Re: Linux 5.4.52

From: Greg Kroah-Hartman
Date: Thu Jul 16 2020 - 04:38:07 EST


diff --git a/Makefile b/Makefile
index 6ac83669e073..435d27be54c9 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 5
PATCHLEVEL = 4
-SUBLEVEL = 51
+SUBLEVEL = 52
EXTRAVERSION =
NAME = Kleptomaniac Octopus

diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index c77a0e3671ac..0284ace0e1ab 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -19,7 +19,7 @@
#define R_ARC_32_PCREL 0x31

/*to set parameters in the core dumps */
-#define ELF_ARCH EM_ARCOMPACT
+#define ELF_ARCH EM_ARC_INUSE
#define ELF_CLASS ELFCLASS32

#ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 72be01270e24..ea74a1eee5d9 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -153,7 +153,6 @@ END(EV_Extension)
tracesys:
; save EFA in case tracer wants the PC of traced task
; using ERET won't work since next-PC has already committed
- lr r12, [efa]
GET_CURR_TASK_FIELD_PTR TASK_THREAD, r11
st r12, [r11, THREAD_FAULT_ADDR] ; thread.fault_address

@@ -196,15 +195,9 @@ tracesys_exit:
; Breakpoint TRAP
; ---------------------------------------------
trap_with_param:
-
- ; stop_pc info by gdb needs this info
- lr r0, [efa]
+ mov r0, r12 ; EFA in case ptracer/gdb wants stop_pc
mov r1, sp

- ; Now that we have read EFA, it is safe to do "fake" rtie
- ; and get out of CPU exception mode
- FAKE_RET_FROM_EXCPN
-
; Save callee regs in case gdb wants to have a look
; SP will grow up by size of CALLEE Reg-File
; NOTE: clobbers r12
@@ -231,6 +224,10 @@ ENTRY(EV_Trap)

EXCEPTION_PROLOGUE

+ lr r12, [efa]
+
+ FAKE_RET_FROM_EXCPN
+
;============ TRAP 1 :breakpoints
; Check ECR for trap with arg (PROLOGUE ensures r10 has ECR)
bmsk.f 0, r10, 7
@@ -238,9 +235,6 @@ ENTRY(EV_Trap)

;============ TRAP (no param): syscall top level

- ; First return from Exception to pure K mode (Exception/IRQs renabled)
- FAKE_RET_FROM_EXCPN
-
; If syscall tracing ongoing, invoke pre-post-hooks
GET_CURR_THR_INFO_FLAGS r10
btst r10, TIF_SYSCALL_TRACE
diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
index 82f7ae030600..ab91c4ebb146 100644
--- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
+++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
@@ -13,8 +13,10 @@
#interrupt-cells = <2>;
#address-cells = <1>;
#size-cells = <0>;
- spi-max-frequency = <3000000>;
+ spi-max-frequency = <9600000>;
spi-cs-high;
+ spi-cpol;
+ spi-cpha;

cpcap_adc: adc {
compatible = "motorola,mapphone-cpcap-adc";
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index 1c0ecad3620e..baf3b47601af 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -493,14 +493,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
if (!ocram_pool) {
pr_warn("%s: ocram pool unavailable!\n", __func__);
ret = -ENODEV;
- goto put_node;
+ goto put_device;
}

ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE);
if (!ocram_base) {
pr_warn("%s: unable to alloc ocram!\n", __func__);
ret = -ENOMEM;
- goto put_node;
+ goto put_device;
}

ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -523,7 +523,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat);
if (ret) {
pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret);
- goto put_node;
+ goto put_device;
}

ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat);
@@ -570,7 +570,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
&imx6_suspend,
MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info));

- goto put_node;
+ goto put_device;

pl310_cache_map_failed:
iounmap(pm_info->gpc_base.vbase);
@@ -580,6 +580,8 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata)
iounmap(pm_info->src_base.vbase);
src_map_failed:
iounmap(pm_info->mmdc_base.vbase);
+put_device:
+ put_device(&pdev->dev);
put_node:
of_node_put(node);

diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 89e4c8b79349..ee9bdaa40532 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -109,7 +109,7 @@ static inline u32 gic_read_pmr(void)
return read_sysreg_s(SYS_ICC_PMR_EL1);
}

-static inline void gic_write_pmr(u32 val)
+static __always_inline void gic_write_pmr(u32 val)
{
write_sysreg_s(val, SYS_ICC_PMR_EL1);
}
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 9cde5d2e768f..10d3048dec7c 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -601,7 +601,7 @@ static inline bool system_supports_generic_auth(void)
cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF));
}

-static inline bool system_uses_irq_prio_masking(void)
+static __always_inline bool system_uses_irq_prio_masking(void)
{
return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index baf52baaa2a5..99b0a32e25c1 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -54,7 +54,7 @@
#define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
#define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
#define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
+#define PAGE_HYP_DEVICE __pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)

#define PAGE_S2_MEMATTR(attr) \
({ \
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 43119922341f..1a157ca33262 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
if (!kgdb_single_step)
return DBG_HOOK_ERROR;

- kgdb_handle_exception(1, SIGTRAP, 0, regs);
+ kgdb_handle_exception(0, SIGTRAP, 0, regs);
return DBG_HOOK_HANDLED;
}
NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 160be2b4696d..dc41b505507d 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -136,11 +136,15 @@ ENTRY(__kvm_handle_stub_hvc)

1: cmp x0, #HVC_RESET_VECTORS
b.ne 1f
-reset:
+
/*
- * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
- * case we coming via HVC_SOFT_RESTART.
+ * Set the HVC_RESET_VECTORS return code before entering the common
+ * path so that we do not clobber x0-x2 in case we are coming via
+ * HVC_SOFT_RESTART.
*/
+ mov x0, xzr
+reset:
+ /* Reset kvm back to the hyp stub. */
mrs x5, sctlr_el2
ldr x6, =SCTLR_ELx_FLAGS
bic x5, x5, x6 // Clear SCTL_M and etc
@@ -151,7 +155,6 @@ reset:
/* Install stub vectors */
adr_l x5, __hyp_stub_vectors
msr vbar_el2, x5
- mov x0, xzr
eret

1: /* Bad stub call */
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f4a8ae918827..784d485218ca 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -258,7 +258,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
const struct kvm_regs *cpu_reset;
- int ret = -EINVAL;
+ int ret;
bool loaded;

/* Reset PMU outside of the non-preemptible section */
@@ -281,15 +281,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)

if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
- if (kvm_vcpu_enable_ptrauth(vcpu))
+ if (kvm_vcpu_enable_ptrauth(vcpu)) {
+ ret = -EINVAL;
goto out;
+ }
}

switch (vcpu->arch.target) {
default:
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
- if (!cpu_has_32bit_el1())
+ if (!cpu_has_32bit_el1()) {
+ ret = -EINVAL;
goto out;
+ }
cpu_reset = &default_regs_reset32;
} else {
cpu_reset = &default_regs_reset;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 43b56f8f6beb..da8375437d16 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -38,7 +38,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
if (kvmhv_on_pseries())
return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
- __pa(to), __pa(from), n);
+ (to != NULL) ? __pa(to): 0,
+ (from != NULL) ? __pa(from): 0, n);

quadrant = 1;
if (!pid)
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index abe60268335d..0fe5600a037e 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -31,12 +31,12 @@
#define KVM_USER_MEM_SLOTS 32

/*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
*/
#define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
#define KVM_HALT_POLL_NS_DEFAULT 50000

/* s390-specific vcpu->requests bit members */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index a470f1fa9f2a..324438889fe1 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -276,6 +276,6 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
}

int copy_to_user_real(void __user *dest, void *src, unsigned long count);
-void s390_kernel_write(void *dst, const void *src, size_t size);
+void *s390_kernel_write(void *dst, const void *src, size_t size);

#endif /* __S390_UACCESS_H */
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index b432d63d0b37..2531776cf6cf 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -169,6 +169,8 @@ static noinline __init void setup_lowcore_early(void)
psw_t psw;

psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+ if (IS_ENABLED(CONFIG_KASAN))
+ psw.mask |= PSW_MASK_DAT;
psw.addr = (unsigned long) s390_base_ext_handler;
S390_lowcore.external_new_psw = psw;
psw.addr = (unsigned long) s390_base_pgm_handler;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 4366962f4930..07b2b61a0289 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1120,6 +1120,7 @@ void __init setup_arch(char **cmdline_p)
if (IS_ENABLED(CONFIG_EXPOLINE_AUTO))
nospec_auto_detect();

+ jump_label_init();
parse_early_param();
#ifdef CONFIG_CRASH_DUMP
/* Deactivate elfcorehdr= kernel parameter */
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 7dfae86afa47..ff8234bca56c 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -117,7 +117,7 @@ static inline pte_t __rste_to_pte(unsigned long rste)
_PAGE_YOUNG);
#ifdef CONFIG_MEM_SOFT_DIRTY
pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
- _PAGE_DIRTY);
+ _PAGE_SOFT_DIRTY);
#endif
pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC,
_PAGE_NOEXEC);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index de7ca4b6718f..1d17413b319a 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -55,19 +55,26 @@ static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t siz
*/
static DEFINE_SPINLOCK(s390_kernel_write_lock);

-void notrace s390_kernel_write(void *dst, const void *src, size_t size)
+notrace void *s390_kernel_write(void *dst, const void *src, size_t size)
{
+ void *tmp = dst;
unsigned long flags;
long copied;

spin_lock_irqsave(&s390_kernel_write_lock, flags);
- while (size) {
- copied = s390_kernel_write_odd(dst, src, size);
- dst += copied;
- src += copied;
- size -= copied;
+ if (!(flags & PSW_MASK_DAT)) {
+ memcpy(dst, src, size);
+ } else {
+ while (size) {
+ copied = s390_kernel_write_odd(tmp, src, size);
+ tmp += copied;
+ src += copied;
+ size -= copied;
+ }
}
spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
+
+ return dst;
}

static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count)
diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig
index 9a7a1446cb3a..4a809c6cbd2f 100644
--- a/arch/x86/events/Kconfig
+++ b/arch/x86/events/Kconfig
@@ -10,11 +10,11 @@ config PERF_EVENTS_INTEL_UNCORE
available on NehalemEX and more modern processors.

config PERF_EVENTS_INTEL_RAPL
- tristate "Intel rapl performance events"
- depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+ tristate "Intel/AMD rapl performance events"
+ depends on PERF_EVENTS && (CPU_SUP_INTEL || CPU_SUP_AMD) && PCI
default y
---help---
- Include support for Intel rapl performance events for power
+ Include support for Intel and AMD rapl performance events for power
monitoring on modern processors.

config PERF_EVENTS_INTEL_CSTATE
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 9e07f554333f..726e83c0a31a 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y += core.o probe.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += rapl.o
obj-y += amd/
obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
index 3468b0c1dc7c..e67a5886336c 100644
--- a/arch/x86/events/intel/Makefile
+++ b/arch/x86/events/intel/Makefile
@@ -2,8 +2,6 @@
obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o
obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o
obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o
-intel-rapl-perf-objs := rapl.o
obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o
intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
deleted file mode 100644
index 5053a403e4ae..000000000000
--- a/arch/x86/events/intel/rapl.c
+++ /dev/null
@@ -1,802 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Support Intel RAPL energy consumption counters
- * Copyright (C) 2013 Google, Inc., Stephane Eranian
- *
- * Intel RAPL interface is specified in the IA-32 Manual Vol3b
- * section 14.7.1 (September 2013)
- *
- * RAPL provides more controls than just reporting energy consumption
- * however here we only expose the 3 energy consumption free running
- * counters (pp0, pkg, dram).
- *
- * Each of those counters increments in a power unit defined by the
- * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules
- * but it can vary.
- *
- * Counter to rapl events mappings:
- *
- * pp0 counter: consumption of all physical cores (power plane 0)
- * event: rapl_energy_cores
- * perf code: 0x1
- *
- * pkg counter: consumption of the whole processor package
- * event: rapl_energy_pkg
- * perf code: 0x2
- *
- * dram counter: consumption of the dram domain (servers only)
- * event: rapl_energy_dram
- * perf code: 0x3
- *
- * gpu counter: consumption of the builtin-gpu domain (client only)
- * event: rapl_energy_gpu
- * perf code: 0x4
- *
- * psys counter: consumption of the builtin-psys domain (client only)
- * event: rapl_energy_psys
- * perf code: 0x5
- *
- * We manage those counters as free running (read-only). They may be
- * use simultaneously by other tools, such as turbostat.
- *
- * The events only support system-wide mode counting. There is no
- * sampling support because it does not make sense and is not
- * supported by the RAPL hardware.
- *
- * Because we want to avoid floating-point operations in the kernel,
- * the events are all reported in fixed point arithmetic (32.32).
- * Tools must adjust the counts to convert them to Watts using
- * the duration of the measurement. Tools may use a function such as
- * ldexp(raw_count, -32);
- */
-
-#define pr_fmt(fmt) "RAPL PMU: " fmt
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/perf_event.h>
-#include <linux/nospec.h>
-#include <asm/cpu_device_id.h>
-#include <asm/intel-family.h>
-#include "../perf_event.h"
-#include "../probe.h"
-
-MODULE_LICENSE("GPL");
-
-/*
- * RAPL energy status counters
- */
-enum perf_rapl_events {
- PERF_RAPL_PP0 = 0, /* all cores */
- PERF_RAPL_PKG, /* entire package */
- PERF_RAPL_RAM, /* DRAM */
- PERF_RAPL_PP1, /* gpu */
- PERF_RAPL_PSYS, /* psys */
-
- PERF_RAPL_MAX,
- NR_RAPL_DOMAINS = PERF_RAPL_MAX,
-};
-
-static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
- "pp0-core",
- "package",
- "dram",
- "pp1-gpu",
- "psys",
-};
-
-/*
- * event code: LSB 8 bits, passed in attr->config
- * any other bit is reserved
- */
-#define RAPL_EVENT_MASK 0xFFULL
-
-#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \
-static ssize_t __rapl_##_var##_show(struct kobject *kobj, \
- struct kobj_attribute *attr, \
- char *page) \
-{ \
- BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
- return sprintf(page, _format "\n"); \
-} \
-static struct kobj_attribute format_attr_##_var = \
- __ATTR(_name, 0444, __rapl_##_var##_show, NULL)
-
-#define RAPL_CNTR_WIDTH 32
-
-#define RAPL_EVENT_ATTR_STR(_name, v, str) \
-static struct perf_pmu_events_attr event_attr_##v = { \
- .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
- .id = 0, \
- .event_str = str, \
-};
-
-struct rapl_pmu {
- raw_spinlock_t lock;
- int n_active;
- int cpu;
- struct list_head active_list;
- struct pmu *pmu;
- ktime_t timer_interval;
- struct hrtimer hrtimer;
-};
-
-struct rapl_pmus {
- struct pmu pmu;
- unsigned int maxdie;
- struct rapl_pmu *pmus[];
-};
-
-struct rapl_model {
- unsigned long events;
- bool apply_quirk;
-};
-
- /* 1/2^hw_unit Joule */
-static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
-static struct rapl_pmus *rapl_pmus;
-static cpumask_t rapl_cpu_mask;
-static unsigned int rapl_cntr_mask;
-static u64 rapl_timer_ms;
-static struct perf_msr rapl_msrs[];
-
-static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
-{
- unsigned int dieid = topology_logical_die_id(cpu);
-
- /*
- * The unsigned check also catches the '-1' return value for non
- * existent mappings in the topology map.
- */
- return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
-}
-
-static inline u64 rapl_read_counter(struct perf_event *event)
-{
- u64 raw;
- rdmsrl(event->hw.event_base, raw);
- return raw;
-}
-
-static inline u64 rapl_scale(u64 v, int cfg)
-{
- if (cfg > NR_RAPL_DOMAINS) {
- pr_warn("Invalid domain %d, failed to scale data\n", cfg);
- return v;
- }
- /*
- * scale delta to smallest unit (1/2^32)
- * users must then scale back: count * 1/(1e9*2^32) to get Joules
- * or use ldexp(count, -32).
- * Watts = Joules/Time delta
- */
- return v << (32 - rapl_hw_unit[cfg - 1]);
-}
-
-static u64 rapl_event_update(struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- u64 prev_raw_count, new_raw_count;
- s64 delta, sdelta;
- int shift = RAPL_CNTR_WIDTH;
-
-again:
- prev_raw_count = local64_read(&hwc->prev_count);
- rdmsrl(event->hw.event_base, new_raw_count);
-
- if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- new_raw_count) != prev_raw_count) {
- cpu_relax();
- goto again;
- }
-
- /*
- * Now we have the new raw value and have updated the prev
- * timestamp already. We can now calculate the elapsed delta
- * (event-)time and add that to the generic event.
- *
- * Careful, not all hw sign-extends above the physical width
- * of the count.
- */
- delta = (new_raw_count << shift) - (prev_raw_count << shift);
- delta >>= shift;
-
- sdelta = rapl_scale(delta, event->hw.config);
-
- local64_add(sdelta, &event->count);
-
- return new_raw_count;
-}
-
-static void rapl_start_hrtimer(struct rapl_pmu *pmu)
-{
- hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
- HRTIMER_MODE_REL_PINNED);
-}
-
-static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
-{
- struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer);
- struct perf_event *event;
- unsigned long flags;
-
- if (!pmu->n_active)
- return HRTIMER_NORESTART;
-
- raw_spin_lock_irqsave(&pmu->lock, flags);
-
- list_for_each_entry(event, &pmu->active_list, active_entry)
- rapl_event_update(event);
-
- raw_spin_unlock_irqrestore(&pmu->lock, flags);
-
- hrtimer_forward_now(hrtimer, pmu->timer_interval);
-
- return HRTIMER_RESTART;
-}
-
-static void rapl_hrtimer_init(struct rapl_pmu *pmu)
-{
- struct hrtimer *hr = &pmu->hrtimer;
-
- hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hr->function = rapl_hrtimer_handle;
-}
-
-static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
- struct perf_event *event)
-{
- if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
- return;
-
- event->hw.state = 0;
-
- list_add_tail(&event->active_entry, &pmu->active_list);
-
- local64_set(&event->hw.prev_count, rapl_read_counter(event));
-
- pmu->n_active++;
- if (pmu->n_active == 1)
- rapl_start_hrtimer(pmu);
-}
-
-static void rapl_pmu_event_start(struct perf_event *event, int mode)
-{
- struct rapl_pmu *pmu = event->pmu_private;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&pmu->lock, flags);
- __rapl_pmu_event_start(pmu, event);
- raw_spin_unlock_irqrestore(&pmu->lock, flags);
-}
-
-static void rapl_pmu_event_stop(struct perf_event *event, int mode)
-{
- struct rapl_pmu *pmu = event->pmu_private;
- struct hw_perf_event *hwc = &event->hw;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&pmu->lock, flags);
-
- /* mark event as deactivated and stopped */
- if (!(hwc->state & PERF_HES_STOPPED)) {
- WARN_ON_ONCE(pmu->n_active <= 0);
- pmu->n_active--;
- if (pmu->n_active == 0)
- hrtimer_cancel(&pmu->hrtimer);
-
- list_del(&event->active_entry);
-
- WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
- hwc->state |= PERF_HES_STOPPED;
- }
-
- /* check if update of sw counter is necessary */
- if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
- /*
- * Drain the remaining delta count out of a event
- * that we are disabling:
- */
- rapl_event_update(event);
- hwc->state |= PERF_HES_UPTODATE;
- }
-
- raw_spin_unlock_irqrestore(&pmu->lock, flags);
-}
-
-static int rapl_pmu_event_add(struct perf_event *event, int mode)
-{
- struct rapl_pmu *pmu = event->pmu_private;
- struct hw_perf_event *hwc = &event->hw;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&pmu->lock, flags);
-
- hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-
- if (mode & PERF_EF_START)
- __rapl_pmu_event_start(pmu, event);
-
- raw_spin_unlock_irqrestore(&pmu->lock, flags);
-
- return 0;
-}
-
-static void rapl_pmu_event_del(struct perf_event *event, int flags)
-{
- rapl_pmu_event_stop(event, PERF_EF_UPDATE);
-}
-
-static int rapl_pmu_event_init(struct perf_event *event)
-{
- u64 cfg = event->attr.config & RAPL_EVENT_MASK;
- int bit, ret = 0;
- struct rapl_pmu *pmu;
-
- /* only look at RAPL events */
- if (event->attr.type != rapl_pmus->pmu.type)
- return -ENOENT;
-
- /* check only supported bits are set */
- if (event->attr.config & ~RAPL_EVENT_MASK)
- return -EINVAL;
-
- if (event->cpu < 0)
- return -EINVAL;
-
- event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
-
- if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
- return -EINVAL;
-
- cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
- bit = cfg - 1;
-
- /* check event supported */
- if (!(rapl_cntr_mask & (1 << bit)))
- return -EINVAL;
-
- /* unsupported modes and filters */
- if (event->attr.sample_period) /* no sampling */
- return -EINVAL;
-
- /* must be done before validate_group */
- pmu = cpu_to_rapl_pmu(event->cpu);
- if (!pmu)
- return -EINVAL;
- event->cpu = pmu->cpu;
- event->pmu_private = pmu;
- event->hw.event_base = rapl_msrs[bit].msr;
- event->hw.config = cfg;
- event->hw.idx = bit;
-
- return ret;
-}
-
-static void rapl_pmu_event_read(struct perf_event *event)
-{
- rapl_event_update(event);
-}
-
-static ssize_t rapl_get_attr_cpumask(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask);
-}
-
-static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
-
-static struct attribute *rapl_pmu_attrs[] = {
- &dev_attr_cpumask.attr,
- NULL,
-};
-
-static struct attribute_group rapl_pmu_attr_group = {
- .attrs = rapl_pmu_attrs,
-};
-
-RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
-RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
-RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
-RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04");
-RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05");
-
-RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
-RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
-RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
-RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules");
-RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules");
-
-/*
- * we compute in 0.23 nJ increments regardless of MSR
- */
-RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
-RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
-RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
-RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
-RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10");
-
-/*
- * There are no default events, but we need to create
- * "events" group (with empty attrs) before updating
- * it with detected events.
- */
-static struct attribute *attrs_empty[] = {
- NULL,
-};
-
-static struct attribute_group rapl_pmu_events_group = {
- .name = "events",
- .attrs = attrs_empty,
-};
-
-DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
-static struct attribute *rapl_formats_attr[] = {
- &format_attr_event.attr,
- NULL,
-};
-
-static struct attribute_group rapl_pmu_format_group = {
- .name = "format",
- .attrs = rapl_formats_attr,
-};
-
-static const struct attribute_group *rapl_attr_groups[] = {
- &rapl_pmu_attr_group,
- &rapl_pmu_format_group,
- &rapl_pmu_events_group,
- NULL,
-};
-
-static struct attribute *rapl_events_cores[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_cores_scale),
- NULL,
-};
-
-static struct attribute_group rapl_events_cores_group = {
- .name = "events",
- .attrs = rapl_events_cores,
-};
-
-static struct attribute *rapl_events_pkg[] = {
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_pkg_scale),
- NULL,
-};
-
-static struct attribute_group rapl_events_pkg_group = {
- .name = "events",
- .attrs = rapl_events_pkg,
-};
-
-static struct attribute *rapl_events_ram[] = {
- EVENT_PTR(rapl_ram),
- EVENT_PTR(rapl_ram_unit),
- EVENT_PTR(rapl_ram_scale),
- NULL,
-};
-
-static struct attribute_group rapl_events_ram_group = {
- .name = "events",
- .attrs = rapl_events_ram,
-};
-
-static struct attribute *rapl_events_gpu[] = {
- EVENT_PTR(rapl_gpu),
- EVENT_PTR(rapl_gpu_unit),
- EVENT_PTR(rapl_gpu_scale),
- NULL,
-};
-
-static struct attribute_group rapl_events_gpu_group = {
- .name = "events",
- .attrs = rapl_events_gpu,
-};
-
-static struct attribute *rapl_events_psys[] = {
- EVENT_PTR(rapl_psys),
- EVENT_PTR(rapl_psys_unit),
- EVENT_PTR(rapl_psys_scale),
- NULL,
-};
-
-static struct attribute_group rapl_events_psys_group = {
- .name = "events",
- .attrs = rapl_events_psys,
-};
-
-static bool test_msr(int idx, void *data)
-{
- return test_bit(idx, (unsigned long *) data);
-}
-
-static struct perf_msr rapl_msrs[] = {
- [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr },
- [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
- [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr },
- [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr },
- [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr },
-};
-
-static int rapl_cpu_offline(unsigned int cpu)
-{
- struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
- int target;
-
- /* Check if exiting cpu is used for collecting rapl events */
- if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask))
- return 0;
-
- pmu->cpu = -1;
- /* Find a new cpu to collect rapl events */
- target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
-
- /* Migrate rapl events to the new target */
- if (target < nr_cpu_ids) {
- cpumask_set_cpu(target, &rapl_cpu_mask);
- pmu->cpu = target;
- perf_pmu_migrate_context(pmu->pmu, cpu, target);
- }
- return 0;
-}
-
-static int rapl_cpu_online(unsigned int cpu)
-{
- struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
- int target;
-
- if (!pmu) {
- pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
- if (!pmu)
- return -ENOMEM;
-
- raw_spin_lock_init(&pmu->lock);
- INIT_LIST_HEAD(&pmu->active_list);
- pmu->pmu = &rapl_pmus->pmu;
- pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
- rapl_hrtimer_init(pmu);
-
- rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
- }
-
- /*
- * Check if there is an online cpu in the package which collects rapl
- * events already.
- */
- target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
- if (target < nr_cpu_ids)
- return 0;
-
- cpumask_set_cpu(cpu, &rapl_cpu_mask);
- pmu->cpu = cpu;
- return 0;
-}
-
-static int rapl_check_hw_unit(bool apply_quirk)
-{
- u64 msr_rapl_power_unit_bits;
- int i;
-
- /* protect rdmsrl() to handle virtualization */
- if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
- return -1;
- for (i = 0; i < NR_RAPL_DOMAINS; i++)
- rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
-
- /*
- * DRAM domain on HSW server and KNL has fixed energy unit which can be
- * different than the unit from power unit MSR. See
- * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
- * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
- */
- if (apply_quirk)
- rapl_hw_unit[PERF_RAPL_RAM] = 16;
-
- /*
- * Calculate the timer rate:
- * Use reference of 200W for scaling the timeout to avoid counter
- * overflows. 200W = 200 Joules/sec
- * Divide interval by 2 to avoid lockstep (2 * 100)
- * if hw unit is 32, then we use 2 ms 1/200/2
- */
- rapl_timer_ms = 2;
- if (rapl_hw_unit[0] < 32) {
- rapl_timer_ms = (1000 / (2 * 100));
- rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1));
- }
- return 0;
-}
-
-static void __init rapl_advertise(void)
-{
- int i;
-
- pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n",
- hweight32(rapl_cntr_mask), rapl_timer_ms);
-
- for (i = 0; i < NR_RAPL_DOMAINS; i++) {
- if (rapl_cntr_mask & (1 << i)) {
- pr_info("hw unit of domain %s 2^-%d Joules\n",
- rapl_domain_names[i], rapl_hw_unit[i]);
- }
- }
-}
-
-static void cleanup_rapl_pmus(void)
-{
- int i;
-
- for (i = 0; i < rapl_pmus->maxdie; i++)
- kfree(rapl_pmus->pmus[i]);
- kfree(rapl_pmus);
-}
-
-static const struct attribute_group *rapl_attr_update[] = {
- &rapl_events_cores_group,
- &rapl_events_pkg_group,
- &rapl_events_ram_group,
- &rapl_events_gpu_group,
- &rapl_events_gpu_group,
- NULL,
-};
-
-static int __init init_rapl_pmus(void)
-{
- int maxdie = topology_max_packages() * topology_max_die_per_package();
- size_t size;
-
- size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
- rapl_pmus = kzalloc(size, GFP_KERNEL);
- if (!rapl_pmus)
- return -ENOMEM;
-
- rapl_pmus->maxdie = maxdie;
- rapl_pmus->pmu.attr_groups = rapl_attr_groups;
- rapl_pmus->pmu.attr_update = rapl_attr_update;
- rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
- rapl_pmus->pmu.event_init = rapl_pmu_event_init;
- rapl_pmus->pmu.add = rapl_pmu_event_add;
- rapl_pmus->pmu.del = rapl_pmu_event_del;
- rapl_pmus->pmu.start = rapl_pmu_event_start;
- rapl_pmus->pmu.stop = rapl_pmu_event_stop;
- rapl_pmus->pmu.read = rapl_pmu_event_read;
- rapl_pmus->pmu.module = THIS_MODULE;
- rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE;
- return 0;
-}
-
-#define X86_RAPL_MODEL_MATCH(model, init) \
- { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
-
-static struct rapl_model model_snb = {
- .events = BIT(PERF_RAPL_PP0) |
- BIT(PERF_RAPL_PKG) |
- BIT(PERF_RAPL_PP1),
- .apply_quirk = false,
-};
-
-static struct rapl_model model_snbep = {
- .events = BIT(PERF_RAPL_PP0) |
- BIT(PERF_RAPL_PKG) |
- BIT(PERF_RAPL_RAM),
- .apply_quirk = false,
-};
-
-static struct rapl_model model_hsw = {
- .events = BIT(PERF_RAPL_PP0) |
- BIT(PERF_RAPL_PKG) |
- BIT(PERF_RAPL_RAM) |
- BIT(PERF_RAPL_PP1),
- .apply_quirk = false,
-};
-
-static struct rapl_model model_hsx = {
- .events = BIT(PERF_RAPL_PP0) |
- BIT(PERF_RAPL_PKG) |
- BIT(PERF_RAPL_RAM),
- .apply_quirk = true,
-};
-
-static struct rapl_model model_knl = {
- .events = BIT(PERF_RAPL_PKG) |
- BIT(PERF_RAPL_RAM),
- .apply_quirk = true,
-};
-
-static struct rapl_model model_skl = {
- .events = BIT(PERF_RAPL_PP0) |
- BIT(PERF_RAPL_PKG) |
- BIT(PERF_RAPL_RAM) |
- BIT(PERF_RAPL_PP1) |
- BIT(PERF_RAPL_PSYS),
- .apply_quirk = false,
-};
-
-static const struct x86_cpu_id rapl_model_match[] __initconst = {
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_L, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_G, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, model_hsx),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, model_skl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE, model_skl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, model_skl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE, model_skl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_L, model_skl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_D, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, model_skl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE, model_skl),
- {},
-};
-
-MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
-
-static int __init rapl_pmu_init(void)
-{
- const struct x86_cpu_id *id;
- struct rapl_model *rm;
- int ret;
-
- id = x86_match_cpu(rapl_model_match);
- if (!id)
- return -ENODEV;
-
- rm = (struct rapl_model *) id->driver_data;
- rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
- false, (void *) &rm->events);
-
- ret = rapl_check_hw_unit(rm->apply_quirk);
- if (ret)
- return ret;
-
- ret = init_rapl_pmus();
- if (ret)
- return ret;
-
- /*
- * Install callbacks. Core will call them for each online cpu.
- */
- ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
- "perf/x86/rapl:online",
- rapl_cpu_online, rapl_cpu_offline);
- if (ret)
- goto out;
-
- ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
- if (ret)
- goto out1;
-
- rapl_advertise();
- return 0;
-
-out1:
- cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-out:
- pr_warn("Initialization failed (%d), disabled\n", ret);
- cleanup_rapl_pmus();
- return ret;
-}
-module_init(rapl_pmu_init);
-
-static void __exit intel_rapl_exit(void)
-{
- cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
- perf_pmu_unregister(&rapl_pmus->pmu);
- cleanup_rapl_pmus();
-}
-module_exit(intel_rapl_exit);
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
new file mode 100644
index 000000000000..3c222d6fdee3
--- /dev/null
+++ b/arch/x86/events/rapl.c
@@ -0,0 +1,805 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Support Intel/AMD RAPL energy consumption counters
+ * Copyright (C) 2013 Google, Inc., Stephane Eranian
+ *
+ * Intel RAPL interface is specified in the IA-32 Manual Vol3b
+ * section 14.7.1 (September 2013)
+ *
+ * AMD RAPL interface for Fam17h is described in the public PPR:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=206537
+ *
+ * RAPL provides more controls than just reporting energy consumption
+ * however here we only expose the 3 energy consumption free running
+ * counters (pp0, pkg, dram).
+ *
+ * Each of those counters increments in a power unit defined by the
+ * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules
+ * but it can vary.
+ *
+ * Counter to rapl events mappings:
+ *
+ * pp0 counter: consumption of all physical cores (power plane 0)
+ * event: rapl_energy_cores
+ * perf code: 0x1
+ *
+ * pkg counter: consumption of the whole processor package
+ * event: rapl_energy_pkg
+ * perf code: 0x2
+ *
+ * dram counter: consumption of the dram domain (servers only)
+ * event: rapl_energy_dram
+ * perf code: 0x3
+ *
+ * gpu counter: consumption of the builtin-gpu domain (client only)
+ * event: rapl_energy_gpu
+ * perf code: 0x4
+ *
+ * psys counter: consumption of the builtin-psys domain (client only)
+ * event: rapl_energy_psys
+ * perf code: 0x5
+ *
+ * We manage those counters as free running (read-only). They may be
+ * use simultaneously by other tools, such as turbostat.
+ *
+ * The events only support system-wide mode counting. There is no
+ * sampling support because it does not make sense and is not
+ * supported by the RAPL hardware.
+ *
+ * Because we want to avoid floating-point operations in the kernel,
+ * the events are all reported in fixed point arithmetic (32.32).
+ * Tools must adjust the counts to convert them to Watts using
+ * the duration of the measurement. Tools may use a function such as
+ * ldexp(raw_count, -32);
+ */
+
+#define pr_fmt(fmt) "RAPL PMU: " fmt
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+#include <linux/nospec.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include "perf_event.h"
+#include "probe.h"
+
+MODULE_LICENSE("GPL");
+
+/*
+ * RAPL energy status counters
+ */
+enum perf_rapl_events {
+ PERF_RAPL_PP0 = 0, /* all cores */
+ PERF_RAPL_PKG, /* entire package */
+ PERF_RAPL_RAM, /* DRAM */
+ PERF_RAPL_PP1, /* gpu */
+ PERF_RAPL_PSYS, /* psys */
+
+ PERF_RAPL_MAX,
+ NR_RAPL_DOMAINS = PERF_RAPL_MAX,
+};
+
+static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
+ "pp0-core",
+ "package",
+ "dram",
+ "pp1-gpu",
+ "psys",
+};
+
+/*
+ * event code: LSB 8 bits, passed in attr->config
+ * any other bit is reserved
+ */
+#define RAPL_EVENT_MASK 0xFFULL
+
+#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \
+static ssize_t __rapl_##_var##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct kobj_attribute format_attr_##_var = \
+ __ATTR(_name, 0444, __rapl_##_var##_show, NULL)
+
+#define RAPL_CNTR_WIDTH 32
+
+#define RAPL_EVENT_ATTR_STR(_name, v, str) \
+static struct perf_pmu_events_attr event_attr_##v = { \
+ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
+ .id = 0, \
+ .event_str = str, \
+};
+
+struct rapl_pmu {
+ raw_spinlock_t lock;
+ int n_active;
+ int cpu;
+ struct list_head active_list;
+ struct pmu *pmu;
+ ktime_t timer_interval;
+ struct hrtimer hrtimer;
+};
+
+struct rapl_pmus {
+ struct pmu pmu;
+ unsigned int maxdie;
+ struct rapl_pmu *pmus[];
+};
+
+struct rapl_model {
+ unsigned long events;
+ bool apply_quirk;
+};
+
+ /* 1/2^hw_unit Joule */
+static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
+static struct rapl_pmus *rapl_pmus;
+static cpumask_t rapl_cpu_mask;
+static unsigned int rapl_cntr_mask;
+static u64 rapl_timer_ms;
+static struct perf_msr rapl_msrs[];
+
+static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
+{
+ unsigned int dieid = topology_logical_die_id(cpu);
+
+ /*
+ * The unsigned check also catches the '-1' return value for non
+ * existent mappings in the topology map.
+ */
+ return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
+}
+
+static inline u64 rapl_read_counter(struct perf_event *event)
+{
+ u64 raw;
+ rdmsrl(event->hw.event_base, raw);
+ return raw;
+}
+
+static inline u64 rapl_scale(u64 v, int cfg)
+{
+ if (cfg > NR_RAPL_DOMAINS) {
+ pr_warn("Invalid domain %d, failed to scale data\n", cfg);
+ return v;
+ }
+ /*
+ * scale delta to smallest unit (1/2^32)
+ * users must then scale back: count * 1/(1e9*2^32) to get Joules
+ * or use ldexp(count, -32).
+ * Watts = Joules/Time delta
+ */
+ return v << (32 - rapl_hw_unit[cfg - 1]);
+}
+
+static u64 rapl_event_update(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 prev_raw_count, new_raw_count;
+ s64 delta, sdelta;
+ int shift = RAPL_CNTR_WIDTH;
+
+again:
+ prev_raw_count = local64_read(&hwc->prev_count);
+ rdmsrl(event->hw.event_base, new_raw_count);
+
+ if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+ new_raw_count) != prev_raw_count) {
+ cpu_relax();
+ goto again;
+ }
+
+ /*
+ * Now we have the new raw value and have updated the prev
+ * timestamp already. We can now calculate the elapsed delta
+ * (event-)time and add that to the generic event.
+ *
+ * Careful, not all hw sign-extends above the physical width
+ * of the count.
+ */
+ delta = (new_raw_count << shift) - (prev_raw_count << shift);
+ delta >>= shift;
+
+ sdelta = rapl_scale(delta, event->hw.config);
+
+ local64_add(sdelta, &event->count);
+
+ return new_raw_count;
+}
+
+static void rapl_start_hrtimer(struct rapl_pmu *pmu)
+{
+ hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
+ HRTIMER_MODE_REL_PINNED);
+}
+
+static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
+{
+ struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer);
+ struct perf_event *event;
+ unsigned long flags;
+
+ if (!pmu->n_active)
+ return HRTIMER_NORESTART;
+
+ raw_spin_lock_irqsave(&pmu->lock, flags);
+
+ list_for_each_entry(event, &pmu->active_list, active_entry)
+ rapl_event_update(event);
+
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
+
+ hrtimer_forward_now(hrtimer, pmu->timer_interval);
+
+ return HRTIMER_RESTART;
+}
+
+static void rapl_hrtimer_init(struct rapl_pmu *pmu)
+{
+ struct hrtimer *hr = &pmu->hrtimer;
+
+ hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hr->function = rapl_hrtimer_handle;
+}
+
+static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
+ struct perf_event *event)
+{
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ event->hw.state = 0;
+
+ list_add_tail(&event->active_entry, &pmu->active_list);
+
+ local64_set(&event->hw.prev_count, rapl_read_counter(event));
+
+ pmu->n_active++;
+ if (pmu->n_active == 1)
+ rapl_start_hrtimer(pmu);
+}
+
+static void rapl_pmu_event_start(struct perf_event *event, int mode)
+{
+ struct rapl_pmu *pmu = event->pmu_private;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&pmu->lock, flags);
+ __rapl_pmu_event_start(pmu, event);
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static void rapl_pmu_event_stop(struct perf_event *event, int mode)
+{
+ struct rapl_pmu *pmu = event->pmu_private;
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&pmu->lock, flags);
+
+ /* mark event as deactivated and stopped */
+ if (!(hwc->state & PERF_HES_STOPPED)) {
+ WARN_ON_ONCE(pmu->n_active <= 0);
+ pmu->n_active--;
+ if (pmu->n_active == 0)
+ hrtimer_cancel(&pmu->hrtimer);
+
+ list_del(&event->active_entry);
+
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+ }
+
+ /* check if update of sw counter is necessary */
+ if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+ /*
+ * Drain the remaining delta count out of a event
+ * that we are disabling:
+ */
+ rapl_event_update(event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static int rapl_pmu_event_add(struct perf_event *event, int mode)
+{
+ struct rapl_pmu *pmu = event->pmu_private;
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&pmu->lock, flags);
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+ if (mode & PERF_EF_START)
+ __rapl_pmu_event_start(pmu, event);
+
+ raw_spin_unlock_irqrestore(&pmu->lock, flags);
+
+ return 0;
+}
+
+static void rapl_pmu_event_del(struct perf_event *event, int flags)
+{
+ rapl_pmu_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int rapl_pmu_event_init(struct perf_event *event)
+{
+ u64 cfg = event->attr.config & RAPL_EVENT_MASK;
+ int bit, ret = 0;
+ struct rapl_pmu *pmu;
+
+ /* only look at RAPL events */
+ if (event->attr.type != rapl_pmus->pmu.type)
+ return -ENOENT;
+
+ /* check only supported bits are set */
+ if (event->attr.config & ~RAPL_EVENT_MASK)
+ return -EINVAL;
+
+ if (event->cpu < 0)
+ return -EINVAL;
+
+ event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
+ if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
+ return -EINVAL;
+
+ cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
+ bit = cfg - 1;
+
+ /* check event supported */
+ if (!(rapl_cntr_mask & (1 << bit)))
+ return -EINVAL;
+
+ /* unsupported modes and filters */
+ if (event->attr.sample_period) /* no sampling */
+ return -EINVAL;
+
+ /* must be done before validate_group */
+ pmu = cpu_to_rapl_pmu(event->cpu);
+ if (!pmu)
+ return -EINVAL;
+ event->cpu = pmu->cpu;
+ event->pmu_private = pmu;
+ event->hw.event_base = rapl_msrs[bit].msr;
+ event->hw.config = cfg;
+ event->hw.idx = bit;
+
+ return ret;
+}
+
+static void rapl_pmu_event_read(struct perf_event *event)
+{
+ rapl_event_update(event);
+}
+
+static ssize_t rapl_get_attr_cpumask(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask);
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
+
+static struct attribute *rapl_pmu_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL,
+};
+
+static struct attribute_group rapl_pmu_attr_group = {
+ .attrs = rapl_pmu_attrs,
+};
+
+RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
+RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
+RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04");
+RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05");
+
+RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules");
+
+/*
+ * we compute in 0.23 nJ increments regardless of MSR
+ */
+RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10");
+
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
+static struct attribute *attrs_empty[] = {
+ NULL,
+};
+
+static struct attribute_group rapl_pmu_events_group = {
+ .name = "events",
+ .attrs = attrs_empty,
+};
+
+DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+static struct attribute *rapl_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group rapl_pmu_format_group = {
+ .name = "format",
+ .attrs = rapl_formats_attr,
+};
+
+static const struct attribute_group *rapl_attr_groups[] = {
+ &rapl_pmu_attr_group,
+ &rapl_pmu_format_group,
+ &rapl_pmu_events_group,
+ NULL,
+};
+
+static struct attribute *rapl_events_cores[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_cores_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_cores_group = {
+ .name = "events",
+ .attrs = rapl_events_cores,
+};
+
+static struct attribute *rapl_events_pkg[] = {
+ EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_pkg_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_pkg_group = {
+ .name = "events",
+ .attrs = rapl_events_pkg,
+};
+
+static struct attribute *rapl_events_ram[] = {
+ EVENT_PTR(rapl_ram),
+ EVENT_PTR(rapl_ram_unit),
+ EVENT_PTR(rapl_ram_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_ram_group = {
+ .name = "events",
+ .attrs = rapl_events_ram,
+};
+
+static struct attribute *rapl_events_gpu[] = {
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_gpu_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_gpu_group = {
+ .name = "events",
+ .attrs = rapl_events_gpu,
+};
+
+static struct attribute *rapl_events_psys[] = {
+ EVENT_PTR(rapl_psys),
+ EVENT_PTR(rapl_psys_unit),
+ EVENT_PTR(rapl_psys_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_psys_group = {
+ .name = "events",
+ .attrs = rapl_events_psys,
+};
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr rapl_msrs[] = {
+ [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr },
+ [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
+ [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr },
+ [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr },
+ [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr },
+};
+
+static int rapl_cpu_offline(unsigned int cpu)
+{
+ struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
+ int target;
+
+ /* Check if exiting cpu is used for collecting rapl events */
+ if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask))
+ return 0;
+
+ pmu->cpu = -1;
+ /* Find a new cpu to collect rapl events */
+ target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
+
+ /* Migrate rapl events to the new target */
+ if (target < nr_cpu_ids) {
+ cpumask_set_cpu(target, &rapl_cpu_mask);
+ pmu->cpu = target;
+ perf_pmu_migrate_context(pmu->pmu, cpu, target);
+ }
+ return 0;
+}
+
+static int rapl_cpu_online(unsigned int cpu)
+{
+ struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
+ int target;
+
+ if (!pmu) {
+ pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+ if (!pmu)
+ return -ENOMEM;
+
+ raw_spin_lock_init(&pmu->lock);
+ INIT_LIST_HEAD(&pmu->active_list);
+ pmu->pmu = &rapl_pmus->pmu;
+ pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+ rapl_hrtimer_init(pmu);
+
+ rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
+ }
+
+ /*
+ * Check if there is an online cpu in the package which collects rapl
+ * events already.
+ */
+ target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
+ if (target < nr_cpu_ids)
+ return 0;
+
+ cpumask_set_cpu(cpu, &rapl_cpu_mask);
+ pmu->cpu = cpu;
+ return 0;
+}
+
+static int rapl_check_hw_unit(bool apply_quirk)
+{
+ u64 msr_rapl_power_unit_bits;
+ int i;
+
+ /* protect rdmsrl() to handle virtualization */
+ if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+ return -1;
+ for (i = 0; i < NR_RAPL_DOMAINS; i++)
+ rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
+
+ /*
+ * DRAM domain on HSW server and KNL has fixed energy unit which can be
+ * different than the unit from power unit MSR. See
+ * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
+ * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
+ */
+ if (apply_quirk)
+ rapl_hw_unit[PERF_RAPL_RAM] = 16;
+
+ /*
+ * Calculate the timer rate:
+ * Use reference of 200W for scaling the timeout to avoid counter
+ * overflows. 200W = 200 Joules/sec
+ * Divide interval by 2 to avoid lockstep (2 * 100)
+ * if hw unit is 32, then we use 2 ms 1/200/2
+ */
+ rapl_timer_ms = 2;
+ if (rapl_hw_unit[0] < 32) {
+ rapl_timer_ms = (1000 / (2 * 100));
+ rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1));
+ }
+ return 0;
+}
+
+static void __init rapl_advertise(void)
+{
+ int i;
+
+ pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n",
+ hweight32(rapl_cntr_mask), rapl_timer_ms);
+
+ for (i = 0; i < NR_RAPL_DOMAINS; i++) {
+ if (rapl_cntr_mask & (1 << i)) {
+ pr_info("hw unit of domain %s 2^-%d Joules\n",
+ rapl_domain_names[i], rapl_hw_unit[i]);
+ }
+ }
+}
+
+static void cleanup_rapl_pmus(void)
+{
+ int i;
+
+ for (i = 0; i < rapl_pmus->maxdie; i++)
+ kfree(rapl_pmus->pmus[i]);
+ kfree(rapl_pmus);
+}
+
+static const struct attribute_group *rapl_attr_update[] = {
+ &rapl_events_cores_group,
+ &rapl_events_pkg_group,
+ &rapl_events_ram_group,
+ &rapl_events_gpu_group,
+ &rapl_events_gpu_group,
+ NULL,
+};
+
+static int __init init_rapl_pmus(void)
+{
+ int maxdie = topology_max_packages() * topology_max_die_per_package();
+ size_t size;
+
+ size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
+ rapl_pmus = kzalloc(size, GFP_KERNEL);
+ if (!rapl_pmus)
+ return -ENOMEM;
+
+ rapl_pmus->maxdie = maxdie;
+ rapl_pmus->pmu.attr_groups = rapl_attr_groups;
+ rapl_pmus->pmu.attr_update = rapl_attr_update;
+ rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
+ rapl_pmus->pmu.event_init = rapl_pmu_event_init;
+ rapl_pmus->pmu.add = rapl_pmu_event_add;
+ rapl_pmus->pmu.del = rapl_pmu_event_del;
+ rapl_pmus->pmu.start = rapl_pmu_event_start;
+ rapl_pmus->pmu.stop = rapl_pmu_event_stop;
+ rapl_pmus->pmu.read = rapl_pmu_event_read;
+ rapl_pmus->pmu.module = THIS_MODULE;
+ rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE;
+ return 0;
+}
+
+#define X86_RAPL_MODEL_MATCH(model, init) \
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
+
+static struct rapl_model model_snb = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
+};
+
+static struct rapl_model model_snbep = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = false,
+};
+
+static struct rapl_model model_hsw = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
+};
+
+static struct rapl_model model_hsx = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
+};
+
+static struct rapl_model model_knl = {
+ .events = BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
+};
+
+static struct rapl_model model_skl = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1) |
+ BIT(PERF_RAPL_PSYS),
+ .apply_quirk = false,
+};
+
+static const struct x86_cpu_id rapl_model_match[] __initconst = {
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_L, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_G, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_D, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE, model_skl),
+ {},
+};
+
+MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
+
+static int __init rapl_pmu_init(void)
+{
+ const struct x86_cpu_id *id;
+ struct rapl_model *rm;
+ int ret;
+
+ id = x86_match_cpu(rapl_model_match);
+ if (!id)
+ return -ENODEV;
+
+ rm = (struct rapl_model *) id->driver_data;
+ rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
+ false, (void *) &rm->events);
+
+ ret = rapl_check_hw_unit(rm->apply_quirk);
+ if (ret)
+ return ret;
+
+ ret = init_rapl_pmus();
+ if (ret)
+ return ret;
+
+ /*
+ * Install callbacks. Core will call them for each online cpu.
+ */
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
+ "perf/x86/rapl:online",
+ rapl_cpu_online, rapl_cpu_offline);
+ if (ret)
+ goto out;
+
+ ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
+ if (ret)
+ goto out1;
+
+ rapl_advertise();
+ return 0;
+
+out1:
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
+out:
+ pr_warn("Initialization failed (%d), disabled\n", ret);
+ cleanup_rapl_pmus();
+ return ret;
+}
+module_init(rapl_pmu_init);
+
+static void __exit intel_rapl_exit(void)
+{
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
+ perf_pmu_unregister(&rapl_pmus->pmu);
+ cleanup_rapl_pmus();
+}
+module_exit(intel_rapl_exit);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 54f5d54280f6..a07dfdf7759e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -334,7 +334,7 @@ struct x86_hw_tss {
#define INVALID_IO_BITMAP_OFFSET 0x8000

struct entry_stack {
- unsigned long words[64];
+ char stack[PAGE_SIZE];
};

struct entry_stack_page {
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 1cc6c47dc77e..341f58a01de0 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -7,7 +7,7 @@
#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
#define KVM_POSSIBLE_CR4_GUEST_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)

#define BUILD_KVM_GPR_ACCESSORS(lname, uname) \
static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index aab02ea2d2cb..342d9ddf35c3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4580,7 +4580,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
rsvd_bits(maxphyaddr, 51);
rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
- nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+ gbpages_bit_rsvd |
rsvd_bits(maxphyaddr, 51);
rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 10e6471896cd..3be65495aeb8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3913,6 +3913,8 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)

void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
{
+ BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS);
+
vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
if (enable_ept)
vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eed1866ae4d3..38b2df0e7109 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -980,6 +980,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
if (is_long_mode(vcpu)) {
if (!(cr4 & X86_CR4_PAE))
return 1;
+ if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+ return 1;
} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
&& ((cr4 ^ old_cr4) & pdptr_bits)
&& !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index ae07dd78e951..c9dc2b17ce25 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -24,6 +24,18 @@ void blk_flush_integrity(void)
flush_workqueue(kintegrityd_wq);
}

+void __bio_integrity_free(struct bio_set *bs, struct bio_integrity_payload *bip)
+{
+ if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
+ if (bip->bip_vec)
+ bvec_free(&bs->bvec_integrity_pool, bip->bip_vec,
+ bip->bip_slab);
+ mempool_free(bip, &bs->bio_integrity_pool);
+ } else {
+ kfree(bip);
+ }
+}
+
/**
* bio_integrity_alloc - Allocate integrity payload and attach it to bio
* @bio: bio to attach integrity metadata to
@@ -75,7 +87,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,

return bip;
err:
- mempool_free(bip, &bs->bio_integrity_pool);
+ __bio_integrity_free(bs, bip);
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(bio_integrity_alloc);
@@ -96,14 +108,7 @@ void bio_integrity_free(struct bio *bio)
kfree(page_address(bip->bip_vec->bv_page) +
bip->bip_vec->bv_offset);

- if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
- bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
-
- mempool_free(bip, &bs->bio_integrity_pool);
- } else {
- kfree(bip);
- }
-
+ __bio_integrity_free(bs, bip);
bio->bi_integrity = NULL;
bio->bi_opf &= ~REQ_INTEGRITY;
}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f1b930a300a3..ae7d31cb5a4e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -829,10 +829,10 @@ static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
void *priv, bool reserved)
{
/*
- * If we find a request that is inflight and the queue matches,
+ * If we find a request that isn't idle and the queue matches,
* we know the queue is busy. Return false to stop the iteration.
*/
- if (rq->state == MQ_RQ_IN_FLIGHT && rq->q == hctx->queue) {
+ if (blk_mq_request_started(rq) && rq->q == hctx->queue) {
bool *busy = priv;

*busy = true;
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 508bbd6ea439..320d23de02c2 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -17,6 +17,7 @@
#include <linux/delay.h>
#include <linux/log2.h>
#include <linux/hwspinlock.h>
+#include <asm/unaligned.h>

#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -249,22 +250,20 @@ static void regmap_format_8(void *buf, unsigned int val, unsigned int shift)

static void regmap_format_16_be(void *buf, unsigned int val, unsigned int shift)
{
- __be16 *b = buf;
-
- b[0] = cpu_to_be16(val << shift);
+ put_unaligned_be16(val << shift, buf);
}

static void regmap_format_16_le(void *buf, unsigned int val, unsigned int shift)
{
- __le16 *b = buf;
-
- b[0] = cpu_to_le16(val << shift);
+ put_unaligned_le16(val << shift, buf);
}

static void regmap_format_16_native(void *buf, unsigned int val,
unsigned int shift)
{
- *(u16 *)buf = val << shift;
+ u16 v = val << shift;
+
+ memcpy(buf, &v, sizeof(v));
}

static void regmap_format_24(void *buf, unsigned int val, unsigned int shift)
@@ -280,43 +279,39 @@ static void regmap_format_24(void *buf, unsigned int val, unsigned int shift)

static void regmap_format_32_be(void *buf, unsigned int val, unsigned int shift)
{
- __be32 *b = buf;
-
- b[0] = cpu_to_be32(val << shift);
+ put_unaligned_be32(val << shift, buf);
}

static void regmap_format_32_le(void *buf, unsigned int val, unsigned int shift)
{
- __le32 *b = buf;
-
- b[0] = cpu_to_le32(val << shift);
+ put_unaligned_le32(val << shift, buf);
}

static void regmap_format_32_native(void *buf, unsigned int val,
unsigned int shift)
{
- *(u32 *)buf = val << shift;
+ u32 v = val << shift;
+
+ memcpy(buf, &v, sizeof(v));
}

#ifdef CONFIG_64BIT
static void regmap_format_64_be(void *buf, unsigned int val, unsigned int shift)
{
- __be64 *b = buf;
-
- b[0] = cpu_to_be64((u64)val << shift);
+ put_unaligned_be64((u64) val << shift, buf);
}

static void regmap_format_64_le(void *buf, unsigned int val, unsigned int shift)
{
- __le64 *b = buf;
-
- b[0] = cpu_to_le64((u64)val << shift);
+ put_unaligned_le64((u64) val << shift, buf);
}

static void regmap_format_64_native(void *buf, unsigned int val,
unsigned int shift)
{
- *(u64 *)buf = (u64)val << shift;
+ u64 v = (u64) val << shift;
+
+ memcpy(buf, &v, sizeof(v));
}
#endif

@@ -333,35 +328,34 @@ static unsigned int regmap_parse_8(const void *buf)

static unsigned int regmap_parse_16_be(const void *buf)
{
- const __be16 *b = buf;
-
- return be16_to_cpu(b[0]);
+ return get_unaligned_be16(buf);
}

static unsigned int regmap_parse_16_le(const void *buf)
{
- const __le16 *b = buf;
-
- return le16_to_cpu(b[0]);
+ return get_unaligned_le16(buf);
}

static void regmap_parse_16_be_inplace(void *buf)
{
- __be16 *b = buf;
+ u16 v = get_unaligned_be16(buf);

- b[0] = be16_to_cpu(b[0]);
+ memcpy(buf, &v, sizeof(v));
}

static void regmap_parse_16_le_inplace(void *buf)
{
- __le16 *b = buf;
+ u16 v = get_unaligned_le16(buf);

- b[0] = le16_to_cpu(b[0]);
+ memcpy(buf, &v, sizeof(v));
}

static unsigned int regmap_parse_16_native(const void *buf)
{
- return *(u16 *)buf;
+ u16 v;
+
+ memcpy(&v, buf, sizeof(v));
+ return v;
}

static unsigned int regmap_parse_24(const void *buf)
@@ -376,69 +370,67 @@ static unsigned int regmap_parse_24(const void *buf)

static unsigned int regmap_parse_32_be(const void *buf)
{
- const __be32 *b = buf;
-
- return be32_to_cpu(b[0]);
+ return get_unaligned_be32(buf);
}

static unsigned int regmap_parse_32_le(const void *buf)
{
- const __le32 *b = buf;
-
- return le32_to_cpu(b[0]);
+ return get_unaligned_le32(buf);
}

static void regmap_parse_32_be_inplace(void *buf)
{
- __be32 *b = buf;
+ u32 v = get_unaligned_be32(buf);

- b[0] = be32_to_cpu(b[0]);
+ memcpy(buf, &v, sizeof(v));
}

static void regmap_parse_32_le_inplace(void *buf)
{
- __le32 *b = buf;
+ u32 v = get_unaligned_le32(buf);

- b[0] = le32_to_cpu(b[0]);
+ memcpy(buf, &v, sizeof(v));
}

static unsigned int regmap_parse_32_native(const void *buf)
{
- return *(u32 *)buf;
+ u32 v;
+
+ memcpy(&v, buf, sizeof(v));
+ return v;
}

#ifdef CONFIG_64BIT
static unsigned int regmap_parse_64_be(const void *buf)
{
- const __be64 *b = buf;
-
- return be64_to_cpu(b[0]);
+ return get_unaligned_be64(buf);
}

static unsigned int regmap_parse_64_le(const void *buf)
{
- const __le64 *b = buf;
-
- return le64_to_cpu(b[0]);
+ return get_unaligned_le64(buf);
}

static void regmap_parse_64_be_inplace(void *buf)
{
- __be64 *b = buf;
+ u64 v = get_unaligned_be64(buf);

- b[0] = be64_to_cpu(b[0]);
+ memcpy(buf, &v, sizeof(v));
}

static void regmap_parse_64_le_inplace(void *buf)
{
- __le64 *b = buf;
+ u64 v = get_unaligned_le64(buf);

- b[0] = le64_to_cpu(b[0]);
+ memcpy(buf, &v, sizeof(v));
}

static unsigned int regmap_parse_64_native(const void *buf)
{
- return *(u64 *)buf;
+ u64 v;
+
+ memcpy(&v, buf, sizeof(v));
+ return v;
}
#endif

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 78181908f0df..7b61d53ba050 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1022,25 +1022,26 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
test_bit(NBD_RT_BOUND, &config->runtime_flags))) {
dev_err(disk_to_dev(nbd->disk),
"Device being setup by another task");
- sockfd_put(sock);
- return -EBUSY;
+ err = -EBUSY;
+ goto put_socket;
+ }
+
+ nsock = kzalloc(sizeof(*nsock), GFP_KERNEL);
+ if (!nsock) {
+ err = -ENOMEM;
+ goto put_socket;
}

socks = krealloc(config->socks, (config->num_connections + 1) *
sizeof(struct nbd_sock *), GFP_KERNEL);
if (!socks) {
- sockfd_put(sock);
- return -ENOMEM;
+ kfree(nsock);
+ err = -ENOMEM;
+ goto put_socket;
}

config->socks = socks;

- nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
- if (!nsock) {
- sockfd_put(sock);
- return -ENOMEM;
- }
-
nsock->fallback_index = -1;
nsock->dead = false;
mutex_init(&nsock->tx_lock);
@@ -1052,6 +1053,10 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
atomic_inc(&config->live_connections);

return 0;
+
+put_socket:
+ sockfd_put(sock);
+ return err;
}

static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 29ba26742c8f..81f5103dccb6 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -107,6 +107,84 @@ static const struct i2c_device_id pca953x_id[] = {
};
MODULE_DEVICE_TABLE(i2c, pca953x_id);

+#ifdef CONFIG_GPIO_PCA953X_IRQ
+
+#include <linux/dmi.h>
+#include <linux/gpio.h>
+#include <linux/list.h>
+
+static const struct dmi_system_id pca953x_dmi_acpi_irq_info[] = {
+ {
+ /*
+ * On Intel Galileo Gen 2 board the IRQ pin of one of
+ * the IÂC GPIO expanders, which has GpioInt() resource,
+ * is provided as an absolute number instead of being
+ * relative. Since first controller (gpio-sch.c) and
+ * second (gpio-dwapb.c) are at the fixed bases, we may
+ * safely refer to the number in the global space to get
+ * an IRQ out of it.
+ */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_BOARD_NAME, "GalileoGen2"),
+ },
+ },
+ {}
+};
+
+#ifdef CONFIG_ACPI
+static int pca953x_acpi_get_pin(struct acpi_resource *ares, void *data)
+{
+ struct acpi_resource_gpio *agpio;
+ int *pin = data;
+
+ if (acpi_gpio_get_irq_resource(ares, &agpio))
+ *pin = agpio->pin_table[0];
+ return 1;
+}
+
+static int pca953x_acpi_find_pin(struct device *dev)
+{
+ struct acpi_device *adev = ACPI_COMPANION(dev);
+ int pin = -ENOENT, ret;
+ LIST_HEAD(r);
+
+ ret = acpi_dev_get_resources(adev, &r, pca953x_acpi_get_pin, &pin);
+ acpi_dev_free_resource_list(&r);
+ if (ret < 0)
+ return ret;
+
+ return pin;
+}
+#else
+static inline int pca953x_acpi_find_pin(struct device *dev) { return -ENXIO; }
+#endif
+
+static int pca953x_acpi_get_irq(struct device *dev)
+{
+ int pin, ret;
+
+ pin = pca953x_acpi_find_pin(dev);
+ if (pin < 0)
+ return pin;
+
+ dev_info(dev, "Applying ACPI interrupt quirk (GPIO %d)\n", pin);
+
+ if (!gpio_is_valid(pin))
+ return -EINVAL;
+
+ ret = gpio_request(pin, "pca953x interrupt");
+ if (ret)
+ return ret;
+
+ ret = gpio_to_irq(pin);
+
+ /* When pin is used as an IRQ, no need to keep it requested */
+ gpio_free(pin);
+
+ return ret;
+}
+#endif
+
static const struct acpi_device_id pca953x_acpi_ids[] = {
{ "INT3491", 16 | PCA953X_TYPE | PCA_LATCH_INT, },
{ }
@@ -772,6 +850,12 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
u8 reg_direction[MAX_BANK];
int ret, i;

+ if (dmi_first_match(pca953x_dmi_acpi_irq_info)) {
+ ret = pca953x_acpi_get_irq(&client->dev);
+ if (ret > 0)
+ client->irq = ret;
+ }
+
if (!client->irq)
return 0;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 96b2a31ccfed..f06a5142d66e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -36,7 +36,8 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)

memset(&ti, 0, sizeof(struct amdgpu_task_info));

- if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
+ if (amdgpu_gpu_recovery &&
+ amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
DRM_ERROR("ring %s timeout, but soft recovered\n",
s_job->sched->name);
return;
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index ffd95bfeaa94..d00ea384dcbf 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -30,12 +30,6 @@ struct drm_dmi_panel_orientation_data {
int orientation;
};

-static const struct drm_dmi_panel_orientation_data acer_s1003 = {
- .width = 800,
- .height = 1280,
- .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
-};
-
static const struct drm_dmi_panel_orientation_data asus_t100ha = {
.width = 800,
.height = 1280,
@@ -114,13 +108,19 @@ static const struct dmi_system_id orientation_data[] = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"),
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"),
},
- .driver_data = (void *)&acer_s1003,
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /* Asus T100HA */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100HAN"),
},
.driver_data = (void *)&asus_t100ha,
+ }, { /* Asus T101HA */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+ },
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /* GPD MicroPC (generic strings, also match on bios date) */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),
diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c
index 5649887d2b90..16e5fb9ec784 100644
--- a/drivers/gpu/drm/mcde/mcde_drv.c
+++ b/drivers/gpu/drm/mcde/mcde_drv.c
@@ -215,7 +215,6 @@ static int mcde_modeset_init(struct drm_device *drm)

drm_mode_config_reset(drm);
drm_kms_helper_poll_init(drm);
- drm_fbdev_generic_setup(drm, 32);

return 0;

@@ -282,6 +281,8 @@ static int mcde_drm_bind(struct device *dev)
if (ret < 0)
goto unbind;

+ drm_fbdev_generic_setup(drm, 32);
+
return 0;

unbind:
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 584a9ecadce6..b7592b16ea94 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -101,6 +101,16 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
true, true);
}

+static void mtk_plane_atomic_disable(struct drm_plane *plane,
+ struct drm_plane_state *old_state)
+{
+ struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
+
+ state->pending.enable = false;
+ wmb(); /* Make sure the above parameter is set before update */
+ state->pending.dirty = true;
+}
+
static void mtk_plane_atomic_update(struct drm_plane *plane,
struct drm_plane_state *old_state)
{
@@ -115,6 +125,11 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
if (!crtc || WARN_ON(!fb))
return;

+ if (!plane->state->visible) {
+ mtk_plane_atomic_disable(plane, old_state);
+ return;
+ }
+
gem = fb->obj[0];
mtk_gem = to_mtk_gem_obj(gem);
addr = mtk_gem->dma_addr;
@@ -136,16 +151,6 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
state->pending.dirty = true;
}

-static void mtk_plane_atomic_disable(struct drm_plane *plane,
- struct drm_plane_state *old_state)
-{
- struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
-
- state->pending.enable = false;
- wmb(); /* Make sure the above parameter is set before update */
- state->pending.dirty = true;
-}
-
static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
.prepare_fb = drm_gem_fb_prepare_fb,
.atomic_check = mtk_plane_atomic_check,
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index c6fd123f60b5..f9685cce1652 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5578,6 +5578,7 @@ static int ci_parse_power_table(struct radeon_device *rdev)
if (!rdev->pm.dpm.ps)
return -ENOMEM;
power_state_offset = (u8 *)state_array->states;
+ rdev->pm.dpm.num_ps = 0;
for (i = 0; i < state_array->ucNumEntries; i++) {
u8 *idx;
power_state = (union pplib_power_state *)power_state_offset;
@@ -5587,10 +5588,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
if (!rdev->pm.power_state[i].clock_info)
return -EINVAL;
ps = kzalloc(sizeof(struct ci_ps), GFP_KERNEL);
- if (ps == NULL) {
- kfree(rdev->pm.dpm.ps);
+ if (ps == NULL)
return -ENOMEM;
- }
rdev->pm.dpm.ps[i].ps_priv = ps;
ci_parse_pplib_non_clock_info(rdev, &rdev->pm.dpm.ps[i],
non_clock_info,
@@ -5612,8 +5611,8 @@ static int ci_parse_power_table(struct radeon_device *rdev)
k++;
}
power_state_offset += 2 + power_state->v2.ucNumDPMLevels;
+ rdev->pm.dpm.num_ps = i + 1;
}
- rdev->pm.dpm.num_ps = state_array->ucNumEntries;

/* fill in the vce power states */
for (i = 0; i < RADEON_MAX_VCE_LEVELS; i++) {
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index 839b49c40e51..767fb440a79d 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -141,7 +141,9 @@ int tegra_display_hub_prepare(struct tegra_display_hub *hub)
for (i = 0; i < hub->soc->num_wgrps; i++) {
struct tegra_windowgroup *wgrp = &hub->wgrps[i];

- tegra_windowgroup_enable(wgrp);
+ /* Skip orphaned window group whose parent DC is disabled */
+ if (wgrp->parent)
+ tegra_windowgroup_enable(wgrp);
}

return 0;
@@ -158,7 +160,9 @@ void tegra_display_hub_cleanup(struct tegra_display_hub *hub)
for (i = 0; i < hub->soc->num_wgrps; i++) {
struct tegra_windowgroup *wgrp = &hub->wgrps[i];

- tegra_windowgroup_disable(wgrp);
+ /* Skip orphaned window group whose parent DC is disabled */
+ if (wgrp->parent)
+ tegra_windowgroup_disable(wgrp);
}
}

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index abf165b2f64f..3ce8ad7603c7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -941,8 +941,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
if (!fence)
return 0;

- if (no_wait_gpu)
+ if (no_wait_gpu) {
+ dma_fence_put(fence);
return -EBUSY;
+ }

dma_resv_add_shared_fence(bo->base.resv, fence);

diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 742aa9ff21b8..fcda8621ae6f 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -686,8 +686,17 @@ EXPORT_SYMBOL(host1x_driver_register_full);
*/
void host1x_driver_unregister(struct host1x_driver *driver)
{
+ struct host1x *host1x;
+
driver_unregister(&driver->driver);

+ mutex_lock(&devices_lock);
+
+ list_for_each_entry(host1x, &devices, list)
+ host1x_detach_driver(host1x, driver);
+
+ mutex_unlock(&devices_lock);
+
mutex_lock(&drivers_lock);
list_del_init(&driver->list);
mutex_unlock(&drivers_lock);
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index bddb5434fbed..d2d70c89193f 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -829,13 +829,20 @@ static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask)
return len;
}

-static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
+static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
{
struct sk_buff *skb = NULL;
struct nlmsghdr *nlh;
void *data;
struct ib_sa_mad *mad;
int len;
+ unsigned long flags;
+ unsigned long delay;
+ gfp_t gfp_flag;
+ int ret;
+
+ INIT_LIST_HEAD(&query->list);
+ query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);

mad = query->mad_buf->mad;
len = ib_nl_get_path_rec_attrs_len(mad->sa_hdr.comp_mask);
@@ -860,36 +867,25 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
/* Repair the nlmsg header length */
nlmsg_end(skb, nlh);

- return rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_mask);
-}
+ gfp_flag = ((gfp_mask & GFP_ATOMIC) == GFP_ATOMIC) ? GFP_ATOMIC :
+ GFP_NOWAIT;

-static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
-{
- unsigned long flags;
- unsigned long delay;
- int ret;
+ spin_lock_irqsave(&ib_nl_request_lock, flags);
+ ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_flag);

- INIT_LIST_HEAD(&query->list);
- query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);
+ if (ret)
+ goto out;

- /* Put the request on the list first.*/
- spin_lock_irqsave(&ib_nl_request_lock, flags);
+ /* Put the request on the list.*/
delay = msecs_to_jiffies(sa_local_svc_timeout_ms);
query->timeout = delay + jiffies;
list_add_tail(&query->list, &ib_nl_request_list);
/* Start the timeout if this is the only request */
if (ib_nl_request_list.next == &query->list)
queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);
- spin_unlock_irqrestore(&ib_nl_request_lock, flags);

- ret = ib_nl_send_msg(query, gfp_mask);
- if (ret) {
- ret = -EIO;
- /* Remove the request */
- spin_lock_irqsave(&ib_nl_request_lock, flags);
- list_del(&query->list);
- spin_unlock_irqrestore(&ib_nl_request_lock, flags);
- }
+out:
+ spin_unlock_irqrestore(&ib_nl_request_lock, flags);

return ret;
}
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 26b792bb1027..fbff6b2f00e7 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -844,6 +844,29 @@ static int create_workqueues(struct hfi1_devdata *dd)
return -ENOMEM;
}

+/**
+ * destroy_workqueues - destroy per port workqueues
+ * @dd: the hfi1_ib device
+ */
+static void destroy_workqueues(struct hfi1_devdata *dd)
+{
+ int pidx;
+ struct hfi1_pportdata *ppd;
+
+ for (pidx = 0; pidx < dd->num_pports; ++pidx) {
+ ppd = dd->pport + pidx;
+
+ if (ppd->hfi1_wq) {
+ destroy_workqueue(ppd->hfi1_wq);
+ ppd->hfi1_wq = NULL;
+ }
+ if (ppd->link_wq) {
+ destroy_workqueue(ppd->link_wq);
+ ppd->link_wq = NULL;
+ }
+ }
+}
+
/**
* enable_general_intr() - Enable the IRQs that will be handled by the
* general interrupt handler.
@@ -1117,15 +1140,10 @@ static void shutdown_device(struct hfi1_devdata *dd)
* We can't count on interrupts since we are stopping.
*/
hfi1_quiet_serdes(ppd);
-
- if (ppd->hfi1_wq) {
- destroy_workqueue(ppd->hfi1_wq);
- ppd->hfi1_wq = NULL;
- }
- if (ppd->link_wq) {
- destroy_workqueue(ppd->link_wq);
- ppd->link_wq = NULL;
- }
+ if (ppd->hfi1_wq)
+ flush_workqueue(ppd->hfi1_wq);
+ if (ppd->link_wq)
+ flush_workqueue(ppd->link_wq);
}
sdma_exit(dd);
}
@@ -1814,6 +1832,7 @@ static void remove_one(struct pci_dev *pdev)
* clear dma engines, etc.
*/
shutdown_device(dd);
+ destroy_workqueues(dd);

stop_timers(dd);

diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index f8e733aa3bb8..acd4400b0092 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -381,7 +381,10 @@ bool _hfi1_schedule_send(struct rvt_qp *qp)
struct hfi1_ibport *ibp =
to_iport(qp->ibqp.device, qp->port_num);
struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
- struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
+ struct hfi1_devdata *dd = ppd->dd;
+
+ if (dd->flags & HFI1_SHUTDOWN)
+ return true;

return iowait_schedule(&priv->s_iowait, ppd->hfi1_wq,
priv->s_sde ?
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index 8a2e0d9351e9..7c6fd720fb2e 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -5406,7 +5406,10 @@ static bool _hfi1_schedule_tid_send(struct rvt_qp *qp)
struct hfi1_ibport *ibp =
to_iport(qp->ibqp.device, qp->port_num);
struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
- struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
+ struct hfi1_devdata *dd = ppd->dd;
+
+ if ((dd->flags & HFI1_SHUTDOWN))
+ return true;

return iowait_tid_schedule(&priv->s_iowait, ppd->hfi1_wq,
priv->s_sde ?
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 4f44a731a48e..b781ad74e6de 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -517,7 +517,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
mdev_port_num);
if (err)
goto out;
- ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet);
+ ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability);
eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);

props->active_width = IB_WIDTH_4X;
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index 130b1e31b978..fb66d6757278 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -66,12 +66,13 @@ static int siw_device_register(struct siw_device *sdev, const char *name)
static int dev_id = 1;
int rv;

+ sdev->vendor_part_id = dev_id++;
+
rv = ib_register_device(base_dev, name);
if (rv) {
pr_warn("siw: device registration error %d\n", rv);
return rv;
}
- sdev->vendor_part_id = dev_id++;

siw_dbg(base_dev, "HWaddr=%pM\n", sdev->netdev->dev_addr);

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6366b5fbb3a4..cdc1f4736a11 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5962,6 +5962,23 @@ static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
}

+/*
+ * Check that the device does not live on an external facing PCI port that is
+ * marked as untrusted. Such devices should not be able to apply quirks and
+ * thus not be able to bypass the IOMMU restrictions.
+ */
+static bool risky_device(struct pci_dev *pdev)
+{
+ if (pdev->untrusted) {
+ pci_info(pdev,
+ "Skipping IOMMU quirk for dev [%04X:%04X] on untrusted PCI link\n",
+ pdev->vendor, pdev->device);
+ pci_info(pdev, "Please check with your BIOS/Platform vendor about this\n");
+ return true;
+ }
+ return false;
+}
+
const struct iommu_ops intel_iommu_ops = {
.capable = intel_iommu_capable,
.domain_alloc = intel_iommu_domain_alloc,
@@ -5990,6 +6007,9 @@ const struct iommu_ops intel_iommu_ops = {

static void quirk_iommu_igfx(struct pci_dev *dev)
{
+ if (risky_device(dev))
+ return;
+
pci_info(dev, "Disabling IOMMU for graphics on this chipset\n");
dmar_map_gfx = 0;
}
@@ -6031,6 +6051,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx);

static void quirk_iommu_rwbf(struct pci_dev *dev)
{
+ if (risky_device(dev))
+ return;
+
/*
* Mobile 4 Series Chipset neglects to set RWBF capability,
* but needs it. Same seems to hold for the desktop versions.
@@ -6061,6 +6084,9 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
{
unsigned short ggc;

+ if (risky_device(dev))
+ return;
+
if (pci_read_config_word(dev, GGC, &ggc))
return;

@@ -6094,6 +6120,12 @@ static void __init check_tylersburg_isoch(void)
pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL);
if (!pdev)
return;
+
+ if (risky_device(pdev)) {
+ pci_dev_put(pdev);
+ return;
+ }
+
pci_dev_put(pdev);

/* System Management Registers. Might be hidden, in which case
@@ -6103,6 +6135,11 @@ static void __init check_tylersburg_isoch(void)
if (!pdev)
return;

+ if (risky_device(pdev)) {
+ pci_dev_put(pdev);
+ return;
+ }
+
if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) {
pci_dev_put(pdev);
return;
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 67eb4e972cc3..ed2f711c24c4 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -2104,6 +2104,12 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
}

if (WC_MODE_PMEM(wc)) {
+ if (!dax_synchronous(wc->ssd_dev->dax_dev)) {
+ r = -EOPNOTSUPP;
+ ti->error = "Asynchronous persistent memory not supported as pmem cache";
+ goto bad;
+ }
+
r = persistent_memory_claim(wc);
if (r) {
ti->error = "Unable to map persistent memory for cache";
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1e6e0c970e19..915019ec0e25 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -12,6 +12,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
@@ -2886,17 +2887,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast);
int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
unsigned cookie)
{
+ int r;
+ unsigned noio_flag;
char udev_cookie[DM_COOKIE_LENGTH];
char *envp[] = { udev_cookie, NULL };

+ noio_flag = memalloc_noio_save();
+
if (!cookie)
- return kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
+ r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
else {
snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u",
DM_COOKIE_ENV_VAR_NAME, cookie);
- return kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
- action, envp);
+ r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
+ action, envp);
}
+
+ memalloc_noio_restore(noio_flag);
+
+ return r;
}

uint32_t dm_next_uevent_seq(struct mapped_device *md)
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index f0737c57ed5f..1491561d2e5c 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -118,8 +118,6 @@ int mptscsih_suspend(struct pci_dev *pdev, pm_message_t state);
int mptscsih_resume(struct pci_dev *pdev);
#endif

-#define SNS_LEN(scp) SCSI_SENSE_BUFFERSIZE
-

/*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
/*
@@ -2422,7 +2420,7 @@ mptscsih_copy_sense_data(struct scsi_cmnd *sc, MPT_SCSI_HOST *hd, MPT_FRAME_HDR
/* Copy the sense received into the scsi command block. */
req_index = le16_to_cpu(mf->u.frame.hwhdr.msgctxu.fld.req_idx);
sense_data = ((u8 *)ioc->sense_buf_pool + (req_index * MPT_SENSE_BUFFER_ALLOC));
- memcpy(sc->sense_buffer, sense_data, SNS_LEN(sc));
+ memcpy(sc->sense_buffer, sense_data, MPT_SENSE_BUFFER_ALLOC);

/* Log SMART data (asc = 0x5D, non-IM case only) if required.
*/
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index e712315c7e8d..545c3f2f8a06 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -1151,9 +1151,11 @@ static int meson_mmc_probe(struct platform_device *pdev)

mmc->caps |= MMC_CAP_CMD23;
if (host->dram_access_quirk) {
+ /* Limit segments to 1 due to low available sram memory */
+ mmc->max_segs = 1;
/* Limit to the available sram memory */
- mmc->max_segs = SD_EMMC_SRAM_DATA_BUF_LEN / mmc->max_blk_size;
- mmc->max_blk_count = mmc->max_segs;
+ mmc->max_blk_count = SD_EMMC_SRAM_DATA_BUF_LEN /
+ mmc->max_blk_size;
} else {
mmc->max_blk_count = CMD_CFG_LENGTH_MASK;
mmc->max_segs = SD_EMMC_DESC_BUF_LEN /
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 24a5e99f7fd5..84c4319e3b31 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1267,6 +1267,9 @@ static int ksz8795_switch_init(struct ksz_device *dev)
return -ENOMEM;
}

+ /* set the real number of ports */
+ dev->ds->num_ports = dev->port_cnt;
+
return 0;
}

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 50ffc63d6231..3afb596d8e43 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -1587,6 +1587,9 @@ static int ksz9477_switch_init(struct ksz_device *dev)
return -ENOMEM;
}

+ /* set the real number of ports */
+ dev->ds->num_ports = dev->port_cnt;
+
return 0;
}

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 1046b22220a3..452be9749827 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -398,6 +398,7 @@ static void bnxt_free_vf_resources(struct bnxt *bp)
}
}

+ bp->pf.active_vfs = 0;
kfree(bp->pf.vf);
bp->pf.vf = NULL;
}
@@ -833,7 +834,6 @@ void bnxt_sriov_disable(struct bnxt *bp)

bnxt_free_vf_resources(bp);

- bp->pf.active_vfs = 0;
/* Reclaim all resources for the PF. */
rtnl_lock();
bnxt_restore_pf_fw_resources(bp);
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 1ec19d9fab00..01ed4d4296db 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4260,7 +4260,7 @@ static int macb_probe(struct platform_device *pdev)
bp->wol = 0;
if (of_get_property(np, "magic-packet", NULL))
bp->wol |= MACB_WOL_HAS_MAGIC_PACKET;
- device_init_wakeup(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);
+ device_set_wakeup_capable(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);

spin_lock_init(&bp->lock);

@@ -4453,7 +4453,8 @@ static int __maybe_unused macb_suspend(struct device *dev)
netif_carrier_off(netdev);
if (bp->ptp_info)
bp->ptp_info->ptp_remove(netdev);
- pm_runtime_force_suspend(dev);
+ if (!device_may_wakeup(dev))
+ pm_runtime_force_suspend(dev);

return 0;
}
@@ -4468,7 +4469,8 @@ static int __maybe_unused macb_resume(struct device *dev)
if (!netif_running(netdev))
return 0;

- pm_runtime_force_resume(dev);
+ if (!device_may_wakeup(dev))
+ pm_runtime_force_resume(dev);

if (bp->wol & MACB_WOL_ENABLED) {
macb_writel(bp, IDR, MACB_BIT(WOL));
@@ -4507,7 +4509,7 @@ static int __maybe_unused macb_runtime_suspend(struct device *dev)
struct net_device *netdev = dev_get_drvdata(dev);
struct macb *bp = netdev_priv(netdev);

- if (!(device_may_wakeup(&bp->dev->dev))) {
+ if (!(device_may_wakeup(dev))) {
clk_disable_unprepare(bp->tx_clk);
clk_disable_unprepare(bp->hclk);
clk_disable_unprepare(bp->pclk);
@@ -4523,7 +4525,7 @@ static int __maybe_unused macb_runtime_resume(struct device *dev)
struct net_device *netdev = dev_get_drvdata(dev);
struct macb *bp = netdev_priv(netdev);

- if (!(device_may_wakeup(&bp->dev->dev))) {
+ if (!(device_may_wakeup(dev))) {
clk_prepare_enable(bp->pclk);
clk_prepare_enable(bp->hclk);
clk_prepare_enable(bp->tx_clk);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 375e1be6a2d8..f459313357c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -839,16 +839,16 @@ static bool is_addr_all_mask(u8 *ipmask, int family)
struct in_addr *addr;

addr = (struct in_addr *)ipmask;
- if (ntohl(addr->s_addr) == 0xffffffff)
+ if (addr->s_addr == htonl(0xffffffff))
return true;
} else if (family == AF_INET6) {
struct in6_addr *addr6;

addr6 = (struct in6_addr *)ipmask;
- if (ntohl(addr6->s6_addr32[0]) == 0xffffffff &&
- ntohl(addr6->s6_addr32[1]) == 0xffffffff &&
- ntohl(addr6->s6_addr32[2]) == 0xffffffff &&
- ntohl(addr6->s6_addr32[3]) == 0xffffffff)
+ if (addr6->s6_addr32[0] == htonl(0xffffffff) &&
+ addr6->s6_addr32[1] == htonl(0xffffffff) &&
+ addr6->s6_addr32[2] == htonl(0xffffffff) &&
+ addr6->s6_addr32[3] == htonl(0xffffffff))
return true;
}
return false;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 31fcfc58e337..588b63473c47 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3499,7 +3499,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
drv_fw = &fw_info->fw_hdr;

/* Read the header of the firmware on the card */
- ret = -t4_read_flash(adap, FLASH_FW_START,
+ ret = t4_read_flash(adap, FLASH_FW_START,
sizeof(*card_fw) / sizeof(uint32_t),
(uint32_t *)card_fw, 1);
if (ret == 0) {
@@ -3528,8 +3528,8 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
should_install_fs_fw(adap, card_fw_usable,
be32_to_cpu(fs_fw->fw_ver),
be32_to_cpu(card_fw->fw_ver))) {
- ret = -t4_fw_upgrade(adap, adap->mbox, fw_data,
- fw_size, 0);
+ ret = t4_fw_upgrade(adap, adap->mbox, fw_data,
+ fw_size, 0);
if (ret != 0) {
dev_err(adap->pdev_dev,
"failed to install firmware: %d\n", ret);
@@ -3560,7 +3560,7 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
FW_HDR_FW_VER_MICRO_G(c), FW_HDR_FW_VER_BUILD_G(c),
FW_HDR_FW_VER_MAJOR_G(k), FW_HDR_FW_VER_MINOR_G(k),
FW_HDR_FW_VER_MICRO_G(k), FW_HDR_FW_VER_BUILD_G(k));
- ret = EINVAL;
+ ret = -EINVAL;
goto bye;
}

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 403e0f089f2a..37537c302080 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3993,9 +3993,8 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)

hns3_put_ring_config(priv);

- hns3_dbg_uninit(handle);
-
out_netdev_free:
+ hns3_dbg_uninit(handle);
free_netdev(netdev);
}

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 52c9d204fe3d..34e5448d59f6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -174,18 +174,21 @@ static void hns3_lb_check_skb_data(struct hns3_enet_ring *ring,
{
struct hns3_enet_tqp_vector *tqp_vector = ring->tqp_vector;
unsigned char *packet = skb->data;
+ u32 len = skb_headlen(skb);
u32 i;

- for (i = 0; i < skb->len; i++)
+ len = min_t(u32, len, HNS3_NIC_LB_TEST_PACKET_SIZE);
+
+ for (i = 0; i < len; i++)
if (packet[i] != (unsigned char)(i & 0xff))
break;

/* The packet is correctly received */
- if (i == skb->len)
+ if (i == HNS3_NIC_LB_TEST_PACKET_SIZE)
tqp_vector->rx_group.total_packets++;
else
print_hex_dump(KERN_ERR, "selftest:", DUMP_PREFIX_OFFSET, 16, 1,
- skb->data, skb->len, true);
+ skb->data, len, true);

dev_kfree_skb_any(skb);
}
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 4f503b9a674c..d58597360699 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1878,13 +1878,18 @@ static int do_reset(struct ibmvnic_adapter *adapter,
release_sub_crqs(adapter, 1);
} else {
rc = ibmvnic_reset_crq(adapter);
- if (!rc)
+ if (rc == H_CLOSED || rc == H_SUCCESS) {
rc = vio_enable_interrupts(adapter->vdev);
+ if (rc)
+ netdev_err(adapter->netdev,
+ "Reset failed to enable interrupts. rc=%d\n",
+ rc);
+ }
}

if (rc) {
netdev_err(adapter->netdev,
- "Couldn't initialize crq. rc=%d\n", rc);
+ "Reset couldn't initialize crq. rc=%d\n", rc);
goto out;
}

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index a8dd0228b678..095ed81cc0ba 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -458,11 +458,15 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev,
i40e_get_netdev_stats_struct_tx(ring, stats);

if (i40e_enabled_xdp_vsi(vsi)) {
- ring++;
+ ring = READ_ONCE(vsi->xdp_rings[i]);
+ if (!ring)
+ continue;
i40e_get_netdev_stats_struct_tx(ring, stats);
}

- ring++;
+ ring = READ_ONCE(vsi->rx_rings[i]);
+ if (!ring)
+ continue;
do {
start = u64_stats_fetch_begin_irq(&ring->syncp);
packets = ring->stats.packets;
@@ -806,6 +810,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
for (q = 0; q < vsi->num_queue_pairs; q++) {
/* locate Tx ring */
p = READ_ONCE(vsi->tx_rings[q]);
+ if (!p)
+ continue;

do {
start = u64_stats_fetch_begin_irq(&p->syncp);
@@ -819,8 +825,11 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
tx_linearize += p->tx_stats.tx_linearize;
tx_force_wb += p->tx_stats.tx_force_wb;

- /* Rx queue is part of the same block as Tx queue */
- p = &p[1];
+ /* locate Rx ring */
+ p = READ_ONCE(vsi->rx_rings[q]);
+ if (!p)
+ continue;
+
do {
start = u64_stats_fetch_begin_irq(&p->syncp);
packets = p->stats.packets;
@@ -10816,10 +10825,10 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi)
if (vsi->tx_rings && vsi->tx_rings[0]) {
for (i = 0; i < vsi->alloc_queue_pairs; i++) {
kfree_rcu(vsi->tx_rings[i], rcu);
- vsi->tx_rings[i] = NULL;
- vsi->rx_rings[i] = NULL;
+ WRITE_ONCE(vsi->tx_rings[i], NULL);
+ WRITE_ONCE(vsi->rx_rings[i], NULL);
if (vsi->xdp_rings)
- vsi->xdp_rings[i] = NULL;
+ WRITE_ONCE(vsi->xdp_rings[i], NULL);
}
}
}
@@ -10853,7 +10862,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
ring->itr_setting = pf->tx_itr_default;
- vsi->tx_rings[i] = ring++;
+ WRITE_ONCE(vsi->tx_rings[i], ring++);

if (!i40e_enabled_xdp_vsi(vsi))
goto setup_rx;
@@ -10871,7 +10880,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
ring->flags = I40E_TXR_FLAGS_WB_ON_ITR;
set_ring_xdp(ring);
ring->itr_setting = pf->tx_itr_default;
- vsi->xdp_rings[i] = ring++;
+ WRITE_ONCE(vsi->xdp_rings[i], ring++);

setup_rx:
ring->queue_index = i;
@@ -10884,7 +10893,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
ring->size = 0;
ring->dcb_tc = 0;
ring->itr_setting = pf->rx_itr_default;
- vsi->rx_rings[i] = ring;
+ WRITE_ONCE(vsi->rx_rings[i], ring);
}

return 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index cc3196ae5aea..636e6e840afa 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -923,7 +923,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
ring->queue_index = txr_idx;

/* assign ring to adapter */
- adapter->tx_ring[txr_idx] = ring;
+ WRITE_ONCE(adapter->tx_ring[txr_idx], ring);

/* update count and index */
txr_count--;
@@ -950,7 +950,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
set_ring_xdp(ring);

/* assign ring to adapter */
- adapter->xdp_ring[xdp_idx] = ring;
+ WRITE_ONCE(adapter->xdp_ring[xdp_idx], ring);

/* update count and index */
xdp_count--;
@@ -993,7 +993,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
ring->queue_index = rxr_idx;

/* assign ring to adapter */
- adapter->rx_ring[rxr_idx] = ring;
+ WRITE_ONCE(adapter->rx_ring[rxr_idx], ring);

/* update count and index */
rxr_count--;
@@ -1022,13 +1022,13 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)

ixgbe_for_each_ring(ring, q_vector->tx) {
if (ring_is_xdp(ring))
- adapter->xdp_ring[ring->queue_index] = NULL;
+ WRITE_ONCE(adapter->xdp_ring[ring->queue_index], NULL);
else
- adapter->tx_ring[ring->queue_index] = NULL;
+ WRITE_ONCE(adapter->tx_ring[ring->queue_index], NULL);
}

ixgbe_for_each_ring(ring, q_vector->rx)
- adapter->rx_ring[ring->queue_index] = NULL;
+ WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL);

adapter->q_vector[v_idx] = NULL;
napi_hash_del(&q_vector->napi);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index edaa0bffa5c3..5336bfcd2d70 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7064,7 +7064,10 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
}

for (i = 0; i < adapter->num_rx_queues; i++) {
- struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
+ struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]);
+
+ if (!rx_ring)
+ continue;
non_eop_descs += rx_ring->rx_stats.non_eop_descs;
alloc_rx_page += rx_ring->rx_stats.alloc_rx_page;
alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
@@ -7085,15 +7088,20 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
packets = 0;
/* gather some stats to the adapter struct that are per queue */
for (i = 0; i < adapter->num_tx_queues; i++) {
- struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+ struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]);
+
+ if (!tx_ring)
+ continue;
restart_queue += tx_ring->tx_stats.restart_queue;
tx_busy += tx_ring->tx_stats.tx_busy;
bytes += tx_ring->stats.bytes;
packets += tx_ring->stats.packets;
}
for (i = 0; i < adapter->num_xdp_queues; i++) {
- struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i];
+ struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]);

+ if (!xdp_ring)
+ continue;
restart_queue += xdp_ring->tx_stats.restart_queue;
tx_busy += xdp_ring->tx_stats.tx_busy;
bytes += xdp_ring->stats.bytes;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index a10ae28ebc8a..ffdb7b113f17 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -104,9 +104,11 @@
#define MVNETA_TX_IN_PRGRS BIT(1)
#define MVNETA_TX_FIFO_EMPTY BIT(8)
#define MVNETA_RX_MIN_FRAME_SIZE 0x247c
+/* Only exists on Armada XP and Armada 370 */
#define MVNETA_SERDES_CFG 0x24A0
#define MVNETA_SGMII_SERDES_PROTO 0x0cc7
#define MVNETA_QSGMII_SERDES_PROTO 0x0667
+#define MVNETA_HSGMII_SERDES_PROTO 0x1107
#define MVNETA_TYPE_PRIO 0x24bc
#define MVNETA_FORCE_UNI BIT(21)
#define MVNETA_TXQ_CMD_1 0x24e4
@@ -3164,26 +3166,60 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
return 0;
}

-static int mvneta_comphy_init(struct mvneta_port *pp)
+static int mvneta_comphy_init(struct mvneta_port *pp, phy_interface_t interface)
{
int ret;

- if (!pp->comphy)
- return 0;
-
- ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET,
- pp->phy_interface);
+ ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET, interface);
if (ret)
return ret;

return phy_power_on(pp->comphy);
}

+static int mvneta_config_interface(struct mvneta_port *pp,
+ phy_interface_t interface)
+{
+ int ret = 0;
+
+ if (pp->comphy) {
+ if (interface == PHY_INTERFACE_MODE_SGMII ||
+ interface == PHY_INTERFACE_MODE_1000BASEX ||
+ interface == PHY_INTERFACE_MODE_2500BASEX) {
+ ret = mvneta_comphy_init(pp, interface);
+ }
+ } else {
+ switch (interface) {
+ case PHY_INTERFACE_MODE_QSGMII:
+ mvreg_write(pp, MVNETA_SERDES_CFG,
+ MVNETA_QSGMII_SERDES_PROTO);
+ break;
+
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_1000BASEX:
+ mvreg_write(pp, MVNETA_SERDES_CFG,
+ MVNETA_SGMII_SERDES_PROTO);
+ break;
+
+ case PHY_INTERFACE_MODE_2500BASEX:
+ mvreg_write(pp, MVNETA_SERDES_CFG,
+ MVNETA_HSGMII_SERDES_PROTO);
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ pp->phy_interface = interface;
+
+ return ret;
+}
+
static void mvneta_start_dev(struct mvneta_port *pp)
{
int cpu;

- WARN_ON(mvneta_comphy_init(pp));
+ WARN_ON(mvneta_config_interface(pp, pp->phy_interface));

mvneta_max_rx_size_set(pp, pp->pkt_size);
mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
@@ -3558,17 +3594,13 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode,
/* When at 2.5G, the link partner can send frames with shortened
* preambles.
*/
- if (state->speed == SPEED_2500)
+ if (state->interface == PHY_INTERFACE_MODE_2500BASEX)
new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE;

- if (pp->comphy && pp->phy_interface != state->interface &&
- (state->interface == PHY_INTERFACE_MODE_SGMII ||
- state->interface == PHY_INTERFACE_MODE_1000BASEX ||
- state->interface == PHY_INTERFACE_MODE_2500BASEX)) {
- pp->phy_interface = state->interface;
-
- WARN_ON(phy_power_off(pp->comphy));
- WARN_ON(mvneta_comphy_init(pp));
+ if (pp->phy_interface != state->interface) {
+ if (pp->comphy)
+ WARN_ON(phy_power_off(pp->comphy));
+ WARN_ON(mvneta_config_interface(pp, state->interface));
}

if (new_ctrl0 != gmac_ctrl0)
@@ -4464,20 +4496,10 @@ static void mvneta_conf_mbus_windows(struct mvneta_port *pp,
}

/* Power up the port */
-static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
+static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
{
/* MAC Cause register should be cleared */
mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
-
- if (phy_mode == PHY_INTERFACE_MODE_QSGMII)
- mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO);
- else if (phy_mode == PHY_INTERFACE_MODE_SGMII ||
- phy_interface_mode_is_8023z(phy_mode))
- mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
- else if (!phy_interface_mode_is_rgmii(phy_mode))
- return -EINVAL;
-
- return 0;
}

/* Device initialization routine */
@@ -4661,11 +4683,7 @@ static int mvneta_probe(struct platform_device *pdev)
if (err < 0)
goto err_netdev;

- err = mvneta_port_power_up(pp, phy_mode);
- if (err < 0) {
- dev_err(&pdev->dev, "can't power up port\n");
- goto err_netdev;
- }
+ mvneta_port_power_up(pp, phy_mode);

/* Armada3700 network controller does not support per-cpu
* operation, so only single NAPI should be initialized.
@@ -4818,11 +4836,7 @@ static int mvneta_resume(struct device *device)
}
}
mvneta_defaults_set(pp);
- err = mvneta_port_power_up(pp, pp->phy_interface);
- if (err < 0) {
- dev_err(device, "can't power up port\n");
- return err;
- }
+ mvneta_port_power_up(pp, pp->phy_interface);

netif_device_attach(dev);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index fce6eccdcf8b..fa81a97f6ba9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -78,11 +78,26 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
[MLX5E_400GAUI_8] = 400000,
};

+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev)
+{
+ struct mlx5e_port_eth_proto eproto;
+ int err;
+
+ if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet))
+ return true;
+
+ err = mlx5_port_query_eth_proto(mdev, 1, true, &eproto);
+ if (err)
+ return false;
+
+ return !!eproto.cap;
+}
+
static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
const u32 **arr, u32 *size,
bool force_legacy)
{
- bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ bool ext = force_legacy ? false : mlx5e_ptys_ext_supported(mdev);

*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
ARRAY_SIZE(mlx5e_link_speed);
@@ -177,7 +192,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
bool ext;
int err;

- ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ ext = mlx5e_ptys_ext_supported(mdev);
err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
if (err)
goto out;
@@ -205,7 +220,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
int err;
int i;

- ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ ext = mlx5e_ptys_ext_supported(mdev);
err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
if (err)
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index 4a7f4497692b..e196888f7056 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -54,7 +54,7 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
bool force_legacy);
-
+bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev);
int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 39ee32518b10..8cd529556b21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -200,7 +200,7 @@ static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
struct ptys2ethtool_config **arr,
u32 *size)
{
- bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ bool ext = mlx5e_ptys_ext_supported(mdev);

*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
@@ -871,7 +871,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
struct ethtool_link_ksettings *link_ksettings)
{
unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
- bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ bool ext = mlx5e_ptys_ext_supported(mdev);

ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
}
@@ -900,7 +900,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
__func__, err);
goto err_query_regs;
}
- ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability);
eth_proto_cap = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
eth_proto_capability);
eth_proto_admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
@@ -1052,7 +1052,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
autoneg = link_ksettings->base.autoneg;
speed = link_ksettings->base.speed;

- ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ ext_supported = mlx5e_ptys_ext_supported(mdev);
ext = ext_requested(autoneg, adver, ext_supported);
if (!ext_supported && ext)
return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index cc262b30aed5..dc589322940c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -293,7 +293,40 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
return 0;
}

-static int mlx5_eeprom_page(int offset)
+static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num,
+ u8 *module_id)
+{
+ u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
+ u32 out[MLX5_ST_SZ_DW(mcia_reg)];
+ int err, status;
+ u8 *ptr;
+
+ MLX5_SET(mcia_reg, in, i2c_device_address, MLX5_I2C_ADDR_LOW);
+ MLX5_SET(mcia_reg, in, module, module_num);
+ MLX5_SET(mcia_reg, in, device_address, 0);
+ MLX5_SET(mcia_reg, in, page_number, 0);
+ MLX5_SET(mcia_reg, in, size, 1);
+ MLX5_SET(mcia_reg, in, l, 0);
+
+ err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+ sizeof(out), MLX5_REG_MCIA, 0, 0);
+ if (err)
+ return err;
+
+ status = MLX5_GET(mcia_reg, out, status);
+ if (status) {
+ mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n",
+ status);
+ return -EIO;
+ }
+ ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+
+ *module_id = ptr[0];
+
+ return 0;
+}
+
+static int mlx5_qsfp_eeprom_page(u16 offset)
{
if (offset < MLX5_EEPROM_PAGE_LENGTH)
/* Addresses between 0-255 - page 00 */
@@ -307,7 +340,7 @@ static int mlx5_eeprom_page(int offset)
MLX5_EEPROM_HIGH_PAGE_LENGTH);
}

-static int mlx5_eeprom_high_page_offset(int page_num)
+static int mlx5_qsfp_eeprom_high_page_offset(int page_num)
{
if (!page_num) /* Page 0 always start from low page */
return 0;
@@ -316,35 +349,62 @@ static int mlx5_eeprom_high_page_offset(int page_num)
return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH;
}

+static void mlx5_qsfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+ *i2c_addr = MLX5_I2C_ADDR_LOW;
+ *page_num = mlx5_qsfp_eeprom_page(*offset);
+ *offset -= mlx5_qsfp_eeprom_high_page_offset(*page_num);
+}
+
+static void mlx5_sfp_eeprom_params_set(u16 *i2c_addr, int *page_num, u16 *offset)
+{
+ *i2c_addr = MLX5_I2C_ADDR_LOW;
+ *page_num = 0;
+
+ if (*offset < MLX5_EEPROM_PAGE_LENGTH)
+ return;
+
+ *i2c_addr = MLX5_I2C_ADDR_HIGH;
+ *offset -= MLX5_EEPROM_PAGE_LENGTH;
+}
+
int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
u16 offset, u16 size, u8 *data)
{
- int module_num, page_num, status, err;
+ int module_num, status, err, page_num = 0;
+ u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {};
u32 out[MLX5_ST_SZ_DW(mcia_reg)];
- u32 in[MLX5_ST_SZ_DW(mcia_reg)];
- u16 i2c_addr;
- void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
+ u16 i2c_addr = 0;
+ u8 module_id;
+ void *ptr;

err = mlx5_query_module_num(dev, &module_num);
if (err)
return err;

- memset(in, 0, sizeof(in));
- size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
-
- /* Get the page number related to the given offset */
- page_num = mlx5_eeprom_page(offset);
+ err = mlx5_query_module_id(dev, module_num, &module_id);
+ if (err)
+ return err;

- /* Set the right offset according to the page number,
- * For page_num > 0, relative offset is always >= 128 (high page).
- */
- offset -= mlx5_eeprom_high_page_offset(page_num);
+ switch (module_id) {
+ case MLX5_MODULE_ID_SFP:
+ mlx5_sfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+ break;
+ case MLX5_MODULE_ID_QSFP:
+ case MLX5_MODULE_ID_QSFP_PLUS:
+ case MLX5_MODULE_ID_QSFP28:
+ mlx5_qsfp_eeprom_params_set(&i2c_addr, &page_num, &offset);
+ break;
+ default:
+ mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
+ return -EINVAL;
+ }

if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
/* Cross pages read, read until offset 256 in low page */
size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;

- i2c_addr = MLX5_I2C_ADDR_LOW;
+ size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);

MLX5_SET(mcia_reg, in, l, 0);
MLX5_SET(mcia_reg, in, module, module_num);
@@ -365,6 +425,7 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
return -EIO;
}

+ ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
memcpy(data, ptr, size);

return size;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index f3d1f9411d10..aa4fef789084 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1401,23 +1401,12 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
u16 num_pages;
int err;

- mutex_init(&mlxsw_pci->cmd.lock);
- init_waitqueue_head(&mlxsw_pci->cmd.wait);
-
mlxsw_pci->core = mlxsw_core;

mbox = mlxsw_cmd_mbox_alloc();
if (!mbox)
return -ENOMEM;

- err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
- if (err)
- goto mbox_put;
-
- err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
- if (err)
- goto err_out_mbox_alloc;
-
err = mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id);
if (err)
goto err_sw_reset;
@@ -1524,9 +1513,6 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
mlxsw_pci_free_irq_vectors(mlxsw_pci);
err_alloc_irq:
err_sw_reset:
- mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
-err_out_mbox_alloc:
- mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
mbox_put:
mlxsw_cmd_mbox_free(mbox);
return err;
@@ -1540,8 +1526,6 @@ static void mlxsw_pci_fini(void *bus_priv)
mlxsw_pci_aqs_fini(mlxsw_pci);
mlxsw_pci_fw_area_fini(mlxsw_pci);
mlxsw_pci_free_irq_vectors(mlxsw_pci);
- mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
- mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
}

static struct mlxsw_pci_queue *
@@ -1755,6 +1739,37 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
.features = MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET,
};

+static int mlxsw_pci_cmd_init(struct mlxsw_pci *mlxsw_pci)
+{
+ int err;
+
+ mutex_init(&mlxsw_pci->cmd.lock);
+ init_waitqueue_head(&mlxsw_pci->cmd.wait);
+
+ err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+ if (err)
+ goto err_in_mbox_alloc;
+
+ err = mlxsw_pci_mbox_alloc(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+ if (err)
+ goto err_out_mbox_alloc;
+
+ return 0;
+
+err_out_mbox_alloc:
+ mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+err_in_mbox_alloc:
+ mutex_destroy(&mlxsw_pci->cmd.lock);
+ return err;
+}
+
+static void mlxsw_pci_cmd_fini(struct mlxsw_pci *mlxsw_pci)
+{
+ mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox);
+ mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox);
+ mutex_destroy(&mlxsw_pci->cmd.lock);
+}
+
static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
const char *driver_name = pdev->driver->name;
@@ -1810,6 +1825,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
mlxsw_pci->pdev = pdev;
pci_set_drvdata(pdev, mlxsw_pci);

+ err = mlxsw_pci_cmd_init(mlxsw_pci);
+ if (err)
+ goto err_pci_cmd_init;
+
mlxsw_pci->bus_info.device_kind = driver_name;
mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
mlxsw_pci->bus_info.dev = &pdev->dev;
@@ -1827,6 +1846,8 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return 0;

err_bus_device_register:
+ mlxsw_pci_cmd_fini(mlxsw_pci);
+err_pci_cmd_init:
iounmap(mlxsw_pci->hw_addr);
err_ioremap:
err_pci_resource_len_check:
@@ -1844,6 +1865,7 @@ static void mlxsw_pci_remove(struct pci_dev *pdev)
struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev);

mlxsw_core_bus_device_unregister(mlxsw_pci->core, false);
+ mlxsw_pci_cmd_fini(mlxsw_pci);
iounmap(mlxsw_pci->hw_addr);
pci_release_regions(mlxsw_pci->pdev);
pci_disable_device(mlxsw_pci->pdev);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index efdf8cb5114c..2f013fc71698 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6287,7 +6287,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
}

fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
- if (WARN_ON(!fib_work))
+ if (!fib_work)
return NOTIFY_BAD;

fib_work->mlxsw_sp = router->mlxsw_sp;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 859caa6c1a1f..8e7be214f959 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -8197,6 +8197,10 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer)
DP_ERR(cdev, "qed_dbg_mcp_trace failed. rc = %d\n", rc);
}

+ /* Re-populate nvm attribute info */
+ qed_mcp_nvm_info_free(p_hwfn);
+ qed_mcp_nvm_info_populate(p_hwfn);
+
/* nvm cfg1 */
rc = qed_dbg_nvm_image(cdev,
(u8 *)buffer + offset + REGDUMP_HEADER_SIZE,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index ecd14474a603..638047b937c6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -4423,12 +4423,6 @@ static int qed_get_dev_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
return 0;
}

-static void qed_nvm_info_free(struct qed_hwfn *p_hwfn)
-{
- kfree(p_hwfn->nvm_info.image_att);
- p_hwfn->nvm_info.image_att = NULL;
-}
-
static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
void __iomem *p_regview,
void __iomem *p_doorbells,
@@ -4513,7 +4507,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
return rc;
err3:
if (IS_LEAD_HWFN(p_hwfn))
- qed_nvm_info_free(p_hwfn);
+ qed_mcp_nvm_info_free(p_hwfn);
err2:
if (IS_LEAD_HWFN(p_hwfn))
qed_iov_free_hw_info(p_hwfn->cdev);
@@ -4574,7 +4568,7 @@ int qed_hw_prepare(struct qed_dev *cdev,
if (rc) {
if (IS_PF(cdev)) {
qed_init_free(p_hwfn);
- qed_nvm_info_free(p_hwfn);
+ qed_mcp_nvm_info_free(p_hwfn);
qed_mcp_free(p_hwfn);
qed_hw_hwfn_free(p_hwfn);
}
@@ -4608,7 +4602,7 @@ void qed_hw_remove(struct qed_dev *cdev)

qed_iov_free_hw_info(cdev);

- qed_nvm_info_free(p_hwfn);
+ qed_mcp_nvm_info_free(p_hwfn);
}

static void qed_chain_free_next_ptr(struct qed_dev *cdev,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 36ddb89856a8..9401b49275f0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -3149,6 +3149,13 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
return rc;
}

+void qed_mcp_nvm_info_free(struct qed_hwfn *p_hwfn)
+{
+ kfree(p_hwfn->nvm_info.image_att);
+ p_hwfn->nvm_info.image_att = NULL;
+ p_hwfn->nvm_info.valid = false;
+}
+
int
qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn,
enum qed_nvm_images image_id,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 9c4c2763de8d..e38297383b00 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -1192,6 +1192,13 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
*/
int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn);

+/**
+ * @brief Delete nvm info shadow in the given hardware function
+ *
+ * @param p_hwfn
+ */
+void qed_mcp_nvm_info_free(struct qed_hwfn *p_hwfn);
+
/**
* @brief Get the engine affinity configuration.
*
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 3cf4dc3433f9..bb4ccbda031a 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1287,11 +1287,14 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)

/* Init all registers */
ret = smsc95xx_reset(dev);
+ if (ret)
+ goto free_pdata;

/* detect device revision as different features may be available */
ret = smsc95xx_read_reg(dev, ID_REV, &val);
if (ret < 0)
- return ret;
+ goto free_pdata;
+
val >>= 16;
pdata->chip_id = val;
pdata->mdix_ctrl = get_mdix_status(dev->net);
@@ -1317,6 +1320,10 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
schedule_delayed_work(&pdata->carrier_check, CARRIER_CHECK_DELAY);

return 0;
+
+free_pdata:
+ kfree(pdata);
+ return ret;
}

static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 4ed21dad6a8e..6049d3766c64 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -643,9 +643,9 @@ static void ath9k_hif_usb_rx_stream(struct hif_device_usb *hif_dev,

static void ath9k_hif_usb_rx_cb(struct urb *urb)
{
- struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
- struct hif_device_usb *hif_dev = rx_buf->hif_dev;
- struct sk_buff *skb = rx_buf->skb;
+ struct sk_buff *skb = (struct sk_buff *) urb->context;
+ struct hif_device_usb *hif_dev =
+ usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0));
int ret;

if (!skb)
@@ -685,15 +685,14 @@ static void ath9k_hif_usb_rx_cb(struct urb *urb)
return;
free:
kfree_skb(skb);
- kfree(rx_buf);
}

static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
{
- struct rx_buf *rx_buf = (struct rx_buf *)urb->context;
- struct hif_device_usb *hif_dev = rx_buf->hif_dev;
- struct sk_buff *skb = rx_buf->skb;
+ struct sk_buff *skb = (struct sk_buff *) urb->context;
struct sk_buff *nskb;
+ struct hif_device_usb *hif_dev =
+ usb_get_intfdata(usb_ifnum_to_if(urb->dev, 0));
int ret;

if (!skb)
@@ -751,7 +750,6 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
return;
free:
kfree_skb(skb);
- kfree(rx_buf);
urb->context = NULL;
}

@@ -797,7 +795,7 @@ static int ath9k_hif_usb_alloc_tx_urbs(struct hif_device_usb *hif_dev)
init_usb_anchor(&hif_dev->mgmt_submitted);

for (i = 0; i < MAX_TX_URB_NUM; i++) {
- tx_buf = kzalloc(sizeof(*tx_buf), GFP_KERNEL);
+ tx_buf = kzalloc(sizeof(struct tx_buf), GFP_KERNEL);
if (!tx_buf)
goto err;

@@ -834,9 +832,8 @@ static void ath9k_hif_usb_dealloc_rx_urbs(struct hif_device_usb *hif_dev)

static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
{
- struct rx_buf *rx_buf = NULL;
- struct sk_buff *skb = NULL;
struct urb *urb = NULL;
+ struct sk_buff *skb = NULL;
int i, ret;

init_usb_anchor(&hif_dev->rx_submitted);
@@ -844,12 +841,6 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)

for (i = 0; i < MAX_RX_URB_NUM; i++) {

- rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL);
- if (!rx_buf) {
- ret = -ENOMEM;
- goto err_rxb;
- }
-
/* Allocate URB */
urb = usb_alloc_urb(0, GFP_KERNEL);
if (urb == NULL) {
@@ -864,14 +855,11 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
goto err_skb;
}

- rx_buf->hif_dev = hif_dev;
- rx_buf->skb = skb;
-
usb_fill_bulk_urb(urb, hif_dev->udev,
usb_rcvbulkpipe(hif_dev->udev,
USB_WLAN_RX_PIPE),
skb->data, MAX_RX_BUF_SIZE,
- ath9k_hif_usb_rx_cb, rx_buf);
+ ath9k_hif_usb_rx_cb, skb);

/* Anchor URB */
usb_anchor_urb(urb, &hif_dev->rx_submitted);
@@ -897,8 +885,6 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
err_skb:
usb_free_urb(urb);
err_urb:
- kfree(rx_buf);
-err_rxb:
ath9k_hif_usb_dealloc_rx_urbs(hif_dev);
return ret;
}
@@ -910,21 +896,14 @@ static void ath9k_hif_usb_dealloc_reg_in_urbs(struct hif_device_usb *hif_dev)

static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev)
{
- struct rx_buf *rx_buf = NULL;
- struct sk_buff *skb = NULL;
struct urb *urb = NULL;
+ struct sk_buff *skb = NULL;
int i, ret;

init_usb_anchor(&hif_dev->reg_in_submitted);

for (i = 0; i < MAX_REG_IN_URB_NUM; i++) {

- rx_buf = kzalloc(sizeof(*rx_buf), GFP_KERNEL);
- if (!rx_buf) {
- ret = -ENOMEM;
- goto err_rxb;
- }
-
/* Allocate URB */
urb = usb_alloc_urb(0, GFP_KERNEL);
if (urb == NULL) {
@@ -939,14 +918,11 @@ static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev)
goto err_skb;
}

- rx_buf->hif_dev = hif_dev;
- rx_buf->skb = skb;
-
usb_fill_int_urb(urb, hif_dev->udev,
usb_rcvintpipe(hif_dev->udev,
USB_REG_IN_PIPE),
skb->data, MAX_REG_IN_BUF_SIZE,
- ath9k_hif_usb_reg_in_cb, rx_buf, 1);
+ ath9k_hif_usb_reg_in_cb, skb, 1);

/* Anchor URB */
usb_anchor_urb(urb, &hif_dev->reg_in_submitted);
@@ -972,8 +948,6 @@ static int ath9k_hif_usb_alloc_reg_in_urbs(struct hif_device_usb *hif_dev)
err_skb:
usb_free_urb(urb);
err_urb:
- kfree(rx_buf);
-err_rxb:
ath9k_hif_usb_dealloc_reg_in_urbs(hif_dev);
return ret;
}
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.h b/drivers/net/wireless/ath/ath9k/hif_usb.h
index 5985aa15ca93..a94e7e1c86e9 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.h
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.h
@@ -86,11 +86,6 @@ struct tx_buf {
struct list_head list;
};

-struct rx_buf {
- struct sk_buff *skb;
- struct hif_device_usb *hif_dev;
-};
-
#define HIF_USB_TX_STOP BIT(0)
#define HIF_USB_TX_FLUSH BIT(1)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 73e8475ddc8a..cd0d49978190 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -451,7 +451,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
* Spread I/O queues completion vectors according their queue index.
* Admin queues can always go on completion vector 0.
*/
- comp_vector = idx == 0 ? idx : idx - 1;
+ comp_vector = (idx == 0 ? idx : idx - 1) % ibdev->num_comp_vectors;

/* Polling queues need direct cq polling context */
if (nvme_rdma_poll_queue(queue))
diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index d0f5c69930d0..77c28313e95f 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -92,11 +92,12 @@ static int jz4740_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
{
struct jz4740_pwm_chip *jz4740 = to_jz4740(pwm->chip);
unsigned long long tmp;
- unsigned long period, duty;
+ unsigned long rate, period, duty;
unsigned int prescaler = 0;
uint16_t ctrl;

- tmp = (unsigned long long)clk_get_rate(jz4740->clk) * state->period;
+ rate = clk_get_rate(jz4740->clk);
+ tmp = rate * state->period;
do_div(tmp, 1000000000);
period = tmp;

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 9a06818d2816..3e0e27731922 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0+
//
// Copyright 2013 Freescale Semiconductor, Inc.
+// Copyright 2020 NXP
//
// Freescale DSPI driver
// This file contains a driver for the Freescale DSPI
@@ -33,6 +34,9 @@
#define SPI_MCR_CLR_TXF BIT(11)
#define SPI_MCR_CLR_RXF BIT(10)
#define SPI_MCR_XSPI BIT(3)
+#define SPI_MCR_DIS_TXF BIT(13)
+#define SPI_MCR_DIS_RXF BIT(12)
+#define SPI_MCR_HALT BIT(0)

#define SPI_TCR 0x08
#define SPI_TCR_GET_TCNT(x) (((x) & GENMASK(31, 16)) >> 16)
@@ -1160,15 +1164,42 @@ static int dspi_remove(struct platform_device *pdev)
struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);

/* Disconnect from the SPI framework */
+ spi_unregister_controller(dspi->ctlr);
+
+ /* Disable RX and TX */
+ regmap_update_bits(dspi->regmap, SPI_MCR,
+ SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF,
+ SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF);
+
+ /* Stop Running */
+ regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, SPI_MCR_HALT);
+
dspi_release_dma(dspi);
if (dspi->irq)
free_irq(dspi->irq, dspi);
clk_disable_unprepare(dspi->clk);
- spi_unregister_controller(dspi->ctlr);

return 0;
}

+static void dspi_shutdown(struct platform_device *pdev)
+{
+ struct spi_controller *ctlr = platform_get_drvdata(pdev);
+ struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+
+ /* Disable RX and TX */
+ regmap_update_bits(dspi->regmap, SPI_MCR,
+ SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF,
+ SPI_MCR_DIS_TXF | SPI_MCR_DIS_RXF);
+
+ /* Stop Running */
+ regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, SPI_MCR_HALT);
+
+ dspi_release_dma(dspi);
+ clk_disable_unprepare(dspi->clk);
+ spi_unregister_controller(dspi->ctlr);
+}
+
static struct platform_driver fsl_dspi_driver = {
.driver.name = DRIVER_NAME,
.driver.of_match_table = fsl_dspi_dt_ids,
@@ -1176,6 +1207,7 @@ static struct platform_driver fsl_dspi_driver = {
.driver.pm = &dspi_pm,
.probe = dspi_probe,
.remove = dspi_remove,
+ .shutdown = dspi_shutdown,
};
module_platform_driver(fsl_dspi_driver);

diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index ab2c3848f5bf..ac6bf1fbbfe6 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -605,15 +605,20 @@ static int spidev_open(struct inode *inode, struct file *filp)
static int spidev_release(struct inode *inode, struct file *filp)
{
struct spidev_data *spidev;
+ int dofree;

mutex_lock(&device_list_lock);
spidev = filp->private_data;
filp->private_data = NULL;

+ spin_lock_irq(&spidev->spi_lock);
+ /* ... after we unbound from the underlying device? */
+ dofree = (spidev->spi == NULL);
+ spin_unlock_irq(&spidev->spi_lock);
+
/* last close? */
spidev->users--;
if (!spidev->users) {
- int dofree;

kfree(spidev->tx_buffer);
spidev->tx_buffer = NULL;
@@ -621,19 +626,14 @@ static int spidev_release(struct inode *inode, struct file *filp)
kfree(spidev->rx_buffer);
spidev->rx_buffer = NULL;

- spin_lock_irq(&spidev->spi_lock);
- if (spidev->spi)
- spidev->speed_hz = spidev->spi->max_speed_hz;
-
- /* ... after we unbound from the underlying device? */
- dofree = (spidev->spi == NULL);
- spin_unlock_irq(&spidev->spi_lock);
-
if (dofree)
kfree(spidev);
+ else
+ spidev->speed_hz = spidev->spi->max_speed_hz;
}
#ifdef CONFIG_SPI_SLAVE
- spi_slave_abort(spidev->spi);
+ if (!dofree)
+ spi_slave_abort(spidev->spi);
#endif
mutex_unlock(&device_list_lock);

@@ -783,13 +783,13 @@ static int spidev_remove(struct spi_device *spi)
{
struct spidev_data *spidev = spi_get_drvdata(spi);

+ /* prevent new opens */
+ mutex_lock(&device_list_lock);
/* make sure ops on existing fds can abort cleanly */
spin_lock_irq(&spidev->spi_lock);
spidev->spi = NULL;
spin_unlock_irq(&spidev->spi_lock);

- /* prevent new opens */
- mutex_lock(&device_list_lock);
list_del(&spidev->device_entry);
device_destroy(spidev_class, spidev->devt);
clear_bit(MINOR(spidev->devt), minors);
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index b67372737dc9..96c05b121fac 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -206,8 +206,10 @@ static void dwc3_pci_resume_work(struct work_struct *work)
int ret;

ret = pm_runtime_get_sync(&dwc3->dev);
- if (ret)
+ if (ret) {
+ pm_runtime_put_sync_autosuspend(&dwc3->dev);
return;
+ }

pm_runtime_mark_last_busy(&dwc3->dev);
pm_runtime_put_sync_autosuspend(&dwc3->dev);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 8aab286f2028..9b214b14a3aa 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5025,25 +5025,28 @@ struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
static void check_buffer_tree_ref(struct extent_buffer *eb)
{
int refs;
- /* the ref bit is tricky. We have to make sure it is set
- * if we have the buffer dirty. Otherwise the
- * code to free a buffer can end up dropping a dirty
- * page
+ /*
+ * The TREE_REF bit is first set when the extent_buffer is added
+ * to the radix tree. It is also reset, if unset, when a new reference
+ * is created by find_extent_buffer.
*
- * Once the ref bit is set, it won't go away while the
- * buffer is dirty or in writeback, and it also won't
- * go away while we have the reference count on the
- * eb bumped.
+ * It is only cleared in two cases: freeing the last non-tree
+ * reference to the extent_buffer when its STALE bit is set or
+ * calling releasepage when the tree reference is the only reference.
*
- * We can't just set the ref bit without bumping the
- * ref on the eb because free_extent_buffer might
- * see the ref bit and try to clear it. If this happens
- * free_extent_buffer might end up dropping our original
- * ref by mistake and freeing the page before we are able
- * to add one more ref.
+ * In both cases, care is taken to ensure that the extent_buffer's
+ * pages are not under io. However, releasepage can be concurrently
+ * called with creating new references, which is prone to race
+ * conditions between the calls to check_buffer_tree_ref in those
+ * codepaths and clearing TREE_REF in try_release_extent_buffer.
*
- * So bump the ref count first, then set the bit. If someone
- * beat us to it, drop the ref we added.
+ * The actual lifetime of the extent_buffer in the radix tree is
+ * adequately protected by the refcount, but the TREE_REF bit and
+ * its corresponding reference are not. To protect against this
+ * class of races, we call check_buffer_tree_ref from the codepaths
+ * which trigger io after they set eb->io_pages. Note that once io is
+ * initiated, TREE_REF can no longer be cleared, so that is the
+ * moment at which any such race is best fixed.
*/
refs = atomic_read(&eb->refs);
if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
@@ -5493,6 +5496,11 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
eb->read_mirror = 0;
atomic_set(&eb->io_pages, num_reads);
+ /*
+ * It is possible for releasepage to clear the TREE_REF bit before we
+ * set io_pages. See check_buffer_tree_ref for a more detailed comment.
+ */
+ check_buffer_tree_ref(eb);
for (i = 0; i < num_pages; i++) {
page = eb->pages[i];

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 280c45c91ddc..e408181a5eba 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1657,12 +1657,8 @@ static noinline int run_delalloc_nocow(struct inode *inode,
ret = fallback_to_cow(inode, locked_page, cow_start,
found_key.offset - 1,
page_started, nr_written);
- if (ret) {
- if (nocow)
- btrfs_dec_nocow_writers(fs_info,
- disk_bytenr);
+ if (ret)
goto error;
- }
cow_start = (u64)-1;
}

@@ -1678,9 +1674,6 @@ static noinline int run_delalloc_nocow(struct inode *inode,
ram_bytes, BTRFS_COMPRESS_NONE,
BTRFS_ORDERED_PREALLOC);
if (IS_ERR(em)) {
- if (nocow)
- btrfs_dec_nocow_writers(fs_info,
- disk_bytenr);
ret = PTR_ERR(em);
goto error;
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 6045b4868275..5ae458505f63 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2270,6 +2270,15 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
if (rc == 0) {
cifsInode->server_eof = attrs->ia_size;
cifs_setsize(inode, attrs->ia_size);
+
+ /*
+ * The man page of truncate says if the size changed,
+ * then the st_ctime and st_mtime fields for the file
+ * are updated.
+ */
+ attrs->ia_ctime = attrs->ia_mtime = current_time(inode);
+ attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME;
+
cifs_truncate_page(inode->i_mapping, inode->i_size);
}

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 3bbc72dbc69e..79830bc9e45c 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -853,12 +853,12 @@ void bpf_jit_compile(struct bpf_prog *prog);
bool bpf_jit_needs_zext(void);
bool bpf_helper_changes_pkt_data(void *func);

-static inline bool bpf_dump_raw_ok(void)
+static inline bool bpf_dump_raw_ok(const struct cred *cred)
{
/* Reconstruction of call-sites is dependent on kallsyms,
* thus make dump the same restriction.
*/
- return kallsyms_show_value() == 1;
+ return kallsyms_show_value(cred);
}

struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index 657a83b943f0..1f96ce2b47df 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -18,6 +18,7 @@
#define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)

+struct cred;
struct module;

static inline int is_kernel_inittext(unsigned long addr)
@@ -98,7 +99,7 @@ int lookup_symbol_name(unsigned long addr, char *symname);
int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name);

/* How and when do we show kallsyms values? */
-extern int kallsyms_show_value(void);
+extern bool kallsyms_show_value(const struct cred *cred);

#else /* !CONFIG_KALLSYMS */

@@ -158,7 +159,7 @@ static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, u
return -ERANGE;
}

-static inline int kallsyms_show_value(void)
+static inline bool kallsyms_show_value(const struct cred *cred)
{
return false;
}
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index bc88d6f964da..006f01922439 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -59,6 +59,7 @@ struct snd_compr_runtime {
* @direction: stream direction, playback/recording
* @metadata_set: metadata set flag, true when set
* @next_track: has userspace signal next track transition, true when set
+ * @partial_drain: undergoing partial_drain for stream, true when set
* @private_data: pointer to DSP private data
*/
struct snd_compr_stream {
@@ -70,6 +71,7 @@ struct snd_compr_stream {
enum snd_compr_direction direction;
bool metadata_set;
bool next_track;
+ bool partial_drain;
void *private_data;
};

@@ -173,7 +175,13 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
if (snd_BUG_ON(!stream))
return;

- stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+ /* for partial_drain case we are back to running state on success */
+ if (stream->partial_drain) {
+ stream->runtime->state = SNDRV_PCM_STATE_RUNNING;
+ stream->partial_drain = false; /* clear this flag as well */
+ } else {
+ stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+ }

wake_up(&stream->runtime->sleep);
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e7af1ac69d75..8bc904f9badb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2248,7 +2248,8 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
return NULL;
}

-static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
+static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
+ const struct cred *f_cred)
{
const struct bpf_map *map;
struct bpf_insn *insns;
@@ -2271,7 +2272,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) {
if (insns[i].code == (BPF_JMP | BPF_CALL_ARGS))
insns[i].code = BPF_JMP | BPF_CALL;
- if (!bpf_dump_raw_ok())
+ if (!bpf_dump_raw_ok(f_cred))
insns[i].imm = 0;
continue;
}
@@ -2323,7 +2324,8 @@ static int set_info_rec_size(struct bpf_prog_info *info)
return 0;
}

-static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
+static int bpf_prog_get_info_by_fd(struct file *file,
+ struct bpf_prog *prog,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
@@ -2392,11 +2394,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
struct bpf_insn *insns_sanitized;
bool fault;

- if (prog->blinded && !bpf_dump_raw_ok()) {
+ if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) {
info.xlated_prog_insns = 0;
goto done;
}
- insns_sanitized = bpf_insn_prepare_dump(prog);
+ insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred);
if (!insns_sanitized)
return -ENOMEM;
uinsns = u64_to_user_ptr(info.xlated_prog_insns);
@@ -2430,7 +2432,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}

if (info.jited_prog_len && ulen) {
- if (bpf_dump_raw_ok()) {
+ if (bpf_dump_raw_ok(file->f_cred)) {
uinsns = u64_to_user_ptr(info.jited_prog_insns);
ulen = min_t(u32, info.jited_prog_len, ulen);

@@ -2465,7 +2467,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
ulen = info.nr_jited_ksyms;
info.nr_jited_ksyms = prog->aux->func_cnt ? : 1;
if (ulen) {
- if (bpf_dump_raw_ok()) {
+ if (bpf_dump_raw_ok(file->f_cred)) {
unsigned long ksym_addr;
u64 __user *user_ksyms;
u32 i;
@@ -2496,7 +2498,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
ulen = info.nr_jited_func_lens;
info.nr_jited_func_lens = prog->aux->func_cnt ? : 1;
if (ulen) {
- if (bpf_dump_raw_ok()) {
+ if (bpf_dump_raw_ok(file->f_cred)) {
u32 __user *user_lens;
u32 func_len, i;

@@ -2553,7 +2555,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
else
info.nr_jited_line_info = 0;
if (info.nr_jited_line_info && ulen) {
- if (bpf_dump_raw_ok()) {
+ if (bpf_dump_raw_ok(file->f_cred)) {
__u64 __user *user_linfo;
u32 i;

@@ -2599,7 +2601,8 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
return 0;
}

-static int bpf_map_get_info_by_fd(struct bpf_map *map,
+static int bpf_map_get_info_by_fd(struct file *file,
+ struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
@@ -2641,7 +2644,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
return 0;
}

-static int bpf_btf_get_info_by_fd(struct btf *btf,
+static int bpf_btf_get_info_by_fd(struct file *file,
+ struct btf *btf,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
@@ -2673,13 +2677,13 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
return -EBADFD;

if (f.file->f_op == &bpf_prog_fops)
- err = bpf_prog_get_info_by_fd(f.file->private_data, attr,
+ err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr,
uattr);
else if (f.file->f_op == &bpf_map_fops)
- err = bpf_map_get_info_by_fd(f.file->private_data, attr,
+ err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr,
uattr);
else if (f.file->f_op == &btf_fops)
- err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr);
+ err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
else
err = -EINVAL;

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 136ce049c4ad..61f9d781f70a 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -645,19 +645,20 @@ static inline int kallsyms_for_perf(void)
* Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to
* block even that).
*/
-int kallsyms_show_value(void)
+bool kallsyms_show_value(const struct cred *cred)
{
switch (kptr_restrict) {
case 0:
if (kallsyms_for_perf())
- return 1;
+ return true;
/* fallthrough */
case 1:
- if (has_capability_noaudit(current, CAP_SYSLOG))
- return 1;
+ if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
+ CAP_OPT_NOAUDIT) == 0)
+ return true;
/* fallthrough */
default:
- return 0;
+ return false;
}
}

@@ -674,7 +675,11 @@ static int kallsyms_open(struct inode *inode, struct file *file)
return -ENOMEM;
reset_iter(iter, 0);

- iter->show_value = kallsyms_show_value();
+ /*
+ * Instead of checking this on every s_show() call, cache
+ * the result here at open time.
+ */
+ iter->show_value = kallsyms_show_value(file->f_cred);
return 0;
}

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 950a5cfd262c..0a967db226d8 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2362,7 +2362,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
else
kprobe_type = "k";

- if (!kallsyms_show_value())
+ if (!kallsyms_show_value(pi->file->f_cred))
addr = NULL;

if (sym)
@@ -2463,7 +2463,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
* If /proc/kallsyms is not showing kernel address, we won't
* show them here either.
*/
- if (!kallsyms_show_value())
+ if (!kallsyms_show_value(m->file->f_cred))
seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
(void *)ent->start_addr);
else
diff --git a/kernel/module.c b/kernel/module.c
index a2a47f4a33a7..6baa1080cdb7 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1507,8 +1507,7 @@ static inline bool sect_empty(const Elf_Shdr *sect)
}

struct module_sect_attr {
- struct module_attribute mattr;
- char *name;
+ struct bin_attribute battr;
unsigned long address;
};

@@ -1518,13 +1517,18 @@ struct module_sect_attrs {
struct module_sect_attr attrs[0];
};

-static ssize_t module_sect_show(struct module_attribute *mattr,
- struct module_kobject *mk, char *buf)
+static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
+ struct bin_attribute *battr,
+ char *buf, loff_t pos, size_t count)
{
struct module_sect_attr *sattr =
- container_of(mattr, struct module_sect_attr, mattr);
- return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
- (void *)sattr->address : NULL);
+ container_of(battr, struct module_sect_attr, battr);
+
+ if (pos != 0)
+ return -EINVAL;
+
+ return sprintf(buf, "0x%px\n",
+ kallsyms_show_value(file->f_cred) ? (void *)sattr->address : NULL);
}

static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
@@ -1532,7 +1536,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
unsigned int section;

for (section = 0; section < sect_attrs->nsections; section++)
- kfree(sect_attrs->attrs[section].name);
+ kfree(sect_attrs->attrs[section].battr.attr.name);
kfree(sect_attrs);
}

@@ -1541,42 +1545,41 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info)
unsigned int nloaded = 0, i, size[2];
struct module_sect_attrs *sect_attrs;
struct module_sect_attr *sattr;
- struct attribute **gattr;
+ struct bin_attribute **gattr;

/* Count loaded sections and allocate structures */
for (i = 0; i < info->hdr->e_shnum; i++)
if (!sect_empty(&info->sechdrs[i]))
nloaded++;
size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded),
- sizeof(sect_attrs->grp.attrs[0]));
- size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]);
+ sizeof(sect_attrs->grp.bin_attrs[0]));
+ size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]);
sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL);
if (sect_attrs == NULL)
return;

/* Setup section attributes. */
sect_attrs->grp.name = "sections";
- sect_attrs->grp.attrs = (void *)sect_attrs + size[0];
+ sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0];

sect_attrs->nsections = 0;
sattr = &sect_attrs->attrs[0];
- gattr = &sect_attrs->grp.attrs[0];
+ gattr = &sect_attrs->grp.bin_attrs[0];
for (i = 0; i < info->hdr->e_shnum; i++) {
Elf_Shdr *sec = &info->sechdrs[i];
if (sect_empty(sec))
continue;
+ sysfs_bin_attr_init(&sattr->battr);
sattr->address = sec->sh_addr;
- sattr->name = kstrdup(info->secstrings + sec->sh_name,
- GFP_KERNEL);
- if (sattr->name == NULL)
+ sattr->battr.attr.name =
+ kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL);
+ if (sattr->battr.attr.name == NULL)
goto out;
sect_attrs->nsections++;
- sysfs_attr_init(&sattr->mattr.attr);
- sattr->mattr.show = module_sect_show;
- sattr->mattr.store = NULL;
- sattr->mattr.attr.name = sattr->name;
- sattr->mattr.attr.mode = S_IRUSR;
- *(gattr++) = &(sattr++)->mattr.attr;
+ sattr->battr.read = module_sect_read;
+ sattr->battr.size = 3 /* "0x", "\n" */ + (BITS_PER_LONG / 4);
+ sattr->battr.attr.mode = 0400;
+ *(gattr++) = &(sattr++)->battr;
}
*gattr = NULL;

@@ -1666,7 +1669,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info)
continue;
if (info->sechdrs[i].sh_type == SHT_NOTE) {
sysfs_bin_attr_init(nattr);
- nattr->attr.name = mod->sect_attrs->attrs[loaded].name;
+ nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name;
nattr->attr.mode = S_IRUGO;
nattr->size = info->sechdrs[i].sh_size;
nattr->private = (void *) info->sechdrs[i].sh_addr;
@@ -4391,7 +4394,7 @@ static int modules_open(struct inode *inode, struct file *file)

if (!err) {
struct seq_file *m = file->private_data;
- m->private = kallsyms_show_value() ? NULL : (void *)8ul;
+ m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul;
}

return err;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7238ef445daf..8b3e99d095ae 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1649,7 +1649,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
goto out;
}

- if (cpumask_equal(p->cpus_ptr, new_mask))
+ if (cpumask_equal(&p->cpus_mask, new_mask))
goto out;

dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 0536ea9298e4..118cf1ace43a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -687,7 +687,7 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
return container_of(parser, struct sk_psock, parser);
}

-static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
+static void sk_psock_skb_redirect(struct sk_buff *skb)
{
struct sk_psock *psock_other;
struct sock *sk_other;
@@ -719,12 +719,11 @@ static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
}
}

-static void sk_psock_tls_verdict_apply(struct sk_psock *psock,
- struct sk_buff *skb, int verdict)
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict)
{
switch (verdict) {
case __SK_REDIRECT:
- sk_psock_skb_redirect(psock, skb);
+ sk_psock_skb_redirect(skb);
break;
case __SK_PASS:
case __SK_DROP:
@@ -745,8 +744,8 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
}
+ sk_psock_tls_verdict_apply(skb, ret);
rcu_read_unlock();
- sk_psock_tls_verdict_apply(psock, skb, ret);
return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
@@ -774,7 +773,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
}
goto out_free;
case __SK_REDIRECT:
- sk_psock_skb_redirect(psock, skb);
+ sk_psock_skb_redirect(skb);
break;
case __SK_DROP:
/* fall-through */
@@ -786,11 +785,18 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,

static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
- struct sk_psock *psock = sk_psock_from_strp(strp);
+ struct sk_psock *psock;
struct bpf_prog *prog;
int ret = __SK_DROP;
+ struct sock *sk;

rcu_read_lock();
+ sk = strp->sk;
+ psock = sk_psock(sk);
+ if (unlikely(!psock)) {
+ kfree_skb(skb);
+ goto out;
+ }
prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
skb_orphan(skb);
@@ -798,8 +804,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
}
- rcu_read_unlock();
sk_psock_verdict_apply(psock, skb, ret);
+out:
+ rcu_read_unlock();
}

static int sk_psock_strp_read_done(struct strparser *strp, int err)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 9f9e00ba3ad7..669cbe1609d9 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -277,7 +277,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && !ret) {
if (jit_enable < 2 ||
- (jit_enable == 2 && bpf_dump_raw_ok())) {
+ (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) {
*(int *)table->data = jit_enable;
if (jit_enable == 2)
pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index d934384f31ad..6e3cf4d19ce8 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -314,7 +314,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
set->variant = &bitmap_ip;
if (!init_map_ip(set, map, first_ip, last_ip,
elements, hosts, netmask)) {
- kfree(map);
+ ip_set_free(map);
return -ENOMEM;
}
if (tb[IPSET_ATTR_TIMEOUT]) {
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index e8532783b43a..ae7cdc0d0f29 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -363,7 +363,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
set->variant = &bitmap_ipmac;
if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
- kfree(map);
+ ip_set_free(map);
return -ENOMEM;
}
if (tb[IPSET_ATTR_TIMEOUT]) {
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index e3ac914fff1a..d4a14750f5c4 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -247,7 +247,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
set->variant = &bitmap_port;
if (!init_map_port(set, map, first_port, last_port)) {
- kfree(map);
+ ip_set_free(map);
return -ENOMEM;
}
if (tb[IPSET_ATTR_TIMEOUT]) {
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 2389c9f89e48..a7a982a3e676 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -682,7 +682,7 @@ mtype_resize(struct ip_set *set, bool retried)
}
t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits));
if (!t->hregion) {
- kfree(t);
+ ip_set_free(t);
ret = -ENOMEM;
goto out;
}
@@ -1533,7 +1533,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
}
t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits));
if (!t->hregion) {
- kfree(t);
+ ip_set_free(t);
kfree(h);
return -ENOMEM;
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 48db4aec02de..200cdad3ff3a 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2012,6 +2012,8 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
err = __nf_conntrack_update(net, skb, ct, ctinfo);
if (err < 0)
return err;
+
+ ct = nf_ct_get(skb, &ctinfo);
}

return nf_confirm_cthelper(skb, ct, ctinfo);
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 2a4d50e04441..14c101e104ce 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -259,7 +259,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
unsigned int ver;
size_t hdrlen;

- if (len & 3)
+ if (len == 0 || len & 3)
return -EINVAL;

skb = netdev_alloc_skb(NULL, len);
@@ -273,6 +273,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)

switch (ver) {
case QRTR_PROTO_VER_1:
+ if (len < sizeof(*v1))
+ goto err;
v1 = data;
hdrlen = sizeof(*v1);

@@ -286,6 +288,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
size = le32_to_cpu(v1->size);
break;
case QRTR_PROTO_VER_2:
+ if (len < sizeof(*v2))
+ goto err;
v2 = data;
hdrlen = sizeof(*v2) + v2->optlen;

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index b65180e874fb..a34bbca80f49 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4798,7 +4798,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
err = nl80211_parse_he_obss_pd(
info->attrs[NL80211_ATTR_HE_OBSS_PD],
&params.he_obss_pd);
- goto out;
+ if (err)
+ goto out;
}

nl80211_calculate_ap_params(&params);
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index f34ce564d92c..1afa06b80f06 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -722,6 +722,9 @@ static int snd_compr_stop(struct snd_compr_stream *stream)

retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
if (!retval) {
+ /* clear flags and stop any drain wait */
+ stream->partial_drain = false;
+ stream->metadata_set = false;
snd_compr_drain_notify(stream);
stream->runtime->total_bytes_available = 0;
stream->runtime->total_bytes_transferred = 0;
@@ -879,6 +882,7 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream)
if (stream->next_track == false)
return -EPERM;

+ stream->partial_drain = true;
retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN);
if (retval) {
pr_debug("Partial drain returned failure\n");
diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c
index e69a4ef0d6bd..08c10ac9d6c8 100644
--- a/sound/drivers/opl3/opl3_synth.c
+++ b/sound/drivers/opl3/opl3_synth.c
@@ -91,6 +91,8 @@ int snd_opl3_ioctl(struct snd_hwdep * hw, struct file *file,
{
struct snd_dm_fm_info info;

+ memset(&info, 0, sizeof(info));
+
info.fm_mode = opl3->fm_mode;
info.rhythm = opl3->rhythm;
if (copy_to_user(argp, &info, sizeof(struct snd_dm_fm_info)))
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index 2c6d2becfe1a..824f4ac1a8ce 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -72,6 +72,12 @@ static int compare_input_type(const void *ap, const void *bp)
if (a->type != b->type)
return (int)(a->type - b->type);

+ /* If has both hs_mic and hp_mic, pick the hs_mic ahead of hp_mic. */
+ if (a->is_headset_mic && b->is_headphone_mic)
+ return -1; /* don't swap */
+ else if (a->is_headphone_mic && b->is_headset_mic)
+ return 1; /* swap */
+
/* In case one has boost and the other one has not,
pick the one with boost first. */
return (int)(b->has_boost_on_pin - a->has_boost_on_pin);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 612441508e80..95b0fdffc504 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2433,6 +2433,9 @@ static const struct pci_device_id azx_ids[] = {
/* Icelake */
{ PCI_DEVICE(0x8086, 0x34c8),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+ /* Icelake-H */
+ { PCI_DEVICE(0x8086, 0x3dc8),
+ .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
/* Jasperlake */
{ PCI_DEVICE(0x8086, 0x38c8),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
@@ -2441,9 +2444,14 @@ static const struct pci_device_id azx_ids[] = {
/* Tigerlake */
{ PCI_DEVICE(0x8086, 0xa0c8),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+ /* Tigerlake-H */
+ { PCI_DEVICE(0x8086, 0x43c8),
+ .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
/* Elkhart Lake */
{ PCI_DEVICE(0x8086, 0x4b55),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+ { PCI_DEVICE(0x8086, 0x4b58),
+ .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
/* Broxton-P(Apollolake) */
{ PCI_DEVICE(0x8086, 0x5a98),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 34868459104d..160e00e8007a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6114,6 +6114,9 @@ enum {
ALC236_FIXUP_HP_MUTE_LED,
ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
+ ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS,
+ ALC269VC_FIXUP_ACER_HEADSET_MIC,
+ ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE,
};

static const struct hda_fixup alc269_fixups[] = {
@@ -7292,6 +7295,35 @@ static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC269_FIXUP_HEADSET_MODE
},
+ [ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x14, 0x90100120 }, /* use as internal speaker */
+ { 0x18, 0x02a111f0 }, /* use as headset mic, without its own jack detect */
+ { 0x1a, 0x01011020 }, /* use as line out */
+ { },
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MIC
+ },
+ [ALC269VC_FIXUP_ACER_HEADSET_MIC] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x18, 0x02a11030 }, /* use as headset mic */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MIC
+ },
+ [ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x18, 0x01a11130 }, /* use as headset mic, without its own jack detect */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MIC
+ },
};

static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7307,10 +7339,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
SND_PCI_QUIRK(0x1025, 0x1099, "Acer Aspire E5-523G", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK),
+ SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
+ SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
@@ -7536,8 +7571,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
- SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
- SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
+ SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c
index d66412a77873..3f79cd03507c 100644
--- a/sound/soc/sof/sof-pci-dev.c
+++ b/sound/soc/sof/sof-pci-dev.c
@@ -420,6 +420,8 @@ static const struct pci_device_id sof_pci_ids[] = {
#if IS_ENABLED(CONFIG_SND_SOC_SOF_COMETLAKE_H)
{ PCI_DEVICE(0x8086, 0x06c8),
.driver_data = (unsigned long)&cml_desc},
+ { PCI_DEVICE(0x8086, 0xa3f0), /* CML-S */
+ .driver_data = (unsigned long)&cml_desc},
#endif
#if IS_ENABLED(CONFIG_SND_SOC_SOF_TIGERLAKE)
{ PCI_DEVICE(0x8086, 0xa0c8),
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 426c55b45e79..d5706b8b68a1 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -350,6 +350,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
goto add_sync_ep_from_ifnum;
case USB_ID(0x07fd, 0x0008): /* MOTU M Series */
case USB_ID(0x31e9, 0x0002): /* Solid State Logic SSL2+ */
+ case USB_ID(0x0d9a, 0x00df): /* RTX6001 */
ep = 0x81;
ifnum = 2;
goto add_sync_ep_from_ifnum;
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 042a5e8eb79d..8d1805d9e5a7 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3695,4 +3695,56 @@ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */
}
},

+/*
+ * MacroSilicon MS2109 based HDMI capture cards
+ *
+ * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch.
+ * They also need QUIRK_AUDIO_ALIGN_TRANSFER, which makes one wonder if
+ * they pretend to be 96kHz mono as a workaround for stereo being broken
+ * by that...
+ *
+ * They also have swapped L-R channels, but that's for userspace to deal
+ * with.
+ */
+{
+ USB_DEVICE(0x534d, 0x2109),
+ .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+ .vendor_name = "MacroSilicon",
+ .product_name = "MS2109",
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_COMPOSITE,
+ .data = &(const struct snd_usb_audio_quirk[]) {
+ {
+ .ifnum = 2,
+ .type = QUIRK_AUDIO_ALIGN_TRANSFER,
+ },
+ {
+ .ifnum = 2,
+ .type = QUIRK_AUDIO_STANDARD_MIXER,
+ },
+ {
+ .ifnum = 3,
+ .type = QUIRK_AUDIO_FIXED_ENDPOINT,
+ .data = &(const struct audioformat) {
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
+ .channels = 2,
+ .iface = 3,
+ .altsetting = 1,
+ .altset_idx = 1,
+ .attributes = 0,
+ .endpoint = 0x82,
+ .ep_attr = USB_ENDPOINT_XFER_ISOC |
+ USB_ENDPOINT_SYNC_ASYNC,
+ .rates = SNDRV_PCM_RATE_CONTINUOUS,
+ .rate_min = 48000,
+ .rate_max = 48000,
+ }
+ },
+ {
+ .ifnum = -1
+ }
+ }
+ }
+},
+
#undef USB_DEVICE_VENDOR_SPEC
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index d43f9dec6998..e768c02ef2ab 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -596,6 +596,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
}
evsel->core.attr.freq = 0;
evsel->core.attr.sample_period = 1;
+ evsel->no_aux_samples = true;
intel_pt_evsel = evsel;
opts->full_auxtrace = true;
}
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index 7bd73a904b4e..d187e46c2683 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -1055,7 +1055,7 @@ def cbr(id, raw_buf):
cbr = data[0]
MHz = (data[4] + 500) / 1000
percent = ((cbr * 1000 / data[2]) + 5) / 10
- value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, MHz, 4, percent)
+ value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, int(MHz), 4, int(percent))
cbr_file.write(value)

def mwait(id, raw_buf):
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 4b28c9d08d5a..04217e8f535a 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -756,7 +756,8 @@ class CallGraphModel(CallGraphModelBase):
" FROM calls"
" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
- " WHERE symbols.name" + match +
+ " WHERE calls.id <> 0"
+ " AND symbols.name" + match +
" GROUP BY comm_id, thread_id, call_path_id"
" ORDER BY comm_id, thread_id, call_path_id")

@@ -950,7 +951,8 @@ class CallTreeModel(CallGraphModelBase):
" FROM calls"
" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
- " WHERE symbols.name" + match +
+ " WHERE calls.id <> 0"
+ " AND symbols.name" + match +
" ORDER BY comm_id, thread_id, call_time, calls.id")

def FindPath(self, query):
@@ -1016,6 +1018,7 @@ class TreeWindowBase(QMdiSubWindow):
child = self.model.index(row, 0, parent)
if child.internalPointer().dbid == dbid:
found = True
+ self.view.setExpanded(parent, True)
self.view.setCurrentIndex(child)
parent = child
break
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 88c3df24b748..514cef3a17b4 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2224,6 +2224,11 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
return browser->he_selection->thread;
}

+static struct res_sample *hist_browser__selected_res_sample(struct hist_browser *browser)
+{
+ return browser->he_selection ? browser->he_selection->res_samples : NULL;
+}
+
/* Check whether the browser is for 'top' or 'report' */
static inline bool is_report_browser(void *timer)
{
@@ -3170,16 +3175,16 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
&options[nr_options], NULL, NULL, evsel);
nr_options += add_res_sample_opt(browser, &actions[nr_options],
&options[nr_options],
- hist_browser__selected_entry(browser)->res_samples,
- evsel, A_NORMAL);
+ hist_browser__selected_res_sample(browser),
+ evsel, A_NORMAL);
nr_options += add_res_sample_opt(browser, &actions[nr_options],
&options[nr_options],
- hist_browser__selected_entry(browser)->res_samples,
- evsel, A_ASM);
+ hist_browser__selected_res_sample(browser),
+ evsel, A_ASM);
nr_options += add_res_sample_opt(browser, &actions[nr_options],
&options[nr_options],
- hist_browser__selected_entry(browser)->res_samples,
- evsel, A_SOURCE);
+ hist_browser__selected_res_sample(browser),
+ evsel, A_SOURCE);
nr_options += add_switch_opt(browser, &actions[nr_options],
&options[nr_options]);
skip_scripting:
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index abc7fda4a0fe..a844715a352d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1028,12 +1028,12 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
if (callchain && callchain->enabled && !evsel->no_aux_samples)
perf_evsel__config_callchain(evsel, opts, callchain);

- if (opts->sample_intr_regs) {
+ if (opts->sample_intr_regs && !evsel->no_aux_samples) {
attr->sample_regs_intr = opts->sample_intr_regs;
perf_evsel__set_sample_bit(evsel, REGS_INTR);
}

- if (opts->sample_user_regs) {
+ if (opts->sample_user_regs && !evsel->no_aux_samples) {
attr->sample_regs_user |= opts->sample_user_regs;
perf_evsel__set_sample_bit(evsel, REGS_USER);
}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index a1c9eb6d4f40..c5cce3a60476 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1707,6 +1707,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
u64 sample_type = evsel->core.attr.sample_type;
u64 id = evsel->core.id[0];
u8 cpumode;
+ u64 regs[8 * sizeof(sample.intr_regs.mask)];

if (intel_pt_skip_event(pt))
return 0;
@@ -1756,8 +1757,8 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
}

if (sample_type & PERF_SAMPLE_REGS_INTR &&
- items->mask[INTEL_PT_GP_REGS_POS]) {
- u64 regs[sizeof(sample.intr_regs.mask)];
+ (items->mask[INTEL_PT_GP_REGS_POS] ||
+ items->mask[INTEL_PT_XMM_POS])) {
u64 regs_mask = evsel->core.attr.sample_regs_intr;
u64 *pos;