Re: Linux 4.14.25

From: Greg KH
Date: Fri Mar 09 2018 - 11:54:10 EST


diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 77f4de59dc9c..d499676890d8 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -508,7 +508,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
min: Minimal size of receive buffer used by TCP sockets.
It is guaranteed to each TCP socket, even under moderate memory
pressure.
- Default: 1 page
+ Default: 4K

default: initial size of receive buffer used by TCP sockets.
This value overrides net.core.rmem_default used by other protocols.
@@ -666,7 +666,7 @@ tcp_window_scaling - BOOLEAN
tcp_wmem - vector of 3 INTEGERs: min, default, max
min: Amount of memory reserved for send buffers for TCP sockets.
Each TCP socket has rights to use it due to fact of its birth.
- Default: 1 page
+ Default: 4K

default: initial size of send buffer used by TCP sockets. This
value overrides net.core.wmem_default used by other protocols.
diff --git a/Makefile b/Makefile
index 38acc6047d7d..0fdae0f455ef 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 14
-SUBLEVEL = 24
+SUBLEVEL = 25
EXTRAVERSION =
NAME = Petit Gorille

diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 4f2c5ec75714..e262fa9ef334 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -97,6 +97,8 @@
};

&i2c1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&i2c1_pins>;
clock-frequency = <2600000>;

twl: twl@48 {
@@ -215,7 +217,12 @@
>;
};

-
+ i2c1_pins: pinmux_i2c1_pins {
+ pinctrl-single,pins = <
+ OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */
+ OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */
+ >;
+ };
};

&omap3_pmx_wkup {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 6d89736c7b44..cf22b35f0a28 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -104,6 +104,8 @@
};

&i2c1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&i2c1_pins>;
clock-frequency = <2600000>;

twl: twl@48 {
@@ -211,6 +213,12 @@
OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0) /* hsusb0_data7.hsusb0_data7 */
>;
};
+ i2c1_pins: pinmux_i2c1_pins {
+ pinctrl-single,pins = <
+ OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */
+ OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */
+ >;
+ };
};

&uart2 {
diff --git a/arch/arm/boot/dts/rk3288-phycore-som.dtsi b/arch/arm/boot/dts/rk3288-phycore-som.dtsi
index 99cfae875e12..5eae4776ffde 100644
--- a/arch/arm/boot/dts/rk3288-phycore-som.dtsi
+++ b/arch/arm/boot/dts/rk3288-phycore-som.dtsi
@@ -110,26 +110,6 @@
};
};

-&cpu0 {
- cpu0-supply = <&vdd_cpu>;
- operating-points = <
- /* KHz uV */
- 1800000 1400000
- 1608000 1350000
- 1512000 1300000
- 1416000 1200000
- 1200000 1100000
- 1008000 1050000
- 816000 1000000
- 696000 950000
- 600000 900000
- 408000 900000
- 312000 900000
- 216000 900000
- 126000 900000
- >;
-};
-
&emmc {
status = "okay";
bus-width = <8>;
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 5638ce0c9524..63d6b404d88e 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -7,6 +7,8 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING

KVM=../../../../virt/kvm

+CFLAGS_ARMV7VE :=$(call cc-option, -march=armv7ve)
+
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
@@ -15,7 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o
obj-$(CONFIG_KVM_ARM_HOST) += vfp.o
obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o
+CFLAGS_banked-sr.o += $(CFLAGS_ARMV7VE)
+
obj-$(CONFIG_KVM_ARM_HOST) += entry.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
obj-$(CONFIG_KVM_ARM_HOST) += switch.o
+CFLAGS_switch.o += $(CFLAGS_ARMV7VE)
obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c
index 111bda8cdebd..be4b8b0a40ad 100644
--- a/arch/arm/kvm/hyp/banked-sr.c
+++ b/arch/arm/kvm/hyp/banked-sr.c
@@ -20,6 +20,10 @@

#include <asm/kvm_hyp.h>

+/*
+ * gcc before 4.9 doesn't understand -march=armv7ve, so we have to
+ * trick the assembler.
+ */
__asm__(".arch_extension virt");

void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt)
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 9b49867154bf..63fa79f9f121 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -42,7 +42,7 @@ config MACH_ARMADA_375
depends on ARCH_MULTI_V7
select ARMADA_370_XP_IRQ
select ARM_ERRATA_720789
- select ARM_ERRATA_753970
+ select PL310_ERRATA_753970
select ARM_GIC
select ARMADA_375_CLK
select HAVE_ARM_SCU
@@ -58,7 +58,7 @@ config MACH_ARMADA_38X
bool "Marvell Armada 380/385 boards"
depends on ARCH_MULTI_V7
select ARM_ERRATA_720789
- select ARM_ERRATA_753970
+ select PL310_ERRATA_753970
select ARM_GIC
select ARM_GLOBAL_TIMER
select CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index aff6994950ba..a2399fd66e97 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -472,28 +472,27 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data,
/*****************************************************************************
* Ethernet switch
****************************************************************************/
-static __initconst const char *orion_ge00_mvmdio_bus_name = "orion-mii";
-static __initdata struct mdio_board_info
- orion_ge00_switch_board_info;
+static __initdata struct mdio_board_info orion_ge00_switch_board_info = {
+ .bus_id = "orion-mii",
+ .modalias = "mv88e6085",
+};

void __init orion_ge00_switch_init(struct dsa_chip_data *d)
{
- struct mdio_board_info *bd;
unsigned int i;

if (!IS_BUILTIN(CONFIG_PHYLIB))
return;

- for (i = 0; i < ARRAY_SIZE(d->port_names); i++)
- if (!strcmp(d->port_names[i], "cpu"))
+ for (i = 0; i < ARRAY_SIZE(d->port_names); i++) {
+ if (!strcmp(d->port_names[i], "cpu")) {
+ d->netdev[i] = &orion_ge00.dev;
break;
+ }
+ }

- bd = &orion_ge00_switch_board_info;
- bd->bus_id = orion_ge00_mvmdio_bus_name;
- bd->mdio_addr = d->sw_addr;
- d->netdev[i] = &orion_ge00.dev;
- strcpy(bd->modalias, "mv88e6085");
- bd->platform_data = d;
+ orion_ge00_switch_board_info.mdio_addr = d->sw_addr;
+ orion_ge00_switch_board_info.platform_data = d;

mdiobus_register_board_info(&orion_ge00_switch_board_info, 1);
}
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 3742508cc534..bd5ce31936f5 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -26,6 +26,7 @@ void flush_user_icache_range_asm(unsigned long, unsigned long);
void flush_kernel_icache_range_asm(unsigned long, unsigned long);
void flush_user_dcache_range_asm(unsigned long, unsigned long);
void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
+void purge_kernel_dcache_range_asm(unsigned long, unsigned long);
void flush_kernel_dcache_page_asm(void *);
void flush_kernel_icache_page(void *);

diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 0e6ab6e4a4e9..2dbe5580a1a4 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -316,6 +316,8 @@ extern int _parisc_requires_coherency;
#define parisc_requires_coherency() (0)
#endif

+extern int running_on_qemu;
+
#endif /* __ASSEMBLY__ */

#endif /* __ASM_PARISC_PROCESSOR_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 19c0c141bc3f..79089778725b 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -465,10 +465,10 @@ EXPORT_SYMBOL(copy_user_page);
int __flush_tlb_range(unsigned long sid, unsigned long start,
unsigned long end)
{
- unsigned long flags, size;
+ unsigned long flags;

- size = (end - start);
- if (size >= parisc_tlb_flush_threshold) {
+ if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+ end - start >= parisc_tlb_flush_threshold) {
flush_tlb_all();
return 1;
}
@@ -539,13 +539,11 @@ void flush_cache_mm(struct mm_struct *mm)
struct vm_area_struct *vma;
pgd_t *pgd;

- /* Flush the TLB to avoid speculation if coherency is required. */
- if (parisc_requires_coherency())
- flush_tlb_all();
-
/* Flushing the whole cache on each cpu takes forever on
rp3440, etc. So, avoid it if the mm isn't too big. */
- if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
+ if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+ mm_total_size(mm) >= parisc_cache_flush_threshold) {
+ flush_tlb_all();
flush_cache_all();
return;
}
@@ -553,9 +551,9 @@ void flush_cache_mm(struct mm_struct *mm)
if (mm->context == mfsp(3)) {
for (vma = mm->mmap; vma; vma = vma->vm_next) {
flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
- if ((vma->vm_flags & VM_EXEC) == 0)
- continue;
- flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+ if (vma->vm_flags & VM_EXEC)
+ flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+ flush_tlb_range(vma, vma->vm_start, vma->vm_end);
}
return;
}
@@ -581,14 +579,9 @@ void flush_cache_mm(struct mm_struct *mm)
void flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- BUG_ON(!vma->vm_mm->context);
-
- /* Flush the TLB to avoid speculation if coherency is required. */
- if (parisc_requires_coherency())
+ if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+ end - start >= parisc_cache_flush_threshold) {
flush_tlb_range(vma, start, end);
-
- if ((end - start) >= parisc_cache_flush_threshold
- || vma->vm_mm->context != mfsp(3)) {
flush_cache_all();
return;
}
@@ -596,6 +589,7 @@ void flush_cache_range(struct vm_area_struct *vma,
flush_user_dcache_range_asm(start, end);
if (vma->vm_flags & VM_EXEC)
flush_user_icache_range_asm(start, end);
+ flush_tlb_range(vma, start, end);
}

void
@@ -604,8 +598,7 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
BUG_ON(!vma->vm_mm->context);

if (pfn_valid(pfn)) {
- if (parisc_requires_coherency())
- flush_tlb_page(vma, vmaddr);
+ flush_tlb_page(vma, vmaddr);
__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
}
}
@@ -613,21 +606,33 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
void flush_kernel_vmap_range(void *vaddr, int size)
{
unsigned long start = (unsigned long)vaddr;
+ unsigned long end = start + size;

- if ((unsigned long)size > parisc_cache_flush_threshold)
+ if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+ (unsigned long)size >= parisc_cache_flush_threshold) {
+ flush_tlb_kernel_range(start, end);
flush_data_cache();
- else
- flush_kernel_dcache_range_asm(start, start + size);
+ return;
+ }
+
+ flush_kernel_dcache_range_asm(start, end);
+ flush_tlb_kernel_range(start, end);
}
EXPORT_SYMBOL(flush_kernel_vmap_range);

void invalidate_kernel_vmap_range(void *vaddr, int size)
{
unsigned long start = (unsigned long)vaddr;
+ unsigned long end = start + size;

- if ((unsigned long)size > parisc_cache_flush_threshold)
+ if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+ (unsigned long)size >= parisc_cache_flush_threshold) {
+ flush_tlb_kernel_range(start, end);
flush_data_cache();
- else
- flush_kernel_dcache_range_asm(start, start + size);
+ return;
+ }
+
+ purge_kernel_dcache_range_asm(start, end);
+ flush_tlb_kernel_range(start, end);
}
EXPORT_SYMBOL(invalidate_kernel_vmap_range);
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 2d40c4ff3f69..67b0f7532e83 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -1110,6 +1110,28 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
.procend
ENDPROC_CFI(flush_kernel_dcache_range_asm)

+ENTRY_CFI(purge_kernel_dcache_range_asm)
+ .proc
+ .callinfo NO_CALLS
+ .entry
+
+ ldil L%dcache_stride, %r1
+ ldw R%dcache_stride(%r1), %r23
+ ldo -1(%r23), %r21
+ ANDCM %r26, %r21, %r26
+
+1: cmpb,COND(<<),n %r26, %r25,1b
+ pdc,m %r23(%r26)
+
+ sync
+ syncdma
+ bv %r0(%r2)
+ nop
+ .exit
+
+ .procend
+ENDPROC_CFI(purge_kernel_dcache_range_asm)
+
ENTRY_CFI(flush_user_icache_range_asm)
.proc
.callinfo NO_CALLS
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 4b8fd6dc22da..f7e684560186 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -76,10 +76,10 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
next_tick = cpuinfo->it_value;

/* Calculate how many ticks have elapsed. */
+ now = mfctl(16);
do {
++ticks_elapsed;
next_tick += cpt;
- now = mfctl(16);
} while (next_tick - now > cpt);

/* Store (in CR16 cycles) up to when we are accounting right now. */
@@ -103,16 +103,17 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
* if one or the other wrapped. If "now" is "bigger" we'll end up
* with a very large unsigned number.
*/
- while (next_tick - mfctl(16) > cpt)
+ now = mfctl(16);
+ while (next_tick - now > cpt)
next_tick += cpt;

/* Program the IT when to deliver the next interrupt.
* Only bottom 32-bits of next_tick are writable in CR16!
* Timer interrupt will be delivered at least a few hundred cycles
- * after the IT fires, so if we are too close (<= 500 cycles) to the
+ * after the IT fires, so if we are too close (<= 8000 cycles) to the
* next cycle, simply skip it.
*/
- if (next_tick - mfctl(16) <= 500)
+ if (next_tick - now <= 8000)
next_tick += cpt;
mtctl(next_tick, 16);

@@ -248,7 +249,7 @@ static int __init init_cr16_clocksource(void)
* different sockets, so mark them unstable and lower rating on
* multi-socket SMP systems.
*/
- if (num_online_cpus() > 1) {
+ if (num_online_cpus() > 1 && !running_on_qemu) {
int cpu;
unsigned long cpu0_loc;
cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index a832ad031cee..5185be314661 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -173,8 +173,15 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)

static int ckc_irq_pending(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm))
+ const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+ const u64 ckc = vcpu->arch.sie_block->ckc;
+
+ if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) {
+ if ((s64)ckc >= (s64)now)
+ return 0;
+ } else if (ckc >= now) {
return 0;
+ }
return ckc_interrupts_enabled(vcpu);
}

@@ -1004,13 +1011,19 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)

static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
{
- u64 now, cputm, sltime = 0;
+ const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+ const u64 ckc = vcpu->arch.sie_block->ckc;
+ u64 cputm, sltime = 0;

if (ckc_interrupts_enabled(vcpu)) {
- now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
- sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
- /* already expired or overflow? */
- if (!sltime || vcpu->arch.sie_block->ckc <= now)
+ if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) {
+ if ((s64)now < (s64)ckc)
+ sltime = tod_to_ns((s64)ckc - (s64)now);
+ } else if (now < ckc) {
+ sltime = tod_to_ns(ckc - now);
+ }
+ /* already expired */
+ if (!sltime)
return 0;
if (cpu_timer_interrupts_enabled(vcpu)) {
cputm = kvm_s390_get_cpu_timer(vcpu);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6e3d80b2048e..f4f12ecd0cec 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -169,6 +169,28 @@ int kvm_arch_hardware_enable(void)
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long end);

+static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta)
+{
+ u8 delta_idx = 0;
+
+ /*
+ * The TOD jumps by delta, we have to compensate this by adding
+ * -delta to the epoch.
+ */
+ delta = -delta;
+
+ /* sign-extension - we're adding to signed values below */
+ if ((s64)delta < 0)
+ delta_idx = -1;
+
+ scb->epoch += delta;
+ if (scb->ecd & ECD_MEF) {
+ scb->epdx += delta_idx;
+ if (scb->epoch < delta)
+ scb->epdx += 1;
+ }
+}
+
/*
* This callback is executed during stop_machine(). All CPUs are therefore
* temporarily stopped. In order not to change guest behavior, we have to
@@ -184,13 +206,17 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
unsigned long long *delta = v;

list_for_each_entry(kvm, &vm_list, vm_list) {
- kvm->arch.epoch -= *delta;
kvm_for_each_vcpu(i, vcpu, kvm) {
- vcpu->arch.sie_block->epoch -= *delta;
+ kvm_clock_sync_scb(vcpu->arch.sie_block, *delta);
+ if (i == 0) {
+ kvm->arch.epoch = vcpu->arch.sie_block->epoch;
+ kvm->arch.epdx = vcpu->arch.sie_block->epdx;
+ }
if (vcpu->arch.cputm_enabled)
vcpu->arch.cputm_start += *delta;
if (vcpu->arch.vsie_block)
- vcpu->arch.vsie_block->epoch -= *delta;
+ kvm_clock_sync_scb(vcpu->arch.vsie_block,
+ *delta);
}
}
return NOTIFY_OK;
@@ -888,12 +914,9 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
return -EFAULT;

- if (test_kvm_facility(kvm, 139))
- kvm_s390_set_tod_clock_ext(kvm, &gtod);
- else if (gtod.epoch_idx == 0)
- kvm_s390_set_tod_clock(kvm, gtod.tod);
- else
+ if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)
return -EINVAL;
+ kvm_s390_set_tod_clock(kvm, &gtod);

VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
gtod.epoch_idx, gtod.tod);
@@ -918,13 +941,14 @@ static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)

static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
- u64 gtod;
+ struct kvm_s390_vm_tod_clock gtod = { 0 };

- if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
+ if (copy_from_user(&gtod.tod, (void __user *)attr->addr,
+ sizeof(gtod.tod)))
return -EFAULT;

- kvm_s390_set_tod_clock(kvm, gtod);
- VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod);
+ kvm_s390_set_tod_clock(kvm, &gtod);
+ VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);
return 0;
}

@@ -2359,6 +2383,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
mutex_lock(&vcpu->kvm->lock);
preempt_disable();
vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
+ vcpu->arch.sie_block->epdx = vcpu->kvm->arch.epdx;
preempt_enable();
mutex_unlock(&vcpu->kvm->lock);
if (!kvm_is_ucontrol(vcpu->kvm)) {
@@ -2945,8 +2970,8 @@ static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
return 0;
}

-void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
- const struct kvm_s390_vm_tod_clock *gtod)
+void kvm_s390_set_tod_clock(struct kvm *kvm,
+ const struct kvm_s390_vm_tod_clock *gtod)
{
struct kvm_vcpu *vcpu;
struct kvm_s390_tod_clock_ext htod;
@@ -2958,10 +2983,12 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
get_tod_clock_ext((char *)&htod);

kvm->arch.epoch = gtod->tod - htod.tod;
- kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
-
- if (kvm->arch.epoch > gtod->tod)
- kvm->arch.epdx -= 1;
+ kvm->arch.epdx = 0;
+ if (test_kvm_facility(kvm, 139)) {
+ kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
+ if (kvm->arch.epoch > gtod->tod)
+ kvm->arch.epdx -= 1;
+ }

kvm_s390_vcpu_block_all(kvm);
kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -2974,22 +3001,6 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
mutex_unlock(&kvm->lock);
}

-void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod)
-{
- struct kvm_vcpu *vcpu;
- int i;
-
- mutex_lock(&kvm->lock);
- preempt_disable();
- kvm->arch.epoch = tod - get_tod_clock();
- kvm_s390_vcpu_block_all(kvm);
- kvm_for_each_vcpu(i, vcpu, kvm)
- vcpu->arch.sie_block->epoch = kvm->arch.epoch;
- kvm_s390_vcpu_unblock_all(kvm);
- preempt_enable();
- mutex_unlock(&kvm->lock);
-}
-
/**
* kvm_arch_fault_in_page - fault-in guest page if necessary
* @vcpu: The corresponding virtual cpu
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 9f8fdd7b2311..e22d94f494a7 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -272,9 +272,8 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
int handle_sthyi(struct kvm_vcpu *vcpu);

/* implemented in kvm-s390.c */
-void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
- const struct kvm_s390_vm_tod_clock *gtod);
-void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod);
+void kvm_s390_set_tod_clock(struct kvm *kvm,
+ const struct kvm_s390_vm_tod_clock *gtod);
long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 7bd3a59232f0..734283a21677 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -84,9 +84,10 @@ int kvm_s390_handle_e3(struct kvm_vcpu *vcpu)
/* Handle SCK (SET CLOCK) interception */
static int handle_set_clock(struct kvm_vcpu *vcpu)
{
+ struct kvm_s390_vm_tod_clock gtod = { 0 };
int rc;
u8 ar;
- u64 op2, val;
+ u64 op2;

if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
@@ -94,12 +95,12 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
op2 = kvm_s390_get_base_disp_s(vcpu, &ar);
if (op2 & 7) /* Operand must be on a doubleword boundary */
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- rc = read_guest(vcpu, op2, ar, &val, sizeof(val));
+ rc = read_guest(vcpu, op2, ar, &gtod.tod, sizeof(gtod.tod));
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);

- VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val);
- kvm_s390_set_tod_clock(vcpu->kvm, val);
+ VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod);
+ kvm_s390_set_tod_clock(vcpu->kvm, &gtod);

kvm_s390_set_psw_cc(vcpu, 0);
return 0;
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 8b8f1f14a0bf..5c790e93657d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -350,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
{
pmdval_t v = native_pmd_val(pmd);

- return __pmd(v | set);
+ return native_make_pmd(v | set);
}

static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
{
pmdval_t v = native_pmd_val(pmd);

- return __pmd(v & ~clear);
+ return native_make_pmd(v & ~clear);
}

static inline pmd_t pmd_mkold(pmd_t pmd)
@@ -409,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
{
pudval_t v = native_pud_val(pud);

- return __pud(v | set);
+ return native_make_pud(v | set);
}

static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
{
pudval_t v = native_pud_val(pud);

- return __pud(v & ~clear);
+ return native_make_pud(v & ~clear);
}

static inline pud_t pud_mkold(pud_t pud)
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index e55466760ff8..b3ec519e3982 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,6 +32,7 @@ extern pmd_t initial_pg_pmd[];
static inline void pgtable_cache_init(void) { }
static inline void check_pgt_cache(void) { }
void paging_init(void);
+void sync_initial_page_table(void);

/*
* Define this if things work differently on an i386 and an i486:
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 81462e9a34f6..1149d2112b2e 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -28,6 +28,7 @@ extern pgd_t init_top_pgt[];
#define swapper_pg_dir init_top_pgt

extern void paging_init(void);
+static inline void sync_initial_page_table(void) { }

#define pte_ERROR(e) \
pr_err("%s:%d: bad pte %p(%016lx)\n", \
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 3696398a9475..246f15b4e64c 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -323,6 +323,11 @@ static inline pudval_t native_pud_val(pud_t pud)
#else
#include <asm-generic/pgtable-nopud.h>

+static inline pud_t native_make_pud(pudval_t val)
+{
+ return (pud_t) { .p4d.pgd = native_make_pgd(val) };
+}
+
static inline pudval_t native_pud_val(pud_t pud)
{
return native_pgd_val(pud.p4d.pgd);
@@ -344,6 +349,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
#else
#include <asm-generic/pgtable-nopmd.h>

+static inline pmd_t native_make_pmd(pmdval_t val)
+{
+ return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) };
+}
+
static inline pmdval_t native_pmd_val(pmd_t pmd)
{
return native_pgd_val(pmd.pud.p4d.pgd);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c54361a22f59..efbcf5283520 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1238,20 +1238,13 @@ void __init setup_arch(char **cmdline_p)

kasan_init();

-#ifdef CONFIG_X86_32
- /* sync back kernel address range */
- clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- KERNEL_PGD_PTRS);
-
/*
- * sync back low identity map too. It is used for example
- * in the 32-bit EFI stub.
+ * Sync back kernel address range.
+ *
+ * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+ * this call?
*/
- clone_pgd_range(initial_page_table,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+ sync_initial_page_table();

tboot_probe();

diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 497aa766fab3..ea554f812ee1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void)
/* Setup cpu initialized, callin, callout masks */
setup_cpu_local_masks();

-#ifdef CONFIG_X86_32
/*
* Sync back kernel address range again. We already did this in
* setup_arch(), but percpu data also needs to be available in
* the smpboot asm. We can't reliably pick up percpu mappings
* using vmalloc_fault(), because exception dispatch needs
* percpu data.
+ *
+ * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+ * this call?
*/
- clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- KERNEL_PGD_PTRS);
-
- /*
- * sync back low identity map too. It is used for example
- * in the 32-bit EFI stub.
- */
- clone_pgd_range(initial_page_table,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+ sync_initial_page_table();
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ef03efba1c23..8cfdb6484fd0 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1944,14 +1944,13 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)

void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
{
- struct kvm_lapic *apic;
+ struct kvm_lapic *apic = vcpu->arch.apic;
int i;

- apic_debug("%s\n", __func__);
+ if (!apic)
+ return;

- ASSERT(vcpu);
- apic = vcpu->arch.apic;
- ASSERT(apic != NULL);
+ apic_debug("%s\n", __func__);

/* Stop the timer in case it's a reset to an active apic */
hrtimer_cancel(&apic->lapic_timer.timer);
@@ -2107,7 +2106,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
*/
vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
- kvm_lapic_reset(vcpu, false);
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);

return 0;
@@ -2511,7 +2509,6 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)

pe = xchg(&apic->pending_events, 0);
if (test_bit(KVM_APIC_INIT, &pe)) {
- kvm_lapic_reset(vcpu, true);
kvm_vcpu_reset(vcpu, true);
if (kvm_vcpu_is_bsp(apic->vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ca000fc644bc..2b6f8a4f2731 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -150,6 +150,20 @@ module_param(dbg, bool, 0644);
/* make pte_list_desc fit well in cache line */
#define PTE_LIST_EXT 3

+/*
+ * Return values of handle_mmio_page_fault and mmu.page_fault:
+ * RET_PF_RETRY: let CPU fault again on the address.
+ * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
+ *
+ * For handle_mmio_page_fault only:
+ * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
+ */
+enum {
+ RET_PF_RETRY = 0,
+ RET_PF_EMULATE = 1,
+ RET_PF_INVALID = 2,
+};
+
struct pte_list_desc {
u64 *sptes[PTE_LIST_EXT];
struct pte_list_desc *more;
@@ -2794,13 +2808,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
return ret;
}

-static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
- int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn,
- bool speculative, bool host_writable)
+static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
+ int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn,
+ bool speculative, bool host_writable)
{
int was_rmapped = 0;
int rmap_count;
- bool emulate = false;
+ int ret = RET_PF_RETRY;

pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
*sptep, write_fault, gfn);
@@ -2830,12 +2844,12 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative,
true, host_writable)) {
if (write_fault)
- emulate = true;
+ ret = RET_PF_EMULATE;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}

if (unlikely(is_mmio_spte(*sptep)))
- emulate = true;
+ ret = RET_PF_EMULATE;

pgprintk("%s: setting spte %llx\n", __func__, *sptep);
pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n",
@@ -2855,7 +2869,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,

kvm_release_pfn_clean(pfn);

- return emulate;
+ return ret;
}

static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
@@ -2994,17 +3008,16 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
* Do not cache the mmio info caused by writing the readonly gfn
* into the spte otherwise read access on readonly gfn also can
* caused mmio page fault and treat it as mmio access.
- * Return 1 to tell kvm to emulate it.
*/
if (pfn == KVM_PFN_ERR_RO_FAULT)
- return 1;
+ return RET_PF_EMULATE;

if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current);
- return 0;
+ return RET_PF_RETRY;
}

- return -EFAULT;
+ return RET_PF_EMULATE;
}

static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
@@ -3286,13 +3299,13 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
}

if (fast_page_fault(vcpu, v, level, error_code))
- return 0;
+ return RET_PF_RETRY;

mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();

if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
- return 0;
+ return RET_PF_RETRY;

if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
return r;
@@ -3312,7 +3325,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
- return 0;
+ return RET_PF_RETRY;
}


@@ -3659,54 +3672,38 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
return reserved;
}

-/*
- * Return values of handle_mmio_page_fault:
- * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction
- * directly.
- * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page
- * fault path update the mmio spte.
- * RET_MMIO_PF_RETRY: let CPU fault again on the address.
- * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed).
- */
-enum {
- RET_MMIO_PF_EMULATE = 1,
- RET_MMIO_PF_INVALID = 2,
- RET_MMIO_PF_RETRY = 0,
- RET_MMIO_PF_BUG = -1
-};
-
static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
u64 spte;
bool reserved;

if (mmio_info_in_cache(vcpu, addr, direct))
- return RET_MMIO_PF_EMULATE;
+ return RET_PF_EMULATE;

reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
if (WARN_ON(reserved))
- return RET_MMIO_PF_BUG;
+ return -EINVAL;

if (is_mmio_spte(spte)) {
gfn_t gfn = get_mmio_spte_gfn(spte);
unsigned access = get_mmio_spte_access(spte);

if (!check_mmio_spte(vcpu, spte))
- return RET_MMIO_PF_INVALID;
+ return RET_PF_INVALID;

if (direct)
addr = 0;

trace_handle_mmio_page_fault(addr, gfn, access);
vcpu_cache_mmio_info(vcpu, addr, gfn, access);
- return RET_MMIO_PF_EMULATE;
+ return RET_PF_EMULATE;
}

/*
* If the page table is zapped by other cpus, let CPU fault again on
* the address.
*/
- return RET_MMIO_PF_RETRY;
+ return RET_PF_RETRY;
}
EXPORT_SYMBOL_GPL(handle_mmio_page_fault);

@@ -3756,7 +3753,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);

if (page_fault_handle_page_track(vcpu, error_code, gfn))
- return 1;
+ return RET_PF_EMULATE;

r = mmu_topup_memory_caches(vcpu);
if (r)
@@ -3877,7 +3874,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));

if (page_fault_handle_page_track(vcpu, error_code, gfn))
- return 1;
+ return RET_PF_EMULATE;

r = mmu_topup_memory_caches(vcpu);
if (r)
@@ -3894,13 +3891,13 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
}

if (fast_page_fault(vcpu, gpa, level, error_code))
- return 0;
+ return RET_PF_RETRY;

mmu_seq = vcpu->kvm->mmu_notifier_seq;
smp_rmb();

if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
- return 0;
+ return RET_PF_RETRY;

if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r))
return r;
@@ -3920,7 +3917,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
- return 0;
+ return RET_PF_RETRY;
}

static void nonpaging_init_context(struct kvm_vcpu *vcpu,
@@ -4919,25 +4916,25 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
vcpu->arch.gpa_val = cr2;
}

+ r = RET_PF_INVALID;
if (unlikely(error_code & PFERR_RSVD_MASK)) {
r = handle_mmio_page_fault(vcpu, cr2, direct);
- if (r == RET_MMIO_PF_EMULATE) {
+ if (r == RET_PF_EMULATE) {
emulation_type = 0;
goto emulate;
}
- if (r == RET_MMIO_PF_RETRY)
- return 1;
- if (r < 0)
- return r;
- /* Must be RET_MMIO_PF_INVALID. */
}

- r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
- false);
+ if (r == RET_PF_INVALID) {
+ r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
+ false);
+ WARN_ON(r == RET_PF_INVALID);
+ }
+
+ if (r == RET_PF_RETRY)
+ return 1;
if (r < 0)
return r;
- if (!r)
- return 1;

/*
* Before emulating the instruction, check if the error code
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index f18d1f8d332b..5abae72266b7 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -593,7 +593,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
struct kvm_mmu_page *sp = NULL;
struct kvm_shadow_walk_iterator it;
unsigned direct_access, access = gw->pt_access;
- int top_level, emulate;
+ int top_level, ret;

direct_access = gw->pte_access;

@@ -659,15 +659,15 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
}

clear_sp_write_flooding_count(it.sptep);
- emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
- it.level, gw->gfn, pfn, prefault, map_writable);
+ ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
+ it.level, gw->gfn, pfn, prefault, map_writable);
FNAME(pte_prefetch)(vcpu, gw, it.sptep);

- return emulate;
+ return ret;

out_gpte_changed:
kvm_release_pfn_clean(pfn);
- return 0;
+ return RET_PF_RETRY;
}

/*
@@ -762,12 +762,12 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
if (!prefault)
inject_page_fault(vcpu, &walker.fault);

- return 0;
+ return RET_PF_RETRY;
}

if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) {
shadow_page_table_clear_flood(vcpu, addr);
- return 1;
+ return RET_PF_EMULATE;
}

vcpu->arch.write_fault_to_shadow_pgtable = false;
@@ -789,7 +789,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,

if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault,
&map_writable))
- return 0;
+ return RET_PF_RETRY;

if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r))
return r;
@@ -834,7 +834,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
- return 0;
+ return RET_PF_RETRY;
}

static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e0bc3ad0f6cd..9fb0daf628cb 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -45,6 +45,7 @@
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
#include <asm/irq_remapping.h>
+#include <asm/microcode.h>
#include <asm/nospec-branch.h>

#include <asm/virtext.h>
@@ -5015,7 +5016,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
* being speculatively taken.
*/
if (svm->spec_ctrl)
- wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+ native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);

asm volatile (
"push %%" _ASM_BP "; \n\t"
@@ -5124,11 +5125,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
* If the L02 MSR bitmap does not intercept the MSR, then we need to
* save it.
*/
- if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
- rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+ if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+ svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

if (svm->spec_ctrl)
- wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);

/* Eliminate branch target predictions from guest mode */
vmexit_fill_RSB();
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5ffde16253cb..315fccb2684b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,6 +51,7 @@
#include <asm/apic.h>
#include <asm/irq_remapping.h>
#include <asm/mmu_context.h>
+#include <asm/microcode.h>
#include <asm/nospec-branch.h>

#include "trace.h"
@@ -9431,7 +9432,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
* being speculatively taken.
*/
if (vmx->spec_ctrl)
- wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+ native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);

vmx->__launched = vmx->loaded_vmcs->launched;
asm(
@@ -9566,11 +9567,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
* If the L02 MSR bitmap does not intercept the MSR, then we need to
* save it.
*/
- if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
- rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+ if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+ vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

if (vmx->spec_ctrl)
- wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);

/* Eliminate branch target predictions from guest mode */
vmexit_fill_RSB();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0dcd7bf45dc1..b9afb4784d12 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7482,13 +7482,13 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);

int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
- if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) {
+ if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
/*
* When EFER.LME and CR0.PG are set, the processor is in
* 64-bit mode (though maybe in a 32-bit code segment).
* CR4.PAE and EFER.LMA must be set.
*/
- if (!(sregs->cr4 & X86_CR4_PAE_BIT)
+ if (!(sregs->cr4 & X86_CR4_PAE)
|| !(sregs->efer & EFER_LMA))
return -EINVAL;
} else {
@@ -7821,6 +7821,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)

void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
+ kvm_lapic_reset(vcpu, init_event);
+
vcpu->arch.hflags = 0;

vcpu->arch.smi_pending = 0;
@@ -8249,10 +8251,8 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
return r;
}

- if (!size) {
- r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
- WARN_ON(r < 0);
- }
+ if (!size)
+ vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);

return 0;
}
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index b9283cc27622..476d810639a8 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -163,4 +163,10 @@ void __init setup_cpu_entry_areas(void)

for_each_possible_cpu(cpu)
setup_cpu_entry_area(cpu);
+
+ /*
+ * This is the last essential update to swapper_pgdir which needs
+ * to be synchronized to initial_page_table on 32bit.
+ */
+ sync_initial_page_table();
}
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 135c9a7898c7..3141e67ec24c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -453,6 +453,21 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base)
}
#endif /* CONFIG_HIGHMEM */

+void __init sync_initial_page_table(void)
+{
+ clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+ swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ KERNEL_PGD_PTRS);
+
+ /*
+ * sync back low identity map too. It is used for example
+ * in the 32-bit EFI stub.
+ */
+ clone_pgd_range(initial_page_table,
+ swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+}
+
void __init native_pagetable_init(void)
{
unsigned long pfn, va;
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 86676cec99a1..09dd7f3cf621 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -79,7 +79,7 @@ static void intel_mid_power_off(void)

static void intel_mid_reboot(void)
{
- intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+ intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
}

static unsigned long __init intel_mid_calibrate_tsc(void)
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 92bf5ecb6baf..3e3a58ea669e 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,12 +1,15 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/types.h>
#include <linux/tick.h>
+#include <linux/percpu-defs.h>

#include <xen/xen.h>
#include <xen/interface/xen.h>
#include <xen/grant_table.h>
#include <xen/events.h>

+#include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
#include <asm/fixmap.h>
@@ -15,6 +18,8 @@
#include "mmu.h"
#include "pmu.h"

+static DEFINE_PER_CPU(u64, spec_ctrl);
+
void xen_arch_pre_suspend(void)
{
if (xen_pv_domain())
@@ -31,6 +36,9 @@ void xen_arch_post_suspend(int cancelled)

static void xen_vcpu_notify_restore(void *data)
{
+ if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+ wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+
/* Boot processor notified via generic timekeeping_resume() */
if (smp_processor_id() == 0)
return;
@@ -40,7 +48,15 @@ static void xen_vcpu_notify_restore(void *data)

static void xen_vcpu_notify_suspend(void *data)
{
+ u64 tmp;
+
tick_suspend_local();
+
+ if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
+ rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+ this_cpu_write(spec_ctrl, tmp);
+ wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ }
}

void xen_arch_resume(void)
diff --git a/block/blk-core.c b/block/blk-core.c
index 95b7ea996ac2..c01f4907dbbc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2277,7 +2277,7 @@ blk_qc_t submit_bio(struct bio *bio)
unsigned int count;

if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
- count = queue_logical_block_size(bio->bi_disk->queue);
+ count = queue_logical_block_size(bio->bi_disk->queue) >> 9;
else
count = bio_sectors(bio);

diff --git a/block/blk-mq.c b/block/blk-mq.c
index b60798a30ea2..f1fb126a3be5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -638,7 +638,6 @@ static void __blk_mq_requeue_request(struct request *rq)

trace_block_rq_requeue(q, rq);
wbt_requeue(q->rq_wb, &rq->issue_stat);
- blk_mq_sched_requeue_request(rq);

if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
if (q->dma_drain_size && blk_rq_bytes(rq))
@@ -650,6 +649,9 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
{
__blk_mq_requeue_request(rq);

+ /* this request will be re-inserted to io scheduler queue */
+ blk_mq_sched_requeue_request(rq);
+
BUG_ON(blk_queued_rq(rq));
blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
}
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index f58cab82105b..09cd5cf2e459 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -814,6 +814,7 @@ static struct elevator_type kyber_sched = {
.limit_depth = kyber_limit_depth,
.prepare_request = kyber_prepare_request,
.finish_request = kyber_finish_request,
+ .requeue_request = kyber_finish_request,
.completed_request = kyber_completed_request,
.dispatch_request = kyber_dispatch_request,
.has_work = kyber_has_work,
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 4d0979e02a28..b6d58cc58f5f 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -66,10 +66,37 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
return 0;
}
#endif
+static int set_gbl_term_list(const struct dmi_system_id *id)
+{
+ acpi_gbl_parse_table_as_term_list = 1;
+ return 0;
+}

-static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
+static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
+ /*
+ * Touchpad on Dell XPS 9570/Precision M5530 doesn't work under I2C
+ * mode.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=198515
+ */
+ {
+ .callback = set_gbl_term_list,
+ .ident = "Dell Precision M5530",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Precision M5530"),
+ },
+ },
+ {
+ .callback = set_gbl_term_list,
+ .ident = "Dell XPS 15 9570",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"),
+ },
+ },
/*
* Invoke DSDT corruption work-around on all Toshiba Satellite.
+ * DSDT will be copied to memory.
* https://bugzilla.kernel.org/show_bug.cgi?id=14679
*/
{
@@ -83,7 +110,7 @@ static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
{}
};
#else
-static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
+static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
{}
};
#endif
@@ -1001,11 +1028,8 @@ void __init acpi_early_init(void)

acpi_permanent_mmap = true;

- /*
- * If the machine falls into the DMI check table,
- * DSDT will be copied to memory
- */
- dmi_check_system(dsdt_dmi_table);
+ /* Check machine-specific quirks */
+ dmi_check_system(acpi_quirks_dmi_table);

status = acpi_reallocate_root_table();
if (ACPI_FAILURE(status)) {
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index d54c3f6f728c..673698c7b143 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -21,6 +21,7 @@
*
*/

+#include <linux/dmi.h>
#include <linux/module.h>
#include <linux/usb.h>
#include <linux/usb/quirks.h>
@@ -381,6 +382,21 @@ static const struct usb_device_id blacklist_table[] = {
{ } /* Terminating entry */
};

+/* The Bluetooth USB module build into some devices needs to be reset on resume,
+ * this is a problem with the platform (likely shutting off all power) not with
+ * the module itself. So we use a DMI list to match known broken platforms.
+ */
+static const struct dmi_system_id btusb_needs_reset_resume_table[] = {
+ {
+ /* Lenovo Yoga 920 (QCA Rome device 0cf3:e300) */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 920"),
+ },
+ },
+ {}
+};
+
#define BTUSB_MAX_ISOC_FRAMES 10

#define BTUSB_INTR_RUNNING 0
@@ -3013,6 +3029,9 @@ static int btusb_probe(struct usb_interface *intf,
hdev->send = btusb_send_frame;
hdev->notify = btusb_notify;

+ if (dmi_check_system(btusb_needs_reset_resume_table))
+ interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
+
#ifdef CONFIG_PM
err = btusb_config_oob_wake(hdev);
if (err)
@@ -3099,12 +3118,6 @@ static int btusb_probe(struct usb_interface *intf,
if (id->driver_info & BTUSB_QCA_ROME) {
data->setup_on_usb = btusb_setup_qca;
hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
-
- /* QCA Rome devices lose their updated firmware over suspend,
- * but the USB hub doesn't notice any status change.
- * explicitly request a device reset on resume.
- */
- interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
}

#ifdef CONFIG_BT_HCIBTUSB_RTL
diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c
index 4d1dc8b46877..f95b9c75175b 100644
--- a/drivers/char/tpm/st33zp24/st33zp24.c
+++ b/drivers/char/tpm/st33zp24/st33zp24.c
@@ -457,7 +457,7 @@ static int st33zp24_recv(struct tpm_chip *chip, unsigned char *buf,
size_t count)
{
int size = 0;
- int expected;
+ u32 expected;

if (!chip)
return -EBUSY;
@@ -474,7 +474,7 @@ static int st33zp24_recv(struct tpm_chip *chip, unsigned char *buf,
}

expected = be32_to_cpu(*(__be32 *)(buf + 2));
- if (expected > count) {
+ if (expected > count || expected < TPM_HEADER_SIZE) {
size = -EIO;
goto out;
}
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 1d6729be4cd6..3cec403a80b3 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -1228,6 +1228,10 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
break;

recd = be32_to_cpu(tpm_cmd.params.getrandom_out.rng_data_len);
+ if (recd > num_bytes) {
+ total = -EFAULT;
+ break;
+ }

rlength = be32_to_cpu(tpm_cmd.header.out.length);
if (rlength < offsetof(struct tpm_getrandom_out, rng_data) +
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index e1a41b788f08..44a3d16231f6 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -683,6 +683,10 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip,
if (!rc) {
data_len = be16_to_cpup(
(__be16 *) &buf.data[TPM_HEADER_SIZE + 4]);
+ if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) {
+ rc = -EFAULT;
+ goto out;
+ }

rlength = be32_to_cpu(((struct tpm2_cmd *)&buf)
->header.out.length);
diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c
index 79d6bbb58e39..d5b44cadac56 100644
--- a/drivers/char/tpm/tpm_i2c_infineon.c
+++ b/drivers/char/tpm/tpm_i2c_infineon.c
@@ -473,7 +473,8 @@ static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count)
static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count)
{
int size = 0;
- int expected, status;
+ int status;
+ u32 expected;

if (count < TPM_HEADER_SIZE) {
size = -EIO;
@@ -488,7 +489,7 @@ static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count)
}

expected = be32_to_cpu(*(__be32 *)(buf + 2));
- if ((size_t) expected > count) {
+ if (((size_t) expected > count) || (expected < TPM_HEADER_SIZE)) {
size = -EIO;
goto out;
}
diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c
index c6428771841f..caa86b19c76d 100644
--- a/drivers/char/tpm/tpm_i2c_nuvoton.c
+++ b/drivers/char/tpm/tpm_i2c_nuvoton.c
@@ -281,7 +281,11 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count)
struct device *dev = chip->dev.parent;
struct i2c_client *client = to_i2c_client(dev);
s32 rc;
- int expected, status, burst_count, retries, size = 0;
+ int status;
+ int burst_count;
+ int retries;
+ int size = 0;
+ u32 expected;

if (count < TPM_HEADER_SIZE) {
i2c_nuvoton_ready(chip); /* return to idle */
@@ -323,7 +327,7 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count)
* to machine native
*/
expected = be32_to_cpu(*(__be32 *) (buf + 2));
- if (expected > count) {
+ if (expected > count || expected < size) {
dev_err(dev, "%s() expected > count\n", __func__);
size = -EIO;
continue;
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 7e55aa9ce680..ebd0e75a3e4d 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -223,7 +223,7 @@ static int tpm_tcg_read_bytes(struct tpm_tis_data *data, u32 addr, u16 len,
}

static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len,
- u8 *value)
+ const u8 *value)
{
struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);

diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 63bc6c3b949e..083578b2517e 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -202,7 +202,8 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count)
{
struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
int size = 0;
- int expected, status;
+ int status;
+ u32 expected;

if (count < TPM_HEADER_SIZE) {
size = -EIO;
@@ -217,7 +218,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count)
}

expected = be32_to_cpu(*(__be32 *) (buf + 2));
- if (expected > count) {
+ if (expected > count || expected < TPM_HEADER_SIZE) {
size = -EIO;
goto out;
}
@@ -252,7 +253,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count)
* tpm.c can skip polling for the data to be available as the interrupt is
* waited for here
*/
-static int tpm_tis_send_data(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_tis_send_data(struct tpm_chip *chip, const u8 *buf, size_t len)
{
struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
int rc, status, burstcnt;
@@ -343,7 +344,7 @@ static void disable_interrupts(struct tpm_chip *chip)
* tpm.c can skip polling for the data to be available as the interrupt is
* waited for here
*/
-static int tpm_tis_send_main(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_tis_send_main(struct tpm_chip *chip, const u8 *buf, size_t len)
{
struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
int rc;
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index e2212f021a02..6bbac319ff3b 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -98,7 +98,7 @@ struct tpm_tis_phy_ops {
int (*read_bytes)(struct tpm_tis_data *data, u32 addr, u16 len,
u8 *result);
int (*write_bytes)(struct tpm_tis_data *data, u32 addr, u16 len,
- u8 *value);
+ const u8 *value);
int (*read16)(struct tpm_tis_data *data, u32 addr, u16 *result);
int (*read32)(struct tpm_tis_data *data, u32 addr, u32 *result);
int (*write32)(struct tpm_tis_data *data, u32 addr, u32 src);
@@ -128,7 +128,7 @@ static inline int tpm_tis_read32(struct tpm_tis_data *data, u32 addr,
}

static inline int tpm_tis_write_bytes(struct tpm_tis_data *data, u32 addr,
- u16 len, u8 *value)
+ u16 len, const u8 *value)
{
return data->phy_ops->write_bytes(data, addr, len, value);
}
diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi.c
index 88fe72ae967f..8ab0bd8445f6 100644
--- a/drivers/char/tpm/tpm_tis_spi.c
+++ b/drivers/char/tpm/tpm_tis_spi.c
@@ -46,9 +46,7 @@
struct tpm_tis_spi_phy {
struct tpm_tis_data priv;
struct spi_device *spi_device;
-
- u8 tx_buf[4];
- u8 rx_buf[4];
+ u8 *iobuf;
};

static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *data)
@@ -57,7 +55,7 @@ static inline struct tpm_tis_spi_phy *to_tpm_tis_spi_phy(struct tpm_tis_data *da
}

static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
- u8 *buffer, u8 direction)
+ u8 *in, const u8 *out)
{
struct tpm_tis_spi_phy *phy = to_tpm_tis_spi_phy(data);
int ret = 0;
@@ -71,14 +69,14 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
while (len) {
transfer_len = min_t(u16, len, MAX_SPI_FRAMESIZE);

- phy->tx_buf[0] = direction | (transfer_len - 1);
- phy->tx_buf[1] = 0xd4;
- phy->tx_buf[2] = addr >> 8;
- phy->tx_buf[3] = addr;
+ phy->iobuf[0] = (in ? 0x80 : 0) | (transfer_len - 1);
+ phy->iobuf[1] = 0xd4;
+ phy->iobuf[2] = addr >> 8;
+ phy->iobuf[3] = addr;

memset(&spi_xfer, 0, sizeof(spi_xfer));
- spi_xfer.tx_buf = phy->tx_buf;
- spi_xfer.rx_buf = phy->rx_buf;
+ spi_xfer.tx_buf = phy->iobuf;
+ spi_xfer.rx_buf = phy->iobuf;
spi_xfer.len = 4;
spi_xfer.cs_change = 1;

@@ -88,9 +86,9 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
if (ret < 0)
goto exit;

- if ((phy->rx_buf[3] & 0x01) == 0) {
+ if ((phy->iobuf[3] & 0x01) == 0) {
// handle SPI wait states
- phy->tx_buf[0] = 0;
+ phy->iobuf[0] = 0;

for (i = 0; i < TPM_RETRY; i++) {
spi_xfer.len = 1;
@@ -99,7 +97,7 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
ret = spi_sync_locked(phy->spi_device, &m);
if (ret < 0)
goto exit;
- if (phy->rx_buf[0] & 0x01)
+ if (phy->iobuf[0] & 0x01)
break;
}

@@ -113,12 +111,12 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
spi_xfer.len = transfer_len;
spi_xfer.delay_usecs = 5;

- if (direction) {
+ if (in) {
spi_xfer.tx_buf = NULL;
- spi_xfer.rx_buf = buffer;
- } else {
- spi_xfer.tx_buf = buffer;
+ } else if (out) {
spi_xfer.rx_buf = NULL;
+ memcpy(phy->iobuf, out, transfer_len);
+ out += transfer_len;
}

spi_message_init(&m);
@@ -127,8 +125,12 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
if (ret < 0)
goto exit;

+ if (in) {
+ memcpy(in, phy->iobuf, transfer_len);
+ in += transfer_len;
+ }
+
len -= transfer_len;
- buffer += transfer_len;
}

exit:
@@ -139,13 +141,13 @@ static int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len,
static int tpm_tis_spi_read_bytes(struct tpm_tis_data *data, u32 addr,
u16 len, u8 *result)
{
- return tpm_tis_spi_transfer(data, addr, len, result, 0x80);
+ return tpm_tis_spi_transfer(data, addr, len, result, NULL);
}

static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr,
- u16 len, u8 *value)
+ u16 len, const u8 *value)
{
- return tpm_tis_spi_transfer(data, addr, len, value, 0);
+ return tpm_tis_spi_transfer(data, addr, len, NULL, value);
}

static int tpm_tis_spi_read16(struct tpm_tis_data *data, u32 addr, u16 *result)
@@ -194,6 +196,10 @@ static int tpm_tis_spi_probe(struct spi_device *dev)

phy->spi_device = dev;

+ phy->iobuf = devm_kmalloc(&dev->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL);
+ if (!phy->iobuf)
+ return -ENOMEM;
+
return tpm_tis_core_init(&dev->dev, &phy->priv, -1, &tpm_spi_phy_ops,
NULL);
}
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index 7b596fa38ad2..6bebc1f9f55a 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -351,7 +351,13 @@ struct clk *s3c_cpufreq_clk_get(struct device *dev, const char *name)
static int s3c_cpufreq_init(struct cpufreq_policy *policy)
{
policy->clk = clk_arm;
- return cpufreq_generic_init(policy, ftab, cpu_cur.info->latency);
+
+ policy->cpuinfo.transition_latency = cpu_cur.info->latency;
+
+ if (ftab)
+ return cpufreq_table_validate_and_show(policy, ftab);
+
+ return 0;
}

static int __init s3c_cpufreq_initclks(void)
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index cd9d6ba03579..0dc0d595c47c 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -279,7 +279,7 @@ static const u32 correrrthrsld[] = {
* sbridge structs
*/

-#define NUM_CHANNELS 4 /* Max channels per MC */
+#define NUM_CHANNELS 6 /* Max channels per MC */
#define MAX_DIMMS 3 /* Max DIMMS per channel */
#define KNL_MAX_CHAS 38 /* KNL max num. of Cache Home Agents */
#define KNL_MAX_CHANNELS 6 /* KNL max num. of PCI channels */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6bf093cef958..e058c209bbcf 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8522,6 +8522,10 @@ static int remove_and_add_spares(struct mddev *mddev,
int removed = 0;
bool remove_some = false;

+ if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ /* Mustn't remove devices when resync thread is running */
+ return 0;
+
rdev_for_each(rdev, mddev) {
if ((this == NULL || rdev == this) &&
rdev->raid_disk >= 0 &&
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index 50bce68ffd66..65d157fe76d1 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -1262,11 +1262,12 @@ static int m88ds3103_select(struct i2c_mux_core *muxc, u32 chan)
* New users must use I2C client binding directly!
*/
struct dvb_frontend *m88ds3103_attach(const struct m88ds3103_config *cfg,
- struct i2c_adapter *i2c, struct i2c_adapter **tuner_i2c_adapter)
+ struct i2c_adapter *i2c,
+ struct i2c_adapter **tuner_i2c_adapter)
{
struct i2c_client *client;
struct i2c_board_info board_info;
- struct m88ds3103_platform_data pdata;
+ struct m88ds3103_platform_data pdata = {};

pdata.clk = cfg->clock;
pdata.i2c_wr_max = cfg->i2c_wr_max;
@@ -1409,6 +1410,8 @@ static int m88ds3103_probe(struct i2c_client *client,
case M88DS3103_CHIP_ID:
break;
default:
+ ret = -ENODEV;
+ dev_err(&client->dev, "Unknown device. Chip_id=%02x\n", dev->chip_id);
goto err_kfree;
}

diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index 35026795be28..fa41d9422d57 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -487,6 +487,7 @@ static unsigned long exynos_dwmmc_caps[4] = {

static const struct dw_mci_drv_data exynos_drv_data = {
.caps = exynos_dwmmc_caps,
+ .num_caps = ARRAY_SIZE(exynos_dwmmc_caps),
.init = dw_mci_exynos_priv_init,
.set_ios = dw_mci_exynos_set_ios,
.parse_dt = dw_mci_exynos_parse_dt,
diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
index 64cda84b2302..864e7fcaffaf 100644
--- a/drivers/mmc/host/dw_mmc-k3.c
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -135,6 +135,9 @@ static int dw_mci_hi6220_parse_dt(struct dw_mci *host)
if (priv->ctrl_id < 0)
priv->ctrl_id = 0;

+ if (priv->ctrl_id >= TIMING_MODE)
+ return -EINVAL;
+
host->priv = priv;
return 0;
}
@@ -207,6 +210,7 @@ static int dw_mci_hi6220_execute_tuning(struct dw_mci_slot *slot, u32 opcode)

static const struct dw_mci_drv_data hi6220_data = {
.caps = dw_mci_hi6220_caps,
+ .num_caps = ARRAY_SIZE(dw_mci_hi6220_caps),
.switch_voltage = dw_mci_hi6220_switch_voltage,
.set_ios = dw_mci_hi6220_set_ios,
.parse_dt = dw_mci_hi6220_parse_dt,
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index a3f1c2b30145..339295212935 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -319,6 +319,7 @@ static const struct dw_mci_drv_data rk2928_drv_data = {

static const struct dw_mci_drv_data rk3288_drv_data = {
.caps = dw_mci_rk3288_dwmmc_caps,
+ .num_caps = ARRAY_SIZE(dw_mci_rk3288_dwmmc_caps),
.set_ios = dw_mci_rk3288_set_ios,
.execute_tuning = dw_mci_rk3288_execute_tuning,
.parse_dt = dw_mci_rk3288_parse_dt,
diff --git a/drivers/mmc/host/dw_mmc-zx.c b/drivers/mmc/host/dw_mmc-zx.c
index d38e94ae2b85..c06b5393312f 100644
--- a/drivers/mmc/host/dw_mmc-zx.c
+++ b/drivers/mmc/host/dw_mmc-zx.c
@@ -195,6 +195,7 @@ static unsigned long zx_dwmmc_caps[3] = {

static const struct dw_mci_drv_data zx_drv_data = {
.caps = zx_dwmmc_caps,
+ .num_caps = ARRAY_SIZE(zx_dwmmc_caps),
.execute_tuning = dw_mci_zx_execute_tuning,
.prepare_hs400_tuning = dw_mci_zx_prepare_hs400_tuning,
.parse_dt = dw_mci_zx_parse_dt,
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 4f2806720c5c..60341a814055 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -165,6 +165,8 @@ static int dw_mci_regs_show(struct seq_file *s, void *v)
{
struct dw_mci *host = s->private;

+ pm_runtime_get_sync(host->dev);
+
seq_printf(s, "STATUS:\t0x%08x\n", mci_readl(host, STATUS));
seq_printf(s, "RINTSTS:\t0x%08x\n", mci_readl(host, RINTSTS));
seq_printf(s, "CMD:\t0x%08x\n", mci_readl(host, CMD));
@@ -172,6 +174,8 @@ static int dw_mci_regs_show(struct seq_file *s, void *v)
seq_printf(s, "INTMASK:\t0x%08x\n", mci_readl(host, INTMASK));
seq_printf(s, "CLKENA:\t0x%08x\n", mci_readl(host, CLKENA));

+ pm_runtime_put_autosuspend(host->dev);
+
return 0;
}

@@ -2758,12 +2762,57 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
return IRQ_HANDLED;
}

+static int dw_mci_init_slot_caps(struct dw_mci_slot *slot)
+{
+ struct dw_mci *host = slot->host;
+ const struct dw_mci_drv_data *drv_data = host->drv_data;
+ struct mmc_host *mmc = slot->mmc;
+ int ctrl_id;
+
+ if (host->pdata->caps)
+ mmc->caps = host->pdata->caps;
+
+ /*
+ * Support MMC_CAP_ERASE by default.
+ * It needs to use trim/discard/erase commands.
+ */
+ mmc->caps |= MMC_CAP_ERASE;
+
+ if (host->pdata->pm_caps)
+ mmc->pm_caps = host->pdata->pm_caps;
+
+ if (host->dev->of_node) {
+ ctrl_id = of_alias_get_id(host->dev->of_node, "mshc");
+ if (ctrl_id < 0)
+ ctrl_id = 0;
+ } else {
+ ctrl_id = to_platform_device(host->dev)->id;
+ }
+
+ if (drv_data && drv_data->caps) {
+ if (ctrl_id >= drv_data->num_caps) {
+ dev_err(host->dev, "invalid controller id %d\n",
+ ctrl_id);
+ return -EINVAL;
+ }
+ mmc->caps |= drv_data->caps[ctrl_id];
+ }
+
+ if (host->pdata->caps2)
+ mmc->caps2 = host->pdata->caps2;
+
+ /* Process SDIO IRQs through the sdio_irq_work. */
+ if (mmc->caps & MMC_CAP_SDIO_IRQ)
+ mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
+
+ return 0;
+}
+
static int dw_mci_init_slot(struct dw_mci *host)
{
struct mmc_host *mmc;
struct dw_mci_slot *slot;
- const struct dw_mci_drv_data *drv_data = host->drv_data;
- int ctrl_id, ret;
+ int ret;
u32 freq[2];

mmc = mmc_alloc_host(sizeof(struct dw_mci_slot), host->dev);
@@ -2797,38 +2846,13 @@ static int dw_mci_init_slot(struct dw_mci *host)
if (!mmc->ocr_avail)
mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;

- if (host->pdata->caps)
- mmc->caps = host->pdata->caps;
-
- /*
- * Support MMC_CAP_ERASE by default.
- * It needs to use trim/discard/erase commands.
- */
- mmc->caps |= MMC_CAP_ERASE;
-
- if (host->pdata->pm_caps)
- mmc->pm_caps = host->pdata->pm_caps;
-
- if (host->dev->of_node) {
- ctrl_id = of_alias_get_id(host->dev->of_node, "mshc");
- if (ctrl_id < 0)
- ctrl_id = 0;
- } else {
- ctrl_id = to_platform_device(host->dev)->id;
- }
- if (drv_data && drv_data->caps)
- mmc->caps |= drv_data->caps[ctrl_id];
-
- if (host->pdata->caps2)
- mmc->caps2 = host->pdata->caps2;
-
ret = mmc_of_parse(mmc);
if (ret)
goto err_host_allocated;

- /* Process SDIO IRQs through the sdio_irq_work. */
- if (mmc->caps & MMC_CAP_SDIO_IRQ)
- mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
+ ret = dw_mci_init_slot_caps(slot);
+ if (ret)
+ goto err_host_allocated;

/* Useful defaults if platform data is unset. */
if (host->use_dma == TRANS_MODE_IDMAC) {
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 34474ad731aa..044c87ce6725 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -542,6 +542,7 @@ struct dw_mci_slot {
/**
* dw_mci driver data - dw-mshc implementation specific driver data.
* @caps: mmc subsystem specified capabilities of the controller(s).
+ * @num_caps: number of capabilities specified by @caps.
* @init: early implementation specific initialization.
* @set_ios: handle bus specific extensions.
* @parse_dt: parse implementation specific device tree properties.
@@ -553,6 +554,7 @@ struct dw_mci_slot {
*/
struct dw_mci_drv_data {
unsigned long *caps;
+ u32 num_caps;
int (*init)(struct dw_mci *host);
void (*set_ios)(struct dw_mci *host, struct mmc_ios *ios);
int (*parse_dt)(struct dw_mci *host);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 67d787fa3306..070f5da06fd2 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -594,9 +594,36 @@ static void byt_read_dsm(struct sdhci_pci_slot *slot)
slot->chip->rpm_retune = intel_host->d3_retune;
}

-static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
+static int intel_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+ int err = sdhci_execute_tuning(mmc, opcode);
+ struct sdhci_host *host = mmc_priv(mmc);
+
+ if (err)
+ return err;
+
+ /*
+ * Tuning can leave the IP in an active state (Buffer Read Enable bit
+ * set) which prevents the entry to low power states (i.e. S0i3). Data
+ * reset will clear it.
+ */
+ sdhci_reset(host, SDHCI_RESET_DATA);
+
+ return 0;
+}
+
+static void byt_probe_slot(struct sdhci_pci_slot *slot)
{
+ struct mmc_host_ops *ops = &slot->host->mmc_host_ops;
+
byt_read_dsm(slot);
+
+ ops->execute_tuning = intel_execute_tuning;
+}
+
+static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
+{
+ byt_probe_slot(slot);
slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR |
MMC_CAP_CMD_DURING_TFR |
@@ -651,7 +678,7 @@ static int ni_byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
{
int err;

- byt_read_dsm(slot);
+ byt_probe_slot(slot);

err = ni_set_max_freq(slot);
if (err)
@@ -664,7 +691,7 @@ static int ni_byt_sdio_probe_slot(struct sdhci_pci_slot *slot)

static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
{
- byt_read_dsm(slot);
+ byt_probe_slot(slot);
slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE |
MMC_CAP_WAIT_WHILE_BUSY;
return 0;
@@ -672,7 +699,7 @@ static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)

static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
{
- byt_read_dsm(slot);
+ byt_probe_slot(slot);
slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY |
MMC_CAP_AGGRESSIVE_PM | MMC_CAP_CD_WAKE;
slot->cd_idx = 0;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 608693d11bd7..75c4455e2271 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -595,7 +595,7 @@ static void xgbe_isr_task(unsigned long data)

reissue_mask = 1 << 0;
if (!pdata->per_channel_irq)
- reissue_mask |= 0xffff < 4;
+ reissue_mask |= 0xffff << 4;

XP_IOWRITE(pdata, XP_INT_REISSUE_EN, reissue_mask);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index 3e5833cf1fab..eb23f9ba1a9a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -426,6 +426,8 @@ static int xgbe_pci_resume(struct pci_dev *pdev)
struct net_device *netdev = pdata->netdev;
int ret = 0;

+ XP_IOWRITE(pdata, XP_INT_EN, 0x1fffff);
+
pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 879a9c4cef59..29f600fd6977 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1877,6 +1877,14 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
ixgbe_rx_pg_size(rx_ring),
DMA_FROM_DEVICE,
IXGBE_RX_DMA_ATTR);
+ } else if (ring_uses_build_skb(rx_ring)) {
+ unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK;
+
+ dma_sync_single_range_for_cpu(rx_ring->dev,
+ IXGBE_CB(skb)->dma,
+ offset,
+ skb_headlen(skb),
+ DMA_FROM_DEVICE);
} else {
struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3cdb932cae76..a863572882b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1918,13 +1918,16 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
param->wq.linear = 1;
}

-static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param)
+static void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
+ struct mlx5e_rq_param *param)
{
void *rqc = param->rqc;
void *wq = MLX5_ADDR_OF(rqc, rqc, wq);

MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST);
MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe)));
+
+ param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
}

static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
@@ -2778,6 +2781,9 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
struct mlx5e_cq *cq,
struct mlx5e_cq_param *param)
{
+ param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+ param->wq.db_numa_node = dev_to_node(&mdev->pdev->dev);
+
return mlx5e_alloc_cq_common(mdev, param, cq);
}

@@ -2789,7 +2795,7 @@ static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev,
struct mlx5e_cq *cq = &drop_rq->cq;
int err;

- mlx5e_build_drop_rq_param(&rq_param);
+ mlx5e_build_drop_rq_param(mdev, &rq_param);

err = mlx5e_alloc_drop_cq(mdev, cq, &cq_param);
if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 91b1b0938931..3476f594c195 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -36,6 +36,7 @@
#include <linux/tcp.h>
#include <linux/bpf_trace.h>
#include <net/busy_poll.h>
+#include <net/ip6_checksum.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
@@ -546,20 +547,33 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
return true;
}

+static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
+{
+ u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
+ u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
+ (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
+
+ tcp->check = 0;
+ tcp->psh = get_cqe_lro_tcppsh(cqe);
+
+ if (tcp_ack) {
+ tcp->ack = 1;
+ tcp->ack_seq = cqe->lro_ack_seq_num;
+ tcp->window = cqe->lro_tcp_win;
+ }
+}
+
static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
u32 cqe_bcnt)
{
struct ethhdr *eth = (struct ethhdr *)(skb->data);
struct tcphdr *tcp;
int network_depth = 0;
+ __wsum check;
__be16 proto;
u16 tot_len;
void *ip_p;

- u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
- u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
- (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
-
skb->mac_len = ETH_HLEN;
proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);

@@ -577,23 +591,30 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
ipv4->check = 0;
ipv4->check = ip_fast_csum((unsigned char *)ipv4,
ipv4->ihl);
+
+ mlx5e_lro_update_tcp_hdr(cqe, tcp);
+ check = csum_partial(tcp, tcp->doff * 4,
+ csum_unfold((__force __sum16)cqe->check_sum));
+ /* Almost done, don't forget the pseudo header */
+ tcp->check = csum_tcpudp_magic(ipv4->saddr, ipv4->daddr,
+ tot_len - sizeof(struct iphdr),
+ IPPROTO_TCP, check);
} else {
+ u16 payload_len = tot_len - sizeof(struct ipv6hdr);
struct ipv6hdr *ipv6 = ip_p;

tcp = ip_p + sizeof(struct ipv6hdr);
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;

ipv6->hop_limit = cqe->lro_min_ttl;
- ipv6->payload_len = cpu_to_be16(tot_len -
- sizeof(struct ipv6hdr));
- }
-
- tcp->psh = get_cqe_lro_tcppsh(cqe);
-
- if (tcp_ack) {
- tcp->ack = 1;
- tcp->ack_seq = cqe->lro_ack_seq_num;
- tcp->window = cqe->lro_tcp_win;
+ ipv6->payload_len = cpu_to_be16(payload_len);
+
+ mlx5e_lro_update_tcp_hdr(cqe, tcp);
+ check = csum_partial(tcp, tcp->doff * 4,
+ csum_unfold((__force __sum16)cqe->check_sum));
+ /* Almost done, don't forget the pseudo header */
+ tcp->check = csum_ipv6_magic(&ipv6->saddr, &ipv6->daddr, payload_len,
+ IPPROTO_TCP, check);
}
}

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 5a4608281f38..707976482c09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -216,7 +216,8 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
if (iph->protocol != IPPROTO_UDP)
goto out;

- udph = udp_hdr(skb);
+ /* Don't assume skb_transport_header() was set */
+ udph = (struct udphdr *)((u8 *)iph + 4 * iph->ihl);
if (udph->dest != htons(9))
goto out;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 1d6925d4369a..eea7f931cad3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -155,7 +155,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
default:
hlen = mlx5e_skb_l2_header_offset(skb);
}
- return min_t(u16, hlen, skb->len);
+ return min_t(u16, hlen, skb_headlen(skb));
}

static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7bef80676464..516e63244606 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -729,26 +729,29 @@ static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr,
static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
u32 tb_id)
{
+ struct mlxsw_sp_fib *fib4;
+ struct mlxsw_sp_fib *fib6;
struct mlxsw_sp_vr *vr;
int err;

vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
if (!vr)
return ERR_PTR(-EBUSY);
- vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
- if (IS_ERR(vr->fib4))
- return ERR_CAST(vr->fib4);
- vr->fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6);
- if (IS_ERR(vr->fib6)) {
- err = PTR_ERR(vr->fib6);
+ fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4);
+ if (IS_ERR(fib4))
+ return ERR_CAST(fib4);
+ fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6);
+ if (IS_ERR(fib6)) {
+ err = PTR_ERR(fib6);
goto err_fib6_create;
}
+ vr->fib4 = fib4;
+ vr->fib6 = fib6;
vr->tb_id = tb_id;
return vr;

err_fib6_create:
- mlxsw_sp_fib_destroy(vr->fib4);
- vr->fib4 = NULL;
+ mlxsw_sp_fib_destroy(fib4);
return ERR_PTR(err);
}

@@ -3029,6 +3032,9 @@ mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
int i;

+ if (!list_is_singular(&nh_grp->fib_list))
+ return;
+
for (i = 0; i < nh_grp->count; i++) {
struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index f5863e5bec81..42a6afcaae03 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1098,6 +1098,7 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
bool dynamic)
{
char *sfd_pl;
+ u8 num_rec;
int err;

sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1107,9 +1108,16 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
mac, fid, action, local_port);
+ num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
- kfree(sfd_pl);
+ if (err)
+ goto out;
+
+ if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+ err = -EBUSY;

+out:
+ kfree(sfd_pl);
return err;
}

@@ -1134,6 +1142,7 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
bool adding, bool dynamic)
{
char *sfd_pl;
+ u8 num_rec;
int err;

sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1144,9 +1153,16 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
mlxsw_reg_sfd_uc_lag_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP,
lag_vid, lag_id);
+ num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
- kfree(sfd_pl);
+ if (err)
+ goto out;
+
+ if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+ err = -EBUSY;

+out:
+ kfree(sfd_pl);
return err;
}

@@ -1191,6 +1207,7 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
u16 fid, u16 mid, bool adding)
{
char *sfd_pl;
+ u8 num_rec;
int err;

sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
@@ -1200,7 +1217,15 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr,
mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
mlxsw_reg_sfd_mc_pack(sfd_pl, 0, addr, fid,
MLXSW_REG_SFD_REC_ACTION_NOP, mid);
+ num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
+ if (err)
+ goto out;
+
+ if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl))
+ err = -EBUSY;
+
+out:
kfree(sfd_pl);
return err;
}
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index db8a4bcfc6c7..14b646b3b084 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1618,6 +1618,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
q_idx = q_idx % cpsw->tx_ch_num;

txch = cpsw->txv[q_idx].ch;
+ txq = netdev_get_tx_queue(ndev, q_idx);
ret = cpsw_tx_packet_submit(priv, skb, txch);
if (unlikely(ret != 0)) {
cpsw_err(priv, tx_err, "desc submit failed\n");
@@ -1628,15 +1629,26 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
* tell the kernel to stop sending us tx frames.
*/
if (unlikely(!cpdma_check_free_tx_desc(txch))) {
- txq = netdev_get_tx_queue(ndev, q_idx);
netif_tx_stop_queue(txq);
+
+ /* Barrier, so that stop_queue visible to other cpus */
+ smp_mb__after_atomic();
+
+ if (cpdma_check_free_tx_desc(txch))
+ netif_tx_wake_queue(txq);
}

return NETDEV_TX_OK;
fail:
ndev->stats.tx_dropped++;
- txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
netif_tx_stop_queue(txq);
+
+ /* Barrier, so that stop_queue visible to other cpus */
+ smp_mb__after_atomic();
+
+ if (cpdma_check_free_tx_desc(txch))
+ netif_tx_wake_queue(txq);
+
return NETDEV_TX_BUSY;
}

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 2b1e67bc1e73..3d860de5e342 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -842,7 +842,7 @@ void phy_start(struct phy_device *phydev)
break;
case PHY_HALTED:
/* make sure interrupts are re-enabled for the PHY */
- if (phydev->irq != PHY_POLL) {
+ if (phy_interrupt_is_valid(phydev)) {
err = phy_enable_interrupts(phydev);
if (err < 0)
break;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 8c6b8918ec31..38cd2e8fae23 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -3158,6 +3158,15 @@ ppp_connect_channel(struct channel *pch, int unit)
goto outl;

ppp_lock(ppp);
+ spin_lock_bh(&pch->downl);
+ if (!pch->chan) {
+ /* Don't connect unregistered channels */
+ spin_unlock_bh(&pch->downl);
+ ppp_unlock(ppp);
+ ret = -ENOTCONN;
+ goto outl;
+ }
+ spin_unlock_bh(&pch->downl);
if (pch->file.hdrlen > ppp->file.hdrlen)
ppp->file.hdrlen = pch->file.hdrlen;
hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fa51b7b0e9ea..bc38d54e37b9 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1315,6 +1315,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
else
*skb_xdp = 0;

+ preempt_disable();
rcu_read_lock();
xdp_prog = rcu_dereference(tun->xdp_prog);
if (xdp_prog && !*skb_xdp) {
@@ -1333,9 +1334,11 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
get_page(alloc_frag->page);
alloc_frag->offset += buflen;
err = xdp_do_redirect(tun->dev, &xdp, xdp_prog);
+ xdp_do_flush_map();
if (err)
goto err_redirect;
rcu_read_unlock();
+ preempt_enable();
return NULL;
case XDP_TX:
xdp_xmit = true;
@@ -1357,6 +1360,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
skb = build_skb(buf, buflen);
if (!skb) {
rcu_read_unlock();
+ preempt_enable();
return ERR_PTR(-ENOMEM);
}

@@ -1369,10 +1373,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
skb->dev = tun->dev;
generic_xdp_tx(skb, xdp_prog);
rcu_read_unlock();
+ preempt_enable();
return NULL;
}

rcu_read_unlock();
+ preempt_enable();

return skb;

@@ -1380,6 +1386,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
put_page(alloc_frag->page);
err_xdp:
rcu_read_unlock();
+ preempt_enable();
this_cpu_inc(tun->pcpu_stats->rx_dropped);
return NULL;
}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7927e28f5336..6a785595b9b8 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1995,8 +1995,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
}

/* Make sure NAPI is not using any XDP TX queues for RX. */
- for (i = 0; i < vi->max_queue_pairs; i++)
- napi_disable(&vi->rq[i].napi);
+ if (netif_running(dev))
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ napi_disable(&vi->rq[i].napi);

netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
err = _virtnet_set_queues(vi, curr_qp + xdp_qp);
@@ -2015,7 +2016,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
}
if (old_prog)
bpf_prog_put(old_prog);
- virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
+ if (netif_running(dev))
+ virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
}

return 0;
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 0d2e00ece804..f3c1d5245978 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -574,7 +574,10 @@ static void ppp_timer(unsigned long arg)
ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0,
0, NULL);
proto->restart_counter--;
- } else
+ } else if (netif_carrier_ok(proto->dev))
+ ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0,
+ 0, NULL);
+ else
ppp_cp_event(proto->dev, proto->pid, TO_BAD, 0, 0,
0, NULL);
break;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 33d4431c2b4b..93a082e0bdd4 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -88,7 +88,6 @@ enum nvme_rdma_queue_flags {

struct nvme_rdma_queue {
struct nvme_rdma_qe *rsp_ring;
- atomic_t sig_count;
int queue_size;
size_t cmnd_capsule_len;
struct nvme_rdma_ctrl *ctrl;
@@ -521,7 +520,6 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
queue->cmnd_capsule_len = sizeof(struct nvme_command);

queue->queue_size = queue_size;
- atomic_set(&queue->sig_count, 0);

queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue,
RDMA_PS_TCP, IB_QPT_RC);
@@ -1232,21 +1230,9 @@ static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
nvme_end_request(rq, req->status, req->result);
}

-/*
- * We want to signal completion at least every queue depth/2. This returns the
- * largest power of two that is not above half of (queue size + 1) to optimize
- * (avoid divisions).
- */
-static inline bool nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
-{
- int limit = 1 << ilog2((queue->queue_size + 1) / 2);
-
- return (atomic_inc_return(&queue->sig_count) & (limit - 1)) == 0;
-}
-
static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge,
- struct ib_send_wr *first, bool flush)
+ struct ib_send_wr *first)
{
struct ib_send_wr wr, *bad_wr;
int ret;
@@ -1255,31 +1241,12 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
sge->length = sizeof(struct nvme_command),
sge->lkey = queue->device->pd->local_dma_lkey;

- qe->cqe.done = nvme_rdma_send_done;
-
wr.next = NULL;
wr.wr_cqe = &qe->cqe;
wr.sg_list = sge;
wr.num_sge = num_sge;
wr.opcode = IB_WR_SEND;
- wr.send_flags = 0;
-
- /*
- * Unsignalled send completions are another giant desaster in the
- * IB Verbs spec: If we don't regularly post signalled sends
- * the send queue will fill up and only a QP reset will rescue us.
- * Would have been way to obvious to handle this in hardware or
- * at least the RDMA stack..
- *
- * Always signal the flushes. The magic request used for the flush
- * sequencer is not allocated in our driver's tagset and it's
- * triggered to be freed by blk_cleanup_queue(). So we need to
- * always mark it as signaled to ensure that the "wr_cqe", which is
- * embedded in request's payload, is not freed when __ib_process_cq()
- * calls wr_cqe->done().
- */
- if (nvme_rdma_queue_sig_limit(queue) || flush)
- wr.send_flags |= IB_SEND_SIGNALED;
+ wr.send_flags = IB_SEND_SIGNALED;

if (first)
first->next = &wr;
@@ -1329,6 +1296,12 @@ static struct blk_mq_tags *nvme_rdma_tagset(struct nvme_rdma_queue *queue)
return queue->ctrl->tag_set.tags[queue_idx - 1];
}

+static void nvme_rdma_async_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ if (unlikely(wc->status != IB_WC_SUCCESS))
+ nvme_rdma_wr_error(cq, wc, "ASYNC");
+}
+
static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
{
struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg);
@@ -1350,10 +1323,12 @@ static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
cmd->common.flags |= NVME_CMD_SGL_METABUF;
nvme_rdma_set_sg_null(cmd);

+ sqe->cqe.done = nvme_rdma_async_done;
+
ib_dma_sync_single_for_device(dev, sqe->dma, sizeof(*cmd),
DMA_TO_DEVICE);

- ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL, false);
+ ret = nvme_rdma_post_send(queue, sqe, &sge, 1, NULL);
WARN_ON_ONCE(ret);
}

@@ -1639,7 +1614,6 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
struct nvme_rdma_qe *sqe = &req->sqe;
struct nvme_command *c = sqe->data;
- bool flush = false;
struct ib_device *dev;
blk_status_t ret;
int err;
@@ -1668,13 +1642,13 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
goto err;
}

+ sqe->cqe.done = nvme_rdma_send_done;
+
ib_dma_sync_single_for_device(dev, sqe->dma,
sizeof(struct nvme_command), DMA_TO_DEVICE);

- if (req_op(rq) == REQ_OP_FLUSH)
- flush = true;
err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
- req->mr->need_inval ? &req->reg_wr.wr : NULL, flush);
+ req->mr->need_inval ? &req->reg_wr.wr : NULL);
if (unlikely(err)) {
nvme_rdma_unmap_data(queue, rq);
goto err;
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index cae54f8320be..633e55c57b13 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -803,10 +803,14 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)

/*
* Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe
- * hierarchies.
+ * hierarchies. Note that some PCIe host implementations omit
+ * the root ports entirely, in which case a downstream port on
+ * a switch may become the root of the link state chain for all
+ * its subordinate endpoints.
*/
if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT ||
- pci_pcie_type(pdev) == PCI_EXP_TYPE_PCIE_BRIDGE) {
+ pci_pcie_type(pdev) == PCI_EXP_TYPE_PCIE_BRIDGE ||
+ !pdev->bus->parent->self) {
link->root = link;
} else {
struct pcie_link_state *parent;
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 92dd4aef21a3..6b1e83539a9d 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -580,6 +580,11 @@ struct qeth_cmd_buffer {
void (*callback) (struct qeth_channel *, struct qeth_cmd_buffer *);
};

+static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob)
+{
+ return (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE);
+}
+
/**
* definition of a qeth channel, used for read and write
*/
@@ -834,7 +839,7 @@ struct qeth_trap_id {
*/
static inline int qeth_get_elements_for_range(addr_t start, addr_t end)
{
- return PFN_UP(end - 1) - PFN_DOWN(start);
+ return PFN_UP(end) - PFN_DOWN(start);
}

static inline int qeth_get_micros(void)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 7c7a244b6684..145b57762d8f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2073,7 +2073,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
unsigned long flags;
struct qeth_reply *reply = NULL;
unsigned long timeout, event_timeout;
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = NULL;

QETH_CARD_TEXT(card, 2, "sendctl");

@@ -2087,23 +2087,27 @@ int qeth_send_control_data(struct qeth_card *card, int len,
}
reply->callback = reply_cb;
reply->param = reply_param;
- if (card->state == CARD_STATE_DOWN)
- reply->seqno = QETH_IDX_COMMAND_SEQNO;
- else
- reply->seqno = card->seqno.ipa++;
+
init_waitqueue_head(&reply->wait_q);
- spin_lock_irqsave(&card->lock, flags);
- list_add_tail(&reply->list, &card->cmd_waiter_list);
- spin_unlock_irqrestore(&card->lock, flags);
QETH_DBF_HEX(CTRL, 2, iob->data, QETH_DBF_CTRL_LEN);

while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
- qeth_prepare_control_data(card, len, iob);

- if (IS_IPA(iob->data))
+ if (IS_IPA(iob->data)) {
+ cmd = __ipa_cmd(iob);
+ cmd->hdr.seqno = card->seqno.ipa++;
+ reply->seqno = cmd->hdr.seqno;
event_timeout = QETH_IPA_TIMEOUT;
- else
+ } else {
+ reply->seqno = QETH_IDX_COMMAND_SEQNO;
event_timeout = QETH_TIMEOUT;
+ }
+ qeth_prepare_control_data(card, len, iob);
+
+ spin_lock_irqsave(&card->lock, flags);
+ list_add_tail(&reply->list, &card->cmd_waiter_list);
+ spin_unlock_irqrestore(&card->lock, flags);
+
timeout = jiffies + event_timeout;

QETH_CARD_TEXT(card, 6, "noirqpnd");
@@ -2128,9 +2132,8 @@ int qeth_send_control_data(struct qeth_card *card, int len,

/* we have only one long running ipassist, since we can ensure
process context of this command we can sleep */
- cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
- if ((cmd->hdr.command == IPA_CMD_SETIP) &&
- (cmd->hdr.prot_version == QETH_PROT_IPV4)) {
+ if (cmd && cmd->hdr.command == IPA_CMD_SETIP &&
+ cmd->hdr.prot_version == QETH_PROT_IPV4) {
if (!wait_event_timeout(reply->wait_q,
atomic_read(&reply->received), event_timeout))
goto time_err;
@@ -2894,7 +2897,7 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card,
memset(cmd, 0, sizeof(struct qeth_ipa_cmd));
cmd->hdr.command = command;
cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST;
- cmd->hdr.seqno = card->seqno.ipa;
+ /* cmd->hdr.seqno is set by qeth_send_control_data() */
cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type);
cmd->hdr.rel_adapter_no = (__u8) card->info.portno;
if (card->options.layer2)
@@ -3859,10 +3862,12 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
int qeth_get_elements_no(struct qeth_card *card,
struct sk_buff *skb, int extra_elems, int data_offset)
{
- int elements = qeth_get_elements_for_range(
- (addr_t)skb->data + data_offset,
- (addr_t)skb->data + skb_headlen(skb)) +
- qeth_get_elements_for_frags(skb);
+ addr_t end = (addr_t)skb->data + skb_headlen(skb);
+ int elements = qeth_get_elements_for_frags(skb);
+ addr_t start = (addr_t)skb->data + data_offset;
+
+ if (start != end)
+ elements += qeth_get_elements_for_range(start, end);

if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index e5833837b799..8727b9517de8 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -40,8 +40,40 @@ struct qeth_ipaddr {
unsigned int pfxlen;
} a6;
} u;
-
};
+
+static inline bool qeth_l3_addr_match_ip(struct qeth_ipaddr *a1,
+ struct qeth_ipaddr *a2)
+{
+ if (a1->proto != a2->proto)
+ return false;
+ if (a1->proto == QETH_PROT_IPV6)
+ return ipv6_addr_equal(&a1->u.a6.addr, &a2->u.a6.addr);
+ return a1->u.a4.addr == a2->u.a4.addr;
+}
+
+static inline bool qeth_l3_addr_match_all(struct qeth_ipaddr *a1,
+ struct qeth_ipaddr *a2)
+{
+ /* Assumes that the pair was obtained via qeth_l3_addr_find_by_ip(),
+ * so 'proto' and 'addr' match for sure.
+ *
+ * For ucast:
+ * - 'mac' is always 0.
+ * - 'mask'/'pfxlen' for RXIP/VIPA is always 0. For NORMAL, matching
+ * values are required to avoid mixups in takeover eligibility.
+ *
+ * For mcast,
+ * - 'mac' is mapped from the IP, and thus always matches.
+ * - 'mask'/'pfxlen' is always 0.
+ */
+ if (a1->type != a2->type)
+ return false;
+ if (a1->proto == QETH_PROT_IPV6)
+ return a1->u.a6.pfxlen == a2->u.a6.pfxlen;
+ return a1->u.a4.mask == a2->u.a4.mask;
+}
+
static inline u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr)
{
u64 ret = 0;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 36dee176f8e2..96576e729222 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -149,6 +149,24 @@ int qeth_l3_string_to_ipaddr(const char *buf, enum qeth_prot_versions proto,
return -EINVAL;
}

+static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card,
+ struct qeth_ipaddr *query)
+{
+ u64 key = qeth_l3_ipaddr_hash(query);
+ struct qeth_ipaddr *addr;
+
+ if (query->is_multicast) {
+ hash_for_each_possible(card->ip_mc_htable, addr, hnode, key)
+ if (qeth_l3_addr_match_ip(addr, query))
+ return addr;
+ } else {
+ hash_for_each_possible(card->ip_htable, addr, hnode, key)
+ if (qeth_l3_addr_match_ip(addr, query))
+ return addr;
+ }
+ return NULL;
+}
+
static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
{
int i, j;
@@ -202,34 +220,6 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
return rc;
}

-inline int
-qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2)
-{
- return addr1->proto == addr2->proto &&
- !memcmp(&addr1->u, &addr2->u, sizeof(addr1->u)) &&
- !memcmp(&addr1->mac, &addr2->mac, sizeof(addr1->mac));
-}
-
-static struct qeth_ipaddr *
-qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
-{
- struct qeth_ipaddr *addr;
-
- if (tmp_addr->is_multicast) {
- hash_for_each_possible(card->ip_mc_htable, addr,
- hnode, qeth_l3_ipaddr_hash(tmp_addr))
- if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
- return addr;
- } else {
- hash_for_each_possible(card->ip_htable, addr,
- hnode, qeth_l3_ipaddr_hash(tmp_addr))
- if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
- return addr;
- }
-
- return NULL;
-}
-
int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
{
int rc = 0;
@@ -244,23 +234,18 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
}

- addr = qeth_l3_ip_from_hash(card, tmp_addr);
- if (!addr)
+ addr = qeth_l3_find_addr_by_ip(card, tmp_addr);
+ if (!addr || !qeth_l3_addr_match_all(addr, tmp_addr))
return -ENOENT;

addr->ref_counter--;
- if (addr->ref_counter > 0 && (addr->type == QETH_IP_TYPE_NORMAL ||
- addr->type == QETH_IP_TYPE_RXIP))
+ if (addr->type == QETH_IP_TYPE_NORMAL && addr->ref_counter > 0)
return rc;
if (addr->in_progress)
return -EINPROGRESS;

- if (!qeth_card_hw_is_reachable(card)) {
- addr->disp_flag = QETH_DISP_ADDR_DELETE;
- return 0;
- }
-
- rc = qeth_l3_deregister_addr_entry(card, addr);
+ if (qeth_card_hw_is_reachable(card))
+ rc = qeth_l3_deregister_addr_entry(card, addr);

hash_del(&addr->hnode);
kfree(addr);
@@ -272,6 +257,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
{
int rc = 0;
struct qeth_ipaddr *addr;
+ char buf[40];

QETH_CARD_TEXT(card, 4, "addip");

@@ -282,8 +268,20 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
}

- addr = qeth_l3_ip_from_hash(card, tmp_addr);
- if (!addr) {
+ addr = qeth_l3_find_addr_by_ip(card, tmp_addr);
+ if (addr) {
+ if (tmp_addr->type != QETH_IP_TYPE_NORMAL)
+ return -EADDRINUSE;
+ if (qeth_l3_addr_match_all(addr, tmp_addr)) {
+ addr->ref_counter++;
+ return 0;
+ }
+ qeth_l3_ipaddr_to_string(tmp_addr->proto, (u8 *)&tmp_addr->u,
+ buf);
+ dev_warn(&card->gdev->dev,
+ "Registering IP address %s failed\n", buf);
+ return -EADDRINUSE;
+ } else {
addr = qeth_l3_get_addr_buffer(tmp_addr->proto);
if (!addr)
return -ENOMEM;
@@ -323,19 +321,15 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
(rc == IPA_RC_LAN_OFFLINE)) {
addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
if (addr->ref_counter < 1) {
- qeth_l3_delete_ip(card, addr);
+ qeth_l3_deregister_addr_entry(card, addr);
+ hash_del(&addr->hnode);
kfree(addr);
}
} else {
hash_del(&addr->hnode);
kfree(addr);
}
- } else {
- if (addr->type == QETH_IP_TYPE_NORMAL ||
- addr->type == QETH_IP_TYPE_RXIP)
- addr->ref_counter++;
}
-
return rc;
}

@@ -403,11 +397,7 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
spin_lock_bh(&card->ip_lock);

hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
- if (addr->disp_flag == QETH_DISP_ADDR_DELETE) {
- qeth_l3_deregister_addr_entry(card, addr);
- hash_del(&addr->hnode);
- kfree(addr);
- } else if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+ if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
if (addr->proto == QETH_PROT_IPV4) {
addr->in_progress = 1;
spin_unlock_bh(&card->ip_lock);
@@ -723,12 +713,7 @@ int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto,
return -ENOMEM;

spin_lock_bh(&card->ip_lock);
-
- if (qeth_l3_ip_from_hash(card, ipaddr))
- rc = -EEXIST;
- else
- qeth_l3_add_ip(card, ipaddr);
-
+ rc = qeth_l3_add_ip(card, ipaddr);
spin_unlock_bh(&card->ip_lock);

kfree(ipaddr);
@@ -791,12 +776,7 @@ int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
return -ENOMEM;

spin_lock_bh(&card->ip_lock);
-
- if (qeth_l3_ip_from_hash(card, ipaddr))
- rc = -EEXIST;
- else
- qeth_l3_add_ip(card, ipaddr);
-
+ rc = qeth_l3_add_ip(card, ipaddr);
spin_unlock_bh(&card->ip_lock);

kfree(ipaddr);
@@ -1404,8 +1384,9 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
memcpy(tmp->mac, buf, sizeof(tmp->mac));
tmp->is_multicast = 1;

- ipm = qeth_l3_ip_from_hash(card, tmp);
+ ipm = qeth_l3_find_addr_by_ip(card, tmp);
if (ipm) {
+ /* for mcast, by-IP match means full match */
ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
} else {
ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
@@ -1488,8 +1469,9 @@ qeth_l3_add_mc6_to_hash(struct qeth_card *card, struct inet6_dev *in6_dev)
sizeof(struct in6_addr));
tmp->is_multicast = 1;

- ipm = qeth_l3_ip_from_hash(card, tmp);
+ ipm = qeth_l3_find_addr_by_ip(card, tmp);
if (ipm) {
+ /* for mcast, by-IP match means full match */
ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
continue;
}
@@ -2633,11 +2615,12 @@ static void qeth_tso_fill_header(struct qeth_card *card,
static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
struct sk_buff *skb, int extra_elems)
{
- addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
- int elements = qeth_get_elements_for_range(
- tcpdptr,
- (addr_t)skb->data + skb_headlen(skb)) +
- qeth_get_elements_for_frags(skb);
+ addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
+ addr_t end = (addr_t)skb->data + skb_headlen(skb);
+ int elements = qeth_get_elements_for_frags(skb);
+
+ if (start != end)
+ elements += qeth_get_elements_for_range(start, end);

if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
QETH_DBF_MESSAGE(2,
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 92155cce926d..fb4e6a7ee521 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -338,11 +338,12 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
{
struct page *page[1];
struct vm_area_struct *vma;
+ struct vm_area_struct *vmas[1];
int ret;

if (mm == current->mm) {
- ret = get_user_pages_fast(vaddr, 1, !!(prot & IOMMU_WRITE),
- page);
+ ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE),
+ page, vmas);
} else {
unsigned int flags = 0;

@@ -351,7 +352,18 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,

down_read(&mm->mmap_sem);
ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
- NULL, NULL);
+ vmas, NULL);
+ /*
+ * The lifetime of a vaddr_get_pfn() page pin is
+ * userspace-controlled. In the fs-dax case this could
+ * lead to indefinite stalls in filesystem operations.
+ * Disallow attempts to pin fs-dax pages via this
+ * interface.
+ */
+ if (ret > 0 && vma_is_fsdax(vmas[0])) {
+ ret = -EOPNOTSUPP;
+ put_page(page[0]);
+ }
up_read(&mm->mmap_sem);
}

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 883881b16c86..4447e0fe9b55 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -422,7 +422,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);

- return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize);
}

BTRFS_ATTR(nodesize, btrfs_nodesize_show);
@@ -432,8 +432,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);

- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}

BTRFS_ATTR(sectorsize, btrfs_sectorsize_show);
@@ -443,8 +442,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);

- return snprintf(buf, PAGE_SIZE, "%u\n",
- fs_info->super_copy->sectorsize);
+ return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
}

BTRFS_ATTR(clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f615d59b0489..46bda13e5727 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1722,19 +1722,23 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)

super = fs_info->super_copy;

+ /* update latest btrfs_super_block::chunk_root refs */
root_item = &fs_info->chunk_root->root_item;
- super->chunk_root = root_item->bytenr;
- super->chunk_root_generation = root_item->generation;
- super->chunk_root_level = root_item->level;
+ btrfs_set_super_chunk_root(super, root_item->bytenr);
+ btrfs_set_super_chunk_root_generation(super, root_item->generation);
+ btrfs_set_super_chunk_root_level(super, root_item->level);

+ /* update latest btrfs_super_block::root refs */
root_item = &fs_info->tree_root->root_item;
- super->root = root_item->bytenr;
- super->generation = root_item->generation;
- super->root_level = root_item->level;
+ btrfs_set_super_root(super, root_item->bytenr);
+ btrfs_set_super_generation(super, root_item->generation);
+ btrfs_set_super_root_level(super, root_item->level);
+
if (btrfs_test_opt(fs_info, SPACE_CACHE))
- super->cache_generation = root_item->generation;
+ btrfs_set_super_cache_generation(super, root_item->generation);
if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
- super->uuid_tree_generation = root_item->generation;
+ btrfs_set_super_uuid_tree_generation(super,
+ root_item->generation);
}

int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b53e66d9abd7..625a84aa6484 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1252,8 +1252,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
*/
if (dio->is_async && iov_iter_rw(iter) == WRITE) {
retval = 0;
- if ((iocb->ki_filp->f_flags & O_DSYNC) ||
- IS_SYNC(iocb->ki_filp->f_mapping->host))
+ if (iocb->ki_flags & IOCB_DSYNC)
retval = dio_set_defer_completion(dio);
else if (!dio->inode->i_sb->s_dio_done_wq) {
/*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 440281f8564d..d54f41a63dbf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3185,7 +3185,7 @@ static inline bool vma_is_fsdax(struct vm_area_struct *vma)
if (!vma_is_dax(vma))
return false;
inode = file_inode(vma->vm_file);
- if (inode->i_mode == S_IFCHR)
+ if (S_ISCHR(inode->i_mode))
return false; /* device-dax */
return true;
}
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index fbc98e2c8228..132e3f5a2e0d 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -72,7 +72,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \
BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \
\
- _i &= _mask; \
- _i; \
+ (typeof(_i)) (_i & _mask); \
})
#endif /* _LINUX_NOSPEC_H */
diff --git a/include/net/udplite.h b/include/net/udplite.h
index 81bdbf97319b..9185e45b997f 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -64,6 +64,7 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh)
UDP_SKB_CB(skb)->cscov = cscov;
if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->ip_summed = CHECKSUM_NONE;
+ skb->csum_valid = 0;
}

return 0;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index db5e6daadd94..9fe525f410bf 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1834,6 +1834,12 @@ int timers_dead_cpu(unsigned int cpu)
raw_spin_lock_irq(&new_base->lock);
raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);

+ /*
+ * The current CPUs base clock might be stale. Update it
+ * before moving the timers over.
+ */
+ forward_timer_base(new_base);
+
BUG_ON(old_base->running_timer);

for (i = 0; i < WHEEL_SIZE; i++)
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 5d5d413a6cf8..a097a8613a02 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -235,6 +235,9 @@ static ssize_t brport_show(struct kobject *kobj,
struct brport_attribute *brport_attr = to_brport_attr(attr);
struct net_bridge_port *p = to_brport(kobj);

+ if (!brport_attr->show)
+ return -EINVAL;
+
return brport_attr->show(p, buf);
}

diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 233a30040c91..9b8a53568b0f 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -157,6 +157,8 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid
masterv = br_vlan_find(vg, vid);
if (WARN_ON(!masterv))
return NULL;
+ refcount_set(&masterv->refcnt, 1);
+ return masterv;
}
refcount_inc(&masterv->refcnt);

diff --git a/net/core/dev.c b/net/core/dev.c
index d33bbed640b1..c75ef9d8105a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2343,8 +2343,11 @@ EXPORT_SYMBOL(netdev_set_num_tc);
*/
int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
{
+ bool disabling;
int rc;

+ disabling = txq < dev->real_num_tx_queues;
+
if (txq < 1 || txq > dev->num_tx_queues)
return -EINVAL;

@@ -2360,15 +2363,19 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
if (dev->num_tc)
netif_setup_tc(dev, txq);

- if (txq < dev->real_num_tx_queues) {
+ dev->real_num_tx_queues = txq;
+
+ if (disabling) {
+ synchronize_net();
qdisc_reset_all_tx_gt(dev, txq);
#ifdef CONFIG_XPS
netif_reset_xps_queues_gt(dev, txq);
#endif
}
+ } else {
+ dev->real_num_tx_queues = txq;
}

- dev->real_num_tx_queues = txq;
return 0;
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 00ecec4891f3..7f980bd7426e 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -66,6 +66,7 @@ struct net_rate_estimator {
static void est_fetch_counters(struct net_rate_estimator *e,
struct gnet_stats_basic_packed *b)
{
+ memset(b, 0, sizeof(*b));
if (e->stats_lock)
spin_lock(e->stats_lock);

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index aff3751df950..1ee6c0d8dde4 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -654,6 +654,11 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
fi->fib_nh, cfg, extack))
return 1;
}
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ if (cfg->fc_flow &&
+ cfg->fc_flow != fi->fib_nh->nh_tclassid)
+ return 1;
+#endif
if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
(!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw))
return 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0ba88efca7ad..9ff06c5051ae 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -128,10 +128,13 @@ static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost __read_mostly = HZ;
static int ip_rt_error_burst __read_mostly = 5 * HZ;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
-static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
+static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;

static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
+
+static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU;
+
/*
* Interface to generic destination cache.
*/
@@ -1829,6 +1832,8 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
return skb_get_hash_raw(skb) >> 1;
memset(&hash_keys, 0, sizeof(hash_keys));
skb_flow_dissect_flow_keys(skb, &keys, flag);
+
+ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
hash_keys.ports.src = keys.ports.src;
@@ -2934,7 +2939,8 @@ static struct ctl_table ipv4_route_table[] = {
.data = &ip_rt_min_pmtu,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &ip_min_valid_pmtu,
},
{
.procname = "min_adv_mss",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d9d215e27b8a..14474acea0bb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2013,11 +2013,6 @@ void tcp_enter_loss(struct sock *sk)
/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
- *
- * In theory F-RTO can be used repeatedly during loss recovery.
- * In practice this interacts badly with broken middle-boxes that
- * falsely raise the receive window, which results in repeated
- * timeouts and stop-and-go behavior.
*/
tp->frto = sysctl_tcp_frto &&
(new_recovery || icsk->icsk_retransmits) &&
@@ -2699,18 +2694,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
tcp_try_undo_loss(sk, false))
return;

- /* The ACK (s)acks some never-retransmitted data meaning not all
- * the data packets before the timeout were lost. Therefore we
- * undo the congestion window and state. This is essentially
- * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since
- * a retransmitted skb is permantly marked, we can apply such an
- * operation even if F-RTO was not used.
- */
- if ((flag & FLAG_ORIG_SACK_ACKED) &&
- tcp_try_undo_loss(sk, tp->undo_marker))
- return;
-
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if ((flag & FLAG_ORIG_SACK_ACKED) &&
+ tcp_try_undo_loss(sk, true))
+ return;
+
if (after(tp->snd_nxt, tp->high_seq)) {
if (flag & FLAG_DATA_SACKED || is_dupack)
tp->frto = 0; /* Step 3.a. loss was real */
@@ -4020,6 +4011,7 @@ void tcp_reset(struct sock *sk)
/* This barrier is coupled with smp_rmb() in tcp_poll() */
smp_wmb();

+ tcp_write_queue_purge(sk);
tcp_done(sk);

if (!sock_flag(sk, SOCK_DEAD))
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cd3d60bb7cc8..83d11cd2eb65 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1681,7 +1681,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
*/
segs = max_t(u32, bytes / mss_now, min_tso_segs);

- return min_t(u32, segs, sk->sk_gso_max_segs);
+ return segs;
}
EXPORT_SYMBOL(tcp_tso_autosize);

@@ -1693,8 +1693,10 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;

- return tso_segs ? :
- tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs);
+ if (!tso_segs)
+ tso_segs = tcp_tso_autosize(sk, mss_now,
+ sysctl_tcp_min_tso_segs);
+ return min_t(u32, tso_segs, sk->sk_gso_max_segs);
}

/* Returns the portion of skb which can be sent right away */
@@ -1973,6 +1975,24 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
}
}

+static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
+{
+ struct sk_buff *skb, *next;
+
+ skb = tcp_send_head(sk);
+ tcp_for_write_queue_from_safe(skb, next, sk) {
+ if (len <= skb->len)
+ break;
+
+ if (unlikely(TCP_SKB_CB(skb)->eor))
+ return false;
+
+ len -= skb->len;
+ }
+
+ return true;
+}
+
/* Create a new MTU probe if we are ready.
* MTU probe is regularly attempting to increase the path MTU by
* deliberately sending larger packets. This discovers routing
@@ -2045,6 +2065,9 @@ static int tcp_mtu_probe(struct sock *sk)
return 0;
}

+ if (!tcp_can_coalesce_send_queue_head(sk, probe_size))
+ return -1;
+
/* We're allowed to probe. Build it now. */
nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
if (!nskb)
@@ -2080,6 +2103,10 @@ static int tcp_mtu_probe(struct sock *sk)
/* We've eaten all the data from this skb.
* Throw it away. */
TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ /* If this is the last SKB we copy and eor is set
+ * we need to propagate it to the new skb.
+ */
+ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
} else {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ebfbccae62fd..c79fa6f6b758 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2032,6 +2032,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
err = udplite_checksum_init(skb, uh);
if (err)
return err;
+
+ if (UDP_SKB_CB(skb)->partial_cov) {
+ skb->csum = inet_compute_pseudo(skb, proto);
+ return 0;
+ }
}

/* Note, we are only interested in != 0 or == 0, thus the
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index ec43d18b5ff9..547515e8450a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
err = udplite_checksum_init(skb, uh);
if (err)
return err;
+
+ if (UDP_SKB_CB(skb)->partial_cov) {
+ skb->csum = ip6_compute_pseudo(skb, proto);
+ return 0;
+ }
}

/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e79854cc5790..cac815cc8600 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -176,7 +176,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel *t = netdev_priv(dev);

- if (t->dev == sitn->fb_tunnel_dev) {
+ if (dev == sitn->fb_tunnel_dev) {
ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
t->ip6rd.relay_prefix = 0;
t->ip6rd.prefixlen = 16;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 533fd0503ba0..9219bc134109 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2276,7 +2276,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
if (cb->start) {
ret = cb->start(cb);
if (ret)
- goto error_unlock;
+ goto error_put;
}

nlk->cb_running = true;
@@ -2296,6 +2296,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
*/
return -EINTR;

+error_put:
+ module_put(control->module);
error_unlock:
sock_put(sk);
mutex_unlock(nlk->cb_mutex);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index d444daf1ac04..6f02499ef007 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1081,6 +1081,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
{
struct sk_buff *tmp;
struct net *net, *prev = NULL;
+ bool delivered = false;
int err;

for_each_net_rcu(net) {
@@ -1092,14 +1093,21 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
}
err = nlmsg_multicast(prev->genl_sock, tmp,
portid, group, flags);
- if (err)
+ if (!err)
+ delivered = true;
+ else if (err != -ESRCH)
goto error;
}

prev = net;
}

- return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+ err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+ if (!err)
+ delivered = true;
+ else if (err != -ESRCH)
+ goto error;
+ return delivered ? 0 : -ESRCH;
error:
kfree_skb(skb);
return err;
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 71e6f713fbe7..5b67cb5d47f0 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -395,7 +395,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
(char *)&opt, sizeof(opt));
if (ret == 0) {
ret = kernel_sendmsg(conn->params.local->socket, &msg,
- iov, 1, iov[0].iov_len);
+ iov, 2, len);

opt = IPV6_PMTUDISC_DO;
kernel_setsockopt(conn->params.local->socket,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 934c239cf98d..c2fab4bcb8be 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -871,13 +871,18 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
if (tca[TCA_CHAIN] &&
nla_get_u32(tca[TCA_CHAIN]) != chain->index)
continue;
- if (!tcf_chain_dump(chain, skb, cb, index_start, &index))
+ if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) {
+ err = -EMSGSIZE;
break;
+ }
}

cb->args[0] = index;

out:
+ /* If we did no progress, the error (EMSGSIZE) is real */
+ if (skb->len == 0 && err)
+ return err;
return skb->len;
}

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index b58eccb21f03..ba37d8f57e68 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -398,10 +398,12 @@ static int u32_init(struct tcf_proto *tp)
static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
bool free_pf)
{
+ struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
+
tcf_exts_destroy(&n->exts);
tcf_exts_put_net(&n->exts);
- if (n->ht_down)
- n->ht_down->refcnt--;
+ if (ht && --ht->refcnt == 0)
+ kfree(ht);
#ifdef CONFIG_CLS_U32_PERF
if (free_pf)
free_percpu(n->pf);
@@ -649,16 +651,15 @@ static void u32_destroy(struct tcf_proto *tp)

hlist_del(&tp_c->hnode);

- for (ht = rtnl_dereference(tp_c->hlist);
- ht;
- ht = rtnl_dereference(ht->next)) {
- ht->refcnt--;
- u32_clear_hnode(tp, ht);
- }
-
while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) {
+ u32_clear_hnode(tp, ht);
RCU_INIT_POINTER(tp_c->hlist, ht->next);
- kfree_rcu(ht, rcu);
+
+ /* u32_destroy_key() will later free ht for us, if it's
+ * still referenced by some knode
+ */
+ if (--ht->refcnt == 0)
+ kfree_rcu(ht, rcu);
}

kfree(tp_c);
@@ -927,7 +928,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
if (TC_U32_KEY(n->handle) == 0)
return -EINVAL;

- if (n->flags != flags)
+ if ((n->flags ^ flags) &
+ ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW))
return -EINVAL;

new = u32_init_knode(tp, n);
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 141c9c466ec1..0247cc432e02 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -897,15 +897,12 @@ int sctp_hash_transport(struct sctp_transport *t)
rhl_for_each_entry_rcu(transport, tmp, list, node)
if (transport->asoc->ep == t->asoc->ep) {
rcu_read_unlock();
- err = -EEXIST;
- goto out;
+ return -EEXIST;
}
rcu_read_unlock();

err = rhltable_insert_key(&sctp_transport_hashtable, &arg,
&t->node, sctp_hash_params);
-
-out:
if (err)
pr_err_once("insert transport fail, errno %d\n", err);

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 3b18085e3b10..f27a9718554c 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -326,8 +326,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
bdst = ip6_dst_lookup_flow(sk, fl6, final_p);

- if (!IS_ERR(bdst) &&
- ipv6_chk_addr(dev_net(bdst->dev),
+ if (IS_ERR(bdst))
+ continue;
+
+ if (ipv6_chk_addr(dev_net(bdst->dev),
&laddr->a.v6.sin6_addr, bdst->dev, 1)) {
if (!IS_ERR_OR_NULL(dst))
dst_release(dst);
@@ -336,8 +338,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
}

bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
- if (matchlen > bmatchlen)
+ if (matchlen > bmatchlen) {
+ dst_release(bdst);
continue;
+ }

if (!IS_ERR_OR_NULL(dst))
dst_release(dst);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index fcd80feb293f..df22a9c352ad 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -514,22 +514,20 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
if (IS_ERR(rt))
continue;

- if (!dst)
- dst = &rt->dst;
-
/* Ensure the src address belongs to the output
* interface.
*/
odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
false);
if (!odev || odev->ifindex != fl4->flowi4_oif) {
- if (&rt->dst != dst)
+ if (!dst)
+ dst = &rt->dst;
+ else
dst_release(&rt->dst);
continue;
}

- if (dst != &rt->dst)
- dst_release(dst);
+ dst_release(dst);
dst = &rt->dst;
break;
}
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 514465b03829..e4a400f88168 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1378,9 +1378,14 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc,
struct sctp_chunk *retval;
struct sk_buff *skb;
struct sock *sk;
+ int chunklen;
+
+ chunklen = SCTP_PAD4(sizeof(*chunk_hdr) + paylen);
+ if (chunklen > SCTP_MAX_CHUNK_LEN)
+ goto nodata;

/* No need to allocate LL here, as this is only a chunk. */
- skb = alloc_skb(SCTP_PAD4(sizeof(*chunk_hdr) + paylen), gfp);
+ skb = alloc_skb(chunklen, gfp);
if (!skb)
goto nodata;

diff --git a/sound/core/control.c b/sound/core/control.c
index 56b3e2d49c82..af7e6165e21e 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -888,7 +888,7 @@ static int snd_ctl_elem_read(struct snd_card *card,

index_offset = snd_ctl_get_ioff(kctl, &control->id);
vd = &kctl->vd[index_offset];
- if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) && kctl->get == NULL)
+ if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL)
return -EPERM;

snd_ctl_build_ioff(&control->id, kctl, index_offset);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index c71dcacea807..96143df19b21 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -181,7 +181,7 @@ static const struct kernel_param_ops param_ops_xint = {
};
#define param_check_xint param_check_int

-static int power_save = CONFIG_SND_HDA_POWER_SAVE_DEFAULT;
+static int power_save = -1;
module_param(power_save, xint, 0644);
MODULE_PARM_DESC(power_save, "Automatic power-saving timeout "
"(in second, 0 = disable).");
@@ -2186,6 +2186,24 @@ static int azx_probe(struct pci_dev *pci,
return err;
}

+#ifdef CONFIG_PM
+/* On some boards setting power_save to a non 0 value leads to clicking /
+ * popping sounds when ever we enter/leave powersaving mode. Ideally we would
+ * figure out how to avoid these sounds, but that is not always feasible.
+ * So we keep a list of devices where we disable powersaving as its known
+ * to causes problems on these devices.
+ */
+static struct snd_pci_quirk power_save_blacklist[] = {
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
+ SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0),
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
+ SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0),
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */
+ SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0),
+ {}
+};
+#endif /* CONFIG_PM */
+
/* number of codec slots for each chipset: 0 = default slots (i.e. 4) */
static unsigned int azx_max_codecs[AZX_NUM_DRIVERS] = {
[AZX_DRIVER_NVIDIA] = 8,
@@ -2198,6 +2216,7 @@ static int azx_probe_continue(struct azx *chip)
struct hdac_bus *bus = azx_bus(chip);
struct pci_dev *pci = chip->pci;
int dev = chip->dev_index;
+ int val;
int err;

hda->probe_continued = 1;
@@ -2278,7 +2297,22 @@ static int azx_probe_continue(struct azx *chip)

chip->running = 1;
azx_add_card_list(chip);
- snd_hda_set_power_save(&chip->bus, power_save * 1000);
+
+ val = power_save;
+#ifdef CONFIG_PM
+ if (val == -1) {
+ const struct snd_pci_quirk *q;
+
+ val = CONFIG_SND_HDA_POWER_SAVE_DEFAULT;
+ q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist);
+ if (q && val) {
+ dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n",
+ q->subvendor, q->subdevice);
+ val = 0;
+ }
+ }
+#endif /* CONFIG_PM */
+ snd_hda_set_power_save(&chip->bus, val * 1000);
if (azx_has_pm_runtime(chip) || hda->use_vga_switcheroo)
pm_runtime_put_autosuspend(&pci->dev);

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b7acffdf16a4..454476b47b79 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4852,13 +4852,14 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec,

if (action == HDA_FIXUP_ACT_PRE_PROBE) {
spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
+ snd_hda_apply_pincfgs(codec, pincfgs);
+ } else if (action == HDA_FIXUP_ACT_INIT) {
/* Enable DOCK device */
snd_hda_codec_write(codec, 0x17, 0,
AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0);
/* Enable DOCK device */
snd_hda_codec_write(codec, 0x19, 0,
AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0);
- snd_hda_apply_pincfgs(codec, pincfgs);
}
}

diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 8a59d4782a0f..69bf5cf1e91e 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3277,4 +3277,51 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
}
},

+{
+ /*
+ * Bower's & Wilkins PX headphones only support the 48 kHz sample rate
+ * even though it advertises more. The capture interface doesn't work
+ * even on windows.
+ */
+ USB_DEVICE(0x19b5, 0x0021),
+ .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_COMPOSITE,
+ .data = (const struct snd_usb_audio_quirk[]) {
+ {
+ .ifnum = 0,
+ .type = QUIRK_AUDIO_STANDARD_MIXER,
+ },
+ /* Capture */
+ {
+ .ifnum = 1,
+ .type = QUIRK_IGNORE_INTERFACE,
+ },
+ /* Playback */
+ {
+ .ifnum = 2,
+ .type = QUIRK_AUDIO_FIXED_ENDPOINT,
+ .data = &(const struct audioformat) {
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
+ .channels = 2,
+ .iface = 2,
+ .altsetting = 1,
+ .altset_idx = 1,
+ .attributes = UAC_EP_CS_ATTR_FILL_MAX |
+ UAC_EP_CS_ATTR_SAMPLE_RATE,
+ .endpoint = 0x03,
+ .ep_attr = USB_ENDPOINT_XFER_ISOC,
+ .rates = SNDRV_PCM_RATE_48000,
+ .rate_min = 48000,
+ .rate_max = 48000,
+ .nr_rates = 1,
+ .rate_table = (unsigned int[]) {
+ 48000
+ }
+ }
+ },
+ }
+ }
+},
+
#undef USB_DEVICE_VENDOR_SPEC
diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c
index a0951505c7f5..697872d8308e 100644
--- a/sound/x86/intel_hdmi_audio.c
+++ b/sound/x86/intel_hdmi_audio.c
@@ -1827,6 +1827,8 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev)
ctx->port = port;
ctx->pipe = -1;

+ spin_lock_init(&ctx->had_spinlock);
+ mutex_init(&ctx->mutex);
INIT_WORK(&ctx->hdmi_audio_wq, had_audio_wq);

ret = snd_pcm_new(card, INTEL_HAD, port, MAX_PB_STREAMS,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8401774f5aeb..d81af263f50b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -975,8 +975,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
/* Check for overlaps */
r = -EEXIST;
kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) {
- if ((slot->id >= KVM_USER_MEM_SLOTS) ||
- (slot->id == id))
+ if (slot->id == id)
continue;
if (!((base_gfn + npages <= slot->base_gfn) ||
(base_gfn >= slot->base_gfn + slot->npages)))