Re: Linux 4.9.33

From: Greg KH
Date: Sat Jun 17 2017 - 03:14:18 EST


diff --git a/Makefile b/Makefile
index 3d8781997968..8470d81d5cc2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 9
-SUBLEVEL = 32
+SUBLEVEL = 33
EXTRAVERSION =
NAME = Roaring Lionus

@@ -797,7 +797,7 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types)
KBUILD_ARFLAGS := $(call ar-option,D)

# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
endif
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 689dd867fdff..8b90d25a15cc 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -71,14 +71,14 @@ ENTRY(stext)
GET_CPU_ID r5
cmp r5, 0
mov.nz r0, r5
-#ifdef CONFIG_ARC_SMP_HALT_ON_RESET
- ; Non-Master can proceed as system would be booted sufficiently
- jnz first_lines_of_secondary
-#else
+ bz .Lmaster_proceed
+
; Non-Masters wait for Master to boot enough and bring them up
- jnz arc_platform_smp_wait_to_boot
-#endif
- ; Master falls thru
+ ; when they resume, tail-call to entry point
+ mov blink, @first_lines_of_secondary
+ j arc_platform_smp_wait_to_boot
+
+.Lmaster_proceed:
#endif

; Clear BSS before updating any globals
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 88674d972c9d..2afbafadb6ab 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -90,22 +90,37 @@ void __init smp_cpus_done(unsigned int max_cpus)
*/
static volatile int wake_flag;

+#ifdef CONFIG_ISA_ARCOMPACT
+
+#define __boot_read(f) f
+#define __boot_write(f, v) f = v
+
+#else
+
+#define __boot_read(f) arc_read_uncached_32(&f)
+#define __boot_write(f, v) arc_write_uncached_32(&f, v)
+
+#endif
+
static void arc_default_smp_cpu_kick(int cpu, unsigned long pc)
{
BUG_ON(cpu == 0);
- wake_flag = cpu;
+
+ __boot_write(wake_flag, cpu);
}

void arc_platform_smp_wait_to_boot(int cpu)
{
- while (wake_flag != cpu)
+ /* for halt-on-reset, we've waited already */
+ if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET))
+ return;
+
+ while (__boot_read(wake_flag) != cpu)
;

- wake_flag = 0;
- __asm__ __volatile__("j @first_lines_of_secondary \n");
+ __boot_write(wake_flag, 0);
}

-
const char *arc_platform_smp_cpuinfo(void)
{
return plat_smp_ops.info ? : "";
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index ea316c4b890e..d3f1768840e2 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -64,8 +64,8 @@ CONFIG_NETFILTER=y
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 18e59feaa307..7f479cdb3479 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -56,8 +56,8 @@ CONFIG_NETFILTER=y
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
CONFIG_NF_CONNTRACK_AMANDA=m
CONFIG_NF_CONNTRACK_FTP=m
CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 1c2a5e264fc7..e93c9494503a 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -139,7 +139,7 @@ static inline void atomic64_dec(atomic64_t *v)
#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
#define atomic64_inc_and_test(v) (atomic64_inc_return((v)) == 0)
-
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)

#define atomic_cmpxchg(v, old, new) (cmpxchg(&(v)->counter, old, new))
#define atomic_xchg(v, new) (xchg(&(v)->counter, new))
@@ -161,6 +161,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
return c;
}

+static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
+{
+ long long c, old;
+
+ c = atomic64_read(v);
+ for (;;) {
+ if (unlikely(c == u))
+ break;
+ old = atomic64_cmpxchg(v, c, c + i);
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+ return c != u;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+ long long c, old, dec;
+
+ c = atomic64_read(v);
+ for (;;) {
+ dec = c - 1;
+ if (unlikely(dec < 0))
+ break;
+ old = atomic64_cmpxchg((v), c, dec);
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+ return dec;
+}
+
#define ATOMIC_OP(op) \
static inline int atomic_fetch_##op(int i, atomic_t *v) \
{ \
diff --git a/arch/mn10300/include/asm/switch_to.h b/arch/mn10300/include/asm/switch_to.h
index 393d311735c8..67e333aa7629 100644
--- a/arch/mn10300/include/asm/switch_to.h
+++ b/arch/mn10300/include/asm/switch_to.h
@@ -16,7 +16,7 @@
struct task_struct;
struct thread_struct;

-#if !defined(CONFIG_LAZY_SAVE_FPU)
+#if defined(CONFIG_FPU) && !defined(CONFIG_LAZY_SAVE_FPU)
struct fpu_state_struct;
extern asmlinkage void fpu_save(struct fpu_state_struct *);
#define switch_fpu(prev, next) \
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index 32c46b424dd0..b53f80f0b4d8 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -130,14 +130,16 @@ static void icp_opal_cause_ipi(int cpu, unsigned long data)
{
int hw_cpu = get_hard_smp_processor_id(cpu);

+ kvmppc_set_host_ipi(cpu, 1);
opal_int_set_mfrr(hw_cpu, IPI_PRIORITY);
}

static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
{
- int hw_cpu = hard_smp_processor_id();
+ int cpu = smp_processor_id();

- opal_int_set_mfrr(hw_cpu, 0xff);
+ kvmppc_set_host_ipi(cpu, 0);
+ opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);

return smp_ipi_demux();
}
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index c43816886839..3bc2825173ef 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -240,12 +240,17 @@ ENTRY(sie64a)
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
.Lsie_done:
# some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions between sie64a and .Lsie_done should not cause program
-# interrupts. So lets use a nop (47 00 00 00) as a landing pad.
+# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
+# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
+# Other instructions between sie64a and .Lsie_done should not cause program
+# interrupts. So lets use 3 nops as a landing pad for all possible rewinds.
# See also .Lcleanup_sie
-.Lrewind_pad:
- nop 0
+.Lrewind_pad6:
+ nopr 7
+.Lrewind_pad4:
+ nopr 7
+.Lrewind_pad2:
+ nopr 7
.globl sie_exit
sie_exit:
lg %r14,__SF_EMPTY+8(%r15) # load guest register save area
@@ -258,7 +263,9 @@ sie_exit:
stg %r14,__SF_EMPTY+16(%r15) # set exit reason code
j sie_exit

- EX_TABLE(.Lrewind_pad,.Lsie_fault)
+ EX_TABLE(.Lrewind_pad6,.Lsie_fault)
+ EX_TABLE(.Lrewind_pad4,.Lsie_fault)
+ EX_TABLE(.Lrewind_pad2,.Lsie_fault)
EX_TABLE(sie_exit,.Lsie_fault)
EXPORT_SYMBOL(sie64a)
EXPORT_SYMBOL(sie_exit)
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4094a51b1970..496fa926e1e0 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -85,7 +85,7 @@ static void dump_tl1_traplog(struct tl1_traplog *p)

void bad_trap(struct pt_regs *regs, long lvl)
{
- char buffer[32];
+ char buffer[36];
siginfo_t info;

if (notify_die(DIE_TRAP, "bad trap", regs,
@@ -116,7 +116,7 @@ void bad_trap(struct pt_regs *regs, long lvl)

void bad_trap_tl1(struct pt_regs *regs, long lvl)
{
- char buffer[32];
+ char buffer[36];

if (notify_die(DIE_TRAP_TL1, "bad trap tl1", regs,
0, lvl, SIGTRAP) == NOTIFY_STOP)
diff --git a/arch/xtensa/include/asm/irq.h b/arch/xtensa/include/asm/irq.h
index f71f88ea7646..19707db966f1 100644
--- a/arch/xtensa/include/asm/irq.h
+++ b/arch/xtensa/include/asm/irq.h
@@ -29,7 +29,8 @@ static inline void variant_irq_disable(unsigned int irq) { }
# define PLATFORM_NR_IRQS 0
#endif
#define XTENSA_NR_IRQS XCHAL_NUM_INTERRUPTS
-#define NR_IRQS (XTENSA_NR_IRQS + VARIANT_NR_IRQS + PLATFORM_NR_IRQS)
+#define NR_IRQS (XTENSA_NR_IRQS + VARIANT_NR_IRQS + PLATFORM_NR_IRQS + 1)
+#define XTENSA_PIC_LINUX_IRQ(hwirq) ((hwirq) + 1)

#if VARIANT_NR_IRQS == 0
static inline void variant_init_irq(void) { }
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 4ac3d23161cf..441694464b1e 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -34,11 +34,6 @@ asmlinkage void do_IRQ(int hwirq, struct pt_regs *regs)
{
int irq = irq_find_mapping(NULL, hwirq);

- if (hwirq >= NR_IRQS) {
- printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
- __func__, hwirq);
- }
-
#ifdef CONFIG_DEBUG_STACKOVERFLOW
/* Debugging check for stack overflow: is there less than 1KB free? */
{
diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
index dbeea2b440a1..1fda7e20dfcb 100644
--- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
+++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
@@ -24,16 +24,18 @@

/* Interrupt configuration. */

-#define PLATFORM_NR_IRQS 10
+#define PLATFORM_NR_IRQS 0

/* Default assignment of LX60 devices to external interrupts. */

#ifdef CONFIG_XTENSA_MX
#define DUART16552_INTNUM XCHAL_EXTINT3_NUM
#define OETH_IRQ XCHAL_EXTINT4_NUM
+#define C67X00_IRQ XCHAL_EXTINT8_NUM
#else
#define DUART16552_INTNUM XCHAL_EXTINT0_NUM
#define OETH_IRQ XCHAL_EXTINT1_NUM
+#define C67X00_IRQ XCHAL_EXTINT5_NUM
#endif

/*
@@ -63,5 +65,5 @@

#define C67X00_PADDR (XCHAL_KIO_PADDR + 0x0D0D0000)
#define C67X00_SIZE 0x10
-#define C67X00_IRQ 5
+
#endif /* __XTENSA_XTAVNET_HARDWARE_H */
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 779be723eb2b..42285f35d313 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -175,8 +175,8 @@ static struct resource ethoc_res[] = {
.flags = IORESOURCE_MEM,
},
[2] = { /* IRQ number */
- .start = OETH_IRQ,
- .end = OETH_IRQ,
+ .start = XTENSA_PIC_LINUX_IRQ(OETH_IRQ),
+ .end = XTENSA_PIC_LINUX_IRQ(OETH_IRQ),
.flags = IORESOURCE_IRQ,
},
};
@@ -213,8 +213,8 @@ static struct resource c67x00_res[] = {
.flags = IORESOURCE_MEM,
},
[1] = { /* IRQ number */
- .start = C67X00_IRQ,
- .end = C67X00_IRQ,
+ .start = XTENSA_PIC_LINUX_IRQ(C67X00_IRQ),
+ .end = XTENSA_PIC_LINUX_IRQ(C67X00_IRQ),
.flags = IORESOURCE_IRQ,
},
};
@@ -247,7 +247,7 @@ static struct resource serial_resource = {
static struct plat_serial8250_port serial_platform_data[] = {
[0] = {
.mapbase = DUART16552_PADDR,
- .irq = DUART16552_INTNUM,
+ .irq = XTENSA_PIC_LINUX_IRQ(DUART16552_INTNUM),
.flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
UPF_IOREMAP,
.iotype = XCHAL_HAVE_BE ? UPIO_MEM32BE : UPIO_MEM32,
diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c
index 93e7c1b32edd..5610cd537da7 100644
--- a/block/partitions/msdos.c
+++ b/block/partitions/msdos.c
@@ -300,6 +300,8 @@ static void parse_bsd(struct parsed_partitions *state,
continue;
bsd_start = le32_to_cpu(p->p_offset);
bsd_size = le32_to_cpu(p->p_size);
+ if (memcmp(flavour, "bsd\0", 4) == 0)
+ bsd_start += offset;
if (offset == bsd_start && size == bsd_size)
/* full parent partition, we have it already */
continue;
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 23f3b95a1158..147d2e3678aa 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -889,13 +889,13 @@ int __pm_runtime_idle(struct device *dev, int rpmflags)
unsigned long flags;
int retval;

- might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count))
return 0;
}

+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
spin_lock_irqsave(&dev->power.lock, flags);
retval = rpm_idle(dev, rpmflags);
spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -921,13 +921,13 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags)
unsigned long flags;
int retval;

- might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
if (rpmflags & RPM_GET_PUT) {
if (!atomic_dec_and_test(&dev->power.usage_count))
return 0;
}

+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
spin_lock_irqsave(&dev->power.lock, flags);
retval = rpm_suspend(dev, rpmflags);
spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -952,7 +952,8 @@ int __pm_runtime_resume(struct device *dev, int rpmflags)
unsigned long flags;
int retval;

- might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+ might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe &&
+ dev->power.runtime_status != RPM_ACTIVE);

if (rpmflags & RPM_GET_PUT)
atomic_inc(&dev->power.usage_count);
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 908011d2c8f5..7abda94fc2cf 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -113,6 +113,7 @@ struct ast_private {
struct ttm_bo_kmap_obj cache_kmap;
int next_cursor;
bool support_wide_screen;
+ bool DisableP2A;

enum ast_tx_chip tx_chip_type;
u8 dp501_maxclk;
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index f75c6421db62..533e762d036d 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -124,6 +124,12 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
} else
*need_post = false;

+ /* Check P2A Access */
+ ast->DisableP2A = true;
+ data = ast_read32(ast, 0xf004);
+ if (data != 0xFFFFFFFF)
+ ast->DisableP2A = false;
+
/* Check if we support wide screen */
switch (ast->chip) {
case AST1180:
@@ -140,15 +146,17 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
ast->support_wide_screen = true;
else {
ast->support_wide_screen = false;
- /* Read SCU7c (silicon revision register) */
- ast_write32(ast, 0xf004, 0x1e6e0000);
- ast_write32(ast, 0xf000, 0x1);
- data = ast_read32(ast, 0x1207c);
- data &= 0x300;
- if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
- ast->support_wide_screen = true;
- if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
- ast->support_wide_screen = true;
+ if (ast->DisableP2A == false) {
+ /* Read SCU7c (silicon revision register) */
+ ast_write32(ast, 0xf004, 0x1e6e0000);
+ ast_write32(ast, 0xf000, 0x1);
+ data = ast_read32(ast, 0x1207c);
+ data &= 0x300;
+ if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
+ ast->support_wide_screen = true;
+ if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
+ ast->support_wide_screen = true;
+ }
}
break;
}
@@ -216,80 +224,81 @@ static int ast_get_dram_info(struct drm_device *dev)
uint32_t data, data2;
uint32_t denum, num, div, ref_pll;

- ast_write32(ast, 0xf004, 0x1e6e0000);
- ast_write32(ast, 0xf000, 0x1);
-
-
- ast_write32(ast, 0x10000, 0xfc600309);
-
- do {
- if (pci_channel_offline(dev->pdev))
- return -EIO;
- } while (ast_read32(ast, 0x10000) != 0x01);
- data = ast_read32(ast, 0x10004);
-
- if (data & 0x40)
+ if (ast->DisableP2A)
+ {
ast->dram_bus_width = 16;
+ ast->dram_type = AST_DRAM_1Gx16;
+ ast->mclk = 396;
+ }
else
- ast->dram_bus_width = 32;
+ {
+ ast_write32(ast, 0xf004, 0x1e6e0000);
+ ast_write32(ast, 0xf000, 0x1);
+ data = ast_read32(ast, 0x10004);
+
+ if (data & 0x40)
+ ast->dram_bus_width = 16;
+ else
+ ast->dram_bus_width = 32;
+
+ if (ast->chip == AST2300 || ast->chip == AST2400) {
+ switch (data & 0x03) {
+ case 0:
+ ast->dram_type = AST_DRAM_512Mx16;
+ break;
+ default:
+ case 1:
+ ast->dram_type = AST_DRAM_1Gx16;
+ break;
+ case 2:
+ ast->dram_type = AST_DRAM_2Gx16;
+ break;
+ case 3:
+ ast->dram_type = AST_DRAM_4Gx16;
+ break;
+ }
+ } else {
+ switch (data & 0x0c) {
+ case 0:
+ case 4:
+ ast->dram_type = AST_DRAM_512Mx16;
+ break;
+ case 8:
+ if (data & 0x40)
+ ast->dram_type = AST_DRAM_1Gx16;
+ else
+ ast->dram_type = AST_DRAM_512Mx32;
+ break;
+ case 0xc:
+ ast->dram_type = AST_DRAM_1Gx32;
+ break;
+ }
+ }

- if (ast->chip == AST2300 || ast->chip == AST2400) {
- switch (data & 0x03) {
- case 0:
- ast->dram_type = AST_DRAM_512Mx16;
- break;
- default:
- case 1:
- ast->dram_type = AST_DRAM_1Gx16;
- break;
- case 2:
- ast->dram_type = AST_DRAM_2Gx16;
- break;
+ data = ast_read32(ast, 0x10120);
+ data2 = ast_read32(ast, 0x10170);
+ if (data2 & 0x2000)
+ ref_pll = 14318;
+ else
+ ref_pll = 12000;
+
+ denum = data & 0x1f;
+ num = (data & 0x3fe0) >> 5;
+ data = (data & 0xc000) >> 14;
+ switch (data) {
case 3:
- ast->dram_type = AST_DRAM_4Gx16;
- break;
- }
- } else {
- switch (data & 0x0c) {
- case 0:
- case 4:
- ast->dram_type = AST_DRAM_512Mx16;
+ div = 0x4;
break;
- case 8:
- if (data & 0x40)
- ast->dram_type = AST_DRAM_1Gx16;
- else
- ast->dram_type = AST_DRAM_512Mx32;
+ case 2:
+ case 1:
+ div = 0x2;
break;
- case 0xc:
- ast->dram_type = AST_DRAM_1Gx32;
+ default:
+ div = 0x1;
break;
}
+ ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000);
}
-
- data = ast_read32(ast, 0x10120);
- data2 = ast_read32(ast, 0x10170);
- if (data2 & 0x2000)
- ref_pll = 14318;
- else
- ref_pll = 12000;
-
- denum = data & 0x1f;
- num = (data & 0x3fe0) >> 5;
- data = (data & 0xc000) >> 14;
- switch (data) {
- case 3:
- div = 0x4;
- break;
- case 2:
- case 1:
- div = 0x2;
- break;
- default:
- div = 0x1;
- break;
- }
- ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000);
return 0;
}

diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index 30672a3df8a9..270e8fb2803f 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -375,12 +375,20 @@ void ast_post_gpu(struct drm_device *dev)
ast_enable_mmio(dev);
ast_set_def_ext_reg(dev);

- if (ast->chip == AST2300 || ast->chip == AST2400)
- ast_init_dram_2300(dev);
- else
- ast_init_dram_reg(dev);
+ if (ast->DisableP2A == false)
+ {
+ if (ast->chip == AST2300 || ast->chip == AST2400)
+ ast_init_dram_2300(dev);
+ else
+ ast_init_dram_reg(dev);

- ast_init_3rdtx(dev);
+ ast_init_3rdtx(dev);
+ }
+ else
+ {
+ if (ast->tx_chip_type != AST_TX_NONE)
+ ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80); /* Enable DVO */
+ }
}

/* AST 2300 DRAM settings */
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 2db7fb510b6c..0e934a9ac63c 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -225,6 +225,7 @@ int drm_connector_init(struct drm_device *dev,

INIT_LIST_HEAD(&connector->probed_modes);
INIT_LIST_HEAD(&connector->modes);
+ mutex_init(&connector->mutex);
connector->edid_blob_ptr = NULL;
connector->status = connector_status_unknown;

@@ -359,6 +360,8 @@ void drm_connector_cleanup(struct drm_connector *connector)
connector->funcs->atomic_destroy_state(connector,
connector->state);

+ mutex_destroy(&connector->mutex);
+
memset(connector, 0, sizeof(*connector));
}
EXPORT_SYMBOL(drm_connector_cleanup);
@@ -374,14 +377,18 @@ EXPORT_SYMBOL(drm_connector_cleanup);
*/
int drm_connector_register(struct drm_connector *connector)
{
- int ret;
+ int ret = 0;

- if (connector->registered)
+ if (!connector->dev->registered)
return 0;

+ mutex_lock(&connector->mutex);
+ if (connector->registered)
+ goto unlock;
+
ret = drm_sysfs_connector_add(connector);
if (ret)
- return ret;
+ goto unlock;

ret = drm_debugfs_connector_add(connector);
if (ret) {
@@ -397,12 +404,14 @@ int drm_connector_register(struct drm_connector *connector)
drm_mode_object_register(connector->dev, &connector->base);

connector->registered = true;
- return 0;
+ goto unlock;

err_debugfs:
drm_debugfs_connector_remove(connector);
err_sysfs:
drm_sysfs_connector_remove(connector);
+unlock:
+ mutex_unlock(&connector->mutex);
return ret;
}
EXPORT_SYMBOL(drm_connector_register);
@@ -415,8 +424,11 @@ EXPORT_SYMBOL(drm_connector_register);
*/
void drm_connector_unregister(struct drm_connector *connector)
{
- if (!connector->registered)
+ mutex_lock(&connector->mutex);
+ if (!connector->registered) {
+ mutex_unlock(&connector->mutex);
return;
+ }

if (connector->funcs->early_unregister)
connector->funcs->early_unregister(connector);
@@ -425,6 +437,7 @@ void drm_connector_unregister(struct drm_connector *connector)
drm_debugfs_connector_remove(connector);

connector->registered = false;
+ mutex_unlock(&connector->mutex);
}
EXPORT_SYMBOL(drm_connector_unregister);

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 0f2fa9044668..362b8cd68a24 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -710,6 +710,8 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags)
if (ret)
goto err_minors;

+ dev->registered = true;
+
if (dev->driver->load) {
ret = dev->driver->load(dev, flags);
if (ret)
@@ -749,6 +751,8 @@ void drm_dev_unregister(struct drm_device *dev)

drm_lastclose(dev);

+ dev->registered = false;
+
if (drm_core_check_feature(dev, DRIVER_MODESET))
drm_modeset_unregister_all(dev);

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index ca6efb69ef66..7513e7678263 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1199,6 +1199,15 @@ int i915_driver_load(struct pci_dev *pdev, const struct pci_device_id *ent)
goto out_free_priv;

pci_set_drvdata(pdev, &dev_priv->drm);
+ /*
+ * Disable the system suspend direct complete optimization, which can
+ * leave the device suspended skipping the driver's suspend handlers
+ * if the device was already runtime suspended. This is needed due to
+ * the difference in our runtime and system suspend sequence and
+ * becaue the HDA driver may require us to enable the audio power
+ * domain during system suspend.
+ */
+ pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;

ret = i915_driver_init_early(dev_priv, ent);
if (ret < 0)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5dc6082639db..f8efd20e4a90 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2253,6 +2253,9 @@ void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
intel_fill_fb_ggtt_view(&view, fb, rotation);
vma = i915_gem_object_to_ggtt(obj, &view);

+ if (WARN_ON_ONCE(!vma))
+ return;
+
i915_vma_unpin_fence(vma);
i915_gem_object_unpin_from_display_plane(vma);
}
@@ -13764,6 +13767,15 @@ static void update_scanline_offset(struct intel_crtc *crtc)
* type. For DP ports it behaves like most other platforms, but on HDMI
* there's an extra 1 line difference. So we need to add two instead of
* one to the value.
+ *
+ * On VLV/CHV DSI the scanline counter would appear to increment
+ * approx. 1/3 of a scanline before start of vblank. Unfortunately
+ * that means we can't tell whether we're in vblank or not while
+ * we're on that particular line. We must still set scanline_offset
+ * to 1 so that the vblank timestamps come out correct when we query
+ * the scanline counter from within the vblank interrupt handler.
+ * However if queried just before the start of vblank we'll get an
+ * answer that's slightly in the future.
*/
if (IS_GEN2(dev)) {
const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 2c6d59d4b6d3..49de4760cc16 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4114,11 +4114,19 @@ skl_compute_wm(struct drm_atomic_state *state)
struct drm_crtc_state *cstate;
struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
struct skl_wm_values *results = &intel_state->wm_results;
+ struct drm_device *dev = state->dev;
struct skl_pipe_wm *pipe_wm;
bool changed = false;
int ret, i;

/*
+ * When we distrust bios wm we always need to recompute to set the
+ * expected DDB allocations for each CRTC.
+ */
+ if (to_i915(dev)->wm.distrust_bios_wm)
+ changed = true;
+
+ /*
* If this transaction isn't actually touching any CRTC's, don't
* bother with watermark calculation. Note that if we pass this
* test, we're guaranteed to hold at least one CRTC state mutex,
@@ -4128,6 +4136,7 @@ skl_compute_wm(struct drm_atomic_state *state)
*/
for_each_crtc_in_state(state, crtc, cstate, i)
changed = true;
+
if (!changed)
return 0;

diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index dbed12c484c9..64f4e2e18594 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -81,10 +81,13 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
*/
void intel_pipe_update_start(struct intel_crtc *crtc)
{
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
long timeout = msecs_to_jiffies_timeout(1);
int scanline, min, max, vblank_start;
wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
+ bool need_vlv_dsi_wa = (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+ intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DSI);
DEFINE_WAIT(wait);

vblank_start = adjusted_mode->crtc_vblank_start;
@@ -136,6 +139,24 @@ void intel_pipe_update_start(struct intel_crtc *crtc)

drm_crtc_vblank_put(&crtc->base);

+ /*
+ * On VLV/CHV DSI the scanline counter would appear to
+ * increment approx. 1/3 of a scanline before start of vblank.
+ * The registers still get latched at start of vblank however.
+ * This means we must not write any registers on the first
+ * line of vblank (since not the whole line is actually in
+ * vblank). And unfortunately we can't use the interrupt to
+ * wait here since it will fire too soon. We could use the
+ * frame start interrupt instead since it will fire after the
+ * critical scanline, but that would require more changes
+ * in the interrupt code. So for now we'll just do the nasty
+ * thing and poll for the bad scanline to pass us by.
+ *
+ * FIXME figure out if BXT+ DSI suffers from this as well
+ */
+ while (need_vlv_dsi_wa && scanline == vblank_start)
+ scanline = intel_get_crtc_scanline(crtc);
+
crtc->debug.scanline_start = scanline;
crtc->debug.start_vbl_time = ktime_get();
crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index afbf557b23d4..2c2b86d68129 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -24,6 +24,7 @@
*
*/

+#include <acpi/video.h>
#include <drm/drmP.h>
#include <drm/drm_crtc_helper.h>

@@ -358,6 +359,57 @@ static struct nouveau_drm_prop_enum_list dither_depth[] = {
} \
} while(0)

+static void
+nouveau_display_hpd_work(struct work_struct *work)
+{
+ struct nouveau_drm *drm = container_of(work, typeof(*drm), hpd_work);
+
+ pm_runtime_get_sync(drm->dev->dev);
+
+ drm_helper_hpd_irq_event(drm->dev);
+ /* enable polling for external displays */
+ drm_kms_helper_poll_enable(drm->dev);
+
+ pm_runtime_mark_last_busy(drm->dev->dev);
+ pm_runtime_put_sync(drm->dev->dev);
+}
+
+#ifdef CONFIG_ACPI
+
+/*
+ * Hans de Goede: This define belongs in acpi/video.h, I've submitted a patch
+ * to the acpi subsys to move it there from drivers/acpi/acpi_video.c .
+ * This should be dropped once that is merged.
+ */
+#ifndef ACPI_VIDEO_NOTIFY_PROBE
+#define ACPI_VIDEO_NOTIFY_PROBE 0x81
+#endif
+
+static int
+nouveau_display_acpi_ntfy(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct nouveau_drm *drm = container_of(nb, typeof(*drm), acpi_nb);
+ struct acpi_bus_event *info = data;
+
+ if (!strcmp(info->device_class, ACPI_VIDEO_CLASS)) {
+ if (info->type == ACPI_VIDEO_NOTIFY_PROBE) {
+ /*
+ * This may be the only indication we receive of a
+ * connector hotplug on a runtime suspended GPU,
+ * schedule hpd_work to check.
+ */
+ schedule_work(&drm->hpd_work);
+
+ /* acpi-video should not generate keypresses for this */
+ return NOTIFY_BAD;
+ }
+ }
+
+ return NOTIFY_DONE;
+}
+#endif
+
int
nouveau_display_init(struct drm_device *dev)
{
@@ -370,9 +422,6 @@ nouveau_display_init(struct drm_device *dev)
if (ret)
return ret;

- /* enable polling for external displays */
- drm_kms_helper_poll_enable(dev);
-
/* enable hotplug interrupts */
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
struct nouveau_connector *conn = nouveau_connector(connector);
@@ -537,6 +586,12 @@ nouveau_display_create(struct drm_device *dev)
}

nouveau_backlight_init(dev);
+ INIT_WORK(&drm->hpd_work, nouveau_display_hpd_work);
+#ifdef CONFIG_ACPI
+ drm->acpi_nb.notifier_call = nouveau_display_acpi_ntfy;
+ register_acpi_notifier(&drm->acpi_nb);
+#endif
+
return 0;

vblank_err:
@@ -552,6 +607,9 @@ nouveau_display_destroy(struct drm_device *dev)
{
struct nouveau_display *disp = nouveau_display(dev);

+#ifdef CONFIG_ACPI
+ unregister_acpi_notifier(&nouveau_drm(dev)->acpi_nb);
+#endif
nouveau_backlight_exit(dev);
nouveau_display_vblank_fini(dev);

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 3100fd88a015..42829a942e33 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -483,6 +483,9 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
pm_runtime_allow(dev->dev);
pm_runtime_mark_last_busy(dev->dev);
pm_runtime_put(dev->dev);
+ } else {
+ /* enable polling for external displays */
+ drm_kms_helper_poll_enable(dev);
}
return 0;

@@ -761,7 +764,7 @@ nouveau_pmops_runtime_resume(struct device *dev)
pci_set_master(pdev);

ret = nouveau_do_resume(drm_dev, true);
- drm_kms_helper_poll_enable(drm_dev);
+
/* do magic */
nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25));
vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 822a0212cd48..1e7f1e326b3c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -37,6 +37,8 @@
* - implemented limited ABI16/NVIF interop
*/

+#include <linux/notifier.h>
+
#include <nvif/client.h>
#include <nvif/device.h>
#include <nvif/ioctl.h>
@@ -161,6 +163,12 @@ struct nouveau_drm {
struct nvbios vbios;
struct nouveau_display *display;
struct backlight_device *backlight;
+ struct work_struct hpd_work;
+ struct work_struct fbcon_work;
+ int fbcon_new_state;
+#ifdef CONFIG_ACPI
+ struct notifier_block acpi_nb;
+#endif

/* power management */
struct nouveau_hwmon *hwmon;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 9f5692726c16..2b79e27dd89c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -491,19 +491,43 @@ static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = {
.fb_probe = nouveau_fbcon_create,
};

+static void
+nouveau_fbcon_set_suspend_work(struct work_struct *work)
+{
+ struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work);
+ int state = READ_ONCE(drm->fbcon_new_state);
+
+ if (state == FBINFO_STATE_RUNNING)
+ pm_runtime_get_sync(drm->dev->dev);
+
+ console_lock();
+ if (state == FBINFO_STATE_RUNNING)
+ nouveau_fbcon_accel_restore(drm->dev);
+ drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
+ if (state != FBINFO_STATE_RUNNING)
+ nouveau_fbcon_accel_save_disable(drm->dev);
+ console_unlock();
+
+ if (state == FBINFO_STATE_RUNNING) {
+ pm_runtime_mark_last_busy(drm->dev->dev);
+ pm_runtime_put_sync(drm->dev->dev);
+ }
+}
+
void
nouveau_fbcon_set_suspend(struct drm_device *dev, int state)
{
struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon) {
- console_lock();
- if (state == FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_restore(dev);
- drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
- if (state != FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_save_disable(dev);
- console_unlock();
- }
+
+ if (!drm->fbcon)
+ return;
+
+ drm->fbcon_new_state = state;
+ /* Since runtime resume can happen as a result of a sysfs operation,
+ * it's possible we already have the console locked. So handle fbcon
+ * init/deinit from a seperate work thread
+ */
+ schedule_work(&drm->fbcon_work);
}

int
@@ -524,6 +548,7 @@ nouveau_fbcon_init(struct drm_device *dev)

fbcon->dev = dev;
drm->fbcon = fbcon;
+ INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work);

drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs);

diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 64c4ce7115ad..75e1f09484ff 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -100,6 +100,7 @@ struct nv84_fence_priv {
struct nouveau_bo *bo;
struct nouveau_bo *bo_gart;
u32 *suspend;
+ struct mutex mutex;
};

u64 nv84_fence_crtc(struct nouveau_channel *, int);
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 08f9c6fa0f7f..1fba38622744 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -313,7 +313,8 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc)
if (!(ret = nvif_unpack(-ENOSYS, &data, &size, argv->v0, 0, 0, true))) {
/* block access to objects not created via this interface */
owner = argv->v0.owner;
- if (argv->v0.object == 0ULL)
+ if (argv->v0.object == 0ULL &&
+ argv->v0.type != NVIF_IOCTL_V0_DEL)
argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */
else
argv->v0.owner = NVDRM_OBJECT_USIF;
diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c
index 18bde9d8e6d6..90a5dd6311c6 100644
--- a/drivers/gpu/drm/nouveau/nv84_fence.c
+++ b/drivers/gpu/drm/nouveau/nv84_fence.c
@@ -121,8 +121,10 @@ nv84_fence_context_del(struct nouveau_channel *chan)
}

nouveau_bo_wr32(priv->bo, chan->chid * 16 / 4, fctx->base.sequence);
+ mutex_lock(&priv->mutex);
nouveau_bo_vma_del(priv->bo, &fctx->vma_gart);
nouveau_bo_vma_del(priv->bo, &fctx->vma);
+ mutex_unlock(&priv->mutex);
nouveau_fence_context_del(&fctx->base);
chan->fence = NULL;
nouveau_fence_context_free(&fctx->base);
@@ -148,11 +150,13 @@ nv84_fence_context_new(struct nouveau_channel *chan)
fctx->base.sync32 = nv84_fence_sync32;
fctx->base.sequence = nv84_fence_read(chan);

+ mutex_lock(&priv->mutex);
ret = nouveau_bo_vma_add(priv->bo, cli->vm, &fctx->vma);
if (ret == 0) {
ret = nouveau_bo_vma_add(priv->bo_gart, cli->vm,
&fctx->vma_gart);
}
+ mutex_unlock(&priv->mutex);

/* map display semaphore buffers into channel's vm */
for (i = 0; !ret && i < chan->drm->dev->mode_config.num_crtc; i++) {
@@ -232,6 +236,8 @@ nv84_fence_create(struct nouveau_drm *drm)
priv->base.context_base = fence_context_alloc(priv->base.contexts);
priv->base.uevent = true;

+ mutex_init(&priv->mutex);
+
/* Use VRAM if there is any ; otherwise fallback to system memory */
domain = drm->device.info.ram_size != 0 ? TTM_PL_FLAG_VRAM :
/*
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index e34d82e79b98..c21ca7bf2efe 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -58,7 +58,7 @@
#define SMBSLVDAT (0xC + piix4_smba)

/* count for request_region */
-#define SMBIOSIZE 8
+#define SMBIOSIZE 9

/* PCI Address Constants */
#define SMBBA 0x090
@@ -592,6 +592,8 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,
u8 port;
int retval;

+ mutex_lock(&piix4_mutex_sb800);
+
/* Request the SMBUS semaphore, avoid conflicts with the IMC */
smbslvcnt = inb_p(SMBSLVCNT);
do {
@@ -605,10 +607,10 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,
usleep_range(1000, 2000);
} while (--retries);
/* SMBus is still owned by the IMC, we give up */
- if (!retries)
+ if (!retries) {
+ mutex_unlock(&piix4_mutex_sb800);
return -EBUSY;
-
- mutex_lock(&piix4_mutex_sb800);
+ }

outb_p(piix4_port_sel_sb800, SB800_PIIX4_SMB_IDX);
smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1);
@@ -623,11 +625,11 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,

outb_p(smba_en_lo, SB800_PIIX4_SMB_IDX + 1);

- mutex_unlock(&piix4_mutex_sb800);
-
/* Release the semaphore */
outb_p(smbslvcnt | 0x20, SMBSLVCNT);

+ mutex_unlock(&piix4_mutex_sb800);
+
return retval;
}

diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 7b74d09a8217..58e92bce6825 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -792,6 +792,9 @@ static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev,
if (device_create_file(&dev->ibdev.dev, qedr_attributes[i]))
goto sysfs_err;

+ if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE);
+
DP_DEBUG(dev, QEDR_MSG_INIT, "qedr driver loaded successfully\n");
return dev;

@@ -824,11 +827,10 @@ static void qedr_remove(struct qedr_dev *dev)
ib_dealloc_device(&dev->ibdev);
}

-static int qedr_close(struct qedr_dev *dev)
+static void qedr_close(struct qedr_dev *dev)
{
- qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ERR);
-
- return 0;
+ if (test_and_clear_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ERR);
}

static void qedr_shutdown(struct qedr_dev *dev)
@@ -837,6 +839,12 @@ static void qedr_shutdown(struct qedr_dev *dev)
qedr_remove(dev);
}

+static void qedr_open(struct qedr_dev *dev)
+{
+ if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE);
+}
+
static void qedr_mac_address_change(struct qedr_dev *dev)
{
union ib_gid *sgid = &dev->sgid_tbl[0];
@@ -863,7 +871,7 @@ static void qedr_mac_address_change(struct qedr_dev *dev)

ether_addr_copy(dev->gsi_ll2_mac_address, dev->ndev->dev_addr);

- qedr_ib_dispatch_event(dev, 1, IB_EVENT_GID_CHANGE);
+ qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_GID_CHANGE);

if (rc)
DP_ERR(dev, "Error updating mac filter\n");
@@ -877,7 +885,7 @@ static void qedr_notify(struct qedr_dev *dev, enum qede_roce_event event)
{
switch (event) {
case QEDE_UP:
- qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
+ qedr_open(dev);
break;
case QEDE_DOWN:
qedr_close(dev);
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 620badd7d4fb..f669d0bb697e 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -113,6 +113,8 @@ struct qedr_device_attr {
struct qed_rdma_events events;
};

+#define QEDR_ENET_STATE_BIT (0)
+
struct qedr_dev {
struct ib_device ibdev;
struct qed_dev *cdev;
@@ -153,6 +155,8 @@ struct qedr_dev {
struct qedr_cq *gsi_sqcq;
struct qedr_cq *gsi_rqcq;
struct qedr_qp *gsi_qp;
+
+ unsigned long enet_state;
};

#define QEDR_MAX_SQ_PBL (0x8000)
@@ -188,6 +192,7 @@ struct qedr_dev {
#define QEDR_ROCE_MAX_CNQ_SIZE (0x4000)

#define QEDR_MAX_PORT (1)
+#define QEDR_PORT (1)

#define QEDR_UVERBS(CMD_NAME) (1ull << IB_USER_VERBS_CMD_##CMD_NAME)

diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index a61514296767..4ba019e3dc56 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -471,8 +471,6 @@ struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
struct ib_ucontext *context, struct ib_udata *udata)
{
struct qedr_dev *dev = get_qedr_dev(ibdev);
- struct qedr_ucontext *uctx = NULL;
- struct qedr_alloc_pd_uresp uresp;
struct qedr_pd *pd;
u16 pd_id;
int rc;
@@ -489,21 +487,33 @@ struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
if (!pd)
return ERR_PTR(-ENOMEM);

- dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+ rc = dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+ if (rc)
+ goto err;

- uresp.pd_id = pd_id;
pd->pd_id = pd_id;

if (udata && context) {
+ struct qedr_alloc_pd_uresp uresp;
+
+ uresp.pd_id = pd_id;
+
rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
- if (rc)
+ if (rc) {
DP_ERR(dev, "copy error pd_id=0x%x.\n", pd_id);
- uctx = get_qedr_ucontext(context);
- uctx->pd = pd;
- pd->uctx = uctx;
+ dev->ops->rdma_dealloc_pd(dev->rdma_ctx, pd_id);
+ goto err;
+ }
+
+ pd->uctx = get_qedr_ucontext(context);
+ pd->uctx->pd = pd;
}

return &pd->ibpd;
+
+err:
+ kfree(pd);
+ return ERR_PTR(rc);
}

int qedr_dealloc_pd(struct ib_pd *ibpd)
@@ -1719,6 +1729,14 @@ static int qedr_update_qp_state(struct qedr_dev *dev,
/* ERR->XXX */
switch (new_state) {
case QED_ROCE_QP_STATE_RESET:
+ if ((qp->rq.prod != qp->rq.cons) ||
+ (qp->sq.prod != qp->sq.cons)) {
+ DP_NOTICE(dev,
+ "Error->Reset with rq/sq not empty rq.prod=%x rq.cons=%x sq.prod=%x sq.cons=%x\n",
+ qp->rq.prod, qp->rq.cons, qp->sq.prod,
+ qp->sq.cons);
+ status = -EINVAL;
+ }
break;
default:
status = -EINVAL;
@@ -2014,7 +2032,7 @@ int qedr_query_qp(struct ib_qp *ibqp,
qp_attr->cap.max_recv_wr = qp->rq.max_wr;
qp_attr->cap.max_send_sge = qp->sq.max_sges;
qp_attr->cap.max_recv_sge = qp->rq.max_sges;
- qp_attr->cap.max_inline_data = qp->max_inline_data;
+ qp_attr->cap.max_inline_data = ROCE_REQ_MAX_INLINE_DATA_SIZE;
qp_init_attr->cap = qp_attr->cap;

memcpy(&qp_attr->ah_attr.grh.dgid.raw[0], &params.dgid.bytes[0],
@@ -3220,9 +3238,10 @@ static int qedr_poll_cq_req(struct qedr_dev *dev,
IB_WC_SUCCESS, 0);
break;
case RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR:
- DP_ERR(dev,
- "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
- cq->icid, qp->icid);
+ if (qp->state != QED_ROCE_QP_STATE_ERR)
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
cnt = process_req(dev, qp, cq, num_entries, wc, req->sq_cons,
IB_WC_WR_FLUSH_ERR, 0);
break;
diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c
index bb3ac5fe5846..72a391e01011 100644
--- a/drivers/irqchip/irq-xtensa-mx.c
+++ b/drivers/irqchip/irq-xtensa-mx.c
@@ -142,7 +142,7 @@ static struct irq_chip xtensa_mx_irq_chip = {
int __init xtensa_mx_init_legacy(struct device_node *interrupt_parent)
{
struct irq_domain *root_domain =
- irq_domain_add_legacy(NULL, NR_IRQS, 0, 0,
+ irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0,
&xtensa_mx_irq_domain_ops,
&xtensa_mx_irq_chip);
irq_set_default_host(root_domain);
diff --git a/drivers/irqchip/irq-xtensa-pic.c b/drivers/irqchip/irq-xtensa-pic.c
index 472ae1770964..f728755fa292 100644
--- a/drivers/irqchip/irq-xtensa-pic.c
+++ b/drivers/irqchip/irq-xtensa-pic.c
@@ -89,7 +89,7 @@ static struct irq_chip xtensa_irq_chip = {
int __init xtensa_pic_init_legacy(struct device_node *interrupt_parent)
{
struct irq_domain *root_domain =
- irq_domain_add_legacy(NULL, NR_IRQS, 0, 0,
+ irq_domain_add_legacy(NULL, NR_IRQS - 1, 1, 0,
&xtensa_irq_domain_ops, &xtensa_irq_chip);
irq_set_default_host(root_domain);
return 0;
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 8af2c88d5b33..45bb0fe50917 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -1153,6 +1153,12 @@ static void init_ring(struct net_device *dev)
if (skb == NULL)
break;
np->rx_info[i].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(np->pci_dev,
+ np->rx_info[i].mapping)) {
+ dev_kfree_skb(skb);
+ np->rx_info[i].skb = NULL;
+ break;
+ }
/* Grrr, we cannot offset to correctly align the IP header. */
np->rx_ring[i].rxaddr = cpu_to_dma(np->rx_info[i].mapping | RxDescValid);
}
@@ -1183,8 +1189,9 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
{
struct netdev_private *np = netdev_priv(dev);
unsigned int entry;
+ unsigned int prev_tx;
u32 status;
- int i;
+ int i, j;

/*
* be cautious here, wrapping the queue has weird semantics
@@ -1202,6 +1209,7 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
}
#endif /* ZEROCOPY && HAS_BROKEN_FIRMWARE */

+ prev_tx = np->cur_tx;
entry = np->cur_tx % TX_RING_SIZE;
for (i = 0; i < skb_num_frags(skb); i++) {
int wrap_ring = 0;
@@ -1235,6 +1243,11 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
skb_frag_size(this_frag),
PCI_DMA_TODEVICE);
}
+ if (pci_dma_mapping_error(np->pci_dev,
+ np->tx_info[entry].mapping)) {
+ dev->stats.tx_dropped++;
+ goto err_out;
+ }

np->tx_ring[entry].addr = cpu_to_dma(np->tx_info[entry].mapping);
np->tx_ring[entry].status = cpu_to_le32(status);
@@ -1269,8 +1282,30 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
netif_stop_queue(dev);

return NETDEV_TX_OK;
-}

+err_out:
+ entry = prev_tx % TX_RING_SIZE;
+ np->tx_info[entry].skb = NULL;
+ if (i > 0) {
+ pci_unmap_single(np->pci_dev,
+ np->tx_info[entry].mapping,
+ skb_first_frag_len(skb),
+ PCI_DMA_TODEVICE);
+ np->tx_info[entry].mapping = 0;
+ entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE;
+ for (j = 1; j < i; j++) {
+ pci_unmap_single(np->pci_dev,
+ np->tx_info[entry].mapping,
+ skb_frag_size(
+ &skb_shinfo(skb)->frags[j-1]),
+ PCI_DMA_TODEVICE);
+ entry++;
+ }
+ }
+ dev_kfree_skb_any(skb);
+ np->cur_tx = prev_tx;
+ return NETDEV_TX_OK;
+}

/* The interrupt handler does all of the Rx thread work and cleans up
after the Tx thread. */
@@ -1570,6 +1605,12 @@ static void refill_rx_ring(struct net_device *dev)
break; /* Better luck next round. */
np->rx_info[entry].mapping =
pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(np->pci_dev,
+ np->rx_info[entry].mapping)) {
+ dev_kfree_skb(skb);
+ np->rx_info[entry].skb = NULL;
+ break;
+ }
np->rx_ring[entry].rxaddr =
cpu_to_dma(np->rx_info[entry].mapping | RxDescValid);
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 48ee4110ef6e..5cc0f8cfec87 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1499,6 +1499,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
netdev_warn(bp->dev, "Link speed %d no longer supported\n",
speed);
}
+ set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event);
/* fall thru */
}
case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
@@ -5110,6 +5111,7 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
struct hwrm_port_phy_qcfg_input req = {0};
struct hwrm_port_phy_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
u8 link_up = link_info->link_up;
+ u16 diff;

bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCFG, -1, -1);

@@ -5197,6 +5199,18 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
link_info->link_up = 0;
}
mutex_unlock(&bp->hwrm_cmd_lock);
+
+ diff = link_info->support_auto_speeds ^ link_info->advertising;
+ if ((link_info->support_auto_speeds | diff) !=
+ link_info->support_auto_speeds) {
+ /* An advertised speed is no longer supported, so we need to
+ * update the advertisement settings. Caller holds RTNL
+ * so we can modify link settings.
+ */
+ link_info->advertising = link_info->support_auto_speeds;
+ if (link_info->autoneg & BNXT_AUTONEG_SPEED)
+ bnxt_hwrm_set_link_setting(bp, true, false);
+ }
return 0;
}

@@ -6080,29 +6094,37 @@ static void bnxt_timer(unsigned long data)
mod_timer(&bp->timer, jiffies + bp->current_interval);
}

-/* Only called from bnxt_sp_task() */
-static void bnxt_reset(struct bnxt *bp, bool silent)
+static void bnxt_rtnl_lock_sp(struct bnxt *bp)
{
- /* bnxt_reset_task() calls bnxt_close_nic() which waits
- * for BNXT_STATE_IN_SP_TASK to clear.
- * If there is a parallel dev_close(), bnxt_close() may be holding
+ /* We are called from bnxt_sp_task which has BNXT_STATE_IN_SP_TASK
+ * set. If the device is being closed, bnxt_close() may be holding
* rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear. So we
* must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
*/
clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
rtnl_lock();
- if (test_bit(BNXT_STATE_OPEN, &bp->state))
- bnxt_reset_task(bp, silent);
+}
+
+static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
+{
set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
rtnl_unlock();
}

+/* Only called from bnxt_sp_task() */
+static void bnxt_reset(struct bnxt *bp, bool silent)
+{
+ bnxt_rtnl_lock_sp(bp);
+ if (test_bit(BNXT_STATE_OPEN, &bp->state))
+ bnxt_reset_task(bp, silent);
+ bnxt_rtnl_unlock_sp(bp);
+}
+
static void bnxt_cfg_ntp_filters(struct bnxt *);

static void bnxt_sp_task(struct work_struct *work)
{
struct bnxt *bp = container_of(work, struct bnxt, sp_task);
- int rc;

set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
smp_mb__after_atomic();
@@ -6116,12 +6138,6 @@ static void bnxt_sp_task(struct work_struct *work)

if (test_and_clear_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event))
bnxt_cfg_ntp_filters(bp);
- if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
- rc = bnxt_update_link(bp, true);
- if (rc)
- netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
- rc);
- }
if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event))
bnxt_hwrm_exec_fwd_req(bp);
if (test_and_clear_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event)) {
@@ -6142,18 +6158,39 @@ static void bnxt_sp_task(struct work_struct *work)
bnxt_hwrm_tunnel_dst_port_free(
bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
}
+ if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
+ bnxt_hwrm_port_qstats(bp);
+
+ /* These functions below will clear BNXT_STATE_IN_SP_TASK. They
+ * must be the last functions to be called before exiting.
+ */
+ if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
+ int rc = 0;
+
+ if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
+ &bp->sp_event))
+ bnxt_hwrm_phy_qcaps(bp);
+
+ bnxt_rtnl_lock_sp(bp);
+ if (test_bit(BNXT_STATE_OPEN, &bp->state))
+ rc = bnxt_update_link(bp, true);
+ bnxt_rtnl_unlock_sp(bp);
+ if (rc)
+ netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
+ rc);
+ }
+ if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
+ bnxt_rtnl_lock_sp(bp);
+ if (test_bit(BNXT_STATE_OPEN, &bp->state))
+ bnxt_get_port_module_status(bp);
+ bnxt_rtnl_unlock_sp(bp);
+ }
if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
bnxt_reset(bp, false);

if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event))
bnxt_reset(bp, true);

- if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event))
- bnxt_get_port_module_status(bp);
-
- if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
- bnxt_hwrm_port_qstats(bp);
-
smp_mb__before_atomic();
clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 51b164a0e844..666bc0608ed7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1089,6 +1089,7 @@ struct bnxt {
#define BNXT_RESET_TASK_SILENT_SP_EVENT 11
#define BNXT_GENEVE_ADD_PORT_SP_EVENT 12
#define BNXT_GENEVE_DEL_PORT_SP_EVENT 13
+#define BNXT_LINK_SPEED_CHNG_SP_EVENT 14

struct bnxt_pf_info pf;
#ifdef CONFIG_BNXT_SRIOV
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 050e21fbb147..679679a4ccb2 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -31,6 +31,7 @@ struct lmac {
u8 lmac_type;
u8 lane_to_sds;
bool use_training;
+ bool autoneg;
bool link_up;
int lmacid; /* ID within BGX */
int lmacid_bd; /* ID on board */
@@ -418,7 +419,17 @@ static int bgx_lmac_sgmii_init(struct bgx *bgx, struct lmac *lmac)
/* power down, reset autoneg, autoneg enable */
cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_PCS_MRX_CTL);
cfg &= ~PCS_MRX_CTL_PWR_DN;
- cfg |= (PCS_MRX_CTL_RST_AN | PCS_MRX_CTL_AN_EN);
+ cfg |= PCS_MRX_CTL_RST_AN;
+ if (lmac->phydev) {
+ cfg |= PCS_MRX_CTL_AN_EN;
+ } else {
+ /* In scenarios where PHY driver is not present or it's a
+ * non-standard PHY, FW sets AN_EN to inform Linux driver
+ * to do auto-neg and link polling or not.
+ */
+ if (cfg & PCS_MRX_CTL_AN_EN)
+ lmac->autoneg = true;
+ }
bgx_reg_write(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, cfg);

if (lmac->lmac_type == BGX_MODE_QSGMII) {
@@ -429,7 +440,7 @@ static int bgx_lmac_sgmii_init(struct bgx *bgx, struct lmac *lmac)
return 0;
}

- if (lmac->lmac_type == BGX_MODE_SGMII) {
+ if ((lmac->lmac_type == BGX_MODE_SGMII) && lmac->phydev) {
if (bgx_poll_reg(bgx, lmacid, BGX_GMP_PCS_MRX_STATUS,
PCS_MRX_STATUS_AN_CPT, false)) {
dev_err(&bgx->pdev->dev, "BGX AN_CPT not completed\n");
@@ -623,12 +634,71 @@ static int bgx_xaui_check_link(struct lmac *lmac)
return -1;
}

+static void bgx_poll_for_sgmii_link(struct lmac *lmac)
+{
+ u64 pcs_link, an_result;
+ u8 speed;
+
+ pcs_link = bgx_reg_read(lmac->bgx, lmac->lmacid,
+ BGX_GMP_PCS_MRX_STATUS);
+
+ /*Link state bit is sticky, read it again*/
+ if (!(pcs_link & PCS_MRX_STATUS_LINK))
+ pcs_link = bgx_reg_read(lmac->bgx, lmac->lmacid,
+ BGX_GMP_PCS_MRX_STATUS);
+
+ if (bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_GMP_PCS_MRX_STATUS,
+ PCS_MRX_STATUS_AN_CPT, false)) {
+ lmac->link_up = false;
+ lmac->last_speed = SPEED_UNKNOWN;
+ lmac->last_duplex = DUPLEX_UNKNOWN;
+ goto next_poll;
+ }
+
+ lmac->link_up = ((pcs_link & PCS_MRX_STATUS_LINK) != 0) ? true : false;
+ an_result = bgx_reg_read(lmac->bgx, lmac->lmacid,
+ BGX_GMP_PCS_ANX_AN_RESULTS);
+
+ speed = (an_result >> 3) & 0x3;
+ lmac->last_duplex = (an_result >> 1) & 0x1;
+ switch (speed) {
+ case 0:
+ lmac->last_speed = 10;
+ break;
+ case 1:
+ lmac->last_speed = 100;
+ break;
+ case 2:
+ lmac->last_speed = 1000;
+ break;
+ default:
+ lmac->link_up = false;
+ lmac->last_speed = SPEED_UNKNOWN;
+ lmac->last_duplex = DUPLEX_UNKNOWN;
+ break;
+ }
+
+next_poll:
+
+ if (lmac->last_link != lmac->link_up) {
+ if (lmac->link_up)
+ bgx_sgmii_change_link_state(lmac);
+ lmac->last_link = lmac->link_up;
+ }
+
+ queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 3);
+}
+
static void bgx_poll_for_link(struct work_struct *work)
{
struct lmac *lmac;
u64 spu_link, smu_link;

lmac = container_of(work, struct lmac, dwork.work);
+ if (lmac->is_sgmii) {
+ bgx_poll_for_sgmii_link(lmac);
+ return;
+ }

/* Receive link is latching low. Force it high and verify it */
bgx_reg_modify(lmac->bgx, lmac->lmacid,
@@ -720,9 +790,21 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
(lmac->lmac_type != BGX_MODE_XLAUI) &&
(lmac->lmac_type != BGX_MODE_40G_KR) &&
(lmac->lmac_type != BGX_MODE_10G_KR)) {
- if (!lmac->phydev)
- return -ENODEV;
-
+ if (!lmac->phydev) {
+ if (lmac->autoneg) {
+ bgx_reg_write(bgx, lmacid,
+ BGX_GMP_PCS_LINKX_TIMER,
+ PCS_LINKX_TIMER_COUNT);
+ goto poll;
+ } else {
+ /* Default to below link speed and duplex */
+ lmac->link_up = true;
+ lmac->last_speed = 1000;
+ lmac->last_duplex = 1;
+ bgx_sgmii_change_link_state(lmac);
+ return 0;
+ }
+ }
lmac->phydev->dev_flags = 0;

if (phy_connect_direct(&lmac->netdev, lmac->phydev,
@@ -731,15 +813,17 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
return -ENODEV;

phy_start_aneg(lmac->phydev);
- } else {
- lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND |
- WQ_MEM_RECLAIM, 1);
- if (!lmac->check_link)
- return -ENOMEM;
- INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link);
- queue_delayed_work(lmac->check_link, &lmac->dwork, 0);
+ return 0;
}

+poll:
+ lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND |
+ WQ_MEM_RECLAIM, 1);
+ if (!lmac->check_link)
+ return -ENOMEM;
+ INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link);
+ queue_delayed_work(lmac->check_link, &lmac->dwork, 0);
+
return 0;
}

diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 01cc7c859131..1143e9575e53 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -144,10 +144,15 @@
#define PCS_MRX_CTL_LOOPBACK1 BIT_ULL(14)
#define PCS_MRX_CTL_RESET BIT_ULL(15)
#define BGX_GMP_PCS_MRX_STATUS 0x30008
+#define PCS_MRX_STATUS_LINK BIT_ULL(2)
#define PCS_MRX_STATUS_AN_CPT BIT_ULL(5)
+#define BGX_GMP_PCS_ANX_ADV 0x30010
#define BGX_GMP_PCS_ANX_AN_RESULTS 0x30020
+#define BGX_GMP_PCS_LINKX_TIMER 0x30040
+#define PCS_LINKX_TIMER_COUNT 0x1E84
#define BGX_GMP_PCS_SGM_AN_ADV 0x30068
#define BGX_GMP_PCS_MISCX_CTL 0x30078
+#define PCS_MISC_CTL_MODE BIT_ULL(8)
#define PCS_MISC_CTL_DISP_EN BIT_ULL(13)
#define PCS_MISC_CTL_GMX_ENO BIT_ULL(11)
#define PCS_MISC_CTL_SAMP_PT_MASK 0x7Full
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 9061c2f82b9c..d391beebe591 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2007,8 +2007,8 @@ static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue)
if (!rxb->page)
continue;

- dma_unmap_single(rx_queue->dev, rxb->dma,
- PAGE_SIZE, DMA_FROM_DEVICE);
+ dma_unmap_page(rx_queue->dev, rxb->dma,
+ PAGE_SIZE, DMA_FROM_DEVICE);
__free_page(rxb->page);

rxb->page = NULL;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index dff7b60345d8..c06845b7b666 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -304,8 +304,8 @@ int hns_nic_net_xmit_hw(struct net_device *ndev,
struct hns_nic_ring_data *ring_data)
{
struct hns_nic_priv *priv = netdev_priv(ndev);
- struct device *dev = priv->dev;
struct hnae_ring *ring = ring_data->ring;
+ struct device *dev = ring_to_dev(ring);
struct netdev_queue *dev_queue;
struct skb_frag_struct *frag;
int buf_num;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 0fbf686f5e7c..9f2184be55dc 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -189,9 +189,10 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
}
ltb->map_id = adapter->map_id;
adapter->map_id++;
+
+ init_completion(&adapter->fw_done);
send_request_map(adapter, ltb->addr,
ltb->size, ltb->map_id);
- init_completion(&adapter->fw_done);
wait_for_completion(&adapter->fw_done);
return 0;
}
@@ -505,7 +506,7 @@ static int ibmvnic_open(struct net_device *netdev)
adapter->rx_pool = NULL;
rx_pool_arr_alloc_failed:
for (i = 0; i < adapter->req_rx_queues; i++)
- napi_enable(&adapter->napi[i]);
+ napi_disable(&adapter->napi[i]);
alloc_napi_failed:
return -ENOMEM;
}
@@ -1133,10 +1134,10 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
crq.request_statistics.ioba = cpu_to_be32(adapter->stats_token);
crq.request_statistics.len =
cpu_to_be32(sizeof(struct ibmvnic_statistics));
- ibmvnic_send_crq(adapter, &crq);

/* Wait for data to be written */
init_completion(&adapter->stats_done);
+ ibmvnic_send_crq(adapter, &crq);
wait_for_completion(&adapter->stats_done);

for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++)
@@ -2197,12 +2198,12 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,

if (!found) {
dev_err(dev, "Couldn't find error id %x\n",
- crq->request_error_rsp.error_id);
+ be32_to_cpu(crq->request_error_rsp.error_id));
return;
}

dev_err(dev, "Detailed info for error id %x:",
- crq->request_error_rsp.error_id);
+ be32_to_cpu(crq->request_error_rsp.error_id));

for (i = 0; i < error_buff->len; i++) {
pr_cont("%02x", (int)error_buff->buff[i]);
@@ -2281,8 +2282,8 @@ static void handle_error_indication(union ibmvnic_crq *crq,
dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
crq->error_indication.
flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "",
- crq->error_indication.error_id,
- crq->error_indication.error_cause);
+ be32_to_cpu(crq->error_indication.error_id),
+ be16_to_cpu(crq->error_indication.error_cause));

error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
if (!error_buff)
@@ -2400,10 +2401,10 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
case PARTIALSUCCESS:
dev_info(dev, "req=%lld, rsp=%ld in %s queue, retrying.\n",
*req_value,
- (long int)be32_to_cpu(crq->request_capability_rsp.
+ (long int)be64_to_cpu(crq->request_capability_rsp.
number), name);
release_sub_crqs_no_irqs(adapter);
- *req_value = be32_to_cpu(crq->request_capability_rsp.number);
+ *req_value = be64_to_cpu(crq->request_capability_rsp.number);
init_sub_crqs(adapter, 1);
return;
default:
@@ -2809,9 +2810,9 @@ static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len,
crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator;
crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok);
crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size;
- ibmvnic_send_crq(adapter, &crq);

init_completion(&adapter->fw_done);
+ ibmvnic_send_crq(adapter, &crq);
wait_for_completion(&adapter->fw_done);

if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
@@ -3591,9 +3592,9 @@ static int ibmvnic_dump_show(struct seq_file *seq, void *v)
memset(&crq, 0, sizeof(crq));
crq.request_dump_size.first = IBMVNIC_CRQ_CMD;
crq.request_dump_size.cmd = REQUEST_DUMP_SIZE;
- ibmvnic_send_crq(adapter, &crq);

init_completion(&adapter->fw_done);
+ ibmvnic_send_crq(adapter, &crq);
wait_for_completion(&adapter->fw_done);

seq_write(seq, adapter->dump_data, adapter->dump_data_size);
@@ -3639,8 +3640,8 @@ static void handle_crq_init_rsp(struct work_struct *work)
}
}

- send_version_xchg(adapter);
reinit_completion(&adapter->init_done);
+ send_version_xchg(adapter);
if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
dev_err(dev, "Passive init timeout\n");
goto task_failed;
@@ -3650,9 +3651,9 @@ static void handle_crq_init_rsp(struct work_struct *work)
if (adapter->renegotiate) {
adapter->renegotiate = false;
release_sub_crqs_no_irqs(adapter);
- send_cap_queries(adapter);

reinit_completion(&adapter->init_done);
+ send_cap_queries(adapter);
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
dev_err(dev, "Passive init timeout\n");
@@ -3780,9 +3781,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
adapter->debugfs_dump = ent;
}
}
- ibmvnic_send_crq_init(adapter);

init_completion(&adapter->init_done);
+ ibmvnic_send_crq_init(adapter);
if (!wait_for_completion_timeout(&adapter->init_done, timeout))
return 0;

@@ -3790,9 +3791,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
if (adapter->renegotiate) {
adapter->renegotiate = false;
release_sub_crqs_no_irqs(adapter);
- send_cap_queries(adapter);

reinit_completion(&adapter->init_done);
+ send_cap_queries(adapter);
if (!wait_for_completion_timeout(&adapter->init_done,
timeout))
return 0;
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 86a89cbd3ec9..4832223f1500 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2518,7 +2518,7 @@ static int mtk_remove(struct platform_device *pdev)
}

const struct of_device_id of_mtk_match[] = {
- { .compatible = "mediatek,mt7623-eth" },
+ { .compatible = "mediatek,mt2701-eth" },
{},
};
MODULE_DEVICE_TABLE(of, of_mtk_match);
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index c7e939945259..53daa6ca5d83 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -158,7 +158,7 @@ static int mlx4_reset_slave(struct mlx4_dev *dev)
return -ETIMEDOUT;
}

-static int mlx4_comm_internal_err(u32 slave_read)
+int mlx4_comm_internal_err(u32 slave_read)
{
return (u32)COMM_CHAN_EVENT_INTERNAL_ERR ==
(slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 0e8b7c44931f..8258d08acd8c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -222,6 +222,18 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
return;

mlx4_stop_catas_poll(dev);
+ if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION &&
+ mlx4_is_slave(dev)) {
+ /* In mlx4_remove_one on a VF */
+ u32 slave_read =
+ swab32(readl(&mlx4_priv(dev)->mfunc.comm->slave_read));
+
+ if (mlx4_comm_internal_err(slave_read)) {
+ mlx4_dbg(dev, "%s: comm channel is down, entering error state.\n",
+ __func__);
+ mlx4_enter_error_state(dev->persist);
+ }
+ }
mutex_lock(&intf_mutex);

list_for_each_entry(intf, &intf_list, list)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 88ee7d8a5923..086920b615af 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1220,6 +1220,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type);
void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);

void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
+int mlx4_comm_internal_err(u32 slave_read);

int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
enum mlx4_port_type *type);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 36fbc6b21a33..8cd7227fbdfc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -1081,7 +1081,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
MLX5_FLOW_NAMESPACE_KERNEL);

if (!priv->fs.ns)
- return -EINVAL;
+ return -EOPNOTSUPP;

err = mlx5e_arfs_create_tables(priv);
if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index c7011ef4e351..a8966e6dbe1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -352,7 +352,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
if (!root_ns) {
esw_warn(dev, "Failed to get FDB flow namespace\n");
- return -ENOMEM;
+ return -EOPNOTSUPP;
}

flow_group_in = mlx5_vzalloc(inlen);
@@ -961,7 +961,7 @@ static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS);
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch egress flow namespace\n");
- return -EIO;
+ return -EOPNOTSUPP;
}

flow_group_in = mlx5_vzalloc(inlen);
@@ -1078,7 +1078,7 @@ static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS);
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n");
- return -EIO;
+ return -EOPNOTSUPP;
}

flow_group_in = mlx5_vzalloc(inlen);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d239f5d0ea36..b08b9e2c6a76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -414,6 +414,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
if (!root_ns) {
esw_warn(dev, "Failed to get FDB flow namespace\n");
+ err = -EOPNOTSUPP;
goto ns_err;
}

@@ -520,7 +521,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS);
if (!ns) {
esw_warn(esw->dev, "Failed to get offloads flow namespace\n");
- return -ENOMEM;
+ return -EOPNOTSUPP;
}

ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0);
@@ -639,7 +640,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw)
esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err);
err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
if (err1)
- esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err);
+ esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err1);
}
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 7e20e4bc4cc7..4de3c28b0547 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1678,7 +1678,7 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
struct mlx5_flow_table *ft;

ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR);
- if (!ns)
+ if (WARN_ON(!ns))
return -EINVAL;
ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL);
if (IS_ERR(ft)) {
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 862f18ed6022..510ff62584d6 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -179,6 +179,49 @@ static struct mdiobb_ops bb_ops = {
.get_mdio_data = ravb_get_mdio_data,
};

+/* Free TX skb function for AVB-IP */
+static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only)
+{
+ struct ravb_private *priv = netdev_priv(ndev);
+ struct net_device_stats *stats = &priv->stats[q];
+ struct ravb_tx_desc *desc;
+ int free_num = 0;
+ int entry;
+ u32 size;
+
+ for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
+ bool txed;
+
+ entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
+ NUM_TX_DESC);
+ desc = &priv->tx_ring[q][entry];
+ txed = desc->die_dt == DT_FEMPTY;
+ if (free_txed_only && !txed)
+ break;
+ /* Descriptor type must be checked before all other reads */
+ dma_rmb();
+ size = le16_to_cpu(desc->ds_tagl) & TX_DS;
+ /* Free the original skb. */
+ if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
+ dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
+ size, DMA_TO_DEVICE);
+ /* Last packet descriptor? */
+ if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
+ entry /= NUM_TX_DESC;
+ dev_kfree_skb_any(priv->tx_skb[q][entry]);
+ priv->tx_skb[q][entry] = NULL;
+ if (txed)
+ stats->tx_packets++;
+ }
+ free_num++;
+ }
+ if (txed)
+ stats->tx_bytes += size;
+ desc->die_dt = DT_EEMPTY;
+ }
+ return free_num;
+}
+
/* Free skb's and DMA buffers for Ethernet AVB */
static void ravb_ring_free(struct net_device *ndev, int q)
{
@@ -194,19 +237,21 @@ static void ravb_ring_free(struct net_device *ndev, int q)
kfree(priv->rx_skb[q]);
priv->rx_skb[q] = NULL;

- /* Free TX skb ringbuffer */
- if (priv->tx_skb[q]) {
- for (i = 0; i < priv->num_tx_ring[q]; i++)
- dev_kfree_skb(priv->tx_skb[q][i]);
- }
- kfree(priv->tx_skb[q]);
- priv->tx_skb[q] = NULL;
-
/* Free aligned TX buffers */
kfree(priv->tx_align[q]);
priv->tx_align[q] = NULL;

if (priv->rx_ring[q]) {
+ for (i = 0; i < priv->num_rx_ring[q]; i++) {
+ struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];
+
+ if (!dma_mapping_error(ndev->dev.parent,
+ le32_to_cpu(desc->dptr)))
+ dma_unmap_single(ndev->dev.parent,
+ le32_to_cpu(desc->dptr),
+ PKT_BUF_SZ,
+ DMA_FROM_DEVICE);
+ }
ring_size = sizeof(struct ravb_ex_rx_desc) *
(priv->num_rx_ring[q] + 1);
dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q],
@@ -215,12 +260,20 @@ static void ravb_ring_free(struct net_device *ndev, int q)
}

if (priv->tx_ring[q]) {
+ ravb_tx_free(ndev, q, false);
+
ring_size = sizeof(struct ravb_tx_desc) *
(priv->num_tx_ring[q] * NUM_TX_DESC + 1);
dma_free_coherent(ndev->dev.parent, ring_size, priv->tx_ring[q],
priv->tx_desc_dma[q]);
priv->tx_ring[q] = NULL;
}
+
+ /* Free TX skb ringbuffer.
+ * SKBs are freed by ravb_tx_free() call above.
+ */
+ kfree(priv->tx_skb[q]);
+ priv->tx_skb[q] = NULL;
}

/* Format skb and descriptor buffer for Ethernet AVB */
@@ -431,44 +484,6 @@ static int ravb_dmac_init(struct net_device *ndev)
return 0;
}

-/* Free TX skb function for AVB-IP */
-static int ravb_tx_free(struct net_device *ndev, int q)
-{
- struct ravb_private *priv = netdev_priv(ndev);
- struct net_device_stats *stats = &priv->stats[q];
- struct ravb_tx_desc *desc;
- int free_num = 0;
- int entry;
- u32 size;
-
- for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
- entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
- NUM_TX_DESC);
- desc = &priv->tx_ring[q][entry];
- if (desc->die_dt != DT_FEMPTY)
- break;
- /* Descriptor type must be checked before all other reads */
- dma_rmb();
- size = le16_to_cpu(desc->ds_tagl) & TX_DS;
- /* Free the original skb. */
- if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
- dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
- size, DMA_TO_DEVICE);
- /* Last packet descriptor? */
- if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
- entry /= NUM_TX_DESC;
- dev_kfree_skb_any(priv->tx_skb[q][entry]);
- priv->tx_skb[q][entry] = NULL;
- stats->tx_packets++;
- }
- free_num++;
- }
- stats->tx_bytes += size;
- desc->die_dt = DT_EEMPTY;
- }
- return free_num;
-}
-
static void ravb_get_tx_tstamp(struct net_device *ndev)
{
struct ravb_private *priv = netdev_priv(ndev);
@@ -902,7 +917,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
spin_lock_irqsave(&priv->lock, flags);
/* Clear TX interrupt */
ravb_write(ndev, ~mask, TIS);
- ravb_tx_free(ndev, q);
+ ravb_tx_free(ndev, q, true);
netif_wake_subqueue(ndev, q);
mmiowb();
spin_unlock_irqrestore(&priv->lock, flags);
@@ -1571,7 +1586,8 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)

priv->cur_tx[q] += NUM_TX_DESC;
if (priv->cur_tx[q] - priv->dirty_tx[q] >
- (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && !ravb_tx_free(ndev, q))
+ (priv->num_tx_ring[q] - 1) * NUM_TX_DESC &&
+ !ravb_tx_free(ndev, q, true))
netif_stop_subqueue(ndev, q);

exit:
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 93dc10b10c09..aa02a03a6d8d 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -100,6 +100,14 @@
/* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)

+#ifdef __BIG_ENDIAN
+#define xemaclite_readl ioread32be
+#define xemaclite_writel iowrite32be
+#else
+#define xemaclite_readl ioread32
+#define xemaclite_writel iowrite32
+#endif
+
/**
* struct net_local - Our private per device data
* @ndev: instance of the network device
@@ -156,15 +164,15 @@ static void xemaclite_enable_interrupts(struct net_local *drvdata)
u32 reg_data;

/* Enable the Tx interrupts for the first Buffer */
- reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
- __raw_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
- drvdata->base_addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
+ drvdata->base_addr + XEL_TSR_OFFSET);

/* Enable the Rx interrupts for the first buffer */
- __raw_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
+ xemaclite_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);

/* Enable the Global Interrupt Enable */
- __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+ xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
}

/**
@@ -179,17 +187,17 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata)
u32 reg_data;

/* Disable the Global Interrupt Enable */
- __raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+ xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);

/* Disable the Tx interrupts for the first buffer */
- reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
- __raw_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
- drvdata->base_addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
+ drvdata->base_addr + XEL_TSR_OFFSET);

/* Disable the Rx interrupts for the first buffer */
- reg_data = __raw_readl(drvdata->base_addr + XEL_RSR_OFFSET);
- __raw_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
- drvdata->base_addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(drvdata->base_addr + XEL_RSR_OFFSET);
+ xemaclite_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
+ drvdata->base_addr + XEL_RSR_OFFSET);
}

/**
@@ -321,7 +329,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
byte_count = ETH_FRAME_LEN;

/* Check if the expected buffer is available */
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
XEL_TSR_XMIT_ACTIVE_MASK)) == 0) {

@@ -334,7 +342,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,

addr = (void __iomem __force *)((u32 __force)addr ^
XEL_BUFFER_OFFSET);
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);

if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
XEL_TSR_XMIT_ACTIVE_MASK)) != 0)
@@ -345,16 +353,16 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
/* Write the frame to the buffer */
xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);

- __raw_writel((byte_count & XEL_TPLR_LENGTH_MASK),
- addr + XEL_TPLR_OFFSET);
+ xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
+ addr + XEL_TPLR_OFFSET);

/* Update the Tx Status Register to indicate that there is a
* frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
* is used by the interrupt handler to check whether a frame
* has been transmitted */
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
- __raw_writel(reg_data, addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);

return 0;
}
@@ -369,7 +377,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
*
* Return: Total number of bytes received
*/
-static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
+static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
{
void __iomem *addr;
u16 length, proto_type;
@@ -379,7 +387,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
addr = (drvdata->base_addr + drvdata->next_rx_buf_to_use);

/* Verify which buffer has valid data */
- reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);

if ((reg_data & XEL_RSR_RECV_DONE_MASK) == XEL_RSR_RECV_DONE_MASK) {
if (drvdata->rx_ping_pong != 0)
@@ -396,27 +404,28 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
return 0; /* No data was available */

/* Verify that buffer has valid data */
- reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
if ((reg_data & XEL_RSR_RECV_DONE_MASK) !=
XEL_RSR_RECV_DONE_MASK)
return 0; /* No data was available */
}

/* Get the protocol type of the ethernet frame that arrived */
- proto_type = ((ntohl(__raw_readl(addr + XEL_HEADER_OFFSET +
+ proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
XEL_RPLR_LENGTH_MASK);

/* Check if received ethernet frame is a raw ethernet frame
* or an IP packet or an ARP packet */
- if (proto_type > (ETH_FRAME_LEN + ETH_FCS_LEN)) {
+ if (proto_type > ETH_DATA_LEN) {

if (proto_type == ETH_P_IP) {
- length = ((ntohl(__raw_readl(addr +
+ length = ((ntohl(xemaclite_readl(addr +
XEL_HEADER_IP_LENGTH_OFFSET +
XEL_RXBUFF_OFFSET)) >>
XEL_HEADER_SHIFT) &
XEL_RPLR_LENGTH_MASK);
+ length = min_t(u16, length, ETH_DATA_LEN);
length += ETH_HLEN + ETH_FCS_LEN;

} else if (proto_type == ETH_P_ARP)
@@ -429,14 +438,17 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
/* Use the length in the frame, plus the header and trailer */
length = proto_type + ETH_HLEN + ETH_FCS_LEN;

+ if (WARN_ON(length > maxlen))
+ length = maxlen;
+
/* Read from the EmacLite device */
xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
data, length);

/* Acknowledge the frame */
- reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
reg_data &= ~XEL_RSR_RECV_DONE_MASK;
- __raw_writel(reg_data, addr + XEL_RSR_OFFSET);
+ xemaclite_writel(reg_data, addr + XEL_RSR_OFFSET);

return length;
}
@@ -463,14 +475,14 @@ static void xemaclite_update_address(struct net_local *drvdata,

xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);

- __raw_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
+ xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);

/* Update the MAC address in the EmacLite */
- reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
- __raw_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
+ reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
+ xemaclite_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);

/* Wait for EmacLite to finish with the MAC address update */
- while ((__raw_readl(addr + XEL_TSR_OFFSET) &
+ while ((xemaclite_readl(addr + XEL_TSR_OFFSET) &
XEL_TSR_PROG_MAC_ADDR) != 0)
;
}
@@ -603,7 +615,7 @@ static void xemaclite_rx_handler(struct net_device *dev)

skb_reserve(skb, 2);

- len = xemaclite_recv_data(lp, (u8 *) skb->data);
+ len = xemaclite_recv_data(lp, (u8 *) skb->data, len);

if (!len) {
dev->stats.rx_errors++;
@@ -640,32 +652,32 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
u32 tx_status;

/* Check if there is Rx Data available */
- if ((__raw_readl(base_addr + XEL_RSR_OFFSET) &
+ if ((xemaclite_readl(base_addr + XEL_RSR_OFFSET) &
XEL_RSR_RECV_DONE_MASK) ||
- (__raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
+ (xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
& XEL_RSR_RECV_DONE_MASK))

xemaclite_rx_handler(dev);

/* Check if the Transmission for the first buffer is completed */
- tx_status = __raw_readl(base_addr + XEL_TSR_OFFSET);
+ tx_status = xemaclite_readl(base_addr + XEL_TSR_OFFSET);
if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {

tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
- __raw_writel(tx_status, base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(tx_status, base_addr + XEL_TSR_OFFSET);

tx_complete = true;
}

/* Check if the Transmission for the second buffer is completed */
- tx_status = __raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+ tx_status = xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {

tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
- __raw_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
- XEL_TSR_OFFSET);
+ xemaclite_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
+ XEL_TSR_OFFSET);

tx_complete = true;
}
@@ -698,7 +710,7 @@ static int xemaclite_mdio_wait(struct net_local *lp)
/* wait for the MDIO interface to not be busy or timeout
after some time.
*/
- while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
+ while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
XEL_MDIOCTRL_MDIOSTS_MASK) {
if (time_before_eq(end, jiffies)) {
WARN_ON(1);
@@ -734,17 +746,17 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
* MDIO Address register. Set the Status bit in the MDIO Control
* register to start a MDIO read transaction.
*/
- ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
- __raw_writel(XEL_MDIOADDR_OP_MASK |
- ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
- lp->base_addr + XEL_MDIOADDR_OFFSET);
- __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
- lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ xemaclite_writel(XEL_MDIOADDR_OP_MASK |
+ ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+ lp->base_addr + XEL_MDIOADDR_OFFSET);
+ xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+ lp->base_addr + XEL_MDIOCTRL_OFFSET);

if (xemaclite_mdio_wait(lp))
return -ETIMEDOUT;

- rc = __raw_readl(lp->base_addr + XEL_MDIORD_OFFSET);
+ rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);

dev_dbg(&lp->ndev->dev,
"xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
@@ -781,13 +793,13 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
* Data register. Finally, set the Status bit in the MDIO Control
* register to start a MDIO write transaction.
*/
- ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
- __raw_writel(~XEL_MDIOADDR_OP_MASK &
- ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
- lp->base_addr + XEL_MDIOADDR_OFFSET);
- __raw_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
- __raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
- lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ xemaclite_writel(~XEL_MDIOADDR_OP_MASK &
+ ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+ lp->base_addr + XEL_MDIOADDR_OFFSET);
+ xemaclite_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
+ xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+ lp->base_addr + XEL_MDIOCTRL_OFFSET);

return 0;
}
@@ -834,8 +846,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev)
/* Enable the MDIO bus by asserting the enable bit in MDIO Control
* register.
*/
- __raw_writel(XEL_MDIOCTRL_MDIOEN_MASK,
- lp->base_addr + XEL_MDIOCTRL_OFFSET);
+ xemaclite_writel(XEL_MDIOCTRL_MDIOEN_MASK,
+ lp->base_addr + XEL_MDIOCTRL_OFFSET);

bus = mdiobus_alloc();
if (!bus) {
@@ -1140,8 +1152,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev)
}

/* Clear the Tx CSR's in case this is a restart */
- __raw_writel(0, lp->base_addr + XEL_TSR_OFFSET);
- __raw_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+ xemaclite_writel(0, lp->base_addr + XEL_TSR_OFFSET);
+ xemaclite_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);

/* Set the MAC address in the EmacLite device */
xemaclite_update_address(lp, ndev->dev_addr);
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 97e0cbca0a08..cebde074d196 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1372,3 +1372,4 @@ MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <hwelte@xxxxxxxxxxx>");
MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic");
MODULE_ALIAS_RTNL_LINK("gtp");
+MODULE_ALIAS_GENL_FAMILY("gtp");
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 1dfe2304daa7..e0a6b1a0ca88 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -648,8 +648,8 @@ static void ax_setup(struct net_device *dev)
{
/* Finish setting up the DEVICE info. */
dev->mtu = AX_MTU;
- dev->hard_header_len = 0;
- dev->addr_len = 0;
+ dev->hard_header_len = AX25_MAX_HEADER_LEN;
+ dev->addr_len = AX25_ADDR_LEN;
dev->type = ARPHRD_AX25;
dev->tx_queue_len = 10;
dev->header_ops = &ax25_header_ops;
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index ea92d524d5a8..fab56c9350cf 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1014,6 +1014,20 @@ static struct phy_driver ksphy_driver[] = {
.get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
+}, {
+ .phy_id = PHY_ID_KSZ8795,
+ .phy_id_mask = MICREL_PHY_ID_MASK,
+ .name = "Micrel KSZ8795",
+ .features = (SUPPORTED_Pause | SUPPORTED_Asym_Pause),
+ .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
+ .config_init = kszphy_config_init,
+ .config_aneg = ksz8873mll_config_aneg,
+ .read_status = ksz8873mll_read_status,
+ .get_sset_count = kszphy_get_sset_count,
+ .get_strings = kszphy_get_strings,
+ .get_stats = kszphy_get_stats,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
} };

module_phy_driver(ksphy_driver);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index c4ceb082e970..14d57d0d1c04 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -860,6 +860,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
struct module *ndev_owner = dev->dev.parent->driver->owner;
struct mii_bus *bus = phydev->mdio.bus;
struct device *d = &phydev->mdio.dev;
+ bool using_genphy = false;
int err;

/* For Ethernet device drivers that register their own MDIO bus, we
@@ -885,12 +886,22 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
d->driver =
&genphy_driver[GENPHY_DRV_1G].mdiodrv.driver;

+ using_genphy = true;
+ }
+
+ if (!try_module_get(d->driver->owner)) {
+ dev_err(&dev->dev, "failed to get the device driver module\n");
+ err = -EIO;
+ goto error_put_device;
+ }
+
+ if (using_genphy) {
err = d->driver->probe(d);
if (err >= 0)
err = device_bind_driver(d);

if (err)
- goto error;
+ goto error_module_put;
}

if (phydev->attached_dev) {
@@ -926,6 +937,13 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
return err;

error:
+ /* phy_detach() does all of the cleanup below */
+ phy_detach(phydev);
+ return err;
+
+error_module_put:
+ module_put(d->driver->owner);
+error_put_device:
put_device(d);
if (ndev_owner != bus->owner)
module_put(bus->owner);
@@ -987,6 +1005,8 @@ void phy_detach(struct phy_device *phydev)
phydev->attached_dev = NULL;
phy_suspend(phydev);

+ module_put(phydev->mdio.dev.driver->owner);
+
/* If the device had no specific driver before (i.e. - it
* was using the generic driver), we unbind the device
* from the generic driver so that there's a chance a
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 90b426c5ffce..afb953a258cd 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
#define NETNEXT_VERSION "08"

/* Information for net */
-#define NET_VERSION "7"
+#define NET_VERSION "8"

#define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@xxxxxxxxxxx>"
@@ -1936,6 +1936,9 @@ static int r8152_poll(struct napi_struct *napi, int budget)
napi_complete(napi);
if (!list_empty(&tp->rx_done))
napi_schedule(napi);
+ else if (!skb_queue_empty(&tp->tx_queue) &&
+ !list_empty(&tp->tx_free))
+ napi_schedule(napi);
}

return work_done;
@@ -3155,10 +3158,13 @@ static void set_carrier(struct r8152 *tp)
if (!netif_carrier_ok(netdev)) {
tp->rtl_ops.enable(tp);
set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+ netif_stop_queue(netdev);
napi_disable(&tp->napi);
netif_carrier_on(netdev);
rtl_start_rx(tp);
napi_enable(&tp->napi);
+ netif_wake_queue(netdev);
+ netif_info(tp, link, netdev, "carrier on\n");
}
} else {
if (netif_carrier_ok(netdev)) {
@@ -3166,6 +3172,7 @@ static void set_carrier(struct r8152 *tp)
napi_disable(&tp->napi);
tp->rtl_ops.disable(tp);
napi_enable(&tp->napi);
+ netif_info(tp, link, netdev, "carrier off\n");
}
}
}
@@ -3515,12 +3522,12 @@ static int rtl8152_pre_reset(struct usb_interface *intf)
if (!netif_running(netdev))
return 0;

+ netif_stop_queue(netdev);
napi_disable(&tp->napi);
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
if (netif_carrier_ok(netdev)) {
- netif_stop_queue(netdev);
mutex_lock(&tp->control);
tp->rtl_ops.disable(tp);
mutex_unlock(&tp->control);
@@ -3545,12 +3552,17 @@ static int rtl8152_post_reset(struct usb_interface *intf)
if (netif_carrier_ok(netdev)) {
mutex_lock(&tp->control);
tp->rtl_ops.enable(tp);
+ rtl_start_rx(tp);
rtl8152_set_rx_mode(netdev);
mutex_unlock(&tp->control);
- netif_wake_queue(netdev);
}

napi_enable(&tp->napi);
+ netif_wake_queue(netdev);
+ usb_submit_urb(tp->intr_urb, GFP_KERNEL);
+
+ if (!list_empty(&tp->rx_done))
+ napi_schedule(&tp->napi);

return 0;
}
@@ -3583,10 +3595,15 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
struct net_device *netdev = tp->netdev;
int ret = 0;

+ set_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
+
if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
u32 rcr = 0;

if (delay_autosuspend(tp)) {
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
ret = -EBUSY;
goto out1;
}
@@ -3603,6 +3620,8 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
if (!(ocp_data & RXFIFO_EMPTY)) {
rxdy_gated_en(tp, false);
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
ret = -EBUSY;
goto out1;
}
@@ -3622,8 +3641,6 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
}
}

- set_bit(SELECTIVE_SUSPEND, &tp->flags);
-
out1:
return ret;
}
@@ -3679,12 +3696,15 @@ static int rtl8152_resume(struct usb_interface *intf)
if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
tp->rtl_ops.autosuspend_en(tp, false);
- clear_bit(SELECTIVE_SUSPEND, &tp->flags);
napi_disable(&tp->napi);
set_bit(WORK_ENABLE, &tp->flags);
if (netif_carrier_ok(tp->netdev))
rtl_start_rx(tp);
napi_enable(&tp->napi);
+ clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+ smp_mb__after_atomic();
+ if (!list_empty(&tp->rx_done))
+ napi_schedule(&tp->napi);
} else {
tp->rtl_ops.up(tp);
netif_carrier_off(tp->netdev);
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index a251588762ec..0b5a84c9022c 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -73,8 +73,6 @@ static atomic_t iface_counter = ATOMIC_INIT(0);
/* Private data structure */
struct sierra_net_data {

- u8 ethr_hdr_tmpl[ETH_HLEN]; /* ethernet header template for rx'd pkts */
-
u16 link_up; /* air link up or down */
u8 tx_hdr_template[4]; /* part of HIP hdr for tx'd packets */

@@ -122,6 +120,7 @@ struct param {

/* LSI Protocol types */
#define SIERRA_NET_PROTOCOL_UMTS 0x01
+#define SIERRA_NET_PROTOCOL_UMTS_DS 0x04
/* LSI Coverage */
#define SIERRA_NET_COVERAGE_NONE 0x00
#define SIERRA_NET_COVERAGE_NOPACKET 0x01
@@ -129,7 +128,8 @@ struct param {
/* LSI Session */
#define SIERRA_NET_SESSION_IDLE 0x00
/* LSI Link types */
-#define SIERRA_NET_AS_LINK_TYPE_IPv4 0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV4 0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV6 0x02

struct lsi_umts {
u8 protocol;
@@ -137,9 +137,14 @@ struct lsi_umts {
__be16 length;
/* eventually use a union for the rest - assume umts for now */
u8 coverage;
- u8 unused2[41];
+ u8 network_len; /* network name len */
+ u8 network[40]; /* network name (UCS2, bigendian) */
u8 session_state;
u8 unused3[33];
+} __packed;
+
+struct lsi_umts_single {
+ struct lsi_umts lsi;
u8 link_type;
u8 pdp_addr_len; /* NW-supplied PDP address len */
u8 pdp_addr[16]; /* NW-supplied PDP address (bigendian)) */
@@ -158,10 +163,31 @@ struct lsi_umts {
u8 reserved[8];
} __packed;

+struct lsi_umts_dual {
+ struct lsi_umts lsi;
+ u8 pdp_addr4_len; /* NW-supplied PDP IPv4 address len */
+ u8 pdp_addr4[4]; /* NW-supplied PDP IPv4 address (bigendian)) */
+ u8 pdp_addr6_len; /* NW-supplied PDP IPv6 address len */
+ u8 pdp_addr6[16]; /* NW-supplied PDP IPv6 address (bigendian)) */
+ u8 unused4[23];
+ u8 dns1_addr4_len; /* NW-supplied 1st DNS v4 address len (bigendian) */
+ u8 dns1_addr4[4]; /* NW-supplied 1st DNS v4 address */
+ u8 dns1_addr6_len; /* NW-supplied 1st DNS v6 address len */
+ u8 dns1_addr6[16]; /* NW-supplied 1st DNS v6 address (bigendian)*/
+ u8 dns2_addr4_len; /* NW-supplied 2nd DNS v4 address len (bigendian) */
+ u8 dns2_addr4[4]; /* NW-supplied 2nd DNS v4 address */
+ u8 dns2_addr6_len; /* NW-supplied 2nd DNS v6 address len */
+ u8 dns2_addr6[16]; /* NW-supplied 2nd DNS v6 address (bigendian)*/
+ u8 unused5[68];
+} __packed;
+
#define SIERRA_NET_LSI_COMMON_LEN 4
-#define SIERRA_NET_LSI_UMTS_LEN (sizeof(struct lsi_umts))
+#define SIERRA_NET_LSI_UMTS_LEN (sizeof(struct lsi_umts_single))
#define SIERRA_NET_LSI_UMTS_STATUS_LEN \
(SIERRA_NET_LSI_UMTS_LEN - SIERRA_NET_LSI_COMMON_LEN)
+#define SIERRA_NET_LSI_UMTS_DS_LEN (sizeof(struct lsi_umts_dual))
+#define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \
+ (SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN)

/* Forward definitions */
static void sierra_sync_timer(unsigned long syncdata);
@@ -191,10 +217,11 @@ static inline void sierra_net_set_private(struct usbnet *dev,
dev->data[0] = (unsigned long)priv;
}

-/* is packet IPv4 */
+/* is packet IPv4/IPv6 */
static inline int is_ip(struct sk_buff *skb)
{
- return skb->protocol == cpu_to_be16(ETH_P_IP);
+ return skb->protocol == cpu_to_be16(ETH_P_IP) ||
+ skb->protocol == cpu_to_be16(ETH_P_IPV6);
}

/*
@@ -350,49 +377,54 @@ static inline int sierra_net_is_valid_addrlen(u8 len)
static int sierra_net_parse_lsi(struct usbnet *dev, char *data, int datalen)
{
struct lsi_umts *lsi = (struct lsi_umts *)data;
+ u32 expected_length;

- if (datalen < sizeof(struct lsi_umts)) {
- netdev_err(dev->net, "%s: Data length %d, exp %Zu\n",
- __func__, datalen,
- sizeof(struct lsi_umts));
+ if (datalen < sizeof(struct lsi_umts_single)) {
+ netdev_err(dev->net, "%s: Data length %d, exp >= %Zu\n",
+ __func__, datalen, sizeof(struct lsi_umts_single));
return -1;
}

- if (lsi->length != cpu_to_be16(SIERRA_NET_LSI_UMTS_STATUS_LEN)) {
- netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
- __func__, be16_to_cpu(lsi->length),
- (u32)SIERRA_NET_LSI_UMTS_STATUS_LEN);
- return -1;
+ /* Validate the session state */
+ if (lsi->session_state == SIERRA_NET_SESSION_IDLE) {
+ netdev_err(dev->net, "Session idle, 0x%02x\n",
+ lsi->session_state);
+ return 0;
}

/* Validate the protocol - only support UMTS for now */
- if (lsi->protocol != SIERRA_NET_PROTOCOL_UMTS) {
+ if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS) {
+ struct lsi_umts_single *single = (struct lsi_umts_single *)lsi;
+
+ /* Validate the link type */
+ if (single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV4 &&
+ single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV6) {
+ netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
+ single->link_type);
+ return -1;
+ }
+ expected_length = SIERRA_NET_LSI_UMTS_STATUS_LEN;
+ } else if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS_DS) {
+ expected_length = SIERRA_NET_LSI_UMTS_DS_STATUS_LEN;
+ } else {
netdev_err(dev->net, "Protocol unsupported, 0x%02x\n",
- lsi->protocol);
+ lsi->protocol);
return -1;
}

- /* Validate the link type */
- if (lsi->link_type != SIERRA_NET_AS_LINK_TYPE_IPv4) {
- netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
- lsi->link_type);
+ if (be16_to_cpu(lsi->length) != expected_length) {
+ netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
+ __func__, be16_to_cpu(lsi->length), expected_length);
return -1;
}

/* Validate the coverage */
- if (lsi->coverage == SIERRA_NET_COVERAGE_NONE
- || lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
+ if (lsi->coverage == SIERRA_NET_COVERAGE_NONE ||
+ lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
netdev_err(dev->net, "No coverage, 0x%02x\n", lsi->coverage);
return 0;
}

- /* Validate the session state */
- if (lsi->session_state == SIERRA_NET_SESSION_IDLE) {
- netdev_err(dev->net, "Session idle, 0x%02x\n",
- lsi->session_state);
- return 0;
- }
-
/* Set link_sense true */
return 1;
}
@@ -662,7 +694,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
u8 numendpoints;
u16 fwattr = 0;
int status;
- struct ethhdr *eth;
struct sierra_net_data *priv;
static const u8 sync_tmplate[sizeof(priv->sync_msg)] = {
0x00, 0x00, SIERRA_NET_HIP_MSYNC_ID, 0x00};
@@ -700,11 +731,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
dev->net->dev_addr[ETH_ALEN-2] = atomic_inc_return(&iface_counter);
dev->net->dev_addr[ETH_ALEN-1] = ifacenum;

- /* we will have to manufacture ethernet headers, prepare template */
- eth = (struct ethhdr *)priv->ethr_hdr_tmpl;
- memcpy(&eth->h_dest, dev->net->dev_addr, ETH_ALEN);
- eth->h_proto = cpu_to_be16(ETH_P_IP);
-
/* prepare shutdown message template */
memcpy(priv->shdwn_msg, shdwn_tmplate, sizeof(priv->shdwn_msg));
/* set context index initially to 0 - prepares tx hdr template */
@@ -833,9 +859,14 @@ static int sierra_net_rx_fixup(struct usbnet *dev, struct sk_buff *skb)

skb_pull(skb, hh.hdrlen);

- /* We are going to accept this packet, prepare it */
- memcpy(skb->data, sierra_net_get_private(dev)->ethr_hdr_tmpl,
- ETH_HLEN);
+ /* We are going to accept this packet, prepare it.
+ * In case protocol is IPv6, keep it, otherwise force IPv4.
+ */
+ skb_reset_mac_header(skb);
+ if (eth_hdr(skb)->h_proto != cpu_to_be16(ETH_P_IPV6))
+ eth_hdr(skb)->h_proto = cpu_to_be16(ETH_P_IP);
+ eth_zero_addr(eth_hdr(skb)->h_source);
+ memcpy(eth_hdr(skb)->h_dest, dev->net->dev_addr, ETH_ALEN);

/* Last packet in batch handled by usbnet */
if (hh.payload_len.word == skb->len)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 005ef5d17a19..ca8ddc3fb19e 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -438,6 +438,10 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
{
struct ib_recv_wr *bad_wr;

+ ib_dma_sync_single_for_device(ndev->device,
+ cmd->sge[0].addr, cmd->sge[0].length,
+ DMA_FROM_DEVICE);
+
if (ndev->srq)
return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
@@ -538,6 +542,11 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
first_wr = &rsp->send_wr;

nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd);
+
+ ib_dma_sync_single_for_device(rsp->queue->dev->device,
+ rsp->send_sge.addr, rsp->send_sge.length,
+ DMA_TO_DEVICE);
+
if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
pr_err("sending cmd response failed\n");
nvmet_rdma_release_rsp(rsp);
@@ -698,6 +707,14 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
cmd->n_rdma = 0;
cmd->req.port = queue->port;

+
+ ib_dma_sync_single_for_cpu(queue->dev->device,
+ cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length,
+ DMA_FROM_DEVICE);
+ ib_dma_sync_single_for_cpu(queue->dev->device,
+ cmd->send_sge.addr, cmd->send_sge.length,
+ DMA_TO_DEVICE);
+
if (!nvmet_req_init(&cmd->req, &queue->nvme_cq,
&queue->nvme_sq, &nvmet_rdma_ops))
return;
diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c
index 6e3a60c78873..50f3bb0dd1f1 100644
--- a/drivers/parport/parport_gsc.c
+++ b/drivers/parport/parport_gsc.c
@@ -293,7 +293,7 @@ struct parport *parport_gsc_probe_port(unsigned long base,
p->irq = PARPORT_IRQ_NONE;
}
if (p->irq != PARPORT_IRQ_NONE) {
- printk(", irq %d", p->irq);
+ pr_cont(", irq %d", p->irq);

if (p->dma == PARPORT_DMA_AUTO) {
p->dma = PARPORT_DMA_NONE;
@@ -303,8 +303,8 @@ struct parport *parport_gsc_probe_port(unsigned long base,
is mandatory (see above) */
p->dma = PARPORT_DMA_NONE;

- printk(" [");
-#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}}
+ pr_cont(" [");
+#define printmode(x) {if(p->modes&PARPORT_MODE_##x){pr_cont("%s%s",f?",":"",#x);f++;}}
{
int f = 0;
printmode(PCSPP);
@@ -315,7 +315,7 @@ struct parport *parport_gsc_probe_port(unsigned long base,
// printmode(DMA);
}
#undef printmode
- printk("]\n");
+ pr_cont("]\n");

if (p->irq != PARPORT_IRQ_NONE) {
if (request_irq (p->irq, parport_irq_handler,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 579c4946dc6e..e7d4048e81f2 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2142,7 +2142,8 @@ bool pci_dev_keep_suspended(struct pci_dev *pci_dev)

if (!pm_runtime_suspended(dev)
|| pci_target_state(pci_dev) != pci_dev->current_state
- || platform_pci_need_resume(pci_dev))
+ || platform_pci_need_resume(pci_dev)
+ || (pci_dev->dev_flags & PCI_DEV_FLAGS_NEEDS_RESUME))
return false;

/*
diff --git a/drivers/pinctrl/berlin/berlin-bg4ct.c b/drivers/pinctrl/berlin/berlin-bg4ct.c
index 09172043d589..c617ec49e9ed 100644
--- a/drivers/pinctrl/berlin/berlin-bg4ct.c
+++ b/drivers/pinctrl/berlin/berlin-bg4ct.c
@@ -217,7 +217,7 @@ static const struct berlin_desc_group berlin4ct_soc_pinctrl_groups[] = {
BERLIN_PINCTRL_GROUP("SCRD0_CRD_PRES", 0xc, 0x3, 0x15,
BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO20 */
BERLIN_PINCTRL_FUNCTION(0x1, "scrd0"), /* crd pres */
- BERLIN_PINCTRL_FUNCTION(0x1, "sd1a")), /* DAT3 */
+ BERLIN_PINCTRL_FUNCTION(0x3, "sd1a")), /* DAT3 */
BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x18,
BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */
BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 583ae3f38fc0..5419de8e20b1 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1250,10 +1250,12 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
debounce = readl(db_reg);
debounce &= ~BYT_DEBOUNCE_PULSE_MASK;

+ if (arg)
+ conf |= BYT_DEBOUNCE_EN;
+ else
+ conf &= ~BYT_DEBOUNCE_EN;
+
switch (arg) {
- case 0:
- conf &= BYT_DEBOUNCE_EN;
- break;
case 375:
debounce |= BYT_DEBOUNCE_PULSE_375US;
break;
@@ -1276,7 +1278,9 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
debounce |= BYT_DEBOUNCE_PULSE_24MS;
break;
default:
- ret = -EINVAL;
+ if (arg)
+ ret = -EINVAL;
+ break;
}

if (!ret)
diff --git a/drivers/staging/media/cec/cec-adap.c b/drivers/staging/media/cec/cec-adap.c
index 611e07b78bfe..057c9b5ab1e5 100644
--- a/drivers/staging/media/cec/cec-adap.c
+++ b/drivers/staging/media/cec/cec-adap.c
@@ -1017,7 +1017,7 @@ static int cec_config_thread_func(void *arg)
las->log_addr[i] = CEC_LOG_ADDR_INVALID;
if (last_la == CEC_LOG_ADDR_INVALID ||
last_la == CEC_LOG_ADDR_UNREGISTERED ||
- !(last_la & type2mask[type]))
+ !((1 << last_la) & type2mask[type]))
last_la = la_list[0];

err = cec_config_log_addr(adap, i, last_la);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 358feca54945..261ed2ca28f9 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1909,6 +1909,14 @@ static void musb_pm_runtime_check_session(struct musb *musb)
static void musb_irq_work(struct work_struct *data)
{
struct musb *musb = container_of(data, struct musb, irq_work.work);
+ int error;
+
+ error = pm_runtime_get_sync(musb->controller);
+ if (error < 0) {
+ dev_err(musb->controller, "Could not enable: %i\n", error);
+
+ return;
+ }

musb_pm_runtime_check_session(musb);

@@ -1916,6 +1924,9 @@ static void musb_irq_work(struct work_struct *data)
musb->xceiv_old_state = musb->xceiv->otg->state;
sysfs_notify(&musb->controller->kobj, NULL, "mode");
}
+
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
}

static void musb_recover_from_babble(struct musb *musb)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index c8823578a1b2..79ddcb05d126 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -1246,6 +1246,8 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container,
static long tce_iommu_take_ownership_ddw(struct tce_container *container,
struct iommu_table_group *table_group)
{
+ long i, ret = 0;
+
if (!table_group->ops->create_table || !table_group->ops->set_window ||
!table_group->ops->release_ownership) {
WARN_ON_ONCE(1);
@@ -1254,7 +1256,27 @@ static long tce_iommu_take_ownership_ddw(struct tce_container *container,

table_group->ops->take_ownership(table_group);

+ /* Set all windows to the new group */
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = container->tables[i];
+
+ if (!tbl)
+ continue;
+
+ ret = table_group->ops->set_window(table_group, i, tbl);
+ if (ret)
+ goto release_exit;
+ }
+
return 0;
+
+release_exit:
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
+ table_group->ops->unset_window(table_group, i);
+
+ table_group->ops->release_ownership(table_group);
+
+ return ret;
}

static int tce_iommu_attach_group(void *iommu_data,
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index a504e2e003da..e3fad302b4fb 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -368,6 +368,7 @@ static void vhost_vsock_handle_rx_kick(struct vhost_work *work)

static int vhost_vsock_start(struct vhost_vsock *vsock)
{
+ struct vhost_virtqueue *vq;
size_t i;
int ret;

@@ -378,19 +379,20 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
goto err;

for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
- struct vhost_virtqueue *vq = &vsock->vqs[i];
+ vq = &vsock->vqs[i];

mutex_lock(&vq->mutex);

if (!vhost_vq_access_ok(vq)) {
ret = -EFAULT;
- mutex_unlock(&vq->mutex);
goto err_vq;
}

if (!vq->private_data) {
vq->private_data = vsock;
- vhost_vq_init_access(vq);
+ ret = vhost_vq_init_access(vq);
+ if (ret)
+ goto err_vq;
}

mutex_unlock(&vq->mutex);
@@ -400,8 +402,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
return 0;

err_vq:
+ vq->private_data = NULL;
+ mutex_unlock(&vq->mutex);
+
for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
- struct vhost_virtqueue *vq = &vsock->vqs[i];
+ vq = &vsock->vqs[i];

mutex_lock(&vq->mutex);
vq->private_data = NULL;
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 4304072161aa..40d61077bead 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -542,6 +542,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
if (invalidate)
set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+ clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
}
} else {
@@ -560,6 +561,10 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t,
TASK_UNINTERRUPTIBLE);

+ /* Make sure any pending writes are cancelled. */
+ if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+ fscache_invalidate_writes(cookie);
+
/* Reset the cookie state if it wasn't relinquished */
if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
atomic_inc(&cookie->n_active);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index 9b28649df3a1..a8aa00be4444 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -48,6 +48,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
cookie->flags = 1 << FSCACHE_COOKIE_ENABLED;

spin_lock_init(&cookie->lock);
+ spin_lock_init(&cookie->stores_lock);
INIT_HLIST_HEAD(&cookie->backing_objects);

/* check the netfs type is not already present */
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 9e792e30f4db..7a182c87f378 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -30,6 +30,7 @@ static const struct fscache_state *fscache_look_up_object(struct fscache_object
static const struct fscache_state *fscache_object_available(struct fscache_object *, int);
static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int);
static const struct fscache_state *fscache_update_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_object_dead(struct fscache_object *, int);

#define __STATE_NAME(n) fscache_osm_##n
#define STATE(n) (&__STATE_NAME(n))
@@ -91,7 +92,7 @@ static WORK_STATE(LOOKUP_FAILURE, "LCFL", fscache_lookup_failure);
static WORK_STATE(KILL_OBJECT, "KILL", fscache_kill_object);
static WORK_STATE(KILL_DEPENDENTS, "KDEP", fscache_kill_dependents);
static WORK_STATE(DROP_OBJECT, "DROP", fscache_drop_object);
-static WORK_STATE(OBJECT_DEAD, "DEAD", (void*)2UL);
+static WORK_STATE(OBJECT_DEAD, "DEAD", fscache_object_dead);

static WAIT_STATE(WAIT_FOR_INIT, "?INI",
TRANSIT_TO(INIT_OBJECT, 1 << FSCACHE_OBJECT_EV_NEW_CHILD));
@@ -229,6 +230,10 @@ static void fscache_object_sm_dispatcher(struct fscache_object *object)
event = -1;
if (new_state == NO_TRANSIT) {
_debug("{OBJ%x} %s notrans", object->debug_id, state->name);
+ if (unlikely(state == STATE(OBJECT_DEAD))) {
+ _leave(" [dead]");
+ return;
+ }
fscache_enqueue_object(object);
event_mask = object->oob_event_mask;
goto unmask_events;
@@ -239,7 +244,7 @@ static void fscache_object_sm_dispatcher(struct fscache_object *object)
object->state = state = new_state;

if (state->work) {
- if (unlikely(state->work == ((void *)2UL))) {
+ if (unlikely(state == STATE(OBJECT_DEAD))) {
_leave(" [dead]");
return;
}
@@ -645,6 +650,12 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob
fscache_mark_object_dead(object);
object->oob_event_mask = 0;

+ if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) {
+ /* Reject any new read/write ops and abort any that are pending. */
+ clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+ fscache_cancel_all_ops(object);
+ }
+
if (list_empty(&object->dependents) &&
object->n_ops == 0 &&
object->n_children == 0)
@@ -1077,3 +1088,20 @@ void fscache_object_mark_killed(struct fscache_object *object,
}
}
EXPORT_SYMBOL(fscache_object_mark_killed);
+
+/*
+ * The object is dead. We can get here if an object gets queued by an event
+ * that would lead to its death (such as EV_KILL) when the dispatcher is
+ * already running (and so can be requeued) but hasn't yet cleared the event
+ * mask.
+ */
+static const struct fscache_state *fscache_object_dead(struct fscache_object *object,
+ int event)
+{
+ if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD,
+ &object->flags))
+ return NO_TRANSIT;
+
+ WARN(true, "FS-Cache object redispatched after death");
+ return NO_TRANSIT;
+}
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 133f322573b5..6528724ad6e5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1425,26 +1425,32 @@ static struct shrinker glock_shrinker = {
* @sdp: the filesystem
* @bucket: the bucket
*
+ * Note that the function can be called multiple times on the same
+ * object. So the user must ensure that the function can cope with
+ * that.
*/

static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
{
struct gfs2_glock *gl;
- struct rhash_head *pos;
- const struct bucket_table *tbl;
- int i;
+ struct rhashtable_iter iter;

- rcu_read_lock();
- tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table);
- for (i = 0; i < tbl->size; i++) {
- rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) {
+ rhashtable_walk_enter(&gl_hash_table, &iter);
+
+ do {
+ gl = ERR_PTR(rhashtable_walk_start(&iter));
+ if (gl)
+ continue;
+
+ while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl))
if ((gl->gl_name.ln_sbd == sdp) &&
lockref_get_not_dead(&gl->gl_lockref))
examiner(gl);
- }
- }
- rcu_read_unlock();
- cond_resched();
+
+ rhashtable_walk_stop(&iter);
+ } while (cond_resched(), gl == ERR_PTR(-EAGAIN));
+
+ rhashtable_walk_exit(&iter);
}

/**
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0959c9661662..92671914067f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1079,6 +1079,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
case -NFS4ERR_BADXDR:
case -NFS4ERR_RESOURCE:
case -NFS4ERR_NOFILEHANDLE:
+ case -NFS4ERR_MOVED:
/* Non-seqid mutating errors */
return;
};
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ca651ac00660..e67fec3c9856 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3181,6 +3181,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
iter.tgid += 1, iter = next_tgid(ns, iter)) {
char name[PROC_NUMBUF];
int len;
+
+ cond_resched();
if (!has_pid_permissions(ns, iter.task, 2))
continue;

diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index d0f8a38dfafa..0186fe6d39f3 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -74,6 +74,7 @@
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/uaccess.h>
+#include <linux/major.h>
#include "internal.h"

static struct kmem_cache *romfs_inode_cachep;
@@ -416,7 +417,22 @@ static void romfs_destroy_inode(struct inode *inode)
static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
- u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+ u64 id = 0;
+
+ /* When calling huge_encode_dev(),
+ * use sb->s_bdev->bd_dev when,
+ * - CONFIG_ROMFS_ON_BLOCK defined
+ * use sb->s_dev when,
+ * - CONFIG_ROMFS_ON_BLOCK undefined and
+ * - CONFIG_ROMFS_ON_MTD defined
+ * leave id as 0 when,
+ * - CONFIG_ROMFS_ON_BLOCK undefined and
+ * - CONFIG_ROMFS_ON_MTD undefined
+ */
+ if (sb->s_bdev)
+ id = huge_encode_dev(sb->s_bdev->bd_dev);
+ else if (sb->s_dev)
+ id = huge_encode_dev(sb->s_dev);

buf->f_type = ROMFS_MAGIC;
buf->f_namelen = ROMFS_MAXFN;
@@ -489,6 +505,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_flags |= MS_RDONLY | MS_NOATIME;
sb->s_op = &romfs_super_ops;

+#ifdef CONFIG_ROMFS_ON_MTD
+ /* Use same dev ID from the underlying mtdblock device */
+ if (sb->s_mtd)
+ sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
/* read the image superblock and check it */
rsb = kmalloc(512, GFP_KERNEL);
if (!rsb)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 85959d8324df..b86054cc41db 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -63,6 +63,7 @@ struct userfaultfd_wait_queue {
struct uffd_msg msg;
wait_queue_t wq;
struct userfaultfd_ctx *ctx;
+ bool waken;
};

struct userfaultfd_wake_range {
@@ -86,6 +87,12 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
if (len && (start > uwq->msg.arg.pagefault.address ||
start + len <= uwq->msg.arg.pagefault.address))
goto out;
+ WRITE_ONCE(uwq->waken, true);
+ /*
+ * The implicit smp_mb__before_spinlock in try_to_wake_up()
+ * renders uwq->waken visible to other CPUs before the task is
+ * waken.
+ */
ret = wake_up_state(wq->private, mode);
if (ret)
/*
@@ -264,6 +271,7 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
struct userfaultfd_wait_queue uwq;
int ret;
bool must_wait, return_to_userland;
+ long blocking_state;

BUG_ON(!rwsem_is_locked(&mm->mmap_sem));

@@ -333,10 +341,13 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
uwq.wq.private = current;
uwq.msg = userfault_msg(fe->address, fe->flags, reason);
uwq.ctx = ctx;
+ uwq.waken = false;

return_to_userland =
(fe->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
+ blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
+ TASK_KILLABLE;

spin_lock(&ctx->fault_pending_wqh.lock);
/*
@@ -349,8 +360,7 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
* following the spin_unlock to happen before the list_add in
* __add_wait_queue.
*/
- set_current_state(return_to_userland ? TASK_INTERRUPTIBLE :
- TASK_KILLABLE);
+ set_current_state(blocking_state);
spin_unlock(&ctx->fault_pending_wqh.lock);

must_wait = userfaultfd_must_wait(ctx, fe->address, fe->flags, reason);
@@ -362,6 +372,29 @@ int handle_userfault(struct fault_env *fe, unsigned long reason)
wake_up_poll(&ctx->fd_wqh, POLLIN);
schedule();
ret |= VM_FAULT_MAJOR;
+
+ /*
+ * False wakeups can orginate even from rwsem before
+ * up_read() however userfaults will wait either for a
+ * targeted wakeup on the specific uwq waitqueue from
+ * wake_userfault() or for signals or for uffd
+ * release.
+ */
+ while (!READ_ONCE(uwq.waken)) {
+ /*
+ * This needs the full smp_store_mb()
+ * guarantee as the state write must be
+ * visible to other CPUs before reading
+ * uwq.waken from other CPUs.
+ */
+ set_current_state(blocking_state);
+ if (READ_ONCE(uwq.waken) ||
+ READ_ONCE(ctx->released) ||
+ (return_to_userland ? signal_pending(current) :
+ fatal_signal_pending(current)))
+ break;
+ schedule();
+ }
}

__set_current_state(TASK_RUNNING);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index e9fb2e802feb..0c4f9c67c221 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -776,6 +776,7 @@ struct drm_device {
struct drm_minor *control; /**< Control node */
struct drm_minor *primary; /**< Primary node */
struct drm_minor *render; /**< Render node */
+ bool registered;

/* currently active master for this device. Protected by master_mutex */
struct drm_master *master;
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index ac9d7d8e0e43..d8bb8d151825 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -345,6 +345,8 @@ struct drm_connector_funcs {
* core drm connector interfaces. Everything added from this callback
* should be unregistered in the early_unregister callback.
*
+ * This is called while holding drm_connector->mutex.
+ *
* Returns:
*
* 0 on success, or a negative error code on failure.
@@ -359,6 +361,8 @@ struct drm_connector_funcs {
* late_register(). It is called from drm_connector_unregister(),
* early in the driver unload sequence to disable userspace access
* before data structures are torndown.
+ *
+ * This is called while holding drm_connector->mutex.
*/
void (*early_unregister)(struct drm_connector *connector);

@@ -511,7 +515,6 @@ struct drm_cmdline_mode {
* @interlace_allowed: can this connector handle interlaced modes?
* @doublescan_allowed: can this connector handle doublescan?
* @stereo_allowed: can this connector handle stereo modes?
- * @registered: is this connector exposed (registered) with userspace?
* @modes: modes available on this connector (from fill_modes() + user)
* @status: one of the drm_connector_status enums (connected, not, or unknown)
* @probed_modes: list of modes derived directly from the display
@@ -560,6 +563,13 @@ struct drm_connector {
char *name;

/**
+ * @mutex: Lock for general connector state, but currently only protects
+ * @registered. Most of the connector state is still protected by the
+ * mutex in &drm_mode_config.
+ */
+ struct mutex mutex;
+
+ /**
* @index: Compacted connector index, which matches the position inside
* the mode_config.list for drivers not supporting hot-add/removing. Can
* be used as an array index. It is invariant over the lifetime of the
@@ -572,6 +582,10 @@ struct drm_connector {
bool interlace_allowed;
bool doublescan_allowed;
bool stereo_allowed;
+ /**
+ * @registered: Is this connector exposed (registered) with userspace?
+ * Protected by @mutex.
+ */
bool registered;
struct list_head modes; /* list of modes on this connector */

diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 13ba552e6c09..4c467ef50159 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -360,6 +360,7 @@ struct fscache_object {
#define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */
#define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */
#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */
+#define FSCACHE_OBJECT_RUN_AFTER_DEAD 8 /* T if object has been dispatched after death */

struct list_head cache_link; /* link in cache->object_list */
struct hlist_node cookie_link; /* link in cookie->backing_objects */
diff --git a/include/linux/log2.h b/include/linux/log2.h
index f38fae23bdac..c373295f359f 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -194,6 +194,17 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
* ... and so on.
*/

-#define order_base_2(n) ilog2(roundup_pow_of_two(n))
+static inline __attribute_const__
+int __order_base_2(unsigned long n)
+{
+ return n > 1 ? ilog2(n - 1) + 1 : 0;
+}

+#define order_base_2(n) \
+( \
+ __builtin_constant_p(n) ? ( \
+ ((n) == 0 || (n) == 1) ? 0 : \
+ ilog2((n) - 1) + 1) : \
+ __order_base_2(n) \
+)
#endif /* _LINUX_LOG2_H */
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 257173e0095e..f541da68d1e7 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -35,6 +35,8 @@
#define PHY_ID_KSZ886X 0x00221430
#define PHY_ID_KSZ8863 0x00221435

+#define PHY_ID_KSZ8795 0x00221550
+
/* struct phy_device dev_flags definitions */
#define MICREL_PHY_50MHZ_CLK 0x00000001
#define MICREL_PHY_FXEN 0x00000002
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bb9b102c15cd..780e7171f548 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -865,11 +865,15 @@ struct netdev_xdp {
* of useless work if you return NETDEV_TX_BUSY.
* Required; cannot be NULL.
*
- * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
- * netdev_features_t features);
- * Adjusts the requested feature flags according to device-specific
- * constraints, and returns the resulting flags. Must not modify
- * the device state.
+ * netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
+ * struct net_device *dev
+ * netdev_features_t features);
+ * Called by core transmit path to determine if device is capable of
+ * performing offload operations on a given packet. This is to give
+ * the device an opportunity to implement any restrictions that cannot
+ * be otherwise expressed by feature flags. The check is called with
+ * the set of features that the stack has calculated and it returns
+ * those the driver believes to be appropriate.
*
* u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
* void *accel_priv, select_queue_fallback_t fallback);
@@ -1027,6 +1031,12 @@ struct netdev_xdp {
* Called to release previously enslaved netdev.
*
* Feature/offload setting functions.
+ * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
+ * netdev_features_t features);
+ * Adjusts the requested feature flags according to device-specific
+ * constraints, and returns the resulting flags. Must not modify
+ * the device state.
+ *
* int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
* Called to update device configuration to new features. Passed
* feature set might be less than what was returned by ndo_fix_features()).
@@ -1099,15 +1109,6 @@ struct netdev_xdp {
* Callback to use for xmit over the accelerated station. This
* is used in place of ndo_start_xmit on accelerated net
* devices.
- * netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
- * struct net_device *dev
- * netdev_features_t features);
- * Called by core transmit path to determine if device is capable of
- * performing offload operations on a given packet. This is to give
- * the device an opportunity to implement any restrictions that cannot
- * be otherwise expressed by feature flags. The check is called with
- * the set of features that the stack has calculated and it returns
- * those the driver believes to be appropriate.
* int (*ndo_set_tx_maxrate)(struct net_device *dev,
* int queue_index, u32 maxrate);
* Called when a user wants to set a max-rate limitation of specific
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index a78c35cff1ae..0a3fadc32693 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -7,6 +7,23 @@
#include <linux/sched.h>
#include <asm/irq.h>

+/*
+ * The run state of the lockup detectors is controlled by the content of the
+ * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
+ * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
+ *
+ * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled'
+ * are variables that are only used as an 'interface' between the parameters
+ * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The
+ * 'watchdog_thresh' variable is handled differently because its value is not
+ * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh'
+ * is equal zero.
+ */
+#define NMI_WATCHDOG_ENABLED_BIT 0
+#define SOFT_WATCHDOG_ENABLED_BIT 1
+#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT)
+#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT)
+
/**
* touch_nmi_watchdog - restart NMI watchdog timeout.
*
@@ -91,9 +108,17 @@ extern int nmi_watchdog_enabled;
extern int soft_watchdog_enabled;
extern int watchdog_user_enabled;
extern int watchdog_thresh;
+extern unsigned long watchdog_enabled;
extern unsigned long *watchdog_cpumask_bits;
+extern atomic_t watchdog_park_in_progress;
+#ifdef CONFIG_SMP
extern int sysctl_softlockup_all_cpu_backtrace;
extern int sysctl_hardlockup_all_cpu_backtrace;
+#else
+#define sysctl_softlockup_all_cpu_backtrace 0
+#define sysctl_hardlockup_all_cpu_backtrace 0
+#endif
+extern bool is_hardlockup(void);
struct ctl_table;
extern int proc_watchdog(struct ctl_table *, int ,
void __user *, size_t *, loff_t *);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index a38772a85588..1b711796d989 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -178,6 +178,11 @@ enum pci_dev_flags {
PCI_DEV_FLAGS_NO_PM_RESET = (__force pci_dev_flags_t) (1 << 7),
/* Get VPD from function 0 VPD */
PCI_DEV_FLAGS_VPD_REF_F0 = (__force pci_dev_flags_t) (1 << 8),
+ /*
+ * Resume before calling the driver's system suspend hooks, disabling
+ * the direct_complete optimization.
+ */
+ PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11),
};

enum pci_irq_reroute_variant {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 91afb4aadaa6..615ce0abba9c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -776,6 +776,11 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
{
u32 hash;

+ /* @flowlabel may include more than a flow label, eg, the traffic class.
+ * Here we want only the flow label value.
+ */
+ flowlabel &= IPV6_FLOWLABEL_MASK;
+
if (flowlabel ||
net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF ||
(!autolabel &&
diff --git a/include/uapi/linux/netfilter/nf_log.h b/include/uapi/linux/netfilter/nf_log.h
index 8be21e02387d..d0b5fa91ff54 100644
--- a/include/uapi/linux/netfilter/nf_log.h
+++ b/include/uapi/linux/netfilter/nf_log.h
@@ -9,4 +9,6 @@
#define NF_LOG_MACDECODE 0x20 /* Decode MAC header */
#define NF_LOG_MASK 0x2f

+#define NF_LOG_PREFIXLEN 128
+
#endif /* _NETFILTER_NF_LOG_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index eb26e12c6c2a..314e7d62f5f0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -84,6 +84,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += debug/
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RELAY) += relay.o
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
diff --git a/kernel/ucount.c b/kernel/ucount.c
index f4ac18509ecf..c761cdba2a2d 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -231,11 +231,10 @@ static __init int user_namespace_sysctl_init(void)
* properly.
*/
user_header = register_sysctl("user", empty);
+ kmemleak_ignore(user_header);
BUG_ON(!user_header);
BUG_ON(!setup_userns_sysctls(&init_user_ns));
#endif
return 0;
}
subsys_initcall(user_namespace_sysctl_init);
-
-
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6d1020c03d41..63177be0159e 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -24,32 +24,14 @@

#include <asm/irq_regs.h>
#include <linux/kvm_para.h>
-#include <linux/perf_event.h>
#include <linux/kthread.h>

-/*
- * The run state of the lockup detectors is controlled by the content of the
- * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
- * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
- *
- * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled'
- * are variables that are only used as an 'interface' between the parameters
- * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The
- * 'watchdog_thresh' variable is handled differently because its value is not
- * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh'
- * is equal zero.
- */
-#define NMI_WATCHDOG_ENABLED_BIT 0
-#define SOFT_WATCHDOG_ENABLED_BIT 1
-#define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT)
-#define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT)
-
static DEFINE_MUTEX(watchdog_proc_mutex);

-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED;
#else
-static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
+unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
#endif
int __read_mostly nmi_watchdog_enabled;
int __read_mostly soft_watchdog_enabled;
@@ -59,9 +41,6 @@ int __read_mostly watchdog_thresh = 10;
#ifdef CONFIG_SMP
int __read_mostly sysctl_softlockup_all_cpu_backtrace;
int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
-#else
-#define sysctl_softlockup_all_cpu_backtrace 0
-#define sysctl_hardlockup_all_cpu_backtrace 0
#endif
static struct cpumask watchdog_cpumask __read_mostly;
unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
@@ -70,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
#define for_each_watchdog_cpu(cpu) \
for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)

+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
+
/*
* The 'watchdog_running' variable is set to 1 when the watchdog threads
* are registered/started and is set to 0 when the watchdog threads are
@@ -100,50 +81,9 @@ static DEFINE_PER_CPU(bool, soft_watchdog_warn);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-static DEFINE_PER_CPU(bool, hard_watchdog_warn);
-static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
-static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
-#endif
static unsigned long soft_lockup_nmi_warn;

-/* boot commands */
-/*
- * Should we panic when a soft-lockup or hard-lockup occurs:
- */
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-unsigned int __read_mostly hardlockup_panic =
- CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
-static unsigned long hardlockup_allcpu_dumped;
-/*
- * We may not want to enable hard lockup detection by default in all cases,
- * for example when running the kernel as a guest on a hypervisor. In these
- * cases this function can be called to disable hard lockup detection. This
- * function should only be executed once by the boot processor before the
- * kernel command line parameters are parsed, because otherwise it is not
- * possible to override this in hardlockup_panic_setup().
- */
-void hardlockup_detector_disable(void)
-{
- watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
-}
-
-static int __init hardlockup_panic_setup(char *str)
-{
- if (!strncmp(str, "panic", 5))
- hardlockup_panic = 1;
- else if (!strncmp(str, "nopanic", 7))
- hardlockup_panic = 0;
- else if (!strncmp(str, "0", 1))
- watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
- else if (!strncmp(str, "1", 1))
- watchdog_enabled |= NMI_WATCHDOG_ENABLED;
- return 1;
-}
-__setup("nmi_watchdog=", hardlockup_panic_setup);
-#endif
-
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;

@@ -264,32 +204,14 @@ void touch_all_softlockup_watchdogs(void)
wq_watchdog_touch(-1);
}

-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-void touch_nmi_watchdog(void)
-{
- /*
- * Using __raw here because some code paths have
- * preemption enabled. If preemption is enabled
- * then interrupts should be enabled too, in which
- * case we shouldn't have to worry about the watchdog
- * going off.
- */
- raw_cpu_write(watchdog_nmi_touch, true);
- touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL(touch_nmi_watchdog);
-
-#endif
-
void touch_softlockup_watchdog_sync(void)
{
__this_cpu_write(softlockup_touch_sync, true);
__this_cpu_write(watchdog_touch_ts, 0);
}

-#ifdef CONFIG_HARDLOCKUP_DETECTOR
/* watchdog detector functions */
-static bool is_hardlockup(void)
+bool is_hardlockup(void)
{
unsigned long hrint = __this_cpu_read(hrtimer_interrupts);

@@ -299,7 +221,6 @@ static bool is_hardlockup(void)
__this_cpu_write(hrtimer_interrupts_saved, hrint);
return false;
}
-#endif

static int is_softlockup(unsigned long touch_ts)
{
@@ -313,77 +234,22 @@ static int is_softlockup(unsigned long touch_ts)
return 0;
}

-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-
-static struct perf_event_attr wd_hw_attr = {
- .type = PERF_TYPE_HARDWARE,
- .config = PERF_COUNT_HW_CPU_CYCLES,
- .size = sizeof(struct perf_event_attr),
- .pinned = 1,
- .disabled = 1,
-};
-
-/* Callback function for perf event subsystem */
-static void watchdog_overflow_callback(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs)
-{
- /* Ensure the watchdog never gets throttled */
- event->hw.interrupts = 0;
-
- if (__this_cpu_read(watchdog_nmi_touch) == true) {
- __this_cpu_write(watchdog_nmi_touch, false);
- return;
- }
-
- /* check for a hardlockup
- * This is done by making sure our timer interrupt
- * is incrementing. The timer interrupt should have
- * fired multiple times before we overflow'd. If it hasn't
- * then this is a good indication the cpu is stuck
- */
- if (is_hardlockup()) {
- int this_cpu = smp_processor_id();
-
- /* only print hardlockups once */
- if (__this_cpu_read(hard_watchdog_warn) == true)
- return;
-
- pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
- print_modules();
- print_irqtrace_events(current);
- if (regs)
- show_regs(regs);
- else
- dump_stack();
-
- /*
- * Perform all-CPU dump only once to avoid multiple hardlockups
- * generating interleaving traces
- */
- if (sysctl_hardlockup_all_cpu_backtrace &&
- !test_and_set_bit(0, &hardlockup_allcpu_dumped))
- trigger_allbutself_cpu_backtrace();
-
- if (hardlockup_panic)
- nmi_panic(regs, "Hard LOCKUP");
-
- __this_cpu_write(hard_watchdog_warn, true);
- return;
- }
-
- __this_cpu_write(hard_watchdog_warn, false);
- return;
-}
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
-
static void watchdog_interrupt_count(void)
{
__this_cpu_inc(hrtimer_interrupts);
}

-static int watchdog_nmi_enable(unsigned int cpu);
-static void watchdog_nmi_disable(unsigned int cpu);
+/*
+ * These two functions are mostly architecture specific
+ * defining them as weak here.
+ */
+int __weak watchdog_nmi_enable(unsigned int cpu)
+{
+ return 0;
+}
+void __weak watchdog_nmi_disable(unsigned int cpu)
+{
+}

static int watchdog_enable_all_cpus(void);
static void watchdog_disable_all_cpus(void);
@@ -396,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
int duration;
int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;

+ if (atomic_read(&watchdog_park_in_progress) != 0)
+ return HRTIMER_NORESTART;
+
/* kick the hardlockup detector */
watchdog_interrupt_count();

@@ -576,109 +445,6 @@ static void watchdog(unsigned int cpu)
watchdog_nmi_disable(cpu);
}

-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-/*
- * People like the simple clean cpu node info on boot.
- * Reduce the watchdog noise by only printing messages
- * that are different from what cpu0 displayed.
- */
-static unsigned long cpu0_err;
-
-static int watchdog_nmi_enable(unsigned int cpu)
-{
- struct perf_event_attr *wd_attr;
- struct perf_event *event = per_cpu(watchdog_ev, cpu);
-
- /* nothing to do if the hard lockup detector is disabled */
- if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
- goto out;
-
- /* is it already setup and enabled? */
- if (event && event->state > PERF_EVENT_STATE_OFF)
- goto out;
-
- /* it is setup but not enabled */
- if (event != NULL)
- goto out_enable;
-
- wd_attr = &wd_hw_attr;
- wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
-
- /* Try to register using hardware perf events */
- event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
-
- /* save cpu0 error for future comparision */
- if (cpu == 0 && IS_ERR(event))
- cpu0_err = PTR_ERR(event);
-
- if (!IS_ERR(event)) {
- /* only print for cpu0 or different than cpu0 */
- if (cpu == 0 || cpu0_err)
- pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
- goto out_save;
- }
-
- /*
- * Disable the hard lockup detector if _any_ CPU fails to set up
- * set up the hardware perf event. The watchdog() function checks
- * the NMI_WATCHDOG_ENABLED bit periodically.
- *
- * The barriers are for syncing up watchdog_enabled across all the
- * cpus, as clear_bit() does not use barriers.
- */
- smp_mb__before_atomic();
- clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled);
- smp_mb__after_atomic();
-
- /* skip displaying the same error again */
- if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
- return PTR_ERR(event);
-
- /* vary the KERN level based on the returned errno */
- if (PTR_ERR(event) == -EOPNOTSUPP)
- pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
- else if (PTR_ERR(event) == -ENOENT)
- pr_warn("disabled (cpu%i): hardware events not enabled\n",
- cpu);
- else
- pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
- cpu, PTR_ERR(event));
-
- pr_info("Shutting down hard lockup detector on all cpus\n");
-
- return PTR_ERR(event);
-
- /* success path */
-out_save:
- per_cpu(watchdog_ev, cpu) = event;
-out_enable:
- perf_event_enable(per_cpu(watchdog_ev, cpu));
-out:
- return 0;
-}
-
-static void watchdog_nmi_disable(unsigned int cpu)
-{
- struct perf_event *event = per_cpu(watchdog_ev, cpu);
-
- if (event) {
- perf_event_disable(event);
- per_cpu(watchdog_ev, cpu) = NULL;
-
- /* should be in cleanup, but blocks oprofile */
- perf_event_release_kernel(event);
- }
- if (cpu == 0) {
- /* watchdog_nmi_enable() expects this to be zero initially. */
- cpu0_err = 0;
- }
-}
-
-#else
-static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
-static void watchdog_nmi_disable(unsigned int cpu) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
-
static struct smp_hotplug_thread watchdog_threads = {
.store = &softlockup_watchdog,
.thread_should_run = watchdog_should_run,
@@ -706,12 +472,16 @@ static int watchdog_park_threads(void)
{
int cpu, ret = 0;

+ atomic_set(&watchdog_park_in_progress, 1);
+
for_each_watchdog_cpu(cpu) {
ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
if (ret)
break;
}

+ atomic_set(&watchdog_park_in_progress, 0);
+
return ret;
}

diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
new file mode 100644
index 000000000000..12b8dd640786
--- /dev/null
+++ b/kernel/watchdog_hld.c
@@ -0,0 +1,230 @@
+/*
+ * Detect hard lockups on a system
+ *
+ * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ * Note: Most of this code is borrowed heavily from the original softlockup
+ * detector, so thanks to Ingo for the initial implementation.
+ * Some chunks also taken from the old x86-specific nmi watchdog code, thanks
+ * to those contributors as well.
+ */
+
+#define pr_fmt(fmt) "NMI watchdog: " fmt
+
+#include <linux/nmi.h>
+#include <linux/module.h>
+#include <asm/irq_regs.h>
+#include <linux/perf_event.h>
+
+static DEFINE_PER_CPU(bool, hard_watchdog_warn);
+static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
+static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+
+/* boot commands */
+/*
+ * Should we panic when a soft-lockup or hard-lockup occurs:
+ */
+unsigned int __read_mostly hardlockup_panic =
+ CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
+static unsigned long hardlockup_allcpu_dumped;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void hardlockup_detector_disable(void)
+{
+ watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+}
+
+static int __init hardlockup_panic_setup(char *str)
+{
+ if (!strncmp(str, "panic", 5))
+ hardlockup_panic = 1;
+ else if (!strncmp(str, "nopanic", 7))
+ hardlockup_panic = 0;
+ else if (!strncmp(str, "0", 1))
+ watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+ else if (!strncmp(str, "1", 1))
+ watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+ return 1;
+}
+__setup("nmi_watchdog=", hardlockup_panic_setup);
+
+void touch_nmi_watchdog(void)
+{
+ /*
+ * Using __raw here because some code paths have
+ * preemption enabled. If preemption is enabled
+ * then interrupts should be enabled too, in which
+ * case we shouldn't have to worry about the watchdog
+ * going off.
+ */
+ raw_cpu_write(watchdog_nmi_touch, true);
+ touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+static struct perf_event_attr wd_hw_attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .size = sizeof(struct perf_event_attr),
+ .pinned = 1,
+ .disabled = 1,
+};
+
+/* Callback function for perf event subsystem */
+static void watchdog_overflow_callback(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ /* Ensure the watchdog never gets throttled */
+ event->hw.interrupts = 0;
+
+ if (atomic_read(&watchdog_park_in_progress) != 0)
+ return;
+
+ if (__this_cpu_read(watchdog_nmi_touch) == true) {
+ __this_cpu_write(watchdog_nmi_touch, false);
+ return;
+ }
+
+ /* check for a hardlockup
+ * This is done by making sure our timer interrupt
+ * is incrementing. The timer interrupt should have
+ * fired multiple times before we overflow'd. If it hasn't
+ * then this is a good indication the cpu is stuck
+ */
+ if (is_hardlockup()) {
+ int this_cpu = smp_processor_id();
+
+ /* only print hardlockups once */
+ if (__this_cpu_read(hard_watchdog_warn) == true)
+ return;
+
+ pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+ print_modules();
+ print_irqtrace_events(current);
+ if (regs)
+ show_regs(regs);
+ else
+ dump_stack();
+
+ /*
+ * Perform all-CPU dump only once to avoid multiple hardlockups
+ * generating interleaving traces
+ */
+ if (sysctl_hardlockup_all_cpu_backtrace &&
+ !test_and_set_bit(0, &hardlockup_allcpu_dumped))
+ trigger_allbutself_cpu_backtrace();
+
+ if (hardlockup_panic)
+ nmi_panic(regs, "Hard LOCKUP");
+
+ __this_cpu_write(hard_watchdog_warn, true);
+ return;
+ }
+
+ __this_cpu_write(hard_watchdog_warn, false);
+ return;
+}
+
+/*
+ * People like the simple clean cpu node info on boot.
+ * Reduce the watchdog noise by only printing messages
+ * that are different from what cpu0 displayed.
+ */
+static unsigned long cpu0_err;
+
+int watchdog_nmi_enable(unsigned int cpu)
+{
+ struct perf_event_attr *wd_attr;
+ struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+ /* nothing to do if the hard lockup detector is disabled */
+ if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+ goto out;
+
+ /* is it already setup and enabled? */
+ if (event && event->state > PERF_EVENT_STATE_OFF)
+ goto out;
+
+ /* it is setup but not enabled */
+ if (event != NULL)
+ goto out_enable;
+
+ wd_attr = &wd_hw_attr;
+ wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
+
+ /* Try to register using hardware perf events */
+ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+
+ /* save cpu0 error for future comparision */
+ if (cpu == 0 && IS_ERR(event))
+ cpu0_err = PTR_ERR(event);
+
+ if (!IS_ERR(event)) {
+ /* only print for cpu0 or different than cpu0 */
+ if (cpu == 0 || cpu0_err)
+ pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
+ goto out_save;
+ }
+
+ /*
+ * Disable the hard lockup detector if _any_ CPU fails to set up
+ * set up the hardware perf event. The watchdog() function checks
+ * the NMI_WATCHDOG_ENABLED bit periodically.
+ *
+ * The barriers are for syncing up watchdog_enabled across all the
+ * cpus, as clear_bit() does not use barriers.
+ */
+ smp_mb__before_atomic();
+ clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled);
+ smp_mb__after_atomic();
+
+ /* skip displaying the same error again */
+ if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
+ return PTR_ERR(event);
+
+ /* vary the KERN level based on the returned errno */
+ if (PTR_ERR(event) == -EOPNOTSUPP)
+ pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
+ else if (PTR_ERR(event) == -ENOENT)
+ pr_warn("disabled (cpu%i): hardware events not enabled\n",
+ cpu);
+ else
+ pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
+ cpu, PTR_ERR(event));
+
+ pr_info("Shutting down hard lockup detector on all cpus\n");
+
+ return PTR_ERR(event);
+
+ /* success path */
+out_save:
+ per_cpu(watchdog_ev, cpu) = event;
+out_enable:
+ perf_event_enable(per_cpu(watchdog_ev, cpu));
+out:
+ return 0;
+}
+
+void watchdog_nmi_disable(unsigned int cpu)
+{
+ struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+ if (event) {
+ perf_event_disable(event);
+ per_cpu(watchdog_ev, cpu) = NULL;
+
+ /* should be in cleanup, but blocks oprofile */
+ perf_event_release_kernel(event);
+ }
+ if (cpu == 0) {
+ /* watchdog_nmi_enable() expects this to be zero initially. */
+ cpu0_err = 0;
+ }
+}
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 073325aedc68..8ca412aebcf1 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,6 +13,7 @@
*
*/

+#include <linux/ftrace.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/printk.h>
@@ -298,6 +299,8 @@ void kasan_report(unsigned long addr, size_t size,
if (likely(!kasan_report_enabled()))
return;

+ disable_trace_on_warning();
+
info.access_addr = (void *)addr;
info.access_size = size;
info.is_write = is_write;
diff --git a/mm/shmem.c b/mm/shmem.c
index 9d32e1cb9f38..d99cfb6eb03a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -412,6 +412,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shrink_control *sc, unsigned long nr_to_split)
{
LIST_HEAD(list), *pos, *next;
+ LIST_HEAD(to_remove);
struct inode *inode;
struct shmem_inode_info *info;
struct page *page;
@@ -438,9 +439,8 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
/* Check if there's anything to gain */
if (round_up(inode->i_size, PAGE_SIZE) ==
round_up(inode->i_size, HPAGE_PMD_SIZE)) {
- list_del_init(&info->shrinklist);
+ list_move(&info->shrinklist, &to_remove);
removed++;
- iput(inode);
goto next;
}

@@ -451,6 +451,13 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
}
spin_unlock(&sbinfo->shrinklist_lock);

+ list_for_each_safe(pos, next, &to_remove) {
+ info = list_entry(pos, struct shmem_inode_info, shrinklist);
+ inode = &info->vfs_inode;
+ list_del_init(&info->shrinklist);
+ iput(inode);
+ }
+
list_for_each_safe(pos, next, &list) {
int ret;

diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 047a1752ece1..072c1f4998c9 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1394,9 +1394,12 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
if (regs.len > reglen)
regs.len = reglen;

- regbuf = vzalloc(reglen);
- if (reglen && !regbuf)
- return -ENOMEM;
+ regbuf = NULL;
+ if (reglen) {
+ regbuf = vzalloc(reglen);
+ if (!regbuf)
+ return -ENOMEM;
+ }

ops->get_regs(dev, &regs, regbuf);

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 89a8cac4726a..51b27ae09fbd 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1263,7 +1263,7 @@ void __init arp_init(void)
/*
* ax25 -> ASCII conversion
*/
-static char *ax2asc2(ax25_address *a, char *buf)
+static void ax2asc2(ax25_address *a, char *buf)
{
char c, *s;
int n;
@@ -1285,10 +1285,10 @@ static char *ax2asc2(ax25_address *a, char *buf)
*s++ = n + '0';
*s++ = '\0';

- if (*buf == '\0' || *buf == '-')
- return "*";
-
- return buf;
+ if (*buf == '\0' || *buf == '-') {
+ buf[0] = '*';
+ buf[1] = '\0';
+ }
}
#endif /* CONFIG_AX25 */

@@ -1322,7 +1322,7 @@ static void arp_format_neigh_entry(struct seq_file *seq,
}
#endif
sprintf(tbuf, "%pI4", n->primary_key);
- seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n",
+ seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n",
tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name);
read_unlock(&n->lock);
}
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index f6c50af24a64..3d063eb37848 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -117,7 +117,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
(fwmark > 0 && skb->mark == fwmark)) &&
(full || tp->snd_cwnd != tcp_probe.lastcwnd)) {

- spin_lock(&tcp_probe.lock);
+ spin_lock_bh(&tcp_probe.lock);
/* If log fills, just silently drop */
if (tcp_probe_avail() > 1) {
struct tcp_log *p = tcp_probe.log + tcp_probe.head;
@@ -157,7 +157,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
}
tcp_probe.lastcwnd = tp->snd_cwnd;
- spin_unlock(&tcp_probe.lock);
+ spin_unlock_bh(&tcp_probe.lock);

wake_up(&tcp_probe.wait);
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f088a1d9a618..045738319e8b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3387,9 +3387,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
}

if (idev) {
- if (idev->if_flags & IF_READY)
- /* device is already configured. */
+ if (idev->if_flags & IF_READY) {
+ /* device is already configured -
+ * but resend MLD reports, we might
+ * have roamed and need to update
+ * multicast snooping switches
+ */
+ ipv6_mc_up(idev);
break;
+ }
idev->if_flags |= IF_READY;
}

@@ -4004,6 +4010,12 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)

if (bump_id)
rt_genid_bump_ipv6(dev_net(dev));
+
+ /* Make sure that a new temporary address will be created
+ * before this temporary address becomes deprecated.
+ */
+ if (ifp->flags & IFA_F_TEMPORARY)
+ addrconf_verify_rtnl();
}

static void addrconf_dad_run(struct inet6_dev *idev)
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 442ec1f39ed1..38062f403ceb 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -166,18 +166,22 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
if (np->sndflow)
fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;

- addr_type = ipv6_addr_type(&usin->sin6_addr);
-
- if (addr_type == IPV6_ADDR_ANY) {
+ if (ipv6_addr_any(&usin->sin6_addr)) {
/*
* connect to self
*/
- usin->sin6_addr.s6_addr[15] = 0x01;
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+ &usin->sin6_addr);
+ else
+ usin->sin6_addr = in6addr_loopback;
}

+ addr_type = ipv6_addr_type(&usin->sin6_addr);
+
daddr = &usin->sin6_addr;

- if (addr_type == IPV6_ADDR_MAPPED) {
+ if (addr_type & IPV6_ADDR_MAPPED) {
struct sockaddr_in sin;

if (__ipv6_only_sock(sk)) {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1ac3cea49171..3ab32ac57ccd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1019,6 +1019,9 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
}
}
#endif
+ if (ipv6_addr_v4mapped(&fl6->saddr) &&
+ !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr)))
+ return -EAFNOSUPPORT;

return 0;

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index aef9b28067f4..7ac2365aa6fb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -148,8 +148,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
* connect() to INADDR_ANY means loopback (BSD'ism).
*/

- if (ipv6_addr_any(&usin->sin6_addr))
- usin->sin6_addr.s6_addr[15] = 0x1;
+ if (ipv6_addr_any(&usin->sin6_addr)) {
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+ &usin->sin6_addr);
+ else
+ usin->sin6_addr = in6addr_loopback;
+ }

addr_type = ipv6_addr_type(&usin->sin6_addr);

@@ -188,7 +193,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
* TCP over IPv4
*/

- if (addr_type == IPV6_ADDR_MAPPED) {
+ if (addr_type & IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 40a289f78d77..2497f62fa4c2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1049,6 +1049,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
daddr = &sin6->sin6_addr;
+ if (ipv6_addr_any(daddr) &&
+ ipv6_addr_v4mapped(&np->saddr))
+ ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+ daddr);
break;
case AF_INET:
goto do_udp_sendmsg;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index c3fc14e021ec..3a8dc39a9116 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1630,8 +1630,6 @@ static int __init nf_conntrack_sip_init(void)
ports[ports_c++] = SIP_PORT;

for (i = 0; i < ports_c; i++) {
- memset(&sip[i], 0, sizeof(sip[i]));
-
nf_ct_helper_init(&sip[4 * i], AF_INET, IPPROTO_UDP, "sip",
SIP_PORT, ports[i], i, sip_exp_policy,
SIP_EXPECT_MAX,
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 3dca90dc24ad..ffb9e8ada899 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -13,7 +13,6 @@
/* Internal logging interface, which relies on the real
LOG target modules */

-#define NF_LOG_PREFIXLEN 128
#define NFLOGGER_NAME_LEN 64

static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e5194f6f906c..778fcdb83225 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3637,10 +3637,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
goto err5;
}

+ if (set->size &&
+ !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) {
+ err = -ENFILE;
+ goto err6;
+ }
+
nft_trans_elem(trans) = elem;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;

+err6:
+ set->ops->remove(set, &elem);
err5:
kfree(trans);
err4:
@@ -3687,15 +3695,9 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
return -EBUSY;

nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
- if (set->size &&
- !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact))
- return -ENFILE;
-
err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags);
- if (err < 0) {
- atomic_dec(&set->nelems);
+ if (err < 0)
break;
- }
}
return err;
}
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 1b01404bb33f..c7704e9123ef 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -38,7 +38,8 @@ static void nft_log_eval(const struct nft_expr *expr,

static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = {
[NFTA_LOG_GROUP] = { .type = NLA_U16 },
- [NFTA_LOG_PREFIX] = { .type = NLA_STRING },
+ [NFTA_LOG_PREFIX] = { .type = NLA_STRING,
+ .len = NF_LOG_PREFIXLEN - 1 },
[NFTA_LOG_SNAPLEN] = { .type = NLA_U32 },
[NFTA_LOG_QTHRESHOLD] = { .type = NLA_U16 },
[NFTA_LOG_LEVEL] = { .type = NLA_U32 },
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 7e869d0cca69..4f5a2b580aa5 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -68,7 +68,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb,
goto out;
}

- segs = skb_segment(skb, features | NETIF_F_HW_CSUM);
+ segs = skb_segment(skb, features | NETIF_F_HW_CSUM | NETIF_F_SG);
if (IS_ERR(segs))
goto out;

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 14346dccc4fe..e1719c695174 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -235,8 +235,12 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk,
sctp_assoc_t id)
{
struct sctp_association *addr_asoc = NULL, *id_asoc = NULL;
- struct sctp_transport *transport;
+ struct sctp_af *af = sctp_get_af_specific(addr->ss_family);
union sctp_addr *laddr = (union sctp_addr *)addr;
+ struct sctp_transport *transport;
+
+ if (sctp_verify_addr(sk, laddr, af->sockaddr_len))
+ return NULL;

addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep,
laddr,
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 28bf4feeb81c..ab8a2d5d1e32 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -110,6 +110,10 @@ int tipc_net_start(struct net *net, u32 addr)
char addr_string[16];

tn->own_addr = addr;
+
+ /* Ensure that the new address is visible before we reinit. */
+ smp_mb();
+
tipc_named_reinit(net);
tipc_sk_reinit(net);

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 9d2f4c2b08ab..27753325e06e 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -263,6 +263,11 @@ static void tipc_node_write_lock(struct tipc_node *n)
write_lock_bh(&n->lock);
}

+static void tipc_node_write_unlock_fast(struct tipc_node *n)
+{
+ write_unlock_bh(&n->lock);
+}
+
static void tipc_node_write_unlock(struct tipc_node *n)
{
struct net *net = n->net;
@@ -417,7 +422,7 @@ void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr)
}
tipc_node_write_lock(n);
list_add_tail(subscr, &n->publ_list);
- tipc_node_write_unlock(n);
+ tipc_node_write_unlock_fast(n);
tipc_node_put(n);
}

@@ -435,7 +440,7 @@ void tipc_node_unsubscribe(struct net *net, struct list_head *subscr, u32 addr)
}
tipc_node_write_lock(n);
list_del_init(subscr);
- tipc_node_write_unlock(n);
+ tipc_node_write_unlock_fast(n);
tipc_node_put(n);
}

diff --git a/net/tipc/server.c b/net/tipc/server.c
index 215849ce453d..f89c0c2e8c16 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -91,7 +91,8 @@ static void tipc_sock_release(struct tipc_conn *con);
static void tipc_conn_kref_release(struct kref *kref)
{
struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
- struct sockaddr_tipc *saddr = con->server->saddr;
+ struct tipc_server *s = con->server;
+ struct sockaddr_tipc *saddr = s->saddr;
struct socket *sock = con->sock;
struct sock *sk;

@@ -106,6 +107,11 @@ static void tipc_conn_kref_release(struct kref *kref)
tipc_sock_release(con);
sock_release(sock);
con->sock = NULL;
+
+ spin_lock_bh(&s->idr_lock);
+ idr_remove(&s->conn_idr, con->conid);
+ s->idr_in_use--;
+ spin_unlock_bh(&s->idr_lock);
}

tipc_clean_outqueues(con);
@@ -128,8 +134,10 @@ static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid)

spin_lock_bh(&s->idr_lock);
con = idr_find(&s->conn_idr, conid);
- if (con)
+ if (con && test_bit(CF_CONNECTED, &con->flags))
conn_get(con);
+ else
+ con = NULL;
spin_unlock_bh(&s->idr_lock);
return con;
}
@@ -198,15 +206,8 @@ static void tipc_sock_release(struct tipc_conn *con)

static void tipc_close_conn(struct tipc_conn *con)
{
- struct tipc_server *s = con->server;
-
if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {

- spin_lock_bh(&s->idr_lock);
- idr_remove(&s->conn_idr, con->conid);
- s->idr_in_use--;
- spin_unlock_bh(&s->idr_lock);
-
/* We shouldn't flush pending works as we may be in the
* thread. In fact the races with pending rx/tx work structs
* are harmless for us here as we have already deleted this
@@ -458,6 +459,11 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
if (!con)
return -EINVAL;

+ if (!test_bit(CF_CONNECTED, &con->flags)) {
+ conn_put(con);
+ return 0;
+ }
+
e = tipc_alloc_entry(data, len);
if (!e) {
conn_put(con);
@@ -471,12 +477,8 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
list_add_tail(&e->list, &con->outqueue);
spin_unlock_bh(&con->outqueue_lock);

- if (test_bit(CF_CONNECTED, &con->flags)) {
- if (!queue_work(s->send_wq, &con->swork))
- conn_put(con);
- } else {
+ if (!queue_work(s->send_wq, &con->swork))
conn_put(con);
- }
return 0;
}

@@ -500,7 +502,7 @@ static void tipc_send_to_sock(struct tipc_conn *con)
int ret;

spin_lock_bh(&con->outqueue_lock);
- while (1) {
+ while (test_bit(CF_CONNECTED, &con->flags)) {
e = list_entry(con->outqueue.next, struct outqueue_entry,
list);
if ((struct list_head *) e == &con->outqueue)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 41f013888f07..25bc5c30d7fb 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -335,8 +335,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
INIT_LIST_HEAD(&tsk->publications);
msg = &tsk->phdr;
tn = net_generic(sock_net(sk), tipc_net_id);
- tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
- NAMED_H_SIZE, 0);

/* Finish initializing socket data structures */
sock->ops = ops;
@@ -346,6 +344,13 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
}
+
+ /* Ensure tsk is visible before we read own_addr. */
+ smp_mb();
+
+ tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
+ NAMED_H_SIZE, 0);
+
msg_set_origport(msg, tsk->portid);
setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
sk->sk_backlog_rcv = tipc_backlog_rcv;
@@ -2264,24 +2269,27 @@ static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
void tipc_sk_reinit(struct net *net)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
- const struct bucket_table *tbl;
- struct rhash_head *pos;
+ struct rhashtable_iter iter;
struct tipc_sock *tsk;
struct tipc_msg *msg;
- int i;

- rcu_read_lock();
- tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht);
- for (i = 0; i < tbl->size; i++) {
- rht_for_each_entry_rcu(tsk, pos, tbl, i, node) {
+ rhashtable_walk_enter(&tn->sk_rht, &iter);
+
+ do {
+ tsk = ERR_PTR(rhashtable_walk_start(&iter));
+ if (tsk)
+ continue;
+
+ while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) {
spin_lock_bh(&tsk->sk.sk_lock.slock);
msg = &tsk->phdr;
msg_set_prevnode(msg, tn->own_addr);
msg_set_orignode(msg, tn->own_addr);
spin_unlock_bh(&tsk->sk.sk_lock.slock);
}
- }
- rcu_read_unlock();
+
+ rhashtable_walk_stop(&iter);
+ } while (tsk == ERR_PTR(-EAGAIN));
}

static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid)
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 0dd02244e21d..9d94e65d0894 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -54,6 +54,8 @@ struct tipc_subscriber {

static void tipc_subscrp_delete(struct tipc_subscription *sub);
static void tipc_subscrb_put(struct tipc_subscriber *subscriber);
+static void tipc_subscrp_put(struct tipc_subscription *subscription);
+static void tipc_subscrp_get(struct tipc_subscription *subscription);

/**
* htohl - convert value to endianness used by destination
@@ -123,6 +125,7 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
{
struct tipc_name_seq seq;

+ tipc_subscrp_get(sub);
tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq);
if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper))
return;
@@ -132,30 +135,23 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,

tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref,
node);
+ tipc_subscrp_put(sub);
}

static void tipc_subscrp_timeout(unsigned long data)
{
struct tipc_subscription *sub = (struct tipc_subscription *)data;
- struct tipc_subscriber *subscriber = sub->subscriber;

/* Notify subscriber of timeout */
tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper,
TIPC_SUBSCR_TIMEOUT, 0, 0);

- spin_lock_bh(&subscriber->lock);
- tipc_subscrp_delete(sub);
- spin_unlock_bh(&subscriber->lock);
-
- tipc_subscrb_put(subscriber);
+ tipc_subscrp_put(sub);
}

static void tipc_subscrb_kref_release(struct kref *kref)
{
- struct tipc_subscriber *subcriber = container_of(kref,
- struct tipc_subscriber, kref);
-
- kfree(subcriber);
+ kfree(container_of(kref,struct tipc_subscriber, kref));
}

static void tipc_subscrb_put(struct tipc_subscriber *subscriber)
@@ -168,6 +164,59 @@ static void tipc_subscrb_get(struct tipc_subscriber *subscriber)
kref_get(&subscriber->kref);
}

+static void tipc_subscrp_kref_release(struct kref *kref)
+{
+ struct tipc_subscription *sub = container_of(kref,
+ struct tipc_subscription,
+ kref);
+ struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
+ struct tipc_subscriber *subscriber = sub->subscriber;
+
+ spin_lock_bh(&subscriber->lock);
+ tipc_nametbl_unsubscribe(sub);
+ list_del(&sub->subscrp_list);
+ atomic_dec(&tn->subscription_count);
+ spin_unlock_bh(&subscriber->lock);
+ kfree(sub);
+ tipc_subscrb_put(subscriber);
+}
+
+static void tipc_subscrp_put(struct tipc_subscription *subscription)
+{
+ kref_put(&subscription->kref, tipc_subscrp_kref_release);
+}
+
+static void tipc_subscrp_get(struct tipc_subscription *subscription)
+{
+ kref_get(&subscription->kref);
+}
+
+/* tipc_subscrb_subscrp_delete - delete a specific subscription or all
+ * subscriptions for a given subscriber.
+ */
+static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber,
+ struct tipc_subscr *s)
+{
+ struct list_head *subscription_list = &subscriber->subscrp_list;
+ struct tipc_subscription *sub, *temp;
+
+ spin_lock_bh(&subscriber->lock);
+ list_for_each_entry_safe(sub, temp, subscription_list, subscrp_list) {
+ if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr)))
+ continue;
+
+ tipc_subscrp_get(sub);
+ spin_unlock_bh(&subscriber->lock);
+ tipc_subscrp_delete(sub);
+ tipc_subscrp_put(sub);
+ spin_lock_bh(&subscriber->lock);
+
+ if (s)
+ break;
+ }
+ spin_unlock_bh(&subscriber->lock);
+}
+
static struct tipc_subscriber *tipc_subscrb_create(int conid)
{
struct tipc_subscriber *subscriber;
@@ -177,8 +226,8 @@ static struct tipc_subscriber *tipc_subscrb_create(int conid)
pr_warn("Subscriber rejected, no memory\n");
return NULL;
}
- kref_init(&subscriber->kref);
INIT_LIST_HEAD(&subscriber->subscrp_list);
+ kref_init(&subscriber->kref);
subscriber->conid = conid;
spin_lock_init(&subscriber->lock);

@@ -187,55 +236,22 @@ static struct tipc_subscriber *tipc_subscrb_create(int conid)

static void tipc_subscrb_delete(struct tipc_subscriber *subscriber)
{
- struct tipc_subscription *sub, *temp;
- u32 timeout;
-
- spin_lock_bh(&subscriber->lock);
- /* Destroy any existing subscriptions for subscriber */
- list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
- subscrp_list) {
- timeout = htohl(sub->evt.s.timeout, sub->swap);
- if ((timeout == TIPC_WAIT_FOREVER) || del_timer(&sub->timer)) {
- tipc_subscrp_delete(sub);
- tipc_subscrb_put(subscriber);
- }
- }
- spin_unlock_bh(&subscriber->lock);
-
+ tipc_subscrb_subscrp_delete(subscriber, NULL);
tipc_subscrb_put(subscriber);
}

static void tipc_subscrp_delete(struct tipc_subscription *sub)
{
- struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
+ u32 timeout = htohl(sub->evt.s.timeout, sub->swap);

- tipc_nametbl_unsubscribe(sub);
- list_del(&sub->subscrp_list);
- kfree(sub);
- atomic_dec(&tn->subscription_count);
+ if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer))
+ tipc_subscrp_put(sub);
}

static void tipc_subscrp_cancel(struct tipc_subscr *s,
struct tipc_subscriber *subscriber)
{
- struct tipc_subscription *sub, *temp;
- u32 timeout;
-
- spin_lock_bh(&subscriber->lock);
- /* Find first matching subscription, exit if not found */
- list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
- subscrp_list) {
- if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) {
- timeout = htohl(sub->evt.s.timeout, sub->swap);
- if ((timeout == TIPC_WAIT_FOREVER) ||
- del_timer(&sub->timer)) {
- tipc_subscrp_delete(sub);
- tipc_subscrb_put(subscriber);
- }
- break;
- }
- }
- spin_unlock_bh(&subscriber->lock);
+ tipc_subscrb_subscrp_delete(subscriber, s);
}

static struct tipc_subscription *tipc_subscrp_create(struct net *net,
@@ -272,6 +288,7 @@ static struct tipc_subscription *tipc_subscrp_create(struct net *net,
sub->swap = swap;
memcpy(&sub->evt.s, s, sizeof(*s));
atomic_inc(&tn->subscription_count);
+ kref_init(&sub->kref);
return sub;
}

@@ -288,17 +305,16 @@ static void tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s,

spin_lock_bh(&subscriber->lock);
list_add(&sub->subscrp_list, &subscriber->subscrp_list);
- tipc_subscrb_get(subscriber);
sub->subscriber = subscriber;
tipc_nametbl_subscribe(sub);
+ tipc_subscrb_get(subscriber);
spin_unlock_bh(&subscriber->lock);

+ setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub);
timeout = htohl(sub->evt.s.timeout, swap);
- if (timeout == TIPC_WAIT_FOREVER)
- return;

- setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub);
- mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
+ if (timeout != TIPC_WAIT_FOREVER)
+ mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
}

/* Handle one termination request for the subscriber */
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index be60103082c9..ffdc214c117a 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -57,6 +57,7 @@ struct tipc_subscriber;
* @evt: template for events generated by subscription
*/
struct tipc_subscription {
+ struct kref kref;
struct tipc_subscriber *subscriber;
struct net *net;
struct timer_list timer;