Re: Linux 5.17.3

From: Greg Kroah-Hartman
Date: Wed Apr 13 2022 - 13:57:44 EST


diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst
index 60a29972d3f1..d063aaee5bb7 100644
--- a/Documentation/virt/kvm/devices/vcpu.rst
+++ b/Documentation/virt/kvm/devices/vcpu.rst
@@ -70,7 +70,7 @@ irqchip.
-ENODEV PMUv3 not supported or GIC not initialized
-ENXIO PMUv3 not properly configured or in-kernel irqchip not
configured as required prior to calling this attribute
- -EBUSY PMUv3 already initialized
+ -EBUSY PMUv3 already initialized or a VCPU has already run
-EINVAL Invalid filter range
======= ======================================================

diff --git a/Makefile b/Makefile
index 06d852cad74f..02fbef1a0213 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 5
PATCHLEVEL = 17
-SUBLEVEL = 2
+SUBLEVEL = 3
EXTRAVERSION =
NAME = Superb Owl

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index bfbf0c4c7c5e..39f5c1672f48 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
#define ARM_CPU_PART_CORTEX_A77 0xD0D
#define ARM_CPU_PART_NEOVERSE_V1 0xD40
#define ARM_CPU_PART_CORTEX_A78 0xD41
+#define ARM_CPU_PART_CORTEX_A78AE 0xD42
#define ARM_CPU_PART_CORTEX_X1 0xD44
#define ARM_CPU_PART_CORTEX_A510 0xD46
#define ARM_CPU_PART_CORTEX_A710 0xD47
@@ -123,6 +124,7 @@
#define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
#define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
#define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 031e3a2537fc..8234626a945a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -136,6 +136,7 @@ struct kvm_arch {

/* Memory Tagging Extension enabled for the guest */
bool mte_enabled;
+ bool ran_once;
};

struct kvm_vcpu_fault_info {
diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c
index 771f543464e0..33e0fabc0b79 100644
--- a/arch/arm64/kernel/patching.c
+++ b/arch/arm64/kernel/patching.c
@@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
int i, ret = 0;
struct aarch64_insn_patch *pp = arg;

- /* The first CPU becomes master */
- if (atomic_inc_return(&pp->cpu_count) == 1) {
+ /* The last CPU becomes master */
+ if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) {
for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
pp->new_insns[i]);
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index 5777929d35bf..40be3a7c2c53 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope)
if (scope == SCOPE_LOCAL_CPU) {
static const struct midr_range spectre_bhb_k32_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 27df5c1e6baa..3b46041f2b97 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void)
* Log the CPU info before it is marked online and might get read.
*/
cpuinfo_store_cpu();
+ store_cpu_topology(cpu);

/*
* Enable GIC and timers.
@@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void)

ipi_setup(cpu);

- store_cpu_topology(cpu);
numa_add_cpu(cpu);

/*
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 4dca6ffd03d4..85a2a75f4498 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -634,6 +634,10 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
if (kvm_vm_is_protected(kvm))
kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu);

+ mutex_lock(&kvm->lock);
+ kvm->arch.ran_once = true;
+ mutex_unlock(&kvm->lock);
+
return ret;
}

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index fbcfd4ec6f92..bc771bc1a041 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -924,6 +924,8 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq)

int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
+ struct kvm *kvm = vcpu->kvm;
+
if (!kvm_vcpu_has_pmu(vcpu))
return -ENODEV;

@@ -941,7 +943,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
int __user *uaddr = (int __user *)(long)attr->addr;
int irq;

- if (!irqchip_in_kernel(vcpu->kvm))
+ if (!irqchip_in_kernel(kvm))
return -EINVAL;

if (get_user(irq, uaddr))
@@ -951,7 +953,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
if (!(irq_is_ppi(irq) || irq_is_spi(irq)))
return -EINVAL;

- if (!pmu_irq_is_valid(vcpu->kvm, irq))
+ if (!pmu_irq_is_valid(kvm, irq))
return -EINVAL;

if (kvm_arm_pmu_irq_initialized(vcpu))
@@ -966,7 +968,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
struct kvm_pmu_event_filter filter;
int nr_events;

- nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1;
+ nr_events = kvm_pmu_event_mask(kvm) + 1;

uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr;

@@ -978,12 +980,17 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
filter.action != KVM_PMU_EVENT_DENY))
return -EINVAL;

- mutex_lock(&vcpu->kvm->lock);
+ mutex_lock(&kvm->lock);
+
+ if (kvm->arch.ran_once) {
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
+ }

- if (!vcpu->kvm->arch.pmu_filter) {
- vcpu->kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT);
- if (!vcpu->kvm->arch.pmu_filter) {
- mutex_unlock(&vcpu->kvm->lock);
+ if (!kvm->arch.pmu_filter) {
+ kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT);
+ if (!kvm->arch.pmu_filter) {
+ mutex_unlock(&kvm->lock);
return -ENOMEM;
}

@@ -994,17 +1001,17 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
* events, the default is to allow.
*/
if (filter.action == KVM_PMU_EVENT_ALLOW)
- bitmap_zero(vcpu->kvm->arch.pmu_filter, nr_events);
+ bitmap_zero(kvm->arch.pmu_filter, nr_events);
else
- bitmap_fill(vcpu->kvm->arch.pmu_filter, nr_events);
+ bitmap_fill(kvm->arch.pmu_filter, nr_events);
}

if (filter.action == KVM_PMU_EVENT_ALLOW)
- bitmap_set(vcpu->kvm->arch.pmu_filter, filter.base_event, filter.nevents);
+ bitmap_set(kvm->arch.pmu_filter, filter.base_event, filter.nevents);
else
- bitmap_clear(vcpu->kvm->arch.pmu_filter, filter.base_event, filter.nevents);
+ bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents);

- mutex_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&kvm->lock);

return 0;
}
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index 3f9ea47a10cd..b998301f179c 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -510,7 +510,7 @@ efuse: efuse@d0 {
#address-cells = <1>;
#size-cells = <1>;

- eth0_addr: eth-mac-addr@0x22 {
+ eth0_addr: eth-mac-addr@22 {
reg = <0x22 0x6>;
};
};
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index bb36a400203d..8c56b862fd9c 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -16,7 +16,7 @@ static inline void setup_8250_early_printk_port(unsigned long base,
unsigned int reg_shift, unsigned int timeout) {}
#endif

-extern void set_handler(unsigned long offset, void *addr, unsigned long len);
+void set_handler(unsigned long offset, const void *addr, unsigned long len);
extern void set_uncached_handler(unsigned long offset, void *addr, unsigned long len);

typedef void (*vi_handler_t)(void);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index a486486b2355..246c6a6b0261 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2091,19 +2091,19 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
* If no shadow set is selected then use the default handler
* that does normal register saving and standard interrupt exit
*/
- extern char except_vec_vi, except_vec_vi_lui;
- extern char except_vec_vi_ori, except_vec_vi_end;
- extern char rollback_except_vec_vi;
- char *vec_start = using_rollback_handler() ?
- &rollback_except_vec_vi : &except_vec_vi;
+ extern const u8 except_vec_vi[], except_vec_vi_lui[];
+ extern const u8 except_vec_vi_ori[], except_vec_vi_end[];
+ extern const u8 rollback_except_vec_vi[];
+ const u8 *vec_start = using_rollback_handler() ?
+ rollback_except_vec_vi : except_vec_vi;
#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
- const int lui_offset = &except_vec_vi_lui - vec_start + 2;
- const int ori_offset = &except_vec_vi_ori - vec_start + 2;
+ const int lui_offset = except_vec_vi_lui - vec_start + 2;
+ const int ori_offset = except_vec_vi_ori - vec_start + 2;
#else
- const int lui_offset = &except_vec_vi_lui - vec_start;
- const int ori_offset = &except_vec_vi_ori - vec_start;
+ const int lui_offset = except_vec_vi_lui - vec_start;
+ const int ori_offset = except_vec_vi_ori - vec_start;
#endif
- const int handler_len = &except_vec_vi_end - vec_start;
+ const int handler_len = except_vec_vi_end - vec_start;

if (handler_len > VECTORSPACING) {
/*
@@ -2311,7 +2311,7 @@ void per_cpu_trap_init(bool is_boot_cpu)
}

/* Install CPU exception handler */
-void set_handler(unsigned long offset, void *addr, unsigned long size)
+void set_handler(unsigned long offset, const void *addr, unsigned long size)
{
#ifdef CONFIG_CPU_MICROMIPS
memcpy((void *)(ebase + offset), ((unsigned char *)addr - 1), size);
diff --git a/arch/mips/ralink/ill_acc.c b/arch/mips/ralink/ill_acc.c
index 115a69fc20ca..f395ae218470 100644
--- a/arch/mips/ralink/ill_acc.c
+++ b/arch/mips/ralink/ill_acc.c
@@ -61,6 +61,7 @@ static int __init ill_acc_of_setup(void)
pdev = of_find_device_by_node(np);
if (!pdev) {
pr_err("%pOFn: failed to lookup pdev\n", np);
+ of_node_put(np);
return -EINVAL;
}

diff --git a/arch/parisc/kernel/patch.c b/arch/parisc/kernel/patch.c
index 80a0ab372802..e59574f65e64 100644
--- a/arch/parisc/kernel/patch.c
+++ b/arch/parisc/kernel/patch.c
@@ -40,10 +40,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags,

*need_unmap = 1;
set_fixmap(fixmap, page_to_phys(page));
- if (flags)
- raw_spin_lock_irqsave(&patch_lock, *flags);
- else
- __acquire(&patch_lock);
+ raw_spin_lock_irqsave(&patch_lock, *flags);

return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK));
}
@@ -52,10 +49,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
{
clear_fixmap(fixmap);

- if (flags)
- raw_spin_unlock_irqrestore(&patch_lock, *flags);
- else
- __release(&patch_lock);
+ raw_spin_unlock_irqrestore(&patch_lock, *flags);
}

void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
@@ -67,8 +61,9 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
int mapped;

/* Make sure we don't have any aliases in cache */
- flush_kernel_vmap_range(addr, len);
- flush_icache_range(start, end);
+ flush_kernel_dcache_range_asm(start, end);
+ flush_kernel_icache_range_asm(start, end);
+ flush_tlb_kernel_range(start, end);

p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, &mapped);

@@ -81,8 +76,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
* We're crossing a page boundary, so
* need to remap
*/
- flush_kernel_vmap_range((void *)fixmap,
- (p-fixmap) * sizeof(*p));
+ flush_kernel_dcache_range_asm((unsigned long)fixmap,
+ (unsigned long)p);
+ flush_tlb_kernel_range((unsigned long)fixmap,
+ (unsigned long)p);
if (mapped)
patch_unmap(FIX_TEXT_POKE0, &flags);
p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags,
@@ -90,10 +87,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len)
}
}

- flush_kernel_vmap_range((void *)fixmap, (p-fixmap) * sizeof(*p));
+ flush_kernel_dcache_range_asm((unsigned long)fixmap, (unsigned long)p);
+ flush_tlb_kernel_range((unsigned long)fixmap, (unsigned long)p);
if (mapped)
patch_unmap(FIX_TEXT_POKE0, &flags);
- flush_icache_range(start, end);
}

void __kprobes __patch_text(void *addr, u32 insn)
diff --git a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
index 099a598c74c0..bfe1ed5be337 100644
--- a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi
@@ -139,12 +139,12 @@ pca9546@77 {
fman@400000 {
ethernet@e6000 {
phy-handle = <&phy_rgmii_0>;
- phy-connection-type = "rgmii";
+ phy-connection-type = "rgmii-id";
};

ethernet@e8000 {
phy-handle = <&phy_rgmii_1>;
- phy-connection-type = "rgmii";
+ phy-connection-type = "rgmii-id";
};

mdio0: mdio@fc000 {
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index fc28f46d2f9d..5404f7abbcf8 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -612,7 +612,7 @@ DECLARE_INTERRUPT_HANDLER_RAW(do_slb_fault);
DECLARE_INTERRUPT_HANDLER(do_bad_segment_interrupt);

/* hash_utils.c */
-DECLARE_INTERRUPT_HANDLER_RAW(do_hash_fault);
+DECLARE_INTERRUPT_HANDLER(do_hash_fault);

/* fault.c */
DECLARE_INTERRUPT_HANDLER(do_page_fault);
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 254687258f42..f2c5c26869f1 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn)
#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)

-#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr))
+#define virt_addr_valid(vaddr) ({ \
+ unsigned long _addr = (unsigned long)vaddr; \
+ _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \
+ pfn_valid(virt_to_pfn(_addr)); \
+})

/*
* On Book-E parts we need __va to parse the device tree and we can't
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 733e6ef36758..1f42aabbbab3 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1313,6 +1313,12 @@ int __init early_init_dt_scan_rtas(unsigned long node,
entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL);
sizep = of_get_flat_dt_prop(node, "rtas-size", NULL);

+#ifdef CONFIG_PPC64
+ /* need this feature to decide the crashkernel offset */
+ if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL))
+ powerpc_firmware_features |= FW_FEATURE_LPAR;
+#endif
+
if (basep && entryp && sizep) {
rtas.base = *basep;
rtas.entry = *entryp;
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
index a0a78aba2083..1ee4640a2641 100644
--- a/arch/powerpc/kernel/secvar-sysfs.c
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -26,15 +26,18 @@ static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr,
const char *format;

node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend");
- if (!of_device_is_available(node))
- return -ENODEV;
+ if (!of_device_is_available(node)) {
+ rc = -ENODEV;
+ goto out;
+ }

rc = of_property_read_string(node, "format", &format);
if (rc)
- return rc;
+ goto out;

rc = sprintf(buf, "%s\n", format);

+out:
of_node_put(node);

return rc;
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 8b68d9f91a03..abf5897ae88c 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -134,11 +134,18 @@ void __init reserve_crashkernel(void)
if (!crashk_res.start) {
#ifdef CONFIG_PPC64
/*
- * On 64bit we split the RMO in half but cap it at half of
- * a small SLB (128MB) since the crash kernel needs to place
- * itself and some stacks to be in the first segment.
+ * On the LPAR platform place the crash kernel to mid of
+ * RMA size (512MB or more) to ensure the crash kernel
+ * gets enough space to place itself and some stack to be
+ * in the first segment. At the same time normal kernel
+ * also get enough space to allocate memory for essential
+ * system resource in the first segment. Keep the crash
+ * kernel starts at 128MB offset on other platforms.
*/
- crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2));
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ crashk_res.start = ppc64_rma_size / 2;
+ else
+ crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2));
#else
crashk_res.start = KDUMP_KERNELBASE;
#endif
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 05e003eb5d90..e42d1c609e47 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
*/
ld r10,HSTATE_SCRATCH0(r13)
cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK
- beq machine_check_common
+ beq .Lcall_machine_check_common

cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET
- beq system_reset_common
+ beq .Lcall_system_reset_common

b .
+
+.Lcall_machine_check_common:
+ b machine_check_common
+
+.Lcall_system_reset_common:
+ b system_reset_common
#endif
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 906d43463366..00c68e7fb11e 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -43,9 +43,14 @@ int raw_patch_instruction(u32 *addr, ppc_inst_t instr)
#ifdef CONFIG_STRICT_KERNEL_RWX
static DEFINE_PER_CPU(struct vm_struct *, text_poke_area);

+static int map_patch_area(void *addr, unsigned long text_poke_addr);
+static void unmap_patch_area(unsigned long addr);
+
static int text_area_cpu_up(unsigned int cpu)
{
struct vm_struct *area;
+ unsigned long addr;
+ int err;

area = get_vm_area(PAGE_SIZE, VM_ALLOC);
if (!area) {
@@ -53,6 +58,15 @@ static int text_area_cpu_up(unsigned int cpu)
cpu);
return -1;
}
+
+ // Map/unmap the area to ensure all page tables are pre-allocated
+ addr = (unsigned long)area->addr;
+ err = map_patch_area(empty_zero_page, addr);
+ if (err)
+ return err;
+
+ unmap_patch_area(addr);
+
this_cpu_write(text_poke_area, area);

return 0;
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 7abf82a698d3..985cabdd7f67 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1621,8 +1621,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);

-DECLARE_INTERRUPT_HANDLER(__do_hash_fault);
-DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
+DEFINE_INTERRUPT_HANDLER(do_hash_fault)
{
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
@@ -1681,35 +1680,6 @@ DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
}
}

-/*
- * The _RAW interrupt entry checks for the in_nmi() case before
- * running the full handler.
- */
-DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
-{
- /*
- * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
- * don't call hash_page, just fail the fault. This is required to
- * prevent re-entrancy problems in the hash code, namely perf
- * interrupts hitting while something holds H_PAGE_BUSY, and taking a
- * hash fault. See the comment in hash_preload().
- *
- * We come here as a result of a DSI at a point where we don't want
- * to call hash_page, such as when we are accessing memory (possibly
- * user memory) inside a PMU interrupt that occurred while interrupts
- * were soft-disabled. We want to invoke the exception handler for
- * the access, or panic if there isn't a handler.
- */
- if (unlikely(in_nmi())) {
- do_bad_page_fault_segv(regs);
- return 0;
- }
-
- __do_hash_fault(regs);
-
- return 0;
-}
-
#ifdef CONFIG_PPC_MM_SLICES
static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
{
@@ -1776,26 +1746,18 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
#endif /* CONFIG_PPC_64K_PAGES */

/*
- * __hash_page_* must run with interrupts off, as it sets the
- * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any
- * time and may take a hash fault reading the user stack, see
- * read_user_stack_slow() in the powerpc/perf code.
- *
- * If that takes a hash fault on the same page as we lock here, it
- * will bail out when seeing H_PAGE_BUSY set, and retry the access
- * leading to an infinite loop.
+ * __hash_page_* must run with interrupts off, including PMI interrupts
+ * off, as it sets the H_PAGE_BUSY bit.
*
- * Disabling interrupts here does not prevent perf interrupts, but it
- * will prevent them taking hash faults (see the NMI test in
- * do_hash_page), then read_user_stack's copy_from_user_nofault will
- * fail and perf will fall back to read_user_stack_slow(), which
- * walks the Linux page tables.
+ * It's otherwise possible for perf interrupts to hit at any time and
+ * may take a hash fault reading the user stack, which could take a
+ * hash miss and deadlock on the same H_PAGE_BUSY bit.
*
* Interrupts must also be off for the duration of the
* mm_is_thread_local test and update, to prevent preempt running the
* mm on another CPU (XXX: this may be racy vs kthread_use_mm).
*/
- local_irq_save(flags);
+ powerpc_local_irq_pmu_save(flags);

/* Is that local to this CPU ? */
if (mm_is_thread_local(mm))
@@ -1820,7 +1782,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
mm_ctx_user_psize(&mm->context),
pte_val(*ptep));

- local_irq_restore(flags);
+ powerpc_local_irq_pmu_restore(flags);
}

/*
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 8e301cd8925b..4d221d033804 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -255,7 +255,7 @@ void __init mem_init(void)
#endif

high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
- set_max_mapnr(max_low_pfn);
+ set_max_mapnr(max_pfn);

kasan_late_init();

diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index 3bb9d168e3b3..85753e32a4de 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c
@@ -15,12 +15,14 @@
#include <asm/pgtable.h>


+static pte_basic_t pte_update_delta(pte_t *ptep, unsigned long addr,
+ unsigned long old, unsigned long new)
+{
+ return pte_update(&init_mm, addr, ptep, old & ~new, new & ~old, 0);
+}
+
/*
- * Updates the attributes of a page in three steps:
- *
- * 1. take the page_table_lock
- * 2. install the new entry with the updated attributes
- * 3. flush the TLB
+ * Updates the attributes of a page atomically.
*
* This sequence is safe against concurrent updates, and also allows updating the
* attributes of a page currently being executed or accessed.
@@ -28,25 +30,21 @@
static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
{
long action = (long)data;
- pte_t pte;

- spin_lock(&init_mm.page_table_lock);
-
- pte = ptep_get(ptep);
-
- /* modify the PTE bits as desired, then apply */
+ /* modify the PTE bits as desired */
switch (action) {
case SET_MEMORY_RO:
- pte = pte_wrprotect(pte);
+ /* Don't clear DIRTY bit */
+ pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_RO);
break;
case SET_MEMORY_RW:
- pte = pte_mkwrite(pte_mkdirty(pte));
+ pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_RW);
break;
case SET_MEMORY_NX:
- pte = pte_exprotect(pte);
+ pte_update_delta(ptep, addr, _PAGE_KERNEL_ROX, _PAGE_KERNEL_RO);
break;
case SET_MEMORY_X:
- pte = pte_mkexec(pte);
+ pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_ROX);
break;
case SET_MEMORY_NP:
pte_update(&init_mm, addr, ptep, _PAGE_PRESENT, 0, 0);
@@ -59,16 +57,12 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
break;
}

- pte_update(&init_mm, addr, ptep, ~0UL, pte_val(pte), 0);
-
/* See ptesync comment in radix__set_pte_at() */
if (radix_enabled())
asm volatile("ptesync": : :"memory");

flush_tlb_kernel_range(addr, addr + PAGE_SIZE);

- spin_unlock(&init_mm.page_table_lock);
-
return 0;
}

diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h
index d6fa6e25234f..19a8d051ddf1 100644
--- a/arch/powerpc/perf/callchain.h
+++ b/arch/powerpc/perf/callchain.h
@@ -2,7 +2,6 @@
#ifndef _POWERPC_PERF_CALLCHAIN_H
#define _POWERPC_PERF_CALLCHAIN_H

-int read_user_stack_slow(const void __user *ptr, void *buf, int nb);
void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs);
void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
@@ -26,17 +25,11 @@ static inline int __read_user_stack(const void __user *ptr, void *ret,
size_t size)
{
unsigned long addr = (unsigned long)ptr;
- int rc;

if (addr > TASK_SIZE - size || (addr & (size - 1)))
return -EFAULT;

- rc = copy_from_user_nofault(ret, ptr, size);
-
- if (IS_ENABLED(CONFIG_PPC64) && !radix_enabled() && rc)
- return read_user_stack_slow(ptr, ret, size);
-
- return rc;
+ return copy_from_user_nofault(ret, ptr, size);
}

#endif /* _POWERPC_PERF_CALLCHAIN_H */
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 8d0df4226328..488e8a21a11e 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -18,33 +18,6 @@

#include "callchain.h"

-/*
- * On 64-bit we don't want to invoke hash_page on user addresses from
- * interrupt context, so if the access faults, we read the page tables
- * to find which page (if any) is mapped and access it directly. Radix
- * has no need for this so it doesn't use read_user_stack_slow.
- */
-int read_user_stack_slow(const void __user *ptr, void *buf, int nb)
-{
-
- unsigned long addr = (unsigned long) ptr;
- unsigned long offset;
- struct page *page;
- void *kaddr;
-
- if (get_user_page_fast_only(addr, FOLL_WRITE, &page)) {
- kaddr = page_address(page);
-
- /* align address to page boundary */
- offset = addr & ~PAGE_MASK;
-
- memcpy(buf, kaddr + offset, nb);
- put_page(page);
- return 0;
- }
- return -EFAULT;
-}
-
static int read_user_stack_64(const unsigned long __user *ptr, unsigned long *ret)
{
return __read_user_stack(ptr, ret, sizeof(*ret));
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 87bc1929ee5a..e2e1fec91c6e 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -107,6 +107,7 @@ config PPC_BOOK3S_64

config PPC_BOOK3E_64
bool "Embedded processors"
+ select PPC_FSL_BOOK3E
select PPC_FPU # Make it a choice ?
select PPC_SMP_MUXED_IPI
select PPC_DOORBELL
@@ -295,7 +296,7 @@ config FSL_BOOKE
config PPC_FSL_BOOK3E
bool
select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64
- select FSL_EMB_PERFMON
+ imply FSL_EMB_PERFMON
select PPC_SMP_MUXED_IPI
select PPC_DOORBELL
select PPC_KUEP
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 89c86f32aff8..bb5bda6b2357 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -1791,7 +1791,7 @@ static int xive_ipi_debug_show(struct seq_file *m, void *private)
if (xive_ops->debug_show)
xive_ops->debug_show(m, private);

- for_each_possible_cpu(cpu)
+ for_each_online_cpu(cpu)
xive_debug_show_ipi(m, cpu);
return 0;
}
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
index 07d1d2152ba5..e0609e1f0864 100644
--- a/arch/riscv/lib/memmove.S
+++ b/arch/riscv/lib/memmove.S
@@ -1,64 +1,316 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 Michael T. Kloos <michael@xxxxxxxxxxxxxxxx>
+ */

#include <linux/linkage.h>
#include <asm/asm.h>

-ENTRY(__memmove)
-WEAK(memmove)
- move t0, a0
- move t1, a1
-
- beq a0, a1, exit_memcpy
- beqz a2, exit_memcpy
- srli t2, a2, 0x2
-
- slt t3, a0, a1
- beqz t3, do_reverse
-
- andi a2, a2, 0x3
- li t4, 1
- beqz t2, byte_copy
-
-word_copy:
- lw t3, 0(a1)
- addi t2, t2, -1
- addi a1, a1, 4
- sw t3, 0(a0)
- addi a0, a0, 4
- bnez t2, word_copy
- beqz a2, exit_memcpy
- j byte_copy
-
-do_reverse:
- add a0, a0, a2
- add a1, a1, a2
- andi a2, a2, 0x3
- li t4, -1
- beqz t2, reverse_byte_copy
-
-reverse_word_copy:
- addi a1, a1, -4
- addi t2, t2, -1
- lw t3, 0(a1)
- addi a0, a0, -4
- sw t3, 0(a0)
- bnez t2, reverse_word_copy
- beqz a2, exit_memcpy
-
-reverse_byte_copy:
- addi a0, a0, -1
- addi a1, a1, -1
+SYM_FUNC_START(__memmove)
+SYM_FUNC_START_WEAK(memmove)
+ /*
+ * Returns
+ * a0 - dest
+ *
+ * Parameters
+ * a0 - Inclusive first byte of dest
+ * a1 - Inclusive first byte of src
+ * a2 - Length of copy n
+ *
+ * Because the return matches the parameter register a0,
+ * we will not clobber or modify that register.
+ *
+ * Note: This currently only works on little-endian.
+ * To port to big-endian, reverse the direction of shifts
+ * in the 2 misaligned fixup copy loops.
+ */

+ /* Return if nothing to do */
+ beq a0, a1, return_from_memmove
+ beqz a2, return_from_memmove
+
+ /*
+ * Register Uses
+ * Forward Copy: a1 - Index counter of src
+ * Reverse Copy: a4 - Index counter of src
+ * Forward Copy: t3 - Index counter of dest
+ * Reverse Copy: t4 - Index counter of dest
+ * Both Copy Modes: t5 - Inclusive first multibyte/aligned of dest
+ * Both Copy Modes: t6 - Non-Inclusive last multibyte/aligned of dest
+ * Both Copy Modes: t0 - Link / Temporary for load-store
+ * Both Copy Modes: t1 - Temporary for load-store
+ * Both Copy Modes: t2 - Temporary for load-store
+ * Both Copy Modes: a5 - dest to src alignment offset
+ * Both Copy Modes: a6 - Shift ammount
+ * Both Copy Modes: a7 - Inverse Shift ammount
+ * Both Copy Modes: a2 - Alternate breakpoint for unrolled loops
+ */
+
+ /*
+ * Solve for some register values now.
+ * Byte copy does not need t5 or t6.
+ */
+ mv t3, a0
+ add t4, a0, a2
+ add a4, a1, a2
+
+ /*
+ * Byte copy if copying less than (2 * SZREG) bytes. This can
+ * cause problems with the bulk copy implementation and is
+ * small enough not to bother.
+ */
+ andi t0, a2, -(2 * SZREG)
+ beqz t0, byte_copy
+
+ /*
+ * Now solve for t5 and t6.
+ */
+ andi t5, t3, -SZREG
+ andi t6, t4, -SZREG
+ /*
+ * If dest(Register t3) rounded down to the nearest naturally
+ * aligned SZREG address, does not equal dest, then add SZREG
+ * to find the low-bound of SZREG alignment in the dest memory
+ * region. Note that this could overshoot the dest memory
+ * region if n is less than SZREG. This is one reason why
+ * we always byte copy if n is less than SZREG.
+ * Otherwise, dest is already naturally aligned to SZREG.
+ */
+ beq t5, t3, 1f
+ addi t5, t5, SZREG
+ 1:
+
+ /*
+ * If the dest and src are co-aligned to SZREG, then there is
+ * no need for the full rigmarole of a full misaligned fixup copy.
+ * Instead, do a simpler co-aligned copy.
+ */
+ xor t0, a0, a1
+ andi t1, t0, (SZREG - 1)
+ beqz t1, coaligned_copy
+ /* Fall through to misaligned fixup copy */
+
+misaligned_fixup_copy:
+ bltu a1, a0, misaligned_fixup_copy_reverse
+
+misaligned_fixup_copy_forward:
+ jal t0, byte_copy_until_aligned_forward
+
+ andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */
+ slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
+ sub a5, a1, t3 /* Find the difference between src and dest */
+ andi a1, a1, -SZREG /* Align the src pointer */
+ addi a2, t6, SZREG /* The other breakpoint for the unrolled loop*/
+
+ /*
+ * Compute The Inverse Shift
+ * a7 = XLEN - a6 = XLEN + -a6
+ * 2s complement negation to find the negative: -a6 = ~a6 + 1
+ * Add that to XLEN. XLEN = SZREG * 8.
+ */
+ not a7, a6
+ addi a7, a7, (SZREG * 8 + 1)
+
+ /*
+ * Fix Misalignment Copy Loop - Forward
+ * load_val0 = load_ptr[0];
+ * do {
+ * load_val1 = load_ptr[1];
+ * store_ptr += 2;
+ * store_ptr[0 - 2] = (load_val0 >> {a6}) | (load_val1 << {a7});
+ *
+ * if (store_ptr == {a2})
+ * break;
+ *
+ * load_val0 = load_ptr[2];
+ * load_ptr += 2;
+ * store_ptr[1 - 2] = (load_val1 >> {a6}) | (load_val0 << {a7});
+ *
+ * } while (store_ptr != store_ptr_end);
+ * store_ptr = store_ptr_end;
+ */
+
+ REG_L t0, (0 * SZREG)(a1)
+ 1:
+ REG_L t1, (1 * SZREG)(a1)
+ addi t3, t3, (2 * SZREG)
+ srl t0, t0, a6
+ sll t2, t1, a7
+ or t2, t0, t2
+ REG_S t2, ((0 * SZREG) - (2 * SZREG))(t3)
+
+ beq t3, a2, 2f
+
+ REG_L t0, (2 * SZREG)(a1)
+ addi a1, a1, (2 * SZREG)
+ srl t1, t1, a6
+ sll t2, t0, a7
+ or t2, t1, t2
+ REG_S t2, ((1 * SZREG) - (2 * SZREG))(t3)
+
+ bne t3, t6, 1b
+ 2:
+ mv t3, t6 /* Fix the dest pointer in case the loop was broken */
+
+ add a1, t3, a5 /* Restore the src pointer */
+ j byte_copy_forward /* Copy any remaining bytes */
+
+misaligned_fixup_copy_reverse:
+ jal t0, byte_copy_until_aligned_reverse
+
+ andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */
+ slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */
+ sub a5, a4, t4 /* Find the difference between src and dest */
+ andi a4, a4, -SZREG /* Align the src pointer */
+ addi a2, t5, -SZREG /* The other breakpoint for the unrolled loop*/
+
+ /*
+ * Compute The Inverse Shift
+ * a7 = XLEN - a6 = XLEN + -a6
+ * 2s complement negation to find the negative: -a6 = ~a6 + 1
+ * Add that to XLEN. XLEN = SZREG * 8.
+ */
+ not a7, a6
+ addi a7, a7, (SZREG * 8 + 1)
+
+ /*
+ * Fix Misalignment Copy Loop - Reverse
+ * load_val1 = load_ptr[0];
+ * do {
+ * load_val0 = load_ptr[-1];
+ * store_ptr -= 2;
+ * store_ptr[1] = (load_val0 >> {a6}) | (load_val1 << {a7});
+ *
+ * if (store_ptr == {a2})
+ * break;
+ *
+ * load_val1 = load_ptr[-2];
+ * load_ptr -= 2;
+ * store_ptr[0] = (load_val1 >> {a6}) | (load_val0 << {a7});
+ *
+ * } while (store_ptr != store_ptr_end);
+ * store_ptr = store_ptr_end;
+ */
+
+ REG_L t1, ( 0 * SZREG)(a4)
+ 1:
+ REG_L t0, (-1 * SZREG)(a4)
+ addi t4, t4, (-2 * SZREG)
+ sll t1, t1, a7
+ srl t2, t0, a6
+ or t2, t1, t2
+ REG_S t2, ( 1 * SZREG)(t4)
+
+ beq t4, a2, 2f
+
+ REG_L t1, (-2 * SZREG)(a4)
+ addi a4, a4, (-2 * SZREG)
+ sll t0, t0, a7
+ srl t2, t1, a6
+ or t2, t0, t2
+ REG_S t2, ( 0 * SZREG)(t4)
+
+ bne t4, t5, 1b
+ 2:
+ mv t4, t5 /* Fix the dest pointer in case the loop was broken */
+
+ add a4, t4, a5 /* Restore the src pointer */
+ j byte_copy_reverse /* Copy any remaining bytes */
+
+/*
+ * Simple copy loops for SZREG co-aligned memory locations.
+ * These also make calls to do byte copies for any unaligned
+ * data at their terminations.
+ */
+coaligned_copy:
+ bltu a1, a0, coaligned_copy_reverse
+
+coaligned_copy_forward:
+ jal t0, byte_copy_until_aligned_forward
+
+ 1:
+ REG_L t1, ( 0 * SZREG)(a1)
+ addi a1, a1, SZREG
+ addi t3, t3, SZREG
+ REG_S t1, (-1 * SZREG)(t3)
+ bne t3, t6, 1b
+
+ j byte_copy_forward /* Copy any remaining bytes */
+
+coaligned_copy_reverse:
+ jal t0, byte_copy_until_aligned_reverse
+
+ 1:
+ REG_L t1, (-1 * SZREG)(a4)
+ addi a4, a4, -SZREG
+ addi t4, t4, -SZREG
+ REG_S t1, ( 0 * SZREG)(t4)
+ bne t4, t5, 1b
+
+ j byte_copy_reverse /* Copy any remaining bytes */
+
+/*
+ * These are basically sub-functions within the function. They
+ * are used to byte copy until the dest pointer is in alignment.
+ * At which point, a bulk copy method can be used by the
+ * calling code. These work on the same registers as the bulk
+ * copy loops. Therefore, the register values can be picked
+ * up from where they were left and we avoid code duplication
+ * without any overhead except the call in and return jumps.
+ */
+byte_copy_until_aligned_forward:
+ beq t3, t5, 2f
+ 1:
+ lb t1, 0(a1)
+ addi a1, a1, 1
+ addi t3, t3, 1
+ sb t1, -1(t3)
+ bne t3, t5, 1b
+ 2:
+ jalr zero, 0x0(t0) /* Return to multibyte copy loop */
+
+byte_copy_until_aligned_reverse:
+ beq t4, t6, 2f
+ 1:
+ lb t1, -1(a4)
+ addi a4, a4, -1
+ addi t4, t4, -1
+ sb t1, 0(t4)
+ bne t4, t6, 1b
+ 2:
+ jalr zero, 0x0(t0) /* Return to multibyte copy loop */
+
+/*
+ * Simple byte copy loops.
+ * These will byte copy until they reach the end of data to copy.
+ * At that point, they will call to return from memmove.
+ */
byte_copy:
- lb t3, 0(a1)
- addi a2, a2, -1
- sb t3, 0(a0)
- add a1, a1, t4
- add a0, a0, t4
- bnez a2, byte_copy
-
-exit_memcpy:
- move a0, t0
- move a1, t1
- ret
-END(__memmove)
+ bltu a1, a0, byte_copy_reverse
+
+byte_copy_forward:
+ beq t3, t4, 2f
+ 1:
+ lb t1, 0(a1)
+ addi a1, a1, 1
+ addi t3, t3, 1
+ sb t1, -1(t3)
+ bne t3, t4, 1b
+ 2:
+ ret
+
+byte_copy_reverse:
+ beq t4, t3, 2f
+ 1:
+ lb t1, -1(a4)
+ addi a4, a4, -1
+ addi t4, t4, -1
+ sb t1, 0(t4)
+ bne t4, t3, 1b
+ 2:
+
+return_from_memmove:
+ ret
+
+SYM_FUNC_END(memmove)
+SYM_FUNC_END(__memmove)
diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h
index f512704a9ec7..22b39de73c24 100644
--- a/arch/um/include/asm/xor.h
+++ b/arch/um/include/asm/xor.h
@@ -4,8 +4,10 @@

#ifdef CONFIG_64BIT
#undef CONFIG_X86_32
+#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_sse_pf64))
#else
#define CONFIG_X86_32 1
+#define TT_CPU_INF_XOR_DEFAULT (AVX_SELECT(&xor_block_8regs))
#endif

#include <asm/cpufeature.h>
@@ -16,7 +18,7 @@
#undef XOR_SELECT_TEMPLATE
/* pick an arbitrary one - measuring isn't possible with inf-cpu */
#define XOR_SELECT_TEMPLATE(x) \
- (time_travel_mode == TT_MODE_INFCPU ? &xor_block_8regs : NULL)
+ (time_travel_mode == TT_MODE_INFCPU ? TT_CPU_INF_XOR_DEFAULT : x))
#endif

#endif
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9f5bd41bf660..d0ecc4005df3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2837,6 +2837,11 @@ config IA32_AOUT
config X86_X32
bool "x32 ABI for 64-bit mode"
depends on X86_64
+ # llvm-objcopy does not convert x86_64 .note.gnu.property or
+ # compressed debug sections to x86_x32 properly:
+ # https://github.com/ClangBuiltLinux/linux/issues/514
+ # https://github.com/ClangBuiltLinux/linux/issues/1141
+ depends on $(success,$(OBJCOPY) --version | head -n1 | grep -qv llvm)
help
Include code to run binaries for the x32 native 32-bit ABI
for 64-bit processors. An x32 process gets access to the
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a3c7ca876aeb..d87c9b246a8f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -281,7 +281,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
- INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE),
INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE),
INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE),
EVENT_EXTRA_END
@@ -5515,7 +5515,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con
/* Disabled fixed counters which are not in CPUID */
c->idxmsk64 &= intel_ctrl;

- if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES)
+ /*
+ * Don't extend the pseudo-encoding to the
+ * generic counters
+ */
+ if (!use_fixed_pseudo_encoding(c->code))
c->idxmsk64 |= (1ULL << num_counters) - 1;
}
c->idxmsk64 &=
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index c878fed3056f..fbcfec4dc4cc 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -154,24 +154,24 @@

# define DEFINE_EXTABLE_TYPE_REG \
".macro extable_type_reg type:req reg:req\n" \
- ".set found, 0\n" \
- ".set regnr, 0\n" \
+ ".set .Lfound, 0\n" \
+ ".set .Lregnr, 0\n" \
".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \
".ifc \\reg, %%\\rs\n" \
- ".set found, found+1\n" \
- ".long \\type + (regnr << 8)\n" \
+ ".set .Lfound, .Lfound+1\n" \
+ ".long \\type + (.Lregnr << 8)\n" \
".endif\n" \
- ".set regnr, regnr+1\n" \
+ ".set .Lregnr, .Lregnr+1\n" \
".endr\n" \
- ".set regnr, 0\n" \
+ ".set .Lregnr, 0\n" \
".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \
".ifc \\reg, %%\\rs\n" \
- ".set found, found+1\n" \
- ".long \\type + (regnr << 8)\n" \
+ ".set .Lfound, .Lfound+1\n" \
+ ".long \\type + (.Lregnr << 8)\n" \
".endif\n" \
- ".set regnr, regnr+1\n" \
+ ".set .Lregnr, .Lregnr+1\n" \
".endr\n" \
- ".if (found != 1)\n" \
+ ".if (.Lfound != 1)\n" \
".error \"extable_type_reg: bad register argument\"\n" \
".endif\n" \
".endm\n"
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index bab883c0b6fe..66570e95af39 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -77,9 +77,9 @@ do { \
*/
#define __WARN_FLAGS(flags) \
do { \
- __auto_type f = BUGFLAG_WARNING|(flags); \
+ __auto_type __flags = BUGFLAG_WARNING|(flags); \
instrumentation_begin(); \
- _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \
+ _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \
instrumentation_end(); \
} while (0)

diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index ae9d40f6c706..05af249d6bec 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -99,7 +99,8 @@
}

#define ASM_CALL_ARG0 \
- "call %P[__func] \n"
+ "call %P[__func] \n" \
+ ASM_REACHABLE

#define ASM_CALL_ARG1 \
"movq %[arg1], %%rdi \n" \
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ec9830d2aabf..17b4e1808b8e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -509,6 +509,7 @@ struct kvm_pmu {
u64 global_ctrl_mask;
u64 global_ovf_ctrl_mask;
u64 reserved_bits;
+ u64 raw_event_mask;
u8 version;
struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
index b85147d75626..d71c7e8b738d 100644
--- a/arch/x86/include/asm/msi.h
+++ b/arch/x86/include/asm/msi.h
@@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
/* Structs and defines for the X86 specific MSI message format */

typedef struct x86_msi_data {
- u32 vector : 8,
- delivery_mode : 3,
- dest_mode_logical : 1,
- reserved : 2,
- active_low : 1,
- is_level : 1;
-
- u32 dmar_subhandle;
+ union {
+ struct {
+ u32 vector : 8,
+ delivery_mode : 3,
+ dest_mode_logical : 1,
+ reserved : 2,
+ active_low : 1,
+ is_level : 1;
+ };
+ u32 dmar_subhandle;
+ };
} __attribute__ ((packed)) arch_msi_msg_data_t;
#define arch_msi_msg_data x86_msi_data

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8fc1b5003713..a2b6626c681f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -241,6 +241,11 @@ struct x86_pmu_capability {
#define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3)
#define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS)

+static inline bool use_fixed_pseudo_encoding(u64 code)
+{
+ return !(code & 0xff);
+}
+
/*
* We model BTS tracing as another fixed-mode PMC.
*
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 5818b837fd4d..2d719e0d2e40 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -834,6 +834,59 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
m->cs = regs->cs;
}

+/*
+ * Disable fast string copy and return from the MCE handler upon the first SRAR
+ * MCE on bank 1 due to a CPU erratum on Intel Skylake/Cascade Lake/Cooper Lake
+ * CPUs.
+ * The fast string copy instructions ("REP; MOVS*") could consume an
+ * uncorrectable memory error in the cache line _right after_ the desired region
+ * to copy and raise an MCE with RIP pointing to the instruction _after_ the
+ * "REP; MOVS*".
+ * This mitigation addresses the issue completely with the caveat of performance
+ * degradation on the CPU affected. This is still better than the OS crashing on
+ * MCEs raised on an irrelevant process due to "REP; MOVS*" accesses from a
+ * kernel context (e.g., copy_page).
+ *
+ * Returns true when fast string copy on CPU has been disabled.
+ */
+static noinstr bool quirk_skylake_repmov(void)
+{
+ u64 mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+ u64 misc_enable = mce_rdmsrl(MSR_IA32_MISC_ENABLE);
+ u64 mc1_status;
+
+ /*
+ * Apply the quirk only to local machine checks, i.e., no broadcast
+ * sync is needed.
+ */
+ if (!(mcgstatus & MCG_STATUS_LMCES) ||
+ !(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING))
+ return false;
+
+ mc1_status = mce_rdmsrl(MSR_IA32_MCx_STATUS(1));
+
+ /* Check for a software-recoverable data fetch error. */
+ if ((mc1_status &
+ (MCI_STATUS_VAL | MCI_STATUS_OVER | MCI_STATUS_UC | MCI_STATUS_EN |
+ MCI_STATUS_ADDRV | MCI_STATUS_MISCV | MCI_STATUS_PCC |
+ MCI_STATUS_AR | MCI_STATUS_S)) ==
+ (MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN |
+ MCI_STATUS_ADDRV | MCI_STATUS_MISCV |
+ MCI_STATUS_AR | MCI_STATUS_S)) {
+ misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
+ mce_wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+ mce_wrmsrl(MSR_IA32_MCx_STATUS(1), 0);
+
+ instrumentation_begin();
+ pr_err_once("Erratum detected, disable fast string copy instructions.\n");
+ instrumentation_end();
+
+ return true;
+ }
+
+ return false;
+}
+
/*
* Do a quick check if any of the events requires a panic.
* This decides if we keep the events around or clear them.
@@ -1403,6 +1456,9 @@ noinstr void do_machine_check(struct pt_regs *regs)
else if (unlikely(!mca_cfg.initialized))
return unexpected_machine_check(regs);

+ if (mce_flags.skx_repmov_quirk && quirk_skylake_repmov())
+ goto clear;
+
/*
* Establish sequential order between the CPUs entering the machine
* check handler.
@@ -1545,6 +1601,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
out:
instrumentation_end();

+clear:
mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
}
EXPORT_SYMBOL_GPL(do_machine_check);
@@ -1858,6 +1915,13 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)

if (c->x86 == 6 && c->x86_model == 45)
mce_flags.snb_ifu_quirk = 1;
+
+ /*
+ * Skylake, Cascacde Lake and Cooper Lake require a quirk on
+ * rep movs.
+ */
+ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_SKYLAKE_X)
+ mce_flags.skx_repmov_quirk = 1;
}

if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 52c633950b38..24d099e2d2a2 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -170,7 +170,10 @@ struct mce_vendor_flags {
/* SandyBridge IFU quirk */
snb_ifu_quirk : 1,

- __reserved_0 : 57;
+ /* Skylake, Cascade Lake, Cooper Lake REP;MOVS* quirk */
+ skx_repmov_quirk : 1,
+
+ __reserved_0 : 56;
};

extern struct mce_vendor_flags mce_flags;
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 531fb4cbb63f..aa72cefdd5be 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -12,10 +12,9 @@ enum insn_type {
};

/*
- * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax
- * The REX.W cancels the effect of any data16.
+ * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax
*/
-static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 };
+static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };

static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 02d061a06aa1..de9d8a27387c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3523,8 +3523,10 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt)
{
u64 tsc_aux = 0;

- if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux))
+ if (!ctxt->ops->guest_has_rdpid(ctxt))
return emulate_ud(ctxt);
+
+ ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux);
ctxt->dst.val = tsc_aux;
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 39eded2426ff..a2a7654d8ace 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -226,6 +226,7 @@ struct x86_emulate_ops {
bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt);
bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt);
bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt);
+ bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);

void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index b1a02993782b..eca39f56c231 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -96,8 +96,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event,

static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
u64 config, bool exclude_user,
- bool exclude_kernel, bool intr,
- bool in_tx, bool in_tx_cp)
+ bool exclude_kernel, bool intr)
{
struct perf_event *event;
struct perf_event_attr attr = {
@@ -116,16 +115,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,

attr.sample_period = get_sample_period(pmc, pmc->counter);

- if (in_tx)
- attr.config |= HSW_IN_TX;
- if (in_tx_cp) {
+ if ((attr.config & HSW_IN_TX_CHECKPOINTED) &&
+ guest_cpuid_is_intel(pmc->vcpu)) {
/*
* HSW_IN_TX_CHECKPOINTED is not supported with nonzero
* period. Just clear the sample period so at least
* allocating the counter doesn't fail.
*/
attr.sample_period = 0;
- attr.config |= HSW_IN_TX_CHECKPOINTED;
}

event = perf_event_create_kernel_counter(&attr, -1, current,
@@ -185,6 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
u32 type = PERF_TYPE_RAW;
struct kvm *kvm = pmc->vcpu->kvm;
struct kvm_pmu_event_filter *filter;
+ struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu);
bool allow_event = true;

if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
@@ -221,7 +219,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
}

if (type == PERF_TYPE_RAW)
- config = eventsel & AMD64_RAW_EVENT_MASK;
+ config = eventsel & pmu->raw_event_mask;

if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
return;
@@ -232,9 +230,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
pmc_reprogram_counter(pmc, type, config,
!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
- eventsel & ARCH_PERFMON_EVENTSEL_INT,
- (eventsel & HSW_IN_TX),
- (eventsel & HSW_IN_TX_CHECKPOINTED));
+ eventsel & ARCH_PERFMON_EVENTSEL_INT);
}
EXPORT_SYMBOL_GPL(reprogram_gp_counter);

@@ -270,7 +266,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc),
!(en_field & 0x2), /* exclude user */
!(en_field & 0x1), /* exclude kernel */
- pmi, false, false);
+ pmi);
}
EXPORT_SYMBOL_GPL(reprogram_fixed_counter);

diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 5aa45f13b16d..ba40b7fced5a 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -262,12 +262,10 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* MSR_EVNTSELn */
pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
if (pmc) {
- if (data == pmc->eventsel)
- return 0;
- if (!(data & pmu->reserved_bits)) {
+ data &= ~pmu->reserved_bits;
+ if (data != pmc->eventsel)
reprogram_gp_counter(pmc, data);
- return 0;
- }
+ return 0;
}

return 1;
@@ -284,6 +282,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)

pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
pmu->reserved_bits = 0xfffffff000280000ull;
+ pmu->raw_event_mask = AMD64_RAW_EVENT_MASK;
pmu->version = 1;
/* not applicable to AMD; but clean them to prevent any fall out */
pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index fa98d6844728..86bcfed6599e 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -22,6 +22,8 @@
#include <asm/svm.h>
#include <asm/sev-common.h>

+#include "kvm_cache_regs.h"
+
#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)

#define IOPM_SIZE PAGE_SIZE * 3
diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c
index 98aa981c04ec..8cdc62c74a96 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.c
+++ b/arch/x86/kvm/svm/svm_onhyperv.c
@@ -4,7 +4,6 @@
*/

#include <linux/kvm_host.h>
-#include "kvm_cache_regs.h"

#include <asm/mshyperv.h>

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 466d18fc0c5d..5fa3870b8988 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -389,6 +389,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
struct kvm_pmc *pmc;
u32 msr = msr_info->index;
u64 data = msr_info->data;
+ u64 reserved_bits;

switch (msr) {
case MSR_CORE_PERF_FIXED_CTR_CTRL:
@@ -443,7 +444,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
if (data == pmc->eventsel)
return 0;
- if (!(data & pmu->reserved_bits)) {
+ reserved_bits = pmu->reserved_bits;
+ if ((pmc->idx == 2) &&
+ (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED))
+ reserved_bits ^= HSW_IN_TX_CHECKPOINTED;
+ if (!(data & reserved_bits)) {
reprogram_gp_counter(pmc, data);
return 0;
}
@@ -485,6 +490,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
pmu->version = 0;
pmu->reserved_bits = 0xffffffff00200000ull;
+ pmu->raw_event_mask = X86_RAW_EVENT_MASK;

entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
if (!entry || !enable_pmu)
@@ -533,8 +539,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
entry = kvm_find_cpuid_entry(vcpu, 7, 0);
if (entry &&
(boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
- (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
- pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+ (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) {
+ pmu->reserved_bits ^= HSW_IN_TX;
+ pmu->raw_event_mask |= (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED);
+ }

bitmap_set(pmu->all_valid_pmc_idx,
0, pmu->nr_arch_gp_counters);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b6166348c94..c81ec70197fb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7675,6 +7675,11 @@ static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt)
return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR);
}

+static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt)
+{
+ return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID);
+}
+
static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
{
return kvm_register_read_raw(emul_to_vcpu(ctxt), reg);
@@ -7757,6 +7762,7 @@ static const struct x86_emulate_ops emulate_ops = {
.guest_has_long_mode = emulator_guest_has_long_mode,
.guest_has_movbe = emulator_guest_has_movbe,
.guest_has_fxsr = emulator_guest_has_fxsr,
+ .guest_has_rdpid = emulator_guest_has_rdpid,
.set_nmi_mask = emulator_set_nmi_mask,
.get_hflags = emulator_get_hflags,
.exiting_smm = emulator_exiting_smm,
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a6cf56a14939..b3cb49de0a64 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -854,13 +854,11 @@ static void flush_tlb_func(void *info)
nr_invalidate);
}

-static bool tlb_is_not_lazy(int cpu)
+static bool tlb_is_not_lazy(int cpu, void *data)
{
return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
}

-static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
-
DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);

@@ -889,36 +887,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
* up on the new contents of what used to be page tables, while
* doing a speculative memory access.
*/
- if (info->freed_tables) {
+ if (info->freed_tables)
on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
- } else {
- /*
- * Although we could have used on_each_cpu_cond_mask(),
- * open-coding it has performance advantages, as it eliminates
- * the need for indirect calls or retpolines. In addition, it
- * allows to use a designated cpumask for evaluating the
- * condition, instead of allocating one.
- *
- * This code works under the assumption that there are no nested
- * TLB flushes, an assumption that is already made in
- * flush_tlb_mm_range().
- *
- * cond_cpumask is logically a stack-local variable, but it is
- * more efficient to have it off the stack and not to allocate
- * it on demand. Preemption is disabled and this code is
- * non-reentrant.
- */
- struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask);
- int cpu;
-
- cpumask_clear(cond_cpumask);
-
- for_each_cpu(cpu, cpumask) {
- if (tlb_is_not_lazy(cpu))
- __cpumask_set_cpu(cpu, cond_cpumask);
- }
- on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true);
- }
+ else
+ on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
+ (void *)info, 1, cpumask);
}

void flush_tlb_multi(const struct cpumask *cpumask,
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 9f2b251e83c5..3822666fb73d 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt)
struct saved_msr *end = msr + ctxt->saved_msrs.num;

while (msr < end) {
- msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q);
+ if (msr->valid)
+ rdmsrl(msr->info.msr_no, msr->info.reg.q);
msr++;
}
}
@@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num)
}

for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) {
+ u64 dummy;
+
msr_array[i].info.msr_no = msr_id[j];
- msr_array[i].valid = false;
+ msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy);
msr_array[i].info.reg.q = 0;
}
saved_msrs->num = total_num;
@@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c)
return ret;
}

+static void pm_save_spec_msr(void)
+{
+ u32 spec_msr_id[] = {
+ MSR_IA32_SPEC_CTRL,
+ MSR_IA32_TSX_CTRL,
+ MSR_TSX_FORCE_ABORT,
+ MSR_IA32_MCU_OPT_CTRL,
+ MSR_AMD64_LS_CFG,
+ };
+
+ msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id));
+}
+
static int pm_check_save_msr(void)
{
dmi_check_system(msr_save_dmi_table);
pm_cpu_check(msr_save_cpu_table);
+ pm_save_spec_msr();

return 0;
}
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index 6ff3c887e0b9..b70afdff419c 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -19,6 +19,12 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void)
*/
xen_vcpu_setup(0);

+ /*
+ * Called again in case the kernel boots on vcpu >= MAX_VIRT_CPUS.
+ * Refer to comments in xen_hvm_init_time_ops().
+ */
+ xen_hvm_init_time_ops();
+
/*
* The alternative logic (which patches the unlock/lock) runs before
* the smp bootup up code is activated. Hence we need to set this up
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index d9c945ee1100..9ef0a5cca96e 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -558,6 +558,11 @@ static void xen_hvm_setup_cpu_clockevents(void)

void __init xen_hvm_init_time_ops(void)
{
+ static bool hvm_time_initialized;
+
+ if (hvm_time_initialized)
+ return;
+
/*
* vector callback is needed otherwise we cannot receive interrupts
* on cpu > 0 and at this point we don't know how many cpus are
@@ -567,7 +572,22 @@ void __init xen_hvm_init_time_ops(void)
return;

if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
- pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
+ pr_info_once("Xen doesn't support pvclock on HVM, disable pv timer");
+ return;
+ }
+
+ /*
+ * Only MAX_VIRT_CPUS 'vcpu_info' are embedded inside 'shared_info'.
+ * The __this_cpu_read(xen_vcpu) is still NULL when Xen HVM guest
+ * boots on vcpu >= MAX_VIRT_CPUS (e.g., kexec), To access
+ * __this_cpu_read(xen_vcpu) via xen_clocksource_read() will panic.
+ *
+ * The xen_hvm_init_time_ops() should be called again later after
+ * __this_cpu_read(xen_vcpu) is available.
+ */
+ if (!__this_cpu_read(xen_vcpu)) {
+ pr_info("Delay xen_init_time_common() as kernel is running on vcpu=%d\n",
+ xen_vcpu_nr(0));
return;
}

@@ -577,6 +597,8 @@ void __init xen_hvm_init_time_ops(void)
x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;

x86_platform.set_wallclock = xen_set_wallclock;
+
+ hvm_time_initialized = true;
}
#endif

diff --git a/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi b/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi
index 9bf8bad1dd18..c33932568aa7 100644
--- a/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga-flash-128m.dtsi
@@ -8,19 +8,19 @@ flash: flash@00000000 {
reg = <0x00000000 0x08000000>;
bank-width = <2>;
device-width = <2>;
- partition@0x0 {
+ partition@0 {
label = "data";
reg = <0x00000000 0x06000000>;
};
- partition@0x6000000 {
+ partition@6000000 {
label = "boot loader area";
reg = <0x06000000 0x00800000>;
};
- partition@0x6800000 {
+ partition@6800000 {
label = "kernel image";
reg = <0x06800000 0x017e0000>;
};
- partition@0x7fe0000 {
+ partition@7fe0000 {
label = "boot environment";
reg = <0x07fe0000 0x00020000>;
};
diff --git a/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi b/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi
index 40c2f81f7cb6..7bde2ab2d6fb 100644
--- a/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga-flash-16m.dtsi
@@ -8,19 +8,19 @@ flash: flash@08000000 {
reg = <0x08000000 0x01000000>;
bank-width = <2>;
device-width = <2>;
- partition@0x0 {
+ partition@0 {
label = "boot loader area";
reg = <0x00000000 0x00400000>;
};
- partition@0x400000 {
+ partition@400000 {
label = "kernel image";
reg = <0x00400000 0x00600000>;
};
- partition@0xa00000 {
+ partition@a00000 {
label = "data";
reg = <0x00a00000 0x005e0000>;
};
- partition@0xfe0000 {
+ partition@fe0000 {
label = "boot environment";
reg = <0x00fe0000 0x00020000>;
};
diff --git a/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi b/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi
index fb8d3a9f33c2..0655b868749a 100644
--- a/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga-flash-4m.dtsi
@@ -8,11 +8,11 @@ flash: flash@08000000 {
reg = <0x08000000 0x00400000>;
bank-width = <2>;
device-width = <2>;
- partition@0x0 {
+ partition@0 {
label = "boot loader area";
reg = <0x00000000 0x003f0000>;
};
- partition@0x3f0000 {
+ partition@3f0000 {
label = "boot environment";
reg = <0x003f0000 0x00010000>;
};
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index f8e9fa82cb9b..05b3985a1984 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -570,8 +570,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
{
struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);

- if (cx->type == ACPI_STATE_C3)
- ACPI_FLUSH_CPU_CACHE();
+ ACPI_FLUSH_CPU_CACHE();

while (1) {

diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index bec33d781ae0..e3263e961045 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -137,7 +137,11 @@ struct sata_dwc_device {
#endif
};

-#define SATA_DWC_QCMD_MAX 32
+/*
+ * Allow one extra special slot for commands and DMA management
+ * to account for libata internal commands.
+ */
+#define SATA_DWC_QCMD_MAX (ATA_MAX_QUEUE + 1)

struct sata_dwc_device_port {
struct sata_dwc_device *hsdev;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index f27d5b0f9a0b..a98bfcf4a5f0 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1642,22 +1642,22 @@ struct sib_info {
};
void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib);

-extern void notify_resource_state(struct sk_buff *,
+extern int notify_resource_state(struct sk_buff *,
unsigned int,
struct drbd_resource *,
struct resource_info *,
enum drbd_notification_type);
-extern void notify_device_state(struct sk_buff *,
+extern int notify_device_state(struct sk_buff *,
unsigned int,
struct drbd_device *,
struct device_info *,
enum drbd_notification_type);
-extern void notify_connection_state(struct sk_buff *,
+extern int notify_connection_state(struct sk_buff *,
unsigned int,
struct drbd_connection *,
struct connection_info *,
enum drbd_notification_type);
-extern void notify_peer_device_state(struct sk_buff *,
+extern int notify_peer_device_state(struct sk_buff *,
unsigned int,
struct drbd_peer_device *,
struct peer_device_info *,
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 6f450816c4fa..5d5beeba3ed4 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2793,12 +2793,12 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig

if (init_submitter(device)) {
err = ERR_NOMEM;
- goto out_idr_remove_vol;
+ goto out_idr_remove_from_resource;
}

err = add_disk(disk);
if (err)
- goto out_idr_remove_vol;
+ goto out_idr_remove_from_resource;

/* inherit the connection state */
device->state.conn = first_connection(resource)->cstate;
@@ -2812,8 +2812,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
drbd_debugfs_device_add(device);
return NO_ERROR;

-out_idr_remove_vol:
- idr_remove(&connection->peer_devices, vnr);
out_idr_remove_from_resource:
for_each_connection(connection, resource) {
peer_device = idr_remove(&connection->peer_devices, vnr);
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 44ccf8b4f4b2..69184cf17b6a 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -4617,7 +4617,7 @@ static int nla_put_notification_header(struct sk_buff *msg,
return drbd_notification_header_to_skb(msg, &nh, true);
}

-void notify_resource_state(struct sk_buff *skb,
+int notify_resource_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_resource *resource,
struct resource_info *resource_info,
@@ -4659,16 +4659,17 @@ void notify_resource_state(struct sk_buff *skb,
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;

nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}

-void notify_device_state(struct sk_buff *skb,
+int notify_device_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_device *device,
struct device_info *device_info,
@@ -4708,16 +4709,17 @@ void notify_device_state(struct sk_buff *skb,
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;

nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}

-void notify_connection_state(struct sk_buff *skb,
+int notify_connection_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_connection *connection,
struct connection_info *connection_info,
@@ -4757,16 +4759,17 @@ void notify_connection_state(struct sk_buff *skb,
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;

nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}

-void notify_peer_device_state(struct sk_buff *skb,
+int notify_peer_device_state(struct sk_buff *skb,
unsigned int seq,
struct drbd_peer_device *peer_device,
struct peer_device_info *peer_device_info,
@@ -4807,13 +4810,14 @@ void notify_peer_device_state(struct sk_buff *skb,
if (err && err != -ESRCH)
goto failed;
}
- return;
+ return 0;

nla_put_failure:
nlmsg_free(skb);
failed:
drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n",
err, seq);
+ return err;
}

void notify_helper(enum drbd_notification_type type,
@@ -4864,7 +4868,7 @@ void notify_helper(enum drbd_notification_type type,
err, seq);
}

-static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq)
+static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq)
{
struct drbd_genlmsghdr *dh;
int err;
@@ -4878,11 +4882,12 @@ static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq)
if (nla_put_notification_header(skb, NOTIFY_EXISTS))
goto nla_put_failure;
genlmsg_end(skb, dh);
- return;
+ return 0;

nla_put_failure:
nlmsg_free(skb);
pr_err("Error %d sending event. Event seq:%u\n", err, seq);
+ return err;
}

static void free_state_changes(struct list_head *list)
@@ -4909,6 +4914,7 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb)
unsigned int seq = cb->args[2];
unsigned int n;
enum drbd_notification_type flags = 0;
+ int err = 0;

/* There is no need for taking notification_mutex here: it doesn't
matter if the initial state events mix with later state chage
@@ -4917,32 +4923,32 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb)

cb->args[5]--;
if (cb->args[5] == 1) {
- notify_initial_state_done(skb, seq);
+ err = notify_initial_state_done(skb, seq);
goto out;
}
n = cb->args[4]++;
if (cb->args[4] < cb->args[3])
flags |= NOTIFY_CONTINUES;
if (n < 1) {
- notify_resource_state_change(skb, seq, state_change->resource,
+ err = notify_resource_state_change(skb, seq, state_change->resource,
NOTIFY_EXISTS | flags);
goto next;
}
n--;
if (n < state_change->n_connections) {
- notify_connection_state_change(skb, seq, &state_change->connections[n],
+ err = notify_connection_state_change(skb, seq, &state_change->connections[n],
NOTIFY_EXISTS | flags);
goto next;
}
n -= state_change->n_connections;
if (n < state_change->n_devices) {
- notify_device_state_change(skb, seq, &state_change->devices[n],
+ err = notify_device_state_change(skb, seq, &state_change->devices[n],
NOTIFY_EXISTS | flags);
goto next;
}
n -= state_change->n_devices;
if (n < state_change->n_devices * state_change->n_connections) {
- notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n],
+ err = notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n],
NOTIFY_EXISTS | flags);
goto next;
}
@@ -4957,7 +4963,10 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb)
cb->args[4] = 0;
}
out:
- return skb->len;
+ if (err)
+ return err;
+ else
+ return skb->len;
}

int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index b8a27818ab3f..4ee11aef6672 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1537,7 +1537,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device,
return rv;
}

-void notify_resource_state_change(struct sk_buff *skb,
+int notify_resource_state_change(struct sk_buff *skb,
unsigned int seq,
struct drbd_resource_state_change *resource_state_change,
enum drbd_notification_type type)
@@ -1550,10 +1550,10 @@ void notify_resource_state_change(struct sk_buff *skb,
.res_susp_fen = resource_state_change->susp_fen[NEW],
};

- notify_resource_state(skb, seq, resource, &resource_info, type);
+ return notify_resource_state(skb, seq, resource, &resource_info, type);
}

-void notify_connection_state_change(struct sk_buff *skb,
+int notify_connection_state_change(struct sk_buff *skb,
unsigned int seq,
struct drbd_connection_state_change *connection_state_change,
enum drbd_notification_type type)
@@ -1564,10 +1564,10 @@ void notify_connection_state_change(struct sk_buff *skb,
.conn_role = connection_state_change->peer_role[NEW],
};

- notify_connection_state(skb, seq, connection, &connection_info, type);
+ return notify_connection_state(skb, seq, connection, &connection_info, type);
}

-void notify_device_state_change(struct sk_buff *skb,
+int notify_device_state_change(struct sk_buff *skb,
unsigned int seq,
struct drbd_device_state_change *device_state_change,
enum drbd_notification_type type)
@@ -1577,10 +1577,10 @@ void notify_device_state_change(struct sk_buff *skb,
.dev_disk_state = device_state_change->disk_state[NEW],
};

- notify_device_state(skb, seq, device, &device_info, type);
+ return notify_device_state(skb, seq, device, &device_info, type);
}

-void notify_peer_device_state_change(struct sk_buff *skb,
+int notify_peer_device_state_change(struct sk_buff *skb,
unsigned int seq,
struct drbd_peer_device_state_change *p,
enum drbd_notification_type type)
@@ -1594,7 +1594,7 @@ void notify_peer_device_state_change(struct sk_buff *skb,
.peer_resync_susp_dependency = p->resync_susp_dependency[NEW],
};

- notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type);
+ return notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type);
}

static void broadcast_state_change(struct drbd_state_change *state_change)
@@ -1602,7 +1602,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change)
struct drbd_resource_state_change *resource_state_change = &state_change->resource[0];
bool resource_state_has_changed;
unsigned int n_device, n_connection, n_peer_device, n_peer_devices;
- void (*last_func)(struct sk_buff *, unsigned int, void *,
+ int (*last_func)(struct sk_buff *, unsigned int, void *,
enum drbd_notification_type) = NULL;
void *last_arg = NULL;

diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h
index ba80f612d6ab..d5b0479bc9a6 100644
--- a/drivers/block/drbd/drbd_state_change.h
+++ b/drivers/block/drbd/drbd_state_change.h
@@ -44,19 +44,19 @@ extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_
extern void copy_old_to_new_state_change(struct drbd_state_change *);
extern void forget_state_change(struct drbd_state_change *);

-extern void notify_resource_state_change(struct sk_buff *,
+extern int notify_resource_state_change(struct sk_buff *,
unsigned int,
struct drbd_resource_state_change *,
enum drbd_notification_type type);
-extern void notify_connection_state_change(struct sk_buff *,
+extern int notify_connection_state_change(struct sk_buff *,
unsigned int,
struct drbd_connection_state_change *,
enum drbd_notification_type type);
-extern void notify_device_state_change(struct sk_buff *,
+extern int notify_device_state_change(struct sk_buff *,
unsigned int,
struct drbd_device_state_change *,
enum drbd_notification_type type);
-extern void notify_peer_device_state_change(struct sk_buff *,
+extern int notify_peer_device_state_change(struct sk_buff *,
unsigned int,
struct drbd_peer_device_state_change *,
enum drbd_notification_type type);
diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h
index 6e7b0c7567c0..0defa68bc2ce 100644
--- a/drivers/bluetooth/btmtk.h
+++ b/drivers/bluetooth/btmtk.h
@@ -5,6 +5,7 @@
#define FIRMWARE_MT7668 "mediatek/mt7668pr2h.bin"
#define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin"

+#define HCI_EV_WMT 0xe4
#define HCI_WMT_MAX_EVENT_SIZE 64

#define BTMTK_WMT_REG_READ 0x2
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index 9b868f187316..ecf29cfa7d79 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -370,13 +370,6 @@ static int btmtksdio_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
struct hci_event_hdr *hdr = (void *)skb->data;
int err;

- /* Fix up the vendor event id with 0xff for vendor specific instead
- * of 0xe4 so that event send via monitoring socket can be parsed
- * properly.
- */
- if (hdr->evt == 0xe4)
- hdr->evt = HCI_EV_VENDOR;
-
/* When someone waits for the WMT event, the skb is being cloned
* and being processed the events from there then.
*/
@@ -392,7 +385,7 @@ static int btmtksdio_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
if (err < 0)
goto err_free_skb;

- if (hdr->evt == HCI_EV_VENDOR) {
+ if (hdr->evt == HCI_EV_WMT) {
if (test_and_clear_bit(BTMTKSDIO_TX_WAIT_VND_EVT,
&bdev->tx_state)) {
/* Barrier to sync with other CPUs */
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2afbd87d77c9..42234d5f602d 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2254,7 +2254,6 @@ static void btusb_mtk_wmt_recv(struct urb *urb)
{
struct hci_dev *hdev = urb->context;
struct btusb_data *data = hci_get_drvdata(hdev);
- struct hci_event_hdr *hdr;
struct sk_buff *skb;
int err;

@@ -2274,13 +2273,6 @@ static void btusb_mtk_wmt_recv(struct urb *urb)
hci_skb_pkt_type(skb) = HCI_EVENT_PKT;
skb_put_data(skb, urb->transfer_buffer, urb->actual_length);

- hdr = (void *)skb->data;
- /* Fix up the vendor event id with 0xff for vendor specific
- * instead of 0xe4 so that event send via monitoring socket can
- * be parsed properly.
- */
- hdr->evt = 0xff;
-
/* When someone waits for the WMT event, the skb is being cloned
* and being processed the events from there then.
*/
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index e3c430539a17..9fa3c76a267f 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -2245,7 +2245,7 @@ static struct virtio_driver virtio_rproc_serial = {
.remove = virtcons_remove,
};

-static int __init init(void)
+static int __init virtio_console_init(void)
{
int err;

@@ -2280,7 +2280,7 @@ static int __init init(void)
return err;
}

-static void __exit fini(void)
+static void __exit virtio_console_fini(void)
{
reclaim_dma_bufs();

@@ -2290,8 +2290,8 @@ static void __exit fini(void)
class_destroy(pdrvdata.class);
debugfs_remove_recursive(pdrvdata.debugfs_dir);
}
-module_init(init);
-module_exit(fini);
+module_init(virtio_console_init);
+module_exit(virtio_console_fini);

MODULE_DESCRIPTION("Virtio console driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/clk/clk-si5341.c b/drivers/clk/clk-si5341.c
index f7b41366666e..4de098b6b0d4 100644
--- a/drivers/clk/clk-si5341.c
+++ b/drivers/clk/clk-si5341.c
@@ -798,6 +798,15 @@ static unsigned long si5341_output_clk_recalc_rate(struct clk_hw *hw,
u32 r_divider;
u8 r[3];

+ err = regmap_read(output->data->regmap,
+ SI5341_OUT_CONFIG(output), &val);
+ if (err < 0)
+ return err;
+
+ /* If SI5341_OUT_CFG_RDIV_FORCE2 is set, r_divider is 2 */
+ if (val & SI5341_OUT_CFG_RDIV_FORCE2)
+ return parent_rate / 2;
+
err = regmap_bulk_read(output->data->regmap,
SI5341_OUT_R_REG(output), r, 3);
if (err < 0)
@@ -814,13 +823,6 @@ static unsigned long si5341_output_clk_recalc_rate(struct clk_hw *hw,
r_divider += 1;
r_divider <<= 1;

- err = regmap_read(output->data->regmap,
- SI5341_OUT_CONFIG(output), &val);
- if (err < 0)
- return err;
-
- if (val & SI5341_OUT_CFG_RDIV_FORCE2)
- r_divider = 2;

return parent_rate / r_divider;
}
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 01b64b962e76..2fdfce116087 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -632,6 +632,24 @@ static void clk_core_get_boundaries(struct clk_core *core,
*max_rate = min(*max_rate, clk_user->max_rate);
}

+static bool clk_core_check_boundaries(struct clk_core *core,
+ unsigned long min_rate,
+ unsigned long max_rate)
+{
+ struct clk *user;
+
+ lockdep_assert_held(&prepare_lock);
+
+ if (min_rate > core->max_rate || max_rate < core->min_rate)
+ return false;
+
+ hlist_for_each_entry(user, &core->clks, clks_node)
+ if (min_rate > user->max_rate || max_rate < user->min_rate)
+ return false;
+
+ return true;
+}
+
void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate,
unsigned long max_rate)
{
@@ -2348,6 +2366,11 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max)
clk->min_rate = min;
clk->max_rate = max;

+ if (!clk_core_check_boundaries(clk->core, min, max)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
rate = clk_core_get_rate_nolock(clk->core);
if (rate < min || rate > max) {
/*
@@ -2376,6 +2399,7 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max)
}
}

+out:
if (clk->exclusive_count)
clk_core_rate_protect(clk->core);

diff --git a/drivers/clk/mediatek/clk-mt8192.c b/drivers/clk/mediatek/clk-mt8192.c
index cbc7c6dbe0f4..79ddb3cc0b98 100644
--- a/drivers/clk/mediatek/clk-mt8192.c
+++ b/drivers/clk/mediatek/clk-mt8192.c
@@ -1236,9 +1236,17 @@ static int clk_mt8192_infra_probe(struct platform_device *pdev)

r = mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks), clk_data);
if (r)
- return r;
+ goto free_clk_data;
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ if (r)
+ goto free_clk_data;
+
+ return r;

- return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+free_clk_data:
+ mtk_free_clk_data(clk_data);
+ return r;
}

static int clk_mt8192_peri_probe(struct platform_device *pdev)
@@ -1253,9 +1261,17 @@ static int clk_mt8192_peri_probe(struct platform_device *pdev)

r = mtk_clk_register_gates(node, peri_clks, ARRAY_SIZE(peri_clks), clk_data);
if (r)
- return r;
+ goto free_clk_data;
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ if (r)
+ goto free_clk_data;

- return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ return r;
+
+free_clk_data:
+ mtk_free_clk_data(clk_data);
+ return r;
}

static int clk_mt8192_apmixed_probe(struct platform_device *pdev)
@@ -1271,9 +1287,17 @@ static int clk_mt8192_apmixed_probe(struct platform_device *pdev)
mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data);
r = mtk_clk_register_gates(node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data);
if (r)
- return r;
+ goto free_clk_data;

- return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ if (r)
+ goto free_clk_data;
+
+ return r;
+
+free_clk_data:
+ mtk_free_clk_data(clk_data);
+ return r;
}

static const struct of_device_id of_match_clk_mt8192[] = {
diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c
index 69a9e8069a48..604a367bc498 100644
--- a/drivers/clk/rockchip/clk-rk3568.c
+++ b/drivers/clk/rockchip/clk-rk3568.c
@@ -1038,13 +1038,13 @@ static struct rockchip_clk_branch rk3568_clk_branches[] __initdata = {
RK3568_CLKGATE_CON(20), 8, GFLAGS),
GATE(HCLK_VOP, "hclk_vop", "hclk_vo", 0,
RK3568_CLKGATE_CON(20), 9, GFLAGS),
- COMPOSITE(DCLK_VOP0, "dclk_vop0", hpll_vpll_gpll_cpll_p, CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+ COMPOSITE(DCLK_VOP0, "dclk_vop0", hpll_vpll_gpll_cpll_p, CLK_SET_RATE_NO_REPARENT,
RK3568_CLKSEL_CON(39), 10, 2, MFLAGS, 0, 8, DFLAGS,
RK3568_CLKGATE_CON(20), 10, GFLAGS),
- COMPOSITE(DCLK_VOP1, "dclk_vop1", hpll_vpll_gpll_cpll_p, CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+ COMPOSITE(DCLK_VOP1, "dclk_vop1", hpll_vpll_gpll_cpll_p, CLK_SET_RATE_NO_REPARENT,
RK3568_CLKSEL_CON(40), 10, 2, MFLAGS, 0, 8, DFLAGS,
RK3568_CLKGATE_CON(20), 11, GFLAGS),
- COMPOSITE(DCLK_VOP2, "dclk_vop2", hpll_vpll_gpll_cpll_p, 0,
+ COMPOSITE(DCLK_VOP2, "dclk_vop2", hpll_vpll_gpll_cpll_p, CLK_SET_RATE_NO_REPARENT,
RK3568_CLKSEL_CON(41), 10, 2, MFLAGS, 0, 8, DFLAGS,
RK3568_CLKGATE_CON(20), 12, GFLAGS),
GATE(CLK_VOP_PWM, "clk_vop_pwm", "xin24m", 0,
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index 3da33c786d77..29eafab4353e 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -131,7 +131,7 @@ int ti_clk_setup_ll_ops(struct ti_clk_ll_ops *ops)
void __init ti_dt_clocks_register(struct ti_dt_clk oclks[])
{
struct ti_dt_clk *c;
- struct device_node *node, *parent;
+ struct device_node *node, *parent, *child;
struct clk *clk;
struct of_phandle_args clkspec;
char buf[64];
@@ -171,10 +171,13 @@ void __init ti_dt_clocks_register(struct ti_dt_clk oclks[])
node = of_find_node_by_name(NULL, buf);
if (num_args && compat_mode) {
parent = node;
- node = of_get_child_by_name(parent, "clock");
- if (!node)
- node = of_get_child_by_name(parent, "clk");
- of_node_put(parent);
+ child = of_get_child_by_name(parent, "clock");
+ if (!child)
+ child = of_get_child_by_name(parent, "clk");
+ if (child) {
+ of_node_put(parent);
+ node = child;
+ }
}

clkspec.np = node;
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index db17196266e4..82d370ae6a4a 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -303,52 +303,48 @@ static u64 cppc_get_dmi_max_khz(void)

/*
* If CPPC lowest_freq and nominal_freq registers are exposed then we can
- * use them to convert perf to freq and vice versa
- *
- * If the perf/freq point lies between Nominal and Lowest, we can treat
- * (Low perf, Low freq) and (Nom Perf, Nom freq) as 2D co-ordinates of a line
- * and extrapolate the rest
- * For perf/freq > Nominal, we use the ratio perf:freq at Nominal for conversion
+ * use them to convert perf to freq and vice versa. The conversion is
+ * extrapolated as an affine function passing by the 2 points:
+ * - (Low perf, Low freq)
+ * - (Nominal perf, Nominal perf)
*/
static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data,
unsigned int perf)
{
struct cppc_perf_caps *caps = &cpu_data->perf_caps;
+ s64 retval, offset = 0;
static u64 max_khz;
u64 mul, div;

if (caps->lowest_freq && caps->nominal_freq) {
- if (perf >= caps->nominal_perf) {
- mul = caps->nominal_freq;
- div = caps->nominal_perf;
- } else {
- mul = caps->nominal_freq - caps->lowest_freq;
- div = caps->nominal_perf - caps->lowest_perf;
- }
+ mul = caps->nominal_freq - caps->lowest_freq;
+ div = caps->nominal_perf - caps->lowest_perf;
+ offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div);
} else {
if (!max_khz)
max_khz = cppc_get_dmi_max_khz();
mul = max_khz;
div = caps->highest_perf;
}
- return (u64)perf * mul / div;
+
+ retval = offset + div64_u64(perf * mul, div);
+ if (retval >= 0)
+ return retval;
+ return 0;
}

static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
unsigned int freq)
{
struct cppc_perf_caps *caps = &cpu_data->perf_caps;
+ s64 retval, offset = 0;
static u64 max_khz;
u64 mul, div;

if (caps->lowest_freq && caps->nominal_freq) {
- if (freq >= caps->nominal_freq) {
- mul = caps->nominal_perf;
- div = caps->nominal_freq;
- } else {
- mul = caps->lowest_perf;
- div = caps->lowest_freq;
- }
+ mul = caps->nominal_perf - caps->lowest_perf;
+ div = caps->nominal_freq - caps->lowest_freq;
+ offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div);
} else {
if (!max_khz)
max_khz = cppc_get_dmi_max_khz();
@@ -356,7 +352,10 @@ static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
div = max_khz;
}

- return (u64)freq * mul / div;
+ retval = offset + div64_u64(freq * mul, div);
+ if (retval >= 0)
+ return retval;
+ return 0;
}

static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index b26ed690f03c..158e5e7defae 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -115,10 +115,8 @@ static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx)
ret = pm_runtime_get(schan->dev);

spin_unlock_irq(&schan->chan_lock);
- if (ret < 0) {
+ if (ret < 0)
dev_err(schan->dev, "%s(): GET = %d\n", __func__, ret);
- pm_runtime_put(schan->dev);
- }

pm_runtime_barrier(schan->dev);

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 6630d92e30ad..344e376b2ee9 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1404,6 +1404,16 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset)
{
struct irq_domain *domain = gc->irq.domain;

+#ifdef CONFIG_GPIOLIB_IRQCHIP
+ /*
+ * Avoid race condition with other code, which tries to lookup
+ * an IRQ before the irqchip has been properly registered,
+ * i.e. while gpiochip is still being brought up.
+ */
+ if (!gc->irq.initialized)
+ return -EPROBE_DEFER;
+#endif
+
if (!gpiochip_irqchip_irq_valid(gc, offset))
return -ENXIO;

@@ -1593,6 +1603,15 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc,

acpi_gpiochip_request_interrupts(gc);

+ /*
+ * Using barrier() here to prevent compiler from reordering
+ * gc->irq.initialized before initialization of above
+ * GPIO chip irq members.
+ */
+ barrier();
+
+ gc->irq.initialized = true;
+
return 0;
}

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index f9bab963a948..5df387c4d7fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1813,12 +1813,6 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
true);
ret = unreserve_bo_and_vms(&ctx, false, false);

- /* Only apply no TLB flush on Aldebaran to
- * workaround regressions on other Asics.
- */
- if (table_freed && (adev->asic_type != CHIP_ALDEBARAN))
- *table_freed = true;
-
goto out;

out_unreserve:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 06d07502a1f6..a34be65c9eaa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1509,6 +1509,7 @@ int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
return 0;

default:
+ dma_fence_put(fence);
return -EINVAL;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f18c698137a6..b87dca6d09fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2723,11 +2723,11 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
}
}

- amdgpu_amdkfd_suspend(adev, false);
-
amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);

+ amdgpu_amdkfd_suspend(adev, false);
+
/* Workaroud for ASICs need to disable SMC first */
amdgpu_device_smu_fini_early(adev);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 1916ec84dd71..e7845df6cad2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
* adev->gfx.mec.num_pipe_per_mec
* adev->gfx.mec.num_queue_per_pipe;

- while (queue_bit-- >= 0) {
+ while (--queue_bit >= 0) {
if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap))
continue;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 5661b82d84d4..dda53fe30975 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1303,7 +1303,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
!(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE))
return;

- dma_resv_lock(bo->base.resv, NULL);
+ if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv)))
+ return;

r = amdgpu_fill_buffer(abo, AMDGPU_POISON, bo->base.resv, &fence);
if (!WARN_ON(r)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index da11ceba0698..0ce2a7aa400b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -569,8 +569,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect);

/* VCN global tiling registers */
- WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET(
- UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
+ UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
}

static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 4bfc0c8ab764..70122978bdd0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1416,6 +1416,12 @@ static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
return ret;
}

+static bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) {
+ return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
+ (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) &&
+ dev->adev->sdma.instance[0].fw_version >= 18);
+}
+
static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
struct kfd_process *p, void *data)
{
@@ -1503,7 +1509,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
}

/* Flush TLBs after waiting for the page table updates to complete */
- if (table_freed) {
+ if (table_freed || !kfd_flush_tlb_after_unmap(dev)) {
for (i = 0; i < args->n_devices; i++) {
peer = kfd_device_by_id(devices_arr[i]);
if (WARN_ON_ONCE(!peer))
@@ -1603,7 +1609,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
}
mutex_unlock(&p->mutex);

- if (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2)) {
+ if (kfd_flush_tlb_after_unmap(dev)) {
err = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev,
(struct kgd_mem *) mem, true);
if (err) {
@@ -1840,13 +1846,9 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data)
if (!args->start_addr || !args->size)
return -EINVAL;

- mutex_lock(&p->mutex);
-
r = svm_ioctl(p, args->op, args->start_addr, args->size, args->nattr,
args->attrs);

- mutex_unlock(&p->mutex);
-
return r;
}
#else
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 9624bbe8b501..281def1c6c08 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -1567,7 +1567,7 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size)
/* Fetch the CRAT table from ACPI */
status = acpi_get_table(CRAT_SIGNATURE, 0, &crat_table);
if (status == AE_NOT_FOUND) {
- pr_warn("CRAT table not found\n");
+ pr_info("CRAT table not found\n");
return -ENODATA;
} else if (ACPI_FAILURE(status)) {
const char *err = acpi_format_exception(status);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d1145da5348f..74f162887d3b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1150,7 +1150,6 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,

cancel_delayed_work_sync(&p->eviction_work);
cancel_delayed_work_sync(&p->restore_work);
- cancel_delayed_work_sync(&p->svms.restore_work);

mutex_lock(&p->mutex);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index deae12dc777d..40d0d8cb3fe8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -268,15 +268,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)
return ret;
}

- ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client,
- O_RDWR);
- if (ret < 0) {
- kfifo_free(&client->fifo);
- kfree(client);
- return ret;
- }
- *fd = ret;
-
init_waitqueue_head(&client->wait_queue);
spin_lock_init(&client->lock);
client->events = 0;
@@ -286,5 +277,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)
list_add_rcu(&client->list, &dev->smi_clients);
spin_unlock(&dev->smi_lock);

+ ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client,
+ O_RDWR);
+ if (ret < 0) {
+ spin_lock(&dev->smi_lock);
+ list_del_rcu(&client->list);
+ spin_unlock(&dev->smi_lock);
+
+ synchronize_rcu();
+
+ kfifo_free(&client->fifo);
+ kfree(client);
+ return ret;
+ }
+ *fd = ret;
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f2805ba74c80..ffec25e642e2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1643,13 +1643,14 @@ static void svm_range_restore_work(struct work_struct *work)

pr_debug("restore svm ranges\n");

- /* kfd_process_notifier_release destroys this worker thread. So during
- * the lifetime of this thread, kfd_process and mm will be valid.
- */
p = container_of(svms, struct kfd_process, svms);
- mm = p->mm;
- if (!mm)
+
+ /* Keep mm reference when svm_range_validate_and_map ranges */
+ mm = get_task_mm(p->lead_thread);
+ if (!mm) {
+ pr_debug("svms 0x%p process mm gone\n", svms);
return;
+ }

svm_range_list_lock_and_flush_work(svms, mm);
mutex_lock(&svms->lock);
@@ -1703,6 +1704,7 @@ static void svm_range_restore_work(struct work_struct *work)
out_reschedule:
mutex_unlock(&svms->lock);
mmap_write_unlock(mm);
+ mmput(mm);

/* If validation failed, reschedule another attempt */
if (evicted_ranges) {
@@ -1985,10 +1987,9 @@ svm_range_update_notifier_and_interval_tree(struct mm_struct *mm,
}

static void
-svm_range_handle_list_op(struct svm_range_list *svms, struct svm_range *prange)
+svm_range_handle_list_op(struct svm_range_list *svms, struct svm_range *prange,
+ struct mm_struct *mm)
{
- struct mm_struct *mm = prange->work_item.mm;
-
switch (prange->work_item.op) {
case SVM_OP_NULL:
pr_debug("NULL OP 0x%p prange 0x%p [0x%lx 0x%lx]\n",
@@ -2065,40 +2066,44 @@ static void svm_range_deferred_list_work(struct work_struct *work)
struct svm_range_list *svms;
struct svm_range *prange;
struct mm_struct *mm;
- struct kfd_process *p;

svms = container_of(work, struct svm_range_list, deferred_list_work);
pr_debug("enter svms 0x%p\n", svms);

- p = container_of(svms, struct kfd_process, svms);
- /* Avoid mm is gone when inserting mmu notifier */
- mm = get_task_mm(p->lead_thread);
- if (!mm) {
- pr_debug("svms 0x%p process mm gone\n", svms);
- return;
- }
-retry:
- mmap_write_lock(mm);
-
- /* Checking for the need to drain retry faults must be inside
- * mmap write lock to serialize with munmap notifiers.
- */
- if (unlikely(atomic_read(&svms->drain_pagefaults))) {
- mmap_write_unlock(mm);
- svm_range_drain_retry_fault(svms);
- goto retry;
- }
-
spin_lock(&svms->deferred_list_lock);
while (!list_empty(&svms->deferred_range_list)) {
prange = list_first_entry(&svms->deferred_range_list,
struct svm_range, deferred_list);
- list_del_init(&prange->deferred_list);
spin_unlock(&svms->deferred_list_lock);

pr_debug("prange 0x%p [0x%lx 0x%lx] op %d\n", prange,
prange->start, prange->last, prange->work_item.op);

+ mm = prange->work_item.mm;
+retry:
+ mmap_write_lock(mm);
+
+ /* Checking for the need to drain retry faults must be inside
+ * mmap write lock to serialize with munmap notifiers.
+ */
+ if (unlikely(atomic_read(&svms->drain_pagefaults))) {
+ mmap_write_unlock(mm);
+ svm_range_drain_retry_fault(svms);
+ goto retry;
+ }
+
+ /* Remove from deferred_list must be inside mmap write lock, for
+ * two race cases:
+ * 1. unmap_from_cpu may change work_item.op and add the range
+ * to deferred_list again, cause use after free bug.
+ * 2. svm_range_list_lock_and_flush_work may hold mmap write
+ * lock and continue because deferred_list is empty, but
+ * deferred_list work is actually waiting for mmap lock.
+ */
+ spin_lock(&svms->deferred_list_lock);
+ list_del_init(&prange->deferred_list);
+ spin_unlock(&svms->deferred_list_lock);
+
mutex_lock(&svms->lock);
mutex_lock(&prange->migrate_mutex);
while (!list_empty(&prange->child_list)) {
@@ -2109,19 +2114,20 @@ static void svm_range_deferred_list_work(struct work_struct *work)
pr_debug("child prange 0x%p op %d\n", pchild,
pchild->work_item.op);
list_del_init(&pchild->child_list);
- svm_range_handle_list_op(svms, pchild);
+ svm_range_handle_list_op(svms, pchild, mm);
}
mutex_unlock(&prange->migrate_mutex);

- svm_range_handle_list_op(svms, prange);
+ svm_range_handle_list_op(svms, prange, mm);
mutex_unlock(&svms->lock);
+ mmap_write_unlock(mm);
+
+ /* Pairs with mmget in svm_range_add_list_work */
+ mmput(mm);

spin_lock(&svms->deferred_list_lock);
}
spin_unlock(&svms->deferred_list_lock);
-
- mmap_write_unlock(mm);
- mmput(mm);
pr_debug("exit svms 0x%p\n", svms);
}

@@ -2139,6 +2145,9 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange,
prange->work_item.op = op;
} else {
prange->work_item.op = op;
+
+ /* Pairs with mmput in deferred_list_work */
+ mmget(mm);
prange->work_item.mm = mm;
list_add_tail(&prange->deferred_list,
&prange->svms->deferred_range_list);
@@ -2830,6 +2839,8 @@ void svm_range_list_fini(struct kfd_process *p)

pr_debug("pasid 0x%x svms 0x%p\n", p->pasid, &p->svms);

+ cancel_delayed_work_sync(&p->svms.restore_work);
+
/* Ensure list work is finished before process is destroyed */
flush_work(&p->svms.deferred_list_work);

@@ -2840,7 +2851,6 @@ void svm_range_list_fini(struct kfd_process *p)
atomic_inc(&p->svms.drain_pagefaults);
svm_range_drain_retry_fault(&p->svms);

-
list_for_each_entry_safe(prange, next, &p->svms.list, list) {
svm_range_unlink(prange);
svm_range_remove_notifier(prange);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index b28b5c490860..90c017859ad4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3951,7 +3951,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap
max - min);
}

-static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
int bl_idx,
u32 user_brightness)
{
@@ -3982,7 +3982,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx);
}

- return rc ? 0 : 1;
+ if (rc)
+ dm->actual_brightness[bl_idx] = user_brightness;
}

static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
@@ -9914,7 +9915,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
/* restore the backlight level */
for (i = 0; i < dm->num_of_edps; i++) {
if (dm->backlight_dev[i] &&
- (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i]))
+ (dm->actual_brightness[i] != dm->brightness[i]))
amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]);
}
#endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index b9a69b0cef23..7a23cd603714 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -540,6 +540,12 @@ struct amdgpu_display_manager {
* cached backlight values.
*/
u32 brightness[AMDGPU_DM_MAX_NUM_EDP];
+ /**
+ * @actual_brightness:
+ *
+ * last successfully applied backlight values.
+ */
+ u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP];
};

enum dsc_clock_force_state {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 26719efa5396..12d437d9a0e4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -227,8 +227,10 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -389,8 +391,10 @@ static ssize_t dp_phy_settings_read(struct file *f, char __user *buf,
break;

r = put_user((*(rd_buf + result)), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -1359,8 +1363,10 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -1376,8 +1382,10 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -1546,8 +1554,10 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -1563,8 +1573,10 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -1731,8 +1743,10 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -1748,8 +1762,10 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -1912,8 +1928,10 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -1929,8 +1947,10 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -2088,8 +2108,10 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -2105,8 +2127,10 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -2145,8 +2169,10 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -2162,8 +2188,10 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -2217,8 +2245,10 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -2234,8 +2264,10 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -2289,8 +2321,10 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,
break;
}

- if (!pipe_ctx)
+ if (!pipe_ctx) {
+ kfree(rd_buf);
return -ENXIO;
+ }

dsc = pipe_ctx->stream_res.dsc;
if (dsc)
@@ -2306,8 +2340,10 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,
break;

r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }

buf += 1;
size -= 1;
@@ -3459,8 +3495,10 @@ static ssize_t dcc_en_bits_read(
dc->hwss.get_dcc_en_bits(dc, dcc_en_bits);

rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
- if (!rd_buf)
+ if (!rd_buf) {
+ kfree(dcc_en_bits);
return -ENOMEM;
+ }

for (i = 0; i < num_pipes; i++)
offset += snprintf(rd_buf + offset, rd_buf_size - offset,
@@ -3473,8 +3511,10 @@ static ssize_t dcc_en_bits_read(
if (*pos >= rd_buf_size)
break;
r = put_user(*(rd_buf + result), buf);
- if (r)
+ if (r) {
+ kfree(rd_buf);
return r; /* r = -EFAULT */
+ }
buf += 1;
size -= 1;
*pos += 1;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index c510638b4f99..a009fc654ac9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -149,10 +149,8 @@ bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream)

link = stream->link;

- psr_config.psr_version = link->dpcd_caps.psr_caps.psr_version;
-
- if (psr_config.psr_version > 0) {
- psr_config.psr_exit_link_training_required = 0x1;
+ if (link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED) {
+ psr_config.psr_version = link->psr_settings.psr_version;
psr_config.psr_frame_capture_indication_req = 0;
psr_config.psr_rfb_setup_time = 0x37;
psr_config.psr_sdp_transmit_line_num_deadline = 0x20;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index ba1aa994db4b..62bc6ce88753 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -76,6 +76,8 @@

#include "dc_trace.h"

+#include "dce/dmub_outbox.h"
+
#define CTX \
dc->ctx

@@ -3707,13 +3709,23 @@ void dc_hardware_release(struct dc *dc)
}
#endif

-/**
- * dc_enable_dmub_notifications - Returns whether dmub notification can be enabled
- * @dc: dc structure
+/*
+ *****************************************************************************
+ * Function: dc_is_dmub_outbox_supported -
+ *
+ * @brief
+ * Checks whether DMUB FW supports outbox notifications, if supported
+ * DM should register outbox interrupt prior to actually enabling interrupts
+ * via dc_enable_dmub_outbox
*
- * Returns: True to enable dmub notifications, False otherwise
+ * @param
+ * [in] dc: dc structure
+ *
+ * @return
+ * True if DMUB FW supports outbox notifications, False otherwise
+ *****************************************************************************
*/
-bool dc_enable_dmub_notifications(struct dc *dc)
+bool dc_is_dmub_outbox_supported(struct dc *dc)
{
#if defined(CONFIG_DRM_AMD_DC_DCN)
/* YELLOW_CARP B0 USB4 DPIA needs dmub notifications for interrupts */
@@ -3728,6 +3740,48 @@ bool dc_enable_dmub_notifications(struct dc *dc)

/**
* dc_process_dmub_aux_transfer_async - Submits aux command to dmub via inbox message
+ * Function: dc_enable_dmub_notifications
+ *
+ * @brief
+ * Calls dc_is_dmub_outbox_supported to check if dmub fw supports outbox
+ * notifications. All DMs shall switch to dc_is_dmub_outbox_supported.
+ * This API shall be removed after switching.
+ *
+ * @param
+ * [in] dc: dc structure
+ *
+ * @return
+ * True if DMUB FW supports outbox notifications, False otherwise
+ *****************************************************************************
+ */
+bool dc_enable_dmub_notifications(struct dc *dc)
+{
+ return dc_is_dmub_outbox_supported(dc);
+}
+
+/**
+ *****************************************************************************
+ * Function: dc_enable_dmub_outbox
+ *
+ * @brief
+ * Enables DMUB unsolicited notifications to x86 via outbox
+ *
+ * @param
+ * [in] dc: dc structure
+ *
+ * @return
+ * None
+ *****************************************************************************
+ */
+void dc_enable_dmub_outbox(struct dc *dc)
+{
+ struct dc_context *dc_ctx = dc->ctx;
+
+ dmub_enable_outbox_notification(dc_ctx->dmub_srv);
+}
+
+/**
+ *****************************************************************************
* Sets port index appropriately for legacy DDC
* @dc: dc structure
* @link_index: link index
@@ -3829,7 +3883,7 @@ uint8_t get_link_index_from_dpia_port_index(const struct dc *dc,
* [in] payload: aux payload
* [out] notify: set_config immediate reply
*
- * @return
+ * @return
* True if successful, False if failure
*****************************************************************************
*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 61b8f29a0c30..49d5271dcfdc 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2378,22 +2378,27 @@ static enum link_training_result dp_perform_8b_10b_link_training(
repeater_id--) {
status = perform_clock_recovery_sequence(link, link_res, lt_settings, repeater_id);

- if (status != LINK_TRAINING_SUCCESS)
+ if (status != LINK_TRAINING_SUCCESS) {
+ repeater_training_done(link, repeater_id);
break;
+ }

status = perform_channel_equalization_sequence(link,
link_res,
lt_settings,
repeater_id);

+ repeater_training_done(link, repeater_id);
+
if (status != LINK_TRAINING_SUCCESS)
break;

- repeater_training_done(link, repeater_id);
+ for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) {
+ lt_settings->dpcd_lane_settings[lane].raw = 0;
+ lt_settings->hw_lane_settings[lane].VOLTAGE_SWING = 0;
+ lt_settings->hw_lane_settings[lane].PRE_EMPHASIS = 0;
+ }
}
-
- for (lane = 0; lane < (uint8_t)lt_settings->link_settings.lane_count; lane++)
- lt_settings->dpcd_lane_settings[lane].raw = 0;
}

if (status == LINK_TRAINING_SUCCESS) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 18757c158523..ac3071e38e4a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1640,6 +1640,9 @@ static bool are_stream_backends_same(
if (is_timing_changed(stream_a, stream_b))
return false;

+ if (stream_a->signal != stream_b->signal)
+ return false;
+
if (stream_a->dpms_off != stream_b->dpms_off)
return false;

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index b51864890621..6a8c100a3688 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1448,8 +1448,11 @@ void dc_z10_restore(const struct dc *dc);
void dc_z10_save_init(struct dc *dc);
#endif

+bool dc_is_dmub_outbox_supported(struct dc *dc);
bool dc_enable_dmub_notifications(struct dc *dc);

+void dc_enable_dmub_outbox(struct dc *dc);
+
bool dc_process_dmub_aux_transfer_async(struct dc *dc,
uint32_t link_index,
struct aux_payload *payload);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c
index faad8555ddbb..fff1d07d865d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c
@@ -22,20 +22,23 @@
* Authors: AMD
*/

-#include "dmub_outbox.h"
+#include "dc.h"
#include "dc_dmub_srv.h"
+#include "dmub_outbox.h"
#include "dmub/inc/dmub_cmd.h"

-/**
- * dmub_enable_outbox_notification - Sends inbox cmd to dmub to enable outbox1
- * messages with interrupt. Dmub sends outbox1
- * message and triggers outbox1 interrupt.
- * @dc: dc structure
+/*
+ * Function: dmub_enable_outbox_notification
+ *
+ * @brief
+ * Sends inbox cmd to dmub for enabling outbox notifications to x86.
+ *
+ * @param
+ * [in] dmub_srv: dmub_srv structure
*/
-void dmub_enable_outbox_notification(struct dc *dc)
+void dmub_enable_outbox_notification(struct dc_dmub_srv *dmub_srv)
{
union dmub_rb_cmd cmd;
- struct dc_context *dc_ctx = dc->ctx;

memset(&cmd, 0x0, sizeof(cmd));
cmd.outbox1_enable.header.type = DMUB_CMD__OUTBOX1_ENABLE;
@@ -45,7 +48,7 @@ void dmub_enable_outbox_notification(struct dc *dc)
sizeof(cmd.outbox1_enable.header);
cmd.outbox1_enable.enable = true;

- dc_dmub_srv_cmd_queue(dc_ctx->dmub_srv, &cmd);
- dc_dmub_srv_cmd_execute(dc_ctx->dmub_srv);
- dc_dmub_srv_wait_idle(dc_ctx->dmub_srv);
+ dc_dmub_srv_cmd_queue(dmub_srv, &cmd);
+ dc_dmub_srv_cmd_execute(dmub_srv);
+ dc_dmub_srv_wait_idle(dmub_srv);
}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.h
index 4e0aa0d1a2d5..58ceabb9d497 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.h
@@ -26,8 +26,8 @@
#ifndef _DMUB_OUTBOX_H_
#define _DMUB_OUTBOX_H_

-#include "dc.h"
+struct dc_dmub_srv;

-void dmub_enable_outbox_notification(struct dc *dc);
+void dmub_enable_outbox_notification(struct dc_dmub_srv *dmub_srv);

#endif /* _DMUB_OUTBOX_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 530a72e3eefe..2cefdd96d0cb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1493,17 +1493,6 @@ void dcn10_init_hw(struct dc *dc)
link->link_status.link_active = true;
}

- /* Power gate DSCs */
- if (!is_optimized_init_done) {
- for (i = 0; i < res_pool->res_cap->num_dsc; i++)
- if (hws->funcs.dsc_pg_control != NULL)
- hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false);
- }
-
- /* Enable outbox notification feature of dmub */
- if (dc->debug.enable_dmub_aux_for_legacy_ddc)
- dmub_enable_outbox_notification(dc);
-
/* we want to turn off all dp displays before doing detection */
if (dc->config.power_down_display_on_boot)
dc_link_blank_all_dp_displays(dc);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index e5cc6bf45743..ca1bbc942fd4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -873,7 +873,7 @@ static const struct dc_debug_options debug_defaults_drv = {
.clock_trace = true,
.disable_pplib_clock_request = true,
.min_disp_clk_khz = 100000,
- .pipe_split_policy = MPC_SPLIT_DYNAMIC,
+ .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
.force_single_disp_pipe_split = false,
.disable_dcc = DCC_ENABLE,
.vsr_support = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 4206ce5bf9a9..1e156f398065 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -194,7 +194,7 @@ void dcn31_init_hw(struct dc *dc)

/* Enables outbox notifications for usb4 dpia */
if (dc->res_pool->usb4_dpia_count)
- dmub_enable_outbox_notification(dc);
+ dmub_enable_outbox_notification(dc->ctx->dmub_srv);

/* we want to turn off all dp displays before doing detection */
if (dc->config.power_down_display_on_boot)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 8d64187478e4..0e11285035b6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -2025,7 +2025,9 @@ bool dcn31_validate_bandwidth(struct dc *dc,

BW_VAL_TRACE_COUNT();

+ DC_FP_START();
out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate);
+ DC_FP_END();

// Disable fast_validate to set min dcfclk in alculate_wm_and_dlg
if (pipe_cnt == 0)
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 08362d506534..a68496b3f929 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -1045,6 +1045,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)

if (!pp_funcs || !pp_funcs->get_asic_baco_capability)
return false;
+ /* Don't use baco for reset in S3.
+ * This is a workaround for some platforms
+ * where entering BACO during suspend
+ * seems to cause reboots or hangs.
+ * This might be related to the fact that BACO controls
+ * power to the whole GPU including devices like audio and USB.
+ * Powering down/up everything may adversely affect these other
+ * devices. Needs more investigation.
+ */
+ if (adev->in_s3)
+ return false;

if (pp_funcs->get_asic_baco_capability(pp_handle, &baco_cap))
return false;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 9ddd8491ff00..ede71de2343d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinFclkByFreq,
hwmgr->display_config->num_display > 3 ?
- data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk :
+ (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) :
min_mclk,
NULL);

smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinSocclkByFreq,
- data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk,
+ data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinVcn,
@@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxFclkByFreq,
- data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk,
+ data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxSocclkByFreq,
- data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk,
+ data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxVcn,
diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c
index 6e484d836cfe..691039aba87f 100644
--- a/drivers/gpu/drm/bridge/nwl-dsi.c
+++ b/drivers/gpu/drm/bridge/nwl-dsi.c
@@ -861,18 +861,19 @@ nwl_dsi_bridge_mode_set(struct drm_bridge *bridge,
memcpy(&dsi->mode, adjusted_mode, sizeof(dsi->mode));
drm_mode_debug_printmodeline(adjusted_mode);

- pm_runtime_get_sync(dev);
+ if (pm_runtime_resume_and_get(dev) < 0)
+ return;

if (clk_prepare_enable(dsi->lcdif_clk) < 0)
- return;
+ goto runtime_put;
if (clk_prepare_enable(dsi->core_clk) < 0)
- return;
+ goto runtime_put;

/* Step 1 from DSI reset-out instructions */
ret = reset_control_deassert(dsi->rst_pclk);
if (ret < 0) {
DRM_DEV_ERROR(dev, "Failed to deassert PCLK: %d\n", ret);
- return;
+ goto runtime_put;
}

/* Step 2 from DSI reset-out instructions */
@@ -882,13 +883,18 @@ nwl_dsi_bridge_mode_set(struct drm_bridge *bridge,
ret = reset_control_deassert(dsi->rst_esc);
if (ret < 0) {
DRM_DEV_ERROR(dev, "Failed to deassert ESC: %d\n", ret);
- return;
+ goto runtime_put;
}
ret = reset_control_deassert(dsi->rst_byte);
if (ret < 0) {
DRM_DEV_ERROR(dev, "Failed to deassert BYTE: %d\n", ret);
- return;
+ goto runtime_put;
}
+
+ return;
+
+runtime_put:
+ pm_runtime_put_sync(dev);
}

static void
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index b8f5419e514a..83e5c115e754 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -212,9 +212,7 @@ static const struct edid_quirk {

/* Windows Mixed Reality Headsets */
EDID_QUIRK('A', 'C', 'R', 0x7fce, EDID_QUIRK_NON_DESKTOP),
- EDID_QUIRK('H', 'P', 'N', 0x3515, EDID_QUIRK_NON_DESKTOP),
EDID_QUIRK('L', 'E', 'N', 0x0408, EDID_QUIRK_NON_DESKTOP),
- EDID_QUIRK('L', 'E', 'N', 0xb800, EDID_QUIRK_NON_DESKTOP),
EDID_QUIRK('F', 'U', 'J', 0x1970, EDID_QUIRK_NON_DESKTOP),
EDID_QUIRK('D', 'E', 'L', 0x7fce, EDID_QUIRK_NON_DESKTOP),
EDID_QUIRK('S', 'E', 'C', 0x144a, EDID_QUIRK_NON_DESKTOP),
@@ -5327,17 +5325,13 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi
info->width_mm = edid->width_cm * 10;
info->height_mm = edid->height_cm * 10;

- info->non_desktop = !!(quirks & EDID_QUIRK_NON_DESKTOP);
-
drm_get_monitor_range(connector, edid);

- DRM_DEBUG_KMS("non_desktop set to %d\n", info->non_desktop);
-
if (edid->revision < 3)
- return quirks;
+ goto out;

if (!(edid->input & DRM_EDID_INPUT_DIGITAL))
- return quirks;
+ goto out;

info->color_formats |= DRM_COLOR_FORMAT_RGB444;
drm_parse_cea_ext(connector, edid);
@@ -5358,7 +5352,7 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi

/* Only defined for 1.4 with digital displays */
if (edid->revision < 4)
- return quirks;
+ goto out;

switch (edid->input & DRM_EDID_DIGITAL_DEPTH_MASK) {
case DRM_EDID_DIGITAL_DEPTH_6:
@@ -5395,6 +5389,13 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi

drm_update_mso(connector, edid);

+out:
+ if (quirks & EDID_QUIRK_NON_DESKTOP) {
+ drm_dbg_kms(connector->dev, "Non-desktop display%s\n",
+ info->non_desktop ? " (redundant quirk)" : "");
+ info->non_desktop = true;
+ }
+
return quirks;
}

diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index b910978d3e48..4e853acfd1e8 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -180,6 +180,12 @@ static const struct dmi_system_id orientation_data[] = {
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "MicroPC"),
},
.driver_data = (void *)&lcd720x1280_rightside_up,
+ }, { /* GPD Win Max */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1619-01"),
+ },
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /*
* GPD Pocket, note that the the DMI data is less generic then
* it seems, devices with a board-vendor of "AMI Corporation"
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index 87428fb23d9f..a2277a0d6d06 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -222,6 +222,7 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev)
struct device_node *np = pdev->dev.of_node;
const struct of_device_id *match = of_match_node(dw_hdmi_imx_dt_ids, np);
struct imx_hdmi *hdmi;
+ int ret;

hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL);
if (!hdmi)
@@ -243,10 +244,15 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev)
hdmi->bridge = of_drm_find_bridge(np);
if (!hdmi->bridge) {
dev_err(hdmi->dev, "Unable to find bridge\n");
+ dw_hdmi_remove(hdmi->hdmi);
return -ENODEV;
}

- return component_add(&pdev->dev, &dw_hdmi_imx_ops);
+ ret = component_add(&pdev->dev, &dw_hdmi_imx_ops);
+ if (ret)
+ dw_hdmi_remove(hdmi->hdmi);
+
+ return ret;
}

static int dw_hdmi_imx_remove(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index e5078d03020d..fb0e951248f6 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -572,6 +572,8 @@ static int imx_ldb_panel_ddc(struct device *dev,
edidp = of_get_property(child, "edid", &edid_len);
if (edidp) {
channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL);
+ if (!channel->edid)
+ return -ENOMEM;
} else if (!channel->panel) {
/* fallback to display-timings node */
ret = of_get_drm_display_mode(child,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 06cb1a59b9bc..63ba2ad84679 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -75,8 +75,10 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
ret = of_get_drm_display_mode(np, &imxpd->mode,
&imxpd->bus_flags,
OF_USE_NATIVE_MODE);
- if (ret)
+ if (ret) {
+ drm_mode_destroy(connector->dev, mode);
return ret;
+ }

drm_mode_copy(mode, &imxpd->mode);
mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 6b3ced4aaaf5..3a3f53f0c8ae 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1877,7 +1877,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi)

/* do not autoenable, will be enabled later */
ret = devm_request_irq(&pdev->dev, msm_host->irq, dsi_host_irq,
- IRQF_TRIGGER_HIGH | IRQF_ONESHOT | IRQF_NO_AUTOEN,
+ IRQF_TRIGGER_HIGH | IRQF_NO_AUTOEN,
"dsi_isr", msm_host);
if (ret < 0) {
dev_err(&pdev->dev, "failed to request IRQ%u: %d\n",
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
index e1772211b0a4..612310d5d481 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
@@ -216,6 +216,7 @@ gm20b_pmu = {
.intr = gt215_pmu_intr,
.recv = gm20b_pmu_recv,
.initmsg = gm20b_pmu_initmsg,
+ .reset = gf100_pmu_reset,
};

#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
index 6bf7fc1bd1e3..1a6f9c3af5ec 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
@@ -23,7 +23,7 @@
*/
#include "priv.h"

-static void
+void
gp102_pmu_reset(struct nvkm_pmu *pmu)
{
struct nvkm_device *device = pmu->subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
index ba1583bb618b..94cfb1791af6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
@@ -83,6 +83,7 @@ gp10b_pmu = {
.intr = gt215_pmu_intr,
.recv = gm20b_pmu_recv,
.initmsg = gm20b_pmu_initmsg,
+ .reset = gp102_pmu_reset,
};

#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
index bcaade758ff7..21abf31f4442 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
@@ -41,6 +41,7 @@ int gt215_pmu_send(struct nvkm_pmu *, u32[2], u32, u32, u32, u32);

bool gf100_pmu_enabled(struct nvkm_pmu *);
void gf100_pmu_reset(struct nvkm_pmu *);
+void gp102_pmu_reset(struct nvkm_pmu *pmu);

void gk110_pmu_pgob(struct nvkm_pmu *, bool);

diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
index 2c3378a259b1..e1542451ef9d 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
@@ -612,8 +612,10 @@ static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc,
int ret;

vcc = devm_regulator_get_optional(dev, "vcc");
- if (IS_ERR(vcc))
+ if (IS_ERR(vcc)) {
dev_err(dev, "get optional vcc failed\n");
+ vcc = NULL;
+ }

dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver,
struct mipi_dbi_dev, drm);
diff --git a/drivers/gpu/drm/sprd/sprd_dpu.c b/drivers/gpu/drm/sprd/sprd_dpu.c
index 06a3414ee43a..1637203ea103 100644
--- a/drivers/gpu/drm/sprd/sprd_dpu.c
+++ b/drivers/gpu/drm/sprd/sprd_dpu.c
@@ -790,6 +790,11 @@ static int sprd_dpu_context_init(struct sprd_dpu *dpu,
int ret;

res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(dev, "failed to get I/O resource\n");
+ return -EINVAL;
+ }
+
ctx->base = devm_ioremap(dev, res->start, resource_size(res));
if (!ctx->base) {
dev_err(dev, "failed to map dpu registers\n");
diff --git a/drivers/gpu/drm/sprd/sprd_drm.c b/drivers/gpu/drm/sprd/sprd_drm.c
index a077e2d4d721..af2be97d5ed0 100644
--- a/drivers/gpu/drm/sprd/sprd_drm.c
+++ b/drivers/gpu/drm/sprd/sprd_drm.c
@@ -155,7 +155,7 @@ static void sprd_drm_shutdown(struct platform_device *pdev)
struct drm_device *drm = platform_get_drvdata(pdev);

if (!drm) {
- drm_warn(drm, "drm device is not available, no shutdown\n");
+ dev_warn(&pdev->dev, "drm device is not available, no shutdown\n");
return;
}

diff --git a/drivers/gpu/drm/sprd/sprd_dsi.c b/drivers/gpu/drm/sprd/sprd_dsi.c
index 911b3cddc264..12b67a5d5923 100644
--- a/drivers/gpu/drm/sprd/sprd_dsi.c
+++ b/drivers/gpu/drm/sprd/sprd_dsi.c
@@ -907,6 +907,11 @@ static int sprd_dsi_context_init(struct sprd_dsi *dsi,
struct resource *res;

res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(dev, "failed to get I/O resource\n");
+ return -EINVAL;
+ }
+
ctx->base = devm_ioremap(dev, res->start, resource_size(res));
if (!ctx->base) {
drm_err(dsi->drm, "failed to map dsi host registers\n");
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index c7ed2e1cbab6..92bc0faee84f 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -798,7 +798,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,

if (!render->base.perfmon) {
ret = -ENOENT;
- goto fail;
+ goto fail_perfmon;
}
}

@@ -847,6 +847,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,

fail_unreserve:
mutex_unlock(&v3d->sched_lock);
+fail_perfmon:
drm_gem_unlock_reservations(last_job->bo,
last_job->bo_count, &acquire_ctx);
fail:
@@ -1027,7 +1028,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
args->perfmon_id);
if (!job->base.perfmon) {
ret = -ENOENT;
- goto fail;
+ goto fail_perfmon;
}
}

@@ -1056,6 +1057,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data,

fail_unreserve:
mutex_unlock(&v3d->sched_lock);
+fail_perfmon:
drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count,
&acquire_ctx);
fail:
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 7dc89dc6b0f0..590376d776a1 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -748,15 +748,15 @@ static const struct hid_device_id apple_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY),
.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021),
- .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
+ .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021),
.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021),
- .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
+ .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021),
.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021),
- .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
+ .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021),
.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 60375879612f..67be81208a2d 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel)
* execute:
*
* (a) In the "normal (i.e., not resuming from hibernation)" path,
- * the full barrier in smp_store_mb() guarantees that the store
+ * the full barrier in virt_store_mb() guarantees that the store
* is propagated to all CPUs before the add_channel_work work
* is queued. In turn, add_channel_work is queued before the
* channel's ring buffer is allocated/initialized and the
@@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel)
* recv_int_page before retrieving the channel pointer from the
* array of channels.
*
- * (b) In the "resuming from hibernation" path, the smp_store_mb()
+ * (b) In the "resuming from hibernation" path, the virt_store_mb()
* guarantees that the store is propagated to all CPUs before
* the VMBus connection is marked as ready for the resume event
* (cf. check_ready_for_resume_event()). The interrupt handler
* of the VMBus driver and vmbus_chan_sched() can not run before
* vmbus_bus_resume() has completed execution (cf. resume_noirq).
*/
- smp_store_mb(
+ virt_store_mb(
vmbus_connection.channels[channel->offermsg.child_relid],
channel);
}
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 12a2b37e87f3..4bea1dfa41cd 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2097,6 +2097,10 @@ int vmbus_device_register(struct hv_device *child_device_obj)
child_device_obj->device.parent = &hv_acpi_dev->dev;
child_device_obj->device.release = vmbus_device_release;

+ child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
+ child_device_obj->device.dma_mask = &child_device_obj->dma_mask;
+ dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64));
+
/*
* Register with the LDM. This will kick off the driver/device
* binding...which will eventually call vmbus_match() and vmbus_probe()
@@ -2122,9 +2126,6 @@ int vmbus_device_register(struct hv_device *child_device_obj)
}
hv_debug_add_dev_dir(child_device_obj);

- child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
- child_device_obj->device.dma_mask = &child_device_obj->dma_mask;
- dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64));
return 0;

err_kset_unregister:
@@ -2780,10 +2781,15 @@ static void __exit vmbus_exit(void)
if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
kmsg_dump_unregister(&hv_kmsg_dumper);
unregister_die_notifier(&hyperv_die_block);
- atomic_notifier_chain_unregister(&panic_notifier_list,
- &hyperv_panic_block);
}

+ /*
+ * The panic notifier is always registered, hence we should
+ * also unconditionally unregister it here as well.
+ */
+ atomic_notifier_chain_unregister(&panic_notifier_list,
+ &hyperv_panic_block);
+
free_page((unsigned long)hv_panic_page);
unregister_sysctl_table(hv_ctl_table_hdr);
hv_ctl_table_hdr = NULL;
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 35f0d5e7533d..1c107d6d03b9 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -2824,6 +2824,7 @@ static int cm_dreq_handler(struct cm_work *work)
switch (cm_id_priv->id.state) {
case IB_CM_REP_SENT:
case IB_CM_DREQ_SENT:
+ case IB_CM_MRA_REP_RCVD:
ib_cancel_mad(cm_id_priv->msg);
break;
case IB_CM_ESTABLISHED:
@@ -2831,8 +2832,6 @@ static int cm_dreq_handler(struct cm_work *work)
cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD)
ib_cancel_mad(cm_id_priv->msg);
break;
- case IB_CM_MRA_REP_RCVD:
- break;
case IB_CM_TIMEWAIT:
atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES]
[CM_DREQ_COUNTER]);
diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
index 876cc78a22cc..7333646021bb 100644
--- a/drivers/infiniband/hw/hfi1/mmu_rb.c
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -80,6 +80,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler)
unsigned long flags;
struct list_head del_list;

+ /* Prevent freeing of mm until we are completely finished. */
+ mmgrab(handler->mn.mm);
+
/* Unregister first so we don't get any more notifications. */
mmu_notifier_unregister(&handler->mn, handler->mn.mm);

@@ -102,6 +105,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler)

do_remove(handler, &del_list);

+ /* Now the mm may be freed. */
+ mmdrop(handler->mn.mm);
+
kfree(handler);
}

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 2910d7833313..d40a1460ef97 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -541,8 +541,10 @@ static void __cache_work_func(struct mlx5_cache_ent *ent)
spin_lock_irq(&ent->lock);
if (ent->disabled)
goto out;
- if (need_delay)
+ if (need_delay) {
queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ);
+ goto out;
+ }
remove_cache_mr_locked(ent);
queue_adjust_cache_locked(ent);
}
@@ -630,6 +632,7 @@ static void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
{
struct mlx5_cache_ent *ent = mr->cache_ent;

+ WRITE_ONCE(dev->cache.last_add, jiffies);
spin_lock_irq(&ent->lock);
list_add_tail(&mr->list, &ent->head);
ent->available_mrs++;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index ae50b56e8913..8ef112f883a7 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -3190,7 +3190,11 @@ void rvt_ruc_loopback(struct rvt_qp *sqp)
spin_lock_irqsave(&sqp->s_lock, flags);
rvt_send_complete(sqp, wqe, send_status);
if (sqp->ibqp.qp_type == IB_QPT_RC) {
- int lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR);
+ int lastwqe;
+
+ spin_lock(&sqp->r_lock);
+ lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR);
+ spin_unlock(&sqp->r_lock);

sqp->s_flags &= ~RVT_S_BUSY;
spin_unlock_irqrestore(&sqp->s_lock, flags);
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 759b85f03331..df4d06d4d183 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -297,6 +297,7 @@ static bool rtrs_clt_change_state_from_to(struct rtrs_clt_path *clt_path,
return changed;
}

+static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_path *clt_path);
static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
{
struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
@@ -304,16 +305,7 @@ static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
if (rtrs_clt_change_state_from_to(clt_path,
RTRS_CLT_CONNECTED,
RTRS_CLT_RECONNECTING)) {
- struct rtrs_clt_sess *clt = clt_path->clt;
- unsigned int delay_ms;
-
- /*
- * Normal scenario, reconnect if we were successfully connected
- */
- delay_ms = clt->reconnect_delay_sec * 1000;
- queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
- msecs_to_jiffies(delay_ms +
- prandom_u32() % RTRS_RECONNECT_SEED));
+ queue_work(rtrs_wq, &clt_path->err_recovery_work);
} else {
/*
* Error can happen just on establishing new connection,
@@ -1511,6 +1503,22 @@ static void rtrs_clt_init_hb(struct rtrs_clt_path *clt_path)
static void rtrs_clt_reconnect_work(struct work_struct *work);
static void rtrs_clt_close_work(struct work_struct *work);

+static void rtrs_clt_err_recovery_work(struct work_struct *work)
+{
+ struct rtrs_clt_path *clt_path;
+ struct rtrs_clt_sess *clt;
+ int delay_ms;
+
+ clt_path = container_of(work, struct rtrs_clt_path, err_recovery_work);
+ clt = clt_path->clt;
+ delay_ms = clt->reconnect_delay_sec * 1000;
+ rtrs_clt_stop_and_destroy_conns(clt_path);
+ queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
+ msecs_to_jiffies(delay_ms +
+ prandom_u32() %
+ RTRS_RECONNECT_SEED));
+}
+
static struct rtrs_clt_path *alloc_path(struct rtrs_clt_sess *clt,
const struct rtrs_addr *path,
size_t con_num, u32 nr_poll_queues)
@@ -1562,6 +1570,7 @@ static struct rtrs_clt_path *alloc_path(struct rtrs_clt_sess *clt,
clt_path->state = RTRS_CLT_CONNECTING;
atomic_set(&clt_path->connected_cnt, 0);
INIT_WORK(&clt_path->close_work, rtrs_clt_close_work);
+ INIT_WORK(&clt_path->err_recovery_work, rtrs_clt_err_recovery_work);
INIT_DELAYED_WORK(&clt_path->reconnect_dwork, rtrs_clt_reconnect_work);
rtrs_clt_init_hb(clt_path);

@@ -2326,6 +2335,7 @@ static void rtrs_clt_close_work(struct work_struct *work)

clt_path = container_of(work, struct rtrs_clt_path, close_work);

+ cancel_work_sync(&clt_path->err_recovery_work);
cancel_delayed_work_sync(&clt_path->reconnect_dwork);
rtrs_clt_stop_and_destroy_conns(clt_path);
rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CLOSED, NULL);
@@ -2638,7 +2648,6 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
{
struct rtrs_clt_path *clt_path;
struct rtrs_clt_sess *clt;
- unsigned int delay_ms;
int err;

clt_path = container_of(to_delayed_work(work), struct rtrs_clt_path,
@@ -2655,8 +2664,6 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
}
clt_path->reconnect_attempts++;

- /* Stop everything */
- rtrs_clt_stop_and_destroy_conns(clt_path);
msleep(RTRS_RECONNECT_BACKOFF);
if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CONNECTING, NULL)) {
err = init_path(clt_path);
@@ -2669,11 +2676,7 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
reconnect_again:
if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_RECONNECTING, NULL)) {
clt_path->stats->reconnects.fail_cnt++;
- delay_ms = clt->reconnect_delay_sec * 1000;
- queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
- msecs_to_jiffies(delay_ms +
- prandom_u32() %
- RTRS_RECONNECT_SEED));
+ queue_work(rtrs_wq, &clt_path->err_recovery_work);
}
}

@@ -2908,6 +2911,7 @@ int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_path *clt_path)
&old_state);
if (changed) {
clt_path->reconnect_attempts = 0;
+ rtrs_clt_stop_and_destroy_conns(clt_path);
queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork, 0);
}
if (changed || old_state == RTRS_CLT_RECONNECTING) {
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index d1b18a154ae0..f848c0392d98 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -134,6 +134,7 @@ struct rtrs_clt_path {
struct rtrs_clt_io_req *reqs;
struct delayed_work reconnect_dwork;
struct work_struct close_work;
+ struct work_struct err_recovery_work;
unsigned int reconnect_attempts;
bool established;
struct rtrs_rbuf *rbufs;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 6dc6d8b6b368..f60381cdf1c4 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1558,6 +1558,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
dev_info(smmu->dev, "\t0x%016llx\n",
(unsigned long long)evt[i]);

+ cond_resched();
}

/*
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index 980e4af3f06b..d2e82a1b56d8 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1661,7 +1661,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev)
num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus",
sizeof(phandle));
if (num_iommus < 0)
- return 0;
+ return ERR_PTR(-ENODEV);

arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL);
if (!arch_data)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index cd772973114a..a0fc764ec9dc 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3011,18 +3011,12 @@ static int __init allocate_lpi_tables(void)
return 0;
}

-static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set)
+static u64 read_vpend_dirty_clear(void __iomem *vlpi_base)
{
u32 count = 1000000; /* 1s! */
bool clean;
u64 val;

- val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
- val &= ~GICR_VPENDBASER_Valid;
- val &= ~clr;
- val |= set;
- gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
do {
val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
clean = !(val & GICR_VPENDBASER_Dirty);
@@ -3033,10 +3027,26 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set)
}
} while (!clean && count);

- if (unlikely(val & GICR_VPENDBASER_Dirty)) {
+ if (unlikely(!clean))
pr_err_ratelimited("ITS virtual pending table not cleaning\n");
+
+ return val;
+}
+
+static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set)
+{
+ u64 val;
+
+ /* Make sure we wait until the RD is done with the initial scan */
+ val = read_vpend_dirty_clear(vlpi_base);
+ val &= ~GICR_VPENDBASER_Valid;
+ val &= ~clr;
+ val |= set;
+ gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+ val = read_vpend_dirty_clear(vlpi_base);
+ if (unlikely(val & GICR_VPENDBASER_Dirty))
val |= GICR_VPENDBASER_PendingLast;
- }

return val;
}
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 5e935d97207d..907af63d1bba 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -206,11 +206,11 @@ static inline void __iomem *gic_dist_base(struct irq_data *d)
}
}

-static void gic_do_wait_for_rwp(void __iomem *base)
+static void gic_do_wait_for_rwp(void __iomem *base, u32 bit)
{
u32 count = 1000000; /* 1s! */

- while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) {
+ while (readl_relaxed(base + GICD_CTLR) & bit) {
count--;
if (!count) {
pr_err_ratelimited("RWP timeout, gone fishing\n");
@@ -224,13 +224,13 @@ static void gic_do_wait_for_rwp(void __iomem *base)
/* Wait for completion of a distributor change */
static void gic_dist_wait_for_rwp(void)
{
- gic_do_wait_for_rwp(gic_data.dist_base);
+ gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP);
}

/* Wait for completion of a redistributor change */
static void gic_redist_wait_for_rwp(void)
{
- gic_do_wait_for_rwp(gic_data_rdist_rd_base());
+ gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP);
}

#ifdef CONFIG_ARM64
@@ -1466,6 +1466,12 @@ static int gic_irq_domain_translate(struct irq_domain *d,
if(fwspec->param_count != 2)
return -EINVAL;

+ if (fwspec->param[0] < 16) {
+ pr_err(FW_BUG "Illegal GSI%d translation request\n",
+ fwspec->param[0]);
+ return -EINVAL;
+ }
+
*hwirq = fwspec->param[0];
*type = fwspec->param[1];

diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index b8bb46c65a97..3dbac62c932d 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1085,6 +1085,12 @@ static int gic_irq_domain_translate(struct irq_domain *d,
if(fwspec->param_count != 2)
return -EINVAL;

+ if (fwspec->param[0] < 16) {
+ pr_err(FW_BUG "Illegal GSI%d translation request\n",
+ fwspec->param[0]);
+ return -EINVAL;
+ }
+
*hwirq = fwspec->param[0];
*type = fwspec->param[1];

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 21fe8652b095..901abd6dea41 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -18,6 +18,7 @@
#include <linux/dm-ioctl.h>
#include <linux/hdreg.h>
#include <linux/compat.h>
+#include <linux/nospec.h>

#include <linux/uaccess.h>
#include <linux/ima.h>
@@ -1788,6 +1789,7 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags)
if (unlikely(cmd >= ARRAY_SIZE(_ioctls)))
return NULL;

+ cmd = array_index_nospec(cmd, ARRAY_SIZE(_ioctls));
*ioctl_flags = _ioctls[cmd].flags;
return _ioctls[cmd].fn;
}
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 579ab6183d4d..dffeb47a9efb 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -499,8 +499,13 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,

if (unlikely(!ti)) {
int srcu_idx;
- struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+ struct dm_table *map;

+ map = dm_get_live_table(md, &srcu_idx);
+ if (unlikely(!map)) {
+ dm_put_live_table(md, srcu_idx);
+ return BLK_STS_RESOURCE;
+ }
ti = dm_table_find_target(map, 0);
dm_put_live_table(md, srcu_idx);
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 394778d8bf54..dcb8d8fc7877 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1519,15 +1519,10 @@ static void dm_submit_bio(struct bio *bio)
struct dm_table *map;

map = dm_get_live_table(md, &srcu_idx);
- if (unlikely(!map)) {
- DMERR_LIMIT("%s: mapping table unavailable, erroring io",
- dm_device_name(md));
- bio_io_error(bio);
- goto out;
- }

- /* If suspended, queue this IO for later */
- if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
+ /* If suspended, or map not yet available, queue this IO for later */
+ if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) ||
+ unlikely(!map)) {
if (bio->bi_opf & REQ_NOWAIT)
bio_wouldblock_error(bio);
else if (bio->bi_opf & REQ_RAHEAD)
diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c
index c1eefaebacb6..bcc6e547e071 100644
--- a/drivers/misc/habanalabs/common/memory.c
+++ b/drivers/misc/habanalabs/common/memory.c
@@ -1967,16 +1967,15 @@ static int export_dmabuf_from_handle(struct hl_ctx *ctx, u64 handle, int flags,
static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)
{
struct hl_device *hdev = hpriv->hdev;
- struct hl_ctx *ctx = hpriv->ctx;
u64 block_handle, device_addr = 0;
+ struct hl_ctx *ctx = hpriv->ctx;
u32 handle = 0, block_size;
- int rc, dmabuf_fd = -EBADF;
+ int rc;

switch (args->in.op) {
case HL_MEM_OP_ALLOC:
if (args->in.alloc.mem_size == 0) {
- dev_err(hdev->dev,
- "alloc size must be larger than 0\n");
+ dev_err(hdev->dev, "alloc size must be larger than 0\n");
rc = -EINVAL;
goto out;
}
@@ -1997,15 +1996,14 @@ static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)

case HL_MEM_OP_MAP:
if (args->in.flags & HL_MEM_USERPTR) {
- device_addr = args->in.map_host.host_virt_addr;
- rc = 0;
+ dev_err(hdev->dev, "Failed to map host memory when MMU is disabled\n");
+ rc = -EPERM;
} else {
- rc = get_paddr_from_handle(ctx, &args->in,
- &device_addr);
+ rc = get_paddr_from_handle(ctx, &args->in, &device_addr);
+ memset(args, 0, sizeof(*args));
+ args->out.device_virt_addr = device_addr;
}

- memset(args, 0, sizeof(*args));
- args->out.device_virt_addr = device_addr;
break;

case HL_MEM_OP_UNMAP:
@@ -2013,20 +2011,14 @@ static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)
break;

case HL_MEM_OP_MAP_BLOCK:
- rc = map_block(hdev, args->in.map_block.block_addr,
- &block_handle, &block_size);
+ rc = map_block(hdev, args->in.map_block.block_addr, &block_handle, &block_size);
args->out.block_handle = block_handle;
args->out.block_size = block_size;
break;

case HL_MEM_OP_EXPORT_DMABUF_FD:
- rc = export_dmabuf_from_addr(ctx,
- args->in.export_dmabuf_fd.handle,
- args->in.export_dmabuf_fd.mem_size,
- args->in.flags,
- &dmabuf_fd);
- memset(args, 0, sizeof(*args));
- args->out.fd = dmabuf_fd;
+ dev_err(hdev->dev, "Failed to export dma-buf object when MMU is disabled\n");
+ rc = -EPERM;
break;

default:
diff --git a/drivers/misc/habanalabs/common/mmu/mmu_v1.c b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
index 6134b6ae7615..3cadef97817d 100644
--- a/drivers/misc/habanalabs/common/mmu/mmu_v1.c
+++ b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
@@ -467,7 +467,7 @@ static void hl_mmu_v1_fini(struct hl_device *hdev)
{
/* MMU H/W fini was already done in device hw_fini() */

- if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.hr.mmu_shadow_hop0)) {
+ if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.dr.mmu_shadow_hop0)) {
kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 013c6da2e3ca..b4dacea80151 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7819,6 +7819,48 @@ static void gaudi_print_fw_alive_info(struct hl_device *hdev,
fw_alive->thread_id, fw_alive->uptime_seconds);
}

+static void gaudi_print_nic_axi_irq_info(struct hl_device *hdev, u16 event_type,
+ void *data)
+{
+ char desc[64] = "", *type;
+ struct eq_nic_sei_event *eq_nic_sei = data;
+ u16 nic_id = event_type - GAUDI_EVENT_NIC_SEI_0;
+
+ switch (eq_nic_sei->axi_error_cause) {
+ case RXB:
+ type = "RXB";
+ break;
+ case RXE:
+ type = "RXE";
+ break;
+ case TXS:
+ type = "TXS";
+ break;
+ case TXE:
+ type = "TXE";
+ break;
+ case QPC_RESP:
+ type = "QPC_RESP";
+ break;
+ case NON_AXI_ERR:
+ type = "NON_AXI_ERR";
+ break;
+ case TMR:
+ type = "TMR";
+ break;
+ default:
+ dev_err(hdev->dev, "unknown NIC AXI cause %d\n",
+ eq_nic_sei->axi_error_cause);
+ type = "N/A";
+ break;
+ }
+
+ snprintf(desc, sizeof(desc), "NIC%d_%s%d", nic_id, type,
+ eq_nic_sei->id);
+ dev_err_ratelimited(hdev->dev, "Received H/W interrupt %d [\"%s\"]\n",
+ event_type, desc);
+}
+
static int gaudi_non_hard_reset_late_init(struct hl_device *hdev)
{
/* GAUDI doesn't support any reset except hard-reset */
@@ -8066,6 +8108,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
struct hl_eq_entry *eq_entry)
{
struct gaudi_device *gaudi = hdev->asic_specific;
+ u64 data = le64_to_cpu(eq_entry->data[0]);
u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
u32 fw_fatal_err_flag = 0;
u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
@@ -8263,6 +8306,11 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
hl_fw_unmask_irq(hdev, event_type);
break;

+ case GAUDI_EVENT_NIC_SEI_0 ... GAUDI_EVENT_NIC_SEI_4:
+ gaudi_print_nic_axi_irq_info(hdev, event_type, &data);
+ hl_fw_unmask_irq(hdev, event_type);
+ break;
+
case GAUDI_EVENT_DMA_IF_SEI_0 ... GAUDI_EVENT_DMA_IF_SEI_3:
gaudi_print_irq_info(hdev, event_type, false);
gaudi_print_sm_sei_info(hdev, event_type,
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 4e67c1403cc9..db99882c95d8 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1880,6 +1880,31 @@ static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq)
brq->data.error || brq->cmd.resp[0] & CMD_ERRORS;
}

+static int mmc_spi_err_check(struct mmc_card *card)
+{
+ u32 status = 0;
+ int err;
+
+ /*
+ * SPI does not have a TRAN state we have to wait on, instead the
+ * card is ready again when it no longer holds the line LOW.
+ * We still have to ensure two things here before we know the write
+ * was successful:
+ * 1. The card has not disconnected during busy and we actually read our
+ * own pull-up, thinking it was still connected, so ensure it
+ * still responds.
+ * 2. Check for any error bits, in particular R1_SPI_IDLE to catch a
+ * just reconnected card after being disconnected during busy.
+ */
+ err = __mmc_send_status(card, &status, 0);
+ if (err)
+ return err;
+ /* All R1 and R2 bits of SPI are errors in our case */
+ if (status)
+ return -EIO;
+ return 0;
+}
+
static int mmc_blk_busy_cb(void *cb_data, bool *busy)
{
struct mmc_blk_busy_data *data = cb_data;
@@ -1903,9 +1928,16 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req)
struct mmc_blk_busy_data cb_data;
int err;

- if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ)
+ if (rq_data_dir(req) == READ)
return 0;

+ if (mmc_host_is_spi(card->host)) {
+ err = mmc_spi_err_check(card);
+ if (err)
+ mqrq->brq.data.bytes_xfered = 0;
+ return err;
+ }
+
cb_data.card = card;
cb_data.status = 0;
err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS,
@@ -2350,6 +2382,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
struct mmc_blk_data *md;
int devidx, ret;
char cap_str[10];
+ bool cache_enabled = false;
+ bool fua_enabled = false;

devidx = ida_simple_get(&mmc_blk_ida, 0, max_devices, GFP_KERNEL);
if (devidx < 0) {
@@ -2429,13 +2463,17 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
md->flags |= MMC_BLK_CMD23;
}

- if (mmc_card_mmc(card) &&
- md->flags & MMC_BLK_CMD23 &&
+ if (md->flags & MMC_BLK_CMD23 &&
((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) ||
card->ext_csd.rel_sectors)) {
md->flags |= MMC_BLK_REL_WR;
- blk_queue_write_cache(md->queue.queue, true, true);
+ fua_enabled = true;
+ cache_enabled = true;
}
+ if (mmc_cache_enabled(card->host))
+ cache_enabled = true;
+
+ blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled);

string_get_size((u64)size, 512, STRING_UNITS_2,
cap_str, sizeof(cap_str));
diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
index 20f568727277..f879dc63d936 100644
--- a/drivers/mmc/core/quirks.h
+++ b/drivers/mmc/core/quirks.h
@@ -149,6 +149,11 @@ static const struct mmc_fixup __maybe_unused sdio_fixup_methods[] = {
static const struct mmc_fixup __maybe_unused sdio_card_init_methods[] = {
SDIO_FIXUP_COMPATIBLE("ti,wl1251", wl1251_quirk, 0),

+ SDIO_FIXUP_COMPATIBLE("silabs,wf200", add_quirk,
+ MMC_QUIRK_BROKEN_BYTE_MODE_512 |
+ MMC_QUIRK_LENIENT_FN0 |
+ MMC_QUIRK_BLKSZ_FOR_BYTE_MODE),
+
END_FIXUP
};

diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c
index 9c13f2c31365..4566d7fc9055 100644
--- a/drivers/mmc/host/mmci_stm32_sdmmc.c
+++ b/drivers/mmc/host/mmci_stm32_sdmmc.c
@@ -62,8 +62,8 @@ static int sdmmc_idma_validate_data(struct mmci_host *host,
* excepted the last element which has no constraint on idmasize
*/
for_each_sg(data->sg, sg, data->sg_len - 1, i) {
- if (!IS_ALIGNED(data->sg->offset, sizeof(u32)) ||
- !IS_ALIGNED(data->sg->length, SDMMC_IDMA_BURST)) {
+ if (!IS_ALIGNED(sg->offset, sizeof(u32)) ||
+ !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) {
dev_err(mmc_dev(host->mmc),
"unaligned scatterlist: ofst:%x length:%d\n",
data->sg->offset, data->sg->length);
@@ -71,7 +71,7 @@ static int sdmmc_idma_validate_data(struct mmci_host *host,
}
}

- if (!IS_ALIGNED(data->sg->offset, sizeof(u32))) {
+ if (!IS_ALIGNED(sg->offset, sizeof(u32))) {
dev_err(mmc_dev(host->mmc),
"unaligned last scatterlist: ofst:%x length:%d\n",
data->sg->offset, data->sg->length);
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 2797a9c0f17d..ddb5ca2f559e 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -144,9 +144,9 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host,
return clk_get_rate(priv->clk);

if (priv->clkh) {
+ /* HS400 with 4TAP needs different clock settings */
bool use_4tap = priv->quirks && priv->quirks->hs400_4taps;
- bool need_slow_clkh = (host->mmc->ios.timing == MMC_TIMING_UHS_SDR104) ||
- (host->mmc->ios.timing == MMC_TIMING_MMC_HS400);
+ bool need_slow_clkh = host->mmc->ios.timing == MMC_TIMING_MMC_HS400;
clkh_shift = use_4tap && need_slow_clkh ? 1 : 2;
ref_clk = priv->clkh;
}
@@ -396,10 +396,10 @@ static void renesas_sdhi_hs400_complete(struct mmc_host *mmc)
SH_MOBILE_SDHI_SCC_TMPPORT2_HS400OSEL) |
sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_TMPPORT2));

- /* Set the sampling clock selection range of HS400 mode */
sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DTCNTL,
SH_MOBILE_SDHI_SCC_DTCNTL_TAPEN |
- 0x4 << SH_MOBILE_SDHI_SCC_DTCNTL_TAPNUM_SHIFT);
+ sd_scc_read32(host, priv,
+ SH_MOBILE_SDHI_SCC_DTCNTL));

/* Avoid bad TAP */
if (bad_taps & BIT(priv->tap_set)) {
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 666cee4c7f7c..08e838400b52 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -241,16 +241,6 @@ static void xenon_voltage_switch(struct sdhci_host *host)
{
/* Wait for 5ms after set 1.8V signal enable bit */
usleep_range(5000, 5500);
-
- /*
- * For some reason the controller's Host Control2 register reports
- * the bit representing 1.8V signaling as 0 when read after it was
- * written as 1. Subsequent read reports 1.
- *
- * Since this may cause some issues, do an empty read of the Host
- * Control2 register here to circumvent this.
- */
- sdhci_readw(host, SDHCI_HOST_CONTROL2);
}

static unsigned int xenon_get_max_clock(struct sdhci_host *host)
diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c
index ec87126e1a7d..8ccda748fd08 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_fd.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c
@@ -172,12 +172,11 @@ static int es58x_fd_rx_event_msg(struct net_device *netdev,
const struct es58x_fd_rx_event_msg *rx_event_msg;
int ret;

+ rx_event_msg = &es58x_fd_urb_cmd->rx_event_msg;
ret = es58x_check_msg_len(es58x_dev->dev, *rx_event_msg, msg_len);
if (ret)
return ret;

- rx_event_msg = &es58x_fd_urb_cmd->rx_event_msg;
-
return es58x_rx_err_msg(netdev, rx_event_msg->error_code,
rx_event_msg->event_code,
get_unaligned_le64(&rx_event_msg->timestamp));
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 33f0ceae381d..2875b5250856 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1940,6 +1940,10 @@ static int vsc9959_psfp_filter_add(struct ocelot *ocelot, int port,
case FLOW_ACTION_GATE:
size = struct_size(sgi, entries, a->gate.num_entries);
sgi = kzalloc(size, GFP_KERNEL);
+ if (!sgi) {
+ ret = -ENOMEM;
+ goto err;
+ }
vsc9959_psfp_parse_gate(a, sgi);
ret = vsc9959_psfp_sgi_table_add(ocelot, sgi);
if (ret) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b1c98d1408b8..6af0ae1d0c46 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3224,6 +3224,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
}
qidx = bp->tc_to_qidx[j];
ring->queue_id = bp->q_info[qidx].queue_id;
+ spin_lock_init(&txr->xdp_tx_lock);
if (i < bp->tx_nr_rings_xdp)
continue;
if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1))
@@ -10294,6 +10295,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
if (irq_re_init)
udp_tunnel_nic_reset_ntf(bp->dev);

+ if (bp->tx_nr_rings_xdp < num_possible_cpus()) {
+ if (!static_key_enabled(&bnxt_xdp_locking_key))
+ static_branch_enable(&bnxt_xdp_locking_key);
+ } else if (static_key_enabled(&bnxt_xdp_locking_key)) {
+ static_branch_disable(&bnxt_xdp_locking_key);
+ }
set_bit(BNXT_STATE_OPEN, &bp->state);
bnxt_enable_int(bp);
/* Enable TX queues */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 666fc1e7a7d2..d57bff46b587 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -593,7 +593,8 @@ struct nqe_cn {
#define BNXT_MAX_MTU 9500
#define BNXT_MAX_PAGE_MODE_MTU \
((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \
- XDP_PACKET_HEADROOM)
+ XDP_PACKET_HEADROOM - \
+ SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)))

#define BNXT_MIN_PKT_SIZE 52

@@ -800,6 +801,8 @@ struct bnxt_tx_ring_info {
u32 dev_state;

struct bnxt_ring_struct tx_ring_struct;
+ /* Synchronize simultaneous xdp_xmit on same ring */
+ spinlock_t xdp_tx_lock;
};

#define BNXT_LEGACY_COAL_CMPL_PARAMS \
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 8aaa2335f848..f09b04556c32 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2101,9 +2101,7 @@ static int bnxt_set_pauseparam(struct net_device *dev,
}

link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
- if (bp->hwrm_spec_code >= 0x10201)
- link_info->req_flow_ctrl =
- PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE;
+ link_info->req_flow_ctrl = 0;
} else {
/* when transition from auto pause to force pause,
* force a link change
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 52fad0fdeacf..03b1d6c04504 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -20,6 +20,8 @@
#include "bnxt.h"
#include "bnxt_xdp.h"

+DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key);
+
struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
struct bnxt_tx_ring_info *txr,
dma_addr_t mapping, u32 len)
@@ -227,11 +229,16 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
ring = smp_processor_id() % bp->tx_nr_rings_xdp;
txr = &bp->tx_ring[ring];

+ if (READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING)
+ return -EINVAL;
+
+ if (static_branch_unlikely(&bnxt_xdp_locking_key))
+ spin_lock(&txr->xdp_tx_lock);
+
for (i = 0; i < num_frames; i++) {
struct xdp_frame *xdp = frames[i];

- if (!txr || !bnxt_tx_avail(bp, txr) ||
- !(bp->bnapi[ring]->flags & BNXT_NAPI_FLAG_XDP))
+ if (!bnxt_tx_avail(bp, txr))
break;

mapping = dma_map_single(&pdev->dev, xdp->data, xdp->len,
@@ -250,6 +257,9 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
bnxt_db_write(bp, &txr->tx_db, txr->tx_prod);
}

+ if (static_branch_unlikely(&bnxt_xdp_locking_key))
+ spin_unlock(&txr->xdp_tx_lock);
+
return nxmit;
}

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 0df40c3beb05..067bb5e821f5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -10,6 +10,8 @@
#ifndef BNXT_XDP_H
#define BNXT_XDP_H

+DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key);
+
struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
struct bnxt_tx_ring_info *txr,
dma_addr_t mapping, u32 len);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
index 5f5f8c53c4a0..c8cb541572ff 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
@@ -167,7 +167,7 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
base = of_iomap(node, 0);
if (!base) {
err = -ENOMEM;
- goto err_close;
+ goto err_put;
}

err = fsl_mc_allocate_irqs(mc_dev);
@@ -210,6 +210,8 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
fsl_mc_free_irqs(mc_dev);
err_unmap:
iounmap(base);
+err_put:
+ of_node_put(node);
err_close:
dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
err_free_mcp:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 9ddeb015eb7e..e830987a8c6d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1899,8 +1899,9 @@ i40e_status i40e_aq_add_vsi(struct i40e_hw *hw,

desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));

- status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
- sizeof(vsi_ctx->info), cmd_details);
+ status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info,
+ sizeof(vsi_ctx->info),
+ cmd_details, true);

if (status)
goto aq_add_vsi_exit;
@@ -2287,8 +2288,9 @@ i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw,

desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));

- status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
- sizeof(vsi_ctx->info), cmd_details);
+ status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info,
+ sizeof(vsi_ctx->info),
+ cmd_details, true);

vsi_ctx->vsis_allocated = le16_to_cpu(resp->vsi_used);
vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free);
@@ -2673,8 +2675,8 @@ i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid,
if (buf_size > I40E_AQ_LARGE_BUF)
desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);

- status = i40e_asq_send_command(hw, &desc, mv_list, buf_size,
- cmd_details);
+ status = i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size,
+ cmd_details, true);

return status;
}
@@ -2715,8 +2717,8 @@ i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
if (buf_size > I40E_AQ_LARGE_BUF)
desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);

- status = i40e_asq_send_command(hw, &desc, mv_list, buf_size,
- cmd_details);
+ status = i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size,
+ cmd_details, true);

return status;
}
@@ -3868,7 +3870,8 @@ i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,

cmd->seid = cpu_to_le16(seid);

- status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+ status = i40e_asq_send_command_atomic(hw, &desc, NULL, 0,
+ cmd_details, true);

return status;
}
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 4babe4705a55..358a9b3031d5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -44,6 +44,9 @@
#define DEFAULT_DEBUG_LEVEL_SHIFT 3
#define PFX "iavf: "

+int iavf_status_to_errno(enum iavf_status status);
+int virtchnl_status_to_errno(enum virtchnl_status_code v_status);
+
/* VSI state flags shared with common code */
enum iavf_vsi_state_t {
__IAVF_VSI_DOWN,
@@ -515,7 +518,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter);
void iavf_del_vlans(struct iavf_adapter *adapter);
void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags);
void iavf_request_stats(struct iavf_adapter *adapter);
-void iavf_request_reset(struct iavf_adapter *adapter);
+int iavf_request_reset(struct iavf_adapter *adapter);
void iavf_get_hena(struct iavf_adapter *adapter);
void iavf_set_hena(struct iavf_adapter *adapter);
void iavf_set_rss_key(struct iavf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 0e178a0a59c5..d10e9a8e8011 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -51,6 +51,113 @@ MODULE_LICENSE("GPL v2");
static const struct net_device_ops iavf_netdev_ops;
struct workqueue_struct *iavf_wq;

+int iavf_status_to_errno(enum iavf_status status)
+{
+ switch (status) {
+ case IAVF_SUCCESS:
+ return 0;
+ case IAVF_ERR_PARAM:
+ case IAVF_ERR_MAC_TYPE:
+ case IAVF_ERR_INVALID_MAC_ADDR:
+ case IAVF_ERR_INVALID_LINK_SETTINGS:
+ case IAVF_ERR_INVALID_PD_ID:
+ case IAVF_ERR_INVALID_QP_ID:
+ case IAVF_ERR_INVALID_CQ_ID:
+ case IAVF_ERR_INVALID_CEQ_ID:
+ case IAVF_ERR_INVALID_AEQ_ID:
+ case IAVF_ERR_INVALID_SIZE:
+ case IAVF_ERR_INVALID_ARP_INDEX:
+ case IAVF_ERR_INVALID_FPM_FUNC_ID:
+ case IAVF_ERR_QP_INVALID_MSG_SIZE:
+ case IAVF_ERR_INVALID_FRAG_COUNT:
+ case IAVF_ERR_INVALID_ALIGNMENT:
+ case IAVF_ERR_INVALID_PUSH_PAGE_INDEX:
+ case IAVF_ERR_INVALID_IMM_DATA_SIZE:
+ case IAVF_ERR_INVALID_VF_ID:
+ case IAVF_ERR_INVALID_HMCFN_ID:
+ case IAVF_ERR_INVALID_PBLE_INDEX:
+ case IAVF_ERR_INVALID_SD_INDEX:
+ case IAVF_ERR_INVALID_PAGE_DESC_INDEX:
+ case IAVF_ERR_INVALID_SD_TYPE:
+ case IAVF_ERR_INVALID_HMC_OBJ_INDEX:
+ case IAVF_ERR_INVALID_HMC_OBJ_COUNT:
+ case IAVF_ERR_INVALID_SRQ_ARM_LIMIT:
+ return -EINVAL;
+ case IAVF_ERR_NVM:
+ case IAVF_ERR_NVM_CHECKSUM:
+ case IAVF_ERR_PHY:
+ case IAVF_ERR_CONFIG:
+ case IAVF_ERR_UNKNOWN_PHY:
+ case IAVF_ERR_LINK_SETUP:
+ case IAVF_ERR_ADAPTER_STOPPED:
+ case IAVF_ERR_MASTER_REQUESTS_PENDING:
+ case IAVF_ERR_AUTONEG_NOT_COMPLETE:
+ case IAVF_ERR_RESET_FAILED:
+ case IAVF_ERR_BAD_PTR:
+ case IAVF_ERR_SWFW_SYNC:
+ case IAVF_ERR_QP_TOOMANY_WRS_POSTED:
+ case IAVF_ERR_QUEUE_EMPTY:
+ case IAVF_ERR_FLUSHED_QUEUE:
+ case IAVF_ERR_OPCODE_MISMATCH:
+ case IAVF_ERR_CQP_COMPL_ERROR:
+ case IAVF_ERR_BACKING_PAGE_ERROR:
+ case IAVF_ERR_NO_PBLCHUNKS_AVAILABLE:
+ case IAVF_ERR_MEMCPY_FAILED:
+ case IAVF_ERR_SRQ_ENABLED:
+ case IAVF_ERR_ADMIN_QUEUE_ERROR:
+ case IAVF_ERR_ADMIN_QUEUE_FULL:
+ case IAVF_ERR_BAD_IWARP_CQE:
+ case IAVF_ERR_NVM_BLANK_MODE:
+ case IAVF_ERR_PE_DOORBELL_NOT_ENABLED:
+ case IAVF_ERR_DIAG_TEST_FAILED:
+ case IAVF_ERR_FIRMWARE_API_VERSION:
+ case IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR:
+ return -EIO;
+ case IAVF_ERR_DEVICE_NOT_SUPPORTED:
+ return -ENODEV;
+ case IAVF_ERR_NO_AVAILABLE_VSI:
+ case IAVF_ERR_RING_FULL:
+ return -ENOSPC;
+ case IAVF_ERR_NO_MEMORY:
+ return -ENOMEM;
+ case IAVF_ERR_TIMEOUT:
+ case IAVF_ERR_ADMIN_QUEUE_TIMEOUT:
+ return -ETIMEDOUT;
+ case IAVF_ERR_NOT_IMPLEMENTED:
+ case IAVF_NOT_SUPPORTED:
+ return -EOPNOTSUPP;
+ case IAVF_ERR_ADMIN_QUEUE_NO_WORK:
+ return -EALREADY;
+ case IAVF_ERR_NOT_READY:
+ return -EBUSY;
+ case IAVF_ERR_BUF_TOO_SHORT:
+ return -EMSGSIZE;
+ }
+
+ return -EIO;
+}
+
+int virtchnl_status_to_errno(enum virtchnl_status_code v_status)
+{
+ switch (v_status) {
+ case VIRTCHNL_STATUS_SUCCESS:
+ return 0;
+ case VIRTCHNL_STATUS_ERR_PARAM:
+ case VIRTCHNL_STATUS_ERR_INVALID_VF_ID:
+ return -EINVAL;
+ case VIRTCHNL_STATUS_ERR_NO_MEMORY:
+ return -ENOMEM;
+ case VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH:
+ case VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR:
+ case VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR:
+ return -EIO;
+ case VIRTCHNL_STATUS_ERR_NOT_SUPPORTED:
+ return -EOPNOTSUPP;
+ }
+
+ return -EIO;
+}
+
/**
* iavf_pdev_to_adapter - go from pci_dev to adapter
* @pdev: pci_dev pointer
@@ -1421,7 +1528,7 @@ static int iavf_config_rss_aq(struct iavf_adapter *adapter)
struct iavf_aqc_get_set_rss_key_data *rss_key =
(struct iavf_aqc_get_set_rss_key_data *)adapter->rss_key;
struct iavf_hw *hw = &adapter->hw;
- int ret = 0;
+ enum iavf_status status;

if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
/* bail because we already have a command pending */
@@ -1430,24 +1537,25 @@ static int iavf_config_rss_aq(struct iavf_adapter *adapter)
return -EBUSY;
}

- ret = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key);
- if (ret) {
+ status = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key);
+ if (status) {
dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n",
- iavf_stat_str(hw, ret),
+ iavf_stat_str(hw, status),
iavf_aq_str(hw, hw->aq.asq_last_status));
- return ret;
+ return iavf_status_to_errno(status);

}

- ret = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false,
- adapter->rss_lut, adapter->rss_lut_size);
- if (ret) {
+ status = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false,
+ adapter->rss_lut, adapter->rss_lut_size);
+ if (status) {
dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n",
- iavf_stat_str(hw, ret),
+ iavf_stat_str(hw, status),
iavf_aq_str(hw, hw->aq.asq_last_status));
+ return iavf_status_to_errno(status);
}

- return ret;
+ return 0;

}

@@ -2003,23 +2111,24 @@ static void iavf_startup(struct iavf_adapter *adapter)
{
struct pci_dev *pdev = adapter->pdev;
struct iavf_hw *hw = &adapter->hw;
- int err;
+ enum iavf_status status;
+ int ret;

WARN_ON(adapter->state != __IAVF_STARTUP);

/* driver loaded, probe complete */
adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
- err = iavf_set_mac_type(hw);
- if (err) {
- dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", err);
+ status = iavf_set_mac_type(hw);
+ if (status) {
+ dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", status);
goto err;
}

- err = iavf_check_reset_complete(hw);
- if (err) {
+ ret = iavf_check_reset_complete(hw);
+ if (ret) {
dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n",
- err);
+ ret);
goto err;
}
hw->aq.num_arq_entries = IAVF_AQ_LEN;
@@ -2027,14 +2136,15 @@ static void iavf_startup(struct iavf_adapter *adapter)
hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE;
hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE;

- err = iavf_init_adminq(hw);
- if (err) {
- dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", err);
+ status = iavf_init_adminq(hw);
+ if (status) {
+ dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n",
+ status);
goto err;
}
- err = iavf_send_api_ver(adapter);
- if (err) {
- dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err);
+ ret = iavf_send_api_ver(adapter);
+ if (ret) {
+ dev_err(&pdev->dev, "Unable to send to PF (%d)\n", ret);
iavf_shutdown_adminq(hw);
goto err;
}
@@ -2070,7 +2180,7 @@ static void iavf_init_version_check(struct iavf_adapter *adapter)
/* aq msg sent, awaiting reply */
err = iavf_verify_api_ver(adapter);
if (err) {
- if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK)
+ if (err == -EALREADY)
err = iavf_send_api_ver(adapter);
else
dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n",
@@ -2171,11 +2281,11 @@ static void iavf_init_get_resources(struct iavf_adapter *adapter)
}
}
err = iavf_get_vf_config(adapter);
- if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK) {
+ if (err == -EALREADY) {
err = iavf_send_vf_config_msg(adapter);
goto err_alloc;
- } else if (err == IAVF_ERR_PARAM) {
- /* We only get ERR_PARAM if the device is in a very bad
+ } else if (err == -EINVAL) {
+ /* We only get -EINVAL if the device is in a very bad
* state or if we've been disabled for previous bad
* behavior. Either way, we're done now.
*/
@@ -2626,6 +2736,7 @@ static void iavf_reset_task(struct work_struct *work)
struct iavf_hw *hw = &adapter->hw;
struct iavf_mac_filter *f, *ftmp;
struct iavf_cloud_filter *cf;
+ enum iavf_status status;
u32 reg_val;
int i = 0, err;
bool running;
@@ -2727,10 +2838,12 @@ static void iavf_reset_task(struct work_struct *work)
/* kill and reinit the admin queue */
iavf_shutdown_adminq(hw);
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
- err = iavf_init_adminq(hw);
- if (err)
+ status = iavf_init_adminq(hw);
+ if (status) {
dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n",
- err);
+ status);
+ goto reset_err;
+ }
adapter->aq_required = 0;

if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) ||
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 5263cefe46f5..b8c5837f8b50 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -22,17 +22,17 @@ static int iavf_send_pf_msg(struct iavf_adapter *adapter,
enum virtchnl_ops op, u8 *msg, u16 len)
{
struct iavf_hw *hw = &adapter->hw;
- enum iavf_status err;
+ enum iavf_status status;

if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
return 0; /* nothing to see here, move along */

- err = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL);
- if (err)
- dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n",
- op, iavf_stat_str(hw, err),
+ status = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL);
+ if (status)
+ dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, status %s, aq_err %s\n",
+ op, iavf_stat_str(hw, status),
iavf_aq_str(hw, hw->aq.asq_last_status));
- return err;
+ return iavf_status_to_errno(status);
}

/**
@@ -1827,11 +1827,13 @@ void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter)
*
* Request that the PF reset this VF. No response is expected.
**/
-void iavf_request_reset(struct iavf_adapter *adapter)
+int iavf_request_reset(struct iavf_adapter *adapter)
{
+ int err;
/* Don't check CURRENT_OP - this is always higher priority */
- iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0);
+ err = iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0);
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+ return err;
}

/**
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2f60230d332a..9c04a71a9fca 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -674,7 +674,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev)

static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi)
{
- return !!vsi->xdp_prog;
+ return !!READ_ONCE(vsi->xdp_prog);
}

static inline void ice_set_ring_xdp(struct ice_tx_ring *ring)
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 53256aca27c7..5fd2bbeab2d1 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1452,6 +1452,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
ring->tx_tstamps = &pf->ptp.port.tx;
ring->dev = dev;
ring->count = vsi->num_tx_desc;
+ ring->txq_teid = ICE_INVAL_TEID;
WRITE_ONCE(vsi->tx_rings[i], ring);
}

@@ -3147,6 +3148,8 @@ int ice_vsi_release(struct ice_vsi *vsi)
}
}

+ if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi))
+ ice_clear_dflt_vsi(pf->first_sw);
ice_fltr_remove_all(vsi);
ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 296f9d5f7408..db2e02e673a7 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2546,7 +2546,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
spin_lock_init(&xdp_ring->tx_lock);
for (j = 0; j < xdp_ring->count; j++) {
tx_desc = ICE_TX_DESC(xdp_ring, j);
- tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE);
+ tx_desc->cmd_type_offset_bsz = 0;
}
}

@@ -2742,8 +2742,10 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi)

ice_for_each_xdp_txq(vsi, i)
if (vsi->xdp_rings[i]) {
- if (vsi->xdp_rings[i]->desc)
+ if (vsi->xdp_rings[i]->desc) {
+ synchronize_rcu();
ice_free_tx_ring(vsi->xdp_rings[i]);
+ }
kfree_rcu(vsi->xdp_rings[i], rcu);
vsi->xdp_rings[i] = NULL;
}
@@ -5432,16 +5434,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)

/* Add filter for new MAC. If filter exists, return success */
err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI);
- if (err == -EEXIST)
+ if (err == -EEXIST) {
/* Although this MAC filter is already present in hardware it's
* possible in some cases (e.g. bonding) that dev_addr was
* modified outside of the driver and needs to be restored back
* to this value.
*/
netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac);
- else if (err)
+
+ return 0;
+ } else if (err) {
/* error if the new filter addition failed */
err = -EADDRNOTAVAIL;
+ }

err_update_filters:
if (err) {
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 1be3cd4b2bef..2bee8f10ad89 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -3351,9 +3351,9 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
goto error_param;
}

- /* Skip queue if not enabled */
if (!test_bit(vf_q_id, vf->txq_ena))
- continue;
+ dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n",
+ vf_q_id, vsi->vsi_num);

ice_fill_txq_meta(vsi, ring, &txq_meta);

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index feb874bde171..30620b942fa0 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
{
ice_clean_tx_ring(vsi->tx_rings[q_idx]);
- if (ice_is_xdp_ena_vsi(vsi))
+ if (ice_is_xdp_ena_vsi(vsi)) {
+ synchronize_rcu();
ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
+ }
ice_clean_rx_ring(vsi->rx_rings[q_idx]);
}

@@ -763,7 +765,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
struct ice_vsi *vsi = np->vsi;
struct ice_tx_ring *ring;

- if (test_bit(ICE_DOWN, vsi->state))
+ if (test_bit(ICE_VSI_DOWN, vsi->state))
return -ENETDOWN;

if (!ice_is_xdp_ena_vsi(vsi))
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 143ca8be5eb5..4008596963be 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -2751,7 +2751,7 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
}

ret = of_get_mac_address(pnp, ppd.mac_addr);
- if (ret)
+ if (ret == -EPROBE_DEFER)
return ret;

mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c
index 6699bdf5cf01..b895c378cfaf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c
@@ -27,11 +27,7 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state,
struct mlx5e_priv *priv,
struct mlx5_flow_attr *attr)
{
- struct mlx5e_sample_attr *sample_attr;
-
- sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL);
- if (!sample_attr)
- return -ENOMEM;
+ struct mlx5e_sample_attr *sample_attr = &attr->sample_attr;

sample_attr->rate = act->sample.rate;
sample_attr->group_num = act->sample.psample_group->group_num;
@@ -39,7 +35,6 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state,
if (act->sample.truncate)
sample_attr->trunc_size = act->sample.trunc_size;

- attr->sample_attr = sample_attr;
flow_flag_set(parse_state->flow, SAMPLE);

return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
index ff4b4f8a5a9d..0faaf9a4b531 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
@@ -513,7 +513,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL);
if (!sample_flow)
return ERR_PTR(-ENOMEM);
- sample_attr = attr->sample_attr;
+ sample_attr = &attr->sample_attr;
sample_attr->sample_flow = sample_flow;

/* For NICs with reg_c_preserve support or decap action, use
@@ -546,6 +546,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
err = PTR_ERR(sample_flow->sampler);
goto err_sampler;
}
+ sample_attr->sampler_id = sample_flow->sampler->sampler_id;

/* Create an id mapping reg_c0 value to sample object. */
restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE;
@@ -585,8 +586,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
pre_attr->outer_match_level = attr->outer_match_level;
pre_attr->chain = attr->chain;
pre_attr->prio = attr->prio;
- pre_attr->sample_attr = attr->sample_attr;
- sample_attr->sampler_id = sample_flow->sampler->sampler_id;
+ pre_attr->sample_attr = *sample_attr;
pre_esw_attr = pre_attr->esw_attr;
pre_esw_attr->in_mdev = esw_attr->in_mdev;
pre_esw_attr->in_rep = esw_attr->in_rep;
@@ -633,11 +633,11 @@ mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample,
* will hit fw syndromes.
*/
esw = tc_psample->esw;
- sample_flow = attr->sample_attr->sample_flow;
+ sample_flow = attr->sample_attr.sample_flow;
mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr);

sample_restore_put(tc_psample, sample_flow->restore);
- mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id);
+ mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr.restore_obj_id);
sampler_put(tc_psample, sample_flow->sampler);
if (sample_flow->post_act_handle)
mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3667f5ef5990..169e3524bb1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5345,6 +5345,7 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *prof
}

netif_carrier_off(netdev);
+ netif_tx_disable(netdev);
dev_net_set(netdev, mlx5_core_net(mdev));

return netdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b27532a9301e..7e5c00349ccf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1634,7 +1634,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
if (flow_flag_test(flow, L3_TO_L2_DECAP))
mlx5e_detach_decap(priv, flow);

- kfree(attr->sample_attr);
kvfree(attr->esw_attr->rx_tun_attr);
kvfree(attr->parse_attr);
kfree(flow->attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 5ffae9b13066..2f09e34db9ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -71,7 +71,7 @@ struct mlx5_flow_attr {
struct mlx5_fc *counter;
struct mlx5_modify_hdr *modify_hdr;
struct mlx5_ct_attr ct_attr;
- struct mlx5e_sample_attr *sample_attr;
+ struct mlx5e_sample_attr sample_attr;
struct mlx5e_tc_flow_parse_attr *parse_attr;
u32 chain;
u16 prio;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index cfcd72bad9af..e7e7b4b0dcdb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -201,12 +201,12 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw,
static int
esw_setup_sampler_dest(struct mlx5_flow_destination *dest,
struct mlx5_flow_act *flow_act,
- struct mlx5_flow_attr *attr,
+ u32 sampler_id,
int i)
{
flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
- dest[i].sampler_id = attr->sample_attr->sampler_id;
+ dest[i].sampler_id = sampler_id;

return 0;
}
@@ -466,7 +466,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE;

if (attr->flags & MLX5_ESW_ATTR_FLAG_SAMPLE) {
- esw_setup_sampler_dest(dest, flow_act, attr, *i);
+ esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i);
(*i)++;
} else if (attr->dest_ft) {
esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 7b16a1188aab..fd79860de723 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -433,35 +433,12 @@ int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
struct mlx5_module_eeprom_query_params *params,
u8 *data)
{
- u8 module_id;
int err;

err = mlx5_query_module_num(dev, &params->module_number);
if (err)
return err;

- err = mlx5_query_module_id(dev, params->module_number, &module_id);
- if (err)
- return err;
-
- switch (module_id) {
- case MLX5_MODULE_ID_SFP:
- if (params->page > 0)
- return -EINVAL;
- break;
- case MLX5_MODULE_ID_QSFP:
- case MLX5_MODULE_ID_QSFP28:
- case MLX5_MODULE_ID_QSFP_PLUS:
- if (params->page > 3)
- return -EINVAL;
- break;
- case MLX5_MODULE_ID_DSFP:
- break;
- default:
- mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
- return -EINVAL;
- }
-
if (params->i2c_address != MLX5_I2C_ADDR_HIGH &&
params->i2c_address != MLX5_I2C_ADDR_LOW) {
mlx5_core_err(dev, "I2C address not recognized: 0x%x\n", params->i2c_address);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index aa411dec62f0..eb1319d63613 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2148,13 +2148,11 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
struct mlxsw_sp *mlxsw_sp = priv;
struct mlxsw_sp_port *mlxsw_sp_port;
enum mlxsw_reg_pude_oper_status status;
- unsigned int max_ports;
u16 local_port;

- max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
local_port = mlxsw_reg_pude_local_port_get(pude_pl);

- if (WARN_ON_ONCE(!local_port || local_port >= max_ports))
+ if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port)))
return;
mlxsw_sp_port = mlxsw_sp->ports[local_port];
if (!mlxsw_sp_port)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index bb2442e1f705..30942b6ffcf9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -481,6 +481,13 @@ int
mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port,
bool is_8021ad_tagged,
bool is_8021q_tagged);
+static inline bool
+mlxsw_sp_local_port_is_valid(struct mlxsw_sp *mlxsw_sp, u16 local_port)
+{
+ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+
+ return local_port < max_ports && local_port;
+}

/* spectrum_buffers.c */
struct mlxsw_sp_hdroom_prio {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index 0ff163fbc775..35422e64d89f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -568,12 +568,11 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
u8 domain_number, u16 sequence_id,
u64 timestamp)
{
- unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
struct mlxsw_sp_port *mlxsw_sp_port;
struct mlxsw_sp1_ptp_key key;
u8 types;

- if (WARN_ON_ONCE(local_port >= max_ports))
+ if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port)))
return;
mlxsw_sp_port = mlxsw_sp->ports[local_port];
if (!mlxsw_sp_port)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 65c1724c63b0..bffdb41fc4ed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2616,7 +2616,6 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
char *sfn_pl, int rec_index,
bool adding)
{
- unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
struct mlxsw_sp_bridge_device *bridge_device;
struct mlxsw_sp_bridge_port *bridge_port;
@@ -2630,7 +2629,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,

mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port);

- if (WARN_ON_ONCE(local_port >= max_ports))
+ if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port)))
return;
mlxsw_sp_port = mlxsw_sp->ports[local_port];
if (!mlxsw_sp_port) {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index e3edca187ddf..5250d1d1e49c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -489,7 +489,7 @@ struct split_type_defs {

#define STATIC_DEBUG_LINE_DWORDS 9

-#define NUM_COMMON_GLOBAL_PARAMS 11
+#define NUM_COMMON_GLOBAL_PARAMS 10

#define MAX_RECURSION_DEPTH 10

diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index b242000a77fd..b7cc36589f59 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -748,6 +748,9 @@ qede_build_skb(struct qede_rx_queue *rxq,
buf = page_address(bd->data) + bd->page_offset;
skb = build_skb(buf, rxq->rx_buf_seg_size);

+ if (unlikely(!skb))
+ return NULL;
+
skb_reserve(skb, pad);
skb_put(skb, len);

diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c
index ead550ae2709..40bfd0ad7d05 100644
--- a/drivers/net/ethernet/sfc/efx_channels.c
+++ b/drivers/net/ethernet/sfc/efx_channels.c
@@ -764,6 +764,85 @@ void efx_remove_channels(struct efx_nic *efx)
kfree(efx->xdp_tx_queues);
}

+static int efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number,
+ struct efx_tx_queue *tx_queue)
+{
+ if (xdp_queue_number >= efx->xdp_tx_queue_count)
+ return -EINVAL;
+
+ netif_dbg(efx, drv, efx->net_dev,
+ "Channel %u TXQ %u is XDP %u, HW %u\n",
+ tx_queue->channel->channel, tx_queue->label,
+ xdp_queue_number, tx_queue->queue);
+ efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
+ return 0;
+}
+
+static void efx_set_xdp_channels(struct efx_nic *efx)
+{
+ struct efx_tx_queue *tx_queue;
+ struct efx_channel *channel;
+ unsigned int next_queue = 0;
+ int xdp_queue_number = 0;
+ int rc;
+
+ /* We need to mark which channels really have RX and TX
+ * queues, and adjust the TX queue numbers if we have separate
+ * RX-only and TX-only channels.
+ */
+ efx_for_each_channel(channel, efx) {
+ if (channel->channel < efx->tx_channel_offset)
+ continue;
+
+ if (efx_channel_is_xdp_tx(channel)) {
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ tx_queue->queue = next_queue++;
+ rc = efx_set_xdp_tx_queue(efx, xdp_queue_number,
+ tx_queue);
+ if (rc == 0)
+ xdp_queue_number++;
+ }
+ } else {
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ tx_queue->queue = next_queue++;
+ netif_dbg(efx, drv, efx->net_dev,
+ "Channel %u TXQ %u is HW %u\n",
+ channel->channel, tx_queue->label,
+ tx_queue->queue);
+ }
+
+ /* If XDP is borrowing queues from net stack, it must
+ * use the queue with no csum offload, which is the
+ * first one of the channel
+ * (note: tx_queue_by_type is not initialized yet)
+ */
+ if (efx->xdp_txq_queues_mode ==
+ EFX_XDP_TX_QUEUES_BORROWED) {
+ tx_queue = &channel->tx_queue[0];
+ rc = efx_set_xdp_tx_queue(efx, xdp_queue_number,
+ tx_queue);
+ if (rc == 0)
+ xdp_queue_number++;
+ }
+ }
+ }
+ WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED &&
+ xdp_queue_number != efx->xdp_tx_queue_count);
+ WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED &&
+ xdp_queue_number > efx->xdp_tx_queue_count);
+
+ /* If we have more CPUs than assigned XDP TX queues, assign the already
+ * existing queues to the exceeding CPUs
+ */
+ next_queue = 0;
+ while (xdp_queue_number < efx->xdp_tx_queue_count) {
+ tx_queue = efx->xdp_tx_queues[next_queue++];
+ rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
+ if (rc == 0)
+ xdp_queue_number++;
+ }
+}
+
int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
{
struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
@@ -835,6 +914,7 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
efx_init_napi_channel(efx->channel[i]);
}

+ efx_set_xdp_channels(efx);
out:
/* Destroy unused channel structures */
for (i = 0; i < efx->n_channels; i++) {
@@ -867,26 +947,9 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
goto out;
}

-static inline int
-efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number,
- struct efx_tx_queue *tx_queue)
-{
- if (xdp_queue_number >= efx->xdp_tx_queue_count)
- return -EINVAL;
-
- netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n",
- tx_queue->channel->channel, tx_queue->label,
- xdp_queue_number, tx_queue->queue);
- efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
- return 0;
-}
-
int efx_set_channels(struct efx_nic *efx)
{
- struct efx_tx_queue *tx_queue;
struct efx_channel *channel;
- unsigned int next_queue = 0;
- int xdp_queue_number;
int rc;

efx->tx_channel_offset =
@@ -904,61 +967,14 @@ int efx_set_channels(struct efx_nic *efx)
return -ENOMEM;
}

- /* We need to mark which channels really have RX and TX
- * queues, and adjust the TX queue numbers if we have separate
- * RX-only and TX-only channels.
- */
- xdp_queue_number = 0;
efx_for_each_channel(channel, efx) {
if (channel->channel < efx->n_rx_channels)
channel->rx_queue.core_index = channel->channel;
else
channel->rx_queue.core_index = -1;
-
- if (channel->channel >= efx->tx_channel_offset) {
- if (efx_channel_is_xdp_tx(channel)) {
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- tx_queue->queue = next_queue++;
- rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
- if (rc == 0)
- xdp_queue_number++;
- }
- } else {
- efx_for_each_channel_tx_queue(tx_queue, channel) {
- tx_queue->queue = next_queue++;
- netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is HW %u\n",
- channel->channel, tx_queue->label,
- tx_queue->queue);
- }
-
- /* If XDP is borrowing queues from net stack, it must use the queue
- * with no csum offload, which is the first one of the channel
- * (note: channel->tx_queue_by_type is not initialized yet)
- */
- if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) {
- tx_queue = &channel->tx_queue[0];
- rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
- if (rc == 0)
- xdp_queue_number++;
- }
- }
- }
}
- WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED &&
- xdp_queue_number != efx->xdp_tx_queue_count);
- WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED &&
- xdp_queue_number > efx->xdp_tx_queue_count);

- /* If we have more CPUs than assigned XDP TX queues, assign the already
- * existing queues to the exceeding CPUs
- */
- next_queue = 0;
- while (xdp_queue_number < efx->xdp_tx_queue_count) {
- tx_queue = efx->xdp_tx_queues[next_queue++];
- rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue);
- if (rc == 0)
- xdp_queue_number++;
- }
+ efx_set_xdp_channels(efx);

rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
if (rc)
@@ -1102,7 +1118,7 @@ void efx_start_channels(struct efx_nic *efx)
struct efx_rx_queue *rx_queue;
struct efx_channel *channel;

- efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rev(channel, efx) {
efx_for_each_channel_tx_queue(tx_queue, channel) {
efx_init_tx_queue(tx_queue);
atomic_inc(&efx->active_queues);
diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index 633ca77a26fd..b925de9b4302 100644
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -166,6 +166,9 @@ static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue)
struct efx_nic *efx = rx_queue->efx;
int i;

+ if (unlikely(!rx_queue->page_ring))
+ return;
+
/* Unmap and release the pages in the recycle ring. Remove the ring. */
for (i = 0; i <= rx_queue->page_ptr_mask; i++) {
struct page *page = rx_queue->page_ring[i];
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index d16e031e95f4..6983799e1c05 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -443,6 +443,9 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs,
if (unlikely(!tx_queue))
return -EINVAL;

+ if (!tx_queue->initialised)
+ return -EINVAL;
+
if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED)
HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu);

diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c
index d530cde2b864..9bc8281b7f5b 100644
--- a/drivers/net/ethernet/sfc/tx_common.c
+++ b/drivers/net/ethernet/sfc/tx_common.c
@@ -101,6 +101,8 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
"shutting down TX queue %d\n", tx_queue->queue);

+ tx_queue->initialised = false;
+
if (!tx_queue->buffer)
return;

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5d29f336315b..11e1055e8260 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -431,8 +431,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
plat->phylink_node = np;

/* Get max speed of operation from device tree */
- if (of_property_read_u32(np, "max-speed", &plat->max_speed))
- plat->max_speed = -1;
+ of_property_read_u32(np, "max-speed", &plat->max_speed);

plat->bus_id = of_alias_get_id(np, "ethernet");
if (plat->bus_id < 0)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 6b12902a803f..cecf8c63096c 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -133,11 +133,17 @@ static void macvtap_setup(struct net_device *dev)
dev->tx_queue_len = TUN_READQ_SIZE;
}

+static struct net *macvtap_link_net(const struct net_device *dev)
+{
+ return dev_net(macvlan_dev_real_dev(dev));
+}
+
static struct rtnl_link_ops macvtap_link_ops __read_mostly = {
.kind = "macvtap",
.setup = macvtap_setup,
.newlink = macvtap_newlink,
.dellink = macvtap_dellink,
+ .get_link_net = macvtap_link_net,
.priv_size = sizeof(struct macvtap_dev),
};

diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c
index 64fb76c1e395..08381038810d 100644
--- a/drivers/net/mdio/mdio-mscc-miim.c
+++ b/drivers/net/mdio/mdio-mscc-miim.c
@@ -93,6 +93,9 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum)
u32 val;
int ret;

+ if (regnum & MII_ADDR_C45)
+ return -EOPNOTSUPP;
+
ret = mscc_miim_wait_pending(bus);
if (ret)
goto out;
@@ -136,6 +139,9 @@ static int mscc_miim_write(struct mii_bus *bus, int mii_id,
struct mscc_miim_dev *miim = bus->priv;
int ret;

+ if (regnum & MII_ADDR_C45)
+ return -EOPNOTSUPP;
+
ret = mscc_miim_wait_pending(bus);
if (ret < 0)
goto out;
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index c1512c9925a6..15aa5ac1ff49 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -74,6 +74,12 @@ static const struct sfp_quirk sfp_quirks[] = {
.vendor = "HUAWEI",
.part = "MA5671A",
.modes = sfp_quirk_2500basex,
+ }, {
+ // Lantech 8330-262D-E can operate at 2500base-X, but
+ // incorrectly report 2500MBd NRZ in their EEPROM
+ .vendor = "Lantech",
+ .part = "8330-262D-E",
+ .modes = sfp_quirk_2500basex,
}, {
.vendor = "UBNT",
.part = "UF-INSTANT",
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 8e3a28ba6b28..ba2ef5437e16 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1198,7 +1198,8 @@ static int tap_sendmsg(struct socket *sock, struct msghdr *m,
struct xdp_buff *xdp;
int i;

- if (ctl && (ctl->type == TUN_MSG_PTR)) {
+ if (m->msg_controllen == sizeof(struct tun_msg_ctl) &&
+ ctl && ctl->type == TUN_MSG_PTR) {
for (i = 0; i < ctl->num; i++) {
xdp = &((struct xdp_buff *)ctl->ptr)[i];
tap_get_user_xdp(q, xdp);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fed85447701a..de999e0fedbc 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2489,7 +2489,8 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
if (!tun)
return -EBADFD;

- if (ctl && (ctl->type == TUN_MSG_PTR)) {
+ if (m->msg_controllen == sizeof(struct tun_msg_ctl) &&
+ ctl && ctl->type == TUN_MSG_PTR) {
struct tun_page tpage;
int n = ctl->num;
int flush = 0;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index e0b1ab99a359..f37adcef4bef 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1266,6 +1266,7 @@ static int vrf_prepare_mac_header(struct sk_buff *skb,
eth = (struct ethhdr *)skb->data;

skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);

/* we set the ethernet destination and the source addresses to the
* address of the VRF device.
@@ -1295,9 +1296,9 @@ static int vrf_prepare_mac_header(struct sk_buff *skb,
*/
static int vrf_add_mac_header_if_unset(struct sk_buff *skb,
struct net_device *vrf_dev,
- u16 proto)
+ u16 proto, struct net_device *orig_dev)
{
- if (skb_mac_header_was_set(skb))
+ if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev))
return 0;

return vrf_prepare_mac_header(skb, vrf_dev, proto);
@@ -1403,6 +1404,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,

/* if packet is NDISC then keep the ingress interface */
if (!is_ndisc) {
+ struct net_device *orig_dev = skb->dev;
+
vrf_rx_stats(vrf_dev, skb->len);
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
@@ -1411,7 +1414,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
int err;

err = vrf_add_mac_header_if_unset(skb, vrf_dev,
- ETH_P_IPV6);
+ ETH_P_IPV6,
+ orig_dev);
if (likely(!err)) {
skb_push(skb, skb->mac_len);
dev_queue_xmit_nit(skb, vrf_dev);
@@ -1441,6 +1445,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
struct sk_buff *skb)
{
+ struct net_device *orig_dev = skb->dev;
+
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
IPCB(skb)->flags |= IPSKB_L3SLAVE;
@@ -1461,7 +1467,8 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
if (!list_empty(&vrf_dev->ptype_all)) {
int err;

- err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP);
+ err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP,
+ orig_dev);
if (likely(!err)) {
skb_push(skb, skb->mac_len);
dev_queue_xmit_nit(skb, vrf_dev);
diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index 3fb0aa000825..24bd0520926b 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -391,6 +391,8 @@ static void ath11k_ahb_free_ext_irq(struct ath11k_base *ab)

for (j = 0; j < irq_grp->num_irq; j++)
free_irq(ab->irq_num[irq_grp->irqs[j]], irq_grp);
+
+ netif_napi_del(&irq_grp->napi);
}
}

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 08e33778f63b..28de877ad6c4 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -5574,7 +5574,7 @@ static int ath11k_mac_mgmt_tx(struct ath11k *ar, struct sk_buff *skb,

skb_queue_tail(q, skb);
atomic_inc(&ar->num_pending_mgmt_tx);
- ieee80211_queue_work(ar->hw, &ar->wmi_mgmt_tx_work);
+ queue_work(ar->ab->workqueue, &ar->wmi_mgmt_tx_work);

return 0;
}
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index cccaa348cf21..8b2143802816 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -561,7 +561,7 @@ static int ath11k_mhi_set_state(struct ath11k_pci *ab_pci,
ret = 0;
break;
case ATH11K_MHI_POWER_ON:
- ret = mhi_async_power_up(ab_pci->mhi_ctrl);
+ ret = mhi_sync_power_up(ab_pci->mhi_ctrl);
break;
case ATH11K_MHI_POWER_OFF:
mhi_power_down(ab_pci->mhi_ctrl, true);
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index de71ad594f34..903758751c99 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -1571,6 +1571,11 @@ static __maybe_unused int ath11k_pci_pm_suspend(struct device *dev)
struct ath11k_base *ab = dev_get_drvdata(dev);
int ret;

+ if (test_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags)) {
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "boot skipping pci suspend as qmi is not initialised\n");
+ return 0;
+ }
+
ret = ath11k_core_suspend(ab);
if (ret)
ath11k_warn(ab, "failed to suspend core: %d\n", ret);
@@ -1583,6 +1588,11 @@ static __maybe_unused int ath11k_pci_pm_resume(struct device *dev)
struct ath11k_base *ab = dev_get_drvdata(dev);
int ret;

+ if (test_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags)) {
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "boot skipping pci resume as qmi is not initialised\n");
+ return 0;
+ }
+
ret = ath11k_core_resume(ab);
if (ret)
ath11k_warn(ab, "failed to resume core: %d\n", ret);
diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c
index 1fbc2c19848f..d444b3d70ba2 100644
--- a/drivers/net/wireless/ath/ath5k/eeprom.c
+++ b/drivers/net/wireless/ath/ath5k/eeprom.c
@@ -746,6 +746,9 @@ ath5k_eeprom_convert_pcal_info_5111(struct ath5k_hw *ah, int mode,
}
}

+ if (idx == AR5K_EEPROM_N_PD_CURVES)
+ goto err_out;
+
ee->ee_pd_gains[mode] = 1;

pd = &chinfo[pier].pd_curves[idx];
diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig
index 85e704283755..a647a406b87b 100644
--- a/drivers/net/wireless/intel/iwlwifi/Kconfig
+++ b/drivers/net/wireless/intel/iwlwifi/Kconfig
@@ -139,6 +139,7 @@ config IWLMEI
tristate "Intel Management Engine communication over WLAN"
depends on INTEL_MEI
depends on PM
+ depends on CFG80211
help
Enables the iwlmei kernel module.

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 456b7eaac570..061fe6cc6cf5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
/*
- * Copyright (C) 2018-2021 Intel Corporation
+ * Copyright (C) 2018-2022 Intel Corporation
*/
#ifndef __iwl_fw_dbg_tlv_h__
#define __iwl_fw_dbg_tlv_h__
@@ -249,11 +249,10 @@ struct iwl_fw_ini_hcmd_tlv {
} __packed; /* FW_TLV_DEBUG_HCMD_API_S_VER_1 */

/**
-* struct iwl_fw_ini_conf_tlv - preset configuration TLV
+* struct iwl_fw_ini_addr_val - Address and value to set it to
*
* @address: the base address
* @value: value to set at address
-
*/
struct iwl_fw_ini_addr_val {
__le32 address;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
index 9af40b0fa37a..a6e6673bf4ee 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2012-2014, 2018-2021 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2022 Intel Corporation
* Copyright (C) 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2017 Intel Deutschland GmbH
*/
@@ -349,18 +349,31 @@ void iwl_mvm_phy_ctxt_unref(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt)
* otherwise we might not be able to reuse this phy.
*/
if (ctxt->ref == 0) {
- struct ieee80211_channel *chan;
+ struct ieee80211_channel *chan = NULL;
struct cfg80211_chan_def chandef;
- struct ieee80211_supported_band *sband = NULL;
- enum nl80211_band band = NL80211_BAND_2GHZ;
+ struct ieee80211_supported_band *sband;
+ enum nl80211_band band;
+ int channel;

- while (!sband && band < NUM_NL80211_BANDS)
- sband = mvm->hw->wiphy->bands[band++];
+ for (band = NL80211_BAND_2GHZ; band < NUM_NL80211_BANDS; band++) {
+ sband = mvm->hw->wiphy->bands[band];

- if (WARN_ON(!sband))
- return;
+ if (!sband)
+ continue;
+
+ for (channel = 0; channel < sband->n_channels; channel++)
+ if (!(sband->channels[channel].flags &
+ IEEE80211_CHAN_DISABLED)) {
+ chan = &sband->channels[channel];
+ break;
+ }

- chan = &sband->channels[0];
+ if (chan)
+ break;
+ }
+
+ if (WARN_ON(!chan))
+ return;

cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_NO_HT);
iwl_mvm_phy_ctxt_changed(mvm, ctxt, &chandef, 1, 1);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 5f92a09db374..4cd507cb412d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1893,7 +1893,10 @@ static u8 iwl_mvm_scan_umac_chan_flags_v2(struct iwl_mvm *mvm,
IWL_SCAN_CHANNEL_FLAG_CACHE_ADD;

/* set fragmented ebs for fragmented scan on HB channels */
- if (iwl_mvm_is_scan_fragmented(params->hb_type))
+ if ((!iwl_mvm_is_cdb_supported(mvm) &&
+ iwl_mvm_is_scan_fragmented(params->type)) ||
+ (iwl_mvm_is_cdb_supported(mvm) &&
+ iwl_mvm_is_scan_fragmented(params->hb_type)))
flags |= IWL_SCAN_CHANNEL_FLAG_EBS_FRAG;

return flags;
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 3a9af8931c35..3d644925a4e0 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -465,6 +465,7 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q)

qbuf.addr = addr + offset;
qbuf.len = len - offset;
+ qbuf.skip_unmap = false;
mt76_dma_add_buf(dev, q, &qbuf, 1, 0, buf, NULL);
frames++;
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 1f6f7a44d3f0..5197fcb06649 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -19,7 +19,7 @@

#define MT_MCU_RING_SIZE 32
#define MT_RX_BUF_SIZE 2048
-#define MT_SKB_HEAD_LEN 128
+#define MT_SKB_HEAD_LEN 256

#define MT_MAX_NON_AQL_PKT 16
#define MT_TXQ_FREE_THR 32
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index ba31bb7caaf9..5d69e77814c9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -1841,7 +1841,7 @@ mt7615_mac_adjust_sensitivity(struct mt7615_phy *phy,
struct mt7615_dev *dev = phy->dev;
int false_cca = ofdm ? phy->false_cca_ofdm : phy->false_cca_cck;
bool ext_phy = phy != &dev->phy;
- u16 def_th = ofdm ? -98 : -110;
+ s16 def_th = ofdm ? -98 : -110;
bool update = false;
s8 *sensitivity;
int signal;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index db267642924d..e4c300aa1526 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1085,6 +1085,7 @@ mt7915_mac_write_txwi_80211(struct mt7915_dev *dev, __le32 *txwi,
val = MT_TXD3_SN_VALID |
FIELD_PREP(MT_TXD3_SEQ, IEEE80211_SEQ_TO_SN(seqno));
txwi[3] |= cpu_to_le32(val);
+ txwi[7] &= ~cpu_to_le32(MT_TXD7_HW_AMSDU);
}

val = FIELD_PREP(MT_TXD7_TYPE, fc_type) |
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 7a8d2596c226..4abb7a6e775a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -273,6 +273,7 @@ static void mt7921_stop(struct ieee80211_hw *hw)

cancel_delayed_work_sync(&dev->pm.ps_work);
cancel_work_sync(&dev->pm.wake_work);
+ cancel_work_sync(&dev->reset_work);
mt76_connac_free_pending_tx_skbs(&dev->pm, NULL);

mt7921_mutex_acquire(dev);
diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c
index e429428232c1..e7e9f17df96a 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.c
+++ b/drivers/net/wireless/realtek/rtw88/debug.c
@@ -390,7 +390,7 @@ static ssize_t rtw_debugfs_set_h2c(struct file *filp,
&param[0], &param[1], &param[2], &param[3],
&param[4], &param[5], &param[6], &param[7]);
if (num != 8) {
- rtw_info(rtwdev, "invalid H2C command format for debug\n");
+ rtw_warn(rtwdev, "invalid H2C command format for debug\n");
return -EINVAL;
}

diff --git a/drivers/net/wireless/realtek/rtw88/debug.h b/drivers/net/wireless/realtek/rtw88/debug.h
index 61f8369fe2d6..066792dd96af 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.h
+++ b/drivers/net/wireless/realtek/rtw88/debug.h
@@ -23,6 +23,7 @@ enum rtw_debug_mask {
RTW_DBG_PATH_DIV = 0x00004000,
RTW_DBG_ADAPTIVITY = 0x00008000,
RTW_DBG_HW_SCAN = 0x00010000,
+ RTW_DBG_STATE = 0x00020000,

RTW_DBG_ALL = 0xffffffff
};
diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index 4c8e5ea5d069..db90d75a8633 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -2131,7 +2131,7 @@ void rtw_hw_scan_status_report(struct rtw_dev *rtwdev, struct sk_buff *skb)
rtw_hw_scan_complete(rtwdev, vif, aborted);

if (aborted)
- rtw_info(rtwdev, "HW scan aborted with code: %d\n", rc);
+ rtw_dbg(rtwdev, RTW_DBG_HW_SCAN, "HW scan aborted with code: %d\n", rc);
}

void rtw_store_op_chan(struct rtw_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c
index 647d2662955b..5cdc54c9a9aa 100644
--- a/drivers/net/wireless/realtek/rtw88/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw88/mac80211.c
@@ -208,7 +208,7 @@ static int rtw_ops_add_interface(struct ieee80211_hw *hw,

mutex_unlock(&rtwdev->mutex);

- rtw_info(rtwdev, "start vif %pM on port %d\n", vif->addr, rtwvif->port);
+ rtw_dbg(rtwdev, RTW_DBG_STATE, "start vif %pM on port %d\n", vif->addr, rtwvif->port);
return 0;
}

@@ -219,7 +219,7 @@ static void rtw_ops_remove_interface(struct ieee80211_hw *hw,
struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
u32 config = 0;

- rtw_info(rtwdev, "stop vif %pM on port %d\n", vif->addr, rtwvif->port);
+ rtw_dbg(rtwdev, RTW_DBG_STATE, "stop vif %pM on port %d\n", vif->addr, rtwvif->port);

mutex_lock(&rtwdev->mutex);

@@ -245,8 +245,8 @@ static int rtw_ops_change_interface(struct ieee80211_hw *hw,
{
struct rtw_dev *rtwdev = hw->priv;

- rtw_info(rtwdev, "change vif %pM (%d)->(%d), p2p (%d)->(%d)\n",
- vif->addr, vif->type, type, vif->p2p, p2p);
+ rtw_dbg(rtwdev, RTW_DBG_STATE, "change vif %pM (%d)->(%d), p2p (%d)->(%d)\n",
+ vif->addr, vif->type, type, vif->p2p, p2p);

rtw_ops_remove_interface(hw, vif);

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 39c223a2e3e2..b00200f81db7 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -314,8 +314,8 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,

rtwdev->sta_cnt++;
rtwdev->beacon_loss = false;
- rtw_info(rtwdev, "sta %pM joined with macid %d\n",
- sta->addr, si->mac_id);
+ rtw_dbg(rtwdev, RTW_DBG_STATE, "sta %pM joined with macid %d\n",
+ sta->addr, si->mac_id);

return 0;
}
@@ -336,8 +336,8 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
kfree(si->mask);

rtwdev->sta_cnt--;
- rtw_info(rtwdev, "sta %pM with macid %d left\n",
- sta->addr, si->mac_id);
+ rtw_dbg(rtwdev, RTW_DBG_STATE, "sta %pM with macid %d left\n",
+ sta->addr, si->mac_id);
}

struct rtw_fwcd_hdr {
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
index db078df63f85..80d4761796b1 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
@@ -499,7 +499,7 @@ static s8 get_cck_rx_pwr(struct rtw_dev *rtwdev, u8 lna_idx, u8 vga_idx)
}

if (lna_idx >= lna_gain_table_size) {
- rtw_info(rtwdev, "incorrect lna index (%d)\n", lna_idx);
+ rtw_warn(rtwdev, "incorrect lna index (%d)\n", lna_idx);
return -120;
}

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index dd4fbb82750d..a23806b69b0f 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -1012,12 +1012,12 @@ static int rtw8822b_set_antenna(struct rtw_dev *rtwdev,
antenna_tx, antenna_rx);

if (!rtw8822b_check_rf_path(antenna_tx)) {
- rtw_info(rtwdev, "unsupported tx path 0x%x\n", antenna_tx);
+ rtw_warn(rtwdev, "unsupported tx path 0x%x\n", antenna_tx);
return -EINVAL;
}

if (!rtw8822b_check_rf_path(antenna_rx)) {
- rtw_info(rtwdev, "unsupported rx path 0x%x\n", antenna_rx);
+ rtw_warn(rtwdev, "unsupported rx path 0x%x\n", antenna_rx);
return -EINVAL;
}

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index 35c46e5209de..ddf4d1a23e60 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -2798,7 +2798,7 @@ static int rtw8822c_set_antenna(struct rtw_dev *rtwdev,
case BB_PATH_AB:
break;
default:
- rtw_info(rtwdev, "unsupported tx path 0x%x\n", antenna_tx);
+ rtw_warn(rtwdev, "unsupported tx path 0x%x\n", antenna_tx);
return -EINVAL;
}

@@ -2808,7 +2808,7 @@ static int rtw8822c_set_antenna(struct rtw_dev *rtwdev,
case BB_PATH_AB:
break;
default:
- rtw_info(rtwdev, "unsupported rx path 0x%x\n", antenna_rx);
+ rtw_warn(rtwdev, "unsupported rx path 0x%x\n", antenna_rx);
return -EINVAL;
}

diff --git a/drivers/net/wireless/realtek/rtw88/sar.c b/drivers/net/wireless/realtek/rtw88/sar.c
index 3383726c4d90..c472f1502b82 100644
--- a/drivers/net/wireless/realtek/rtw88/sar.c
+++ b/drivers/net/wireless/realtek/rtw88/sar.c
@@ -91,10 +91,10 @@ int rtw_set_sar_specs(struct rtw_dev *rtwdev,
return -EINVAL;

power = sar->sub_specs[i].power;
- rtw_info(rtwdev, "On freq %u to %u, set SAR %d in 1/%lu dBm\n",
- rtw_common_sar_freq_ranges[idx].start_freq,
- rtw_common_sar_freq_ranges[idx].end_freq,
- power, BIT(RTW_COMMON_SAR_FCT));
+ rtw_dbg(rtwdev, RTW_DBG_REGD, "On freq %u to %u, set SAR %d in 1/%lu dBm\n",
+ rtw_common_sar_freq_ranges[idx].start_freq,
+ rtw_common_sar_freq_ranges[idx].end_freq,
+ power, BIT(RTW_COMMON_SAR_FCT));

for (j = 0; j < RTW_RF_PATH_MAX; j++) {
for (k = 0; k < RTW_RATE_SECTION_MAX; k++) {
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index a0737eea9f81..9632e7f218dd 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -1509,11 +1509,12 @@ static void rtw89_core_txq_push(struct rtw89_dev *rtwdev,
unsigned long i;
int ret;

+ rcu_read_lock();
for (i = 0; i < frame_cnt; i++) {
skb = ieee80211_tx_dequeue_ni(rtwdev->hw, txq);
if (!skb) {
rtw89_debug(rtwdev, RTW89_DBG_TXRX, "dequeue a NULL skb\n");
- return;
+ goto out;
}
rtw89_core_txq_check_agg(rtwdev, rtwtxq, skb);
ret = rtw89_core_tx_write(rtwdev, vif, sta, skb, NULL);
@@ -1523,6 +1524,8 @@ static void rtw89_core_txq_push(struct rtw89_dev *rtwdev,
break;
}
}
+out:
+ rcu_read_unlock();
}

static u32 rtw89_check_and_reclaim_tx_resource(struct rtw89_dev *rtwdev, u8 tid)
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index 596c185b5dda..b5f2f9f39392 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -10,6 +10,7 @@
#include <linux/debugfs.h>
#include <linux/device.h>
#include <linux/err.h>
+#include <linux/of.h>
#include <linux/init.h>
#include <linux/limits.h>
#include <linux/slab.h>
@@ -131,9 +132,13 @@ void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend);
debugfs_create_u32("performance_state", S_IRUGO, d, &opp->pstate);
debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate);
+ debugfs_create_u32("level", S_IRUGO, d, &opp->level);
debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
&opp->clock_latency_ns);

+ opp->of_name = of_node_full_name(opp->np);
+ debugfs_create_str("of_name", S_IRUGO, d, (char **)&opp->of_name);
+
opp_debug_create_supplies(opp, opp_table, d);
opp_debug_create_bw(opp, opp_table, d);

diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 407c3bfe51d9..45e3a55239a1 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -96,6 +96,7 @@ struct dev_pm_opp {

#ifdef CONFIG_DEBUG_FS
struct dentry *dentry;
+ const char *of_name;
#endif
};

diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index 952a92504df6..e33036281327 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -142,9 +142,8 @@ struct dino_device
{
struct pci_hba_data hba; /* 'C' inheritance - must be first */
spinlock_t dinosaur_pen;
- unsigned long txn_addr; /* EIR addr to generate interrupt */
- u32 txn_data; /* EIR data assign to each dino */
u32 imr; /* IRQ's which are enabled */
+ struct gsc_irq gsc_irq;
int global_irq[DINO_LOCAL_IRQS]; /* map IMR bit to global irq */
#ifdef DINO_DEBUG
unsigned int dino_irr0; /* save most recent IRQ line stat */
@@ -339,14 +338,43 @@ static void dino_unmask_irq(struct irq_data *d)
if (tmp & DINO_MASK_IRQ(local_irq)) {
DBG(KERN_WARNING "%s(): IRQ asserted! (ILR 0x%x)\n",
__func__, tmp);
- gsc_writel(dino_dev->txn_data, dino_dev->txn_addr);
+ gsc_writel(dino_dev->gsc_irq.txn_data, dino_dev->gsc_irq.txn_addr);
}
}

+#ifdef CONFIG_SMP
+static int dino_set_affinity_irq(struct irq_data *d, const struct cpumask *dest,
+ bool force)
+{
+ struct dino_device *dino_dev = irq_data_get_irq_chip_data(d);
+ struct cpumask tmask;
+ int cpu_irq;
+ u32 eim;
+
+ if (!cpumask_and(&tmask, dest, cpu_online_mask))
+ return -EINVAL;
+
+ cpu_irq = cpu_check_affinity(d, &tmask);
+ if (cpu_irq < 0)
+ return cpu_irq;
+
+ dino_dev->gsc_irq.txn_addr = txn_affinity_addr(d->irq, cpu_irq);
+ eim = ((u32) dino_dev->gsc_irq.txn_addr) | dino_dev->gsc_irq.txn_data;
+ __raw_writel(eim, dino_dev->hba.base_addr+DINO_IAR0);
+
+ irq_data_update_effective_affinity(d, &tmask);
+
+ return IRQ_SET_MASK_OK;
+}
+#endif
+
static struct irq_chip dino_interrupt_type = {
.name = "GSC-PCI",
.irq_unmask = dino_unmask_irq,
.irq_mask = dino_mask_irq,
+#ifdef CONFIG_SMP
+ .irq_set_affinity = dino_set_affinity_irq,
+#endif
};


@@ -806,7 +834,6 @@ static int __init dino_common_init(struct parisc_device *dev,
{
int status;
u32 eim;
- struct gsc_irq gsc_irq;
struct resource *res;

pcibios_register_hba(&dino_dev->hba);
@@ -821,10 +848,8 @@ static int __init dino_common_init(struct parisc_device *dev,
** still only has 11 IRQ input lines - just map some of them
** to a different processor.
*/
- dev->irq = gsc_alloc_irq(&gsc_irq);
- dino_dev->txn_addr = gsc_irq.txn_addr;
- dino_dev->txn_data = gsc_irq.txn_data;
- eim = ((u32) gsc_irq.txn_addr) | gsc_irq.txn_data;
+ dev->irq = gsc_alloc_irq(&dino_dev->gsc_irq);
+ eim = ((u32) dino_dev->gsc_irq.txn_addr) | dino_dev->gsc_irq.txn_data;

/*
** Dino needs a PA "IRQ" to get a processor's attention.
diff --git a/drivers/parisc/gsc.c b/drivers/parisc/gsc.c
index ed9371acf37e..ec175ae99873 100644
--- a/drivers/parisc/gsc.c
+++ b/drivers/parisc/gsc.c
@@ -135,10 +135,41 @@ static void gsc_asic_unmask_irq(struct irq_data *d)
*/
}

+#ifdef CONFIG_SMP
+static int gsc_set_affinity_irq(struct irq_data *d, const struct cpumask *dest,
+ bool force)
+{
+ struct gsc_asic *gsc_dev = irq_data_get_irq_chip_data(d);
+ struct cpumask tmask;
+ int cpu_irq;
+
+ if (!cpumask_and(&tmask, dest, cpu_online_mask))
+ return -EINVAL;
+
+ cpu_irq = cpu_check_affinity(d, &tmask);
+ if (cpu_irq < 0)
+ return cpu_irq;
+
+ gsc_dev->gsc_irq.txn_addr = txn_affinity_addr(d->irq, cpu_irq);
+ gsc_dev->eim = ((u32) gsc_dev->gsc_irq.txn_addr) | gsc_dev->gsc_irq.txn_data;
+
+ /* switch IRQ's for devices below LASI/WAX to other CPU */
+ gsc_writel(gsc_dev->eim, gsc_dev->hpa + OFFSET_IAR);
+
+ irq_data_update_effective_affinity(d, &tmask);
+
+ return IRQ_SET_MASK_OK;
+}
+#endif
+
+
static struct irq_chip gsc_asic_interrupt_type = {
.name = "GSC-ASIC",
.irq_unmask = gsc_asic_unmask_irq,
.irq_mask = gsc_asic_mask_irq,
+#ifdef CONFIG_SMP
+ .irq_set_affinity = gsc_set_affinity_irq,
+#endif
};

int gsc_assign_irq(struct irq_chip *type, void *data)
diff --git a/drivers/parisc/gsc.h b/drivers/parisc/gsc.h
index 86abad3fa215..73cbd0bb1975 100644
--- a/drivers/parisc/gsc.h
+++ b/drivers/parisc/gsc.h
@@ -31,6 +31,7 @@ struct gsc_asic {
int version;
int type;
int eim;
+ struct gsc_irq gsc_irq;
int global_irq[32];
};

diff --git a/drivers/parisc/lasi.c b/drivers/parisc/lasi.c
index 4e4fd12c2112..6ef621adb63a 100644
--- a/drivers/parisc/lasi.c
+++ b/drivers/parisc/lasi.c
@@ -163,7 +163,6 @@ static int __init lasi_init_chip(struct parisc_device *dev)
{
extern void (*chassis_power_off)(void);
struct gsc_asic *lasi;
- struct gsc_irq gsc_irq;
int ret;

lasi = kzalloc(sizeof(*lasi), GFP_KERNEL);
@@ -185,7 +184,7 @@ static int __init lasi_init_chip(struct parisc_device *dev)
lasi_init_irq(lasi);

/* the IRQ lasi should use */
- dev->irq = gsc_alloc_irq(&gsc_irq);
+ dev->irq = gsc_alloc_irq(&lasi->gsc_irq);
if (dev->irq < 0) {
printk(KERN_ERR "%s(): cannot get GSC irq\n",
__func__);
@@ -193,9 +192,9 @@ static int __init lasi_init_chip(struct parisc_device *dev)
return -EBUSY;
}

- lasi->eim = ((u32) gsc_irq.txn_addr) | gsc_irq.txn_data;
+ lasi->eim = ((u32) lasi->gsc_irq.txn_addr) | lasi->gsc_irq.txn_data;

- ret = request_irq(gsc_irq.irq, gsc_asic_intr, 0, "lasi", lasi);
+ ret = request_irq(lasi->gsc_irq.irq, gsc_asic_intr, 0, "lasi", lasi);
if (ret < 0) {
kfree(lasi);
return ret;
diff --git a/drivers/parisc/wax.c b/drivers/parisc/wax.c
index 5b6df1516235..73a2b01f8d9c 100644
--- a/drivers/parisc/wax.c
+++ b/drivers/parisc/wax.c
@@ -68,7 +68,6 @@ static int __init wax_init_chip(struct parisc_device *dev)
{
struct gsc_asic *wax;
struct parisc_device *parent;
- struct gsc_irq gsc_irq;
int ret;

wax = kzalloc(sizeof(*wax), GFP_KERNEL);
@@ -85,7 +84,7 @@ static int __init wax_init_chip(struct parisc_device *dev)
wax_init_irq(wax);

/* the IRQ wax should use */
- dev->irq = gsc_claim_irq(&gsc_irq, WAX_GSC_IRQ);
+ dev->irq = gsc_claim_irq(&wax->gsc_irq, WAX_GSC_IRQ);
if (dev->irq < 0) {
printk(KERN_ERR "%s(): cannot get GSC irq\n",
__func__);
@@ -93,9 +92,9 @@ static int __init wax_init_chip(struct parisc_device *dev)
return -EBUSY;
}

- wax->eim = ((u32) gsc_irq.txn_addr) | gsc_irq.txn_data;
+ wax->eim = ((u32) wax->gsc_irq.txn_addr) | wax->gsc_irq.txn_data;

- ret = request_irq(gsc_irq.irq, gsc_asic_intr, 0, "wax", wax);
+ ret = request_irq(wax->gsc_irq.irq, gsc_asic_intr, 0, "wax", wax);
if (ret < 0) {
kfree(wax);
return ret;
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 82e2c618d532..15348be1a8aa 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -1186,7 +1186,7 @@ static void advk_msi_irq_compose_msi_msg(struct irq_data *data,

msg->address_lo = lower_32_bits(msi_msg);
msg->address_hi = upper_32_bits(msi_msg);
- msg->data = data->irq;
+ msg->data = data->hwirq;
}

static int advk_msi_set_affinity(struct irq_data *irq_data,
@@ -1203,15 +1203,11 @@ static int advk_msi_irq_domain_alloc(struct irq_domain *domain,
int hwirq, i;

mutex_lock(&pcie->msi_used_lock);
- hwirq = bitmap_find_next_zero_area(pcie->msi_used, MSI_IRQ_NUM,
- 0, nr_irqs, 0);
- if (hwirq >= MSI_IRQ_NUM) {
- mutex_unlock(&pcie->msi_used_lock);
- return -ENOSPC;
- }
-
- bitmap_set(pcie->msi_used, hwirq, nr_irqs);
+ hwirq = bitmap_find_free_region(pcie->msi_used, MSI_IRQ_NUM,
+ order_base_2(nr_irqs));
mutex_unlock(&pcie->msi_used_lock);
+ if (hwirq < 0)
+ return -ENOSPC;

for (i = 0; i < nr_irqs; i++)
irq_domain_set_info(domain, virq + i, hwirq + i,
@@ -1229,7 +1225,7 @@ static void advk_msi_irq_domain_free(struct irq_domain *domain,
struct advk_pcie *pcie = domain->host_data;

mutex_lock(&pcie->msi_used_lock);
- bitmap_clear(pcie->msi_used, d->hwirq, nr_irqs);
+ bitmap_release_region(pcie->msi_used, d->hwirq, order_base_2(nr_irqs));
mutex_unlock(&pcie->msi_used_lock);
}

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 90d84d3bc868..5b833f00e980 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -285,7 +285,17 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test)
if (ret)
dev_err(dev, "Data transfer failed\n");
} else {
- memcpy(dst_addr, src_addr, reg->size);
+ void *buf;
+
+ buf = kzalloc(reg->size, GFP_KERNEL);
+ if (!buf) {
+ ret = -ENOMEM;
+ goto err_map_addr;
+ }
+
+ memcpy_fromio(buf, src_addr, reg->size);
+ memcpy_toio(dst_addr, buf, reg->size);
+ kfree(buf);
}
ktime_get_ts64(&end);
pci_epf_test_print_rate("COPY", reg->size, &start, &end, use_dma);
@@ -441,7 +451,7 @@ static int pci_epf_test_write(struct pci_epf_test *epf_test)
if (!epf_test->dma_supported) {
dev_err(dev, "Cannot transfer data using DMA\n");
ret = -EINVAL;
- goto err_map_addr;
+ goto err_dma_map;
}

src_phys_addr = dma_map_single(dma_dev, buf, reg->size,
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 85dce560831a..040ae076ec0e 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -1086,6 +1086,8 @@ static void quirk_cmd_compl(struct pci_dev *pdev)
}
DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
PCI_CLASS_BRIDGE_PCI, 8, quirk_cmd_compl);
+DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_QCOM, 0x0110,
+ PCI_CLASS_BRIDGE_PCI, 8, quirk_cmd_compl);
DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_QCOM, 0x0400,
PCI_CLASS_BRIDGE_PCI, 8, quirk_cmd_compl);
DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_QCOM, 0x0401,
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 7640491aab12..30234c261b05 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -736,7 +736,7 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster(
{
u64 mpidr;
int cpu_cluster_id;
- struct cluster_pmu *cluster = NULL;
+ struct cluster_pmu *cluster;

/*
* This assumes that the cluster_id is in MPIDR[aff1] for
@@ -758,10 +758,10 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster(
cluster->cluster_id);
cpumask_set_cpu(cpu, &cluster->cluster_cpus);
*per_cpu_ptr(l2cache_pmu->pmu_cluster, cpu) = cluster;
- break;
+ return cluster;
}

- return cluster;
+ return NULL;
}

static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
diff --git a/drivers/phy/amlogic/phy-meson-gxl-usb2.c b/drivers/phy/amlogic/phy-meson-gxl-usb2.c
index 2b3c0d730f20..db17c3448bfe 100644
--- a/drivers/phy/amlogic/phy-meson-gxl-usb2.c
+++ b/drivers/phy/amlogic/phy-meson-gxl-usb2.c
@@ -114,8 +114,10 @@ static int phy_meson_gxl_usb2_init(struct phy *phy)
return ret;

ret = clk_prepare_enable(priv->clk);
- if (ret)
+ if (ret) {
+ reset_control_rearm(priv->reset);
return ret;
+ }

return 0;
}
@@ -125,6 +127,7 @@ static int phy_meson_gxl_usb2_exit(struct phy *phy)
struct phy_meson_gxl_usb2_priv *priv = phy_get_drvdata(phy);

clk_disable_unprepare(priv->clk);
+ reset_control_rearm(priv->reset);

return 0;
}
diff --git a/drivers/phy/amlogic/phy-meson8b-usb2.c b/drivers/phy/amlogic/phy-meson8b-usb2.c
index cf10bed40528..dd96763911b8 100644
--- a/drivers/phy/amlogic/phy-meson8b-usb2.c
+++ b/drivers/phy/amlogic/phy-meson8b-usb2.c
@@ -154,6 +154,7 @@ static int phy_meson8b_usb2_power_on(struct phy *phy)
ret = clk_prepare_enable(priv->clk_usb_general);
if (ret) {
dev_err(&phy->dev, "Failed to enable USB general clock\n");
+ reset_control_rearm(priv->reset);
return ret;
}

@@ -161,6 +162,7 @@ static int phy_meson8b_usb2_power_on(struct phy *phy)
if (ret) {
dev_err(&phy->dev, "Failed to enable USB DDR clock\n");
clk_disable_unprepare(priv->clk_usb_general);
+ reset_control_rearm(priv->reset);
return ret;
}

@@ -199,6 +201,7 @@ static int phy_meson8b_usb2_power_on(struct phy *phy)
dev_warn(&phy->dev, "USB ID detect failed!\n");
clk_disable_unprepare(priv->clk_usb);
clk_disable_unprepare(priv->clk_usb_general);
+ reset_control_rearm(priv->reset);
return -EINVAL;
}
}
@@ -218,6 +221,7 @@ static int phy_meson8b_usb2_power_off(struct phy *phy)

clk_disable_unprepare(priv->clk_usb);
clk_disable_unprepare(priv->clk_usb_general);
+ reset_control_rearm(priv->reset);

/* power off the PHY by putting it into reset mode */
regmap_update_bits(priv->regmap, REG_CTRL, REG_CTRL_POWER_ON_RESET,
@@ -265,8 +269,9 @@ static int phy_meson8b_usb2_probe(struct platform_device *pdev)
return PTR_ERR(priv->clk_usb);

priv->reset = devm_reset_control_get_optional_shared(&pdev->dev, NULL);
- if (PTR_ERR(priv->reset) == -EPROBE_DEFER)
- return PTR_ERR(priv->reset);
+ if (IS_ERR(priv->reset))
+ return dev_err_probe(&pdev->dev, PTR_ERR(priv->reset),
+ "Failed to get the reset line");

priv->dr_mode = of_usb_get_dr_mode_by_phy(pdev->dev.of_node, -1);
if (priv->dr_mode == USB_DR_MODE_UNKNOWN) {
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 24deeeb29af2..53abd553b842 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -1027,7 +1027,7 @@ config TOUCHSCREEN_DMI

config X86_ANDROID_TABLETS
tristate "X86 Android tablet support"
- depends on I2C && SERIAL_DEV_BUS && ACPI && GPIOLIB
+ depends on I2C && SPI && SERIAL_DEV_BUS && ACPI && EFI && GPIOLIB
help
X86 tablets which ship with Android as (part of) the factory image
typically have various problems with their DSDTs. The factory kernels
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 48a46466f086..88f0bfd6ecf1 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -35,10 +35,6 @@ MODULE_LICENSE("GPL");
MODULE_ALIAS("wmi:95F24279-4D7B-4334-9387-ACCDC67EF61C");
MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4");

-static int enable_tablet_mode_sw = -1;
-module_param(enable_tablet_mode_sw, int, 0444);
-MODULE_PARM_DESC(enable_tablet_mode_sw, "Enable SW_TABLET_MODE reporting (-1=auto, 0=no, 1=yes)");
-
#define HPWMI_EVENT_GUID "95F24279-4D7B-4334-9387-ACCDC67EF61C"
#define HPWMI_BIOS_GUID "5FB7F034-2C63-45e9-BE91-3D44E2C707E4"
#define HP_OMEN_EC_THERMAL_PROFILE_OFFSET 0x95
@@ -107,6 +103,7 @@ enum hp_wmi_commandtype {
HPWMI_FEATURE2_QUERY = 0x0d,
HPWMI_WIRELESS2_QUERY = 0x1b,
HPWMI_POSTCODEERROR_QUERY = 0x2a,
+ HPWMI_SYSTEM_DEVICE_MODE = 0x40,
HPWMI_THERMAL_PROFILE_QUERY = 0x4c,
};

@@ -217,6 +214,19 @@ struct rfkill2_device {
static int rfkill2_count;
static struct rfkill2_device rfkill2[HPWMI_MAX_RFKILL2_DEVICES];

+/*
+ * Chassis Types values were obtained from SMBIOS reference
+ * specification version 3.00. A complete list of system enclosures
+ * and chassis types is available on Table 17.
+ */
+static const char * const tablet_chassis_types[] = {
+ "30", /* Tablet*/
+ "31", /* Convertible */
+ "32" /* Detachable */
+};
+
+#define DEVICE_MODE_TABLET 0x06
+
/* map output size to the corresponding WMI method id */
static inline int encode_outsize_for_pvsz(int outsize)
{
@@ -320,7 +330,7 @@ static int hp_wmi_get_fan_speed(int fan)
char fan_data[4] = { fan, 0, 0, 0 };

int ret = hp_wmi_perform_query(HPWMI_FAN_SPEED_GET_QUERY, HPWMI_GM,
- &fan_data, sizeof(fan_data),
+ &fan_data, sizeof(char),
sizeof(fan_data));

if (ret != 0)
@@ -345,14 +355,39 @@ static int hp_wmi_read_int(int query)
return val;
}

-static int hp_wmi_hw_state(int mask)
+static int hp_wmi_get_dock_state(void)
{
int state = hp_wmi_read_int(HPWMI_HARDWARE_QUERY);

if (state < 0)
return state;

- return !!(state & mask);
+ return !!(state & HPWMI_DOCK_MASK);
+}
+
+static int hp_wmi_get_tablet_mode(void)
+{
+ char system_device_mode[4] = { 0 };
+ const char *chassis_type;
+ bool tablet_found;
+ int ret;
+
+ chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE);
+ if (!chassis_type)
+ return -ENODEV;
+
+ tablet_found = match_string(tablet_chassis_types,
+ ARRAY_SIZE(tablet_chassis_types),
+ chassis_type) >= 0;
+ if (!tablet_found)
+ return -ENODEV;
+
+ ret = hp_wmi_perform_query(HPWMI_SYSTEM_DEVICE_MODE, HPWMI_READ,
+ system_device_mode, 0, sizeof(system_device_mode));
+ if (ret < 0)
+ return ret;
+
+ return system_device_mode[0] == DEVICE_MODE_TABLET;
}

static int omen_thermal_profile_set(int mode)
@@ -364,7 +399,7 @@ static int omen_thermal_profile_set(int mode)
return -EINVAL;

ret = hp_wmi_perform_query(HPWMI_SET_PERFORMANCE_MODE, HPWMI_GM,
- &buffer, sizeof(buffer), sizeof(buffer));
+ &buffer, sizeof(buffer), 0);

if (ret)
return ret < 0 ? ret : -EINVAL;
@@ -401,7 +436,7 @@ static int hp_wmi_fan_speed_max_set(int enabled)
int ret;

ret = hp_wmi_perform_query(HPWMI_FAN_SPEED_MAX_SET_QUERY, HPWMI_GM,
- &enabled, sizeof(enabled), sizeof(enabled));
+ &enabled, sizeof(enabled), 0);

if (ret)
return ret < 0 ? ret : -EINVAL;
@@ -414,7 +449,7 @@ static int hp_wmi_fan_speed_max_get(void)
int val = 0, ret;

ret = hp_wmi_perform_query(HPWMI_FAN_SPEED_MAX_GET_QUERY, HPWMI_GM,
- &val, sizeof(val), sizeof(val));
+ &val, 0, sizeof(val));

if (ret)
return ret < 0 ? ret : -EINVAL;
@@ -426,7 +461,7 @@ static int __init hp_wmi_bios_2008_later(void)
{
int state = 0;
int ret = hp_wmi_perform_query(HPWMI_FEATURE_QUERY, HPWMI_READ, &state,
- sizeof(state), sizeof(state));
+ 0, sizeof(state));
if (!ret)
return 1;

@@ -437,7 +472,7 @@ static int __init hp_wmi_bios_2009_later(void)
{
u8 state[128];
int ret = hp_wmi_perform_query(HPWMI_FEATURE2_QUERY, HPWMI_READ, &state,
- sizeof(state), sizeof(state));
+ 0, sizeof(state));
if (!ret)
return 1;

@@ -515,7 +550,7 @@ static int hp_wmi_rfkill2_refresh(void)
int err, i;

err = hp_wmi_perform_query(HPWMI_WIRELESS2_QUERY, HPWMI_READ, &state,
- sizeof(state), sizeof(state));
+ 0, sizeof(state));
if (err)
return err;

@@ -568,7 +603,7 @@ static ssize_t als_show(struct device *dev, struct device_attribute *attr,
static ssize_t dock_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- int value = hp_wmi_hw_state(HPWMI_DOCK_MASK);
+ int value = hp_wmi_get_dock_state();
if (value < 0)
return value;
return sprintf(buf, "%d\n", value);
@@ -577,7 +612,7 @@ static ssize_t dock_show(struct device *dev, struct device_attribute *attr,
static ssize_t tablet_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- int value = hp_wmi_hw_state(HPWMI_TABLET_MASK);
+ int value = hp_wmi_get_tablet_mode();
if (value < 0)
return value;
return sprintf(buf, "%d\n", value);
@@ -604,7 +639,7 @@ static ssize_t als_store(struct device *dev, struct device_attribute *attr,
return ret;

ret = hp_wmi_perform_query(HPWMI_ALS_QUERY, HPWMI_WRITE, &tmp,
- sizeof(tmp), sizeof(tmp));
+ sizeof(tmp), 0);
if (ret)
return ret < 0 ? ret : -EINVAL;

@@ -625,9 +660,9 @@ static ssize_t postcode_store(struct device *dev, struct device_attribute *attr,
if (clear == false)
return -EINVAL;

- /* Clear the POST error code. It is kept until until cleared. */
+ /* Clear the POST error code. It is kept until cleared. */
ret = hp_wmi_perform_query(HPWMI_POSTCODEERROR_QUERY, HPWMI_WRITE, &tmp,
- sizeof(tmp), sizeof(tmp));
+ sizeof(tmp), 0);
if (ret)
return ret < 0 ? ret : -EINVAL;

@@ -699,10 +734,10 @@ static void hp_wmi_notify(u32 value, void *context)
case HPWMI_DOCK_EVENT:
if (test_bit(SW_DOCK, hp_wmi_input_dev->swbit))
input_report_switch(hp_wmi_input_dev, SW_DOCK,
- hp_wmi_hw_state(HPWMI_DOCK_MASK));
+ hp_wmi_get_dock_state());
if (test_bit(SW_TABLET_MODE, hp_wmi_input_dev->swbit))
input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE,
- hp_wmi_hw_state(HPWMI_TABLET_MASK));
+ hp_wmi_get_tablet_mode());
input_sync(hp_wmi_input_dev);
break;
case HPWMI_PARK_HDD:
@@ -780,19 +815,17 @@ static int __init hp_wmi_input_setup(void)
__set_bit(EV_SW, hp_wmi_input_dev->evbit);

/* Dock */
- val = hp_wmi_hw_state(HPWMI_DOCK_MASK);
+ val = hp_wmi_get_dock_state();
if (!(val < 0)) {
__set_bit(SW_DOCK, hp_wmi_input_dev->swbit);
input_report_switch(hp_wmi_input_dev, SW_DOCK, val);
}

/* Tablet mode */
- if (enable_tablet_mode_sw > 0) {
- val = hp_wmi_hw_state(HPWMI_TABLET_MASK);
- if (val >= 0) {
- __set_bit(SW_TABLET_MODE, hp_wmi_input_dev->swbit);
- input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, val);
- }
+ val = hp_wmi_get_tablet_mode();
+ if (!(val < 0)) {
+ __set_bit(SW_TABLET_MODE, hp_wmi_input_dev->swbit);
+ input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, val);
}

err = sparse_keymap_setup(hp_wmi_input_dev, hp_wmi_keymap, NULL);
@@ -919,7 +952,7 @@ static int __init hp_wmi_rfkill2_setup(struct platform_device *device)
int err, i;

err = hp_wmi_perform_query(HPWMI_WIRELESS2_QUERY, HPWMI_READ, &state,
- sizeof(state), sizeof(state));
+ 0, sizeof(state));
if (err)
return err < 0 ? err : -EINVAL;

@@ -1227,10 +1260,10 @@ static int hp_wmi_resume_handler(struct device *device)
if (hp_wmi_input_dev) {
if (test_bit(SW_DOCK, hp_wmi_input_dev->swbit))
input_report_switch(hp_wmi_input_dev, SW_DOCK,
- hp_wmi_hw_state(HPWMI_DOCK_MASK));
+ hp_wmi_get_dock_state());
if (test_bit(SW_TABLET_MODE, hp_wmi_input_dev->swbit))
input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE,
- hp_wmi_hw_state(HPWMI_TABLET_MASK));
+ hp_wmi_get_tablet_mode());
input_sync(hp_wmi_input_dev);
}

diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 3424b080db77..3fb8cda31eb9 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -8699,10 +8699,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
TPACPI_Q_LNV3('N', '2', 'N', TPACPI_FAN_2CTL), /* P53 / P73 */
TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */
TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */
- TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */
- TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (4nd gen) */
TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */
- TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */
TPACPI_Q_LNV3('N', '3', '7', TPACPI_FAN_2CTL), /* T15g (2nd gen) */
TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */
};
@@ -8746,6 +8743,9 @@ static int __init fan_init(struct ibm_init_struct *iibm)
* ThinkPad ECs supports the fan control register */
if (likely(acpi_ec_read(fan_status_offset,
&fan_control_initial_status))) {
+ int res;
+ unsigned int speed;
+
fan_status_access_mode = TPACPI_FAN_RD_TPEC;
if (quirks & TPACPI_FAN_Q1)
fan_quirk1_setup();
@@ -8758,6 +8758,15 @@ static int __init fan_init(struct ibm_init_struct *iibm)
tp_features.second_fan_ctl = 1;
pr_info("secondary fan control enabled\n");
}
+ /* Try and probe the 2nd fan */
+ res = fan2_get_speed(&speed);
+ if (res >= 0) {
+ /* It responded - so let's assume it's there */
+ tp_features.second_fan = 1;
+ tp_features.second_fan_ctl = 1;
+ pr_info("secondary fan control detected & enabled\n");
+ }
+
} else {
pr_err("ThinkPad ACPI EC access misbehaving, fan status and control unavailable\n");
return -ENODEV;
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index b366e2fd8e97..5e4a69352811 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -351,14 +351,14 @@ config AXP20X_POWER

config AXP288_CHARGER
tristate "X-Powers AXP288 Charger"
- depends on MFD_AXP20X && EXTCON_AXP288 && IOSF_MBI
+ depends on MFD_AXP20X && EXTCON_AXP288 && IOSF_MBI && ACPI
help
Say yes here to have support X-Power AXP288 power management IC (PMIC)
integrated charger.

config AXP288_FUEL_GAUGE
tristate "X-Powers AXP288 Fuel Gauge"
- depends on MFD_AXP20X && IIO && IOSF_MBI
+ depends on MFD_AXP20X && IIO && IOSF_MBI && ACPI
help
Say yes here to have support for X-Power power management IC (PMIC)
Fuel Gauge. The device provides battery statistics and status
diff --git a/drivers/power/supply/axp20x_battery.c b/drivers/power/supply/axp20x_battery.c
index 5d197141f476..9106077c0dbb 100644
--- a/drivers/power/supply/axp20x_battery.c
+++ b/drivers/power/supply/axp20x_battery.c
@@ -186,7 +186,6 @@ static int axp20x_battery_get_prop(struct power_supply *psy,
union power_supply_propval *val)
{
struct axp20x_batt_ps *axp20x_batt = power_supply_get_drvdata(psy);
- struct iio_channel *chan;
int ret = 0, reg, val1;

switch (psp) {
@@ -266,12 +265,12 @@ static int axp20x_battery_get_prop(struct power_supply *psy,
if (ret)
return ret;

- if (reg & AXP20X_PWR_STATUS_BAT_CHARGING)
- chan = axp20x_batt->batt_chrg_i;
- else
- chan = axp20x_batt->batt_dischrg_i;
-
- ret = iio_read_channel_processed(chan, &val->intval);
+ if (reg & AXP20X_PWR_STATUS_BAT_CHARGING) {
+ ret = iio_read_channel_processed(axp20x_batt->batt_chrg_i, &val->intval);
+ } else {
+ ret = iio_read_channel_processed(axp20x_batt->batt_dischrg_i, &val1);
+ val->intval = -val1;
+ }
if (ret)
return ret;

diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index ec41f6cd3f93..19746e658a6a 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -42,11 +42,11 @@
#define VBUS_ISPOUT_CUR_LIM_1500MA 0x1 /* 1500mA */
#define VBUS_ISPOUT_CUR_LIM_2000MA 0x2 /* 2000mA */
#define VBUS_ISPOUT_CUR_NO_LIM 0x3 /* 2500mA */
-#define VBUS_ISPOUT_VHOLD_SET_MASK 0x31
+#define VBUS_ISPOUT_VHOLD_SET_MASK 0x38
#define VBUS_ISPOUT_VHOLD_SET_BIT_POS 0x3
#define VBUS_ISPOUT_VHOLD_SET_OFFSET 4000 /* 4000mV */
#define VBUS_ISPOUT_VHOLD_SET_LSB_RES 100 /* 100mV */
-#define VBUS_ISPOUT_VHOLD_SET_4300MV 0x3 /* 4300mV */
+#define VBUS_ISPOUT_VHOLD_SET_4400MV 0x4 /* 4400mV */
#define VBUS_ISPOUT_VBUS_PATH_DIS BIT(7)

#define CHRG_CCCV_CC_MASK 0xf /* 4 bits */
@@ -769,6 +769,16 @@ static int charger_init_hw_regs(struct axp288_chrg_info *info)
ret = axp288_charger_vbus_path_select(info, true);
if (ret < 0)
return ret;
+ } else {
+ /* Set Vhold to the factory default / recommended 4.4V */
+ val = VBUS_ISPOUT_VHOLD_SET_4400MV << VBUS_ISPOUT_VHOLD_SET_BIT_POS;
+ ret = regmap_update_bits(info->regmap, AXP20X_VBUS_IPSOUT_MGMT,
+ VBUS_ISPOUT_VHOLD_SET_MASK, val);
+ if (ret < 0) {
+ dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
+ AXP20X_VBUS_IPSOUT_MGMT, ret);
+ return ret;
+ }
}

/* Read current charge voltage and current limit */
@@ -828,6 +838,13 @@ static int axp288_charger_probe(struct platform_device *pdev)
struct power_supply_config charger_cfg = {};
unsigned int val;

+ /*
+ * Normally the native AXP288 fg/charger drivers are preferred but
+ * on some devices the ACPI drivers should be used instead.
+ */
+ if (!acpi_quirk_skip_acpi_ac_and_battery())
+ return -ENODEV;
+
/*
* On some devices the fuelgauge and charger parts of the axp288 are
* not used, check that the fuelgauge is enabled (CC_CTRL != 0).
diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c
index c1da217fdb0e..ce8ffd0a41b5 100644
--- a/drivers/power/supply/axp288_fuel_gauge.c
+++ b/drivers/power/supply/axp288_fuel_gauge.c
@@ -9,6 +9,7 @@
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/

+#include <linux/acpi.h>
#include <linux/dmi.h>
#include <linux/module.h>
#include <linux/kernel.h>
@@ -560,12 +561,6 @@ static const struct dmi_system_id axp288_no_battery_list[] = {
DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1.000"),
},
},
- {
- /* ECS EF20EA */
- .matches = {
- DMI_MATCH(DMI_PRODUCT_NAME, "EF20EA"),
- },
- },
{
/* Intel Cherry Trail Compute Stick, Windows version */
.matches = {
@@ -624,6 +619,13 @@ static int axp288_fuel_gauge_probe(struct platform_device *pdev)
};
unsigned int val;

+ /*
+ * Normally the native AXP288 fg/charger drivers are preferred but
+ * on some devices the ACPI drivers should be used instead.
+ */
+ if (!acpi_quirk_skip_acpi_ac_and_battery())
+ return -ENODEV;
+
if (dmi_check_system(axp288_no_battery_list))
return -ENODEV;

diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c
index 41b92dc2f011..9233bfedeb17 100644
--- a/drivers/ptp/ptp_sysfs.c
+++ b/drivers/ptp/ptp_sysfs.c
@@ -14,7 +14,7 @@ static ssize_t clock_name_show(struct device *dev,
struct device_attribute *attr, char *page)
{
struct ptp_clock *ptp = dev_get_drvdata(dev);
- return snprintf(page, PAGE_SIZE-1, "%s\n", ptp->info->name);
+ return sysfs_emit(page, "%s\n", ptp->info->name);
}
static DEVICE_ATTR_RO(clock_name);

@@ -387,7 +387,7 @@ static ssize_t ptp_pin_show(struct device *dev, struct device_attribute *attr,

mutex_unlock(&ptp->pincfg_mux);

- return snprintf(page, PAGE_SIZE, "%u %u\n", func, chan);
+ return sysfs_emit(page, "%u %u\n", func, chan);
}

static ssize_t ptp_pin_store(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/regulator/atc260x-regulator.c b/drivers/regulator/atc260x-regulator.c
index 05147d2c3842..485e58b264c0 100644
--- a/drivers/regulator/atc260x-regulator.c
+++ b/drivers/regulator/atc260x-regulator.c
@@ -292,6 +292,7 @@ enum atc2603c_reg_ids {
.bypass_mask = BIT(5), \
.active_discharge_reg = ATC2603C_PMU_SWITCH_CTL, \
.active_discharge_mask = BIT(1), \
+ .active_discharge_on = BIT(1), \
.owner = THIS_MODULE, \
}

diff --git a/drivers/regulator/rtq2134-regulator.c b/drivers/regulator/rtq2134-regulator.c
index f21e3f8b21f2..8e13dea354a2 100644
--- a/drivers/regulator/rtq2134-regulator.c
+++ b/drivers/regulator/rtq2134-regulator.c
@@ -285,6 +285,7 @@ static const unsigned int rtq2134_buck_ramp_delay_table[] = {
.enable_mask = RTQ2134_VOUTEN_MASK, \
.active_discharge_reg = RTQ2134_REG_BUCK##_id##_CFG0, \
.active_discharge_mask = RTQ2134_ACTDISCHG_MASK, \
+ .active_discharge_on = RTQ2134_ACTDISCHG_MASK, \
.ramp_reg = RTQ2134_REG_BUCK##_id##_RSPCFG, \
.ramp_mask = RTQ2134_RSPUP_MASK, \
.ramp_delay_table = rtq2134_buck_ramp_delay_table, \
diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c
index 2018614f258f..6eaa9321c074 100644
--- a/drivers/rtc/rtc-wm8350.c
+++ b/drivers/rtc/rtc-wm8350.c
@@ -432,14 +432,21 @@ static int wm8350_rtc_probe(struct platform_device *pdev)
return ret;
}

- wm8350_register_irq(wm8350, WM8350_IRQ_RTC_SEC,
+ ret = wm8350_register_irq(wm8350, WM8350_IRQ_RTC_SEC,
wm8350_rtc_update_handler, 0,
"RTC Seconds", wm8350);
+ if (ret)
+ return ret;
+
wm8350_mask_irq(wm8350, WM8350_IRQ_RTC_SEC);

- wm8350_register_irq(wm8350, WM8350_IRQ_RTC_ALM,
+ ret = wm8350_register_irq(wm8350, WM8350_IRQ_RTC_ALM,
wm8350_rtc_alarm_handler, 0,
"RTC Alarm", wm8350);
+ if (ret) {
+ wm8350_free_irq(wm8350, WM8350_IRQ_RTC_SEC, wm8350);
+ return ret;
+ }

return 0;
}
diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c
index d17880b57d17..2449b4215b32 100644
--- a/drivers/scsi/aha152x.c
+++ b/drivers/scsi/aha152x.c
@@ -3375,13 +3375,11 @@ static int __init aha152x_setup(char *str)
setup[setup_count].synchronous = ints[0] >= 6 ? ints[6] : 1;
setup[setup_count].delay = ints[0] >= 7 ? ints[7] : DELAY_DEFAULT;
setup[setup_count].ext_trans = ints[0] >= 8 ? ints[8] : 0;
- if (ints[0] > 8) { /*}*/
+ if (ints[0] > 8)
printk(KERN_NOTICE "aha152x: usage: aha152x=<IOBASE>[,<IRQ>[,<SCSI ID>"
"[,<RECONNECT>[,<PARITY>[,<SYNCHRONOUS>[,<DELAY>[,<EXT_TRANS>]]]]]]]\n");
- } else {
+ else
setup_count++;
- return 0;
- }

return 1;
}
diff --git a/drivers/scsi/bfa/bfad_attr.c b/drivers/scsi/bfa/bfad_attr.c
index f46989bd083c..5a85401e9e2d 100644
--- a/drivers/scsi/bfa/bfad_attr.c
+++ b/drivers/scsi/bfa/bfad_attr.c
@@ -711,7 +711,7 @@ bfad_im_serial_num_show(struct device *dev, struct device_attribute *attr,
char serial_num[BFA_ADAPTER_SERIAL_NUM_LEN];

bfa_get_adapter_serial_num(&bfad->bfa, serial_num);
- return snprintf(buf, PAGE_SIZE, "%s\n", serial_num);
+ return sysfs_emit(buf, "%s\n", serial_num);
}

static ssize_t
@@ -725,7 +725,7 @@ bfad_im_model_show(struct device *dev, struct device_attribute *attr,
char model[BFA_ADAPTER_MODEL_NAME_LEN];

bfa_get_adapter_model(&bfad->bfa, model);
- return snprintf(buf, PAGE_SIZE, "%s\n", model);
+ return sysfs_emit(buf, "%s\n", model);
}

static ssize_t
@@ -805,7 +805,7 @@ bfad_im_model_desc_show(struct device *dev, struct device_attribute *attr,
snprintf(model_descr, BFA_ADAPTER_MODEL_DESCR_LEN,
"Invalid Model");

- return snprintf(buf, PAGE_SIZE, "%s\n", model_descr);
+ return sysfs_emit(buf, "%s\n", model_descr);
}

static ssize_t
@@ -819,7 +819,7 @@ bfad_im_node_name_show(struct device *dev, struct device_attribute *attr,
u64 nwwn;

nwwn = bfa_fcs_lport_get_nwwn(port->fcs_port);
- return snprintf(buf, PAGE_SIZE, "0x%llx\n", cpu_to_be64(nwwn));
+ return sysfs_emit(buf, "0x%llx\n", cpu_to_be64(nwwn));
}

static ssize_t
@@ -836,7 +836,7 @@ bfad_im_symbolic_name_show(struct device *dev, struct device_attribute *attr,
bfa_fcs_lport_get_attr(&bfad->bfa_fcs.fabric.bport, &port_attr);
strlcpy(symname, port_attr.port_cfg.sym_name.symname,
BFA_SYMNAME_MAXLEN);
- return snprintf(buf, PAGE_SIZE, "%s\n", symname);
+ return sysfs_emit(buf, "%s\n", symname);
}

static ssize_t
@@ -850,14 +850,14 @@ bfad_im_hw_version_show(struct device *dev, struct device_attribute *attr,
char hw_ver[BFA_VERSION_LEN];

bfa_get_pci_chip_rev(&bfad->bfa, hw_ver);
- return snprintf(buf, PAGE_SIZE, "%s\n", hw_ver);
+ return sysfs_emit(buf, "%s\n", hw_ver);
}

static ssize_t
bfad_im_drv_version_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%s\n", BFAD_DRIVER_VERSION);
+ return sysfs_emit(buf, "%s\n", BFAD_DRIVER_VERSION);
}

static ssize_t
@@ -871,7 +871,7 @@ bfad_im_optionrom_version_show(struct device *dev,
char optrom_ver[BFA_VERSION_LEN];

bfa_get_adapter_optrom_ver(&bfad->bfa, optrom_ver);
- return snprintf(buf, PAGE_SIZE, "%s\n", optrom_ver);
+ return sysfs_emit(buf, "%s\n", optrom_ver);
}

static ssize_t
@@ -885,7 +885,7 @@ bfad_im_fw_version_show(struct device *dev, struct device_attribute *attr,
char fw_ver[BFA_VERSION_LEN];

bfa_get_adapter_fw_ver(&bfad->bfa, fw_ver);
- return snprintf(buf, PAGE_SIZE, "%s\n", fw_ver);
+ return sysfs_emit(buf, "%s\n", fw_ver);
}

static ssize_t
@@ -897,7 +897,7 @@ bfad_im_num_of_ports_show(struct device *dev, struct device_attribute *attr,
(struct bfad_im_port_s *) shost->hostdata[0];
struct bfad_s *bfad = im_port->bfad;

- return snprintf(buf, PAGE_SIZE, "%d\n",
+ return sysfs_emit(buf, "%d\n",
bfa_get_nports(&bfad->bfa));
}

@@ -905,7 +905,7 @@ static ssize_t
bfad_im_drv_name_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%s\n", BFAD_DRIVER_NAME);
+ return sysfs_emit(buf, "%s\n", BFAD_DRIVER_NAME);
}

static ssize_t
@@ -924,14 +924,14 @@ bfad_im_num_of_discovered_ports_show(struct device *dev,
rports = kcalloc(nrports, sizeof(struct bfa_rport_qualifier_s),
GFP_ATOMIC);
if (rports == NULL)
- return snprintf(buf, PAGE_SIZE, "Failed\n");
+ return sysfs_emit(buf, "Failed\n");

spin_lock_irqsave(&bfad->bfad_lock, flags);
bfa_fcs_lport_get_rport_quals(port->fcs_port, rports, &nrports);
spin_unlock_irqrestore(&bfad->bfad_lock, flags);
kfree(rports);

- return snprintf(buf, PAGE_SIZE, "%d\n", nrports);
+ return sysfs_emit(buf, "%d\n", nrports);
}

static DEVICE_ATTR(serial_number, S_IRUGO,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 70173389f6eb..52089538e9de 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2398,17 +2398,25 @@ static irqreturn_t cq_interrupt_v3_hw(int irq_no, void *p)
return IRQ_WAKE_THREAD;
}

+static void hisi_sas_v3_free_vectors(void *data)
+{
+ struct pci_dev *pdev = data;
+
+ pci_free_irq_vectors(pdev);
+}
+
static int interrupt_preinit_v3_hw(struct hisi_hba *hisi_hba)
{
int vectors;
int max_msi = HISI_SAS_MSI_COUNT_V3_HW, min_msi;
struct Scsi_Host *shost = hisi_hba->shost;
+ struct pci_dev *pdev = hisi_hba->pci_dev;
struct irq_affinity desc = {
.pre_vectors = BASE_VECTORS_V3_HW,
};

min_msi = MIN_AFFINE_VECTORS_V3_HW;
- vectors = pci_alloc_irq_vectors_affinity(hisi_hba->pci_dev,
+ vectors = pci_alloc_irq_vectors_affinity(pdev,
min_msi, max_msi,
PCI_IRQ_MSI |
PCI_IRQ_AFFINITY,
@@ -2420,6 +2428,7 @@ static int interrupt_preinit_v3_hw(struct hisi_hba *hisi_hba)
hisi_hba->cq_nvecs = vectors - BASE_VECTORS_V3_HW;
shost->nr_hw_queues = hisi_hba->cq_nvecs;

+ devm_add_action(&pdev->dev, hisi_sas_v3_free_vectors, pdev);
return 0;
}

@@ -3967,6 +3976,54 @@ static const struct file_operations debugfs_bist_phy_v3_hw_fops = {
.owner = THIS_MODULE,
};

+static ssize_t debugfs_bist_cnt_v3_hw_write(struct file *filp,
+ const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct seq_file *m = filp->private_data;
+ struct hisi_hba *hisi_hba = m->private;
+ unsigned int cnt;
+ int val;
+
+ if (hisi_hba->debugfs_bist_enable)
+ return -EPERM;
+
+ val = kstrtouint_from_user(buf, count, 0, &cnt);
+ if (val)
+ return val;
+
+ if (cnt)
+ return -EINVAL;
+
+ hisi_hba->debugfs_bist_cnt = 0;
+ return count;
+}
+
+static int debugfs_bist_cnt_v3_hw_show(struct seq_file *s, void *p)
+{
+ struct hisi_hba *hisi_hba = s->private;
+
+ seq_printf(s, "%u\n", hisi_hba->debugfs_bist_cnt);
+
+ return 0;
+}
+
+static int debugfs_bist_cnt_v3_hw_open(struct inode *inode,
+ struct file *filp)
+{
+ return single_open(filp, debugfs_bist_cnt_v3_hw_show,
+ inode->i_private);
+}
+
+static const struct file_operations debugfs_bist_cnt_v3_hw_ops = {
+ .open = debugfs_bist_cnt_v3_hw_open,
+ .read = seq_read,
+ .write = debugfs_bist_cnt_v3_hw_write,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
static const struct {
int value;
char *name;
@@ -4604,8 +4661,8 @@ static void debugfs_bist_init_v3_hw(struct hisi_hba *hisi_hba)
debugfs_create_file("phy_id", 0600, hisi_hba->debugfs_bist_dentry,
hisi_hba, &debugfs_bist_phy_v3_hw_fops);

- debugfs_create_u32("cnt", 0600, hisi_hba->debugfs_bist_dentry,
- &hisi_hba->debugfs_bist_cnt);
+ debugfs_create_file("cnt", 0600, hisi_hba->debugfs_bist_dentry,
+ hisi_hba, &debugfs_bist_cnt_v3_hw_ops);

debugfs_create_file("loopback_mode", 0600,
hisi_hba->debugfs_bist_dentry,
@@ -4769,7 +4826,7 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)

rc = scsi_add_host(shost, dev);
if (rc)
- goto err_out_free_irq_vectors;
+ goto err_out_debugfs;

rc = sas_register_ha(sha);
if (rc)
@@ -4800,8 +4857,6 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
sas_unregister_ha(sha);
err_out_register_ha:
scsi_remove_host(shost);
-err_out_free_irq_vectors:
- pci_free_irq_vectors(pdev);
err_out_debugfs:
debugfs_exit_v3_hw(hisi_hba);
err_out_ha:
@@ -4825,7 +4880,6 @@ hisi_sas_v3_destroy_irqs(struct pci_dev *pdev, struct hisi_hba *hisi_hba)

devm_free_irq(&pdev->dev, pci_irq_vector(pdev, nr), cq);
}
- pci_free_irq_vectors(pdev);
}

static void hisi_sas_v3_remove(struct pci_dev *pdev)
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 841000445b9a..aa223db4cf53 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -1701,6 +1701,7 @@ static void fc_exch_abts_resp(struct fc_exch *ep, struct fc_frame *fp)
if (cancel_delayed_work_sync(&ep->timeout_work)) {
FC_EXCH_DBG(ep, "Exchange timer canceled due to ABTS response\n");
fc_exch_release(ep); /* release from pending timer hold */
+ return;
}

spin_lock_bh(&ep->ex_lock);
diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h
index fc4eaf6d1e47..d892ade421bf 100644
--- a/drivers/scsi/mpi3mr/mpi3mr.h
+++ b/drivers/scsi/mpi3mr/mpi3mr.h
@@ -866,6 +866,8 @@ struct mpi3mr_ioc {
* @send_ack: Event acknowledgment required or not
* @process_evt: Bottomhalf processing required or not
* @evt_ctx: Event context to send in Ack
+ * @pending_at_sml: waiting for device add/remove API to complete
+ * @discard: discard this event
* @ref_count: kref count
* @event_data: Actual MPI3 event data
*/
@@ -877,6 +879,8 @@ struct mpi3mr_fwevt {
bool send_ack;
bool process_evt;
u32 evt_ctx;
+ bool pending_at_sml;
+ bool discard;
struct kref ref_count;
char event_data[0] __aligned(4);
};
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 15bdc21ead66..e44868230197 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -1520,7 +1520,7 @@ static void mpi3mr_free_op_req_q_segments(struct mpi3mr_ioc *mrioc, u16 q_idx)
MPI3MR_MAX_SEG_LIST_SIZE,
mrioc->req_qinfo[q_idx].q_segment_list,
mrioc->req_qinfo[q_idx].q_segment_list_dma);
- mrioc->op_reply_qinfo[q_idx].q_segment_list = NULL;
+ mrioc->req_qinfo[q_idx].q_segment_list = NULL;
}
} else
size = mrioc->req_qinfo[q_idx].segment_qd *
@@ -4353,8 +4353,8 @@ int mpi3mr_soft_reset_handler(struct mpi3mr_ioc *mrioc,
memset(mrioc->devrem_bitmap, 0, mrioc->devrem_bitmap_sz);
memset(mrioc->removepend_bitmap, 0, mrioc->dev_handle_bitmap_sz);
memset(mrioc->evtack_cmds_bitmap, 0, mrioc->evtack_cmds_bitmap_sz);
- mpi3mr_cleanup_fwevt_list(mrioc);
mpi3mr_flush_host_io(mrioc);
+ mpi3mr_cleanup_fwevt_list(mrioc);
mpi3mr_invalidate_devhandles(mrioc);
if (mrioc->prepare_for_reset) {
mrioc->prepare_for_reset = 0;
diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
index 284117da9086..f7893de35b26 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -285,6 +285,35 @@ static struct mpi3mr_fwevt *mpi3mr_dequeue_fwevt(
return fwevt;
}

+/**
+ * mpi3mr_cancel_work - cancel firmware event
+ * @fwevt: fwevt object which needs to be canceled
+ *
+ * Return: Nothing.
+ */
+static void mpi3mr_cancel_work(struct mpi3mr_fwevt *fwevt)
+{
+ /*
+ * Wait on the fwevt to complete. If this returns 1, then
+ * the event was never executed.
+ *
+ * If it did execute, we wait for it to finish, and the put will
+ * happen from mpi3mr_process_fwevt()
+ */
+ if (cancel_work_sync(&fwevt->work)) {
+ /*
+ * Put fwevt reference count after
+ * dequeuing it from worker queue
+ */
+ mpi3mr_fwevt_put(fwevt);
+ /*
+ * Put fwevt reference count to neutralize
+ * kref_init increment
+ */
+ mpi3mr_fwevt_put(fwevt);
+ }
+}
+
/**
* mpi3mr_cleanup_fwevt_list - Cleanup firmware event list
* @mrioc: Adapter instance reference
@@ -302,28 +331,25 @@ void mpi3mr_cleanup_fwevt_list(struct mpi3mr_ioc *mrioc)
!mrioc->fwevt_worker_thread)
return;

- while ((fwevt = mpi3mr_dequeue_fwevt(mrioc)) ||
- (fwevt = mrioc->current_event)) {
+ while ((fwevt = mpi3mr_dequeue_fwevt(mrioc)))
+ mpi3mr_cancel_work(fwevt);
+
+ if (mrioc->current_event) {
+ fwevt = mrioc->current_event;
/*
- * Wait on the fwevt to complete. If this returns 1, then
- * the event was never executed, and we need a put for the
- * reference the work had on the fwevt.
- *
- * If it did execute, we wait for it to finish, and the put will
- * happen from mpi3mr_process_fwevt()
+ * Don't call cancel_work_sync() API for the
+ * fwevt work if the controller reset is
+ * get called as part of processing the
+ * same fwevt work (or) when worker thread is
+ * waiting for device add/remove APIs to complete.
+ * Otherwise we will see deadlock.
*/
- if (cancel_work_sync(&fwevt->work)) {
- /*
- * Put fwevt reference count after
- * dequeuing it from worker queue
- */
- mpi3mr_fwevt_put(fwevt);
- /*
- * Put fwevt reference count to neutralize
- * kref_init increment
- */
- mpi3mr_fwevt_put(fwevt);
+ if (current_work() == &fwevt->work || fwevt->pending_at_sml) {
+ fwevt->discard = 1;
+ return;
}
+
+ mpi3mr_cancel_work(fwevt);
}
}

@@ -690,6 +716,24 @@ static struct mpi3mr_tgt_dev *__mpi3mr_get_tgtdev_from_tgtpriv(
return tgtdev;
}

+/**
+ * mpi3mr_print_device_event_notice - print notice related to post processing of
+ * device event after controller reset.
+ *
+ * @mrioc: Adapter instance reference
+ * @device_add: true for device add event and false for device removal event
+ *
+ * Return: None.
+ */
+static void mpi3mr_print_device_event_notice(struct mpi3mr_ioc *mrioc,
+ bool device_add)
+{
+ ioc_notice(mrioc, "Device %s was in progress before the reset and\n",
+ (device_add ? "addition" : "removal"));
+ ioc_notice(mrioc, "completed after reset, verify whether the exposed devices\n");
+ ioc_notice(mrioc, "are matched with attached devices for correctness\n");
+}
+
/**
* mpi3mr_remove_tgtdev_from_host - Remove dev from upper layers
* @mrioc: Adapter instance reference
@@ -714,8 +758,17 @@ static void mpi3mr_remove_tgtdev_from_host(struct mpi3mr_ioc *mrioc,
}

if (tgtdev->starget) {
+ if (mrioc->current_event)
+ mrioc->current_event->pending_at_sml = 1;
scsi_remove_target(&tgtdev->starget->dev);
tgtdev->host_exposed = 0;
+ if (mrioc->current_event) {
+ mrioc->current_event->pending_at_sml = 0;
+ if (mrioc->current_event->discard) {
+ mpi3mr_print_device_event_notice(mrioc, false);
+ return;
+ }
+ }
}
ioc_info(mrioc, "%s :Removed handle(0x%04x), wwid(0x%016llx)\n",
__func__, tgtdev->dev_handle, (unsigned long long)tgtdev->wwid);
@@ -749,11 +802,20 @@ static int mpi3mr_report_tgtdev_to_host(struct mpi3mr_ioc *mrioc,
}
if (!tgtdev->host_exposed && !mrioc->reset_in_progress) {
tgtdev->host_exposed = 1;
+ if (mrioc->current_event)
+ mrioc->current_event->pending_at_sml = 1;
scsi_scan_target(&mrioc->shost->shost_gendev, 0,
tgtdev->perst_id,
SCAN_WILD_CARD, SCSI_SCAN_INITIAL);
if (!tgtdev->starget)
tgtdev->host_exposed = 0;
+ if (mrioc->current_event) {
+ mrioc->current_event->pending_at_sml = 0;
+ if (mrioc->current_event->discard) {
+ mpi3mr_print_device_event_notice(mrioc, true);
+ goto out;
+ }
+ }
}
out:
if (tgtdev)
@@ -1193,6 +1255,8 @@ static void mpi3mr_sastopochg_evt_bh(struct mpi3mr_ioc *mrioc,
mpi3mr_sastopochg_evt_debug(mrioc, event_data);

for (i = 0; i < event_data->num_entries; i++) {
+ if (fwevt->discard)
+ return;
handle = le16_to_cpu(event_data->phy_entry[i].attached_dev_handle);
if (!handle)
continue;
@@ -1324,6 +1388,8 @@ static void mpi3mr_pcietopochg_evt_bh(struct mpi3mr_ioc *mrioc,
mpi3mr_pcietopochg_evt_debug(mrioc, event_data);

for (i = 0; i < event_data->num_entries; i++) {
+ if (fwevt->discard)
+ return;
handle =
le16_to_cpu(event_data->port_entry[i].attached_dev_handle);
if (!handle)
@@ -1362,8 +1428,8 @@ static void mpi3mr_pcietopochg_evt_bh(struct mpi3mr_ioc *mrioc,
static void mpi3mr_fwevt_bh(struct mpi3mr_ioc *mrioc,
struct mpi3mr_fwevt *fwevt)
{
- mrioc->current_event = fwevt;
mpi3mr_fwevt_del_from_list(mrioc, fwevt);
+ mrioc->current_event = fwevt;

if (mrioc->stop_drv_processing)
goto out;
@@ -2551,6 +2617,8 @@ void mpi3mr_process_op_reply_desc(struct mpi3mr_ioc *mrioc,
scmd->result = DID_OK << 16;
goto out_success;
}
+
+ scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_count);
if (ioc_status == MPI3_IOCSTATUS_SCSI_DATA_UNDERRUN &&
xfer_count == 0 && (scsi_status == MPI3_SCSI_STATUS_BUSY ||
scsi_status == MPI3_SCSI_STATUS_RESERVATION_CONFLICT ||
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 00792767c620..7e476f50935b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -11035,6 +11035,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
{
struct _sas_port *mpt3sas_port, *next;
unsigned long flags;
+ int port_id;

/* remove sibling ports attached to this expander */
list_for_each_entry_safe(mpt3sas_port, next,
@@ -11055,6 +11056,8 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
mpt3sas_port->hba_port);
}

+ port_id = sas_expander->port->port_id;
+
mpt3sas_transport_port_remove(ioc, sas_expander->sas_address,
sas_expander->sas_address_parent, sas_expander->port);

@@ -11062,7 +11065,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
"expander_remove: handle(0x%04x), sas_addr(0x%016llx), port:%d\n",
sas_expander->handle, (unsigned long long)
sas_expander->sas_address,
- sas_expander->port->port_id);
+ port_id);

spin_lock_irqsave(&ioc->sas_node_lock, flags);
list_del(&sas_expander->list);
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index dcae2d4464f9..44df7c03aab8 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -696,7 +696,7 @@ static struct pci_driver mvs_pci_driver = {
static ssize_t driver_version_show(struct device *cdev,
struct device_attribute *attr, char *buffer)
{
- return snprintf(buffer, PAGE_SIZE, "%s\n", DRV_VERSION);
+ return sysfs_emit(buffer, "%s\n", DRV_VERSION);
}

static DEVICE_ATTR_RO(driver_version);
@@ -744,7 +744,7 @@ static ssize_t interrupt_coalescing_store(struct device *cdev,
static ssize_t interrupt_coalescing_show(struct device *cdev,
struct device_attribute *attr, char *buffer)
{
- return snprintf(buffer, PAGE_SIZE, "%d\n", interrupt_coalescing);
+ return sysfs_emit(buffer, "%d\n", interrupt_coalescing);
}

static DEVICE_ATTR_RW(interrupt_coalescing);
diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index d853e8d0195a..27ead825c2bb 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -1522,7 +1522,6 @@ void pm8001_work_fn(struct work_struct *work)
case IO_XFER_ERROR_BREAK:
{ /* This one stashes the sas_task instead */
struct sas_task *t = (struct sas_task *)pm8001_dev;
- u32 tag;
struct pm8001_ccb_info *ccb;
struct pm8001_hba_info *pm8001_ha = pw->pm8001_ha;
unsigned long flags, flags1;
@@ -1544,8 +1543,8 @@ void pm8001_work_fn(struct work_struct *work)
/* Search for a possible ccb that matches the task */
for (i = 0; ccb = NULL, i < PM8001_MAX_CCB; i++) {
ccb = &pm8001_ha->ccb_info[i];
- tag = ccb->ccb_tag;
- if ((tag != 0xFFFFFFFF) && (ccb->task == t))
+ if ((ccb->ccb_tag != PM8001_INVALID_TAG) &&
+ (ccb->task == t))
break;
}
if (!ccb) {
@@ -1567,11 +1566,11 @@ void pm8001_work_fn(struct work_struct *work)
spin_unlock_irqrestore(&t->task_state_lock, flags1);
pm8001_dbg(pm8001_ha, FAIL, "task 0x%p done with event 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n",
t, pw->handler, ts->resp, ts->stat);
- pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
+ pm8001_ccb_task_free(pm8001_ha, t, ccb, ccb->ccb_tag);
spin_unlock_irqrestore(&pm8001_ha->lock, flags);
} else {
spin_unlock_irqrestore(&t->task_state_lock, flags1);
- pm8001_ccb_task_free(pm8001_ha, t, ccb, tag);
+ pm8001_ccb_task_free(pm8001_ha, t, ccb, ccb->ccb_tag);
mb();/* in order to force CPU ordering */
spin_unlock_irqrestore(&pm8001_ha->lock, flags);
t->task_done(t);
@@ -1580,7 +1579,6 @@ void pm8001_work_fn(struct work_struct *work)
case IO_XFER_OPEN_RETRY_TIMEOUT:
{ /* This one stashes the sas_task instead */
struct sas_task *t = (struct sas_task *)pm8001_dev;
- u32 tag;
struct pm8001_ccb_info *ccb;
struct pm8001_hba_info *pm8001_ha = pw->pm8001_ha;
unsigned long flags, flags1;
@@ -1614,8 +1612,8 @@ void pm8001_work_fn(struct work_struct *work)
/* Search for a possible ccb that matches the task */
for (i = 0; ccb = NULL, i < PM8001_MAX_CCB; i++) {
ccb = &pm8001_ha->ccb_info[i];
- tag = ccb->ccb_tag;
- if ((tag != 0xFFFFFFFF) && (ccb->task == t))
+ if ((ccb->ccb_tag != PM8001_INVALID_TAG) &&
+ (ccb->task == t))
break;
}
if (!ccb) {
@@ -1686,19 +1684,13 @@ void pm8001_work_fn(struct work_struct *work)
struct task_status_struct *ts;
struct sas_task *task;
int i;
- u32 tag, device_id;
+ u32 device_id;

for (i = 0; ccb = NULL, i < PM8001_MAX_CCB; i++) {
ccb = &pm8001_ha->ccb_info[i];
task = ccb->task;
ts = &task->task_status;
- tag = ccb->ccb_tag;
- /* check if tag is NULL */
- if (!tag) {
- pm8001_dbg(pm8001_ha, FAIL,
- "tag Null\n");
- continue;
- }
+
if (task != NULL) {
dev = task->dev;
if (!dev) {
@@ -1707,10 +1699,11 @@ void pm8001_work_fn(struct work_struct *work)
continue;
}
/*complete sas task and update to top layer */
- pm8001_ccb_task_free(pm8001_ha, task, ccb, tag);
+ pm8001_ccb_task_free(pm8001_ha, task, ccb,
+ ccb->ccb_tag);
ts->resp = SAS_TASK_COMPLETE;
task->task_done(task);
- } else if (tag != 0xFFFFFFFF) {
+ } else if (ccb->ccb_tag != PM8001_INVALID_TAG) {
/* complete the internal commands/non-sas task */
pm8001_dev = ccb->device;
if (pm8001_dev->dcompletion) {
@@ -1718,7 +1711,7 @@ void pm8001_work_fn(struct work_struct *work)
pm8001_dev->dcompletion = NULL;
}
complete(pm8001_ha->nvmd_completion);
- pm8001_tag_free(pm8001_ha, tag);
+ pm8001_tag_free(pm8001_ha, ccb->ccb_tag);
}
}
/* Deregister all the device ids */
@@ -1772,7 +1765,6 @@ static void pm8001_send_abort_all(struct pm8001_hba_info *pm8001_ha,
}

task = sas_alloc_slow_task(GFP_ATOMIC);
-
if (!task) {
pm8001_dbg(pm8001_ha, FAIL, "cannot allocate task\n");
return;
@@ -1781,8 +1773,10 @@ static void pm8001_send_abort_all(struct pm8001_hba_info *pm8001_ha,
task->task_done = pm8001_task_done;

res = pm8001_tag_alloc(pm8001_ha, &ccb_tag);
- if (res)
+ if (res) {
+ sas_free_task(task);
return;
+ }

ccb = &pm8001_ha->ccb_info[ccb_tag];
ccb->device = pm8001_ha_dev;
@@ -1799,8 +1793,10 @@ static void pm8001_send_abort_all(struct pm8001_hba_info *pm8001_ha,

ret = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &task_abort,
sizeof(task_abort), 0);
- if (ret)
+ if (ret) {
+ sas_free_task(task);
pm8001_tag_free(pm8001_ha, ccb_tag);
+ }

}

@@ -2316,11 +2312,6 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
param = le32_to_cpu(psataPayload->param);
tag = le32_to_cpu(psataPayload->tag);

- if (!tag) {
- pm8001_dbg(pm8001_ha, FAIL, "tag null\n");
- return;
- }
-
ccb = &pm8001_ha->ccb_info[tag];
t = ccb->task;
pm8001_dev = ccb->device;
@@ -3056,7 +3047,7 @@ void pm8001_mpi_set_dev_state_resp(struct pm8001_hba_info *pm8001_ha,
device_id, pds, nds, status);
complete(pm8001_dev->setds_completion);
ccb->task = NULL;
- ccb->ccb_tag = 0xFFFFFFFF;
+ ccb->ccb_tag = PM8001_INVALID_TAG;
pm8001_tag_free(pm8001_ha, tag);
}

@@ -3074,7 +3065,7 @@ void pm8001_mpi_set_nvmd_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
dlen_status);
}
ccb->task = NULL;
- ccb->ccb_tag = 0xFFFFFFFF;
+ ccb->ccb_tag = PM8001_INVALID_TAG;
pm8001_tag_free(pm8001_ha, tag);
}

@@ -3101,7 +3092,7 @@ pm8001_mpi_get_nvmd_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
* freed by requesting path anywhere.
*/
ccb->task = NULL;
- ccb->ccb_tag = 0xFFFFFFFF;
+ ccb->ccb_tag = PM8001_INVALID_TAG;
pm8001_tag_free(pm8001_ha, tag);
return;
}
@@ -3147,7 +3138,7 @@ pm8001_mpi_get_nvmd_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
complete(pm8001_ha->nvmd_completion);
pm8001_dbg(pm8001_ha, MSG, "Get nvmd data complete!\n");
ccb->task = NULL;
- ccb->ccb_tag = 0xFFFFFFFF;
+ ccb->ccb_tag = PM8001_INVALID_TAG;
pm8001_tag_free(pm8001_ha, tag);
}

@@ -3560,7 +3551,7 @@ int pm8001_mpi_reg_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
}
complete(pm8001_dev->dcompletion);
ccb->task = NULL;
- ccb->ccb_tag = 0xFFFFFFFF;
+ ccb->ccb_tag = PM8001_INVALID_TAG;
pm8001_tag_free(pm8001_ha, htag);
return 0;
}
@@ -3632,7 +3623,7 @@ int pm8001_mpi_fw_flash_update_resp(struct pm8001_hba_info *pm8001_ha,
}
kfree(ccb->fw_control_context);
ccb->task = NULL;
- ccb->ccb_tag = 0xFFFFFFFF;
+ ccb->ccb_tag = PM8001_INVALID_TAG;
pm8001_tag_free(pm8001_ha, tag);
complete(pm8001_ha->nvmd_completion);
return 0;
@@ -3668,10 +3659,6 @@ int pm8001_mpi_task_abort_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)

status = le32_to_cpu(pPayload->status);
tag = le32_to_cpu(pPayload->tag);
- if (!tag) {
- pm8001_dbg(pm8001_ha, FAIL, " TAG NULL. RETURNING !!!\n");
- return -1;
- }

scp = le32_to_cpu(pPayload->scp);
ccb = &pm8001_ha->ccb_info[tag];
@@ -3706,12 +3693,11 @@ int pm8001_mpi_task_abort_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
mb();

if (pm8001_dev->id & NCQ_ABORT_ALL_FLAG) {
- pm8001_tag_free(pm8001_ha, tag);
sas_free_task(t);
- /* clear the flag */
- pm8001_dev->id &= 0xBFFFFFFF;
- } else
+ pm8001_dev->id &= ~NCQ_ABORT_ALL_FLAG;
+ } else {
t->task_done(t);
+ }

return 0;
}
@@ -4479,6 +4465,9 @@ static int pm8001_chip_reg_dev_req(struct pm8001_hba_info *pm8001_ha,
SAS_ADDR_SIZE);
rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
sizeof(payload), 0);
+ if (rc)
+ pm8001_tag_free(pm8001_ha, tag);
+
return rc;
}

@@ -4891,6 +4880,11 @@ pm8001_chip_fw_flash_update_req(struct pm8001_hba_info *pm8001_ha,
ccb->ccb_tag = tag;
rc = pm8001_chip_fw_flash_update_build(pm8001_ha, &flash_update_info,
tag);
+ if (rc) {
+ kfree(fw_control_context);
+ pm8001_tag_free(pm8001_ha, tag);
+ }
+
return rc;
}

@@ -4995,6 +4989,9 @@ pm8001_chip_set_dev_state_req(struct pm8001_hba_info *pm8001_ha,
payload.nds = cpu_to_le32(state);
rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
sizeof(payload), 0);
+ if (rc)
+ pm8001_tag_free(pm8001_ha, tag);
+
return rc;

}
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index d8a2121cb8d9..d2a2593f669d 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -1216,10 +1216,11 @@ pm8001_init_ccb_tag(struct pm8001_hba_info *pm8001_ha, struct Scsi_Host *shost,
goto err_out;
}
pm8001_ha->ccb_info[i].task = NULL;
- pm8001_ha->ccb_info[i].ccb_tag = 0xffffffff;
+ pm8001_ha->ccb_info[i].ccb_tag = PM8001_INVALID_TAG;
pm8001_ha->ccb_info[i].device = NULL;
++pm8001_ha->tags_num;
}
+
return 0;

err_out_noccb:
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 32edda3e55c6..b68c8400ca15 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -567,7 +567,7 @@ void pm8001_ccb_task_free(struct pm8001_hba_info *pm8001_ha,

task->lldd_task = NULL;
ccb->task = NULL;
- ccb->ccb_tag = 0xFFFFFFFF;
+ ccb->ccb_tag = PM8001_INVALID_TAG;
ccb->open_retry = 0;
pm8001_tag_free(pm8001_ha, ccb_idx);
}
@@ -847,10 +847,10 @@ pm8001_exec_internal_task_abort(struct pm8001_hba_info *pm8001_ha,

res = PM8001_CHIP_DISP->task_abort(pm8001_ha,
pm8001_dev, flag, task_tag, ccb_tag);
-
if (res) {
del_timer(&task->slow_task->timer);
pm8001_dbg(pm8001_ha, FAIL, "Executing internal task failed\n");
+ pm8001_tag_free(pm8001_ha, ccb_tag);
goto ex_err;
}
wait_for_completion(&task->slow_task->completion);
@@ -952,9 +952,11 @@ void pm8001_open_reject_retry(
struct task_status_struct *ts;
struct pm8001_device *pm8001_dev;
unsigned long flags1;
- u32 tag;
struct pm8001_ccb_info *ccb = &pm8001_ha->ccb_info[i];

+ if (ccb->ccb_tag == PM8001_INVALID_TAG)
+ continue;
+
pm8001_dev = ccb->device;
if (!pm8001_dev || (pm8001_dev->dev_type == SAS_PHY_UNUSED))
continue;
@@ -966,9 +968,6 @@ void pm8001_open_reject_retry(
continue;
} else if (pm8001_dev != device_to_close)
continue;
- tag = ccb->ccb_tag;
- if (!tag || (tag == 0xFFFFFFFF))
- continue;
task = ccb->task;
if (!task || !task->task_done)
continue;
@@ -989,11 +988,11 @@ void pm8001_open_reject_retry(
& SAS_TASK_STATE_ABORTED))) {
spin_unlock_irqrestore(&task->task_state_lock,
flags1);
- pm8001_ccb_task_free(pm8001_ha, task, ccb, tag);
+ pm8001_ccb_task_free(pm8001_ha, task, ccb, ccb->ccb_tag);
} else {
spin_unlock_irqrestore(&task->task_state_lock,
flags1);
- pm8001_ccb_task_free(pm8001_ha, task, ccb, tag);
+ pm8001_ccb_task_free(pm8001_ha, task, ccb, ccb->ccb_tag);
mb();/* in order to force CPU ordering */
spin_unlock_irqrestore(&pm8001_ha->lock, flags);
task->task_done(task);
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index a17da1cebce1..1791cdf30276 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -738,6 +738,8 @@ void pm8001_free_dev(struct pm8001_device *pm8001_dev);
/* ctl shared API */
extern const struct attribute_group *pm8001_host_groups[];

+#define PM8001_INVALID_TAG ((u32)-1)
+
static inline void
pm8001_ccb_task_free_done(struct pm8001_hba_info *pm8001_ha,
struct sas_task *task, struct pm8001_ccb_info *ccb,
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index 908dbac20b48..55163469030d 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -67,18 +67,16 @@ int pm80xx_bar4_shift(struct pm8001_hba_info *pm8001_ha, u32 shift_value)
}

static void pm80xx_pci_mem_copy(struct pm8001_hba_info *pm8001_ha, u32 soffset,
- const void *destination,
+ __le32 *destination,
u32 dw_count, u32 bus_base_number)
{
u32 index, value, offset;
- u32 *destination1;
- destination1 = (u32 *)destination;

- for (index = 0; index < dw_count; index += 4, destination1++) {
+ for (index = 0; index < dw_count; index += 4, destination++) {
offset = (soffset + index);
if (offset < (64 * 1024)) {
value = pm8001_cr32(pm8001_ha, bus_base_number, offset);
- *destination1 = cpu_to_le32(value);
+ *destination = cpu_to_le32(value);
}
}
return;
@@ -2406,11 +2404,6 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha,
param = le32_to_cpu(psataPayload->param);
tag = le32_to_cpu(psataPayload->tag);

- if (!tag) {
- pm8001_dbg(pm8001_ha, FAIL, "tag null\n");
- return;
- }
-
ccb = &pm8001_ha->ccb_info[tag];
t = ccb->task;
pm8001_dev = ccb->device;
@@ -4927,8 +4920,13 @@ static int pm80xx_chip_phy_ctl_req(struct pm8001_hba_info *pm8001_ha,
payload.tag = cpu_to_le32(tag);
payload.phyop_phyid =
cpu_to_le32(((phy_op & 0xFF) << 8) | (phyId & 0xFF));
- return pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
- sizeof(payload), 0);
+
+ rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &payload,
+ sizeof(payload), 0);
+ if (rc)
+ pm8001_tag_free(pm8001_ha, tag);
+
+ return rc;
}

static u32 pm80xx_chip_is_our_interrupt(struct pm8001_hba_info *pm8001_ha)
diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c
index 1f8f80b2dbfc..a9f8de5e9639 100644
--- a/drivers/scsi/scsi_logging.c
+++ b/drivers/scsi/scsi_logging.c
@@ -30,7 +30,7 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd)
{
struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd);

- if (!rq->q->disk)
+ if (!rq->q || !rq->q->disk)
return NULL;
return rq->q->disk->disk_name;
}
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index f4e6c68ac99e..2ef78083f1ef 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -223,6 +223,8 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
int ret;
struct sbitmap sb_backup;

+ depth = min_t(unsigned int, depth, scsi_device_max_queue_depth(sdev));
+
/*
* realloc if new shift is calculated, which is caused by setting
* up one new default queue depth after calling ->slave_configure
@@ -245,6 +247,9 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
scsi_device_max_queue_depth(sdev),
new_shift, GFP_KERNEL,
sdev->request_queue->node, false, true);
+ if (!ret)
+ sbitmap_resize(&sdev->budget_map, depth);
+
if (need_free) {
if (ret)
sdev->budget_map = sb_backup;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 66056806159a..8b5d2a4076c2 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3320,6 +3320,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
sd_read_block_limits(sdkp);
sd_read_block_characteristics(sdkp);
sd_zbc_read_zones(sdkp, buffer);
+ sd_read_cpr(sdkp);
}

sd_print_capacity(sdkp, old_capacity);
@@ -3329,7 +3330,6 @@ static int sd_revalidate_disk(struct gendisk *disk)
sd_read_app_tag_own(sdkp, buffer);
sd_read_write_same(sdkp, buffer);
sd_read_security(sdkp, buffer);
- sd_read_cpr(sdkp);
}

/*
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index f0897d587454..f3749e508673 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -2513,17 +2513,15 @@ static void pqi_remove_all_scsi_devices(struct pqi_ctrl_info *ctrl_info)
struct pqi_scsi_dev *device;
struct pqi_scsi_dev *next;

- spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
-
list_for_each_entry_safe(device, next, &ctrl_info->scsi_device_list,
scsi_device_list_entry) {
if (pqi_is_device_added(device))
pqi_remove_device(ctrl_info, device);
+ spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
list_del(&device->scsi_device_list_entry);
pqi_free_device(device);
+ spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
}
-
- spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
}

static int pqi_scan_scsi_devices(struct pqi_ctrl_info *ctrl_info)
@@ -7857,6 +7855,21 @@ static int pqi_force_sis_mode(struct pqi_ctrl_info *ctrl_info)
return pqi_revert_to_sis_mode(ctrl_info);
}

+static void pqi_perform_lockup_action(void)
+{
+ switch (pqi_lockup_action) {
+ case PANIC:
+ panic("FATAL: Smart Family Controller lockup detected");
+ break;
+ case REBOOT:
+ emergency_restart();
+ break;
+ case NONE:
+ default:
+ break;
+ }
+}
+
static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
{
int rc;
@@ -7881,8 +7894,15 @@ static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info)
* commands.
*/
rc = sis_wait_for_ctrl_ready(ctrl_info);
- if (rc)
+ if (rc) {
+ if (reset_devices) {
+ dev_err(&ctrl_info->pci_dev->dev,
+ "kdump init failed with error %d\n", rc);
+ pqi_lockup_action = REBOOT;
+ pqi_perform_lockup_action();
+ }
return rc;
+ }

/*
* Get the controller properties. This allows us to determine
@@ -8607,21 +8627,6 @@ static int pqi_ofa_ctrl_restart(struct pqi_ctrl_info *ctrl_info, unsigned int de
return pqi_ctrl_init_resume(ctrl_info);
}

-static void pqi_perform_lockup_action(void)
-{
- switch (pqi_lockup_action) {
- case PANIC:
- panic("FATAL: Smart Family Controller lockup detected");
- break;
- case REBOOT:
- emergency_restart();
- break;
- case NONE:
- default:
- break;
- }
-}
-
static struct pqi_raid_error_info pqi_ctrl_offline_raid_error_info = {
.data_out_result = PQI_DATA_IN_OUT_HARDWARE_ERROR,
.status = SAM_STAT_CHECK_CONDITION,
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index f925b1f1f9ad..a0beb11abdc9 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -578,7 +578,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,

scsi_autopm_get_device(sdev);

- if (ret != CDROMCLOSETRAY && ret != CDROMEJECT) {
+ if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) {
ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg);
if (ret != -ENOSYS)
goto put;
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index f76692053ca1..e892b9feffb1 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -428,6 +428,12 @@ static int ufs_intel_adl_init(struct ufs_hba *hba)
return ufs_intel_common_init(hba);
}

+static int ufs_intel_mtl_init(struct ufs_hba *hba)
+{
+ hba->caps |= UFSHCD_CAP_CRYPTO | UFSHCD_CAP_WB_EN;
+ return ufs_intel_common_init(hba);
+}
+
static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = {
.name = "intel-pci",
.init = ufs_intel_common_init,
@@ -465,6 +471,16 @@ static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = {
.device_reset = ufs_intel_device_reset,
};

+static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = {
+ .name = "intel-pci",
+ .init = ufs_intel_mtl_init,
+ .exit = ufs_intel_common_exit,
+ .hce_enable_notify = ufs_intel_hce_enable_notify,
+ .link_startup_notify = ufs_intel_link_startup_notify,
+ .resume = ufs_intel_resume,
+ .device_reset = ufs_intel_device_reset,
+};
+
#ifdef CONFIG_PM_SLEEP
static int ufshcd_pci_restore(struct device *dev)
{
@@ -579,6 +595,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops },
{ PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops },
{ PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops },
+ { PCI_VDEVICE(INTEL, 0x7E47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops },
{ } /* terminate list */
};

diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index 2d36a0715fca..b34feba1f53d 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -869,12 +869,6 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb)
struct ufshpb_region *rgn, *victim_rgn = NULL;

list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) {
- if (!rgn) {
- dev_err(&hpb->sdev_ufs_lu->sdev_dev,
- "%s: no region allocated\n",
- __func__);
- return NULL;
- }
if (ufshpb_check_srgns_issue_state(hpb, rgn))
continue;

@@ -890,6 +884,11 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb)
break;
}

+ if (!victim_rgn)
+ dev_err(&hpb->sdev_ufs_lu->sdev_dev,
+ "%s: no region allocated\n",
+ __func__);
+
return victim_rgn;
}

diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c
index 27b9e2baab1a..7acf9193a9e8 100644
--- a/drivers/scsi/zorro7xx.c
+++ b/drivers/scsi/zorro7xx.c
@@ -159,6 +159,8 @@ static void zorro7xx_remove_one(struct zorro_dev *z)
scsi_remove_host(host);

NCR_700_release(host);
+ if (host->base > 0x01000000)
+ iounmap(hostdata->base);
kfree(hostdata);
free_irq(host->irq, host);
zorro_release_device(z);
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 86c76211b3d3..cad2d55dcd3d 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -1205,7 +1205,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
addr = op->addr.val;
len = op->data.nbytes;

- if (bcm_qspi_bspi_ver_three(qspi) == true) {
+ if (has_bspi(qspi) && bcm_qspi_bspi_ver_three(qspi) == true) {
/*
* The address coming into this function is a raw flash offset.
* But for BSPI <= V3, we need to convert it to a remapped BSPI
@@ -1224,7 +1224,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
len < 4)
mspi_read = true;

- if (mspi_read)
+ if (!has_bspi(qspi) || mspi_read)
return bcm_qspi_mspi_exec_mem_op(spi, op);

ret = bcm_qspi_bspi_set_mode(qspi, op, 0);
diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c
index fe82f3575df4..24ec1c83f379 100644
--- a/drivers/spi/spi-rpc-if.c
+++ b/drivers/spi/spi-rpc-if.c
@@ -158,14 +158,18 @@ static int rpcif_spi_probe(struct platform_device *pdev)

error = rpcif_hw_init(rpc, false);
if (error)
- return error;
+ goto out_disable_rpm;

error = spi_register_controller(ctlr);
if (error) {
dev_err(&pdev->dev, "spi_register_controller failed\n");
- rpcif_disable_rpm(rpc);
+ goto out_disable_rpm;
}

+ return 0;
+
+out_disable_rpm:
+ rpcif_disable_rpm(rpc);
return error;
}

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index d96082dc3340..bbf977a0d2c5 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1149,11 +1149,15 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)

if (ctlr->dma_tx)
tx_dev = ctlr->dma_tx->device->dev;
+ else if (ctlr->dma_map_dev)
+ tx_dev = ctlr->dma_map_dev;
else
tx_dev = ctlr->dev.parent;

if (ctlr->dma_rx)
rx_dev = ctlr->dma_rx->device->dev;
+ else if (ctlr->dma_map_dev)
+ rx_dev = ctlr->dma_map_dev;
else
rx_dev = ctlr->dev.parent;

diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 3a2e4582db8e..a3e3c9f9aa18 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -1209,6 +1209,9 @@ int vchiq_dump_platform_instances(void *dump_context)
int len;
int i;

+ if (!state)
+ return -ENOTCONN;
+
/*
* There is no list of instances, so instead scan all services,
* marking those that have been dumped.
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
index 7fe20d4b7ba2..b7295236671c 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
@@ -2306,6 +2306,9 @@ void vchiq_msg_queue_push(unsigned int handle, struct vchiq_header *header)
struct vchiq_service *service = find_service_by_handle(handle);
int pos;

+ if (!service)
+ return;
+
while (service->msg_queue_write == service->msg_queue_read +
VCHIQ_MAX_SLOTS) {
if (wait_for_completion_interruptible(&service->msg_queue_pop))
@@ -2326,6 +2329,9 @@ struct vchiq_header *vchiq_msg_hold(unsigned int handle)
struct vchiq_header *header;
int pos;

+ if (!service)
+ return NULL;
+
if (service->msg_queue_write == service->msg_queue_read)
return NULL;

diff --git a/drivers/staging/wfx/bus_sdio.c b/drivers/staging/wfx/bus_sdio.c
index a670176ba06f..0612f8a7c085 100644
--- a/drivers/staging/wfx/bus_sdio.c
+++ b/drivers/staging/wfx/bus_sdio.c
@@ -207,9 +207,6 @@ static int wfx_sdio_probe(struct sdio_func *func,

bus->func = func;
sdio_set_drvdata(func, bus);
- func->card->quirks |= MMC_QUIRK_LENIENT_FN0 |
- MMC_QUIRK_BLKSZ_FOR_BYTE_MODE |
- MMC_QUIRK_BROKEN_BYTE_MODE_512;

sdio_claim_host(func);
ret = sdio_enable_func(func);
diff --git a/drivers/staging/wfx/main.c b/drivers/staging/wfx/main.c
index 858d778cc589..e3999e95ce85 100644
--- a/drivers/staging/wfx/main.c
+++ b/drivers/staging/wfx/main.c
@@ -322,7 +322,8 @@ struct wfx_dev *wfx_init_common(struct device *dev,
wdev->pdata.gpio_wakeup = devm_gpiod_get_optional(dev, "wakeup",
GPIOD_OUT_LOW);
if (IS_ERR(wdev->pdata.gpio_wakeup))
- return NULL;
+ goto err;
+
if (wdev->pdata.gpio_wakeup)
gpiod_set_consumer_name(wdev->pdata.gpio_wakeup, "wfx wakeup");

@@ -341,6 +342,10 @@ struct wfx_dev *wfx_init_common(struct device *dev,
return NULL;

return wdev;
+
+err:
+ ieee80211_free_hw(hw);
+ return NULL;
}

int wfx_probe(struct wfx_dev *wdev)
diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c
index d002a4e48ed9..0d94a7cb275e 100644
--- a/drivers/tty/serial/samsung_tty.c
+++ b/drivers/tty/serial/samsung_tty.c
@@ -921,11 +921,8 @@ static void s3c24xx_serial_tx_chars(struct s3c24xx_uart_port *ourport)
return;
}

- if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) {
- spin_unlock(&port->lock);
+ if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
uart_write_wakeup(port);
- spin_lock(&port->lock);
- }

if (uart_circ_empty(xmit))
s3c24xx_serial_stop_tx(port);
diff --git a/drivers/usb/cdns3/cdnsp-debug.h b/drivers/usb/cdns3/cdnsp-debug.h
index a8776df2d4e0..f0ca865cce2a 100644
--- a/drivers/usb/cdns3/cdnsp-debug.h
+++ b/drivers/usb/cdns3/cdnsp-debug.h
@@ -182,208 +182,211 @@ static inline const char *cdnsp_decode_trb(char *str, size_t size, u32 field0,
int ep_id = TRB_TO_EP_INDEX(field3) - 1;
int type = TRB_FIELD_TO_TYPE(field3);
unsigned int ep_num;
- int ret = 0;
+ int ret;
u32 temp;

ep_num = DIV_ROUND_UP(ep_id, 2);

switch (type) {
case TRB_LINK:
- ret += snprintf(str, size,
- "LINK %08x%08x intr %ld type '%s' flags %c:%c:%c:%c",
- field1, field0, GET_INTR_TARGET(field2),
- cdnsp_trb_type_string(type),
- field3 & TRB_IOC ? 'I' : 'i',
- field3 & TRB_CHAIN ? 'C' : 'c',
- field3 & TRB_TC ? 'T' : 't',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "LINK %08x%08x intr %ld type '%s' flags %c:%c:%c:%c",
+ field1, field0, GET_INTR_TARGET(field2),
+ cdnsp_trb_type_string(type),
+ field3 & TRB_IOC ? 'I' : 'i',
+ field3 & TRB_CHAIN ? 'C' : 'c',
+ field3 & TRB_TC ? 'T' : 't',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_TRANSFER:
case TRB_COMPLETION:
case TRB_PORT_STATUS:
case TRB_HC_EVENT:
- ret += snprintf(str, size,
- "ep%d%s(%d) type '%s' TRB %08x%08x status '%s'"
- " len %ld slot %ld flags %c:%c",
- ep_num, ep_id % 2 ? "out" : "in",
- TRB_TO_EP_INDEX(field3),
- cdnsp_trb_type_string(type), field1, field0,
- cdnsp_trb_comp_code_string(GET_COMP_CODE(field2)),
- EVENT_TRB_LEN(field2), TRB_TO_SLOT_ID(field3),
- field3 & EVENT_DATA ? 'E' : 'e',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "ep%d%s(%d) type '%s' TRB %08x%08x status '%s'"
+ " len %ld slot %ld flags %c:%c",
+ ep_num, ep_id % 2 ? "out" : "in",
+ TRB_TO_EP_INDEX(field3),
+ cdnsp_trb_type_string(type), field1, field0,
+ cdnsp_trb_comp_code_string(GET_COMP_CODE(field2)),
+ EVENT_TRB_LEN(field2), TRB_TO_SLOT_ID(field3),
+ field3 & EVENT_DATA ? 'E' : 'e',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_MFINDEX_WRAP:
- ret += snprintf(str, size, "%s: flags %c",
- cdnsp_trb_type_string(type),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size, "%s: flags %c",
+ cdnsp_trb_type_string(type),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_SETUP:
- ret += snprintf(str, size,
- "type '%s' bRequestType %02x bRequest %02x "
- "wValue %02x%02x wIndex %02x%02x wLength %d "
- "length %ld TD size %ld intr %ld Setup ID %ld "
- "flags %c:%c:%c",
- cdnsp_trb_type_string(type),
- field0 & 0xff,
- (field0 & 0xff00) >> 8,
- (field0 & 0xff000000) >> 24,
- (field0 & 0xff0000) >> 16,
- (field1 & 0xff00) >> 8,
- field1 & 0xff,
- (field1 & 0xff000000) >> 16 |
- (field1 & 0xff0000) >> 16,
- TRB_LEN(field2), GET_TD_SIZE(field2),
- GET_INTR_TARGET(field2),
- TRB_SETUPID_TO_TYPE(field3),
- field3 & TRB_IDT ? 'D' : 'd',
- field3 & TRB_IOC ? 'I' : 'i',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "type '%s' bRequestType %02x bRequest %02x "
+ "wValue %02x%02x wIndex %02x%02x wLength %d "
+ "length %ld TD size %ld intr %ld Setup ID %ld "
+ "flags %c:%c:%c",
+ cdnsp_trb_type_string(type),
+ field0 & 0xff,
+ (field0 & 0xff00) >> 8,
+ (field0 & 0xff000000) >> 24,
+ (field0 & 0xff0000) >> 16,
+ (field1 & 0xff00) >> 8,
+ field1 & 0xff,
+ (field1 & 0xff000000) >> 16 |
+ (field1 & 0xff0000) >> 16,
+ TRB_LEN(field2), GET_TD_SIZE(field2),
+ GET_INTR_TARGET(field2),
+ TRB_SETUPID_TO_TYPE(field3),
+ field3 & TRB_IDT ? 'D' : 'd',
+ field3 & TRB_IOC ? 'I' : 'i',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_DATA:
- ret += snprintf(str, size,
- "type '%s' Buffer %08x%08x length %ld TD size %ld "
- "intr %ld flags %c:%c:%c:%c:%c:%c:%c",
- cdnsp_trb_type_string(type),
- field1, field0, TRB_LEN(field2),
- GET_TD_SIZE(field2),
- GET_INTR_TARGET(field2),
- field3 & TRB_IDT ? 'D' : 'i',
- field3 & TRB_IOC ? 'I' : 'i',
- field3 & TRB_CHAIN ? 'C' : 'c',
- field3 & TRB_NO_SNOOP ? 'S' : 's',
- field3 & TRB_ISP ? 'I' : 'i',
- field3 & TRB_ENT ? 'E' : 'e',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "type '%s' Buffer %08x%08x length %ld TD size %ld "
+ "intr %ld flags %c:%c:%c:%c:%c:%c:%c",
+ cdnsp_trb_type_string(type),
+ field1, field0, TRB_LEN(field2),
+ GET_TD_SIZE(field2),
+ GET_INTR_TARGET(field2),
+ field3 & TRB_IDT ? 'D' : 'i',
+ field3 & TRB_IOC ? 'I' : 'i',
+ field3 & TRB_CHAIN ? 'C' : 'c',
+ field3 & TRB_NO_SNOOP ? 'S' : 's',
+ field3 & TRB_ISP ? 'I' : 'i',
+ field3 & TRB_ENT ? 'E' : 'e',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_STATUS:
- ret += snprintf(str, size,
- "Buffer %08x%08x length %ld TD size %ld intr"
- "%ld type '%s' flags %c:%c:%c:%c",
- field1, field0, TRB_LEN(field2),
- GET_TD_SIZE(field2),
- GET_INTR_TARGET(field2),
- cdnsp_trb_type_string(type),
- field3 & TRB_IOC ? 'I' : 'i',
- field3 & TRB_CHAIN ? 'C' : 'c',
- field3 & TRB_ENT ? 'E' : 'e',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "Buffer %08x%08x length %ld TD size %ld intr"
+ "%ld type '%s' flags %c:%c:%c:%c",
+ field1, field0, TRB_LEN(field2),
+ GET_TD_SIZE(field2),
+ GET_INTR_TARGET(field2),
+ cdnsp_trb_type_string(type),
+ field3 & TRB_IOC ? 'I' : 'i',
+ field3 & TRB_CHAIN ? 'C' : 'c',
+ field3 & TRB_ENT ? 'E' : 'e',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_NORMAL:
case TRB_ISOC:
case TRB_EVENT_DATA:
case TRB_TR_NOOP:
- ret += snprintf(str, size,
- "type '%s' Buffer %08x%08x length %ld "
- "TD size %ld intr %ld "
- "flags %c:%c:%c:%c:%c:%c:%c:%c:%c",
- cdnsp_trb_type_string(type),
- field1, field0, TRB_LEN(field2),
- GET_TD_SIZE(field2),
- GET_INTR_TARGET(field2),
- field3 & TRB_BEI ? 'B' : 'b',
- field3 & TRB_IDT ? 'T' : 't',
- field3 & TRB_IOC ? 'I' : 'i',
- field3 & TRB_CHAIN ? 'C' : 'c',
- field3 & TRB_NO_SNOOP ? 'S' : 's',
- field3 & TRB_ISP ? 'I' : 'i',
- field3 & TRB_ENT ? 'E' : 'e',
- field3 & TRB_CYCLE ? 'C' : 'c',
- !(field3 & TRB_EVENT_INVALIDATE) ? 'V' : 'v');
+ ret = snprintf(str, size,
+ "type '%s' Buffer %08x%08x length %ld "
+ "TD size %ld intr %ld "
+ "flags %c:%c:%c:%c:%c:%c:%c:%c:%c",
+ cdnsp_trb_type_string(type),
+ field1, field0, TRB_LEN(field2),
+ GET_TD_SIZE(field2),
+ GET_INTR_TARGET(field2),
+ field3 & TRB_BEI ? 'B' : 'b',
+ field3 & TRB_IDT ? 'T' : 't',
+ field3 & TRB_IOC ? 'I' : 'i',
+ field3 & TRB_CHAIN ? 'C' : 'c',
+ field3 & TRB_NO_SNOOP ? 'S' : 's',
+ field3 & TRB_ISP ? 'I' : 'i',
+ field3 & TRB_ENT ? 'E' : 'e',
+ field3 & TRB_CYCLE ? 'C' : 'c',
+ !(field3 & TRB_EVENT_INVALIDATE) ? 'V' : 'v');
break;
case TRB_CMD_NOOP:
case TRB_ENABLE_SLOT:
- ret += snprintf(str, size, "%s: flags %c",
- cdnsp_trb_type_string(type),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size, "%s: flags %c",
+ cdnsp_trb_type_string(type),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_DISABLE_SLOT:
- ret += snprintf(str, size, "%s: slot %ld flags %c",
- cdnsp_trb_type_string(type),
- TRB_TO_SLOT_ID(field3),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size, "%s: slot %ld flags %c",
+ cdnsp_trb_type_string(type),
+ TRB_TO_SLOT_ID(field3),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_ADDR_DEV:
- ret += snprintf(str, size,
- "%s: ctx %08x%08x slot %ld flags %c:%c",
- cdnsp_trb_type_string(type), field1, field0,
- TRB_TO_SLOT_ID(field3),
- field3 & TRB_BSR ? 'B' : 'b',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "%s: ctx %08x%08x slot %ld flags %c:%c",
+ cdnsp_trb_type_string(type), field1, field0,
+ TRB_TO_SLOT_ID(field3),
+ field3 & TRB_BSR ? 'B' : 'b',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_CONFIG_EP:
- ret += snprintf(str, size,
- "%s: ctx %08x%08x slot %ld flags %c:%c",
- cdnsp_trb_type_string(type), field1, field0,
- TRB_TO_SLOT_ID(field3),
- field3 & TRB_DC ? 'D' : 'd',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "%s: ctx %08x%08x slot %ld flags %c:%c",
+ cdnsp_trb_type_string(type), field1, field0,
+ TRB_TO_SLOT_ID(field3),
+ field3 & TRB_DC ? 'D' : 'd',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_EVAL_CONTEXT:
- ret += snprintf(str, size,
- "%s: ctx %08x%08x slot %ld flags %c",
- cdnsp_trb_type_string(type), field1, field0,
- TRB_TO_SLOT_ID(field3),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "%s: ctx %08x%08x slot %ld flags %c",
+ cdnsp_trb_type_string(type), field1, field0,
+ TRB_TO_SLOT_ID(field3),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_RESET_EP:
case TRB_HALT_ENDPOINT:
case TRB_FLUSH_ENDPOINT:
- ret += snprintf(str, size,
- "%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
- cdnsp_trb_type_string(type),
- ep_num, ep_id % 2 ? "out" : "in",
- TRB_TO_EP_INDEX(field3), field1, field0,
- TRB_TO_SLOT_ID(field3),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
+ cdnsp_trb_type_string(type),
+ ep_num, ep_id % 2 ? "out" : "in",
+ TRB_TO_EP_INDEX(field3), field1, field0,
+ TRB_TO_SLOT_ID(field3),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_STOP_RING:
- ret += snprintf(str, size,
- "%s: ep%d%s(%d) slot %ld sp %d flags %c",
- cdnsp_trb_type_string(type),
- ep_num, ep_id % 2 ? "out" : "in",
- TRB_TO_EP_INDEX(field3),
- TRB_TO_SLOT_ID(field3),
- TRB_TO_SUSPEND_PORT(field3),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "%s: ep%d%s(%d) slot %ld sp %d flags %c",
+ cdnsp_trb_type_string(type),
+ ep_num, ep_id % 2 ? "out" : "in",
+ TRB_TO_EP_INDEX(field3),
+ TRB_TO_SLOT_ID(field3),
+ TRB_TO_SUSPEND_PORT(field3),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_SET_DEQ:
- ret += snprintf(str, size,
- "%s: ep%d%s(%d) deq %08x%08x stream %ld slot %ld flags %c",
- cdnsp_trb_type_string(type),
- ep_num, ep_id % 2 ? "out" : "in",
- TRB_TO_EP_INDEX(field3), field1, field0,
- TRB_TO_STREAM_ID(field2),
- TRB_TO_SLOT_ID(field3),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size,
+ "%s: ep%d%s(%d) deq %08x%08x stream %ld slot %ld flags %c",
+ cdnsp_trb_type_string(type),
+ ep_num, ep_id % 2 ? "out" : "in",
+ TRB_TO_EP_INDEX(field3), field1, field0,
+ TRB_TO_STREAM_ID(field2),
+ TRB_TO_SLOT_ID(field3),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_RESET_DEV:
- ret += snprintf(str, size, "%s: slot %ld flags %c",
- cdnsp_trb_type_string(type),
- TRB_TO_SLOT_ID(field3),
- field3 & TRB_CYCLE ? 'C' : 'c');
+ ret = snprintf(str, size, "%s: slot %ld flags %c",
+ cdnsp_trb_type_string(type),
+ TRB_TO_SLOT_ID(field3),
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
case TRB_ENDPOINT_NRDY:
- temp = TRB_TO_HOST_STREAM(field2);
-
- ret += snprintf(str, size,
- "%s: ep%d%s(%d) H_SID %x%s%s D_SID %lx flags %c:%c",
- cdnsp_trb_type_string(type),
- ep_num, ep_id % 2 ? "out" : "in",
- TRB_TO_EP_INDEX(field3), temp,
- temp == STREAM_PRIME_ACK ? "(PRIME)" : "",
- temp == STREAM_REJECTED ? "(REJECTED)" : "",
- TRB_TO_DEV_STREAM(field0),
- field3 & TRB_STAT ? 'S' : 's',
- field3 & TRB_CYCLE ? 'C' : 'c');
+ temp = TRB_TO_HOST_STREAM(field2);
+
+ ret = snprintf(str, size,
+ "%s: ep%d%s(%d) H_SID %x%s%s D_SID %lx flags %c:%c",
+ cdnsp_trb_type_string(type),
+ ep_num, ep_id % 2 ? "out" : "in",
+ TRB_TO_EP_INDEX(field3), temp,
+ temp == STREAM_PRIME_ACK ? "(PRIME)" : "",
+ temp == STREAM_REJECTED ? "(REJECTED)" : "",
+ TRB_TO_DEV_STREAM(field0),
+ field3 & TRB_STAT ? 'S' : 's',
+ field3 & TRB_CYCLE ? 'C' : 'c');
break;
default:
- ret += snprintf(str, size,
- "type '%s' -> raw %08x %08x %08x %08x",
- cdnsp_trb_type_string(type),
- field0, field1, field2, field3);
+ ret = snprintf(str, size,
+ "type '%s' -> raw %08x %08x %08x %08x",
+ cdnsp_trb_type_string(type),
+ field0, field1, field2, field3);
}

+ if (ret >= size)
+ pr_info("CDNSP: buffer overflowed.\n");
+
return str;
}

diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index e196673f5c64..efaf0db595f4 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -242,7 +242,7 @@ static void dwc3_omap_set_mailbox(struct dwc3_omap *omap,
break;

case OMAP_DWC3_ID_FLOAT:
- if (omap->vbus_reg)
+ if (omap->vbus_reg && regulator_is_enabled(omap->vbus_reg))
regulator_disable(omap->vbus_reg);
val = dwc3_omap_read_utmi_ctrl(omap);
val |= USBOTGSS_UTMI_OTG_CTRL_IDDIG;
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 06d0e88ec8af..4d9608cc55f7 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -185,7 +185,8 @@ static const struct software_node dwc3_pci_amd_mr_swnode = {
.properties = dwc3_pci_mr_properties,
};

-static int dwc3_pci_quirks(struct dwc3_pci *dwc)
+static int dwc3_pci_quirks(struct dwc3_pci *dwc,
+ const struct software_node *swnode)
{
struct pci_dev *pdev = dwc->pci;

@@ -242,7 +243,7 @@ static int dwc3_pci_quirks(struct dwc3_pci *dwc)
}
}

- return 0;
+ return device_add_software_node(&dwc->dwc3->dev, swnode);
}

#ifdef CONFIG_PM
@@ -307,11 +308,7 @@ static int dwc3_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
dwc->dwc3->dev.parent = dev;
ACPI_COMPANION_SET(&dwc->dwc3->dev, ACPI_COMPANION(dev));

- ret = device_add_software_node(&dwc->dwc3->dev, (void *)id->driver_data);
- if (ret < 0)
- goto err;
-
- ret = dwc3_pci_quirks(dwc);
+ ret = dwc3_pci_quirks(dwc, (void *)id->driver_data);
if (ret)
goto err;

diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index 43f1b0d461c1..be76f891b9c5 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -32,9 +32,6 @@
#include <linux/workqueue.h>

/* XUSB_DEV registers */
-#define SPARAM 0x000
-#define SPARAM_ERSTMAX_MASK GENMASK(20, 16)
-#define SPARAM_ERSTMAX(x) (((x) << 16) & SPARAM_ERSTMAX_MASK)
#define DB 0x004
#define DB_TARGET_MASK GENMASK(15, 8)
#define DB_TARGET(x) (((x) << 8) & DB_TARGET_MASK)
@@ -275,8 +272,10 @@ BUILD_EP_CONTEXT_RW(deq_hi, deq_hi, 0, 0xffffffff)
BUILD_EP_CONTEXT_RW(avg_trb_len, tx_info, 0, 0xffff)
BUILD_EP_CONTEXT_RW(max_esit_payload, tx_info, 16, 0xffff)
BUILD_EP_CONTEXT_RW(edtla, rsvd[0], 0, 0xffffff)
-BUILD_EP_CONTEXT_RW(seq_num, rsvd[0], 24, 0xff)
+BUILD_EP_CONTEXT_RW(rsvd, rsvd[0], 24, 0x1)
BUILD_EP_CONTEXT_RW(partial_td, rsvd[0], 25, 0x1)
+BUILD_EP_CONTEXT_RW(splitxstate, rsvd[0], 26, 0x1)
+BUILD_EP_CONTEXT_RW(seq_num, rsvd[0], 27, 0x1f)
BUILD_EP_CONTEXT_RW(cerrcnt, rsvd[1], 18, 0x3)
BUILD_EP_CONTEXT_RW(data_offset, rsvd[2], 0, 0x1ffff)
BUILD_EP_CONTEXT_RW(numtrbs, rsvd[2], 22, 0x1f)
@@ -1557,6 +1556,9 @@ static int __tegra_xudc_ep_set_halt(struct tegra_xudc_ep *ep, bool halt)
ep_reload(xudc, ep->index);

ep_ctx_write_state(ep->context, EP_STATE_RUNNING);
+ ep_ctx_write_rsvd(ep->context, 0);
+ ep_ctx_write_partial_td(ep->context, 0);
+ ep_ctx_write_splitxstate(ep->context, 0);
ep_ctx_write_seq_num(ep->context, 0);

ep_reload(xudc, ep->index);
@@ -2812,7 +2814,10 @@ static void tegra_xudc_reset(struct tegra_xudc *xudc)
xudc->setup_seq_num = 0;
xudc->queued_setup_packet = false;

- ep_ctx_write_seq_num(ep0->context, xudc->setup_seq_num);
+ ep_ctx_write_rsvd(ep0->context, 0);
+ ep_ctx_write_partial_td(ep0->context, 0);
+ ep_ctx_write_splitxstate(ep0->context, 0);
+ ep_ctx_write_seq_num(ep0->context, 0);

deq_ptr = trb_virt_to_phys(ep0, &ep0->transfer_ring[ep0->deq_ptr]);

@@ -3295,11 +3300,6 @@ static void tegra_xudc_init_event_ring(struct tegra_xudc *xudc)
unsigned int i;
u32 val;

- val = xudc_readl(xudc, SPARAM);
- val &= ~(SPARAM_ERSTMAX_MASK);
- val |= SPARAM_ERSTMAX(XUDC_NR_EVENT_RINGS);
- xudc_writel(xudc, val, SPARAM);
-
for (i = 0; i < ARRAY_SIZE(xudc->event_ring); i++) {
memset(xudc->event_ring[i], 0, XUDC_EVENT_RING_SIZE *
sizeof(*xudc->event_ring[i]));
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index e87cf3a00fa4..638f03b89739 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -21,6 +21,9 @@ static const char hcd_name[] = "ehci-pci";
/* defined here to avoid adding to pci_ids.h for single instance use */
#define PCI_DEVICE_ID_INTEL_CE4100_USB 0x2e70

+#define PCI_VENDOR_ID_ASPEED 0x1a03
+#define PCI_DEVICE_ID_ASPEED_EHCI 0x2603
+
/*-------------------------------------------------------------------------*/
#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC 0x0939
static inline bool is_intel_quark_x1000(struct pci_dev *pdev)
@@ -222,6 +225,12 @@ static int ehci_pci_setup(struct usb_hcd *hcd)
ehci->has_synopsys_hc_bug = 1;
}
break;
+ case PCI_VENDOR_ID_ASPEED:
+ if (pdev->device == PCI_DEVICE_ID_ASPEED_EHCI) {
+ ehci_info(ehci, "applying Aspeed HC workaround\n");
+ ehci->is_aspeed = 1;
+ }
+ break;
}

/* optional debug port, normally in the first BAR */
diff --git a/drivers/usb/host/xen-hcd.c b/drivers/usb/host/xen-hcd.c
index 19b8c7ed74cb..4ed3ee328a4a 100644
--- a/drivers/usb/host/xen-hcd.c
+++ b/drivers/usb/host/xen-hcd.c
@@ -51,6 +51,7 @@ struct vdevice_status {
struct usb_shadow {
struct xenusb_urb_request req;
struct urb *urb;
+ bool in_flight;
};

struct xenhcd_info {
@@ -722,6 +723,12 @@ static void xenhcd_gnttab_done(struct xenhcd_info *info, unsigned int id)
int nr_segs = 0;
int i;

+ if (!shadow->in_flight) {
+ xenhcd_set_error(info, "Illegal request id");
+ return;
+ }
+ shadow->in_flight = false;
+
nr_segs = shadow->req.nr_buffer_segs;

if (xenusb_pipeisoc(shadow->req.pipe))
@@ -805,6 +812,7 @@ static int xenhcd_do_request(struct xenhcd_info *info, struct urb_priv *urbp)

info->urb_ring.req_prod_pvt++;
info->shadow[id].urb = urb;
+ info->shadow[id].in_flight = true;

RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&info->urb_ring, notify);
if (notify)
@@ -933,10 +941,27 @@ static int xenhcd_unlink_urb(struct xenhcd_info *info, struct urb_priv *urbp)
return ret;
}

-static int xenhcd_urb_request_done(struct xenhcd_info *info)
+static void xenhcd_res_to_urb(struct xenhcd_info *info,
+ struct xenusb_urb_response *res, struct urb *urb)
+{
+ if (unlikely(!urb))
+ return;
+
+ if (res->actual_length > urb->transfer_buffer_length)
+ urb->actual_length = urb->transfer_buffer_length;
+ else if (res->actual_length < 0)
+ urb->actual_length = 0;
+ else
+ urb->actual_length = res->actual_length;
+ urb->error_count = res->error_count;
+ urb->start_frame = res->start_frame;
+ xenhcd_giveback_urb(info, urb, res->status);
+}
+
+static int xenhcd_urb_request_done(struct xenhcd_info *info,
+ unsigned int *eoiflag)
{
struct xenusb_urb_response res;
- struct urb *urb;
RING_IDX i, rp;
__u16 id;
int more_to_do = 0;
@@ -963,16 +988,12 @@ static int xenhcd_urb_request_done(struct xenhcd_info *info)
xenhcd_gnttab_done(info, id);
if (info->error)
goto err;
- urb = info->shadow[id].urb;
- if (likely(urb)) {
- urb->actual_length = res.actual_length;
- urb->error_count = res.error_count;
- urb->start_frame = res.start_frame;
- xenhcd_giveback_urb(info, urb, res.status);
- }
+ xenhcd_res_to_urb(info, &res, info->shadow[id].urb);
}

xenhcd_add_id_to_freelist(info, id);
+
+ *eoiflag = 0;
}
info->urb_ring.rsp_cons = i;

@@ -990,7 +1011,7 @@ static int xenhcd_urb_request_done(struct xenhcd_info *info)
return 0;
}

-static int xenhcd_conn_notify(struct xenhcd_info *info)
+static int xenhcd_conn_notify(struct xenhcd_info *info, unsigned int *eoiflag)
{
struct xenusb_conn_response res;
struct xenusb_conn_request *req;
@@ -1035,6 +1056,8 @@ static int xenhcd_conn_notify(struct xenhcd_info *info)
info->conn_ring.req_prod_pvt);
req->id = id;
info->conn_ring.req_prod_pvt++;
+
+ *eoiflag = 0;
}

if (rc != info->conn_ring.req_prod_pvt)
@@ -1057,14 +1080,19 @@ static int xenhcd_conn_notify(struct xenhcd_info *info)
static irqreturn_t xenhcd_int(int irq, void *dev_id)
{
struct xenhcd_info *info = (struct xenhcd_info *)dev_id;
+ unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;

- if (unlikely(info->error))
+ if (unlikely(info->error)) {
+ xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
return IRQ_HANDLED;
+ }

- while (xenhcd_urb_request_done(info) | xenhcd_conn_notify(info))
+ while (xenhcd_urb_request_done(info, &eoiflag) |
+ xenhcd_conn_notify(info, &eoiflag))
/* Yield point for this unbounded loop. */
cond_resched();

+ xen_irq_lateeoi(irq, eoiflag);
return IRQ_HANDLED;
}

@@ -1141,9 +1169,9 @@ static int xenhcd_setup_rings(struct xenbus_device *dev,
goto fail;
}

- err = bind_evtchn_to_irq(info->evtchn);
+ err = bind_evtchn_to_irq_lateeoi(info->evtchn);
if (err <= 0) {
- xenbus_dev_fatal(dev, err, "bind_evtchn_to_irq");
+ xenbus_dev_fatal(dev, err, "bind_evtchn_to_irq_lateeoi");
goto fail;
}

@@ -1496,6 +1524,7 @@ static struct usb_hcd *xenhcd_create_hcd(struct xenbus_device *dev)
for (i = 0; i < XENUSB_URB_RING_SIZE; i++) {
info->shadow[i].req.id = i + 1;
info->shadow[i].urb = NULL;
+ info->shadow[i].in_flight = false;
}
info->shadow[XENUSB_URB_RING_SIZE - 1].req.id = 0x0fff;

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 9fe1071a9644..1b5de3af1a62 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -163,6 +163,7 @@ struct mlx5_vdpa_net {
u32 cur_num_vqs;
struct notifier_block nb;
struct vdpa_callback config_cb;
+ struct mlx5_vdpa_wq_ent cvq_ent;
};

static void free_resources(struct mlx5_vdpa_net *ndev);
@@ -1616,10 +1617,10 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)
ndev = to_mlx5_vdpa_ndev(mvdev);
cvq = &mvdev->cvq;
if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)))
- goto out;
+ return;

if (!cvq->ready)
- goto out;
+ return;

while (true) {
err = vringh_getdesc_iotlb(&cvq->vring, &cvq->riov, &cvq->wiov, &cvq->head,
@@ -1653,9 +1654,10 @@ static void mlx5_cvq_kick_handler(struct work_struct *work)

if (vringh_need_notify_iotlb(&cvq->vring))
vringh_notify(&cvq->vring);
+
+ queue_work(mvdev->wq, &wqent->work);
+ break;
}
-out:
- kfree(wqent);
}

static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
@@ -1663,7 +1665,6 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
struct mlx5_vdpa_virtqueue *mvq;
- struct mlx5_vdpa_wq_ent *wqent;

if (!is_index_valid(mvdev, idx))
return;
@@ -1672,13 +1673,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
if (!mvdev->wq || !mvdev->cvq.ready)
return;

- wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
- if (!wqent)
- return;
-
- wqent->mvdev = mvdev;
- INIT_WORK(&wqent->work, mlx5_cvq_kick_handler);
- queue_work(mvdev->wq, &wqent->work);
+ queue_work(mvdev->wq, &ndev->cvq_ent.work);
return;
}

@@ -2668,6 +2663,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
if (err)
goto err_mr;

+ ndev->cvq_ent.mvdev = mvdev;
+ INIT_WORK(&ndev->cvq_ent.work, mlx5_cvq_kick_handler);
mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq");
if (!mvdev->wq) {
err = -ENOMEM;
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 57d3b2cbbd8e..82ac1569deb0 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -288,6 +288,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
return done;
}

+#ifdef CONFIG_VFIO_PCI_VGA
ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite)
{
@@ -355,6 +356,7 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,

return done;
}
+#endif

static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
bool test_mem)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 28ef323882fb..792ab5f23647 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -473,6 +473,7 @@ static void vhost_tx_batch(struct vhost_net *net,
goto signal_used;

msghdr->msg_control = &ctl;
+ msghdr->msg_controllen = sizeof(ctl);
err = sock->ops->sendmsg(sock, msghdr, 0);
if (unlikely(err < 0)) {
vq_err(&nvq->vq, "Fail to batch sending packets\n");
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index ad9aac06427a..00f0f282e7a1 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1583,7 +1583,14 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a,
* If it's not a platform device, at least print a warning. A
* fix would add code to remove the device from the system.
*/
- if (dev_is_platform(device)) {
+ if (!device) {
+ /* TODO: Represent each OF framebuffer as its own
+ * device in the device hierarchy. For now, offb
+ * doesn't have such a device, so unregister the
+ * framebuffer as before without warning.
+ */
+ do_unregister_framebuffer(registered_fb[i]);
+ } else if (dev_is_platform(device)) {
registered_fb[i]->forced_out = true;
platform_device_unregister(to_platform_device(device));
} else {
diff --git a/drivers/w1/slaves/w1_therm.c b/drivers/w1/slaves/w1_therm.c
index 565578002d79..c7b8a8e787e2 100644
--- a/drivers/w1/slaves/w1_therm.c
+++ b/drivers/w1/slaves/w1_therm.c
@@ -2089,16 +2089,20 @@ static ssize_t w1_seq_show(struct device *device,
if (sl->reg_num.id == reg_num->id)
seq = i;

+ if (w1_reset_bus(sl->master))
+ goto error;
+
+ /* Put the device into chain DONE state */
+ w1_write_8(sl->master, W1_MATCH_ROM);
+ w1_write_block(sl->master, (u8 *)&rn, 8);
w1_write_8(sl->master, W1_42_CHAIN);
w1_write_8(sl->master, W1_42_CHAIN_DONE);
w1_write_8(sl->master, W1_42_CHAIN_DONE_INV);
- w1_read_block(sl->master, &ack, sizeof(ack));

/* check for acknowledgment */
ack = w1_read_8(sl->master);
if (ack != W1_42_SUCCESS_CONFIRM_BYTE)
goto error;
-
}

/* Exit from CHAIN state */
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0399cf8e3c32..151e9da5da2d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -118,7 +118,7 @@ struct btrfs_bio_ctrl {
*/
struct extent_changeset {
/* How many bytes are set/cleared in this operation */
- unsigned int bytes_changed;
+ u64 bytes_changed;

/* Changed ranges */
struct ulist range_changed;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0f4408f9dadd..ec4950cfe1ea 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4466,6 +4466,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
dest->root_key.objectid);
return -EPERM;
}
+ if (atomic_read(&dest->nr_swapfiles)) {
+ spin_unlock(&dest->root_item_lock);
+ btrfs_warn(fs_info,
+ "attempt to delete subvolume %llu with active swapfile",
+ root->root_key.objectid);
+ return -EPERM;
+ }
root_flags = btrfs_root_flags(&dest->root_item);
btrfs_set_root_flags(&dest->root_item,
root_flags | BTRFS_ROOT_SUBVOL_DEAD);
@@ -10424,8 +10431,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
* set. We use this counter to prevent snapshots. We must increment it
* before walking the extents because we don't want a concurrent
* snapshot to run after we've already checked the extents.
+ *
+ * It is possible that subvolume is marked for deletion but still not
+ * removed yet. To prevent this race, we check the root status before
+ * activating the swapfile.
*/
+ spin_lock(&root->root_item_lock);
+ if (btrfs_root_dead(root)) {
+ spin_unlock(&root->root_item_lock);
+
+ btrfs_exclop_finish(fs_info);
+ btrfs_warn(fs_info,
+ "cannot activate swapfile because subvolume %llu is being deleted",
+ root->root_key.objectid);
+ return -EPERM;
+ }
atomic_inc(&root->nr_swapfiles);
+ spin_unlock(&root->root_item_lock);

isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize);

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8d47ec5fc4f4..8fe9d55d6862 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1215,7 +1215,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em)
}

static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
- bool locked)
+ u32 extent_thresh, u64 newer_than, bool locked)
{
struct extent_map *next;
bool ret = false;
@@ -1225,11 +1225,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
return false;

/*
- * We want to check if the next extent can be merged with the current
- * one, which can be an extent created in a past generation, so we pass
- * a minimum generation of 0 to defrag_lookup_extent().
+ * Here we need to pass @newer_then when checking the next extent, or
+ * we will hit a case we mark current extent for defrag, but the next
+ * one will not be a target.
+ * This will just cause extra IO without really reducing the fragments.
*/
- next = defrag_lookup_extent(inode, em->start + em->len, 0, locked);
+ next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked);
/* No more em or hole */
if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
goto out;
@@ -1241,6 +1242,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
*/
if (next->len >= get_extent_max_capacity(em))
goto out;
+ /* Skip older extent */
+ if (next->generation < newer_than)
+ goto out;
+ /* Also check extent size */
+ if (next->len >= extent_thresh)
+ goto out;
+
ret = true;
out:
free_extent_map(next);
@@ -1446,7 +1454,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
goto next;

next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em,
- locked);
+ extent_thresh, newer_than, locked);
if (!next_mergeable) {
struct defrag_target_range *last;

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f5b11c1a000a..f5688a25fca3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1945,23 +1945,18 @@ static void update_dev_time(const char *device_path)
path_put(&path);
}

-static int btrfs_rm_dev_item(struct btrfs_device *device)
+static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans,
+ struct btrfs_device *device)
{
struct btrfs_root *root = device->fs_info->chunk_root;
int ret;
struct btrfs_path *path;
struct btrfs_key key;
- struct btrfs_trans_handle *trans;

path = btrfs_alloc_path();
if (!path)
return -ENOMEM;

- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
- return PTR_ERR(trans);
- }
key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
key.type = BTRFS_DEV_ITEM_KEY;
key.offset = device->devid;
@@ -1972,21 +1967,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device)
if (ret) {
if (ret > 0)
ret = -ENOENT;
- btrfs_abort_transaction(trans, ret);
- btrfs_end_transaction(trans);
goto out;
}

ret = btrfs_del_item(trans, root, path);
- if (ret) {
- btrfs_abort_transaction(trans, ret);
- btrfs_end_transaction(trans);
- }
-
out:
btrfs_free_path(path);
- if (!ret)
- ret = btrfs_commit_transaction(trans);
return ret;
}

@@ -2127,6 +2113,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
struct btrfs_dev_lookup_args *args,
struct block_device **bdev, fmode_t *mode)
{
+ struct btrfs_trans_handle *trans;
struct btrfs_device *device;
struct btrfs_fs_devices *cur_devices;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
@@ -2142,7 +2129,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,

ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1);
if (ret)
- goto out;
+ return ret;

device = btrfs_find_device(fs_info->fs_devices, args);
if (!device) {
@@ -2150,27 +2137,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
else
ret = -ENOENT;
- goto out;
+ return ret;
}

if (btrfs_pinned_by_swapfile(fs_info, device)) {
btrfs_warn_in_rcu(fs_info,
"cannot remove device %s (devid %llu) due to active swapfile",
rcu_str_deref(device->name), device->devid);
- ret = -ETXTBSY;
- goto out;
+ return -ETXTBSY;
}

- if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
- ret = BTRFS_ERROR_DEV_TGT_REPLACE;
- goto out;
- }
+ if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
+ return BTRFS_ERROR_DEV_TGT_REPLACE;

if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
- fs_info->fs_devices->rw_devices == 1) {
- ret = BTRFS_ERROR_DEV_ONLY_WRITABLE;
- goto out;
- }
+ fs_info->fs_devices->rw_devices == 1)
+ return BTRFS_ERROR_DEV_ONLY_WRITABLE;

if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
mutex_lock(&fs_info->chunk_mutex);
@@ -2183,14 +2165,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
if (ret)
goto error_undo;

- /*
- * TODO: the superblock still includes this device in its num_devices
- * counter although write_all_supers() is not locked out. This
- * could give a filesystem state which requires a degraded mount.
- */
- ret = btrfs_rm_dev_item(device);
- if (ret)
+ trans = btrfs_start_transaction(fs_info->chunk_root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
goto error_undo;
+ }
+
+ ret = btrfs_rm_dev_item(trans, device);
+ if (ret) {
+ /* Any error in dev item removal is critical */
+ btrfs_crit(fs_info,
+ "failed to remove device item for devid %llu: %d",
+ device->devid, ret);
+ btrfs_abort_transaction(trans, ret);
+ btrfs_end_transaction(trans);
+ return ret;
+ }

clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
btrfs_scrub_cancel_dev(device);
@@ -2273,7 +2263,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
free_fs_devices(cur_devices);
}

-out:
+ ret = btrfs_commit_transaction(trans);
+
return ret;

error_undo:
@@ -2284,7 +2275,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
device->fs_devices->rw_devices++;
mutex_unlock(&fs_info->chunk_mutex);
}
- goto out;
+ return ret;
}

void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index f559d517c7c4..f03705d2f8a8 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1927,18 +1927,19 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group)

bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags)
{
+ struct btrfs_fs_info *fs_info = fs_devices->fs_info;
struct btrfs_device *device;
bool ret = false;

- if (!btrfs_is_zoned(fs_devices->fs_info))
+ if (!btrfs_is_zoned(fs_info))
return true;

/* Non-single profiles are not supported yet */
ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0);

/* Check if there is a device with active zones left */
- mutex_lock(&fs_devices->device_list_mutex);
- list_for_each_entry(device, &fs_devices->devices, dev_list) {
+ mutex_lock(&fs_info->chunk_mutex);
+ list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
struct btrfs_zoned_device_info *zinfo = device->zone_info;

if (!device->bdev)
@@ -1950,7 +1951,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags)
break;
}
}
- mutex_unlock(&fs_devices->device_list_mutex);
+ mutex_unlock(&fs_info->chunk_mutex);

return ret;
}
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 133dbd9338e7..d91fa53e12b3 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -478,8 +478,11 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
2 : (fpos_off(rde->offset) + 1);
err = note_last_dentry(dfi, rde->name, rde->name_len,
next_offset);
- if (err)
+ if (err) {
+ ceph_mdsc_put_request(dfi->last_readdir);
+ dfi->last_readdir = NULL;
return err;
+ }
} else if (req->r_reply_info.dir_end) {
dfi->next_offset = 2;
/* keep last name */
@@ -520,6 +523,12 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
if (!dir_emit(ctx, rde->name, rde->name_len,
ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
le32_to_cpu(rde->inode.in->mode) >> 12)) {
+ /*
+ * NOTE: Here no need to put the 'dfi->last_readdir',
+ * because when dir_emit stops us it's most likely
+ * doesn't have enough memory, etc. So for next readdir
+ * it will continue.
+ */
dout("filldir stopping us...\n");
return 0;
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index ef4a980a7bf3..c092dce0485c 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -87,13 +87,13 @@ struct inode *ceph_get_snapdir(struct inode *parent)
if (!S_ISDIR(parent->i_mode)) {
pr_warn_once("bad snapdir parent type (mode=0%o)\n",
parent->i_mode);
- return ERR_PTR(-ENOTDIR);
+ goto err;
}

if (!(inode->i_state & I_NEW) && !S_ISDIR(inode->i_mode)) {
pr_warn_once("bad snapdir inode type (mode=0%o)\n",
inode->i_mode);
- return ERR_PTR(-ENOTDIR);
+ goto err;
}

inode->i_mode = parent->i_mode;
@@ -113,6 +113,12 @@ struct inode *ceph_get_snapdir(struct inode *parent)
}

return inode;
+err:
+ if ((inode->i_state & I_NEW))
+ discard_new_inode(inode);
+ else
+ iput(inode);
+ return ERR_PTR(-ENOTDIR);
}

const struct inode_operations ceph_file_iops = {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d6f8ccc7bfe2..c3be6a541c8f 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -453,9 +453,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_
return rc;
}

-static int
-reconnect_dfs_server(struct TCP_Server_Info *server,
- bool mark_smb_session)
+static int reconnect_dfs_server(struct TCP_Server_Info *server)
{
int rc = 0;
const char *refpath = server->current_fullpath + 1;
@@ -479,7 +477,12 @@ reconnect_dfs_server(struct TCP_Server_Info *server,
if (!cifs_tcp_ses_needs_reconnect(server, num_targets))
return 0;

- cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session);
+ /*
+ * Unconditionally mark all sessions & tcons for reconnect as we might be connecting to a
+ * different server or share during failover. It could be improved by adding some logic to
+ * only do that in case it connects to a different server or share, though.
+ */
+ cifs_mark_tcp_ses_conns_for_reconnect(server, true);

cifs_abort_connection(server);

@@ -537,7 +540,7 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session)
}
spin_unlock(&cifs_tcp_ses_lock);

- return reconnect_dfs_server(server, mark_smb_session);
+ return reconnect_dfs_server(server);
}
#else
int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session)
@@ -4465,7 +4468,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco
*/
if (rc && server->current_fullpath != server->origin_fullpath) {
server->current_fullpath = server->origin_fullpath;
- cifs_reconnect(tcon->ses->server, true);
+ cifs_signal_cifsd_for_reconnect(server, true);
}

dfs_cache_free_tgts(tl);
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index ebe236b9d9f5..235aa1b395eb 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -896,7 +896,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr)
if (class == ERRSRV && code == ERRbaduid) {
cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n",
code);
- cifs_reconnect(mid->server, false);
+ cifs_signal_cifsd_for_reconnect(mid->server, false);
}
}

diff --git a/fs/file_table.c b/fs/file_table.c
index 7d2e692b66a9..ada8fe814db9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -412,6 +412,7 @@ void __fput_sync(struct file *file)
}

EXPORT_SYMBOL(fput);
+EXPORT_SYMBOL(__fput_sync);

void __init files_init(void)
{
diff --git a/fs/io-wq.h b/fs/io-wq.h
index dbecd27656c7..04d374e65e54 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack)
struct io_wq_work {
struct io_wq_work_node list;
unsigned flags;
+ int fd;
};

static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5e6788ab188f..1a9630dc5361 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -112,8 +112,7 @@
IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)

#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
- REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
- REQ_F_ASYNC_DATA)
+ REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA)

#define IO_TCTX_REFS_CACHE_NR (1U << 10)

@@ -469,7 +468,6 @@ struct io_uring_task {
const struct io_ring_ctx *last;
struct io_wq *io_wq;
struct percpu_counter inflight;
- atomic_t inflight_tracked;
atomic_t in_idle;

spinlock_t task_lock;
@@ -560,7 +558,8 @@ struct io_rw {
/* NOTE: kiocb has the file as the first member, so don't do it here */
struct kiocb kiocb;
u64 addr;
- u64 len;
+ u32 len;
+ u32 flags;
};

struct io_connect {
@@ -621,10 +620,10 @@ struct io_epoll {

struct io_splice {
struct file *file_out;
- struct file *file_in;
loff_t off_out;
loff_t off_in;
u64 len;
+ int splice_fd_in;
unsigned int flags;
};

@@ -1127,8 +1126,11 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
struct io_uring_rsrc_update2 *up,
unsigned nr_args);
static void io_clean_op(struct io_kiocb *req);
-static struct file *io_file_get(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd, bool fixed);
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+ unsigned issue_flags);
+static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd);
+static void io_drop_inflight_file(struct io_kiocb *req);
+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags);
static void __io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);

@@ -1257,13 +1259,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
}

static inline void io_req_set_rsrc_node(struct io_kiocb *req,
- struct io_ring_ctx *ctx)
+ struct io_ring_ctx *ctx,
+ unsigned int issue_flags)
{
if (!req->fixed_rsrc_refs) {
req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
- ctx->rsrc_cached_refs--;
- if (unlikely(ctx->rsrc_cached_refs < 0))
- io_rsrc_refs_refill(ctx);
+
+ if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+ lockdep_assert_held(&ctx->uring_lock);
+ ctx->rsrc_cached_refs--;
+ if (unlikely(ctx->rsrc_cached_refs < 0))
+ io_rsrc_refs_refill(ctx);
+ } else {
+ percpu_ref_get(req->fixed_rsrc_refs);
+ }
}
}

@@ -1303,29 +1312,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
bool cancel_all)
__must_hold(&req->ctx->timeout_lock)
{
- struct io_kiocb *req;
-
if (task && head->task != task)
return false;
- if (cancel_all)
- return true;
-
- io_for_each_link(req, head) {
- if (req->flags & REQ_F_INFLIGHT)
- return true;
- }
- return false;
-}
-
-static bool io_match_linked(struct io_kiocb *head)
-{
- struct io_kiocb *req;
-
- io_for_each_link(req, head) {
- if (req->flags & REQ_F_INFLIGHT)
- return true;
- }
- return false;
+ return cancel_all;
}

/*
@@ -1335,24 +1324,9 @@ static bool io_match_linked(struct io_kiocb *head)
static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all)
{
- bool matched;
-
if (task && head->task != task)
return false;
- if (cancel_all)
- return true;
-
- if (head->flags & REQ_F_LINK_TIMEOUT) {
- struct io_ring_ctx *ctx = head->ctx;
-
- /* protect against races with linked timeouts */
- spin_lock_irq(&ctx->timeout_lock);
- matched = io_match_linked(head);
- spin_unlock_irq(&ctx->timeout_lock);
- } else {
- matched = io_match_linked(head);
- }
- return matched;
+ return cancel_all;
}

static inline bool req_has_async_data(struct io_kiocb *req)
@@ -1500,14 +1474,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req)
return req->flags & REQ_F_FIXED_FILE;
}

-static inline void io_req_track_inflight(struct io_kiocb *req)
-{
- if (!(req->flags & REQ_F_INFLIGHT)) {
- req->flags |= REQ_F_INFLIGHT;
- atomic_inc(&current->io_uring->inflight_tracked);
- }
-}
-
static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
if (WARN_ON_ONCE(!req->link))
@@ -1551,14 +1517,6 @@ static void io_prep_async_work(struct io_kiocb *req)
if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
-
- switch (req->opcode) {
- case IORING_OP_SPLICE:
- case IORING_OP_TEE:
- if (!S_ISREG(file_inode(req->splice.file_in)->i_mode))
- req->work.flags |= IO_WQ_WORK_UNBOUND;
- break;
- }
}

static void io_prep_async_link(struct io_kiocb *req)
@@ -1652,12 +1610,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
__must_hold(&ctx->completion_lock)
{
u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+ struct io_kiocb *req, *tmp;

spin_lock_irq(&ctx->timeout_lock);
- while (!list_empty(&ctx->timeout_list)) {
+ list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
u32 events_needed, events_got;
- struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
- struct io_kiocb, timeout.list);

if (io_is_timeout_noseq(req))
break;
@@ -1674,7 +1631,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
if (events_got < events_needed)
break;

- list_del_init(&req->timeout.list);
io_kill_timeout(req, 0);
}
ctx->cq_last_tm_flush = seq;
@@ -2381,6 +2337,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority)

WARN_ON_ONCE(!tctx);

+ io_drop_inflight_file(req);
+
spin_lock_irqsave(&tctx->task_lock, flags);
if (priority)
wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list);
@@ -2994,50 +2952,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req)

static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw.kiocb;
- struct file *file = req->file;
unsigned ioprio;
int ret;

- if (!io_req_ffs_set(req))
- req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
-
kiocb->ki_pos = READ_ONCE(sqe->off);
- if (kiocb->ki_pos == -1) {
- if (!(file->f_mode & FMODE_STREAM)) {
- req->flags |= REQ_F_CUR_POS;
- kiocb->ki_pos = file->f_pos;
- } else {
- kiocb->ki_pos = 0;
- }
- }
- kiocb->ki_flags = iocb_flags(file);
- ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
- if (unlikely(ret))
- return ret;
-
- /*
- * If the file is marked O_NONBLOCK, still allow retry for it if it
- * supports async. Otherwise it's impossible to use O_NONBLOCK files
- * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
- */
- if ((kiocb->ki_flags & IOCB_NOWAIT) ||
- ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
- req->flags |= REQ_F_NOWAIT;
-
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
- return -EOPNOTSUPP;
-
- kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
- kiocb->ki_complete = io_complete_rw_iopoll;
- req->iopoll_completed = 0;
- } else {
- if (kiocb->ki_flags & IOCB_HIPRI)
- return -EINVAL;
- kiocb->ki_complete = io_complete_rw;
- }

ioprio = READ_ONCE(sqe->ioprio);
if (ioprio) {
@@ -3053,6 +2972,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
req->imu = NULL;
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
+ req->rw.flags = READ_ONCE(sqe->rw_flags);
req->buf_index = READ_ONCE(sqe->buf_index);
return 0;
}
@@ -3169,7 +3089,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter
return 0;
}

-static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
+static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
+ unsigned int issue_flags)
{
struct io_mapped_ubuf *imu = req->imu;
u16 index, buf_index = req->buf_index;
@@ -3179,7 +3100,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)

if (unlikely(buf_index >= ctx->nr_user_bufs))
return -EFAULT;
- io_req_set_rsrc_node(req, ctx);
+ io_req_set_rsrc_node(req, ctx, issue_flags);
index = array_index_nospec(buf_index, ctx->nr_user_bufs);
imu = READ_ONCE(ctx->user_bufs[index]);
req->imu = imu;
@@ -3335,7 +3256,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
ssize_t ret;

if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
- ret = io_import_fixed(req, rw, iter);
+ ret = io_import_fixed(req, rw, iter, issue_flags);
if (ret)
return ERR_PTR(ret);
return NULL;
@@ -3533,13 +3454,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
return 0;
}

-static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (unlikely(!(req->file->f_mode & FMODE_READ)))
- return -EBADF;
- return io_prep_rw(req, sqe);
-}
-
/*
* This is our waitqueue callback handler, registered through __folio_lock_async()
* when we initially tried to do the IO with the iocb armed our waitqueue.
@@ -3627,6 +3541,58 @@ static bool need_read_all(struct io_kiocb *req)
S_ISBLK(file_inode(req->file)->i_mode);
}

+static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
+{
+ struct kiocb *kiocb = &req->rw.kiocb;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = req->file;
+ int ret;
+
+ if (unlikely(!file || !(file->f_mode & mode)))
+ return -EBADF;
+
+ if (!io_req_ffs_set(req))
+ req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
+
+ if (kiocb->ki_pos == -1) {
+ if (!(file->f_mode & FMODE_STREAM)) {
+ req->flags |= REQ_F_CUR_POS;
+ kiocb->ki_pos = file->f_pos;
+ } else {
+ kiocb->ki_pos = 0;
+ }
+ }
+
+ kiocb->ki_flags = iocb_flags(file);
+ ret = kiocb_set_rw_flags(kiocb, req->rw.flags);
+ if (unlikely(ret))
+ return ret;
+
+ /*
+ * If the file is marked O_NONBLOCK, still allow retry for it if it
+ * supports async. Otherwise it's impossible to use O_NONBLOCK files
+ * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
+ */
+ if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+ ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
+ req->flags |= REQ_F_NOWAIT;
+
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
+ return -EOPNOTSUPP;
+
+ kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
+ kiocb->ki_complete = io_complete_rw_iopoll;
+ req->iopoll_completed = 0;
+ } else {
+ if (kiocb->ki_flags & IOCB_HIPRI)
+ return -EINVAL;
+ kiocb->ki_complete = io_complete_rw;
+ }
+
+ return 0;
+}
+
static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_rw_state __s, *s = &__s;
@@ -3651,6 +3617,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
}
+ ret = io_rw_init_file(req, FMODE_READ);
+ if (unlikely(ret))
+ return ret;
req->result = iov_iter_count(&s->iter);

if (force_nonblock) {
@@ -3749,14 +3718,6 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
return 0;
}

-static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
- return -EBADF;
- req->rw.kiocb.ki_hint = ki_hint_validate(file_write_hint(req->file));
- return io_prep_rw(req, sqe);
-}
-
static int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_rw_state __s, *s = &__s;
@@ -3776,6 +3737,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
}
+ ret = io_rw_init_file(req, FMODE_WRITE);
+ if (unlikely(ret))
+ return ret;
req->result = iov_iter_count(&s->iter);

if (force_nonblock) {
@@ -4144,18 +4108,11 @@ static int __io_splice_prep(struct io_kiocb *req,
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;

- sp->file_in = NULL;
sp->len = READ_ONCE(sqe->len);
sp->flags = READ_ONCE(sqe->splice_flags);
-
if (unlikely(sp->flags & ~valid_flags))
return -EINVAL;
-
- sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in),
- (sp->flags & SPLICE_F_FD_IN_FIXED));
- if (!sp->file_in)
- return -EBADF;
- req->flags |= REQ_F_NEED_CLEANUP;
+ sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in);
return 0;
}

@@ -4170,20 +4127,29 @@ static int io_tee_prep(struct io_kiocb *req,
static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_splice *sp = &req->splice;
- struct file *in = sp->file_in;
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+ struct file *in;
long ret = 0;

if (issue_flags & IO_URING_F_NONBLOCK)
return -EAGAIN;
+
+ if (sp->flags & SPLICE_F_FD_IN_FIXED)
+ in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+ else
+ in = io_file_get_normal(req, sp->splice_fd_in);
+ if (!in) {
+ ret = -EBADF;
+ goto done;
+ }
+
if (sp->len)
ret = do_tee(in, out, sp->len, flags);

if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
io_put_file(in);
- req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
if (ret != sp->len)
req_set_fail(req);
io_req_complete(req, ret);
@@ -4202,15 +4168,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_splice *sp = &req->splice;
- struct file *in = sp->file_in;
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
loff_t *poff_in, *poff_out;
+ struct file *in;
long ret = 0;

if (issue_flags & IO_URING_F_NONBLOCK)
return -EAGAIN;

+ if (sp->flags & SPLICE_F_FD_IN_FIXED)
+ in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+ else
+ in = io_file_get_normal(req, sp->splice_fd_in);
+ if (!in) {
+ ret = -EBADF;
+ goto done;
+ }
+
poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;

@@ -4219,8 +4194,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags)

if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
io_put_file(in);
- req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
if (ret != sp->len)
req_set_fail(req);
io_req_complete(req, ret);
@@ -4245,9 +4219,6 @@ static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;

- if (!req->file)
- return -EBADF;
-
if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index ||
@@ -5514,7 +5485,7 @@ static void io_poll_remove_entries(struct io_kiocb *req)
* either spurious wakeup or multishot CQE is served. 0 when it's done with
* the request, then the mask is stored in req->result.
*/
-static int io_poll_check_events(struct io_kiocb *req)
+static int io_poll_check_events(struct io_kiocb *req, bool locked)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_poll_iocb *poll = io_poll_get_single(req);
@@ -5536,7 +5507,10 @@ static int io_poll_check_events(struct io_kiocb *req)
if (!req->result) {
struct poll_table_struct pt = { ._key = poll->events };

- req->result = vfs_poll(req->file, &pt) & poll->events;
+ if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED)))
+ req->result = -EBADF;
+ else
+ req->result = vfs_poll(req->file, &pt) & poll->events;
}

/* multishot, just fill an CQE and proceed */
@@ -5570,7 +5544,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
struct io_ring_ctx *ctx = req->ctx;
int ret;

- ret = io_poll_check_events(req);
+ ret = io_poll_check_events(req, *locked);
if (ret > 0)
return;

@@ -5595,7 +5569,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked)
struct io_ring_ctx *ctx = req->ctx;
int ret;

- ret = io_poll_check_events(req);
+ ret = io_poll_check_events(req, *locked);
if (ret > 0)
return;

@@ -6281,6 +6255,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
return -EINVAL;

+ INIT_LIST_HEAD(&req->timeout.list);
data->mode = io_translate_timeout_mode(flags);
hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);

@@ -6507,11 +6482,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
case IORING_OP_READ:
- return io_read_prep(req, sqe);
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
case IORING_OP_WRITE:
- return io_write_prep(req, sqe);
+ return io_prep_rw(req, sqe);
case IORING_OP_POLL_ADD:
return io_poll_add_prep(req, sqe);
case IORING_OP_POLL_REMOVE:
@@ -6689,11 +6663,6 @@ static void io_clean_op(struct io_kiocb *req)
kfree(io->free_iov);
break;
}
- case IORING_OP_SPLICE:
- case IORING_OP_TEE:
- if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED))
- io_put_file(req->splice.file_in);
- break;
case IORING_OP_OPENAT:
case IORING_OP_OPENAT2:
if (req->open.filename)
@@ -6724,11 +6693,6 @@ static void io_clean_op(struct io_kiocb *req)
kfree(req->apoll);
req->apoll = NULL;
}
- if (req->flags & REQ_F_INFLIGHT) {
- struct io_uring_task *tctx = req->task->io_uring;
-
- atomic_dec(&tctx->inflight_tracked);
- }
if (req->flags & REQ_F_CREDS)
put_cred(req->creds);
if (req->flags & REQ_F_ASYNC_DATA) {
@@ -6738,6 +6702,23 @@ static void io_clean_op(struct io_kiocb *req)
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}

+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags)
+{
+ if (req->file || !io_op_defs[req->opcode].needs_file)
+ return true;
+
+ if (req->flags & REQ_F_FIXED_FILE)
+ req->file = io_file_get_fixed(req, req->work.fd, issue_flags);
+ else
+ req->file = io_file_get_normal(req, req->work.fd);
+ if (req->file)
+ return true;
+
+ req_set_fail(req);
+ req->result = -EBADF;
+ return false;
+}
+
static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
const struct cred *creds = NULL;
@@ -6748,6 +6729,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)

if (!io_op_defs[req->opcode].audit_skip)
audit_uring_entry(req->opcode);
+ if (unlikely(!io_assign_file(req, issue_flags)))
+ return -EBADF;

switch (req->opcode) {
case IORING_OP_NOP:
@@ -6889,10 +6872,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
static void io_wq_submit_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ const struct io_op_def *def = &io_op_defs[req->opcode];
unsigned int issue_flags = IO_URING_F_UNLOCKED;
bool needs_poll = false;
struct io_kiocb *timeout;
- int ret = 0;
+ int ret = 0, err = -ECANCELED;

/* one will be dropped by ->io_free_work() after returning to io-wq */
if (!(req->flags & REQ_F_REFCOUNT))
@@ -6904,14 +6888,18 @@ static void io_wq_submit_work(struct io_wq_work *work)
if (timeout)
io_queue_linked_timeout(timeout);

+ if (!io_assign_file(req, issue_flags)) {
+ err = -EBADF;
+ work->flags |= IO_WQ_WORK_CANCEL;
+ }
+
/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
if (work->flags & IO_WQ_WORK_CANCEL) {
- io_req_task_queue_fail(req, -ECANCELED);
+ io_req_task_queue_fail(req, err);
return;
}

if (req->flags & REQ_F_FORCE_ASYNC) {
- const struct io_op_def *def = &io_op_defs[req->opcode];
bool opcode_poll = def->pollin || def->pollout;

if (opcode_poll && file_can_poll(req->file)) {
@@ -6968,46 +6956,56 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file
file_slot->file_ptr = file_ptr;
}

-static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd)
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+ unsigned int issue_flags)
{
- struct file *file;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = NULL;
unsigned long file_ptr;

+ if (issue_flags & IO_URING_F_UNLOCKED)
+ mutex_lock(&ctx->uring_lock);
+
if (unlikely((unsigned int)fd >= ctx->nr_user_files))
- return NULL;
+ goto out;
fd = array_index_nospec(fd, ctx->nr_user_files);
file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
file = (struct file *) (file_ptr & FFS_MASK);
file_ptr &= ~FFS_MASK;
/* mask in overlapping REQ_F and FFS bits */
req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
- io_req_set_rsrc_node(req, ctx);
+ io_req_set_rsrc_node(req, ctx, 0);
+out:
+ if (issue_flags & IO_URING_F_UNLOCKED)
+ mutex_unlock(&ctx->uring_lock);
return file;
}

-static struct file *io_file_get_normal(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd)
+/*
+ * Drop the file for requeue operations. Only used of req->file is the
+ * io_uring descriptor itself.
+ */
+static void io_drop_inflight_file(struct io_kiocb *req)
+{
+ if (unlikely(req->flags & REQ_F_INFLIGHT)) {
+ fput(req->file);
+ req->file = NULL;
+ req->flags &= ~REQ_F_INFLIGHT;
+ }
+}
+
+static struct file *io_file_get_normal(struct io_kiocb *req, int fd)
{
struct file *file = fget(fd);

- trace_io_uring_file_get(ctx, fd);
+ trace_io_uring_file_get(req->ctx, fd);

/* we don't allow fixed io_uring files */
- if (file && unlikely(file->f_op == &io_uring_fops))
- io_req_track_inflight(req);
+ if (file && file->f_op == &io_uring_fops)
+ req->flags |= REQ_F_INFLIGHT;
return file;
}

-static inline struct file *io_file_get(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd, bool fixed)
-{
- if (fixed)
- return io_file_get_fixed(ctx, req, fd);
- else
- return io_file_get_normal(ctx, req, fd);
-}
-
static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
{
struct io_kiocb *prev = req->timeout.prev;
@@ -7245,6 +7243,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
if (io_op_defs[opcode].needs_file) {
struct io_submit_state *state = &ctx->submit_state;

+ req->work.fd = READ_ONCE(sqe->fd);
+
/*
* Plug now if we have more than 2 IO left after this, and the
* target is potentially a read/write to block based storage.
@@ -7254,11 +7254,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
state->need_plug = false;
blk_start_plug_nr_ios(&state->plug, state->submit_nr);
}
-
- req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
- (sqe_flags & IOSQE_FIXED_FILE));
- if (unlikely(!req->file))
- return -EBADF;
}

personality = READ_ONCE(sqe->personality);
@@ -8237,8 +8232,12 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
skb_queue_head(&sk->sk_receive_queue, skb);

- for (i = 0; i < nr_files; i++)
- fput(fpl->fp[i]);
+ for (i = 0; i < nr; i++) {
+ struct file *file = io_file_from_index(ctx, i + offset);
+
+ if (file)
+ fput(file);
+ }
} else {
kfree_skb(skb);
free_uid(fpl->user);
@@ -8700,7 +8699,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
err = -EBADF;
break;
}
- *io_get_tag_slot(data, up->offset + done) = tag;
+ *io_get_tag_slot(data, i) = tag;
io_fixed_file_set(file_slot, file);
err = io_sqe_file_register(ctx, file, i);
if (err) {
@@ -8775,7 +8774,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task,
xa_init(&tctx->xa);
init_waitqueue_head(&tctx->wait);
atomic_set(&tctx->in_idle, 0);
- atomic_set(&tctx->inflight_tracked, 0);
task->io_uring = tctx;
spin_lock_init(&tctx->task_lock);
INIT_WQ_LIST(&tctx->task_list);
@@ -9913,7 +9911,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
{
if (tracked)
- return atomic_read(&tctx->inflight_tracked);
+ return 0;
return percpu_counter_sum(&tctx->inflight);
}

@@ -10866,7 +10864,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
if (len > cpumask_size())
len = cpumask_size();

- if (copy_from_user(new_mask, arg, len)) {
+ if (in_compat_syscall()) {
+ ret = compat_get_bitmap(cpumask_bits(new_mask),
+ (const compat_ulong_t __user *)arg,
+ len * 8 /* CHAR_BIT */);
+ } else {
+ ret = copy_from_user(new_mask, arg, len);
+ }
+
+ if (ret) {
free_cpumask_var(new_mask);
return -EFAULT;
}
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 57ab424c05ff..072821b50ab9 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -146,12 +146,13 @@ void jfs_evict_inode(struct inode *inode)
dquot_initialize(inode);

if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
+ struct inode *ipimap = JFS_SBI(inode->i_sb)->ipimap;
truncate_inode_pages_final(&inode->i_data);

if (test_cflag(COMMIT_Freewmap, inode))
jfs_free_zero_link(inode);

- if (JFS_SBI(inode->i_sb)->ipimap)
+ if (ipimap && JFS_IP(ipimap)->i_imap)
diFree(inode);

/*
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index a71f1cf894b9..d4bd94234ef7 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -447,7 +447,8 @@ static const struct address_space_operations minix_aops = {
.writepage = minix_writepage,
.write_begin = minix_write_begin,
.write_end = generic_write_end,
- .bmap = minix_bmap
+ .bmap = minix_bmap,
+ .direct_IO = noop_direct_IO
};

static const struct inode_operations minix_symlink_inode_operations = {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 75cb1cbe4cde..911bdb35eb08 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1853,16 +1853,6 @@ const struct dentry_operations nfs4_dentry_operations = {
};
EXPORT_SYMBOL_GPL(nfs4_dentry_operations);

-static fmode_t flags_to_mode(int flags)
-{
- fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
- if ((flags & O_ACCMODE) != O_WRONLY)
- res |= FMODE_READ;
- if ((flags & O_ACCMODE) != O_RDONLY)
- res |= FMODE_WRITE;
- return res;
-}
-
static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp)
{
return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index eabfdab543c8..11c566d8769f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -173,8 +173,8 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);

if (iov_iter_rw(iter) == READ)
- return nfs_file_direct_read(iocb, iter);
- return nfs_file_direct_write(iocb, iter);
+ return nfs_file_direct_read(iocb, iter, true);
+ return nfs_file_direct_write(iocb, iter, true);
}

static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -425,6 +425,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_read - file direct read operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers into which to read data
+ * @swap: flag indicating this is swap IO, not O_DIRECT IO
*
* We use this function for direct reads instead of calling
* generic_file_aio_read() in order to avoid gfar's check to see if
@@ -440,7 +441,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* client must read the updated atime from the server back into its
* cache.
*/
-ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
+ bool swap)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -482,12 +484,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
if (iter_is_iovec(iter))
dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;

- nfs_start_io_direct(inode);
+ if (!swap)
+ nfs_start_io_direct(inode);

NFS_I(inode)->read_io += count;
requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);

- nfs_end_io_direct(inode);
+ if (!swap)
+ nfs_end_io_direct(inode);

if (requested > 0) {
result = nfs_direct_wait(dreq);
@@ -790,7 +794,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
*/
static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
struct iov_iter *iter,
- loff_t pos)
+ loff_t pos, int ioflags)
{
struct nfs_pageio_descriptor desc;
struct inode *inode = dreq->inode;
@@ -798,7 +802,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
size_t requested_bytes = 0;
size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE);

- nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
+ nfs_pageio_init_write(&desc, inode, ioflags, false,
&nfs_direct_write_completion_ops);
desc.pg_dreq = dreq;
get_dreq(dreq);
@@ -876,6 +880,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_write - file direct write operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers from which to write data
+ * @swap: flag indicating this is swap IO, not O_DIRECT IO
*
* We use this function for direct writes instead of calling
* generic_file_aio_write() in order to avoid taking the inode
@@ -892,7 +897,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
* Note that O_APPEND is not supported for NFS direct writes, as there
* is no atomic O_APPEND write facility in the NFS protocol.
*/
-ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
+ bool swap)
{
ssize_t result, requested;
size_t count;
@@ -906,7 +912,11 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
file, iov_iter_count(iter), (long long) iocb->ki_pos);

- result = generic_write_checks(iocb, iter);
+ if (swap)
+ /* bypass generic checks */
+ result = iov_iter_count(iter);
+ else
+ result = generic_write_checks(iocb, iter);
if (result <= 0)
return result;
count = result;
@@ -937,16 +947,22 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
dreq->iocb = iocb;
pnfs_init_ds_commit_info_ops(&dreq->ds_cinfo, inode);

- nfs_start_io_direct(inode);
+ if (swap) {
+ requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
+ FLUSH_STABLE);
+ } else {
+ nfs_start_io_direct(inode);

- requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+ requested = nfs_direct_write_schedule_iovec(dreq, iter, pos,
+ FLUSH_COND_STABLE);

- if (mapping->nrpages) {
- invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT, end);
- }
+ if (mapping->nrpages) {
+ invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_SHIFT, end);
+ }

- nfs_end_io_direct(inode);
+ nfs_end_io_direct(inode);
+ }

if (requested > 0) {
result = nfs_direct_wait(dreq);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 76d76acbc594..d8583f57ff99 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -162,7 +162,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
ssize_t result;

if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_read(iocb, to);
+ return nfs_file_direct_read(iocb, to, false);

dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
@@ -619,7 +619,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
return result;

if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_write(iocb, from);
+ return nfs_file_direct_write(iocb, from, false);

dprintk("NFS: write(%pD2, %zu@%Ld)\n",
file, iov_iter_count(from), (long long) iocb->ki_pos);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index d96baa4450e3..e4fb939a2904 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp)
nfs_fscache_open_file(inode, filp);
return 0;
}
-EXPORT_SYMBOL_GPL(nfs_open);

/*
* This function is called whenever some part of NFS notices that
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2de7c56a1fbe..465e39ff018d 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry)
return true;
}

+static inline fmode_t flags_to_mode(int flags)
+{
+ fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
+ if ((flags & O_ACCMODE) != O_WRONLY)
+ res |= FMODE_READ;
+ if ((flags & O_ACCMODE) != O_RDONLY)
+ res |= FMODE_WRITE;
+ return res;
+}
+
/*
* Note: RFC 1813 doesn't limit the number of auth flavors that
* a server can return, so make something up.
@@ -573,6 +583,13 @@ nfs_write_match_verf(const struct nfs_writeverf *verf,
!nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier);
}

+static inline gfp_t nfs_io_gfp_mask(void)
+{
+ if (current->flags & PF_WQ_WORKER)
+ return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+ return GFP_KERNEL;
+}
+
/* unlink.c */
extern struct rpc_task *
nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 32129446beca..ca878d021fab 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -591,8 +591,10 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst,

ctx = get_nfs_open_context(nfs_file_open_context(src));
l_ctx = nfs_get_lock_context(ctx);
- if (IS_ERR(l_ctx))
- return PTR_ERR(l_ctx);
+ if (IS_ERR(l_ctx)) {
+ status = PTR_ERR(l_ctx);
+ goto out;
+ }

status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx,
FMODE_READ);
@@ -600,7 +602,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
if (status) {
if (status == -EAGAIN)
status = -NFS4ERR_BAD_STATEID;
- return status;
+ goto out;
}

status = nfs4_call_sync(src_server->client, src_server, &msg,
@@ -609,6 +611,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst,
if (status == -ENOTSUPP)
src_server->caps &= ~NFS_CAP_COPY_NOTIFY;

+out:
put_nfs_open_context(nfs_file_open_context(src));
return status;
}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index e79ae4cbc395..e34af48fb4f4 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
struct dentry *parent = NULL;
struct inode *dir;
unsigned openflags = filp->f_flags;
+ fmode_t f_mode;
struct iattr attr;
int err;

@@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp)
if (err)
return err;

+ f_mode = filp->f_mode;
if ((openflags & O_ACCMODE) == 3)
- return nfs_open(inode, filp);
+ f_mode |= flags_to_mode(openflags);

/* We can't create new files here */
openflags &= ~(O_CREAT|O_EXCL);
@@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
parent = dget_parent(dentry);
dir = d_inode(parent);

- ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp);
+ ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp);
err = PTR_ERR(ctx);
if (IS_ERR(ctx))
goto out;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index f5a62c0d999b..0f4818627ef0 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -49,6 +49,7 @@
#include <linux/workqueue.h>
#include <linux/bitops.h>
#include <linux/jiffies.h>
+#include <linux/sched/mm.h>

#include <linux/sunrpc/clnt.h>

@@ -2560,9 +2561,17 @@ static void nfs4_layoutreturn_any_run(struct nfs_client *clp)

static void nfs4_state_manager(struct nfs_client *clp)
{
+ unsigned int memflags;
int status = 0;
const char *section = "", *section_sep = "";

+ /*
+ * State recovery can deadlock if the direct reclaim code tries
+ * start NFS writeback. So ensure memory allocations are all
+ * GFP_NOFS.
+ */
+ memflags = memalloc_nofs_save();
+
/* Ensure exclusive access to NFSv4 state */
do {
trace_nfs4_state_mgr(clp);
@@ -2657,6 +2666,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
}

+ memalloc_nofs_restore(memflags);
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);

@@ -2674,6 +2684,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
return;
if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
return;
+ memflags = memalloc_nofs_save();
} while (refcount_read(&clp->cl_count) > 1 && !signalled());
goto out_drain;

@@ -2686,6 +2697,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
clp->cl_hostname, -status);
ssleep(1);
out_drain:
+ memalloc_nofs_restore(memflags);
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 815d63080245..9157dd19b8b4 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -90,10 +90,10 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
}
}

-static inline struct nfs_page *
-nfs_page_alloc(void)
+static inline struct nfs_page *nfs_page_alloc(void)
{
- struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
+ struct nfs_page *p =
+ kmem_cache_zalloc(nfs_page_cachep, nfs_io_gfp_mask());
if (p)
INIT_LIST_HEAD(&p->wb_list);
return p;
@@ -892,7 +892,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
struct nfs_commit_info cinfo;
struct nfs_page_array *pg_array = &hdr->page_array;
unsigned int pagecount, pageused;
- gfp_t gfp_flags = GFP_KERNEL;
+ gfp_t gfp_flags = nfs_io_gfp_mask();

pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
pg_array->npages = pagecount;
@@ -979,7 +979,7 @@ nfs_pageio_alloc_mirrors(struct nfs_pageio_descriptor *desc,
desc->pg_mirrors_dynamic = NULL;
if (mirror_count == 1)
return desc->pg_mirrors_static;
- ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_KERNEL);
+ ret = kmalloc_array(mirror_count, sizeof(*ret), nfs_io_gfp_mask());
if (ret != NULL) {
for (i = 0; i < mirror_count; i++)
nfs_pageio_mirror_init(&ret[i], desc->pg_bsize);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 316f68f96e57..657c242a18ff 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -419,7 +419,7 @@ static struct nfs_commit_data *
pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo)
{
- struct nfs_commit_data *data = nfs_commitdata_alloc(false);
+ struct nfs_commit_data *data = nfs_commitdata_alloc();

if (!data)
return NULL;
@@ -515,7 +515,11 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
unsigned int nreq = 0;

if (!list_empty(mds_pages)) {
- data = nfs_commitdata_alloc(true);
+ data = nfs_commitdata_alloc();
+ if (!data) {
+ nfs_retry_commit(mds_pages, NULL, cinfo, -1);
+ return -ENOMEM;
+ }
data->ds_commit_index = -1;
list_splice_init(mds_pages, &data->pages);
list_add_tail(&data->list, &list);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 60693ab6a032..938850303099 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -70,27 +70,17 @@ static mempool_t *nfs_wdata_mempool;
static struct kmem_cache *nfs_cdata_cachep;
static mempool_t *nfs_commit_mempool;

-struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail)
+struct nfs_commit_data *nfs_commitdata_alloc(void)
{
struct nfs_commit_data *p;

- if (never_fail)
- p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
- else {
- /* It is OK to do some reclaim, not no safe to wait
- * for anything to be returned to the pool.
- * mempool_alloc() cannot handle that particular combination,
- * so we need two separate attempts.
- */
+ p = kmem_cache_zalloc(nfs_cdata_cachep, nfs_io_gfp_mask());
+ if (!p) {
p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT);
- if (!p)
- p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO |
- __GFP_NOWARN | __GFP_NORETRY);
if (!p)
return NULL;
+ memset(p, 0, sizeof(*p));
}
-
- memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->pages);
return p;
}
@@ -104,9 +94,15 @@ EXPORT_SYMBOL_GPL(nfs_commit_free);

static struct nfs_pgio_header *nfs_writehdr_alloc(void)
{
- struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_KERNEL);
+ struct nfs_pgio_header *p;

- memset(p, 0, sizeof(*p));
+ p = kmem_cache_zalloc(nfs_wdata_cachep, nfs_io_gfp_mask());
+ if (!p) {
+ p = mempool_alloc(nfs_wdata_mempool, GFP_NOWAIT);
+ if (!p)
+ return NULL;
+ memset(p, 0, sizeof(*p));
+ }
p->rw_mode = FMODE_WRITE;
return p;
}
@@ -1826,7 +1822,11 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
if (list_empty(head))
return 0;

- data = nfs_commitdata_alloc(true);
+ data = nfs_commitdata_alloc();
+ if (!data) {
+ nfs_retry_commit(head, NULL, cinfo, -1);
+ return -ENOMEM;
+ }

/* Set up the argument struct */
nfs_init_commit(data, head, NULL, cinfo);
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index b0728c8ad90c..f8996b46f430 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -218,6 +218,15 @@ struct gpio_irq_chip {
*/
bool per_parent_data;

+ /**
+ * @initialized:
+ *
+ * Flag to track GPIO chip irq member's initialization.
+ * This flag will make sure GPIO chip irq members are not used
+ * before they are initialized.
+ */
+ bool initialized;
+
/**
* @init_hw: optional routine to initialize hardware before
* an IRQ chip will be added. This is quite useful when
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index a59d25f19385..b8641dc0ee66 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -51,7 +51,7 @@ struct ipv6_devconf {
__s32 use_optimistic;
#endif
#ifdef CONFIG_IPV6_MROUTE
- __s32 mc_forwarding;
+ atomic_t mc_forwarding;
#endif
__s32 disable_ipv6;
__s32 drop_unicast_in_l2_multicast;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index aed44e9b5d89..c7a0d500b396 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1389,13 +1389,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms)

static inline struct mem_section *__nr_to_section(unsigned long nr)
{
+ unsigned long root = SECTION_NR_TO_ROOT(nr);
+
+ if (unlikely(root >= NR_SECTION_ROOTS))
+ return NULL;
+
#ifdef CONFIG_SPARSEMEM_EXTREME
- if (!mem_section)
+ if (!mem_section || !mem_section[root])
return NULL;
#endif
- if (!mem_section[SECTION_NR_TO_ROOT(nr)])
- return NULL;
- return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
+ return &mem_section[root][nr & SECTION_ROOT_MASK];
}
extern size_t mem_section_usage_size(void);

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 68f81d8d36de..c9d3dc79d587 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -513,10 +513,10 @@ static inline const struct cred *nfs_file_cred(struct file *file)
* linux/fs/nfs/direct.c
*/
extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *);
-extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
- struct iov_iter *iter);
-extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
- struct iov_iter *iter);
+ssize_t nfs_file_direct_read(struct kiocb *iocb,
+ struct iov_iter *iter, bool swap);
+ssize_t nfs_file_direct_write(struct kiocb *iocb,
+ struct iov_iter *iter, bool swap);

/*
* linux/fs/nfs/dir.c
@@ -585,7 +585,7 @@ extern int nfs_wb_all(struct inode *inode);
extern int nfs_wb_page(struct inode *inode, struct page *page);
extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
extern int nfs_commit_inode(struct inode *, int);
-extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail);
+extern struct nfs_commit_data *nfs_commitdata_alloc(void);
extern void nfs_commit_free(struct nfs_commit_data *data);
bool nfs_commit_end(struct nfs_mds_commit_info *cinfo);

diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h
index 60f3453be23e..a443abda937d 100644
--- a/include/linux/ref_tracker.h
+++ b/include/linux/ref_tracker.h
@@ -13,6 +13,7 @@ struct ref_tracker_dir {
spinlock_t lock;
unsigned int quarantine_avail;
refcount_t untracked;
+ bool dead;
struct list_head list; /* List of active trackers */
struct list_head quarantine; /* List of dead trackers */
#endif
@@ -26,6 +27,7 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
INIT_LIST_HEAD(&dir->quarantine);
spin_lock_init(&dir->lock);
dir->quarantine_avail = quarantine_count;
+ dir->dead = false;
refcount_set(&dir->untracked, 1);
stack_depot_init();
}
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 3e56a9751c06..fcc5b48989b3 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -248,10 +248,7 @@ static inline int static_call_text_reserved(void *start, void *end)
return 0;
}

-static inline long __static_call_return0(void)
-{
- return 0;
-}
+extern long __static_call_return0(void);

#define EXPORT_STATIC_CALL(name) \
EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index ef9a44b6cf5d..ae6f4838ab75 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -159,8 +159,17 @@ extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev,
extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite);

+#ifdef CONFIG_VFIO_PCI_VGA
extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf,
size_t count, loff_t *ppos, bool iswrite);
+#else
+static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev,
+ char __user *buf, size_t count,
+ loff_t *ppos, bool iswrite)
+{
+ return -EINVAL;
+}
+#endif

extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
uint64_t data, int count, int fd);
diff --git a/include/net/arp.h b/include/net/arp.h
index 031374ac2f22..d7ef4ec71dfe 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -65,6 +65,7 @@ void arp_send(int type, int ptype, __be32 dest_ip,
const unsigned char *src_hw, const unsigned char *th);
int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir);
void arp_ifdown(struct net_device *dev);
+int arp_invalidate(struct net_device *dev, __be32 ip, bool force);

struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
struct net_device *dev, __be32 src_ip,
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index a647e5fabdbd..2aa5e95808a5 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -204,19 +204,21 @@ void bt_err_ratelimited(const char *fmt, ...);
#define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__)
#endif

+#define bt_dev_name(hdev) ((hdev) ? (hdev)->name : "null")
+
#define bt_dev_info(hdev, fmt, ...) \
- BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+ BT_INFO("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__)
#define bt_dev_warn(hdev, fmt, ...) \
- BT_WARN("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+ BT_WARN("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__)
#define bt_dev_err(hdev, fmt, ...) \
- BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+ BT_ERR("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__)
#define bt_dev_dbg(hdev, fmt, ...) \
- BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+ BT_DBG("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__)

#define bt_dev_warn_ratelimited(hdev, fmt, ...) \
- bt_warn_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+ bt_warn_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__)
#define bt_dev_err_ratelimited(hdev, fmt, ...) \
- bt_err_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__)
+ bt_err_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__)

/* Connection and socket states */
enum {
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index e336e9c1dda4..36d727f94ac2 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -294,6 +294,9 @@ struct adv_monitor {

#define HCI_MAX_SHORT_NAME_LENGTH 10

+#define HCI_CONN_HANDLE_UNSET 0xffff
+#define HCI_CONN_HANDLE_MAX 0x0eff
+
/* Min encryption key size to match with SMP */
#define HCI_MIN_ENC_KEY_SIZE 7

diff --git a/include/net/mctp.h b/include/net/mctp.h
index 7e35ec79b909..204ae3aebc0d 100644
--- a/include/net/mctp.h
+++ b/include/net/mctp.h
@@ -36,8 +36,6 @@ struct mctp_hdr {
#define MCTP_HDR_TAG_SHIFT 0
#define MCTP_HDR_TAG_MASK GENMASK(2, 0)

-#define MCTP_HEADER_MAXLEN 4
-
#define MCTP_INITIAL_DEFAULT_NET 1

static inline bool mctp_address_ok(mctp_eid_t eid)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 5b61c462e534..374cc7b260fc 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -513,4 +513,10 @@ static inline void fnhe_genid_bump(struct net *net)
atomic_inc(&net->fnhe_genid);
}

+#ifdef CONFIG_NET
+void net_ns_init(void);
+#else
+static inline void net_ns_init(void) {}
+#endif
+
#endif /* __NET_NET_NAMESPACE_H */
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 29982d60b68a..5be3faf88c1a 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1005,7 +1005,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect);
DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto);
DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done);
DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force);
-DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup);
DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy);

DECLARE_EVENT_CLASS(rpc_xprt_event,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 015bfec0dbfd..4b46021eafa9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5500,7 +5500,8 @@ struct bpf_sock {
__u32 src_ip4;
__u32 src_ip6[4];
__u32 src_port; /* host byte order */
- __u32 dst_port; /* network byte order */
+ __be16 dst_port; /* network byte order */
+ __u16 :16; /* zero padding */
__u32 dst_ip4;
__u32 dst_ip6[4];
__u32 state;
@@ -6378,7 +6379,8 @@ struct bpf_sk_lookup {
__u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
__u32 remote_ip4; /* Network byte order */
__u32 remote_ip6[4]; /* Network byte order */
- __u32 remote_port; /* Network byte order */
+ __be16 remote_port; /* Network byte order */
+ __u16 :16; /* Zero padding */
__u32 local_ip4; /* Network byte order */
__u32 local_ip6[4]; /* Network byte order */
__u32 local_port; /* Host byte order */
diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h
index c55935b64ccc..590f8aea2b6d 100644
--- a/include/uapi/linux/can/isotp.h
+++ b/include/uapi/linux/can/isotp.h
@@ -137,20 +137,16 @@ struct can_isotp_ll_options {
#define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */
#define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */

-/* default values */
+/* protocol machine default values */

#define CAN_ISOTP_DEFAULT_FLAGS 0
#define CAN_ISOTP_DEFAULT_EXT_ADDRESS 0x00
#define CAN_ISOTP_DEFAULT_PAD_CONTENT 0xCC /* prevent bit-stuffing */
-#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 0
+#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 50000 /* 50 micro seconds */
#define CAN_ISOTP_DEFAULT_RECV_BS 0
#define CAN_ISOTP_DEFAULT_RECV_STMIN 0x00
#define CAN_ISOTP_DEFAULT_RECV_WFTMAX 0

-#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU
-#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN
-#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0
-
/*
* Remark on CAN_ISOTP_DEFAULT_RECV_* values:
*
@@ -162,4 +158,24 @@ struct can_isotp_ll_options {
* consistency and copied directly into the flow control (FC) frame.
*/

+/* link layer default values => make use of Classical CAN frames */
+
+#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU
+#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN
+#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0
+
+/*
+ * The CAN_ISOTP_DEFAULT_FRAME_TXTIME has become a non-zero value as
+ * it only makes sense for isotp implementation tests to run without
+ * a N_As value. As user space applications usually do not set the
+ * frame_txtime element of struct can_isotp_options the new in-kernel
+ * default is very likely overwritten with zero when the sockopt()
+ * CAN_ISOTP_OPTS is invoked.
+ * To make sure that a N_As value of zero is only set intentional the
+ * value '0' is now interpreted as 'do not change the current value'.
+ * When a frame_txtime of zero is required for testing purposes this
+ * CAN_ISOTP_FRAME_TXTIME_ZERO u32 value has to be set in frame_txtime.
+ */
+#define CAN_ISOTP_FRAME_TXTIME_ZERO 0xFFFFFFFF
+
#endif /* !_UAPI_CAN_ISOTP_H */
diff --git a/init/main.c b/init/main.c
index 65fa2e41a9c0..9a5097b2251a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -99,6 +99,7 @@
#include <linux/kcsan.h>
#include <linux/init_syscalls.h>
#include <linux/stackdepot.h>
+#include <net/net_namespace.h>

#include <asm/io.h>
#include <asm/bugs.h>
@@ -1116,6 +1117,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
key_init();
security_init();
dbg_late_init();
+ net_ns_init();
vfs_caches_init();
pagecache_init();
signals_init();
@@ -1190,7 +1192,7 @@ static int __init initcall_blacklist(char *str)
}
} while (str_entry);

- return 0;
+ return 1;
}

static bool __init_or_module initcall_blacklisted(initcall_t fn)
@@ -1452,7 +1454,9 @@ static noinline void __init kernel_init_freeable(void);
bool rodata_enabled __ro_after_init = true;
static int __init set_debug_rodata(char *str)
{
- return strtobool(str, &rodata_enabled);
+ if (strtobool(str, &rodata_enabled))
+ pr_warn("Invalid option string for rodata: '%s'\n", str);
+ return 1;
}
__setup("rodata=", set_debug_rodata);
#endif
diff --git a/kernel/Makefile b/kernel/Makefile
index 56f4ee97f328..a18d169732d2 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -113,7 +113,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o
obj-$(CONFIG_BPF) += bpf/
obj-$(CONFIG_KCSAN) += kcsan/
obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
-obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o
+obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o
+obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o
obj-$(CONFIG_CFI_CLANG) += cfi.o

obj-$(CONFIG_PERF_EVENTS) += events/
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 69cf71d97312..0ee9ffceb976 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11640,6 +11640,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,

event->state = PERF_EVENT_STATE_INACTIVE;

+ if (parent_event)
+ event->event_caps = parent_event->event_caps;
+
if (event->attr.sigtrap)
atomic_set(&event->event_limit, 1);

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1620ae8535dc..1eec4925b8c6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5675,6 +5675,8 @@ static inline struct task_struct *pick_task(struct rq *rq)

extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);

+static void queue_core_balance(struct rq *rq);
+
static struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
@@ -5724,7 +5726,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
}

rq->core_pick = NULL;
- return next;
+ goto out;
}

put_prev_task_balance(rq, prev, rf);
@@ -5774,7 +5776,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
*/
WARN_ON_ONCE(fi_before);
task_vruntime_update(rq, next, false);
- goto done;
+ goto out_set_next;
}
}

@@ -5893,8 +5895,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
resched_curr(rq_i);
}

-done:
+out_set_next:
set_next_task(rq, next);
+out:
+ if (rq->core->core_forceidle_count && next == rq->idle)
+ queue_core_balance(rq);
+
return next;
}

@@ -5923,7 +5929,7 @@ static bool try_steal_cookie(int this, int that)
if (p == src->core_pick || p == src->curr)
goto next;

- if (!cpumask_test_cpu(this, &p->cpus_mask))
+ if (!is_cpu_allowed(p, this))
goto next;

if (p->core_occupation > dst->idle->core_occupation)
@@ -5989,7 +5995,7 @@ static void sched_core_balance(struct rq *rq)

static DEFINE_PER_CPU(struct callback_head, core_balance_head);

-void queue_core_balance(struct rq *rq)
+static void queue_core_balance(struct rq *rq)
{
if (!sched_core_enabled(rq))
return;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index d17b0a5ce6ac..314c36fc9c42 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -437,7 +437,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
{
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
- queue_core_balance(rq);
}

#ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9b33ba9c3c42..e8a5549488dd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1247,8 +1247,6 @@ static inline bool sched_group_cookie_match(struct rq *rq,
return false;
}

-extern void queue_core_balance(struct rq *rq);
-
static inline bool sched_core_enqueued(struct task_struct *p)
{
return !RB_EMPTY_NODE(&p->core_node);
@@ -1282,10 +1280,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
return &rq->__lock;
}

-static inline void queue_core_balance(struct rq *rq)
-{
-}
-
static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p)
{
return true;
diff --git a/kernel/static_call.c b/kernel/static_call.c
index 43ba0b1e0edb..e9c3e69f3837 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -1,548 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
#include <linux/static_call.h>
-#include <linux/bug.h>
-#include <linux/smp.h>
-#include <linux/sort.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/processor.h>
-#include <asm/sections.h>
-
-extern struct static_call_site __start_static_call_sites[],
- __stop_static_call_sites[];
-extern struct static_call_tramp_key __start_static_call_tramp_key[],
- __stop_static_call_tramp_key[];
-
-static bool static_call_initialized;
-
-/* mutex to protect key modules/sites */
-static DEFINE_MUTEX(static_call_mutex);
-
-static void static_call_lock(void)
-{
- mutex_lock(&static_call_mutex);
-}
-
-static void static_call_unlock(void)
-{
- mutex_unlock(&static_call_mutex);
-}
-
-static inline void *static_call_addr(struct static_call_site *site)
-{
- return (void *)((long)site->addr + (long)&site->addr);
-}
-
-static inline unsigned long __static_call_key(const struct static_call_site *site)
-{
- return (long)site->key + (long)&site->key;
-}
-
-static inline struct static_call_key *static_call_key(const struct static_call_site *site)
-{
- return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
-}
-
-/* These assume the key is word-aligned. */
-static inline bool static_call_is_init(struct static_call_site *site)
-{
- return __static_call_key(site) & STATIC_CALL_SITE_INIT;
-}
-
-static inline bool static_call_is_tail(struct static_call_site *site)
-{
- return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
-}
-
-static inline void static_call_set_init(struct static_call_site *site)
-{
- site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
- (long)&site->key;
-}
-
-static int static_call_site_cmp(const void *_a, const void *_b)
-{
- const struct static_call_site *a = _a;
- const struct static_call_site *b = _b;
- const struct static_call_key *key_a = static_call_key(a);
- const struct static_call_key *key_b = static_call_key(b);
-
- if (key_a < key_b)
- return -1;
-
- if (key_a > key_b)
- return 1;
-
- return 0;
-}
-
-static void static_call_site_swap(void *_a, void *_b, int size)
-{
- long delta = (unsigned long)_a - (unsigned long)_b;
- struct static_call_site *a = _a;
- struct static_call_site *b = _b;
- struct static_call_site tmp = *a;
-
- a->addr = b->addr - delta;
- a->key = b->key - delta;
-
- b->addr = tmp.addr + delta;
- b->key = tmp.key + delta;
-}
-
-static inline void static_call_sort_entries(struct static_call_site *start,
- struct static_call_site *stop)
-{
- sort(start, stop - start, sizeof(struct static_call_site),
- static_call_site_cmp, static_call_site_swap);
-}
-
-static inline bool static_call_key_has_mods(struct static_call_key *key)
-{
- return !(key->type & 1);
-}
-
-static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
-{
- if (!static_call_key_has_mods(key))
- return NULL;
-
- return key->mods;
-}
-
-static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
-{
- if (static_call_key_has_mods(key))
- return NULL;
-
- return (struct static_call_site *)(key->type & ~1);
-}
-
-void __static_call_update(struct static_call_key *key, void *tramp, void *func)
-{
- struct static_call_site *site, *stop;
- struct static_call_mod *site_mod, first;
-
- cpus_read_lock();
- static_call_lock();
-
- if (key->func == func)
- goto done;
-
- key->func = func;
-
- arch_static_call_transform(NULL, tramp, func, false);
-
- /*
- * If uninitialized, we'll not update the callsites, but they still
- * point to the trampoline and we just patched that.
- */
- if (WARN_ON_ONCE(!static_call_initialized))
- goto done;
-
- first = (struct static_call_mod){
- .next = static_call_key_next(key),
- .mod = NULL,
- .sites = static_call_key_sites(key),
- };
-
- for (site_mod = &first; site_mod; site_mod = site_mod->next) {
- bool init = system_state < SYSTEM_RUNNING;
- struct module *mod = site_mod->mod;
-
- if (!site_mod->sites) {
- /*
- * This can happen if the static call key is defined in
- * a module which doesn't use it.
- *
- * It also happens in the has_mods case, where the
- * 'first' entry has no sites associated with it.
- */
- continue;
- }
-
- stop = __stop_static_call_sites;
-
- if (mod) {
-#ifdef CONFIG_MODULES
- stop = mod->static_call_sites +
- mod->num_static_call_sites;
- init = mod->state == MODULE_STATE_COMING;
-#endif
- }
-
- for (site = site_mod->sites;
- site < stop && static_call_key(site) == key; site++) {
- void *site_addr = static_call_addr(site);
-
- if (!init && static_call_is_init(site))
- continue;
-
- if (!kernel_text_address((unsigned long)site_addr)) {
- /*
- * This skips patching built-in __exit, which
- * is part of init_section_contains() but is
- * not part of kernel_text_address().
- *
- * Skipping built-in __exit is fine since it
- * will never be executed.
- */
- WARN_ONCE(!static_call_is_init(site),
- "can't patch static call site at %pS",
- site_addr);
- continue;
- }
-
- arch_static_call_transform(site_addr, NULL, func,
- static_call_is_tail(site));
- }
- }
-
-done:
- static_call_unlock();
- cpus_read_unlock();
-}
-EXPORT_SYMBOL_GPL(__static_call_update);
-
-static int __static_call_init(struct module *mod,
- struct static_call_site *start,
- struct static_call_site *stop)
-{
- struct static_call_site *site;
- struct static_call_key *key, *prev_key = NULL;
- struct static_call_mod *site_mod;
-
- if (start == stop)
- return 0;
-
- static_call_sort_entries(start, stop);
-
- for (site = start; site < stop; site++) {
- void *site_addr = static_call_addr(site);
-
- if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
- (!mod && init_section_contains(site_addr, 1)))
- static_call_set_init(site);
-
- key = static_call_key(site);
- if (key != prev_key) {
- prev_key = key;
-
- /*
- * For vmlinux (!mod) avoid the allocation by storing
- * the sites pointer in the key itself. Also see
- * __static_call_update()'s @first.
- *
- * This allows architectures (eg. x86) to call
- * static_call_init() before memory allocation works.
- */
- if (!mod) {
- key->sites = site;
- key->type |= 1;
- goto do_transform;
- }
-
- site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
- if (!site_mod)
- return -ENOMEM;
-
- /*
- * When the key has a direct sites pointer, extract
- * that into an explicit struct static_call_mod, so we
- * can have a list of modules.
- */
- if (static_call_key_sites(key)) {
- site_mod->mod = NULL;
- site_mod->next = NULL;
- site_mod->sites = static_call_key_sites(key);
-
- key->mods = site_mod;
-
- site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
- if (!site_mod)
- return -ENOMEM;
- }
-
- site_mod->mod = mod;
- site_mod->sites = site;
- site_mod->next = static_call_key_next(key);
- key->mods = site_mod;
- }
-
-do_transform:
- arch_static_call_transform(site_addr, NULL, key->func,
- static_call_is_tail(site));
- }
-
- return 0;
-}
-
-static int addr_conflict(struct static_call_site *site, void *start, void *end)
-{
- unsigned long addr = (unsigned long)static_call_addr(site);
-
- if (addr <= (unsigned long)end &&
- addr + CALL_INSN_SIZE > (unsigned long)start)
- return 1;
-
- return 0;
-}
-
-static int __static_call_text_reserved(struct static_call_site *iter_start,
- struct static_call_site *iter_stop,
- void *start, void *end, bool init)
-{
- struct static_call_site *iter = iter_start;
-
- while (iter < iter_stop) {
- if (init || !static_call_is_init(iter)) {
- if (addr_conflict(iter, start, end))
- return 1;
- }
- iter++;
- }
-
- return 0;
-}
-
-#ifdef CONFIG_MODULES
-
-static int __static_call_mod_text_reserved(void *start, void *end)
-{
- struct module *mod;
- int ret;
-
- preempt_disable();
- mod = __module_text_address((unsigned long)start);
- WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
- if (!try_module_get(mod))
- mod = NULL;
- preempt_enable();
-
- if (!mod)
- return 0;
-
- ret = __static_call_text_reserved(mod->static_call_sites,
- mod->static_call_sites + mod->num_static_call_sites,
- start, end, mod->state == MODULE_STATE_COMING);
-
- module_put(mod);
-
- return ret;
-}
-
-static unsigned long tramp_key_lookup(unsigned long addr)
-{
- struct static_call_tramp_key *start = __start_static_call_tramp_key;
- struct static_call_tramp_key *stop = __stop_static_call_tramp_key;
- struct static_call_tramp_key *tramp_key;
-
- for (tramp_key = start; tramp_key != stop; tramp_key++) {
- unsigned long tramp;
-
- tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp;
- if (tramp == addr)
- return (long)tramp_key->key + (long)&tramp_key->key;
- }
-
- return 0;
-}
-
-static int static_call_add_module(struct module *mod)
-{
- struct static_call_site *start = mod->static_call_sites;
- struct static_call_site *stop = start + mod->num_static_call_sites;
- struct static_call_site *site;
-
- for (site = start; site != stop; site++) {
- unsigned long s_key = __static_call_key(site);
- unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
- unsigned long key;
-
- /*
- * Is the key is exported, 'addr' points to the key, which
- * means modules are allowed to call static_call_update() on
- * it.
- *
- * Otherwise, the key isn't exported, and 'addr' points to the
- * trampoline so we need to lookup the key.
- *
- * We go through this dance to prevent crazy modules from
- * abusing sensitive static calls.
- */
- if (!kernel_text_address(addr))
- continue;
-
- key = tramp_key_lookup(addr);
- if (!key) {
- pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n",
- static_call_addr(site));
- return -EINVAL;
- }
-
- key |= s_key & STATIC_CALL_SITE_FLAGS;
- site->key = key - (long)&site->key;
- }
-
- return __static_call_init(mod, start, stop);
-}
-
-static void static_call_del_module(struct module *mod)
-{
- struct static_call_site *start = mod->static_call_sites;
- struct static_call_site *stop = mod->static_call_sites +
- mod->num_static_call_sites;
- struct static_call_key *key, *prev_key = NULL;
- struct static_call_mod *site_mod, **prev;
- struct static_call_site *site;
-
- for (site = start; site < stop; site++) {
- key = static_call_key(site);
- if (key == prev_key)
- continue;
-
- prev_key = key;
-
- for (prev = &key->mods, site_mod = key->mods;
- site_mod && site_mod->mod != mod;
- prev = &site_mod->next, site_mod = site_mod->next)
- ;
-
- if (!site_mod)
- continue;
-
- *prev = site_mod->next;
- kfree(site_mod);
- }
-}
-
-static int static_call_module_notify(struct notifier_block *nb,
- unsigned long val, void *data)
-{
- struct module *mod = data;
- int ret = 0;
-
- cpus_read_lock();
- static_call_lock();
-
- switch (val) {
- case MODULE_STATE_COMING:
- ret = static_call_add_module(mod);
- if (ret) {
- WARN(1, "Failed to allocate memory for static calls");
- static_call_del_module(mod);
- }
- break;
- case MODULE_STATE_GOING:
- static_call_del_module(mod);
- break;
- }
-
- static_call_unlock();
- cpus_read_unlock();
-
- return notifier_from_errno(ret);
-}
-
-static struct notifier_block static_call_module_nb = {
- .notifier_call = static_call_module_notify,
-};
-
-#else
-
-static inline int __static_call_mod_text_reserved(void *start, void *end)
-{
- return 0;
-}
-
-#endif /* CONFIG_MODULES */
-
-int static_call_text_reserved(void *start, void *end)
-{
- bool init = system_state < SYSTEM_RUNNING;
- int ret = __static_call_text_reserved(__start_static_call_sites,
- __stop_static_call_sites, start, end, init);
-
- if (ret)
- return ret;
-
- return __static_call_mod_text_reserved(start, end);
-}
-
-int __init static_call_init(void)
-{
- int ret;
-
- if (static_call_initialized)
- return 0;
-
- cpus_read_lock();
- static_call_lock();
- ret = __static_call_init(NULL, __start_static_call_sites,
- __stop_static_call_sites);
- static_call_unlock();
- cpus_read_unlock();
-
- if (ret) {
- pr_err("Failed to allocate memory for static_call!\n");
- BUG();
- }
-
- static_call_initialized = true;
-
-#ifdef CONFIG_MODULES
- register_module_notifier(&static_call_module_nb);
-#endif
- return 0;
-}
-early_initcall(static_call_init);

long __static_call_return0(void)
{
return 0;
}
-
-#ifdef CONFIG_STATIC_CALL_SELFTEST
-
-static int func_a(int x)
-{
- return x+1;
-}
-
-static int func_b(int x)
-{
- return x+2;
-}
-
-DEFINE_STATIC_CALL(sc_selftest, func_a);
-
-static struct static_call_data {
- int (*func)(int);
- int val;
- int expect;
-} static_call_data [] __initdata = {
- { NULL, 2, 3 },
- { func_b, 2, 4 },
- { func_a, 2, 3 }
-};
-
-static int __init test_static_call_init(void)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) {
- struct static_call_data *scd = &static_call_data[i];
-
- if (scd->func)
- static_call_update(sc_selftest, scd->func);
-
- WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect);
- }
-
- return 0;
-}
-early_initcall(test_static_call_init);
-
-#endif /* CONFIG_STATIC_CALL_SELFTEST */
+EXPORT_SYMBOL_GPL(__static_call_return0);
diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c
new file mode 100644
index 000000000000..dc5665b62814
--- /dev/null
+++ b/kernel/static_call_inline.c
@@ -0,0 +1,543 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/static_call.h>
+#include <linux/bug.h>
+#include <linux/smp.h>
+#include <linux/sort.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/processor.h>
+#include <asm/sections.h>
+
+extern struct static_call_site __start_static_call_sites[],
+ __stop_static_call_sites[];
+extern struct static_call_tramp_key __start_static_call_tramp_key[],
+ __stop_static_call_tramp_key[];
+
+static bool static_call_initialized;
+
+/* mutex to protect key modules/sites */
+static DEFINE_MUTEX(static_call_mutex);
+
+static void static_call_lock(void)
+{
+ mutex_lock(&static_call_mutex);
+}
+
+static void static_call_unlock(void)
+{
+ mutex_unlock(&static_call_mutex);
+}
+
+static inline void *static_call_addr(struct static_call_site *site)
+{
+ return (void *)((long)site->addr + (long)&site->addr);
+}
+
+static inline unsigned long __static_call_key(const struct static_call_site *site)
+{
+ return (long)site->key + (long)&site->key;
+}
+
+static inline struct static_call_key *static_call_key(const struct static_call_site *site)
+{
+ return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
+}
+
+/* These assume the key is word-aligned. */
+static inline bool static_call_is_init(struct static_call_site *site)
+{
+ return __static_call_key(site) & STATIC_CALL_SITE_INIT;
+}
+
+static inline bool static_call_is_tail(struct static_call_site *site)
+{
+ return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
+}
+
+static inline void static_call_set_init(struct static_call_site *site)
+{
+ site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
+ (long)&site->key;
+}
+
+static int static_call_site_cmp(const void *_a, const void *_b)
+{
+ const struct static_call_site *a = _a;
+ const struct static_call_site *b = _b;
+ const struct static_call_key *key_a = static_call_key(a);
+ const struct static_call_key *key_b = static_call_key(b);
+
+ if (key_a < key_b)
+ return -1;
+
+ if (key_a > key_b)
+ return 1;
+
+ return 0;
+}
+
+static void static_call_site_swap(void *_a, void *_b, int size)
+{
+ long delta = (unsigned long)_a - (unsigned long)_b;
+ struct static_call_site *a = _a;
+ struct static_call_site *b = _b;
+ struct static_call_site tmp = *a;
+
+ a->addr = b->addr - delta;
+ a->key = b->key - delta;
+
+ b->addr = tmp.addr + delta;
+ b->key = tmp.key + delta;
+}
+
+static inline void static_call_sort_entries(struct static_call_site *start,
+ struct static_call_site *stop)
+{
+ sort(start, stop - start, sizeof(struct static_call_site),
+ static_call_site_cmp, static_call_site_swap);
+}
+
+static inline bool static_call_key_has_mods(struct static_call_key *key)
+{
+ return !(key->type & 1);
+}
+
+static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
+{
+ if (!static_call_key_has_mods(key))
+ return NULL;
+
+ return key->mods;
+}
+
+static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
+{
+ if (static_call_key_has_mods(key))
+ return NULL;
+
+ return (struct static_call_site *)(key->type & ~1);
+}
+
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+ struct static_call_site *site, *stop;
+ struct static_call_mod *site_mod, first;
+
+ cpus_read_lock();
+ static_call_lock();
+
+ if (key->func == func)
+ goto done;
+
+ key->func = func;
+
+ arch_static_call_transform(NULL, tramp, func, false);
+
+ /*
+ * If uninitialized, we'll not update the callsites, but they still
+ * point to the trampoline and we just patched that.
+ */
+ if (WARN_ON_ONCE(!static_call_initialized))
+ goto done;
+
+ first = (struct static_call_mod){
+ .next = static_call_key_next(key),
+ .mod = NULL,
+ .sites = static_call_key_sites(key),
+ };
+
+ for (site_mod = &first; site_mod; site_mod = site_mod->next) {
+ bool init = system_state < SYSTEM_RUNNING;
+ struct module *mod = site_mod->mod;
+
+ if (!site_mod->sites) {
+ /*
+ * This can happen if the static call key is defined in
+ * a module which doesn't use it.
+ *
+ * It also happens in the has_mods case, where the
+ * 'first' entry has no sites associated with it.
+ */
+ continue;
+ }
+
+ stop = __stop_static_call_sites;
+
+ if (mod) {
+#ifdef CONFIG_MODULES
+ stop = mod->static_call_sites +
+ mod->num_static_call_sites;
+ init = mod->state == MODULE_STATE_COMING;
+#endif
+ }
+
+ for (site = site_mod->sites;
+ site < stop && static_call_key(site) == key; site++) {
+ void *site_addr = static_call_addr(site);
+
+ if (!init && static_call_is_init(site))
+ continue;
+
+ if (!kernel_text_address((unsigned long)site_addr)) {
+ /*
+ * This skips patching built-in __exit, which
+ * is part of init_section_contains() but is
+ * not part of kernel_text_address().
+ *
+ * Skipping built-in __exit is fine since it
+ * will never be executed.
+ */
+ WARN_ONCE(!static_call_is_init(site),
+ "can't patch static call site at %pS",
+ site_addr);
+ continue;
+ }
+
+ arch_static_call_transform(site_addr, NULL, func,
+ static_call_is_tail(site));
+ }
+ }
+
+done:
+ static_call_unlock();
+ cpus_read_unlock();
+}
+EXPORT_SYMBOL_GPL(__static_call_update);
+
+static int __static_call_init(struct module *mod,
+ struct static_call_site *start,
+ struct static_call_site *stop)
+{
+ struct static_call_site *site;
+ struct static_call_key *key, *prev_key = NULL;
+ struct static_call_mod *site_mod;
+
+ if (start == stop)
+ return 0;
+
+ static_call_sort_entries(start, stop);
+
+ for (site = start; site < stop; site++) {
+ void *site_addr = static_call_addr(site);
+
+ if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
+ (!mod && init_section_contains(site_addr, 1)))
+ static_call_set_init(site);
+
+ key = static_call_key(site);
+ if (key != prev_key) {
+ prev_key = key;
+
+ /*
+ * For vmlinux (!mod) avoid the allocation by storing
+ * the sites pointer in the key itself. Also see
+ * __static_call_update()'s @first.
+ *
+ * This allows architectures (eg. x86) to call
+ * static_call_init() before memory allocation works.
+ */
+ if (!mod) {
+ key->sites = site;
+ key->type |= 1;
+ goto do_transform;
+ }
+
+ site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+ if (!site_mod)
+ return -ENOMEM;
+
+ /*
+ * When the key has a direct sites pointer, extract
+ * that into an explicit struct static_call_mod, so we
+ * can have a list of modules.
+ */
+ if (static_call_key_sites(key)) {
+ site_mod->mod = NULL;
+ site_mod->next = NULL;
+ site_mod->sites = static_call_key_sites(key);
+
+ key->mods = site_mod;
+
+ site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+ if (!site_mod)
+ return -ENOMEM;
+ }
+
+ site_mod->mod = mod;
+ site_mod->sites = site;
+ site_mod->next = static_call_key_next(key);
+ key->mods = site_mod;
+ }
+
+do_transform:
+ arch_static_call_transform(site_addr, NULL, key->func,
+ static_call_is_tail(site));
+ }
+
+ return 0;
+}
+
+static int addr_conflict(struct static_call_site *site, void *start, void *end)
+{
+ unsigned long addr = (unsigned long)static_call_addr(site);
+
+ if (addr <= (unsigned long)end &&
+ addr + CALL_INSN_SIZE > (unsigned long)start)
+ return 1;
+
+ return 0;
+}
+
+static int __static_call_text_reserved(struct static_call_site *iter_start,
+ struct static_call_site *iter_stop,
+ void *start, void *end, bool init)
+{
+ struct static_call_site *iter = iter_start;
+
+ while (iter < iter_stop) {
+ if (init || !static_call_is_init(iter)) {
+ if (addr_conflict(iter, start, end))
+ return 1;
+ }
+ iter++;
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_MODULES
+
+static int __static_call_mod_text_reserved(void *start, void *end)
+{
+ struct module *mod;
+ int ret;
+
+ preempt_disable();
+ mod = __module_text_address((unsigned long)start);
+ WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+ if (!try_module_get(mod))
+ mod = NULL;
+ preempt_enable();
+
+ if (!mod)
+ return 0;
+
+ ret = __static_call_text_reserved(mod->static_call_sites,
+ mod->static_call_sites + mod->num_static_call_sites,
+ start, end, mod->state == MODULE_STATE_COMING);
+
+ module_put(mod);
+
+ return ret;
+}
+
+static unsigned long tramp_key_lookup(unsigned long addr)
+{
+ struct static_call_tramp_key *start = __start_static_call_tramp_key;
+ struct static_call_tramp_key *stop = __stop_static_call_tramp_key;
+ struct static_call_tramp_key *tramp_key;
+
+ for (tramp_key = start; tramp_key != stop; tramp_key++) {
+ unsigned long tramp;
+
+ tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp;
+ if (tramp == addr)
+ return (long)tramp_key->key + (long)&tramp_key->key;
+ }
+
+ return 0;
+}
+
+static int static_call_add_module(struct module *mod)
+{
+ struct static_call_site *start = mod->static_call_sites;
+ struct static_call_site *stop = start + mod->num_static_call_sites;
+ struct static_call_site *site;
+
+ for (site = start; site != stop; site++) {
+ unsigned long s_key = __static_call_key(site);
+ unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
+ unsigned long key;
+
+ /*
+ * Is the key is exported, 'addr' points to the key, which
+ * means modules are allowed to call static_call_update() on
+ * it.
+ *
+ * Otherwise, the key isn't exported, and 'addr' points to the
+ * trampoline so we need to lookup the key.
+ *
+ * We go through this dance to prevent crazy modules from
+ * abusing sensitive static calls.
+ */
+ if (!kernel_text_address(addr))
+ continue;
+
+ key = tramp_key_lookup(addr);
+ if (!key) {
+ pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n",
+ static_call_addr(site));
+ return -EINVAL;
+ }
+
+ key |= s_key & STATIC_CALL_SITE_FLAGS;
+ site->key = key - (long)&site->key;
+ }
+
+ return __static_call_init(mod, start, stop);
+}
+
+static void static_call_del_module(struct module *mod)
+{
+ struct static_call_site *start = mod->static_call_sites;
+ struct static_call_site *stop = mod->static_call_sites +
+ mod->num_static_call_sites;
+ struct static_call_key *key, *prev_key = NULL;
+ struct static_call_mod *site_mod, **prev;
+ struct static_call_site *site;
+
+ for (site = start; site < stop; site++) {
+ key = static_call_key(site);
+ if (key == prev_key)
+ continue;
+
+ prev_key = key;
+
+ for (prev = &key->mods, site_mod = key->mods;
+ site_mod && site_mod->mod != mod;
+ prev = &site_mod->next, site_mod = site_mod->next)
+ ;
+
+ if (!site_mod)
+ continue;
+
+ *prev = site_mod->next;
+ kfree(site_mod);
+ }
+}
+
+static int static_call_module_notify(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+ int ret = 0;
+
+ cpus_read_lock();
+ static_call_lock();
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ ret = static_call_add_module(mod);
+ if (ret) {
+ WARN(1, "Failed to allocate memory for static calls");
+ static_call_del_module(mod);
+ }
+ break;
+ case MODULE_STATE_GOING:
+ static_call_del_module(mod);
+ break;
+ }
+
+ static_call_unlock();
+ cpus_read_unlock();
+
+ return notifier_from_errno(ret);
+}
+
+static struct notifier_block static_call_module_nb = {
+ .notifier_call = static_call_module_notify,
+};
+
+#else
+
+static inline int __static_call_mod_text_reserved(void *start, void *end)
+{
+ return 0;
+}
+
+#endif /* CONFIG_MODULES */
+
+int static_call_text_reserved(void *start, void *end)
+{
+ bool init = system_state < SYSTEM_RUNNING;
+ int ret = __static_call_text_reserved(__start_static_call_sites,
+ __stop_static_call_sites, start, end, init);
+
+ if (ret)
+ return ret;
+
+ return __static_call_mod_text_reserved(start, end);
+}
+
+int __init static_call_init(void)
+{
+ int ret;
+
+ if (static_call_initialized)
+ return 0;
+
+ cpus_read_lock();
+ static_call_lock();
+ ret = __static_call_init(NULL, __start_static_call_sites,
+ __stop_static_call_sites);
+ static_call_unlock();
+ cpus_read_unlock();
+
+ if (ret) {
+ pr_err("Failed to allocate memory for static_call!\n");
+ BUG();
+ }
+
+ static_call_initialized = true;
+
+#ifdef CONFIG_MODULES
+ register_module_notifier(&static_call_module_nb);
+#endif
+ return 0;
+}
+early_initcall(static_call_init);
+
+#ifdef CONFIG_STATIC_CALL_SELFTEST
+
+static int func_a(int x)
+{
+ return x+1;
+}
+
+static int func_b(int x)
+{
+ return x+2;
+}
+
+DEFINE_STATIC_CALL(sc_selftest, func_a);
+
+static struct static_call_data {
+ int (*func)(int);
+ int val;
+ int expect;
+} static_call_data [] __initdata = {
+ { NULL, 2, 3 },
+ { func_b, 2, 4 },
+ { func_a, 2, 3 }
+};
+
+static int __init test_static_call_init(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) {
+ struct static_call_data *scd = &static_call_data[i];
+
+ if (scd->func)
+ static_call_update(sc_selftest, scd->func);
+
+ WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect);
+ }
+
+ return 0;
+}
+early_initcall(test_static_call_init);
+
+#endif /* CONFIG_STATIC_CALL_SELFTEST */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 14b89aa37c5c..440fd666c16d 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -416,7 +416,8 @@ config SECTION_MISMATCH_WARN_ONLY
If unsure, say Y.

config DEBUG_FORCE_FUNCTION_ALIGN_64B
- bool "Force all function address 64B aligned" if EXPERT
+ bool "Force all function address 64B aligned"
+ depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC)
help
There are cases that a commit from one domain changes the function
address alignment of other domains, and cause magic performance
diff --git a/lib/logic_iomem.c b/lib/logic_iomem.c
index 8c3365f26e51..b247d412ddef 100644
--- a/lib/logic_iomem.c
+++ b/lib/logic_iomem.c
@@ -68,7 +68,7 @@ int logic_iomem_add_region(struct resource *resource,
}
EXPORT_SYMBOL(logic_iomem_add_region);

-#ifndef CONFIG_LOGIC_IOMEM_FALLBACK
+#ifndef CONFIG_INDIRECT_IOMEM_FALLBACK
static void __iomem *real_ioremap(phys_addr_t offset, size_t size)
{
WARN(1, "invalid ioremap(0x%llx, 0x%zx)\n",
@@ -81,7 +81,7 @@ static void real_iounmap(volatile void __iomem *addr)
WARN(1, "invalid iounmap for addr 0x%llx\n",
(unsigned long long)(uintptr_t __force)addr);
}
-#endif /* CONFIG_LOGIC_IOMEM_FALLBACK */
+#endif /* CONFIG_INDIRECT_IOMEM_FALLBACK */

void __iomem *ioremap(phys_addr_t offset, size_t size)
{
@@ -168,7 +168,7 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);

-#ifndef CONFIG_LOGIC_IOMEM_FALLBACK
+#ifndef CONFIG_INDIRECT_IOMEM_FALLBACK
#define MAKE_FALLBACK(op, sz) \
static u##sz real_raw_read ## op(const volatile void __iomem *addr) \
{ \
@@ -213,7 +213,7 @@ static void real_memcpy_toio(volatile void __iomem *addr, const void *buffer,
WARN(1, "Invalid memcpy_toio at address 0x%llx\n",
(unsigned long long)(uintptr_t __force)addr);
}
-#endif /* CONFIG_LOGIC_IOMEM_FALLBACK */
+#endif /* CONFIG_INDIRECT_IOMEM_FALLBACK */

#define MAKE_OP(op, sz) \
u##sz __raw_read ## op(const volatile void __iomem *addr) \
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 926f4823d5ea..fd1728d94bab 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -271,8 +271,12 @@ static FORCE_INLINE int LZ4_decompress_generic(
ip += length;
op += length;

- /* Necessarily EOF, due to parsing restrictions */
- if (!partialDecoding || (cpy == oend))
+ /* Necessarily EOF when !partialDecoding.
+ * When partialDecoding, it is EOF if we've either
+ * filled the output buffer or
+ * can't proceed with reading an offset for following match.
+ */
+ if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2)))
break;
} else {
/* may overwrite up to WILDCOPYLENGTH beyond cpy */
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index a6789c0c626b..32ff6bd497f8 100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -20,6 +20,7 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
unsigned long flags;
bool leak = false;

+ dir->dead = true;
spin_lock_irqsave(&dir->lock, flags);
list_for_each_entry_safe(tracker, n, &dir->quarantine, head) {
list_del(&tracker->head);
@@ -72,6 +73,8 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir,
gfp_t gfp_mask = gfp;
unsigned long flags;

+ WARN_ON_ONCE(dir->dead);
+
if (gfp & __GFP_DIRECT_RECLAIM)
gfp_mask |= __GFP_NOFAIL;
*trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask);
@@ -100,6 +103,8 @@ int ref_tracker_free(struct ref_tracker_dir *dir,
unsigned int nr_entries;
unsigned long flags;

+ WARN_ON_ONCE(dir->dead);
+
if (!tracker) {
refcount_dec(&dir->untracked);
return -EEXIST;
diff --git a/mm/highmem.c b/mm/highmem.c
index 762679050c9a..916b66e0776c 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -624,7 +624,7 @@ void __kmap_local_sched_out(void)

/* With debug all even slots are unmapped and act as guard */
if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
- WARN_ON_ONCE(!pte_none(pteval));
+ WARN_ON_ONCE(pte_val(pteval) != 0);
continue;
}
if (WARN_ON_ONCE(pte_none(pteval)))
@@ -661,7 +661,7 @@ void __kmap_local_sched_in(void)

/* With debug all even slots are unmapped and act as guard */
if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
- WARN_ON_ONCE(!pte_none(pteval));
+ WARN_ON_ONCE(pte_val(pteval) != 0);
continue;
}
if (WARN_ON_ONCE(pte_none(pteval)))
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 13128fa13062..d4c7978cd75e 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -555,6 +555,8 @@ static bool __init kfence_init_pool(void)
* enters __slab_free() slow-path.
*/
for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) {
+ struct slab *slab = page_slab(&pages[i]);
+
if (!i || (i % 2))
continue;

@@ -562,7 +564,11 @@ static bool __init kfence_init_pool(void)
if (WARN_ON(compound_head(&pages[i]) != &pages[i]))
goto err;

- __SetPageSlab(&pages[i]);
+ __folio_set_slab(slab_folio(slab));
+#ifdef CONFIG_MEMCG
+ slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg |
+ MEMCG_DATA_OBJCGS;
+#endif
}

/*
@@ -938,6 +944,9 @@ void __kfence_free(void *addr)
{
struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr);

+#ifdef CONFIG_MEMCG
+ KFENCE_WARN_ON(meta->objcg);
+#endif
/*
* If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing
* the object, as the object page may be recycled for other-typed
diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h
index 2a2d5de9d379..9a6c4b1b12a8 100644
--- a/mm/kfence/kfence.h
+++ b/mm/kfence/kfence.h
@@ -89,6 +89,9 @@ struct kfence_metadata {
struct kfence_track free_track;
/* For updating alloc_covered on frees. */
u32 alloc_stack_hash;
+#ifdef CONFIG_MEMCG
+ struct obj_cgroup *objcg;
+#endif
};

extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS];
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1628cd90d9fc..f468bd911c3b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2736,6 +2736,7 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!mpol_new)
goto err_out;
+ atomic_set(&mpol_new->refcnt, 1);
goto restart;
}

diff --git a/mm/mremap.c b/mm/mremap.c
index 002eec83e91e..0e175aef536e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -486,6 +486,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
pmd_t *old_pmd, *new_pmd;
pud_t *old_pud, *new_pud;

+ if (!len)
+ return 0;
+
old_end = old_addr + len;
flush_cache_range(vma, old_addr, old_end);

diff --git a/mm/rmap.c b/mm/rmap.c
index 6a1e8c7f6213..9e27f9f038d3 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1599,7 +1599,30 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,

/* MADV_FREE page check */
if (!PageSwapBacked(page)) {
- if (!PageDirty(page)) {
+ int ref_count, map_count;
+
+ /*
+ * Synchronize with gup_pte_range():
+ * - clear PTE; barrier; read refcount
+ * - inc refcount; barrier; read PTE
+ */
+ smp_mb();
+
+ ref_count = page_ref_count(page);
+ map_count = page_mapcount(page);
+
+ /*
+ * Order reads for page refcount and dirty flag
+ * (see comments in __remove_mapping()).
+ */
+ smp_rmb();
+
+ /*
+ * The only page refs must be one from isolation
+ * plus the rmap(s) (dropped by discard:).
+ */
+ if (ref_count == 1 + map_count &&
+ !PageDirty(page)) {
/* Invalidate as we cleared the pte */
mmu_notifier_invalidate_range(mm,
address, address + PAGE_SIZE);
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index f4004cf0ff6f..9f311fddfaf9 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -134,7 +134,7 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
{
struct inet6_dev *in6_dev = __in6_dev_get(dev);

- if (in6_dev && in6_dev->cnf.mc_forwarding)
+ if (in6_dev && atomic_read(&in6_dev->cnf.mc_forwarding))
return BATADV_NO_FLAGS;
else
return BATADV_MCAST_WANT_NO_RTR6;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 3bb2b3b6a1c9..84312c836549 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -691,6 +691,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst,

bacpy(&conn->dst, dst);
bacpy(&conn->src, &hdev->bdaddr);
+ conn->handle = HCI_CONN_HANDLE_UNSET;
conn->hdev = hdev;
conn->type = type;
conn->role = role;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a105b7317560..d984777c9b58 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3068,6 +3068,11 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
struct hci_ev_conn_complete *ev = data;
struct hci_conn *conn;

+ if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) {
+ bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle");
+ return;
+ }
+
bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);

hci_dev_lock(hdev);
@@ -3106,6 +3111,17 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
}
}

+ /* The HCI_Connection_Complete event is only sent once per connection.
+ * Processing it more than once per connection can corrupt kernel memory.
+ *
+ * As the connection handle is set here for the first time, it indicates
+ * whether the connection is already set up.
+ */
+ if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+ bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection");
+ goto unlock;
+ }
+
if (!ev->status) {
conn->handle = __le16_to_cpu(ev->handle);

@@ -4661,6 +4677,24 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data,
struct hci_ev_sync_conn_complete *ev = data;
struct hci_conn *conn;

+ switch (ev->link_type) {
+ case SCO_LINK:
+ case ESCO_LINK:
+ break;
+ default:
+ /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type
+ * for HCI_Synchronous_Connection_Complete is limited to
+ * either SCO or eSCO
+ */
+ bt_dev_err(hdev, "Ignoring connect complete event for invalid link type");
+ return;
+ }
+
+ if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) {
+ bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle");
+ return;
+ }
+
bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);

hci_dev_lock(hdev);
@@ -4684,23 +4718,19 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data,
goto unlock;
}

+ /* The HCI_Synchronous_Connection_Complete event is only sent once per connection.
+ * Processing it more than once per connection can corrupt kernel memory.
+ *
+ * As the connection handle is set here for the first time, it indicates
+ * whether the connection is already set up.
+ */
+ if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+ bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection");
+ goto unlock;
+ }
+
switch (ev->status) {
case 0x00:
- /* The synchronous connection complete event should only be
- * sent once per new connection. Receiving a successful
- * complete event when the connection status is already
- * BT_CONNECTED means that the device is misbehaving and sent
- * multiple complete event packets for the same new connection.
- *
- * Registering the device more than once can corrupt kernel
- * memory, hence upon detecting this invalid event, we report
- * an error and ignore the packet.
- */
- if (conn->state == BT_CONNECTED) {
- bt_dev_err(hdev, "Ignoring connect complete event for existing connection");
- goto unlock;
- }
-
conn->handle = __le16_to_cpu(ev->handle);
conn->state = BT_CONNECTED;
conn->type = ev->link_type;
@@ -5423,8 +5453,9 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, void *data,
hci_dev_lock(hdev);

hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle);
- if (hcon) {
+ if (hcon && hcon->type == AMP_LINK) {
hcon->state = BT_CLOSED;
+ hci_disconn_cfm(hcon, ev->reason);
hci_conn_del(hcon);
}

@@ -5496,6 +5527,11 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
struct smp_irk *irk;
u8 addr_type;

+ if (handle > HCI_CONN_HANDLE_MAX) {
+ bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle");
+ return;
+ }
+
hci_dev_lock(hdev);

/* All controllers implicitly stop advertising in the event of a
@@ -5537,6 +5573,17 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
cancel_delayed_work(&conn->le_conn_timeout);
}

+ /* The HCI_LE_Connection_Complete event is only sent once per connection.
+ * Processing it more than once per connection can corrupt kernel memory.
+ *
+ * As the connection handle is set here for the first time, it indicates
+ * whether the connection is already set up.
+ */
+ if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+ bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection");
+ goto unlock;
+ }
+
le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa);

/* Lookup the identity address from the stored connection
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 405d48c3e63e..8f4c5698913d 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -379,6 +379,9 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
{
struct hci_cmd_sync_work_entry *entry;

+ if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+ return -ENODEV;
+
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return -ENOMEM;
@@ -5156,8 +5159,8 @@ static void set_ext_conn_params(struct hci_conn *conn,
p->max_ce_len = cpu_to_le16(0x0000);
}

-int hci_le_ext_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn,
- u8 own_addr_type)
+static int hci_le_ext_create_conn_sync(struct hci_dev *hdev,
+ struct hci_conn *conn, u8 own_addr_type)
{
struct hci_cp_le_ext_create_conn *cp;
struct hci_cp_le_ext_conn_param *p;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index e817ff0607a0..8df99c07f272 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1436,6 +1436,7 @@ static void l2cap_ecred_connect(struct l2cap_chan *chan)

l2cap_ecred_init(chan, 0);

+ memset(&data, 0, sizeof(data));
data.pdu.req.psm = chan->psm;
data.pdu.req.mtu = cpu_to_le16(chan->imtu);
data.pdu.req.mps = cpu_to_le16(chan->mps);
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 46dd95755967..eb43aaac0392 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -960,7 +960,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx)))
goto out;

- if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) {
+ if (user_ctx->local_port > U16_MAX) {
ret = -ERANGE;
goto out;
}
@@ -968,7 +968,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat
ctx.family = (u16)user_ctx->family;
ctx.protocol = (u16)user_ctx->protocol;
ctx.dport = (u16)user_ctx->local_port;
- ctx.sport = (__force __be16)user_ctx->remote_port;
+ ctx.sport = user_ctx->remote_port;

switch (ctx.family) {
case AF_INET:
diff --git a/net/can/isotp.c b/net/can/isotp.c
index a95d171b3a64..5bce7c66c121 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -141,6 +141,7 @@ struct isotp_sock {
struct can_isotp_options opt;
struct can_isotp_fc_options rxfc, txfc;
struct can_isotp_ll_options ll;
+ u32 frame_txtime;
u32 force_tx_stmin;
u32 force_rx_stmin;
struct tpcon rx, tx;
@@ -360,7 +361,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)

so->tx_gap = ktime_set(0, 0);
/* add transmission time for CAN frame N_As */
- so->tx_gap = ktime_add_ns(so->tx_gap, so->opt.frame_txtime);
+ so->tx_gap = ktime_add_ns(so->tx_gap, so->frame_txtime);
/* add waiting time for consecutive frames N_Cs */
if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN)
so->tx_gap = ktime_add_ns(so->tx_gap,
@@ -1247,6 +1248,14 @@ static int isotp_setsockopt_locked(struct socket *sock, int level, int optname,
/* no separate rx_ext_address is given => use ext_address */
if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR))
so->opt.rx_ext_address = so->opt.ext_address;
+
+ /* check for frame_txtime changes (0 => no changes) */
+ if (so->opt.frame_txtime) {
+ if (so->opt.frame_txtime == CAN_ISOTP_FRAME_TXTIME_ZERO)
+ so->frame_txtime = 0;
+ else
+ so->frame_txtime = so->opt.frame_txtime;
+ }
break;

case CAN_ISOTP_RECV_FC:
@@ -1448,6 +1457,7 @@ static int isotp_init(struct sock *sk)
so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME;
+ so->frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME;
so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS;
so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN;
so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX;
diff --git a/net/core/dev.c b/net/core/dev.c
index 1baab07820f6..91cf709c98b3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10732,8 +10732,7 @@ static int __net_init netdev_init(struct net *net)
BUILD_BUG_ON(GRO_HASH_BUCKETS >
8 * sizeof_field(struct napi_struct, gro_bitmask));

- if (net != &init_net)
- INIT_LIST_HEAD(&net->dev_base_head);
+ INIT_LIST_HEAD(&net->dev_base_head);

net->dev_name_head = netdev_create_hash();
if (net->dev_name_head == NULL)
diff --git a/net/core/filter.c b/net/core/filter.c
index 9eb785842258..af0bafe9dcce 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6777,24 +6777,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
if (!th->ack || th->rst || th->syn)
return -ENOENT;

+ if (unlikely(iph_len < sizeof(struct iphdr)))
+ return -EINVAL;
+
if (tcp_synq_no_recent_overflow(sk))
return -ENOENT;

cookie = ntohl(th->ack_seq) - 1;

- switch (sk->sk_family) {
- case AF_INET:
- if (unlikely(iph_len < sizeof(struct iphdr)))
+ /* Both struct iphdr and struct ipv6hdr have the version field at the
+ * same offset so we can cast to the shorter header (struct iphdr).
+ */
+ switch (((struct iphdr *)iph)->version) {
+ case 4:
+ if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
return -EINVAL;

ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
break;

#if IS_BUILTIN(CONFIG_IPV6)
- case AF_INET6:
+ case 6:
if (unlikely(iph_len < sizeof(struct ipv6hdr)))
return -EINVAL;

+ if (sk->sk_family != AF_INET6)
+ return -EINVAL;
+
ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
break;
#endif /* CONFIG_IPV6 */
@@ -8033,6 +8042,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
const int size_default = sizeof(__u32);
+ int field_size;

if (off < 0 || off >= sizeof(struct bpf_sock))
return false;
@@ -8044,7 +8054,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
case offsetof(struct bpf_sock, family):
case offsetof(struct bpf_sock, type):
case offsetof(struct bpf_sock, protocol):
- case offsetof(struct bpf_sock, dst_port):
case offsetof(struct bpf_sock, src_port):
case offsetof(struct bpf_sock, rx_queue_mapping):
case bpf_ctx_range(struct bpf_sock, src_ip4):
@@ -8053,6 +8062,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]):
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
+ case bpf_ctx_range(struct bpf_sock, dst_port):
+ field_size = size == size_default ?
+ size_default : sizeof_field(struct bpf_sock, dst_port);
+ bpf_ctx_record_field_size(info, field_size);
+ return bpf_ctx_narrow_access_ok(off, size, field_size);
+ case offsetofend(struct bpf_sock, dst_port) ...
+ offsetof(struct bpf_sock, dst_ip4) - 1:
+ return false;
}

return size == size_default;
@@ -10604,12 +10621,24 @@ static bool sk_lookup_is_valid_access(int off, int size,
case bpf_ctx_range(struct bpf_sk_lookup, local_ip4):
case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]):
case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]):
- case bpf_ctx_range(struct bpf_sk_lookup, remote_port):
case bpf_ctx_range(struct bpf_sk_lookup, local_port):
case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex):
bpf_ctx_record_field_size(info, sizeof(__u32));
return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32));

+ case bpf_ctx_range(struct bpf_sk_lookup, remote_port):
+ /* Allow 4-byte access to 2-byte field for backward compatibility */
+ if (size == sizeof(__u32))
+ return true;
+ bpf_ctx_record_field_size(info, sizeof(__be16));
+ return bpf_ctx_narrow_access_ok(off, size, sizeof(__be16));
+
+ case offsetofend(struct bpf_sk_lookup, remote_port) ...
+ offsetof(struct bpf_sk_lookup, local_ip4) - 1:
+ /* Allow access to zero padding for backward compatibility */
+ bpf_ctx_record_field_size(info, sizeof(__u16));
+ return bpf_ctx_narrow_access_ok(off, size, sizeof(__u16));
+
default:
return false;
}
@@ -10691,6 +10720,11 @@ static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type,
sport, 2, target_size));
break;

+ case offsetofend(struct bpf_sk_lookup, remote_port):
+ *target_size = 2;
+ *insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+ break;
+
case offsetof(struct bpf_sk_lookup, local_port):
*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
bpf_target_off(struct bpf_sk_lookup_kern,
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a5b5bb99c644..212e65add951 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -44,13 +44,7 @@ EXPORT_SYMBOL_GPL(net_rwsem);
static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) };
#endif

-struct net init_net = {
- .ns.count = REFCOUNT_INIT(1),
- .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
-#ifdef CONFIG_KEYS
- .key_domain = &init_net_key_domain,
-#endif
-};
+struct net init_net;
EXPORT_SYMBOL(init_net);

static bool init_net_initialized;
@@ -1084,7 +1078,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
rtnl_set_sk_err(net, RTNLGRP_NSID, err);
}

-static int __init net_ns_init(void)
+void __init net_ns_init(void)
{
struct net_generic *ng;

@@ -1105,6 +1099,9 @@ static int __init net_ns_init(void)

rcu_assign_pointer(init_net.gen, ng);

+#ifdef CONFIG_KEYS
+ init_net.key_domain = &init_net_key_domain;
+#endif
down_write(&pernet_ops_rwsem);
if (setup_net(&init_net, &init_user_ns))
panic("Could not setup the initial network namespace");
@@ -1119,12 +1116,8 @@ static int __init net_ns_init(void)
RTNL_FLAG_DOIT_UNLOCKED);
rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid,
RTNL_FLAG_DOIT_UNLOCKED);
-
- return 0;
}

-pure_initcall(net_ns_init);
-
static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list)
{
ops_pre_exit_list(ops, net_exit_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2fb8eb6791e8..43b995e935cd 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3652,13 +3652,24 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr,
bool *changed, struct netlink_ext_ack *extack)
{
char *alt_ifname;
+ size_t size;
int err;

err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack);
if (err)
return err;

- alt_ifname = nla_strdup(attr, GFP_KERNEL);
+ if (cmd == RTM_NEWLINKPROP) {
+ size = rtnl_prop_list_size(dev);
+ size += nla_total_size(ALTIFNAMSIZ);
+ if (size >= U16_MAX) {
+ NL_SET_ERR_MSG(extack,
+ "effective property list too long");
+ return -EINVAL;
+ }
+ }
+
+ alt_ifname = nla_strdup(attr, GFP_KERNEL_ACCOUNT);
if (!alt_ifname)
return -ENOMEM;

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a8a2fb745274..180fa6a26ad4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5275,11 +5275,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
if (skb_cloned(to))
return false;

- /* The page pool signature of struct page will eventually figure out
- * which pages can be recycled or not but for now let's prohibit slab
- * allocated and page_pool allocated SKBs from being coalesced.
+ /* In general, avoid mixing slab allocated and page_pool allocated
+ * pages within the same SKB. However when @to is not pp_recycle and
+ * @from is cloned, we can transition frag pages from page_pool to
+ * reference counted.
+ *
+ * On the other hand, don't allow coalescing two pp_recycle SKBs if
+ * @from is cloned, in case the SKB is using page_pool fragment
+ * references (PP_FLAG_PAGE_FRAG). Since we only take full page
+ * references for cloned SKBs at the moment that would result in
+ * inconsistent reference counts.
*/
- if (to->pp_recycle != from->pp_recycle)
+ if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from)))
return false;

if (len <= skb_tailroom(to)) {
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 880f910b23a9..10b51ffbb6f4 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -337,11 +337,24 @@ static const struct attribute_group dsa_group = {

static struct lock_class_key dsa_master_addr_list_lock_key;

+static void dsa_master_reset_mtu(struct net_device *dev)
+{
+ int err;
+
+ err = dev_set_mtu(dev, ETH_DATA_LEN);
+ if (err)
+ netdev_dbg(dev,
+ "Unable to reset MTU to exclude DSA overheads\n");
+}
+
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
+ const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops;
struct dsa_switch *ds = cpu_dp->ds;
struct device_link *consumer_link;
- int ret;
+ int mtu, ret;
+
+ mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops);

/* The DSA master must use SET_NETDEV_DEV for this to work. */
consumer_link = device_link_add(ds->dev, dev->dev.parent,
@@ -351,6 +364,15 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
"Failed to create a device link to DSA switch %s\n",
dev_name(ds->dev));

+ /* The switch driver may not implement ->port_change_mtu(), case in
+ * which dsa_slave_change_mtu() will not update the master MTU either,
+ * so we need to do that here.
+ */
+ ret = dev_set_mtu(dev, mtu);
+ if (ret)
+ netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n",
+ ret, mtu);
+
/* If we use a tagging format that doesn't have an ethertype
* field, make sure that all packets from this point on get
* sent to the tag format's receive function.
@@ -388,6 +410,7 @@ void dsa_master_teardown(struct net_device *dev)
sysfs_remove_group(&dev->dev.kobj, &dsa_group);
dsa_netdev_ops_set(dev, NULL);
dsa_master_ethtool_teardown(dev);
+ dsa_master_reset_mtu(dev);
dsa_master_set_promiscuity(dev, -1);

dev->dsa_ptr = NULL;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 4db0325f6e1a..dc28f0588e54 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1116,13 +1116,18 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev)
return err;
}

-static int arp_invalidate(struct net_device *dev, __be32 ip)
+int arp_invalidate(struct net_device *dev, __be32 ip, bool force)
{
struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev);
int err = -ENXIO;
struct neigh_table *tbl = &arp_tbl;

if (neigh) {
+ if ((neigh->nud_state & NUD_VALID) && !force) {
+ neigh_release(neigh);
+ return 0;
+ }
+
if (neigh->nud_state & ~NUD_NOARP)
err = neigh_update(neigh, NULL, NUD_FAILED,
NEIGH_UPDATE_F_OVERRIDE|
@@ -1169,7 +1174,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
if (!dev)
return -EINVAL;
}
- return arp_invalidate(dev, ip);
+ return arp_invalidate(dev, ip, true);
}

/*
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 85117b45216d..89a5a4875595 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1115,9 +1115,11 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
return;

/* Add broadcast address, if it is explicitly assigned. */
- if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
+ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) {
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32,
prim, 0);
+ arp_invalidate(dev, ifa->ifa_broadcast, false);
+ }

if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
(prefix != addr || ifa->ifa_prefixlen < 32)) {
@@ -1131,6 +1133,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
if (ifa->ifa_prefixlen < 31) {
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
32, prim, 0);
+ arp_invalidate(dev, prefix | ~mask, false);
}
}
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2dd375f7407b..0a0f49770345 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -888,8 +888,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
}

if (cfg->fc_oif || cfg->fc_gw_family) {
- struct fib_nh *nh = fib_info_nh(fi, 0);
+ struct fib_nh *nh;
+
+ /* cannot match on nexthop object attributes */
+ if (fi->nh)
+ return 1;

+ nh = fib_info_nh(fi, 0);
if (cfg->fc_encap) {
if (fib_encap_match(net, cfg->fc_encap_type,
cfg->fc_encap, nh, cfg, extack))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 30ab717ff1b8..17440840a791 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -637,7 +637,9 @@ int __inet_hash(struct sock *sk, struct sock *osk)
int err = 0;

if (sk->sk_state != TCP_LISTEN) {
+ local_bh_disable();
inet_ehash_nolisten(sk, osk, NULL);
+ local_bh_enable();
return 0;
}
WARN_ON(!sk_unhashed(sk));
@@ -669,45 +671,54 @@ int inet_hash(struct sock *sk)
{
int err = 0;

- if (sk->sk_state != TCP_CLOSE) {
- local_bh_disable();
+ if (sk->sk_state != TCP_CLOSE)
err = __inet_hash(sk, NULL);
- local_bh_enable();
- }

return err;
}
EXPORT_SYMBOL_GPL(inet_hash);

-void inet_unhash(struct sock *sk)
+static void __inet_unhash(struct sock *sk, struct inet_listen_hashbucket *ilb)
{
- struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
- struct inet_listen_hashbucket *ilb = NULL;
- spinlock_t *lock;
-
if (sk_unhashed(sk))
return;

- if (sk->sk_state == TCP_LISTEN) {
- ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
- lock = &ilb->lock;
- } else {
- lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
- }
- spin_lock_bh(lock);
- if (sk_unhashed(sk))
- goto unlock;
-
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_stop_listen_sock(sk);
if (ilb) {
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
inet_unhash2(hashinfo, sk);
ilb->count--;
}
__sk_nulls_del_node_init_rcu(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-unlock:
- spin_unlock_bh(lock);
+}
+
+void inet_unhash(struct sock *sk)
+{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
+ if (sk_unhashed(sk))
+ return;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ struct inet_listen_hashbucket *ilb;
+
+ ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
+ /* Don't disable bottom halves while acquiring the lock to
+ * avoid circular locking dependency on PREEMPT_RT.
+ */
+ spin_lock(&ilb->lock);
+ __inet_unhash(sk, ilb);
+ spin_unlock(&ilb->lock);
+ } else {
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+
+ spin_lock_bh(lock);
+ __inet_unhash(sk, NULL);
+ spin_unlock_bh(lock);
+ }
}
EXPORT_SYMBOL_GPL(inet_unhash);

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f908e2fd30b2..4df84013c4e6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -554,7 +554,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
#ifdef CONFIG_IPV6_MROUTE
if ((all || type == NETCONFA_MC_FORWARDING) &&
nla_put_s32(skb, NETCONFA_MC_FORWARDING,
- devconf->mc_forwarding) < 0)
+ atomic_read(&devconf->mc_forwarding)) < 0)
goto nla_put_failure;
#endif
if ((all || type == NETCONFA_PROXY_NEIGH) &&
@@ -5539,7 +5539,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic;
#endif
#ifdef CONFIG_IPV6_MROUTE
- array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding;
+ array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding);
#endif
array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6;
array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8fe7900f1949..7d7b7523d126 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -441,11 +441,14 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
struct sock *sk = sock->sk;
u32 flags = BIND_WITH_LOCK;
+ const struct proto *prot;
int err = 0;

+ /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+ prot = READ_ONCE(sk->sk_prot);
/* If the socket has its own bind function then use it. */
- if (sk->sk_prot->bind)
- return sk->sk_prot->bind(sk, uaddr, addr_len);
+ if (prot->bind)
+ return prot->bind(sk, uaddr, addr_len);

if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
@@ -555,6 +558,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
void __user *argp = (void __user *)arg;
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
+ const struct proto *prot;

switch (cmd) {
case SIOCADDRT:
@@ -572,9 +576,11 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
case SIOCSIFDSTADDR:
return addrconf_set_dstaddr(net, argp);
default:
- if (!sk->sk_prot->ioctl)
+ /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+ prot = READ_ONCE(sk->sk_prot);
+ if (!prot->ioctl)
return -ENOIOCTLCMD;
- return sk->sk_prot->ioctl(sk, cmd, arg);
+ return prot->ioctl(sk, cmd, arg);
}
/*NOTREACHED*/
return 0;
@@ -636,11 +642,14 @@ INDIRECT_CALLABLE_DECLARE(int udpv6_sendmsg(struct sock *, struct msghdr *,
int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
struct sock *sk = sock->sk;
+ const struct proto *prot;

if (unlikely(inet_send_prepare(sk)))
return -EAGAIN;

- return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udpv6_sendmsg,
+ /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+ prot = READ_ONCE(sk->sk_prot);
+ return INDIRECT_CALL_2(prot->sendmsg, tcp_sendmsg, udpv6_sendmsg,
sk, msg, size);
}

@@ -650,13 +659,16 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
struct sock *sk = sock->sk;
+ const struct proto *prot;
int addr_len = 0;
int err;

if (likely(!(flags & MSG_ERRQUEUE)))
sock_rps_record_flow(sk);

- err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udpv6_recvmsg,
+ /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+ prot = READ_ONCE(sk->sk_prot);
+ err = INDIRECT_CALL_2(prot->recvmsg, tcp_recvmsg, udpv6_recvmsg,
sk, msg, size, flags & MSG_DONTWAIT,
flags & ~MSG_DONTWAIT, &addr_len);
if (err >= 0)
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 4514444e96c8..4740afecf7c6 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -333,11 +333,8 @@ int inet6_hash(struct sock *sk)
{
int err = 0;

- if (sk->sk_state != TCP_CLOSE) {
- local_bh_disable();
+ if (sk->sk_state != TCP_CLOSE)
err = __inet_hash(sk, NULL);
- local_bh_enable();
- }

return err;
}
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 80256717868e..d4b1e2c5aa76 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -508,7 +508,7 @@ int ip6_mc_input(struct sk_buff *skb)
/*
* IPv6 multicast router mode is now supported ;)
*/
- if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
+ if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) &&
!(ipv6_addr_type(&hdr->daddr) &
(IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) &&
likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 8a2db926b5eb..e3c884678dbe 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -734,7 +734,7 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify,

in6_dev = __in6_dev_get(dev);
if (in6_dev) {
- in6_dev->cnf.mc_forwarding--;
+ atomic_dec(&in6_dev->cnf.mc_forwarding);
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in6_dev->cnf);
@@ -902,7 +902,7 @@ static int mif6_add(struct net *net, struct mr_table *mrt,

in6_dev = __in6_dev_get(dev);
if (in6_dev) {
- in6_dev->cnf.mc_forwarding++;
+ atomic_inc(&in6_dev->cnf.mc_forwarding);
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in6_dev->cnf);
@@ -1553,7 +1553,7 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk)
} else {
rcu_assign_pointer(mrt->mroute_sk, sk);
sock_set_flag(sk, SOCK_RCU_FREE);
- net->ipv6.devconf_all->mc_forwarding++;
+ atomic_inc(&net->ipv6.devconf_all->mc_forwarding);
}
write_unlock_bh(&mrt_lock);

@@ -1586,7 +1586,7 @@ int ip6mr_sk_done(struct sock *sk)
* so the RCU grace period before sk freeing
* is guaranteed by sk_destruct()
*/
- net->ipv6.devconf_all->mc_forwarding--;
+ atomic_dec(&net->ipv6.devconf_all->mc_forwarding);
write_unlock_bh(&mrt_lock);
inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a733803a710c..222f6bf220ba 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -475,7 +475,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, &tcp_prot, 1);

- sk->sk_prot = &tcp_prot;
+ /* Paired with READ_ONCE(sk->sk_prot) in net/ipv6/af_inet6.c */
+ WRITE_ONCE(sk->sk_prot, &tcp_prot);
icsk->icsk_af_ops = &ipv4_specific;
sk->sk_socket->ops = &inet_stream_ops;
sk->sk_family = PF_INET;
@@ -489,7 +490,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, prot, 1);

- sk->sk_prot = prot;
+ /* Paired with READ_ONCE(sk->sk_prot) in net/ipv6/af_inet6.c */
+ WRITE_ONCE(sk->sk_prot, prot);
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ea1cf414a92e..da1bf48e7937 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4495,7 +4495,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
struct inet6_dev *idev;
int type;

- if (netif_is_l3_master(skb->dev) &&
+ if (netif_is_l3_master(skb->dev) ||
dst->dev == net->loopback_dev)
idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
else
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index c921de63b494..fc05351d3a82 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -90,13 +90,13 @@ static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
{
DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
- const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr);
int rc, addrlen = msg->msg_namelen;
struct sock *sk = sock->sk;
struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
struct mctp_skb_cb *cb;
struct mctp_route *rt;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
+ int hlen;

if (addr) {
if (addrlen < sizeof(struct sockaddr_mctp))
@@ -119,6 +119,34 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
if (addr->smctp_network == MCTP_NET_ANY)
addr->smctp_network = mctp_default_net(sock_net(sk));

+ /* direct addressing */
+ if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+ DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+ extaddr, msg->msg_name);
+ struct net_device *dev;
+
+ rc = -EINVAL;
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex);
+ /* check for correct halen */
+ if (dev && extaddr->smctp_halen == dev->addr_len) {
+ hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr);
+ rc = 0;
+ }
+ rcu_read_unlock();
+ if (rc)
+ goto err_free;
+ rt = NULL;
+ } else {
+ rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
+ addr->smctp_addr.s_addr);
+ if (!rt) {
+ rc = -EHOSTUNREACH;
+ goto err_free;
+ }
+ hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr);
+ }
+
skb = sock_alloc_send_skb(sk, hlen + 1 + len,
msg->msg_flags & MSG_DONTWAIT, &rc);
if (!skb)
@@ -137,8 +165,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
cb = __mctp_cb(skb);
cb->net = addr->smctp_network;

- /* direct addressing */
- if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+ if (!rt) {
+ /* fill extended address in cb */
DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
extaddr, msg->msg_name);

@@ -149,17 +177,9 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
}

cb->ifindex = extaddr->smctp_ifindex;
+ /* smctp_halen is checked above */
cb->halen = extaddr->smctp_halen;
memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen);
-
- rt = NULL;
- } else {
- rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
- addr->smctp_addr.s_addr);
- if (!rt) {
- rc = -EHOSTUNREACH;
- goto err_free;
- }
}

rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr,
diff --git a/net/mctp/device.c b/net/mctp/device.c
index ef2755f82f87..f86ef6d751bd 100644
--- a/net/mctp/device.c
+++ b/net/mctp/device.c
@@ -24,12 +24,25 @@ struct mctp_dump_cb {
size_t a_idx;
};

-/* unlocked: caller must hold rcu_read_lock */
+/* unlocked: caller must hold rcu_read_lock.
+ * Returned mctp_dev has its refcount incremented, or NULL if unset.
+ */
struct mctp_dev *__mctp_dev_get(const struct net_device *dev)
{
- return rcu_dereference(dev->mctp_ptr);
+ struct mctp_dev *mdev = rcu_dereference(dev->mctp_ptr);
+
+ /* RCU guarantees that any mdev is still live.
+ * Zero refcount implies a pending free, return NULL.
+ */
+ if (mdev)
+ if (!refcount_inc_not_zero(&mdev->refs))
+ return NULL;
+ return mdev;
}

+/* Returned mctp_dev does not have refcount incremented. The returned pointer
+ * remains live while rtnl_lock is held, as that prevents mctp_unregister()
+ */
struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev)
{
return rtnl_dereference(dev->mctp_ptr);
@@ -123,6 +136,7 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb)
if (mdev) {
rc = mctp_dump_dev_addrinfo(mdev,
skb, cb);
+ mctp_dev_put(mdev);
// Error indicates full buffer, this
// callback will get retried.
if (rc < 0)
@@ -297,7 +311,7 @@ void mctp_dev_hold(struct mctp_dev *mdev)

void mctp_dev_put(struct mctp_dev *mdev)
{
- if (refcount_dec_and_test(&mdev->refs)) {
+ if (mdev && refcount_dec_and_test(&mdev->refs)) {
dev_put(mdev->dev);
kfree_rcu(mdev, rcu);
}
@@ -369,6 +383,7 @@ static size_t mctp_get_link_af_size(const struct net_device *dev,
if (!mdev)
return 0;
ret = nla_total_size(4); /* IFLA_MCTP_NET */
+ mctp_dev_put(mdev);
return ret;
}

diff --git a/net/mctp/route.c b/net/mctp/route.c
index e52cef750500..1a296e211a50 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -498,6 +498,11 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)

if (cb->ifindex) {
/* direct route; use the hwaddr we stashed in sendmsg */
+ if (cb->halen != skb->dev->addr_len) {
+ /* sanity check, sendmsg should have already caught this */
+ kfree_skb(skb);
+ return -EMSGSIZE;
+ }
daddr = cb->haddr;
} else {
/* If lookup fails let the device handle daddr==NULL */
@@ -507,7 +512,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)

rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol),
daddr, skb->dev->dev_addr, skb->len);
- if (rc) {
+ if (rc < 0) {
kfree_skb(skb);
return -EHOSTUNREACH;
}
@@ -707,7 +712,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
{
const unsigned int hlen = sizeof(struct mctp_hdr);
struct mctp_hdr *hdr, *hdr2;
- unsigned int pos, size;
+ unsigned int pos, size, headroom;
struct sk_buff *skb2;
int rc;
u8 seq;
@@ -721,6 +726,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
return -EMSGSIZE;
}

+ /* keep same headroom as the original skb */
+ headroom = skb_headroom(skb);
+
/* we've got the header */
skb_pull(skb, hlen);

@@ -728,7 +736,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
/* size of message payload */
size = min(mtu - hlen, skb->len - pos);

- skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL);
+ skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL);
if (!skb2) {
rc = -ENOMEM;
break;
@@ -744,7 +752,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
skb_set_owner_w(skb2, skb->sk);

/* establish packet */
- skb_reserve(skb2, MCTP_HEADER_MAXLEN);
+ skb_reserve(skb2, headroom);
skb_reset_network_header(skb2);
skb_put(skb2, hlen + size);
skb2->transport_header = skb2->network_header + hlen;
@@ -786,7 +794,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
{
struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
struct mctp_skb_cb *cb = mctp_cb(skb);
- struct mctp_route tmp_rt;
+ struct mctp_route tmp_rt = {0};
struct mctp_sk_key *key;
struct net_device *dev;
struct mctp_hdr *hdr;
@@ -892,6 +900,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
mctp_route_release(rt);

dev_put(dev);
+ mctp_dev_put(tmp_rt.dev);

return rc;

@@ -1057,11 +1066,13 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev,

rt->output(rt, skb);
mctp_route_release(rt);
+ mctp_dev_put(mdev);

return NET_RX_SUCCESS;

err_drop:
kfree_skb(skb);
+ mctp_dev_put(mdev);
return NET_RX_DROP;
}

diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c
index 7b7918702592..e03ba66bbe18 100644
--- a/net/mctp/test/utils.c
+++ b/net/mctp/test/utils.c
@@ -54,7 +54,6 @@ struct mctp_test_dev *mctp_test_create_dev(void)

rcu_read_lock();
dev->mdev = __mctp_dev_get(ndev);
- mctp_dev_hold(dev->mdev);
rcu_read_unlock();

return dev;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index bf1e17c678f1..7552e1e9fd62 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -67,6 +67,8 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash);
struct conntrack_gc_work {
struct delayed_work dwork;
u32 next_bucket;
+ u32 avg_timeout;
+ u32 start_time;
bool exiting;
bool early_drop;
};
@@ -78,8 +80,19 @@ static __read_mostly bool nf_conntrack_locks_all;
/* serialize hash resizes and nf_ct_iterate_cleanup */
static DEFINE_MUTEX(nf_conntrack_mutex);

-#define GC_SCAN_INTERVAL (120u * HZ)
+#define GC_SCAN_INTERVAL_MAX (60ul * HZ)
+#define GC_SCAN_INTERVAL_MIN (1ul * HZ)
+
+/* clamp timeouts to this value (TCP unacked) */
+#define GC_SCAN_INTERVAL_CLAMP (300ul * HZ)
+
+/* large initial bias so that we don't scan often just because we have
+ * three entries with a 1s timeout.
+ */
+#define GC_SCAN_INTERVAL_INIT INT_MAX
+
#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10)
+#define GC_SCAN_EXPIRED_MAX (64000u / HZ)

#define MIN_CHAINLEN 8u
#define MAX_CHAINLEN (32u - MIN_CHAINLEN)
@@ -1421,16 +1434,28 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct)

static void gc_worker(struct work_struct *work)
{
- unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION;
unsigned int i, hashsz, nf_conntrack_max95 = 0;
- unsigned long next_run = GC_SCAN_INTERVAL;
+ u32 end_time, start_time = nfct_time_stamp;
struct conntrack_gc_work *gc_work;
+ unsigned int expired_count = 0;
+ unsigned long next_run;
+ s32 delta_time;
+
gc_work = container_of(work, struct conntrack_gc_work, dwork.work);

i = gc_work->next_bucket;
if (gc_work->early_drop)
nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;

+ if (i == 0) {
+ gc_work->avg_timeout = GC_SCAN_INTERVAL_INIT;
+ gc_work->start_time = start_time;
+ }
+
+ next_run = gc_work->avg_timeout;
+
+ end_time = start_time + GC_SCAN_MAX_DURATION;
+
do {
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_head *ct_hash;
@@ -1447,6 +1472,7 @@ static void gc_worker(struct work_struct *work)

hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
struct nf_conntrack_net *cnet;
+ unsigned long expires;
struct net *net;

tmp = nf_ct_tuplehash_to_ctrack(h);
@@ -1456,11 +1482,29 @@ static void gc_worker(struct work_struct *work)
continue;
}

+ if (expired_count > GC_SCAN_EXPIRED_MAX) {
+ rcu_read_unlock();
+
+ gc_work->next_bucket = i;
+ gc_work->avg_timeout = next_run;
+
+ delta_time = nfct_time_stamp - gc_work->start_time;
+
+ /* re-sched immediately if total cycle time is exceeded */
+ next_run = delta_time < (s32)GC_SCAN_INTERVAL_MAX;
+ goto early_exit;
+ }
+
if (nf_ct_is_expired(tmp)) {
nf_ct_gc_expired(tmp);
+ expired_count++;
continue;
}

+ expires = clamp(nf_ct_expires(tmp), GC_SCAN_INTERVAL_MIN, GC_SCAN_INTERVAL_CLAMP);
+ next_run += expires;
+ next_run /= 2u;
+
if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
continue;

@@ -1478,8 +1522,10 @@ static void gc_worker(struct work_struct *work)
continue;
}

- if (gc_worker_can_early_drop(tmp))
+ if (gc_worker_can_early_drop(tmp)) {
nf_ct_kill(tmp);
+ expired_count++;
+ }

nf_ct_put(tmp);
}
@@ -1492,33 +1538,38 @@ static void gc_worker(struct work_struct *work)
cond_resched();
i++;

- if (time_after(jiffies, end_time) && i < hashsz) {
+ delta_time = nfct_time_stamp - end_time;
+ if (delta_time > 0 && i < hashsz) {
+ gc_work->avg_timeout = next_run;
gc_work->next_bucket = i;
next_run = 0;
- break;
+ goto early_exit;
}
} while (i < hashsz);

+ gc_work->next_bucket = 0;
+
+ next_run = clamp(next_run, GC_SCAN_INTERVAL_MIN, GC_SCAN_INTERVAL_MAX);
+
+ delta_time = max_t(s32, nfct_time_stamp - gc_work->start_time, 1);
+ if (next_run > (unsigned long)delta_time)
+ next_run -= delta_time;
+ else
+ next_run = 1;
+
+early_exit:
if (gc_work->exiting)
return;

- /*
- * Eviction will normally happen from the packet path, and not
- * from this gc worker.
- *
- * This worker is only here to reap expired entries when system went
- * idle after a busy period.
- */
- if (next_run) {
+ if (next_run)
gc_work->early_drop = false;
- gc_work->next_bucket = 0;
- }
+
queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run);
}

static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
{
- INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker);
+ INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
gc_work->exiting = false;
}

diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 7b727d3ebf9d..04bd2f89afe8 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -287,7 +287,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track,
if (!track->regs[priv->sreg].selector)
return false;

- bitwise = nft_expr_priv(expr);
+ bitwise = nft_expr_priv(track->regs[priv->dreg].selector);
if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector &&
track->regs[priv->dreg].bitwise &&
track->regs[priv->dreg].bitwise->ops == expr->ops &&
@@ -434,7 +434,7 @@ static bool nft_bitwise_fast_reduce(struct nft_regs_track *track,
if (!track->regs[priv->sreg].selector)
return false;

- bitwise = nft_expr_priv(expr);
+ bitwise = nft_expr_priv(track->regs[priv->dreg].selector);
if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector &&
track->regs[priv->dreg].bitwise &&
track->regs[priv->dreg].bitwise->ops == expr->ops &&
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index beb0e573266d..54c083003947 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -885,6 +885,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len,
unsigned char bitmask;
unsigned char byte;

+ if (offset >= bitmap_len)
+ return -1;
byte_offset = offset / 8;
byte = bitmap[byte_offset];
bit_spot = offset;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 780d9e2246f3..8955f31fa47e 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1051,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb,
int rem = nla_len(attr);
bool dont_clone_flow_key;

- /* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+ /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */
clone_arg = nla_data(attr);
dont_clone_flow_key = nla_get_u32(clone_arg);
actions = nla_next(clone_arg, &rem);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 0d677c9c2c80..c591b923016a 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2288,6 +2288,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size)
return sfa;
}

+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len);
+
+static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action)
+{
+ const struct nlattr *a;
+ int rem;
+
+ nla_for_each_nested(a, action, rem) {
+ switch (nla_type(a)) {
+ case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL:
+ case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER:
+ ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+ break;
+ }
+ }
+}
+
+static void ovs_nla_free_clone_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+ int rem = nla_len(action);
+
+ switch (nla_type(a)) {
+ case OVS_CLONE_ATTR_EXEC:
+ /* The real list of actions follows this attribute. */
+ a = nla_next(a, &rem);
+ ovs_nla_free_nested_actions(a, rem);
+ break;
+ }
+}
+
+static void ovs_nla_free_dec_ttl_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+
+ switch (nla_type(a)) {
+ case OVS_DEC_TTL_ATTR_ACTION:
+ ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+ break;
+ }
+}
+
+static void ovs_nla_free_sample_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+ int rem = nla_len(action);
+
+ switch (nla_type(a)) {
+ case OVS_SAMPLE_ATTR_ARG:
+ /* The real list of actions follows this attribute. */
+ a = nla_next(a, &rem);
+ ovs_nla_free_nested_actions(a, rem);
+ break;
+ }
+}
+
static void ovs_nla_free_set_action(const struct nlattr *a)
{
const struct nlattr *ovs_key = nla_data(a);
@@ -2301,25 +2357,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a)
}
}

-void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len)
{
const struct nlattr *a;
int rem;

- if (!sf_acts)
+ /* Whenever new actions are added, the need to update this
+ * function should be considered.
+ */
+ BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23);
+
+ if (!actions)
return;

- nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) {
+ nla_for_each_attr(a, actions, len, rem) {
switch (nla_type(a)) {
- case OVS_ACTION_ATTR_SET:
- ovs_nla_free_set_action(a);
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ ovs_nla_free_check_pkt_len_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_CLONE:
+ ovs_nla_free_clone_action(a);
break;
+
case OVS_ACTION_ATTR_CT:
ovs_ct_free_action(a);
break;
+
+ case OVS_ACTION_ATTR_DEC_TTL:
+ ovs_nla_free_dec_ttl_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_SAMPLE:
+ ovs_nla_free_sample_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_SET:
+ ovs_nla_free_set_action(a);
+ break;
}
}
+}
+
+void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+{
+ if (!sf_acts)
+ return;

+ ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len);
kfree(sf_acts);
}

@@ -3429,7 +3514,9 @@ static int clone_action_to_attr(const struct nlattr *attr,
if (!start)
return -EMSGSIZE;

- err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+ /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */
+ attr = nla_next(nla_data(attr), &rem);
+ err = ovs_nla_put_actions(attr, rem, skb);

if (err)
nla_nest_cancel(skb, start);
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 25bbc4cc8b13..f15d6942da45 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -113,8 +113,8 @@ static __net_exit void rxrpc_exit_net(struct net *net)
struct rxrpc_net *rxnet = rxrpc_net(net);

rxnet->live = false;
- del_timer_sync(&rxnet->peer_keepalive_timer);
cancel_work_sync(&rxnet->peer_keepalive_work);
+ del_timer_sync(&rxnet->peer_keepalive_timer);
rxrpc_destroy_all_calls(rxnet);
rxrpc_destroy_all_connections(rxnet);
rxrpc_destroy_all_peers(rxnet);
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index a18609f608fb..e213aaf45d67 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -914,6 +914,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
ctx->asoc->base.sk->sk_err = -error;
return;
}
+ ctx->asoc->stats.octrlchunks++;
break;

case SCTP_CID_ABORT:
@@ -938,7 +939,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)

case SCTP_CID_HEARTBEAT:
if (chunk->pmtu_probe) {
- sctp_packet_singleton(ctx->transport, chunk, ctx->gfp);
+ error = sctp_packet_singleton(ctx->transport,
+ chunk, ctx->gfp);
+ if (!error)
+ ctx->asoc->stats.octrlchunks++;
break;
}
fallthrough;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 284befa90967..303c5e56e4df 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2625,8 +2625,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
sk->sk_state != SMC_CLOSED) {
if (val) {
SMC_STAT_INC(smc, ndly_cnt);
- mod_delayed_work(smc->conn.lgr->tx_wq,
- &smc->conn.tx_work, 0);
+ smc_tx_pending(&smc->conn);
+ cancel_delayed_work(&smc->conn.tx_work);
}
}
break;
@@ -2636,8 +2636,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
sk->sk_state != SMC_CLOSED) {
if (!val) {
SMC_STAT_INC(smc, cork_cnt);
- mod_delayed_work(smc->conn.lgr->tx_wq,
- &smc->conn.tx_work, 0);
+ smc_tx_pending(&smc->conn);
+ cancel_delayed_work(&smc->conn.tx_work);
}
}
break;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index be7d704976ff..f40f6ed0fbdb 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1989,7 +1989,7 @@ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize,
*/
static inline int smc_rmb_wnd_update_limit(int rmbe_size)
{
- return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
+ return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
}

/* map an rmb buf to a link */
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index be241d53020f..7b0b6e24582f 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -597,27 +597,32 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
return rc;
}

-/* Wakeup sndbuf consumers from process context
- * since there is more data to transmit
- */
-void smc_tx_work(struct work_struct *work)
+void smc_tx_pending(struct smc_connection *conn)
{
- struct smc_connection *conn = container_of(to_delayed_work(work),
- struct smc_connection,
- tx_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
int rc;

- lock_sock(&smc->sk);
if (smc->sk.sk_err)
- goto out;
+ return;

rc = smc_tx_sndbuf_nonempty(conn);
if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked &&
!atomic_read(&conn->bytes_to_rcv))
conn->local_rx_ctrl.prod_flags.write_blocked = 0;
+}
+
+/* Wakeup sndbuf consumers from process context
+ * since there is more data to transmit
+ */
+void smc_tx_work(struct work_struct *work)
+{
+ struct smc_connection *conn = container_of(to_delayed_work(work),
+ struct smc_connection,
+ tx_work);
+ struct smc_sock *smc = container_of(conn, struct smc_sock, conn);

-out:
+ lock_sock(&smc->sk);
+ smc_tx_pending(conn);
release_sock(&smc->sk);
}

diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index 07e6ad76224a..a59f370b8b43 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -27,6 +27,7 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn)
return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
}

+void smc_tx_pending(struct smc_connection *conn);
void smc_tx_work(struct work_struct *work);
void smc_tx_init(struct smc_sock *smc);
int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index b36d235d2d6d..0222ad4523a9 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2197,6 +2197,7 @@ call_transmit_status(struct rpc_task *task)
* socket just returned a connection error,
* then hold onto the transport lock.
*/
+ case -ENOMEM:
case -ENOBUFS:
rpc_delay(task, HZ>>2);
fallthrough;
@@ -2280,6 +2281,7 @@ call_bc_transmit_status(struct rpc_task *task)
case -ENOTCONN:
case -EPIPE:
break;
+ case -ENOMEM:
case -ENOBUFS:
rpc_delay(task, HZ>>2);
fallthrough;
@@ -2362,6 +2364,11 @@ call_status(struct rpc_task *task)
case -EPIPE:
case -EAGAIN:
break;
+ case -ENFILE:
+ case -ENOBUFS:
+ case -ENOMEM:
+ rpc_delay(task, HZ>>2);
+ break;
case -EIO:
/* shutdown or soft timeout */
goto out_exit;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index ae295844ac55..9020cedb7c95 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -186,11 +186,6 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue,

/*
* Add new request to wait queue.
- *
- * Swapper tasks always get inserted at the head of the queue.
- * This should avoid many nasty memory deadlocks and hopefully
- * improve overall performance.
- * Everyone else gets appended to the queue to ensure proper FIFO behavior.
*/
static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
struct rpc_task *task,
@@ -199,8 +194,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
INIT_LIST_HEAD(&task->u.tk_wait.timer_list);
if (RPC_IS_PRIORITY(queue))
__rpc_add_wait_queue_priority(queue, task, queue_priority);
- else if (RPC_IS_SWAPPER(task))
- list_add(&task->u.tk_wait.list, &queue->tasks[0]);
else
list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]);
task->tk_waitqueue = queue;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 478f857cdaed..6ea3d87e1147 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1096,7 +1096,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr,
int ret;

*sentp = 0;
- xdr_alloc_bvec(xdr, GFP_KERNEL);
+ ret = xdr_alloc_bvec(xdr, GFP_KERNEL);
+ if (ret < 0)
+ return ret;

ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len);
if (ret < 0)
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 396a74974f60..d557a3cb2ad4 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -929,12 +929,7 @@ void xprt_connect(struct rpc_task *task)
if (!xprt_lock_write(xprt, task))
return;

- if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
- trace_xprt_disconnect_cleanup(xprt);
- xprt->ops->close(xprt);
- }
-
- if (!xprt_connected(xprt)) {
+ if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie;
rpc_sleep_on_timeout(&xprt->pending, task, NULL,
xprt_request_timeout(task->tk_rqstp));
@@ -1354,17 +1349,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
INIT_LIST_HEAD(&req->rq_xmit2);
goto out;
}
- } else if (RPC_IS_SWAPPER(task)) {
- list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
- if (pos->rq_cong || pos->rq_bytes_sent)
- continue;
- if (RPC_IS_SWAPPER(pos->rq_task))
- continue;
- /* Note: req is added _before_ pos */
- list_add_tail(&req->rq_xmit, &pos->rq_xmit);
- INIT_LIST_HEAD(&req->rq_xmit2);
- goto out;
- }
} else if (!req->rq_seqno) {
list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
if (pos->rq_task->tk_owner != task->tk_owner)
@@ -1690,12 +1674,15 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task
static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt)
{
struct rpc_rqst *req = ERR_PTR(-EAGAIN);
+ gfp_t gfp_mask = GFP_KERNEL;

if (xprt->num_reqs >= xprt->max_reqs)
goto out;
++xprt->num_reqs;
spin_unlock(&xprt->reserve_lock);
- req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS);
+ if (current->flags & PF_WQ_WORKER)
+ gfp_mask |= __GFP_NORETRY | __GFP_NOWARN;
+ req = kzalloc(sizeof(*req), gfp_mask);
spin_lock(&xprt->reserve_lock);
if (req != NULL)
goto out;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index ff78a296fa81..6b7e10e5a141 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -521,7 +521,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
return;

out_sleep:
- task->tk_status = -EAGAIN;
+ task->tk_status = -ENOMEM;
xprt_add_backlog(xprt, task);
}

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 11eab0f0333b..7aef2876beb3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -763,12 +763,12 @@ xs_stream_start_connect(struct sock_xprt *transport)
/**
* xs_nospace - handle transmit was incomplete
* @req: pointer to RPC request
+ * @transport: pointer to struct sock_xprt
*
*/
-static int xs_nospace(struct rpc_rqst *req)
+static int xs_nospace(struct rpc_rqst *req, struct sock_xprt *transport)
{
- struct rpc_xprt *xprt = req->rq_xprt;
- struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct rpc_xprt *xprt = &transport->xprt;
struct sock *sk = transport->inet;
int ret = -EAGAIN;

@@ -779,25 +779,49 @@ static int xs_nospace(struct rpc_rqst *req)

/* Don't race with disconnect */
if (xprt_connected(xprt)) {
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags);
+ rcu_read_unlock();
+
/* wait for more buffer space */
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
xprt_wait_for_buffer_space(xprt);
} else
ret = -ENOTCONN;

spin_unlock(&xprt->transport_lock);
+ return ret;
+}

- /* Race breaker in case memory is freed before above code is called */
- if (ret == -EAGAIN) {
- struct socket_wq *wq;
+static int xs_sock_nospace(struct rpc_rqst *req)
+{
+ struct sock_xprt *transport =
+ container_of(req->rq_xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
+ int ret = -EAGAIN;

- rcu_read_lock();
- wq = rcu_dereference(sk->sk_wq);
- set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags);
- rcu_read_unlock();
+ lock_sock(sk);
+ if (!sock_writeable(sk))
+ ret = xs_nospace(req, transport);
+ release_sock(sk);
+ return ret;
+}

- sk->sk_write_space(sk);
- }
+static int xs_stream_nospace(struct rpc_rqst *req)
+{
+ struct sock_xprt *transport =
+ container_of(req->rq_xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
+ int ret = -EAGAIN;
+
+ lock_sock(sk);
+ if (!sk_stream_memory_free(sk))
+ ret = xs_nospace(req, transport);
+ release_sock(sk);
return ret;
}

@@ -856,7 +880,7 @@ static int xs_local_send_request(struct rpc_rqst *req)

/* Close the stream if the previous transmission was incomplete */
if (xs_send_request_was_aborted(transport, req)) {
- xs_close(xprt);
+ xprt_force_disconnect(xprt);
return -ENOTCONN;
}

@@ -887,14 +911,14 @@ static int xs_local_send_request(struct rpc_rqst *req)
case -ENOBUFS:
break;
case -EAGAIN:
- status = xs_nospace(req);
+ status = xs_stream_nospace(req);
break;
default:
dprintk("RPC: sendmsg returned unrecognized error %d\n",
-status);
fallthrough;
case -EPIPE:
- xs_close(xprt);
+ xprt_force_disconnect(xprt);
status = -ENOTCONN;
}

@@ -963,7 +987,7 @@ static int xs_udp_send_request(struct rpc_rqst *req)
/* Should we call xs_close() here? */
break;
case -EAGAIN:
- status = xs_nospace(req);
+ status = xs_sock_nospace(req);
break;
case -ENETUNREACH:
case -ENOBUFS:
@@ -1083,7 +1107,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
/* Should we call xs_close() here? */
break;
case -EAGAIN:
- status = xs_nospace(req);
+ status = xs_stream_nospace(req);
break;
case -ECONNRESET:
case -ECONNREFUSED:
@@ -1179,6 +1203,16 @@ static void xs_reset_transport(struct sock_xprt *transport)

if (sk == NULL)
return;
+ /*
+ * Make sure we're calling this in a context from which it is safe
+ * to call __fput_sync(). In practice that means rpciod and the
+ * system workqueue.
+ */
+ if (!(current->flags & PF_WQ_WORKER)) {
+ WARN_ON_ONCE(1);
+ set_bit(XPRT_CLOSE_WAIT, &xprt->state);
+ return;
+ }

if (atomic_read(&transport->xprt.swapper))
sk_clear_memalloc(sk);
@@ -1202,7 +1236,7 @@ static void xs_reset_transport(struct sock_xprt *transport)
mutex_unlock(&transport->recv_mutex);

trace_rpc_socket_close(xprt, sock);
- fput(filp);
+ __fput_sync(filp);

xprt_disconnect_done(xprt);
}
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index efc84845bb6b..75a699591383 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1495,7 +1495,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
if (prot->version == TLS_1_3_VERSION ||
prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305)
memcpy(iv + iv_offset, tls_ctx->rx.iv,
- crypto_aead_ivsize(ctx->aead_recv));
+ prot->iv_size + prot->salt_size);
else
memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index b888522f133b..b2fdac96bab0 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -700,8 +700,12 @@ static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap,

for (i = 0; i < request->n_ssids; i++) {
/* wildcard ssid in the scan request */
- if (!request->ssids[i].ssid_len)
+ if (!request->ssids[i].ssid_len) {
+ if (ap->multi_bss && !ap->transmitted_bssid)
+ continue;
+
return true;
+ }

if (ap->ssid_len &&
ap->ssid_len == request->ssids[i].ssid_len) {
@@ -827,6 +831,9 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
!cfg80211_find_ssid_match(ap, request))
continue;

+ if (!request->n_ssids && ap->multi_bss && !ap->transmitted_bssid)
+ continue;
+
cfg80211_scan_req_add_chan(request, chan, true);
memcpy(scan_6ghz_params->bssid, ap->bssid, ETH_ALEN);
scan_6ghz_params->short_ssid = ap->short_ssid;
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 1480910c792e..de66e1cc0734 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -217,9 +217,16 @@ strip-libs = $(filter-out -l%,$(1))
PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)

+ifeq ($(CC_NO_CLANG), 0)
+ PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
+ PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
+ PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+ FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro
+endif
+
$(OUTPUT)test-libperl.bin:
$(BUILD) $(FLAGS_PERL_EMBED)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index f947b61b2107..b8b37fe76006 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -131,7 +131,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
sort -u | wc -l)
VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
sed 's/\[.*\]//' | \
- awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)

CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
@@ -194,7 +194,7 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
sort -u > $(OUTPUT)libbpf_global_syms.tmp; \
readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
sed 's/\[.*\]//' | \
- awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \
+ awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'| \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \
sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \
diff -u $(OUTPUT)libbpf_global_syms.tmp \
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index e1b505606882..122d79c8f4b4 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -112,6 +112,10 @@

#elif defined(bpf_target_s390)

+struct pt_regs___s390 {
+ unsigned long orig_gpr2;
+};
+
/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
#define __PT_PARM1_REG gprs[2]
@@ -124,6 +128,8 @@
#define __PT_RC_REG gprs[2]
#define __PT_SP_REG gprs[15]
#define __PT_IP_REG psw.addr
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)

#elif defined(bpf_target_arm)

@@ -140,6 +146,10 @@

#elif defined(bpf_target_arm64)

+struct pt_regs___arm64 {
+ unsigned long orig_x0;
+};
+
/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
#define __PT_PARM1_REG regs[0]
@@ -152,6 +162,8 @@
#define __PT_RC_REG regs[0]
#define __PT_SP_REG sp
#define __PT_IP_REG pc
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)

#elif defined(bpf_target_mips)

@@ -178,6 +190,8 @@
#define __PT_RC_REG gpr[3]
#define __PT_SP_REG sp
#define __PT_IP_REG nip
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx

#elif defined(bpf_target_sparc)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 7c33ec67c4a9..3470813daf4a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1090,6 +1090,17 @@ static void annotate_call_site(struct objtool_file *file,
: arch_nop_insn(insn->len));

insn->type = sibling ? INSN_RETURN : INSN_NOP;
+
+ if (sibling) {
+ /*
+ * We've replaced the tail-call JMP insn by two new
+ * insn: RET; INT3, except we only have a single struct
+ * insn here. Mark it retpoline_safe to avoid the SLS
+ * warning, instead of adding another insn.
+ */
+ insn->retpoline_safe = true;
+ }
+
return;
}

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 96ad944ca6a8..f3bf9297bcc0 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG
PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+ ifeq ($(CC_NO_CLANG), 0)
+ PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS))
+ endif
endif

FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
@@ -790,6 +793,9 @@ else
LDFLAGS += $(PERL_EMBED_LDFLAGS)
EXTLIBS += $(PERL_EMBED_LIBADD)
CFLAGS += -DHAVE_LIBPERL_SUPPORT
+ ifeq ($(CC_NO_CLANG), 0)
+ CFLAGS += -Wno-compound-token-split-by-macro
+ endif
$(call detected,CONFIG_LIBPERL)
endif
endif
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 2100d46ccf5e..bb4ab99afa7f 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -239,6 +239,12 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
arm_spe_set_timestamp(itr, arm_spe_evsel);
}

+ /*
+ * Set this only so that perf report knows that SPE generates memory info. It has no effect
+ * on the opening of the event or the SPE data produced.
+ */
+ evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
+
/* Add dummy event to keep tracking */
err = parse_events(evlist, "dummy:u", NULL);
if (err)
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 2f6b67189b42..6aae7b6c376b 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -434,7 +434,7 @@ void pthread__unblock_sigwinch(void)
static int libperf_print(enum libperf_print_level level,
const char *fmt, va_list ap)
{
- return eprintf(level, verbose, fmt, ap);
+ return veprintf(level, verbose, fmt, ap);
}

int main(int argc, const char **argv)
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2dab2d262060..afdca7f2959f 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr
}

err = unwind__get_entries(unwind_entry, &cnt, thread,
- &sample, MAX_STACK);
+ &sample, MAX_STACK, false);
if (err)
pr_debug("unwind failed\n");
else if (cnt != MAX_STACK) {
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
index 2242a885fbd7..4940be4a0569 100644
--- a/tools/perf/util/arm64-frame-pointer-unwind-support.c
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
}

- ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+ ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true);
sample->user_regs = old_regs;

if (ret || entries.length != 2)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 394550003693..564abe17a0bd 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2983,7 +2983,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
return 0;

return unwind__get_entries(unwind_entry, cursor,
- thread, sample, max_stack);
+ thread, sample, max_stack, false);
}

int thread__resolve_callchain(struct thread *thread,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 498b05708db5..245dc70d1882 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2084,6 +2084,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
bool needs_swap, union perf_event *error)
{
union perf_event *event;
+ u16 event_size;

/*
* Ensure we have enough space remaining to read
@@ -2096,15 +2097,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
if (needs_swap)
perf_event_header__bswap(&event->header);

- if (head + event->header.size <= mmap_size)
+ event_size = event->header.size;
+ if (head + event_size <= mmap_size)
return event;

/* We're not fetching the event so swap back again */
if (needs_swap)
perf_event_header__bswap(&event->header);

- pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:"
- " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size);
+ /* Check if the event fits into the next mmapped buf. */
+ if (event_size <= mmap_size - head % page_size) {
+ /* Remap buf and fetch again. */
+ return NULL;
+ }
+
+ /* Invalid input. Event size should never exceed mmap_size. */
+ pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:"
+ " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size);

return error;
}
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 483f05004e68..c255a2c90cd6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,12 +1,14 @@
-from os import getenv
+from os import getenv, path
from subprocess import Popen, PIPE
from re import sub

cc = getenv("CC")
cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline()
+src_feature_tests = getenv('srctree') + '/tools/build/feature'

def clang_has_option(option):
- return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
+ cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines()
+ return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ]

if cc_is_clang:
from distutils.sysconfig import get_config_vars
@@ -23,6 +25,8 @@ if cc_is_clang:
vars[var] = sub("-fstack-protector-strong", "", vars[var])
if not clang_has_option("-fno-semantic-interposition"):
vars[var] = sub("-fno-semantic-interposition", "", vars[var])
+ if not clang_has_option("-ffat-lto-objects"):
+ vars[var] = sub("-ffat-lto-objects", "", vars[var])

from distutils.core import setup, Extension

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index a74b517f7497..94aa40f6e348 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
bool isactivation;

if (!dwfl_frame_pc(state, &pc, NULL)) {
- pr_err("%s", dwfl_errmsg(-1));
+ if (!ui->best_effort)
+ pr_err("%s", dwfl_errmsg(-1));
return DWARF_CB_ABORT;
}

@@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
report_module(pc, ui);

if (!dwfl_frame_pc(state, &pc, &isactivation)) {
- pr_err("%s", dwfl_errmsg(-1));
+ if (!ui->best_effort)
+ pr_err("%s", dwfl_errmsg(-1));
return DWARF_CB_ABORT;
}

@@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
struct perf_sample *data,
- int max_stack)
+ int max_stack,
+ bool best_effort)
{
struct unwind_info *ui, ui_buf = {
.sample = data,
@@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
.cb = cb,
.arg = arg,
.max_stack = max_stack,
+ .best_effort = best_effort
};
Dwarf_Word ip;
int err = -EINVAL, i;
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 0cbd2650e280..8c88bc4f2304 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -20,6 +20,7 @@ struct unwind_info {
void *arg;
int max_stack;
int idx;
+ bool best_effort;
struct unwind_entry entries[];
};

diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 71a353349181..41e29fc7648a 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -96,6 +96,7 @@ struct unwind_info {
struct perf_sample *sample;
struct machine *machine;
struct thread *thread;
+ bool best_effort;
};

#define dw_read(ptr, type, end) ({ \
@@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as,

ret = perf_reg_value(&val, &ui->sample->user_regs, id);
if (ret) {
- pr_err("unwind: can't read reg %d\n", regnum);
+ if (!ui->best_effort)
+ pr_err("unwind: can't read reg %d\n", regnum);
return ret;
}

@@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
return -1;

ret = unw_init_remote(&c, addr_space, ui);
- if (ret)
+ if (ret && !ui->best_effort)
display_error(ret);

while (!ret && (unw_step(&c) > 0) && i < max_stack) {
@@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,

static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack)
+ struct perf_sample *data, int max_stack,
+ bool best_effort)
{
struct unwind_info ui = {
.sample = data,
.thread = thread,
.machine = thread->maps->machine,
+ .best_effort = best_effort
};

if (!data->user_regs.regs)
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index e89a5479b361..509c287ee762 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps)

int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack)
+ struct perf_sample *data, int max_stack,
+ bool best_effort)
{
if (thread->maps->unwind_libunwind_ops)
- return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+ return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data,
+ max_stack, best_effort);
return 0;
}
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index ab8ad469c8de..b2a03fa5289b 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -23,13 +23,19 @@ struct unwind_libunwind_ops {
void (*finish_access)(struct maps *maps);
int (*get_entries)(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack);
+ struct perf_sample *data, int max_stack, bool best_effort);
};

#ifdef HAVE_DWARF_UNWIND_SUPPORT
+/*
+ * When best_effort is set, don't report errors and fail silently. This could
+ * be expanded in the future to be more permissive about things other than
+ * error messages.
+ */
int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack);
+ struct perf_sample *data, int max_stack,
+ bool best_effort);
/* libunwind specific */
#ifdef HAVE_LIBUNWIND_SUPPORT
#ifndef LIBUNWIND__ARCH_REG_ID
@@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
void *arg __maybe_unused,
struct thread *thread __maybe_unused,
struct perf_sample *data __maybe_unused,
- int max_stack __maybe_unused)
+ int max_stack __maybe_unused,
+ bool best_effort __maybe_unused)
{
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
index 83b0aaa52ef7..a0e0d85e29da 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -412,8 +412,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx)

/* Narrow loads from remote_port field. Expect SRC_PORT. */
if (LSB(ctx->remote_port, 0) != ((SRC_PORT >> 0) & 0xff) ||
- LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff) ||
- LSB(ctx->remote_port, 2) != 0 || LSB(ctx->remote_port, 3) != 0)
+ LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff))
return SK_DROP;
if (LSW(ctx->remote_port, 0) != SRC_PORT)
return SK_DROP;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index ffa5502ad95e..5f8296d29e77 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -266,22 +266,24 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
}

static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
- struct ifobject *ifobject, u32 qid)
+ struct ifobject *ifobject, bool shared)
{
- struct xsk_socket_config cfg;
+ struct xsk_socket_config cfg = {};
struct xsk_ring_cons *rxr;
struct xsk_ring_prod *txr;

xsk->umem = umem;
cfg.rx_size = xsk->rxqsize;
cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
- cfg.libbpf_flags = 0;
+ cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
cfg.xdp_flags = ifobject->xdp_flags;
cfg.bind_flags = ifobject->bind_flags;
+ if (shared)
+ cfg.bind_flags |= XDP_SHARED_UMEM;

txr = ifobject->tx_on ? &xsk->tx : NULL;
rxr = ifobject->rx_on ? &xsk->rx : NULL;
- return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg);
+ return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg);
}

static struct option long_options[] = {
@@ -387,7 +389,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
for (i = 0; i < MAX_INTERFACES; i++) {
struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;

- ifobj->umem = &ifobj->umem_arr[0];
ifobj->xsk = &ifobj->xsk_arr[0];
ifobj->use_poll = false;
ifobj->pacing_on = true;
@@ -401,11 +402,12 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
ifobj->tx_on = false;
}

+ memset(ifobj->umem, 0, sizeof(*ifobj->umem));
+ ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS;
+ ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
+
for (j = 0; j < MAX_SOCKETS; j++) {
- memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
- ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS;
- ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
}
}
@@ -950,7 +952,10 @@ static void tx_stats_validate(struct ifobject *ifobject)

static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
{
+ u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+ int ret, ifindex;
+ void *bufs;
u32 i;

ifobject->ns_fd = switch_namespace(ifobject->nsname);
@@ -958,23 +963,20 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
if (ifobject->umem->unaligned_mode)
mmap_flags |= MAP_HUGETLB;

- for (i = 0; i < test->nb_sockets; i++) {
- u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
- u32 ctr = 0;
- void *bufs;
- int ret;
+ bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+ if (bufs == MAP_FAILED)
+ exit_with_error(errno);

- bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
- if (bufs == MAP_FAILED)
- exit_with_error(errno);
+ ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz);
+ if (ret)
+ exit_with_error(-ret);

- ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz);
- if (ret)
- exit_with_error(-ret);
+ for (i = 0; i < test->nb_sockets; i++) {
+ u32 ctr = 0;

while (ctr++ < SOCK_RECONF_CTR) {
- ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i],
- ifobject, i);
+ ret = xsk_configure_socket(&ifobject->xsk_arr[i], ifobject->umem,
+ ifobject, !!i);
if (!ret)
break;

@@ -985,8 +987,22 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
}
}

- ifobject->umem = &ifobject->umem_arr[0];
ifobject->xsk = &ifobject->xsk_arr[0];
+
+ if (!ifobject->rx_on)
+ return;
+
+ ifindex = if_nametoindex(ifobject->ifname);
+ if (!ifindex)
+ exit_with_error(errno);
+
+ ret = xsk_setup_xdp_prog(ifindex, &ifobject->xsk_map_fd);
+ if (ret)
+ exit_with_error(-ret);
+
+ ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd);
+ if (ret)
+ exit_with_error(-ret);
}

static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
@@ -1142,14 +1158,16 @@ static void testapp_bidi(struct test_spec *test)

static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
{
+ int ret;
+
xsk_socket__delete(ifobj_tx->xsk->xsk);
- xsk_umem__delete(ifobj_tx->umem->umem);
xsk_socket__delete(ifobj_rx->xsk->xsk);
- xsk_umem__delete(ifobj_rx->umem->umem);
- ifobj_tx->umem = &ifobj_tx->umem_arr[1];
ifobj_tx->xsk = &ifobj_tx->xsk_arr[1];
- ifobj_rx->umem = &ifobj_rx->umem_arr[1];
ifobj_rx->xsk = &ifobj_rx->xsk_arr[1];
+
+ ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd);
+ if (ret)
+ exit_with_error(-ret);
}

static void testapp_bpf_res(struct test_spec *test)
@@ -1408,13 +1426,13 @@ static struct ifobject *ifobject_create(void)
if (!ifobj->xsk_arr)
goto out_xsk_arr;

- ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr));
- if (!ifobj->umem_arr)
- goto out_umem_arr;
+ ifobj->umem = calloc(1, sizeof(*ifobj->umem));
+ if (!ifobj->umem)
+ goto out_umem;

return ifobj;

-out_umem_arr:
+out_umem:
free(ifobj->xsk_arr);
out_xsk_arr:
free(ifobj);
@@ -1423,7 +1441,7 @@ static struct ifobject *ifobject_create(void)

static void ifobject_delete(struct ifobject *ifobj)
{
- free(ifobj->umem_arr);
+ free(ifobj->umem);
free(ifobj->xsk_arr);
free(ifobj);
}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 2f705f44b748..62a3e6388632 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -125,10 +125,10 @@ struct ifobject {
struct xsk_socket_info *xsk;
struct xsk_socket_info *xsk_arr;
struct xsk_umem_info *umem;
- struct xsk_umem_info *umem_arr;
thread_func_t func_ptr;
struct pkt_stream *pkt_stream;
int ns_fd;
+ int xsk_map_fd;
u32 dst_ip;
u32 src_ip;
u32 xdp_flags;
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
index 7eca97799917..554ca649d470 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -306,7 +306,8 @@ static void guest_restore_active(struct test_args *args,
uint32_t prio, intid, ap1r;
int i;

- /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
+ /*
+ * Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
* in descending order, so intid+1 can preempt intid.
*/
for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) {
@@ -315,7 +316,8 @@ static void guest_restore_active(struct test_args *args,
gic_set_priority(intid, prio);
}

- /* In a real migration, KVM would restore all GIC state before running
+ /*
+ * In a real migration, KVM would restore all GIC state before running
* guest code.
*/
for (i = 0; i < num; i++) {
@@ -472,10 +474,10 @@ static void test_restore_active(struct test_args *args, struct kvm_inject_desc *
guest_restore_active(args, MIN_SPI, 4, f->cmd);
}

-static void guest_code(struct test_args args)
+static void guest_code(struct test_args *args)
{
- uint32_t i, nr_irqs = args.nr_irqs;
- bool level_sensitive = args.level_sensitive;
+ uint32_t i, nr_irqs = args->nr_irqs;
+ bool level_sensitive = args->level_sensitive;
struct kvm_inject_desc *f, *inject_fns;

gic_init(GIC_V3, 1, dist, redist);
@@ -484,11 +486,11 @@ static void guest_code(struct test_args args)
gic_irq_enable(i);

for (i = MIN_SPI; i < nr_irqs; i++)
- gic_irq_set_config(i, !args.level_sensitive);
+ gic_irq_set_config(i, !level_sensitive);

- gic_set_eoi_split(args.eoi_split);
+ gic_set_eoi_split(args->eoi_split);

- reset_priorities(&args);
+ reset_priorities(args);
gic_set_priority_mask(CPU_PRIO_MASK);

inject_fns = level_sensitive ? inject_level_fns
@@ -497,17 +499,18 @@ static void guest_code(struct test_args args)
local_irq_enable();

/* Start the tests. */
- for_each_supported_inject_fn(&args, inject_fns, f) {
- test_injection(&args, f);
- test_preemption(&args, f);
- test_injection_failure(&args, f);
+ for_each_supported_inject_fn(args, inject_fns, f) {
+ test_injection(args, f);
+ test_preemption(args, f);
+ test_injection_failure(args, f);
}

- /* Restore the active state of IRQs. This would happen when live
+ /*
+ * Restore the active state of IRQs. This would happen when live
* migrating IRQs in the middle of being handled.
*/
- for_each_supported_activate_fn(&args, set_active_fns, f)
- test_restore_active(&args, f);
+ for_each_supported_activate_fn(args, set_active_fns, f)
+ test_restore_active(args, f);

GUEST_DONE();
}
@@ -573,8 +576,8 @@ static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm,
kvm_gsi_routing_write(vm, routing);
} else {
ret = _kvm_gsi_routing_write(vm, routing);
- /* The kernel only checks for KVM_IRQCHIP_NUM_PINS. */
- if (intid >= KVM_IRQCHIP_NUM_PINS)
+ /* The kernel only checks e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS */
+ if (((uint64_t)intid + num - 1 - MIN_SPI) >= KVM_IRQCHIP_NUM_PINS)
TEST_ASSERT(ret != 0 && errno == EINVAL,
"Bad intid %u did not cause KVM_SET_GSI_ROUTING "
"error: rc: %i errno: %i", intid, ret, errno);
@@ -739,6 +742,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
int gic_fd;
struct kvm_vm *vm;
struct kvm_inject_args inject_args;
+ vm_vaddr_t args_gva;

struct test_args args = {
.nr_irqs = nr_irqs,
@@ -757,7 +761,9 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
vcpu_init_descriptor_tables(vm, VCPU_ID);

/* Setup the guest args page (so it gets the args). */
- vcpu_args_set(vm, 0, 1, args);
+ args_gva = vm_vaddr_alloc_page(vm);
+ memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args));
+ vcpu_args_set(vm, 0, 1, args_gva);

gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
GICD_BASE_GPA, GICR_BASE_GPA);
@@ -841,7 +847,8 @@ int main(int argc, char **argv)
}
}

- /* If the user just specified nr_irqs and/or gic_version, then run all
+ /*
+ * If the user just specified nr_irqs and/or gic_version, then run all
* combinations.
*/
if (default_args) {
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
index 00f613c0583c..263bf3ed8fd5 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -19,7 +19,7 @@ struct gicv3_data {
unsigned int nr_spis;
};

-#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K)
+#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K)
#define DIST_BIT (1U << 31)

enum gicv3_intid_range {
@@ -105,7 +105,8 @@ static void gicv3_set_eoi_split(bool split)
{
uint32_t val;

- /* All other fields are read-only, so no need to read CTLR first. In
+ /*
+ * All other fields are read-only, so no need to read CTLR first. In
* fact, the kernel does the same.
*/
val = split ? (1U << 1) : 0;
@@ -159,9 +160,10 @@ static void gicv3_access_reg(uint32_t intid, uint64_t offset,
uint32_t cpu_or_dist;

GUEST_ASSERT(bits_per_field <= reg_bits);
- GUEST_ASSERT(*val < (1U << bits_per_field));
- /* Some registers like IROUTER are 64 bit long. Those are currently not
- * supported by readl nor writel, so just asserting here until then.
+ GUEST_ASSERT(!write || *val < (1U << bits_per_field));
+ /*
+ * This function does not support 64 bit accesses. Just asserting here
+ * until we implement readq/writeq.
*/
GUEST_ASSERT(reg_bits == 32);

diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index f5cd0c536d85..5d45046c1b80 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -140,9 +140,6 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid,
uint64_t val;
bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid);

- /* Check that the addr part of the attr is within 32 bits. */
- assert(attr <= KVM_DEV_ARM_VGIC_OFFSET_MASK);
-
uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
: KVM_DEV_ARM_VGIC_GRP_DIST_REGS;

@@ -152,7 +149,11 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid,
attr += SZ_64K;
}

- /* All calls will succeed, even with invalid intid's, as long as the
+ /* Check that the addr part of the attr is within 32 bits. */
+ assert((attr & ~KVM_DEV_ARM_VGIC_OFFSET_MASK) == 0);
+
+ /*
+ * All calls will succeed, even with invalid intid's, as long as the
* addr part of the attr is within 32 bits (checked above). An invalid
* intid will just make the read/writes point to above the intended
* register space (i.e., ICPENDR after ISPENDR).
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 246168310a75..610cc7920c8a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -439,8 +439,8 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)

static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
{
- kvm_dirty_ring_free(&vcpu->dirty_ring);
kvm_arch_vcpu_destroy(vcpu);
+ kvm_dirty_ring_free(&vcpu->dirty_ring);

/*
* No need for rcu_read_lock as VCPU_RUN is the only place that changes