_ON(i->pin && atomic_read(i->pin) != 1);
- cache_set_err_on(n != i->j.seq, s,
-"bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)",
- n, i->j.seq - 1, start, end);
+ if (n != i->j.seq) {
+ if (n == start && is_discard_enabled(s))
+ pr_info("bcache: journal entries %llu-%llu may be discarded! (replaying %llu-%llu)",
+ n, i->j.seq - 1, start, end);
+ else {
+ pr_err("bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)",
+ n, i->j.seq - 1, start, end);
+ ret = -EIO;
+ goto err;
+ }
+ }
for (k = i->j.start;
k < bset_bkey_last(&i->j);
@@ -369,60 +415,90 @@ err:
}
/* Journalling */
-#define journal_max_cmp(l, r) \
- (fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
- fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
-#define journal_min_cmp(l, r) \
- (fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
- fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
static void btree_flush_write(struct cache_set *c)
{
- /*
- * Try to find the btree node with that references the oldest journal
- * entry, best is our current candidate and is locked if non NULL:
- */
- struct btree *b;
- int i;
+ struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR];
+ unsigned int i, n;
+
+ if (c->journal.btree_flushing)
+ return;
+
+ spin_lock(&c->journal.flush_write_lock);
+ if (c->journal.btree_flushing) {
+ spin_unlock(&c->journal.flush_write_lock);
+ return;
+ }
+ c->journal.btree_flushing = true;
+ spin_unlock(&c->journal.flush_write_lock);
atomic_long_inc(&c->flush_write);
+ memset(btree_nodes, 0, sizeof(btree_nodes));
+ n = 0;
-retry:
- spin_lock(&c->journal.lock);
- if (heap_empty(&c->flush_btree)) {
- for_each_cached_btree(b, c, i)
- if (btree_current_write(b)->journal) {
- if (!heap_full(&c->flush_btree))
- heap_add(&c->flush_btree, b,
- journal_max_cmp);
- else if (journal_max_cmp(b,
- heap_peek(&c->flush_btree))) {
- c->flush_btree.data[0] = b;
- heap_sift(&c->flush_btree, 0,
- journal_max_cmp);
- }
- }
+ mutex_lock(&c->bucket_lock);
+ list_for_each_entry_safe_reverse(b, t, &c->btree_cache, list) {
+ if (btree_node_journal_flush(b))
+ pr_err("BUG: flush_write bit should not be set here!");
+
+ mutex_lock(&b->write_lock);
+
+ if (!btree_node_dirty(b)) {
+ mutex_unlock(&b->write_lock);
+ continue;
+ }
- for (i = c->flush_btree.used / 2 - 1; i >= 0; --i)
- heap_sift(&c->flush_btree, i, journal_min_cmp);
+ if (!btree_current_write(b)->journal) {
+ mutex_unlock(&b->write_lock);
+ continue;
+ }
+
+ set_btree_node_journal_flush(b);
+
+ mutex_unlock(&b->write_lock);
+
+ btree_nodes[n++] = b;
+ if (n == BTREE_FLUSH_NR)
+ break;
}
+ mutex_unlock(&c->bucket_lock);
- b = NULL;
- heap_pop(&c->flush_btree, b, journal_min_cmp);
- spin_unlock(&c->journal.lock);
+ for (i = 0; i < n; i++) {
+ b = btree_nodes[i];
+ if (!b) {
+ pr_err("BUG: btree_nodes[%d] is NULL", i);
+ continue;
+ }
+
+ /* safe to check without holding b->write_lock */
+ if (!btree_node_journal_flush(b)) {
+ pr_err("BUG: bnode %p: journal_flush bit cleaned", b);
+ continue;
+ }
- if (b) {
mutex_lock(&b->write_lock);
if (!btree_current_write(b)->journal) {
+ clear_bit(BTREE_NODE_journal_flush, &b->flags);
mutex_unlock(&b->write_lock);
- /* We raced */
- atomic_long_inc(&c->retry_flush_write);
- goto retry;
+ pr_debug("bnode %p: written by others", b);
+ continue;
+ }
+
+ if (!btree_node_dirty(b)) {
+ clear_bit(BTREE_NODE_journal_flush, &b->flags);
+ mutex_unlock(&b->write_lock);
+ pr_debug("bnode %p: dirty bit cleaned by others", b);
+ continue;
}
__bch_btree_node_write(b, NULL);
+ clear_bit(BTREE_NODE_journal_flush, &b->flags);
mutex_unlock(&b->write_lock);
}
+
+ spin_lock(&c->journal.flush_write_lock);
+ c->journal.btree_flushing = false;
+ spin_unlock(&c->journal.flush_write_lock);
}
#define last_seq(j) ((j)->seq - fifo_used(&(j)->pin) + 1)
@@ -537,13 +613,14 @@ static void journal_reclaim(struct cache_set *c)
k->ptr[n++] = MAKE_PTR(0,
bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
ca->sb.nr_this_dev);
+ atomic_long_inc(&c->reclaimed_journal_buckets);
}
- bkey_init(k);
- SET_KEY_PTRS(k, n);
-
- if (n)
+ if (n) {
+ bkey_init(k);
+ SET_KEY_PTRS(k, n);
c->journal.blocks_free = c->sb.bucket_size >> c->block_bits;
+ }
out:
if (!journal_full(&c->journal))
__closure_wake_up(&c->journal.wait);
@@ -670,6 +747,9 @@ static void journal_write_unlocked(struct closure *cl)
ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
}
+ /* If KEY_PTRS(k) == 0, this jset gets lost in air */
+ BUG_ON(i == 0);
+
atomic_dec_bug(&fifo_back(&c->journal.pin));
bch_journal_next(&c->journal);
journal_reclaim(c);
@@ -786,6 +866,10 @@ atomic_t *bch_journal(struct cache_set *c,
struct journal_write *w;
atomic_t *ret;
+ /* No journaling if CACHE_SET_IO_DISABLE set already */
+ if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
+ return NULL;
+
if (!CACHE_SYNC(&c->sb))
return NULL;
@@ -830,7 +914,6 @@ void bch_journal_free(struct cache_set *c)
free_pages((unsigned long) c->journal.w[1].data, JSET_BITS);
free_pages((unsigned long) c->journal.w[0].data, JSET_BITS);
free_fifo(&c->journal.pin);
- free_heap(&c->flush_btree);
}
int bch_journal_alloc(struct cache_set *c)
@@ -838,6 +921,7 @@ int bch_journal_alloc(struct cache_set *c)
struct journal *j = &c->journal;
spin_lock_init(&j->lock);
+ spin_lock_init(&j->flush_write_lock);
INIT_DELAYED_WORK(&j->work, journal_write_work);
c->journal_delay_ms = 100;
@@ -845,8 +929,7 @@ int bch_journal_alloc(struct cache_set *c)
j->w[0].c = c;
j->w[1].c = c;
- if (!(init_heap(&c->flush_btree, 128, GFP_KERNEL)) ||
- !(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
+ if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
!(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
!(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
return -ENOMEM;
diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h
index 85f0d0fe904d..703ecabc7208 100644
--- a/drivers/md/bcache/journal.h
+++ b/drivers/md/bcache/journal.h
@@ -102,6 +102,8 @@ struct journal_write {
/* Embedded in struct cache_set */
struct journal {
spinlock_t lock;
+ spinlock_t flush_write_lock;
+ bool btree_flushing;
/* used when waiting because the journal was full */
struct closure_waitlist wait;
struct closure io;
@@ -153,6 +155,8 @@ struct journal_device {
struct bio_vec bv[8];
};
+#define BTREE_FLUSH_NR 8
+
#define journal_pin_cmp(c, l, r) \
(fifo_idx(&(c)->journal.pin, (l)) > fifo_idx(&(c)->journal.pin, (r)))
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 528205b1b7c9..f5224b662e8b 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -328,12 +328,13 @@ void bch_data_insert(struct closure *cl)
bch_data_insert_start(cl);
}
-/* Congested? */
-
-unsigned int bch_get_congested(struct cache_set *c)
+/*
+ * Congested? Return 0 (not congested) or the limit (in sectors)
+ * beyond which we should bypass the cache due to congestion.
+ */
+unsigned int bch_get_congested(const struct cache_set *c)
{
int i;
- long rand;
if (!c->congested_read_threshold_us &&
!c->congested_write_threshold_us)
@@ -352,8 +353,7 @@ unsigned int bch_get_congested(struct cache_set *c)
if (i > 0)
i = fract_exp_two(i, 6);
- rand = get_random_int();
- i -= bitmap_weight(&rand, BITS_PER_LONG);
+ i -= hweight32(get_random_u32());
return i > 0 ? i : 1;
}
@@ -375,7 +375,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
{
struct cache_set *c = dc->disk.c;
unsigned int mode = cache_mode(dc);
- unsigned int sectors, congested = bch_get_congested(c);
+ unsigned int sectors, congested;
struct task_struct *task = current;
struct io *i;
@@ -411,6 +411,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
goto rescale;
}
+ congested = bch_get_congested(c);
if (!congested && !dc->sequential_cutoff)
goto rescale;
@@ -706,14 +707,14 @@ static void search_free(struct closure *cl)
{
struct search *s = container_of(cl, struct search, cl);
- atomic_dec(&s->d->c->search_inflight);
+ atomic_dec(&s->iop.c->search_inflight);
if (s->iop.bio)
bio_put(s->iop.bio);
bio_complete(s);
closure_debug_destroy(cl);
- mempool_free(s, s->d->c->search);
+ mempool_free(s, s->iop.c->search);
}
static inline struct search *search_alloc(struct bio *bio,
@@ -756,13 +757,13 @@ static void cached_dev_bio_complete(struct closure *cl)
struct search *s = container_of(cl, struct search, cl);
struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
- search_free(cl);
cached_dev_put(dc);
+ search_free(cl);
}
/* Process reads */
-static void cached_dev_cache_miss_done(struct closure *cl)
+static void cached_dev_read_error_done(struct closure *cl)
{
struct search *s = container_of(cl, struct search, cl);
@@ -800,7 +801,22 @@ static void cached_dev_read_error(struct closure *cl)
closure_bio_submit(s->iop.c, bio, cl);
}
- continue_at(cl, cached_dev_cache_miss_done, NULL);
+ continue_at(cl, cached_dev_read_error_done, NULL);
+}
+
+static void cached_dev_cache_miss_done(struct closure *cl)
+{
+ struct search *s = container_of(cl, struct search, cl);
+ struct bcache_device *d = s->d;
+
+ if (s->iop.replace_collision)
+ bch_mark_cache_miss_collision(s->iop.c, s->d);
+
+ if (s->iop.bio)
+ bio_free_pages(s->iop.bio);
+
+ cached_dev_bio_complete(cl);
+ closure_put(&d->cl);
}
static void cached_dev_read_done(struct closure *cl)
@@ -833,6 +849,7 @@ static void cached_dev_read_done(struct closure *cl)
if (verify(dc) && s->recoverable && !s->read_dirty_data)
bch_data_verify(dc, s->orig_bio);
+ closure_get(&dc->disk.cl);
bio_complete(s);
if (s->iop.bio &&
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 4177c0437286..a4c8351c649c 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -32,7 +32,7 @@ struct data_insert_op {
BKEY_PADDED(replace_key);
};
-unsigned int bch_get_congested(struct cache_set *c);
+unsigned int bch_get_congested(const struct cache_set *c);
void bch_data_insert(struct closure *cl);
void bch_cached_dev_request_init(struct cached_dev *dc);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index a363ad5d8348..2b6cac99abce 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -41,6 +41,7 @@ static const char invalid_uuid[] = {
static struct kobject *bcache_kobj;
struct mutex bch_register_lock;
+bool bcache_is_reboot;
LIST_HEAD(bch_cache_sets);
static LIST_HEAD(uncached_devices);
@@ -50,6 +51,7 @@ static wait_queue_head_t unregister_wait;
struct workqueue_struct *bcache_wq;
struct workqueue_struct *bch_journal_wq;
+
#define BTREE_MAX_PAGES (256 * 1024 / PAGE_SIZE)
/* limitation of partitions number on single bcache device */
#define BCACHE_MINORS 128
@@ -198,7 +200,9 @@ err:
static void write_bdev_super_endio(struct bio *bio)
{
struct cached_dev *dc = bio->bi_private;
- /* XXX: error checking */
+
+ if (bio->bi_status)
+ bch_count_backing_io_errors(dc, bio);
closure_put(&dc->sb_write);
}
@@ -663,6 +667,11 @@ static const struct block_device_operations bcache_ops = {
void bcache_device_stop(struct bcache_device *d)
{
if (!test_and_set_bit(BCACHE_DEV_CLOSING, &d->flags))
+ /*
+ * closure_fn set to
+ * - cached device: cached_dev_flush()
+ * - flash dev: flash_dev_flush()
+ */
closure_queue(&d->cl);
}
@@ -687,6 +696,7 @@ static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
{
unsigned int i;
struct cache *ca;
+ int ret;
for_each_cache(ca, d->c, i)
bd_link_disk_holder(ca->bdev, d->disk);
@@ -694,9 +704,13 @@ static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
snprintf(d->name, BCACHEDEVNAME_SIZE,
"%s%u", name, d->id);
- WARN(sysfs_create_link(&d->kobj, &c->kobj, "cache") ||
- sysfs_create_link(&c->kobj, &d->kobj, d->name),
- "Couldn't create device <-> cache set symlinks");
+ ret = sysfs_create_link(&d->kobj, &c->kobj, "cache");
+ if (ret < 0)
+ pr_err("Couldn't create device -> cache set symlink");
+
+ ret = sysfs_create_link(&c->kobj, &d->kobj, d->name);
+ if (ret < 0)
+ pr_err("Couldn't create cache set -> device symlink");
clear_bit(BCACHE_DEV_UNLINK_DONE, &d->flags);
}
@@ -807,13 +821,14 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
if (idx < 0)
return idx;
- if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
- BIOSET_NEED_BVECS |
- BIOSET_NEED_RESCUER)) ||
- !(d->disk = alloc_disk(BCACHE_MINORS))) {
- ida_simple_remove(&bcache_device_idx, idx);
- return -ENOMEM;
- }
+ d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
+ BIOSET_NEED_BVECS | BIOSET_NEED_RESCUER);
+ if (!d->bio_split)
+ goto err;
+
+ d->disk = alloc_disk(BCACHE_MINORS);
+ if (!d->disk)
+ goto err;
set_capacity(d->disk, sectors);
snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@@ -847,6 +862,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
blk_queue_write_cache(q, true, true);
return 0;
+
+err:
+ ida_simple_remove(&bcache_device_idx, idx);
+ return -ENOMEM;
+
}
/* Cached device */
@@ -900,7 +920,7 @@ static int cached_dev_status_update(void *arg)
}
-void bch_cached_dev_run(struct cached_dev *dc)
+int bch_cached_dev_run(struct cached_dev *dc)
{
struct bcache_device *d = &dc->disk;
char buf[SB_LABEL_SIZE + 1];
@@ -911,6 +931,12 @@ void bch_cached_dev_run(struct cached_dev *dc)
NULL,
};
+ if (dc->io_disable) {
+ pr_err("I/O disabled on cached dev %s",
+ dc->backing_dev_name);
+ return -EIO;
+ }
+
memcpy(buf, dc->sb.label, SB_LABEL_SIZE);
buf[SB_LABEL_SIZE] = '\0';
env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf);
@@ -918,7 +944,9 @@ void bch_cached_dev_run(struct cached_dev *dc)
if (atomic_xchg(&dc->running, 1)) {
kfree(env[1]);
kfree(env[2]);
- return;
+ pr_info("cached dev %s is running already",
+ dc->backing_dev_name);
+ return -EBUSY;
}
if (!d->c &&
@@ -943,8 +971,11 @@ void bch_cached_dev_run(struct cached_dev *dc)
kfree(env[2]);
if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
- sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
- pr_debug("error creating sysfs link");
+ sysfs_create_link(&disk_to_dev(d->disk)->kobj,
+ &d->kobj, "bcache")) {
+ pr_err("Couldn't create bcache dev <-> disk sysfs symlinks");
+ return -ENOMEM;
+ }
dc->status_update_thread = kthread_run(cached_dev_status_update,
dc, "bcache_status_update");
@@ -953,6 +984,8 @@ void bch_cached_dev_run(struct cached_dev *dc)
"continue to run without monitoring backing "
"device status");
}
+
+ return 0;
}
/*
@@ -990,7 +1023,6 @@ static void cached_dev_detach_finish(struct work_struct *w)
BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
BUG_ON(refcount_read(&dc->count));
- mutex_lock(&bch_register_lock);
if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
cancel_writeback_rate_update_dwork(dc);
@@ -1006,6 +1038,8 @@ static void cached_dev_detach_finish(struct work_struct *w)
bch_write_bdev_super(dc, &cl);
closure_sync(&cl);
+ mutex_lock(&bch_register_lock);
+
calc_cached_dev_sectors(dc->disk.c);
bcache_device_detach(&dc->disk);
list_move(&dc->list, &uncached_devices);
@@ -1048,6 +1082,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
uint32_t rtime = cpu_to_le32((u32)ktime_get_real_seconds());
struct uuid_entry *u;
struct cached_dev *exist_dc, *t;
+ int ret = 0;
if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
(!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
@@ -1147,6 +1182,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
down_write(&dc->writeback_lock);
if (bch_cached_dev_writeback_start(dc)) {
up_write(&dc->writeback_lock);
+ pr_err("Couldn't start writeback facilities for %s",
+ dc->disk.disk->disk_name);
return -ENOMEM;
}
@@ -1157,7 +1194,22 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
bch_sectors_dirty_init(&dc->disk);
- bch_cached_dev_run(dc);
+ ret = bch_cached_dev_run(dc);
+ if (ret && (ret != -EBUSY)) {
+ up_write(&dc->writeback_lock);
+ /*
+ * bch_register_lock is held, bcache_device_stop() is not
+ * able to be directly called. The kthread and kworker
+ * created previously in bch_cached_dev_writeback_start()
+ * have to be stopped manually here.
+ */
+ kthread_stop(dc->writeback_thread);
+ cancel_writeback_rate_update_dwork(dc);
+ pr_err("Couldn't run cached device %s",
+ dc->backing_dev_name);
+ return ret;
+ }
+
bcache_device_link(&dc->disk, c, "bdev");
atomic_inc(&c->attached_dev_nr);
@@ -1171,6 +1223,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
return 0;
}
+/* when dc->disk.kobj released */
void bch_cached_dev_release(struct kobject *kobj)
{
struct cached_dev *dc = container_of(kobj, struct cached_dev,
@@ -1183,18 +1236,16 @@ static void cached_dev_free(struct closure *cl)
{
struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
- mutex_lock(&bch_register_lock);
-
if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
cancel_writeback_rate_update_dwork(dc);
if (!IS_ERR_OR_NULL(dc->writeback_thread))
kthread_stop(dc->writeback_thread);
- if (dc->writeback_write_wq)
- destroy_workqueue(dc->writeback_write_wq);
if (!IS_ERR_OR_NULL(dc->status_update_thread))
kthread_stop(dc->status_update_thread);
+ mutex_lock(&bch_register_lock);
+
if (atomic_read(&dc->running))
bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
bcache_device_free(&dc->disk);
@@ -1277,12 +1328,13 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
/* Cached device - bcache superblock */
-static void register_bdev(struct cache_sb *sb, struct page *sb_page,
+static int register_bdev(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev,
struct cached_dev *dc)
{
const char *err = "cannot allocate memory";
struct cache_set *c;
+ int ret = -ENOMEM;
bdevname(bdev, dc->backing_dev_name);
memcpy(&dc->sb, sb, sizeof(struct cache_sb));
@@ -1312,17 +1364,23 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
bch_cached_dev_attach(dc, c, NULL);
if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
- BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
- bch_cached_dev_run(dc);
+ BDEV_STATE(&dc->sb) == BDEV_STATE_STALE) {
+ err = "failed to run cached device";
+ ret = bch_cached_dev_run(dc);
+ if (ret)
+ goto err;
+ }
- return;
+ return 0;
err:
pr_notice("error %s: %s", dc->backing_dev_name, err);
bcache_device_stop(&dc->disk);
+ return ret;
}
/* Flash only volumes */
+/* When d->kobj released */
void bch_flash_dev_release(struct kobject *kobj)
{
struct bcache_device *d = container_of(kobj, struct bcache_device,
@@ -1428,8 +1486,6 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
bool bch_cached_dev_error(struct cached_dev *dc)
{
- struct cache_set *c;
-
if (!dc || test_bit(BCACHE_DEV_CLOSING, &dc->disk.flags))
return false;
@@ -1440,21 +1496,6 @@ bool bch_cached_dev_error(struct cached_dev *dc)
pr_err("stop %s: too many IO errors on backing device %s\n",
dc->disk.disk->disk_name, dc->backing_dev_name);
- /*
- * If the cached device is still attached to a cache set,
- * even dc->io_disable is true and no more I/O requests
- * accepted, cache device internal I/O (writeback scan or
- * garbage collection) may still prevent bcache device from
- * being stopped. So here CACHE_SET_IO_DISABLE should be
- * set to c->flags too, to make the internal I/O to cache
- * device rejected and stopped immediately.
- * If c is NULL, that means the bcache device is not attached
- * to any cache set, then no CACHE_SET_IO_DISABLE bit to set.
- */
- c = dc->disk.c;
- if (c && test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
- pr_info("CACHE_SET_IO_DISABLE already set");
-
bcache_device_stop(&dc->disk);
return true;
}
@@ -1493,6 +1534,7 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
return true;
}
+/* When c->kobj released */
void bch_cache_set_release(struct kobject *kobj)
{
struct cache_set *c = container_of(kobj, struct cache_set, kobj);
@@ -1513,6 +1555,7 @@ static void cache_set_free(struct closure *cl)
bch_btree_cache_free(c);
bch_journal_free(c);
+ mutex_lock(&bch_register_lock);
for_each_cache(ca, c, i)
if (ca) {
ca->set = NULL;
@@ -1535,7 +1578,6 @@ static void cache_set_free(struct closure *cl)
mempool_destroy(c->search);
kfree(c->devices);
- mutex_lock(&bch_register_lock);
list_del(&c->list);
mutex_unlock(&bch_register_lock);
@@ -1558,19 +1600,23 @@ static void cache_set_flush(struct closure *cl)
kobject_put(&c->internal);
kobject_del(&c->kobj);
- if (c->gc_thread)
+ if (!IS_ERR_OR_NULL(c->gc_thread))
kthread_stop(c->gc_thread);
if (!IS_ERR_OR_NULL(c->root))
list_add(&c->root->list, &c->btree_cache);
- /* Should skip this if we're unregistering because of an error */
- list_for_each_entry(b, &c->btree_cache, list) {
- mutex_lock(&b->write_lock);
- if (btree_node_dirty(b))
- __bch_btree_node_write(b, NULL);
- mutex_unlock(&b->write_lock);
- }
+ /*
+ * Avoid flushing cached nodes if cache set is retiring
+ * due to too many I/O errors detected.
+ */
+ if (!test_bit(CACHE_SET_IO_DISABLE, &c->flags))
+ list_for_each_entry(b, &c->btree_cache, list) {
+ mutex_lock(&b->write_lock);
+ if (btree_node_dirty(b))
+ __bch_btree_node_write(b, NULL);
+ mutex_unlock(&b->write_lock);
+ }
for_each_cache(ca, c, i)
if (ca->alloc_thread)
@@ -1674,6 +1720,7 @@ static void __cache_set_unregister(struct closure *cl)
void bch_cache_set_stop(struct cache_set *c)
{
if (!test_and_set_bit(CACHE_SET_STOPPING, &c->flags))
+ /* closure_fn set to __cache_set_unregister() */
closure_queue(&c->caching);
}
@@ -1780,13 +1827,15 @@ err:
return NULL;
}
-static void run_cache_set(struct cache_set *c)
+static int run_cache_set(struct cache_set *c)
{
const char *err = "cannot allocate memory";
struct cached_dev *dc, *t;
struct cache *ca;
struct closure cl;
unsigned int i;
+ LIST_HEAD(journal);
+ struct journal_replay *l;
closure_init_stack(&cl);
@@ -1795,7 +1844,6 @@ static void run_cache_set(struct cache_set *c)
set_gc_sectors(c);
if (CACHE_SYNC(&c->sb)) {
- LIST_HEAD(journal);
struct bkey *k;
struct jset *j;
@@ -1845,6 +1893,23 @@ static void run_cache_set(struct cache_set *c)
if (bch_btree_check(c))
goto err;
+ /*
+ * bch_btree_check() may occupy too much system memory which
+ * has negative effects to user space application (e.g. data
+ * base) performance. Shrink the mca cache memory proactively
+ * here to avoid competing memory with user space workloads..
+ */
+ if (!c->shrinker_disabled) {
+ struct shrink_control sc;
+
+ sc.gfp_mask = GFP_KERNEL;
+ sc.nr_to_scan = c->btree_cache_used * c->btree_pages;
+ /* first run to clear b->accessed tag */
+ c->shrink.scan_objects(&c->shrink, &sc);
+ /* second run to reap non-accessed nodes */
+ c->shrink.scan_objects(&c->shrink, &sc);
+ }
+
bch_journal_mark(c, &journal);
bch_initial_gc_finish(c);
pr_debug("btree_check() done");
@@ -1874,7 +1939,9 @@ static void run_cache_set(struct cache_set *c)
if (j->version < BCACHE_JSET_VERSION_UUID)
__uuid_write(c);
- bch_journal_replay(c, &journal);
+ err = "bcache: replay journal failed";
+ if (bch_journal_replay(c, &journal))
+ goto err;
} else {
pr_notice("invalidating existing data");
@@ -1942,11 +2009,19 @@ static void run_cache_set(struct cache_set *c)
flash_devs_run(c);
set_bit(CACHE_SET_RUNNING, &c->flags);
- return;
+ return 0;
err:
+ while (!list_empty(&journal)) {
+ l = list_first_entry(&journal, struct journal_replay, list);
+ list_del(&l->list);
+ kfree(l);
+ }
+
closure_sync(&cl);
- /* XXX: test this, it's broken */
+
bch_cache_set_error(c, "%s", err);
+
+ return -EIO;
}
static bool can_attach_cache(struct cache *ca, struct cache_set *c)
@@ -2010,8 +2085,11 @@ found:
ca->set->cache[ca->sb.nr_this_dev] = ca;
c->cache_by_alloc[c->caches_loaded++] = ca;
- if (c->caches_loaded == c->sb.nr_in_set)
- run_cache_set(c);
+ if (c->caches_loaded == c->sb.nr_in_set) {
+ err = "failed to run cache set";
+ if (run_cache_set(c) < 0)
+ goto err;
+ }
return NULL;
err:
@@ -2021,6 +2099,7 @@ err:
/* Cache device */
+/* When ca->kobj released */
void bch_cache_release(struct kobject *kobj)
{
struct cache *ca = container_of(kobj, struct cache, kobj);
@@ -2185,6 +2264,12 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
ret = cache_alloc(ca);
if (ret != 0) {
+ /*
+ * If we failed here, it means ca->kobj is not initialized yet,
+ * kobject_put() won't be called and there is no chance to
+ * call blkdev_put() to bdev in bch_cache_release(). So we
+ * explicitly call blkdev_put() here.
+ */
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
if (ret == -ENOMEM)
err = "cache_alloc(): -ENOMEM";
@@ -2228,9 +2313,13 @@ err:
static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
const char *buffer, size_t size);
+static ssize_t bch_pending_bdevs_cleanup(struct kobject *k,
+ struct kobj_attribute *attr,
+ const char *buffer, size_t size);
kobj_attribute_write(register, register_bcache);
kobj_attribute_write(register_quiet, register_bcache);
+kobj_attribute_write(pendings_cleanup, bch_pending_bdevs_cleanup);
static bool bch_is_open_backing(struct block_device *bdev)
{
@@ -2268,7 +2357,7 @@ static bool bch_is_open(struct block_device *bdev)
static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
const char *buffer, size_t size)
{
- ssize_t ret = size;
+ ssize_t ret = -EINVAL;
const char *err = "cannot allocate memory";
char *path = NULL;
struct cache_sb *sb = NULL;
@@ -2278,6 +2367,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
if (!try_module_get(THIS_MODULE))
return -EBUSY;
+ /* For latest state of bcache_is_reboot */
+ smp_mb();
+ if (bcache_is_reboot)
+ return -EBUSY;
+
path = kstrndup(buffer, size, GFP_KERNEL);
if (!path)
goto err;
@@ -2302,7 +2396,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
if (!IS_ERR(bdev))
bdput(bdev);
if (attr == &ksysfs_register_quiet)
- goto out;
+ goto quiet_out;
}
goto err;
}
@@ -2323,17 +2417,23 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
goto err_close;
mutex_lock(&bch_register_lock);
- register_bdev(sb, sb_page, bdev, dc);
+ ret = register_bdev(sb, sb_page, bdev, dc);
mutex_unlock(&bch_register_lock);
+ /* blkdev_put() will be called in cached_dev_free() */
+ if (ret < 0)
+ goto err;
} else {
struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
if (!ca)
goto err_close;
+ /* blkdev_put() will be called in bch_cache_release() */
if (register_cache(sb, sb_page, bdev, ca) != 0)
goto err;
}
+quiet_out:
+ ret = size;
out:
if (sb_page)
put_page(sb_page);
@@ -2346,12 +2446,64 @@ err_close:
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
err:
pr_info("error %s: %s", path, err);
- ret = -EINVAL;
goto out;
}
+
+struct pdev {
+ struct list_head list;
+ struct cached_dev *dc;
+};
+
+static ssize_t bch_pending_bdevs_cleanup(struct kobject *k,
+ struct kobj_attribute *attr,
+ const char *buffer,
+ size_t size)
+{
+ LIST_HEAD(pending_devs);
+ ssize_t ret = size;
+ struct cached_dev *dc, *tdc;
+ struct pdev *pdev, *tpdev;
+ struct cache_set *c, *tc;
+
+ mutex_lock(&bch_register_lock);
+ list_for_each_entry_safe(dc, tdc, &uncached_devices, list) {
+ pdev = kmalloc(sizeof(struct pdev), GFP_KERNEL);
+ if (!pdev)
+ break;
+ pdev->dc = dc;
+ list_add(&pdev->list, &pending_devs);
+ }
+
+ list_for_each_entry_safe(pdev, tpdev, &pending_devs, list) {
+ list_for_each_entry_safe(c, tc, &bch_cache_sets, list) {
+ char *pdev_set_uuid = pdev->dc->sb.set_uuid;
+ char *set_uuid = c->sb.uuid;
+
+ if (!memcmp(pdev_set_uuid, set_uuid, 16)) {
+ list_del(&pdev->list);
+ kfree(pdev);
+ break;
+ }
+ }
+ }
+ mutex_unlock(&bch_register_lock);
+
+ list_for_each_entry_safe(pdev, tpdev, &pending_devs, list) {
+ pr_info("delete pdev %p", pdev);
+ list_del(&pdev->list);
+ bcache_device_stop(&pdev->dc->disk);
+ kfree(pdev);
+ }
+
+ return ret;
+}
+
static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
{
+ if (bcache_is_reboot)
+ return NOTIFY_DONE;
+
if (code == SYS_DOWN ||
code == SYS_HALT ||
code == SYS_POWER_OFF) {
@@ -2364,22 +2516,57 @@ static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
mutex_lock(&bch_register_lock);
+ if (bcache_is_reboot)
+ goto out;
+
+ /* New registration is rejected since now */
+ bcache_is_reboot = true;
+ /*
+ * Make registering caller (if there is) on other CPU
+ * core know bcache_is_reboot set to true earlier
+ */
+ smp_mb();
+
if (list_empty(&bch_cache_sets) &&
list_empty(&uncached_devices))
goto out;
+ mutex_unlock(&bch_register_lock);
+
pr_info("Stopping all devices:");
+ /*
+ * The reason bch_register_lock is not held to call
+ * bch_cache_set_stop() and bcache_device_stop() is to
+ * avoid potential deadlock during reboot, because cache
+ * set or bcache device stopping process will acqurie
+ * bch_register_lock too.
+ *
+ * We are safe here because bcache_is_reboot sets to
+ * true already, register_bcache() will reject new
+ * registration now. bcache_is_reboot also makes sure
+ * bcache_reboot() won't be re-entered on by other thread,
+ * so there is no race in following list iteration by
+ * list_for_each_entry_safe().
+ */
list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
bch_cache_set_stop(c);
list_for_each_entry_safe(dc, tdc, &uncached_devices, list)
bcache_device_stop(&dc->disk);
+
+ /*
+ * Give an early chance for other kthreads and
+ * kworkers to stop themselves
+ */
+ schedule();
+
/* What's a condition variable? */
while (1) {
- long timeout = start + 2 * HZ - jiffies;
+ long timeout = start + 10 * HZ - jiffies;
+ mutex_lock(&bch_register_lock);
stopped = list_empty(&bch_cache_sets) &&
list_empty(&uncached_devices);
@@ -2391,7 +2578,6 @@ static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
mutex_unlock(&bch_register_lock);
schedule_timeout(timeout);
- mutex_lock(&bch_register_lock);
}
finish_wait(&unregister_wait, &wait);
@@ -2460,6 +2646,7 @@ static int __init bcache_init(void)
static const struct attribute *files[] = {
&ksysfs_register.attr,
&ksysfs_register_quiet.attr,
+ &ksysfs_pendings_cleanup.attr,
NULL
};
@@ -2495,6 +2682,8 @@ static int __init bcache_init(void)
bch_debug_init();
closure_debug_init();
+ bcache_is_reboot = false;
+
return 0;
err:
bcache_exit();
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 00095344a23d..1c19a4b652e1 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -15,33 +15,31 @@
#include <linux/sort.h>
#include <linux/sched/clock.h>
+extern bool bcache_is_reboot;
+
/* Default is 0 ("writethrough") */
static const char * const bch_cache_modes[] = {
"writethrough",
"writeback",
"writearound",
- "none",
- NULL
+ "none"
};
/* Default is 0 ("auto") */
static const char * const bch_stop_on_failure_modes[] = {
"auto",
- "always",
- NULL
+ "always"
};
static const char * const cache_replacement_policies[] = {
"lru",
"fifo",
- "random",
- NULL
+ "random"
};
static const char * const error_actions[] = {
"unregister",
- "panic",
- NULL
+ "panic"
};
write_attribute(attach);
@@ -83,8 +81,8 @@ read_attribute(bset_tree_stats);
read_attribute(state);
read_attribute(cache_read_races);
read_attribute(reclaim);
+read_attribute(reclaimed_journal_buckets);
read_attribute(flush_write);
-read_attribute(retry_flush_write);
read_attribute(writeback_keys_done);
read_attribute(writeback_keys_failed);
read_attribute(io_errors);
@@ -179,7 +177,7 @@ SHOW(__bch_cached_dev)
var_print(writeback_percent);
sysfs_hprint(writeback_rate,
wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0);
- sysfs_hprint(io_errors, atomic_read(&dc->io_errors));
+ sysfs_printf(io_errors, "%i", atomic_read(&dc->io_errors));
sysfs_printf(io_error_limit, "%i", dc->error_limit);
sysfs_printf(io_disable, "%i", dc->io_disable);
var_print(writeback_rate_update_seconds);
@@ -270,6 +268,10 @@ STORE(__cached_dev)
struct cache_set *c;
struct kobj_uevent_env *env;
+ /* no user space access if system is rebooting */
+ if (bcache_is_reboot)
+ return -EBUSY;
+
#define d_strtoul(var) sysfs_strtoul(var, dc->var)
#define d_strtoul_nonzero(var) sysfs_strtoul_clamp(var, dc->var, 1, INT_MAX)
#define d_strtoi_h(var) sysfs_hatoi(var, dc->var)
@@ -328,11 +330,14 @@ STORE(__cached_dev)
bch_cache_accounting_clear(&dc->accounting);
if (attr == &sysfs_running &&
- strtoul_or_return(buf))
- bch_cached_dev_run(dc);
+ strtoul_or_return(buf)) {
+ v = bch_cached_dev_run(dc);
+ if (v)
+ return v;
+ }
if (attr == &sysfs_cache_mode) {
- v = __sysfs_match_string(bch_cache_modes, -1, buf);
+ v = sysfs_match_string(bch_cache_modes, buf);
if (v < 0)
return v;
@@ -343,7 +348,7 @@ STORE(__cached_dev)
}
if (attr == &sysfs_stop_when_cache_set_failed) {
- v = __sysfs_match_string(bch_stop_on_failure_modes, -1, buf);
+ v = sysfs_match_string(bch_stop_on_failure_modes, buf);
if (v < 0)
return v;
@@ -407,6 +412,10 @@ STORE(bch_cached_dev)
struct cached_dev *dc = container_of(kobj, struct cached_dev,
disk.kobj);
+ /* no user space access if system is rebooting */
+ if (bcache_is_reboot)
+ return -EBUSY;
+
mutex_lock(&bch_register_lock);
size = __cached_dev_store(kobj, attr, buf, size);
@@ -430,8 +439,13 @@ STORE(bch_cached_dev)
bch_writeback_queue(dc);
}
+ /*
+ * Only set BCACHE_DEV_WB_RUNNING when cached device attached to
+ * a cache set, otherwise it doesn't make sense.
+ */
if (attr == &sysfs_writeback_percent)
- if (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
+ if ((dc->disk.c != NULL) &&
+ (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)))
schedule_delayed_work(&dc->writeback_rate_update,
dc->writeback_rate_update_seconds * HZ);
@@ -458,7 +472,7 @@ static struct attribute *bch_cached_dev_files[] = {
&sysfs_writeback_rate_p_term_inverse,
&sysfs_writeback_rate_minimum,
&sysfs_writeback_rate_debug,
- &sysfs_errors,
+ &sysfs_io_errors,
&sysfs_io_error_limit,
&sysfs_io_disable,
&sysfs_dirty_data,
@@ -505,6 +519,10 @@ STORE(__bch_flash_dev)
kobj);
struct uuid_entry *u = &d->c->uuids[d->id];
+ /* no user space access if system is rebooting */
+ if (bcache_is_reboot)
+ return -EBUSY;
+
sysfs_strtoul(data_csum, d->data_csum);
if (attr == &sysfs_size) {
@@ -687,12 +705,12 @@ SHOW(__bch_cache_set)
sysfs_print(reclaim,
atomic_long_read(&c->reclaim));
+ sysfs_print(reclaimed_journal_buckets,
+ atomic_long_read(&c->reclaimed_journal_buckets));
+
sysfs_print(flush_write,
atomic_long_read(&c->flush_write));
- sysfs_print(retry_flush_write,
- atomic_long_read(&c->retry_flush_write));
-
sysfs_print(writeback_keys_done,
atomic_long_read(&c->writeback_keys_done));
sysfs_print(writeback_keys_failed,
@@ -740,6 +758,10 @@ STORE(__bch_cache_set)
struct cache_set *c = container_of(kobj, struct cache_set, kobj);
ssize_t v;
+ /* no user space access if system is rebooting */
+ if (bcache_is_reboot)
+ return -EBUSY;
+
if (attr == &sysfs_unregister)
bch_cache_set_unregister(c);
@@ -793,7 +815,7 @@ STORE(__bch_cache_set)
0, UINT_MAX);
if (attr == &sysfs_errors) {
- v = __sysfs_match_string(error_actions, -1, buf);
+ v = sysfs_match_string(error_actions, buf);
if (v < 0)
return v;
@@ -859,6 +881,10 @@ STORE(bch_cache_set_internal)
{
struct cache_set *c = container_of(kobj, struct cache_set, internal);
+ /* no user space access if system is rebooting */
+ if (bcache_is_reboot)
+ return -EBUSY;
+
return bch_cache_set_store(&c->kobj, attr, buf, size);
}
@@ -908,8 +934,8 @@ static struct attribute *bch_cache_set_internal_files[] = {
&sysfs_bset_tree_stats,
&sysfs_cache_read_races,
&sysfs_reclaim,
+ &sysfs_reclaimed_journal_buckets,
&sysfs_flush_write,
- &sysfs_retry_flush_write,
&sysfs_writeback_keys_done,
&sysfs_writeback_keys_failed,
@@ -994,8 +1020,6 @@ SHOW(__bch_cache)
!cached[n - 1])
--n;
- unused = ca->sb.nbuckets - n;
-
while (cached < p + n &&
*cached == BTREE_PRIO)
cached++, n--;
@@ -1045,6 +1069,10 @@ STORE(__bch_cache)
struct cache *ca = container_of(kobj, struct cache, kobj);
ssize_t v;
+ /* no user space access if system is rebooting */
+ if (bcache_is_reboot)
+ return -EBUSY;
+
if (attr == &sysfs_discard) {
bool v = strtoul_or_return(buf);
@@ -1058,7 +1086,7 @@ STORE(__bch_cache)
}
if (attr == &sysfs_cache_replacement_policy) {
- v = __sysfs_match_string(cache_replacement_policies, -1, buf);
+ v = sysfs_match_string(cache_replacement_policies, buf);
if (v < 0)
return v;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index a421b63c0990..417cc29b1d68 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -112,8 +112,6 @@ do { \
#define heap_full(h) ((h)->used == (h)->size)
-#define heap_empty(h) ((h)->used == 0)
-
#define DECLARE_FIFO(type, name) \
struct { \
size_t front, back, size, mask; \
@@ -559,17 +557,29 @@ static inline uint64_t bch_crc64_update(uint64_t crc,
return crc;
}
-/* Does linear interpolation between powers of two */
+/*
+ * A stepwise-linear pseudo-exponential. This returns 1 << (x >>
+ * frac_bits), with the less-significant bits filled in by linear
+ * interpolation.
+ *
+ * This can also be interpreted as a floating-point number format,
+ * where the low frac_bits are the mantissa (with implicit leading
+ * 1 bit), and the more significant bits are the exponent.
+ * The return value is 1.mantissa * 2^exponent.
+ *
+ * The way this is used, fract_bits is 6 and the largest possible
+ * input is CONGESTED_MAX-1 = 1023 (exponent 16, mantissa 0x1.fc),
+ * so the maximum output is 0x1fc00.
+ */
static inline unsigned int fract_exp_two(unsigned int x,
unsigned int fract_bits)
{
- unsigned int fract = x & ~(~0 << fract_bits);
-
- x >>= fract_bits;
- x = 1 << x;
- x += (x * fract) >> fract_bits;
+ unsigned int mantissa = 1 << fract_bits; /* Implicit bit */
- return x;
+ mantissa += x & (mantissa - 1);
+ x >>= fract_bits; /* The exponent */
+ /* Largest intermediate value 0x7f0000 */
+ return mantissa << x >> fract_bits;
}
void bch_bio_map(struct bio *bio, void *base);
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 2c1b47a599c7..e676600e81f9 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -121,6 +121,9 @@ static void __update_writeback_rate(struct cached_dev *dc)
static bool set_at_max_writeback_rate(struct cache_set *c,
struct cached_dev *dc)
{
+ /* Don't set max writeback rate if gc is running */
+ if (!c->gc_mark_valid)
+ return false;
/*
* Idle_counter is increased everytime when update_writeback_rate() is
* called. If all backing devices attached to the same cache set have
@@ -734,6 +737,10 @@ static int bch_writeback_thread(void *arg)
}
}
+ if (dc->writeback_write_wq) {
+ flush_workqueue(dc->writeback_write_wq);
+ destroy_workqueue(dc->writeback_write_wq);
+ }
cached_dev_put(dc);
wait_for_kthread_stop();
@@ -829,6 +836,7 @@ int bch_cached_dev_writeback_start(struct cached_dev *dc)
"bcache_writeback");
if (IS_ERR(dc->writeback_thread)) {
cached_dev_put(dc);
+ destroy_workqueue(dc->writeback_write_wq);
return PTR_ERR(dc->writeback_thread);
}
dc->writeback_running = true;
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c
index a8bda6679422..8028ecdc157f 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.c
+++ b/drivers/media/platform/marvell-ccic/mcam-core.c
@@ -199,7 +199,6 @@ struct mcam_vb_buffer {
struct list_head queue;
struct mcam_dma_desc *dma_desc; /* Descriptor virtual address */
dma_addr_t dma_desc_pa; /* Descriptor physical address */
- int dma_desc_nent; /* Number of mapped descriptors */
};
static inline struct mcam_vb_buffer *vb_to_mvb(struct vb2_v4l2_buffer *vb)
@@ -606,9 +605,11 @@ static void mcam_dma_contig_done(struct mcam_camera *cam, int frame)
static void mcam_sg_next_buffer(struct mcam_camera *cam)
{
struct mcam_vb_buffer *buf;
+ struct sg_table *sg_table;
buf = list_first_entry(&cam->buffers, struct mcam_vb_buffer, queue);
list_del_init(&buf->queue);
+ sg_table = vb2_dma_sg_plane_desc(&buf->vb_buf.vb2_buf, 0);
/*
* Very Bad Not Good Things happen if you don't clear
* C1_DESC_ENA before making any descriptor changes.
@@ -616,7 +617,7 @@ static void mcam_sg_next_buffer(struct mcam_camera *cam)
mcam_reg_clear_bit(cam, REG_CTRL1, C1_DESC_ENA);
mcam_reg_write(cam, REG_DMA_DESC_Y, buf->dma_desc_pa);
mcam_reg_write(cam, REG_DESC_LEN_Y,
- buf->dma_desc_nent*sizeof(struct mcam_dma_desc));
+ sg_table->nents * sizeof(struct mcam_dma_desc));
mcam_reg_write(cam, REG_DESC_LEN_U, 0);
mcam_reg_write(cam, REG_DESC_LEN_V, 0);
mcam_reg_set_bit(cam, REG_CTRL1, C1_DESC_ENA);
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
index eb85cedc5ef3..5e080f32b0e8 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
@@ -38,6 +38,11 @@ int s5p_mfc_init_pm(struct s5p_mfc_dev *dev)
for (i = 0; i < pm->num_clocks; i++) {
pm->clocks[i] = devm_clk_get(pm->device, pm->clk_names[i]);
if (IS_ERR(pm->clocks[i])) {
+ /* additional clocks are optional */
+ if (i && PTR_ERR(pm->clocks[i]) == -ENOENT) {
+ pm->clocks[i] = NULL;
+ continue;
+ }
mfc_err("Failed to get clock: %s\n",
pm->clk_names[i]);
return PTR_ERR(pm->clocks[i]);
diff --git a/drivers/media/platform/vivid/vivid-osd.c b/drivers/media/platform/vivid/vivid-osd.c
index bdc380b14e0c..a95b7c56569e 100644
--- a/drivers/media/platform/vivid/vivid-osd.c
+++ b/drivers/media/platform/vivid/vivid-osd.c
@@ -167,7 +167,7 @@ static int _vivid_fb_check_var(struct fb_var_screeninfo *var, struct vivid_dev *
var->nonstd = 0;
var->vmode &= ~FB_VMODE_MASK;
- var->vmode = FB_VMODE_NONINTERLACED;
+ var->vmode |= FB_VMODE_NONINTERLACED;
/* Dummy values */
var->hsync_len = 24;
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index bd49b698c02c..a74275168ef5 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -2109,16 +2109,15 @@ struct v4l2_ctrl *v4l2_ctrl_new_custom(struct v4l2_ctrl_handler *hdl,
v4l2_ctrl_fill(cfg->id, &name, &type, &min, &max, &step,
&def, &flags);
- is_menu = (cfg->type == V4L2_CTRL_TYPE_MENU ||
- cfg->type == V4L2_CTRL_TYPE_INTEGER_MENU);
+ is_menu = (type == V4L2_CTRL_TYPE_MENU ||
+ type == V4L2_CTRL_TYPE_INTEGER_MENU);
if (is_menu)
WARN_ON(step);
else
WARN_ON(cfg->menu_skip_mask);
- if (cfg->type == V4L2_CTRL_TYPE_MENU && qmenu == NULL)
+ if (type == V4L2_CTRL_TYPE_MENU && !qmenu) {
qmenu = v4l2_ctrl_get_menu(cfg->id);
- else if (cfg->type == V4L2_CTRL_TYPE_INTEGER_MENU &&
- qmenu_int == NULL) {
+ } else if (type == V4L2_CTRL_TYPE_INTEGER_MENU && !qmenu_int) {
handler_set_err(hdl, -EINVAL);
return NULL;
}
diff --git a/drivers/memory/tegra/mc.c b/drivers/memory/tegra/mc.c
index 1d49a8dd4a37..7c040a3b45be 100644
--- a/drivers/memory/tegra/mc.c
+++ b/drivers/memory/tegra/mc.c
@@ -72,7 +72,7 @@ static int tegra_mc_setup_latency_allowance(struct tegra_mc *mc)
u32 value;
/* compute the number of MC clock cycles per tick */
- tick = mc->tick * clk_get_rate(mc->clk);
+ tick = (unsigned long long)mc->tick * clk_get_rate(mc->clk);
do_div(tick, NSEC_PER_SEC);
value = readl(mc->regs + MC_EMEM_ARB_CFG);
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index 1246d69ba187..b1564cacd19e 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -629,13 +629,18 @@ static int __init memstick_init(void)
return -ENOMEM;
rc = bus_register(&memstick_bus_type);
- if (!rc)
- rc = class_register(&memstick_host_class);
+ if (rc)
+ goto error_destroy_workqueue;
- if (!rc)
- return 0;
+ rc = class_register(&memstick_host_class);
+ if (rc)
+ goto error_bus_unregister;
+
+ return 0;
+error_bus_unregister:
bus_unregister(&memstick_bus_type);
+error_destroy_workqueue:
destroy_workqueue(workqueue);
return rc;
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 929141202334..f6fb853961fa 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -1613,8 +1613,13 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
host->mmc->caps2 |= MMC_CAP2_NO_PRESCAN_POWERUP;
if (slot->cd_idx >= 0) {
- ret = mmc_gpiod_request_cd(host->mmc, NULL, slot->cd_idx,
+ ret = mmc_gpiod_request_cd(host->mmc, "cd", slot->cd_idx,
slot->cd_override_level, 0, NULL);
+ if (ret && ret != -EPROBE_DEFER)
+ ret = mmc_gpiod_request_cd(host->mmc, NULL,
+ slot->cd_idx,
+ slot->cd_override_level,
+ 0, NULL);
if (ret == -EPROBE_DEFER)
goto remove;
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index bfc20b45b806..d79c2bccf582 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -1178,6 +1178,10 @@ static int ath6kl_wmi_pstream_timeout_event_rx(struct wmi *wmi, u8 *datap,
return -EINVAL;
ev = (struct wmi_pstream_timeout_event *) datap;
+ if (ev->traffic_class >= WMM_NUM_AC) {
+ ath6kl_err("invalid traffic class: %d\n", ev->traffic_class);
+ return -EINVAL;
+ }
/*
* When the pstream (fat pipe == AC) timesout, it means there were
@@ -1519,6 +1523,10 @@ static int ath6kl_wmi_cac_event_rx(struct wmi *wmi, u8 *datap, int len,
return -EINVAL;
reply = (struct wmi_cac_event *) datap;
+ if (reply->ac >= WMM_NUM_AC) {
+ ath6kl_err("invalid AC: %d\n", reply->ac);
+ return -EINVAL;
+ }
if ((reply->cac_indication == CAC_INDICATION_ADMISSION_RESP) &&
(reply->status_code != IEEE80211_TSPEC_STATUS_ADMISS_ACCEPTED)) {
@@ -2635,7 +2643,7 @@ int ath6kl_wmi_delete_pstream_cmd(struct wmi *wmi, u8 if_idx, u8 traffic_class,
u16 active_tsids = 0;
int ret;
- if (traffic_class > 3) {
+ if (traffic_class >= WMM_NUM_AC) {
ath6kl_err("invalid traffic class: %d\n", traffic_class);
return -EINVAL;
}
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 84d91606e6f3..c7e4715a1053 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -675,6 +675,7 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
[GRO_HELD] = "GRO_HELD",
[GRO_NORMAL] = "GRO_NORMAL",
[GRO_DROP] = "GRO_DROP",
+ [GRO_CONSUMED] = "GRO_CONSUMED",
};
if (ndev->features & NETIF_F_RXHASH)
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 865087e36935..5a759e9f539e 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -1743,9 +1743,16 @@ struct mwifiex_ie_types_wmm_queue_status {
struct ieee_types_vendor_header {
u8 element_id;
u8 len;
+#ifdef __GENKSYMS__
u8 oui[4]; /* 0~2: oui, 3: oui_type */
u8 oui_subtype;
u8 version;
+#else
+ struct {
+ u8 oui[3];
+ u8 oui_type;
+ } __packed oui;
+#endif
} __packed;
struct ieee_types_wmm_parameter {
@@ -1759,6 +1766,11 @@ struct ieee_types_wmm_parameter {
* Version [1]
*/
struct ieee_types_vendor_header vend_hdr;
+#ifndef __GENKSYMS__
+ u8 oui_subtype;
+ u8 version;
+#endif
+
u8 qos_info_bitmap;
u8 reserved;
struct ieee_types_wmm_ac_parameters ac_params[IEEE80211_NUM_ACS];
@@ -1776,6 +1788,10 @@ struct ieee_types_wmm_info {
* Version [1]
*/
struct ieee_types_vendor_header vend_hdr;
+#ifndef __GENKSYMS__
+ u8 oui_subtype;
+ u8 version;
+#endif
u8 qos_info_bitmap;
} __packed;
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 04730ae2386b..787d8fc46193 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1357,21 +1357,25 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
break;
case WLAN_EID_VENDOR_SPECIFIC:
- if (element_len + 2 < sizeof(vendor_ie->vend_hdr))
- return -EINVAL;
-
vendor_ie = (struct ieee_types_vendor_specific *)
current_ptr;
- if (!memcmp
- (vendor_ie->vend_hdr.oui, wpa_oui,
- sizeof(wpa_oui))) {
+ /* 802.11 requires at least 3-byte OUI. */
+ if (element_len < sizeof(vendor_ie->vend_hdr.oui.oui))
+ return -EINVAL;
+
+ /* Not long enough for a match? Skip it. */
+ if (element_len < sizeof(wpa_oui))
+ break;
+
+ if (!memcmp(&vendor_ie->vend_hdr.oui, wpa_oui,
+ sizeof(wpa_oui))) {
bss_entry->bcn_wpa_ie =
(struct ieee_types_vendor_specific *)
current_ptr;
bss_entry->wpa_offset = (u16)
(current_ptr - bss_entry->beacon_buf);
- } else if (!memcmp(vendor_ie->vend_hdr.oui, wmm_oui,
+ } else if (!memcmp(&vendor_ie->vend_hdr.oui, wmm_oui,
sizeof(wmm_oui))) {
if (total_ie_len ==
sizeof(struct ieee_types_wmm_parameter) ||
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 8ab314b4e71d..91464cfccb3b 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -1332,7 +1332,7 @@ mwifiex_set_gen_ie_helper(struct mwifiex_private *priv, u8 *ie_data_ptr,
/* Test to see if it is a WPA IE, if not, then it is a
* gen IE
*/
- if (!memcmp(pvendor_ie->oui, wpa_oui,
+ if (!memcmp(&pvendor_ie->oui, wpa_oui,
sizeof(wpa_oui))) {
find_wpa_ie = 1;
break;
@@ -1341,7 +1341,7 @@ mwifiex_set_gen_ie_helper(struct mwifiex_private *priv, u8 *ie_data_ptr,
/* Test to see if it is a WPS IE, if so, enable
* wps session flag
*/
- if (!memcmp(pvendor_ie->oui, wps_oui,
+ if (!memcmp(&pvendor_ie->oui, wps_oui,
sizeof(wps_oui))) {
priv->wps.session_enable = true;
mwifiex_dbg(priv->adapter, MSG,
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index e4ff3b973850..caea1073bdd0 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -240,7 +240,7 @@ mwifiex_wmm_setup_queue_priorities(struct mwifiex_private *priv,
mwifiex_dbg(priv->adapter, INFO,
"info: WMM Parameter IE: version=%d,\t"
"qos_info Parameter Set Count=%d, Reserved=%#x\n",
- wmm_ie->vend_hdr.version, wmm_ie->qos_info_bitmap &
+ wmm_ie->version, wmm_ie->qos_info_bitmap &
IEEE80211_WMM_IE_AP_QOSINFO_PARAM_SET_CNT_MASK,
wmm_ie->reserved);
diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index d4d089c37944..63a6881c7078 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -453,6 +453,14 @@ static const struct dmi_system_id critclk_systems[] = {
},
{
/* pmc_plt_clk* - are used for ethernet controllers */
+ .ident = "Beckhoff CB4063",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Beckhoff Automation"),
+ DMI_MATCH(DMI_BOARD_NAME, "CB4063"),
+ },
+ },
+ {
+ /* pmc_plt_clk* - are used for ethernet controllers */
.ident = "Beckhoff CB6263",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Beckhoff Automation"),
diff --git a/drivers/staging/comedi/drivers/amplc_pci230.c b/drivers/staging/comedi/drivers/amplc_pci230.c
index 48c7890c3007..2b0b757dc626 100644
--- a/drivers/staging/comedi/drivers/amplc_pci230.c
+++ b/drivers/staging/comedi/drivers/amplc_pci230.c
@@ -2339,7 +2339,8 @@ static irqreturn_t pci230_interrupt(int irq, void *d)
devpriv->intr_running = false;
spin_unlock_irqrestore(&devpriv->isr_spinlock, irqflags);
- comedi_handle_events(dev, s_ao);
+ if (s_ao)
+ comedi_handle_events(dev, s_ao);
comedi_handle_events(dev, s_ai);
return IRQ_HANDLED;
diff --git a/drivers/staging/comedi/drivers/dt282x.c b/drivers/staging/comedi/drivers/dt282x.c
index d5295bbdd28c..37133d54dda1 100644
--- a/drivers/staging/comedi/drivers/dt282x.c
+++ b/drivers/staging/comedi/drivers/dt282x.c
@@ -566,7 +566,8 @@ static irqreturn_t dt282x_interrupt(int irq, void *d)
}
#endif
comedi_handle_events(dev, s);
- comedi_handle_events(dev, s_ao);
+ if (s_ao)
+ comedi_handle_events(dev, s_ao);
return IRQ_RETVAL(handled);
}
diff --git a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
index e30a5be5f318..c383d026797d 100644
--- a/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
+++ b/drivers/staging/rtl8712/rtl871x_ioctl_linux.c
@@ -137,10 +137,91 @@ static inline void handle_group_key(struct ieee_param *param,
}
}
-static noinline_for_stack char *translate_scan(struct _adapter *padapter,
- struct iw_request_info *info,
- struct wlan_network *pnetwork,
- char *start, char *stop)
+static noinline_for_stack char *translate_scan_wpa(struct iw_request_info *info,
+ struct wlan_network *pnetwork,
+ struct iw_event *iwe,
+ char *start, char *stop)
+{
+ /* parsing WPA/WPA2 IE */
+ u8 buf[MAX_WPA_IE_LEN];
+ u8 wpa_ie[255], rsn_ie[255];
+ u16 wpa_len = 0, rsn_len = 0;
+ int n, i;
+
+ r8712_get_sec_ie(pnetwork->network.IEs,
+ pnetwork->network.IELength, rsn_ie, &rsn_len,
+ wpa_ie, &wpa_len);
+ if (wpa_len > 0) {
+ memset(buf, 0, MAX_WPA_IE_LEN);
+ n = sprintf(buf, "wpa_ie=");
+ for (i = 0; i < wpa_len; i++) {
+ n += snprintf(buf + n, MAX_WPA_IE_LEN - n,
+ "%02x", wpa_ie[i]);
+ if (n >= MAX_WPA_IE_LEN)
+ break;
+ }
+ memset(iwe, 0, sizeof(*iwe));
+ iwe->cmd = IWEVCUSTOM;
+ iwe->u.data.length = (u16)strlen(buf);
+ start = iwe_stream_add_point(info, start, stop,
+ iwe, buf);
+ memset(iwe, 0, sizeof(*iwe));
+ iwe->cmd = IWEVGENIE;
+ iwe->u.data.length = (u16)wpa_len;
+ start = iwe_stream_add_point(info, start, stop,
+ iwe, wpa_ie);
+ }
+ if (rsn_len > 0) {
+ memset(buf, 0, MAX_WPA_IE_LEN);
+ n = sprintf(buf, "rsn_ie=");
+ for (i = 0; i < rsn_len; i++) {
+ n += snprintf(buf + n, MAX_WPA_IE_LEN - n,
+ "%02x", rsn_ie[i]);
+ if (n >= MAX_WPA_IE_LEN)
+ break;
+ }
+ memset(iwe, 0, sizeof(*iwe));
+ iwe->cmd = IWEVCUSTOM;
+ iwe->u.data.length = strlen(buf);
+ start = iwe_stream_add_point(info, start, stop,
+ iwe, buf);
+ memset(iwe, 0, sizeof(*iwe));
+ iwe->cmd = IWEVGENIE;
+ iwe->u.data.length = rsn_len;
+ start = iwe_stream_add_point(info, start, stop, iwe,
+ rsn_ie);
+ }
+
+ return start;
+}
+
+static noinline_for_stack char *translate_scan_wps(struct iw_request_info *info,
+ struct wlan_network *pnetwork,
+ struct iw_event *iwe,
+ char *start, char *stop)
+{
+ /* parsing WPS IE */
+ u8 wps_ie[512];
+ uint wps_ielen;
+
+ if (r8712_get_wps_ie(pnetwork->network.IEs,
+ pnetwork->network.IELength,
+ wps_ie, &wps_ielen)) {
+ if (wps_ielen > 2) {
+ iwe->cmd = IWEVGENIE;
+ iwe->u.data.length = (u16)wps_ielen;
+ start = iwe_stream_add_point(info, start, stop,
+ iwe, wps_ie);
+ }
+ }
+
+ return start;
+}
+
+static char *translate_scan(struct _adapter *padapter,
+ struct iw_request_info *info,
+ struct wlan_network *pnetwork,
+ char *start, char *stop)
{
struct iw_event iwe;
struct ieee80211_ht_cap *pht_capie;
@@ -253,73 +334,11 @@ static noinline_for_stack char *translate_scan(struct _adapter *padapter,
/* Check if we added any event */
if ((current_val - start) > iwe_stream_lcp_len(info))
start = current_val;
- /* parsing WPA/WPA2 IE */
- {
- u8 buf[MAX_WPA_IE_LEN];
- u8 wpa_ie[255], rsn_ie[255];
- u16 wpa_len = 0, rsn_len = 0;
- int n;
-
- r8712_get_sec_ie(pnetwork->network.IEs,
- pnetwork->network.IELength, rsn_ie, &rsn_len,
- wpa_ie, &wpa_len);
- if (wpa_len > 0) {
- memset(buf, 0, MAX_WPA_IE_LEN);
- n = sprintf(buf, "wpa_ie=");
- for (i = 0; i < wpa_len; i++) {
- n += snprintf(buf + n, MAX_WPA_IE_LEN - n,
- "%02x", wpa_ie[i]);
- if (n >= MAX_WPA_IE_LEN)
- break;
- }
- memset(&iwe, 0, sizeof(iwe));
- iwe.cmd = IWEVCUSTOM;
- iwe.u.data.length = (u16)strlen(buf);
- start = iwe_stream_add_point(info, start, stop,
- &iwe, buf);
- memset(&iwe, 0, sizeof(iwe));
- iwe.cmd = IWEVGENIE;
- iwe.u.data.length = (u16)wpa_len;
- start = iwe_stream_add_point(info, start, stop,
- &iwe, wpa_ie);
- }
- if (rsn_len > 0) {
- memset(buf, 0, MAX_WPA_IE_LEN);
- n = sprintf(buf, "rsn_ie=");
- for (i = 0; i < rsn_len; i++) {
- n += snprintf(buf + n, MAX_WPA_IE_LEN - n,
- "%02x", rsn_ie[i]);
- if (n >= MAX_WPA_IE_LEN)
- break;
- }
- memset(&iwe, 0, sizeof(iwe));
- iwe.cmd = IWEVCUSTOM;
- iwe.u.data.length = strlen(buf);
- start = iwe_stream_add_point(info, start, stop,
- &iwe, buf);
- memset(&iwe, 0, sizeof(iwe));
- iwe.cmd = IWEVGENIE;
- iwe.u.data.length = rsn_len;
- start = iwe_stream_add_point(info, start, stop, &iwe,
- rsn_ie);
- }
- }
- { /* parsing WPS IE */
- u8 wps_ie[512];
- uint wps_ielen;
+ start = translate_scan_wpa(info, pnetwork, &iwe, start, stop);
+
+ start = translate_scan_wps(info, pnetwork, &iwe, start, stop);
- if (r8712_get_wps_ie(pnetwork->network.IEs,
- pnetwork->network.IELength,
- wps_ie, &wps_ielen)) {
- if (wps_ielen > 2) {
- iwe.cmd = IWEVGENIE;
- iwe.u.data.length = (u16)wps_ielen;
- start = iwe_stream_add_point(info, start, stop,
- &iwe, wps_ie);
- }
- }
- }
/* Add quality statistics */
iwe.cmd = IWEVQUAL;
rssi = r8712_signal_scale_mapping(pnetwork->network.Rssi);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0512723d2fc6..be26e2583ce7 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -68,42 +68,6 @@ noinline void btrfs_set_path_blocking(struct btrfs_path *p)
}
}
-/*
- * reset all the locked nodes in the patch to spinning locks.
- *
- * held is used to keep lockdep happy, when lockdep is enabled
- * we set held to a blocking lock before we go around and
- * retake all the spinlocks in the path. You can safely use NULL
- * for held
- */
-noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
- struct extent_buffer *held, int held_rw)
-{
- int i;
-
- if (held) {
- btrfs_set_lock_blocking_rw(held, held_rw);
- if (held_rw == BTRFS_WRITE_LOCK)
- held_rw = BTRFS_WRITE_LOCK_BLOCKING;
- else if (held_rw == BTRFS_READ_LOCK)
- held_rw = BTRFS_READ_LOCK_BLOCKING;
- }
- btrfs_set_path_blocking(p);
-
- for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
- if (p->nodes[i] && p->locks[i]) {
- btrfs_clear_lock_blocking_rw(p->nodes[i], p->locks[i]);
- if (p->locks[i] == BTRFS_WRITE_LOCK_BLOCKING)
- p->locks[i] = BTRFS_WRITE_LOCK;
- else if (p->locks[i] == BTRFS_READ_LOCK_BLOCKING)
- p->locks[i] = BTRFS_READ_LOCK;
- }
- }
-
- if (held)
- btrfs_clear_lock_blocking_rw(held, held_rw);
-}
-
/* this also releases the path */
void btrfs_free_path(struct btrfs_path *p)
{
@@ -1429,7 +1393,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
}
}
- btrfs_clear_path_blocking(path, NULL, BTRFS_READ_LOCK);
btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
@@ -2611,7 +2574,6 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
btrfs_set_path_blocking(p);
reada_for_balance(fs_info, p, level);
sret = split_node(trans, root, p, level);
- btrfs_clear_path_blocking(p, NULL, 0);
BUG_ON(sret > 0);
if (sret) {
@@ -2632,7 +2594,6 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
btrfs_set_path_blocking(p);
reada_for_balance(fs_info, p, level);
sret = balance_level(trans, root, p, level);
- btrfs_clear_path_blocking(p, NULL, 0);
if (sret) {
ret = sret;
@@ -2928,7 +2889,10 @@ again:
}
cow_done:
p->nodes[level] = b;
- btrfs_clear_path_blocking(p, NULL, 0);
+ /*
+ * Leave path with blocking locks to avoid massive
+ * lock context switch, this is made on purpose.
+ */
/*
* we have a lock on b and as long as we aren't changing
@@ -3010,8 +2974,6 @@ cow_done:
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_lock(b);
- btrfs_clear_path_blocking(p, b,
- BTRFS_WRITE_LOCK);
}
p->locks[level] = BTRFS_WRITE_LOCK;
} else {
@@ -3019,8 +2981,6 @@ cow_done:
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
- btrfs_clear_path_blocking(p, b,
- BTRFS_READ_LOCK);
}
p->locks[level] = BTRFS_READ_LOCK;
}
@@ -3039,7 +2999,6 @@ cow_done:
btrfs_set_path_blocking(p);
err = split_leaf(trans, root, key,
p, ins_len, ret == 0);
- btrfs_clear_path_blocking(p, NULL, 0);
BUG_ON(err > 0);
if (err) {
@@ -3106,7 +3065,6 @@ again:
while (b) {
level = btrfs_header_level(b);
p->nodes[level] = b;
- btrfs_clear_path_blocking(p, NULL, 0);
/*
* we have a lock on b and as long as we aren't changing
@@ -3152,8 +3110,6 @@ again:
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
- btrfs_clear_path_blocking(p, b,
- BTRFS_READ_LOCK);
}
b = tree_mod_log_rewind(fs_info, p, b, time_seq);
if (!b) {
@@ -5358,7 +5314,6 @@ find_next_key:
path->locks[level - 1] = BTRFS_READ_LOCK;
path->nodes[level - 1] = cur;
unlock_up(path, level, 1, 0, NULL);
- btrfs_clear_path_blocking(path, NULL, 0);
}
out:
path->keep_locks = keep_locks;
@@ -5948,8 +5903,6 @@ again:
if (!ret) {
btrfs_set_path_blocking(path);
btrfs_tree_read_lock(next);
- btrfs_clear_path_blocking(path, next,
- BTRFS_READ_LOCK);
}
next_rw_lock = BTRFS_READ_LOCK;
}
@@ -5985,8 +5938,6 @@ again:
if (!ret) {
btrfs_set_path_blocking(path);
btrfs_tree_read_lock(next);
- btrfs_clear_path_blocking(path, next,
- BTRFS_READ_LOCK);
}
next_rw_lock = BTRFS_READ_LOCK;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ad071b77c04a..cabd87614a39 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2938,8 +2938,6 @@ void btrfs_release_path(struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_clear_path_blocking(struct btrfs_path *p,
- struct extent_buffer *held, int held_rw);
void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 9b1df3912260..baccc5215fa4 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -755,9 +755,6 @@ static int btrfs_batch_insert_items(struct btrfs_root *root,
i++;
}
- /* reset all the locked nodes in the patch to spinning locks. */
- btrfs_clear_path_blocking(path, NULL, 0);
-
/* insert the keys of the items */
setup_items_for_insert(root, path, keys, data_size,
total_data_size, total_size, nitems);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 5193218f5889..8b6b416e9ae1 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -434,6 +434,7 @@ static void ocfs2_remove_lockres_tracking(struct ocfs2_lock_res *res)
static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
{
res->l_lock_refresh = 0;
+ res->l_lock_wait = 0;
memset(&res->l_lock_prmode, 0, sizeof(struct ocfs2_lock_stats));
memset(&res->l_lock_exmode, 0, sizeof(struct ocfs2_lock_stats));
}
@@ -468,6 +469,8 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level,
if (ret)
stats->ls_fail++;
+
+ stats->ls_last = ktime_to_us(ktime_get_real());
}
static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
@@ -475,6 +478,21 @@ static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
lockres->l_lock_refresh++;
}
+static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres)
+{
+ struct ocfs2_mask_waiter *mw;
+
+ if (list_empty(&lockres->l_mask_waiters)) {
+ lockres->l_lock_wait = 0;
+ return;
+ }
+
+ mw = list_first_entry(&lockres->l_mask_waiters,
+ struct ocfs2_mask_waiter, mw_item);
+ lockres->l_lock_wait =
+ ktime_to_us(ktime_mono_to_real(mw->mw_lock_start));
+}
+
static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
{
mw->mw_lock_start = ktime_get();
@@ -490,6 +508,9 @@ static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res,
static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
{
}
+static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres)
+{
+}
static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
{
}
@@ -861,6 +882,7 @@ static void lockres_set_flags(struct ocfs2_lock_res *lockres,
list_del_init(&mw->mw_item);
mw->mw_status = 0;
complete(&mw->mw_complete);
+ ocfs2_track_lock_wait(lockres);
}
}
static void lockres_or_flags(struct ocfs2_lock_res *lockres, unsigned long or)
@@ -1372,6 +1394,7 @@ static void lockres_add_mask_waiter(struct ocfs2_lock_res *lockres,
list_add_tail(&mw->mw_item, &lockres->l_mask_waiters);
mw->mw_mask = mask;
mw->mw_goal = goal;
+ ocfs2_track_lock_wait(lockres);
}
/* returns 0 if the mw that was removed was already satisfied, -EBUSY
@@ -1388,6 +1411,7 @@ static int __lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
list_del_init(&mw->mw_item);
init_completion(&mw->mw_complete);
+ ocfs2_track_lock_wait(lockres);
}
return ret;
@@ -2825,6 +2849,8 @@ struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void)
kref_init(&dlm_debug->d_refcnt);
INIT_LIST_HEAD(&dlm_debug->d_lockres_tracking);
dlm_debug->d_locking_state = NULL;
+ dlm_debug->d_locking_filter = NULL;
+ dlm_debug->d_filter_secs = 0;
out:
return dlm_debug;
}
@@ -2915,17 +2941,43 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos)
* - Lock stats printed
* New in version 3
* - Max time in lock stats is in usecs (instead of nsecs)
+ * New in version 4
+ * - Add last pr/ex unlock times and first lock wait time in usecs
*/
-#define OCFS2_DLM_DEBUG_STR_VERSION 3
+#define OCFS2_DLM_DEBUG_STR_VERSION 4
static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
{
int i;
char *lvb;
struct ocfs2_lock_res *lockres = v;
+#ifdef CONFIG_OCFS2_FS_STATS
+ u64 now, last;
+ struct ocfs2_dlm_debug *dlm_debug =
+ ((struct ocfs2_dlm_seq_priv *)m->private)->p_dlm_debug;
+#endif
if (!lockres)
return -EINVAL;
+#ifdef CONFIG_OCFS2_FS_STATS
+ if (!lockres->l_lock_wait && dlm_debug->d_filter_secs) {
+ now = ktime_to_us(ktime_get_real());
+ if (lockres->l_lock_prmode.ls_last >
+ lockres->l_lock_exmode.ls_last)
+ last = lockres->l_lock_prmode.ls_last;
+ else
+ last = lockres->l_lock_exmode.ls_last;
+ /*
+ * Use d_filter_secs field to filter lock resources dump,
+ * the default d_filter_secs(0) value filters nothing,
+ * otherwise, only dump the last N seconds active lock
+ * resources.
+ */
+ if (div_u64(now - last, 1000000) > dlm_debug->d_filter_secs)
+ return 0;
+ }
+#endif
+
seq_printf(m, "0x%x\t", OCFS2_DLM_DEBUG_STR_VERSION);
if (lockres->l_type == OCFS2_LOCK_TYPE_DENTRY)
@@ -2967,6 +3019,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
# define lock_max_prmode(_l) ((_l)->l_lock_prmode.ls_max)
# define lock_max_exmode(_l) ((_l)->l_lock_exmode.ls_max)
# define lock_refresh(_l) ((_l)->l_lock_refresh)
+# define lock_last_prmode(_l) ((_l)->l_lock_prmode.ls_last)
+# define lock_last_exmode(_l) ((_l)->l_lock_exmode.ls_last)
+# define lock_wait(_l) ((_l)->l_lock_wait)
#else
# define lock_num_prmode(_l) (0)
# define lock_num_exmode(_l) (0)
@@ -2977,6 +3032,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
# define lock_max_prmode(_l) (0)
# define lock_max_exmode(_l) (0)
# define lock_refresh(_l) (0)
+# define lock_last_prmode(_l) (0ULL)
+# define lock_last_exmode(_l) (0ULL)
+# define lock_wait(_l) (0ULL)
#endif
/* The following seq_print was added in version 2 of this output */
seq_printf(m, "%u\t"
@@ -2987,7 +3045,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
"%llu\t"
"%u\t"
"%u\t"
- "%u\t",
+ "%u\t"
+ "%llu\t"
+ "%llu\t"
+ "%llu\t",
lock_num_prmode(lockres),
lock_num_exmode(lockres),
lock_num_prmode_failed(lockres),
@@ -2996,7 +3057,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
lock_total_exmode(lockres),
lock_max_prmode(lockres),
lock_max_exmode(lockres),
- lock_refresh(lockres));
+ lock_refresh(lockres),
+ lock_last_prmode(lockres),
+ lock_last_exmode(lockres),
+ lock_wait(lockres));
/* End the line */
seq_printf(m, "\n");
@@ -3067,6 +3131,17 @@ static int ocfs2_dlm_init_debug(struct ocfs2_super *osb)
goto out;
}
+ dlm_debug->d_locking_filter = debugfs_create_u32("locking_filter",
+ 0600,
+ osb->osb_debug_root,
+ &dlm_debug->d_filter_secs);
+ if (!dlm_debug->d_locking_filter) {
+ ret = -EINVAL;
+ mlog(ML_ERROR,
+ "Unable to create locking filter debugfs file.\n");
+ goto out;
+ }
+
ocfs2_get_dlm_debug(dlm_debug);
out:
return ret;
@@ -3078,6 +3153,7 @@ static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
if (dlm_debug) {
debugfs_remove(dlm_debug->d_locking_state);
+ debugfs_remove(dlm_debug->d_locking_filter);
ocfs2_put_dlm_debug(dlm_debug);
}
}
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 0c39d71c67a1..b7fd0681c5ed 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -162,6 +162,7 @@ struct ocfs2_lock_stats {
/* Storing max wait in usecs saves 24 bytes per inode */
u32 ls_max; /* Max wait in USEC */
+ u64 ls_last; /* Last unlock time in USEC */
};
#endif
@@ -203,6 +204,7 @@ struct ocfs2_lock_res {
#ifdef CONFIG_OCFS2_FS_STATS
struct ocfs2_lock_stats l_lock_prmode; /* PR mode stats */
u32 l_lock_refresh; /* Disk refreshes */
+ u64 l_lock_wait; /* First lock wait time */
struct ocfs2_lock_stats l_lock_exmode; /* EX mode stats */
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -234,6 +236,8 @@ struct ocfs2_orphan_scan {
struct ocfs2_dlm_debug {
struct kref d_refcnt;
struct dentry *d_locking_state;
+ struct dentry *d_locking_filter;
+ u32 d_filter_secs;
struct list_head d_lockres_tracking;
};
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 710a005c6b7a..89f7ac762803 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -462,7 +462,7 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
*
* Find the css for the (@task, @subsys_id) combination, increment a
* reference on and return it. This function is guaranteed to return a
- * valid css.
+ * valid css. The returned css may already have been offlined.
*/
static inline struct cgroup_subsys_state *
task_get_css(struct task_struct *task, int subsys_id)
@@ -472,7 +472,13 @@ task_get_css(struct task_struct *task, int subsys_id)
rcu_read_lock();
while (true) {
css = task_css(task, subsys_id);
- if (likely(css_tryget_online(css)))
+ /*
+ * Can't use css_tryget_online() here. A task which has
+ * PF_EXITING set may stay associated with an offline css.
+ * If such task calls this function, css_tryget_online()
+ * will keep failing.
+ */
+ if (likely(css_tryget(css)))
break;
cpu_relax();
}
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 5240eba8ea75..0828eaf9fc48 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -245,20 +245,12 @@ __ATTR(_name, 0644, show_##_name, store_##_name)
static struct freq_attr _name = \
__ATTR(_name, 0200, NULL, store_##_name)
-struct global_attr {
- struct attribute attr;
- ssize_t (*show)(struct kobject *kobj,
- struct attribute *attr, char *buf);
- ssize_t (*store)(struct kobject *a, struct attribute *b,
- const char *c, size_t count);
-};
-
#define define_one_global_ro(_name) \
-static struct global_attr _name = \
+static struct kobj_attribute _name = \
__ATTR(_name, 0444, show_##_name, NULL)
#define define_one_global_rw(_name) \
-static struct global_attr _name = \
+static struct kobj_attribute _name = \
__ATTR(_name, 0644, show_##_name, store_##_name)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f7b6cc667457..4467d542a8dd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1265,4 +1265,14 @@ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu)
}
#endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */
+#ifdef CONFIG_HAVE_KVM_NO_POLL
+/* Callback that tells if we must not poll */
+bool kvm_arch_no_poll(struct kvm_vcpu *vcpu);
+#else
+static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+#endif /* CONFIG_HAVE_KVM_NO_POLL */
+
#endif
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 9a532805364b..9a8d4ecdbc52 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -603,7 +603,7 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
/* if no digit is after '-', it's wrong*/
if (at_start && in_range)
return -EINVAL;
- if (!(a <= b) || !(used_size <= group_size))
+ if (!(a <= b) || group_size == 0 || !(used_size <= group_size))
return -EINVAL;
if (b >= nmaskbits)
return -ERANGE;
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index be7b4dd6b68d..355f2e90b72c 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -496,17 +496,18 @@ static bool sg_miter_get_next_page(struct sg_mapping_iter *miter)
{
if (!miter->__remaining) {
struct scatterlist *sg;
- unsigned long pgoffset;
if (!__sg_page_iter_next(&miter->piter))
return false;
sg = miter->piter.sg;
- pgoffset = miter->piter.sg_pgoffset;
- miter->__offset = pgoffset ? 0 : sg->offset;
+ miter->__offset = miter->piter.sg_pgoffset ? 0 : sg->offset;
+ miter->piter.sg_pgoffset += miter->__offset >> PAGE_SHIFT;
+ miter->__offset &= PAGE_SIZE - 1;
miter->__remaining = sg->offset + sg->length -
- (pgoffset << PAGE_SHIFT) - miter->__offset;
+ (miter->piter.sg_pgoffset << PAGE_SHIFT) -
+ miter->__offset;
miter->__remaining = min_t(unsigned long, miter->__remaining,
PAGE_SIZE - miter->__offset);
}
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index e454bd29671e..cf95de7e1489 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -3793,6 +3793,8 @@ static void batadv_tt_purge(struct work_struct *work)
void batadv_tt_free(struct batadv_priv *bat_priv)
{
+ batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_ROAM, 1);
+
batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_TT, 1);
batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_TT, 1);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 54ebe68ead43..0fb534943da5 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -907,8 +907,13 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
if (rc >= 0)
info.n_priv_flags = rc;
}
- if (ops->get_regs_len)
- info.regdump_len = ops->get_regs_len(dev);
+ if (ops->get_regs_len) {
+ int ret = ops->get_regs_len(dev);
+
+ if (ret > 0)
+ info.regdump_len = ret;
+ }
+
if (ops->get_eeprom_len)
info.eedump_len = ops->get_eeprom_len(dev);
@@ -1409,6 +1414,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
return -EFAULT;
reglen = ops->get_regs_len(dev);
+ if (reglen <= 0)
+ return reglen;
+
if (regs.len > reglen)
regs.len = reglen;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 3b2034f6d49d..2e9401312eb2 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3149,7 +3149,13 @@ static int pktgen_wait_thread_run(struct pktgen_thread *t)
{
while (thread_is_running(t)) {
+ /* note: 't' will still be around even after the unlock/lock
+ * cycle because pktgen_thread threads are only cleared at
+ * net exit
+ */
+ mutex_unlock(&pktgen_thread_lock);
msleep_interruptible(100);
+ mutex_lock(&pktgen_thread_lock);
if (signal_pending(current))
goto signal;
@@ -3164,6 +3170,10 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
struct pktgen_thread *t;
int sig = 1;
+ /* prevent from racing with rmmod */
+ if (!try_module_get(THIS_MODULE))
+ return sig;
+
mutex_lock(&pktgen_thread_lock);
list_for_each_entry(t, &pn->pktgen_threads, th_list) {
@@ -3177,6 +3187,7 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn)
t->control |= (T_STOP);
mutex_unlock(&pktgen_thread_lock);
+ module_put(THIS_MODULE);
return sig;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 75a2b0a665ac..d6f437883d13 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2823,9 +2823,9 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
- if (WARN_ON(!tp->packets_out && tp->sacked_out))
+ if (!tp->packets_out && tp->sacked_out)
tp->sacked_out = 0;
- if (WARN_ON(!tp->sacked_out && tp->fackets_out))
+ if (!tp->sacked_out && tp->fackets_out)
tp->fackets_out = 0;
/* Now state machine starts.
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e0560c41e371..570c5353cb85 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -934,19 +934,22 @@ static unsigned int early_drop_list(struct net *net,
return drops;
}
-static noinline int early_drop(struct net *net, unsigned int _hash)
+static noinline int early_drop(struct net *net, unsigned int hash)
{
- unsigned int i;
+ unsigned int i, bucket;
for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
struct hlist_nulls_head *ct_hash;
- unsigned int hash, hsize, drops;
+ unsigned int hsize, drops;
rcu_read_lock();
nf_conntrack_get_ht(&ct_hash, &hsize);
- hash = reciprocal_scale(_hash++, hsize);
+ if (!i)
+ bucket = reciprocal_scale(hash, hsize);
+ else
+ bucket = (bucket + 1) % hsize;
- drops = early_drop_list(net, &ct_hash[hash]);
+ drops = early_drop_list(net, &ct_hash[bucket]);
rcu_read_unlock();
if (drops) {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2d3f6d177132..02241f3d1020 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3390,20 +3390,29 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name) {
+ int copy_len;
+
/* If the address length field is there to be filled
* in, we fill it in now.
*/
if (sock->type == SOCK_PACKET) {
__sockaddr_check_size(sizeof(struct sockaddr_pkt));
msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ copy_len = msg->msg_namelen;
} else {
struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
msg->msg_namelen = sll->sll_halen +
offsetof(struct sockaddr_ll, sll_addr);
+ copy_len = msg->msg_namelen;
+ if (msg->msg_namelen < sizeof(struct sockaddr_ll)) {
+ memset(msg->msg_name +
+ offsetof(struct sockaddr_ll, sll_addr),
+ 0, sizeof(sll->sll_addr));
+ msg->msg_namelen = sizeof(struct sockaddr_ll);
+ }
}
- memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
- msg->msg_namelen);
+ memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
}
if (pkt_sk(sk)->auxdata) {
@@ -4345,7 +4354,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
req3->tp_sizeof_priv ||
req3->tp_feature_req_word) {
err = -EINVAL;
- goto out;
+ goto out_free_pg_vec;
}
}
break;
@@ -4409,6 +4418,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
prb_shutdown_retire_blk_timer(po, rb_queue);
}
+out_free_pg_vec:
if (pg_vec)
free_pg_vec(pg_vec, order, req->tp_block_nr);
out:
diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 48332a6ed738..d290416e79e9 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -61,6 +61,7 @@ static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev,
pool->fmr_attr.max_pages);
if (IS_ERR(frmr->mr)) {
pr_warn("RDS/IB: %s failed to allocate MR", __func__);
+ err = PTR_ERR(frmr->mr);
goto out_no_cigar;
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 85ec5460e6b2..c96d129a0959 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -745,14 +745,6 @@ static struct proto unix_proto = {
.obj_size = sizeof(struct unix_sock),
};
-/*
- * AF_UNIX sockets do not interact with hardware, hence they
- * dont trigger interrupts - so it's safe for them to have
- * bh-unsafe locking for their sk_receive_queue.lock. Split off
- * this special lock-class by reinitializing the spinlock key:
- */
-static struct lock_class_key af_unix_sk_receive_queue_lock_key;
-
static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
{
struct sock *sk = NULL;
@@ -767,8 +759,6 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
goto out;
sock_init_data(sock, sk);
- lockdep_set_class(&sk->sk_receive_queue.lock,
- &af_unix_sk_receive_queue_lock_key);
sk->sk_allocation = GFP_KERNEL_ACCOUNT;
sk->sk_write_space = unix_write_space;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1bec4fbe5730..1866184111d3 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3258,6 +3258,7 @@ static void alc256_init(struct hda_codec *codec)
alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x4); /* Hight power */
alc_update_coefex_idx(codec, 0x53, 0x02, 0x8000, 1 << 15); /* Clear bit */
alc_update_coefex_idx(codec, 0x53, 0x02, 0x8000, 0 << 15);
+ alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/
}
static void alc256_shutup(struct hda_codec *codec)
@@ -7686,7 +7687,6 @@ static int patch_alc269(struct hda_codec *codec)
spec->shutup = alc256_shutup;
spec->init_hook = alc256_init;
spec->gen.mixer_nid = 0; /* ALC256 does not have any loopback mixer path */
- alc_update_coef_idx(codec, 0x36, 1 << 13, 1 << 5); /* Switch pcbeep path to Line in path*/
break;
case 0x10ec0257:
spec->codec_variant = ALC269_TYPE_ALC257;
diff --git a/sound/soc/codecs/cs4265.c b/sound/soc/codecs/cs4265.c
index 6e8eb1f5a041..bed64723e5d9 100644
--- a/sound/soc/codecs/cs4265.c
+++ b/sound/soc/codecs/cs4265.c
@@ -60,7 +60,7 @@ static const struct reg_default cs4265_reg_defaults[] = {
static bool cs4265_readable_register(struct device *dev, unsigned int reg)
{
switch (reg) {
- case CS4265_CHIP_ID ... CS4265_SPDIF_CTL2:
+ case CS4265_CHIP_ID ... CS4265_MAX_REGISTER:
return true;
default:
return false;
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index ecab7d71ca74..9ac056ad9e36 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -1924,6 +1924,21 @@ static int max98090_configure_dmic(struct max98090_priv *max98090,
return 0;
}
+static int max98090_dai_startup(struct snd_pcm_substream *substream,
+ struct snd_soc_dai *dai)
+{
+ struct snd_soc_component *component = dai->component;
+ struct max98090_priv *max98090 = snd_soc_component_get_drvdata(component);
+ unsigned int fmt = max98090->dai_fmt;
+
+ /* Remove 24-bit format support if it is not in right justified mode. */
+ if ((fmt & SND_SOC_DAIFMT_FORMAT_MASK) != SND_SOC_DAIFMT_RIGHT_J) {
+ substream->runtime->hw.formats = SNDRV_PCM_FMTBIT_S16_LE;
+ snd_pcm_hw_constraint_msbits(substream->runtime, 0, 16, 16);
+ }
+ return 0;
+}
+
static int max98090_dai_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params,
struct snd_soc_dai *dai)
@@ -2331,6 +2346,7 @@ EXPORT_SYMBOL_GPL(max98090_mic_detect);
#define MAX98090_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE)
static const struct snd_soc_dai_ops max98090_dai_ops = {
+ .startup = max98090_dai_startup,
.set_sysclk = max98090_dai_set_sysclk,
.set_fmt = max98090_dai_set_fmt,
.set_tdm_slot = max98090_set_tdm_slot,
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 10e6b9877ac6..bedf08edb91b 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -2233,7 +2233,8 @@ int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream)
if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
- (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND))
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND) &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
continue;
dev_dbg(be->dev, "ASoC: prepare BE %s\n",
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index b0cc1a34db27..ac1568a6fac0 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -50,3 +50,6 @@ config KVM_COMPAT
config HAVE_KVM_IRQ_BYPASS
bool
+
+config HAVE_KVM_NO_POLL
+ bool
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 3649baa0b666..0ed72fd01de6 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2205,7 +2205,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
u64 block_ns;
start = cur = ktime_get();
- if (vcpu->halt_poll_ns) {
+ if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) {
ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
++vcpu->stat.halt_attempted_poll;