diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index e7e160954e79..0579860b5529 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -562,7 +562,8 @@ Description: Control Symmetric Multi Threading (SMT) ================ =========================================

If control status is "forceoff" or "notsupported" writes - are rejected. + are rejected. Note that enabling SMT on PowerPC skips + offline cores.

What: /sys/devices/system/cpu/cpuX/power/energy_perf_bias Date: March 2019 diff --git a/Makefile b/Makefile index 361a70264e1f..ab77d171e268 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 10 -SUBLEVEL = 6 +SUBLEVEL = 7 EXTRAVERSION = NAME = Baby Opossum Posse

@@ -1986,7 +1986,7 @@ nsdeps: modules quiet_cmd_gen_compile_commands = GEN $@ cmd_gen_compile_commands = $(PYTHON3) $< -a $(AR) -o $@ $(filter-out $<, $(real-prereqs))

-$(extmod_prefix)compile_commands.json: scripts/clang-tools/gen_compile_commands.py \ +$(extmod_prefix)compile_commands.json: $(srctree)/scripts/clang-tools/gen_compile_commands.py \ $(if $(KBUILD_EXTMOD),, vmlinux.a $(KBUILD_VMLINUX_LIBS)) \ $(if $(CONFIG_MODULES), $(MODORDER)) FORCE $(call if_changed,gen_compile_commands) diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index e51535a5f939..ccbff21ce1fa 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -27,7 +27,7 @@

#include <asm/numa.h>

-static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; +static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE };

int __init acpi_numa_get_nid(unsigned int cpu) { diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index a096e2451044..b22d28ec8028 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -355,9 +355,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) smp_init_cpus(); smp_build_mpidr_hash();

- /* Init percpu seeds for random tags after cpus are set up. */ - kasan_init_sw_tags(); - #ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Make sure init_thread_info.ttbr0 always generates translation diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 5de85dccc09c..05688f6a275f 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -469,6 +469,8 @@ void __init smp_prepare_boot_cpu(void) init_gic_priority_masking();

kasan_init_hw_tags(); + /* Init percpu seeds for random tags after cpus are set up. */ + kasan_init_sw_tags(); }

/* diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 22b45a15d068..33d866ca8f65 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -33,6 +33,7 @@ #include <trace/events/kvm.h>

#include "sys_regs.h" +#include "vgic/vgic.h"

#include "trace.h"

@@ -428,6 +429,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu, { bool g1;

+ if (!kvm_has_gicv3(vcpu->kvm)) { + kvm_inject_undefined(vcpu); + return false; + } + if (!p->is_write) return read_from_write_only(vcpu, p, r);

diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index bcbc8c986b1d..980fbe4fd82c 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -84,7 +84,7 @@ static void iter_unmark_lpis(struct kvm *kvm) struct vgic_irq *irq; unsigned long intid;

- xa_for_each(&dist->lpi_xa, intid, irq) { + xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) { xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); vgic_put_irq(kvm, irq); } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 03d356a12377..55e3b7108dc9 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -346,4 +346,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm); void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq);

+static inline bool kvm_has_gicv3(struct kvm *kvm) +{ + return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) && + irqchip_in_kernel(kvm) && + kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3); +} + #endif diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index bda7f193baab..af7412549e6e 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1724,12 +1724,16 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM | MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2); c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */ + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; case PRID_IMP_LOONGSON_64G: __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); decode_cpucfg(c); + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; default: panic("Unknown Loongson Processor ID!"); diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index f4e6f2dd04b7..16bacfe8c7a2 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -145,6 +145,7 @@ static inline int cpu_to_coregroup_id(int cpu)

#ifdef CONFIG_HOTPLUG_SMT #include <linux/cpu_smt.h> +#include <linux/cpumask.h> #include <asm/cputhreads.h>

static inline bool topology_is_primary_thread(unsigned int cpu) @@ -156,6 +157,18 @@ static inline bool topology_smt_thread_allowed(unsigned int cpu) { return cpu_thread_in_core(cpu) < cpu_smt_num_threads; } + +#define topology_is_core_online topology_is_core_online +static inline bool topology_is_core_online(unsigned int cpu) +{ + int i, first_cpu = cpu_first_thread_sibling(cpu); + + for (i = first_cpu; i < first_cpu + threads_per_core; ++i) { + if (cpu_online(i)) + return true; + } + return false; +} #endif

#endif /* __KERNEL__ */ diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 05a16b1f0aee..51ebfd23e007 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -319,6 +319,7 @@ void do_trap_ecall_u(struct pt_regs *regs)

regs->epc += 4; regs->orig_a0 = regs->a0; + regs->a0 = -ENOSYS;

riscv_v_vstate_discard(regs);

@@ -328,8 +329,7 @@ void do_trap_ecall_u(struct pt_regs *regs)

if (syscall >= 0 && syscall < NR_syscalls) syscall_handler(regs, syscall); - else if (syscall != -1) - regs->a0 = -ENOSYS; + /* * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), * so the maximum stack offset is 1k bytes (10 bits). diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 7e25606f858a..c5c66f53971a 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -931,7 +931,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir, PMD_SIZE, PAGE_KERNEL_EXEC);

/* Map the data in RAM */ - end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size; + end_va = kernel_map.virt_addr + kernel_map.size; for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE) create_pgd_mapping(pgdir, va, kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)), @@ -1100,7 +1100,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)

phys_ram_base = CONFIG_PHYS_RAM_BASE; kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; - kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata); + kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start);

kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom; #else diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 5a36d5538dae..6d88f241dd43 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -161,7 +161,7 @@ static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, loc = (long)*reloc + phys_offset; if (loc < min_addr || loc > max_addr) error("64-bit relocation outside of kernel!\n"); - *(u64 *)loc += offset - __START_KERNEL; + *(u64 *)loc += offset; } }

@@ -176,7 +176,7 @@ static void kaslr_adjust_got(unsigned long offset) */ for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) { if (*entry) - *entry += offset - __START_KERNEL; + *entry += offset; } }

@@ -251,7 +251,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);

/* choose kernel address space layout: 4 or 3 levels. */ - BUILD_BUG_ON(!IS_ALIGNED(__START_KERNEL, THREAD_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(TEXT_OFFSET, THREAD_SIZE)); BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE)); BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE); vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE); @@ -378,31 +378,25 @@ static void kaslr_adjust_vmlinux_info(long offset) #endif }

-static void fixup_vmlinux_info(void) -{ - vmlinux.entry -= __START_KERNEL; - kaslr_adjust_vmlinux_info(-__START_KERNEL); -} - void startup_kernel(void) { - unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size; - unsigned long nokaslr_offset_phys, kaslr_large_page_offset; - unsigned long amode31_lma = 0; + unsigned long vmlinux_size = vmlinux.image_size + vmlinux.bss_size; + unsigned long nokaslr_text_lma, text_lma = 0, amode31_lma = 0; + unsigned long kernel_size = TEXT_OFFSET + vmlinux_size; + unsigned long kaslr_large_page_offset; unsigned long max_physmem_end; unsigned long asce_limit; unsigned long safe_addr; psw_t psw;

- fixup_vmlinux_info(); setup_lpp();

/* * Non-randomized kernel physical start address must be _SEGMENT_SIZE * aligned (see blow). */ - nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE); - safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size); + nokaslr_text_lma = ALIGN(mem_safe_offset(), _SEGMENT_SIZE); + safe_addr = PAGE_ALIGN(nokaslr_text_lma + vmlinux_size);

/* * Reserve decompressor memory together with decompression heap, @@ -446,16 +440,27 @@ void startup_kernel(void) */ kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK; if (kaslr_enabled()) { - unsigned long end = ident_map_size - kaslr_large_page_offset; + unsigned long size = vmlinux_size + kaslr_large_page_offset;

- __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end); + text_lma = randomize_within_range(size, _SEGMENT_SIZE, TEXT_OFFSET, ident_map_size); } - if (!__kaslr_offset_phys) - __kaslr_offset_phys = nokaslr_offset_phys; - __kaslr_offset_phys |= kaslr_large_page_offset; + if (!text_lma) + text_lma = nokaslr_text_lma; + text_lma |= kaslr_large_page_offset; + + /* + * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region is + * never accessed via the kernel image mapping as per the linker script: + * + * . = TEXT_OFFSET; + * + * Therefore, this region could be used for something else and does + * not need to be reserved. See how it is skipped in setup_vmem(). + */ + __kaslr_offset_phys = text_lma - TEXT_OFFSET; kaslr_adjust_vmlinux_info(__kaslr_offset_phys); - physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size); - deploy_kernel((void *)__kaslr_offset_phys); + physmem_reserve(RR_VMLINUX, text_lma, vmlinux_size); + deploy_kernel((void *)text_lma);

/* vmlinux decompression is done, shrink reserved low memory */ physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end); @@ -474,7 +479,7 @@ void startup_kernel(void) if (kaslr_enabled()) amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G); if (!amode31_lma) - amode31_lma = __kaslr_offset_phys - vmlinux.amode31_size; + amode31_lma = text_lma - vmlinux.amode31_size; physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size);

/* @@ -490,8 +495,8 @@ void startup_kernel(void) * - copy_bootdata() must follow setup_vmem() to propagate changes * to bootdata made by setup_vmem() */ - clear_bss_section(__kaslr_offset_phys); - kaslr_adjust_relocs(__kaslr_offset_phys, __kaslr_offset_phys + vmlinux.image_size, + clear_bss_section(text_lma); + kaslr_adjust_relocs(text_lma, text_lma + vmlinux.image_size, __kaslr_offset, __kaslr_offset_phys); kaslr_adjust_got(__kaslr_offset); setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 40cfce2687c4..3d4dae9905cd 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -89,7 +89,7 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern } memgap_start = end; } - kasan_populate(kernel_start, kernel_end, POPULATE_KASAN_MAP_SHADOW); + kasan_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KASAN_MAP_SHADOW); kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW); kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { @@ -466,7 +466,17 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l (unsigned long)__identity_va(end), POPULATE_IDENTITY); } - pgtable_populate(kernel_start, kernel_end, POPULATE_KERNEL); + + /* + * [kernel_start..kernel_start + TEXT_OFFSET] region is never + * accessed as per the linker script: + * + * . = TEXT_OFFSET; + * + * Therefore, skip mapping TEXT_OFFSET bytes to prevent access to + * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region. + */ + pgtable_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KERNEL); pgtable_populate(AMODE31_START, AMODE31_END, POPULATE_DIRECT); pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore), POPULATE_ABS_LOWCORE); diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index a750711d44c8..66670212a361 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -109,7 +109,12 @@ SECTIONS #ifdef CONFIG_KERNEL_UNCOMPRESSED . = ALIGN(PAGE_SIZE); . += AMODE31_SIZE; /* .amode31 section */ - . = ALIGN(1 << 20); /* _SEGMENT_SIZE */ + + /* + * Make sure the location counter is not less than TEXT_OFFSET. + * _SEGMENT_SIZE is not available, use ALIGN(1 << 20) instead. + */ + . = MAX(TEXT_OFFSET, ALIGN(1 << 20)); #else . = ALIGN(8); #endif diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 224ff9d433ea..8cac1a737424 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -276,8 +276,9 @@ static inline unsigned long virt_to_pfn(const void *kaddr) #define AMODE31_SIZE (3 * PAGE_SIZE)

#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) -#define __START_KERNEL 0x100000 #define __NO_KASLR_START_KERNEL CONFIG_KERNEL_IMAGE_BASE #define __NO_KASLR_END_KERNEL (__NO_KASLR_START_KERNEL + KERNEL_IMAGE_SIZE)

+#define TEXT_OFFSET 0x100000 + #endif /* _S390_PAGE_H */ diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0e7bd3873907..b2e2f9a4163c 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -442,7 +442,10 @@ static inline int share(unsigned long addr, u16 cmd)

if (!uv_call(0, (u64)&uvcb)) return 0; - return -EINVAL; + pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n", + uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare", + uvcb.header.rc, uvcb.header.rrc); + panic("System security cannot be guaranteed unless the system panics now.\n"); }

/* diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index a1ce3925ec71..52bd969b2828 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -39,7 +39,7 @@ PHDRS {

SECTIONS { - . = __START_KERNEL; + . = TEXT_OFFSET; .text : { _stext = .; /* Start of text section */ _text = .; /* Text and read-only data */ diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index bf8534218af3..e680c6bf0c9d 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -267,7 +267,12 @@ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots)

static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) { - u32 gd = virt_to_phys(kvm->arch.gisa_int.origin); + u32 gd; + + if (!kvm->arch.gisa_int.origin) + return 0; + + gd = virt_to_phys(kvm->arch.gisa_int.origin);

if (gd && sclp.has_gisaf) gd |= GISA_FORMAT1; diff --git a/arch/s390/tools/relocs.c b/arch/s390/tools/relocs.c index a74dbd5c9896..30a732c808f3 100644 --- a/arch/s390/tools/relocs.c +++ b/arch/s390/tools/relocs.c @@ -280,7 +280,7 @@ static int do_reloc(struct section *sec, Elf_Rel *rel) case R_390_GOTOFF64: break; case R_390_64: - add_reloc(&relocs64, offset - ehdr.e_entry); + add_reloc(&relocs64, offset); break; default: die("Unsupported relocation type: %d\n", r_type); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index cc57e2dd9a0b..2cafcf11ee8b 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + unsigned long flags; struct blk_mq_tags *tags = hctx->tags;

/* @@ -56,11 +57,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) return; }

- spin_lock_irq(&tags->lock); + spin_lock_irqsave(&tags->lock, flags); users = tags->active_queues + 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); - spin_unlock_irq(&tags->lock); + spin_unlock_irqrestore(&tags->lock, flags); }

/* diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index 2133085deda7..1c5218b79fc2 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -188,13 +188,9 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj, u8 acpi_ns_is_locked);

void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function);

-void -acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node, - acpi_adr_space_type space_id); - acpi_status acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function);

diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index dc6004daf624..cf53b9535f18 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -20,6 +20,10 @@ extern u8 acpi_gbl_default_address_spaces[];

/* Local prototypes */

+static void +acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, + acpi_adr_space_type space_id); + static acpi_status acpi_ev_reg_run(acpi_handle obj_handle, u32 level, void *context, void **return_value); @@ -61,6 +65,7 @@ acpi_status acpi_ev_initialize_op_regions(void) acpi_gbl_default_address_spaces [i])) { acpi_ev_execute_reg_methods(acpi_gbl_root_node, + ACPI_UINT32_MAX, acpi_gbl_default_address_spaces [i], ACPI_REG_CONNECT); } @@ -668,6 +673,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function) * FUNCTION: acpi_ev_execute_reg_methods * * PARAMETERS: node - Namespace node for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * function - Passed to _REG: On (1) or Off (0) * @@ -679,7 +685,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function) ******************************************************************************/

void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function) { struct acpi_reg_walk_info info; @@ -713,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, * regions and _REG methods. (i.e. handlers must be installed for all * regions of this Space ID before we can run any _REG methods) */ - (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX, + (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, max_depth, ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run, NULL, &info, NULL);

@@ -814,7 +820,7 @@ acpi_ev_reg_run(acpi_handle obj_handle, * ******************************************************************************/

-void +static void acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, acpi_adr_space_type space_id) { diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 624361a5f34d..95f78383bbdb 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -85,7 +85,8 @@ acpi_install_address_space_handler_internal(acpi_handle device, /* Run all _REG methods for this address space */

if (run_reg) { - acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, ACPI_UINT32_MAX, space_id, + ACPI_REG_CONNECT); }

unlock_and_exit: @@ -263,6 +264,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * FUNCTION: acpi_execute_reg_methods * * PARAMETERS: device - Handle for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * * RETURN: Status @@ -271,7 +273,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * ******************************************************************************/ acpi_status -acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) +acpi_execute_reg_methods(acpi_handle device, u32 max_depth, + acpi_adr_space_type space_id) { struct acpi_namespace_node *node; acpi_status status; @@ -296,7 +299,8 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)

/* Run all _REG methods for this address space */

- acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, max_depth, space_id, + ACPI_REG_CONNECT); } else { status = AE_BAD_PARAMETER; } @@ -306,57 +310,3 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) }

ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods) - -/******************************************************************************* - * - * FUNCTION: acpi_execute_orphan_reg_method - * - * PARAMETERS: device - Handle for the device - * space_id - The address space ID - * - * RETURN: Status - * - * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI - * device. This is a _REG method that has no corresponding region - * within the device's scope. - * - ******************************************************************************/ -acpi_status -acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id) -{ - struct acpi_namespace_node *node; - acpi_status status; - - ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method); - - /* Parameter validation */ - - if (!device) { - return_ACPI_STATUS(AE_BAD_PARAMETER); - } - - status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); - if (ACPI_FAILURE(status)) { - return_ACPI_STATUS(status); - } - - /* Convert and validate the device handle */ - - node = acpi_ns_validate_handle(device); - if (node) { - - /* - * If an "orphan" _REG method is present in the device's scope - * for the given address space ID, run it. - */ - - acpi_ev_execute_orphan_reg_method(node, space_id); - } else { - status = AE_BAD_PARAMETER; - } - - (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); - return_ACPI_STATUS(status); -} - -ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 299ec653388c..38d2f6e6b12b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1487,12 +1487,13 @@ static bool install_gpio_irq_event_handler(struct acpi_ec *ec) static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, bool call_reg) { - acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; acpi_status status;

acpi_ec_start(ec, false);

if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { + acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; + acpi_ec_enter_noirq(ec); status = acpi_install_address_space_handler_no_reg(scope_handle, ACPI_ADR_SPACE_EC, @@ -1506,10 +1507,7 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, }

if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { - acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); - if (scope_handle != ec->handle) - acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC); - + acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); }

@@ -1724,6 +1722,12 @@ static void acpi_ec_remove(struct acpi_device *device) } }

+void acpi_ec_register_opregions(struct acpi_device *adev) +{ + if (first_ec && first_ec->handle != adev->handle) + acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC); +} + static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context) { diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 601b670356e5..aadd4c218b32 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -223,6 +223,7 @@ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, void *data); void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); +void acpi_ec_register_opregions(struct acpi_device *adev);

#ifdef CONFIG_PM_SLEEP void acpi_ec_flush_work(void); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 503773707e01..cdc5a74092c7 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2264,6 +2264,8 @@ static int acpi_bus_attach(struct acpi_device *device, void *first_pass) if (device->handler) goto ok;

+ acpi_ec_register_opregions(device); + if (!device->flags.initialized) { device->flags.power_manageable = device->power.states[ACPI_STATE_D0].flags.valid; diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 2cc3821b2b16..ff6f260433a1 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -54,6 +54,8 @@ static void acpi_video_parse_cmdline(void) acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec; if (!strcmp("apple_gmux", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_apple_gmux; + if (!strcmp("dell_uart", acpi_video_backlight_string)) + acpi_backlight_cmdline = acpi_backlight_dell_uart; if (!strcmp("none", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_none; } @@ -805,6 +807,21 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, },

+ /* + * Dell AIO (All in Ones) which advertise an UART attached backlight + * controller board in their ACPI tables (and may even have one), but + * which need native backlight control nevertheless. + */ + { + /* https://bugzilla.redhat.com/show_bug.cgi?id=2303936 */ + .callback = video_detect_force_native, + /* Dell OptiPlex 7760 AIO */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7760 AIO"), + }, + }, + /* * Models which have nvidia-ec-wmi support, but should not use it. * Note this indicates a likely firmware bug on these models and should @@ -902,6 +919,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; static bool apple_gmux_present; + static bool dell_uart_present; static bool native_available; static bool init_done; static long video_caps; @@ -916,6 +934,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto &video_caps, NULL); nvidia_wmi_ec_present = nvidia_wmi_ec_supported(); apple_gmux_present = apple_gmux_detect(NULL, NULL); + dell_uart_present = acpi_dev_present("DELL0501", NULL, -1); init_done = true; } if (native) @@ -946,6 +965,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto if (apple_gmux_present) return acpi_backlight_apple_gmux;

+ if (dell_uart_present) + return acpi_backlight_dell_uart; + /* Use ACPI video if available, except when native should be preferred. */ if ((video_caps & ACPI_VIDEO_BACKLIGHT) && !(native_available && prefer_native_over_acpi_video())) diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 3cb455a32d92..99fc5d9d95d7 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -208,6 +208,19 @@ static const char* macio_ata_names[] = { /* Don't let a DMA segment go all the way to 64K */ #define MAX_DBDMA_SEG 0xff00

+#ifdef CONFIG_PAGE_SIZE_64KB +/* + * The SCSI core requires the segment size to cover at least a page, so + * for 64K page size kernels it must be at least 64K. However the + * hardware can't handle 64K, so pata_macio_qc_prep() will split large + * requests. To handle the split requests the tablesize must be halved. + */ +#define PATA_MACIO_MAX_SEGMENT_SIZE SZ_64K +#define PATA_MACIO_SG_TABLESIZE (MAX_DCMDS / 2) +#else +#define PATA_MACIO_MAX_SEGMENT_SIZE MAX_DBDMA_SEG +#define PATA_MACIO_SG_TABLESIZE MAX_DCMDS +#endif

/* * Wait 1s for disk to answer on IDE bus after a hard reset @@ -912,16 +925,10 @@ static int pata_macio_do_resume(struct pata_macio_priv *priv)

static const struct scsi_host_template pata_macio_sht = { __ATA_BASE_SHT(DRV_NAME), - .sg_tablesize = MAX_DCMDS, + .sg_tablesize = PATA_MACIO_SG_TABLESIZE, /* We may not need that strict one */ .dma_boundary = ATA_DMA_BOUNDARY, - /* - * The SCSI core requires the segment size to cover at least a page, so - * for 64K page size kernels this must be at least 64K. However the - * hardware can't handle 64K, so pata_macio_qc_prep() will split large - * requests. - */ - .max_segment_size = SZ_64K, + .max_segment_size = PATA_MACIO_MAX_SEGMENT_SIZE, .device_configure = pata_macio_device_configure, .sdev_groups = ata_common_sdev_groups, .can_queue = ATA_DEF_QUEUE, diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e7f713cd70d3..a876024d8a05 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len;

if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len;

l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6);

@@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb);

+ truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx);

- if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 93900c37349c..c084dc88d3d9 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2876,9 +2876,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) INTEL_ROM_LEGACY_NO_WBS_SUPPORT)) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22) - set_bit(HCI_QUIRK_VALID_LE_STATES, - &hdev->quirks);

err = btintel_legacy_rom_setup(hdev, &ver); break; @@ -2887,7 +2884,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) case 0x12: /* ThP */ case 0x13: /* HrP */ case 0x14: /* CcP */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); fallthrough; case 0x0c: /* WsP */ /* Apply the device specific HCI quirks @@ -2979,9 +2975,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) /* These variants don't seem to support LE Coded PHY */ set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks);

- /* Set Valid LE States quirk */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, ver.hw_variant);

@@ -3003,9 +2996,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

- /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index b8120b98a239..1fd3b7073ab9 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1182,9 +1182,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

- /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 8ded9ef8089a..bc4700ed3b78 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -1144,9 +1144,6 @@ static int btmtksdio_setup(struct hci_dev *hdev) } }

- /* Valid LE States quirk for MediaTek 7921 */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - break; case 0x7663: case 0x7668: diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 4f1e37b4f780..bfcb41a57655 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) case CHIP_ID_8852C: case CHIP_ID_8851B: case CHIP_ID_8852BT: - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

/* RTL8852C needs to transmit mSBC data continuously without diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 789c492df6fa..0927f51867c2 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4545,8 +4545,8 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_WIDEBAND_SPEECH) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

- if (id->driver_info & BTUSB_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(id->driver_info & BTUSB_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);

if (id->driver_info & BTUSB_DIGIANSWER) { data->cmdreq_type = USB_TYPE_VENDOR; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 9a0bc86f9aac..34c36f0f781e 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2408,8 +2408,8 @@ static int qca_serdev_probe(struct serdev_device *serdev) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

- if (data->capabilities & QCA_CAP_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(data->capabilities & QCA_CAP_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); }

return 0; diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 28750a40f0ed..b652d68f0ee1 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) if (opcode & 0x80) set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks);

- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); hci_free_dev(hdev); diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c index 5a5afa14ca8c..45771b1a3716 100644 --- a/drivers/char/xillybus/xillyusb.c +++ b/drivers/char/xillybus/xillyusb.c @@ -50,6 +50,7 @@ MODULE_LICENSE("GPL v2"); static const char xillyname[] = "xillyusb";

static unsigned int fifo_buf_order; +static struct workqueue_struct *wakeup_wq;

#define USB_VENDOR_ID_XILINX 0x03fd #define USB_VENDOR_ID_ALTERA 0x09fb @@ -569,10 +570,6 @@ static void cleanup_dev(struct kref *kref) * errors if executed. The mechanism relies on that xdev->error is assigned * a non-zero value by report_io_error() prior to queueing wakeup_all(), * which prevents bulk_in_work() from calling process_bulk_in(). - * - * The fact that wakeup_all() and bulk_in_work() are queued on the same - * workqueue makes their concurrent execution very unlikely, however the - * kernel's API doesn't seem to ensure this strictly. */

static void wakeup_all(struct work_struct *work) @@ -627,7 +624,7 @@ static void report_io_error(struct xillyusb_dev *xdev,

if (do_once) { kref_get(&xdev->kref); /* xdev is used by work item */ - queue_work(xdev->workq, &xdev->wakeup_workitem); + queue_work(wakeup_wq, &xdev->wakeup_workitem); } }

@@ -1906,6 +1903,13 @@ static const struct file_operations xillyusb_fops = {

static int xillyusb_setup_base_eps(struct xillyusb_dev *xdev) { + struct usb_device *udev = xdev->udev; + + /* Verify that device has the two fundamental bulk in/out endpoints */ + if (usb_pipe_type_check(udev, usb_sndbulkpipe(udev, MSG_EP_NUM)) || + usb_pipe_type_check(udev, usb_rcvbulkpipe(udev, IN_EP_NUM))) + return -ENODEV; + xdev->msg_ep = endpoint_alloc(xdev, MSG_EP_NUM | USB_DIR_OUT, bulk_out_work, 1, 2); if (!xdev->msg_ep) @@ -1935,14 +1939,15 @@ static int setup_channels(struct xillyusb_dev *xdev, __le16 *chandesc, int num_channels) { - struct xillyusb_channel *chan; + struct usb_device *udev = xdev->udev; + struct xillyusb_channel *chan, *new_channels; int i;

chan = kcalloc(num_channels, sizeof(*chan), GFP_KERNEL); if (!chan) return -ENOMEM;

- xdev->channels = chan; + new_channels = chan;

for (i = 0; i < num_channels; i++, chan++) { unsigned int in_desc = le16_to_cpu(*chandesc++); @@ -1971,6 +1976,15 @@ static int setup_channels(struct xillyusb_dev *xdev, */

if ((out_desc & 0x80) && i < 14) { /* Entry is valid */ + if (usb_pipe_type_check(udev, + usb_sndbulkpipe(udev, i + 2))) { + dev_err(xdev->dev, + "Missing BULK OUT endpoint %d\n", + i + 2); + kfree(new_channels); + return -ENODEV; + } + chan->writable = 1; chan->out_synchronous = !!(out_desc & 0x40); chan->out_seekable = !!(out_desc & 0x20); @@ -1980,6 +1994,7 @@ static int setup_channels(struct xillyusb_dev *xdev, } }

+ xdev->channels = new_channels; return 0; }

@@ -2096,9 +2111,11 @@ static int xillyusb_discovery(struct usb_interface *interface) * just after responding with the IDT, there is no reason for any * work item to be running now. To be sure that xdev->channels * is updated on anything that might run in parallel, flush the - * workqueue, which rarely does anything. + * device's workqueue and the wakeup work item. This rarely + * does anything. */ flush_workqueue(xdev->workq); + flush_work(&xdev->wakeup_workitem);

xdev->num_channels = num_channels;

@@ -2258,6 +2275,10 @@ static int __init xillyusb_init(void) { int rc = 0;

+ wakeup_wq = alloc_workqueue(xillyname, 0, 0); + if (!wakeup_wq) + return -ENOMEM; + if (LOG2_INITIAL_FIFO_BUF_SIZE > PAGE_SHIFT) fifo_buf_order = LOG2_INITIAL_FIFO_BUF_SIZE - PAGE_SHIFT; else @@ -2265,12 +2286,17 @@ static int __init xillyusb_init(void)

rc = usb_register(&xillyusb_driver);

+ if (rc) + destroy_workqueue(wakeup_wq); + return rc; }

static void __exit xillyusb_exit(void) { usb_deregister(&xillyusb_driver); + + destroy_workqueue(wakeup_wq); }

module_init(xillyusb_init); diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c index d5906d419b0a..10ea71273c89 100644 --- a/drivers/gpio/gpio-mlxbf3.c +++ b/drivers/gpio/gpio-mlxbf3.c @@ -39,6 +39,8 @@ #define MLXBF_GPIO_CAUSE_OR_EVTEN0 0x14 #define MLXBF_GPIO_CAUSE_OR_CLRCAUSE 0x18

+#define MLXBF_GPIO_CLR_ALL_INTS GENMASK(31, 0) + struct mlxbf3_gpio_context { struct gpio_chip gc;

@@ -82,6 +84,8 @@ static void mlxbf3_gpio_irq_disable(struct irq_data *irqd) val = readl(gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); val &= ~BIT(offset); writel(val, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + + writel(BIT(offset), gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);

gpiochip_disable_irq(gc, offset); @@ -253,6 +257,15 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) return 0; }

+static void mlxbf3_gpio_shutdown(struct platform_device *pdev) +{ + struct mlxbf3_gpio_context *gs = platform_get_drvdata(pdev); + + /* Disable and clear all interrupts */ + writel(0, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + writel(MLXBF_GPIO_CLR_ALL_INTS, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); +} + static const struct acpi_device_id mlxbf3_gpio_acpi_match[] = { { "MLNXBF33", 0 }, {} @@ -265,6 +278,7 @@ static struct platform_driver mlxbf3_gpio_driver = { .acpi_match_table = mlxbf3_gpio_acpi_match, }, .probe = mlxbf3_gpio_probe, + .shutdown = mlxbf3_gpio_shutdown, }; module_platform_driver(mlxbf3_gpio_driver);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 13eb2bc69e34..936c98a13a24 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1057,6 +1057,9 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p, r = amdgpu_ring_parse_cs(ring, p, job, ib); if (r) return r; + + if (ib->sa_bo) + ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo); } else { ib->ptr = (uint32_t *)kptr; r = amdgpu_ring_patch_cs_in_place(ring, p, job, ib); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 5cb33ac99f70..c43d1b6e5d66 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -685,16 +685,24 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,

switch (args->in.op) { case AMDGPU_CTX_OP_ALLOC_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id); args->out.alloc.ctx_id = id; break; case AMDGPU_CTX_OP_FREE_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_free(fpriv, id); break; case AMDGPU_CTX_OP_QUERY_STATE: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_QUERY_STATE2: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query2(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_GET_STABLE_PSTATE: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index 8e8afbd237bc..9aff579c6abf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -166,6 +166,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t if (ret) return -EFAULT;

+ if (ta_bin_len > PSP_1_MEG) + return -EINVAL; + copy_pos += sizeof(uint32_t);

ta_bin = kzalloc(ta_bin_len, GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 677eb141554e..ceb3f1e4ed1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -151,6 +151,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) } }

+ /* from vcn4 and above, only unified queue is used */ + adev->vcn.using_unified_queue = + amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0); + hdr = (const struct common_firmware_header *)adev->vcn.fw[0]->data; adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);

@@ -279,18 +283,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) return 0; }

-/* from vcn4 and above, only unified queue is used */ -static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring) -{ - struct amdgpu_device *adev = ring->adev; - bool ret = false; - - if (amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0)) - ret = true; - - return ret; -} - bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance) { bool ret = false; @@ -401,7 +393,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work) for (i = 0; i < adev->vcn.num_enc_rings; ++i) fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);

- if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.using_unified_queue) { struct dpg_pause_state new_state;

if (fence[j] || @@ -447,7 +441,9 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_UNGATE);

- if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.using_unified_queue) { struct dpg_pause_state new_state;

if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) { @@ -473,8 +469,12 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)

void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring) { + struct amdgpu_device *adev = ring->adev; + + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && - ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) + ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC && + !adev->vcn.using_unified_queue) atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt);

atomic_dec(&ring->adev->vcn.total_submission_cnt); @@ -728,12 +728,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, struct amdgpu_job *job; struct amdgpu_ib *ib; uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr); - bool sq = amdgpu_vcn_using_unified_queue(ring); uint32_t *ib_checksum; uint32_t ib_pack_in_dw; int i, r;

- if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8;

r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -746,7 +745,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, ib->length_dw = 0;

/* single queue headers */ - if (sq) { + if (adev->vcn.using_unified_queue) { ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t) + 4 + 2; /* engine info + decoding ib in dw */ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false); @@ -765,7 +764,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0;

- if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw);

r = amdgpu_job_submit_direct(job, ring, &f); @@ -855,15 +854,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand struct dma_fence **fence) { unsigned int ib_size_dw = 16; + struct amdgpu_device *adev = ring->adev; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; uint32_t *ib_checksum = NULL; uint64_t addr; - bool sq = amdgpu_vcn_using_unified_queue(ring); int i, r;

- if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8;

r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -877,7 +876,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand

ib->length_dw = 0;

- if (sq) + if (adev->vcn.using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);

ib->ptr[ib->length_dw++] = 0x00000018; @@ -899,7 +898,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0;

- if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);

r = amdgpu_job_submit_direct(job, ring, &f); @@ -922,15 +921,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han struct dma_fence **fence) { unsigned int ib_size_dw = 16; + struct amdgpu_device *adev = ring->adev; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; uint32_t *ib_checksum = NULL; uint64_t addr; - bool sq = amdgpu_vcn_using_unified_queue(ring); int i, r;

- if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8;

r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL, @@ -944,7 +943,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han

ib->length_dw = 0;

- if (sq) + if (adev->vcn.using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);

ib->ptr[ib->length_dw++] = 0x00000018; @@ -966,7 +965,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0;

- if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);

r = amdgpu_job_submit_direct(job, ring, &f); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 9f06def236fd..1a5439abd1a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -329,6 +329,7 @@ struct amdgpu_vcn {

uint16_t inst_mask; uint8_t num_inst_per_aid; + bool using_unified_queue; };

struct amdgpu_fw_shared_rb_ptrs_struct { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index ef3e42f6b841..63f84ef6dfcf 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -543,11 +543,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,

amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));

amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));

amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c index d66af11aa66c..d24d06f6d682 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c @@ -23,6 +23,7 @@

#include "amdgpu.h" #include "amdgpu_jpeg.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "jpeg_v4_0_3.h" @@ -773,11 +774,15 @@ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,

amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + + if (ring->funcs->parse_cs) + amdgpu_ring_write(ring, 0); + else + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));

amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));

amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); @@ -1063,6 +1068,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = { .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr, .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr, .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr, + .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + @@ -1227,3 +1233,56 @@ static void jpeg_v4_0_3_set_ras_funcs(struct amdgpu_device *adev) { adev->jpeg.ras = &jpeg_v4_0_3_ras; } + +/** + * jpeg_v4_0_3_dec_ring_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ +int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t i, reg, res, cond, type; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res) /* only support 0 at the moment */ + return -EINVAL; + + switch (type) { + case PACKETJ_TYPE0: + if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE3: + if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + } + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] == CP_PACKETJ_NOP) + continue; + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + return -EINVAL; + default: + dev_err(adev->dev, "Unknown packet type %d !\n", type); + return -EINVAL; + } + } + + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h index 747a3e5f6856..71c54b294e15 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h @@ -46,6 +46,9 @@

#define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000

+#define JPEG_REG_RANGE_START 0x4000 +#define JPEG_REG_RANGE_END 0x41c2 + extern const struct amdgpu_ip_block_version jpeg_v4_0_3_ip_block;

void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring, @@ -62,5 +65,7 @@ void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring); void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val); void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg, uint32_t val, uint32_t mask); - +int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); #endif /* __JPEG_V4_0_3_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c index 64c856bfe0cb..90299f66a444 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c @@ -523,6 +523,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = { .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr, + .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index af1e90159ce3..2e72d445415f 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -176,14 +176,16 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring) DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n", ring->doorbell_index, ring->wptr << 2); WDOORBELL64(ring->doorbell_index, ring->wptr << 2); - /* SDMA seems to miss doorbells sometimes when powergating kicks in. - * Updating the wptr directly will wake it. This is only safe because - * we disallow gfxoff in begin_use() and then allow it again in end_use(). - */ - WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), - lower_32_bits(ring->wptr << 2)); - WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), - upper_32_bits(ring->wptr << 2)); + if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(5, 2, 1)) { + /* SDMA seems to miss doorbells sometimes when powergating kicks in. + * Updating the wptr directly will wake it. This is only safe because + * we disallow gfxoff in begin_use() and then allow it again in end_use(). + */ + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), + lower_32_bits(ring->wptr << 2)); + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), + upper_32_bits(ring->wptr << 2)); + } } else { DRM_DEBUG("Not using doorbell -- " "mmSDMA%i_GFX_RB_WPTR == 0x%08x " diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h index 2357ff39323f..e74e1983da53 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15d.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h @@ -76,6 +76,12 @@ ((cond & 0xF) << 24) | \ ((type & 0xF) << 28))

+#define CP_PACKETJ_NOP 0x60000000 +#define CP_PACKETJ_GET_REG(x) ((x) & 0x3FFFF) +#define CP_PACKETJ_GET_RES(x) (((x) >> 18) & 0x3F) +#define CP_PACKETJ_GET_COND(x) (((x) >> 24) & 0xF) +#define CP_PACKETJ_GET_TYPE(x) (((x) >> 28) & 0xF) + /* Packet 3 types */ #define PACKET3_NOP 0x10 #define PACKET3_SET_BASE 0x11 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 836bf9ba620d..8d4ad15b8e17 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2724,6 +2724,9 @@ static int dm_suspend(void *handle)

hpd_rx_irq_work_suspend(dm);

+ if (adev->dm.dc->caps.ips_support) + dc_allow_idle_optimizations(adev->dm.dc, true); + dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3); dc_dmub_srv_set_power_state(dm->dc->ctx->dmub_srv, DC_ACPI_CM_POWER_STATE_D3);

@@ -6559,12 +6562,34 @@ static const struct attribute_group amdgpu_group = { .attrs = amdgpu_attrs };

+static bool +amdgpu_dm_should_create_sysfs(struct amdgpu_dm_connector *amdgpu_dm_connector) +{ + if (amdgpu_dm_abm_level >= 0) + return false; + + if (amdgpu_dm_connector->base.connector_type != DRM_MODE_CONNECTOR_eDP) + return false; + + /* check for OLED panels */ + if (amdgpu_dm_connector->bl_idx >= 0) { + struct drm_device *drm = amdgpu_dm_connector->base.dev; + struct amdgpu_display_manager *dm = &drm_to_adev(drm)->dm; + struct amdgpu_dm_backlight_caps *caps; + + caps = &dm->backlight_caps[amdgpu_dm_connector->bl_idx]; + if (caps->aux_support) + return false; + } + + return true; +} + static void amdgpu_dm_connector_unregister(struct drm_connector *connector) { struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector);

- if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && - amdgpu_dm_abm_level < 0) + if (amdgpu_dm_should_create_sysfs(amdgpu_dm_connector)) sysfs_remove_group(&connector->kdev->kobj, &amdgpu_group);

drm_dp_aux_unregister(&amdgpu_dm_connector->dm_dp_aux.aux); @@ -6671,8 +6696,7 @@ amdgpu_dm_connector_late_register(struct drm_connector *connector) to_amdgpu_dm_connector(connector); int r;

- if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && - amdgpu_dm_abm_level < 0) { + if (amdgpu_dm_should_create_sysfs(amdgpu_dm_connector)) { r = sysfs_create_group(&connector->kdev->kobj, &amdgpu_group); if (r) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 3306684e805a..872f994dd356 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -3605,7 +3605,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = temp_x + viewport_width; + pos_cpy.x = 2 * viewport_width - temp_x; } } } else { @@ -3698,7 +3698,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = 2 * viewport_width - temp_x; + pos_cpy.x = temp_x + viewport_width; } } } else { diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index 9a3cc0514a36..8e0588b1cf30 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -1778,6 +1778,9 @@ static bool dcn321_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1;

+ /* Use pipe context based otg sync logic */ + dc->config.use_pipe_ctx_sync_logic = true; + dc->config.dc_mode_clk_limit_support = true; dc->config.enable_windowed_mpo_odm = true; /* read VBIOS LTTPR caps */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c index 92b03073acdd..555428606e12 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -39,7 +39,9 @@ static u32 transcoder_to_stream_enc_status(enum transcoder cpu_transcoder) static void intel_dp_hdcp_wait_for_cp_irq(struct intel_connector *connector, int timeout) { - struct intel_hdcp *hdcp = &connector->hdcp; + struct intel_digital_port *dig_port = intel_attached_dig_port(connector); + struct intel_dp *dp = &dig_port->dp; + struct intel_hdcp *hdcp = &dp->attached_connector->hdcp; long ret;

#define C (hdcp->cp_irq_count_cached != atomic_read(&hdcp->cp_irq_count)) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 697ad4a64051..a6c5e3bc9bf1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -1179,8 +1179,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,

cstate->num_mixers = num_lm;

- dpu_enc->connector = conn_state->connector; - for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];

@@ -1277,6 +1275,8 @@ static void dpu_encoder_virt_atomic_enable(struct drm_encoder *drm_enc,

dpu_enc->commit_done_timedout = false;

+ dpu_enc->connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;

dpu_enc->wide_bus_en = dpu_encoder_is_widebus_enabled(drm_enc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 9b72977feafa..e61b5681f3bb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -308,8 +308,8 @@ static const u32 wb2_formats_rgb_yuv[] = { { \ .maxdwnscale = SSPP_UNITY_SCALE, \ .maxupscale = SSPP_UNITY_SCALE, \ - .format_list = plane_formats_yuv, \ - .num_formats = ARRAY_SIZE(plane_formats_yuv), \ + .format_list = plane_formats, \ + .num_formats = ARRAY_SIZE(plane_formats), \ .virt_format_list = plane_formats, \ .virt_num_formats = ARRAY_SIZE(plane_formats), \ } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index e2adc937ea63..935ff6fd172c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -31,24 +31,14 @@ * @fmt: Pointer to format string */ #define DPU_DEBUG(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_KMS)) \ - DRM_DEBUG(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)

/** * DPU_DEBUG_DRIVER - macro for hardware driver logging * @fmt: Pointer to format string */ #define DPU_DEBUG_DRIVER(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_DRIVER)) \ - DRM_ERROR(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)

#define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__) #define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 1c3a2657450c..c31d283d1c6c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -680,6 +680,9 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane, new_state->fb, &layout); if (ret) { DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret); + if (pstate->aspace) + msm_framebuffer_cleanup(new_state->fb, pstate->aspace, + pstate->needs_dirtyfb); return ret; }

@@ -743,10 +746,9 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1;

if (MSM_FORMAT_IS_YUV(fmt) && - (!pipe->sspp->cap->sblk->scaler_blk.len || - !pipe->sspp->cap->sblk->csc_blk.len)) { + !pipe->sspp->cap->sblk->csc_blk.len) { DPU_DEBUG_PLANE(pdpu, - "plane doesn't have scaler/csc for yuv\n"); + "plane doesn't have csc for yuv\n"); return -EINVAL; }

@@ -863,6 +865,10 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,

max_linewidth = pdpu->catalog->caps->max_linewidth;

+ drm_rect_rotate(&pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) || _dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) { /* @@ -912,6 +918,14 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; }

+ drm_rect_rotate_inv(&pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + if (r_pipe->sspp) + drm_rect_rotate_inv(&r_pipe_cfg->src_rect, + new_plane_state->fb->width, new_plane_state->fb->height, + new_plane_state->rotation); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, &crtc_state->adjusted_mode); if (ret) return ret; diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 7bc8a9f0657a..f342fc5ae41e 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1286,6 +1286,8 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, link_info.rate = ctrl->link->link_params.rate; link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING;

+ dp_link_reset_phy_params_vx_px(ctrl->link); + dp_aux_link_configure(ctrl->aux, &link_info);

if (drm_dp_max_downspread(dpcd)) diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 07db8f37cd06..017fb8cc8ab6 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -90,22 +90,22 @@ static int dp_panel_read_dpcd(struct dp_panel *dp_panel) static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel, u32 mode_edid_bpp, u32 mode_pclk_khz) { - struct dp_link_info *link_info; + const struct dp_link_info *link_info; const u32 max_supported_bpp = 30, min_supported_bpp = 18; - u32 bpp = 0, data_rate_khz = 0; + u32 bpp, data_rate_khz;

- bpp = min_t(u32, mode_edid_bpp, max_supported_bpp); + bpp = min(mode_edid_bpp, max_supported_bpp);

link_info = &dp_panel->link_info; data_rate_khz = link_info->num_lanes * link_info->rate * 8;

- while (bpp > min_supported_bpp) { + do { if (mode_pclk_khz * bpp <= data_rate_khz) - break; + return bpp; bpp -= 6; - } + } while (bpp > min_supported_bpp);

- return bpp; + return min_supported_bpp; }

static int dp_panel_update_modes(struct drm_connector *connector, @@ -442,8 +442,9 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel) drm_mode->clock); drm_dbg_dp(panel->drm_dev, "bpp = %d\n", dp_panel->dp_mode.bpp);

- dp_panel->dp_mode.bpp = max_t(u32, 18, - min_t(u32, dp_panel->dp_mode.bpp, 30)); + dp_panel->dp_mode.bpp = dp_panel_get_mode_bpp(dp_panel, dp_panel->dp_mode.bpp, + dp_panel->dp_mode.drm_mode.clock); + drm_dbg_dp(panel->drm_dev, "updated bpp = %d\n", dp_panel->dp_mode.bpp);

diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index fab6ad4e5107..ec7527417802 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -577,7 +577,7 @@ static const struct msm_mdss_data sc7180_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, .ubwc_static = 0x1e, - .highest_bank_bit = 0x3, + .highest_bank_bit = 0x1, .reg_bus_bw = 76800, };

diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c index adc60b25f8e6..0af01a0ec601 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c @@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw) break; case NVKM_FIRMWARE_IMG_DMA: nvkm_memory_unref(&memory); - dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys); + dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), + fw->img, fw->phys, DMA_TO_DEVICE); break; case NVKM_FIRMWARE_IMG_SGT: nvkm_memory_unref(&memory); @@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name, break; case NVKM_FIRMWARE_IMG_DMA: { dma_addr_t addr; - len = ALIGN(fw->len, PAGE_SIZE);

- fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL); + fw->img = dma_alloc_noncoherent(fw->device->dev, + len, &addr, + DMA_TO_DEVICE, + GFP_KERNEL); if (fw->img) { memcpy(fw->img, src, fw->len); fw->phys = addr; diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c index 80a480b12174..a1c8545f1249 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c @@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, nvkm_falcon_fw_dtor_sigs(fw); }

+ /* after last write to the img, sync dma mappings */ + dma_sync_single_for_device(fw->fw.device->dev, + fw->fw.phys, + sg_dma_len(&fw->fw.mem.sgl), + DMA_TO_DEVICE); + FLCNFW_DBG(fw, "resetting"); fw->func->reset(fw);

diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 30d5366d6288..0132403b8159 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -315,7 +315,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) struct v3d_dev *v3d = job->base.v3d; struct drm_device *dev = &v3d->drm; struct dma_fence *fence; - int i, csd_cfg0_reg, csd_cfg_reg_count; + int i, csd_cfg0_reg;

v3d->csd_job = job;

@@ -335,9 +335,17 @@ v3d_csd_job_run(struct drm_sched_job *sched_job) v3d_switch_perfmon(v3d, &job->base);

csd_cfg0_reg = V3D_CSD_QUEUED_CFG0(v3d->ver); - csd_cfg_reg_count = v3d->ver < 71 ? 6 : 7; - for (i = 1; i <= csd_cfg_reg_count; i++) + for (i = 1; i <= 6; i++) V3D_CORE_WRITE(0, csd_cfg0_reg + 4 * i, job->args.cfg[i]); + + /* Although V3D 7.1 has an eighth configuration register, we are not + * using it. Therefore, make sure it remains unused. + * + * XXX: Set the CFG7 register + */ + if (v3d->ver >= 71) + V3D_CORE_WRITE(0, V3D_V7_CSD_QUEUED_CFG7, 0); + /* CFG0 write kicks off the job. */ V3D_CORE_WRITE(0, csd_cfg0_reg, job->args.cfg[0]);

diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 0de0566e5b39..7cdc03dc40ed 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -134,7 +134,7 @@ static void xe_display_fini_noirq(struct drm_device *dev, void *dummy) return;

intel_display_driver_remove_noirq(xe); - intel_power_domains_driver_remove(xe); + intel_opregion_cleanup(xe); }

int xe_display_init_noirq(struct xe_device *xe) @@ -160,8 +160,10 @@ int xe_display_init_noirq(struct xe_device *xe) intel_display_device_info_runtime_init(xe);

err = intel_display_driver_probe_noirq(xe); - if (err) + if (err) { + intel_opregion_cleanup(xe); return err; + }

return drmm_add_action_or_reset(&xe->drm, xe_display_fini_noirq, NULL); } diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 5ef9b50a20d0..a1cbdafbff75 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -551,7 +551,9 @@ int xe_device_probe(struct xe_device *xe) if (err) return err;

- xe_mmio_probe_tiles(xe); + err = xe_mmio_probe_tiles(xe); + if (err) + return err;

xe_ttm_sys_mgr_init(xe);

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 395de93579fa..2ae4420e2935 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -96,17 +96,11 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe, } }

- if (xe_exec_queue_is_parallel(q)) { - q->parallel.composite_fence_ctx = dma_fence_context_alloc(1); - q->parallel.composite_fence_seqno = XE_FENCE_INITIAL_SEQNO; - } - return q; }

static int __xe_exec_queue_init(struct xe_exec_queue *q) { - struct xe_device *xe = gt_to_xe(q->gt); int i, err;

for (i = 0; i < q->width; ++i) { @@ -119,17 +113,6 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q) if (err) goto err_lrc;

- /* - * Normally the user vm holds an rpm ref to keep the device - * awake, and the context holds a ref for the vm, however for - * some engines we use the kernels migrate vm underneath which offers no - * such rpm ref, or we lack a vm. Make sure we keep a ref here, so we - * can perform GuC CT actions when needed. Caller is expected to have - * already grabbed the rpm ref outside any sensitive locks. - */ - if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm)) - xe_pm_runtime_get_noresume(xe); - return 0;

err_lrc: @@ -216,8 +199,6 @@ void xe_exec_queue_fini(struct xe_exec_queue *q)

for (i = 0; i < q->width; ++i) xe_lrc_finish(q->lrc + i); - if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm)) - xe_pm_runtime_put(gt_to_xe(q->gt)); __xe_exec_queue_free(q); }

diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index ee78d497d838..f0c40e8ad80a 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -103,16 +103,6 @@ struct xe_exec_queue { struct xe_guc_exec_queue *guc; };

- /** - * @parallel: parallel submission state - */ - struct { - /** @parallel.composite_fence_ctx: context composite fence */ - u64 composite_fence_ctx; - /** @parallel.composite_fence_seqno: seqno for composite fence */ - u32 composite_fence_seqno; - } parallel; - /** @sched_props: scheduling properties */ struct { /** @sched_props.timeslice_us: timeslice period in micro-seconds */ diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index fa9e9853c53b..67e8efcaa93f 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -402,6 +402,18 @@ static void pf_queue_work_func(struct work_struct *w)

static void acc_queue_work_func(struct work_struct *w);

+static void pagefault_fini(void *arg) +{ + struct xe_gt *gt = arg; + struct xe_device *xe = gt_to_xe(gt); + + if (!xe->info.has_usm) + return; + + destroy_workqueue(gt->usm.acc_wq); + destroy_workqueue(gt->usm.pf_wq); +} + int xe_gt_pagefault_init(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); @@ -429,10 +441,12 @@ int xe_gt_pagefault_init(struct xe_gt *gt) gt->usm.acc_wq = alloc_workqueue("xe_gt_access_counter_work_queue", WQ_UNBOUND | WQ_HIGHPRI, NUM_ACC_QUEUE); - if (!gt->usm.acc_wq) + if (!gt->usm.acc_wq) { + destroy_workqueue(gt->usm.pf_wq); return -ENOMEM; + }

- return 0; + return devm_add_action_or_reset(xe->drm.dev, pagefault_fini, gt); }

void xe_gt_pagefault_reset(struct xe_gt *gt) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 0f42971ff0a8..e48285c81bf5 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -35,6 +35,7 @@ #include "xe_macros.h" #include "xe_map.h" #include "xe_mocs.h" +#include "xe_pm.h" #include "xe_ring_ops_types.h" #include "xe_sched_job.h" #include "xe_trace.h" @@ -916,8 +917,9 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) return DRM_GPU_SCHED_STAT_NOMINAL; }

- drm_notice(&xe->drm, "Timedout job: seqno=%u, guc_id=%d, flags=0x%lx", - xe_sched_job_seqno(job), q->guc->id, q->flags); + drm_notice(&xe->drm, "Timedout job: seqno=%u, lrc_seqno=%u, guc_id=%d, flags=0x%lx", + xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job), + q->guc->id, q->flags); xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_KERNEL, "Kernel-submitted job timed out\n"); xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q), @@ -1011,6 +1013,7 @@ static void __guc_exec_queue_fini_async(struct work_struct *w) struct xe_exec_queue *q = ge->q; struct xe_guc *guc = exec_queue_to_guc(q);

+ xe_pm_runtime_get(guc_to_xe(guc)); trace_xe_exec_queue_destroy(q);

if (xe_exec_queue_is_lr(q)) @@ -1021,6 +1024,7 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)

kfree(ge); xe_exec_queue_fini(q); + xe_pm_runtime_put(guc_to_xe(guc)); }

static void guc_exec_queue_fini_async(struct xe_exec_queue *q) diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c index f872ef103127..35c0063a831a 100644 --- a/drivers/gpu/drm/xe/xe_hw_fence.c +++ b/drivers/gpu/drm/xe/xe_hw_fence.c @@ -208,23 +208,58 @@ static struct xe_hw_fence *to_xe_hw_fence(struct dma_fence *fence) return container_of(fence, struct xe_hw_fence, dma); }

-struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx, - struct iosys_map seqno_map) +/** + * xe_hw_fence_alloc() - Allocate an hw fence. + * + * Allocate but don't initialize an hw fence. + * + * Return: Pointer to the allocated fence or + * negative error pointer on error. + */ +struct dma_fence *xe_hw_fence_alloc(void) { - struct xe_hw_fence *fence; + struct xe_hw_fence *hw_fence = fence_alloc();

- fence = fence_alloc(); - if (!fence) + if (!hw_fence) return ERR_PTR(-ENOMEM);

- fence->ctx = ctx; - fence->seqno_map = seqno_map; - INIT_LIST_HEAD(&fence->irq_link); + return &hw_fence->dma; +}

- dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock, - ctx->dma_fence_ctx, ctx->next_seqno++); +/** + * xe_hw_fence_free() - Free an hw fence. + * @fence: Pointer to the fence to free. + * + * Frees an hw fence that hasn't yet been + * initialized. + */ +void xe_hw_fence_free(struct dma_fence *fence) +{ + fence_free(&fence->rcu); +}

- trace_xe_hw_fence_create(fence); +/** + * xe_hw_fence_init() - Initialize an hw fence. + * @fence: Pointer to the fence to initialize. + * @ctx: Pointer to the struct xe_hw_fence_ctx fence context. + * @seqno_map: Pointer to the map into where the seqno is blitted. + * + * Initializes a pre-allocated hw fence. + * After initialization, the fence is subject to normal + * dma-fence refcounting. + */ +void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx, + struct iosys_map seqno_map) +{ + struct xe_hw_fence *hw_fence = + container_of(fence, typeof(*hw_fence), dma); + + hw_fence->ctx = ctx; + hw_fence->seqno_map = seqno_map; + INIT_LIST_HEAD(&hw_fence->irq_link); + + dma_fence_init(fence, &xe_hw_fence_ops, &ctx->irq->lock, + ctx->dma_fence_ctx, ctx->next_seqno++);

- return fence; + trace_xe_hw_fence_create(hw_fence); } diff --git a/drivers/gpu/drm/xe/xe_hw_fence.h b/drivers/gpu/drm/xe/xe_hw_fence.h index cfe5fd603787..f13a1c4982c7 100644 --- a/drivers/gpu/drm/xe/xe_hw_fence.h +++ b/drivers/gpu/drm/xe/xe_hw_fence.h @@ -24,7 +24,10 @@ void xe_hw_fence_ctx_init(struct xe_hw_fence_ctx *ctx, struct xe_gt *gt, struct xe_hw_fence_irq *irq, const char *name); void xe_hw_fence_ctx_finish(struct xe_hw_fence_ctx *ctx);

-struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx, - struct iosys_map seqno_map); +struct dma_fence *xe_hw_fence_alloc(void);

+void xe_hw_fence_free(struct dma_fence *fence); + +void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx, + struct iosys_map seqno_map); #endif diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index d7bf7bc9dc14..995f47eb365c 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -901,10 +901,54 @@ u32 xe_lrc_seqno_ggtt_addr(struct xe_lrc *lrc) return __xe_lrc_seqno_ggtt_addr(lrc); }

+/** + * xe_lrc_alloc_seqno_fence() - Allocate an lrc seqno fence. + * + * Allocate but don't initialize an lrc seqno fence. + * + * Return: Pointer to the allocated fence or + * negative error pointer on error. + */ +struct dma_fence *xe_lrc_alloc_seqno_fence(void) +{ + return xe_hw_fence_alloc(); +} + +/** + * xe_lrc_free_seqno_fence() - Free an lrc seqno fence. + * @fence: Pointer to the fence to free. + * + * Frees an lrc seqno fence that hasn't yet been + * initialized. + */ +void xe_lrc_free_seqno_fence(struct dma_fence *fence) +{ + xe_hw_fence_free(fence); +} + +/** + * xe_lrc_init_seqno_fence() - Initialize an lrc seqno fence. + * @lrc: Pointer to the lrc. + * @fence: Pointer to the fence to initialize. + * + * Initializes a pre-allocated lrc seqno fence. + * After initialization, the fence is subject to normal + * dma-fence refcounting. + */ +void xe_lrc_init_seqno_fence(struct xe_lrc *lrc, struct dma_fence *fence) +{ + xe_hw_fence_init(fence, &lrc->fence_ctx, __xe_lrc_seqno_map(lrc)); +} + struct dma_fence *xe_lrc_create_seqno_fence(struct xe_lrc *lrc) { - return &xe_hw_fence_create(&lrc->fence_ctx, - __xe_lrc_seqno_map(lrc))->dma; + struct dma_fence *fence = xe_lrc_alloc_seqno_fence(); + + if (IS_ERR(fence)) + return fence; + + xe_lrc_init_seqno_fence(lrc, fence); + return fence; }

s32 xe_lrc_seqno(struct xe_lrc *lrc) diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h index d32fa31faa2c..f57c5836dab8 100644 --- a/drivers/gpu/drm/xe/xe_lrc.h +++ b/drivers/gpu/drm/xe/xe_lrc.h @@ -38,6 +38,9 @@ void xe_lrc_write_ctx_reg(struct xe_lrc *lrc, int reg_nr, u32 val); u64 xe_lrc_descriptor(struct xe_lrc *lrc);

u32 xe_lrc_seqno_ggtt_addr(struct xe_lrc *lrc); +struct dma_fence *xe_lrc_alloc_seqno_fence(void); +void xe_lrc_free_seqno_fence(struct dma_fence *fence); +void xe_lrc_init_seqno_fence(struct xe_lrc *lrc, struct dma_fence *fence); struct dma_fence *xe_lrc_create_seqno_fence(struct xe_lrc *lrc); s32 xe_lrc_seqno(struct xe_lrc *lrc);

diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index 334637511e75..beb4e276ba84 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -254,6 +254,21 @@ static int xe_mmio_tile_vram_size(struct xe_tile *tile, u64 *vram_size, return xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); }

+static void vram_fini(void *arg) +{ + struct xe_device *xe = arg; + struct xe_tile *tile; + int id; + + if (xe->mem.vram.mapping) + iounmap(xe->mem.vram.mapping); + + xe->mem.vram.mapping = NULL; + + for_each_tile(tile, xe, id) + tile->mem.vram.mapping = NULL; +} + int xe_mmio_probe_vram(struct xe_device *xe) { struct xe_tile *tile; @@ -330,10 +345,21 @@ int xe_mmio_probe_vram(struct xe_device *xe) drm_info(&xe->drm, "Available VRAM: %pa, %pa\n", &xe->mem.vram.io_start, &available_size);

- return 0; + return devm_add_action_or_reset(xe->drm.dev, vram_fini, xe); }

-void xe_mmio_probe_tiles(struct xe_device *xe) +static void tiles_fini(void *arg) +{ + struct xe_device *xe = arg; + struct xe_tile *tile; + int id; + + for_each_tile(tile, xe, id) + if (tile != xe_device_get_root_tile(xe)) + tile->mmio.regs = NULL; +} + +int xe_mmio_probe_tiles(struct xe_device *xe) { size_t tile_mmio_size = SZ_16M, tile_mmio_ext_size = xe->info.tile_mmio_ext_size; u8 id, tile_count = xe->info.tile_count; @@ -384,15 +410,18 @@ void xe_mmio_probe_tiles(struct xe_device *xe) regs += tile_mmio_ext_size; } } + + return devm_add_action_or_reset(xe->drm.dev, tiles_fini, xe); }

-static void mmio_fini(struct drm_device *drm, void *arg) +static void mmio_fini(void *arg) { struct xe_device *xe = arg; + struct xe_tile *root_tile = xe_device_get_root_tile(xe);

pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs); - if (xe->mem.vram.mapping) - iounmap(xe->mem.vram.mapping); + xe->mmio.regs = NULL; + root_tile->mmio.regs = NULL; }

int xe_mmio_init(struct xe_device *xe) @@ -417,7 +446,7 @@ int xe_mmio_init(struct xe_device *xe) root_tile->mmio.size = SZ_16M; root_tile->mmio.regs = xe->mmio.regs;

- return drmm_add_action_or_reset(&xe->drm, mmio_fini, xe); + return devm_add_action_or_reset(xe->drm.dev, mmio_fini, xe); }

u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg) diff --git a/drivers/gpu/drm/xe/xe_mmio.h b/drivers/gpu/drm/xe/xe_mmio.h index a3cd7b3036c7..a929d090bb2f 100644 --- a/drivers/gpu/drm/xe/xe_mmio.h +++ b/drivers/gpu/drm/xe/xe_mmio.h @@ -21,7 +21,7 @@ struct xe_device; #define LMEM_BAR 2

int xe_mmio_init(struct xe_device *xe); -void xe_mmio_probe_tiles(struct xe_device *xe); +int xe_mmio_probe_tiles(struct xe_device *xe);

u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg); u16 xe_mmio_read16(struct xe_gt *gt, struct xe_reg reg); diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index aca7a9af6e84..c59c4373aefa 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -380,7 +380,7 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,

dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */

- i = emit_bb_start(job->batch_addr[0], BIT(8), dw, i); + i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i);

if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) { /* XXX: Do we need this? Leaving for now. */ @@ -389,7 +389,7 @@ static void emit_migration_job_gen12(struct xe_sched_job *job, dw[i++] = preparser_disable(false); }

- i = emit_bb_start(job->batch_addr[1], BIT(8), dw, i); + i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i);

dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | job->migrate_flush_flags | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW; @@ -411,8 +411,8 @@ static void emit_job_gen12_gsc(struct xe_sched_job *job) xe_gt_assert(gt, job->q->width <= 1); /* no parallel submission for GSCCS */

__emit_job_gen12_simple(job, job->q->lrc, - job->batch_addr[0], - xe_sched_job_seqno(job)); + job->ptrs[0].batch_addr, + xe_sched_job_lrc_seqno(job)); }

static void emit_job_gen12_copy(struct xe_sched_job *job) @@ -421,14 +421,14 @@ static void emit_job_gen12_copy(struct xe_sched_job *job)

if (xe_sched_job_is_migration(job->q)) { emit_migration_job_gen12(job, job->q->lrc, - xe_sched_job_seqno(job)); + xe_sched_job_lrc_seqno(job)); return; }

for (i = 0; i < job->q->width; ++i) __emit_job_gen12_simple(job, job->q->lrc + i, - job->batch_addr[i], - xe_sched_job_seqno(job)); + job->ptrs[i].batch_addr, + xe_sched_job_lrc_seqno(job)); }

static void emit_job_gen12_video(struct xe_sched_job *job) @@ -438,8 +438,8 @@ static void emit_job_gen12_video(struct xe_sched_job *job) /* FIXME: Not doing parallel handshake for now */ for (i = 0; i < job->q->width; ++i) __emit_job_gen12_video(job, job->q->lrc + i, - job->batch_addr[i], - xe_sched_job_seqno(job)); + job->ptrs[i].batch_addr, + xe_sched_job_lrc_seqno(job)); }

static void emit_job_gen12_render_compute(struct xe_sched_job *job) @@ -448,8 +448,8 @@ static void emit_job_gen12_render_compute(struct xe_sched_job *job)

for (i = 0; i < job->q->width; ++i) __emit_job_gen12_render_compute(job, job->q->lrc + i, - job->batch_addr[i], - xe_sched_job_seqno(job)); + job->ptrs[i].batch_addr, + xe_sched_job_lrc_seqno(job)); }

static const struct xe_ring_ops ring_ops_gen12_gsc = { diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c index cd8a2fba5438..2b064680abb9 100644 --- a/drivers/gpu/drm/xe/xe_sched_job.c +++ b/drivers/gpu/drm/xe/xe_sched_job.c @@ -6,7 +6,7 @@ #include "xe_sched_job.h"

#include <drm/xe_drm.h> -#include <linux/dma-fence-array.h> +#include <linux/dma-fence-chain.h> #include <linux/slab.h>

#include "xe_device.h" @@ -29,7 +29,7 @@ int __init xe_sched_job_module_init(void) xe_sched_job_slab = kmem_cache_create("xe_sched_job", sizeof(struct xe_sched_job) + - sizeof(u64), 0, + sizeof(struct xe_job_ptrs), 0, SLAB_HWCACHE_ALIGN, NULL); if (!xe_sched_job_slab) return -ENOMEM; @@ -37,7 +37,7 @@ int __init xe_sched_job_module_init(void) xe_sched_job_parallel_slab = kmem_cache_create("xe_sched_job_parallel", sizeof(struct xe_sched_job) + - sizeof(u64) * + sizeof(struct xe_job_ptrs) * XE_HW_ENGINE_MAX_INSTANCE, 0, SLAB_HWCACHE_ALIGN, NULL); if (!xe_sched_job_parallel_slab) { @@ -79,26 +79,33 @@ static struct xe_device *job_to_xe(struct xe_sched_job *job) return gt_to_xe(job->q->gt); }

+/* Free unused pre-allocated fences */ +static void xe_sched_job_free_fences(struct xe_sched_job *job) +{ + int i; + + for (i = 0; i < job->q->width; ++i) { + struct xe_job_ptrs *ptrs = &job->ptrs[i]; + + if (ptrs->lrc_fence) + xe_lrc_free_seqno_fence(ptrs->lrc_fence); + if (ptrs->chain_fence) + dma_fence_chain_free(ptrs->chain_fence); + } +} + struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q, u64 *batch_addr) { - struct xe_sched_job *job; - struct dma_fence **fences; bool is_migration = xe_sched_job_is_migration(q); + struct xe_sched_job *job; int err; - int i, j; + int i; u32 width;

/* only a kernel context can submit a vm-less job */ XE_WARN_ON(!q->vm && !(q->flags & EXEC_QUEUE_FLAG_KERNEL));

- /* Migration and kernel engines have their own locking */ - if (!(q->flags & (EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_VM))) { - lockdep_assert_held(&q->vm->lock); - if (!xe_vm_in_lr_mode(q->vm)) - xe_vm_assert_held(q->vm); - } - job = job_alloc(xe_exec_queue_is_parallel(q) || is_migration); if (!job) return ERR_PTR(-ENOMEM); @@ -111,44 +118,25 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q, if (err) goto err_free;

- if (!xe_exec_queue_is_parallel(q)) { - job->fence = xe_lrc_create_seqno_fence(q->lrc); - if (IS_ERR(job->fence)) { - err = PTR_ERR(job->fence); - goto err_sched_job; - } - } else { - struct dma_fence_array *cf; + for (i = 0; i < q->width; ++i) { + struct dma_fence *fence = xe_lrc_alloc_seqno_fence(); + struct dma_fence_chain *chain;

- fences = kmalloc_array(q->width, sizeof(*fences), GFP_KERNEL); - if (!fences) { - err = -ENOMEM; + if (IS_ERR(fence)) { + err = PTR_ERR(fence); goto err_sched_job; } + job->ptrs[i].lrc_fence = fence;

- for (j = 0; j < q->width; ++j) { - fences[j] = xe_lrc_create_seqno_fence(q->lrc + j); - if (IS_ERR(fences[j])) { - err = PTR_ERR(fences[j]); - goto err_fences; - } - } + if (i + 1 == q->width) + continue;

- cf = dma_fence_array_create(q->width, fences, - q->parallel.composite_fence_ctx, - q->parallel.composite_fence_seqno++, - false); - if (!cf) { - --q->parallel.composite_fence_seqno; + chain = dma_fence_chain_alloc(); + if (!chain) { err = -ENOMEM; - goto err_fences; + goto err_sched_job; } - - /* Sanity check */ - for (j = 0; j < q->width; ++j) - xe_assert(job_to_xe(job), cf->base.seqno == fences[j]->seqno); - - job->fence = &cf->base; + job->ptrs[i].chain_fence = chain; }

width = q->width; @@ -156,23 +144,14 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q, width = 2;

for (i = 0; i < width; ++i) - job->batch_addr[i] = batch_addr[i]; - - /* All other jobs require a VM to be open which has a ref */ - if (unlikely(q->flags & EXEC_QUEUE_FLAG_KERNEL)) - xe_pm_runtime_get_noresume(job_to_xe(job)); - xe_device_assert_mem_access(job_to_xe(job)); + job->ptrs[i].batch_addr = batch_addr[i];

+ xe_pm_runtime_get_noresume(job_to_xe(job)); trace_xe_sched_job_create(job); return job;

-err_fences: - for (j = j - 1; j >= 0; --j) { - --q->lrc[j].fence_ctx.next_seqno; - dma_fence_put(fences[j]); - } - kfree(fences); err_sched_job: + xe_sched_job_free_fences(job); drm_sched_job_cleanup(&job->drm); err_free: xe_exec_queue_put(q); @@ -191,36 +170,43 @@ void xe_sched_job_destroy(struct kref *ref) { struct xe_sched_job *job = container_of(ref, struct xe_sched_job, refcount); + struct xe_device *xe = job_to_xe(job); + struct xe_exec_queue *q = job->q;

- if (unlikely(job->q->flags & EXEC_QUEUE_FLAG_KERNEL)) - xe_pm_runtime_put(job_to_xe(job)); - xe_exec_queue_put(job->q); + xe_sched_job_free_fences(job); dma_fence_put(job->fence); drm_sched_job_cleanup(&job->drm); job_free(job); + xe_exec_queue_put(q); + xe_pm_runtime_put(xe); }

-void xe_sched_job_set_error(struct xe_sched_job *job, int error) +/* Set the error status under the fence to avoid racing with signaling */ +static bool xe_fence_set_error(struct dma_fence *fence, int error) { - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags)) - return; + unsigned long irq_flags; + bool signaled;

- dma_fence_set_error(job->fence, error); + spin_lock_irqsave(fence->lock, irq_flags); + signaled = test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags); + if (!signaled) + dma_fence_set_error(fence, error); + spin_unlock_irqrestore(fence->lock, irq_flags);

- if (dma_fence_is_array(job->fence)) { - struct dma_fence_array *array = - to_dma_fence_array(job->fence); - struct dma_fence **child = array->fences; - unsigned int nchild = array->num_fences; + return signaled; +} + +void xe_sched_job_set_error(struct xe_sched_job *job, int error) +{ + if (xe_fence_set_error(job->fence, error)) + return;

- do { - struct dma_fence *current_fence = *child++; + if (dma_fence_is_chain(job->fence)) { + struct dma_fence *iter;

- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, - &current_fence->flags)) - continue; - dma_fence_set_error(current_fence, error); - } while (--nchild); + dma_fence_chain_for_each(iter, job->fence) + xe_fence_set_error(dma_fence_chain_contained(iter), + error); }

trace_xe_sched_job_set_error(job); @@ -233,9 +219,9 @@ bool xe_sched_job_started(struct xe_sched_job *job) { struct xe_lrc *lrc = job->q->lrc;

- return !__dma_fence_is_later(xe_sched_job_seqno(job), + return !__dma_fence_is_later(xe_sched_job_lrc_seqno(job), xe_lrc_start_seqno(lrc), - job->fence->ops); + dma_fence_chain_contained(job->fence)->ops); }

bool xe_sched_job_completed(struct xe_sched_job *job) @@ -247,14 +233,26 @@ bool xe_sched_job_completed(struct xe_sched_job *job) * parallel handshake is done. */

- return !__dma_fence_is_later(xe_sched_job_seqno(job), xe_lrc_seqno(lrc), - job->fence->ops); + return !__dma_fence_is_later(xe_sched_job_lrc_seqno(job), + xe_lrc_seqno(lrc), + dma_fence_chain_contained(job->fence)->ops); }

void xe_sched_job_arm(struct xe_sched_job *job) { struct xe_exec_queue *q = job->q; + struct dma_fence *fence, *prev; struct xe_vm *vm = q->vm; + u64 seqno = 0; + int i; + + /* Migration and kernel engines have their own locking */ + if (IS_ENABLED(CONFIG_LOCKDEP) && + !(q->flags & (EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_VM))) { + lockdep_assert_held(&q->vm->lock); + if (!xe_vm_in_lr_mode(q->vm)) + xe_vm_assert_held(q->vm); + }

if (vm && !xe_sched_job_is_migration(q) && !xe_vm_in_lr_mode(vm) && (vm->batch_invalidate_tlb || vm->tlb_flush_seqno != q->tlb_flush_seqno)) { @@ -263,6 +261,27 @@ void xe_sched_job_arm(struct xe_sched_job *job) job->ring_ops_flush_tlb = true; }

+ /* Arm the pre-allocated fences */ + for (i = 0; i < q->width; prev = fence, ++i) { + struct dma_fence_chain *chain; + + fence = job->ptrs[i].lrc_fence; + xe_lrc_init_seqno_fence(&q->lrc[i], fence); + job->ptrs[i].lrc_fence = NULL; + if (!i) { + job->lrc_seqno = fence->seqno; + continue; + } else { + xe_assert(gt_to_xe(q->gt), job->lrc_seqno == fence->seqno); + } + + chain = job->ptrs[i - 1].chain_fence; + dma_fence_chain_init(chain, prev, fence, seqno++); + job->ptrs[i - 1].chain_fence = NULL; + fence = &chain->base; + } + + job->fence = fence; drm_sched_job_arm(&job->drm); }

@@ -322,7 +341,8 @@ xe_sched_job_snapshot_capture(struct xe_sched_job *job)

snapshot->batch_addr_len = q->width; for (i = 0; i < q->width; i++) - snapshot->batch_addr[i] = xe_device_uncanonicalize_addr(xe, job->batch_addr[i]); + snapshot->batch_addr[i] = + xe_device_uncanonicalize_addr(xe, job->ptrs[i].batch_addr);

return snapshot; } diff --git a/drivers/gpu/drm/xe/xe_sched_job.h b/drivers/gpu/drm/xe/xe_sched_job.h index c75018f4660d..f362e28455db 100644 --- a/drivers/gpu/drm/xe/xe_sched_job.h +++ b/drivers/gpu/drm/xe/xe_sched_job.h @@ -70,7 +70,12 @@ to_xe_sched_job(struct drm_sched_job *drm)

static inline u32 xe_sched_job_seqno(struct xe_sched_job *job) { - return job->fence->seqno; + return job->fence ? job->fence->seqno : 0; +} + +static inline u32 xe_sched_job_lrc_seqno(struct xe_sched_job *job) +{ + return job->lrc_seqno; }

static inline void diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h index 5e12724219fd..0d3f76fb05ce 100644 --- a/drivers/gpu/drm/xe/xe_sched_job_types.h +++ b/drivers/gpu/drm/xe/xe_sched_job_types.h @@ -11,6 +11,20 @@ #include <drm/gpu_scheduler.h>

struct xe_exec_queue; +struct dma_fence; +struct dma_fence_chain; + +/** + * struct xe_job_ptrs - Per hw engine instance data + */ +struct xe_job_ptrs { + /** @lrc_fence: Pre-allocated uinitialized lrc fence.*/ + struct dma_fence *lrc_fence; + /** @chain_fence: Pre-allocated ninitialized fence chain node. */ + struct dma_fence_chain *chain_fence; + /** @batch_addr: Batch buffer address. */ + u64 batch_addr; +};

/** * struct xe_sched_job - XE schedule job (batch buffer tracking) @@ -37,12 +51,14 @@ struct xe_sched_job { /** @user_fence.value: write back value */ u64 value; } user_fence; + /** @lrc_seqno: LRC seqno */ + u32 lrc_seqno; /** @migrate_flush_flags: Additional flush flags for migration jobs */ u32 migrate_flush_flags; /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */ bool ring_ops_flush_tlb; - /** @batch_addr: batch buffer address of job */ - u64 batch_addr[]; + /** @ptrs: per instance pointers. */ + struct xe_job_ptrs ptrs[]; };

struct xe_sched_job_snapshot { diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h index 2d56cfc09e42..e4cba64474e6 100644 --- a/drivers/gpu/drm/xe/xe_trace.h +++ b/drivers/gpu/drm/xe/xe_trace.h @@ -254,6 +254,7 @@ DECLARE_EVENT_CLASS(xe_sched_job,

TP_STRUCT__entry( __field(u32, seqno) + __field(u32, lrc_seqno) __field(u16, guc_id) __field(u32, guc_state) __field(u32, flags) @@ -264,17 +265,19 @@ DECLARE_EVENT_CLASS(xe_sched_job,

TP_fast_assign( __entry->seqno = xe_sched_job_seqno(job); + __entry->lrc_seqno = xe_sched_job_lrc_seqno(job); __entry->guc_id = job->q->guc->id; __entry->guc_state = atomic_read(&job->q->guc->state); __entry->flags = job->q->flags; - __entry->error = job->fence->error; + __entry->error = job->fence ? job->fence->error : 0; __entry->fence = job->fence; - __entry->batch_addr = (u64)job->batch_addr[0]; + __entry->batch_addr = (u64)job->ptrs[0].batch_addr; ),

- TP_printk("fence=%p, seqno=%u, guc_id=%d, batch_addr=0x%012llx, guc_state=0x%x, flags=0x%x, error=%d", - __entry->fence, __entry->seqno, __entry->guc_id, + TP_printk("fence=%p, seqno=%u, lrc_seqno=%u, guc_id=%d, batch_addr=0x%012llx, guc_state=0x%x, flags=0x%x, error=%d", + __entry->fence, __entry->seqno, + __entry->lrc_seqno, __entry->guc_id, __entry->batch_addr, __entry->guc_state, __entry->flags, __entry->error) ); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 20de97ce0f5e..d84740be9642 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1924,12 +1924,14 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage, int fmax = field->logical_maximum; unsigned int equivalent_usage = wacom_equivalent_usage(usage->hid); int resolution_code = code; - int resolution = hidinput_calc_abs_res(field, resolution_code); + int resolution;

if (equivalent_usage == HID_DG_TWIST) { resolution_code = ABS_RZ; }

+ resolution = hidinput_calc_abs_res(field, resolution_code); + if (equivalent_usage == HID_GD_X) { fmin += features->offset_left; fmax -= features->offset_right; diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 365e37bba0f3..06e836e3e877 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -986,8 +986,10 @@ static int __maybe_unused geni_i2c_runtime_resume(struct device *dev) return ret;

ret = clk_prepare_enable(gi2c->core_clk); - if (ret) + if (ret) { + geni_icc_disable(&gi2c->se); return ret; + }

ret = geni_se_resources_on(&gi2c->se); if (ret) { diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 85b31edc558d..1df5b4204142 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -1802,9 +1802,9 @@ static int tegra_i2c_probe(struct platform_device *pdev) * domain. * * VI I2C device shouldn't be marked as IRQ-safe because VI I2C won't - * be used for atomic transfers. + * be used for atomic transfers. ACPI device is not IRQ safe also. */ - if (!IS_VI(i2c_dev)) + if (!IS_VI(i2c_dev) && !has_acpi_companion(i2c_dev->dev)) pm_runtime_irq_safe(i2c_dev->dev);

pm_runtime_enable(i2c_dev->dev); diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c index 14b53dac1253..6b04a674f832 100644 --- a/drivers/input/input-mt.c +++ b/drivers/input/input-mt.c @@ -46,6 +46,9 @@ int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots, return 0; if (mt) return mt->num_slots != num_slots ? -EINVAL : 0; + /* Arbitrary limit for avoiding too large memory allocation. */ + if (num_slots > 1024) + return -EINVAL;

mt = kzalloc(struct_size(mt, slots, num_slots), GFP_KERNEL); if (!mt) diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 5b50475ec414..e9eb9554dd7b 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -83,6 +83,7 @@ static inline void i8042_write_command(int val) #define SERIO_QUIRK_KBDRESET BIT(12) #define SERIO_QUIRK_DRITEK BIT(13) #define SERIO_QUIRK_NOPNP BIT(14) +#define SERIO_QUIRK_FORCENORESTORE BIT(15)

/* Quirk table for different mainboards. Options similar or identical to i8042 * module parameters. @@ -1149,18 +1150,10 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, { - /* - * Setting SERIO_QUIRK_NOMUX or SERIO_QUIRK_RESET_ALWAYS makes - * the keyboard very laggy for ~5 seconds after boot and - * sometimes also after resume. - * However both are required for the keyboard to not fail - * completely sometimes after boot or resume. - */ .matches = { DMI_MATCH(DMI_BOARD_NAME, "N150CU"), }, - .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | - SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + .driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE) }, { .matches = { @@ -1685,6 +1678,8 @@ static void __init i8042_check_quirks(void) if (quirks & SERIO_QUIRK_NOPNP) i8042_nopnp = true; #endif + if (quirks & SERIO_QUIRK_FORCENORESTORE) + i8042_forcenorestore = true; } #else static inline void i8042_check_quirks(void) {} @@ -1718,7 +1713,7 @@ static int __init i8042_platform_init(void)

i8042_check_quirks();

- pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s\n", + pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", i8042_nokbd ? " nokbd" : "", i8042_noaux ? " noaux" : "", i8042_nomux ? " nomux" : "", @@ -1738,10 +1733,11 @@ static int __init i8042_platform_init(void) "", #endif #ifdef CONFIG_PNP - i8042_nopnp ? " nopnp" : ""); + i8042_nopnp ? " nopnp" : "", #else - ""); + "", #endif + i8042_forcenorestore ? " forcenorestore" : "");

retval = i8042_pnp_init(); if (retval) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 9fbb8d31575a..2233d93f90e8 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -115,6 +115,10 @@ module_param_named(nopnp, i8042_nopnp, bool, 0); MODULE_PARM_DESC(nopnp, "Do not use PNP to detect controller settings"); #endif

+static bool i8042_forcenorestore; +module_param_named(forcenorestore, i8042_forcenorestore, bool, 0); +MODULE_PARM_DESC(forcenorestore, "Force no restore on s3 resume, copying s2idle behaviour"); + #define DEBUG #ifdef DEBUG static bool i8042_debug; @@ -1232,7 +1236,7 @@ static int i8042_pm_suspend(struct device *dev) { int i;

- if (pm_suspend_via_firmware()) + if (!i8042_forcenorestore && pm_suspend_via_firmware()) i8042_controller_reset(true);

/* Set up serio interrupts for system wakeup. */ @@ -1248,7 +1252,7 @@ static int i8042_pm_suspend(struct device *dev)

static int i8042_pm_resume_noirq(struct device *dev) { - if (!pm_resume_via_firmware()) + if (i8042_forcenorestore || !pm_resume_via_firmware()) i8042_interrupt(0, NULL);

return 0; @@ -1271,7 +1275,7 @@ static int i8042_pm_resume(struct device *dev) * not restore the controller state to whatever it had been at boot * time, so we do not need to do anything. */ - if (!pm_suspend_via_firmware()) + if (i8042_forcenorestore || !pm_suspend_via_firmware()) return 0;

/* diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 06d78fcc79fd..f2c87c695a17 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -192,6 +192,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) report_partial_fault(iopf_param, fault); iopf_put_dev_fault_param(iopf_param); /* A request that is not the last does not need to be ack'd */ + return; }

/* diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 873630c111c1..e333793e88eb 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -525,7 +525,7 @@ iommufd_device_do_replace(struct iommufd_device *idev, err_unresv: if (hwpt_is_paging(hwpt)) iommufd_group_remove_reserved_iova(igroup, - to_hwpt_paging(old_hwpt)); + to_hwpt_paging(hwpt)); err_unlock: mutex_unlock(&idev->igroup->lock); return ERR_PTR(rc); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index c2c07bfa6471..f299ff393a6a 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1181,8 +1181,26 @@ static int do_resume(struct dm_ioctl *param) suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG; if (param->flags & DM_NOFLUSH_FLAG) suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG; - if (!dm_suspended_md(md)) - dm_suspend(md, suspend_flags); + if (!dm_suspended_md(md)) { + r = dm_suspend(md, suspend_flags); + if (r) { + down_write(&_hash_lock); + hc = dm_get_mdptr(md); + if (hc && !hc->new_map) { + hc->new_map = new_map; + new_map = NULL; + } else { + r = -ENXIO; + } + up_write(&_hash_lock); + if (new_map) { + dm_sync_table(md); + dm_table_destroy(new_map); + } + dm_put(md); + return r; + } + }

old_size = dm_get_size(md); old_map = dm_swap_table(md, new_map); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 13037d6a6f62..6e15ac4e0845 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2594,7 +2594,7 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta break;

if (signal_pending_state(task_state, current)) { - r = -EINTR; + r = -ERESTARTSYS; break; }

@@ -2619,7 +2619,7 @@ static int dm_wait_for_completion(struct mapped_device *md, unsigned int task_st break;

if (signal_pending_state(task_state, current)) { - r = -EINTR; + r = -ERESTARTSYS; break; }

diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 04698fd03e60..d48c4fafc779 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -277,7 +277,7 @@ static void sm_metadata_destroy(struct dm_space_map *sm) { struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);

- kfree(smm); + kvfree(smm); }

static int sm_metadata_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count) @@ -772,7 +772,7 @@ struct dm_space_map *dm_sm_metadata_init(void) { struct sm_metadata *smm;

- smm = kmalloc(sizeof(*smm), GFP_KERNEL); + smm = kvmalloc(sizeof(*smm), GFP_KERNEL); if (!smm) return ERR_PTR(-ENOMEM);

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 5ea57b6748c5..687bd374cde8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -617,6 +617,12 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio, return -1; }

+static bool rdev_in_recovery(struct md_rdev *rdev, struct r1bio *r1_bio) +{ + return !test_bit(In_sync, &rdev->flags) && + rdev->recovery_offset < r1_bio->sector + r1_bio->sectors; +} + static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors) { @@ -635,6 +641,7 @@ static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,

rdev = conf->mirrors[disk].rdev; if (!rdev || test_bit(Faulty, &rdev->flags) || + rdev_in_recovery(rdev, r1_bio) || test_bit(WriteMostly, &rdev->flags)) continue;

@@ -673,7 +680,8 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,

rdev = conf->mirrors[disk].rdev; if (!rdev || test_bit(Faulty, &rdev->flags) || - !test_bit(WriteMostly, &rdev->flags)) + !test_bit(WriteMostly, &rdev->flags) || + rdev_in_recovery(rdev, r1_bio)) continue;

/* there are no bad blocks, we can use this disk */ @@ -733,9 +741,7 @@ static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio) if (!rdev || test_bit(Faulty, &rdev->flags)) return false;

- /* still in recovery */ - if (!test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < r1_bio->sector + r1_bio->sectors) + if (rdev_in_recovery(rdev, r1_bio)) return false;

/* don't read from slow disk unless have to */ diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index a7a2bcedb37e..5680856c0fb8 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -2087,16 +2087,6 @@ static int fastrpc_req_mem_map(struct fastrpc_user *fl, char __user *argp) return err; }

-static int is_attach_rejected(struct fastrpc_user *fl) -{ - /* Check if the device node is non-secure */ - if (!fl->is_secure_dev) { - dev_dbg(&fl->cctx->rpdev->dev, "untrusted app trying to attach to privileged DSP PD\n"); - return -EACCES; - } - return 0; -} - static long fastrpc_device_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -2109,19 +2099,13 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd, err = fastrpc_invoke(fl, argp); break; case FASTRPC_IOCTL_INIT_ATTACH: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_attach(fl, ROOT_PD); + err = fastrpc_init_attach(fl, ROOT_PD); break; case FASTRPC_IOCTL_INIT_ATTACH_SNS: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_attach(fl, SENSORS_PD); + err = fastrpc_init_attach(fl, SENSORS_PD); break; case FASTRPC_IOCTL_INIT_CREATE_STATIC: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_create_static_process(fl, argp); + err = fastrpc_init_create_static_process(fl, argp); break; case FASTRPC_IOCTL_INIT_CREATE: err = fastrpc_init_create_process(fl, argp); diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index 8f7f587a0025..b7f627a9fdea 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -3125,13 +3125,13 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf, test->buffer = kzalloc(BUFFER_SIZE, GFP_KERNEL); #ifdef CONFIG_HIGHMEM test->highmem = alloc_pages(GFP_KERNEL | __GFP_HIGHMEM, BUFFER_ORDER); + if (!test->highmem) { + count = -ENOMEM; + goto free_test_buffer; + } #endif

-#ifdef CONFIG_HIGHMEM - if (test->buffer && test->highmem) { -#else if (test->buffer) { -#endif mutex_lock(&mmc_test_lock); mmc_test_run(test, testcase); mutex_unlock(&mmc_test_lock); @@ -3139,6 +3139,7 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,

#ifdef CONFIG_HIGHMEM __free_pages(test->highmem, BUFFER_ORDER); +free_test_buffer: #endif kfree(test->buffer); kfree(test); diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 8e2d676b9239..a4f813ea177a 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -3293,6 +3293,10 @@ int dw_mci_probe(struct dw_mci *host) host->biu_clk = devm_clk_get(host->dev, "biu"); if (IS_ERR(host->biu_clk)) { dev_dbg(host->dev, "biu clock not available\n"); + ret = PTR_ERR(host->biu_clk); + if (ret == -EPROBE_DEFER) + return ret; + } else { ret = clk_prepare_enable(host->biu_clk); if (ret) { @@ -3304,6 +3308,10 @@ int dw_mci_probe(struct dw_mci *host) host->ciu_clk = devm_clk_get(host->dev, "ciu"); if (IS_ERR(host->ciu_clk)) { dev_dbg(host->dev, "ciu clock not available\n"); + ret = PTR_ERR(host->ciu_clk); + if (ret == -EPROBE_DEFER) + goto err_clk_biu; + host->bus_hz = host->pdata->bus_hz; } else { ret = clk_prepare_enable(host->ciu_clk); diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index a94835b8ab93..e386f78e3267 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -1230,7 +1230,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events, }

if (!sbc_error && !(events & MSDC_INT_CMDRDY)) { - if (events & MSDC_INT_CMDTMO || + if ((events & MSDC_INT_CMDTMO && !host->hs400_tuning) || (!mmc_op_tuning(cmd->opcode) && !host->hs400_tuning)) /* * should not clear fifo/interrupt as the tune data @@ -1323,9 +1323,9 @@ static void msdc_start_command(struct msdc_host *host, static void msdc_cmd_next(struct msdc_host *host, struct mmc_request *mrq, struct mmc_command *cmd) { - if ((cmd->error && - !(cmd->error == -EILSEQ && - (mmc_op_tuning(cmd->opcode) || host->hs400_tuning))) || + if ((cmd->error && !host->hs400_tuning && + !(cmd->error == -EILSEQ && + mmc_op_tuning(cmd->opcode))) || (mrq->sbc && mrq->sbc->error)) msdc_request_done(host, mrq); else if (cmd == mrq->sbc) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2ed0da068490..b257504a8534 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -582,7 +582,6 @@ static void bond_ipsec_del_sa_all(struct bonding *bond) } else { slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); } - ipsec->xs->xso.real_dev = NULL; } spin_unlock_bh(&bond->ipsec_lock); rcu_read_unlock(); @@ -599,34 +598,30 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) struct net_device *real_dev; struct slave *curr_active; struct bonding *bond; - int err; + bool ok = false;

bond = netdev_priv(bond_dev); rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); + if (!curr_active) + goto out; real_dev = curr_active->dev;

- if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { - err = false; + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) goto out; - }

- if (!xs->xso.real_dev) { - err = false; + if (!xs->xso.real_dev) goto out; - }

if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_offload_ok || - netif_is_bond_master(real_dev)) { - err = false; + netif_is_bond_master(real_dev)) goto out; - }

- err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); out: rcu_read_unlock(); - return err; + return ok; }

static const struct xfrmdev_ops bond_xfrmdev_ops = { diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index bc80fb6397dc..95d59a18c022 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -936,7 +936,7 @@ static int bond_option_active_slave_set(struct bonding *bond, /* check to see if we are clearing active */ if (!slave_dev) { netdev_dbg(bond->dev, "Clearing current active slave\n"); - RCU_INIT_POINTER(bond->curr_active_slave, NULL); + bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); } else { struct slave *old_active = rtnl_dereference(bond->curr_active_slave); diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index 1fe105913c75..beb969f391be 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -266,7 +266,6 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev) struct ksz_port *prt; struct dsa_port *dp; bool tag_en = false; - int ret;

dsa_switch_for_each_user_port(dp, dev->ds) { prt = &dev->ports[dp->index]; @@ -277,9 +276,7 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev) }

if (tag_en) { - ret = ptp_schedule_worker(ptp_data->clock, 0); - if (ret) - return ret; + ptp_schedule_worker(ptp_data->clock, 0); } else { ptp_cancel_worker_sync(ptp_data->clock); } diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index ce3b3690c3c0..c47f068f56b3 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -457,7 +457,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) trace_mv88e6xxx_atu_full_violation(chip->dev, spid, entry.portvec, entry.mac, fid); - chip->ports[spid].atu_full_violation++; + if (spid < ARRAY_SIZE(chip->ports)) + chip->ports[spid].atu_full_violation++; }

return IRQ_HANDLED; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 61e95487732d..f5d26e724ae6 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -528,7 +528,9 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) * so we need to be careful that there are no extra frames to be * dequeued over MMIO, since we would never know to discard them. */ + ocelot_lock_xtr_grp_bh(ocelot, 0); ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp_bh(ocelot, 0);

return 0; } @@ -1504,6 +1506,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) int port = xmit_work->dp->index; int retries = 10;

+ ocelot_lock_inj_grp(ocelot, 0); + do { if (ocelot_can_inject(ocelot, 0)) break; @@ -1512,6 +1516,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work) } while (--retries);

if (!retries) { + ocelot_unlock_inj_grp(ocelot, 0); dev_err(ocelot->dev, "port %d failed to inject skb\n", port); ocelot_port_purge_txtstamp_skb(ocelot, port, skb); @@ -1521,6 +1526,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)

ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);

+ ocelot_unlock_inj_grp(ocelot, 0); + consume_skb(skb); kfree(xmit_work); } @@ -1671,6 +1678,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) if (!felix->info->quirk_no_xtr_irq) return false;

+ ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; unsigned int type; @@ -1707,6 +1716,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) ocelot_drain_cpu_queue(ocelot, 0); }

+ ocelot_unlock_xtr_grp(ocelot, grp); + return true; }

diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index 4b031fefcec6..56bb77dbd28a 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -38,6 +38,10 @@ #define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */

+/* MII Block subblock */ +#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */ +#define VSC73XX_BLOCK_MII_EXTERNAL 0x1 /* External MDIO subblock */ + #define CPU_PORT 6 /* CPU port */

/* MAC Block registers */ @@ -196,6 +200,8 @@ #define VSC73XX_MII_CMD 0x1 #define VSC73XX_MII_DATA 0x2

+#define VSC73XX_MII_STAT_BUSY BIT(3) + /* Arbiter block 5 registers */ #define VSC73XX_ARBEMPTY 0x0c #define VSC73XX_ARBDISC 0x0e @@ -270,6 +276,7 @@ #define IS_739X(a) (IS_7395(a) || IS_7398(a))

#define VSC73XX_POLL_SLEEP_US 1000 +#define VSC73XX_MDIO_POLL_SLEEP_US 5 #define VSC73XX_POLL_TIMEOUT_US 10000

struct vsc73xx_counter { @@ -487,6 +494,22 @@ static int vsc73xx_detect(struct vsc73xx *vsc) return 0; }

+static int vsc73xx_mdio_busy_check(struct vsc73xx *vsc) +{ + int ret, err; + u32 val; + + ret = read_poll_timeout(vsc73xx_read, err, + err < 0 || !(val & VSC73XX_MII_STAT_BUSY), + VSC73XX_MDIO_POLL_SLEEP_US, + VSC73XX_POLL_TIMEOUT_US, false, vsc, + VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_STAT, &val); + if (ret) + return ret; + return err; +} + static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) { struct vsc73xx *vsc = ds->priv; @@ -494,12 +517,20 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) u32 val; int ret;

+ ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + /* Setting bit 26 means "read" */ cmd = BIT(26) | (phy << 21) | (regnum << 16); ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; - msleep(2); + + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val); if (ret) return ret; @@ -523,6 +554,10 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, u32 cmd; int ret;

+ ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + /* It was found through tedious experiments that this router * chip really hates to have it's PHYs reset. They * never recover if that happens: autonegotiation stops @@ -534,7 +569,7 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, return 0; }

- cmd = (phy << 21) | (regnum << 16); + cmd = (phy << 21) | (regnum << 16) | val; ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; @@ -817,6 +852,11 @@ static void vsc73xx_mac_link_up(struct phylink_config *config,

if (duplex == DUPLEX_FULL) val |= VSC73XX_MAC_CFG_FDX; + else + /* In datasheet description ("Port Mode Procedure" in 5.6.2) + * this bit is configured only for half duplex. + */ + val |= VSC73XX_MAC_CFG_WEXC_DIS;

/* This routine is described in the datasheet (below ARBDISC register * description) @@ -827,7 +867,6 @@ static void vsc73xx_mac_link_up(struct phylink_config *config, get_random_bytes(&seed, 1); val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET; val |= VSC73XX_MAC_CFG_SEED_LOAD; - val |= VSC73XX_MAC_CFG_WEXC_DIS; vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);

/* Flow control for the PHY facing ports: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 345681d5007e..f88b641533fc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -297,11 +297,6 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, * redirect is coming from a frame received by the * bnxt_en driver. */ - rx_buf = &rxr->rx_buf_ring[cons]; - mapping = rx_buf->mapping - bp->rx_dma_offset; - dma_unmap_page_attrs(&pdev->dev, mapping, - BNXT_RX_PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING);

/* if we are unable to allocate a new buffer, abort and reuse */ if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 786ceae34488..dd9e68465e69 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1244,7 +1244,8 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs, * in the Compressed Filter Tuple. */ if (tp->vlan_shift >= 0 && fs->mask.ivlan) - ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift; + ntuple |= (u64)(FT_VLAN_VLD_F | + fs->val.ivlan) << tp->vlan_shift;

if (tp->port_shift >= 0 && fs->mask.iport) ntuple |= (u64)fs->val.iport << tp->port_shift; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index a71f848adc05..a293b08f36d4 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2638,13 +2638,14 @@ static int dpaa2_switch_refill_bp(struct ethsw_core *ethsw)

static int dpaa2_switch_seed_bp(struct ethsw_core *ethsw) { - int *count, i; + int *count, ret, i;

for (i = 0; i < DPAA2_ETHSW_NUM_BUFS; i += BUFS_PER_CMD) { + ret = dpaa2_switch_add_bufs(ethsw, ethsw->bpid); count = &ethsw->buf_count; - *count += dpaa2_switch_add_bufs(ethsw, ethsw->bpid); + *count += ret;

- if (unlikely(*count < BUFS_PER_CMD)) + if (unlikely(ret < BUFS_PER_CMD)) return -ENOMEM; }

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index a5fc0209d628..4cbc4d069a1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5724,6 +5724,9 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) struct net_device *netdev = handle->kinfo.netdev; struct hns3_nic_priv *priv = netdev_priv(netdev);

+ if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + hns3_nic_net_stop(netdev); + if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) { netdev_warn(netdev, "already uninitialized\n"); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 82574ce0194f..465f0d582283 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2653,8 +2653,17 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; + int ret; + + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + + if (ret) + return ret;

- return hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + hdev->hw.mac.req_speed = speed; + hdev->hw.mac.req_duplex = duplex; + + return 0; }

static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) @@ -2956,17 +2965,20 @@ static int hclge_mac_init(struct hclge_dev *hdev) if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) hdev->hw.mac.duplex = HCLGE_MAC_FULL;

- ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, - hdev->hw.mac.duplex, hdev->hw.mac.lane_num); - if (ret) - return ret; - if (hdev->hw.mac.support_autoneg) { ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg); if (ret) return ret; }

+ if (!hdev->hw.mac.autoneg) { + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.req_speed, + hdev->hw.mac.req_duplex, + hdev->hw.mac.lane_num); + if (ret) + return ret; + } + mac->link = 0;

if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) { @@ -11516,8 +11528,8 @@ static void hclge_reset_done(struct hnae3_ae_dev *ae_dev) dev_err(&hdev->pdev->dev, "fail to rebuild, ret=%d\n", ret);

hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); }

static void hclge_clear_resetting_state(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 85fb11de43a1..80079657afeb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -191,6 +191,9 @@ static void hclge_mac_adjust_link(struct net_device *netdev) if (ret) netdev_err(netdev, "failed to adjust link.\n");

+ hdev->hw.mac.req_speed = (u32)speed; + hdev->hw.mac.req_duplex = (u8)duplex; + ret = hclge_cfg_flowctrl(hdev); if (ret) netdev_err(netdev, "failed to configure flow control.\n"); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 3735d2fed11f..094a7c7b5592 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1747,8 +1747,8 @@ static void hclgevf_reset_done(struct hnae3_ae_dev *ae_dev) ret);

hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); }

static u32 hclgevf_get_fw_version(struct hnae3_handle *handle) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c index 13e6790d3cae..afcf64dab48a 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c @@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) return -EIO;

attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = pf->hw.bus.func; + attrs.phys.port_number = pf->hw.pf_id;

/* As FW supports only port split options for whole device, * set port split options only for first PF. @@ -399,7 +399,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) return -EINVAL;

attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; - attrs.pci_vf.pf = pf->hw.bus.func; + attrs.pci_vf.pf = pf->hw.pf_id; attrs.pci_vf.vf = vf->vf_id;

ice_devlink_set_switch_id(pf, &attrs.switch_id); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1facf179a96f..f448d3a84564 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -512,6 +512,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) xsk_pool_fill_cb(ring->xsk_pool, &desc); }

+/** + * ice_get_frame_sz - calculate xdp_buff::frame_sz + * @rx_ring: the ring being configured + * + * Return frame size based on underlying PAGE_SIZE + */ +static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) +{ + unsigned int frame_sz; + +#if (PAGE_SIZE >= 8192) + frame_sz = rx_ring->rx_buf_len; +#else + frame_sz = ice_rx_pg_size(rx_ring) / 2; +#endif + + return frame_sz; +} + /** * ice_vsi_cfg_rxq - Configure an Rx queue * @ring: the ring being configured @@ -576,7 +595,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } }

- xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 8d25b6981269..c9bc3f1add5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -521,30 +521,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) return -ENOMEM; }

-/** - * ice_rx_frame_truesize - * @rx_ring: ptr to Rx ring - * @size: size - * - * calculate the truesize with taking into the account PAGE_SIZE of - * underlying arch - */ -static unsigned int -ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) -{ - unsigned int truesize; - -#if (PAGE_SIZE < 8192) - truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ -#else - truesize = rx_ring->rx_offset ? - SKB_DATA_ALIGN(rx_ring->rx_offset + size) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : - SKB_DATA_ALIGN(size); -#endif - return truesize; -} - /** * ice_run_xdp - Executes an XDP program on initialized xdp_buff * @rx_ring: Rx ring @@ -837,16 +813,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) if (!dev_page_is_reusable(page)) return false;

-#if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) return false; -#else +#if (PAGE_SIZE >= 8192) #define ICE_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048) + (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072) if (rx_buf->page_offset > ICE_LAST_OFFSET) return false; -#endif /* PAGE_SIZE < 8192) */ +#endif /* PAGE_SIZE >= 8192) */

/* If we have drained the page fragment pool we need to update * the pagecnt_bias and page count so that we fully restock the @@ -949,12 +924,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, struct ice_rx_buf *rx_buf;

rx_buf = &rx_ring->rx_buf[ntc]; - rx_buf->pgcnt = -#if (PAGE_SIZE < 8192) - page_count(rx_buf->page); -#else - 0; -#endif + rx_buf->pgcnt = page_count(rx_buf->page); prefetchw(rx_buf->page);

if (!size) @@ -1160,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) bool failure; u32 first;

- /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ -#if (PAGE_SIZE < 8192) - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0); -#endif - xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { xdp_ring = rx_ring->xdp_ring; @@ -1223,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) hard_start = page_address(rx_buf->page) + rx_buf->page_offset - offset; xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); -#if (PAGE_SIZE > 4096) - /* At larger PAGE_SIZE, frame_sz depend on len size */ - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size); -#endif xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { break; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fce2930ae6af..b6aa449aa56a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4809,6 +4809,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter,

#if (PAGE_SIZE < 8192) if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + IGB_2K_TOO_SMALL_WITH_PADDING || rd32(E1000_RCTL) & E1000_RCTL_SBP) set_ring_uses_large_buffer(rx_ring); #endif diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 5f92b3c7c3d4..511384f3ec5c 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -404,6 +404,12 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */

+/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 33069880c86c..3041f8142324 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6319,12 +6319,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL;

+ igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true;

- igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n];

diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedf..d68fa7f3d5f0 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -49,12 +49,19 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; }

+static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u16 txoffset;

- if (!is_any_launchtime(adapter)) + if (!igc_tsn_is_tx_mode_in_tsn(adapter)) return;

switch (adapter->link_speed) { @@ -78,6 +85,23 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); }

+static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + adapter->taprio_offload_enable; +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -91,6 +115,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);

+ if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); @@ -111,6 +138,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) return 0; }

+/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -123,6 +169,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);

+ if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; @@ -262,14 +311,6 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle);

base_time = ktime_add_ns(base_time, (n + 1) * cycle); - - /* Increase the counter if scheduling into the past while - * Gate Control List (GCL) is running. - */ - if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && - (adapter->qbv_count > 1)) - adapter->qbv_config_change_errors++; } else { if (igc_is_device_id_i226(hw)) { ktime_t adjust_time, expires_time; @@ -331,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; }

-int igc_tsn_offload_apply(struct igc_adapter *adapter) +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED);

- /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +} + +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index b53e6af560b7..98ec845a86bf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -7,5 +7,6 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter);

#endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 3e09d2285814..daf4b951e905 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -632,7 +632,9 @@ int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu, return ret; }

-static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) +static bool validate_and_update_reg_offset(struct rvu *rvu, + struct cpt_rd_wr_reg_msg *req, + u64 *reg_offset) { u64 offset = req->reg_offset; int blkaddr, num_lfs, lf; @@ -663,6 +665,11 @@ static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) if (lf < 0) return false;

+ /* Translate local LF's offset to global CPT LF's offset to + * access LFX register. + */ + *reg_offset = (req->reg_offset & 0xFF000) + (lf << 3); + return true; } else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) { /* Registers that can be accessed from PF */ @@ -697,7 +704,7 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, struct cpt_rd_wr_reg_msg *rsp) { u64 offset = req->reg_offset; - int blkaddr, lf; + int blkaddr;

blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr); if (blkaddr < 0) @@ -708,18 +715,10 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, !is_cpt_vf(rvu, req->hdr.pcifunc)) return CPT_AF_ERR_ACCESS_DENIED;

- if (!is_valid_offset(rvu, req)) + if (!validate_and_update_reg_offset(rvu, req, &offset)) return CPT_AF_ERR_ACCESS_DENIED;

- /* Translate local LF used by VFs to global CPT LF */ - lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], req->hdr.pcifunc, - (offset & 0xFFF) >> 3); - - /* Translate local LF's offset to global CPT LF's offset */ - offset &= 0xFF000; - offset += lf << 3; - - rsp->reg_offset = offset; + rsp->reg_offset = req->reg_offset; rsp->ret_val = req->ret_val; rsp->is_write = req->is_write;

diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 61334a71058c..e212a4ba9275 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -2666,14 +2666,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri { struct mtk_wed_flow_block_priv *priv = cb_priv; struct flow_cls_offload *cls = type_data; - struct mtk_wed_hw *hw = priv->hw; + struct mtk_wed_hw *hw = NULL;

- if (!tc_can_offload(priv->dev)) + if (!priv || !tc_can_offload(priv->dev)) return -EOPNOTSUPP;

if (type != TC_SETUP_CLSFLOWER) return -EOPNOTSUPP;

+ hw = priv->hw; return mtk_flow_offload_cmd(hw->eth, cls, hw->index); }

@@ -2729,6 +2730,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev, flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); kfree(block_cb->cb_priv); + block_cb->cb_priv = NULL; } return 0; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 22918b2ef7f1..09433b91be17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -146,7 +146,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) return err; }

+ mutex_lock(&priv->state_lock); err = mlx5e_safe_reopen_channels(priv); + mutex_unlock(&priv->state_lock); if (!err) { to_ctx->status = 1; /* all channels recovered */ return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 3eccdadc0357..773624bb2c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, if (num_tuples <= 0) { netdev_warn(priv->netdev, "%s: flow is not valid %d\n", __func__, num_tuples); - return num_tuples; + return num_tuples < 0 ? num_tuples : -EINVAL; }

eth_ft = get_flow_table(priv, fs, num_tuples); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index eedbcba22689..409f525f1703 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3005,15 +3005,18 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = priv->mdev; - int num_comp_vectors, ix, irq; - - num_comp_vectors = mlx5_comp_vectors_max(mdev); + int ix;

for (ix = 0; ix < params->num_channels; ix++) { + int num_comp_vectors, irq, vec_ix; + struct mlx5_core_dev *mdev; + + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + num_comp_vectors = mlx5_comp_vectors_max(mdev); cpumask_clear(priv->scratchpad.cpumask); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix);

- for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) { int cpu = mlx5_comp_vector_get_cpu(mdev, irq);

cpumask_set_cpu(cpu, priv->scratchpad.cpumask); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c index 234cd00f71a1..b7d4b1a2baf2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c @@ -386,7 +386,8 @@ static int ipsec_fs_roce_tx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP;

peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } @@ -455,7 +456,8 @@ static int ipsec_fs_roce_rx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP;

peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index f6deb5a3f820..eeb0b7ea05f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -126,7 +126,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) }

static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, - u8 *host_buses, u8 *sd_group) + u8 *host_buses) { u32 out[MLX5_ST_SZ_DW(mpir_reg)]; int err; @@ -135,10 +135,6 @@ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, if (err) return err;

- err = mlx5_query_nic_vport_sd_group(dev, sd_group); - if (err) - return err; - *sdm = MLX5_GET(mpir_reg, out, sdm); *host_buses = MLX5_GET(mpir_reg, out, host_buses);

@@ -166,19 +162,23 @@ static int sd_init(struct mlx5_core_dev *dev) if (mlx5_core_is_ecpf(dev)) return 0;

+ err = mlx5_query_nic_vport_sd_group(dev, &sd_group); + if (err) + return err; + + if (!sd_group) + return 0; + if (!MLX5_CAP_MCAM_REG(dev, mpir)) return 0;

- err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + err = mlx5_query_sd(dev, &sdm, &host_buses); if (err) return err;

if (!sdm) return 0;

- if (!sd_group) - return 0; - group_id = mlx5_sd_group_id(dev, sd_group);

if (!mlx5_sd_is_supported(dev, host_buses)) { diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h index bc94e75a7aeb..e7777700ee18 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -40,6 +40,7 @@ */ #define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0 #define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1 +#define MLXBF_GIGE_MAX_FILTER_IDX 3

/* Define for broadcast MAC literal */ #define BCAST_MAC_ADDR 0xFFFFFFFFFFFF @@ -175,6 +176,13 @@ enum mlxbf_gige_res { int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv); void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv); + +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 dmac); void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index b157f0f1c5a8..385a56ac7348 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev) if (err) goto napi_deinit;

+ mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX); + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX); + mlxbf_gige_enable_multicast_rx(priv); + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev) void __iomem *plu_base; void __iomem *base; int addr, phy_irq; + unsigned int i; int err;

base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); @@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ; priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ;

+ for (i = 0; i <= MLXBF_GIGE_MAX_FILTER_IDX; i++) + mlxbf_gige_disable_mac_rx_filter(priv, i); + mlxbf_gige_disable_multicast_rx(priv); + mlxbf_gige_disable_promisc(priv); + /* Write initial MAC address to hardware */ mlxbf_gige_initial_mac(priv);

diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index 98a8681c21b9..4d14cb13fd64 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -62,6 +62,8 @@ #define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520 #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528 +#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530 +#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540 #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548 diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 699984358493..eb62620b63c7 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -11,15 +11,31 @@ #include "mlxbf_gige.h" #include "mlxbf_gige_regs.h"

-void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, - unsigned int index, u64 dmac) +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv) { void __iomem *base = priv->base; - u64 control; + u64 data;

- /* Write destination MAC to specified MAC RX filter */ - writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + - (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data |= MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 data; + + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data &= ~MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control;

/* Enable MAC receive filter mask for specified index */ control = readq(base + MLXBF_GIGE_CONTROL); @@ -27,6 +43,28 @@ void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, writeq(control, base + MLXBF_GIGE_CONTROL); }

+void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; + + /* Disable MAC receive filter mask for specified index */ + control = readq(base + MLXBF_GIGE_CONTROL); + control &= ~(MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index); + writeq(control, base + MLXBF_GIGE_CONTROL); +} + +void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 dmac) +{ + void __iomem *base = priv->base; + + /* Write destination MAC to specified MAC RX filter */ + writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + + (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); +} + void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 *dmac) { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index ad7ae7ba2b8f..482b9cd36950 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, else *headroom = XDP_PACKET_HEADROOM;

- *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; + *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom); + + /* Using page pool in this case, so alloc_size is PAGE_SIZE */ + if (*alloc_size < PAGE_SIZE) + *alloc_size = PAGE_SIZE;

*datasize = mtu + ETH_HLEN; } @@ -1773,7 +1777,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w;

WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1784,16 +1787,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq);

w = cq->work_done; - - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + cq->work_done_since_doorbell += w; + + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; }

- mana_gd_ring_cq(gdma_queue, arm_bit); - return w; }

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ed2fb44500b0..f4e027a6fe95 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1099,6 +1099,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, } EXPORT_SYMBOL(ocelot_ptp_rx_timestamp);

+void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp); + +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp); + +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp); + +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp); + +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __acquires(&ocelot->xtr_lock) +{ + spin_lock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh); + +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __releases(&ocelot->xtr_lock) +{ + spin_unlock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh); + int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) { u64 timestamp, src_port, len; @@ -1109,6 +1151,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) u32 val, *buf; int err;

+ lockdep_assert_held(&ocelot->xtr_lock); + err = ocelot_xtr_poll_xfh(ocelot, grp, xfh); if (err) return err; @@ -1184,6 +1228,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) { u32 val = ocelot_read(ocelot, QS_INJ_STATUS);

+ lockdep_assert_held(&ocelot->inj_lock); + if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp)))) return false; if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp))) @@ -1193,28 +1239,55 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject);

-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +/** + * ocelot_ifh_set_basic - Set basic information in Injection Frame Header + * @ifh: Pointer to Injection Frame Header memory + * @ocelot: Switch private data structure + * @port: Egress port number + * @rew_op: Egress rewriter operation for PTP + * @skb: Pointer to socket buffer (packet) + * + * Populate the Injection Frame Header with basic information for this skb: the + * analyzer bypass bit, destination port, VLAN info, egress rewriter info. + */ +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct net_device *dev = skb->dev; + u64 vlan_tci, tag_type; + int qos_class; + + ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, + &tag_type); + + qos_class = netdev_get_num_tc(dev) ? + netdev_get_prio_tc_map(dev, skb->priority) : skb->priority; + + memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); + ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - if (vlan_tag) - ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + ocelot_ifh_set_qos_class(ifh, qos_class); + ocelot_ifh_set_tag_type(ifh, tag_type); + ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) ocelot_ifh_set_rew_op(ifh, rew_op); } -EXPORT_SYMBOL(ocelot_ifh_port_set); +EXPORT_SYMBOL(ocelot_ifh_set_basic);

void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) { - u32 ifh[OCELOT_TAG_LEN / 4] = {0}; + u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last;

+ lockdep_assert_held(&ocelot->inj_lock); + ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);

- ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);

for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); @@ -1247,6 +1320,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame);

void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) { + lockdep_assert_held(&ocelot->xtr_lock); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) ocelot_read_rix(ocelot, QS_XTR_RD, grp); } @@ -2929,6 +3004,8 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->fwd_domain_lock); spin_lock_init(&ocelot->ptp_clock_lock); spin_lock_init(&ocelot->ts_id_lock); + spin_lock_init(&ocelot->inj_lock); + spin_lock_init(&ocelot->xtr_lock);

ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0); if (!ocelot->owq) diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 312a46832154..00326ae8c708 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -665,8 +665,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op,

ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); - memset(ifh, 0, OCELOT_TAG_LEN); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);

return 0; } diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 993212c3a7da..c09dd2e3343c 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) struct ocelot *ocelot = arg; int grp = 0, err;

+ ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb;

@@ -69,6 +71,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) if (err < 0) ocelot_drain_cpu_queue(ocelot, 0);

+ ocelot_unlock_xtr_grp(ocelot, grp); + return IRQ_HANDLED; }

diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c index ec54b18c5fe7..a5e9b779c44d 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c @@ -124,8 +124,12 @@ static int ngbe_phylink_init(struct wx *wx) MAC_SYM_PAUSE | MAC_ASYM_PAUSE; config->mac_managed_pm = true;

- phy_mode = PHY_INTERFACE_MODE_RGMII_ID; - __set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces); + /* The MAC only has add the Tx delay and it can not be modified. + * So just disable TX delay in PHY, and it is does not matter to + * internal phy. + */ + phy_mode = PHY_INTERFACE_MODE_RGMII_RXID; + __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, config->supported_interfaces);

phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops); if (IS_ERR(phylink)) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fa5500decc96..09c9f9787180 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -160,16 +160,17 @@ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ #define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */ -#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */ -#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */ +#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ +#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ -#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */ -#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */ -#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */ -#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */ +#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ +#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ +#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ +#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ -#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */ +#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ +#define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */

@@ -308,7 +309,7 @@ */ #define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF

-/* Bit masks for Axi Ethernet FMI register */ +/* Bit masks for Axi Ethernet FMC register */ #define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */ #define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index fa510f4e2600..559c0d60d948 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -432,7 +432,7 @@ static int netdev_set_mac_address(struct net_device *ndev, void *p) */ static void axienet_set_multicast_list(struct net_device *ndev) { - int i; + int i = 0; u32 reg, af0reg, af1reg; struct axienet_local *lp = netdev_priv(ndev);

@@ -450,7 +450,10 @@ static void axienet_set_multicast_list(struct net_device *ndev) } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha;

- i = 0; + reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg &= ~XAE_FMI_PM_MASK; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) break; @@ -469,6 +472,7 @@ static void axienet_set_multicast_list(struct net_device *ndev) axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_AF0_OFFSET, af0reg); axienet_iow(lp, XAE_AF1_OFFSET, af1reg); + axienet_iow(lp, XAE_FFE_OFFSET, 1); i++; } } else { @@ -476,18 +480,15 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg &= ~XAE_FMI_PM_MASK;

axienet_iow(lp, XAE_FMI_OFFSET, reg); - - for (i = 0; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; - reg |= i; - - axienet_iow(lp, XAE_FMI_OFFSET, reg); - axienet_iow(lp, XAE_AF0_OFFSET, 0); - axienet_iow(lp, XAE_AF1_OFFSET, 0); - } - dev_info(&ndev->dev, "Promiscuous mode disabled.\n"); } + + for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { + reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg |= i; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + axienet_iow(lp, XAE_FFE_OFFSET, 0); + } }

/** diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 427b91aca50d..0696faf60013 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1269,6 +1269,9 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_cow_head(skb, dev->needed_headroom)) goto tx_err;

+ if (!pskb_inet_may_pull(skb)) + goto tx_err; + skb_reset_inner_headers(skb);

/* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */ diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c index a7c7a868c14c..fca9f7e510b4 100644 --- a/drivers/net/wireless/ath/ath12k/dp_tx.c +++ b/drivers/net/wireless/ath/ath12k/dp_tx.c @@ -124,6 +124,60 @@ static void ath12k_hal_tx_cmd_ext_desc_setup(struct ath12k_base *ab, HAL_TX_MSDU_EXT_INFO1_ENCRYPT_TYPE); }

+static void ath12k_dp_tx_move_payload(struct sk_buff *skb, + unsigned long delta, + bool head) +{ + unsigned long len = skb->len; + + if (head) { + skb_push(skb, delta); + memmove(skb->data, skb->data + delta, len); + skb_trim(skb, len); + } else { + skb_put(skb, delta); + memmove(skb->data + delta, skb->data, len); + skb_pull(skb, delta); + } +} + +static int ath12k_dp_tx_align_payload(struct ath12k_base *ab, + struct sk_buff **pskb) +{ + u32 iova_mask = ab->hw_params->iova_mask; + unsigned long offset, delta1, delta2; + struct sk_buff *skb2, *skb = *pskb; + unsigned int headroom = skb_headroom(skb); + int tailroom = skb_tailroom(skb); + int ret = 0; + + offset = (unsigned long)skb->data & iova_mask; + delta1 = offset; + delta2 = iova_mask - offset + 1; + + if (headroom >= delta1) { + ath12k_dp_tx_move_payload(skb, delta1, true); + } else if (tailroom >= delta2) { + ath12k_dp_tx_move_payload(skb, delta2, false); + } else { + skb2 = skb_realloc_headroom(skb, iova_mask); + if (!skb2) { + ret = -ENOMEM; + goto out; + } + + dev_kfree_skb_any(skb); + + offset = (unsigned long)skb2->data & iova_mask; + if (offset) + ath12k_dp_tx_move_payload(skb2, offset, true); + *pskb = skb2; + } + +out: + return ret; +} + int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif, struct sk_buff *skb) { @@ -145,6 +199,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif, u8 ring_selector, ring_map = 0; bool tcl_ring_retry; bool msdu_ext_desc = false; + u32 iova_mask = ab->hw_params->iova_mask;

if (test_bit(ATH12K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags)) return -ESHUTDOWN; @@ -240,6 +295,23 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif, goto fail_remove_tx_buf; }

+ if (iova_mask && + (unsigned long)skb->data & iova_mask) { + ret = ath12k_dp_tx_align_payload(ab, &skb); + if (ret) { + ath12k_warn(ab, "failed to align TX buffer %d\n", ret); + /* don't bail out, give original buffer + * a chance even unaligned. + */ + goto map; + } + + /* hdr is pointing to a wrong place after alignment, + * so refresh it for later use. + */ + hdr = (void *)skb->data; + } +map: ti.paddr = dma_map_single(ab->dev, skb->data, skb->len, DMA_TO_DEVICE); if (dma_mapping_error(ab->dev, ti.paddr)) { atomic_inc(&ab->soc_stats.tx_err.misc_fail); diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c index bff8cf97a18c..2a92147d15fa 100644 --- a/drivers/net/wireless/ath/ath12k/hw.c +++ b/drivers/net/wireless/ath/ath12k/hw.c @@ -922,6 +922,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .supports_sta_ps = false,

.acpi_guid = NULL, + + .iova_mask = 0, }, { .name = "wcn7850 hw2.0", @@ -997,6 +999,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .supports_sta_ps = true,

.acpi_guid = &wcn7850_uuid, + + .iova_mask = ATH12K_PCIE_MAX_PAYLOAD_SIZE - 1, }, { .name = "qcn9274 hw2.0", @@ -1067,6 +1071,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .supports_sta_ps = false,

.acpi_guid = NULL, + + .iova_mask = 0, }, };

diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h index 2a314cfc8cb8..400bda17e02f 100644 --- a/drivers/net/wireless/ath/ath12k/hw.h +++ b/drivers/net/wireless/ath/ath12k/hw.h @@ -96,6 +96,8 @@ #define ATH12K_M3_FILE "m3.bin" #define ATH12K_REGDB_FILE_NAME "regdb.bin"

+#define ATH12K_PCIE_MAX_PAYLOAD_SIZE 128 + enum ath12k_hw_rate_cck { ATH12K_HW_RATE_CCK_LP_11M = 0, ATH12K_HW_RATE_CCK_LP_5_5M, @@ -214,6 +216,8 @@ struct ath12k_hw_params { bool supports_sta_ps;

const guid_t *acpi_guid; + + u32 iova_mask; };

struct ath12k_hw_ops { diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index ead37a4e002a..8474e25d2ac6 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -8737,6 +8737,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)

hw->vif_data_size = sizeof(struct ath12k_vif); hw->sta_data_size = sizeof(struct ath12k_sta); + hw->extra_tx_headroom = ab->hw_params->iova_mask;

wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 5fe0e671ecb3..826b768196e2 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -4320,9 +4320,16 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, struct cfg80211_pmksa *pmksa, /* Single PMK operation */ pmk_op->count = cpu_to_le16(1); length += sizeof(struct brcmf_pmksa_v3); - memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); - memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); - pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + if (pmksa->bssid) + memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); + if (pmksa->pmkid) { + memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); + pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + } + if (pmksa->ssid && pmksa->ssid_len) { + memcpy(pmk_op->pmk[0].ssid.SSID, pmksa->ssid, pmksa->ssid_len); + pmk_op->pmk[0].ssid.SSID_len = pmksa->ssid_len; + } pmk_op->pmk[0].time_left = cpu_to_le32(alive ? BRCMF_PMKSA_NO_EXPIRY : 0); }

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 782090ce0bc1..d973d063bbf5 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4522,7 +4522,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) { nvme_mpath_stop(ctrl); nvme_auth_stop(ctrl); - nvme_stop_keep_alive(ctrl); nvme_stop_failfast_work(ctrl); flush_work(&ctrl->async_event_work); cancel_work_sync(&ctrl->fw_act_work); @@ -4558,6 +4557,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);

void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) { + nvme_stop_keep_alive(ctrl); nvme_hwmon_exit(ctrl); nvme_fault_inject_fini(&ctrl->fault_inject); dev_pm_qos_hide_latency_tolerance(ctrl->device); diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c index 7fc602e01487..7e89f547999b 100644 --- a/drivers/platform/surface/aggregator/controller.c +++ b/drivers/platform/surface/aggregator/controller.c @@ -1354,7 +1354,8 @@ void ssam_controller_destroy(struct ssam_controller *ctrl) if (ctrl->state == SSAM_CONTROLLER_UNINITIALIZED) return;

- WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED); + WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED && + ctrl->state != SSAM_CONTROLLER_INITIALIZED);

/* * Note: New events could still have been received after the previous diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig index 195a8bf532cc..de0bfd8f4b66 100644 --- a/drivers/platform/x86/dell/Kconfig +++ b/drivers/platform/x86/dell/Kconfig @@ -148,6 +148,7 @@ config DELL_SMO8800 config DELL_UART_BACKLIGHT tristate "Dell AIO UART Backlight driver" depends on ACPI + depends on ACPI_VIDEO depends on BACKLIGHT_CLASS_DEVICE depends on SERIAL_DEV_BUS help diff --git a/drivers/platform/x86/dell/dell-uart-backlight.c b/drivers/platform/x86/dell/dell-uart-backlight.c index 87d2a20b4cb3..3995f90add45 100644 --- a/drivers/platform/x86/dell/dell-uart-backlight.c +++ b/drivers/platform/x86/dell/dell-uart-backlight.c @@ -20,6 +20,7 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/wait.h> +#include <acpi/video.h> #include "../serdev_helpers.h"

/* The backlight controller must respond within 1 second */ @@ -332,10 +333,17 @@ struct serdev_device_driver dell_uart_bl_serdev_driver = {

static int dell_uart_bl_pdev_probe(struct platform_device *pdev) { + enum acpi_backlight_type bl_type; struct serdev_device *serdev; struct device *ctrl_dev; int ret;

+ bl_type = acpi_video_get_backlight_type(); + if (bl_type != acpi_backlight_dell_uart) { + dev_dbg(&pdev->dev, "Not loading (ACPI backlight type = %d)\n", bl_type); + return -ENODEV; + } + ctrl_dev = get_serdev_controller("DELL0501", NULL, 0, "serial0"); if (IS_ERR(ctrl_dev)) return PTR_ERR(ctrl_dev); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c index 7fa360073f6e..404582307109 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -1549,8 +1549,7 @@ int tpmi_sst_dev_add(struct auxiliary_device *auxdev) goto unlock_free; }

- ret = sst_main(auxdev, &pd_info[i]); - if (ret) { + if (sst_main(auxdev, &pd_info[i])) { /* * This entry is not valid, hardware can partially * populate dies. In this case MMIO will have 0xFFs. diff --git a/drivers/pmdomain/imx/imx93-pd.c b/drivers/pmdomain/imx/imx93-pd.c index 1e94b499c19b..d750a7dc58d2 100644 --- a/drivers/pmdomain/imx/imx93-pd.c +++ b/drivers/pmdomain/imx/imx93-pd.c @@ -20,6 +20,7 @@ #define FUNC_STAT_PSW_STAT_MASK BIT(0) #define FUNC_STAT_RST_STAT_MASK BIT(2) #define FUNC_STAT_ISO_STAT_MASK BIT(4) +#define FUNC_STAT_SSAR_STAT_MASK BIT(8)

struct imx93_power_domain { struct generic_pm_domain genpd; @@ -50,7 +51,7 @@ static int imx93_pd_on(struct generic_pm_domain *genpd) writel(val, addr + MIX_SLICE_SW_CTRL_OFF);

ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val, - !(val & FUNC_STAT_ISO_STAT_MASK), 1, 10000); + !(val & FUNC_STAT_SSAR_STAT_MASK), 1, 10000); if (ret) { dev_err(domain->dev, "pd_on timeout: name: %s, stat: %x\n", genpd->name, val); return ret; @@ -72,7 +73,7 @@ static int imx93_pd_off(struct generic_pm_domain *genpd) writel(val, addr + MIX_SLICE_SW_CTRL_OFF);

ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val, - val & FUNC_STAT_PSW_STAT_MASK, 1, 1000); + val & FUNC_STAT_PSW_STAT_MASK, 1, 10000); if (ret) { dev_err(domain->dev, "pd_off timeout: name: %s, stat: %x\n", genpd->name, val); return ret; diff --git a/drivers/pmdomain/imx/scu-pd.c b/drivers/pmdomain/imx/scu-pd.c index 05841b0bf7f3..01d465d88f60 100644 --- a/drivers/pmdomain/imx/scu-pd.c +++ b/drivers/pmdomain/imx/scu-pd.c @@ -223,11 +223,6 @@ static const struct imx_sc_pd_range imx8qxp_scu_pd_ranges[] = { { "lvds1-pwm", IMX_SC_R_LVDS_1_PWM_0, 1, false, 0 }, { "lvds1-lpi2c", IMX_SC_R_LVDS_1_I2C_0, 2, true, 0 },

- { "mipi1", IMX_SC_R_MIPI_1, 1, 0 }, - { "mipi1-pwm0", IMX_SC_R_MIPI_1_PWM_0, 1, 0 }, - { "mipi1-i2c", IMX_SC_R_MIPI_1_I2C_0, 2, 1 }, - { "lvds1", IMX_SC_R_LVDS_1, 1, 0 }, - /* DC SS */ { "dc0", IMX_SC_R_DC_0, 1, false, 0 }, { "dc0-pll", IMX_SC_R_DC_0_PLL_0, 2, true, 0 }, diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 0a97cfedd706..42a4a996defb 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1601,9 +1601,15 @@ static int dasd_ese_needs_format(struct dasd_block *block, struct irb *irb) if (!sense) return 0;

- return !!(sense[1] & SNS1_NO_REC_FOUND) || - !!(sense[1] & SNS1_FILE_PROTECTED) || - scsw_cstat(&irb->scsw) == SCHN_STAT_INCORR_LEN; + if (sense[1] & SNS1_NO_REC_FOUND) + return 1; + + if ((sense[1] & SNS1_INV_TRACK_FORMAT) && + scsw_is_tm(&irb->scsw) && + !(sense[2] & SNS2_ENV_DATA_PRESENT)) + return 1; + + return 0; }

static int dasd_ese_oos_cond(u8 *sense) @@ -1624,7 +1630,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, struct dasd_device *device; unsigned long now; int nrf_suppressed = 0; - int fp_suppressed = 0; + int it_suppressed = 0; struct request *req; u8 *sense = NULL; int expires; @@ -1679,8 +1685,9 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, */ sense = dasd_get_sense(irb); if (sense) { - fp_suppressed = (sense[1] & SNS1_FILE_PROTECTED) && - test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); + it_suppressed = (sense[1] & SNS1_INV_TRACK_FORMAT) && + !(sense[2] & SNS2_ENV_DATA_PRESENT) && + test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags); nrf_suppressed = (sense[1] & SNS1_NO_REC_FOUND) && test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);

@@ -1695,7 +1702,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, return; } } - if (!(fp_suppressed || nrf_suppressed)) + if (!(it_suppressed || nrf_suppressed)) device->discipline->dump_sense_dbf(device, irb, "int");

if (device->features & DASD_FEATURE_ERPLOG) @@ -2459,14 +2466,17 @@ static int _dasd_sleep_on_queue(struct list_head *ccw_queue, int interruptible) rc = 0; list_for_each_entry_safe(cqr, n, ccw_queue, blocklist) { /* - * In some cases the 'File Protected' or 'Incorrect Length' - * error might be expected and error recovery would be - * unnecessary in these cases. Check if the according suppress - * bit is set. + * In some cases certain errors might be expected and + * error recovery would be unnecessary in these cases. + * Check if the according suppress bit is set. */ sense = dasd_get_sense(&cqr->irb); - if (sense && sense[1] & SNS1_FILE_PROTECTED && - test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags)) + if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) && + !(sense[2] & SNS2_ENV_DATA_PRESENT) && + test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags)) + continue; + if (sense && (sense[1] & SNS1_NO_REC_FOUND) && + test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags)) continue; if (scsw_cstat(&cqr->irb.scsw) == 0x40 && test_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags)) diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index bbbacfc386f2..d0aa267462c5 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -1386,14 +1386,8 @@ dasd_3990_erp_file_prot(struct dasd_ccw_req * erp)

struct dasd_device *device = erp->startdev;

- /* - * In some cases the 'File Protected' error might be expected and - * log messages shouldn't be written then. - * Check if the according suppress bit is set. - */ - if (!test_bit(DASD_CQR_SUPPRESS_FP, &erp->flags)) - dev_err(&device->cdev->dev, - "Accessing the DASD failed because of a hardware error\n"); + dev_err(&device->cdev->dev, + "Accessing the DASD failed because of a hardware error\n");

return dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index a76c6af9ea63..a47443d3cc36 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2274,6 +2274,7 @@ dasd_eckd_analysis_ccw(struct dasd_device *device) cqr->status = DASD_CQR_FILLED; /* Set flags to suppress output for expected errors */ set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags);

return cqr; } @@ -2555,7 +2556,6 @@ dasd_eckd_build_check_tcw(struct dasd_device *base, struct format_data_t *fdata, cqr->buildclk = get_tod_clock(); cqr->status = DASD_CQR_FILLED; /* Set flags to suppress output for expected errors */ - set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags);

return cqr; @@ -4129,8 +4129,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(

/* Set flags to suppress output for expected errors */ if (dasd_eckd_is_ese(basedev)) { - set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); - set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags); set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); }

@@ -4632,9 +4630,8 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(

/* Set flags to suppress output for expected errors */ if (dasd_eckd_is_ese(basedev)) { - set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags); - set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags); set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags); + set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags); }

return cqr; @@ -5779,36 +5776,32 @@ static void dasd_eckd_dump_sense(struct dasd_device *device, { u8 *sense = dasd_get_sense(irb);

- if (scsw_is_tm(&irb->scsw)) { - /* - * In some cases the 'File Protected' or 'Incorrect Length' - * error might be expected and log messages shouldn't be written - * then. Check if the according suppress bit is set. - */ - if (sense && (sense[1] & SNS1_FILE_PROTECTED) && - test_bit(DASD_CQR_SUPPRESS_FP, &req->flags)) - return; - if (scsw_cstat(&irb->scsw) == 0x40 && - test_bit(DASD_CQR_SUPPRESS_IL, &req->flags)) - return; + /* + * In some cases certain errors might be expected and + * log messages shouldn't be written then. + * Check if the according suppress bit is set. + */ + if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) && + !(sense[2] & SNS2_ENV_DATA_PRESENT) && + test_bit(DASD_CQR_SUPPRESS_IT, &req->flags)) + return;

- dasd_eckd_dump_sense_tcw(device, req, irb); - } else { - /* - * In some cases the 'Command Reject' or 'No Record Found' - * error might be expected and log messages shouldn't be - * written then. Check if the according suppress bit is set. - */ - if (sense && sense[0] & SNS0_CMD_REJECT && - test_bit(DASD_CQR_SUPPRESS_CR, &req->flags)) - return; + if (sense && sense[0] & SNS0_CMD_REJECT && + test_bit(DASD_CQR_SUPPRESS_CR, &req->flags)) + return;

- if (sense && sense[1] & SNS1_NO_REC_FOUND && - test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags)) - return; + if (sense && sense[1] & SNS1_NO_REC_FOUND && + test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags)) + return;

+ if (scsw_cstat(&irb->scsw) == 0x40 && + test_bit(DASD_CQR_SUPPRESS_IL, &req->flags)) + return; + + if (scsw_is_tm(&irb->scsw)) + dasd_eckd_dump_sense_tcw(device, req, irb); + else dasd_eckd_dump_sense_ccw(device, req, irb); - } }

static int dasd_eckd_reload_device(struct dasd_device *device) diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 4533dd055ca8..23d6e638f381 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -41,7 +41,6 @@ int dasd_gendisk_alloc(struct dasd_block *block) */ .max_segment_size = PAGE_SIZE, .seg_boundary_mask = PAGE_SIZE - 1, - .dma_alignment = PAGE_SIZE - 1, .max_segments = USHRT_MAX, }; struct gendisk *gdp; diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index e5f40536b425..81cfb5c89681 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -196,7 +196,7 @@ struct dasd_ccw_req { * The following flags are used to suppress output of certain errors. */ #define DASD_CQR_SUPPRESS_NRF 4 /* Suppress 'No Record Found' error */ -#define DASD_CQR_SUPPRESS_FP 5 /* Suppress 'File Protected' error*/ +#define DASD_CQR_SUPPRESS_IT 5 /* Suppress 'Invalid Track' error*/ #define DASD_CQR_SUPPRESS_IL 6 /* Suppress 'Incorrect Length' error */ #define DASD_CQR_SUPPRESS_CR 7 /* Suppress 'Command Reject' error */

diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 898865be0dad..99fadfb4cd9f 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -971,11 +971,16 @@ int ap_driver_register(struct ap_driver *ap_drv, struct module *owner, char *name) { struct device_driver *drv = &ap_drv->driver; + int rc;

drv->bus = &ap_bus_type; drv->owner = owner; drv->name = name; - return driver_register(drv); + rc = driver_register(drv); + + ap_check_bindings_complete(); + + return rc; } EXPORT_SYMBOL(ap_driver_register);

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 05ebb03d319f..d4607cb89c48 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -2000,13 +2000,25 @@ static int cqspi_runtime_resume(struct device *dev) static int cqspi_suspend(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); + int ret;

- return spi_controller_suspend(cqspi->host); + ret = spi_controller_suspend(cqspi->host); + if (ret) + return ret; + + return pm_runtime_force_suspend(dev); }

static int cqspi_resume(struct device *dev) { struct cqspi_st *cqspi = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) { + dev_err(dev, "pm_runtime_force_resume failed on resume\n"); + return ret; + }

return spi_controller_resume(cqspi->host); } diff --git a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h index 961c61288083..aad860e54d3a 100644 --- a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h +++ b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h @@ -27,12 +27,16 @@ #include "ia_css_prbs.h" #include "ia_css_input_port.h"

-/* Input modes, these enumerate all supported input modes. - * Note that not all ISP modes support all input modes. +/* + * Input modes, these enumerate all supported input modes. + * This enum is part of the atomisp firmware ABI and must + * NOT be changed! + * Note that not all ISP modes support all input modes. */ enum ia_css_input_mode { IA_CSS_INPUT_MODE_SENSOR, /** data from sensor */ IA_CSS_INPUT_MODE_FIFO, /** data from input-fifo */ + IA_CSS_INPUT_MODE_TPG, /** data from test-pattern generator */ IA_CSS_INPUT_MODE_PRBS, /** data from pseudo-random bit stream */ IA_CSS_INPUT_MODE_MEMORY, /** data from a frame in memory */ IA_CSS_INPUT_MODE_BUFFERED_SENSOR /** data is sent through mipi buffer */ diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h index bef2b8c5132b..419aba9b0e49 100644 --- a/drivers/staging/media/atomisp/pci/sh_css_internal.h +++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h @@ -341,7 +341,14 @@ struct sh_css_sp_input_formatter_set {

#define IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT (3)

-/* SP configuration information */ +/* + * SP configuration information + * + * This struct is part of the atomisp firmware ABI and is directly copied + * to ISP DRAM by sh_css_store_sp_group_to_ddr() + * + * Do NOT change this struct's layout or remove seemingly unused fields! + */ struct sh_css_sp_config { u8 no_isp_sync; /* Signal host immediately after start */ u8 enable_raw_pool_locking; /** Enable Raw Buffer Locking for HALv3 Support */ @@ -351,6 +358,10 @@ struct sh_css_sp_config { host (true) or when they are passed to the preview/video pipe (false). */

+ /* + * Note the fields below are only used on the ISP2400 not on the ISP2401, + * sh_css_store_sp_group_to_ddr() skip copying these when run on the ISP2401. + */ struct { u8 a_changed; u8 b_changed; @@ -360,11 +371,13 @@ struct sh_css_sp_config { } input_formatter;

sync_generator_cfg_t sync_gen; + tpg_cfg_t tpg; prbs_cfg_t prbs; input_system_cfg_t input_circuit; u8 input_circuit_cfg_changed; - u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT]; - u8 enable_isys_event_queue; + u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT]; + /* These last 2 fields are used on both the ISP2400 and the ISP2401 */ + u8 enable_isys_event_queue; u8 disable_cont_vf; };

diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index acb52c9ee10f..daed67d19efb 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -13,6 +13,28 @@

#include "thermal_core.h"

+static void bang_bang_set_instance_target(struct thermal_instance *instance, + unsigned int target) +{ + if (instance->target != 0 && instance->target != 1 && + instance->target != THERMAL_NO_TARGET) + pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n", + instance->target, instance->name); + + /* + * Enable the fan when the trip is crossed on the way up and disable it + * when the trip is crossed on the way down. + */ + instance->target = target; + instance->initialized = true; + + dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target); + + mutex_lock(&instance->cdev->lock); + __thermal_cdev_update(instance->cdev); + mutex_unlock(&instance->cdev->lock); +} + /** * bang_bang_control - controls devices associated with the given zone * @tz: thermal_zone_device @@ -54,41 +76,60 @@ static void bang_bang_control(struct thermal_zone_device *tz, tz->temperature, trip->hysteresis);

list_for_each_entry(instance, &tz->thermal_instances, tz_node) { - if (instance->trip != trip) - continue; + if (instance->trip == trip) + bang_bang_set_instance_target(instance, crossed_up); + } +} + +static void bang_bang_manage(struct thermal_zone_device *tz) +{ + const struct thermal_trip_desc *td; + struct thermal_instance *instance;

- if (instance->target == THERMAL_NO_TARGET) - instance->target = 0; + /* If the code below has run already, nothing needs to be done. */ + if (tz->governor_data) + return;

- if (instance->target != 0 && instance->target != 1) { - pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n", - instance->target, instance->name); + for_each_trip_desc(tz, td) { + const struct thermal_trip *trip = &td->trip;

- instance->target = 1; - } + if (tz->temperature >= td->threshold || + trip->temperature == THERMAL_TEMP_INVALID || + trip->type == THERMAL_TRIP_CRITICAL || + trip->type == THERMAL_TRIP_HOT) + continue;

/* - * Enable the fan when the trip is crossed on the way up and - * disable it when the trip is crossed on the way down. + * If the initial cooling device state is "on", but the zone + * temperature is not above the trip point, the core will not + * call bang_bang_control() until the zone temperature reaches + * the trip point temperature which may be never. In those + * cases, set the initial state of the cooling device to 0. */ - if (instance->target == 0 && crossed_up) - instance->target = 1; - else if (instance->target == 1 && !crossed_up) - instance->target = 0; - - dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target); - - mutex_lock(&instance->cdev->lock); - instance->cdev->updated = false; /* cdev needs update */ - mutex_unlock(&instance->cdev->lock); + list_for_each_entry(instance, &tz->thermal_instances, tz_node) { + if (!instance->initialized && instance->trip == trip) + bang_bang_set_instance_target(instance, 0); + } }

- list_for_each_entry(instance, &tz->thermal_instances, tz_node) - thermal_cdev_update(instance->cdev); + tz->governor_data = (void *)true; +} + +static void bang_bang_update_tz(struct thermal_zone_device *tz, + enum thermal_notify_event reason) +{ + /* + * Let bang_bang_manage() know that it needs to walk trips after binding + * a new cdev and after system resume. + */ + if (reason == THERMAL_TZ_BIND_CDEV || reason == THERMAL_TZ_RESUME) + tz->governor_data = NULL; }

static struct thermal_governor thermal_gov_bang_bang = { .name = "bang_bang", .trip_crossed = bang_bang_control, + .manage = bang_bang_manage, + .update_tz = bang_bang_update_tz, }; THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index f2d31bc48f52..b8d889ef4fa5 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1715,7 +1715,8 @@ static void thermal_zone_device_resume(struct work_struct *work) tz->suspended = false;

thermal_zone_device_init(tz); - __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); + thermal_governor_update_tz(tz, THERMAL_TZ_RESUME); + __thermal_zone_device_update(tz, THERMAL_TZ_RESUME);

complete(&tz->resume); tz->resuming = false; diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c index 942447229157..6d55f5fc4ca0 100644 --- a/drivers/thermal/thermal_debugfs.c +++ b/drivers/thermal/thermal_debugfs.c @@ -178,11 +178,11 @@ struct thermal_debugfs { void thermal_debug_init(void) { d_root = debugfs_create_dir("thermal", NULL); - if (!d_root) + if (IS_ERR(d_root)) return;

d_cdev = debugfs_create_dir("cooling_devices", d_root); - if (!d_cdev) + if (IS_ERR(d_cdev)) return;

d_tz = debugfs_create_dir("thermal_zones", d_root); @@ -202,7 +202,7 @@ static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id) snprintf(ids, IDSLENGTH, "%d", id);

thermal_dbg->d_top = debugfs_create_dir(ids, d); - if (!thermal_dbg->d_top) { + if (IS_ERR(thermal_dbg->d_top)) { kfree(thermal_dbg); return NULL; } diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index aa34b6e82e26..1f252692815a 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -125,7 +125,7 @@ static int thermal_of_populate_trip(struct device_node *np, static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *ntrips) { struct thermal_trip *tt; - struct device_node *trips, *trip; + struct device_node *trips; int ret, count;

trips = of_get_child_by_name(np, "trips"); @@ -150,7 +150,7 @@ static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *n *ntrips = count;

count = 0; - for_each_child_of_node(trips, trip) { + for_each_child_of_node_scoped(trips, trip) { ret = thermal_of_populate_trip(trip, &tt[count++]); if (ret) goto out_kfree; @@ -184,14 +184,14 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int * Search for each thermal zone, a defined sensor * corresponding to the one passed as parameter */ - for_each_available_child_of_node(np, tz) { + for_each_available_child_of_node_scoped(np, child) {

int count, i;

- count = of_count_phandle_with_args(tz, "thermal-sensors", + count = of_count_phandle_with_args(child, "thermal-sensors", "#thermal-sensor-cells"); if (count <= 0) { - pr_err("%pOFn: missing thermal sensor\n", tz); + pr_err("%pOFn: missing thermal sensor\n", child); tz = ERR_PTR(-EINVAL); goto out; } @@ -200,18 +200,19 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int

int ret;

- ret = of_parse_phandle_with_args(tz, "thermal-sensors", + ret = of_parse_phandle_with_args(child, "thermal-sensors", "#thermal-sensor-cells", i, &sensor_specs); if (ret < 0) { - pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", tz, ret); + pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", child, ret); tz = ERR_PTR(ret); goto out; }

if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ? sensor_specs.args[0] : 0)) { - pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, tz); + pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child); + tz = no_free_ptr(child); goto out; } } @@ -491,7 +492,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node * trips = thermal_of_trips_init(np, &ntrips); if (IS_ERR(trips)) { pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id); - return ERR_CAST(trips); + ret = PTR_ERR(trips); + goto out_of_node_put; }

ret = thermal_of_monitor_init(np, &delay, &pdelay); @@ -519,6 +521,7 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node * goto out_kfree_trips; }

+ of_node_put(np); kfree(trips);

ret = thermal_zone_device_enable(tz); @@ -533,6 +536,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *

out_kfree_trips: kfree(trips); +out_of_node_put: + of_node_put(np);

return ERR_PTR(ret); } diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 326433df5880..6a2116cbb06f 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -3392,6 +3392,7 @@ void tb_switch_remove(struct tb_switch *sw) tb_switch_remove(port->remote->sw); port->remote = NULL; } else if (port->xdomain) { + port->xdomain->is_unplugged = true; tb_xdomain_remove(port->xdomain); port->xdomain = NULL; } diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 1af9aed99c65..afef1dd4ddf4 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -27,7 +27,6 @@ #include <linux/pm_wakeirq.h> #include <linux/dma-mapping.h> #include <linux/sys_soc.h> -#include <linux/pm_domain.h>

#include "8250.h"

@@ -119,12 +118,6 @@ #define UART_OMAP_TO_L 0x26 #define UART_OMAP_TO_H 0x27

-/* - * Copy of the genpd flags for the console. - * Only used if console suspend is disabled - */ -static unsigned int genpd_flags_console; - struct omap8250_priv { void __iomem *membase; int line; @@ -1655,7 +1648,6 @@ static int omap8250_suspend(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); struct uart_8250_port *up = serial8250_get_port(priv->line); - struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain); int err = 0;

serial8250_suspend_port(priv->line); @@ -1666,19 +1658,8 @@ static int omap8250_suspend(struct device *dev) if (!device_may_wakeup(dev)) priv->wer = 0; serial_out(up, UART_OMAP_WER, priv->wer); - if (uart_console(&up->port)) { - if (console_suspend_enabled) - err = pm_runtime_force_suspend(dev); - else { - /* - * The pd shall not be powered-off (no console suspend). - * Make copy of genpd flags before to set it always on. - * The original value is restored during the resume. - */ - genpd_flags_console = genpd->flags; - genpd->flags |= GENPD_FLAG_ALWAYS_ON; - } - } + if (uart_console(&up->port) && console_suspend_enabled) + err = pm_runtime_force_suspend(dev); flush_work(&priv->qos_work);

return err; @@ -1688,16 +1669,12 @@ static int omap8250_resume(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); struct uart_8250_port *up = serial8250_get_port(priv->line); - struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain); int err;

if (uart_console(&up->port) && console_suspend_enabled) { - if (console_suspend_enabled) { - err = pm_runtime_force_resume(dev); - if (err) - return err; - } else - genpd->flags = genpd_flags_console; + err = pm_runtime_force_resume(dev); + if (err) + return err; }

serial8250_resume_port(priv->line); diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 0a90964d6d10..09b246c9e389 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2514,7 +2514,7 @@ static const struct uart_ops atmel_pops = { };

static const struct serial_rs485 atmel_rs485_supported = { - .flags = SER_RS485_ENABLED | SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX, + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RX_DURING_TX, .delay_rts_before_send = 1, .delay_rts_after_send = 1, }; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 615291ea9b5e..77efa7ee6eda 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2923,6 +2923,7 @@ static int lpuart_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(&pdev->dev, UART_AUTOSUSPEND_TIMEOUT); pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); + pm_runtime_mark_last_busy(&pdev->dev);

ret = lpuart_global_reset(sport); if (ret) diff --git a/drivers/tty/vt/conmakehash.c b/drivers/tty/vt/conmakehash.c index 82d9db68b2ce..a931fcde7ad9 100644 --- a/drivers/tty/vt/conmakehash.c +++ b/drivers/tty/vt/conmakehash.c @@ -11,8 +11,6 @@ * Copyright (C) 1995-1997 H. Peter Anvin */

-#include <libgen.h> -#include <linux/limits.h> #include <stdio.h> #include <stdlib.h> #include <sysexits.h> @@ -79,7 +77,6 @@ int main(int argc, char *argv[]) { FILE *ctbl; const char *tblname; - char base_tblname[PATH_MAX]; char buffer[65536]; int fontlen; int i, nuni, nent; @@ -245,20 +242,15 @@ int main(int argc, char *argv[]) for ( i = 0 ; i < fontlen ; i++ ) nuni += unicount[i];

- strncpy(base_tblname, tblname, PATH_MAX); - base_tblname[PATH_MAX - 1] = 0; printf("\ /*\n\ - * Do not edit this file; it was automatically generated by\n\ - *\n\ - * conmakehash %s > [this file]\n\ - *\n\ + * Automatically generated file; Do not edit.\n\ */\n\ \n\ #include <linux/types.h>\n\ \n\ u8 dfont_unicount[%d] = \n\ -{\n\t", basename(base_tblname), fontlen); +{\n\t", fontlen);

for ( i = 0 ; i < fontlen ; i++ ) { diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 3100219d6496..f591ddd08662 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1877,7 +1877,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)

cancel_delayed_work_sync(&xhci->cmd_timer);

- for (i = 0; i < xhci->max_interrupters; i++) { + for (i = 0; xhci->interrupters && i < xhci->max_interrupters; i++) { if (xhci->interrupters[i]) { xhci_remove_interrupter(xhci, xhci->interrupters[i]); xhci_free_interrupter(xhci, xhci->interrupters[i]); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 0a8cf6c17f82..efdf4c228b8c 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2837,7 +2837,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci, xhci->num_active_eps); return -ENOMEM; } - if ((xhci->quirks & XHCI_SW_BW_CHECKING) && + if ((xhci->quirks & XHCI_SW_BW_CHECKING) && !ctx_change && xhci_reserve_bandwidth(xhci, virt_dev, command->in_ctx)) { if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) xhci_free_host_resources(xhci, ctrl_ctx); @@ -4200,8 +4200,10 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, mutex_unlock(&xhci->mutex); ret = xhci_disable_slot(xhci, udev->slot_id); xhci_free_virt_device(xhci, udev->slot_id); - if (!ret) - xhci_alloc_dev(hcd, udev); + if (!ret) { + if (xhci_alloc_dev(hcd, udev) == 1) + xhci_setup_addressable_virt_dev(xhci, udev); + } kfree(command->completion); kfree(command); return -EPROTO; diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c index 2d30fc1be306..1a8d5e80b9ae 100644 --- a/drivers/usb/misc/usb-ljca.c +++ b/drivers/usb/misc/usb-ljca.c @@ -169,6 +169,7 @@ static const struct acpi_device_id ljca_gpio_hids[] = { { "INTC1096" }, { "INTC100B" }, { "INTC10D1" }, + { "INTC10B5" }, {}, };

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 5d4da962acc8..ea388e793f88 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5630,7 +5630,6 @@ static void run_state_machine(struct tcpm_port *port) break; case PORT_RESET: tcpm_reset_port(port); - port->pd_events = 0; if (port->self_powered) tcpm_set_cc(port, TYPEC_CC_OPEN); else diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 6cc80fb10da2..5eb06fccc32e 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -1169,6 +1169,73 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt return find_ref_head(delayed_refs, bytenr, false); }

+static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent) +{ + int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY; + + if (type < entry->type) + return -1; + if (type > entry->type) + return 1; + + if (type == BTRFS_TREE_BLOCK_REF_KEY) { + if (root < entry->ref_root) + return -1; + if (root > entry->ref_root) + return 1; + } else { + if (parent < entry->parent) + return -1; + if (parent > entry->parent) + return 1; + } + return 0; +} + +/* + * Check to see if a given root/parent reference is attached to the head. This + * only checks for BTRFS_ADD_DELAYED_REF references that match, as that + * indicates the reference exists for the given root or parent. This is for + * tree blocks only. + * + * @head: the head of the bytenr we're searching. + * @root: the root objectid of the reference if it is a normal reference. + * @parent: the parent if this is a shared backref. + */ +bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, + u64 root, u64 parent) +{ + struct rb_node *node; + bool found = false; + + lockdep_assert_held(&head->mutex); + + spin_lock(&head->lock); + node = head->ref_tree.rb_root.rb_node; + while (node) { + struct btrfs_delayed_ref_node *entry; + int ret; + + entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); + ret = find_comp(entry, root, parent); + if (ret < 0) { + node = node->rb_left; + } else if (ret > 0) { + node = node->rb_right; + } else { + /* + * We only want to count ADD actions, as drops mean the + * ref doesn't exist. + */ + if (entry->action == BTRFS_ADD_DELAYED_REF) + found = true; + break; + } + } + spin_unlock(&head->lock); + return found; +} + void __cold btrfs_delayed_ref_exit(void) { kmem_cache_destroy(btrfs_delayed_ref_head_cachep); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 04b180ebe1fe..1d11a1a6f9cb 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -389,6 +389,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, u64 num_bytes); bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info); +bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, + u64 root, u64 parent);

static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 844b677d054e..8bf980123c5c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5387,23 +5387,62 @@ static int check_ref_exists(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 parent, int level) { + struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_head *head; struct btrfs_path *path; struct btrfs_extent_inline_ref *iref; int ret; + bool exists = false;

path = btrfs_alloc_path(); if (!path) return -ENOMEM; - +again: ret = lookup_extent_backref(trans, path, &iref, bytenr, root->fs_info->nodesize, parent, btrfs_root_id(root), level, 0); + if (ret != -ENOENT) { + /* + * If we get 0 then we found our reference, return 1, else + * return the error if it's not -ENOENT; + */ + btrfs_free_path(path); + return (ret < 0 ) ? ret : 1; + } + + /* + * We could have a delayed ref with this reference, so look it up while + * we're holding the path open to make sure we don't race with the + * delayed ref running. + */ + delayed_refs = &trans->transaction->delayed_refs; + spin_lock(&delayed_refs->lock); + head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); + if (!head) + goto out; + if (!mutex_trylock(&head->mutex)) { + /* + * We're contended, means that the delayed ref is running, get a + * reference and wait for the ref head to be complete and then + * try again. + */ + refcount_inc(&head->refs); + spin_unlock(&delayed_refs->lock); + + btrfs_release_path(path); + + mutex_lock(&head->mutex); + mutex_unlock(&head->mutex); + btrfs_put_delayed_ref_head(head); + goto again; + } + + exists = btrfs_find_delayed_tree_ref(head, root->root_key.objectid, parent); + mutex_unlock(&head->mutex); +out: + spin_unlock(&delayed_refs->lock); btrfs_free_path(path); - if (ret == -ENOENT) - return 0; - if (ret < 0) - return ret; - return 1; + return exists ? 1 : 0; }

/* diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 0486b1f91124..3bad7c0be1f1 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1420,6 +1420,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, free_extent_map(em); em = NULL;

+ /* + * Although the PageDirty bit might be cleared before entering + * this function, subpage dirty bit is not cleared. + * So clear subpage dirty bit here so next time we won't submit + * page for range already written to disk. + */ + btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize); btrfs_set_range_writeback(inode, cur, cur + iosize - 1); if (!PageWriteback(page)) { btrfs_err(inode->root->fs_info, @@ -1427,13 +1434,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, page->index, cur, end); }

- /* - * Although the PageDirty bit is cleared before entering this - * function, subpage dirty bit is not cleared. - * So clear subpage dirty bit here so next time we won't submit - * page for range already written to disk. - */ - btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);

submit_extent_page(bio_ctrl, disk_bytenr, page, iosize, cur - page_offset(page)); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index b4c9a6aa118c..6853f043c2c1 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -1065,8 +1065,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c return 0;

/* - * We want to be fast because we can be called from any path trying to - * allocate memory, so if the lock is busy we don't want to spend time + * We want to be fast so if the lock is busy we don't want to spend time * waiting for it - either some task is about to do IO for the inode or * we may have another task shrinking extent maps, here in this code, so * skip this inode. @@ -1109,9 +1108,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c /* * Stop if we need to reschedule or there's contention on the * lock. This is to avoid slowing other tasks trying to take the - * lock and because the shrinker might be called during a memory - * allocation path and we want to avoid taking a very long time - * and slowing down all sorts of tasks. + * lock. */ if (need_resched() || rwlock_needbreak(&tree->lock)) break; @@ -1139,12 +1136,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx if (ctx->scanned >= ctx->nr_to_scan) break;

- /* - * We may be called from memory allocation paths, so we don't - * want to take too much time and slowdown tasks. - */ - if (need_resched()) - break; + cond_resched();

inode = btrfs_find_first_inode(root, min_ino); } @@ -1202,14 +1194,12 @@ long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan) ctx.last_ino); }

- /* - * We may be called from memory allocation paths, so we don't want to - * take too much time and slowdown tasks, so stop if we need reschedule. - */ - while (ctx.scanned < ctx.nr_to_scan && !need_resched()) { + while (ctx.scanned < ctx.nr_to_scan) { struct btrfs_root *root; unsigned long count;

+ cond_resched(); + spin_lock(&fs_info->fs_roots_radix_lock); count = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)&root, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 62c3dea9572a..1926a228d0ba 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2698,15 +2698,16 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, u64 offset = bytenr - block_group->start; u64 to_free, to_unusable; int bg_reclaim_threshold = 0; - bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0)); + bool initial; u64 reclaimable_unusable;

- WARN_ON(!initial && offset + size > block_group->zone_capacity); + spin_lock(&block_group->lock);

+ initial = ((size == block_group->length) && (block_group->alloc_offset == 0)); + WARN_ON(!initial && offset + size > block_group->zone_capacity); if (!initial) bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold);

- spin_lock(&ctl->tree_lock); if (!used) to_free = size; else if (initial) @@ -2719,7 +2720,9 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, to_free = offset + size - block_group->alloc_offset; to_unusable = size - to_free;

+ spin_lock(&ctl->tree_lock); ctl->free_space += to_free; + spin_unlock(&ctl->tree_lock); /* * If the block group is read-only, we should account freed space into * bytes_readonly. @@ -2728,11 +2731,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, block_group->zone_unusable += to_unusable; WARN_ON(block_group->zone_unusable > block_group->length); } - spin_unlock(&ctl->tree_lock); if (!used) { - spin_lock(&block_group->lock); block_group->alloc_offset -= size; - spin_unlock(&block_group->lock); }

reclaimable_unusable = block_group->zone_unusable - @@ -2746,6 +2746,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, btrfs_mark_bg_to_reclaim(block_group); }

+ spin_unlock(&block_group->lock); + return 0; }

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 3dd4a48479a9..d1a04c0c576e 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6158,25 +6158,51 @@ static int send_write_or_clone(struct send_ctx *sctx, u64 offset = key->offset; u64 end; u64 bs = sctx->send_root->fs_info->sectorsize; + struct btrfs_file_extent_item *ei; + u64 disk_byte; + u64 data_offset; + u64 num_bytes; + struct btrfs_inode_info info = { 0 };

end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size); if (offset >= end) return 0;

- if (clone_root && IS_ALIGNED(end, bs)) { - struct btrfs_file_extent_item *ei; - u64 disk_byte; - u64 data_offset; + num_bytes = end - offset;

- ei = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_file_extent_item); - disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei); - data_offset = btrfs_file_extent_offset(path->nodes[0], ei); - ret = clone_range(sctx, path, clone_root, disk_byte, - data_offset, offset, end - offset); - } else { - ret = send_extent_data(sctx, path, offset, end - offset); - } + if (!clone_root) + goto write_data; + + if (IS_ALIGNED(end, bs)) + goto clone_data; + + /* + * If the extent end is not aligned, we can clone if the extent ends at + * the i_size of the inode and the clone range ends at the i_size of the + * source inode, otherwise the clone operation fails with -EINVAL. + */ + if (end != sctx->cur_inode_size) + goto write_data; + + ret = get_inode_info(clone_root->root, clone_root->ino, &info); + if (ret < 0) + return ret; + + if (clone_root->offset + num_bytes == info.size) + goto clone_data; + +write_data: + ret = send_extent_data(sctx, path, offset, num_bytes); + sctx->cur_inode_next_write_offset = end; + return ret; + +clone_data: + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei); + data_offset = btrfs_file_extent_offset(path->nodes[0], ei); + ret = clone_range(sctx, path, clone_root, disk_byte, data_offset, offset, + num_bytes); sctx->cur_inode_next_write_offset = end; return ret; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index f05cce7c8b8d..03107c01b287 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -28,6 +28,7 @@ #include <linux/btrfs.h> #include <linux/security.h> #include <linux/fs_parser.h> +#include <linux/swap.h> #include "messages.h" #include "delayed-inode.h" #include "ctree.h" @@ -2386,7 +2387,13 @@ static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_contro

trace_btrfs_extent_map_shrinker_count(fs_info, nr);

- return nr; + /* + * Only report the real number for DEBUG builds, as there are reports of + * serious performance degradation caused by too frequent shrinks. + */ + if (IS_ENABLED(CONFIG_BTRFS_DEBUG)) + return nr; + return 0; }

static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc) @@ -2394,6 +2401,15 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan); struct btrfs_fs_info *fs_info = btrfs_sb(sb);

+ /* + * We may be called from any task trying to allocate memory and we don't + * want to slow it down with scanning and dropping extent maps. It would + * also cause heavy lock contention if many tasks concurrently enter + * here. Therefore only allow kswapd tasks to scan and drop extent maps. + */ + if (!current_is_kswapd()) + return 0; + return btrfs_free_extent_maps(fs_info, nr_to_scan); }

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index a2c3651a3d8f..897e19790522 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -551,9 +551,10 @@ static int check_dir_item(struct extent_buffer *leaf,

/* dir type check */ dir_type = btrfs_dir_ftype(leaf, di); - if (unlikely(dir_type >= BTRFS_FT_MAX)) { + if (unlikely(dir_type <= BTRFS_FT_UNKNOWN || + dir_type >= BTRFS_FT_MAX)) { dir_item_err(leaf, slot, - "invalid dir item type, have %u expect [0, %u)", + "invalid dir item type, have %u expect (0, %u)", dir_type, BTRFS_FT_MAX); return -EUCLEAN; } @@ -1717,6 +1718,72 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf, return 0; }

+static int check_dev_extent_item(const struct extent_buffer *leaf, + const struct btrfs_key *key, + int slot, + struct btrfs_key *prev_key) +{ + struct btrfs_dev_extent *de; + const u32 sectorsize = leaf->fs_info->sectorsize; + + de = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent); + /* Basic fixed member checks. */ + if (unlikely(btrfs_dev_extent_chunk_tree(leaf, de) != + BTRFS_CHUNK_TREE_OBJECTID)) { + generic_err(leaf, slot, + "invalid dev extent chunk tree id, has %llu expect %llu", + btrfs_dev_extent_chunk_tree(leaf, de), + BTRFS_CHUNK_TREE_OBJECTID); + return -EUCLEAN; + } + if (unlikely(btrfs_dev_extent_chunk_objectid(leaf, de) != + BTRFS_FIRST_CHUNK_TREE_OBJECTID)) { + generic_err(leaf, slot, + "invalid dev extent chunk objectid, has %llu expect %llu", + btrfs_dev_extent_chunk_objectid(leaf, de), + BTRFS_FIRST_CHUNK_TREE_OBJECTID); + return -EUCLEAN; + } + /* Alignment check. */ + if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) { + generic_err(leaf, slot, + "invalid dev extent key.offset, has %llu not aligned to %u", + key->offset, sectorsize); + return -EUCLEAN; + } + if (unlikely(!IS_ALIGNED(btrfs_dev_extent_chunk_offset(leaf, de), + sectorsize))) { + generic_err(leaf, slot, + "invalid dev extent chunk offset, has %llu not aligned to %u", + btrfs_dev_extent_chunk_objectid(leaf, de), + sectorsize); + return -EUCLEAN; + } + if (unlikely(!IS_ALIGNED(btrfs_dev_extent_length(leaf, de), + sectorsize))) { + generic_err(leaf, slot, + "invalid dev extent length, has %llu not aligned to %u", + btrfs_dev_extent_length(leaf, de), sectorsize); + return -EUCLEAN; + } + /* Overlap check with previous dev extent. */ + if (slot && prev_key->objectid == key->objectid && + prev_key->type == key->type) { + struct btrfs_dev_extent *prev_de; + u64 prev_len; + + prev_de = btrfs_item_ptr(leaf, slot - 1, struct btrfs_dev_extent); + prev_len = btrfs_dev_extent_length(leaf, prev_de); + if (unlikely(prev_key->offset + prev_len > key->offset)) { + generic_err(leaf, slot, + "dev extent overlap, prev offset %llu len %llu current offset %llu", + prev_key->objectid, prev_len, key->offset); + return -EUCLEAN; + } + } + return 0; +} + /* * Common point to switch the item-specific validation. */ @@ -1753,6 +1820,9 @@ static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf, case BTRFS_DEV_ITEM_KEY: ret = check_dev_item(leaf, key, slot); break; + case BTRFS_DEV_EXTENT_KEY: + ret = check_dev_extent_item(leaf, key, slot, prev_key); + break; case BTRFS_INODE_ITEM_KEY: ret = check_inode_item(leaf, key, slot); break; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c16bc5250ef..73b5a07bf94d 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -498,6 +498,11 @@ const struct netfs_request_ops ceph_netfs_ops = { };

#ifdef CONFIG_CEPH_FSCACHE +static void ceph_set_page_fscache(struct page *page) +{ + folio_start_private_2(page_folio(page)); /* [DEPRECATED] */ +} + static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async) { struct inode *inode = priv; @@ -515,6 +520,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b ceph_fscache_write_terminated, inode, true, caching); } #else +static inline void ceph_set_page_fscache(struct page *page) +{ +} + static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) { } @@ -706,6 +715,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) len = wlen;

set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); ceph_fscache_write_to_cache(inode, page_off, len, caching);

if (IS_ENCRYPTED(inode)) { @@ -789,6 +800,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) return AOP_WRITEPAGE_ACTIVATE; }

+ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ + err = writepage_nounlock(page, wbc); if (err == -ERESTARTSYS) { /* direct memory reclaimer was killed by SIGKILL. return 0 @@ -1062,7 +1075,8 @@ static int ceph_writepages_start(struct address_space *mapping, unlock_page(page); break; } - if (PageWriteback(page)) { + if (PageWriteback(page) || + PagePrivate2(page) /* [DEPRECATED] */) { if (wbc->sync_mode == WB_SYNC_NONE) { doutc(cl, "%p under writeback\n", page); unlock_page(page); @@ -1070,6 +1084,7 @@ static int ceph_writepages_start(struct address_space *mapping, } doutc(cl, "waiting on writeback %p\n", page); wait_on_page_writeback(page); + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ }

if (!clear_page_dirty_for_io(page)) { @@ -1254,6 +1269,8 @@ static int ceph_writepages_start(struct address_space *mapping, }

set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); len += thp_size(page); } ceph_fscache_write_to_cache(inode, offset, len, caching); diff --git a/fs/file.c b/fs/file.c index a11e59b5d602..655338effe9c 100644 --- a/fs/file.c +++ b/fs/file.c @@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu) #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long))

+#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ -static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, - unsigned int count) +static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, + unsigned int copy_words) { - unsigned int cpy, set; - - cpy = count / BITS_PER_BYTE; - set = (nfdt->max_fds - count) / BITS_PER_BYTE; - memcpy(nfdt->open_fds, ofdt->open_fds, cpy); - memset((char *)nfdt->open_fds + cpy, 0, set); - memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); - memset((char *)nfdt->close_on_exec + cpy, 0, set); - - cpy = BITBIT_SIZE(count); - set = BITBIT_SIZE(nfdt->max_fds) - cpy; - memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); - memset((char *)nfdt->full_fds_bits + cpy, 0, set); + unsigned int nwords = fdt_words(nfdt); + + bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, + copy_words, nwords); }

/* @@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set);

- copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); + copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); }

/* @@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int open_files = sane_fdtable_size(old_fdt, max_fds); }

- copy_fd_bitmaps(new_fdt, old_fdt, open_files); + copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);

old_fds = old_fdt->fd; new_fds = new_fdt->fd; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 9eb191b5c4de..7146038b2fe7 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1618,9 +1618,11 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,

this_num = min_t(unsigned, num, PAGE_SIZE - offset); err = fuse_copy_page(cs, &page, offset, this_num, 0); - if (!err && offset == 0 && - (this_num == PAGE_SIZE || file_size == end)) + if (!PageUptodate(page) && !err && offset == 0 && + (this_num == PAGE_SIZE || file_size == end)) { + zero_user_segment(page, this_num, PAGE_SIZE); SetPageUptodate(page); + } unlock_page(page); put_page(page);

diff --git a/fs/inode.c b/fs/inode.c index 3a41f83a4ba5..f5add7222c98 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -486,6 +486,39 @@ static void inode_lru_list_del(struct inode *inode) this_cpu_dec(nr_unused); }

+static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -655,6 +688,8 @@ static void evict(struct inode *inode)

inode_sb_list_del(inode);

+ inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -843,7 +878,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } diff --git a/fs/libfs.c b/fs/libfs.c index b635ee5adbcc..65279e53fbf2 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -450,6 +450,14 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); }

+static int offset_dir_open(struct inode *inode, struct file *file) +{ + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + + file->private_data = (void *)ctx->next_offset; + return 0; +} + /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -463,6 +471,9 @@ void simple_offset_destroy(struct offset_ctx *octx) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { + struct inode *inode = file->f_inode; + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -476,7 +487,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) }

/* In this case, ->private_data is protected by f_pos_lock */ - file->private_data = NULL; + if (!offset) + file->private_data = (void *)ctx->next_offset; return vfs_setpos(file, offset, LONG_MAX); }

@@ -507,7 +519,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) inode->i_ino, fs_umode_to_dtype(inode->i_mode)); }

-static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) +static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) { struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; @@ -515,17 +527,21 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) while (true) { dentry = offset_find_next(octx, ctx->pos); if (!dentry) - return ERR_PTR(-ENOENT); + return; + + if (dentry2offset(dentry) >= last_index) { + dput(dentry); + return; + }

if (!offset_dir_emit(ctx, dentry)) { dput(dentry); - break; + return; }

ctx->pos = dentry2offset(dentry) + 1; dput(dentry); } - return NULL; }

/** @@ -552,22 +568,19 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; + long last_index = (long)file->private_data;

lockdep_assert_held(&d_inode(dir)->i_rwsem);

if (!dir_emit_dots(file, ctx)) return 0;

- /* In this case, ->private_data is protected by f_pos_lock */ - if (ctx->pos == DIR_OFFSET_MIN) - file->private_data = NULL; - else if (file->private_data == ERR_PTR(-ENOENT)) - return 0; - file->private_data = offset_iterate_dir(d_inode(dir), ctx); + offset_iterate_dir(d_inode(dir), ctx, last_index); return 0; }

const struct file_operations simple_offset_dir_operations = { + .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, diff --git a/fs/locks.c b/fs/locks.c index 9afb16e0683f..e45cad40f8b6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2984,7 +2984,7 @@ static int __init filelock_init(void) filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL);

- filelease_cache = kmem_cache_create("file_lock_cache", + filelease_cache = kmem_cache_create("file_lease_cache", sizeof(struct file_lease), 0, SLAB_PANIC, NULL);

for_each_possible_cpu(i) { diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 4c0401dbbfcf..9aa045e2ab0a 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -466,7 +466,7 @@ int netfs_write_begin(struct netfs_inode *ctx, if (!netfs_is_cache_enabled(ctx) && netfs_skip_folio_read(folio, pos, len, false)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio; + goto have_folio_no_wait; }

rreq = netfs_alloc_request(mapping, file, @@ -507,6 +507,12 @@ int netfs_write_begin(struct netfs_inode *ctx, netfs_put_request(rreq, false, netfs_rreq_trace_put_return);

have_folio: + if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) { + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; + } +have_folio_no_wait: *_folio = folio; kleave(" = 0"); return 0; diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index ecbc99ec7d36..18055c1e0183 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -184,7 +184,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; - size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; + size_t max_chunk = mapping_max_folio_size(mapping); bool maybe_trouble = false;

if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) || diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c index 4d1e8bf4c615..431a1905fcb4 100644 --- a/fs/netfs/fscache_cookie.c +++ b/fs/netfs/fscache_cookie.c @@ -741,6 +741,10 @@ static void fscache_cookie_state_machine(struct fscache_cookie *cookie) spin_lock(&cookie->lock); } if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) { + if (atomic_read(&cookie->n_accesses) != 0) + /* still being accessed: postpone it */ + break; + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_LRU_DISCARDING); wake = true; diff --git a/fs/netfs/io.c b/fs/netfs/io.c index c7576481c321..f3abc5dfdbc0 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -98,6 +98,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); }

+/* + * [DEPRECATED] Deal with the completion of writing the data to the cache. We + * have to clear the PG_fscache bits on the folios involved and release the + * caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + if (xas_retry(&xas, folio)) + continue; + + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio->index <= unlocked) + continue; + unlocked = folio_next_index(folio) - 1; + trace_netfs_folio(folio, netfs_folio_trace_end_copy); + folio_end_private_2(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) /* [DEPRECATED] */ +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref + * from the caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + subreq->len, rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */ +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */ +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + /* * Handle a short read. */ @@ -275,6 +415,10 @@ static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async) clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);

+ if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) && + test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + netfs_rreq_completed(rreq, was_async); }

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index d4bcc7da700c..0a271b9fbc62 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -290,7 +290,7 @@ struct smb_version_operations { int (*check_receive)(struct mid_q_entry *, struct TCP_Server_Info *, bool); void (*add_credits)(struct TCP_Server_Info *server, - const struct cifs_credits *credits, + struct cifs_credits *credits, const int optype); void (*set_credits)(struct TCP_Server_Info *, const int); int * (*get_credits_field)(struct TCP_Server_Info *, const int); @@ -550,8 +550,8 @@ struct smb_version_operations { size_t *, struct cifs_credits *); /* adjust previously taken mtu credits to request size */ int (*adjust_credits)(struct TCP_Server_Info *server, - struct cifs_credits *credits, - const unsigned int payload_size); + struct cifs_io_subrequest *subreq, + unsigned int /*enum smb3_rw_credits_trace*/ trace); /* check if we need to issue closedir */ bool (*dir_needs_close)(struct cifsFileInfo *); long (*fallocate)(struct file *, struct cifs_tcon *, int, loff_t, @@ -848,6 +848,9 @@ static inline void cifs_server_unlock(struct TCP_Server_Info *server) struct cifs_credits { unsigned int value; unsigned int instance; + unsigned int in_flight_check; + unsigned int rreq_debug_id; + unsigned int rreq_debug_index; };

static inline unsigned int @@ -873,7 +876,7 @@ has_credits(struct TCP_Server_Info *server, int *credits, int num_credits) }

static inline void -add_credits(struct TCP_Server_Info *server, const struct cifs_credits *credits, +add_credits(struct TCP_Server_Info *server, struct cifs_credits *credits, const int optype) { server->ops->add_credits(server, credits, optype); @@ -897,11 +900,11 @@ set_credits(struct TCP_Server_Info *server, const int val) }

static inline int -adjust_credits(struct TCP_Server_Info *server, struct cifs_credits *credits, - const unsigned int payload_size) +adjust_credits(struct TCP_Server_Info *server, struct cifs_io_subrequest *subreq, + unsigned int /* enum smb3_rw_credits_trace */ trace) { return server->ops->adjust_credits ? - server->ops->adjust_credits(server, credits, payload_size) : 0; + server->ops->adjust_credits(server, subreq, trace) : 0; }

static inline __le64 diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 04ec1b9737a8..b202eac6584e 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -80,6 +80,16 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq) return netfs_prepare_write_failed(subreq); }

+ wdata->credits.rreq_debug_id = subreq->rreq->debug_id; + wdata->credits.rreq_debug_index = subreq->debug_index; + wdata->credits.in_flight_check = 1; + trace_smb3_rw_credits(wdata->rreq->debug_id, + wdata->subreq.debug_index, + wdata->credits.value, + server->credits, server->in_flight, + wdata->credits.value, + cifs_trace_rw_credits_write_prepare); + #ifdef CONFIG_CIFS_SMB_DIRECT if (server->smbd_conn) subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; @@ -101,7 +111,7 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq) goto fail; }

- rc = adjust_credits(wdata->server, &wdata->credits, wdata->subreq.len); + rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust); if (rc) goto fail;

@@ -163,7 +173,18 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq) return false; }

+ rdata->credits.in_flight_check = 1; + rdata->credits.rreq_debug_id = rreq->debug_id; + rdata->credits.rreq_debug_index = subreq->debug_index; + + trace_smb3_rw_credits(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->credits.value, + server->credits, server->in_flight, 0, + cifs_trace_rw_credits_read_submit); + subreq->len = min_t(size_t, subreq->len, rsize); + #ifdef CONFIG_CIFS_SMB_DIRECT if (server->smbd_conn) subreq->max_nr_segs = server->smbd_conn->max_frmr_depth; @@ -294,7 +315,20 @@ static void cifs_free_subrequest(struct netfs_io_subrequest *subreq) #endif }

- add_credits_and_wake_if(rdata->server, &rdata->credits, 0); + if (rdata->credits.value != 0) { + trace_smb3_rw_credits(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->credits.value, + rdata->server ? rdata->server->credits : 0, + rdata->server ? rdata->server->in_flight : 0, + -rdata->credits.value, + cifs_trace_rw_credits_free_subreq); + if (rdata->server) + add_credits_and_wake_if(rdata->server, &rdata->credits, 0); + else + rdata->credits.value = 0; + } + if (rdata->have_xid) free_xid(rdata->xid); } @@ -2719,6 +2753,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file->f_mapping->host; struct cifsInodeInfo *cinode = CIFS_I(inode); struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); ssize_t rc;

rc = netfs_start_io_write(inode); @@ -2735,12 +2770,16 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) if (rc <= 0) goto out;

- if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from), + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) && + (cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from), server->vals->exclusive_lock_type, 0, - NULL, CIFS_WRITE_OP)) - rc = netfs_buffered_write_iter_locked(iocb, from, NULL); - else + NULL, CIFS_WRITE_OP))) { rc = -EACCES; + goto out; + } + + rc = netfs_buffered_write_iter_locked(iocb, from, NULL); + out: up_read(&cinode->lock_sem); netfs_end_io_write(inode); @@ -2872,9 +2911,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to) if (!CIFS_CACHE_READ(cinode)) return netfs_unbuffered_read_iter(iocb, to);

- if (cap_unix(tcon->ses) && - (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) { if (iocb->ki_flags & IOCB_DIRECT) return netfs_unbuffered_read_iter(iocb, to); return netfs_buffered_read_iter(iocb, to); diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 689d8a506d45..48c27581ec51 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -378,6 +378,8 @@ int parse_reparse_point(struct reparse_data_buffer *buf, u32 plen, struct cifs_sb_info *cifs_sb, bool unicode, struct cifs_open_info_data *data) { + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + data->reparse.buf = buf;

/* See MS-FSCC 2.1.2 */ @@ -394,12 +396,13 @@ int parse_reparse_point(struct reparse_data_buffer *buf, case IO_REPARSE_TAG_LX_FIFO: case IO_REPARSE_TAG_LX_CHR: case IO_REPARSE_TAG_LX_BLK: - return 0; + break; default: - cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n", - __func__, le32_to_cpu(buf->ReparseTag)); - return -EOPNOTSUPP; + cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n", + le32_to_cpu(buf->ReparseTag)); + break; } + return 0; }

int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 212ec6f66ec6..e1f2feb56f45 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -108,7 +108,7 @@ cifs_find_mid(struct TCP_Server_Info *server, char *buffer)

static void cifs_add_credits(struct TCP_Server_Info *server, - const struct cifs_credits *credits, const int optype) + struct cifs_credits *credits, const int optype) { spin_lock(&server->req_lock); server->credits += credits->value; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index c8e536540895..7fe59235f090 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -66,7 +66,7 @@ change_conf(struct TCP_Server_Info *server)

static void smb2_add_credits(struct TCP_Server_Info *server, - const struct cifs_credits *credits, const int optype) + struct cifs_credits *credits, const int optype) { int *val, rc = -1; int scredits, in_flight; @@ -94,7 +94,21 @@ smb2_add_credits(struct TCP_Server_Info *server, server->conn_id, server->hostname, *val, add, server->in_flight); } - WARN_ON_ONCE(server->in_flight == 0); + if (credits->in_flight_check > 1) { + pr_warn_once("rreq R=%08x[%x] Credits not in flight\n", + credits->rreq_debug_id, credits->rreq_debug_index); + } else { + credits->in_flight_check = 2; + } + if (WARN_ON_ONCE(server->in_flight == 0)) { + pr_warn_once("rreq R=%08x[%x] Zero in_flight\n", + credits->rreq_debug_id, credits->rreq_debug_index); + trace_smb3_rw_credits(credits->rreq_debug_id, + credits->rreq_debug_index, + credits->value, + server->credits, server->in_flight, 0, + cifs_trace_rw_credits_zero_in_flight); + } server->in_flight--; if (server->in_flight == 0 && ((optype & CIFS_OP_MASK) != CIFS_NEG_OP) && @@ -283,16 +297,23 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, size_t size,

static int smb2_adjust_credits(struct TCP_Server_Info *server, - struct cifs_credits *credits, - const unsigned int payload_size) + struct cifs_io_subrequest *subreq, + unsigned int /*enum smb3_rw_credits_trace*/ trace) { - int new_val = DIV_ROUND_UP(payload_size, SMB2_MAX_BUFFER_SIZE); + struct cifs_credits *credits = &subreq->credits; + int new_val = DIV_ROUND_UP(subreq->subreq.len, SMB2_MAX_BUFFER_SIZE); int scredits, in_flight;

if (!credits->value || credits->value == new_val) return 0;

if (credits->value < new_val) { + trace_smb3_rw_credits(subreq->rreq->debug_id, + subreq->subreq.debug_index, + credits->value, + server->credits, server->in_flight, + new_val - credits->value, + cifs_trace_rw_credits_no_adjust_up); trace_smb3_too_many_credits(server->CurrentMid, server->conn_id, server->hostname, 0, credits->value - new_val, 0); cifs_server_dbg(VFS, "request has less credits (%d) than required (%d)", @@ -308,6 +329,12 @@ smb2_adjust_credits(struct TCP_Server_Info *server, in_flight = server->in_flight; spin_unlock(&server->req_lock);

+ trace_smb3_rw_credits(subreq->rreq->debug_id, + subreq->subreq.debug_index, + credits->value, + server->credits, server->in_flight, + new_val - credits->value, + cifs_trace_rw_credits_old_session); trace_smb3_reconnect_detected(server->CurrentMid, server->conn_id, server->hostname, scredits, credits->value - new_val, in_flight); @@ -316,6 +343,11 @@ smb2_adjust_credits(struct TCP_Server_Info *server, return -EAGAIN; }

+ trace_smb3_rw_credits(subreq->rreq->debug_id, + subreq->subreq.debug_index, + credits->value, + server->credits, server->in_flight, + new_val - credits->value, trace); server->credits += credits->value - new_val; scredits = server->credits; in_flight = server->in_flight; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 896147ba6660..4cd5c33be2a1 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4505,8 +4505,15 @@ smb2_readv_callback(struct mid_q_entry *mid) struct TCP_Server_Info *server = rdata->server; struct smb2_hdr *shdr = (struct smb2_hdr *)rdata->iov[0].iov_base; - struct cifs_credits credits = { .value = 0, .instance = 0 }; + struct cifs_credits credits = { + .value = 0, + .instance = 0, + .rreq_debug_id = rdata->rreq->debug_id, + .rreq_debug_index = rdata->subreq.debug_index, + }; struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 }; + unsigned int rreq_debug_id = rdata->rreq->debug_id; + unsigned int subreq_debug_index = rdata->subreq.debug_index;

if (rdata->got_bytes) { rqst.rq_iter = rdata->subreq.io_iter; @@ -4590,10 +4597,16 @@ smb2_readv_callback(struct mid_q_entry *mid) if (rdata->subreq.start < rdata->subreq.rreq->i_size) rdata->result = 0; } + trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, + server->credits, server->in_flight, + 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; INIT_WORK(&rdata->subreq.work, smb2_readv_worker); queue_work(cifsiod_wq, &rdata->subreq.work); release_mid(mid); + trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, + server->credits, server->in_flight, + credits.value, cifs_trace_rw_credits_read_response_add); add_credits(server, &credits, 0); }

@@ -4650,7 +4663,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata) min_t(int, server->max_credits - server->credits, credit_request));

- rc = adjust_credits(server, &rdata->credits, rdata->subreq.len); + rc = adjust_credits(server, rdata, cifs_trace_rw_credits_call_readv_adjust); if (rc) goto async_readv_out;

@@ -4769,7 +4782,14 @@ smb2_writev_callback(struct mid_q_entry *mid) struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink); struct TCP_Server_Info *server = wdata->server; struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf; - struct cifs_credits credits = { .value = 0, .instance = 0 }; + struct cifs_credits credits = { + .value = 0, + .instance = 0, + .rreq_debug_id = wdata->rreq->debug_id, + .rreq_debug_index = wdata->subreq.debug_index, + }; + unsigned int rreq_debug_id = wdata->rreq->debug_id; + unsigned int subreq_debug_index = wdata->subreq.debug_index; ssize_t result = 0; size_t written;

@@ -4840,9 +4860,15 @@ smb2_writev_callback(struct mid_q_entry *mid) tcon->tid, tcon->ses->Suid, wdata->subreq.start, wdata->subreq.len);

+ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, wdata->credits.value, + server->credits, server->in_flight, + 0, cifs_trace_rw_credits_write_response_clear); wdata->credits.value = 0; cifs_write_subrequest_terminated(wdata, result ?: written, true); release_mid(mid); + trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, + server->credits, server->in_flight, + credits.value, cifs_trace_rw_credits_write_response_add); add_credits(server, &credits, 0); }

@@ -4972,7 +4998,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) min_t(int, server->max_credits - server->credits, credit_request));

- rc = adjust_credits(server, &wdata->credits, io_parms->length); + rc = adjust_credits(server, wdata, cifs_trace_rw_credits_call_writev_adjust); if (rc) goto async_writev_out;

@@ -4997,6 +5023,12 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) cifs_small_buf_release(req); out: if (rc) { + trace_smb3_rw_credits(wdata->rreq->debug_id, + wdata->subreq.debug_index, + wdata->credits.value, + server->credits, server->in_flight, + -(int)wdata->credits.value, + cifs_trace_rw_credits_write_response_clear); add_credits_and_wake_if(wdata->server, &wdata->credits, 0); cifs_write_subrequest_terminated(wdata, rc, true); } diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 36d47ce59631..36d5295c2a6f 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -20,6 +20,22 @@ /* * Specify enums for tracing information. */ +#define smb3_rw_credits_traces \ + EM(cifs_trace_rw_credits_call_readv_adjust, "rd-call-adj") \ + EM(cifs_trace_rw_credits_call_writev_adjust, "wr-call-adj") \ + EM(cifs_trace_rw_credits_free_subreq, "free-subreq") \ + EM(cifs_trace_rw_credits_issue_read_adjust, "rd-issu-adj") \ + EM(cifs_trace_rw_credits_issue_write_adjust, "wr-issu-adj") \ + EM(cifs_trace_rw_credits_no_adjust_up, "no-adj-up ") \ + EM(cifs_trace_rw_credits_old_session, "old-session") \ + EM(cifs_trace_rw_credits_read_response_add, "rd-resp-add") \ + EM(cifs_trace_rw_credits_read_response_clear, "rd-resp-clr") \ + EM(cifs_trace_rw_credits_read_submit, "rd-submit ") \ + EM(cifs_trace_rw_credits_write_prepare, "wr-prepare ") \ + EM(cifs_trace_rw_credits_write_response_add, "wr-resp-add") \ + EM(cifs_trace_rw_credits_write_response_clear, "wr-resp-clr") \ + E_(cifs_trace_rw_credits_zero_in_flight, "ZERO-IN-FLT") + #define smb3_tcon_ref_traces \ EM(netfs_trace_tcon_ref_dec_dfs_refer, "DEC DfsRef") \ EM(netfs_trace_tcon_ref_free, "FRE ") \ @@ -59,7 +75,8 @@ #define EM(a, b) a, #define E_(a, b) a

-enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte); +enum smb3_rw_credits_trace { smb3_rw_credits_traces } __mode(byte); +enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);

#undef EM #undef E_ @@ -71,6 +88,7 @@ enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte); #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a);

+smb3_rw_credits_traces; smb3_tcon_ref_traces;

#undef EM @@ -1316,6 +1334,41 @@ TRACE_EVENT(smb3_tcon_ref, __entry->ref) );

+TRACE_EVENT(smb3_rw_credits, + TP_PROTO(unsigned int rreq_debug_id, + unsigned int subreq_debug_index, + unsigned int subreq_credits, + unsigned int server_credits, + int server_in_flight, + int credit_change, + enum smb3_rw_credits_trace trace), + TP_ARGS(rreq_debug_id, subreq_debug_index, subreq_credits, + server_credits, server_in_flight, credit_change, trace), + TP_STRUCT__entry( + __field(unsigned int, rreq_debug_id) + __field(unsigned int, subreq_debug_index) + __field(unsigned int, subreq_credits) + __field(unsigned int, server_credits) + __field(int, in_flight) + __field(int, credit_change) + __field(enum smb3_rw_credits_trace, trace) + ), + TP_fast_assign( + __entry->rreq_debug_id = rreq_debug_id; + __entry->subreq_debug_index = subreq_debug_index; + __entry->subreq_credits = subreq_credits; + __entry->server_credits = server_credits; + __entry->in_flight = server_in_flight; + __entry->credit_change = credit_change; + __entry->trace = trace; + ), + TP_printk("R=%08x[%x] %s cred=%u chg=%d pool=%u ifl=%d", + __entry->rreq_debug_id, __entry->subreq_debug_index, + __print_symbolic(__entry->trace, smb3_rw_credits_traces), + __entry->subreq_credits, __entry->credit_change, + __entry->server_credits, __entry->in_flight) + ); +

#undef EM #undef E_ diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 012b9bd06995..adfe0d058701 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -988,10 +988,10 @@ static void cifs_compound_callback(struct mid_q_entry *mid) { struct TCP_Server_Info *server = mid->server; - struct cifs_credits credits; - - credits.value = server->ops->get_credits(mid); - credits.instance = server->reconnect_instance; + struct cifs_credits credits = { + .value = server->ops->get_credits(mid), + .instance = server->reconnect_instance, + };

add_credits(server, &credits, mid->optype);

diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 09e1e7771592..7889df8112b4 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -165,11 +165,43 @@ void ksmbd_all_conn_set_status(u64 sess_id, u32 status) up_read(&conn_list_lock); }

-void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id) +void ksmbd_conn_wait_idle(struct ksmbd_conn *conn) { wait_event(conn->req_running_q, atomic_read(&conn->req_running) < 2); }

+int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id) +{ + struct ksmbd_conn *conn; + int rc, retry_count = 0, max_timeout = 120; + int rcount = 1; + +retry_idle: + if (retry_count >= max_timeout) + return -EIO; + + down_read(&conn_list_lock); + list_for_each_entry(conn, &conn_list, conns_list) { + if (conn->binding || xa_load(&conn->sessions, sess_id)) { + if (conn == curr_conn) + rcount = 2; + if (atomic_read(&conn->req_running) >= rcount) { + rc = wait_event_timeout(conn->req_running_q, + atomic_read(&conn->req_running) < rcount, + HZ); + if (!rc) { + up_read(&conn_list_lock); + retry_count++; + goto retry_idle; + } + } + } + } + up_read(&conn_list_lock); + + return 0; +} + int ksmbd_conn_write(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 0e04cf8b1d89..b93e5437793e 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -145,7 +145,8 @@ extern struct list_head conn_list; extern struct rw_semaphore conn_list_lock;

bool ksmbd_conn_alive(struct ksmbd_conn *conn); -void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id); +void ksmbd_conn_wait_idle(struct ksmbd_conn *conn); +int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id); struct ksmbd_conn *ksmbd_conn_alloc(void); void ksmbd_conn_free(struct ksmbd_conn *conn); bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c); diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index aec0a7a12405..dac5f984f175 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -310,6 +310,7 @@ void destroy_previous_session(struct ksmbd_conn *conn, { struct ksmbd_session *prev_sess; struct ksmbd_user *prev_user; + int err;

down_write(&sessions_table_lock); down_write(&conn->session_lock); @@ -324,8 +325,15 @@ void destroy_previous_session(struct ksmbd_conn *conn, memcmp(user->passkey, prev_user->passkey, user->passkey_sz)) goto out;

+ ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_RECONNECT); + err = ksmbd_conn_wait_idle_sess_id(conn, id); + if (err) { + ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE); + goto out; + } ksmbd_destroy_file_table(&prev_sess->file_table); prev_sess->state = SMB2_SESSION_EXPIRED; + ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE); out: up_write(&conn->session_lock); up_write(&sessions_table_lock); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 840c71c66b30..8cfdf0d1a186 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2210,7 +2210,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_conn_unlock(conn);

ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn, sess_id); + ksmbd_conn_wait_idle(conn);

/* * Re-lookup session to validate if session is deleted @@ -4406,7 +4406,8 @@ int smb2_query_dir(struct ksmbd_work *work) rsp->OutputBufferLength = cpu_to_le32(0); rsp->Buffer[0] = 0; rc = ksmbd_iov_pin_rsp(work, (void *)rsp, - sizeof(struct smb2_query_directory_rsp)); + offsetof(struct smb2_query_directory_rsp, Buffer) + + 1); if (rc) goto err_out; } else { diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 80dc36f9d527..9f1c1d225e32 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -660,12 +660,9 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status void *context)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_execute_reg_methods(acpi_handle device, + u32 nax_depth, acpi_adr_space_type space_id)) -ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_execute_orphan_reg_method(acpi_handle device, - acpi_adr_space_type - space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_remove_address_space_handler(acpi_handle device, diff --git a/include/acpi/video.h b/include/acpi/video.h index 3d538d4178ab..044c463138df 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -50,6 +50,7 @@ enum acpi_backlight_type { acpi_backlight_native, acpi_backlight_nvidia_wmi_ec, acpi_backlight_apple_gmux, + acpi_backlight_dell_uart, };

#if IS_ENABLED(CONFIG_ACPI_VIDEO) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 70bf1004076b..f00a8e18f389 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -451,30 +451,11 @@ #endif #endif

-/* - * Some symbol definitions will not exist yet during the first pass of the - * link, but are guaranteed to exist in the final link. Provide preliminary - * definitions that will be superseded in the final link to avoid having to - * rely on weak external linkage, which requires a GOT when used in position - * independent code. - */ -#define PRELIMINARY_SYMBOL_DEFINITIONS \ - PROVIDE(kallsyms_addresses = .); \ - PROVIDE(kallsyms_offsets = .); \ - PROVIDE(kallsyms_names = .); \ - PROVIDE(kallsyms_num_syms = .); \ - PROVIDE(kallsyms_relative_base = .); \ - PROVIDE(kallsyms_token_table = .); \ - PROVIDE(kallsyms_token_index = .); \ - PROVIDE(kallsyms_markers = .); \ - PROVIDE(kallsyms_seqs_of_names = .); - /* * Read only Data */ #define RO_DATA(align) \ . = ALIGN((align)); \ - PRELIMINARY_SYMBOL_DEFINITIONS \ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ __start_rodata = .; \ *(.rodata) *(.rodata.*) \ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 8c4768c44a01..d3b66d77df7a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); }

+static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ff2a6cdb1fa3..5db4a3f35480 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -846,8 +846,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; }

static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index dca2969015d8..6fbfbde68a37 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,8 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H

+#include <linux/if_bridge.h> +#include <linux/if_vlan.h> #include <linux/kthread.h> #include <linux/packing.h> #include <linux/skbuff.h> @@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) return rew_op; }

+/** + * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame + * @skb: Pointer to socket buffer + * @br: Pointer to bridge device that the port is under, if any + * @vlan_tci: + * @tag_type: + * + * If the port is under a VLAN-aware bridge, remove the VLAN header from the + * payload and move it into the DSA tag, which will make the switch classify + * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, + * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not + * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()). + * Anyway, VID 0 is fine because it is stripped on egress for these port modes, + * and source address learning is not performed for packets injected from the + * CPU anyway, so it doesn't matter that the VID is "wrong". + */ +static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb, + struct net_device *br, + u64 *vlan_tci, u64 *tag_type) +{ + struct vlan_ethhdr *hdr; + u16 proto, tci; + + if (!br || !br_vlan_enabled(br)) { + *vlan_tci = 0; + *tag_type = IFH_TAG_TYPE_C; + return; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + br_vlan_get_proto(br, &proto); + + if (ntohs(hdr->h_vlan_proto) == proto) { + vlan_remove_tag(skb, &tci); + *vlan_tci = tci; + } else { + rcu_read_lock(); + br_vlan_get_pvid_rcu(br, &tci); + rcu_read_unlock(); + *vlan_tci = tci; + } + + *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; +} + #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 93ac1a859d69..36b9e8743922 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2370,6 +2370,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2393,6 +2396,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING)

#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8120d1976188..18cf440866d9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -967,10 +967,37 @@ static inline bool htlb_allow_alloc_fallback(int reason) static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { - if (huge_page_size(h) == PMD_SIZE) + const unsigned long size = huge_page_size(h); + + VM_WARN_ON(size == PAGE_SIZE); + + /* + * hugetlb must use the exact same PT locks as core-mm page table + * walkers would. When modifying a PTE table, hugetlb must take the + * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD + * PT lock etc. + * + * The expectation is that any hugetlb folio smaller than a PMD is + * always mapped into a single PTE table and that any hugetlb folio + * smaller than a PUD (but at least as big as a PMD) is always mapped + * into a single PMD table. + * + * If that does not hold for an architecture, then that architecture + * must disable split PT locks such that all *_lockptr() functions + * will give us the same result: the per-MM PT lock. + * + * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where + * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() + * and core-mm would use pmd_lockptr(). However, in such configurations + * split PMD locks are disabled -- they don't make sense on a single + * PGDIR page table -- and the end result is the same. + */ + if (size >= PUD_SIZE) + return pud_lockptr(mm, (pud_t *) pte); + else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); - return &mm->page_table_lock; + /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ + return ptep_lockptr(mm, pte); }

#ifndef hugepages_supported diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 7abdc0927124..b18e998c8b88 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -410,7 +410,7 @@ struct io_ring_ctx { spinlock_t napi_lock; /* napi_list lock */

/* napi busy poll default timeout */ - unsigned int napi_busy_poll_to; + ktime_t napi_busy_poll_dt; bool napi_prefer_busy_poll; bool napi_enabled;

diff --git a/include/linux/mm.h b/include/linux/mm.h index b58bad248eef..f32177152921 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2960,6 +2960,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); }

+static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); + BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); + return ptlock_ptr(virt_to_ptdesc(pte)); +} + static inline bool ptlock_init(struct ptdesc *ptdesc) { /* @@ -2984,6 +2991,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + return &mm->page_table_lock; +} static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} diff --git a/include/linux/panic.h b/include/linux/panic.h index 6717b15e798c..556b4e2ad9aa 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -16,6 +16,7 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void);

+extern bool panic_triggering_all_cpu_backtrace; extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 18cd0c0c73d9..207f0c83c8e9 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref) page_ext_put(page_ext_from_codetag_ref(ref)); }

+static inline void clear_page_tag_ref(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } +} + static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) { @@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)

static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} diff --git a/include/linux/thermal.h b/include/linux/thermal.h index f1155c0439c4..13f88317b81b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -55,6 +55,7 @@ enum thermal_notify_event { THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */ THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */ + THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */ };

/** diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 535701efc1e5..24d970f7a4fa 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -230,8 +230,12 @@ struct vsock_tap { int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags);

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e372a88e8c3f..d1d073089f38 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -206,14 +206,17 @@ enum { */ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,

- /* When this quirk is set, the controller has validated that - * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are - * valid. This mechanism is necessary as many controllers have - * been seen has having trouble initiating a connectable - * advertisement despite the state combination being reported as - * supported. + /* When this quirk is set, the LE states reported through the + * HCI_LE_READ_SUPPORTED_STATES are invalid/broken. + * + * This mechanism is necessary as many controllers have been seen has + * having trouble initiating a connectable advertisement despite the + * state combination being reported as supported. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. */ - HCI_QUIRK_VALID_LE_STATES, + HCI_QUIRK_BROKEN_LE_STATES,

/* When this quirk is set, then erroneous data reporting * is ignored. This is mainly due to the fact that the HCI diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index b15f51ae3bfd..c97ff64c9189 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -826,7 +826,7 @@ extern struct mutex hci_cb_list_lock; } while (0)

#define hci_dev_le_state_simultaneous(hdev) \ - (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ + (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ (hdev->le_states[4] & 0x08) && /* Central */ \ (hdev->le_states[4] & 0x40) && /* Peripheral */ \ (hdev->le_states[3] & 0x10)) /* Simultaneous */ diff --git a/include/net/kcm.h b/include/net/kcm.h index 90279e5e09a5..441e993be634 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1;

/* Don't use bit fields here, these are set under different locks */ diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index f207a6e1042a..9bdb1fdc7c51 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -274,6 +274,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; };

diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 45c40d200154..8ecfb94049db 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -234,7 +234,7 @@ static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd)

static inline unsigned int scsi_logical_block_count(struct scsi_cmnd *scmd) { - unsigned int shift = ilog2(scmd->device->sector_size) - SECTOR_SHIFT; + unsigned int shift = ilog2(scmd->device->sector_size);

return blk_rq_bytes(scsi_cmd_to_rq(scmd)) >> shift; } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1e1b40f4e664..846132ca5503 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -813,6 +813,9 @@ struct ocelot { const u32 *const *map; struct list_head stats_regions;

+ spinlock_t inj_lock; + spinlock_t xtr_lock; + u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; int packet_buffer_size; int num_frame_refs; @@ -966,10 +969,17 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset);

/* Packet I/O */ +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp); bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index da23484268df..24ec3434d32e 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -145,6 +145,7 @@ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ + EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 91583690bddc..f33d914d8f46 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -8,14 +8,11 @@ #define FASTRPC_IOCTL_ALLOC_DMA_BUFF _IOWR('R', 1, struct fastrpc_alloc_dma_buf) #define FASTRPC_IOCTL_FREE_DMA_BUFF _IOWR('R', 2, __u32) #define FASTRPC_IOCTL_INVOKE _IOWR('R', 3, struct fastrpc_invoke) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH _IO('R', 4) #define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create) #define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap) #define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static) #define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map) #define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap) diff --git a/init/Kconfig b/init/Kconfig index d8a971b804d3..9684e5d2b81c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1789,24 +1789,6 @@ config KALLSYMS_ABSOLUTE_PERCPU depends on KALLSYMS default X86_64 && SMP

-config KALLSYMS_BASE_RELATIVE - bool - depends on KALLSYMS - default y - help - Instead of emitting them as absolute values in the native word size, - emit the symbol references in the kallsyms table as 32-bit entries, - each containing a relative value in the range [base, base + U32_MAX] - or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either - an absolute value in the range [0, S32_MAX] or a relative value in the - range [base, base + S32_MAX], where base is the lowest relative symbol - address encountered in the image. - - On 64-bit builds, this reduces the size of the address table by 50%, - but more importantly, it results in entries whose values are build - time constants, and no relocation pass is required at runtime to fix - up the entries based on the runtime load address of the kernel. - # end of the "standard kernel features (expert users)" menu

config ARCH_HAS_MEMBARRIER_CALLBACKS @@ -1924,12 +1906,15 @@ config RUST config RUSTC_VERSION_TEXT string depends on RUST - default $(shell,command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n) + default "$(shell,$(RUSTC) --version 2>/dev/null)"

config BINDGEN_VERSION_TEXT string depends on RUST - default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version || echo n) + # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 + # (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when + # the minimum version is upgraded past that (0.69.1 already fixed the issue). + default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)"

# # Place an empty function call at each tracepoint site. Can be diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 726e6367af4d..af46d03d5884 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -43,7 +43,7 @@ struct io_wait_queue { ktime_t timeout;

#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned int napi_busy_poll_to; + ktime_t napi_busy_poll_dt; bool napi_prefer_busy_poll; #endif }; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index c95dc1736dd9..1af2bd56af44 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -218,10 +218,13 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,

buf = io_ring_head_to_buf(br, head, bl->mask); if (arg->max_len) { - int needed; + u32 len = READ_ONCE(buf->len); + size_t needed;

- needed = (arg->max_len + buf->len - 1) / buf->len; - needed = min(needed, PEEK_MAX_IMPORT); + if (unlikely(!len)) + return -ENOBUFS; + needed = (arg->max_len + len - 1) / len; + needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT); if (nr_avail > needed) nr_avail = needed; } diff --git a/io_uring/napi.c b/io_uring/napi.c index 080d10e0e0af..ab5d68d4440c 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -33,6 +33,12 @@ static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list, return NULL; }

+static inline ktime_t net_to_ktime(unsigned long t) +{ + /* napi approximating usecs, reverse busy_loop_current_time */ + return ns_to_ktime(t << 10); +} + void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock) { struct hlist_head *hash_list; @@ -102,14 +108,14 @@ static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale) __io_napi_remove_stale(ctx); }

-static inline bool io_napi_busy_loop_timeout(unsigned long start_time, - unsigned long bp_usec) +static inline bool io_napi_busy_loop_timeout(ktime_t start_time, + ktime_t bp) { - if (bp_usec) { - unsigned long end_time = start_time + bp_usec; - unsigned long now = busy_loop_current_time(); + if (bp) { + ktime_t end_time = ktime_add(start_time, bp); + ktime_t now = net_to_ktime(busy_loop_current_time());

- return time_after(now, end_time); + return ktime_after(now, end_time); }

return true; @@ -124,7 +130,8 @@ static bool io_napi_busy_loop_should_end(void *data, return true; if (io_should_wake(iowq) || io_has_work(iowq->ctx)) return true; - if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to)) + if (io_napi_busy_loop_timeout(net_to_ktime(start_time), + iowq->napi_busy_poll_dt)) return true;

return false; @@ -181,10 +188,12 @@ static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx, */ void io_napi_init(struct io_ring_ctx *ctx) { + u64 sys_dt = READ_ONCE(sysctl_net_busy_poll) * NSEC_PER_USEC; + INIT_LIST_HEAD(&ctx->napi_list); spin_lock_init(&ctx->napi_lock); ctx->napi_prefer_busy_poll = false; - ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll); + ctx->napi_busy_poll_dt = ns_to_ktime(sys_dt); }

/* @@ -217,7 +226,7 @@ void io_napi_free(struct io_ring_ctx *ctx) int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) { const struct io_uring_napi curr = { - .busy_poll_to = ctx->napi_busy_poll_to, + .busy_poll_to = ktime_to_us(ctx->napi_busy_poll_dt), .prefer_busy_poll = ctx->napi_prefer_busy_poll }; struct io_uring_napi napi; @@ -232,7 +241,7 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) if (copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT;

- WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to); + WRITE_ONCE(ctx->napi_busy_poll_dt, napi.busy_poll_to * NSEC_PER_USEC); WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll); WRITE_ONCE(ctx->napi_enabled, true); return 0; @@ -249,14 +258,14 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) { const struct io_uring_napi curr = { - .busy_poll_to = ctx->napi_busy_poll_to, + .busy_poll_to = ktime_to_us(ctx->napi_busy_poll_dt), .prefer_busy_poll = ctx->napi_prefer_busy_poll };

if (arg && copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT;

- WRITE_ONCE(ctx->napi_busy_poll_to, 0); + WRITE_ONCE(ctx->napi_busy_poll_dt, 0); WRITE_ONCE(ctx->napi_prefer_busy_poll, false); WRITE_ONCE(ctx->napi_enabled, false); return 0; @@ -275,23 +284,20 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, struct timespec64 *ts) { - unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to); + ktime_t poll_dt = READ_ONCE(ctx->napi_busy_poll_dt);

if (ts) { struct timespec64 poll_to_ts;

- poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to); + poll_to_ts = ns_to_timespec64(ktime_to_ns(poll_dt)); if (timespec64_compare(ts, &poll_to_ts) < 0) { s64 poll_to_ns = timespec64_to_ns(ts); - if (poll_to_ns > 0) { - u64 val = poll_to_ns + 999; - do_div(val, (s64) 1000); - poll_to = val; - } + if (poll_to_ns > 0) + poll_dt = ns_to_ktime(poll_to_ns); } }

- iowq->napi_busy_poll_to = poll_to; + iowq->napi_busy_poll_dt = poll_dt; }

/* @@ -305,7 +311,7 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);

- if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled) + if (!(ctx->flags & IORING_SETUP_SQPOLL)) io_napi_blocking_busy_loop(ctx, iowq); }

@@ -320,7 +326,7 @@ int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx) LIST_HEAD(napi_list); bool is_stale = false;

- if (!READ_ONCE(ctx->napi_busy_poll_to)) + if (!READ_ONCE(ctx->napi_busy_poll_dt)) return 0; if (list_empty_careful(&ctx->napi_list)) return 0; diff --git a/io_uring/napi.h b/io_uring/napi.h index 6fc0393d0dbe..341d010cf66b 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -55,7 +55,7 @@ static inline void io_napi_add(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; struct socket *sock;

- if (!READ_ONCE(ctx->napi_busy_poll_to)) + if (!READ_ONCE(ctx->napi_enabled)) return;

sock = sock_from_file(req->file); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a8845cc299fe..521bd7efae03 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16881,8 +16881,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, spi = i / BPF_REG_SIZE;

if (exact != NOT_EXACT && - old->stack[spi].slot_type[i % BPF_REG_SIZE] != - cur->stack[spi].slot_type[i % BPF_REG_SIZE]) + (i >= cur->allocated_stack || + old->stack[spi].slot_type[i % BPF_REG_SIZE] != + cur->stack[spi].slot_type[i % BPF_REG_SIZE])) return false;

if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5e468db95810..fc1c6236460d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1940,6 +1940,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, part_error = PERR_CPUSEMPTY; goto write_error; } + /* Check newmask again, whether cpus are available for parent/cs */ + nocpu |= tasks_nocpu_error(parent, cs, newmask);

/* * partcmd_update with newmask: @@ -2472,7 +2474,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, */ if (!*buf) { cpumask_clear(trialcs->cpus_allowed); - cpumask_clear(trialcs->effective_xcpus); + if (cpumask_empty(trialcs->exclusive_cpus)) + cpumask_clear(trialcs->effective_xcpus); } else { retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) diff --git a/kernel/cpu.c b/kernel/cpu.c index 3d2bf1d50a0c..6dee328bfe6f 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2679,6 +2679,16 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) return ret; }

+/** + * Check if the core a CPU belongs to is online + */ +#if !defined(topology_is_core_online) +static inline bool topology_is_core_online(unsigned int cpu) +{ + return true; +} +#endif + int cpuhp_smt_enable(void) { int cpu, ret = 0; @@ -2689,7 +2699,7 @@ int cpuhp_smt_enable(void) /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; - if (!cpu_smt_thread_allowed(cpu)) + if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu)) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) diff --git a/kernel/events/core.c b/kernel/events/core.c index b2a6aec118f3..7891d5a75526 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9708,7 +9708,8 @@ static int __perf_event_overflow(struct perf_event *event,

ret = __perf_event_account_interrupt(event, throttle);

- if (event->prog && !bpf_overflow_handler(event, data, regs)) + if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT && + !bpf_overflow_handler(event, data, regs)) return ret;

/* diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 98b9622d372e..a9a0ca605d4a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -148,9 +148,6 @@ static unsigned int get_symbol_offset(unsigned long pos)

unsigned long kallsyms_sym_address(int idx) { - if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) - return kallsyms_addresses[idx]; - /* values are unsigned offsets if --absolute-percpu is not in effect */ if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU)) return kallsyms_relative_base + (u32)kallsyms_offsets[idx]; @@ -163,38 +160,6 @@ unsigned long kallsyms_sym_address(int idx) return kallsyms_relative_base - 1 - kallsyms_offsets[idx]; }

-static void cleanup_symbol_name(char *s) -{ - char *res; - - if (!IS_ENABLED(CONFIG_LTO_CLANG)) - return; - - /* - * LLVM appends various suffixes for local functions and variables that - * must be promoted to global scope as part of LTO. This can break - * hooking of static functions with kprobes. '.' is not a valid - * character in an identifier in C. Suffixes only in LLVM LTO observed: - * - foo.llvm.[0-9a-f]+ - */ - res = strstr(s, ".llvm."); - if (res) - *res = '\0'; - - return; -} - -static int compare_symbol_name(const char *name, char *namebuf) -{ - /* The kallsyms_seqs_of_names is sorted based on names after - * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled. - * To ensure correct bisection in kallsyms_lookup_names(), do - * cleanup_symbol_name(namebuf) before comparing name and namebuf. - */ - cleanup_symbol_name(namebuf); - return strcmp(name, namebuf); -} - static unsigned int get_symbol_seq(int index) { unsigned int i, seq = 0; @@ -222,7 +187,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(mid); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - ret = compare_symbol_name(name, namebuf); + ret = strcmp(name, namebuf); if (ret > 0) low = mid + 1; else if (ret < 0) @@ -239,7 +204,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(low - 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - if (compare_symbol_name(name, namebuf)) + if (strcmp(name, namebuf)) break; low--; } @@ -251,7 +216,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(high + 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - if (compare_symbol_name(name, namebuf)) + if (strcmp(name, namebuf)) break; high++; } @@ -325,7 +290,7 @@ static unsigned long get_symbol_pos(unsigned long addr, unsigned long symbol_start = 0, symbol_end = 0; unsigned long i, low, high, mid;

- /* Do a binary search on the sorted kallsyms_addresses array. */ + /* Do a binary search on the sorted kallsyms_offsets array. */ low = 0; high = kallsyms_num_syms;

@@ -410,8 +375,7 @@ static int kallsyms_lookup_buildid(unsigned long addr, if (modbuildid) *modbuildid = NULL;

- ret = strlen(namebuf); - goto found; + return strlen(namebuf); }

/* See if it's in a module or a BPF JITed image. */ @@ -425,8 +389,6 @@ static int kallsyms_lookup_buildid(unsigned long addr, ret = ftrace_mod_address_lookup(addr, symbolsize, offset, modname, namebuf);

-found: - cleanup_symbol_name(namebuf); return ret; }

@@ -453,8 +415,6 @@ const char *kallsyms_lookup(unsigned long addr,

int lookup_symbol_name(unsigned long addr, char *symname) { - int res; - symname[0] = '\0'; symname[KSYM_NAME_LEN - 1] = '\0';

@@ -465,16 +425,10 @@ int lookup_symbol_name(unsigned long addr, char *symname) /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), symname, KSYM_NAME_LEN); - goto found; + return 0; } /* See if it's in a module. */ - res = lookup_module_symbol_name(addr, symname); - if (res) - return res; - -found: - cleanup_symbol_name(symname); - return 0; + return lookup_module_symbol_name(addr, symname); }

/* Look up a kernel symbol and return it in a text buffer. */ diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h index 85480274fc8f..9633782f8250 100644 --- a/kernel/kallsyms_internal.h +++ b/kernel/kallsyms_internal.h @@ -4,12 +4,6 @@

#include <linux/types.h>

-/* - * These will be re-linked against their real values during the second link - * stage. Preliminary values must be provided in the linker script using the - * PROVIDE() directive so that the first link stage can complete successfully. - */ -extern const unsigned long kallsyms_addresses[]; extern const int kallsyms_offsets[]; extern const u8 kallsyms_names[];

diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index 2f84896a7bcb..873f7c445488 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -187,31 +187,11 @@ static void test_perf_kallsyms_lookup_name(void) stat.min, stat.max, div_u64(stat.sum, stat.real_cnt)); }

-static bool match_cleanup_name(const char *s, const char *name) -{ - char *p; - int len; - - if (!IS_ENABLED(CONFIG_LTO_CLANG)) - return false; - - p = strstr(s, ".llvm."); - if (!p) - return false; - - len = strlen(name); - if (p - s != len) - return false; - - return !strncmp(s, name, len); -} - static int find_symbol(void *data, const char *name, unsigned long addr) { struct test_stat *stat = (struct test_stat *)data;

- if (strcmp(name, stat->name) == 0 || - (!stat->perf && match_cleanup_name(name, stat->name))) { + if (!strcmp(name, stat->name)) { stat->real_cnt++; stat->addr = addr;

diff --git a/kernel/panic.c b/kernel/panic.c index 8bff183d6180..30342568e935 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -63,6 +63,8 @@ unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; static unsigned int warn_limit __read_mostly;

+bool panic_triggering_all_cpu_backtrace; + int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout);

@@ -252,8 +254,12 @@ void check_panic_on_warn(const char *origin) */ static void panic_other_cpus_shutdown(bool crash_kexec) { - if (panic_print & PANIC_PRINT_ALL_CPU_BT) + if (panic_print & PANIC_PRINT_ALL_CPU_BT) { + /* Temporary allow non-panic CPUs to write their backtraces. */ + panic_triggering_all_cpu_backtrace = true; trigger_all_cpu_backtrace(); + panic_triggering_all_cpu_backtrace = false; + }

/* * Note that smp_send_stop() is the usual SMP shutdown function, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index dddb15f48d59..c5d844f727f6 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2316,7 +2316,7 @@ asmlinkage int vprintk_emit(int facility, int level, * non-panic CPUs are generating any messages, they will be * silently dropped. */ - if (other_cpu_in_panic()) + if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace) return 0;

if (level == LOGLEVEL_SCHED) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 578a49ff5c32..cb507860163d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7956,7 +7956,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, trace_access_unlock(iter->cpu_file);

if (ret < 0) { - if (trace_empty(iter)) { + if (trace_empty(iter) && !iter->closed) { if ((filp->f_flags & O_NONBLOCK)) return -EAGAIN;

diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index 1d5eadd9dd61..8b4f8cc2e0ec 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -216,12 +216,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(kallsyms_num_syms); VMCOREINFO_SYMBOL(kallsyms_token_table); VMCOREINFO_SYMBOL(kallsyms_token_index); -#ifdef CONFIG_KALLSYMS_BASE_RELATIVE VMCOREINFO_SYMBOL(kallsyms_offsets); VMCOREINFO_SYMBOL(kallsyms_relative_base); -#else - VMCOREINFO_SYMBOL(kallsyms_addresses); -#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */ #endif /* CONFIG_KALLSYMS */

arch_crash_save_vmcoreinfo(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f98247ec99c2..c970eec25c5a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -896,7 +896,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work)

static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { - return (v >> shift) & ((1 << bits) - 1); + return (v >> shift) & ((1U << bits) - 1); }

static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) @@ -4190,7 +4190,6 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; - unsigned long data;

if (WARN_ON(!wq_online)) return false; @@ -4208,29 +4207,35 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ - data = *work_data_bits(work); - if (from_cancel && - !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { - /* - * On RT, prevent a live lock when %current preempted soft - * interrupt processing or prevents ksoftirqd from running by - * keeping flipping BH. If the BH work item runs on a different - * CPU then this has no effect other than doing the BH - * disable/enable dance for nothing. This is copied from - * kernel/softirq.c::tasklet_unlock_spin_wait(). - */ - while (!try_wait_for_completion(&barr.done)) { - if (IS_ENABLED(CONFIG_PREEMPT_RT)) { - local_bh_disable(); - local_bh_enable(); - } else { - cpu_relax(); + if (from_cancel) { + unsigned long data = *work_data_bits(work); + + if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && + (data & WORK_OFFQ_BH)) { + /* + * On RT, prevent a live lock when %current preempted + * soft interrupt processing or prevents ksoftirqd from + * running by keeping flipping BH. If the BH work item + * runs on a different CPU then this has no effect other + * than doing the BH disable/enable dance for nothing. + * This is copied from + * kernel/softirq.c::tasklet_unlock_spin_wait(). + */ + while (!try_wait_for_completion(&barr.done)) { + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + local_bh_disable(); + local_bh_enable(); + } else { + cpu_relax(); + } } + goto out_destroy; } - } else { - wait_for_completion(&barr.done); }

+ wait_for_completion(&barr.done); + +out_destroy: destroy_work_on_stack(&barr.work); return true; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5f32a196a612..4d9c1277e5e4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1672,7 +1672,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); - goto out; + return 0; }

pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1715,22 +1715,16 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { flags |= TNF_MIGRATED; nid = target_nid; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { - spin_unlock(vmf->ptl); - goto out; - } - goto out_map; - } - -out: - if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; + }

- return 0; - + flags |= TNF_MIGRATE_FAIL; + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + spin_unlock(vmf->ptl); + return 0; + } out_map: /* Restore the PMD */ pmd = pmd_modify(oldpmd, vma->vm_page_prot); @@ -1740,7 +1734,10 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); + return 0; }

/* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 88c7a0861017..332f190bf3d6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5282,9 +5282,12 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, buf = endp + 1;

cfd = simple_strtoul(buf, &endp, 10); - if ((*endp != ' ') && (*endp != '\0')) + if (*endp == '\0') + buf = endp; + else if (*endp == ' ') + buf = endp + 1; + else return -EINVAL; - buf = endp + 1;

event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d3c830e817e3..7e2e454142bc 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2406,7 +2406,7 @@ struct memory_failure_entry { struct memory_failure_cpu { DECLARE_KFIFO(fifo, struct memory_failure_entry, MEMORY_FAILURE_FIFO_SIZE); - spinlock_t lock; + raw_spinlock_t lock; struct work_struct work; };

@@ -2432,20 +2432,22 @@ void memory_failure_queue(unsigned long pfn, int flags) { struct memory_failure_cpu *mf_cpu; unsigned long proc_flags; + bool buffer_overflow; struct memory_failure_entry entry = { .pfn = pfn, .flags = flags, };

mf_cpu = &get_cpu_var(memory_failure_cpu); - spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, entry)) + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); + buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry); + if (!buffer_overflow) schedule_work_on(smp_processor_id(), &mf_cpu->work); - else + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); + if (buffer_overflow) pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); - put_cpu_var(memory_failure_cpu); } EXPORT_SYMBOL_GPL(memory_failure_queue);

@@ -2458,9 +2460,9 @@ static void memory_failure_work_func(struct work_struct *work)

mf_cpu = container_of(work, struct memory_failure_cpu, work); for (;;) { - spin_lock_irqsave(&mf_cpu->lock, proc_flags); + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) @@ -2490,7 +2492,7 @@ static int __init memory_failure_init(void)

for_each_possible_cpu(cpu) { mf_cpu = &per_cpu(memory_failure_cpu, cpu); - spin_lock_init(&mf_cpu->lock); + raw_spin_lock_init(&mf_cpu->lock); INIT_KFIFO(mf_cpu->fifo); INIT_WORK(&mf_cpu->work, memory_failure_work_func); } diff --git a/mm/memory.c b/mm/memory.c index 755ffe082e21..72d00a38585d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5155,7 +5155,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)

if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + return 0; }

pte = pte_modify(old_pte, vma->vm_page_prot); @@ -5218,23 +5218,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (!migrate_misplaced_folio(folio, vma, target_nid)) { nid = target_nid; flags |= TNF_MIGRATED; - } else { - flags |= TNF_MIGRATE_FAIL; - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (unlikely(!vmf->pte)) - goto out; - if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; - } - goto out_map; + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; }

-out: - if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, nr_pages, flags); - return 0; + flags |= TNF_MIGRATE_FAIL; + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte)) + return 0; + if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } out_map: /* * Make it present again, depending on how arch implements @@ -5247,7 +5243,10 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, writable); pte_unmap_unlock(vmf->pte, vmf->ptl); - goto out; + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; }

static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) diff --git a/mm/mm_init.c b/mm/mm_init.c index 3ec04933f7fd..2addc701790a 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2293,6 +2293,8 @@ void __init init_cma_reserved_pageblock(struct page *page)

set_pageblock_migratetype(page, MIGRATE_CMA); set_page_refcounted(page); + /* pages were reserved and not allocated */ + clear_page_tag_ref(page); __free_pages(page, pageblock_order);

adjust_managed_page_count(page, pageblock_nr_pages); @@ -2505,15 +2507,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, }

/* pages were reserved and not allocated */ - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } - + clear_page_tag_ref(page); __free_pages_core(page, order); }

diff --git a/mm/mseal.c b/mm/mseal.c index bf783bba8ed0..15bba28acc00 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -40,9 +40,17 @@ static bool can_modify_vma(struct vm_area_struct *vma)

static bool is_madv_discard(int behavior) { - return behavior & - (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED | - MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK); + switch (behavior) { + case MADV_FREE: + case MADV_DONTNEED: + case MADV_DONTNEED_LOCKED: + case MADV_REMOVE: + case MADV_DONTFORK: + case MADV_WIPEONFORK: + return true; + } + + return false; }

static bool is_ro_anon(struct vm_area_struct *vma) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df2c442f1c47..b50060405d94 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes);

static bool page_contains_unaccepted(struct page *page, unsigned int order); static void accept_page(struct page *page, unsigned int order); -static bool try_to_accept_memory(struct zone *zone, unsigned int order); +static bool cond_accept_memory(struct zone *zone, unsigned int order); static inline bool has_unaccepted_memory(void); static bool __free_unaccepted(struct page *page);

@@ -3059,9 +3059,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z, if (!(alloc_flags & ALLOC_CMA)) unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES); #endif -#ifdef CONFIG_UNACCEPTED_MEMORY - unusable_free += zone_page_state(z, NR_UNACCEPTED); -#endif

return unusable_free; } @@ -3355,6 +3352,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, } }

+ cond_accept_memory(zone, order); + /* * Detect whether the number of free pages is below high * watermark. If so, we will decrease pcp->high and free @@ -3380,10 +3379,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, gfp_mask)) { int ret;

- if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -3437,10 +3434,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,

return page; } else { - if (has_unaccepted_memory()) { - if (try_to_accept_memory(zone, order)) - goto try_this_zone; - } + if (cond_accept_memory(zone, order)) + goto try_this_zone;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* Try again if zone has deferred pages */ @@ -5811,14 +5806,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char

void free_reserved_page(struct page *page) { - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } + clear_page_tag_ref(page); ClearPageReserved(page); init_page_count(page); __free_page(page); @@ -6933,9 +6921,6 @@ static bool try_to_accept_memory_one(struct zone *zone) struct page *page; bool last;

- if (list_empty(&zone->unaccepted_pages)) - return false; - spin_lock_irqsave(&zone->lock, flags); page = list_first_entry_or_null(&zone->unaccepted_pages, struct page, lru); @@ -6961,23 +6946,29 @@ static bool try_to_accept_memory_one(struct zone *zone) return true; }

-static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { long to_accept; - int ret = false; + bool ret = false; + + if (!has_unaccepted_memory()) + return false; + + if (list_empty(&zone->unaccepted_pages)) + return false;

/* How much to accept to get to high watermark? */ to_accept = high_wmark_pages(zone) - (zone_page_state(zone, NR_FREE_PAGES) - - __zone_watermark_unusable_free(zone, order, 0)); + __zone_watermark_unusable_free(zone, order, 0) - + zone_page_state(zone, NR_UNACCEPTED));

- /* Accept at least one page */ - do { + while (to_accept > 0) { if (!try_to_accept_memory_one(zone)) break; ret = true; to_accept -= MAX_ORDER_NR_PAGES; - } while (to_accept > 0); + }

return ret; } @@ -7020,7 +7011,7 @@ static void accept_page(struct page *page, unsigned int order) { }

-static bool try_to_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order) { return false; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e34ea860153f..881e497137e5 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3583,15 +3583,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid, page = alloc_pages_noprof(alloc_gfp, order); else page = alloc_pages_node_noprof(nid, alloc_gfp, order); - if (unlikely(!page)) { - if (!nofail) - break; - - /* fall back to the zero order allocations */ - alloc_gfp |= __GFP_NOFAIL; - order = 0; - continue; - } + if (unlikely(!page)) + break;

/* * Higher order allocations must be able to be treated as diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 6ecb110bf46b..b488d0742c96 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3674,19 +3674,19 @@ static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; - int quote, cnt, tmp; + int quote, *cnt, tmp;

BT_DBG("%s", hdev->name);

if (!hci_conn_num(hdev, LE_LINK)) return;

- cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; + cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt;

- __check_timeout(hdev, cnt, LE_LINK); + __check_timeout(hdev, *cnt, LE_LINK);

- tmp = cnt; - while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, &quote))) { + tmp = *cnt; + while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, &quote))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, @@ -3701,7 +3701,7 @@ static void hci_sched_le(struct hci_dev *hdev) hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies;

- cnt--; + (*cnt)--; chan->sent++; chan->conn->sent++;

@@ -3711,12 +3711,7 @@ static void hci_sched_le(struct hci_dev *hdev) } }

- if (hdev->le_pkts) - hdev->le_cnt = cnt; - else - hdev->acl_cnt = cnt; - - if (cnt != tmp) + if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); }

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index a78f6d706cd4..59d9086db75f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5921,7 +5921,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || + (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL;

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 80f220b7e19d..ad4793ea052d 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3457,6 +3457,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * will be kept and this function does nothing. */ p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + if (!p) { + err = -EIO; + goto unlock; + }

if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) p->auto_connect = HCI_AUTO_CONN_DISABLED; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1e7ea3a4b7ef..4f9fdf400584 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { - if (hcon->role == HCI_ROLE_MASTER) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp->method = CFM_PASSKEY; else smp->method = REQ_PASSKEY; @@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp)

smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp);

- if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); else SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp) int ret;

bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder");

ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp) return SMP_CONFIRM_FAILED; }

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 stk[16]; __le64 rand = 0; __le16 ediv = 0; @@ -1256,14 +1257,15 @@ static void smp_distribute_keys(struct smp_chan *smp) rsp = (void *) &smp->prsp[1];

/* The responder sends its keys first */ - if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) && + (smp->remote_key_dist & KEY_DIST_MASK)) { smp_allow_key_dist(smp); return; }

req = (void *) &smp->preq[1];

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -1432,7 +1434,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16]) struct hci_conn *hcon = smp->conn->hcon; u8 *na, *nb, a[7], b[7];

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { na = smp->prnd; nb = smp->rrnd; } else { @@ -1460,7 +1462,7 @@ static void sc_dhkey_check(struct smp_chan *smp) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type;

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->preq[1], 3); @@ -1539,7 +1541,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) /* The round is only complete when the initiator * receives pairing random. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); if (smp->passkey_round == 20) @@ -1567,7 +1569,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)

SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); return 0; @@ -1578,7 +1580,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) case SMP_CMD_PUBLIC_KEY: default: /* Initiating device starts the round */ - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0;

bt_dev_dbg(hdev, "Starting passkey round %u", @@ -1623,7 +1625,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey) }

/* Initiator sends DHKey check first */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) { @@ -1746,7 +1748,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_pairing rsp, *req = (void *) skb->data; struct l2cap_chan *chan = conn->smp; struct hci_dev *hdev = conn->hcon->hdev; - struct smp_chan *smp; + struct smp_chan *smp = chan->data; u8 key_size, auth, sec_level; int ret;

@@ -1755,16 +1757,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*req)) return SMP_INVALID_PARAMS;

- if (conn->hcon->role != HCI_ROLE_SLAVE) + if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP;

- if (!chan->data) + if (!smp) { smp = smp_chan_create(conn); - else - smp = chan->data; - - if (!smp) - return SMP_UNSPECIFIED; + if (!smp) + return SMP_UNSPECIFIED; + }

/* We didn't start the pairing, so match remote */ auth = req->auth_req & AUTH_REQ_MASK(hdev); @@ -1946,7 +1946,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rsp)) return SMP_INVALID_PARAMS;

- if (conn->hcon->role != HCI_ROLE_MASTER) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP;

skb_pull(skb, sizeof(*rsp)); @@ -2041,7 +2041,7 @@ static u8 sc_check_confirm(struct smp_chan *smp) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM);

- if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2063,7 +2063,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) u8 auth;

/* The issue is only observed when we're in responder role */ - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_UNSPECIFIED;

if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { @@ -2099,7 +2099,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_dev *hdev = hcon->hdev;

bt_dev_dbg(hdev, "conn %p %s", conn, - hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder");

if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2121,7 +2122,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) return ret; }

- if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2156,7 +2157,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (!test_bit(SMP_FLAG_SC, &smp->flags)) return smp_random(smp);

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { pkax = smp->local_pk; pkbx = smp->remote_pk; na = smp->prnd; @@ -2169,7 +2170,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) }

if (smp->method == REQ_OOB) { - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); @@ -2180,7 +2181,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM);

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 cfm[16];

err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk, @@ -2221,7 +2222,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) return SMP_UNSPECIFIED;

if (smp->method == REQ_OOB) { - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } @@ -2295,10 +2296,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, return false; }

+static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_pairing cp; + + if (smp->conn->hcon->type == ACL_LINK) + build_bredr_pairing_cmd(smp, &cp, NULL); + else + build_pairing_cmd(smp->conn, &cp, NULL, auth); + + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); + + smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + + set_bit(SMP_FLAG_INITIATOR, &smp->flags); +} + static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_security_req *rp = (void *) skb->data; - struct smp_cmd_pairing cp; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; struct smp_chan *smp; @@ -2347,16 +2365,20 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)

skb_pull(skb, sizeof(*rp));

- memset(&cp, 0, sizeof(cp)); - build_pairing_cmd(conn, &cp, NULL, auth); + smp_send_pairing_req(smp, auth);

- smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); + return 0; +}

- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); +static void smp_send_security_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_security_req cp;

- return 0; + cp.auth_req = auth; + smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); + + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); }

int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) @@ -2427,23 +2449,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq |= SMP_AUTH_MITM; }

- if (hcon->role == HCI_ROLE_MASTER) { - struct smp_cmd_pairing cp; - - build_pairing_cmd(conn, &cp, NULL, authreq); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); - } else { - struct smp_cmd_security_req cp; - cp.auth_req = authreq; - smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); - } + if (hcon->role == HCI_ROLE_MASTER) + smp_send_pairing_req(smp, authreq); + else + smp_send_security_req(smp, authreq);

- set_bit(SMP_FLAG_INITIATOR, &smp->flags); ret = 0;

unlock: @@ -2694,8 +2704,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)

static u8 sc_select_method(struct smp_chan *smp) { - struct l2cap_conn *conn = smp->conn; - struct hci_conn *hcon = conn->hcon; struct smp_cmd_pairing *local, *remote; u8 local_mitm, remote_mitm, local_io, remote_io, method;

@@ -2708,7 +2716,7 @@ static u8 sc_select_method(struct smp_chan *smp) * the "struct smp_cmd_pairing" from them we need to skip the * first byte which contains the opcode. */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local = (void *) &smp->preq[1]; remote = (void *) &smp->prsp[1]; } else { @@ -2777,7 +2785,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* Non-initiating device sends its public key after receiving * the key from the initiating device. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { err = sc_send_public_key(smp); if (err) return err; @@ -2839,7 +2847,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) }

if (smp->method == REQ_OOB) { - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd);

@@ -2848,7 +2856,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) return 0; }

- if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);

if (smp->method == REQ_PASSKEY) { @@ -2863,7 +2871,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* The Initiating device waits for the non-initiating device to * send the confirm value. */ - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0;

err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd, @@ -2897,7 +2905,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type;

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->prsp[1], 3); @@ -2922,7 +2930,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED;

- if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) { set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags); return 0; @@ -2934,7 +2942,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)

sc_add_ltk(smp);

- if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size); hcon->enc_key_size = smp->enc_key_size; } @@ -3083,7 +3091,6 @@ static void bredr_pairing(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - struct smp_cmd_pairing req; struct smp_chan *smp;

bt_dev_dbg(hdev, "chan %p", chan); @@ -3135,14 +3142,7 @@ static void bredr_pairing(struct l2cap_chan *chan)

bt_dev_dbg(hdev, "starting SMP over BR/EDR");

- /* Prepare and send the BR/EDR SMP Pairing Request */ - build_bredr_pairing_cmd(smp, &req, NULL); - - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &req, sizeof(req)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + smp_send_pairing_req(smp, 0x00); }

static void smp_resume_cb(struct l2cap_chan *chan) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index bf30c50b5689..a9e1b56f854d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -619,8 +619,12 @@ static unsigned int br_nf_local_in(void *priv, if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT;

+ if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + WARN_ON_ONCE(skb_shared(skb)); - WARN_ON_ONCE(refcount_read(&nfct->use) != 1);

/* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville"

-/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class;

- ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type);

qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ecd521108559..2c52f6dcbd29 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ if (unlikely(len != icsk->icsk_ack.rcv_mss)) { u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + u8 old_ratio = tcp_sk(sk)->scaling_ratio;

do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; + + if (old_ratio != tcp_sk(sk)->scaling_ratio) + WRITE_ONCE(tcp_sk(sk)->window_clamp, + tcp_win_from_space(sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk) * <prev RTT . ><current RTT .. ><next RTT .... > */

- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && + !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { u64 rcvwin, grow; int rcvbuf;

@@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk)

rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - if (rcvbuf > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - - /* Make the window clamp follow along. */ - WRITE_ONCE(tp->window_clamp, - tcp_win_from_space(sk, rcvbuf)); - } - } else { - /* Make the window clamp follow along while being bounded - * by SO_RCVBUF. - */ - int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf)); + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);

- if (clamp > tp->window_clamp) - WRITE_ONCE(tp->window_clamp, clamp); + /* Make the window clamp follow along. */ + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); } } tp->rcvq_space.space = copied; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a541659b6562..8f8f93716ff8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -95,6 +95,8 @@ EXPORT_SYMBOL(tcp_hashinfo);

static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);

+static DEFINE_MUTEX(tcp_exit_batch_mutex); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -3509,6 +3511,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net;

+ /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work + * and failed setup_net error unwinding path are serialized. + * + * tcp_twsk_purge() handles twsk in any dead netns, not just those in + * net_exit_list, the thread that dismantles a particular twsk must + * do so without other thread progressing to refcount_dec_and_test() of + * tcp_death_row.tw_refcount. + */ + mutex_lock(&tcp_exit_batch_mutex); + tcp_twsk_purge(net_exit_list);

list_for_each_entry(net, net_exit_list, exit_list) { @@ -3516,6 +3528,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } + + mutex_unlock(&tcp_exit_batch_mutex); }

static struct pernet_operations __net_initdata tcp_sk_ops = { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index ee9af921556a..5b54f4f32b1c 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -279,7 +279,8 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, return ERR_PTR(-EINVAL);

if (unlikely(skb_checksum_start(gso_skb) != - skb_transport_header(gso_skb))) + skb_transport_header(gso_skb) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL);

if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 784424ac4147..c49344d8311a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *

/* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOMEM; } + rcu_read_unlock(); }

hdr = ipv6_hdr(skb); @@ -283,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, head_room += opt->opt_nflen + opt->opt_flen;

if (unlikely(head_room > skb_headroom(skb))) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOBUFS; } + rcu_read_unlock(); }

if (opt) { @@ -1953,6 +1961,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err;

+ rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) @@ -1962,6 +1971,7 @@ int ip6_send_skb(struct sk_buff *skb) IPSTATS_MIB_OUTDISCARDS); }

+ rcu_read_unlock(); return err; }

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9dee0c127955..87dfb565a9f8 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link);

if (tdev) { - dev->hard_header_len = tdev->hard_header_len + t_hlen; + dev->needed_headroom = tdev->hard_header_len + + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);

mtu = mtu - t_hlen; @@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); + int t_hlen;

+ t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; @@ -1740,10 +1743,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { - if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { - if (new_mtu > IP_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); @@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t_hlen = t->hlen + sizeof(struct ipv6hdr);

dev->type = ARPHRD_TUNNEL6; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; + dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen;

netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 5e1b50c6a44d..3e9779ed7dae 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q;

+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0; + q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index b7bf34a5eb37..123530702007 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs, { struct device *dev; va_list vargs; + char buf[20]; int rc;

dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) goto out_error; va_start(vargs, fmt); - rc = dev_set_name(dev, fmt, vargs); + vsnprintf(buf, sizeof(buf), fmt, vargs); + rc = dev_set_name(dev, "%s", buf); va_end(vargs); if (rc) goto out_error; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2f191e50d4fc..d4118c796290 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE;

+ mutex_lock(&kcm->tx_mutex); lock_sock(sk);

/* Per tcp_sendmsg this should be in poll */ @@ -926,6 +927,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) KCM_STATS_ADD(kcm->stats.tx_bytes, copied);

release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied;

out_error: @@ -951,6 +953,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) sk->sk_write_space(sk);

release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; }

@@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock);

INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex);

spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 77e5dd422258..8551dab1d1e6 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test)

skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2); - KUNIT_EXPECT_EQ(test, skb->len, 1); + KUNIT_EXPECT_EQ(test, skb2->len, 1);

skb_free_datagram(sock->sk, skb2);

diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 3ae46b545d2c..2d3efb405437 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */ diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 23bb89c94e90..3e6e0f5510bb 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -60,16 +60,6 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ return 0; }

-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) -{ - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); - - spin_lock_bh(&msk->pm.lock); - mptcp_pm_nl_rm_subflow_received(msk, rm_list); - spin_unlock_bh(&msk->pm.lock); - return 0; -} - /* path manager event handlers */

void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) @@ -444,9 +434,6 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id *flags = 0; *ifindex = 0;

- if (!id) - return 0; - if (mptcp_pm_is_userspace(msk)) return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 4cae2aa7be5c..3e4ad801786f 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -143,11 +143,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, return false; }

-static struct mptcp_pm_addr_entry * +static bool select_local_address(const struct pm_nl_pernet *pernet, - const struct mptcp_sock *msk) + const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false;

msk_owned_by_me(msk);

@@ -159,17 +161,21 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue;

- ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; }

-static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) +static bool +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false;

rcu_read_lock(); /* do not keep any additional per socket state, just signal @@ -184,11 +190,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue;

- ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; }

unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) @@ -512,9 +520,10 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)

static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { - struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL; struct sock *sk = (struct sock *)msk; + struct mptcp_pm_addr_entry local; unsigned int add_addr_signal_max; + bool signal_and_subflow = false; unsigned int local_addr_max; struct pm_nl_pernet *pernet; unsigned int subflows_max; @@ -565,23 +574,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return;

- local = select_signal_address(pernet, msk); - if (!local) + if (!select_signal_address(pernet, msk, &local)) goto subflow;

/* If the alloc fails, we are on memory pressure, not worth * continuing, and trying to create subflows. */ - if (!mptcp_pm_alloc_anno_list(msk, &local->addr)) + if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) return;

- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); + mptcp_pm_announce_addr(msk, &local.addr, false); mptcp_pm_nl_addr_send_ack(msk);

- if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) - signal_and_subflow = local; + if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = true; }

subflow: @@ -592,26 +600,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) bool fullmesh; int i, nr;

- if (signal_and_subflow) { - local = signal_and_subflow; - signal_and_subflow = NULL; - } else { - local = select_local_address(pernet, msk); - if (!local) - break; - } + if (signal_and_subflow) + signal_and_subflow = false; + else if (!select_local_address(pernet, msk, &local)) + break;

- fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);

msk->pm.local_addr_used++; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs); if (nr == 0) continue;

spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); + __mptcp_subflow_connect(sk, &local.addr, &addrs[i]); spin_lock_bh(&msk->pm.lock); } mptcp_pm_nl_check_work_pending(msk); @@ -636,6 +640,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; + struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; @@ -643,6 +648,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk);

+ mptcp_local_address((struct sock_common *)msk, &mpc_addr); + rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) @@ -653,7 +660,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,

if (msk->pm.subflows < subflows_max) { msk->pm.subflows++; - addrs[i++] = entry->addr; + addrs[i] = entry->addr; + + /* Special case for ID0: set the correct ID */ + if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port)) + addrs[i].id = 0; + + i++; } } rcu_read_unlock(); @@ -829,25 +842,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock);

- removed = true; + removed |= subflow->request_join; if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } - if (rm_type == MPTCP_MIB_RMSUBFLOW) - __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); - else if (rm_type == MPTCP_MIB_RMADDR) + + if (rm_type == MPTCP_MIB_RMADDR) __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (!removed) continue;

if (!mptcp_pm_is_kernel(msk)) continue;

- if (rm_type == MPTCP_MIB_RMADDR) { - msk->pm.add_addr_accepted--; - WRITE_ONCE(msk->pm.accept_addr, true); - } else if (rm_type == MPTCP_MIB_RMSUBFLOW) { - msk->pm.local_addr_used--; + if (rm_type == MPTCP_MIB_RMADDR && rm_id && + !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + /* Note: if the subflow has been closed before, this + * add_addr_accepted counter will not be decremented. + */ + if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk)) + WRITE_ONCE(msk->pm.accept_addr, true); } } } @@ -857,8 +872,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR); }

-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list) +static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW); } @@ -1393,6 +1408,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk);

+ /* No entries with ID 0 */ + if (id == 0) + return 0; + rcu_read_lock(); entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); if (entry) { @@ -1431,13 +1450,24 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); - msk->pm.add_addr_signaled -= ret; + if (ret) { + __set_bit(addr->id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled--; + } mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } return ret; }

+static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) +{ + /* If it was marked as used, and not ID 0, decrement local_addr_used */ + if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && + id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) + msk->pm.local_addr_used--; +} + static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { @@ -1466,8 +1496,19 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); - if (remove_subflow) - mptcp_pm_remove_subflow(msk, &list); + + if (remove_subflow) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_nl_rm_subflow_received(msk, &list); + spin_unlock_bh(&msk->pm.lock); + } + + if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + spin_lock_bh(&msk->pm.lock); + __mark_subflow_endp_available(msk, list.ids[0]); + spin_unlock_bh(&msk->pm.lock); + } + release_sock(sk);

next: @@ -1502,6 +1543,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk);

@@ -1605,14 +1647,17 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, alist.ids[alist.nr++] = entry->addr.id; }

+ spin_lock_bh(&msk->pm.lock); if (alist.nr) { - spin_lock_bh(&msk->pm.lock); msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); - spin_unlock_bh(&msk->pm.lock); } if (slist.nr) - mptcp_pm_remove_subflow(msk, &slist); + mptcp_pm_nl_rm_subflow_received(msk, &slist); + /* Reset counters: maybe some subflows have been removed before */ + bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + msk->pm.local_addr_used = 0; + spin_unlock_bh(&msk->pm.lock); }

static void mptcp_nl_remove_addrs_list(struct net *net, @@ -1900,6 +1945,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,

spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8357046732f7..c7c846805c4e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1021,7 +1021,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);

void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -1128,8 +1127,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo

void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list); unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 6eef15648b7b..b0f199171932 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,

switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return NF_ACCEPT; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); proto = veth->h_vlan_encapsulated_proto; break; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index c2c005234dcd..98edcaa37b38 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,

switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return false; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); if (veth->h_vlan_encapsulated_proto == proto) { *offset += VLAN_HLEN; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index a010b25076ca..3d46372b538e 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, struct list_head *block_cb_list) { struct flow_cls_offload cls_flow = {}; + struct netlink_ext_ack extack = {}; struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0;

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 91cc3a81ba8f..41d7faeb101c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7977,6 +7977,19 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; }

+static int nf_tables_dumpreset_obj(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_obj(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -7993,12 +8006,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb) if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));

- if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - ctx->reset = true; - return 0; }

+static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb) +{ + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_obj_start(cb); +} + static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -8009,8 +8028,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) }

/* called with rcu_read_lock held */ -static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); @@ -8019,72 +8039,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; - bool reset = false; u32 objtype; int err;

- if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start = nf_tables_dump_obj_start, - .dump = nf_tables_dump_obj, - .done = nf_tables_dump_obj_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) - return -EINVAL; + return ERR_PTR(-EINVAL);

table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); }

objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); - return PTR_ERR(obj); + return ERR_CAST(obj); }

skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; + return ERR_PTR(-ENOMEM);

- if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; + err = nf_tables_fill_obj_info(skb2, net, portid, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj, reset); + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + }

- if (reset) { - const struct nftables_pernet *nft_net; - char *buf; + return skb2; +}

- nft_net = nft_pernet(net); - buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + u32 portid = NETLINK_CB(skb).portid; + struct sk_buff *skb2;

- audit_log_nfcfg(buf, - family, - 1, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, + .dump = nf_tables_dump_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); }

- err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj, reset); - if (err < 0) - goto err_fill_obj_info; + skb2 = nf_tables_getobj_single(portid, info, nla, false); + if (IS_ERR(skb2)) + return PTR_ERR(skb2);

- return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, info->net, portid); +}

-err_fill_obj_info: - kfree_skb(skb2); - return err; +static int nf_tables_getobj_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dumpreset_obj_start, + .dump = nf_tables_dumpreset_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getobj_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_OBJ_TABLE]), + (char *)nla_data(nla[NFTA_OBJ_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); + + return nfnetlink_unicast(skb2, net, portid); }

static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) @@ -9367,7 +9424,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abf660c7baf..932b3ddb34f1 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -427,8 +427,10 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,

nfnl_unlock(subsys_id);

- if (nlh->nlmsg_flags & NLM_F_ACK) + if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); + }

while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -577,6 +579,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } else if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); } } else { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 55e28e1da66e..e0716da256bf 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - const struct nf_conn *ct = (void *)skb_nfct(entry->skb); + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + unsigned long status; + unsigned int use;

- if (ct && ((ct->status & flags) == IPS_DYING)) + if (!ct) + return false; + + status = READ_ONCE(ct->status); + if ((status & flags) == IPS_DYING) return true; + + if (status & IPS_CONFIRMED) + return false; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * We can't be solved with serialization here because one clone could + * have been queued for local delivery. + */ + use = refcount_read(&ct->ct_general.use); + if (likely(use == 1)) + return false; + + /* Can't decrement further? Exclusive ownership. */ + if (!refcount_dec_not_one(&ct->ct_general.use)) + return false; + + skb_set_nfct(entry->skb, 0); + /* No nf_ct_put(): we already decremented .use and it cannot + * drop down to 0. + */ + return true; #endif return false; } diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 291ed2026367..eab0dc66bee6 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv, struct nft_counter *total) { struct nft_counter *this_cpu; + seqcount_t *myseq;

local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); + myseq = this_cpu_ptr(&nft_counter_seq); + + write_seqcount_begin(myseq); this_cpu->packets -= total->packets; this_cpu->bytes -= total->bytes; + write_seqcount_end(myseq); local_bh_enable(); }

@@ -265,7 +270,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, struct nft_counter *this_cpu; seqcount_t *myseq;

- preempt_disable(); + local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); myseq = this_cpu_ptr(&nft_counter_seq);

@@ -273,7 +278,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, this_cpu->packets += stats->pkts; this_cpu->bytes += stats->bytes; write_seqcount_end(myseq); - preempt_enable(); + local_bh_enable(); }

void nft_counter_init_seqcount(void) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 99d72543abd3..78d9961fcd44 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = { };

static const char * const ovs_drop_reasons[] = { -#define S(x) (#x), +#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x), OVS_DROP_REASONS(S) #undef S }; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edc72962ae63..0f8d581438c3 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; - int rc_drop = NET_XMIT_DROP;

/* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb);

/* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root_bh(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - rc_drop = NET_XMIT_SUCCESS; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC);

/* * Randomized packet corruption. @@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) - return rc_drop; + goto finish_segs; + segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); - return rc_drop; + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; }

qdisc_qstats_backlog_inc(sch, skb); @@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, }

finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { unsigned int len, last_len; - int nb; + int rc, nb;

len = skb ? skb->len : 0; nb = skb ? 1 : 0; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..0ff9b2dd86ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ static int vsock_dgram_connect(struct socket *sock, return err; }

+int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk;

- sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif

- return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);

@@ -2174,15 +2177,12 @@ static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, }

int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err;

sk = sock->sk; @@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; }

-#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2242,22 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg);

static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err;

if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE;

diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 47978efe4797..839d9c49f28c 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -5,8 +5,7 @@ * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. * - * Usage: kallsyms [--all-symbols] [--absolute-percpu] - * [--base-relative] [--lto-clang] in.map > out.S + * Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S * * Table compression uses all the unused char codes on the symbols and * maps these to the most used substrings (tokens). For instance, it might @@ -63,8 +62,6 @@ static struct sym_entry **table; static unsigned int table_size, table_cnt; static int all_symbols; static int absolute_percpu; -static int base_relative; -static int lto_clang;

static int token_profit[0x10000];

@@ -75,8 +72,7 @@ static unsigned char best_table_len[256];

static void usage(void) { - fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] " - "[--base-relative] [--lto-clang] in.map > out.S\n"); + fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n"); exit(1); }

@@ -259,12 +255,6 @@ static void shrink_table(void) } } table_cnt = pos; - - /* When valid symbol is not registered, exit to error */ - if (!table_cnt) { - fprintf(stderr, "No valid symbol.\n"); - exit(1); - } }

static void read_map(const char *in) @@ -352,25 +342,6 @@ static int symbol_absolute(const struct sym_entry *s) return s->percpu_absolute; }

-static void cleanup_symbol_name(char *s) -{ - char *p; - - /* - * ASCII[.] = 2e - * ASCII[0-9] = 30,39 - * ASCII[A-Z] = 41,5a - * ASCII[_] = 5f - * ASCII[a-z] = 61,7a - * - * As above, replacing the first '.' in ".llvm." with '\0' does not - * affect the main sorting, but it helps us with subsorting. - */ - p = strstr(s, ".llvm."); - if (p) - *p = '\0'; -} - static int compare_names(const void *a, const void *b) { int ret; @@ -497,58 +468,43 @@ static void write_src(void) printf("\t.short\t%d\n", best_idx[i]); printf("\n");

- if (!base_relative) - output_label("kallsyms_addresses"); - else - output_label("kallsyms_offsets"); + output_label("kallsyms_offsets");

for (i = 0; i < table_cnt; i++) { - if (base_relative) { - /* - * Use the offset relative to the lowest value - * encountered of all relative symbols, and emit - * non-relocatable fixed offsets that will be fixed - * up at runtime. - */ + /* + * Use the offset relative to the lowest value + * encountered of all relative symbols, and emit + * non-relocatable fixed offsets that will be fixed + * up at runtime. + */

- long long offset; - int overflow; - - if (!absolute_percpu) { - offset = table[i]->addr - relative_base; - overflow = (offset < 0 || offset > UINT_MAX); - } else if (symbol_absolute(table[i])) { - offset = table[i]->addr; - overflow = (offset < 0 || offset > INT_MAX); - } else { - offset = relative_base - table[i]->addr - 1; - overflow = (offset < INT_MIN || offset >= 0); - } - if (overflow) { - fprintf(stderr, "kallsyms failure: " - "%s symbol value %#llx out of range in relative mode\n", - symbol_absolute(table[i]) ? "absolute" : "relative", - table[i]->addr); - exit(EXIT_FAILURE); - } - printf("\t.long\t%#x /* %s */\n", (int)offset, table[i]->sym); - } else if (!symbol_absolute(table[i])) { - output_address(table[i]->addr); + long long offset; + int overflow; + + if (!absolute_percpu) { + offset = table[i]->addr - relative_base; + overflow = (offset < 0 || offset > UINT_MAX); + } else if (symbol_absolute(table[i])) { + offset = table[i]->addr; + overflow = (offset < 0 || offset > INT_MAX); } else { - printf("\tPTR\t%#llx\n", table[i]->addr); + offset = relative_base - table[i]->addr - 1; + overflow = (offset < INT_MIN || offset >= 0); + } + if (overflow) { + fprintf(stderr, "kallsyms failure: " + "%s symbol value %#llx out of range in relative mode\n", + symbol_absolute(table[i]) ? "absolute" : "relative", + table[i]->addr); + exit(EXIT_FAILURE); } + printf("\t.long\t%#x /* %s */\n", (int)offset, table[i]->sym); } printf("\n");

- if (base_relative) { - output_label("kallsyms_relative_base"); - output_address(relative_base); - printf("\n"); - } - - if (lto_clang) - for (i = 0; i < table_cnt; i++) - cleanup_symbol_name((char *)table[i]->sym); + output_label("kallsyms_relative_base"); + output_address(relative_base); + printf("\n");

sort_symbols_by_name(); output_label("kallsyms_seqs_of_names"); @@ -826,8 +782,6 @@ int main(int argc, char **argv) static const struct option long_options[] = { {"all-symbols", no_argument, &all_symbols, 1}, {"absolute-percpu", no_argument, &absolute_percpu, 1}, - {"base-relative", no_argument, &base_relative, 1}, - {"lto-clang", no_argument, &lto_clang, 1}, {}, };

@@ -847,8 +801,7 @@ int main(int argc, char **argv) if (absolute_percpu) make_percpus_absolute(); sort_symbols(); - if (base_relative) - record_relative_base(); + record_relative_base(); optimize_token_table(); write_src();

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 518c70b8db50..070a319140e8 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -45,7 +45,6 @@ info()

# Link of vmlinux # ${1} - output file -# ${2}, ${3}, ... - optional extra .o files vmlinux_link() { local output=${1} @@ -90,7 +89,7 @@ vmlinux_link() ldflags="${ldflags} ${wl}--script=${objtree}/${KBUILD_LDS}"

# The kallsyms linking does not need debug symbols included. - if [ "$output" != "${output#.tmp_vmlinux.kallsyms}" ] ; then + if [ -n "${strip_debug}" ] ; then ldflags="${ldflags} ${wl}--strip-debug" fi

@@ -101,15 +100,15 @@ vmlinux_link() ${ld} ${ldflags} -o ${output} \ ${wl}--whole-archive ${objs} ${wl}--no-whole-archive \ ${wl}--start-group ${libs} ${wl}--end-group \ - $@ ${ldlibs} + ${kallsymso} ${btf_vmlinux_bin_o} ${ldlibs} }

# generate .BTF typeinfo from DWARF debuginfo # ${1} - vmlinux image -# ${2} - file to dump raw BTF data into gen_btf() { local pahole_ver + local btf_data=${1}.btf.o

if ! [ -x "$(command -v ${PAHOLE})" ]; then echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available" @@ -122,18 +121,16 @@ gen_btf() return 1 fi

- vmlinux_link ${1} - - info "BTF" ${2} + info BTF "${btf_data}" LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${PAHOLE_FLAGS} ${1}

- # Create ${2} which contains just .BTF section but no symbols. Add + # Create ${btf_data} which contains just .BTF section but no symbols. Add # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all # deletes all symbols including __start_BTF and __stop_BTF, which will # be redefined in the linker script. Add 2>/dev/null to suppress GNU # objcopy warnings: "empty loadable segment detected at ..." ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \ - --strip-all ${1} ${2} 2>/dev/null + --strip-all ${1} "${btf_data}" 2>/dev/null # Change e_type to ET_REL so that it can be used to link final vmlinux. # GNU ld 2.35+ and lld do not allow an ET_EXEC input. if is_enabled CONFIG_CPU_BIG_ENDIAN; then @@ -141,10 +138,12 @@ gen_btf() else et_rel='\1\0' fi - printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none + printf "${et_rel}" | dd of="${btf_data}" conv=notrunc bs=1 seek=16 status=none + + btf_vmlinux_bin_o=${btf_data} }

-# Create ${2} .S file with all symbols from the ${1} object file +# Create ${2}.o file with all symbols from the ${1} object file kallsyms() { local kallsymopt; @@ -157,35 +156,23 @@ kallsyms() kallsymopt="${kallsymopt} --absolute-percpu" fi

- if is_enabled CONFIG_KALLSYMS_BASE_RELATIVE; then - kallsymopt="${kallsymopt} --base-relative" - fi + info KSYMS "${2}.S" + scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"

- if is_enabled CONFIG_LTO_CLANG; then - kallsymopt="${kallsymopt} --lto-clang" - fi + info AS "${2}.o" + ${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \ + ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} -c -o "${2}.o" "${2}.S"

- info KSYMS ${2} - scripts/kallsyms ${kallsymopt} ${1} > ${2} + kallsymso=${2}.o }

-# Perform one step in kallsyms generation, including temporary linking of -# vmlinux. -kallsyms_step() +# Perform kallsyms for the given temporary vmlinux. +sysmap_and_kallsyms() { - kallsymso_prev=${kallsymso} - kallsyms_vmlinux=.tmp_vmlinux.kallsyms${1} - kallsymso=${kallsyms_vmlinux}.o - kallsyms_S=${kallsyms_vmlinux}.S + mksysmap "${1}" "${1}.syms" + kallsyms "${1}.syms" "${1}.kallsyms"

- vmlinux_link ${kallsyms_vmlinux} "${kallsymso_prev}" ${btf_vmlinux_bin_o} - mksysmap ${kallsyms_vmlinux} ${kallsyms_vmlinux}.syms - kallsyms ${kallsyms_vmlinux}.syms ${kallsyms_S} - - info AS ${kallsymso} - ${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \ - ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \ - -c -o ${kallsymso} ${kallsyms_S} + kallsyms_sysmap=${1}.syms }

# Create map file with all symbols from ${1} @@ -223,26 +210,41 @@ fi

${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init init/version-timestamp.o

-btf_vmlinux_bin_o="" +btf_vmlinux_bin_o= +kallsymso= +strip_debug= + +if is_enabled CONFIG_KALLSYMS; then + truncate -s0 .tmp_vmlinux.kallsyms0.syms + kallsyms .tmp_vmlinux.kallsyms0.syms .tmp_vmlinux0.kallsyms +fi + +if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then + + # The kallsyms linking does not need debug symbols, but the BTF does. + if ! is_enabled CONFIG_DEBUG_INFO_BTF; then + strip_debug=1 + fi + + vmlinux_link .tmp_vmlinux1 +fi + if is_enabled CONFIG_DEBUG_INFO_BTF; then - btf_vmlinux_bin_o=.btf.vmlinux.bin.o - if ! gen_btf .tmp_vmlinux.btf $btf_vmlinux_bin_o ; then + if ! gen_btf .tmp_vmlinux1; then echo >&2 "Failed to generate BTF for vmlinux" echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF" exit 1 fi fi

-kallsymso="" -kallsymso_prev="" -kallsyms_vmlinux="" if is_enabled CONFIG_KALLSYMS; then

# kallsyms support # Generate section listing all symbols and add it into vmlinux - # It's a three step process: + # It's a four step process: + # 0) Generate a dummy __kallsyms with empty symbol list. # 1) Link .tmp_vmlinux.kallsyms1 so it has all symbols and sections, - # but __kallsyms is empty. + # with a dummy __kallsyms. # Running kallsyms on that gives us .tmp_kallsyms1.o with # the right size # 2) Link .tmp_vmlinux.kallsyms2 so it now has a __kallsyms section of @@ -261,19 +263,25 @@ if is_enabled CONFIG_KALLSYMS; then # a) Verify that the System.map from vmlinux matches the map from # ${kallsymso}.

- kallsyms_step 1 - kallsyms_step 2 + # The kallsyms linking does not need debug symbols included. + strip_debug=1 + + sysmap_and_kallsyms .tmp_vmlinux1 + size1=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})

- # step 3 - size1=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso_prev}) + vmlinux_link .tmp_vmlinux2 + sysmap_and_kallsyms .tmp_vmlinux2 size2=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})

if [ $size1 -ne $size2 ] || [ -n "${KALLSYMS_EXTRA_PASS}" ]; then - kallsyms_step 3 + vmlinux_link .tmp_vmlinux3 + sysmap_and_kallsyms .tmp_vmlinux3 fi fi

-vmlinux_link vmlinux "${kallsymso}" ${btf_vmlinux_bin_o} +strip_debug= + +vmlinux_link vmlinux

# fill in BTF IDs if is_enabled CONFIG_DEBUG_INFO_BTF && is_enabled CONFIG_BPF; then @@ -293,7 +301,7 @@ fi

# step a (see comment above) if is_enabled CONFIG_KALLSYMS; then - if ! cmp -s System.map ${kallsyms_vmlinux}.syms; then + if ! cmp -s System.map "${kallsyms_sysmap}"; then echo >&2 Inconsistent kallsyms data echo >&2 'Try "make KALLSYMS_EXTRA_PASS=1" as a workaround' exit 1 diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index 117018946b57..a6fdcf13e0e5 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -129,8 +129,12 @@ fi # Check that the Rust bindings generator is suitable. # # Non-stable and distributions' versions may have a version suffix, e.g. `-dev`. +# +# The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 +# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when +# the minimum version is upgraded past that (0.69.1 already fixed the issue). rust_bindings_generator_output=$( \ - LC_ALL=C "$BINDGEN" --version 2>/dev/null + LC_ALL=C "$BINDGEN" --version workaround-for-0.69.0 2>/dev/null ) || rust_bindings_generator_code=$? if [ -n "$rust_bindings_generator_code" ]; then echo >&2 "***" diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c index b5f81a05be36..4edc5bbbcda3 100644 --- a/security/keys/trusted-keys/trusted_dcp.c +++ b/security/keys/trusted-keys/trusted_dcp.c @@ -186,20 +186,21 @@ static int do_aead_crypto(u8 *in, u8 *out, size_t len, u8 *key, u8 *nonce, return ret; }

-static int decrypt_blob_key(u8 *key) +static int decrypt_blob_key(u8 *encrypted_key, u8 *plain_key) { - return do_dcp_crypto(key, key, false); + return do_dcp_crypto(encrypted_key, plain_key, false); }

-static int encrypt_blob_key(u8 *key) +static int encrypt_blob_key(u8 *plain_key, u8 *encrypted_key) { - return do_dcp_crypto(key, key, true); + return do_dcp_crypto(plain_key, encrypted_key, true); }

static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; int blen, ret; + u8 plain_blob_key[AES_KEYSIZE_128];

blen = calc_blob_len(p->key_len); if (blen > MAX_BLOB_SIZE) @@ -207,30 +208,36 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob)

b->fmt_version = DCP_BLOB_VERSION; get_random_bytes(b->nonce, AES_KEYSIZE_128); - get_random_bytes(b->blob_key, AES_KEYSIZE_128); + get_random_bytes(plain_blob_key, AES_KEYSIZE_128);

- ret = do_aead_crypto(p->key, b->payload, p->key_len, b->blob_key, + ret = do_aead_crypto(p->key, b->payload, p->key_len, plain_blob_key, b->nonce, true); if (ret) { pr_err("Unable to encrypt blob payload: %i\n", ret); - return ret; + goto out; }

- ret = encrypt_blob_key(b->blob_key); + ret = encrypt_blob_key(plain_blob_key, b->blob_key); if (ret) { pr_err("Unable to encrypt blob key: %i\n", ret); - return ret; + goto out; }

- b->payload_len = get_unaligned_le32(&p->key_len); + put_unaligned_le32(p->key_len, &b->payload_len); p->blob_len = blen; - return 0; + ret = 0; + +out: + memzero_explicit(plain_blob_key, sizeof(plain_blob_key)); + + return ret; }

static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) { struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob; int blen, ret; + u8 plain_blob_key[AES_KEYSIZE_128];

if (b->fmt_version != DCP_BLOB_VERSION) { pr_err("DCP blob has bad version: %i, expected %i\n", @@ -248,14 +255,14 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob) goto out; }

- ret = decrypt_blob_key(b->blob_key); + ret = decrypt_blob_key(b->blob_key, plain_blob_key); if (ret) { pr_err("Unable to decrypt blob key: %i\n", ret); goto out; }

ret = do_aead_crypto(b->payload, p->key, p->key_len + DCP_BLOB_AUTHLEN, - b->blob_key, b->nonce, false); + plain_blob_key, b->nonce, false); if (ret) { pr_err("Unwrap of DCP payload failed: %i\n", ret); goto out; @@ -263,6 +270,8 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)

ret = 0; out: + memzero_explicit(plain_blob_key, sizeof(plain_blob_key)); + return ret; }

diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 32eb67fb3e42..b49c44869dc4 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -330,12 +330,12 @@ static int avc_add_xperms_decision(struct avc_node *node, { struct avc_xperms_decision_node *dest_xpd;

- node->ae.xp_node->xp.len++; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); + node->ae.xp_node->xp.len++; return 0; }

@@ -907,7 +907,11 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: - avc_add_xperms_decision(node, xpd); + rc = avc_add_xperms_decision(node, xpd); + if (rc) { + avc_node_kill(node); + goto out_unlock; + } break; } avc_node_replace(node, orig); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 55c78c318ccd..bfa61e005aac 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3852,7 +3852,17 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; - if (vma_is_initial_heap(vma)) { + /* + * We don't use the vma_is_initial_heap() helper as it has + * a history of problems and is currently broken on systems + * where there is no heap, e.g. brk == start_brk. Before + * replacing the conditional below with vma_is_initial_heap(), + * or something similar, please ensure that the logic is the + * same as what we have below or you have tested every possible + * corner case you can think to test. + */ + if (vma->vm_start >= vma->vm_mm->start_brk && + vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || diff --git a/sound/core/timer.c b/sound/core/timer.c index d104adc75a8b..71a07c1662f5 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -547,7 +547,7 @@ static int snd_timer_start1(struct snd_timer_instance *timeri, /* check the actual time for the start tick; * bail out as error if it's way too low (< 100us) */ - if (start) { + if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) { if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) return -EINVAL; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3840565ef8b0..c9d76bca9923 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -583,7 +583,6 @@ static void alc_shutup_pins(struct hda_codec *codec) switch (codec->core.vendor_id) { case 0x10ec0236: case 0x10ec0256: - case 0x10ec0257: case 0x19e58326: case 0x10ec0283: case 0x10ec0285: diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index fdee6592c502..9e88d39eac1e 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -2,10 +2,12 @@ // // TAS2781 HDA I2C driver // -// Copyright 2023 Texas Instruments, Inc. +// Copyright 2023 - 2024 Texas Instruments, Inc. // // Author: Shenghao Ding shenghao-ding@ti.com +// Current maintainer: Baojun Xu baojun.xu@ti.com

+#include <asm/unaligned.h> #include <linux/acpi.h> #include <linux/crc8.h> #include <linux/crc32.h> @@ -519,20 +521,22 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) static const unsigned char rgno_array[CALIB_MAX] = { 0x74, 0x0c, 0x14, 0x70, 0x7c, }; - unsigned char *data; + int offset = 0; int i, j, rc; + __be32 data;

for (i = 0; i < tas_priv->ndev; i++) { - data = tas_priv->cali_data.data + - i * TASDEVICE_SPEAKER_CALIBRATION_SIZE; for (j = 0; j < CALIB_MAX; j++) { + data = cpu_to_be32( + *(uint32_t *)&tas_priv->cali_data.data[offset]); rc = tasdevice_dev_bulk_write(tas_priv, i, TASDEVICE_REG(0, page_array[j], rgno_array[j]), - &(data[4 * j]), 4); + (unsigned char *)&data, 4); if (rc < 0) dev_err(tas_priv->dev, "chn %d calib %d bulk_wr err = %d\n", i, j, rc); + offset += 4; } } } diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index f13a8d63a019..aaa6a515d0f8 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -273,6 +273,7 @@ YAMAHA_DEVICE(0x105a, NULL), YAMAHA_DEVICE(0x105b, NULL), YAMAHA_DEVICE(0x105c, NULL), YAMAHA_DEVICE(0x105d, NULL), +YAMAHA_DEVICE(0x1718, "P-125"), { USB_DEVICE(0x0499, 0x1503), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ea063a14cdd8..e7b68c67852e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2221,6 +2221,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */ diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index e30fd55f8e51..cd3b480d20bd 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -26,7 +26,6 @@ static bool is_ignored_symbol(const char *name, char type) * when --all-symbols is specified so exclude them to get a * stable symbol list. */ - "kallsyms_addresses", "kallsyms_offsets", "kallsyms_relative_base", "kallsyms_num_syms", diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index fe65e0952a1e..179bfe25dbc6 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1434,4 +1434,58 @@ int iter_arr_with_actual_elem_count(const void *ctx) return sum; }

+__u32 upper, select_n, result; +__u64 global; + +static __noinline bool nest_2(char *str) +{ + /* some insns (including branch insns) to ensure stacksafe() is triggered + * in nest_2(). This way, stacksafe() can compare frame associated with nest_1(). + */ + if (str[0] == 't') + return true; + if (str[1] == 'e') + return true; + if (str[2] == 's') + return true; + if (str[3] == 't') + return true; + return false; +} + +static __noinline bool nest_1(int n) +{ + /* case 0: allocate stack, case 1: no allocate stack */ + switch (n) { + case 0: { + char comm[16]; + + if (bpf_get_current_comm(comm, 16)) + return false; + return nest_2(comm); + } + case 1: + return nest_2((char *)&global); + default: + return false; + } +} + +SEC("raw_tp") +__success +int iter_subprog_check_stacksafe(const void *ctx) +{ + long i; + + bpf_for(i, 0, upper) { + if (!nest_1(select_n)) { + result = 1; + return 0; + } + } + + result = 2; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 991c473e3859..12b4eb9d0434 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot) EXPECT_EQ(close(fd3), 0); }

+TEST(close_range_bitmap_corruption) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* get the first 128 descriptors open */ + for (int i = 2; i < 128; i++) + EXPECT_GE(dup2(0, i), 0); + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* unshare and truncate descriptor table down to 64 */ + if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE)) + exit(EXIT_FAILURE); + + ASSERT_EQ(fcntl(64, F_GETFD), -1); + /* ... and verify that the range 64..127 is not + stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh index 877cd6df94a1..fe905a7f34b3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh @@ -2,6 +2,7 @@ # SPDX-License-Identifier: GPL-2.0

lib_dir=$(dirname $0)/../../../net/forwarding +ethtool_lib_dir=$(dirname $0)/../hw

ALL_TESTS=" autoneg @@ -11,7 +12,7 @@ ALL_TESTS=" NUM_NETIFS=2 : ${TIMEOUT:=30000} # ms source $lib_dir/lib.sh -source $lib_dir/ethtool_lib.sh +source $ethtool_lib_dir/ethtool_lib.sh

setup_prepare() { diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 478cd26f62fd..1285b82fbd8a 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -51,7 +51,9 @@ TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate +ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64)) TEST_GEN_FILES += memfd_secret +endif TEST_GEN_FILES += migration TEST_GEN_FILES += mkdirty TEST_GEN_FILES += mlock-random-test diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 3157204b9047..1c7cdfd29fcc 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -367,8 +367,11 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate

+if [ -x ./memfd_secret ] +then (echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix CATEGORY="memfd_secret" run_test ./memfd_secret +fi

# KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 CATEGORY="ksm" run_test ./ksm_tests -H -s 100 diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 16d0c172eaeb..535eb2c3d7d1 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata,

static void __recvpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, - const void *expected_buf, int expected_len, + const char *expected_buf, int expected_len, int buf_len, int flags) { int i, ret[2], recv_errno[2], expected_errno = 0; diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 9155c914c064..93de05fedd91 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -128,25 +128,18 @@ slowwait_for_counter() cleanup_ns() { local ns="" - local errexit=0 local ret=0

- # disable errexit temporary - if [[ $- =~ "e" ]]; then - errexit=1 - set +e - fi - for ns in "$@"; do [ -z "${ns}" ] && continue - ip netns delete "${ns}" &> /dev/null + ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true + ip netns delete "${ns}" &> /dev/null || true if ! busywait $BUSYWAIT_TIMEOUT ip netns list | grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" ret=1 fi done

- [ $errexit -eq 1 ] && set -e return $ret }

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index a3293043c85d..ed30c0ed55e7 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -436,9 +436,10 @@ reset_with_tcp_filter() local ns="${!1}" local src="${2}" local target="${3}" + local chain="${4:-INPUT}"

if ! ip netns exec "${ns}" ${iptables} \ - -A INPUT \ + -A "${chain}" \ -s "${src}" \ -p tcp \ -j "${target}"; then @@ -3058,6 +3059,7 @@ fullmesh_tests() pm_nl_set_limits $ns1 1 3 pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh fullmesh=1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 @@ -3571,10 +3573,10 @@ endpoint_tests() mptcp_lib_kill_wait $tests_pid fi

- if reset "delete and re-add" && + if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow test_linkfail=4 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & @@ -3591,11 +3593,27 @@ endpoint_tests() chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0

- pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 + + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_attempt_fail $ns2 + chk_subflow_nr "after new reject" 2 + chk_mptcp_info subflows 1 subflows 1 + + ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT + pm_nl_del_endpoint $ns2 3 10.0.3.2 + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_mpj $ns2 + chk_subflow_nr "after no reject" 3 + chk_mptcp_info subflows 2 subflows 2 + mptcp_lib_kill_wait $tests_pid + + chk_join_nr 3 3 3 + chk_rm_nr 1 1 fi }

diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 11a1ebda564f..d5ffd8c9172e 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -7,8 +7,6 @@ source net_helper.sh

readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"

-BPF_FILE="xdp_dummy.bpf.o" - # set global exit status, but never reset nonzero one. check_err() { @@ -38,7 +36,7 @@ cfg_veth() { ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad ip -netns "${PEER_NS}" link set dev veth1 up - ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp + ip netns exec "${PEER_NS}" ethtool -K veth1 gro on }

run_one() { @@ -46,17 +44,19 @@ run_one() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0

cfg_veth

- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \ - echo "ok" || \ - echo "failed" & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} & + local PID1=$!

wait_local_port_listen ${PEER_NS} 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - wait $(jobs -p) + check_err $? + wait ${PID1} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret }

@@ -73,6 +73,7 @@ run_one_nat() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0

if [[ ${tx_args} = *-4* ]]; then ipt_cmd=iptables @@ -93,16 +94,17 @@ run_one_nat() { # ... so that GRO will match the UDP_GRO enabled socket, but packets # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & - pid=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \ - echo "ok" || \ - echo "failed"& + local PID1=$! + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} & + local PID2=$!

wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - kill -INT $pid - wait $(jobs -p) + check_err $? + kill -INT ${PID1} + wait ${PID2} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret }

@@ -111,20 +113,26 @@ run_one_2sock() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0

cfg_veth

ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \ - echo "ok" || \ - echo "failed" & + local PID1=$! + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} & + local PID2=$!

wait_local_port_listen "${PEER_NS}" 12345 udp ./udpgso_bench_tx ${tx_args} -p 12345 + check_err $? wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - wait $(jobs -p) + check_err $? + wait ${PID1} + check_err $? + wait ${PID2} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret }

@@ -196,11 +204,6 @@ run_all() { return $ret }

-if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Run 'make' first" - exit -1 -fi - if [[ $# -eq 0 ]]; then run_all elif [[ $1 == "__subprocess" ]]; then diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index ee349187636f..4f255cec0c22 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -143,7 +143,6 @@ class PluginMgr: except Exception as ee: print('exception {} in call to pre_case for {} plugin'. format(ee, pgn_inst.__class__)) - print('test_ordinal is {}'.format(test_ordinal)) print('testid is {}'.format(caseinfo['id'])) raise

diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index 07ba55d4ec06..de33ea5005b6 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -640,8 +640,10 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params) return NULL;

tool->data = osnoise_alloc_top(nr_cpus); - if (!tool->data) - goto out_err; + if (!tool->data) { + osnoise_destroy_tool(tool); + return NULL; + }

tool->params = params;

@@ -649,11 +651,6 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params) osnoise_top_handler, NULL);

return tool; - -out_err: - osnoise_free_top(tool->data); - osnoise_destroy_tool(tool); - return NULL; }

static int stop_tracing;