diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 533415644c54d..a78350a8fed43 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -39,7 +39,7 @@ Documentation written by Tom Zanussi will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound - keys consisting of up to two fields can be specified by the 'keys' + keys consisting of up to three fields can be specified by the 'keys' keyword. Hashing a compound key produces a unique entry in the table for each unique combination of component keys, and can be useful for providing more fine-grained summaries of event data. diff --git a/Makefile b/Makefile index 3e712ea4c745d..397dcb7af1c85 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 15 -SUBLEVEL = 77 +SUBLEVEL = 78 EXTRAVERSION = NAME = Trick or Treat diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi index 68e5ab2e27e22..6bb4855d13ce5 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi @@ -29,7 +29,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = ; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi index 8e23cec7149e5..696427b487f01 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi @@ -26,7 +26,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = ; }; diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 34e5549ea748a..a00b0f14c222f 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -597,12 +597,26 @@ polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 0>; + trips { + pmic_crit0: trip0 { + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; soc { polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 3>; + trips { + soc_crit0: trip0 { + temperature = <80000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; big_cluster_thermal_zone: big-cluster { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index 6050723172436..63441028622a6 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -758,6 +758,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; @@ -767,6 +770,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index 1282b61da8a55..12e59777363fe 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -525,6 +525,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -534,6 +537,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 51c4f61007cdb..1bc7f538f6905 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1369,6 +1369,9 @@ #address-cells = <1>; #size-cells = <0>; little-endian; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -1379,6 +1382,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index a79f42a9618ec..639220dbff008 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -38,9 +38,9 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc0_lpcg IMX_LPCG_CLK_0>, + <&sdhc0_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; }; @@ -49,9 +49,9 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc1_lpcg IMX_LPCG_CLK_0>, + <&sdhc1_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; fsl,tuning-step= <2>; @@ -62,9 +62,9 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc2_lpcg IMX_LPCG_CLK_0>, + <&sdhc2_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; }; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 60225bc09b017..8ecca795aca0b 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -320,7 +320,8 @@ static void cortex_a76_erratum_1463225_svc_handler(void) __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0); } -static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static __always_inline bool +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) return false; diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index c5d0097154020..aa06e28f2991f 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -13,6 +13,7 @@ #include #include #include +#include #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) #error Hypervisor code only! @@ -115,7 +116,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, new |= (old & PSR_C_BIT); new |= (old & PSR_V_BIT); - if (kvm_has_mte(vcpu->kvm)) + if (kvm_has_mte(kern_hyp_va(vcpu->kvm))) new |= PSR_TCO_BIT; new |= (old & PSR_DIT_BIT); diff --git a/arch/parisc/include/asm/hardware.h b/arch/parisc/include/asm/hardware.h index 9d3d7737c58b1..a005ebc547793 100644 --- a/arch/parisc/include/asm/hardware.h +++ b/arch/parisc/include/asm/hardware.h @@ -10,12 +10,12 @@ #define SVERSION_ANY_ID PA_SVERSION_ANY_ID struct hp_hardware { - unsigned short hw_type:5; /* HPHW_xxx */ - unsigned short hversion; - unsigned long sversion:28; - unsigned short opt; - const char name[80]; /* The hardware description */ -}; + unsigned int hw_type:8; /* HPHW_xxx */ + unsigned int hversion:12; + unsigned int sversion:12; + unsigned char opt; + unsigned char name[59]; /* The hardware description */ +} __packed; struct parisc_device; diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index d126e78e101ae..e7ee0c0c91d35 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -882,15 +882,13 @@ void __init walk_central_bus(void) &root); } -static void print_parisc_device(struct parisc_device *dev) +static __init void print_parisc_device(struct parisc_device *dev) { - char hw_path[64]; - static int count; + static int count __initdata; - print_pa_hwpath(dev, hw_path); - pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }", - ++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type, - dev->id.hversion_rev, dev->id.hversion, dev->id.sversion); + pr_info("%d. %s at %pap { type:%d, hv:%#x, sv:%#x, rev:%#x }", + ++count, dev->name, &(dev->hpa.start), dev->id.hw_type, + dev->id.hversion, dev->id.sversion, dev->id.hversion_rev); if (dev->num_addrs) { int k; @@ -1079,7 +1077,7 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) -static int print_one_device(struct device * dev, void * data) +static __init int print_one_device(struct device * dev, void * data) { struct parisc_device * pdev = to_parisc_device(dev); diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S index 918e05137d4c6..1686a852534fc 100644 --- a/arch/s390/boot/compressed/vmlinux.lds.S +++ b/arch/s390/boot/compressed/vmlinux.lds.S @@ -93,8 +93,17 @@ SECTIONS _compressed_start = .; *(.vmlinux.bin.compressed) _compressed_end = .; - FILL(0xff); - . = ALIGN(4096); + } + +#define SB_TRAILER_SIZE 32 + /* Trailer needed for Secure Boot */ + . += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */ + . = ALIGN(4096) - SB_TRAILER_SIZE; + .sb.trailer : { + QUAD(0) + QUAD(0) + QUAD(0) + QUAD(0x000000207a49504c) } _end = .; diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index a596e69d3c474..0b012ce0921c1 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -212,7 +212,7 @@ static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size asm volatile( " llilh 0,%[spec]\n" "0: .insn ss,0xc80000000000,0(%0,%1),0(%4),0\n" - " jz 4f\n" + "6: jz 4f\n" "1: algr %0,%2\n" " slgr %1,%2\n" " j 0b\n" @@ -222,11 +222,11 @@ static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size " clgr %0,%3\n" /* copy crosses next page boundary? */ " jnh 5f\n" "3: .insn ss,0xc80000000000,0(%3,%1),0(%4),0\n" - " slgr %0,%3\n" + "7: slgr %0,%3\n" " j 5f\n" "4: slgr %0,%0\n" "5:\n" - EX_TABLE(0b,2b) EX_TABLE(3b,5b) + EX_TABLE(0b,2b) EX_TABLE(6b,2b) EX_TABLE(3b,5b) EX_TABLE(7b,5b) : "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2) : "a" (empty_zero_page), [spec] "K" (0x81UL) : "cc", "memory", "0"); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 588b83cc730d3..f36fda2672e04 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4713,6 +4713,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 266ac8263696a..21a9cb48daf5d 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -936,8 +936,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ @@ -958,8 +963,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), INTEL_PSD_CONSTRAINT(0x2cd, 0x1), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 6a2827d0681fc..e8ab7c1f1080a 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,7 +6,7 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H -struct pt_regs; +#include extern long __x64_sys_ni_syscall(const struct pt_regs *regs); extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d85a0808a446e..05b27b4a54c9d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -902,11 +902,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = min(entry->eax, 0x8000001f); break; case 0x80000001: + entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000006: - /* L2 cache and TLB: pass through host info. */ + /* Drop reserved bits, pass host L2 cache and TLB info. */ + entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ @@ -936,6 +938,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); + entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; @@ -955,6 +958,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = entry->edx = 0; break; case 0x8000001a: + entry->eax &= GENMASK(2, 0); + entry->ebx = entry->ecx = entry->edx = 0; + break; case 0x8000001e: break; case 0x8000001F: @@ -962,7 +968,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = entry->edx = 0; } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); - + /* Clear NumVMPL since KVM does not support VMPL. */ + entry->ebx &= ~GENMASK(31, 12); /* * Enumerate '0' for "PA bits reduction", the adjusted * MAXPHYADDR is enumerated directly (see 0x80000008). diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 45d82a9501328..cb96e4354f317 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -795,8 +795,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ctxt->mode, linear); } -static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -806,41 +805,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } +static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); } -static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt); -#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc; - ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -2153,7 +2182,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2234,7 +2263,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2617,7 +2646,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) * those side effects need to be explicitly handled for both success * and shutdown. */ - return X86EMUL_CONTINUE; + return emulator_recalc_and_set_mode(ctxt); emulate_shutdown: ctxt->ops->triple_fault(ctxt); @@ -2861,6 +2890,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; + ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; @@ -3457,7 +3487,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; @@ -3599,11 +3629,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt) static int em_cr_write(struct x86_emulate_ctxt *ctxt) { - if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + int cr_num = ctxt->modrm_reg; + int r; + + if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; + + if (cr_num == 0) { + /* + * CR0 write might have updated CR0.PE and/or CR0.PG + * which can affect the cpu's execution mode. + */ + r = emulator_recalc_and_set_mode(ctxt); + if (r != X86EMUL_CONTINUE) + return r; + } + return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 03ebe368333ef..c41506ed8c7dd 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -355,25 +355,29 @@ TRACE_EVENT(kvm_inj_virq, * Tracepoint for kvm interrupt injection: */ TRACE_EVENT(kvm_inj_exception, - TP_PROTO(unsigned exception, bool has_error, unsigned error_code), - TP_ARGS(exception, has_error, error_code), + TP_PROTO(unsigned exception, bool has_error, unsigned error_code, + bool reinjected), + TP_ARGS(exception, has_error, error_code, reinjected), TP_STRUCT__entry( __field( u8, exception ) __field( u8, has_error ) __field( u32, error_code ) + __field( bool, reinjected ) ), TP_fast_assign( __entry->exception = exception; __entry->has_error = has_error; __entry->error_code = error_code; + __entry->reinjected = reinjected; ), - TP_printk("%s (0x%x)", + TP_printk("%s (0x%x)%s", __print_symbolic(__entry->exception, kvm_trace_sym_exc), /* FIXME: don't print error_code if not present */ - __entry->has_error ? __entry->error_code : 0) + __entry->has_error ? __entry->error_code : 0, + __entry->reinjected ? " [reinjected]" : "") ); /* diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ba457167ae8a2..6918f597b8ab7 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7902,6 +7902,11 @@ static __init int hardware_setup(void) if (!cpu_has_virtual_nmis()) enable_vnmi = 0; +#ifdef CONFIG_X86_SGX_KVM + if (!cpu_has_vmx_encls_vmexit()) + enable_sgx = false; +#endif + /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8648799d48f8b..ec2a37ba07e66 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -525,6 +525,7 @@ static int exception_class(int vector) #define EXCPT_TRAP 1 #define EXCPT_ABORT 2 #define EXCPT_INTERRUPT 3 +#define EXCPT_DB 4 static int exception_type(int vector) { @@ -535,8 +536,14 @@ static int exception_type(int vector) mask = 1 << vector; - /* #DB is trap, as instruction watchpoints are handled elsewhere */ - if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR))) + /* + * #DBs can be trap-like or fault-like, the caller must check other CPU + * state, e.g. DR6, to determine whether a #DB is a trap or fault. + */ + if (mask & (1 << DB_VECTOR)) + return EXCPT_DB; + + if (mask & ((1 << BP_VECTOR) | (1 << OF_VECTOR))) return EXCPT_TRAP; if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR))) @@ -5763,6 +5770,11 @@ split_irqchip_unlock: r = 0; break; case KVM_CAP_X86_USER_SPACE_MSR: + r = -EINVAL; + if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER)) + break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; @@ -5883,23 +5895,22 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, return 0; } -static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) +static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, + struct kvm_msr_filter *filter) { - struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_x86_msr_filter *new_filter, *old_filter; - struct kvm_msr_filter filter; bool default_allow; bool empty = true; int r = 0; u32 i; - if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) - return -EFAULT; + if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + return -EINVAL; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) - empty &= !filter.ranges[i].nmsrs; + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) + empty &= !filter->ranges[i].nmsrs; - default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY); + default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL; @@ -5907,8 +5918,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (!new_filter) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { + r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); if (r) { kvm_free_msr_filter(new_filter); return r; @@ -5931,6 +5942,62 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) return 0; } +#ifdef CONFIG_KVM_COMPAT +/* for KVM_X86_SET_MSR_FILTER */ +struct kvm_msr_filter_range_compat { + __u32 flags; + __u32 nmsrs; + __u32 base; + __u32 bitmap; +}; + +struct kvm_msr_filter_compat { + __u32 flags; + struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES]; +}; + +#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat) + +long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct kvm *kvm = filp->private_data; + long r = -ENOTTY; + + switch (ioctl) { + case KVM_X86_SET_MSR_FILTER_COMPAT: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter_compat filter_compat; + struct kvm_msr_filter filter; + int i; + + if (copy_from_user(&filter_compat, user_msr_filter, + sizeof(filter_compat))) + return -EFAULT; + + filter.flags = filter_compat.flags; + for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { + struct kvm_msr_filter_range_compat *cr; + + cr = &filter_compat.ranges[i]; + filter.ranges[i] = (struct kvm_msr_filter_range) { + .flags = cr->flags, + .nmsrs = cr->nmsrs, + .base = cr->base, + .bitmap = (__u8 *)(ulong)cr->bitmap, + }; + } + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); + break; + } + } + + return r; +} +#endif + #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_arch_suspend_notifier(struct kvm *kvm) { @@ -6305,9 +6372,16 @@ set_pit2_out: case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; - case KVM_X86_SET_MSR_FILTER: - r = kvm_vm_ioctl_set_msr_filter(kvm, argp); + case KVM_X86_SET_MSR_FILTER: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter filter; + + if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) + return -EFAULT; + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; + } default: r = -ENOTTY; } @@ -8134,6 +8208,12 @@ restart: unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + + /* + * Note, EXCPT_DB is assumed to be fault-like as the emulator + * only supports code breakpoints and general detect #DB, both + * of which are fault-like. + */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { kvm_rip_write(vcpu, ctxt->eip); @@ -9010,6 +9090,11 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu) static void kvm_inject_exception(struct kvm_vcpu *vcpu) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code, + vcpu->arch.exception.injected); + if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) vcpu->arch.exception.error_code = false; static_call(kvm_x86_queue_exception)(vcpu); @@ -9067,13 +9152,16 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) /* try to inject new event if pending */ if (vcpu->arch.exception.pending) { - trace_kvm_inj_exception(vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); - - vcpu->arch.exception.pending = false; - vcpu->arch.exception.injected = true; - + /* + * Fault-class exceptions, except #DBs, set RF=1 in the RFLAGS + * value pushed on the stack. Trap-like exception and all #DBs + * leave RF as-is (KVM follows Intel's behavior in this regard; + * AMD states that code breakpoint #DBs excplitly clear RF=0). + * + * Note, most versions of Intel's SDM and AMD's APM incorrectly + * describe the behavior of General Detect #DBs, which are + * fault-like. They do _not_ set RF, a la code breakpoints. + */ if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); @@ -9087,6 +9175,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) } kvm_inject_exception(vcpu); + + vcpu->arch.exception.pending = false; + vcpu->arch.exception.injected = true; + can_inject = false; } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 4b862f18f4b2e..7d8fe13573f64 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -461,6 +461,8 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd, */ void bfq_schedule_dispatch(struct bfq_data *bfqd) { + lockdep_assert_held(&bfqd->lock); + if (bfqd->queued != 0) { bfq_log(bfqd, "schedule dispatch"); blk_mq_run_hw_queues(bfqd->queue, true); @@ -6745,8 +6747,8 @@ bfq_idle_slice_timer_body(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_bfqq_expire(bfqd, bfqq, true, reason); schedule_dispatch: - spin_unlock_irqrestore(&bfqd->lock, flags); bfq_schedule_dispatch(bfqd); + spin_unlock_irqrestore(&bfqd->lock, flags); } /* diff --git a/block/genhd.c b/block/genhd.c index 74e19d67ceab5..68065189ca176 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -527,6 +527,7 @@ out_unregister_bdi: bdi_unregister(disk->bdi); out_unregister_queue: blk_unregister_queue(disk); + rq_qos_exit(disk->queue); out_put_slave_dir: kobject_put(disk->slave_dir); out_put_holder_dir: diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index d490670f8d55a..8678e162181f4 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -163,7 +163,7 @@ static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx) clear_fixmap(fixmap_idx); } -int ghes_estatus_pool_init(int num_ghes) +int ghes_estatus_pool_init(unsigned int num_ghes) { unsigned long addr, len; int rc; diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index 0a8bf09a5c19e..03c580625c2cc 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -315,9 +315,10 @@ static void pdc20230_set_piomode(struct ata_port *ap, struct ata_device *adev) outb(inb(0x1F4) & 0x07, 0x1F4); rt = inb(0x1F3); - rt &= 0x07 << (3 * adev->devno); + rt &= ~(0x07 << (3 * !adev->devno)); if (pio) - rt |= (1 + 3 * pio) << (3 * adev->devno); + rt |= (1 + 3 * pio) << (3 * !adev->devno); + outb(rt, 0x1F3); udelay(100); outb(inb(0x1F2) | 0x01, 0x1F2); diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 076e4942a3f0e..612f10456849f 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -219,7 +219,7 @@ static void virtbt_rx_work(struct work_struct *work) if (!skb) return; - skb->len = len; + skb_put(skb, len); virtbt_rx_handle(vbt, skb); if (virtbt_add_inbuf(vbt) < 0) diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c index ce7c5ba2b9b7a..d10efbf260b7a 100644 --- a/drivers/clk/qcom/gcc-sc7280.c +++ b/drivers/clk/qcom/gcc-sc7280.c @@ -3571,6 +3571,7 @@ static int gcc_sc7280_probe(struct platform_device *pdev) regmap_update_bits(regmap, 0x28004, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x28014, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x7100C, BIT(13), BIT(13)); ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks, ARRAY_SIZE(gcc_dfs_clocks)); diff --git a/drivers/clk/qcom/gpucc-sc7280.c b/drivers/clk/qcom/gpucc-sc7280.c index 9a832f2bcf491..1490cd45a654a 100644 --- a/drivers/clk/qcom/gpucc-sc7280.c +++ b/drivers/clk/qcom/gpucc-sc7280.c @@ -463,6 +463,7 @@ static int gpu_cc_sc7280_probe(struct platform_device *pdev) */ regmap_update_bits(regmap, 0x1170, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x1098, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x1098, BIT(13), BIT(13)); return qcom_cc_really_probe(pdev, &gpu_cc_sc7280_desc, regmap); } diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index e815b8f987393..16569af4a2ba8 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1516,8 +1516,12 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id) { int ret = scmi_chan_setup(info, dev, prot_id, true); - if (!ret) /* Rx is optional, hence no error check */ - scmi_chan_setup(info, dev, prot_id, false); + if (!ret) { + /* Rx is optional, report only memory errors */ + ret = scmi_chan_setup(info, dev, prot_id, false); + if (ret && ret != -ENOMEM) + ret = 0; + } return ret; } @@ -2009,6 +2013,7 @@ MODULE_DEVICE_TABLE(of, scmi_of_match); static struct platform_driver scmi_driver = { .driver = { .name = "arm-scmi", + .suppress_bind_attrs = true, .of_match_table = scmi_of_match, .dev_groups = versions_groups, }, diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 87039c5c03fdb..0c351eeee7463 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -247,19 +247,19 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, for (i = 0; i < vioch->max_msg; i++) { struct scmi_vio_msg *msg; - msg = devm_kzalloc(cinfo->dev, sizeof(*msg), GFP_KERNEL); + msg = devm_kzalloc(dev, sizeof(*msg), GFP_KERNEL); if (!msg) return -ENOMEM; if (tx) { - msg->request = devm_kzalloc(cinfo->dev, + msg->request = devm_kzalloc(dev, VIRTIO_SCMI_MAX_PDU_SIZE, GFP_KERNEL); if (!msg->request) return -ENOMEM; } - msg->input = devm_kzalloc(cinfo->dev, VIRTIO_SCMI_MAX_PDU_SIZE, + msg->input = devm_kzalloc(dev, VIRTIO_SCMI_MAX_PDU_SIZE, GFP_KERNEL); if (!msg->input) return -ENOMEM; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index e3df82d5d37a8..70be9c87fb673 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -590,7 +590,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, seed = early_memremap(efi_rng_seed, sizeof(*seed)); if (seed != NULL) { - size = READ_ONCE(seed->size); + size = min(seed->size, EFI_RANDOM_SEED_SIZE); early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c index 24aa375353724..33ab567695951 100644 --- a/drivers/firmware/efi/libstub/random.c +++ b/drivers/firmware/efi/libstub/random.c @@ -75,7 +75,12 @@ efi_status_t efi_random_get_seed(void) if (status != EFI_SUCCESS) return status; - status = efi_bs_call(allocate_pool, EFI_RUNTIME_SERVICES_DATA, + /* + * Use EFI_ACPI_RECLAIM_MEMORY here so that it is guaranteed that the + * allocation will survive a kexec reboot (although we refresh the seed + * beforehand) + */ + status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, sizeof(*seed) + EFI_RANDOM_SEED_SIZE, (void **)&seed); if (status != EFI_SUCCESS) diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 8f665678e9e39..e8d69bd548f3f 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -97,7 +97,7 @@ int __init efi_tpm_eventlog_init(void) goto out_calc; } - memblock_reserve((unsigned long)final_tbl, + memblock_reserve(efi.tpm_final_log, tbl_size + sizeof(*final_tbl)); efi_tpm_final_log_size = tbl_size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index a0803425b4566..b508126a9738f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -706,6 +706,12 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE; } + if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID) + /* VF MMIO access (except mailbox range) from CPU + * will be blocked during sriov runtime + */ + adev->virt.caps |= AMDGPU_VF_MMIO_ACCESS_PROTECT; + /* we have the ability to check now */ if (amdgpu_sriov_vf(adev)) { switch (adev->asic_type) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 9adfb8d63280a..ce31d4fdee935 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -31,6 +31,7 @@ #define AMDGPU_SRIOV_CAPS_IS_VF (1 << 2) /* this GPU is a virtual function */ #define AMDGPU_PASSTHROUGH_MODE (1 << 3) /* thw whole GPU is pass through for VM */ #define AMDGPU_SRIOV_CAPS_RUNTIME (1 << 4) /* is out of full access mode */ +#define AMDGPU_VF_MMIO_ACCESS_PROTECT (1 << 5) /* MMIO write access is not allowed in sriov runtime */ /* all asic after AI use this offset */ #define mmRCC_IOV_FUNC_IDENTIFIER 0xDE5 @@ -278,6 +279,9 @@ struct amdgpu_video_codec_info; #define amdgpu_passthrough(adev) \ ((adev)->virt.caps & AMDGPU_PASSTHROUGH_MODE) +#define amdgpu_sriov_vf_mmio_access_protection(adev) \ +((adev)->virt.caps & AMDGPU_VF_MMIO_ACCESS_PROTECT) + static inline bool is_virtual_machine(void) { #ifdef CONFIG_X86 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index fd37bb39774c8..01710cd0d9727 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3224,7 +3224,11 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev) */ #ifdef CONFIG_X86_64 if (amdgpu_vm_update_mode == -1) { - if (amdgpu_gmc_vram_full_visible(&adev->gmc)) + /* For asic with VF MMIO access protection + * avoid using CPU for VM table updates + */ + if (amdgpu_gmc_vram_full_visible(&adev->gmc) && + !amdgpu_sriov_vf_mmio_access_protection(adev)) adev->vm_manager.vm_update_mode = AMDGPU_VM_USE_CPU_FOR_COMPUTE; else diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index 7072fb2ec07fa..278ff281a1bd5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -36,10 +36,14 @@ void amdgpu_dm_set_psr_caps(struct dc_link *link) { uint8_t dpcd_data[EDP_PSR_RECEIVER_CAP_SIZE]; - if (!(link->connector_signal & SIGNAL_TYPE_EDP)) + if (!(link->connector_signal & SIGNAL_TYPE_EDP)) { + link->psr_settings.psr_feature_enabled = false; return; - if (link->type == dc_connection_none) + } + if (link->type == dc_connection_none) { + link->psr_settings.psr_feature_enabled = false; return; + } if (dm_helpers_dp_read_dpcd(NULL, link, DP_PSR_SUPPORT, dpcd_data, sizeof(dpcd_data))) { link->dpcd_caps.psr_caps.psr_version = dpcd_data[0]; diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 6cb27599ea030..adb1693b15758 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2762,13 +2762,10 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) if (!intel_sdvo_connector) return false; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS1; - } intel_connector = &intel_sdvo_connector->base; connector = &intel_connector->base; @@ -2823,7 +2820,6 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type) encoder->encoder_type = DRM_MODE_ENCODER_TVDAC; connector->connector_type = DRM_MODE_CONNECTOR_SVIDEO; - intel_sdvo->controlled_output |= type; intel_sdvo_connector->output_flag = type; if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { @@ -2864,13 +2860,10 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_DAC; connector->connector_type = DRM_MODE_CONNECTOR_VGA; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB1; - } if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2900,13 +2893,10 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_LVDS; connector->connector_type = DRM_MODE_CONNECTOR_LVDS; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS1; - } if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2939,16 +2929,39 @@ err: return false; } +static u16 intel_sdvo_filter_output_flags(u16 flags) +{ + flags &= SDVO_OUTPUT_MASK; + + /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + if (!(flags & SDVO_OUTPUT_TMDS0)) + flags &= ~SDVO_OUTPUT_TMDS1; + + if (!(flags & SDVO_OUTPUT_RGB0)) + flags &= ~SDVO_OUTPUT_RGB1; + + if (!(flags & SDVO_OUTPUT_LVDS0)) + flags &= ~SDVO_OUTPUT_LVDS1; + + return flags; +} + static bool intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) { - /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + struct drm_i915_private *i915 = to_i915(intel_sdvo->base.base.dev); + + flags = intel_sdvo_filter_output_flags(flags); + + intel_sdvo->controlled_output = flags; + + intel_sdvo_select_ddc_bus(i915, intel_sdvo); if (flags & SDVO_OUTPUT_TMDS0) if (!intel_sdvo_dvi_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_TMDS_MASK) == SDVO_TMDS_MASK) + if (flags & SDVO_OUTPUT_TMDS1) if (!intel_sdvo_dvi_init(intel_sdvo, 1)) return false; @@ -2969,7 +2982,7 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) if (!intel_sdvo_analog_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_RGB_MASK) == SDVO_RGB_MASK) + if (flags & SDVO_OUTPUT_RGB1) if (!intel_sdvo_analog_init(intel_sdvo, 1)) return false; @@ -2977,14 +2990,13 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) if (!intel_sdvo_lvds_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_LVDS_MASK) == SDVO_LVDS_MASK) + if (flags & SDVO_OUTPUT_LVDS1) if (!intel_sdvo_lvds_init(intel_sdvo, 1)) return false; - if ((flags & SDVO_OUTPUT_MASK) == 0) { + if (flags == 0) { unsigned char bytes[2]; - intel_sdvo->controlled_output = 0; memcpy(bytes, &intel_sdvo->caps.output_flags, 2); DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%02x%02x)\n", SDVO_NAME(intel_sdvo), @@ -3396,8 +3408,6 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv, */ intel_sdvo->base.cloneable = 0; - intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo); - /* Set the input timing to the screen. Assume always input 0. */ if (!intel_sdvo_set_target_input(intel_sdvo)) goto err_output; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index e082e01b5e8d1..f6b09e8eca672 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -330,8 +330,8 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, goto fail; } - ret = devm_request_irq(&pdev->dev, hdmi->irq, - msm_hdmi_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + ret = devm_request_irq(dev->dev, hdmi->irq, + msm_hdmi_irq, IRQF_TRIGGER_HIGH, "hdmi_isr", hdmi); if (ret < 0) { DRM_DEV_ERROR(dev->dev, "failed to request IRQ%u: %d\n", diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c index 59c3d8ef6bf9a..1129f98fe7f94 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c @@ -1027,23 +1027,31 @@ static int dw_mipi_dsi_rockchip_host_attach(void *priv_data, if (ret) { DRM_DEV_ERROR(dsi->dev, "Failed to register component: %d\n", ret); - return ret; + goto out; } second = dw_mipi_dsi_rockchip_find_second(dsi); - if (IS_ERR(second)) - return PTR_ERR(second); + if (IS_ERR(second)) { + ret = PTR_ERR(second); + goto out; + } if (second) { ret = component_add(second, &dw_mipi_dsi_rockchip_ops); if (ret) { DRM_DEV_ERROR(second, "Failed to register component: %d\n", ret); - return ret; + goto out; } } return 0; + +out: + mutex_lock(&dsi->usage_mutex); + dsi->usage_mode = DW_DSI_USAGE_IDLE; + mutex_unlock(&dsi->usage_mutex); + return ret; } static int dw_mipi_dsi_rockchip_host_detach(void *priv_data, @@ -1630,5 +1638,11 @@ struct platform_driver dw_mipi_dsi_rockchip_driver = { .of_match_table = dw_mipi_dsi_rockchip_dt_ids, .pm = &dw_mipi_dsi_rockchip_pm_ops, .name = "dw-mipi-dsi-rockchip", + /* + * For dual-DSI display, one DSI pokes at the other DSI's + * drvdata in dw_mipi_dsi_rockchip_find_second(). This is not + * safe for asynchronous probe. + */ + .probe_type = PROBE_FORCE_SYNCHRONOUS, }, }; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index cb2b48d6915ee..c8a313c84a57d 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -845,6 +845,7 @@ #define USB_DEVICE_ID_MADCATZ_BEATPAD 0x4540 #define USB_DEVICE_ID_MADCATZ_RAT5 0x1705 #define USB_DEVICE_ID_MADCATZ_RAT9 0x1709 +#define USB_DEVICE_ID_MADCATZ_MMO7 0x1713 #define USB_VENDOR_ID_MCC 0x09db #define USB_DEVICE_ID_MCC_PMD1024LS 0x0076 @@ -1109,6 +1110,7 @@ #define USB_DEVICE_ID_SONY_PS4_CONTROLLER_2 0x09cc #define USB_DEVICE_ID_SONY_PS4_CONTROLLER_DONGLE 0x0ba0 #define USB_DEVICE_ID_SONY_PS5_CONTROLLER 0x0ce6 +#define USB_DEVICE_ID_SONY_PS5_CONTROLLER_2 0x0df2 #define USB_DEVICE_ID_SONY_MOTION_CONTROLLER 0x03d5 #define USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER 0x042f #define USB_DEVICE_ID_SONY_BUZZ_CONTROLLER 0x0002 diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index ab7c82c2e8867..bd0e0fe2f6279 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -1282,7 +1282,8 @@ static int ps_probe(struct hid_device *hdev, const struct hid_device_id *id) goto err_stop; } - if (hdev->product == USB_DEVICE_ID_SONY_PS5_CONTROLLER) { + if (hdev->product == USB_DEVICE_ID_SONY_PS5_CONTROLLER || + hdev->product == USB_DEVICE_ID_SONY_PS5_CONTROLLER_2) { dev = dualsense_create(hdev); if (IS_ERR(dev)) { hid_err(hdev, "Failed to create dualsense.\n"); @@ -1320,6 +1321,8 @@ static void ps_remove(struct hid_device *hdev) static const struct hid_device_id ps_devices[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER) }, { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER) }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER_2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS5_CONTROLLER_2) }, { } }; MODULE_DEVICE_TABLE(hid, ps_devices); diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 544d1197aca48..8d36cb7551cf1 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -608,6 +608,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_MMO7) }, { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_RAT5) }, { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_RAT9) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_MMO7) }, #endif #if IS_ENABLED(CONFIG_HID_SAMSUNG) { HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_IR_REMOTE) }, diff --git a/drivers/hid/hid-saitek.c b/drivers/hid/hid-saitek.c index c7bf14c019605..b84e975977c42 100644 --- a/drivers/hid/hid-saitek.c +++ b/drivers/hid/hid-saitek.c @@ -187,6 +187,8 @@ static const struct hid_device_id saitek_devices[] = { .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_MMO7), .driver_data = SAITEK_RELEASE_MODE_MMO7 }, + { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_MMO7), + .driver_data = SAITEK_RELEASE_MODE_MMO7 }, { } }; diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 39cb1b7bb8656..809fbd014cd68 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -1080,6 +1080,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) "", &piix4_main_adapters[0]); if (retval < 0) return retval; + piix4_adapter_count = 1; } /* Check for auxiliary SMBus on some AMD chipsets */ diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 612343771ce25..34b8da949462a 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -934,6 +934,7 @@ static struct platform_driver xiic_i2c_driver = { module_platform_driver(xiic_i2c_driver); +MODULE_ALIAS("platform:" DRIVER_NAME); MODULE_AUTHOR("info@mocean-labs.com"); MODULE_DESCRIPTION("Xilinx I2C bus driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 0da66dd40d6a8..fd192104fd8d3 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1433,7 +1433,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev, return false; memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_iif = net_dev->ifindex; + fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 6ab46648af909..1519379b116e2 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2814,10 +2814,18 @@ static int __init ib_core_init(void) nldev_init(); rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table); - roce_gid_mgmt_init(); + ret = roce_gid_mgmt_init(); + if (ret) { + pr_warn("Couldn't init RoCE GID management\n"); + goto err_parent; + } return 0; +err_parent: + rdma_nl_unregister(RDMA_NL_LS); + nldev_exit(); + unregister_pernet_device(&rdma_dev_net_ops); err_compat: unregister_blocking_lsm_notifier(&ibdev_lsm_nb); err_sa: diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index e9b4b2cccaa0f..cd89e59cbe332 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2349,7 +2349,7 @@ void __init nldev_init(void) rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table); } -void __exit nldev_exit(void) +void nldev_exit(void) { rdma_nl_unregister(RDMA_NL_NLDEV); } diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 3d42bd2b36bd4..51ae58c02b15c 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -913,8 +913,7 @@ void sc_disable(struct send_context *sc) spin_unlock(&sc->release_lock); write_seqlock(&sc->waitlock); - if (!list_empty(&sc->piowait)) - list_move(&sc->piowait, &wake_list); + list_splice_init(&sc->piowait, &wake_list); write_sequnlock(&sc->waitlock); while (!list_empty(&wake_list)) { struct iowait *wait; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 1dbad159f3792..1421896abaf09 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -82,7 +82,6 @@ static const u32 hns_roce_op_code[] = { HR_OPC_MAP(ATOMIC_CMP_AND_SWP, ATOM_CMP_AND_SWAP), HR_OPC_MAP(ATOMIC_FETCH_AND_ADD, ATOM_FETCH_AND_ADD), HR_OPC_MAP(SEND_WITH_INV, SEND_WITH_INV), - HR_OPC_MAP(LOCAL_INV, LOCAL_INV), HR_OPC_MAP(MASKED_ATOMIC_CMP_AND_SWP, ATOM_MSK_CMP_AND_SWAP), HR_OPC_MAP(MASKED_ATOMIC_FETCH_AND_ADD, ATOM_MSK_FETCH_AND_ADD), HR_OPC_MAP(REG_MR, FAST_REG_PMR), @@ -149,8 +148,7 @@ static void set_atomic_seg(const struct ib_send_wr *wr, aseg->cmp_data = 0; } - roce_set_field(rc_sq_wqe->byte_16, V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SGE_NUM, valid_num_sge); } static int fill_ext_sge_inl_data(struct hns_roce_qp *qp, @@ -271,8 +269,7 @@ static int set_rc_inl(struct hns_roce_qp *qp, const struct ib_send_wr *wr, dseg += sizeof(struct hns_roce_v2_rc_send_wqe); if (msg_len <= HNS_ROCE_V2_MAX_RC_INL_INN_SZ) { - roce_set_bit(rc_sq_wqe->byte_20, - V2_RC_SEND_WQE_BYTE_20_INL_TYPE_S, 0); + hr_reg_clear(rc_sq_wqe, RC_SEND_WQE_INL_TYPE); for (i = 0; i < wr->num_sge; i++) { memcpy(dseg, ((void *)wr->sg_list[i].addr), @@ -280,17 +277,13 @@ static int set_rc_inl(struct hns_roce_qp *qp, const struct ib_send_wr *wr, dseg += wr->sg_list[i].length; } } else { - roce_set_bit(rc_sq_wqe->byte_20, - V2_RC_SEND_WQE_BYTE_20_INL_TYPE_S, 1); + hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_INL_TYPE); ret = fill_ext_sge_inl_data(qp, wr, &curr_idx, msg_len); if (ret) return ret; - roce_set_field(rc_sq_wqe->byte_16, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, - curr_idx - *sge_idx); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SGE_NUM, curr_idx - *sge_idx); } *sge_idx = curr_idx; @@ -309,12 +302,10 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr, int j = 0; int i; - roce_set_field(rc_sq_wqe->byte_20, - V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M, - V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, - (*sge_ind) & (qp->sge.sge_cnt - 1)); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_MSG_START_SGE_IDX, + (*sge_ind) & (qp->sge.sge_cnt - 1)); - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_INLINE_S, + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_INLINE, !!(wr->send_flags & IB_SEND_INLINE)); if (wr->send_flags & IB_SEND_INLINE) return set_rc_inl(qp, wr, rc_sq_wqe, sge_ind); @@ -339,9 +330,7 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr, valid_num_sge - HNS_ROCE_SGE_IN_WQE); } - roce_set_field(rc_sq_wqe->byte_16, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SGE_NUM, valid_num_sge); return 0; } @@ -412,8 +401,7 @@ static int set_ud_opcode(struct hns_roce_v2_ud_send_wqe *ud_sq_wqe, ud_sq_wqe->immtdata = get_immtdata(wr); - roce_set_field(ud_sq_wqe->byte_4, V2_UD_SEND_WQE_BYTE_4_OPCODE_M, - V2_UD_SEND_WQE_BYTE_4_OPCODE_S, to_hr_opcode(ib_op)); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_OPCODE, to_hr_opcode(ib_op)); return 0; } @@ -424,21 +412,15 @@ static int fill_ud_av(struct hns_roce_v2_ud_send_wqe *ud_sq_wqe, struct ib_device *ib_dev = ah->ibah.device; struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev); - roce_set_field(ud_sq_wqe->byte_24, V2_UD_SEND_WQE_BYTE_24_UDPSPN_M, - V2_UD_SEND_WQE_BYTE_24_UDPSPN_S, ah->av.udp_sport); - - roce_set_field(ud_sq_wqe->byte_36, V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_M, - V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_S, ah->av.hop_limit); - roce_set_field(ud_sq_wqe->byte_36, V2_UD_SEND_WQE_BYTE_36_TCLASS_M, - V2_UD_SEND_WQE_BYTE_36_TCLASS_S, ah->av.tclass); - roce_set_field(ud_sq_wqe->byte_40, V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_M, - V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_S, ah->av.flowlabel); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_UDPSPN, ah->av.udp_sport); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_HOPLIMIT, ah->av.hop_limit); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_TCLASS, ah->av.tclass); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_FLOW_LABEL, ah->av.flowlabel); if (WARN_ON(ah->av.sl > MAX_SERVICE_LEVEL)) return -EINVAL; - roce_set_field(ud_sq_wqe->byte_40, V2_UD_SEND_WQE_BYTE_40_SL_M, - V2_UD_SEND_WQE_BYTE_40_SL_S, ah->av.sl); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_SL, ah->av.sl); ud_sq_wqe->sgid_index = ah->av.gid_index; @@ -448,10 +430,8 @@ static int fill_ud_av(struct hns_roce_v2_ud_send_wqe *ud_sq_wqe, if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) return 0; - roce_set_bit(ud_sq_wqe->byte_40, V2_UD_SEND_WQE_BYTE_40_UD_VLAN_EN_S, - ah->av.vlan_en); - roce_set_field(ud_sq_wqe->byte_36, V2_UD_SEND_WQE_BYTE_36_VLAN_M, - V2_UD_SEND_WQE_BYTE_36_VLAN_S, ah->av.vlan_id); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_VLAN_EN, ah->av.vlan_en); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_VLAN, ah->av.vlan_id); return 0; } @@ -476,27 +456,19 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp, ud_sq_wqe->msg_len = cpu_to_le32(msg_len); - roce_set_bit(ud_sq_wqe->byte_4, V2_UD_SEND_WQE_BYTE_4_CQE_S, + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_CQE, !!(wr->send_flags & IB_SEND_SIGNALED)); - - roce_set_bit(ud_sq_wqe->byte_4, V2_UD_SEND_WQE_BYTE_4_SE_S, + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_SE, !!(wr->send_flags & IB_SEND_SOLICITED)); - roce_set_field(ud_sq_wqe->byte_16, V2_UD_SEND_WQE_BYTE_16_PD_M, - V2_UD_SEND_WQE_BYTE_16_PD_S, to_hr_pd(qp->ibqp.pd)->pdn); - - roce_set_field(ud_sq_wqe->byte_16, V2_UD_SEND_WQE_BYTE_16_SGE_NUM_M, - V2_UD_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge); - - roce_set_field(ud_sq_wqe->byte_20, - V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M, - V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, - curr_idx & (qp->sge.sge_cnt - 1)); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_PD, to_hr_pd(qp->ibqp.pd)->pdn); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_SGE_NUM, valid_num_sge); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_MSG_START_SGE_IDX, + curr_idx & (qp->sge.sge_cnt - 1)); ud_sq_wqe->qkey = cpu_to_le32(ud_wr(wr)->remote_qkey & 0x80000000 ? qp->qkey : ud_wr(wr)->remote_qkey); - roce_set_field(ud_sq_wqe->byte_32, V2_UD_SEND_WQE_BYTE_32_DQPN_M, - V2_UD_SEND_WQE_BYTE_32_DQPN_S, ud_wr(wr)->remote_qpn); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_DQPN, ud_wr(wr)->remote_qpn); ret = fill_ud_av(ud_sq_wqe, ah); if (ret) @@ -516,8 +488,7 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp, dma_wmb(); *sge_idx = curr_idx; - roce_set_bit(ud_sq_wqe->byte_4, V2_UD_SEND_WQE_BYTE_4_OWNER_S, - owner_bit); + hr_reg_write(ud_sq_wqe, UD_SEND_WQE_OWNER, owner_bit); return 0; } @@ -552,9 +523,6 @@ static int set_rc_opcode(struct hns_roce_dev *hr_dev, else ret = -EOPNOTSUPP; break; - case IB_WR_LOCAL_INV: - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_SO_S, 1); - fallthrough; case IB_WR_SEND_WITH_INV: rc_sq_wqe->inv_key = cpu_to_le32(wr->ex.invalidate_rkey); break; @@ -565,11 +533,11 @@ static int set_rc_opcode(struct hns_roce_dev *hr_dev, if (unlikely(ret)) return ret; - roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OPCODE_M, - V2_RC_SEND_WQE_BYTE_4_OPCODE_S, to_hr_opcode(ib_op)); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_OPCODE, to_hr_opcode(ib_op)); return ret; } + static inline int set_rc_wqe(struct hns_roce_qp *qp, const struct ib_send_wr *wr, void *wqe, unsigned int *sge_idx, @@ -590,13 +558,13 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp, if (WARN_ON(ret)) return ret; - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_FENCE_S, + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_FENCE, (wr->send_flags & IB_SEND_FENCE) ? 1 : 0); - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_SE_S, + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SE, (wr->send_flags & IB_SEND_SOLICITED) ? 1 : 0); - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_CQE_S, + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_CQE, (wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0); if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP || @@ -616,8 +584,7 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp, dma_wmb(); *sge_idx = curr_idx; - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OWNER_S, - owner_bit); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_OWNER, owner_bit); return ret; } @@ -678,16 +645,15 @@ static void hns_roce_write512(struct hns_roce_dev *hr_dev, u64 *val, static void write_dwqe(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp, void *wqe) { +#define HNS_ROCE_SL_SHIFT 2 struct hns_roce_v2_rc_send_wqe *rc_sq_wqe = wqe; /* All kinds of DirectWQE have the same header field layout */ - roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_FLAG_S, 1); - roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_DB_SL_L_M, - V2_RC_SEND_WQE_BYTE_4_DB_SL_L_S, qp->sl); - roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_DB_SL_H_M, - V2_RC_SEND_WQE_BYTE_4_DB_SL_H_S, qp->sl >> 2); - roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_WQE_INDEX_M, - V2_RC_SEND_WQE_BYTE_4_WQE_INDEX_S, qp->sq.head); + hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_FLAG); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_DB_SL_L, qp->sl); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_DB_SL_H, + qp->sl >> HNS_ROCE_SL_SHIFT); + hr_reg_write(rc_sq_wqe, RC_SEND_WQE_WQE_INDEX, qp->sq.head); hns_roce_write512(hr_dev, wqe, qp->sq.db_reg); } @@ -1783,17 +1749,16 @@ static int __hns_roce_set_vf_switch_param(struct hns_roce_dev *hr_dev, swt = (struct hns_roce_vf_switch *)desc.data; hns_roce_cmq_setup_basic_desc(&desc, HNS_SWITCH_PARAMETER_CFG, true); swt->rocee_sel |= cpu_to_le32(HNS_ICL_SWITCH_CMD_ROCEE_SEL); - roce_set_field(swt->fun_id, VF_SWITCH_DATA_FUN_ID_VF_ID_M, - VF_SWITCH_DATA_FUN_ID_VF_ID_S, vf_id); + hr_reg_write(swt, VF_SWITCH_VF_ID, vf_id); ret = hns_roce_cmq_send(hr_dev, &desc, 1); if (ret) return ret; desc.flag = cpu_to_le16(HNS_ROCE_CMD_FLAG_IN); desc.flag &= cpu_to_le16(~HNS_ROCE_CMD_FLAG_WR); - roce_set_bit(swt->cfg, VF_SWITCH_DATA_CFG_ALW_LPBK_S, 1); - roce_set_bit(swt->cfg, VF_SWITCH_DATA_CFG_ALW_LCL_LPBK_S, 0); - roce_set_bit(swt->cfg, VF_SWITCH_DATA_CFG_ALW_DST_OVRD_S, 1); + hr_reg_enable(swt, VF_SWITCH_ALW_LPBK); + hr_reg_clear(swt, VF_SWITCH_ALW_LCL_LPBK); + hr_reg_enable(swt, VF_SWITCH_ALW_DST_OVRD); return hns_roce_cmq_send(hr_dev, &desc, 1); } @@ -2942,10 +2907,8 @@ static int config_sgid_table(struct hns_roce_dev *hr_dev, hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_SGID_TB, false); - roce_set_field(sgid_tb->table_idx_rsv, CFG_SGID_TB_TABLE_IDX_M, - CFG_SGID_TB_TABLE_IDX_S, gid_index); - roce_set_field(sgid_tb->vf_sgid_type_rsv, CFG_SGID_TB_VF_SGID_TYPE_M, - CFG_SGID_TB_VF_SGID_TYPE_S, sgid_type); + hr_reg_write(sgid_tb, CFG_SGID_TB_TABLE_IDX, gid_index); + hr_reg_write(sgid_tb, CFG_SGID_TB_VF_SGID_TYPE, sgid_type); copy_gid(&sgid_tb->vf_sgid_l, gid); @@ -2980,19 +2943,14 @@ static int config_gmv_table(struct hns_roce_dev *hr_dev, copy_gid(&tb_a->vf_sgid_l, gid); - roce_set_field(tb_a->vf_sgid_type_vlan, CFG_GMV_TB_VF_SGID_TYPE_M, - CFG_GMV_TB_VF_SGID_TYPE_S, sgid_type); - roce_set_bit(tb_a->vf_sgid_type_vlan, CFG_GMV_TB_VF_VLAN_EN_S, - vlan_id < VLAN_CFI_MASK); - roce_set_field(tb_a->vf_sgid_type_vlan, CFG_GMV_TB_VF_VLAN_ID_M, - CFG_GMV_TB_VF_VLAN_ID_S, vlan_id); + hr_reg_write(tb_a, GMV_TB_A_VF_SGID_TYPE, sgid_type); + hr_reg_write(tb_a, GMV_TB_A_VF_VLAN_EN, vlan_id < VLAN_CFI_MASK); + hr_reg_write(tb_a, GMV_TB_A_VF_VLAN_ID, vlan_id); tb_b->vf_smac_l = cpu_to_le32(*(u32 *)mac); - roce_set_field(tb_b->vf_smac_h, CFG_GMV_TB_SMAC_H_M, - CFG_GMV_TB_SMAC_H_S, *(u16 *)&mac[4]); - roce_set_field(tb_b->table_idx_rsv, CFG_GMV_TB_SGID_IDX_M, - CFG_GMV_TB_SGID_IDX_S, gid_index); + hr_reg_write(tb_b, GMV_TB_B_SMAC_H, *(u16 *)&mac[4]); + hr_reg_write(tb_b, GMV_TB_B_SGID_IDX, gid_index); return hns_roce_cmq_send(hr_dev, desc, 2); } @@ -3041,10 +2999,8 @@ static int hns_roce_v2_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, reg_smac_l = *(u32 *)(&addr[0]); reg_smac_h = *(u16 *)(&addr[4]); - roce_set_field(smac_tb->tb_idx_rsv, CFG_SMAC_TB_IDX_M, - CFG_SMAC_TB_IDX_S, phy_port); - roce_set_field(smac_tb->vf_smac_h_rsv, CFG_SMAC_TB_VF_SMAC_H_M, - CFG_SMAC_TB_VF_SMAC_H_S, reg_smac_h); + hr_reg_write(smac_tb, CFG_SMAC_TB_IDX, phy_port); + hr_reg_write(smac_tb, CFG_SMAC_TB_VF_SMAC_H, reg_smac_h); smac_tb->vf_smac_l = cpu_to_le32(reg_smac_l); return hns_roce_cmq_send(hr_dev, &desc, 1); @@ -3073,21 +3029,15 @@ static int set_mtpt_pbl(struct hns_roce_dev *hr_dev, mpt_entry->pbl_size = cpu_to_le32(mr->npages); mpt_entry->pbl_ba_l = cpu_to_le32(pbl_ba >> 3); - roce_set_field(mpt_entry->byte_48_mode_ba, - V2_MPT_BYTE_48_PBL_BA_H_M, V2_MPT_BYTE_48_PBL_BA_H_S, - upper_32_bits(pbl_ba >> 3)); + hr_reg_write(mpt_entry, MPT_PBL_BA_H, upper_32_bits(pbl_ba >> 3)); mpt_entry->pa0_l = cpu_to_le32(lower_32_bits(pages[0])); - roce_set_field(mpt_entry->byte_56_pa0_h, V2_MPT_BYTE_56_PA0_H_M, - V2_MPT_BYTE_56_PA0_H_S, upper_32_bits(pages[0])); + hr_reg_write(mpt_entry, MPT_PA0_H, upper_32_bits(pages[0])); mpt_entry->pa1_l = cpu_to_le32(lower_32_bits(pages[1])); - roce_set_field(mpt_entry->byte_64_buf_pa1, V2_MPT_BYTE_64_PA1_H_M, - V2_MPT_BYTE_64_PA1_H_S, upper_32_bits(pages[1])); - roce_set_field(mpt_entry->byte_64_buf_pa1, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_M, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_S, - to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.buf_pg_shift)); + hr_reg_write(mpt_entry, MPT_PA1_H, upper_32_bits(pages[1])); + hr_reg_write(mpt_entry, MPT_PBL_BUF_PG_SZ, + to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.buf_pg_shift)); return 0; } @@ -3104,7 +3054,6 @@ static int hns_roce_v2_write_mtpt(struct hns_roce_dev *hr_dev, hr_reg_write(mpt_entry, MPT_ST, V2_MPT_ST_VALID); hr_reg_write(mpt_entry, MPT_PD, mr->pd); - hr_reg_enable(mpt_entry, MPT_L_INV_EN); hr_reg_write_bool(mpt_entry, MPT_BIND_EN, mr->access & IB_ACCESS_MW_BIND); @@ -3149,24 +3098,19 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev, u32 mr_access_flags = mr->access; int ret = 0; - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_MPT_ST_M, - V2_MPT_BYTE_4_MPT_ST_S, V2_MPT_ST_VALID); - - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PD_M, - V2_MPT_BYTE_4_PD_S, mr->pd); + hr_reg_write(mpt_entry, MPT_ST, V2_MPT_ST_VALID); + hr_reg_write(mpt_entry, MPT_PD, mr->pd); if (flags & IB_MR_REREG_ACCESS) { - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, - V2_MPT_BYTE_8_BIND_EN_S, + hr_reg_write(mpt_entry, MPT_BIND_EN, (mr_access_flags & IB_ACCESS_MW_BIND ? 1 : 0)); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, - V2_MPT_BYTE_8_ATOMIC_EN_S, + hr_reg_write(mpt_entry, MPT_ATOMIC_EN, mr_access_flags & IB_ACCESS_REMOTE_ATOMIC ? 1 : 0); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RR_EN_S, + hr_reg_write(mpt_entry, MPT_RR_EN, mr_access_flags & IB_ACCESS_REMOTE_READ ? 1 : 0); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RW_EN_S, + hr_reg_write(mpt_entry, MPT_RW_EN, mr_access_flags & IB_ACCESS_REMOTE_WRITE ? 1 : 0); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, + hr_reg_write(mpt_entry, MPT_LW_EN, mr_access_flags & IB_ACCESS_LOCAL_WRITE ? 1 : 0); } @@ -3197,37 +3141,27 @@ static int hns_roce_v2_frmr_write_mtpt(struct hns_roce_dev *hr_dev, return -ENOBUFS; } - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_MPT_ST_M, - V2_MPT_BYTE_4_MPT_ST_S, V2_MPT_ST_FREE); - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PBL_HOP_NUM_M, - V2_MPT_BYTE_4_PBL_HOP_NUM_S, 1); - roce_set_field(mpt_entry->byte_4_pd_hop_st, - V2_MPT_BYTE_4_PBL_BA_PG_SZ_M, - V2_MPT_BYTE_4_PBL_BA_PG_SZ_S, - to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.ba_pg_shift)); - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PD_M, - V2_MPT_BYTE_4_PD_S, mr->pd); + hr_reg_write(mpt_entry, MPT_ST, V2_MPT_ST_FREE); + hr_reg_write(mpt_entry, MPT_PD, mr->pd); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RA_EN_S, 1); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_R_INV_EN_S, 1); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_L_INV_EN_S, 1); + hr_reg_enable(mpt_entry, MPT_RA_EN); + hr_reg_enable(mpt_entry, MPT_R_INV_EN); - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_FRE_S, 1); - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S, 0); - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_MR_MW_S, 0); - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_BPD_S, 1); + hr_reg_enable(mpt_entry, MPT_FRE); + hr_reg_clear(mpt_entry, MPT_MR_MW); + hr_reg_enable(mpt_entry, MPT_BPD); + hr_reg_clear(mpt_entry, MPT_PA); + + hr_reg_write(mpt_entry, MPT_PBL_HOP_NUM, 1); + hr_reg_write(mpt_entry, MPT_PBL_BA_PG_SZ, + to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.ba_pg_shift)); + hr_reg_write(mpt_entry, MPT_PBL_BUF_PG_SZ, + to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.buf_pg_shift)); mpt_entry->pbl_size = cpu_to_le32(mr->npages); mpt_entry->pbl_ba_l = cpu_to_le32(lower_32_bits(pbl_ba >> 3)); - roce_set_field(mpt_entry->byte_48_mode_ba, V2_MPT_BYTE_48_PBL_BA_H_M, - V2_MPT_BYTE_48_PBL_BA_H_S, - upper_32_bits(pbl_ba >> 3)); - - roce_set_field(mpt_entry->byte_64_buf_pa1, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_M, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_S, - to_hr_hw_page_shift(mr->pbl_mtr.hem_cfg.buf_pg_shift)); + hr_reg_write(mpt_entry, MPT_PBL_BA_H, upper_32_bits(pbl_ba >> 3)); return 0; } @@ -3239,36 +3173,28 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw) mpt_entry = mb_buf; memset(mpt_entry, 0, sizeof(*mpt_entry)); - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_MPT_ST_M, - V2_MPT_BYTE_4_MPT_ST_S, V2_MPT_ST_FREE); - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PD_M, - V2_MPT_BYTE_4_PD_S, mw->pdn); - roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PBL_HOP_NUM_M, - V2_MPT_BYTE_4_PBL_HOP_NUM_S, - mw->pbl_hop_num == HNS_ROCE_HOP_NUM_0 ? 0 : - mw->pbl_hop_num); - roce_set_field(mpt_entry->byte_4_pd_hop_st, - V2_MPT_BYTE_4_PBL_BA_PG_SZ_M, - V2_MPT_BYTE_4_PBL_BA_PG_SZ_S, - mw->pbl_ba_pg_sz + PG_SHIFT_OFFSET); - - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_R_INV_EN_S, 1); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_L_INV_EN_S, 1); - roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, 1); - - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S, 0); - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_MR_MW_S, 1); - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_BPD_S, 1); - roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_BQP_S, - mw->ibmw.type == IB_MW_TYPE_1 ? 0 : 1); + hr_reg_write(mpt_entry, MPT_ST, V2_MPT_ST_FREE); + hr_reg_write(mpt_entry, MPT_PD, mw->pdn); - roce_set_field(mpt_entry->byte_64_buf_pa1, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_M, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_S, - mw->pbl_buf_pg_sz + PG_SHIFT_OFFSET); + hr_reg_enable(mpt_entry, MPT_R_INV_EN); + hr_reg_enable(mpt_entry, MPT_LW_EN); + + hr_reg_enable(mpt_entry, MPT_MR_MW); + hr_reg_enable(mpt_entry, MPT_BPD); + hr_reg_clear(mpt_entry, MPT_PA); + hr_reg_write(mpt_entry, MPT_BQP, + mw->ibmw.type == IB_MW_TYPE_1 ? 0 : 1); mpt_entry->lkey = cpu_to_le32(mw->rkey); + hr_reg_write(mpt_entry, MPT_PBL_HOP_NUM, + mw->pbl_hop_num == HNS_ROCE_HOP_NUM_0 ? 0 : + mw->pbl_hop_num); + hr_reg_write(mpt_entry, MPT_PBL_BA_PG_SZ, + mw->pbl_ba_pg_sz + PG_SHIFT_OFFSET); + hr_reg_write(mpt_entry, MPT_PBL_BUF_PG_SZ, + mw->pbl_buf_pg_sz + PG_SHIFT_OFFSET); + return 0; } @@ -3607,7 +3533,6 @@ static const u32 wc_send_op_map[] = { HR_WC_OP_MAP(RDMA_READ, RDMA_READ), HR_WC_OP_MAP(RDMA_WRITE, RDMA_WRITE), HR_WC_OP_MAP(RDMA_WRITE_WITH_IMM, RDMA_WRITE), - HR_WC_OP_MAP(LOCAL_INV, LOCAL_INV), HR_WC_OP_MAP(ATOM_CMP_AND_SWAP, COMP_SWAP), HR_WC_OP_MAP(ATOM_FETCH_AND_ADD, FETCH_ADD), HR_WC_OP_MAP(ATOM_MSK_CMP_AND_SWAP, MASKED_COMP_SWAP), @@ -3657,9 +3582,6 @@ static void fill_send_wc(struct ib_wc *wc, struct hns_roce_v2_cqe *cqe) case HNS_ROCE_V2_WQE_OP_RDMA_WRITE_WITH_IMM: wc->wc_flags |= IB_WC_WITH_IMM; break; - case HNS_ROCE_V2_WQE_OP_LOCAL_INV: - wc->wc_flags |= IB_WC_WITH_INVALIDATE; - break; case HNS_ROCE_V2_WQE_OP_ATOM_CMP_AND_SWAP: case HNS_ROCE_V2_WQE_OP_ATOM_FETCH_AND_ADD: case HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP: diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index d3d5b5f57052c..2f4a0019a716d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -184,7 +184,6 @@ enum { HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP = 0x8, HNS_ROCE_V2_WQE_OP_ATOM_MSK_FETCH_AND_ADD = 0x9, HNS_ROCE_V2_WQE_OP_FAST_REG_PMR = 0xa, - HNS_ROCE_V2_WQE_OP_LOCAL_INV = 0xb, HNS_ROCE_V2_WQE_OP_BIND_MW = 0xc, HNS_ROCE_V2_WQE_OP_MASK = 0x1f, }; @@ -790,12 +789,15 @@ struct hns_roce_v2_mpt_entry { #define MPT_LKEY MPT_FIELD_LOC(223, 192) #define MPT_VA MPT_FIELD_LOC(287, 224) #define MPT_PBL_SIZE MPT_FIELD_LOC(319, 288) -#define MPT_PBL_BA MPT_FIELD_LOC(380, 320) +#define MPT_PBL_BA_L MPT_FIELD_LOC(351, 320) +#define MPT_PBL_BA_H MPT_FIELD_LOC(380, 352) #define MPT_BLK_MODE MPT_FIELD_LOC(381, 381) #define MPT_RSV0 MPT_FIELD_LOC(383, 382) -#define MPT_PA0 MPT_FIELD_LOC(441, 384) +#define MPT_PA0_L MPT_FIELD_LOC(415, 384) +#define MPT_PA0_H MPT_FIELD_LOC(441, 416) #define MPT_BOUND_VA MPT_FIELD_LOC(447, 442) -#define MPT_PA1 MPT_FIELD_LOC(505, 448) +#define MPT_PA1_L MPT_FIELD_LOC(479, 448) +#define MPT_PA1_H MPT_FIELD_LOC(505, 480) #define MPT_PERSIST_EN MPT_FIELD_LOC(506, 506) #define MPT_RSV2 MPT_FIELD_LOC(507, 507) #define MPT_PBL_BUF_PG_SZ MPT_FIELD_LOC(511, 508) @@ -901,48 +903,24 @@ struct hns_roce_v2_ud_send_wqe { u8 dgid[GID_LEN_V2]; }; -#define V2_UD_SEND_WQE_BYTE_4_OPCODE_S 0 -#define V2_UD_SEND_WQE_BYTE_4_OPCODE_M GENMASK(4, 0) - -#define V2_UD_SEND_WQE_BYTE_4_OWNER_S 7 - -#define V2_UD_SEND_WQE_BYTE_4_CQE_S 8 - -#define V2_UD_SEND_WQE_BYTE_4_SE_S 11 - -#define V2_UD_SEND_WQE_BYTE_16_PD_S 0 -#define V2_UD_SEND_WQE_BYTE_16_PD_M GENMASK(23, 0) - -#define V2_UD_SEND_WQE_BYTE_16_SGE_NUM_S 24 -#define V2_UD_SEND_WQE_BYTE_16_SGE_NUM_M GENMASK(31, 24) - -#define V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S 0 -#define V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M GENMASK(23, 0) - -#define V2_UD_SEND_WQE_BYTE_24_UDPSPN_S 16 -#define V2_UD_SEND_WQE_BYTE_24_UDPSPN_M GENMASK(31, 16) - -#define V2_UD_SEND_WQE_BYTE_32_DQPN_S 0 -#define V2_UD_SEND_WQE_BYTE_32_DQPN_M GENMASK(23, 0) - -#define V2_UD_SEND_WQE_BYTE_36_VLAN_S 0 -#define V2_UD_SEND_WQE_BYTE_36_VLAN_M GENMASK(15, 0) - -#define V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_S 16 -#define V2_UD_SEND_WQE_BYTE_36_HOPLIMIT_M GENMASK(23, 16) - -#define V2_UD_SEND_WQE_BYTE_36_TCLASS_S 24 -#define V2_UD_SEND_WQE_BYTE_36_TCLASS_M GENMASK(31, 24) - -#define V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_S 0 -#define V2_UD_SEND_WQE_BYTE_40_FLOW_LABEL_M GENMASK(19, 0) - -#define V2_UD_SEND_WQE_BYTE_40_SL_S 20 -#define V2_UD_SEND_WQE_BYTE_40_SL_M GENMASK(23, 20) - -#define V2_UD_SEND_WQE_BYTE_40_UD_VLAN_EN_S 30 - -#define V2_UD_SEND_WQE_BYTE_40_LBI_S 31 +#define UD_SEND_WQE_FIELD_LOC(h, l) FIELD_LOC(struct hns_roce_v2_ud_send_wqe, h, l) + +#define UD_SEND_WQE_OPCODE UD_SEND_WQE_FIELD_LOC(4, 0) +#define UD_SEND_WQE_OWNER UD_SEND_WQE_FIELD_LOC(7, 7) +#define UD_SEND_WQE_CQE UD_SEND_WQE_FIELD_LOC(8, 8) +#define UD_SEND_WQE_SE UD_SEND_WQE_FIELD_LOC(11, 11) +#define UD_SEND_WQE_PD UD_SEND_WQE_FIELD_LOC(119, 96) +#define UD_SEND_WQE_SGE_NUM UD_SEND_WQE_FIELD_LOC(127, 120) +#define UD_SEND_WQE_MSG_START_SGE_IDX UD_SEND_WQE_FIELD_LOC(151, 128) +#define UD_SEND_WQE_UDPSPN UD_SEND_WQE_FIELD_LOC(191, 176) +#define UD_SEND_WQE_DQPN UD_SEND_WQE_FIELD_LOC(247, 224) +#define UD_SEND_WQE_VLAN UD_SEND_WQE_FIELD_LOC(271, 256) +#define UD_SEND_WQE_HOPLIMIT UD_SEND_WQE_FIELD_LOC(279, 272) +#define UD_SEND_WQE_TCLASS UD_SEND_WQE_FIELD_LOC(287, 280) +#define UD_SEND_WQE_FLOW_LABEL UD_SEND_WQE_FIELD_LOC(307, 288) +#define UD_SEND_WQE_SL UD_SEND_WQE_FIELD_LOC(311, 308) +#define UD_SEND_WQE_VLAN_EN UD_SEND_WQE_FIELD_LOC(318, 318) +#define UD_SEND_WQE_LBI UD_SEND_WQE_FIELD_LOC(319, 319) struct hns_roce_v2_rc_send_wqe { __le32 byte_4; @@ -957,42 +935,22 @@ struct hns_roce_v2_rc_send_wqe { __le64 va; }; -#define V2_RC_SEND_WQE_BYTE_4_OPCODE_S 0 -#define V2_RC_SEND_WQE_BYTE_4_OPCODE_M GENMASK(4, 0) - -#define V2_RC_SEND_WQE_BYTE_4_DB_SL_L_S 5 -#define V2_RC_SEND_WQE_BYTE_4_DB_SL_L_M GENMASK(6, 5) - -#define V2_RC_SEND_WQE_BYTE_4_DB_SL_H_S 13 -#define V2_RC_SEND_WQE_BYTE_4_DB_SL_H_M GENMASK(14, 13) - -#define V2_RC_SEND_WQE_BYTE_4_WQE_INDEX_S 15 -#define V2_RC_SEND_WQE_BYTE_4_WQE_INDEX_M GENMASK(30, 15) - -#define V2_RC_SEND_WQE_BYTE_4_OWNER_S 7 - -#define V2_RC_SEND_WQE_BYTE_4_CQE_S 8 - -#define V2_RC_SEND_WQE_BYTE_4_FENCE_S 9 - -#define V2_RC_SEND_WQE_BYTE_4_SO_S 10 - -#define V2_RC_SEND_WQE_BYTE_4_SE_S 11 - -#define V2_RC_SEND_WQE_BYTE_4_INLINE_S 12 - -#define V2_RC_SEND_WQE_BYTE_4_FLAG_S 31 - -#define V2_RC_SEND_WQE_BYTE_16_XRC_SRQN_S 0 -#define V2_RC_SEND_WQE_BYTE_16_XRC_SRQN_M GENMASK(23, 0) - -#define V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S 24 -#define V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M GENMASK(31, 24) - -#define V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S 0 -#define V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M GENMASK(23, 0) - -#define V2_RC_SEND_WQE_BYTE_20_INL_TYPE_S 31 +#define RC_SEND_WQE_FIELD_LOC(h, l) FIELD_LOC(struct hns_roce_v2_rc_send_wqe, h, l) + +#define RC_SEND_WQE_OPCODE RC_SEND_WQE_FIELD_LOC(4, 0) +#define RC_SEND_WQE_DB_SL_L RC_SEND_WQE_FIELD_LOC(6, 5) +#define RC_SEND_WQE_DB_SL_H RC_SEND_WQE_FIELD_LOC(14, 13) +#define RC_SEND_WQE_OWNER RC_SEND_WQE_FIELD_LOC(7, 7) +#define RC_SEND_WQE_CQE RC_SEND_WQE_FIELD_LOC(8, 8) +#define RC_SEND_WQE_FENCE RC_SEND_WQE_FIELD_LOC(9, 9) +#define RC_SEND_WQE_SE RC_SEND_WQE_FIELD_LOC(11, 11) +#define RC_SEND_WQE_INLINE RC_SEND_WQE_FIELD_LOC(12, 12) +#define RC_SEND_WQE_WQE_INDEX RC_SEND_WQE_FIELD_LOC(30, 15) +#define RC_SEND_WQE_FLAG RC_SEND_WQE_FIELD_LOC(31, 31) +#define RC_SEND_WQE_XRC_SRQN RC_SEND_WQE_FIELD_LOC(119, 96) +#define RC_SEND_WQE_SGE_NUM RC_SEND_WQE_FIELD_LOC(127, 120) +#define RC_SEND_WQE_MSG_START_SGE_IDX RC_SEND_WQE_FIELD_LOC(151, 128) +#define RC_SEND_WQE_INL_TYPE RC_SEND_WQE_FIELD_LOC(159, 159) struct hns_roce_wqe_frmr_seg { __le32 pbl_size; @@ -1114,12 +1072,12 @@ struct hns_roce_vf_switch { __le32 resv3; }; -#define VF_SWITCH_DATA_FUN_ID_VF_ID_S 3 -#define VF_SWITCH_DATA_FUN_ID_VF_ID_M GENMASK(10, 3) +#define VF_SWITCH_FIELD_LOC(h, l) FIELD_LOC(struct hns_roce_vf_switch, h, l) -#define VF_SWITCH_DATA_CFG_ALW_LPBK_S 1 -#define VF_SWITCH_DATA_CFG_ALW_LCL_LPBK_S 2 -#define VF_SWITCH_DATA_CFG_ALW_DST_OVRD_S 3 +#define VF_SWITCH_VF_ID VF_SWITCH_FIELD_LOC(42, 35) +#define VF_SWITCH_ALW_LPBK VF_SWITCH_FIELD_LOC(65, 65) +#define VF_SWITCH_ALW_LCL_LPBK VF_SWITCH_FIELD_LOC(66, 66) +#define VF_SWITCH_ALW_DST_OVRD VF_SWITCH_FIELD_LOC(67, 67) struct hns_roce_post_mbox { __le32 in_param_l; @@ -1182,11 +1140,10 @@ struct hns_roce_cfg_sgid_tb { __le32 vf_sgid_type_rsv; }; -#define CFG_SGID_TB_TABLE_IDX_S 0 -#define CFG_SGID_TB_TABLE_IDX_M GENMASK(7, 0) +#define SGID_TB_FIELD_LOC(h, l) FIELD_LOC(struct hns_roce_cfg_sgid_tb, h, l) -#define CFG_SGID_TB_VF_SGID_TYPE_S 0 -#define CFG_SGID_TB_VF_SGID_TYPE_M GENMASK(1, 0) +#define CFG_SGID_TB_TABLE_IDX SGID_TB_FIELD_LOC(7, 0) +#define CFG_SGID_TB_VF_SGID_TYPE SGID_TB_FIELD_LOC(161, 160) struct hns_roce_cfg_smac_tb { __le32 tb_idx_rsv; @@ -1194,11 +1151,11 @@ struct hns_roce_cfg_smac_tb { __le32 vf_smac_h_rsv; __le32 rsv[3]; }; -#define CFG_SMAC_TB_IDX_S 0 -#define CFG_SMAC_TB_IDX_M GENMASK(7, 0) -#define CFG_SMAC_TB_VF_SMAC_H_S 0 -#define CFG_SMAC_TB_VF_SMAC_H_M GENMASK(15, 0) +#define SMAC_TB_FIELD_LOC(h, l) FIELD_LOC(struct hns_roce_cfg_smac_tb, h, l) + +#define CFG_SMAC_TB_IDX SMAC_TB_FIELD_LOC(7, 0) +#define CFG_SMAC_TB_VF_SMAC_H SMAC_TB_FIELD_LOC(79, 64) struct hns_roce_cfg_gmv_tb_a { __le32 vf_sgid_l; @@ -1209,16 +1166,11 @@ struct hns_roce_cfg_gmv_tb_a { __le32 resv; }; -#define CFG_GMV_TB_SGID_IDX_S 0 -#define CFG_GMV_TB_SGID_IDX_M GENMASK(7, 0) - -#define CFG_GMV_TB_VF_SGID_TYPE_S 0 -#define CFG_GMV_TB_VF_SGID_TYPE_M GENMASK(1, 0) +#define GMV_TB_A_FIELD_LOC(h, l) FIELD_LOC(struct hns_roce_cfg_gmv_tb_a, h, l) -#define CFG_GMV_TB_VF_VLAN_EN_S 2 - -#define CFG_GMV_TB_VF_VLAN_ID_S 16 -#define CFG_GMV_TB_VF_VLAN_ID_M GENMASK(27, 16) +#define GMV_TB_A_VF_SGID_TYPE GMV_TB_A_FIELD_LOC(129, 128) +#define GMV_TB_A_VF_VLAN_EN GMV_TB_A_FIELD_LOC(130, 130) +#define GMV_TB_A_VF_VLAN_ID GMV_TB_A_FIELD_LOC(155, 144) struct hns_roce_cfg_gmv_tb_b { __le32 vf_smac_l; @@ -1227,8 +1179,10 @@ struct hns_roce_cfg_gmv_tb_b { __le32 resv[3]; }; -#define CFG_GMV_TB_SMAC_H_S 0 -#define CFG_GMV_TB_SMAC_H_M GENMASK(15, 0) +#define GMV_TB_B_FIELD_LOC(h, l) FIELD_LOC(struct hns_roce_cfg_gmv_tb_b, h, l) + +#define GMV_TB_B_SMAC_H GMV_TB_B_FIELD_LOC(47, 32) +#define GMV_TB_B_SGID_IDX GMV_TB_B_FIELD_LOC(71, 64) #define HNS_ROCE_QUERY_PF_CAPS_CMD_NUM 5 struct hns_roce_query_pf_caps_a { diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 755930be01b8e..6b59f97a182b0 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -345,6 +345,10 @@ static int qedr_alloc_resources(struct qedr_dev *dev) if (IS_IWARP(dev)) { xa_init(&dev->qps); dev->iwarp_wq = create_singlethread_workqueue("qedr_iwarpq"); + if (!dev->iwarp_wq) { + rc = -ENOMEM; + goto err1; + } } /* Allocate Status blocks for CNQ */ @@ -352,7 +356,7 @@ static int qedr_alloc_resources(struct qedr_dev *dev) GFP_KERNEL); if (!dev->sb_array) { rc = -ENOMEM; - goto err1; + goto err_destroy_wq; } dev->cnq_array = kcalloc(dev->num_cnq, @@ -403,6 +407,9 @@ err3: kfree(dev->cnq_array); err2: kfree(dev->sb_array); +err_destroy_wq: + if (IS_IWARP(dev)) + destroy_workqueue(dev->iwarp_wq); err1: kfree(dev->sgid_tbl); return rc; diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index a52f275f82634..f8447135a9022 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -956,7 +956,7 @@ nj_release(struct tiger_hw *card) } if (card->irq > 0) free_irq(card->irq, card); - if (card->isac.dch.dev.dev.class) + if (device_is_registered(&card->isac.dch.dev.dev)) mISDN_unregister_device(&card->isac.dch.dev); for (i = 0; i < 2; i++) { diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c index a41b4b2645941..7ea0100f218a0 100644 --- a/drivers/isdn/mISDN/core.c +++ b/drivers/isdn/mISDN/core.c @@ -233,11 +233,12 @@ mISDN_register_device(struct mISDNdevice *dev, if (debug & DEBUG_CORE) printk(KERN_DEBUG "mISDN_register %s %d\n", dev_name(&dev->dev), dev->id); + dev->dev.class = &mISDN_class; + err = create_stack(dev); if (err) goto error1; - dev->dev.class = &mISDN_class; dev->dev.platform_data = dev; dev->dev.parent = parent; dev_set_drvdata(&dev->dev, dev); @@ -249,8 +250,8 @@ mISDN_register_device(struct mISDNdevice *dev, error3: delete_stack(dev); - return err; error1: + put_device(&dev->dev); return err; } diff --git a/drivers/media/cec/platform/cros-ec/cros-ec-cec.c b/drivers/media/cec/platform/cros-ec/cros-ec-cec.c index 2d95e16cd2489..f66699d5dc66e 100644 --- a/drivers/media/cec/platform/cros-ec/cros-ec-cec.c +++ b/drivers/media/cec/platform/cros-ec/cros-ec-cec.c @@ -44,6 +44,8 @@ static void handle_cec_message(struct cros_ec_cec *cros_ec_cec) uint8_t *cec_message = cros_ec->event_data.data.cec_message; unsigned int len = cros_ec->event_size; + if (len > CEC_MAX_MSG_SIZE) + len = CEC_MAX_MSG_SIZE; cros_ec_cec->rx_msg.len = len; memcpy(cros_ec_cec->rx_msg.msg, cec_message, len); diff --git a/drivers/media/cec/platform/s5p/s5p_cec.c b/drivers/media/cec/platform/s5p/s5p_cec.c index 028a09a7531ef..102f1af01000a 100644 --- a/drivers/media/cec/platform/s5p/s5p_cec.c +++ b/drivers/media/cec/platform/s5p/s5p_cec.c @@ -115,6 +115,8 @@ static irqreturn_t s5p_cec_irq_handler(int irq, void *priv) dev_dbg(cec->dev, "Buffer overrun (worker did not process previous message)\n"); cec->rx = STATE_BUSY; cec->msg.len = status >> 24; + if (cec->msg.len > CEC_MAX_MSG_SIZE) + cec->msg.len = CEC_MAX_MSG_SIZE; cec->msg.rx_status = CEC_RX_STATUS_OK; s5p_cec_get_rx_buf(cec, cec->msg.len, cec->msg.msg); diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c index d7fc2595f15b8..efe92eef67db6 100644 --- a/drivers/media/dvb-frontends/drxk_hard.c +++ b/drivers/media/dvb-frontends/drxk_hard.c @@ -6673,7 +6673,7 @@ static int drxk_read_snr(struct dvb_frontend *fe, u16 *snr) static int drxk_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks) { struct drxk_state *state = fe->demodulator_priv; - u16 err; + u16 err = 0; dprintk(1, "\n"); diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c index 41988eb0ec0a5..0f980f68058c0 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c @@ -1270,11 +1270,12 @@ static int rkisp1_capture_link_validate(struct media_link *link) struct rkisp1_capture *cap = video_get_drvdata(vdev); const struct rkisp1_capture_fmt_cfg *fmt = rkisp1_find_fmt_cfg(cap, cap->pix.fmt.pixelformat); - struct v4l2_subdev_format sd_fmt; + struct v4l2_subdev_format sd_fmt = { + .which = V4L2_SUBDEV_FORMAT_ACTIVE, + .pad = link->source->index, + }; int ret; - sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE; - sd_fmt.pad = link->source->index; ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &sd_fmt); if (ret) return ret; diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c index 8fa5b0abf1f9c..e0e7d0b4ea047 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-params.c @@ -275,7 +275,7 @@ static void rkisp1_lsc_config(struct rkisp1_params *params, RKISP1_CIF_ISP_LSC_XSIZE_01 + i * 4); /* program x grad tables */ - data = RKISP1_CIF_ISP_LSC_SECT_SIZE(arg->x_grad_tbl[i * 2], + data = RKISP1_CIF_ISP_LSC_SECT_GRAD(arg->x_grad_tbl[i * 2], arg->x_grad_tbl[i * 2 + 1]); rkisp1_write(params->rkisp1, data, RKISP1_CIF_ISP_LSC_XGRAD_01 + i * 4); @@ -287,7 +287,7 @@ static void rkisp1_lsc_config(struct rkisp1_params *params, RKISP1_CIF_ISP_LSC_YSIZE_01 + i * 4); /* program y grad tables */ - data = RKISP1_CIF_ISP_LSC_SECT_SIZE(arg->y_grad_tbl[i * 2], + data = RKISP1_CIF_ISP_LSC_SECT_GRAD(arg->y_grad_tbl[i * 2], arg->y_grad_tbl[i * 2 + 1]); rkisp1_write(params->rkisp1, data, RKISP1_CIF_ISP_LSC_YGRAD_01 + i * 4); @@ -751,7 +751,7 @@ static void rkisp1_ie_enable(struct rkisp1_params *params, bool en) } } -static void rkisp1_csm_config(struct rkisp1_params *params, bool full_range) +static void rkisp1_csm_config(struct rkisp1_params *params) { static const u16 full_range_coeff[] = { 0x0026, 0x004b, 0x000f, @@ -765,7 +765,7 @@ static void rkisp1_csm_config(struct rkisp1_params *params, bool full_range) }; unsigned int i; - if (full_range) { + if (params->quantization == V4L2_QUANTIZATION_FULL_RANGE) { for (i = 0; i < ARRAY_SIZE(full_range_coeff); i++) rkisp1_write(params->rkisp1, full_range_coeff[i], RKISP1_CIF_ISP_CC_COEFF_0 + i * 4); @@ -1235,11 +1235,7 @@ static void rkisp1_params_config_parameter(struct rkisp1_params *params) rkisp1_param_set_bits(params, RKISP1_CIF_ISP_HIST_PROP, rkisp1_hst_params_default_config.mode); - /* set the range */ - if (params->quantization == V4L2_QUANTIZATION_FULL_RANGE) - rkisp1_csm_config(params, true); - else - rkisp1_csm_config(params, false); + rkisp1_csm_config(params); spin_lock_irq(¶ms->config_lock); diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h index fa33080f51db5..f584ccfe0286f 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-regs.h @@ -480,7 +480,7 @@ (((v0) & 0xFFF) | (((v1) & 0xFFF) << 12)) #define RKISP1_CIF_ISP_LSC_SECT_SIZE(v0, v1) \ (((v0) & 0xFFF) | (((v1) & 0xFFF) << 16)) -#define RKISP1_CIF_ISP_LSC_GRAD_SIZE(v0, v1) \ +#define RKISP1_CIF_ISP_LSC_SECT_GRAD(v0, v1) \ (((v0) & 0xFFF) | (((v1) & 0xFFF) << 16)) /* LSC: ISP_LSC_TABLE_SEL */ diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c index 2070f4b067059..a166ede409675 100644 --- a/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c +++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c @@ -510,6 +510,10 @@ static int rkisp1_rsz_init_config(struct v4l2_subdev *sd, sink_fmt->height = RKISP1_DEFAULT_HEIGHT; sink_fmt->field = V4L2_FIELD_NONE; sink_fmt->code = RKISP1_DEF_FMT; + sink_fmt->colorspace = V4L2_COLORSPACE_SRGB; + sink_fmt->xfer_func = V4L2_XFER_FUNC_SRGB; + sink_fmt->ycbcr_enc = V4L2_YCBCR_ENC_601; + sink_fmt->quantization = V4L2_QUANTIZATION_LIM_RANGE; sink_crop = v4l2_subdev_get_try_crop(sd, sd_state, RKISP1_RSZ_PAD_SINK); diff --git a/drivers/mtd/parsers/bcm47xxpart.c b/drivers/mtd/parsers/bcm47xxpart.c index 6012a10f10c83..13daf9bffd081 100644 --- a/drivers/mtd/parsers/bcm47xxpart.c +++ b/drivers/mtd/parsers/bcm47xxpart.c @@ -233,11 +233,11 @@ static int bcm47xxpart_parse(struct mtd_info *master, } /* Read middle of the block */ - err = mtd_read(master, offset + 0x8000, 0x4, &bytes_read, + err = mtd_read(master, offset + (blocksize / 2), 0x4, &bytes_read, (uint8_t *)buf); if (err && !mtd_is_bitflip(err)) { pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", - offset, err); + offset + (blocksize / 2), err); continue; } diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index e638e3eea9112..e6e1054339b59 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -376,6 +376,17 @@ static struct mdio_driver dsa_loop_drv = { #define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2) +static void dsa_loop_phydevs_unregister(void) +{ + unsigned int i; + + for (i = 0; i < NUM_FIXED_PHYS; i++) + if (!IS_ERR(phydevs[i])) { + fixed_phy_unregister(phydevs[i]); + phy_device_free(phydevs[i]); + } +} + static int __init dsa_loop_init(void) { struct fixed_phy_status status = { @@ -383,23 +394,23 @@ static int __init dsa_loop_init(void) .speed = SPEED_100, .duplex = DUPLEX_FULL, }; - unsigned int i; + unsigned int i, ret; for (i = 0; i < NUM_FIXED_PHYS; i++) phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL); - return mdio_driver_register(&dsa_loop_drv); + ret = mdio_driver_register(&dsa_loop_drv); + if (ret) + dsa_loop_phydevs_unregister(); + + return ret; } module_init(dsa_loop_init); static void __exit dsa_loop_exit(void) { - unsigned int i; - mdio_driver_unregister(&dsa_loop_drv); - for (i = 0; i < NUM_FIXED_PHYS; i++) - if (!IS_ERR(phydevs[i])) - fixed_phy_unregister(phydevs[i]); + dsa_loop_phydevs_unregister(); } module_exit(dsa_loop_exit); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 313ae81120679..a829ba128b9d5 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -656,7 +656,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, dev_kfree_skb_any(skb); if (net_ratelimit()) netdev_err(ndev, "Tx DMA memory map failed\n"); - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } bdp->cbd_datlen = cpu_to_fec16(size); @@ -718,7 +718,7 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, dev_kfree_skb_any(skb); if (net_ratelimit()) netdev_err(ndev, "Tx DMA memory map failed\n"); - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4a070724a8fb6..8a92c6a6e764f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2621,19 +2621,19 @@ static void __ibmvnic_reset(struct work_struct *work) rwi = get_next_rwi(adapter); /* - * If there is another reset queued, free the previous rwi - * and process the new reset even if previous reset failed - * (the previous reset could have failed because of a fail - * over for instance, so process the fail over). - * * If there are no resets queued and the previous reset failed, * the adapter would be in an undefined state. So retry the * previous reset as a hard reset. + * + * Else, free the previous rwi and, if there is another reset + * queued, process the new reset even if previous reset failed + * (the previous reset could have failed because of a fail + * over for instance, so process the fail over). */ - if (rwi) - kfree(tmprwi); - else if (rc) + if (!rwi && rc) rwi = tmprwi; + else + kfree(tmprwi); if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER || rwi->reset_reason == VNIC_RESET_MOBILITY || rc)) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index ecf759ee1c9f5..220bb454626ce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -51,7 +51,6 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id struct stmmac_resources res; struct device_node *np; int ret, i, phy_mode; - bool mdio = false; np = dev_of_node(&pdev->dev); @@ -69,12 +68,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (!plat) return -ENOMEM; + plat->mdio_node = of_get_child_by_name(np, "mdio"); if (plat->mdio_node) { - dev_err(&pdev->dev, "Found MDIO subnode\n"); - mdio = true; - } + dev_info(&pdev->dev, "Found MDIO subnode\n"); - if (mdio) { plat->mdio_bus_data = devm_kzalloc(&pdev->dev, sizeof(*plat->mdio_bus_data), GFP_KERNEL); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 2c0216fe58def..dd7739b5f7918 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -577,7 +577,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) } for (i = 0; i < PHY_MAX_ADDR; i++) { - if ((bus->phy_mask & (1 << i)) == 0) { + if ((bus->phy_mask & BIT(i)) == 0) { struct phy_device *phydev; phydev = mdiobus_scan(bus, i); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index f92d6a12831fe..9909f430d723f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1445,7 +1445,8 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, int err; int i; - if (it->nr_segs > MAX_SKB_FRAGS + 1) + if (it->nr_segs > MAX_SKB_FRAGS + 1 || + len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE); local_bh_disable(); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index bc3f4e4edcdf9..dac7eb77799bd 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -228,6 +228,10 @@ static void brcmf_fweh_event_worker(struct work_struct *work) brcmf_fweh_event_name(event->code), event->code, event->emsg.ifidx, event->emsg.bsscfgidx, event->emsg.addr); + if (event->emsg.bsscfgidx >= BRCMF_MAX_IFS) { + bphy_err(drvr, "invalid bsscfg index: %u\n", event->emsg.bsscfgidx); + goto event_free; + } /* convert event message */ emsg_be = &event->emsg; diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index c6b3334f24c9e..f12f903a9dd13 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -249,11 +249,19 @@ static int fdp_nci_close(struct nci_dev *ndev) static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); + int ret; if (atomic_dec_and_test(&info->data_pkt_counter)) info->data_pkt_counter_cb(ndev); - return info->phy_ops->write(info->phy, skb); + ret = info->phy_ops->write(info->phy, skb); + if (ret < 0) { + kfree_skb(skb); + return ret; + } + + consume_skb(skb); + return 0; } static int fdp_nci_request_firmware(struct nci_dev *ndev) diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 01329b91d59d5..a902720cd8493 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -132,10 +132,15 @@ static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv, ret = -EREMOTEIO; } else ret = 0; + } + + if (ret) { kfree_skb(skb); + return ret; } - return ret; + consume_skb(skb); + return 0; } static void nfcmrvl_i2c_nci_update_config(struct nfcmrvl_private *priv, diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index 518e2afb43a8d..13c433eb694dc 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -77,10 +77,13 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) return -EINVAL; r = info->phy_ops->write(info->phy_id, skb); - if (r < 0) + if (r < 0) { kfree_skb(skb); + return r; + } - return r; + consume_skb(skb); + return 0; } static const struct nci_ops nxp_nci_ops = { diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index 1c412007fabb6..0270e05b68dff 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -110,11 +110,15 @@ static int s3fwrn5_nci_send(struct nci_dev *ndev, struct sk_buff *skb) } ret = s3fwrn5_write(info, skb); - if (ret < 0) + if (ret < 0) { kfree_skb(skb); + mutex_unlock(&info->mutex); + return ret; + } + consume_skb(skb); mutex_unlock(&info->mutex); - return ret; + return 0; } static int s3fwrn5_nci_post_setup(struct nci_dev *ndev) diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c index 8a3b0c3a1e92b..fd99735dca3e6 100644 --- a/drivers/parisc/iosapic.c +++ b/drivers/parisc/iosapic.c @@ -875,6 +875,7 @@ int iosapic_serial_irq(struct parisc_device *dev) return vi->txn_irq; } +EXPORT_SYMBOL(iosapic_serial_irq); #endif diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index c278097926093..2ba9e01355659 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -792,9 +792,8 @@ static int __unset_online(struct device *dev, void *data) { struct idset *set = data; struct subchannel *sch = to_subchannel(dev); - struct ccw_device *cdev = sch_get_cdev(sch); - if (cdev && cdev->online) + if (sch->st == SUBCHANNEL_TYPE_IO && sch->config.ena) idset_sch_del(set, sch->schid); return 0; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index b2508a00bafdf..457ff86e02b30 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -1558,10 +1558,7 @@ struct lpfc_hba { u32 cgn_acqe_cnt; /* RX monitor handling for CMF */ - struct rxtable_entry *rxtable; /* RX_monitor information */ - atomic_t rxtable_idx_head; -#define LPFC_RXMONITOR_TABLE_IN_USE (LPFC_MAX_RXMONITOR_ENTRY + 73) - atomic_t rxtable_idx_tail; + struct lpfc_rx_info_monitor *rx_monitor; atomic_t rx_max_read_cnt; /* Maximum read bytes */ uint64_t rx_block_cnt; @@ -1610,7 +1607,8 @@ struct lpfc_hba { #define LPFC_MAX_RXMONITOR_ENTRY 800 #define LPFC_MAX_RXMONITOR_DUMP 32 -struct rxtable_entry { +struct rx_info_entry { + uint64_t cmf_bytes; /* Total no of read bytes for CMF_SYNC_WQE */ uint64_t total_bytes; /* Total no of read bytes requested */ uint64_t rcv_bytes; /* Total no of read bytes completed */ uint64_t avg_io_size; @@ -1624,6 +1622,13 @@ struct rxtable_entry { uint32_t timer_interval; }; +struct lpfc_rx_info_monitor { + struct rx_info_entry *ring; /* info organized in a circular buffer */ + u32 head_idx, tail_idx; /* index to head/tail of ring */ + spinlock_t lock; /* spinlock for ring */ + u32 entries; /* storing number entries/size of ring */ +}; + static inline struct Scsi_Host * lpfc_shost_from_vport(struct lpfc_vport *vport) { diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index c9770b1d2366a..470239394e649 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -90,6 +90,14 @@ void lpfc_cgn_dump_rxmonitor(struct lpfc_hba *phba); void lpfc_cgn_update_stat(struct lpfc_hba *phba, uint32_t dtag); void lpfc_unblock_requests(struct lpfc_hba *phba); void lpfc_block_requests(struct lpfc_hba *phba); +int lpfc_rx_monitor_create_ring(struct lpfc_rx_info_monitor *rx_monitor, + u32 entries); +void lpfc_rx_monitor_destroy_ring(struct lpfc_rx_info_monitor *rx_monitor); +void lpfc_rx_monitor_record(struct lpfc_rx_info_monitor *rx_monitor, + struct rx_info_entry *entry); +u32 lpfc_rx_monitor_report(struct lpfc_hba *phba, + struct lpfc_rx_info_monitor *rx_monitor, char *buf, + u32 buf_len, u32 max_read_entries); void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *, LPFC_MBOXQ_t *); void lpfc_mbx_cmpl_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *); diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 79bc86ba59b35..8e8bbe734e875 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -5520,7 +5520,7 @@ lpfc_rx_monitor_open(struct inode *inode, struct file *file) if (!debug) goto out; - debug->buffer = vmalloc(MAX_DEBUGFS_RX_TABLE_SIZE); + debug->buffer = vmalloc(MAX_DEBUGFS_RX_INFO_SIZE); if (!debug->buffer) { kfree(debug); goto out; @@ -5541,55 +5541,18 @@ lpfc_rx_monitor_read(struct file *file, char __user *buf, size_t nbytes, struct lpfc_rx_monitor_debug *debug = file->private_data; struct lpfc_hba *phba = (struct lpfc_hba *)debug->i_private; char *buffer = debug->buffer; - struct rxtable_entry *entry; - int i, len = 0, head, tail, last, start; - - head = atomic_read(&phba->rxtable_idx_head); - while (head == LPFC_RXMONITOR_TABLE_IN_USE) { - /* Table is getting updated */ - msleep(20); - head = atomic_read(&phba->rxtable_idx_head); - } - tail = atomic_xchg(&phba->rxtable_idx_tail, head); - if (!phba->rxtable || head == tail) { - len += scnprintf(buffer + len, MAX_DEBUGFS_RX_TABLE_SIZE - len, - "Rxtable is empty\n"); - goto out; - } - last = (head > tail) ? head : LPFC_MAX_RXMONITOR_ENTRY; - start = tail; - - len += scnprintf(buffer + len, MAX_DEBUGFS_RX_TABLE_SIZE - len, - " MaxBPI\t Total Data Cmd Total Data Cmpl " - " Latency(us) Avg IO Size\tMax IO Size IO cnt " - "Info BWutil(ms)\n"); -get_table: - for (i = start; i < last; i++) { - entry = &phba->rxtable[i]; - len += scnprintf(buffer + len, MAX_DEBUGFS_RX_TABLE_SIZE - len, - "%3d:%12lld %12lld\t%12lld\t" - "%8lldus\t%8lld\t%10lld " - "%8d %2d %2d(%2d)\n", - i, entry->max_bytes_per_interval, - entry->total_bytes, - entry->rcv_bytes, - entry->avg_io_latency, - entry->avg_io_size, - entry->max_read_cnt, - entry->io_cnt, - entry->cmf_info, - entry->timer_utilization, - entry->timer_interval); + if (!phba->rx_monitor) { + scnprintf(buffer, MAX_DEBUGFS_RX_INFO_SIZE, + "Rx Monitor Info is empty.\n"); + } else { + lpfc_rx_monitor_report(phba, phba->rx_monitor, buffer, + MAX_DEBUGFS_RX_INFO_SIZE, + LPFC_MAX_RXMONITOR_ENTRY); } - if (head != last) { - start = 0; - last = head; - goto get_table; - } -out: - return simple_read_from_buffer(buf, nbytes, ppos, buffer, len); + return simple_read_from_buffer(buf, nbytes, ppos, buffer, + strlen(buffer)); } static int diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h index a5bf71b349720..f71e5b6311ac0 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.h +++ b/drivers/scsi/lpfc/lpfc_debugfs.h @@ -282,7 +282,7 @@ struct lpfc_idiag { void *ptr_private; }; -#define MAX_DEBUGFS_RX_TABLE_SIZE (100 * LPFC_MAX_RXMONITOR_ENTRY) +#define MAX_DEBUGFS_RX_INFO_SIZE (128 * LPFC_MAX_RXMONITOR_ENTRY) struct lpfc_rx_monitor_debug { char *i_private; char *buffer; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index fe8b4258cdc05..855817f6fe671 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -5428,38 +5428,12 @@ lpfc_async_link_speed_to_read_top(struct lpfc_hba *phba, uint8_t speed_code) void lpfc_cgn_dump_rxmonitor(struct lpfc_hba *phba) { - struct rxtable_entry *entry; - int cnt = 0, head, tail, last, start; - - head = atomic_read(&phba->rxtable_idx_head); - tail = atomic_read(&phba->rxtable_idx_tail); - if (!phba->rxtable || head == tail) { - lpfc_printf_log(phba, KERN_ERR, LOG_CGN_MGMT, - "4411 Rxtable is empty\n"); - return; - } - last = tail; - start = head; - - /* Display the last LPFC_MAX_RXMONITOR_DUMP entries from the rxtable */ - while (start != last) { - if (start) - start--; - else - start = LPFC_MAX_RXMONITOR_ENTRY - 1; - entry = &phba->rxtable[start]; + if (!phba->rx_monitor) { lpfc_printf_log(phba, KERN_INFO, LOG_CGN_MGMT, - "4410 %02d: MBPI %lld Xmit %lld Cmpl %lld " - "Lat %lld ASz %lld Info %02d BWUtil %d " - "Int %d slot %d\n", - cnt, entry->max_bytes_per_interval, - entry->total_bytes, entry->rcv_bytes, - entry->avg_io_latency, entry->avg_io_size, - entry->cmf_info, entry->timer_utilization, - entry->timer_interval, start); - cnt++; - if (cnt >= LPFC_MAX_RXMONITOR_DUMP) - return; + "4411 Rx Monitor Info is empty.\n"); + } else { + lpfc_rx_monitor_report(phba, phba->rx_monitor, NULL, 0, + LPFC_MAX_RXMONITOR_DUMP); } } @@ -5866,11 +5840,10 @@ lpfc_cmf_timer(struct hrtimer *timer) { struct lpfc_hba *phba = container_of(timer, struct lpfc_hba, cmf_timer); - struct rxtable_entry *entry; + struct rx_info_entry entry; uint32_t io_cnt; - uint32_t head, tail; uint32_t busy, max_read; - uint64_t total, rcv, lat, mbpi; + uint64_t total, rcv, lat, mbpi, extra, cnt; int timer_interval = LPFC_CMF_INTERVAL; uint32_t ms; struct lpfc_cgn_stat *cgs; @@ -5937,12 +5910,27 @@ lpfc_cmf_timer(struct hrtimer *timer) phba->hba_flag & HBA_SETUP) { mbpi = phba->cmf_last_sync_bw; phba->cmf_last_sync_bw = 0; - lpfc_issue_cmf_sync_wqe(phba, LPFC_CMF_INTERVAL, total); + extra = 0; + + /* Calculate any extra bytes needed to account for the + * timer accuracy. If we are less than LPFC_CMF_INTERVAL + * calculate the adjustment needed for total to reflect + * a full LPFC_CMF_INTERVAL. + */ + if (ms && ms < LPFC_CMF_INTERVAL) { + cnt = div_u64(total, ms); /* bytes per ms */ + cnt *= LPFC_CMF_INTERVAL; /* what total should be */ + if (cnt > mbpi) + cnt = mbpi; + extra = cnt - total; + } + lpfc_issue_cmf_sync_wqe(phba, LPFC_CMF_INTERVAL, total + extra); } else { /* For Monitor mode or link down we want mbpi * to be the full link speed */ mbpi = phba->cmf_link_byte_count; + extra = 0; } phba->cmf_timer_cnt++; @@ -5968,39 +5956,30 @@ lpfc_cmf_timer(struct hrtimer *timer) } /* Save rxmonitor information for debug */ - if (phba->rxtable) { - head = atomic_xchg(&phba->rxtable_idx_head, - LPFC_RXMONITOR_TABLE_IN_USE); - entry = &phba->rxtable[head]; - entry->total_bytes = total; - entry->rcv_bytes = rcv; - entry->cmf_busy = busy; - entry->cmf_info = phba->cmf_active_info; + if (phba->rx_monitor) { + entry.total_bytes = total; + entry.cmf_bytes = total + extra; + entry.rcv_bytes = rcv; + entry.cmf_busy = busy; + entry.cmf_info = phba->cmf_active_info; if (io_cnt) { - entry->avg_io_latency = div_u64(lat, io_cnt); - entry->avg_io_size = div_u64(rcv, io_cnt); + entry.avg_io_latency = div_u64(lat, io_cnt); + entry.avg_io_size = div_u64(rcv, io_cnt); } else { - entry->avg_io_latency = 0; - entry->avg_io_size = 0; + entry.avg_io_latency = 0; + entry.avg_io_size = 0; } - entry->max_read_cnt = max_read; - entry->io_cnt = io_cnt; - entry->max_bytes_per_interval = mbpi; + entry.max_read_cnt = max_read; + entry.io_cnt = io_cnt; + entry.max_bytes_per_interval = mbpi; if (phba->cmf_active_mode == LPFC_CFG_MANAGED) - entry->timer_utilization = phba->cmf_last_ts; + entry.timer_utilization = phba->cmf_last_ts; else - entry->timer_utilization = ms; - entry->timer_interval = ms; + entry.timer_utilization = ms; + entry.timer_interval = ms; phba->cmf_last_ts = 0; - /* Increment rxtable index */ - head = (head + 1) % LPFC_MAX_RXMONITOR_ENTRY; - tail = atomic_read(&phba->rxtable_idx_tail); - if (head == tail) { - tail = (tail + 1) % LPFC_MAX_RXMONITOR_ENTRY; - atomic_set(&phba->rxtable_idx_tail, tail); - } - atomic_set(&phba->rxtable_idx_head, head); + lpfc_rx_monitor_record(phba->rx_monitor, &entry); } if (phba->cmf_active_mode == LPFC_CFG_MONITOR) { diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c index 870e53b8f81dd..5d36b35148646 100644 --- a/drivers/scsi/lpfc/lpfc_mem.c +++ b/drivers/scsi/lpfc/lpfc_mem.c @@ -344,9 +344,12 @@ lpfc_mem_free_all(struct lpfc_hba *phba) phba->cgn_i = NULL; } - /* Free RX table */ - kfree(phba->rxtable); - phba->rxtable = NULL; + /* Free RX Monitor */ + if (phba->rx_monitor) { + lpfc_rx_monitor_destroy_ring(phba->rx_monitor); + kfree(phba->rx_monitor); + phba->rx_monitor = NULL; + } /* Free the iocb lookup array */ kfree(psli->iocbq_lookup); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 0024c0e0afd30..d6e761adf1f1d 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -7878,6 +7878,172 @@ static void lpfc_sli4_dip(struct lpfc_hba *phba) } } +/** + * lpfc_rx_monitor_create_ring - Initialize ring buffer for rx_monitor + * @rx_monitor: Pointer to lpfc_rx_info_monitor object + * @entries: Number of rx_info_entry objects to allocate in ring + * + * Return: + * 0 - Success + * ENOMEM - Failure to kmalloc + **/ +int lpfc_rx_monitor_create_ring(struct lpfc_rx_info_monitor *rx_monitor, + u32 entries) +{ + rx_monitor->ring = kmalloc_array(entries, sizeof(struct rx_info_entry), + GFP_KERNEL); + if (!rx_monitor->ring) + return -ENOMEM; + + rx_monitor->head_idx = 0; + rx_monitor->tail_idx = 0; + spin_lock_init(&rx_monitor->lock); + rx_monitor->entries = entries; + + return 0; +} + +/** + * lpfc_rx_monitor_destroy_ring - Free ring buffer for rx_monitor + * @rx_monitor: Pointer to lpfc_rx_info_monitor object + **/ +void lpfc_rx_monitor_destroy_ring(struct lpfc_rx_info_monitor *rx_monitor) +{ + spin_lock(&rx_monitor->lock); + kfree(rx_monitor->ring); + rx_monitor->ring = NULL; + rx_monitor->entries = 0; + rx_monitor->head_idx = 0; + rx_monitor->tail_idx = 0; + spin_unlock(&rx_monitor->lock); +} + +/** + * lpfc_rx_monitor_record - Insert an entry into rx_monitor's ring + * @rx_monitor: Pointer to lpfc_rx_info_monitor object + * @entry: Pointer to rx_info_entry + * + * Used to insert an rx_info_entry into rx_monitor's ring. Note that this is a + * deep copy of rx_info_entry not a shallow copy of the rx_info_entry ptr. + * + * This is called from lpfc_cmf_timer, which is in timer/softirq context. + * + * In cases of old data overflow, we do a best effort of FIFO order. + **/ +void lpfc_rx_monitor_record(struct lpfc_rx_info_monitor *rx_monitor, + struct rx_info_entry *entry) +{ + struct rx_info_entry *ring = rx_monitor->ring; + u32 *head_idx = &rx_monitor->head_idx; + u32 *tail_idx = &rx_monitor->tail_idx; + spinlock_t *ring_lock = &rx_monitor->lock; + u32 ring_size = rx_monitor->entries; + + spin_lock(ring_lock); + memcpy(&ring[*tail_idx], entry, sizeof(*entry)); + *tail_idx = (*tail_idx + 1) % ring_size; + + /* Best effort of FIFO saved data */ + if (*tail_idx == *head_idx) + *head_idx = (*head_idx + 1) % ring_size; + + spin_unlock(ring_lock); +} + +/** + * lpfc_rx_monitor_report - Read out rx_monitor's ring + * @phba: Pointer to lpfc_hba object + * @rx_monitor: Pointer to lpfc_rx_info_monitor object + * @buf: Pointer to char buffer that will contain rx monitor info data + * @buf_len: Length buf including null char + * @max_read_entries: Maximum number of entries to read out of ring + * + * Used to dump/read what's in rx_monitor's ring buffer. + * + * If buf is NULL || buf_len == 0, then it is implied that we want to log the + * information to kmsg instead of filling out buf. + * + * Return: + * Number of entries read out of the ring + **/ +u32 lpfc_rx_monitor_report(struct lpfc_hba *phba, + struct lpfc_rx_info_monitor *rx_monitor, char *buf, + u32 buf_len, u32 max_read_entries) +{ + struct rx_info_entry *ring = rx_monitor->ring; + struct rx_info_entry *entry; + u32 *head_idx = &rx_monitor->head_idx; + u32 *tail_idx = &rx_monitor->tail_idx; + spinlock_t *ring_lock = &rx_monitor->lock; + u32 ring_size = rx_monitor->entries; + u32 cnt = 0; + char tmp[DBG_LOG_STR_SZ] = {0}; + bool log_to_kmsg = (!buf || !buf_len) ? true : false; + + if (!log_to_kmsg) { + /* clear the buffer to be sure */ + memset(buf, 0, buf_len); + + scnprintf(buf, buf_len, "\t%-16s%-16s%-16s%-16s%-8s%-8s%-8s" + "%-8s%-8s%-8s%-16s\n", + "MaxBPI", "Tot_Data_CMF", + "Tot_Data_Cmd", "Tot_Data_Cmpl", + "Lat(us)", "Avg_IO", "Max_IO", "Bsy", + "IO_cnt", "Info", "BWutil(ms)"); + } + + /* Needs to be _bh because record is called from timer interrupt + * context + */ + spin_lock_bh(ring_lock); + while (*head_idx != *tail_idx) { + entry = &ring[*head_idx]; + + /* Read out this entry's data. */ + if (!log_to_kmsg) { + /* If !log_to_kmsg, then store to buf. */ + scnprintf(tmp, sizeof(tmp), + "%03d:\t%-16llu%-16llu%-16llu%-16llu%-8llu" + "%-8llu%-8llu%-8u%-8u%-8u%u(%u)\n", + *head_idx, entry->max_bytes_per_interval, + entry->cmf_bytes, entry->total_bytes, + entry->rcv_bytes, entry->avg_io_latency, + entry->avg_io_size, entry->max_read_cnt, + entry->cmf_busy, entry->io_cnt, + entry->cmf_info, entry->timer_utilization, + entry->timer_interval); + + /* Check for buffer overflow */ + if ((strlen(buf) + strlen(tmp)) >= buf_len) + break; + + /* Append entry's data to buffer */ + strlcat(buf, tmp, buf_len); + } else { + lpfc_printf_log(phba, KERN_INFO, LOG_CGN_MGMT, + "4410 %02u: MBPI %llu Xmit %llu " + "Cmpl %llu Lat %llu ASz %llu Info %02u " + "BWUtil %u Int %u slot %u\n", + cnt, entry->max_bytes_per_interval, + entry->total_bytes, entry->rcv_bytes, + entry->avg_io_latency, + entry->avg_io_size, entry->cmf_info, + entry->timer_utilization, + entry->timer_interval, *head_idx); + } + + *head_idx = (*head_idx + 1) % ring_size; + + /* Don't feed more than max_read_entries */ + cnt++; + if (cnt >= max_read_entries) + break; + } + spin_unlock_bh(ring_lock); + + return cnt; +} + /** * lpfc_cmf_setup - Initialize idle_stat tracking * @phba: Pointer to HBA context object. @@ -8069,19 +8235,29 @@ no_cmf: phba->cmf_interval_rate = LPFC_CMF_INTERVAL; /* Allocate RX Monitor Buffer */ - if (!phba->rxtable) { - phba->rxtable = kmalloc_array(LPFC_MAX_RXMONITOR_ENTRY, - sizeof(struct rxtable_entry), - GFP_KERNEL); - if (!phba->rxtable) { + if (!phba->rx_monitor) { + phba->rx_monitor = kzalloc(sizeof(*phba->rx_monitor), + GFP_KERNEL); + + if (!phba->rx_monitor) { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "2644 Failed to alloc memory " "for RX Monitor Buffer\n"); return -ENOMEM; } + + /* Instruct the rx_monitor object to instantiate its ring */ + if (lpfc_rx_monitor_create_ring(phba->rx_monitor, + LPFC_MAX_RXMONITOR_ENTRY)) { + kfree(phba->rx_monitor); + phba->rx_monitor = NULL; + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2645 Failed to alloc memory " + "for RX Monitor's Ring\n"); + return -ENOMEM; + } } - atomic_set(&phba->rxtable_idx_head, 0); - atomic_set(&phba->rxtable_idx_tail, 0); + return 0; } diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 920aae661c5b2..774864b54b97c 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -816,6 +816,14 @@ store_state_field(struct device *dev, struct device_attribute *attr, } mutex_lock(&sdev->state_mutex); + switch (sdev->sdev_state) { + case SDEV_RUNNING: + case SDEV_OFFLINE: + break; + default: + mutex_unlock(&sdev->state_mutex); + return -EINVAL; + } if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) { ret = 0; } else { diff --git a/drivers/staging/media/meson/vdec/vdec.c b/drivers/staging/media/meson/vdec/vdec.c index e51d69c4729df..040ed56eb24f3 100644 --- a/drivers/staging/media/meson/vdec/vdec.c +++ b/drivers/staging/media/meson/vdec/vdec.c @@ -1105,6 +1105,7 @@ static int vdec_probe(struct platform_device *pdev) err_vdev_release: video_device_release(vdev); + v4l2_device_unregister(&core->v4l2_dev); return ret; } @@ -1113,6 +1114,7 @@ static int vdec_remove(struct platform_device *pdev) struct amvdec_core *core = platform_get_drvdata(pdev); video_unregister_device(core->vdev_dec); + v4l2_device_unregister(&core->v4l2_dev); return 0; } diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 3fc426dad2df3..a44e5b53e7a91 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -334,6 +334,9 @@ tee_ioctl_shm_register(struct tee_context *ctx, if (data.flags) return -EINVAL; + if (!access_ok((void __user *)(unsigned long)data.addr, data.length)) + return -EFAULT; + shm = tee_shm_register(ctx, data.addr, data.length, TEE_SHM_DMA_BUF | TEE_SHM_USER_MAPPED); if (IS_ERR(shm)) diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index bd96ebb82c8ec..6fb4400333fb4 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -223,9 +223,6 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, goto err; } - if (!access_ok((void __user *)addr, length)) - return ERR_PTR(-EFAULT); - mutex_lock(&teedev->mutex); shm->id = idr_alloc(&teedev->idr, shm, 1, 0, GFP_KERNEL); mutex_unlock(&teedev->mutex); diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index 39fc96dc2531c..da63e76c7530c 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -118,7 +118,7 @@ config SERIAL_8250_CONSOLE config SERIAL_8250_GSC tristate - depends on SERIAL_8250 && GSC + depends on SERIAL_8250 && PARISC default SERIAL_8250 config SERIAL_8250_DMA diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index 4379ca4842ae7..0f2677695b521 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -591,6 +591,11 @@ static int ar933x_config_rs485(struct uart_port *port, dev_err(port->dev, "RS485 needs rts-gpio\n"); return 1; } + + if (rs485conf->flags & SER_RS485_ENABLED) + gpiod_set_value(up->rts_gpiod, + !!(rs485conf->flags & SER_RS485_RTS_AFTER_SEND)); + port->rs485 = *rs485conf; return 0; } diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index b0470f4f595ee..3feb6e40d56d8 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1041,6 +1041,48 @@ stifb_copyarea(struct fb_info *info, const struct fb_copyarea *area) SETUP_FB(fb); } +#define ARTIST_VRAM_SIZE 0x000804 +#define ARTIST_VRAM_SRC 0x000808 +#define ARTIST_VRAM_SIZE_TRIGGER_WINFILL 0x000a04 +#define ARTIST_VRAM_DEST_TRIGGER_BLOCKMOVE 0x000b00 +#define ARTIST_SRC_BM_ACCESS 0x018008 +#define ARTIST_FGCOLOR 0x018010 +#define ARTIST_BGCOLOR 0x018014 +#define ARTIST_BITMAP_OP 0x01801c + +static void +stifb_fillrect(struct fb_info *info, const struct fb_fillrect *rect) +{ + struct stifb_info *fb = container_of(info, struct stifb_info, info); + + if (rect->rop != ROP_COPY || + (fb->id == S9000_ID_HCRX && fb->info.var.bits_per_pixel == 32)) + return cfb_fillrect(info, rect); + + SETUP_HW(fb); + + if (fb->info.var.bits_per_pixel == 32) { + WRITE_WORD(0xBBA0A000, fb, REG_10); + + NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xffffffff); + } else { + WRITE_WORD(fb->id == S9000_ID_HCRX ? 0x13a02000 : 0x13a01000, fb, REG_10); + + NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xff); + } + + WRITE_WORD(0x03000300, fb, ARTIST_BITMAP_OP); + WRITE_WORD(0x2ea01000, fb, ARTIST_SRC_BM_ACCESS); + NGLE_QUICK_SET_DST_BM_ACCESS(fb, 0x2ea01000); + NGLE_REALLY_SET_IMAGE_FG_COLOR(fb, rect->color); + WRITE_WORD(0, fb, ARTIST_BGCOLOR); + + NGLE_SET_DSTXY(fb, (rect->dx << 16) | (rect->dy)); + SET_LENXY_START_RECFILL(fb, (rect->width << 16) | (rect->height)); + + SETUP_FB(fb); +} + static void __init stifb_init_display(struct stifb_info *fb) { @@ -1105,7 +1147,7 @@ static const struct fb_ops stifb_ops = { .owner = THIS_MODULE, .fb_setcolreg = stifb_setcolreg, .fb_blank = stifb_blank, - .fb_fillrect = cfb_fillrect, + .fb_fillrect = stifb_fillrect, .fb_copyarea = stifb_copyarea, .fb_imageblit = cfb_imageblit, }; @@ -1297,7 +1339,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) goto out_err0; } info->screen_size = fix->smem_len; - info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_COPYAREA; + info->flags = FBINFO_HWACCEL_COPYAREA | FBINFO_HWACCEL_FILLRECT; info->pseudo_palette = &fb->pseudo_palette; /* This has to be done !!! */ diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2e7c3e48bc9ce..60bec5a108fa3 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -289,8 +289,10 @@ static void prelim_release(struct preftree *preftree) struct prelim_ref *ref, *next_ref; rbtree_postorder_for_each_entry_safe(ref, next_ref, - &preftree->root.rb_root, rbnode) + &preftree->root.rb_root, rbnode) { + free_inode_elem_list(ref->inode_list); free_pref(ref); + } preftree->root = RB_ROOT_CACHED; preftree->count = 0; @@ -648,6 +650,18 @@ unode_aux_to_inode_list(struct ulist_node *node) return (struct extent_inode_elem *)(uintptr_t)node->aux; } +static void free_leaf_list(struct ulist *ulist) +{ + struct ulist_node *node; + struct ulist_iterator uiter; + + ULIST_ITER_INIT(&uiter); + while ((node = ulist_next(ulist, &uiter))) + free_inode_elem_list(unode_aux_to_inode_list(node)); + + ulist_free(ulist); +} + /* * We maintain three separate rbtrees: one for direct refs, one for * indirect refs which have a key, and one for indirect refs which do not @@ -762,7 +776,11 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, cond_resched(); } out: - ulist_free(parents); + /* + * We may have inode lists attached to refs in the parents ulist, so we + * must free them before freeing the ulist and its refs. + */ + free_leaf_list(parents); return ret; } @@ -1371,6 +1389,12 @@ again: if (ret < 0) goto out; ref->inode_list = eie; + /* + * We transferred the list ownership to the ref, + * so set to NULL to avoid a double free in case + * an error happens after this. + */ + eie = NULL; } ret = ulist_add_merge_ptr(refs, ref->parent, ref->inode_list, @@ -1396,6 +1420,14 @@ again: eie->next = ref->inode_list; } eie = NULL; + /* + * We have transferred the inode list ownership from + * this ref to the ref we added to the 'refs' ulist. + * So set this ref's inode list to NULL to avoid + * use-after-free when our caller uses it or double + * frees in case an error happens before we return. + */ + ref->inode_list = NULL; } cond_resched(); } @@ -1412,24 +1444,6 @@ out: return ret; } -static void free_leaf_list(struct ulist *blocks) -{ - struct ulist_node *node = NULL; - struct extent_inode_elem *eie; - struct ulist_iterator uiter; - - ULIST_ITER_INIT(&uiter); - while ((node = ulist_next(blocks, &uiter))) { - if (!node->aux) - continue; - eie = unode_aux_to_inode_list(node); - free_inode_elem_list(eie); - node->aux = 0; - } - - ulist_free(blocks); -} - /* * Finds all leafs with a reference to the specified combination of bytenr and * offset. key_list_head will point to a list of corresponding keys (caller must diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 1d4c2397d0d62..fab7eb76e53b2 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -58,7 +58,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, } struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h index f32f4113c976a..5afb7ca428289 100644 --- a/fs/btrfs/export.h +++ b/fs/btrfs/export.h @@ -19,7 +19,7 @@ struct btrfs_fid { } __attribute__ ((packed)); struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation); struct dentry *btrfs_get_parent(struct dentry *child); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b90e9aa24005a..e72973f7c2cd3 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3307,21 +3307,22 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, } /* - * If this is a leaf and there are tree mod log users, we may - * have recorded mod log operations that point to this leaf. - * So we must make sure no one reuses this leaf's extent before - * mod log operations are applied to a node, otherwise after - * rewinding a node using the mod log operations we get an - * inconsistent btree, as the leaf's extent may now be used as - * a node or leaf for another different btree. + * If there are tree mod log users we may have recorded mod log + * operations for this node. If we re-allocate this node we + * could replay operations on this node that happened when it + * existed in a completely different root. For example if it + * was part of root A, then was reallocated to root B, and we + * are doing a btrfs_old_search_slot(root b), we could replay + * operations that happened when the block was part of root A, + * giving us an inconsistent view of the btree. + * * We are safe from races here because at this point no other * node or root points to this extent buffer, so if after this - * check a new tree mod log user joins, it will not be able to - * find a node pointing to this leaf and record operations that - * point to this leaf. + * check a new tree mod log user joins we will not have an + * existing log of operations on this node that we have to + * contend with. */ - if (btrfs_header_level(buf) == 0 && - test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags)) + if (test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags)) must_pin = true; if (must_pin || btrfs_is_zoned(fs_info)) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 1c597cd6c0247..90934711dcf0f 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1906,7 +1906,6 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { - const bool is_sync_write = (iocb->ki_flags & IOCB_DSYNC); struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -1917,6 +1916,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) loff_t endbyte; ssize_t err; unsigned int ilock_flags = 0; + struct iomap_dio *dio; if (iocb->ki_flags & IOCB_NOWAIT) ilock_flags |= BTRFS_ILOCK_TRY; @@ -1959,15 +1959,6 @@ relock: goto buffered; } - /* - * We remove IOCB_DSYNC so that we don't deadlock when iomap_dio_rw() - * calls generic_write_sync() (through iomap_dio_complete()), because - * that results in calling fsync (btrfs_sync_file()) which will try to - * lock the inode in exclusive/write mode. - */ - if (is_sync_write) - iocb->ki_flags &= ~IOCB_DSYNC; - /* * The iov_iter can be mapped to the same file range we are writing to. * If that's the case, then we will deadlock in the iomap code, because @@ -1986,12 +1977,23 @@ relock: * So here we disable page faults in the iov_iter and then retry if we * got -EFAULT, faulting in the pages before the retry. */ -again: from->nofault = true; - err = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - IOMAP_DIO_PARTIAL, written); + dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + IOMAP_DIO_PARTIAL, written); from->nofault = false; + /* + * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync + * iocb, and that needs to lock the inode. So unlock it before calling + * iomap_dio_complete() to avoid a deadlock. + */ + btrfs_inode_unlock(inode, ilock_flags); + + if (IS_ERR_OR_NULL(dio)) + err = PTR_ERR_OR_ZERO(dio); + else + err = iomap_dio_complete(dio); + /* No increment (+=) because iomap returns a cumulative value. */ if (err > 0) written = err; @@ -2017,19 +2019,10 @@ again: } else { fault_in_iov_iter_readable(from, left); prev_left = left; - goto again; + goto relock; } } - btrfs_inode_unlock(inode, ilock_flags); - - /* - * Add back IOCB_DSYNC. Our caller, btrfs_file_write_iter(), will do - * the fsync (call generic_write_sync()). - */ - if (is_sync_write) - iocb->ki_flags |= IOCB_DSYNC; - /* If 'err' is -ENOTBLK then it means we must fallback to buffered IO. */ if ((err < 0 && err != -ENOTBLK) || !iov_iter_count(from)) goto out; diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 19ba7d5b7d8ff..a374b62c9de9e 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -232,8 +232,10 @@ static int test_no_shared_qgroup(struct btrfs_root *root, ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { @@ -266,8 +268,10 @@ static int test_no_shared_qgroup(struct btrfs_root *root, } ret = remove_extent_item(root, nodesize, nodesize); - if (ret) + if (ret) { + ulist_free(old_roots); return -EINVAL; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { @@ -329,8 +333,10 @@ static int test_multiple_refs(struct btrfs_root *root, ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { @@ -362,8 +368,10 @@ static int test_multiple_refs(struct btrfs_root *root, ret = add_tree_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { @@ -401,8 +409,10 @@ static int test_multiple_refs(struct btrfs_root *root, ret = remove_extent_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 278634a63895d..ad5c935f7f069 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3711,12 +3711,11 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, pSMB->AndXCommand = 0xFF; pSMB->Flags = cpu_to_le16(TCON_EXTENDED_SECINFO); bcc_ptr = &pSMB->Password[0]; - if (tcon->pipe || (ses->server->sec_mode & SECMODE_USER)) { - pSMB->PasswordLength = cpu_to_le16(1); /* minimum */ - *bcc_ptr = 0; /* password is null byte */ - bcc_ptr++; /* skip password */ - /* already aligned so no need to do it below */ - } + + pSMB->PasswordLength = cpu_to_le16(1); /* minimum */ + *bcc_ptr = 0; /* password is null byte */ + bcc_ptr++; /* skip password */ + /* already aligned so no need to do it below */ if (ses->server->sign) smb_buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE; diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index cb25ef0cdf1f3..373c434b375c0 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -220,7 +220,7 @@ struct fscrypt_info { * will be NULL if the master key was found in a process-subscribed * keyring rather than in the filesystem-level keyring. */ - struct key *ci_master_key; + struct fscrypt_master_key *ci_master_key; /* * Link in list of inodes that were unlocked with the master key. @@ -430,6 +430,40 @@ struct fscrypt_master_key_secret { */ struct fscrypt_master_key { + /* + * Back-pointer to the super_block of the filesystem to which this + * master key has been added. Only valid if ->mk_active_refs > 0. + */ + struct super_block *mk_sb; + + /* + * Link in ->mk_sb->s_master_keys->key_hashtable. + * Only valid if ->mk_active_refs > 0. + */ + struct hlist_node mk_node; + + /* Semaphore that protects ->mk_secret and ->mk_users */ + struct rw_semaphore mk_sem; + + /* + * Active and structural reference counts. An active ref guarantees + * that the struct continues to exist, continues to be in the keyring + * ->mk_sb->s_master_keys, and that any embedded subkeys (e.g. + * ->mk_direct_keys) that have been prepared continue to exist. + * A structural ref only guarantees that the struct continues to exist. + * + * There is one active ref associated with ->mk_secret being present, + * and one active ref for each inode in ->mk_decrypted_inodes. + * + * There is one structural ref associated with the active refcount being + * nonzero. Finding a key in the keyring also takes a structural ref, + * which is then held temporarily while the key is operated on. + */ + refcount_t mk_active_refs; + refcount_t mk_struct_refs; + + struct rcu_head mk_rcu_head; + /* * The secret key material. After FS_IOC_REMOVE_ENCRYPTION_KEY is * executed, this is wiped and no new inodes can be unlocked with this @@ -438,7 +472,10 @@ struct fscrypt_master_key { * FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or * FS_IOC_ADD_ENCRYPTION_KEY can add the secret again. * - * Locking: protected by this master key's key->sem. + * While ->mk_secret is present, one ref in ->mk_active_refs is held. + * + * Locking: protected by ->mk_sem. The manipulation of ->mk_active_refs + * associated with this field is protected by ->mk_sem as well. */ struct fscrypt_master_key_secret mk_secret; @@ -459,22 +496,12 @@ struct fscrypt_master_key { * * This is NULL for v1 policy keys; those can only be added by root. * - * Locking: in addition to this keyring's own semaphore, this is - * protected by this master key's key->sem, so we can do atomic - * search+insert. It can also be searched without taking any locks, but - * in that case the returned key may have already been removed. + * Locking: protected by ->mk_sem. (We don't just rely on the keyrings + * subsystem semaphore ->mk_users->sem, as we need support for atomic + * search+insert along with proper synchronization with ->mk_secret.) */ struct key *mk_users; - /* - * Length of ->mk_decrypted_inodes, plus one if mk_secret is present. - * Once this goes to 0, the master key is removed from ->s_master_keys. - * The 'struct fscrypt_master_key' will continue to live as long as the - * 'struct key' whose payload it is, but we won't let this reference - * count rise again. - */ - refcount_t mk_refcount; - /* * List of inodes that were unlocked using this key. This allows the * inodes to be evicted efficiently if the key is removed. @@ -500,10 +527,10 @@ static inline bool is_master_key_secret_present(const struct fscrypt_master_key_secret *secret) { /* - * The READ_ONCE() is only necessary for fscrypt_drop_inode() and - * fscrypt_key_describe(). These run in atomic context, so they can't - * take the key semaphore and thus 'secret' can change concurrently - * which would be a data race. But they only need to know whether the + * The READ_ONCE() is only necessary for fscrypt_drop_inode(). + * fscrypt_drop_inode() runs in atomic context, so it can't take the key + * semaphore and thus 'secret' can change concurrently which would be a + * data race. But fscrypt_drop_inode() only need to know whether the * secret *was* present at the time of check, so READ_ONCE() suffices. */ return READ_ONCE(secret->size) != 0; @@ -532,7 +559,11 @@ static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec) return 0; } -struct key * +void fscrypt_put_master_key(struct fscrypt_master_key *mk); + +void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk); + +struct fscrypt_master_key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec); diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index af74599ae1cf0..be5c650e49573 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -5,8 +5,6 @@ * Encryption hooks for higher-level filesystem operations. */ -#include - #include "fscrypt_private.h" /** @@ -142,7 +140,6 @@ int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags) { struct fscrypt_info *ci; - struct key *key; struct fscrypt_master_key *mk; int err; @@ -158,14 +155,13 @@ int fscrypt_prepare_setflags(struct inode *inode, ci = inode->i_crypt_info; if (ci->ci_policy.version != FSCRYPT_POLICY_V2) return -EINVAL; - key = ci->ci_master_key; - mk = key->payload.data[0]; - down_read(&key->sem); + mk = ci->ci_master_key; + down_read(&mk->mk_sem); if (is_master_key_secret_present(&mk->mk_secret)) err = fscrypt_derive_dirhash_key(ci, mk); else err = -ENOKEY; - up_read(&key->sem); + up_read(&mk->mk_sem); return err; } return 0; diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 0b3ffbb4faf4a..02f8bf8bd54da 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -18,6 +18,7 @@ * information about these ioctls. */ +#include #include #include #include @@ -25,6 +26,18 @@ #include "fscrypt_private.h" +/* The master encryption keys for a filesystem (->s_master_keys) */ +struct fscrypt_keyring { + /* + * Lock that protects ->key_hashtable. It does *not* protect the + * fscrypt_master_key structs themselves. + */ + spinlock_t lock; + + /* Hash table that maps fscrypt_key_specifier to fscrypt_master_key */ + struct hlist_head key_hashtable[128]; +}; + static void wipe_master_key_secret(struct fscrypt_master_key_secret *secret) { fscrypt_destroy_hkdf(&secret->hkdf); @@ -38,20 +51,70 @@ static void move_master_key_secret(struct fscrypt_master_key_secret *dst, memzero_explicit(src, sizeof(*src)); } -static void free_master_key(struct fscrypt_master_key *mk) +static void fscrypt_free_master_key(struct rcu_head *head) +{ + struct fscrypt_master_key *mk = + container_of(head, struct fscrypt_master_key, mk_rcu_head); + /* + * The master key secret and any embedded subkeys should have already + * been wiped when the last active reference to the fscrypt_master_key + * struct was dropped; doing it here would be unnecessarily late. + * Nevertheless, use kfree_sensitive() in case anything was missed. + */ + kfree_sensitive(mk); +} + +void fscrypt_put_master_key(struct fscrypt_master_key *mk) +{ + if (!refcount_dec_and_test(&mk->mk_struct_refs)) + return; + /* + * No structural references left, so free ->mk_users, and also free the + * fscrypt_master_key struct itself after an RCU grace period ensures + * that concurrent keyring lookups can no longer find it. + */ + WARN_ON(refcount_read(&mk->mk_active_refs) != 0); + key_put(mk->mk_users); + mk->mk_users = NULL; + call_rcu(&mk->mk_rcu_head, fscrypt_free_master_key); +} + +void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk) { + struct super_block *sb = mk->mk_sb; + struct fscrypt_keyring *keyring = sb->s_master_keys; size_t i; - wipe_master_key_secret(&mk->mk_secret); + if (!refcount_dec_and_test(&mk->mk_active_refs)) + return; + /* + * No active references left, so complete the full removal of this + * fscrypt_master_key struct by removing it from the keyring and + * destroying any subkeys embedded in it. + */ + + spin_lock(&keyring->lock); + hlist_del_rcu(&mk->mk_node); + spin_unlock(&keyring->lock); + + /* + * ->mk_active_refs == 0 implies that ->mk_secret is not present and + * that ->mk_decrypted_inodes is empty. + */ + WARN_ON(is_master_key_secret_present(&mk->mk_secret)); + WARN_ON(!list_empty(&mk->mk_decrypted_inodes)); for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { fscrypt_destroy_prepared_key(&mk->mk_direct_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_64_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_32_keys[i]); } + memzero_explicit(&mk->mk_ino_hash_key, + sizeof(mk->mk_ino_hash_key)); + mk->mk_ino_hash_key_initialized = false; - key_put(mk->mk_users); - kfree_sensitive(mk); + /* Drop the structural ref associated with the active refs. */ + fscrypt_put_master_key(mk); } static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec) @@ -61,44 +124,6 @@ static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec) return master_key_spec_len(spec) != 0; } -static int fscrypt_key_instantiate(struct key *key, - struct key_preparsed_payload *prep) -{ - key->payload.data[0] = (struct fscrypt_master_key *)prep->data; - return 0; -} - -static void fscrypt_key_destroy(struct key *key) -{ - free_master_key(key->payload.data[0]); -} - -static void fscrypt_key_describe(const struct key *key, struct seq_file *m) -{ - seq_puts(m, key->description); - - if (key_is_positive(key)) { - const struct fscrypt_master_key *mk = key->payload.data[0]; - - if (!is_master_key_secret_present(&mk->mk_secret)) - seq_puts(m, ": secret removed"); - } -} - -/* - * Type of key in ->s_master_keys. Each key of this type represents a master - * key which has been added to the filesystem. Its payload is a - * 'struct fscrypt_master_key'. The "." prefix in the key type name prevents - * users from adding keys of this type via the keyrings syscalls rather than via - * the intended method of FS_IOC_ADD_ENCRYPTION_KEY. - */ -static struct key_type key_type_fscrypt = { - .name = "._fscrypt", - .instantiate = fscrypt_key_instantiate, - .destroy = fscrypt_key_destroy, - .describe = fscrypt_key_describe, -}; - static int fscrypt_user_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { @@ -131,32 +156,6 @@ static struct key_type key_type_fscrypt_user = { .describe = fscrypt_user_key_describe, }; -/* Search ->s_master_keys or ->mk_users */ -static struct key *search_fscrypt_keyring(struct key *keyring, - struct key_type *type, - const char *description) -{ - /* - * We need to mark the keyring reference as "possessed" so that we - * acquire permission to search it, via the KEY_POS_SEARCH permission. - */ - key_ref_t keyref = make_key_ref(keyring, true /* possessed */); - - keyref = keyring_search(keyref, type, description, false); - if (IS_ERR(keyref)) { - if (PTR_ERR(keyref) == -EAGAIN || /* not found */ - PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ - keyref = ERR_PTR(-ENOKEY); - return ERR_CAST(keyref); - } - return key_ref_to_ptr(keyref); -} - -#define FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE \ - (CONST_STRLEN("fscrypt-") + sizeof_field(struct super_block, s_id)) - -#define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1) - #define FSCRYPT_MK_USERS_DESCRIPTION_SIZE \ (CONST_STRLEN("fscrypt-") + 2 * FSCRYPT_KEY_IDENTIFIER_SIZE + \ CONST_STRLEN("-users") + 1) @@ -164,21 +163,6 @@ static struct key *search_fscrypt_keyring(struct key *keyring, #define FSCRYPT_MK_USER_DESCRIPTION_SIZE \ (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + CONST_STRLEN(".uid.") + 10 + 1) -static void format_fs_keyring_description( - char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE], - const struct super_block *sb) -{ - sprintf(description, "fscrypt-%s", sb->s_id); -} - -static void format_mk_description( - char description[FSCRYPT_MK_DESCRIPTION_SIZE], - const struct fscrypt_key_specifier *mk_spec) -{ - sprintf(description, "%*phN", - master_key_spec_len(mk_spec), (u8 *)&mk_spec->u); -} - static void format_mk_users_keyring_description( char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE], const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) @@ -199,20 +183,15 @@ static void format_mk_user_description( /* Create ->s_master_keys if needed. Synchronized by fscrypt_add_key_mutex. */ static int allocate_filesystem_keyring(struct super_block *sb) { - char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE]; - struct key *keyring; + struct fscrypt_keyring *keyring; if (sb->s_master_keys) return 0; - format_fs_keyring_description(description, sb); - keyring = keyring_alloc(description, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, - current_cred(), KEY_POS_SEARCH | - KEY_USR_SEARCH | KEY_USR_READ | KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); - if (IS_ERR(keyring)) - return PTR_ERR(keyring); - + keyring = kzalloc(sizeof(*keyring), GFP_KERNEL); + if (!keyring) + return -ENOMEM; + spin_lock_init(&keyring->lock); /* * Pairs with the smp_load_acquire() in fscrypt_find_master_key(). * I.e., here we publish ->s_master_keys with a RELEASE barrier so that @@ -222,21 +201,80 @@ static int allocate_filesystem_keyring(struct super_block *sb) return 0; } -void fscrypt_sb_free(struct super_block *sb) +/* + * Release all encryption keys that have been added to the filesystem, along + * with the keyring that contains them. + * + * This is called at unmount time. The filesystem's underlying block device(s) + * are still available at this time; this is important because after user file + * accesses have been allowed, this function may need to evict keys from the + * keyslots of an inline crypto engine, which requires the block device(s). + * + * This is also called when the super_block is being freed. This is needed to + * avoid a memory leak if mounting fails after the "test_dummy_encryption" + * option was processed, as in that case the unmount-time call isn't made. + */ +void fscrypt_destroy_keyring(struct super_block *sb) { - key_put(sb->s_master_keys); + struct fscrypt_keyring *keyring = sb->s_master_keys; + size_t i; + + if (!keyring) + return; + + for (i = 0; i < ARRAY_SIZE(keyring->key_hashtable); i++) { + struct hlist_head *bucket = &keyring->key_hashtable[i]; + struct fscrypt_master_key *mk; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(mk, tmp, bucket, mk_node) { + /* + * Since all inodes were already evicted, every key + * remaining in the keyring should have an empty inode + * list, and should only still be in the keyring due to + * the single active ref associated with ->mk_secret. + * There should be no structural refs beyond the one + * associated with the active ref. + */ + WARN_ON(refcount_read(&mk->mk_active_refs) != 1); + WARN_ON(refcount_read(&mk->mk_struct_refs) != 1); + WARN_ON(!is_master_key_secret_present(&mk->mk_secret)); + wipe_master_key_secret(&mk->mk_secret); + fscrypt_put_master_key_activeref(mk); + } + } + kfree_sensitive(keyring); sb->s_master_keys = NULL; } +static struct hlist_head * +fscrypt_mk_hash_bucket(struct fscrypt_keyring *keyring, + const struct fscrypt_key_specifier *mk_spec) +{ + /* + * Since key specifiers should be "random" values, it is sufficient to + * use a trivial hash function that just takes the first several bits of + * the key specifier. + */ + unsigned long i = get_unaligned((unsigned long *)&mk_spec->u); + + return &keyring->key_hashtable[i % ARRAY_SIZE(keyring->key_hashtable)]; +} + /* - * Find the specified master key in ->s_master_keys. - * Returns ERR_PTR(-ENOKEY) if not found. + * Find the specified master key struct in ->s_master_keys and take a structural + * ref to it. The structural ref guarantees that the key struct continues to + * exist, but it does *not* guarantee that ->s_master_keys continues to contain + * the key struct. The structural ref needs to be dropped by + * fscrypt_put_master_key(). Returns NULL if the key struct is not found. */ -struct key *fscrypt_find_master_key(struct super_block *sb, - const struct fscrypt_key_specifier *mk_spec) +struct fscrypt_master_key * +fscrypt_find_master_key(struct super_block *sb, + const struct fscrypt_key_specifier *mk_spec) { - struct key *keyring; - char description[FSCRYPT_MK_DESCRIPTION_SIZE]; + struct fscrypt_keyring *keyring; + struct hlist_head *bucket; + struct fscrypt_master_key *mk; /* * Pairs with the smp_store_release() in allocate_filesystem_keyring(). @@ -246,10 +284,38 @@ struct key *fscrypt_find_master_key(struct super_block *sb, */ keyring = smp_load_acquire(&sb->s_master_keys); if (keyring == NULL) - return ERR_PTR(-ENOKEY); /* No keyring yet, so no keys yet. */ - - format_mk_description(description, mk_spec); - return search_fscrypt_keyring(keyring, &key_type_fscrypt, description); + return NULL; /* No keyring yet, so no keys yet. */ + + bucket = fscrypt_mk_hash_bucket(keyring, mk_spec); + rcu_read_lock(); + switch (mk_spec->type) { + case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR: + hlist_for_each_entry_rcu(mk, bucket, mk_node) { + if (mk->mk_spec.type == + FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && + memcmp(mk->mk_spec.u.descriptor, + mk_spec->u.descriptor, + FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 && + refcount_inc_not_zero(&mk->mk_struct_refs)) + goto out; + } + break; + case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER: + hlist_for_each_entry_rcu(mk, bucket, mk_node) { + if (mk->mk_spec.type == + FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER && + memcmp(mk->mk_spec.u.identifier, + mk_spec->u.identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE) == 0 && + refcount_inc_not_zero(&mk->mk_struct_refs)) + goto out; + } + break; + } + mk = NULL; +out: + rcu_read_unlock(); + return mk; } static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk) @@ -277,17 +343,30 @@ static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk) static struct key *find_master_key_user(struct fscrypt_master_key *mk) { char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE]; + key_ref_t keyref; format_mk_user_description(description, mk->mk_spec.u.identifier); - return search_fscrypt_keyring(mk->mk_users, &key_type_fscrypt_user, - description); + + /* + * We need to mark the keyring reference as "possessed" so that we + * acquire permission to search it, via the KEY_POS_SEARCH permission. + */ + keyref = keyring_search(make_key_ref(mk->mk_users, true /*possessed*/), + &key_type_fscrypt_user, description, false); + if (IS_ERR(keyref)) { + if (PTR_ERR(keyref) == -EAGAIN || /* not found */ + PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ + keyref = ERR_PTR(-ENOKEY); + return ERR_CAST(keyref); + } + return key_ref_to_ptr(keyref); } /* * Give the current user a "key" in ->mk_users. This charges the user's quota * and marks the master key as added by the current user, so that it cannot be - * removed by another user with the key. Either the master key's key->sem must - * be held for write, or the master key must be still undergoing initialization. + * removed by another user with the key. Either ->mk_sem must be held for + * write, or the master key must be still undergoing initialization. */ static int add_master_key_user(struct fscrypt_master_key *mk) { @@ -309,7 +388,7 @@ static int add_master_key_user(struct fscrypt_master_key *mk) /* * Remove the current user's "key" from ->mk_users. - * The master key's key->sem must be held for write. + * ->mk_sem must be held for write. * * Returns 0 if removed, -ENOKEY if not found, or another -errno code. */ @@ -327,63 +406,49 @@ static int remove_master_key_user(struct fscrypt_master_key *mk) } /* - * Allocate a new fscrypt_master_key which contains the given secret, set it as - * the payload of a new 'struct key' of type fscrypt, and link the 'struct key' - * into the given keyring. Synchronized by fscrypt_add_key_mutex. + * Allocate a new fscrypt_master_key, transfer the given secret over to it, and + * insert it into sb->s_master_keys. */ -static int add_new_master_key(struct fscrypt_master_key_secret *secret, - const struct fscrypt_key_specifier *mk_spec, - struct key *keyring) +static int add_new_master_key(struct super_block *sb, + struct fscrypt_master_key_secret *secret, + const struct fscrypt_key_specifier *mk_spec) { + struct fscrypt_keyring *keyring = sb->s_master_keys; struct fscrypt_master_key *mk; - char description[FSCRYPT_MK_DESCRIPTION_SIZE]; - struct key *key; int err; mk = kzalloc(sizeof(*mk), GFP_KERNEL); if (!mk) return -ENOMEM; + mk->mk_sb = sb; + init_rwsem(&mk->mk_sem); + refcount_set(&mk->mk_struct_refs, 1); mk->mk_spec = *mk_spec; - move_master_key_secret(&mk->mk_secret, secret); - - refcount_set(&mk->mk_refcount, 1); /* secret is present */ INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock); if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = allocate_master_key_users_keyring(mk); if (err) - goto out_free_mk; + goto out_put; err = add_master_key_user(mk); if (err) - goto out_free_mk; + goto out_put; } - /* - * Note that we don't charge this key to anyone's quota, since when - * ->mk_users is in use those keys are charged instead, and otherwise - * (when ->mk_users isn't in use) only root can add these keys. - */ - format_mk_description(description, mk_spec); - key = key_alloc(&key_type_fscrypt, description, - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), - KEY_POS_SEARCH | KEY_USR_SEARCH | KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA, NULL); - if (IS_ERR(key)) { - err = PTR_ERR(key); - goto out_free_mk; - } - err = key_instantiate_and_link(key, mk, sizeof(*mk), keyring, NULL); - key_put(key); - if (err) - goto out_free_mk; + move_master_key_secret(&mk->mk_secret, secret); + refcount_set(&mk->mk_active_refs, 1); /* ->mk_secret is present */ + spin_lock(&keyring->lock); + hlist_add_head_rcu(&mk->mk_node, + fscrypt_mk_hash_bucket(keyring, mk_spec)); + spin_unlock(&keyring->lock); return 0; -out_free_mk: - free_master_key(mk); +out_put: + fscrypt_put_master_key(mk); return err; } @@ -392,42 +457,34 @@ out_free_mk: static int add_existing_master_key(struct fscrypt_master_key *mk, struct fscrypt_master_key_secret *secret) { - struct key *mk_user; - bool rekey; int err; /* * If the current user is already in ->mk_users, then there's nothing to - * do. (Not applicable for v1 policy keys, which have NULL ->mk_users.) + * do. Otherwise, we need to add the user to ->mk_users. (Neither is + * applicable for v1 policy keys, which have NULL ->mk_users.) */ if (mk->mk_users) { - mk_user = find_master_key_user(mk); + struct key *mk_user = find_master_key_user(mk); + if (mk_user != ERR_PTR(-ENOKEY)) { if (IS_ERR(mk_user)) return PTR_ERR(mk_user); key_put(mk_user); return 0; } - } - - /* If we'll be re-adding ->mk_secret, try to take the reference. */ - rekey = !is_master_key_secret_present(&mk->mk_secret); - if (rekey && !refcount_inc_not_zero(&mk->mk_refcount)) - return KEY_DEAD; - - /* Add the current user to ->mk_users, if applicable. */ - if (mk->mk_users) { err = add_master_key_user(mk); - if (err) { - if (rekey && refcount_dec_and_test(&mk->mk_refcount)) - return KEY_DEAD; + if (err) return err; - } } /* Re-add the secret if needed. */ - if (rekey) + if (!is_master_key_secret_present(&mk->mk_secret)) { + if (!refcount_inc_not_zero(&mk->mk_active_refs)) + return KEY_DEAD; move_master_key_secret(&mk->mk_secret, secret); + } + return 0; } @@ -436,38 +493,36 @@ static int do_add_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec) { static DEFINE_MUTEX(fscrypt_add_key_mutex); - struct key *key; + struct fscrypt_master_key *mk; int err; mutex_lock(&fscrypt_add_key_mutex); /* serialize find + link */ -retry: - key = fscrypt_find_master_key(sb, mk_spec); - if (IS_ERR(key)) { - err = PTR_ERR(key); - if (err != -ENOKEY) - goto out_unlock; + + mk = fscrypt_find_master_key(sb, mk_spec); + if (!mk) { /* Didn't find the key in ->s_master_keys. Add it. */ err = allocate_filesystem_keyring(sb); - if (err) - goto out_unlock; - err = add_new_master_key(secret, mk_spec, sb->s_master_keys); + if (!err) + err = add_new_master_key(sb, secret, mk_spec); } else { /* * Found the key in ->s_master_keys. Re-add the secret if * needed, and add the user to ->mk_users if needed. */ - down_write(&key->sem); - err = add_existing_master_key(key->payload.data[0], secret); - up_write(&key->sem); + down_write(&mk->mk_sem); + err = add_existing_master_key(mk, secret); + up_write(&mk->mk_sem); if (err == KEY_DEAD) { - /* Key being removed or needs to be removed */ - key_invalidate(key); - key_put(key); - goto retry; + /* + * We found a key struct, but it's already been fully + * removed. Ignore the old struct and add a new one. + * fscrypt_add_key_mutex means we don't need to worry + * about concurrent adds. + */ + err = add_new_master_key(sb, secret, mk_spec); } - key_put(key); + fscrypt_put_master_key(mk); } -out_unlock: mutex_unlock(&fscrypt_add_key_mutex); return err; } @@ -731,19 +786,19 @@ int fscrypt_verify_key_added(struct super_block *sb, const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) { struct fscrypt_key_specifier mk_spec; - struct key *key, *mk_user; struct fscrypt_master_key *mk; + struct key *mk_user; int err; mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; memcpy(mk_spec.u.identifier, identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); - key = fscrypt_find_master_key(sb, &mk_spec); - if (IS_ERR(key)) { - err = PTR_ERR(key); + mk = fscrypt_find_master_key(sb, &mk_spec); + if (!mk) { + err = -ENOKEY; goto out; } - mk = key->payload.data[0]; + down_read(&mk->mk_sem); mk_user = find_master_key_user(mk); if (IS_ERR(mk_user)) { err = PTR_ERR(mk_user); @@ -751,7 +806,8 @@ int fscrypt_verify_key_added(struct super_block *sb, key_put(mk_user); err = 0; } - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); out: if (err == -ENOKEY && capable(CAP_FOWNER)) err = 0; @@ -913,11 +969,10 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_remove_key_arg __user *uarg = _uarg; struct fscrypt_remove_key_arg arg; - struct key *key; struct fscrypt_master_key *mk; u32 status_flags = 0; int err; - bool dead; + bool inodes_remain; if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; @@ -937,12 +992,10 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) return -EACCES; /* Find the key being removed. */ - key = fscrypt_find_master_key(sb, &arg.key_spec); - if (IS_ERR(key)) - return PTR_ERR(key); - mk = key->payload.data[0]; - - down_write(&key->sem); + mk = fscrypt_find_master_key(sb, &arg.key_spec); + if (!mk) + return -ENOKEY; + down_write(&mk->mk_sem); /* If relevant, remove current user's (or all users) claim to the key */ if (mk->mk_users && mk->mk_users->keys.nr_leaves_on_tree != 0) { @@ -951,7 +1004,7 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) else err = remove_master_key_user(mk); if (err) { - up_write(&key->sem); + up_write(&mk->mk_sem); goto out_put_key; } if (mk->mk_users->keys.nr_leaves_on_tree != 0) { @@ -963,26 +1016,22 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) status_flags |= FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS; err = 0; - up_write(&key->sem); + up_write(&mk->mk_sem); goto out_put_key; } } /* No user claims remaining. Go ahead and wipe the secret. */ - dead = false; + err = -ENOKEY; if (is_master_key_secret_present(&mk->mk_secret)) { wipe_master_key_secret(&mk->mk_secret); - dead = refcount_dec_and_test(&mk->mk_refcount); - } - up_write(&key->sem); - if (dead) { - /* - * No inodes reference the key, and we wiped the secret, so the - * key object is free to be removed from the keyring. - */ - key_invalidate(key); + fscrypt_put_master_key_activeref(mk); err = 0; - } else { + } + inodes_remain = refcount_read(&mk->mk_active_refs) > 0; + up_write(&mk->mk_sem); + + if (inodes_remain) { /* Some inodes still reference this key; try to evict them. */ err = try_to_lock_encrypted_files(sb, mk); if (err == -EBUSY) { @@ -998,7 +1047,7 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) * has been fully removed including all files locked. */ out_put_key: - key_put(key); + fscrypt_put_master_key(mk); if (err == 0) err = put_user(status_flags, &uarg->removal_status_flags); return err; @@ -1045,7 +1094,6 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) { struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_get_key_status_arg arg; - struct key *key; struct fscrypt_master_key *mk; int err; @@ -1062,19 +1110,18 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) arg.user_count = 0; memset(arg.__out_reserved, 0, sizeof(arg.__out_reserved)); - key = fscrypt_find_master_key(sb, &arg.key_spec); - if (IS_ERR(key)) { - if (key != ERR_PTR(-ENOKEY)) - return PTR_ERR(key); + mk = fscrypt_find_master_key(sb, &arg.key_spec); + if (!mk) { arg.status = FSCRYPT_KEY_STATUS_ABSENT; err = 0; goto out; } - mk = key->payload.data[0]; - down_read(&key->sem); + down_read(&mk->mk_sem); if (!is_master_key_secret_present(&mk->mk_secret)) { - arg.status = FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED; + arg.status = refcount_read(&mk->mk_active_refs) > 0 ? + FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED : + FSCRYPT_KEY_STATUS_ABSENT /* raced with full removal */; err = 0; goto out_release_key; } @@ -1096,8 +1143,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) } err = 0; out_release_key: - up_read(&key->sem); - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); out: if (!err && copy_to_user(uarg, &arg, sizeof(arg))) err = -EFAULT; @@ -1109,13 +1156,9 @@ int __init fscrypt_init_keyring(void) { int err; - err = register_key_type(&key_type_fscrypt); - if (err) - return err; - err = register_key_type(&key_type_fscrypt_user); if (err) - goto err_unregister_fscrypt; + return err; err = register_key_type(&key_type_fscrypt_provisioning); if (err) @@ -1125,7 +1168,5 @@ int __init fscrypt_init_keyring(void) err_unregister_fscrypt_user: unregister_key_type(&key_type_fscrypt_user); -err_unregister_fscrypt: - unregister_key_type(&key_type_fscrypt); return err; } diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 89cd533a88bff..c3fbd594cc79e 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -9,7 +9,6 @@ */ #include -#include #include #include "fscrypt_private.h" @@ -151,6 +150,7 @@ void fscrypt_destroy_prepared_key(struct fscrypt_prepared_key *prep_key) { crypto_free_skcipher(prep_key->tfm); fscrypt_destroy_inline_crypt_key(prep_key); + memzero_explicit(prep_key, sizeof(*prep_key)); } /* Given a per-file encryption key, set up the file's crypto transform object */ @@ -404,20 +404,18 @@ static bool fscrypt_valid_master_key_size(const struct fscrypt_master_key *mk, /* * Find the master key, then set up the inode's actual encryption key. * - * If the master key is found in the filesystem-level keyring, then the - * corresponding 'struct key' is returned in *master_key_ret with its semaphore - * read-locked. This is needed to ensure that only one task links the - * fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race to create - * an fscrypt_info for the same inode), and to synchronize the master key being - * removed with a new inode starting to use it. + * If the master key is found in the filesystem-level keyring, then it is + * returned in *mk_ret with its semaphore read-locked. This is needed to ensure + * that only one task links the fscrypt_info into ->mk_decrypted_inodes (as + * multiple tasks may race to create an fscrypt_info for the same inode), and to + * synchronize the master key being removed with a new inode starting to use it. */ static int setup_file_encryption_key(struct fscrypt_info *ci, bool need_dirhash_key, - struct key **master_key_ret) + struct fscrypt_master_key **mk_ret) { - struct key *key; - struct fscrypt_master_key *mk = NULL; struct fscrypt_key_specifier mk_spec; + struct fscrypt_master_key *mk; int err; err = fscrypt_select_encryption_impl(ci); @@ -442,11 +440,10 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, return -EINVAL; } - key = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); - if (IS_ERR(key)) { - if (key != ERR_PTR(-ENOKEY) || - ci->ci_policy.version != FSCRYPT_POLICY_V1) - return PTR_ERR(key); + mk = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); + if (!mk) { + if (ci->ci_policy.version != FSCRYPT_POLICY_V1) + return -ENOKEY; /* * As a legacy fallback for v1 policies, search for the key in @@ -456,9 +453,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, */ return fscrypt_setup_v1_file_key_via_subscribed_keyrings(ci); } - - mk = key->payload.data[0]; - down_read(&key->sem); + down_read(&mk->mk_sem); /* Has the secret been removed (via FS_IOC_REMOVE_ENCRYPTION_KEY)? */ if (!is_master_key_secret_present(&mk->mk_secret)) { @@ -486,18 +481,18 @@ static int setup_file_encryption_key(struct fscrypt_info *ci, if (err) goto out_release_key; - *master_key_ret = key; + *mk_ret = mk; return 0; out_release_key: - up_read(&key->sem); - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); return err; } static void put_crypt_info(struct fscrypt_info *ci) { - struct key *key; + struct fscrypt_master_key *mk; if (!ci) return; @@ -507,24 +502,18 @@ static void put_crypt_info(struct fscrypt_info *ci) else if (ci->ci_owns_key) fscrypt_destroy_prepared_key(&ci->ci_enc_key); - key = ci->ci_master_key; - if (key) { - struct fscrypt_master_key *mk = key->payload.data[0]; - + mk = ci->ci_master_key; + if (mk) { /* * Remove this inode from the list of inodes that were unlocked - * with the master key. - * - * In addition, if we're removing the last inode from a key that - * already had its secret removed, invalidate the key so that it - * gets removed from ->s_master_keys. + * with the master key. In addition, if we're removing the last + * inode from a master key struct that already had its secret + * removed, then complete the full removal of the struct. */ spin_lock(&mk->mk_decrypted_inodes_lock); list_del(&ci->ci_master_key_link); spin_unlock(&mk->mk_decrypted_inodes_lock); - if (refcount_dec_and_test(&mk->mk_refcount)) - key_invalidate(key); - key_put(key); + fscrypt_put_master_key_activeref(mk); } memzero_explicit(ci, sizeof(*ci)); kmem_cache_free(fscrypt_info_cachep, ci); @@ -538,7 +527,7 @@ fscrypt_setup_encryption_info(struct inode *inode, { struct fscrypt_info *crypt_info; struct fscrypt_mode *mode; - struct key *master_key = NULL; + struct fscrypt_master_key *mk = NULL; int res; res = fscrypt_initialize(inode->i_sb->s_cop->flags); @@ -561,8 +550,7 @@ fscrypt_setup_encryption_info(struct inode *inode, WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE); crypt_info->ci_mode = mode; - res = setup_file_encryption_key(crypt_info, need_dirhash_key, - &master_key); + res = setup_file_encryption_key(crypt_info, need_dirhash_key, &mk); if (res) goto out; @@ -577,12 +565,9 @@ fscrypt_setup_encryption_info(struct inode *inode, * We won the race and set ->i_crypt_info to our crypt_info. * Now link it into the master key's inode list. */ - if (master_key) { - struct fscrypt_master_key *mk = - master_key->payload.data[0]; - - refcount_inc(&mk->mk_refcount); - crypt_info->ci_master_key = key_get(master_key); + if (mk) { + crypt_info->ci_master_key = mk; + refcount_inc(&mk->mk_active_refs); spin_lock(&mk->mk_decrypted_inodes_lock); list_add(&crypt_info->ci_master_key_link, &mk->mk_decrypted_inodes); @@ -592,9 +577,9 @@ fscrypt_setup_encryption_info(struct inode *inode, } res = 0; out: - if (master_key) { - up_read(&master_key->sem); - key_put(master_key); + if (mk) { + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); } put_crypt_info(crypt_info); return res; @@ -759,7 +744,6 @@ EXPORT_SYMBOL(fscrypt_free_inode); int fscrypt_drop_inode(struct inode *inode) { const struct fscrypt_info *ci = fscrypt_get_info(inode); - const struct fscrypt_master_key *mk; /* * If ci is NULL, then the inode doesn't have an encryption key set up @@ -769,7 +753,6 @@ int fscrypt_drop_inode(struct inode *inode) */ if (!ci || !ci->ci_master_key) return 0; - mk = ci->ci_master_key->payload.data[0]; /* * With proper, non-racy use of FS_IOC_REMOVE_ENCRYPTION_KEY, all inodes @@ -788,6 +771,6 @@ int fscrypt_drop_inode(struct inode *inode) * then the thread removing the key will either evict the inode itself * or will correctly detect that it wasn't evicted due to the race. */ - return !is_master_key_secret_present(&mk->mk_secret); + return !is_master_key_secret_present(&ci->ci_master_key->mk_secret); } EXPORT_SYMBOL_GPL(fscrypt_drop_inode); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index ed3d623724cdd..cad34dbe8e298 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -692,12 +692,8 @@ int fscrypt_set_context(struct inode *inode, void *fs_data) * delayed key setup that requires the inode number. */ if (ci->ci_policy.version == FSCRYPT_POLICY_V2 && - (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) { - const struct fscrypt_master_key *mk = - ci->ci_master_key->payload.data[0]; - - fscrypt_hash_inode_number(ci, mk); - } + (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) + fscrypt_hash_inode_number(ci, ci->ci_master_key); return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, fs_data); } diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index af5a75a89e6e1..b0ea646454ac8 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -425,7 +425,8 @@ int ext4_ext_migrate(struct inode *inode) * already is extent-based, error out. */ if (!ext4_has_feature_extents(inode->i_sb) || - (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || + ext4_has_inline_data(inode)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 971a08d947f42..b8cf3e986b000 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2259,8 +2259,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, memset(de, 0, len); /* wipe old data */ de = (struct ext4_dir_entry_2 *) data2; top = data2 + len; - while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) + while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { + if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, + (data2 + (blocksize - csum_size) - + (char *) de))) { + brelse(bh2); + brelse(bh); + return -EFSCORRUPTED; + } de = de2; + } de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - (char *) de, blocksize); diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index eacbd489e3bf1..840639e7a7caa 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -364,13 +364,14 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index fe5acdccaae19..a28968bb56e62 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -261,13 +261,14 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 71e9e301e569d..307e7dae3ab6b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2975,6 +2975,10 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, goto out; } + err = file_modified(file); + if (err) + goto out; + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7c9eb679dbdbf..6a3ba306c3216 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -228,8 +228,7 @@ again: * */ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, - fmode_t type, - const nfs4_stateid *stateid, + fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) { struct nfs_delegation *delegation; @@ -239,25 +238,24 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation != NULL) { spin_lock(&delegation->lock); - if (nfs4_is_valid_delegation(delegation, 0)) { - nfs4_stateid_copy(&delegation->stateid, stateid); - delegation->type = type; - delegation->pagemod_limit = pagemod_limit; - oldcred = delegation->cred; - delegation->cred = get_cred(cred); - clear_bit(NFS_DELEGATION_NEED_RECLAIM, - &delegation->flags); - spin_unlock(&delegation->lock); - rcu_read_unlock(); - put_cred(oldcred); - trace_nfs4_reclaim_delegation(inode, type); - return; - } - /* We appear to have raced with a delegation return. */ + nfs4_stateid_copy(&delegation->stateid, stateid); + delegation->type = type; + delegation->pagemod_limit = pagemod_limit; + oldcred = delegation->cred; + delegation->cred = get_cred(cred); + clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); + if (test_and_clear_bit(NFS_DELEGATION_REVOKED, + &delegation->flags)) + atomic_long_inc(&nfs_active_delegations); spin_unlock(&delegation->lock); + rcu_read_unlock(); + put_cred(oldcred); + trace_nfs4_reclaim_delegation(inode, type); + } else { + rcu_read_unlock(); + nfs_inode_set_delegation(inode, cred, type, stateid, + pagemod_limit); } - rcu_read_unlock(); - nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit); } static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 93f4d8257525b..da94bf2afd070 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1077,6 +1077,9 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); if (status == 0) { + /* a zero-length count means clone to EOF in src */ + if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE) + count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset; nfs42_copy_dest_done(dst_inode, dst_offset, count); status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ed06b68b2b4e9..1bf7a72ebda6e 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -346,6 +346,7 @@ int nfs40_init_client(struct nfs_client *clp) ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE, "NFSv4.0 transport Slot table"); if (ret) { + nfs4_shutdown_slot_table(tbl); kfree(tbl); return ret; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 32ee79a992461..ecac56be6cb72 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1778,6 +1778,7 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) { + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); /* Mark all delegations for reclaim */ nfs_delegation_mark_reclaim(clp); nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot); @@ -2651,6 +2652,7 @@ static void nfs4_state_manager(struct nfs_client *clp) if (status < 0) goto out_error; nfs4_state_end_reclaim_reboot(clp); + continue; } /* Detect expired delegations... */ diff --git a/fs/super.c b/fs/super.c index 87379bb1f7a30..7fa3ee79ec898 100644 --- a/fs/super.c +++ b/fs/super.c @@ -293,7 +293,7 @@ static void __put_super(struct super_block *s) WARN_ON(s->s_inode_lru.node); WARN_ON(!list_empty(&s->s_mounts)); security_sb_free(s); - fscrypt_sb_free(s); + fscrypt_destroy_keyring(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); call_rcu(&s->rcu, destroy_super_rcu); @@ -454,6 +454,7 @@ void generic_shutdown_super(struct super_block *sb) evict_inodes(sb); /* only nonzero refcount inodes can have marks */ fsnotify_sb_delete(sb); + fscrypt_destroy_keyring(sb); security_sb_delete(sb); if (sb->s_dio_done_wq) { diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 34fb3431a8f36..292a5c40bd0c6 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -71,7 +71,7 @@ int ghes_register_vendor_record_notifier(struct notifier_block *nb); void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); #endif -int ghes_estatus_pool_init(int num_ghes); +int ghes_estatus_pool_init(unsigned int num_ghes); /* From drivers/edac/ghes_edac.c */ diff --git a/include/linux/efi.h b/include/linux/efi.h index d34e8a7ed4d5c..4cd4ed34d3cb8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1165,7 +1165,7 @@ efi_status_t efi_random_get_seed(void); arch_efi_call_virt_teardown(); \ }) -#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE struct linux_efi_random_seed { u32 size; diff --git a/include/linux/fs.h b/include/linux/fs.h index fd4c450dc6128..806ac72c72202 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1487,7 +1487,7 @@ struct super_block { const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; - struct key *s_master_keys; /* master crypto keys in use */ + struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e912ed9141d9d..3c7ea2cf85a58 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -294,7 +294,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -void fscrypt_sb_free(struct super_block *sb); +void fscrypt_destroy_keyring(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); @@ -482,7 +482,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) } /* keyring.c */ -static inline void fscrypt_sb_free(struct super_block *sb) +static inline void fscrypt_destroy_keyring(struct super_block *sb) { } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 22c1d935e22dd..af8e7045017fd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -198,8 +198,8 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, struct page *follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift); -struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags); +struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, + int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags); struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, @@ -286,8 +286,8 @@ static inline struct page *follow_huge_pd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_huge_pmd(struct mm_struct *mm, - unsigned long address, pmd_t *pmd, int flags) +static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, + unsigned long address, int flags) { return NULL; } diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 95ec18c2f49ce..9a476f902c425 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -995,6 +995,8 @@ v4l2_subdev_get_try_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_fmt; @@ -1013,6 +1015,8 @@ v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_crop; @@ -1031,6 +1035,8 @@ v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { + if (WARN_ON(!state)) + return NULL; if (WARN_ON(pad >= sd->entity.num_pads)) pad = 0; return &state->pads[pad].try_compose; diff --git a/include/net/protocol.h b/include/net/protocol.h index f51c06ae365f5..6aef8cb11cc8c 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -35,8 +35,6 @@ /* This is used to register protocols. */ struct net_protocol { - int (*early_demux)(struct sk_buff *skb); - int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); /* This returns an error if we weren't able to handle the error. */ @@ -52,8 +50,6 @@ struct net_protocol { #if IS_ENABLED(CONFIG_IPV6) struct inet6_protocol { - void (*early_demux)(struct sk_buff *skb); - void (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); /* This returns an error if we weren't able to handle the error. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index d2de3b7788a97..81ef95dc27ba5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -921,7 +921,7 @@ extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb)); +void tcp_v6_early_demux(struct sk_buff *skb); #endif diff --git a/include/net/udp.h b/include/net/udp.h index 438b1b01a56ce..930666c0b6e50 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -173,7 +173,7 @@ INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); +void udp_v6_early_demux(struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9df585b9467e4..55fffb7e6f1cc 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2208,8 +2208,11 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); - if (ret) + if (ret) { p->flags |= KPROBE_FLAG_DISABLED; + if (p != kp) + kp->flags |= KPROBE_FLAG_DISABLED; + } } out: mutex_unlock(&kprobe_mutex); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 37db5bfa8edc1..c197f39fdb78d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2948,18 +2948,8 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) command |= FTRACE_UPDATE_TRACE_FUNC; } - if (!command || !ftrace_enabled) { - /* - * If these are dynamic or per_cpu ops, they still - * need their data freed. Since, function tracing is - * not currently active, we can just free them - * without synchronizing all CPUs. - */ - if (ops->flags & FTRACE_OPS_FL_DYNAMIC) - goto free_ops; - - return 0; - } + if (!command || !ftrace_enabled) + goto out; /* * If the ops uses a trampoline, then it needs to be @@ -2996,6 +2986,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) removed_ops = NULL; ops->flags &= ~FTRACE_OPS_FL_REMOVING; +out: /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. @@ -3023,7 +3014,6 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) if (IS_ENABLED(CONFIG_PREEMPTION)) synchronize_rcu_tasks(); - free_ops: ftrace_trampoline_free(ops); } diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index 80e04a1e19772..d81f7c51025c7 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -100,20 +100,20 @@ static int __init test_gen_kprobe_cmd(void) KPROBE_GEN_TEST_FUNC, KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1); if (ret) - goto free; + goto out; /* Use kprobe_event_add_fields to add the rest of the fields */ ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kprobe_test event file. We need to prevent @@ -136,13 +136,11 @@ static int __init test_gen_kprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kprobe_test"); - free: - kfree(buf); - goto out; } @@ -170,14 +168,14 @@ static int __init test_gen_kretprobe_cmd(void) KPROBE_GEN_TEST_FUNC, "$retval"); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kretprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kretprobe_test event file. We need to @@ -201,13 +199,11 @@ static int __init test_gen_kretprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kretprobe_test"); - free: - kfree(buf); - goto out; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 90fc95e852322..5e8ae0b3ef712 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -901,6 +901,9 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *rbwork; + if (!buffer) + return; + if (cpu == RING_BUFFER_ALL_CPUS) { /* Wake up individual ones too. One level recursion */ @@ -909,7 +912,15 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &buffer->irq_work; } else { + if (WARN_ON_ONCE(!buffer->buffers)) + return; + if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) + return; + cpu_buffer = buffer->buffers[cpu]; + /* The CPU buffer may not have been initialized yet */ + if (!cpu_buffer) + return; rbwork = &cpu_buffer->irq_work; } diff --git a/mm/gup.c b/mm/gup.c index 1a23cd0b4fba1..69e45cbe58f8c 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -509,6 +509,18 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); + + /* + * Considering PTE level hugetlb, like continuous-PTE hugetlb on + * ARM64 architecture. + */ + if (is_vm_hugetlb_page(vma)) { + page = follow_huge_pmd_pte(vma, address, flags); + if (page) + return page; + return no_page_table(vma, flags); + } + retry: if (unlikely(pmd_bad(*pmd))) return no_page_table(vma, flags); @@ -652,7 +664,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, if (pmd_none(pmdval)) return no_page_table(vma, flags); if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) { - page = follow_huge_pmd(mm, address, pmd, flags); + page = follow_huge_pmd_pte(vma, address, flags); if (page) return page; return no_page_table(vma, flags); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f5f8929fad515..dbb63ec3b5fab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6182,12 +6182,13 @@ follow_huge_pd(struct vm_area_struct *vma, } struct page * __weak -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int flags) +follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags) { + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; struct page *page = NULL; spinlock_t *ptl; - pte_t pte; + pte_t *ptep, pte; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == @@ -6195,17 +6196,15 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, return NULL; retry: - ptl = pmd_lockptr(mm, pmd); - spin_lock(ptl); - /* - * make sure that the address range covered by this pmd is not - * unmapped from other threads. - */ - if (!pmd_huge(*pmd)) - goto out; - pte = huge_ptep_get((pte_t *)pmd); + ptep = huge_pte_offset(mm, address, huge_page_size(h)); + if (!ptep) + return NULL; + + ptl = huge_pte_lock(h, mm, ptep); + pte = huge_ptep_get(ptep); if (pte_present(pte)) { - page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT); + page = pte_page(pte) + + ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); /* * try_grab_page() should always succeed here, because: a) we * hold the pmd (ptl) lock, and b) we've just checked that the @@ -6221,7 +6220,7 @@ retry: } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); - __migration_entry_wait(mm, (pte_t *)pmd, ptl); + __migration_entry_wait(mm, ptep, ptl); goto retry; } /* diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 8f1a95b9d3207..16f954a4802c3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3764,7 +3764,8 @@ done: l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc, endptr - ptr); - if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { + if (remote_efs && + test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->remote_id = efs.id; chan->remote_stype = efs.stype; chan->remote_msdu = le16_to_cpu(efs.msdu); @@ -5813,6 +5814,19 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm), scid, mtu, mps); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + chan = NULL; + goto response; + } + /* Check if we have socket listening on psm */ pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, &conn->hcon->dst, LE_LINK); @@ -6001,6 +6015,18 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, psm = req->psm; + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + goto response; + } + BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps); memset(&pdu, 0, sizeof(pdu)); @@ -6885,6 +6911,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb, u8 event) { + struct l2cap_ctrl local_control; int err = 0; bool skb_in_use = false; @@ -6909,15 +6936,32 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, chan->buffer_seq = chan->expected_tx_seq; skb_in_use = true; + /* l2cap_reassemble_sdu may free skb, hence invalidate + * control, so make a copy in advance to use it after + * l2cap_reassemble_sdu returns and to avoid the race + * condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but + * it was freed by skb_free_datagram. + */ + local_control = *control; err = l2cap_reassemble_sdu(chan, skb, control); if (err) break; - if (control->final) { + if (local_control.final) { if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) { - control->final = 0; - l2cap_retransmit_all(chan, control); + local_control.final = 0; + l2cap_retransmit_all(chan, &local_control); l2cap_ertm_send(chan); } } @@ -7297,11 +7341,27 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb) { + /* l2cap_reassemble_sdu may free skb, hence invalidate control, so store + * the txseq field in advance to use it after l2cap_reassemble_sdu + * returns and to avoid the race condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but it was freed by + * skb_free_datagram. + */ + u16 txseq = control->txseq; + BT_DBG("chan %p, control %p, skb %p, state %d", chan, control, skb, chan->rx_state); - if (l2cap_classify_txseq(chan, control->txseq) == - L2CAP_TXSEQ_EXPECTED) { + if (l2cap_classify_txseq(chan, txseq) == L2CAP_TXSEQ_EXPECTED) { l2cap_pass_to_tx(chan, control); BT_DBG("buffer_seq %u->%u", chan->buffer_seq, @@ -7324,8 +7384,8 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, } } - chan->last_acked_seq = control->txseq; - chan->expected_tx_seq = __next_seq(chan, control->txseq); + chan->last_acked_seq = txseq; + chan->expected_tx_seq = __next_seq(chan, txseq); return 0; } @@ -7581,6 +7641,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, return; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); } else { BT_DBG("unknown cid 0x%4.4x", cid); @@ -8426,9 +8487,8 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) * expected length. */ if (skb->len < L2CAP_LEN_SIZE) { - if (l2cap_recv_frag(conn, skb, conn->mtu) < 0) - goto drop; - return; + l2cap_recv_frag(conn, skb, conn->mtu); + break; } len = get_unaligned_le16(skb->data) + L2CAP_HDR_SIZE; @@ -8472,7 +8532,7 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) /* Header still could not be read just continue */ if (conn->rx_skb->len < L2CAP_LEN_SIZE) - return; + break; } if (skb->len > conn->rx_len) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index b3556c5c1c08e..0e22ecb469771 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -372,7 +372,7 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 64a56db3de586..34763f575c308 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1253,9 +1253,9 @@ static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, const char *user_protocol) { + const struct dsa_device_ops *tag_ops = NULL; struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; - const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol default_proto; /* Find out which protocol the switch would prefer. */ @@ -1278,10 +1278,17 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, } tag_ops = dsa_find_tagger_by_name(user_protocol); - } else { - tag_ops = dsa_tag_driver_get(default_proto); + if (IS_ERR(tag_ops)) { + dev_warn(ds->dev, + "Failed to find a tagging driver for protocol %s, using default\n", + user_protocol); + tag_ops = NULL; + } } + if (!tag_ops) + tag_ops = dsa_tag_driver_get(default_proto); + if (IS_ERR(tag_ops)) { if (PTR_ERR(tag_ops) == -ENOPROTOOPT) return -EPROBE_DEFER; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e4b2ced66261b..91710e5eedff0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1728,24 +1728,14 @@ static const struct net_protocol igmp_protocol = { }; #endif -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol tcp_protocol = { - .early_demux = tcp_v4_early_demux, - .early_demux_handler = tcp_v4_early_demux, +static const struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol udp_protocol = { - .early_demux = udp_v4_early_demux, - .early_demux_handler = udp_v4_early_demux, +static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d5222c0fa87cb..459d7e630cb04 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -310,14 +310,13 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, ip_hdr(hint)->tos == iph->tos; } -INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *)); +int tcp_v4_early_demux(struct sk_buff *skb); +int udp_v4_early_demux(struct sk_buff *skb); static int ip_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); - int (*edemux)(struct sk_buff *skb); int err, drop_reason; struct rtable *rt; @@ -330,21 +329,29 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, goto drop_error; } - if (net->ipv4.sysctl_ip_early_demux && + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && !ip_is_fragment(iph)) { - const struct net_protocol *ipprot; - int protocol = iph->protocol; - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - err = INDIRECT_CALL_2(edemux, tcp_v4_early_demux, - udp_v4_early_demux, skb); - if (unlikely(err)) - goto drop_error; - /* must reload iph, skb->head might have changed */ - iph = ip_hdr(skb); + switch (iph->protocol) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) { + tcp_v4_early_demux(skb); + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { + err = udp_v4_early_demux(skb); + if (unlikely(err)) + goto drop_error; + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; } } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a36728277e321..495c58e442e2a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -363,61 +363,6 @@ bad_key: return ret; } -static void proc_configure_early_demux(int enabled, int protocol) -{ - struct net_protocol *ipprot; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_protocol *ip6prot; -#endif - - rcu_read_lock(); - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot) - ipprot->early_demux = enabled ? ipprot->early_demux_handler : - NULL; - -#if IS_ENABLED(CONFIG_IPV6) - ip6prot = rcu_dereference(inet6_protos[protocol]); - if (ip6prot) - ip6prot->early_demux = enabled ? ip6prot->early_demux_handler : - NULL; -#endif - rcu_read_unlock(); -} - -static int proc_tcp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_tcp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_TCP); - } - - return ret; -} - -static int proc_udp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_udp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_UDP); - } - - return ret; -} - static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -720,14 +665,14 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_udp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_tcp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "nexthop_compat_mode", diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index d4b1e2c5aa76d..32071529bfd98 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -45,20 +45,23 @@ #include #include -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *)); static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) { - void (*edemux)(struct sk_buff *skb); - - if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { - const struct inet6_protocol *ipprot; - - ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) - INDIRECT_CALL_2(edemux, tcp_v6_early_demux, - udp_v6_early_demux, skb); + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && + !skb_dst(skb) && !skb->sk) { + switch (ipv6_hdr(skb)->nexthdr) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) + tcp_v6_early_demux(skb); + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) + udp_v6_early_demux(skb); + break; + } } + if (!skb_valid_dst(skb)) ip6_route_input(skb); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 27274fc3619ab..0655fd8c67e93 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6570,10 +6570,16 @@ static void __net_exit ip6_route_net_exit(struct net *net) static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, - sizeof(struct ipv6_route_iter)); - proc_create_net_single("rt6_stats", 0444, net->proc_net, - rt6_stats_seq_show, NULL); + if (!proc_create_net("ipv6_route", 0, net->proc_net, + &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter))) + return -ENOMEM; + + if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, + rt6_stats_seq_show, NULL)) { + remove_proc_entry("ipv6_route", net->proc_net); + return -ENOMEM; + } #endif return 0; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 66d00368db828..51f4d330e820b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1854,7 +1854,7 @@ do_time_wait: goto discard_it; } -INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) +void tcp_v6_early_demux(struct sk_buff *skb) { const struct ipv6hdr *hdr; const struct tcphdr *th; @@ -2209,12 +2209,7 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol tcpv6_protocol = { - .early_demux = tcp_v6_early_demux, - .early_demux_handler = tcp_v6_early_demux, +static const struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 19b6c4da0f42a..9dfb4bb54344b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1046,7 +1046,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, return NULL; } -INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) +void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; @@ -1659,12 +1659,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol udpv6_protocol = { - .early_demux = udp_v6_early_demux, - .early_demux_handler = udp_v6_early_demux, +static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 6e391308431da..3adc291d9ce18 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -42,31 +42,8 @@ #define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE) /* Max muber of elements in the array block when tuned */ #define AHASH_MAX_TUNED 64 - #define AHASH_MAX(h) ((h)->bucketsize) -/* Max number of elements can be tuned */ -#ifdef IP_SET_HASH_WITH_MULTI -static u8 -tune_bucketsize(u8 curr, u32 multi) -{ - u32 n; - - if (multi < curr) - return curr; - - n = curr + AHASH_INIT_SIZE; - /* Currently, at listing one hash bucket must fit into a message. - * Therefore we have a hard limit here. - */ - return n > curr && n <= AHASH_MAX_TUNED ? n : curr; -} -#define TUNE_BUCKETSIZE(h, multi) \ - ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi)) -#else -#define TUNE_BUCKETSIZE(h, multi) -#endif - /* A hash bucket */ struct hbucket { struct rcu_head rcu; /* for call_rcu */ @@ -936,7 +913,12 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto set_full; /* Create a new slot */ if (n->pos >= n->size) { - TUNE_BUCKETSIZE(h, multi); +#ifdef IP_SET_HASH_WITH_MULTI + if (h->bucketsize >= AHASH_MAX_TUNED) + goto set_full; + else if (h->bucketsize < multi) + h->bucketsize += AHASH_INIT_SIZE; +#endif if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index f9b16f2b22191..fdacbc3c15bef 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -599,13 +599,19 @@ static const struct seq_operations ip_vs_app_seq_ops = { int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->app_list); - proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops, - sizeof(struct seq_net_private)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, + &ip_vs_app_seq_ops, + sizeof(struct seq_net_private))) + return -ENOMEM; +#endif return 0; } void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { unregister_ip_vs_app(ipvs, NULL /* all */); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_app", ipvs->net->proc_net); +#endif } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index fb67f1ca2495b..cb6d68220c265 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1265,8 +1265,8 @@ static inline int todrop_entry(struct ip_vs_conn *cp) * The drop rate array needs tuning for real environments. * Called from timer bh only => no locking */ - static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; - static char todrop_counter[9] = {0}; + static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; + static signed char todrop_counter[9] = {0}; int i; /* if the conn entry hasn't lasted for 60 seconds, don't drop it. @@ -1447,20 +1447,36 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { atomic_set(&ipvs->conn_count, 0); - proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, - &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state)); - proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, - &ip_vs_conn_sync_seq_ops, - sizeof(struct ip_vs_iter_state)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, + &ip_vs_conn_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn; + + if (!proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, + &ip_vs_conn_sync_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn_sync; +#endif + return 0; + +#ifdef CONFIG_PROC_FS +err_conn_sync: + remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); +err_conn: + return -ENOMEM; +#endif } void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net); +#endif } int __init ip_vs_conn_init(void) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f7a5b8414423d..899f01c6c26c6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8308,9 +8308,6 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); - nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: @@ -8767,6 +8764,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); + + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -9824,6 +9824,8 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, nft_net = nft_pernet(net); deleted = 0; mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nf_tables_destroy_list)) + rcu_barrier(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index f6102e6f51617..730d2205f1976 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -236,6 +236,9 @@ void rose_transmit_clear_request(struct rose_neigh *neigh, unsigned int lci, uns unsigned char *dptr; int len; + if (!neigh->dev) + return; + len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 3; if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index f1e013e3f04a9..935d90874b1b7 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -72,6 +72,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; + unsigned int len; int ret; q->vars.qavg = red_calc_qavg(&q->parms, @@ -126,9 +127,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; } + len = qdisc_pkt_len(skb); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 26f81e2e1dfba..d5ddf283ed8e2 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2744,14 +2744,14 @@ static int __init smc_init(void) rc = register_pernet_subsys(&smc_net_stat_ops); if (rc) - return rc; + goto out_pernet_subsys; smc_ism_init(); smc_clc_init(); rc = smc_nl_init(); if (rc) - goto out_pernet_subsys; + goto out_pernet_subsys_stat; rc = smc_pnet_init(); if (rc) @@ -2829,6 +2829,8 @@ out_pnet: smc_pnet_exit(); out_nl: smc_nl_exit(); +out_pernet_subsys_stat: + unregister_pernet_subsys(&smc_net_stat_ops); out_pernet_subsys: unregister_pernet_subsys(&smc_net_ops); diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index a7020b1f3ec72..55da1b627a7db 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -525,13 +525,16 @@ void rpc_sysfs_client_setup(struct rpc_clnt *clnt, struct net *net) { struct rpc_sysfs_client *rpc_client; + struct rpc_sysfs_xprt_switch *xswitch = + (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; + + if (!xswitch) + return; rpc_client = rpc_sysfs_client_alloc(rpc_sunrpc_client_kobj, net, clnt->cl_clid); if (rpc_client) { char name[] = "switch"; - struct rpc_sysfs_xprt_switch *xswitch = - (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; int ret; clnt->cl_sysfs = rpc_client; @@ -565,6 +568,8 @@ void rpc_sysfs_xprt_switch_setup(struct rpc_xprt_switch *xprt_switch, rpc_xprt_switch->xprt_switch = xprt_switch; rpc_xprt_switch->xprt = xprt; kobject_uevent(&rpc_xprt_switch->kobject, KOBJ_ADD); + } else { + xprt_switch->xps_sysfs = NULL; } } @@ -576,6 +581,9 @@ void rpc_sysfs_xprt_setup(struct rpc_xprt_switch *xprt_switch, struct rpc_sysfs_xprt_switch *switch_obj = (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; + if (!switch_obj) + return; + rpc_xprt = rpc_sysfs_xprt_alloc(&switch_obj->kobject, xprt, gfp_flags); if (rpc_xprt) { xprt->xprt_sysfs = rpc_xprt; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b7be8d066753c..a579e28bd213f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -504,12 +504,6 @@ static void unix_sock_destructor(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } -#endif WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); @@ -556,6 +550,13 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_unlock(sk); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + wake_up_interruptible_all(&u->peer_wait); if (skpair != NULL) { diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 5d46036f3ad74..dc36a46ce0e75 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1897,8 +1897,11 @@ static int vsock_connectible_wait_data(struct sock *sk, err = 0; transport = vsk->transport; - while ((data = vsock_connectible_has_data(vsk)) == 0) { + while (1) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); + data = vsock_connectible_has_data(vsk); + if (data != 0) + break; if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) || diff --git a/security/commoncap.c b/security/commoncap.c index 5fc8986c3c77c..bc751fa5adad7 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -401,8 +401,10 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, &tmpbuf, size, GFP_NOFS); dput(dentry); - if (ret < 0 || !tmpbuf) - return ret; + if (ret < 0 || !tmpbuf) { + size = ret; + goto out_free; + } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index 3e2c6f2ed587f..d64020c1922c2 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -2408,9 +2408,9 @@ static __attribute__((unused)) int memcmp(const void *s1, const void *s2, size_t n) { size_t ofs = 0; - char c1 = 0; + int c1 = 0; - while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) { ofs++; } return c1;