diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml index 29de7807df54..bcd41e491f1d 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml @@ -31,11 +31,11 @@ properties: clocks: minItems: 1 - maxItems: 3 + maxItems: 7 clock-names: minItems: 1 - maxItems: 3 + maxItems: 7 required: - compatible @@ -72,6 +72,32 @@ allOf: contains: enum: - qcom,sdm660-a2noc + then: + properties: + clocks: + items: + - description: Bus Clock. + - description: Bus A Clock. + - description: IPA Clock. + - description: UFS AXI Clock. + - description: Aggregate2 UFS AXI Clock. + - description: Aggregate2 USB3 AXI Clock. + - description: Config NoC USB2 AXI Clock. + clock-names: + items: + - const: bus + - const: bus_a + - const: ipa + - const: ufs_axi + - const: aggre2_ufs_axi + - const: aggre2_usb3_axi + - const: cfg_noc_usb2_axi + + - if: + properties: + compatible: + contains: + enum: - qcom,sdm660-bimc - qcom,sdm660-cnoc - qcom,sdm660-gnoc @@ -91,6 +117,7 @@ examples: - | #include #include + #include bimc: interconnect@1008000 { compatible = "qcom,sdm660-bimc"; @@ -123,9 +150,20 @@ examples: compatible = "qcom,sdm660-a2noc"; reg = <0x01704000 0xc100>; #interconnect-cells = <1>; - clock-names = "bus", "bus_a"; + clock-names = "bus", + "bus_a", + "ipa", + "ufs_axi", + "aggre2_ufs_axi", + "aggre2_usb3_axi", + "cfg_noc_usb2_axi"; clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>, - <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>; + <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>, + <&rpmcc RPM_SMD_IPA_CLK>, + <&gcc GCC_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_USB3_AXI_CLK>, + <&gcc GCC_CFG_NOC_USB2_AXI_CLK>; }; mnoc: interconnect@1745000 { diff --git a/Documentation/hwmon/k10temp.rst b/Documentation/hwmon/k10temp.rst index 8557e26281c3..91b99adc6c48 100644 --- a/Documentation/hwmon/k10temp.rst +++ b/Documentation/hwmon/k10temp.rst @@ -132,20 +132,3 @@ On Family 17h and Family 18h CPUs, additional temperature sensors may report Core Complex Die (CCD) temperatures. Up to 8 such temperatures are reported as temp{3..10}_input, labeled Tccd{1..8}. Actual support depends on the CPU variant. - -Various Family 17h and 18h CPUs report voltage and current telemetry -information. The following attributes may be reported. - -Attribute Label Description -=============== ======= ================ -in0_input Vcore Core voltage -in1_input Vsoc SoC voltage -curr1_input Icore Core current -curr2_input Isoc SoC current -=============== ======= ================ - -Current values are raw (unscaled) as reported by the CPU. Core current is -reported as multiples of 1A / LSB. SoC is reported as multiples of 0.25A -/ LSB. The real current is board specific. Reported currents should be seen -as rough guidance, and should be scaled using sensors3.conf as appropriate -for a given board. diff --git a/MAINTAINERS b/MAINTAINERS index c4c8de673fc9..ee91c5472bc1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -414,7 +414,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm F: drivers/acpi/pmic/ ACPI THERMAL DRIVER -M: Zhang Rui +M: Rafael J. Wysocki +R: Zhang Rui L: linux-acpi@vger.kernel.org S: Supported W: https://01.org/linux-acpi @@ -810,7 +811,7 @@ F: Documentation/devicetree/bindings/dma/altr,msgdma.yaml F: drivers/dma/altera-msgdma.c ALTERA PIO DRIVER -M: Joyce Ooi +M: Mun Yew Tham L: linux-gpio@vger.kernel.org S: Maintained F: drivers/gpio/gpio-altera.c @@ -2961,7 +2962,7 @@ F: crypto/async_tx/ F: include/linux/async_tx.h AT24 EEPROM DRIVER -M: Bartosz Golaszewski +M: Bartosz Golaszewski L: linux-i2c@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git @@ -3384,9 +3385,11 @@ F: Documentation/networking/filter.rst F: Documentation/userspace-api/ebpf/ F: arch/*/net/* F: include/linux/bpf* +F: include/linux/btf* F: include/linux/filter.h F: include/trace/events/xdp.h F: include/uapi/linux/bpf* +F: include/uapi/linux/btf* F: include/uapi/linux/filter.h F: kernel/bpf/ F: kernel/trace/bpf_trace.c @@ -3820,7 +3823,6 @@ F: drivers/scsi/mpi3mr/ BROADCOM NETXTREME-E ROCE DRIVER M: Selvin Xavier -M: Naresh Kumar PBS L: linux-rdma@vger.kernel.org S: Supported W: http://www.broadcom.com @@ -4655,7 +4657,7 @@ W: http://linux-cifs.samba.org/ T: git git://git.samba.org/sfrench/cifs-2.6.git F: Documentation/admin-guide/cifs/ F: fs/cifs/ -F: fs/cifs_common/ +F: fs/smbfs_common/ COMPACTPCI HOTPLUG CORE M: Scott Murray @@ -7985,7 +7987,7 @@ F: include/linux/gpio/regmap.h GPIO SUBSYSTEM M: Linus Walleij -M: Bartosz Golaszewski +M: Bartosz Golaszewski L: linux-gpio@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git @@ -10194,8 +10196,8 @@ M: Hyunchul Lee L: linux-cifs@vger.kernel.org S: Maintained T: git git://git.samba.org/ksmbd.git -F: fs/cifs_common/ F: fs/ksmbd/ +F: fs/smbfs_common/ KERNEL UNIT TESTING FRAMEWORK (KUnit) M: Brendan Higgins @@ -11367,7 +11369,7 @@ F: Documentation/devicetree/bindings/iio/proximity/maxbotix,mb1232.yaml F: drivers/iio/proximity/mb1232.c MAXIM MAX77650 PMIC MFD DRIVER -M: Bartosz Golaszewski +M: Bartosz Golaszewski L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/*/*max77650.yaml @@ -17892,7 +17894,8 @@ M: Olivier Moysan M: Arnaud Pouliquen L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained -F: Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml +F: Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml +F: Documentation/devicetree/bindings/sound/st,stm32-*.yaml F: sound/soc/stm/ STM32 TIMER/LPTIMER DRIVERS @@ -18556,13 +18559,14 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/radio/radio-raremono.c THERMAL -M: Zhang Rui +M: Rafael J. Wysocki M: Daniel Lezcano R: Amit Kucheria +R: Zhang Rui L: linux-pm@vger.kernel.org S: Supported Q: https://patchwork.kernel.org/project/linux-pm/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/thermal/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git thermal F: Documentation/devicetree/bindings/thermal/ F: drivers/thermal/ F: include/linux/cpu_cooling.h @@ -18691,7 +18695,7 @@ F: include/linux/clk/ti.h TI DAVINCI MACHINE SUPPORT M: Sekhar Nori -R: Bartosz Golaszewski +R: Bartosz Golaszewski L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci.git diff --git a/Makefile b/Makefile index 437ccc66a1c2..7b74223d1309 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Opossums on Parade # *DOCUMENTATION* diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 5df6193fc430..8d741f71377f 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -54,7 +54,7 @@ $(obj)/kvm_nvhe.tmp.o: $(obj)/hyp.lds $(addprefix $(obj)/,$(hyp-obj)) FORCE # runtime. Because the hypervisor is part of the kernel binary, relocations # produce a kernel VA. We enumerate relocations targeting hyp at build time # and convert the kernel VAs at those positions to hyp VAs. -$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel +$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel FORCE $(call if_changed,hyprel) # 5) Compile hyp-reloc.S and link it into the existing partially linked object. diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c index f9bb3b14130e..c84fe24b2ea1 100644 --- a/arch/arm64/kvm/perf.c +++ b/arch/arm64/kvm/perf.c @@ -50,9 +50,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { int kvm_perf_init(void) { - if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled()) - static_branch_enable(&kvm_arm_pmu_available); - return perf_register_guest_info_callbacks(&kvm_guest_cbs); } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index f5065f23b413..2af3c37445e0 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -740,7 +740,14 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, kvm_pmu_create_perf_event(vcpu, select_idx); } -int kvm_pmu_probe_pmuver(void) +void kvm_host_pmu_init(struct arm_pmu *pmu) +{ + if (pmu->pmuver != 0 && pmu->pmuver != ID_AA64DFR0_PMUVER_IMP_DEF && + !kvm_arm_support_pmu_v3() && !is_protected_kvm_enabled()) + static_branch_enable(&kvm_arm_pmu_available); +} + +static int kvm_pmu_probe_pmuver(void) { struct perf_event_attr attr = { }; struct perf_event *event; diff --git a/arch/m68k/68000/entry.S b/arch/m68k/68000/entry.S index 259b3661b614..997b54933015 100644 --- a/arch/m68k/68000/entry.S +++ b/arch/m68k/68000/entry.S @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -25,7 +24,6 @@ .globl system_call .globl resume .globl ret_from_exception -.globl ret_from_signal .globl sys_call_table .globl bad_interrupt .globl inthandler1 @@ -59,8 +57,6 @@ do_trace: subql #4,%sp /* dummy return address */ SAVE_SWITCH_STACK jbsr syscall_trace_leave - -ret_from_signal: RESTORE_SWITCH_STACK addql #4,%sp jra ret_from_exception diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 774c35f47eea..0b50da08a9c5 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -29,7 +29,6 @@ config M68K select NO_DMA if !MMU && !COLDFIRE select OLD_SIGACTION select OLD_SIGSUSPEND3 - select SET_FS select UACCESS_MEMCPY if !MMU select VIRT_TO_BUS select ZONE_DMA diff --git a/arch/m68k/coldfire/entry.S b/arch/m68k/coldfire/entry.S index d43a02795a4a..9f337c70243a 100644 --- a/arch/m68k/coldfire/entry.S +++ b/arch/m68k/coldfire/entry.S @@ -31,7 +31,6 @@ #include #include #include -#include #include #include @@ -51,7 +50,6 @@ sw_usp: .globl system_call .globl resume .globl ret_from_exception -.globl ret_from_signal .globl sys_call_table .globl inthandler @@ -98,8 +96,6 @@ ENTRY(system_call) subql #4,%sp /* dummy return address */ SAVE_SWITCH_STACK jbsr syscall_trace_leave - -ret_from_signal: RESTORE_SWITCH_STACK addql #4,%sp diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index 3750819ac5a1..f4d82c619a5c 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -9,7 +9,6 @@ #define __ASM_M68K_PROCESSOR_H #include -#include #include #include @@ -75,11 +74,37 @@ static inline void wrusp(unsigned long usp) #define TASK_UNMAPPED_BASE 0 #endif +/* Address spaces (or Function Codes in Motorola lingo) */ +#define USER_DATA 1 +#define USER_PROGRAM 2 +#define SUPER_DATA 5 +#define SUPER_PROGRAM 6 +#define CPU_SPACE 7 + +#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES +/* + * Set the SFC/DFC registers for special MM operations. For most normal + * operation these remain set to USER_DATA for the uaccess routines. + */ +static inline void set_fc(unsigned long val) +{ + WARN_ON_ONCE(in_interrupt()); + + __asm__ __volatile__ ("movec %0,%/sfc\n\t" + "movec %0,%/dfc\n\t" + : /* no outputs */ : "r" (val) : "memory"); +} +#else +static inline void set_fc(unsigned long val) +{ +} +#endif /* CONFIG_CPU_HAS_ADDRESS_SPACES */ + struct thread_struct { unsigned long ksp; /* kernel stack pointer */ unsigned long usp; /* user stack pointer */ unsigned short sr; /* saved status register */ - unsigned short fs; /* saved fs (sfc, dfc) */ + unsigned short fc; /* saved fc (sfc, dfc) */ unsigned long crp[2]; /* cpu root pointer */ unsigned long esp0; /* points to SR of stack frame */ unsigned long faddr; /* info about last fault */ @@ -92,7 +117,7 @@ struct thread_struct { #define INIT_THREAD { \ .ksp = sizeof(init_stack) + (unsigned long) init_stack, \ .sr = PS_S, \ - .fs = __KERNEL_DS, \ + .fc = USER_DATA, \ } /* diff --git a/arch/m68k/include/asm/segment.h b/arch/m68k/include/asm/segment.h deleted file mode 100644 index 2b5e68a71ef7..000000000000 --- a/arch/m68k/include/asm/segment.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _M68K_SEGMENT_H -#define _M68K_SEGMENT_H - -/* define constants */ -/* Address spaces (FC0-FC2) */ -#define USER_DATA (1) -#ifndef __USER_DS -#define __USER_DS (USER_DATA) -#endif -#define USER_PROGRAM (2) -#define SUPER_DATA (5) -#ifndef __KERNEL_DS -#define __KERNEL_DS (SUPER_DATA) -#endif -#define SUPER_PROGRAM (6) -#define CPU_SPACE (7) - -#ifndef __ASSEMBLY__ - -typedef struct { - unsigned long seg; -} mm_segment_t; - -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - -#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES -/* - * Get/set the SFC/DFC registers for MOVES instructions - */ -#define USER_DS MAKE_MM_SEG(__USER_DS) -#define KERNEL_DS MAKE_MM_SEG(__KERNEL_DS) - -static inline mm_segment_t get_fs(void) -{ - mm_segment_t _v; - __asm__ ("movec %/dfc,%0":"=r" (_v.seg):); - return _v; -} - -static inline void set_fs(mm_segment_t val) -{ - __asm__ __volatile__ ("movec %0,%/sfc\n\t" - "movec %0,%/dfc\n\t" - : /* no outputs */ : "r" (val.seg) : "memory"); -} - -#else -#define USER_DS MAKE_MM_SEG(TASK_SIZE) -#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFF) -#define get_fs() (current_thread_info()->addr_limit) -#define set_fs(x) (current_thread_info()->addr_limit = (x)) -#endif - -#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) - -#endif /* __ASSEMBLY__ */ - -#endif /* _M68K_SEGMENT_H */ diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h index 15a757073fa5..c952658ba792 100644 --- a/arch/m68k/include/asm/thread_info.h +++ b/arch/m68k/include/asm/thread_info.h @@ -4,7 +4,6 @@ #include #include -#include /* * On machines with 4k pages we default to an 8k thread size, though we @@ -27,7 +26,6 @@ struct thread_info { struct task_struct *task; /* main task structure */ unsigned long flags; - mm_segment_t addr_limit; /* thread address space */ int preempt_count; /* 0 => preemptable, <0 => BUG */ __u32 cpu; /* should always be 0 on m68k */ unsigned long tp_value; /* thread pointer */ @@ -37,7 +35,6 @@ struct thread_info { #define INIT_THREAD_INFO(tsk) \ { \ .task = &tsk, \ - .addr_limit = KERNEL_DS, \ .preempt_count = INIT_PREEMPT_COUNT, \ } diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h index a6318ccd308f..b882e2f4f551 100644 --- a/arch/m68k/include/asm/tlbflush.h +++ b/arch/m68k/include/asm/tlbflush.h @@ -13,13 +13,12 @@ static inline void flush_tlb_kernel_page(void *addr) if (CPU_IS_COLDFIRE) { mmu_write(MMUOR, MMUOR_CNL); } else if (CPU_IS_040_OR_060) { - mm_segment_t old_fs = get_fs(); - set_fs(KERNEL_DS); + set_fc(SUPER_DATA); __asm__ __volatile__(".chip 68040\n\t" "pflush (%0)\n\t" ".chip 68k" : : "a" (addr)); - set_fs(old_fs); + set_fc(USER_DATA); } else if (CPU_IS_020_OR_030) __asm__ __volatile__("pflush #4,#4,(%0)" : : "a" (addr)); } @@ -84,12 +83,8 @@ static inline void flush_tlb_mm(struct mm_struct *mm) static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) { - if (vma->vm_mm == current->active_mm) { - mm_segment_t old_fs = force_uaccess_begin(); - + if (vma->vm_mm == current->active_mm) __flush_tlb_one(addr); - force_uaccess_end(old_fs); - } } static inline void flush_tlb_range(struct vm_area_struct *vma, diff --git a/arch/m68k/include/asm/traps.h b/arch/m68k/include/asm/traps.h index 4aff3358fbaf..a9d5c1c870d3 100644 --- a/arch/m68k/include/asm/traps.h +++ b/arch/m68k/include/asm/traps.h @@ -267,6 +267,10 @@ struct frame { } un; }; +#ifdef CONFIG_M68040 +asmlinkage void berr_040cleanup(struct frame *fp); +#endif + #endif /* __ASSEMBLY__ */ #endif /* _M68K_TRAPS_H */ diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index f98208ccbbcd..ba670523885c 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -9,13 +9,16 @@ */ #include #include -#include #include /* We let the MMU do all checking */ static inline int access_ok(const void __user *addr, unsigned long size) { + /* + * XXX: for !CONFIG_CPU_HAS_ADDRESS_SPACES this really needs to check + * for TASK_SIZE! + */ return 1; } @@ -35,12 +38,9 @@ static inline int access_ok(const void __user *addr, #define MOVES "move" #endif -extern int __put_user_bad(void); -extern int __get_user_bad(void); - -#define __put_user_asm(res, x, ptr, bwl, reg, err) \ +#define __put_user_asm(inst, res, x, ptr, bwl, reg, err) \ asm volatile ("\n" \ - "1: "MOVES"."#bwl" %2,%1\n" \ + "1: "inst"."#bwl" %2,%1\n" \ "2:\n" \ " .section .fixup,\"ax\"\n" \ " .even\n" \ @@ -56,6 +56,31 @@ asm volatile ("\n" \ : "+d" (res), "=m" (*(ptr)) \ : #reg (x), "i" (err)) +#define __put_user_asm8(inst, res, x, ptr) \ +do { \ + const void *__pu_ptr = (const void __force *)(ptr); \ + \ + asm volatile ("\n" \ + "1: "inst".l %2,(%1)+\n" \ + "2: "inst".l %R2,(%1)\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .even\n" \ + "10: movel %3,%0\n" \ + " jra 3b\n" \ + " .previous\n" \ + "\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 4\n" \ + " .long 1b,10b\n" \ + " .long 2b,10b\n" \ + " .long 3b,10b\n" \ + " .previous" \ + : "+d" (res), "+a" (__pu_ptr) \ + : "r" (x), "i" (-EFAULT) \ + : "memory"); \ +} while (0) + /* * These are the main single-value transfer routines. They automatically * use the right size if we just have the right pointer type. @@ -68,51 +93,29 @@ asm volatile ("\n" \ __chk_user_ptr(ptr); \ switch (sizeof (*(ptr))) { \ case 1: \ - __put_user_asm(__pu_err, __pu_val, ptr, b, d, -EFAULT); \ + __put_user_asm(MOVES, __pu_err, __pu_val, ptr, b, d, -EFAULT); \ break; \ case 2: \ - __put_user_asm(__pu_err, __pu_val, ptr, w, r, -EFAULT); \ + __put_user_asm(MOVES, __pu_err, __pu_val, ptr, w, r, -EFAULT); \ break; \ case 4: \ - __put_user_asm(__pu_err, __pu_val, ptr, l, r, -EFAULT); \ + __put_user_asm(MOVES, __pu_err, __pu_val, ptr, l, r, -EFAULT); \ break; \ case 8: \ - { \ - const void __user *__pu_ptr = (ptr); \ - asm volatile ("\n" \ - "1: "MOVES".l %2,(%1)+\n" \ - "2: "MOVES".l %R2,(%1)\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .even\n" \ - "10: movel %3,%0\n" \ - " jra 3b\n" \ - " .previous\n" \ - "\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 4\n" \ - " .long 1b,10b\n" \ - " .long 2b,10b\n" \ - " .long 3b,10b\n" \ - " .previous" \ - : "+d" (__pu_err), "+a" (__pu_ptr) \ - : "r" (__pu_val), "i" (-EFAULT) \ - : "memory"); \ + __put_user_asm8(MOVES, __pu_err, __pu_val, ptr); \ break; \ - } \ default: \ - __pu_err = __put_user_bad(); \ - break; \ + BUILD_BUG(); \ } \ __pu_err; \ }) #define put_user(x, ptr) __put_user(x, ptr) -#define __get_user_asm(res, x, ptr, type, bwl, reg, err) ({ \ +#define __get_user_asm(inst, res, x, ptr, type, bwl, reg, err) ({ \ type __gu_val; \ asm volatile ("\n" \ - "1: "MOVES"."#bwl" %2,%1\n" \ + "1: "inst"."#bwl" %2,%1\n" \ "2:\n" \ " .section .fixup,\"ax\"\n" \ " .even\n" \ @@ -130,53 +133,57 @@ asm volatile ("\n" \ (x) = (__force typeof(*(ptr)))(__force unsigned long)__gu_val; \ }) +#define __get_user_asm8(inst, res, x, ptr) \ +do { \ + const void *__gu_ptr = (const void __force *)(ptr); \ + union { \ + u64 l; \ + __typeof__(*(ptr)) t; \ + } __gu_val; \ + \ + asm volatile ("\n" \ + "1: "inst".l (%2)+,%1\n" \ + "2: "inst".l (%2),%R1\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .even\n" \ + "10: move.l %3,%0\n" \ + " sub.l %1,%1\n" \ + " sub.l %R1,%R1\n" \ + " jra 3b\n" \ + " .previous\n" \ + "\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 4\n" \ + " .long 1b,10b\n" \ + " .long 2b,10b\n" \ + " .previous" \ + : "+d" (res), "=&r" (__gu_val.l), \ + "+a" (__gu_ptr) \ + : "i" (-EFAULT) \ + : "memory"); \ + (x) = __gu_val.t; \ +} while (0) + #define __get_user(x, ptr) \ ({ \ int __gu_err = 0; \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm(__gu_err, x, ptr, u8, b, d, -EFAULT); \ + __get_user_asm(MOVES, __gu_err, x, ptr, u8, b, d, -EFAULT); \ break; \ case 2: \ - __get_user_asm(__gu_err, x, ptr, u16, w, r, -EFAULT); \ + __get_user_asm(MOVES, __gu_err, x, ptr, u16, w, r, -EFAULT); \ break; \ case 4: \ - __get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT); \ + __get_user_asm(MOVES, __gu_err, x, ptr, u32, l, r, -EFAULT); \ break; \ - case 8: { \ - const void __user *__gu_ptr = (ptr); \ - union { \ - u64 l; \ - __typeof__(*(ptr)) t; \ - } __gu_val; \ - asm volatile ("\n" \ - "1: "MOVES".l (%2)+,%1\n" \ - "2: "MOVES".l (%2),%R1\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .even\n" \ - "10: move.l %3,%0\n" \ - " sub.l %1,%1\n" \ - " sub.l %R1,%R1\n" \ - " jra 3b\n" \ - " .previous\n" \ - "\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 4\n" \ - " .long 1b,10b\n" \ - " .long 2b,10b\n" \ - " .previous" \ - : "+d" (__gu_err), "=&r" (__gu_val.l), \ - "+a" (__gu_ptr) \ - : "i" (-EFAULT) \ - : "memory"); \ - (x) = __gu_val.t; \ + case 8: \ + __get_user_asm8(MOVES, __gu_err, x, ptr); \ break; \ - } \ default: \ - __gu_err = __get_user_bad(); \ - break; \ + BUILD_BUG(); \ } \ __gu_err; \ }) @@ -322,16 +329,19 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n) switch (n) { case 1: - __put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1); + __put_user_asm(MOVES, res, *(u8 *)from, (u8 __user *)to, + b, d, 1); break; case 2: - __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, r, 2); + __put_user_asm(MOVES, res, *(u16 *)from, (u16 __user *)to, + w, r, 2); break; case 3: __constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,); break; case 4: - __put_user_asm(res, *(u32 *)from, (u32 __user *)to, l, r, 4); + __put_user_asm(MOVES, res, *(u32 *)from, (u32 __user *)to, + l, r, 4); break; case 5: __constant_copy_to_user_asm(res, to, from, tmp, 5, l, b,); @@ -380,8 +390,65 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) #define INLINE_COPY_FROM_USER #define INLINE_COPY_TO_USER -#define user_addr_max() \ - (uaccess_kernel() ? ~0UL : TASK_SIZE) +#define HAVE_GET_KERNEL_NOFAULT + +#define __get_kernel_nofault(dst, src, type, err_label) \ +do { \ + type *__gk_dst = (type *)(dst); \ + type *__gk_src = (type *)(src); \ + int __gk_err = 0; \ + \ + switch (sizeof(type)) { \ + case 1: \ + __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \ + u8, b, d, -EFAULT); \ + break; \ + case 2: \ + __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \ + u16, w, r, -EFAULT); \ + break; \ + case 4: \ + __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \ + u32, l, r, -EFAULT); \ + break; \ + case 8: \ + __get_user_asm8("move", __gk_err, *__gk_dst, __gk_src); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + if (unlikely(__gk_err)) \ + goto err_label; \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, err_label) \ +do { \ + type __pk_src = *(type *)(src); \ + type *__pk_dst = (type *)(dst); \ + int __pk_err = 0; \ + \ + switch (sizeof(type)) { \ + case 1: \ + __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \ + b, d, -EFAULT); \ + break; \ + case 2: \ + __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \ + w, r, -EFAULT); \ + break; \ + case 4: \ + __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \ + l, r, -EFAULT); \ + break; \ + case 8: \ + __put_user_asm8("move", __pk_err, __pk_src, __pk_dst); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + if (unlikely(__pk_err)) \ + goto err_label; \ +} while (0) extern long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); diff --git a/arch/m68k/kernel/asm-offsets.c b/arch/m68k/kernel/asm-offsets.c index ccea355052ef..906d73230537 100644 --- a/arch/m68k/kernel/asm-offsets.c +++ b/arch/m68k/kernel/asm-offsets.c @@ -31,7 +31,7 @@ int main(void) DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp)); DEFINE(THREAD_USP, offsetof(struct thread_struct, usp)); DEFINE(THREAD_SR, offsetof(struct thread_struct, sr)); - DEFINE(THREAD_FS, offsetof(struct thread_struct, fs)); + DEFINE(THREAD_FC, offsetof(struct thread_struct, fc)); DEFINE(THREAD_CRP, offsetof(struct thread_struct, crp)); DEFINE(THREAD_ESP0, offsetof(struct thread_struct, esp0)); DEFINE(THREAD_FPREG, offsetof(struct thread_struct, fp)); diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 9dd76fbb7c6b..9434fca68de5 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -36,7 +36,6 @@ #include #include #include -#include #include #include #include @@ -78,20 +77,38 @@ ENTRY(__sys_clone3) ENTRY(sys_sigreturn) SAVE_SWITCH_STACK - movel %sp,%sp@- | switch_stack pointer - pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer + movel %sp,%a1 | switch_stack pointer + lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer + lea %sp@(-84),%sp | leave a gap + movel %a1,%sp@- + movel %a0,%sp@- jbsr do_sigreturn - addql #8,%sp - RESTORE_SWITCH_STACK - rts + jra 1f | shared with rt_sigreturn() ENTRY(sys_rt_sigreturn) SAVE_SWITCH_STACK - movel %sp,%sp@- | switch_stack pointer - pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer + movel %sp,%a1 | switch_stack pointer + lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer + lea %sp@(-84),%sp | leave a gap + movel %a1,%sp@- + movel %a0,%sp@- + | stack contents: + | [original pt_regs address] [original switch_stack address] + | [gap] [switch_stack] [pt_regs] [exception frame] jbsr do_rt_sigreturn - addql #8,%sp + +1: + | stack contents now: + | [original pt_regs address] [original switch_stack address] + | [unused part of the gap] [moved switch_stack] [moved pt_regs] + | [replacement exception frame] + | return value of do_{rt_,}sigreturn() points to moved switch_stack. + + movel %d0,%sp | discard the leftover junk RESTORE_SWITCH_STACK + | stack contents now is just [syscall return address] [pt_regs] [frame] + | return pt_regs.d0 + movel %sp@(PT_OFF_D0+4),%d0 rts ENTRY(buserr) @@ -182,25 +199,6 @@ do_trace_exit: addql #4,%sp jra .Lret_from_exception -ENTRY(ret_from_signal) - movel %curptr@(TASK_STACK),%a1 - tstb %a1@(TINFO_FLAGS+2) - jge 1f - jbsr syscall_trace -1: RESTORE_SWITCH_STACK - addql #4,%sp -/* on 68040 complete pending writebacks if any */ -#ifdef CONFIG_M68040 - bfextu %sp@(PT_OFF_FORMATVEC){#0,#4},%d0 - subql #7,%d0 | bus error frame ? - jbne 1f - movel %sp,%sp@- - jbsr berr_040cleanup - addql #4,%sp -1: -#endif - jra .Lret_from_exception - ENTRY(system_call) SAVE_ALL_SYS @@ -338,7 +336,7 @@ resume: /* save fs (sfc,%dfc) (may be pointing to kernel memory) */ movec %sfc,%d0 - movew %d0,%a0@(TASK_THREAD+THREAD_FS) + movew %d0,%a0@(TASK_THREAD+THREAD_FC) /* save usp */ /* it is better to use a movel here instead of a movew 8*) */ @@ -424,7 +422,7 @@ resume: movel %a0,%usp /* restore fs (sfc,%dfc) */ - movew %a1@(TASK_THREAD+THREAD_FS),%a0 + movew %a1@(TASK_THREAD+THREAD_FC),%a0 movec %a0,%sfc movec %a0,%dfc diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index db49f9091711..1ab692b952cd 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -92,7 +92,7 @@ void show_regs(struct pt_regs * regs) void flush_thread(void) { - current->thread.fs = __USER_DS; + current->thread.fc = USER_DATA; #ifdef CONFIG_FPU if (!FPU_IS_EMU) { unsigned long zero = 0; @@ -155,7 +155,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, * Must save the current SFC/DFC value, NOT the value when * the parent was last descheduled - RGH 10-08-96 */ - p->thread.fs = get_fs().seg; + p->thread.fc = USER_DATA; if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 8f215e79e70e..338817d0cb3f 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -447,7 +447,7 @@ static inline void save_fpu_state(struct sigcontext *sc, struct pt_regs *regs) if (CPU_IS_060 ? sc->sc_fpstate[2] : sc->sc_fpstate[0]) { fpu_version = sc->sc_fpstate[0]; - if (CPU_IS_020_OR_030 && + if (CPU_IS_020_OR_030 && !regs->stkadj && regs->vector >= (VEC_FPBRUC * 4) && regs->vector <= (VEC_FPNAN * 4)) { /* Clear pending exception in 68882 idle frame */ @@ -510,7 +510,7 @@ static inline int rt_save_fpu_state(struct ucontext __user *uc, struct pt_regs * if (!(CPU_IS_060 || CPU_IS_COLDFIRE)) context_size = fpstate[1]; fpu_version = fpstate[0]; - if (CPU_IS_020_OR_030 && + if (CPU_IS_020_OR_030 && !regs->stkadj && regs->vector >= (VEC_FPBRUC * 4) && regs->vector <= (VEC_FPNAN * 4)) { /* Clear pending exception in 68882 idle frame */ @@ -641,56 +641,35 @@ static inline void siginfo_build_tests(void) static int mangle_kernel_stack(struct pt_regs *regs, int formatvec, void __user *fp) { - int fsize = frame_extra_sizes(formatvec >> 12); - if (fsize < 0) { + int extra = frame_extra_sizes(formatvec >> 12); + char buf[sizeof_field(struct frame, un)]; + + if (extra < 0) { /* * user process trying to return with weird frame format */ pr_debug("user process returning with weird frame format\n"); - return 1; + return -1; } - if (!fsize) { - regs->format = formatvec >> 12; - regs->vector = formatvec & 0xfff; - } else { - struct switch_stack *sw = (struct switch_stack *)regs - 1; - /* yes, twice as much as max(sizeof(frame.un.fmt)) */ - unsigned long buf[sizeof_field(struct frame, un) / 2]; + if (extra && copy_from_user(buf, fp, extra)) + return -1; + regs->format = formatvec >> 12; + regs->vector = formatvec & 0xfff; + if (extra) { + void *p = (struct switch_stack *)regs - 1; + struct frame *new = (void *)regs - extra; + int size = sizeof(struct pt_regs)+sizeof(struct switch_stack); - /* that'll make sure that expansion won't crap over data */ - if (copy_from_user(buf + fsize / 4, fp, fsize)) - return 1; - - /* point of no return */ - regs->format = formatvec >> 12; - regs->vector = formatvec & 0xfff; -#define frame_offset (sizeof(struct pt_regs)+sizeof(struct switch_stack)) - __asm__ __volatile__ ( -#ifdef CONFIG_COLDFIRE - " movel %0,%/sp\n\t" - " bra ret_from_signal\n" -#else - " movel %0,%/a0\n\t" - " subl %1,%/a0\n\t" /* make room on stack */ - " movel %/a0,%/sp\n\t" /* set stack pointer */ - /* move switch_stack and pt_regs */ - "1: movel %0@+,%/a0@+\n\t" - " dbra %2,1b\n\t" - " lea %/sp@(%c3),%/a0\n\t" /* add offset of fmt */ - " lsrl #2,%1\n\t" - " subql #1,%1\n\t" - /* copy to the gap we'd made */ - "2: movel %4@+,%/a0@+\n\t" - " dbra %1,2b\n\t" - " bral ret_from_signal\n" + memmove(p - extra, p, size); + memcpy(p - extra + size, buf, extra); + current->thread.esp0 = (unsigned long)&new->ptregs; +#ifdef CONFIG_M68040 + /* on 68040 complete pending writebacks if any */ + if (new->ptregs.format == 7) // bus error frame + berr_040cleanup(new); #endif - : /* no outputs, it doesn't ever return */ - : "a" (sw), "d" (fsize), "d" (frame_offset/4-1), - "n" (frame_offset), "a" (buf + fsize/4) - : "a0"); -#undef frame_offset } - return 0; + return extra; } static inline int @@ -698,7 +677,6 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u { int formatvec; struct sigcontext context; - int err = 0; siginfo_build_tests(); @@ -707,7 +685,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u /* get previous context */ if (copy_from_user(&context, usc, sizeof(context))) - goto badframe; + return -1; /* restore passed registers */ regs->d0 = context.sc_d0; @@ -720,15 +698,10 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u wrusp(context.sc_usp); formatvec = context.sc_formatvec; - err = restore_fpu_state(&context); + if (restore_fpu_state(&context)) + return -1; - if (err || mangle_kernel_stack(regs, formatvec, fp)) - goto badframe; - - return 0; - -badframe: - return 1; + return mangle_kernel_stack(regs, formatvec, fp); } static inline int @@ -745,7 +718,7 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw, err = __get_user(temp, &uc->uc_mcontext.version); if (temp != MCONTEXT_VERSION) - goto badframe; + return -1; /* restore passed registers */ err |= __get_user(regs->d0, &gregs[0]); err |= __get_user(regs->d1, &gregs[1]); @@ -774,22 +747,17 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw, err |= restore_altstack(&uc->uc_stack); if (err) - goto badframe; + return -1; - if (mangle_kernel_stack(regs, temp, &uc->uc_extra)) - goto badframe; - - return 0; - -badframe: - return 1; + return mangle_kernel_stack(regs, temp, &uc->uc_extra); } -asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) +asmlinkage void *do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) { unsigned long usp = rdusp(); struct sigframe __user *frame = (struct sigframe __user *)(usp - 4); sigset_t set; + int size; if (!access_ok(frame, sizeof(*frame))) goto badframe; @@ -801,20 +769,22 @@ asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->sc, frame + 1)) + size = restore_sigcontext(regs, &frame->sc, frame + 1); + if (size < 0) goto badframe; - return regs->d0; + return (void *)sw - size; badframe: force_sig(SIGSEGV); - return 0; + return sw; } -asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) +asmlinkage void *do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) { unsigned long usp = rdusp(); struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(usp - 4); sigset_t set; + int size; if (!access_ok(frame, sizeof(*frame))) goto badframe; @@ -823,27 +793,34 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) set_current_blocked(&set); - if (rt_restore_ucontext(regs, sw, &frame->uc)) + size = rt_restore_ucontext(regs, sw, &frame->uc); + if (size < 0) goto badframe; - return regs->d0; + return (void *)sw - size; badframe: force_sig(SIGSEGV); - return 0; + return sw; +} + +static inline struct pt_regs *rte_regs(struct pt_regs *regs) +{ + return (void *)regs + regs->stkadj; } static void setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs, unsigned long mask) { + struct pt_regs *tregs = rte_regs(regs); sc->sc_mask = mask; sc->sc_usp = rdusp(); sc->sc_d0 = regs->d0; sc->sc_d1 = regs->d1; sc->sc_a0 = regs->a0; sc->sc_a1 = regs->a1; - sc->sc_sr = regs->sr; - sc->sc_pc = regs->pc; - sc->sc_formatvec = regs->format << 12 | regs->vector; + sc->sc_sr = tregs->sr; + sc->sc_pc = tregs->pc; + sc->sc_formatvec = tregs->format << 12 | tregs->vector; save_a5_state(sc, regs); save_fpu_state(sc, regs); } @@ -851,6 +828,7 @@ static void setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs, static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs *regs) { struct switch_stack *sw = (struct switch_stack *)regs - 1; + struct pt_regs *tregs = rte_regs(regs); greg_t __user *gregs = uc->uc_mcontext.gregs; int err = 0; @@ -871,9 +849,9 @@ static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs * err |= __put_user(sw->a5, &gregs[13]); err |= __put_user(sw->a6, &gregs[14]); err |= __put_user(rdusp(), &gregs[15]); - err |= __put_user(regs->pc, &gregs[16]); - err |= __put_user(regs->sr, &gregs[17]); - err |= __put_user((regs->format << 12) | regs->vector, &uc->uc_formatvec); + err |= __put_user(tregs->pc, &gregs[16]); + err |= __put_user(tregs->sr, &gregs[17]); + err |= __put_user((tregs->format << 12) | tregs->vector, &uc->uc_formatvec); err |= rt_save_fpu_state(uc, regs); return err; } @@ -890,13 +868,14 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct sigframe __user *frame; - int fsize = frame_extra_sizes(regs->format); + struct pt_regs *tregs = rte_regs(regs); + int fsize = frame_extra_sizes(tregs->format); struct sigcontext context; int err = 0, sig = ksig->sig; if (fsize < 0) { pr_debug("setup_frame: Unknown frame format %#x\n", - regs->format); + tregs->format); return -EFAULT; } @@ -907,7 +886,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, err |= __put_user(sig, &frame->sig); - err |= __put_user(regs->vector, &frame->code); + err |= __put_user(tregs->vector, &frame->code); err |= __put_user(&frame->sc, &frame->psc); if (_NSIG_WORDS > 1) @@ -933,34 +912,28 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, push_cache ((unsigned long) &frame->retcode); - /* - * Set up registers for signal handler. All the state we are about - * to destroy is successfully copied to sigframe. - */ - wrusp ((unsigned long) frame); - regs->pc = (unsigned long) ksig->ka.sa.sa_handler; - adjustformat(regs); - /* * This is subtle; if we build more than one sigframe, all but the * first one will see frame format 0 and have fsize == 0, so we won't * screw stkadj. */ - if (fsize) + if (fsize) { regs->stkadj = fsize; - - /* Prepare to skip over the extra stuff in the exception frame. */ - if (regs->stkadj) { - struct pt_regs *tregs = - (struct pt_regs *)((ulong)regs + regs->stkadj); + tregs = rte_regs(regs); pr_debug("Performing stackadjust=%04lx\n", regs->stkadj); - /* This must be copied with decreasing addresses to - handle overlaps. */ tregs->vector = 0; tregs->format = 0; - tregs->pc = regs->pc; tregs->sr = regs->sr; } + + /* + * Set up registers for signal handler. All the state we are about + * to destroy is successfully copied to sigframe. + */ + wrusp ((unsigned long) frame); + tregs->pc = (unsigned long) ksig->ka.sa.sa_handler; + adjustformat(regs); + return 0; } @@ -968,7 +941,8 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe __user *frame; - int fsize = frame_extra_sizes(regs->format); + struct pt_regs *tregs = rte_regs(regs); + int fsize = frame_extra_sizes(tregs->format); int err = 0, sig = ksig->sig; if (fsize < 0) { @@ -1018,34 +992,27 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, push_cache ((unsigned long) &frame->retcode); - /* - * Set up registers for signal handler. All the state we are about - * to destroy is successfully copied to sigframe. - */ - wrusp ((unsigned long) frame); - regs->pc = (unsigned long) ksig->ka.sa.sa_handler; - adjustformat(regs); - /* * This is subtle; if we build more than one sigframe, all but the * first one will see frame format 0 and have fsize == 0, so we won't * screw stkadj. */ - if (fsize) + if (fsize) { regs->stkadj = fsize; - - /* Prepare to skip over the extra stuff in the exception frame. */ - if (regs->stkadj) { - struct pt_regs *tregs = - (struct pt_regs *)((ulong)regs + regs->stkadj); + tregs = rte_regs(regs); pr_debug("Performing stackadjust=%04lx\n", regs->stkadj); - /* This must be copied with decreasing addresses to - handle overlaps. */ tregs->vector = 0; tregs->format = 0; - tregs->pc = regs->pc; tregs->sr = regs->sr; } + + /* + * Set up registers for signal handler. All the state we are about + * to destroy is successfully copied to sigframe. + */ + wrusp ((unsigned long) frame); + tregs->pc = (unsigned long) ksig->ka.sa.sa_handler; + adjustformat(regs); return 0; } diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 5b19fcdcd69e..9718ce94cc84 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -181,9 +181,8 @@ static inline void access_error060 (struct frame *fp) static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs) { unsigned long mmusr; - mm_segment_t old_fs = get_fs(); - set_fs(MAKE_MM_SEG(wbs)); + set_fc(wbs); if (iswrite) asm volatile (".chip 68040; ptestw (%0); .chip 68k" : : "a" (addr)); @@ -192,7 +191,7 @@ static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs) asm volatile (".chip 68040; movec %%mmusr,%0; .chip 68k" : "=r" (mmusr)); - set_fs(old_fs); + set_fc(USER_DATA); return mmusr; } @@ -201,10 +200,8 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba, unsigned long wbd) { int res = 0; - mm_segment_t old_fs = get_fs(); - /* set_fs can not be moved, otherwise put_user() may oops */ - set_fs(MAKE_MM_SEG(wbs)); + set_fc(wbs); switch (wbs & WBSIZ_040) { case BA_SIZE_BYTE: @@ -218,9 +215,7 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba, break; } - /* set_fs can not be moved, otherwise put_user() may oops */ - set_fs(old_fs); - + set_fc(USER_DATA); pr_debug("do_040writeback1, res=%d\n", res); diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index 90f4e9ca1276..4fab34791758 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -18,7 +18,6 @@ #include #include -#include #include #include #include diff --git a/arch/m68k/mm/cache.c b/arch/m68k/mm/cache.c index b486c0889eec..dde978e66f14 100644 --- a/arch/m68k/mm/cache.c +++ b/arch/m68k/mm/cache.c @@ -49,24 +49,7 @@ static unsigned long virt_to_phys_slow(unsigned long vaddr) if (mmusr & MMU_R_040) return (mmusr & PAGE_MASK) | (vaddr & ~PAGE_MASK); } else { - unsigned short mmusr; - unsigned long *descaddr; - - asm volatile ("ptestr %3,%2@,#7,%0\n\t" - "pmove %%psr,%1" - : "=a&" (descaddr), "=m" (mmusr) - : "a" (vaddr), "d" (get_fs().seg)); - if (mmusr & (MMU_I|MMU_B|MMU_L)) - return 0; - descaddr = phys_to_virt((unsigned long)descaddr); - switch (mmusr & MMU_NUM) { - case 1: - return (*descaddr & 0xfe000000) | (vaddr & 0x01ffffff); - case 2: - return (*descaddr & 0xfffc0000) | (vaddr & 0x0003ffff); - case 3: - return (*descaddr & PAGE_MASK) | (vaddr & ~PAGE_MASK); - } + WARN_ON_ONCE(!CPU_IS_040_OR_060); } return 0; } @@ -107,11 +90,9 @@ void flush_icache_user_range(unsigned long address, unsigned long endaddr) void flush_icache_range(unsigned long address, unsigned long endaddr) { - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); + set_fc(SUPER_DATA); flush_icache_user_range(address, endaddr); - set_fs(old_fs); + set_fc(USER_DATA); } EXPORT_SYMBOL(flush_icache_range); diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 5d749e188246..1b47bec15832 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -72,12 +72,6 @@ void __init paging_init(void) if (!empty_zero_page) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); - - /* - * Set up SFC/DFC registers (user data space). - */ - set_fs (USER_DS); - max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT; free_area_init(max_zone_pfn); } diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c index 1269d513b221..20ddf71b43d0 100644 --- a/arch/m68k/mm/kmap.c +++ b/arch/m68k/mm/kmap.c @@ -17,7 +17,6 @@ #include #include -#include #include #include #include diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c index fe75aecfb238..c2c03b0a1567 100644 --- a/arch/m68k/mm/memory.c +++ b/arch/m68k/mm/memory.c @@ -15,7 +15,6 @@ #include #include -#include #include #include #include diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 3a653f0a4188..9f3f77785aa7 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -467,7 +467,7 @@ void __init paging_init(void) /* * Set up SFC/DFC registers */ - set_fs(KERNEL_DS); + set_fc(USER_DATA); #ifdef DEBUG printk ("before free_area_init\n"); diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index f7dd47232b6c..203f428a0344 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -31,7 +31,6 @@ #include #include #include -#include #include char sun3_reserved_pmeg[SUN3_PMEGS_NUM]; @@ -89,7 +88,7 @@ void __init sun3_init(void) sun3_reserved_pmeg[249] = 1; sun3_reserved_pmeg[252] = 1; sun3_reserved_pmeg[253] = 1; - set_fs(KERNEL_DS); + set_fc(USER_DATA); } /* Without this, Bad Things happen when something calls arch_reset. */ diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c index 7aa879b7c7ff..7ec20817c0c9 100644 --- a/arch/m68k/sun3/mmu_emu.c +++ b/arch/m68k/sun3/mmu_emu.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -191,14 +190,13 @@ void __init mmu_emu_init(unsigned long bootmem_end) for(seg = 0; seg < PAGE_OFFSET; seg += SUN3_PMEG_SIZE) sun3_put_segmap(seg, SUN3_INVALID_PMEG); - set_fs(MAKE_MM_SEG(3)); + set_fc(3); for(seg = 0; seg < 0x10000000; seg += SUN3_PMEG_SIZE) { i = sun3_get_segmap(seg); for(j = 1; j < CONTEXTS_NUM; j++) (*(romvec->pv_setctxt))(j, (void *)seg, i); } - set_fs(KERNEL_DS); - + set_fc(USER_DATA); } /* erase the mappings for a dead context. Uses the pg_dir for hints diff --git a/arch/m68k/sun3/sun3ints.c b/arch/m68k/sun3/sun3ints.c index 41ae422119d3..36cc280a4505 100644 --- a/arch/m68k/sun3/sun3ints.c +++ b/arch/m68k/sun3/sun3ints.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/m68k/sun3x/prom.c b/arch/m68k/sun3x/prom.c index 74d2fe57524b..64c23bfaa90c 100644 --- a/arch/m68k/sun3x/prom.c +++ b/arch/m68k/sun3x/prom.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 0af88622c619..cb6d22439f71 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -662,6 +662,11 @@ static void build_epilogue(struct jit_ctx *ctx) ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative : func) : \ func##_positive) +static bool is_bad_offset(int b_off) +{ + return b_off > 0x1ffff || b_off < -0x20000; +} + static int build_body(struct jit_ctx *ctx) { const struct bpf_prog *prog = ctx->skf; @@ -728,7 +733,10 @@ load_common: /* Load return register on DS for failures */ emit_reg_move(r_ret, r_zero, ctx); /* Return with error */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); break; case BPF_LD | BPF_W | BPF_IND: @@ -775,8 +783,10 @@ load_ind: emit_jalr(MIPS_R_RA, r_s0, ctx); emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */ /* Check the error value */ - emit_bcond(MIPS_COND_NE, r_ret, 0, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_NE, r_ret, 0, b_off, ctx); emit_reg_move(r_ret, r_zero, ctx); /* We are good */ /* X <- P[1:K] & 0xf */ @@ -855,8 +865,10 @@ load_ind: /* A /= X */ ctx->flags |= SEEN_X | SEEN_A; /* Check if r_X is zero */ - emit_bcond(MIPS_COND_EQ, r_X, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx); emit_load_imm(r_ret, 0, ctx); /* delay slot */ emit_div(r_A, r_X, ctx); break; @@ -864,8 +876,10 @@ load_ind: /* A %= X */ ctx->flags |= SEEN_X | SEEN_A; /* Check if r_X is zero */ - emit_bcond(MIPS_COND_EQ, r_X, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx); emit_load_imm(r_ret, 0, ctx); /* delay slot */ emit_mod(r_A, r_X, ctx); break; @@ -926,7 +940,10 @@ load_ind: break; case BPF_JMP | BPF_JA: /* pc += K */ - emit_b(b_imm(i + k + 1, ctx), ctx); + b_off = b_imm(i + k + 1, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); break; case BPF_JMP | BPF_JEQ | BPF_K: @@ -1056,12 +1073,16 @@ jmp_cmp: break; case BPF_RET | BPF_A: ctx->flags |= SEEN_A; - if (i != prog->len - 1) + if (i != prog->len - 1) { /* * If this is not the last instruction * then jump to the epilogue */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); + } emit_reg_move(r_ret, r_A, ctx); /* delay slot */ break; case BPF_RET | BPF_K: @@ -1075,7 +1096,10 @@ jmp_cmp: * If this is not the last instruction * then jump to the epilogue */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); } break; @@ -1133,8 +1157,10 @@ jmp_cmp: /* Load *dev pointer */ emit_load_ptr(r_s0, r_skb, off, ctx); /* error (0) in the delay slot */ - emit_bcond(MIPS_COND_EQ, r_s0, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_s0, r_zero, b_off, ctx); emit_reg_move(r_ret, r_zero, ctx); if (code == (BPF_ANC | SKF_AD_IFINDEX)) { BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); @@ -1244,7 +1270,10 @@ void bpf_jit_compile(struct bpf_prog *fp) /* Generate the actual JIT code */ build_prologue(&ctx); - build_body(&ctx); + if (build_body(&ctx)) { + module_memfree(ctx.target); + goto out; + } build_epilogue(&ctx); /* Update the icache */ diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug index a8bc06e96ef5..ca1beb87f987 100644 --- a/arch/nios2/Kconfig.debug +++ b/arch/nios2/Kconfig.debug @@ -3,9 +3,10 @@ config EARLY_PRINTK bool "Activate early kernel debugging" default y + depends on TTY select SERIAL_CORE_CONSOLE help - Enable early printk on console + Enable early printk on console. This is useful for kernel debugging when your machine crashes very early before the console code is initialized. You should normally say N here, unless you want to debug such a crash. diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index cf8d687a2644..40bc8fb75e0b 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -149,8 +149,6 @@ static void __init find_limits(unsigned long *min, unsigned long *max_low, void __init setup_arch(char **cmdline_p) { - int dram_start; - console_verbose(); memory_start = memblock_start_of_DRAM(); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 16256e17a544..10722455fd02 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -419,13 +419,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) static void __set_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT); - set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __unset_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT); - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 752a0ffab9bf..6a6dd5e1daf6 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4066,7 +4066,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) kvm_s390_patch_guest_per_regs(vcpu); } - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); vcpu->arch.sie_block->icptcode = 0; cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index ecd741ee3276..52bc8fbaa60a 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -79,7 +79,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) static inline int is_vcpu_idle(struct kvm_vcpu *vcpu) { - return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + return test_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static inline int kvm_is_ucontrol(struct kvm *kvm) diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index fa2c3f50aecb..18d2f5199194 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -367,10 +367,11 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8) * %rdx: src (1..8 blocks) * %rcx: num blocks (1..8) */ - FRAME_BEGIN - cmpq $5, %rcx; jb sm4_aesni_avx_crypt4; + + FRAME_BEGIN + vmovdqu (0 * 16)(%rdx), RA0; vmovdqu (1 * 16)(%rdx), RA1; vmovdqu (2 * 16)(%rdx), RA2; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..6dfa8ddaa60f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2465,6 +2465,7 @@ static int x86_pmu_event_init(struct perf_event *event) if (err) { if (event->destroy) event->destroy(event); + event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..9a044438072b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -263,6 +263,7 @@ static struct event_constraint intel_icl_event_constraints[] = { INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT(0xef, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), EVENT_CONSTRAINT_END }; diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 87bd6025d91d..6a5f3acf2b33 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -46,7 +46,7 @@ struct kvm_page_track_notifier_node { struct kvm_page_track_notifier_node *node); }; -void kvm_page_track_init(struct kvm *kvm); +int kvm_page_track_init(struct kvm *kvm); void kvm_page_track_cleanup(struct kvm *kvm); void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index eceea9299097..6c5765192102 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -2,6 +2,20 @@ #ifndef _ASM_X86_KVM_CLOCK_H #define _ASM_X86_KVM_CLOCK_H +#include + extern struct clocksource kvm_clock; +DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} + #endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index ad273e5861c1..73c74b961d0f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); static struct pvclock_vsyscall_time_info hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); static struct pvclock_wall_clock wall_clock __bss_decrypted; -static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static struct pvclock_vsyscall_time_info *hvclock_mem; - -static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) -{ - return &this_cpu_read(hv_clock_per_cpu)->pvti; -} - -static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) -{ - return this_cpu_read(hv_clock_per_cpu); -} +DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu); /* * The wallclock is the time of day when we booted. Since then, some time may diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index fe03bd978761..751aa85a3001 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( for (i = 0; i < nent; i++) { e = &entries[i]; - if (e->function == function && (e->index == index || - !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + if (e->function == function && + (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)) return e; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2837110e66ed..9a144ca8e146 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -435,7 +435,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); __FOP_RET(#op) asm(".pushsection .fixup, \"ax\"\n" - ".global kvm_fastop_exception \n" "kvm_fastop_exception: xor %esi, %esi; ret\n" ".popsection"); @@ -4206,7 +4205,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt) u64 cr4 = ctxt->ops->get_cr(ctxt, 4); if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt)) - return emulate_ud(ctxt); + return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 232a86a6faaf..d5124b520f76 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_init(&hv_vcpu->stimer[i], i); - hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); + hv_vcpu->vp_index = vcpu->vcpu_idx; return 0; } @@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); - int vcpu_idx = kvm_vcpu_get_idx(vcpu); u32 new_vp_index = (u32)data; if (!host || new_vp_index >= KVM_MAX_VCPUS) @@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) * VP index is changing, adjust num_mismatched_vp_indexes if * it now matches or no longer matches vcpu_idx. */ - if (hv_vcpu->vp_index == vcpu_idx) + if (hv_vcpu->vp_index == vcpu->vcpu_idx) atomic_inc(&hv->num_mismatched_vp_indexes); - else if (new_vp_index == vcpu_idx) + else if (new_vp_index == vcpu->vcpu_idx) atomic_dec(&hv->num_mismatched_vp_indexes); hv_vcpu->vp_index = new_vp_index; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 730da8537d05..ed1c4e546d04 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu); + return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx; } int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index ff005fe738a4..8c065da73f8e 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -319,8 +319,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) unsigned index; bool mask_before, mask_after; union kvm_ioapic_redirect_entry *e; - unsigned long vcpu_bitmap; int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; + DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS); switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -384,9 +384,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) irq.shorthand = APIC_DEST_NOSHORT; irq.dest_id = e->fields.dest_id; irq.msi_redir_hint = false; - bitmap_zero(&vcpu_bitmap, 16); + bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); if (old_dest_mode != e->fields.dest_mode || old_dest_id != e->fields.dest_id) { /* @@ -399,10 +399,10 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) kvm_lapic_irq_dest_mode( !!e->fields.dest_mode); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); } kvm_make_scan_ioapic_request_mask(ioapic->kvm, - &vcpu_bitmap); + vcpu_bitmap); } else { kvm_make_scan_ioapic_request(ioapic->kvm); } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2d7e61122af8..1a64ba5b9437 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2027,8 +2027,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) } while (!sp->unsync_children); } -static void mmu_sync_children(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *parent) +static int mmu_sync_children(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *parent, bool can_yield) { int i; struct kvm_mmu_page *sp; @@ -2055,12 +2055,18 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + if (!can_yield) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + return -EINTR; + } + cond_resched_rwlock_write(&vcpu->kvm->mmu_lock); flush = false; } } kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + return 0; } static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) @@ -2146,9 +2152,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (sp->unsync_children) - kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - __clear_sp_write_flooding_count(sp); trace_get_page: @@ -3684,7 +3687,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); write_unlock(&vcpu->kvm->mmu_lock); @@ -3700,7 +3703,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) if (IS_VALID_PAE_ROOT(root)) { root &= PT64_BASE_ADDR_MASK; sp = to_shadow_page(root); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); } } diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 269f11f92fd0..21427e84a82e 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -164,13 +164,13 @@ void kvm_page_track_cleanup(struct kvm *kvm) cleanup_srcu_struct(&head->track_srcu); } -void kvm_page_track_init(struct kvm *kvm) +int kvm_page_track_init(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; head = &kvm->arch.track_notifier_head; - init_srcu_struct(&head->track_srcu); INIT_HLIST_HEAD(&head->track_notifier_list); + return init_srcu_struct(&head->track_srcu); } /* diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 7d03e9b7ccfa..913d52a7923e 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -707,8 +707,27 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; access = gw->pt_access[it.level - 2]; - sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, - false, access); + sp = kvm_mmu_get_page(vcpu, table_gfn, addr, + it.level-1, false, access); + /* + * We must synchronize the pagetable before linking it + * because the guest doesn't need to flush tlb when + * the gpte is changed from non-present to present. + * Otherwise, the guest may use the wrong mapping. + * + * For PG_LEVEL_4K, kvm_mmu_get_page() has already + * synchronized it transiently via kvm_sync_page(). + * + * For higher level pagetable, we synchronize it via + * the slower mmu_sync_children(). If it needs to + * break, some progress has been made; return + * RET_PF_RETRY and retry on the next #PF. + * KVM_REQ_MMU_SYNC is not necessary but it + * expedites the process. + */ + if (sp->unsync_children && + mmu_sync_children(vcpu, sp, false)) + return RET_PF_RETRY; } /* @@ -1047,14 +1066,6 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, * Using the cached information from sp->gfns is safe because: * - The spte has a reference to the struct page, so the pfn for a given gfn * can't change unless all sptes pointing to it are nuked first. - * - * Note: - * We should flush all tlbs if spte is dropped even though guest is - * responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page - * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't - * used by guest then tlbs are not flushed, so guest is allowed to access the - * freed pages. - * And we increase kvm->tlbs_dirty to delay tlbs flush in this case. */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -1107,13 +1118,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return 0; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - /* - * Update spte before increasing tlbs_dirty to make - * sure no tlb flush is lost after spte is zapped; see - * the comments in kvm_flush_remote_tlbs(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; continue; } @@ -1128,12 +1133,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (gfn != sp->gfns[i]) { drop_spte(vcpu->kvm, &sp->spt[i]); - /* - * The same as above where we are doing - * prefetch_invalid_gpte(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; continue; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 2545d0c61985..510b833cbd39 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -545,7 +545,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits); - svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; svm->vmcb->control.int_state = svm->nested.ctl.int_state; svm->vmcb->control.event_inj = svm->nested.ctl.event_inj; @@ -579,7 +578,7 @@ static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, - struct vmcb *vmcb12) + struct vmcb *vmcb12, bool from_vmrun) { struct vcpu_svm *svm = to_svm(vcpu); int ret; @@ -609,13 +608,16 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, - nested_npt_enabled(svm), true); + nested_npt_enabled(svm), from_vmrun); if (ret) return ret; if (!npt_enabled) vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested; + if (!from_vmrun) + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + svm_set_gif(svm, true); return 0; @@ -681,7 +683,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) svm->nested.nested_run_pending = 1; - if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12)) + if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true)) goto out_exit_err; if (nested_svm_vmrun_msrpm(svm)) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 75e0b21ad07c..c36b5fe4c27c 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -595,43 +595,50 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) return 0; } +static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, + int *error) +{ + struct sev_data_launch_update_vmsa vmsa; + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + /* Perform some pre-encryption checks against the VMSA */ + ret = sev_es_sync_vmsa(svm); + if (ret) + return ret; + + /* + * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of + * the VMSA memory content (i.e it will write the same memory region + * with the guest's key), so invalidate it first. + */ + clflush_cache_range(svm->vmsa, PAGE_SIZE); + + vmsa.reserved = 0; + vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; + vmsa.address = __sme_pa(svm->vmsa); + vmsa.len = PAGE_SIZE; + return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); +} + static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_launch_update_vmsa vmsa; struct kvm_vcpu *vcpu; int i, ret; if (!sev_es_guest(kvm)) return -ENOTTY; - vmsa.reserved = 0; - kvm_for_each_vcpu(i, vcpu, kvm) { - struct vcpu_svm *svm = to_svm(vcpu); - - /* Perform some pre-encryption checks against the VMSA */ - ret = sev_es_sync_vmsa(svm); + ret = mutex_lock_killable(&vcpu->mutex); if (ret) return ret; - /* - * The LAUNCH_UPDATE_VMSA command will perform in-place - * encryption of the VMSA memory content (i.e it will write - * the same memory region with the guest's key), so invalidate - * it first. - */ - clflush_cache_range(svm->vmsa, PAGE_SIZE); + ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error); - vmsa.handle = sev->handle; - vmsa.address = __sme_pa(svm->vmsa); - vmsa.len = PAGE_SIZE; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, - &argp->error); + mutex_unlock(&vcpu->mutex); if (ret) return ret; - - svm->vcpu.arch.guest_state_protected = true; } return 0; @@ -1397,8 +1404,10 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start.handle, error); - if (ret) + if (ret) { + sev_decommission(start.handle); goto e_free_session; + } params.handle = start.handle; if (copy_to_user((void __user *)(uintptr_t)argp->data, @@ -1464,7 +1473,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, - PAGE_SIZE, &n, 0); + PAGE_SIZE, &n, 1); if (IS_ERR(guest_page)) { ret = PTR_ERR(guest_page); goto e_free_trans; @@ -1501,6 +1510,20 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); } +static bool cmd_allowed_from_miror(u32 cmd_id) +{ + /* + * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES + * active mirror VMs. Also allow the debugging and status commands. + */ + if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA || + cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT || + cmd_id == KVM_SEV_DBG_ENCRYPT) + return true; + + return false; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1517,8 +1540,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) mutex_lock(&kvm->lock); - /* enc_context_owner handles all memory enc operations */ - if (is_mirroring_enc_context(kvm)) { + /* Only the enc_context_owner handles some memory enc operations. */ + if (is_mirroring_enc_context(kvm) && + !cmd_allowed_from_miror(sev_cmd.id)) { r = -EINVAL; goto out; } @@ -1715,8 +1739,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info *mirror_sev; - unsigned int asid; + struct kvm_sev_info source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); @@ -1739,7 +1762,8 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) goto e_source_unlock; } - asid = to_kvm_svm(source_kvm)->sev_info.asid; + memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, + sizeof(source_sev)); /* * The mirror kvm holds an enc_context_owner ref so its asid can't @@ -1759,8 +1783,16 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; - mirror_sev->asid = asid; mirror_sev->active = true; + mirror_sev->asid = source_sev.asid; + mirror_sev->fd = source_sev.fd; + mirror_sev->es_active = source_sev.es_active; + mirror_sev->handle = source_sev.handle; + /* + * Do not copy ap_jump_table. Since the mirror does not share the same + * KVM contexts as the original, and they may have different + * memory-views. + */ mutex_unlock(&kvm->lock); return 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 05e8d4d27969..989685098b3e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1566,6 +1566,8 @@ static void svm_clear_vintr(struct vcpu_svm *svm) svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & V_IRQ_INJECTION_BITS_MASK; + + svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; } vmcb_mark_dirty(svm->vmcb, VMCB_INTR); @@ -2222,6 +2224,10 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (error_code) goto reinject; + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + /* Decode the instruction for usage later */ if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) goto reinject; @@ -4285,43 +4291,44 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) struct kvm_host_map map_save; int ret; - if (is_guest_mode(vcpu)) { - /* FED8h - SVM Guest */ - put_smstate(u64, smstate, 0x7ed8, 1); - /* FEE0h - SVM Guest VMCB Physical Address */ - put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); + if (!is_guest_mode(vcpu)) + return 0; - svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + /* FED8h - SVM Guest */ + put_smstate(u64, smstate, 0x7ed8, 1); + /* FEE0h - SVM Guest VMCB Physical Address */ + put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); - ret = nested_svm_vmexit(svm); - if (ret) - return ret; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; - /* - * KVM uses VMCB01 to store L1 host state while L2 runs but - * VMCB01 is going to be used during SMM and thus the state will - * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save - * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the - * format of the area is identical to guest save area offsetted - * by 0x400 (matches the offset of 'struct vmcb_save_area' - * within 'struct vmcb'). Note: HSAVE area may also be used by - * L1 hypervisor to save additional host context (e.g. KVM does - * that, see svm_prepare_guest_switch()) which must be - * preserved. - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + ret = nested_svm_vmexit(svm); + if (ret) + return ret; - BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_guest_switch()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; - svm_copy_vmrun_state(map_save.hva + 0x400, - &svm->vmcb01.ptr->save); + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); - kvm_vcpu_unmap(vcpu, &map_save, true); - } + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); return 0; } @@ -4329,50 +4336,54 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map, map_save; - int ret = 0; + u64 saved_efer, vmcb12_gpa; + struct vmcb *vmcb12; + int ret; - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { - u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); - u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); - u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); - struct vmcb *vmcb12; + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 0; - if (guest) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - return 1; + /* Non-zero if SMI arrived while vCPU was in guest mode. */ + if (!GET_SMSTATE(u64, smstate, 0x7ed8)) + return 0; - if (!(saved_efer & EFER_SVME)) - return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; - if (kvm_vcpu_map(vcpu, - gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) - return 1; + saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); + if (!(saved_efer & EFER_SVME)) + return 1; - if (svm_allocate_nested(svm)) - return 1; + vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) + return 1; - vmcb12 = map.hva; + ret = 1; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL) + goto unmap_map; - nested_load_control_from_vmcb12(svm, &vmcb12->control); + if (svm_allocate_nested(svm)) + goto unmap_save; - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); - kvm_vcpu_unmap(vcpu, &map, true); + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ - /* - * Restore L1 host state from L1 HSAVE area as VMCB01 was - * used during SMM (see svm_enter_smm()) - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400); - svm_copy_vmrun_state(&svm->vmcb01.ptr->save, - map_save.hva + 0x400); + /* + * Enter the nested guest now + */ - kvm_vcpu_unmap(vcpu, &map_save, true); - } - } + vmcb12 = map.hva; + nested_load_control_from_vmcb12(svm, &vmcb12->control); + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); +unmap_save: + kvm_vcpu_unmap(vcpu, &map_save, true); +unmap_map: + kvm_vcpu_unmap(vcpu, &map, true); return ret; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 524d943f3efc..128a54b1fbf1 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -459,7 +459,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } -int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12); +int enter_svm_guest_mode(struct kvm_vcpu *vcpu, + u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 0dab1b7b529f..ba6f99f584ac 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -353,14 +353,20 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; + break; + case MSR_IA32_VMX_PINBASED_CTLS: + ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; + break; + case MSR_IA32_VMX_VMFUNC: + ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC; break; } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ccb03d69546c..eedcebf58004 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2583,8 +2583,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Guest state is invalid and unrestricted guest is disabled, * which means L1 attempted VMEntry to L2 with invalid state. * Fail the VMEntry. + * + * However when force loading the guest state (SMM exit or + * loading nested state after migration, it is possible to + * have invalid guest state now, which will be later fixed by + * restoring L2 register state */ - if (CC(!vmx_guest_state_valid(vcpu))) { + if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -4351,6 +4356,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); + + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) @@ -4899,14 +4906,7 @@ out_vmcs02: return -ENOMEM; } -/* - * Emulate the VMXON instruction. - * Currently, we just remember that VMX is active, and do not save or even - * inspect the argument to VMXON (the so-called "VMXON pointer") because we - * do not currently need to store anything in that guest-allocated memory - * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their - * argument is different from the VMXON pointer (which the spec says they do). - */ +/* Emulate the VMXON instruction. */ static int handle_vmon(struct kvm_vcpu *vcpu) { int ret; @@ -5903,6 +5903,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ return true; + case EXIT_REASON_BUS_LOCK: + /* + * At present, bus lock VM exit is never exposed to L1. + * Handle L2's bus locks in L0 directly. + */ + return true; default: break; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0c2c0d5ae873..116b08904ac3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1323,7 +1323,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) vmx_prepare_switch_to_host(to_vmx(vcpu)); } -static bool emulation_required(struct kvm_vcpu *vcpu) +bool vmx_emulation_required(struct kvm_vcpu *vcpu) { return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu); } @@ -1367,7 +1367,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) @@ -1837,10 +1837,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &msr_info->data)) return 1; /* - * Enlightened VMCS v1 doesn't have certain fields, but buggy - * Hyper-V versions are still trying to use corresponding - * features when they are exposed. Filter out the essential - * minimum. + * Enlightened VMCS v1 doesn't have certain VMCS fields but + * instead of just ignoring the features, different Hyper-V + * versions are either trying to use them and fail or do some + * sanity checking and refuse to boot. Filter all unsupported + * features out. */ if (!msr_info->host_initiated && vmx->nested.enlightened_vmcs_enabled) @@ -3077,7 +3078,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } static int vmx_get_max_tdp_level(void) @@ -3330,7 +3331,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int { __vmx_set_segment(vcpu, var, seg); - to_vmx(vcpu)->emulation_required = emulation_required(vcpu); + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -6621,10 +6622,24 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->entry_time = ktime_get(); - /* Don't enter VMX if guest state is invalid, let the exit handler - start emulation until we arrive back to a valid state */ - if (vmx->emulation_required) + /* + * Don't enter VMX if guest state is invalid, let the exit handler + * start emulation until we arrive back to a valid state. Synthesize a + * consistency check VM-Exit due to invalid guest state and bail. + */ + if (unlikely(vmx->emulation_required)) { + + /* We don't emulate invalid state of a nested guest */ + vmx->fail = is_guest_mode(vcpu); + + vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; + vmx->exit_reason.failed_vmentry = 1; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + vmx->exit_qualification = ENTRY_FAIL_DEFAULT; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + vmx->exit_intr_info = 0; return EXIT_FASTPATH_NONE; + } trace_kvm_entry(vcpu); @@ -6833,7 +6848,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) - vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4858c5fd95f2..592217fd7d92 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -248,12 +248,8 @@ struct vcpu_vmx { * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to * be loaded into hardware if those conditions aren't met. - * nr_active_uret_msrs tracks the number of MSRs that need to be loaded - * into hardware when running the guest. guest_uret_msrs[] is resorted - * whenever the number of "active" uret MSRs is modified. */ struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; - int nr_active_uret_msrs; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; @@ -359,6 +355,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); +bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 28ef14155726..aabd3a2ec1bc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1332,6 +1332,13 @@ static const u32 msrs_to_save_all[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; @@ -2969,7 +2976,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (v == kvm_get_vcpu(v->kvm, 0)) + if (!v->vcpu_idx) kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } @@ -7658,6 +7665,13 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) /* Process a latched INIT or SMI, if any. */ kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, + * on SMM exit we still need to reload them from + * guest memory + */ + vcpu->arch.pdptrs_from_userspace = false; } kvm_mmu_reset_context(vcpu); @@ -10652,6 +10666,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) int r; vcpu->arch.last_vmentry_cpu = -1; + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -10893,6 +10909,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); + vcpu->arch.cr3 = 0; + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + /* * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions * of Intel's SDM list CD/NW as being set on INIT, but they contradict @@ -11139,9 +11158,15 @@ void kvm_arch_free_vm(struct kvm *kvm) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { + int ret; + if (type) return -EINVAL; + ret = kvm_page_track_init(kvm); + if (ret) + return ret; + INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); @@ -11174,7 +11199,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); - kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); kvm_xen_init_vm(kvm); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0fe6aacef3db..9ea57389c554 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1341,9 +1341,10 @@ st: if (is_imm8(insn->off)) if (insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH)) { - u8 *branch_target; bool is64 = BPF_SIZE(insn->code) == BPF_DW; u32 real_src_reg = src_reg; + u32 real_dst_reg = dst_reg; + u8 *branch_target; /* * Can't be implemented with a single x86 insn. @@ -1354,11 +1355,13 @@ st: if (is_imm8(insn->off)) emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0); if (src_reg == BPF_REG_0) real_src_reg = BPF_REG_AX; + if (dst_reg == BPF_REG_0) + real_dst_reg = BPF_REG_AX; branch_target = prog; /* Load old value */ emit_ldx(&prog, BPF_SIZE(insn->code), - BPF_REG_0, dst_reg, insn->off); + BPF_REG_0, real_dst_reg, insn->off); /* * Perform the (commutative) operation locally, * put the result in the AUX_REG. @@ -1369,7 +1372,8 @@ st: if (is_imm8(insn->off)) add_2reg(0xC0, AUX_REG, real_src_reg)); /* Attempt to swap in new value */ err = emit_atomic(&prog, BPF_CMPXCHG, - dst_reg, AUX_REG, insn->off, + real_dst_reg, AUX_REG, + insn->off, BPF_SIZE(insn->code)); if (WARN_ON(err)) return err; @@ -1383,11 +1387,10 @@ st: if (is_imm8(insn->off)) /* Restore R0 after clobbering RAX */ emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX); break; - } err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, - insn->off, BPF_SIZE(insn->code)); + insn->off, BPF_SIZE(insn->code)); if (err) return err; break; @@ -1744,7 +1747,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, - struct bpf_prog *p, int stack_size, bool mod_ret) + struct bpf_prog *p, int stack_size, bool save_ret) { u8 *prog = *pprog; u8 *jmp_insn; @@ -1777,11 +1780,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (emit_call(&prog, p->bpf_func, prog)) return -EINVAL; - /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + /* + * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return * of the previous call which is then passed on the stack to * the next BPF program. + * + * BPF_TRAMP_FENTRY trampoline may need to return the return + * value of BPF_PROG_TYPE_STRUCT_OPS prog. */ - if (mod_ret) + if (save_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); /* replace 2 nops with JE insn, since jmp target is known */ @@ -1828,13 +1835,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) } static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, - struct bpf_tramp_progs *tp, int stack_size) + struct bpf_tramp_progs *tp, int stack_size, + bool save_ret) { int i; u8 *prog = *pprog; for (i = 0; i < tp->nr_progs; i++) { - if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, + save_ret)) return -EINVAL; } *pprog = prog; @@ -1877,6 +1886,23 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, return 0; } +static bool is_valid_bpf_tramp_flags(unsigned int flags) +{ + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return false; + + /* + * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, + * and it must be used alone. + */ + if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) && + (flags & ~BPF_TRAMP_F_RET_FENTRY_RET)) + return false; + + return true; +} + /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -1949,17 +1975,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; u8 **branches = NULL; u8 *prog; + bool save_ret; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ if (nr_args > 6) return -ENOTSUPP; - if ((flags & BPF_TRAMP_F_RESTORE_REGS) && - (flags & BPF_TRAMP_F_SKIP_FRAME)) + if (!is_valid_bpf_tramp_flags(flags)) return -EINVAL; - if (flags & BPF_TRAMP_F_CALL_ORIG) - stack_size += 8; /* room for return value of orig_call */ + /* room for return value of orig_call or fentry prog */ + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) + stack_size += 8; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2005,7 +2033,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fentry->nr_progs) - if (invoke_bpf(m, &prog, fentry, stack_size)) + if (invoke_bpf(m, &prog, fentry, stack_size, + flags & BPF_TRAMP_F_RET_FENTRY_RET)) return -EINVAL; if (fmod_ret->nr_progs) { @@ -2052,7 +2081,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fexit->nr_progs) - if (invoke_bpf(m, &prog, fexit, stack_size)) { + if (invoke_bpf(m, &prog, fexit, stack_size, false)) { ret = -EINVAL; goto cleanup; } @@ -2072,9 +2101,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - /* restore original return value back into RAX */ - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); } + /* restore return value of orig_call or fentry prog back into RAX */ + if (save_ret) + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); EMIT1(0x5B); /* pop rbx */ EMIT1(0xC9); /* leave */ diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index dd13c2bbc29c..480e1a134859 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2662,15 +2662,6 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) * are likely to increase the throughput. */ bfqq->new_bfqq = new_bfqq; - /* - * The above assignment schedules the following redirections: - * each time some I/O for bfqq arrives, the process that - * generated that I/O is disassociated from bfqq and - * associated with new_bfqq. Here we increases new_bfqq->ref - * in advance, adding the number of processes that are - * expected to be associated with new_bfqq as they happen to - * issue I/O. - */ new_bfqq->ref += process_refs; return new_bfqq; } @@ -2733,10 +2724,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, { struct bfq_queue *in_service_bfqq, *new_bfqq; - /* if a merge has already been setup, then proceed with that first */ - if (bfqq->new_bfqq) - return bfqq->new_bfqq; - /* * Check delayed stable merge for rotational or non-queueing * devs. For this branch to be executed, bfqq must not be @@ -2838,6 +2825,9 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (bfq_too_late_for_merging(bfqq)) return NULL; + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) return NULL; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index a3ef6cce644c..7dd80acf92c7 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3007,6 +3007,18 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, ndr_desc->target_node = NUMA_NO_NODE; } + /* Fallback to address based numa information if node lookup failed */ + if (ndr_desc->numa_node == NUMA_NO_NODE) { + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address); + dev_info(acpi_desc->dev, "changing numa node from %d to %d for nfit region [%pa-%pa]", + NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end); + } + if (ndr_desc->target_node == NUMA_NO_NODE) { + ndr_desc->target_node = phys_to_target_node(spa->address); + dev_info(acpi_desc->dev, "changing target node from %d to %d for nfit region [%pa-%pa]", + NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end); + } + /* * Persistence domain bits are hierarchical, if * ACPI_NFIT_CAPABILITY_CACHE_FLUSH is set then diff --git a/drivers/base/core.c b/drivers/base/core.c index e65dd803a453..15986cc2fe5e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -95,12 +95,29 @@ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup) list_add(&link->s_hook, &sup->consumers); list_add(&link->c_hook, &con->suppliers); + pr_debug("%pfwP Linked as a fwnode consumer to %pfwP\n", + con, sup); out: mutex_unlock(&fwnode_link_lock); return ret; } +/** + * __fwnode_link_del - Delete a link between two fwnode_handles. + * @link: the fwnode_link to be deleted + * + * The fwnode_link_lock needs to be held when this function is called. + */ +static void __fwnode_link_del(struct fwnode_link *link) +{ + pr_debug("%pfwP Dropping the fwnode link to %pfwP\n", + link->consumer, link->supplier); + list_del(&link->s_hook); + list_del(&link->c_hook); + kfree(link); +} + /** * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle. * @fwnode: fwnode whose supplier links need to be deleted @@ -112,11 +129,8 @@ static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode) struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); - list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) { - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); - } + list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) + __fwnode_link_del(link); mutex_unlock(&fwnode_link_lock); } @@ -131,11 +145,8 @@ static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode) struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); - list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) { - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); - } + list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) + __fwnode_link_del(link); mutex_unlock(&fwnode_link_lock); } @@ -975,6 +986,7 @@ int device_links_check_suppliers(struct device *dev) { struct device_link *link; int ret = 0; + struct fwnode_handle *sup_fw; /* * Device waiting for supplier to become available is not allowed to @@ -983,10 +995,11 @@ int device_links_check_suppliers(struct device *dev) mutex_lock(&fwnode_link_lock); if (dev->fwnode && !list_empty(&dev->fwnode->suppliers) && !fw_devlink_is_permissive()) { - dev_dbg(dev, "probe deferral - wait for supplier %pfwP\n", - list_first_entry(&dev->fwnode->suppliers, - struct fwnode_link, - c_hook)->supplier); + sup_fw = list_first_entry(&dev->fwnode->suppliers, + struct fwnode_link, + c_hook)->supplier; + dev_err_probe(dev, -EPROBE_DEFER, "wait for supplier %pfwP\n", + sup_fw); mutex_unlock(&fwnode_link_lock); return -EPROBE_DEFER; } @@ -1001,8 +1014,9 @@ int device_links_check_suppliers(struct device *dev) if (link->status != DL_STATE_AVAILABLE && !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) { device_links_missing_supplier(dev); - dev_dbg(dev, "probe deferral - supplier %s not ready\n", - dev_name(link->supplier)); + dev_err_probe(dev, -EPROBE_DEFER, + "supplier %s not ready\n", + dev_name(link->supplier)); ret = -EPROBE_DEFER; break; } @@ -1722,6 +1736,25 @@ static int fw_devlink_create_devlink(struct device *con, struct device *sup_dev; int ret = 0; + /* + * In some cases, a device P might also be a supplier to its child node + * C. However, this would defer the probe of C until the probe of P + * completes successfully. This is perfectly fine in the device driver + * model. device_add() doesn't guarantee probe completion of the device + * by the time it returns. + * + * However, there are a few drivers that assume C will finish probing + * as soon as it's added and before P finishes probing. So, we provide + * a flag to let fw_devlink know not to delay the probe of C until the + * probe of P completes successfully. + * + * When such a flag is set, we can't create device links where P is the + * supplier of C as that would delay the probe of C. + */ + if (sup_handle->flags & FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD && + fwnode_is_ancestor_of(sup_handle, con->fwnode)) + return -EINVAL; + sup_dev = get_dev_from_fwnode(sup_handle); if (sup_dev) { /* @@ -1772,14 +1805,21 @@ static int fw_devlink_create_devlink(struct device *con, * be broken by applying logic. Check for these types of cycles and * break them so that devices in the cycle probe properly. * - * If the supplier's parent is dependent on the consumer, then - * the consumer-supplier dependency is a false dependency. So, - * treat it as an invalid link. + * If the supplier's parent is dependent on the consumer, then the + * consumer and supplier have a cyclic dependency. Since fw_devlink + * can't tell which of the inferred dependencies are incorrect, don't + * enforce probe ordering between any of the devices in this cyclic + * dependency. Do this by relaxing all the fw_devlink device links in + * this cycle and by treating the fwnode link between the consumer and + * the supplier as an invalid dependency. */ sup_dev = fwnode_get_next_parent_dev(sup_handle); if (sup_dev && device_is_dependent(con, sup_dev)) { - dev_dbg(con, "Not linking to %pfwP - False link\n", - sup_handle); + dev_info(con, "Fixing up cyclic dependency with %pfwP (%s)\n", + sup_handle, dev_name(sup_dev)); + device_links_write_lock(); + fw_devlink_relax_cycle(con, sup_dev); + device_links_write_unlock(); ret = -EINVAL; } else { /* @@ -1858,9 +1898,7 @@ static void __fw_devlink_link_to_consumers(struct device *dev) if (!own_link || ret == -EAGAIN) continue; - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); + __fwnode_link_del(link); } } @@ -1912,9 +1950,7 @@ static void __fw_devlink_link_to_suppliers(struct device *dev, if (!own_link || ret == -EAGAIN) continue; - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); + __fwnode_link_del(link); /* If no device link was created, nothing more to do. */ if (ret) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5170a630778d..1183f7872b71 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -97,13 +97,18 @@ struct nbd_config { atomic_t recv_threads; wait_queue_head_t recv_wq; - loff_t blksize; + unsigned int blksize_bits; loff_t bytesize; #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbg_dir; #endif }; +static inline unsigned int nbd_blksize(struct nbd_config *config) +{ + return 1u << config->blksize_bits; +} + struct nbd_device { struct blk_mq_tag_set tag_set; @@ -146,7 +151,7 @@ static struct dentry *nbd_dbg_dir; #define NBD_MAGIC 0x68797548 -#define NBD_DEF_BLKSIZE 1024 +#define NBD_DEF_BLKSIZE_BITS 10 static unsigned int nbds_max = 16; static int max_part = 16; @@ -317,12 +322,12 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { if (!blksize) - blksize = NBD_DEF_BLKSIZE; + blksize = 1u << NBD_DEF_BLKSIZE_BITS; if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize)) return -EINVAL; nbd->config->bytesize = bytesize; - nbd->config->blksize = blksize; + nbd->config->blksize_bits = __ffs(blksize); if (!nbd->task_recv) return 0; @@ -1337,7 +1342,7 @@ static int nbd_start_device(struct nbd_device *nbd) args->index = i; queue_work(nbd->recv_workq, &args->work); } - return nbd_set_size(nbd, config->bytesize, config->blksize); + return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev) @@ -1406,11 +1411,11 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, case NBD_SET_BLKSIZE: return nbd_set_size(nbd, config->bytesize, arg); case NBD_SET_SIZE: - return nbd_set_size(nbd, arg, config->blksize); + return nbd_set_size(nbd, arg, nbd_blksize(config)); case NBD_SET_SIZE_BLOCKS: - if (check_mul_overflow((loff_t)arg, config->blksize, &bytesize)) + if (check_shl_overflow(arg, config->blksize_bits, &bytesize)) return -EINVAL; - return nbd_set_size(nbd, bytesize, config->blksize); + return nbd_set_size(nbd, bytesize, nbd_blksize(config)); case NBD_SET_TIMEOUT: nbd_set_cmd_timeout(nbd, arg); return 0; @@ -1476,7 +1481,7 @@ static struct nbd_config *nbd_alloc_config(void) atomic_set(&config->recv_threads, 0); init_waitqueue_head(&config->recv_wq); init_waitqueue_head(&config->conn_wait); - config->blksize = NBD_DEF_BLKSIZE; + config->blksize_bits = NBD_DEF_BLKSIZE_BITS; atomic_set(&config->live_connections, 0); try_module_get(THIS_MODULE); return config; @@ -1604,7 +1609,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd) debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_fops); debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize); debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout); - debugfs_create_u64("blocksize", 0444, dir, &config->blksize); + debugfs_create_u32("blocksize_bits", 0444, dir, &config->blksize_bits); debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_fops); return 0; @@ -1826,7 +1831,7 @@ nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = { static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) { struct nbd_config *config = nbd->config; - u64 bsize = config->blksize; + u64 bsize = nbd_blksize(config); u64 bytes = config->bytesize; if (info->attrs[NBD_ATTR_SIZE_BYTES]) @@ -1835,7 +1840,7 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]); - if (bytes != config->bytesize || bsize != config->blksize) + if (bytes != config->bytesize || bsize != nbd_blksize(config)) return nbd_set_size(nbd, bytes, bsize); return 0; } diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index bb88198c874e..aa4e1a500691 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -778,7 +778,7 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); if (ret) - goto e_ctx; + goto e_aad; if (in_place) { dst = src; @@ -863,7 +863,7 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) op.u.aes.size = 0; ret = cmd_q->ccp->vdata->perform->aes(&op); if (ret) - goto e_dst; + goto e_final_wa; if (aes->action == CCP_AES_ACTION_ENCRYPT) { /* Put the ciphered tag after the ciphertext. */ @@ -873,17 +873,19 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) ret = ccp_init_dm_workarea(&tag, cmd_q, authsize, DMA_BIDIRECTIONAL); if (ret) - goto e_tag; + goto e_final_wa; ret = ccp_set_dm_area(&tag, 0, p_tag, 0, authsize); - if (ret) - goto e_tag; + if (ret) { + ccp_dm_free(&tag); + goto e_final_wa; + } ret = crypto_memneq(tag.address, final_wa.address, authsize) ? -EBADMSG : 0; ccp_dm_free(&tag); } -e_tag: +e_final_wa: ccp_dm_free(&final_wa); e_dst: diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index f5cfc0698799..8ebf369b3ba0 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -468,15 +468,8 @@ static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off) mutex_lock(&chip->i2c_lock); ret = regmap_read(chip->regmap, inreg, ®_val); mutex_unlock(&chip->i2c_lock); - if (ret < 0) { - /* - * NOTE: - * diagnostic already emitted; that's all we should - * do unless gpio_*_value_cansleep() calls become different - * from their nonsleeping siblings (and report faults). - */ - return 0; - } + if (ret < 0) + return ret; return !!(reg_val & bit); } diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 3335bd57761d..ce63cbd14d69 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -689,6 +689,7 @@ static int rockchip_gpio_probe(struct platform_device *pdev) struct device_node *pctlnp = of_get_parent(np); struct pinctrl_dev *pctldev = NULL; struct rockchip_pin_bank *bank = NULL; + struct rockchip_pin_output_deferred *cfg; static int gpio; int id, ret; @@ -716,12 +717,33 @@ static int rockchip_gpio_probe(struct platform_device *pdev) if (ret) return ret; + /* + * Prevent clashes with a deferred output setting + * being added right at this moment. + */ + mutex_lock(&bank->deferred_lock); + ret = rockchip_gpiolib_register(bank); if (ret) { clk_disable_unprepare(bank->clk); + mutex_unlock(&bank->deferred_lock); return ret; } + while (!list_empty(&bank->deferred_output)) { + cfg = list_first_entry(&bank->deferred_output, + struct rockchip_pin_output_deferred, head); + list_del(&cfg->head); + + ret = rockchip_gpio_direction_output(&bank->gpio_chip, cfg->pin, cfg->arg); + if (ret) + dev_warn(dev, "setting output pin %u to %u failed\n", cfg->pin, cfg->arg); + + kfree(cfg); + } + + mutex_unlock(&bank->deferred_lock); + platform_set_drvdata(pdev, bank); dev_info(dev, "probed %pOF\n", np); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 7a7316731911..dc50c05f23fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -837,6 +837,28 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb) return 0; } +/* Mirrors the is_displayable check in radeonsi's gfx6_compute_surface */ +static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb) +{ + u64 micro_tile_mode; + + /* Zero swizzle mode means linear */ + if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0) + return 0; + + micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE); + switch (micro_tile_mode) { + case 0: /* DISPLAY */ + case 3: /* RENDER */ + return 0; + default: + drm_dbg_kms(afb->base.dev, + "Micro tile mode %llu not supported for scanout\n", + micro_tile_mode); + return -EINVAL; + } +} + static void get_block_dimensions(unsigned int block_log2, unsigned int cpp, unsigned int *width, unsigned int *height) { @@ -1103,6 +1125,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *obj) { + struct amdgpu_device *adev = drm_to_adev(dev); int ret, i; /* @@ -1122,6 +1145,14 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev, if (ret) return ret; + if (!dev->mode_config.allow_fb_modifiers) { + drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI, + "GFX9+ requires FB check based on format modifier\n"); + ret = check_tiling_flags_gfx6(rfb); + if (ret) + return ret; + } + if (dev->mode_config.allow_fb_modifiers && !(rfb->base.flags & DRM_MODE_FB_MODIFIERS)) { ret = convert_tiling_flags_to_modifier(rfb); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 603c259b073b..025184a556ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3599,7 +3599,7 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring) /* set static priority for a queue/ring */ gfx_v9_0_mqd_set_priority(ring, mqd); - mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM); + mqd->cp_hqd_quantum = RREG32_SOC15(GC, 0, mmCP_HQD_QUANTUM); /* map_queues packet doesn't need activate the queue, * so only kiq need set this field. diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 41c3a0d70b7c..e47104a1f559 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1098,6 +1098,8 @@ static int gmc_v10_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v10_0_gart_disable(adev); + if (amdgpu_sriov_vf(adev)) { /* full access mode, so don't touch any GMC register */ DRM_DEBUG("For SRIOV client, shouldn't do anything.\n"); @@ -1106,7 +1108,6 @@ static int gmc_v10_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); - gmc_v10_0_gart_disable(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index d90c16a6b2b8..5551359d5dfd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1794,6 +1794,8 @@ static int gmc_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v9_0_gart_disable(adev); + if (amdgpu_sriov_vf(adev)) { /* full access mode, so don't touch any GMC register */ DRM_DEBUG("For SRIOV client, shouldn't do anything.\n"); @@ -1802,7 +1804,6 @@ static int gmc_v9_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); - gmc_v9_0_gart_disable(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 779f5c911e11..e32efcfb0c8b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -868,6 +868,12 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) msleep(1000); } + /* TODO: check whether can submit a doorbell request to raise + * a doorbell fence to exit gfxoff. + */ + if (adev->in_s0ix) + amdgpu_gfx_off_ctrl(adev, false); + sdma_v5_2_soft_reset(adev); /* unhalt the MEs */ sdma_v5_2_enable(adev, true); @@ -876,6 +882,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) /* start the gfx rings and rlc compute queues */ r = sdma_v5_2_gfx_resume(adev); + if (adev->in_s0ix) + amdgpu_gfx_off_ctrl(adev, true); if (r) return r; r = sdma_v5_2_rlc_resume(adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 66c799f5c7cf..1ea31dcc7a8b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1115,6 +1115,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) init_data.asic_id.pci_revision_id = adev->pdev->revision; init_data.asic_id.hw_internal_rev = adev->external_rev_id; + init_data.asic_id.chip_id = adev->pdev->device; init_data.asic_id.vram_width = adev->gmc.vram_width; /* TODO: initialize init_data.asic_id.vram_type here!!!! */ @@ -1719,6 +1720,7 @@ static int dm_late_init(void *handle) linear_lut[i] = 0xFFFF * i / 15; params.set = 0; + params.backlight_ramping_override = false; params.backlight_ramping_start = 0xCCCC; params.backlight_ramping_reduction = 0xCCCCCCCC; params.backlight_lut_array_size = 16; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index f6dbc5a74757..05eaec03d9f7 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1826,14 +1826,13 @@ bool perform_link_training_with_retries( if (panel_mode == DP_PANEL_MODE_EDP) { struct cp_psp *cp_psp = &stream->ctx->cp_psp; - if (cp_psp && cp_psp->funcs.enable_assr) { - if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) { - /* since eDP implies ASSR on, change panel - * mode to disable ASSR - */ - panel_mode = DP_PANEL_MODE_DEFAULT; - } - } + if (cp_psp && cp_psp->funcs.enable_assr) + /* ASSR is bound to fail with unsigned PSP + * verstage used during devlopment phase. + * Report and continue with eDP panel mode to + * perform eDP link training with right settings + */ + cp_psp->funcs.enable_assr(cp_psp->handle, link); } #endif diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 9870c4e6af36..b5001db7a95c 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -793,7 +793,6 @@ static int exynos5433_decon_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct decon_context *ctx; - struct resource *res; int ret; int i; @@ -818,8 +817,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev) ctx->clks[i] = clk; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->addr = devm_ioremap_resource(dev, res); + ctx->addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->addr)) return PTR_ERR(ctx->addr); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index e39fac889edc..8d137857818c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1738,7 +1738,6 @@ static const struct component_ops exynos_dsi_component_ops = { static int exynos_dsi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct exynos_dsi *dsi; int ret, i; @@ -1789,8 +1788,7 @@ static int exynos_dsi_probe(struct platform_device *pdev) } } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dsi->reg_base = devm_ioremap_resource(dev, res); + dsi->reg_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(dsi->reg_base)) return PTR_ERR(dsi->reg_base); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index a3c718148c45..ecfd82d0afb7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -85,7 +85,6 @@ struct fimc_scaler { /* * A structure of fimc context. * - * @regs_res: register resources. * @regs: memory mapped io registers. * @lock: locking of operations. * @clocks: fimc clocks. @@ -103,7 +102,6 @@ struct fimc_context { struct exynos_drm_ipp_formats *formats; unsigned int num_formats; - struct resource *regs_res; void __iomem *regs; spinlock_t lock; struct clk *clocks[FIMC_CLKS_MAX]; @@ -1327,8 +1325,7 @@ static int fimc_probe(struct platform_device *pdev) ctx->num_formats = num_formats; /* resource memory */ - ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->regs = devm_ioremap_resource(dev, ctx->regs_res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 700ca4fa6665..c735e53939d8 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -1202,9 +1202,7 @@ static int fimd_probe(struct platform_device *pdev) return PTR_ERR(ctx->lcd_clk); } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - ctx->regs = devm_ioremap_resource(dev, res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index b00230626c6a..471fd6c8135f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1449,7 +1449,6 @@ static const struct component_ops g2d_component_ops = { static int g2d_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct g2d_data *g2d; int ret; @@ -1491,9 +1490,7 @@ static int g2d_probe(struct platform_device *pdev) clear_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags); clear_bit(G2D_BIT_ENGINE_BUSY, &g2d->flags); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - g2d->regs = devm_ioremap_resource(dev, res); + g2d->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(g2d->regs)) { ret = PTR_ERR(g2d->regs); goto err_put_clk; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 90d7bf906885..166a80262896 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -86,7 +86,6 @@ struct gsc_scaler { /* * A structure of gsc context. * - * @regs_res: register resources. * @regs: memory mapped io registers. * @gsc_clk: gsc gate clock. * @sc: scaler infomations. @@ -103,7 +102,6 @@ struct gsc_context { struct exynos_drm_ipp_formats *formats; unsigned int num_formats; - struct resource *regs_res; void __iomem *regs; const char **clk_names; struct clk *clocks[GSC_MAX_CLOCKS]; @@ -1272,9 +1270,7 @@ static int gsc_probe(struct platform_device *pdev) } } - /* resource memory */ - ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->regs = devm_ioremap_resource(dev, ctx->regs_res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index ee61be4cf152..dec7df35baa9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -278,7 +278,6 @@ static const struct component_ops rotator_component_ops = { static int rotator_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *regs_res; struct rot_context *rot; const struct rot_variant *variant; int irq; @@ -292,8 +291,7 @@ static int rotator_probe(struct platform_device *pdev) rot->formats = variant->formats; rot->num_formats = variant->num_formats; rot->dev = dev; - regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - rot->regs = devm_ioremap_resource(dev, regs_res); + rot->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rot->regs)) return PTR_ERR(rot->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index f9ae5b038d59..3a7851b7dc66 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -485,7 +485,6 @@ static const struct component_ops scaler_component_ops = { static int scaler_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *regs_res; struct scaler_context *scaler; int irq; int ret, i; @@ -498,8 +497,7 @@ static int scaler_probe(struct platform_device *pdev) (struct scaler_data *)of_device_get_match_data(dev); scaler->dev = dev; - regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - scaler->regs = devm_ioremap_resource(dev, regs_res); + scaler->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(scaler->regs)) return PTR_ERR(scaler->regs); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index c769dec576de..7655142a4651 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1957,7 +1957,6 @@ static int hdmi_probe(struct platform_device *pdev) struct hdmi_audio_infoframe *audio_infoframe; struct device *dev = &pdev->dev; struct hdmi_context *hdata; - struct resource *res; int ret; hdata = devm_kzalloc(dev, sizeof(struct hdmi_context), GFP_KERNEL); @@ -1979,8 +1978,7 @@ static int hdmi_probe(struct platform_device *pdev) return ret; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hdata->regs = devm_ioremap_resource(dev, res); + hdata->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hdata->regs)) { ret = PTR_ERR(hdata->regs); return ret; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 745e84c72c90..e866105dd174 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -362,8 +362,9 @@ static int __intel_context_active(struct i915_active *active) return 0; } -static int sw_fence_dummy_notify(struct i915_sw_fence *sf, - enum i915_sw_fence_notify state) +static int __i915_sw_fence_call +sw_fence_dummy_notify(struct i915_sw_fence *sf, + enum i915_sw_fence_notify state) { return NOTIFY_DONE; } diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 591a5224287e..0a03fbed9f9b 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -882,8 +882,6 @@ void intel_rps_park(struct intel_rps *rps) if (!intel_rps_is_enabled(rps)) return; - GEM_BUG_ON(atomic_read(&rps->num_waiters)); - if (!intel_rps_clear_active(rps)) return; diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h index 99e1fad5ca20..c9086a600bce 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h @@ -102,11 +102,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64); * | +-------+--------------------------------------------------------------+ * | | 7:0 | NUM_DWORDS = length (in dwords) of the embedded HXG message | * +---+-------+--------------------------------------------------------------+ - * | 1 | 31:0 | +--------------------------------------------------------+ | - * +---+-------+ | | | - * |...| | | Embedded `HXG Message`_ | | - * +---+-------+ | | | - * | n | 31:0 | +--------------------------------------------------------+ | + * | 1 | 31:0 | | + * +---+-------+ | + * |...| | [Embedded `HXG Message`_] | + * +---+-------+ | + * | n | 31:0 | | * +---+-------+--------------------------------------------------------------+ */ diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h index bbf1ddb77434..9baa3cb07d13 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h @@ -38,11 +38,11 @@ * +---+-------+--------------------------------------------------------------+ * | | Bits | Description | * +===+=======+==============================================================+ - * | 0 | 31:0 | +--------------------------------------------------------+ | - * +---+-------+ | | | - * |...| | | Embedded `HXG Message`_ | | - * +---+-------+ | | | - * | n | 31:0 | +--------------------------------------------------------+ | + * | 0 | 31:0 | | + * +---+-------+ | + * |...| | [Embedded `HXG Message`_] | + * +---+-------+ | + * | n | 31:0 | | * +---+-------+--------------------------------------------------------------+ */ diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index b56a8e37a3cd..1bb1be5c48c8 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -576,7 +576,7 @@ retry: /* No one is going to touch shadow bb from now on. */ i915_gem_object_flush_map(bb->obj); - i915_gem_object_unlock(bb->obj); + i915_gem_ww_ctx_fini(&ww); } } return 0; @@ -630,7 +630,7 @@ retry: return ret; } - i915_gem_object_unlock(wa_ctx->indirect_ctx.obj); + i915_gem_ww_ctx_fini(&ww); /* FIXME: we are not tracking our pinned VMA leaving it * up to the core to fix up the stray pin_count upon diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index ce446716d092..79da5eca60af 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -829,8 +829,6 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->submit, submit_notify); i915_sw_fence_init(&rq->semaphore, semaphore_notify); - dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0); - rq->capture_list = NULL; init_llist_head(&rq->execute_cb); @@ -905,17 +903,12 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) rq->ring = ce->ring; rq->execution_mask = ce->engine->mask; - kref_init(&rq->fence.refcount); - rq->fence.flags = 0; - rq->fence.error = 0; - INIT_LIST_HEAD(&rq->fence.cb_list); - ret = intel_timeline_get_seqno(tl, rq, &seqno); if (ret) goto err_free; - rq->fence.context = tl->fence_context; - rq->fence.seqno = seqno; + dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, + tl->fence_context, seqno); RCU_INIT_POINTER(rq->timeline, tl); rq->hwsp_seqno = tl->hwsp_seqno; diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 16c7aabb94d3..a29d64f87563 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -1845,7 +1845,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc, bool prepare_bandwidth_transition) { const struct tegra_plane_state *old_tegra_state, *new_tegra_state; - const struct tegra_dc_state *old_dc_state, *new_dc_state; u32 i, new_avg_bw, old_avg_bw, new_peak_bw, old_peak_bw; const struct drm_plane_state *old_plane_state; const struct drm_crtc_state *old_crtc_state; @@ -1858,8 +1857,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc, return; old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); - old_dc_state = to_const_dc_state(old_crtc_state); - new_dc_state = to_const_dc_state(crtc->state); if (!crtc->state->active) { if (!old_crtc_state->active) diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h index f0cb691852a1..40378308d527 100644 --- a/drivers/gpu/drm/tegra/dc.h +++ b/drivers/gpu/drm/tegra/dc.h @@ -35,12 +35,6 @@ static inline struct tegra_dc_state *to_dc_state(struct drm_crtc_state *state) return NULL; } -static inline const struct tegra_dc_state * -to_const_dc_state(const struct drm_crtc_state *state) -{ - return to_dc_state((struct drm_crtc_state *)state); -} - struct tegra_dc_stats { unsigned long frames; unsigned long vblank; diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index dc16a24f4dbe..690a339c52ec 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -222,7 +222,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f mapping->iova = sg_dma_address(mapping->sgt->sgl); } - mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->size; + mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->gem.size; err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX), GFP_KERNEL); diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c index 6941add95d0f..ecab72882192 100644 --- a/drivers/gpu/host1x/fence.c +++ b/drivers/gpu/host1x/fence.c @@ -15,7 +15,7 @@ #include "intr.h" #include "syncpt.h" -DEFINE_SPINLOCK(lock); +static DEFINE_SPINLOCK(lock); struct host1x_syncpt_fence { struct dma_fence base; @@ -152,8 +152,10 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) return ERR_PTR(-ENOMEM); fence->waiter = kzalloc(sizeof(*fence->waiter), GFP_KERNEL); - if (!fence->waiter) + if (!fence->waiter) { + kfree(fence); return ERR_PTR(-ENOMEM); + } fence->sp = sp; fence->threshold = threshold; diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 38bc35ac8135..3618a924e78e 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -362,12 +362,6 @@ static const struct hwmon_channel_info *k10temp_info[] = { HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL), - HWMON_CHANNEL_INFO(in, - HWMON_I_INPUT | HWMON_I_LABEL, - HWMON_I_INPUT | HWMON_I_LABEL), - HWMON_CHANNEL_INFO(curr, - HWMON_C_INPUT | HWMON_C_LABEL, - HWMON_C_INPUT | HWMON_C_LABEL), NULL }; diff --git a/drivers/hwmon/ltc2947-core.c b/drivers/hwmon/ltc2947-core.c index bb3f7749a0b0..5423466de697 100644 --- a/drivers/hwmon/ltc2947-core.c +++ b/drivers/hwmon/ltc2947-core.c @@ -989,8 +989,12 @@ static int ltc2947_setup(struct ltc2947_data *st) return ret; /* check external clock presence */ - extclk = devm_clk_get(st->dev, NULL); - if (!IS_ERR(extclk)) { + extclk = devm_clk_get_optional(st->dev, NULL); + if (IS_ERR(extclk)) + return dev_err_probe(st->dev, PTR_ERR(extclk), + "Failed to get external clock\n"); + + if (extclk) { unsigned long rate_hz; u8 pre = 0, div, tbctl; u64 aux; diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c index 116681fde33d..89fe7b9fe26b 100644 --- a/drivers/hwmon/mlxreg-fan.c +++ b/drivers/hwmon/mlxreg-fan.c @@ -315,8 +315,8 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, { struct mlxreg_fan *fan = cdev->devdata; unsigned long cur_state; + int i, config = 0; u32 regval; - int i; int err; /* @@ -329,6 +329,12 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, * overwritten. */ if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) { + /* + * This is configuration change, which is only supported through sysfs. + * For configuration non-zero value is to be returned to avoid thermal + * statistics update. + */ + config = 1; state -= MLXREG_FAN_MAX_STATE; for (i = 0; i < state; i++) fan->cooling_levels[i] = state; @@ -343,7 +349,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval); if (state < cur_state) - return 0; + return config; state = cur_state; } @@ -359,7 +365,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, dev_err(fan->dev, "Failed to write PWM duty\n"); return err; } - return 0; + return config; } static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = { diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index 0d68a78be980..ae664613289c 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -340,18 +340,11 @@ static ssize_t occ_show_temp_10(struct device *dev, if (val == OCC_TEMP_SENSOR_FAULT) return -EREMOTEIO; - /* - * VRM doesn't return temperature, only alarm bit. This - * attribute maps to tempX_alarm instead of tempX_input for - * VRM - */ - if (temp->fru_type != OCC_FRU_TYPE_VRM) { - /* sensor not ready */ - if (val == 0) - return -EAGAIN; + /* sensor not ready */ + if (val == 0) + return -EAGAIN; - val *= 1000; - } + val *= 1000; break; case 2: val = temp->fru_type; @@ -886,7 +879,7 @@ static int occ_setup_sensor_attrs(struct occ *occ) 0, i); attr++; - if (sensors->temp.version > 1 && + if (sensors->temp.version == 2 && temp->fru_type == OCC_FRU_TYPE_VRM) { snprintf(attr->name, sizeof(attr->name), "temp%d_alarm", s); diff --git a/drivers/hwmon/pmbus/ibm-cffps.c b/drivers/hwmon/pmbus/ibm-cffps.c index df712ce4b164..53f7d1418bc9 100644 --- a/drivers/hwmon/pmbus/ibm-cffps.c +++ b/drivers/hwmon/pmbus/ibm-cffps.c @@ -171,8 +171,14 @@ static ssize_t ibm_cffps_debugfs_read(struct file *file, char __user *buf, cmd = CFFPS_SN_CMD; break; case CFFPS_DEBUGFS_MAX_POWER_OUT: - rc = i2c_smbus_read_word_swapped(psu->client, - CFFPS_MAX_POWER_OUT_CMD); + if (psu->version == cffps1) { + rc = i2c_smbus_read_word_swapped(psu->client, + CFFPS_MAX_POWER_OUT_CMD); + } else { + rc = i2c_smbus_read_word_data(psu->client, + CFFPS_MAX_POWER_OUT_CMD); + } + if (rc < 0) return rc; diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c index eb94bd5f4e2a..51986adfbf47 100644 --- a/drivers/hwmon/pmbus/mp2975.c +++ b/drivers/hwmon/pmbus/mp2975.c @@ -54,7 +54,7 @@ #define MP2975_RAIL2_FUNC (PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | \ PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | \ - PMBUS_PHASE_VIRTUAL) + PMBUS_HAVE_POUT | PMBUS_PHASE_VIRTUAL) struct mp2975_data { struct pmbus_driver_info info; diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c index ede66ea6a730..b963a369c5ab 100644 --- a/drivers/hwmon/tmp421.c +++ b/drivers/hwmon/tmp421.c @@ -100,71 +100,81 @@ struct tmp421_data { s16 temp[4]; }; -static int temp_from_s16(s16 reg) +static int temp_from_raw(u16 reg, bool extended) { /* Mask out status bits */ int temp = reg & ~0xf; - return (temp * 1000 + 128) / 256; + if (extended) + temp = temp - 64 * 256; + else + temp = (s16)temp; + + return DIV_ROUND_CLOSEST(temp * 1000, 256); } -static int temp_from_u16(u16 reg) +static int tmp421_update_device(struct tmp421_data *data) { - /* Mask out status bits */ - int temp = reg & ~0xf; - - /* Add offset for extended temperature range. */ - temp -= 64 * 256; - - return (temp * 1000 + 128) / 256; -} - -static struct tmp421_data *tmp421_update_device(struct device *dev) -{ - struct tmp421_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; + int ret = 0; int i; mutex_lock(&data->update_lock); if (time_after(jiffies, data->last_updated + (HZ / 2)) || !data->valid) { - data->config = i2c_smbus_read_byte_data(client, - TMP421_CONFIG_REG_1); + ret = i2c_smbus_read_byte_data(client, TMP421_CONFIG_REG_1); + if (ret < 0) + goto exit; + data->config = ret; for (i = 0; i < data->channels; i++) { - data->temp[i] = i2c_smbus_read_byte_data(client, - TMP421_TEMP_MSB[i]) << 8; - data->temp[i] |= i2c_smbus_read_byte_data(client, - TMP421_TEMP_LSB[i]); + ret = i2c_smbus_read_byte_data(client, TMP421_TEMP_MSB[i]); + if (ret < 0) + goto exit; + data->temp[i] = ret << 8; + + ret = i2c_smbus_read_byte_data(client, TMP421_TEMP_LSB[i]); + if (ret < 0) + goto exit; + data->temp[i] |= ret; } data->last_updated = jiffies; data->valid = 1; } +exit: mutex_unlock(&data->update_lock); - return data; + if (ret < 0) { + data->valid = 0; + return ret; + } + + return 0; } static int tmp421_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { - struct tmp421_data *tmp421 = tmp421_update_device(dev); + struct tmp421_data *tmp421 = dev_get_drvdata(dev); + int ret = 0; + + ret = tmp421_update_device(tmp421); + if (ret) + return ret; switch (attr) { case hwmon_temp_input: - if (tmp421->config & TMP421_CONFIG_RANGE) - *val = temp_from_u16(tmp421->temp[channel]); - else - *val = temp_from_s16(tmp421->temp[channel]); + *val = temp_from_raw(tmp421->temp[channel], + tmp421->config & TMP421_CONFIG_RANGE); return 0; case hwmon_temp_fault: /* - * The OPEN bit signals a fault. This is bit 0 of the temperature - * register (low byte). + * Any of OPEN or /PVLD bits indicate a hardware mulfunction + * and the conversion result may be incorrect */ - *val = tmp421->temp[channel] & 0x01; + *val = !!(tmp421->temp[channel] & 0x03); return 0; default: return -EOPNOTSUPP; @@ -177,9 +187,6 @@ static umode_t tmp421_is_visible(const void *data, enum hwmon_sensor_types type, { switch (attr) { case hwmon_temp_fault: - if (channel == 0) - return 0; - return 0444; case hwmon_temp_input: return 0444; default: diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c index 37b25a1474c4..3c1be2c11fdf 100644 --- a/drivers/hwmon/w83791d.c +++ b/drivers/hwmon/w83791d.c @@ -273,9 +273,6 @@ struct w83791d_data { char valid; /* !=0 if following fields are valid */ unsigned long last_updated; /* In jiffies */ - /* array of 2 pointers to subclients */ - struct i2c_client *lm75[2]; - /* volts */ u8 in[NUMBER_OF_VIN]; /* Register value */ u8 in_max[NUMBER_OF_VIN]; /* Register value */ @@ -1257,7 +1254,6 @@ static const struct attribute_group w83791d_group_fanpwm45 = { static int w83791d_detect_subclients(struct i2c_client *client) { struct i2c_adapter *adapter = client->adapter; - struct w83791d_data *data = i2c_get_clientdata(client); int address = client->addr; int i, id; u8 val; @@ -1280,22 +1276,19 @@ static int w83791d_detect_subclients(struct i2c_client *client) } val = w83791d_read(client, W83791D_REG_I2C_SUBADDR); - if (!(val & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + (val & 0x7)); - if (!(val & 0x80)) { - if (!IS_ERR(data->lm75[0]) && - ((val & 0x7) == ((val >> 4) & 0x7))) { - dev_err(&client->dev, - "duplicate addresses 0x%x, " - "use force_subclient\n", - data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + ((val >> 4) & 0x7)); + + if (!(val & 0x88) && (val & 0x7) == ((val >> 4) & 0x7)) { + dev_err(&client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (val & 0x7)); + return -ENODEV; } + if (!(val & 0x08)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + (val & 0x7)); + + if (!(val & 0x80)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + ((val >> 4) & 0x7)); + return 0; } diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c index abd5c3a722b9..1f175f381350 100644 --- a/drivers/hwmon/w83792d.c +++ b/drivers/hwmon/w83792d.c @@ -264,9 +264,6 @@ struct w83792d_data { char valid; /* !=0 if following fields are valid */ unsigned long last_updated; /* In jiffies */ - /* array of 2 pointers to subclients */ - struct i2c_client *lm75[2]; - u8 in[9]; /* Register value */ u8 in_max[9]; /* Register value */ u8 in_min[9]; /* Register value */ @@ -927,7 +924,6 @@ w83792d_detect_subclients(struct i2c_client *new_client) int address = new_client->addr; u8 val; struct i2c_adapter *adapter = new_client->adapter; - struct w83792d_data *data = i2c_get_clientdata(new_client); id = i2c_adapter_id(adapter); if (force_subclients[0] == id && force_subclients[1] == address) { @@ -946,21 +942,19 @@ w83792d_detect_subclients(struct i2c_client *new_client) } val = w83792d_read_value(new_client, W83792D_REG_I2C_SUBADDR); - if (!(val & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&new_client->dev, adapter, - 0x48 + (val & 0x7)); - if (!(val & 0x80)) { - if (!IS_ERR(data->lm75[0]) && - ((val & 0x7) == ((val >> 4) & 0x7))) { - dev_err(&new_client->dev, - "duplicate addresses 0x%x, use force_subclient\n", - data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&new_client->dev, adapter, - 0x48 + ((val >> 4) & 0x7)); + + if (!(val & 0x88) && (val & 0x7) == ((val >> 4) & 0x7)) { + dev_err(&new_client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (val & 0x7)); + return -ENODEV; } + if (!(val & 0x08)) + devm_i2c_new_dummy_device(&new_client->dev, adapter, 0x48 + (val & 0x7)); + + if (!(val & 0x80)) + devm_i2c_new_dummy_device(&new_client->dev, adapter, 0x48 + ((val >> 4) & 0x7)); + return 0; } diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c index e7d0484eabe4..1d2854de1cfc 100644 --- a/drivers/hwmon/w83793.c +++ b/drivers/hwmon/w83793.c @@ -202,7 +202,6 @@ static inline s8 TEMP_TO_REG(long val, s8 min, s8 max) } struct w83793_data { - struct i2c_client *lm75[2]; struct device *hwmon_dev; struct mutex update_lock; char valid; /* !=0 if following fields are valid */ @@ -1566,7 +1565,6 @@ w83793_detect_subclients(struct i2c_client *client) int address = client->addr; u8 tmp; struct i2c_adapter *adapter = client->adapter; - struct w83793_data *data = i2c_get_clientdata(client); id = i2c_adapter_id(adapter); if (force_subclients[0] == id && force_subclients[1] == address) { @@ -1586,21 +1584,19 @@ w83793_detect_subclients(struct i2c_client *client) } tmp = w83793_read_value(client, W83793_REG_I2C_SUBADDR); - if (!(tmp & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + (tmp & 0x7)); - if (!(tmp & 0x80)) { - if (!IS_ERR(data->lm75[0]) - && ((tmp & 0x7) == ((tmp >> 4) & 0x7))) { - dev_err(&client->dev, - "duplicate addresses 0x%x, " - "use force_subclients\n", data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + ((tmp >> 4) & 0x7)); + + if (!(tmp & 0x88) && (tmp & 0x7) == ((tmp >> 4) & 0x7)) { + dev_err(&client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (tmp & 0x7)); + return -ENODEV; } + if (!(tmp & 0x08)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + (tmp & 0x7)); + + if (!(tmp & 0x80)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + ((tmp >> 4) & 0x7)); + return 0; } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index c40791baced5..704ce595542c 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1746,15 +1746,16 @@ static void cma_cancel_route(struct rdma_id_private *id_priv) } } -static void cma_cancel_listens(struct rdma_id_private *id_priv) +static void _cma_cancel_listens(struct rdma_id_private *id_priv) { struct rdma_id_private *dev_id_priv; + lockdep_assert_held(&lock); + /* * Remove from listen_any_list to prevent added devices from spawning * additional listen requests. */ - mutex_lock(&lock); list_del(&id_priv->list); while (!list_empty(&id_priv->listen_list)) { @@ -1768,6 +1769,12 @@ static void cma_cancel_listens(struct rdma_id_private *id_priv) rdma_destroy_id(&dev_id_priv->id); mutex_lock(&lock); } +} + +static void cma_cancel_listens(struct rdma_id_private *id_priv) +{ + mutex_lock(&lock); + _cma_cancel_listens(id_priv); mutex_unlock(&lock); } @@ -1776,6 +1783,14 @@ static void cma_cancel_operation(struct rdma_id_private *id_priv, { switch (state) { case RDMA_CM_ADDR_QUERY: + /* + * We can avoid doing the rdma_addr_cancel() based on state, + * only RDMA_CM_ADDR_QUERY has a work that could still execute. + * Notice that the addr_handler work could still be exiting + * outside this state, however due to the interaction with the + * handler_mutex the work is guaranteed not to touch id_priv + * during exit. + */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: @@ -1810,6 +1825,8 @@ static void cma_release_port(struct rdma_id_private *id_priv) static void destroy_mc(struct rdma_id_private *id_priv, struct cma_multicast *mc) { + bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); + if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) ib_sa_free_multicast(mc->sa_mc); @@ -1826,7 +1843,10 @@ static void destroy_mc(struct rdma_id_private *id_priv, cma_set_mgid(id_priv, (struct sockaddr *)&mc->addr, &mgid); - cma_igmp_send(ndev, &mgid, false); + + if (!send_only) + cma_igmp_send(ndev, &mgid, false); + dev_put(ndev); } @@ -2574,7 +2594,7 @@ static int cma_listen_on_all(struct rdma_id_private *id_priv) return 0; err_listen: - list_del(&id_priv->list); + _cma_cancel_listens(id_priv); mutex_unlock(&lock); if (to_destroy) rdma_destroy_id(&to_destroy->id); @@ -3413,6 +3433,21 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { + /* + * The FSM can return back to RDMA_CM_ADDR_BOUND after + * rdma_resolve_ip() is called, eg through the error + * path in addr_handler(). If this happens the existing + * request must be canceled before issuing a new one. + * Since canceling a request is a bit slow and this + * oddball path is rare, keep track once a request has + * been issued. The track turns out to be a permanent + * state since this is the only cancel as it is + * immediately before rdma_resolve_ip(). + */ + if (id_priv->used_resolve_ip) + rdma_addr_cancel(&id->route.addr.dev_addr); + else + id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, @@ -3771,9 +3806,13 @@ int rdma_listen(struct rdma_cm_id *id, int backlog) int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) { + struct sockaddr_in any_in = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_ANY), + }; + /* For a well behaved ULP state will be RDMA_CM_IDLE */ - id->route.addr.src_addr.ss_family = AF_INET; - ret = rdma_bind_addr(id, cma_src_addr(id_priv)); + ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, diff --git a/drivers/infiniband/core/cma_priv.h b/drivers/infiniband/core/cma_priv.h index 5c463da99845..f92f101ea981 100644 --- a/drivers/infiniband/core/cma_priv.h +++ b/drivers/infiniband/core/cma_priv.h @@ -91,6 +91,7 @@ struct rdma_id_private { u8 afonly; u8 timeout; u8 min_rnr_timer; + u8 used_resolve_ip; enum ib_gid_type gid_type; /* diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index e74ddbe46589..15b0cb0f363f 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -876,14 +876,14 @@ void hfi1_ipoib_tx_timeout(struct net_device *dev, unsigned int q) struct hfi1_ipoib_txq *txq = &priv->txqs[q]; u64 completed = atomic64_read(&txq->complete_txreqs); - dd_dev_info(priv->dd, "timeout txq %llx q %u stopped %u stops %d no_desc %d ring_full %d\n", - (unsigned long long)txq, q, + dd_dev_info(priv->dd, "timeout txq %p q %u stopped %u stops %d no_desc %d ring_full %d\n", + txq, q, __netif_subqueue_stopped(dev, txq->q_idx), atomic_read(&txq->stops), atomic_read(&txq->no_desc), atomic_read(&txq->ring_full)); - dd_dev_info(priv->dd, "sde %llx engine %u\n", - (unsigned long long)txq->sde, + dd_dev_info(priv->dd, "sde %p engine %u\n", + txq->sde, txq->sde ? txq->sde->this_idx : 0); dd_dev_info(priv->dd, "flow %x\n", txq->flow.as_int); dd_dev_info(priv->dd, "sent %llu completed %llu used %llu\n", diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index 1e9c3c5bee68..d763f097599f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -326,19 +326,30 @@ static void set_cq_param(struct hns_roce_cq *hr_cq, u32 cq_entries, int vector, INIT_LIST_HEAD(&hr_cq->rq_list); } -static void set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata, - struct hns_roce_ib_create_cq *ucmd) +static int set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata, + struct hns_roce_ib_create_cq *ucmd) { struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device); - if (udata) { - if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size)) - hr_cq->cqe_size = ucmd->cqe_size; - else - hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE; - } else { + if (!udata) { hr_cq->cqe_size = hr_dev->caps.cqe_sz; + return 0; } + + if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size)) { + if (ucmd->cqe_size != HNS_ROCE_V2_CQE_SIZE && + ucmd->cqe_size != HNS_ROCE_V3_CQE_SIZE) { + ibdev_err(&hr_dev->ib_dev, + "invalid cqe size %u.\n", ucmd->cqe_size); + return -EINVAL; + } + + hr_cq->cqe_size = ucmd->cqe_size; + } else { + hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE; + } + + return 0; } int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, @@ -366,7 +377,9 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, set_cq_param(hr_cq, attr->cqe, attr->comp_vector, &ucmd); - set_cqe_size(hr_cq, udata, &ucmd); + ret = set_cqe_size(hr_cq, udata, &ucmd); + if (ret) + return ret; ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr); if (ret) { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 5b9953105752..d5f3faa1627a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -3299,7 +3299,7 @@ static void __hns_roce_v2_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn, dest = get_cqe_v2(hr_cq, (prod_index + nfreed) & hr_cq->ib_cq.cqe); owner_bit = hr_reg_read(dest, CQE_OWNER); - memcpy(dest, cqe, sizeof(*cqe)); + memcpy(dest, cqe, hr_cq->cqe_size); hr_reg_write(dest, CQE_OWNER, owner_bit); } } @@ -4397,7 +4397,12 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, hr_qp->path_mtu = ib_mtu; mtu = ib_mtu_enum_to_int(ib_mtu); - if (WARN_ON(mtu < 0)) + if (WARN_ON(mtu <= 0)) + return -EINVAL; +#define MAX_LP_MSG_LEN 65536 + /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */ + lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); + if (WARN_ON(lp_pktn_ini >= 0xF)) return -EINVAL; if (attr_mask & IB_QP_PATH_MTU) { @@ -4405,10 +4410,6 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, hr_reg_clear(qpc_mask, QPC_MTU); } -#define MAX_LP_MSG_LEN 65536 - /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */ - lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); - hr_reg_write(context, QPC_LP_PKTN_INI, lp_pktn_ini); hr_reg_clear(qpc_mask, QPC_LP_PKTN_INI); diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 6b62299abfbb..6dea0a49d171 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -3496,7 +3496,7 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp) original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT || last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE || last_ae == IRDMA_AE_BAD_CLOSE || - last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->reset)) { + last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset)) { issue_close = 1; iwqp->cm_id = NULL; qp->term_flags = 0; @@ -4250,7 +4250,7 @@ void irdma_cm_teardown_connections(struct irdma_device *iwdev, u32 *ipaddr, teardown_entry); attr.qp_state = IB_QPS_ERR; irdma_modify_qp(&cm_node->iwqp->ibqp, &attr, IB_QP_STATE, NULL); - if (iwdev->reset) + if (iwdev->rf->reset) irdma_cm_disconn(cm_node->iwqp); irdma_rem_ref_cm_node(cm_node); } diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 00de5ee9a260..7de525a5ccf8 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -176,6 +176,14 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp, case IRDMA_AE_LLP_RECEIVED_MPA_CRC_ERROR: qp->flush_code = FLUSH_GENERAL_ERR; break; + case IRDMA_AE_LLP_TOO_MANY_RETRIES: + qp->flush_code = FLUSH_RETRY_EXC_ERR; + break; + case IRDMA_AE_AMP_MWBIND_INVALID_RIGHTS: + case IRDMA_AE_AMP_MWBIND_BIND_DISABLED: + case IRDMA_AE_AMP_MWBIND_INVALID_BOUNDS: + qp->flush_code = FLUSH_MW_BIND_ERR; + break; default: qp->flush_code = FLUSH_FATAL_ERR; break; @@ -1489,7 +1497,7 @@ void irdma_reinitialize_ieq(struct irdma_sc_vsi *vsi) irdma_puda_dele_rsrc(vsi, IRDMA_PUDA_RSRC_TYPE_IEQ, false); if (irdma_initialize_ieq(iwdev)) { - iwdev->reset = true; + iwdev->rf->reset = true; rf->gen_ops.request_reset(rf); } } @@ -1632,13 +1640,13 @@ void irdma_rt_deinit_hw(struct irdma_device *iwdev) case IEQ_CREATED: if (!iwdev->roce_mode) irdma_puda_dele_rsrc(&iwdev->vsi, IRDMA_PUDA_RSRC_TYPE_IEQ, - iwdev->reset); + iwdev->rf->reset); fallthrough; case ILQ_CREATED: if (!iwdev->roce_mode) irdma_puda_dele_rsrc(&iwdev->vsi, IRDMA_PUDA_RSRC_TYPE_ILQ, - iwdev->reset); + iwdev->rf->reset); break; default: ibdev_warn(&iwdev->ibdev, "bad init_state = %d\n", iwdev->init_state); diff --git a/drivers/infiniband/hw/irdma/i40iw_if.c b/drivers/infiniband/hw/irdma/i40iw_if.c index bddf88194d09..d219f64b2c3d 100644 --- a/drivers/infiniband/hw/irdma/i40iw_if.c +++ b/drivers/infiniband/hw/irdma/i40iw_if.c @@ -55,7 +55,7 @@ static void i40iw_close(struct i40e_info *cdev_info, struct i40e_client *client, iwdev = to_iwdev(ibdev); if (reset) - iwdev->reset = true; + iwdev->rf->reset = true; iwdev->iw_status = 0; irdma_port_ibevent(iwdev); diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h index 743d9e143a99..b678fe712447 100644 --- a/drivers/infiniband/hw/irdma/main.h +++ b/drivers/infiniband/hw/irdma/main.h @@ -346,7 +346,6 @@ struct irdma_device { bool roce_mode:1; bool roce_dcqcn_en:1; bool dcb:1; - bool reset:1; bool iw_ooo:1; enum init_completion_state init_state; diff --git a/drivers/infiniband/hw/irdma/user.h b/drivers/infiniband/hw/irdma/user.h index ff705f323233..3dcbb1fbf2c6 100644 --- a/drivers/infiniband/hw/irdma/user.h +++ b/drivers/infiniband/hw/irdma/user.h @@ -102,6 +102,8 @@ enum irdma_flush_opcode { FLUSH_REM_OP_ERR, FLUSH_LOC_LEN_ERR, FLUSH_FATAL_ERR, + FLUSH_RETRY_EXC_ERR, + FLUSH_MW_BIND_ERR, }; enum irdma_cmpl_status { diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index e94470991fe0..ac91ea5296db 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -2507,7 +2507,7 @@ void irdma_modify_qp_to_err(struct irdma_sc_qp *sc_qp) struct irdma_qp *qp = sc_qp->qp_uk.back_qp; struct ib_qp_attr attr; - if (qp->iwdev->reset) + if (qp->iwdev->rf->reset) return; attr.qp_state = IB_QPS_ERR; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 4fc323402073..7110ebf834f9 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -535,8 +535,7 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) irdma_qp_rem_ref(&iwqp->ibqp); wait_for_completion(&iwqp->free_qp); irdma_free_lsmm_rsrc(iwqp); - if (!iwdev->reset) - irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); + irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); if (!iwqp->user_mode) { if (iwqp->iwscq) { @@ -2035,7 +2034,7 @@ static int irdma_create_cq(struct ib_cq *ibcq, /* Kmode allocations */ int rsize; - if (entries > rf->max_cqe) { + if (entries < 1 || entries > rf->max_cqe) { err_code = -EINVAL; goto cq_free_rsrc; } @@ -3353,6 +3352,10 @@ static enum ib_wc_status irdma_flush_err_to_ib_wc_status(enum irdma_flush_opcode return IB_WC_LOC_LEN_ERR; case FLUSH_GENERAL_ERR: return IB_WC_WR_FLUSH_ERR; + case FLUSH_RETRY_EXC_ERR: + return IB_WC_RETRY_EXC_ERR; + case FLUSH_MW_BIND_ERR: + return IB_WC_MW_BIND_ERR; case FLUSH_FATAL_ERR: default: return IB_WC_FATAL_ERR; diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 452e2355d24e..0a3b28142c05 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -403,7 +403,7 @@ static ssize_t diagc_attr_store(struct ib_device *ibdev, u32 port_num, } #define QIB_DIAGC_ATTR(N) \ - static_assert(&((struct qib_ibport *)0)->rvp.n_##N != (u64 *)NULL); \ + static_assert(__same_type(((struct qib_ibport *)0)->rvp.n_##N, u64)); \ static struct qib_diagc_attr qib_diagc_attr_##N = { \ .attr = __ATTR(N, 0664, diagc_attr_show, diagc_attr_store), \ .counter = \ diff --git a/drivers/infiniband/hw/usnic/usnic_ib.h b/drivers/infiniband/hw/usnic/usnic_ib.h index 84dd682d2334..b350081aeb5a 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib.h +++ b/drivers/infiniband/hw/usnic/usnic_ib.h @@ -90,7 +90,7 @@ struct usnic_ib_dev { struct usnic_ib_vf { struct usnic_ib_dev *pf; - spinlock_t lock; + struct mutex lock; struct usnic_vnic *vnic; unsigned int qp_grp_ref_cnt; struct usnic_ib_pd *pd; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index 228e9a36dad0..d346dd48e731 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -572,7 +572,7 @@ static int usnic_ib_pci_probe(struct pci_dev *pdev, } vf->pf = pf; - spin_lock_init(&vf->lock); + mutex_init(&vf->lock); mutex_lock(&pf->usdev_lock); list_add_tail(&vf->link, &pf->vf_dev_list); /* diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index 06a4e9d4545d..756a83bcff58 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -196,7 +196,7 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, for (i = 0; dev_list[i]; i++) { dev = dev_list[i]; vf = dev_get_drvdata(dev); - spin_lock(&vf->lock); + mutex_lock(&vf->lock); vnic = vf->vnic; if (!usnic_vnic_check_room(vnic, res_spec)) { usnic_dbg("Found used vnic %s from %s\n", @@ -208,10 +208,10 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, vf, pd, res_spec, trans_spec); - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); goto qp_grp_check; } - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); } usnic_uiom_free_dev_list(dev_list); @@ -220,7 +220,7 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, /* Try to find resources on an unused vf */ list_for_each_entry(vf, &us_ibdev->vf_dev_list, link) { - spin_lock(&vf->lock); + mutex_lock(&vf->lock); vnic = vf->vnic; if (vf->qp_grp_ref_cnt == 0 && usnic_vnic_check_room(vnic, res_spec) == 0) { @@ -228,10 +228,10 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, vf, pd, res_spec, trans_spec); - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); goto qp_grp_check; } - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); } usnic_info("No free qp grp found on %s\n", @@ -253,9 +253,9 @@ static void qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp) WARN_ON(qp_grp->state != IB_QPS_RESET); - spin_lock(&vf->lock); + mutex_lock(&vf->lock); usnic_ib_qp_grp_destroy(qp_grp); - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); } static int create_qp_validate_user_data(struct usnic_ib_create_qp_cmd cmd) diff --git a/drivers/interconnect/qcom/sdm660.c b/drivers/interconnect/qcom/sdm660.c index 632dbdd21915..fb23a5b780a4 100644 --- a/drivers/interconnect/qcom/sdm660.c +++ b/drivers/interconnect/qcom/sdm660.c @@ -44,9 +44,9 @@ #define NOC_PERM_MODE_BYPASS (1 << NOC_QOS_MODE_BYPASS) #define NOC_QOS_PRIORITYn_ADDR(n) (0x8 + (n * 0x1000)) -#define NOC_QOS_PRIORITY_MASK 0xf +#define NOC_QOS_PRIORITY_P1_MASK 0xc +#define NOC_QOS_PRIORITY_P0_MASK 0x3 #define NOC_QOS_PRIORITY_P1_SHIFT 0x2 -#define NOC_QOS_PRIORITY_P0_SHIFT 0x3 #define NOC_QOS_MODEn_ADDR(n) (0xc + (n * 0x1000)) #define NOC_QOS_MODEn_MASK 0x3 @@ -173,6 +173,16 @@ static const struct clk_bulk_data bus_mm_clocks[] = { { .id = "iface" }, }; +static const struct clk_bulk_data bus_a2noc_clocks[] = { + { .id = "bus" }, + { .id = "bus_a" }, + { .id = "ipa" }, + { .id = "ufs_axi" }, + { .id = "aggre2_ufs_axi" }, + { .id = "aggre2_usb3_axi" }, + { .id = "cfg_noc_usb2_axi" }, +}; + /** * struct qcom_icc_provider - Qualcomm specific interconnect provider * @provider: generic interconnect provider @@ -307,7 +317,7 @@ DEFINE_QNODE(slv_bimc_cfg, SDM660_SLAVE_BIMC_CFG, 4, -1, 56, true, -1, 0, -1, 0) DEFINE_QNODE(slv_prng, SDM660_SLAVE_PRNG, 4, -1, 44, true, -1, 0, -1, 0); DEFINE_QNODE(slv_spdm, SDM660_SLAVE_SPDM, 4, -1, 60, true, -1, 0, -1, 0); DEFINE_QNODE(slv_qdss_cfg, SDM660_SLAVE_QDSS_CFG, 4, -1, 63, true, -1, 0, -1, 0); -DEFINE_QNODE(slv_cnoc_mnoc_cfg, SDM660_SLAVE_BLSP_1, 4, -1, 66, true, -1, 0, -1, SDM660_MASTER_CNOC_MNOC_CFG); +DEFINE_QNODE(slv_cnoc_mnoc_cfg, SDM660_SLAVE_CNOC_MNOC_CFG, 4, -1, 66, true, -1, 0, -1, SDM660_MASTER_CNOC_MNOC_CFG); DEFINE_QNODE(slv_snoc_cfg, SDM660_SLAVE_SNOC_CFG, 4, -1, 70, true, -1, 0, -1, 0); DEFINE_QNODE(slv_qm_cfg, SDM660_SLAVE_QM_CFG, 4, -1, 212, true, -1, 0, -1, 0); DEFINE_QNODE(slv_clk_ctl, SDM660_SLAVE_CLK_CTL, 4, -1, 47, true, -1, 0, -1, 0); @@ -624,13 +634,12 @@ static int qcom_icc_noc_set_qos_priority(struct regmap *rmap, /* Must be updated one at a time, P1 first, P0 last */ val = qos->areq_prio << NOC_QOS_PRIORITY_P1_SHIFT; rc = regmap_update_bits(rmap, NOC_QOS_PRIORITYn_ADDR(qos->qos_port), - NOC_QOS_PRIORITY_MASK, val); + NOC_QOS_PRIORITY_P1_MASK, val); if (rc) return rc; - val = qos->prio_level << NOC_QOS_PRIORITY_P0_SHIFT; return regmap_update_bits(rmap, NOC_QOS_PRIORITYn_ADDR(qos->qos_port), - NOC_QOS_PRIORITY_MASK, val); + NOC_QOS_PRIORITY_P0_MASK, qos->prio_level); } static int qcom_icc_set_noc_qos(struct icc_node *src, u64 max_bw) @@ -810,6 +819,10 @@ static int qnoc_probe(struct platform_device *pdev) qp->bus_clks = devm_kmemdup(dev, bus_mm_clocks, sizeof(bus_mm_clocks), GFP_KERNEL); qp->num_clks = ARRAY_SIZE(bus_mm_clocks); + } else if (of_device_is_compatible(dev->of_node, "qcom,sdm660-a2noc")) { + qp->bus_clks = devm_kmemdup(dev, bus_a2noc_clocks, + sizeof(bus_a2noc_clocks), GFP_KERNEL); + qp->num_clks = ARRAY_SIZE(bus_a2noc_clocks); } else { if (of_device_is_compatible(dev->of_node, "qcom,sdm660-bimc")) qp->is_bimc_node = true; diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 559db9259e65..fdfa39ec2a4d 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -183,7 +183,6 @@ struct apple_dart_master_cfg { static struct platform_driver apple_dart_driver; static const struct iommu_ops apple_dart_iommu_ops; -static const struct iommu_flush_ops apple_dart_tlb_ops; static struct apple_dart_domain *to_dart_domain(struct iommu_domain *dom) { @@ -338,22 +337,6 @@ static void apple_dart_iotlb_sync_map(struct iommu_domain *domain, apple_dart_domain_flush_tlb(to_dart_domain(domain)); } -static void apple_dart_tlb_flush_all(void *cookie) -{ - apple_dart_domain_flush_tlb(cookie); -} - -static void apple_dart_tlb_flush_walk(unsigned long iova, size_t size, - size_t granule, void *cookie) -{ - apple_dart_domain_flush_tlb(cookie); -} - -static const struct iommu_flush_ops apple_dart_tlb_ops = { - .tlb_flush_all = apple_dart_tlb_flush_all, - .tlb_flush_walk = apple_dart_tlb_flush_walk, -}; - static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { @@ -435,7 +418,6 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain, .ias = 32, .oas = 36, .coherent_walk = 1, - .tlb = &apple_dart_tlb_ops, .iommu_dev = dart->dev, }; @@ -661,16 +643,34 @@ static int apple_dart_of_xlate(struct device *dev, struct of_phandle_args *args) return -EINVAL; } +static DEFINE_MUTEX(apple_dart_groups_lock); + +static void apple_dart_release_group(void *iommu_data) +{ + int i, sid; + struct apple_dart_stream_map *stream_map; + struct apple_dart_master_cfg *group_master_cfg = iommu_data; + + mutex_lock(&apple_dart_groups_lock); + + for_each_stream_map(i, group_master_cfg, stream_map) + for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) + stream_map->dart->sid2group[sid] = NULL; + + kfree(iommu_data); + mutex_unlock(&apple_dart_groups_lock); +} + static struct iommu_group *apple_dart_device_group(struct device *dev) { - static DEFINE_MUTEX(lock); int i, sid; struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); struct apple_dart_stream_map *stream_map; + struct apple_dart_master_cfg *group_master_cfg; struct iommu_group *group = NULL; struct iommu_group *res = ERR_PTR(-EINVAL); - mutex_lock(&lock); + mutex_lock(&apple_dart_groups_lock); for_each_stream_map(i, cfg, stream_map) { for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) { @@ -698,6 +698,20 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) #endif group = generic_device_group(dev); + res = ERR_PTR(-ENOMEM); + if (!group) + goto out; + + group_master_cfg = kzalloc(sizeof(*group_master_cfg), GFP_KERNEL); + if (!group_master_cfg) { + iommu_group_put(group); + goto out; + } + + memcpy(group_master_cfg, cfg, sizeof(*group_master_cfg)); + iommu_group_set_iommudata(group, group_master_cfg, + apple_dart_release_group); + for_each_stream_map(i, cfg, stream_map) for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) stream_map->dart->sid2group[sid] = group; @@ -705,7 +719,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) res = group; out: - mutex_unlock(&lock); + mutex_unlock(&apple_dart_groups_lock); return res; } diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 0ec5514c9980..b7708b93f3fa 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1942,18 +1942,18 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, reason = dmar_get_fault_reason(fault_reason, &fault_type); if (fault_type == INTR_REMAP) - pr_err("[INTR-REMAP] Request device [0x%02x:0x%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n", source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); else if (pasid == INVALID_IOASID) - pr_err("[%s NO_PASID] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason); else - pr_err("[%s PASID 0x%x] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[%s PASID 0x%x] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", pasid, source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr, diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index c14e65a5d38f..c709861198e5 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -33,6 +33,7 @@ struct ipoctal_channel { unsigned int pointer_read; unsigned int pointer_write; struct tty_port tty_port; + bool tty_registered; union scc2698_channel __iomem *regs; union scc2698_block __iomem *block_regs; unsigned int board_id; @@ -81,22 +82,34 @@ static int ipoctal_port_activate(struct tty_port *port, struct tty_struct *tty) return 0; } -static int ipoctal_open(struct tty_struct *tty, struct file *file) +static int ipoctal_install(struct tty_driver *driver, struct tty_struct *tty) { struct ipoctal_channel *channel = dev_get_drvdata(tty->dev); struct ipoctal *ipoctal = chan_to_ipoctal(channel, tty->index); - int err; - - tty->driver_data = channel; + int res; if (!ipack_get_carrier(ipoctal->dev)) return -EBUSY; - err = tty_port_open(&channel->tty_port, tty, file); - if (err) - ipack_put_carrier(ipoctal->dev); + res = tty_standard_install(driver, tty); + if (res) + goto err_put_carrier; - return err; + tty->driver_data = channel; + + return 0; + +err_put_carrier: + ipack_put_carrier(ipoctal->dev); + + return res; +} + +static int ipoctal_open(struct tty_struct *tty, struct file *file) +{ + struct ipoctal_channel *channel = tty->driver_data; + + return tty_port_open(&channel->tty_port, tty, file); } static void ipoctal_reset_stats(struct ipoctal_stats *stats) @@ -264,7 +277,6 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, int res; int i; struct tty_driver *tty; - char name[20]; struct ipoctal_channel *channel; struct ipack_region *region; void __iomem *addr; @@ -355,8 +367,11 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, /* Fill struct tty_driver with ipoctal data */ tty->owner = THIS_MODULE; tty->driver_name = KBUILD_MODNAME; - sprintf(name, KBUILD_MODNAME ".%d.%d.", bus_nr, slot); - tty->name = name; + tty->name = kasprintf(GFP_KERNEL, KBUILD_MODNAME ".%d.%d.", bus_nr, slot); + if (!tty->name) { + res = -ENOMEM; + goto err_put_driver; + } tty->major = 0; tty->minor_start = 0; @@ -371,8 +386,7 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, res = tty_register_driver(tty); if (res) { dev_err(&ipoctal->dev->dev, "Can't register tty driver.\n"); - tty_driver_kref_put(tty); - return res; + goto err_free_name; } /* Save struct tty_driver for use it when uninstalling the device */ @@ -383,7 +397,9 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, channel = &ipoctal->channel[i]; tty_port_init(&channel->tty_port); - tty_port_alloc_xmit_buf(&channel->tty_port); + res = tty_port_alloc_xmit_buf(&channel->tty_port); + if (res) + continue; channel->tty_port.ops = &ipoctal_tty_port_ops; ipoctal_reset_stats(&channel->stats); @@ -391,13 +407,15 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, spin_lock_init(&channel->lock); channel->pointer_read = 0; channel->pointer_write = 0; - tty_dev = tty_port_register_device(&channel->tty_port, tty, i, NULL); + tty_dev = tty_port_register_device_attr(&channel->tty_port, tty, + i, NULL, channel, NULL); if (IS_ERR(tty_dev)) { dev_err(&ipoctal->dev->dev, "Failed to register tty device.\n"); + tty_port_free_xmit_buf(&channel->tty_port); tty_port_destroy(&channel->tty_port); continue; } - dev_set_drvdata(tty_dev, channel); + channel->tty_registered = true; } /* @@ -409,6 +427,13 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, ipoctal_irq_handler, ipoctal); return 0; + +err_free_name: + kfree(tty->name); +err_put_driver: + tty_driver_kref_put(tty); + + return res; } static inline int ipoctal_copy_write_buffer(struct ipoctal_channel *channel, @@ -648,6 +673,7 @@ static void ipoctal_cleanup(struct tty_struct *tty) static const struct tty_operations ipoctal_fops = { .ioctl = NULL, + .install = ipoctal_install, .open = ipoctal_open, .close = ipoctal_close, .write = ipoctal_write_tty, @@ -690,12 +716,17 @@ static void __ipoctal_remove(struct ipoctal *ipoctal) for (i = 0; i < NR_CHANNELS; i++) { struct ipoctal_channel *channel = &ipoctal->channel[i]; + + if (!channel->tty_registered) + continue; + tty_unregister_device(ipoctal->tty_drv, i); tty_port_free_xmit_buf(&channel->tty_port); tty_port_destroy(&channel->tty_port); } tty_unregister_driver(ipoctal->tty_drv); + kfree(ipoctal->tty_drv->name); tty_driver_kref_put(ipoctal->tty_drv); kfree(ipoctal); } diff --git a/drivers/media/tuners/tuner-types.c b/drivers/media/tuners/tuner-types.c index 01f61ebabd56..0ed2c5bc082e 100644 --- a/drivers/media/tuners/tuner-types.c +++ b/drivers/media/tuners/tuner-types.c @@ -1942,6 +1942,10 @@ struct tunertype tuners[] = { .params = tuner_sony_btf_pg463z_params, .count = ARRAY_SIZE(tuner_sony_btf_pg463z_params), }, + [TUNER_SI2157] = { + .name = "Silicon Labs Si2157 tuner", + /* see si2157.c for details */ + }, }; EXPORT_SYMBOL(tuners); diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c index 948e22e29b42..b207f34af5c6 100644 --- a/drivers/media/usb/em28xx/em28xx-cards.c +++ b/drivers/media/usb/em28xx/em28xx-cards.c @@ -2508,12 +2508,17 @@ const struct em28xx_board em28xx_boards[] = { .def_i2c_bus = 1, .i2c_speed = EM28XX_I2C_CLK_WAIT_ENABLE | EM28XX_I2C_FREQ_400_KHZ, - .tuner_type = TUNER_ABSENT, + .tuner_type = TUNER_SI2157, .tuner_gpio = hauppauge_dualhd_dvb, .has_dvb = 1, .has_dual_ts = 1, .ir_codes = RC_MAP_HAUPPAUGE, .leds = hauppauge_dualhd_leds, + .input = { { + .type = EM28XX_VMUX_COMPOSITE, + .vmux = TVP5150_COMPOSITE1, + .amux = EM28XX_AMUX_LINE_IN, + } }, }, /* * 2040:026d Hauppauge WinTV-dualHD (model 01595 - ATSC/QAM) Isoc. diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 6578cc64ae9e..380f9aa56eb2 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -1802,10 +1802,15 @@ static enum hrtimer_restart dw_mci_fault_timer(struct hrtimer *t) spin_lock_irqsave(&host->irq_lock, flags); - if (!host->data_status) + /* + * Only inject an error if we haven't already got an error or data over + * interrupt. + */ + if (!host->data_status) { host->data_status = SDMMC_INT_DCRC; - set_bit(EVENT_DATA_ERROR, &host->pending_events); - tasklet_schedule(&host->tasklet); + set_bit(EVENT_DATA_ERROR, &host->pending_events); + tasklet_schedule(&host->tasklet); + } spin_unlock_irqrestore(&host->irq_lock, flags); @@ -2721,12 +2726,16 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) } if (pending & DW_MCI_DATA_ERROR_FLAGS) { + spin_lock(&host->irq_lock); + /* if there is an error report DATA_ERROR */ mci_writel(host, RINTSTS, DW_MCI_DATA_ERROR_FLAGS); host->data_status = pending; smp_wmb(); /* drain writebuffer */ set_bit(EVENT_DATA_ERROR, &host->pending_events); tasklet_schedule(&host->tasklet); + + spin_unlock(&host->irq_lock); } if (pending & SDMMC_INT_DATA_OVER) { diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 6fc4cf3c9dce..a4407f391f66 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -561,6 +561,8 @@ static void renesas_sdhi_reset(struct tmio_mmc_host *host) /* Unknown why but without polling reset status, it will hang */ read_poll_timeout(reset_control_status, ret, ret == 0, 1, 100, false, priv->rstc); + /* At least SDHI_VER_GEN2_SDR50 needs manual release of reset */ + sd_ctrl_write16(host, CTL_RESET_SD, 0x0001); priv->needs_adjust_hs400 = false; renesas_sdhi_set_clock(host, host->clk_cache); } else if (priv->scc_ctl) { diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8ab0be793811..03744d1c43fc 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2834,8 +2834,8 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; - /* Port Control 2: don't force a good FCS, set the maximum frame size to - * 10240 bytes, disable 802.1q tags checking, don't discard tagged or + /* Port Control 2: don't force a good FCS, set the MTU size to + * 10222 bytes, disable 802.1q tags checking, don't discard tagged or * untagged frames on this port, do a destination address lookup on all * received packets as usual, disable ARP mirroring and don't send a * copy of all transmitted/received frames on this port to the CPU. @@ -2854,7 +2854,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; if (chip->info->ops->port_set_jumbo_size) { - err = chip->info->ops->port_set_jumbo_size(chip, port, 10240); + err = chip->info->ops->port_set_jumbo_size(chip, port, 10218); if (err) return err; } @@ -2944,10 +2944,10 @@ static int mv88e6xxx_get_max_mtu(struct dsa_switch *ds, int port) struct mv88e6xxx_chip *chip = ds->priv; if (chip->info->ops->port_set_jumbo_size) - return 10240; + return 10240 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; else if (chip->info->ops->set_max_frame_size) - return 1632; - return 1522; + return 1632 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; + return 1522 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; } static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) @@ -2955,6 +2955,9 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) struct mv88e6xxx_chip *chip = ds->priv; int ret = 0; + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + new_mtu += EDSA_HLEN; + mv88e6xxx_reg_lock(chip); if (chip->info->ops->port_set_jumbo_size) ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu); @@ -3725,7 +3728,6 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, .port_set_ether_type = mv88e6351_port_set_ether_type, - .port_set_jumbo_size = mv88e6165_port_set_jumbo_size, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_limit = mv88e6097_port_pause_limit, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, @@ -3750,6 +3752,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .avb_ops = &mv88e6165_avb_ops, .ptp_ops = &mv88e6165_ptp_ops, .phylink_validate = mv88e6185_phylink_validate, + .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; static const struct mv88e6xxx_ops mv88e6165_ops = { diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 675b1f3e43b7..59f316cc8583 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -18,6 +18,7 @@ #include #include +#define EDSA_HLEN 8 #define MV88E6XXX_N_FID 4096 /* PVT limits for 4-bit port and 5-bit switch */ diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 815b0f681d69..5848112036b0 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -232,6 +232,8 @@ int mv88e6185_g1_set_max_frame_size(struct mv88e6xxx_chip *chip, int mtu) u16 val; int err; + mtu += ETH_HLEN + ETH_FCS_LEN; + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &val); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index f77e2ee64a60..451028c57af8 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -1277,6 +1277,8 @@ int mv88e6165_port_set_jumbo_size(struct mv88e6xxx_chip *chip, int port, u16 reg; int err; + size += VLAN_ETH_HLEN + ETH_FCS_LEN; + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_CTL2, ®); if (err) return err; diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 4ab5bf64d353..df8ff839cc62 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -192,6 +192,9 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->dma_dev = &pdev->dev; ret = of_get_mac_address(np, bgmac->net_dev->dev_addr); + if (ret == -EPROBE_DEFER) + return ret; + if (ret) dev_warn(&pdev->dev, "MAC address not present in device tree\n"); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 60d94e0a07d6..4c977dfc44f0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -541,8 +541,7 @@ static void enetc_mac_config(struct enetc_hw *hw, phy_interface_t phy_mode) if (phy_interface_mode_is_rgmii(phy_mode)) { val = enetc_port_rd(hw, ENETC_PM0_IF_MODE); - val &= ~ENETC_PM0_IFM_EN_AUTO; - val &= ENETC_PM0_IFM_IFMODE_MASK; + val &= ~(ENETC_PM0_IFM_EN_AUTO | ENETC_PM0_IFM_IFMODE_MASK); val |= ENETC_PM0_IFM_IFMODE_GMII | ENETC_PM0_IFM_RG; enetc_port_wr(hw, ENETC_PM0_IF_MODE, val); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 546a60530384..8ba21d6dc220 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -752,7 +752,6 @@ struct hnae3_tc_info { u8 prio_tc[HNAE3_MAX_USER_PRIO]; /* TC indexed by prio */ u16 tqp_count[HNAE3_MAX_TC]; u16 tqp_offset[HNAE3_MAX_TC]; - unsigned long tc_en; /* bitmap of TC enabled */ u8 num_tc; /* Total number of enabled TCs */ bool mqprio_active; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index adc54a726661..468b8f07bf47 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -623,13 +623,9 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev) return ret; } - for (i = 0; i < HNAE3_MAX_TC; i++) { - if (!test_bit(i, &tc_info->tc_en)) - continue; - + for (i = 0; i < tc_info->num_tc; i++) netdev_set_tc_queue(netdev, i, tc_info->tqp_count[i], tc_info->tqp_offset[i]); - } } ret = netif_set_real_num_tx_queues(netdev, queue_size); @@ -779,6 +775,11 @@ static int hns3_nic_net_open(struct net_device *netdev) if (hns3_nic_resetting(netdev)) return -EBUSY; + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) { + netdev_warn(netdev, "net open repeatedly!\n"); + return 0; + } + netif_carrier_off(netdev); ret = hns3_nic_set_real_num_queue(netdev); @@ -4865,12 +4866,9 @@ static void hns3_init_tx_ring_tc(struct hns3_nic_priv *priv) struct hnae3_tc_info *tc_info = &kinfo->tc_info; int i; - for (i = 0; i < HNAE3_MAX_TC; i++) { + for (i = 0; i < tc_info->num_tc; i++) { int j; - if (!test_bit(i, &tc_info->tc_en)) - continue; - for (j = 0; j < tc_info->tqp_count[i]; j++) { struct hnae3_queue *q; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 7ea511d59e91..5ebd96f6833d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -334,7 +334,8 @@ static void hns3_selftest_prepare(struct net_device *ndev, #if IS_ENABLED(CONFIG_VLAN_8021Q) /* Disable the vlan filter for selftest does not support it */ - if (h->ae_algo->ops->enable_vlan_filter) + if (h->ae_algo->ops->enable_vlan_filter && + ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) h->ae_algo->ops->enable_vlan_filter(h, false); #endif @@ -359,7 +360,8 @@ static void hns3_selftest_restore(struct net_device *ndev, bool if_running) h->ae_algo->ops->halt_autoneg(h, false); #if IS_ENABLED(CONFIG_VLAN_8021Q) - if (h->ae_algo->ops->enable_vlan_filter) + if (h->ae_algo->ops->enable_vlan_filter && + ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) h->ae_algo->ops->enable_vlan_filter(h, true); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index ac9b69513332..9c2eeaa82294 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -467,7 +467,7 @@ err_csq: return ret; } -static int hclge_firmware_compat_config(struct hclge_dev *hdev) +static int hclge_firmware_compat_config(struct hclge_dev *hdev, bool en) { struct hclge_firmware_compat_cmd *req; struct hclge_desc desc; @@ -475,13 +475,16 @@ static int hclge_firmware_compat_config(struct hclge_dev *hdev) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_IMP_COMPAT_CFG, false); - req = (struct hclge_firmware_compat_cmd *)desc.data; + if (en) { + req = (struct hclge_firmware_compat_cmd *)desc.data; - hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1); - hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1); - if (hnae3_dev_phy_imp_supported(hdev)) - hnae3_set_bit(compat, HCLGE_PHY_IMP_EN_B, 1); - req->compat = cpu_to_le32(compat); + hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1); + hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1); + if (hnae3_dev_phy_imp_supported(hdev)) + hnae3_set_bit(compat, HCLGE_PHY_IMP_EN_B, 1); + + req->compat = cpu_to_le32(compat); + } return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -538,7 +541,7 @@ int hclge_cmd_init(struct hclge_dev *hdev) /* ask the firmware to enable some features, driver can work without * it. */ - ret = hclge_firmware_compat_config(hdev); + ret = hclge_firmware_compat_config(hdev, true); if (ret) dev_warn(&hdev->pdev->dev, "Firmware compatible features not enabled(%d).\n", @@ -568,6 +571,8 @@ static void hclge_cmd_uninit_regs(struct hclge_hw *hw) void hclge_cmd_uninit(struct hclge_dev *hdev) { + hclge_firmware_compat_config(hdev, false); + set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); /* wait to ensure that the firmware completes the possible left * over commands. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 4a619e5d3f35..307c9e830510 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -247,6 +247,10 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) } hclge_tm_schd_info_update(hdev, num_tc); + if (num_tc > 1) + hdev->flag |= HCLGE_FLAG_DCB_ENABLE; + else + hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; ret = hclge_ieee_ets_to_tm_info(hdev, ets); if (ret) @@ -306,8 +310,7 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) u8 i, j, pfc_map, *prio_tc; int ret; - if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || - hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) + if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; if (pfc->pfc_en == hdev->tm_info.pfc_en) @@ -441,8 +444,6 @@ static int hclge_mqprio_qopt_check(struct hclge_dev *hdev, static void hclge_sync_mqprio_qopt(struct hnae3_tc_info *tc_info, struct tc_mqprio_qopt_offload *mqprio_qopt) { - int i; - memset(tc_info, 0, sizeof(*tc_info)); tc_info->num_tc = mqprio_qopt->qopt.num_tc; memcpy(tc_info->prio_tc, mqprio_qopt->qopt.prio_tc_map, @@ -451,9 +452,6 @@ static void hclge_sync_mqprio_qopt(struct hnae3_tc_info *tc_info, sizeof_field(struct hnae3_tc_info, tqp_count)); memcpy(tc_info->tqp_offset, mqprio_qopt->qopt.offset, sizeof_field(struct hnae3_tc_info, tqp_offset)); - - for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) - set_bit(tc_info->prio_tc[i], &tc_info->tc_en); } static int hclge_config_tc(struct hclge_dev *hdev, @@ -519,12 +517,17 @@ static int hclge_setup_tc(struct hnae3_handle *h, return hclge_notify_init_up(hdev); err_out: - /* roll-back */ - memcpy(&kinfo->tc_info, &old_tc_info, sizeof(old_tc_info)); - if (hclge_config_tc(hdev, &kinfo->tc_info)) - dev_err(&hdev->pdev->dev, - "failed to roll back tc configuration\n"); - + if (!tc) { + dev_warn(&hdev->pdev->dev, + "failed to destroy mqprio, will active after reset, ret = %d\n", + ret); + } else { + /* roll-back */ + memcpy(&kinfo->tc_info, &old_tc_info, sizeof(old_tc_info)); + if (hclge_config_tc(hdev, &kinfo->tc_info)) + dev_err(&hdev->pdev->dev, + "failed to roll back tc configuration\n"); + } hclge_notify_init_up(hdev); return ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 87d96f82c318..32f62cd2dd99 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -719,9 +719,9 @@ static void hclge_dbg_fill_shaper_content(struct hclge_tm_shaper_para *para, sprintf(result[(*index)++], "%6u", para->rate); } -static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) +static int __hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *data_str, + char *buf, int len) { - char data_str[ARRAY_SIZE(tm_pg_items)][HCLGE_DBG_DATA_STR_LEN]; struct hclge_tm_shaper_para c_shaper_para, p_shaper_para; char *result[ARRAY_SIZE(tm_pg_items)], *sch_mode_str; u8 pg_id, sch_mode, weight, pri_bit_map, i, j; @@ -729,8 +729,10 @@ static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) int pos = 0; int ret; - for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++) - result[i] = &data_str[i][0]; + for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++) { + result[i] = data_str; + data_str += HCLGE_DBG_DATA_STR_LEN; + } hclge_dbg_fill_content(content, sizeof(content), tm_pg_items, NULL, ARRAY_SIZE(tm_pg_items)); @@ -781,6 +783,24 @@ static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) return 0; } +static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) +{ + char *data_str; + int ret; + + data_str = kcalloc(ARRAY_SIZE(tm_pg_items), + HCLGE_DBG_DATA_STR_LEN, GFP_KERNEL); + + if (!data_str) + return -ENOMEM; + + ret = __hclge_dbg_dump_tm_pg(hdev, data_str, buf, len); + + kfree(data_str); + + return ret; +} + static int hclge_dbg_dump_tm_port(struct hclge_dev *hdev, char *buf, int len) { struct hclge_tm_shaper_para shaper_para; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 47fea8985861..f5b8d1fee0f1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8708,15 +8708,8 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, } /* check if we just hit the duplicate */ - if (!ret) { - dev_warn(&hdev->pdev->dev, "VF %u mac(%pM) exists\n", - vport->vport_id, addr); - return 0; - } - - dev_err(&hdev->pdev->dev, - "PF failed to add unicast entry(%pM) in the MAC table\n", - addr); + if (!ret) + return -EEXIST; return ret; } @@ -8868,7 +8861,13 @@ static void hclge_sync_vport_mac_list(struct hclge_vport *vport, } else { set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state); - break; + + /* If one unicast mac address is existing in hardware, + * we need to try whether other unicast mac addresses + * are new addresses that can be added. + */ + if (ret != -EEXIST) + break; } } } @@ -12797,8 +12796,12 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev) continue; if (vport->vf_info.trusted) { - uc_en = vport->vf_info.request_uc_en > 0; - mc_en = vport->vf_info.request_mc_en > 0; + uc_en = vport->vf_info.request_uc_en > 0 || + vport->overflow_promisc_flags & + HNAE3_OVERFLOW_UPE; + mc_en = vport->vf_info.request_mc_en > 0 || + vport->overflow_promisc_flags & + HNAE3_OVERFLOW_MPE; } bc_en = vport->vf_info.request_bc_en > 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 44618cc4cca1..f314dbd3ce11 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -687,12 +687,10 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) for (i = 0; i < HNAE3_MAX_TC; i++) { if (hdev->hw_tc_map & BIT(i) && i < kinfo->tc_info.num_tc) { - set_bit(i, &kinfo->tc_info.tc_en); kinfo->tc_info.tqp_offset[i] = i * kinfo->rss_size; kinfo->tc_info.tqp_count[i] = kinfo->rss_size; } else { /* Set to default queue if TC is disable */ - clear_bit(i, &kinfo->tc_info.tc_en); kinfo->tc_info.tqp_offset[i] = 0; kinfo->tc_info.tqp_count[i] = 1; } @@ -729,14 +727,6 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev) for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) hdev->tm_info.prio_tc[i] = (i >= hdev->tm_info.num_tc) ? 0 : i; - - /* DCB is enabled if we have more than 1 TC or pfc_en is - * non-zero. - */ - if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en) - hdev->flag |= HCLGE_FLAG_DCB_ENABLE; - else - hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; } static void hclge_tm_pg_info_init(struct hclge_dev *hdev) @@ -767,10 +757,10 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev) static void hclge_update_fc_mode_by_dcb_flag(struct hclge_dev *hdev) { - if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) { + if (hdev->tm_info.num_tc == 1 && !hdev->tm_info.pfc_en) { if (hdev->fc_mode_last_time == HCLGE_FC_PFC) dev_warn(&hdev->pdev->dev, - "DCB is disable, but last mode is FC_PFC\n"); + "Only 1 tc used, but last mode is FC_PFC\n"); hdev->tm_info.fc_mode = hdev->fc_mode_last_time; } else if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) { @@ -796,7 +786,7 @@ static void hclge_update_fc_mode(struct hclge_dev *hdev) } } -static void hclge_pfc_info_init(struct hclge_dev *hdev) +void hclge_tm_pfc_info_update(struct hclge_dev *hdev) { if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) hclge_update_fc_mode(hdev); @@ -812,7 +802,7 @@ static void hclge_tm_schd_info_init(struct hclge_dev *hdev) hclge_tm_vport_info_update(hdev); - hclge_pfc_info_init(hdev); + hclge_tm_pfc_info_update(hdev); } static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev) @@ -1558,19 +1548,6 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc) hclge_tm_schd_info_init(hdev); } -void hclge_tm_pfc_info_update(struct hclge_dev *hdev) -{ - /* DCB is enabled if we have more than 1 TC or pfc_en is - * non-zero. - */ - if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en) - hdev->flag |= HCLGE_FLAG_DCB_ENABLE; - else - hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; - - hclge_pfc_info_init(hdev); -} - int hclge_tm_init_hw(struct hclge_dev *hdev, bool init) { int ret; @@ -1616,7 +1593,7 @@ int hclge_tm_vport_map_update(struct hclge_dev *hdev) if (ret) return ret; - if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) + if (hdev->tm_info.num_tc == 1 && !hdev->tm_info.pfc_en) return 0; return hclge_tm_bp_setup(hdev); diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 3e54017a2a5b..07fdab58001d 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -354,7 +354,7 @@ static int hns_mdio_reset(struct mii_bus *bus) if (dev_of_node(bus->parent)) { if (!mdio_dev->subctrl_vbase) { - dev_err(&bus->dev, "mdio sys ctl reg has not maped\n"); + dev_err(&bus->dev, "mdio sys ctl reg has not mapped\n"); return -ENODEV; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index a4579b340120..6aa6ff89a765 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4708,14 +4708,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, return 0; } - if (adapter->failover_pending) { - adapter->init_done_rc = -EAGAIN; - netdev_dbg(netdev, "Failover pending, ignoring login response\n"); - complete(&adapter->init_done); - /* login response buffer will be released on reset */ - return 0; - } - netdev->mtu = adapter->req_mtu - ETH_HLEN; netdev_dbg(adapter->netdev, "Login Response Buffer:\n"); diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 373eb027b925..09ae1939e6db 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2437,11 +2437,15 @@ static void e100_get_drvinfo(struct net_device *netdev, sizeof(info->bus_info)); } -#define E100_PHY_REGS 0x1C +#define E100_PHY_REGS 0x1D static int e100_get_regs_len(struct net_device *netdev) { struct nic *nic = netdev_priv(netdev); - return 1 + E100_PHY_REGS + sizeof(nic->mem->dump_buf); + + /* We know the number of registers, and the size of the dump buffer. + * Calculate the total size in bytes. + */ + return (1 + E100_PHY_REGS) * sizeof(u32) + sizeof(nic->mem->dump_buf); } static void e100_get_regs(struct net_device *netdev, @@ -2455,14 +2459,18 @@ static void e100_get_regs(struct net_device *netdev, buff[0] = ioread8(&nic->csr->scb.cmd_hi) << 24 | ioread8(&nic->csr->scb.cmd_lo) << 16 | ioread16(&nic->csr->scb.status); - for (i = E100_PHY_REGS; i >= 0; i--) - buff[1 + E100_PHY_REGS - i] = - mdio_read(netdev, nic->mii.phy_id, i); + for (i = 0; i < E100_PHY_REGS; i++) + /* Note that we read the registers in reverse order. This + * ordering is the ABI apparently used by ethtool and other + * applications. + */ + buff[1 + i] = mdio_read(netdev, nic->mii.phy_id, + E100_PHY_REGS - 1 - i); memset(nic->mem->dump_buf, 0, sizeof(nic->mem->dump_buf)); e100_exec_cb(nic, NULL, e100_dump); msleep(10); - memcpy(&buff[2 + E100_PHY_REGS], nic->mem->dump_buf, - sizeof(nic->mem->dump_buf)); + memcpy(&buff[1 + E100_PHY_REGS], nic->mem->dump_buf, + sizeof(nic->mem->dump_buf)); } static void e100_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index fc26e4ddeb0d..beda8e0ef7d4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3208,7 +3208,7 @@ static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter) max_combined = ixgbe_max_rss_indices(adapter); } - return max_combined; + return min_t(int, max_combined, num_online_cpus()); } static void ixgbe_get_channels(struct net_device *dev, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 24e06ba6f5e9..13c4782b920a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10112,6 +10112,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) struct ixgbe_adapter *adapter = netdev_priv(dev); struct bpf_prog *old_prog; bool need_reset; + int num_queues; if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) return -EINVAL; @@ -10161,11 +10162,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) /* Kick start the NAPI context if there is an AF_XDP socket open * on that queue id. This so that receiving will start. */ - if (need_reset && prog) - for (i = 0; i < adapter->num_rx_queues; i++) + if (need_reset && prog) { + num_queues = min_t(int, adapter->num_rx_queues, + adapter->num_xdp_queues); + for (i = 0; i < num_queues; i++) if (adapter->xdp_ring[i]->xsk_pool) (void)ixgbe_xsk_wakeup(adapter->netdev, i, XDP_WAKEUP_RX); + } return 0; } diff --git a/drivers/net/ethernet/micrel/Makefile b/drivers/net/ethernet/micrel/Makefile index 5cc00d22c708..6ecc4eb30e74 100644 --- a/drivers/net/ethernet/micrel/Makefile +++ b/drivers/net/ethernet/micrel/Makefile @@ -4,8 +4,6 @@ # obj-$(CONFIG_KS8842) += ks8842.o -obj-$(CONFIG_KS8851) += ks8851.o -ks8851-objs = ks8851_common.o ks8851_spi.o -obj-$(CONFIG_KS8851_MLL) += ks8851_mll.o -ks8851_mll-objs = ks8851_common.o ks8851_par.o +obj-$(CONFIG_KS8851) += ks8851_common.o ks8851_spi.o +obj-$(CONFIG_KS8851_MLL) += ks8851_common.o ks8851_par.o obj-$(CONFIG_KSZ884X_PCI) += ksz884x.o diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 3f69bb59ba49..a6db1a8156e1 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -1057,6 +1057,7 @@ int ks8851_suspend(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(ks8851_suspend); int ks8851_resume(struct device *dev) { @@ -1070,6 +1071,7 @@ int ks8851_resume(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(ks8851_resume); #endif static int ks8851_register_mdiobus(struct ks8851_net *ks, struct device *dev) @@ -1243,6 +1245,7 @@ err_reg: err_reg_io: return ret; } +EXPORT_SYMBOL_GPL(ks8851_probe_common); int ks8851_remove_common(struct device *dev) { @@ -1261,3 +1264,8 @@ int ks8851_remove_common(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(ks8851_remove_common); + +MODULE_DESCRIPTION("KS8851 Network driver"); +MODULE_AUTHOR("Ben Dooks "); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c index 58a854666c62..c14de5fcedea 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -380,15 +380,6 @@ static void ionic_sw_stats_get_txq_values(struct ionic_lif *lif, u64 **buf, &ionic_dbg_intr_stats_desc[i]); (*buf)++; } - for (i = 0; i < IONIC_NUM_DBG_NAPI_STATS; i++) { - **buf = IONIC_READ_STAT64(&txqcq->napi_stats, - &ionic_dbg_napi_stats_desc[i]); - (*buf)++; - } - for (i = 0; i < IONIC_MAX_NUM_NAPI_CNTR; i++) { - **buf = txqcq->napi_stats.work_done_cntr[i]; - (*buf)++; - } for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { **buf = txstats->sg_cntr[i]; (*buf)++; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 553c4403258a..981ccf47dcea 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -486,6 +486,10 @@ bool stmmac_eee_init(struct stmmac_priv *priv) timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS, eee_tw_timer); + if (priv->hw->xpcs) + xpcs_config_eee(priv->hw->xpcs, + priv->plat->mult_fact_100ns, + true); } if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) { diff --git a/drivers/net/ethernet/sun/Kconfig b/drivers/net/ethernet/sun/Kconfig index 309de38a7530..b0d3f9a2950c 100644 --- a/drivers/net/ethernet/sun/Kconfig +++ b/drivers/net/ethernet/sun/Kconfig @@ -73,6 +73,7 @@ config CASSINI config SUNVNET_COMMON tristate "Common routines to support Sun Virtual Networking" depends on SUN_LDOMS + depends on INET default m config SUNVNET diff --git a/drivers/net/hamradio/Kconfig b/drivers/net/hamradio/Kconfig index f4843f9672c1..441da03c23ee 100644 --- a/drivers/net/hamradio/Kconfig +++ b/drivers/net/hamradio/Kconfig @@ -48,6 +48,7 @@ config BPQETHER config DMASCC tristate "High-speed (DMA) SCC driver for AX.25" depends on ISA && AX25 && BROKEN_ON_SMP && ISA_DMA_API + depends on VIRT_TO_BUS help This is a driver for high-speed SCC boards, i.e. those supporting DMA on one port. You usually use those boards to connect your diff --git a/drivers/net/mdio/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c index 0d7d3e15d2f0..5f4cd24a0241 100644 --- a/drivers/net/mdio/mdio-ipq4019.c +++ b/drivers/net/mdio/mdio-ipq4019.c @@ -207,6 +207,7 @@ static int ipq4019_mdio_probe(struct platform_device *pdev) { struct ipq4019_mdio_data *priv; struct mii_bus *bus; + struct resource *res; int ret; bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*priv)); @@ -224,7 +225,10 @@ static int ipq4019_mdio_probe(struct platform_device *pdev) return PTR_ERR(priv->mdio_clk); /* The platform resource is provided on the chipset IPQ5018 */ - priv->eth_ldo_rdy = devm_platform_ioremap_resource(pdev, 1); + /* This resource is optional */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (res) + priv->eth_ldo_rdy = devm_ioremap_resource(&pdev->dev, res); bus->name = "ipq4019_mdio"; bus->read = ipq4019_mdio_read; diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index 1ee592d3eae4..17f98f609ec8 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -134,8 +134,9 @@ static int mscc_miim_reset(struct mii_bus *bus) static int mscc_miim_probe(struct platform_device *pdev) { - struct mii_bus *bus; struct mscc_miim_dev *dev; + struct resource *res; + struct mii_bus *bus; int ret; bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*dev)); @@ -156,10 +157,14 @@ static int mscc_miim_probe(struct platform_device *pdev) return PTR_ERR(dev->regs); } - dev->phy_regs = devm_platform_ioremap_resource(pdev, 1); - if (IS_ERR(dev->phy_regs)) { - dev_err(&pdev->dev, "Unable to map internal phy registers\n"); - return PTR_ERR(dev->phy_regs); + /* This resource is optional */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (res) { + dev->phy_regs = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(dev->phy_regs)) { + dev_err(&pdev->dev, "Unable to map internal phy registers\n"); + return PTR_ERR(dev->phy_regs); + } } ret = of_mdiobus_register(bus, pdev->dev.of_node); diff --git a/drivers/net/mhi_net.c b/drivers/net/mhi_net.c index d127eb6e9257..aaa628f859fd 100644 --- a/drivers/net/mhi_net.c +++ b/drivers/net/mhi_net.c @@ -321,7 +321,7 @@ static int mhi_net_newlink(struct mhi_device *mhi_dev, struct net_device *ndev) /* Start MHI channels */ err = mhi_prepare_for_transfer(mhi_dev); if (err) - goto out_err; + return err; /* Number of transfer descriptors determines size of the queue */ mhi_netdev->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE); @@ -331,10 +331,6 @@ static int mhi_net_newlink(struct mhi_device *mhi_dev, struct net_device *ndev) return err; return 0; - -out_err: - free_netdev(ndev); - return err; } static void mhi_net_dellink(struct mhi_device *mhi_dev, struct net_device *ndev) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index e79297a4bae8..27b6a3f507ae 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -27,7 +27,12 @@ #define MII_BCM7XXX_SHD_2_ADDR_CTRL 0xe #define MII_BCM7XXX_SHD_2_CTRL_STAT 0xf #define MII_BCM7XXX_SHD_2_BIAS_TRIM 0x1a +#define MII_BCM7XXX_SHD_3_PCS_CTRL 0x0 +#define MII_BCM7XXX_SHD_3_PCS_STATUS 0x1 +#define MII_BCM7XXX_SHD_3_EEE_CAP 0x2 #define MII_BCM7XXX_SHD_3_AN_EEE_ADV 0x3 +#define MII_BCM7XXX_SHD_3_EEE_LP 0x4 +#define MII_BCM7XXX_SHD_3_EEE_WK_ERR 0x5 #define MII_BCM7XXX_SHD_3_PCS_CTRL_2 0x6 #define MII_BCM7XXX_PCS_CTRL_2_DEF 0x4400 #define MII_BCM7XXX_SHD_3_AN_STAT 0xb @@ -216,25 +221,37 @@ static int bcm7xxx_28nm_resume(struct phy_device *phydev) return genphy_config_aneg(phydev); } -static int phy_set_clr_bits(struct phy_device *dev, int location, - int set_mask, int clr_mask) +static int __phy_set_clr_bits(struct phy_device *dev, int location, + int set_mask, int clr_mask) { int v, ret; - v = phy_read(dev, location); + v = __phy_read(dev, location); if (v < 0) return v; v &= ~clr_mask; v |= set_mask; - ret = phy_write(dev, location, v); + ret = __phy_write(dev, location, v); if (ret < 0) return ret; return v; } +static int phy_set_clr_bits(struct phy_device *dev, int location, + int set_mask, int clr_mask) +{ + int ret; + + mutex_lock(&dev->mdio.bus->mdio_lock); + ret = __phy_set_clr_bits(dev, location, set_mask, clr_mask); + mutex_unlock(&dev->mdio.bus->mdio_lock); + + return ret; +} + static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev) { int ret; @@ -398,6 +415,93 @@ static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev) return bcm7xxx_28nm_ephy_apd_enable(phydev); } +#define MII_BCM7XXX_REG_INVALID 0xff + +static u8 bcm7xxx_28nm_ephy_regnum_to_shd(u16 regnum) +{ + switch (regnum) { + case MDIO_CTRL1: + return MII_BCM7XXX_SHD_3_PCS_CTRL; + case MDIO_STAT1: + return MII_BCM7XXX_SHD_3_PCS_STATUS; + case MDIO_PCS_EEE_ABLE: + return MII_BCM7XXX_SHD_3_EEE_CAP; + case MDIO_AN_EEE_ADV: + return MII_BCM7XXX_SHD_3_AN_EEE_ADV; + case MDIO_AN_EEE_LPABLE: + return MII_BCM7XXX_SHD_3_EEE_LP; + case MDIO_PCS_EEE_WK_ERR: + return MII_BCM7XXX_SHD_3_EEE_WK_ERR; + default: + return MII_BCM7XXX_REG_INVALID; + } +} + +static bool bcm7xxx_28nm_ephy_dev_valid(int devnum) +{ + return devnum == MDIO_MMD_AN || devnum == MDIO_MMD_PCS; +} + +static int bcm7xxx_28nm_ephy_read_mmd(struct phy_device *phydev, + int devnum, u16 regnum) +{ + u8 shd = bcm7xxx_28nm_ephy_regnum_to_shd(regnum); + int ret; + + if (!bcm7xxx_28nm_ephy_dev_valid(devnum) || + shd == MII_BCM7XXX_REG_INVALID) + return -EOPNOTSUPP; + + /* set shadow mode 2 */ + ret = __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Access the desired shadow register address */ + ret = __phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, shd); + if (ret < 0) + goto reset_shadow_mode; + + ret = __phy_read(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT); + +reset_shadow_mode: + /* reset shadow mode 2 */ + __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); + return ret; +} + +static int bcm7xxx_28nm_ephy_write_mmd(struct phy_device *phydev, + int devnum, u16 regnum, u16 val) +{ + u8 shd = bcm7xxx_28nm_ephy_regnum_to_shd(regnum); + int ret; + + if (!bcm7xxx_28nm_ephy_dev_valid(devnum) || + shd == MII_BCM7XXX_REG_INVALID) + return -EOPNOTSUPP; + + /* set shadow mode 2 */ + ret = __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Access the desired shadow register address */ + ret = __phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, shd); + if (ret < 0) + goto reset_shadow_mode; + + /* Write the desired value in the shadow register */ + __phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, val); + +reset_shadow_mode: + /* reset shadow mode 2 */ + return __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); +} + static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev) { int ret; @@ -595,6 +699,8 @@ static void bcm7xxx_28nm_remove(struct phy_device *phydev) .get_stats = bcm7xxx_28nm_get_phy_stats, \ .probe = bcm7xxx_28nm_probe, \ .remove = bcm7xxx_28nm_remove, \ + .read_mmd = bcm7xxx_28nm_ephy_read_mmd, \ + .write_mmd = bcm7xxx_28nm_ephy_write_mmd, \ } #define BCM7XXX_40NM_EPHY(_oui, _name) \ diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 53f034fc2ef7..e37edf70f2f8 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -525,6 +525,10 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) NULL == bus->read || NULL == bus->write) return -EINVAL; + if (bus->parent && bus->parent->of_node) + bus->parent->of_node->fwnode.flags |= + FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD; + BUG_ON(bus->state != MDIOBUS_ALLOCATED && bus->state != MDIOBUS_UNREGISTERED); @@ -537,6 +541,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); + put_device(&bus->dev); return -EINVAL; } diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 2d5d5081c3b6..5ce1bf03bbd7 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -493,6 +493,25 @@ static int gpy_loopback(struct phy_device *phydev, bool enable) return ret; } +static int gpy115_loopback(struct phy_device *phydev, bool enable) +{ + int ret; + int fw_minor; + + if (enable) + return gpy_loopback(phydev, enable); + + ret = phy_read(phydev, PHY_FWV); + if (ret < 0) + return ret; + + fw_minor = FIELD_GET(PHY_FWV_MINOR_MASK, ret); + if (fw_minor > 0x0076) + return gpy_loopback(phydev, 0); + + return genphy_soft_reset(phydev); +} + static struct phy_driver gpy_drivers[] = { { PHY_ID_MATCH_MODEL(PHY_ID_GPY2xx), @@ -527,7 +546,7 @@ static struct phy_driver gpy_drivers[] = { .handle_interrupt = gpy_handle_interrupt, .set_wol = gpy_set_wol, .get_wol = gpy_get_wol, - .set_loopback = gpy_loopback, + .set_loopback = gpy115_loopback, }, { PHY_ID_MATCH_MODEL(PHY_ID_GPY115C), @@ -544,7 +563,7 @@ static struct phy_driver gpy_drivers[] = { .handle_interrupt = gpy_handle_interrupt, .set_wol = gpy_set_wol, .get_wol = gpy_get_wol, - .set_loopback = gpy_loopback, + .set_loopback = gpy115_loopback, }, { .phy_id = PHY_ID_GPY211B, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 7d953974eb9b..26b1bd8e845b 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1178,7 +1178,10 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) static void smsc95xx_handle_link_change(struct net_device *net) { + struct usbnet *dev = netdev_priv(net); + phy_print_status(net->phydev); + usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); } static int smsc95xx_start_phy(struct usbnet *dev) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index ffa894f7312a..0adae76eb8df 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1867,8 +1867,8 @@ mac80211_hwsim_beacon(struct hrtimer *timer) bcn_int -= data->bcn_delta; data->bcn_delta = 0; } - hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer), - ns_to_ktime(bcn_int * NSEC_PER_USEC)); + hrtimer_forward_now(&data->beacon_timer, + ns_to_ktime(bcn_int * NSEC_PER_USEC)); return HRTIMER_RESTART; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 72de88ff0d30..ef4950f80832 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -380,7 +380,6 @@ static int pmem_attach_disk(struct device *dev, struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; struct request_queue *q; - struct device *gendev; struct gendisk *disk; void *addr; int rc; @@ -489,10 +488,8 @@ static int pmem_attach_disk(struct device *dev, } dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); pmem->dax_dev = dax_dev; - gendev = disk_to_dev(disk); - gendev->groups = pmem_attribute_groups; - device_add_disk(dev, disk, NULL); + device_add_disk(dev, disk, pmem_attribute_groups); if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) return -ENOMEM; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e486845d2c7e..7712a8f78337 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -978,6 +978,7 @@ EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) { struct nvme_command *cmd = nvme_req(req)->cmd; + struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; blk_status_t ret = BLK_STS_OK; if (!(req->rq_flags & RQF_DONTPREP)) { @@ -1026,7 +1027,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) return BLK_STS_IOERR; } - nvme_req(req)->genctr++; + if (!(ctrl->quirks & NVME_QUIRK_SKIP_CID_GEN)) + nvme_req(req)->genctr++; cmd->common.command_id = nvme_cid(req); trace_nvme_setup_cmd(req, cmd); return ret; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9871c0c9374c..ed79a6c7e804 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -138,6 +138,12 @@ enum nvme_quirks { * 48 bits. */ NVME_QUIRK_DMA_ADDRESS_BITS_48 = (1 << 16), + + /* + * The controller requires the command_id value be be limited, so skip + * encoding the generation sequence number. + */ + NVME_QUIRK_SKIP_CID_GEN = (1 << 17), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b82492cd7503..456a0e8a5718 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3369,7 +3369,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005), .driver_data = NVME_QUIRK_SINGLE_VECTOR | NVME_QUIRK_128_BYTES_SQES | - NVME_QUIRK_SHARED_TAGS }, + NVME_QUIRK_SHARED_TAGS | + NVME_QUIRK_SKIP_CID_GEN }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { 0, } diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 3cbc3baf087f..295cc7952d0e 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -952,6 +952,8 @@ int armpmu_register(struct arm_pmu *pmu) pmu->name, pmu->num_events, has_nmi ? ", using NMIs" : ""); + kvm_host_pmu_init(pmu); + return 0; out_destroy: diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index a4ac87c8b4f8..5082102d7d0d 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2306,7 +2306,7 @@ EXPORT_SYMBOL_GPL(devm_pinctrl_register_and_init); /** * devm_pinctrl_unregister() - Resource managed version of pinctrl_unregister(). - * @dev: device for which which resource was allocated + * @dev: device for which resource was allocated * @pctldev: the pinctrl device to unregister. */ void devm_pinctrl_unregister(struct device *dev, struct pinctrl_dev *pctldev) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index c001f2ed20f8..8d0f88e9ca88 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -445,6 +445,7 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3); + int err; raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); @@ -457,6 +458,15 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) writel(pin_reg, gpio_dev->base + (d->hwirq)*4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + if (on) + err = enable_irq_wake(gpio_dev->irq); + else + err = disable_irq_wake(gpio_dev->irq); + + if (err) + dev_err(&gpio_dev->pdev->dev, "failed to %s wake-up interrupt\n", + on ? "enable" : "disable"); + return 0; } @@ -902,7 +912,6 @@ static struct pinctrl_desc amd_pinctrl_desc = { static int amd_gpio_probe(struct platform_device *pdev) { int ret = 0; - int irq_base; struct resource *res; struct amd_gpio *gpio_dev; struct gpio_irq_chip *girq; @@ -925,9 +934,9 @@ static int amd_gpio_probe(struct platform_device *pdev) if (!gpio_dev->base) return -ENOMEM; - irq_base = platform_get_irq(pdev, 0); - if (irq_base < 0) - return irq_base; + gpio_dev->irq = platform_get_irq(pdev, 0); + if (gpio_dev->irq < 0) + return gpio_dev->irq; #ifdef CONFIG_PM_SLEEP gpio_dev->saved_regs = devm_kcalloc(&pdev->dev, amd_pinctrl_desc.npins, @@ -987,7 +996,7 @@ static int amd_gpio_probe(struct platform_device *pdev) goto out2; } - ret = devm_request_irq(&pdev->dev, irq_base, amd_gpio_irq_handler, + ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler, IRQF_SHARED, KBUILD_MODNAME, gpio_dev); if (ret) goto out2; diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 95e763424042..1d4317073654 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -98,6 +98,7 @@ struct amd_gpio { struct resource *res; struct platform_device *pdev; u32 *saved_regs; + int irq; }; /* KERNCZ configuration*/ diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index ae33e376695f..5ce260f152ce 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -2092,6 +2092,23 @@ static bool rockchip_pinconf_pull_valid(struct rockchip_pin_ctrl *ctrl, return false; } +static int rockchip_pinconf_defer_output(struct rockchip_pin_bank *bank, + unsigned int pin, u32 arg) +{ + struct rockchip_pin_output_deferred *cfg; + + cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) + return -ENOMEM; + + cfg->pin = pin; + cfg->arg = arg; + + list_add_tail(&cfg->head, &bank->deferred_output); + + return 0; +} + /* set the pin config settings for a specified pin */ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, unsigned long *configs, unsigned num_configs) @@ -2136,6 +2153,22 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, if (rc != RK_FUNC_GPIO) return -EINVAL; + /* + * Check for gpio driver not being probed yet. + * The lock makes sure that either gpio-probe has completed + * or the gpio driver hasn't probed yet. + */ + mutex_lock(&bank->deferred_lock); + if (!gpio || !gpio->direction_output) { + rc = rockchip_pinconf_defer_output(bank, pin - bank->pin_base, arg); + mutex_unlock(&bank->deferred_lock); + if (rc) + return rc; + + break; + } + mutex_unlock(&bank->deferred_lock); + rc = gpio->direction_output(gpio, pin - bank->pin_base, arg); if (rc) @@ -2204,6 +2237,11 @@ static int rockchip_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin, if (rc != RK_FUNC_GPIO) return -EINVAL; + if (!gpio || !gpio->get) { + arg = 0; + break; + } + rc = gpio->get(gpio, pin - bank->pin_base); if (rc < 0) return rc; @@ -2450,6 +2488,9 @@ static int rockchip_pinctrl_register(struct platform_device *pdev, pin_bank->name, pin); pdesc++; } + + INIT_LIST_HEAD(&pin_bank->deferred_output); + mutex_init(&pin_bank->deferred_lock); } ret = rockchip_pinctrl_parse_dt(pdev, info); @@ -2716,6 +2757,31 @@ static int rockchip_pinctrl_probe(struct platform_device *pdev) return 0; } +static int rockchip_pinctrl_remove(struct platform_device *pdev) +{ + struct rockchip_pinctrl *info = platform_get_drvdata(pdev); + struct rockchip_pin_bank *bank; + struct rockchip_pin_output_deferred *cfg; + int i; + + of_platform_depopulate(&pdev->dev); + + for (i = 0; i < info->ctrl->nr_banks; i++) { + bank = &info->ctrl->pin_banks[i]; + + mutex_lock(&bank->deferred_lock); + while (!list_empty(&bank->deferred_output)) { + cfg = list_first_entry(&bank->deferred_output, + struct rockchip_pin_output_deferred, head); + list_del(&cfg->head); + kfree(cfg); + } + mutex_unlock(&bank->deferred_lock); + } + + return 0; +} + static struct rockchip_pin_bank px30_pin_banks[] = { PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", IOMUX_SOURCE_PMU, IOMUX_SOURCE_PMU, @@ -3175,6 +3241,7 @@ static const struct of_device_id rockchip_pinctrl_dt_match[] = { static struct platform_driver rockchip_pinctrl_driver = { .probe = rockchip_pinctrl_probe, + .remove = rockchip_pinctrl_remove, .driver = { .name = "rockchip-pinctrl", .pm = &rockchip_pinctrl_dev_pm_ops, diff --git a/drivers/pinctrl/pinctrl-rockchip.h b/drivers/pinctrl/pinctrl-rockchip.h index 589d4d2a98c9..91f10279d084 100644 --- a/drivers/pinctrl/pinctrl-rockchip.h +++ b/drivers/pinctrl/pinctrl-rockchip.h @@ -141,6 +141,8 @@ struct rockchip_drv { * @toggle_edge_mode: bit mask to toggle (falling/rising) edge mode * @recalced_mask: bit mask to indicate a need to recalulate the mask * @route_mask: bits describing the routing pins of per bank + * @deferred_output: gpio output settings to be done after gpio bank probed + * @deferred_lock: mutex for the deferred_output shared btw gpio and pinctrl */ struct rockchip_pin_bank { struct device *dev; @@ -169,6 +171,8 @@ struct rockchip_pin_bank { u32 toggle_edge_mode; u32 recalced_mask; u32 route_mask; + struct list_head deferred_output; + struct mutex deferred_lock; }; /** @@ -243,6 +247,12 @@ struct rockchip_pin_config { unsigned int nconfigs; }; +struct rockchip_pin_output_deferred { + struct list_head head; + unsigned int pin; + u32 arg; +}; + /** * struct rockchip_pin_group: represent group of pins of a pinmux function. * @name: name of the pin group, used to lookup the group. diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c index afddf6d60dbe..9017ede409c9 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7280.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c @@ -1496,6 +1496,7 @@ static const struct of_device_id sc7280_pinctrl_of_match[] = { static struct platform_driver sc7280_pinctrl_driver = { .driver = { .name = "sc7280-pinctrl", + .pm = &msm_pinctrl_dev_pm_ops, .of_match_table = sc7280_pinctrl_of_match, }, .probe = sc7280_pinctrl_probe, diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 98bf0e2a2a8d..b2562e893139 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved. + * Copyright (c) 2012-2014, 2016-2021 The Linux Foundation. All rights reserved. */ #include @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -171,6 +172,8 @@ struct pmic_gpio_state { struct pinctrl_dev *ctrl; struct gpio_chip chip; struct irq_chip irq; + u8 usid; + u8 pid_base; }; static const struct pinconf_generic_params pmic_gpio_bindings[] = { @@ -949,12 +952,36 @@ static int pmic_gpio_child_to_parent_hwirq(struct gpio_chip *chip, unsigned int *parent_hwirq, unsigned int *parent_type) { - *parent_hwirq = child_hwirq + 0xc0; + struct pmic_gpio_state *state = gpiochip_get_data(chip); + + *parent_hwirq = child_hwirq + state->pid_base; *parent_type = child_type; return 0; } +static void *pmic_gpio_populate_parent_fwspec(struct gpio_chip *chip, + unsigned int parent_hwirq, + unsigned int parent_type) +{ + struct pmic_gpio_state *state = gpiochip_get_data(chip); + struct irq_fwspec *fwspec; + + fwspec = kzalloc(sizeof(*fwspec), GFP_KERNEL); + if (!fwspec) + return NULL; + + fwspec->fwnode = chip->irq.parent_domain->fwnode; + + fwspec->param_count = 4; + fwspec->param[0] = state->usid; + fwspec->param[1] = parent_hwirq; + /* param[2] must be left as 0 */ + fwspec->param[3] = parent_type; + + return fwspec; +} + static int pmic_gpio_probe(struct platform_device *pdev) { struct irq_domain *parent_domain; @@ -965,6 +992,7 @@ static int pmic_gpio_probe(struct platform_device *pdev) struct pmic_gpio_pad *pad, *pads; struct pmic_gpio_state *state; struct gpio_irq_chip *girq; + const struct spmi_device *parent_spmi_dev; int ret, npins, i; u32 reg; @@ -984,6 +1012,9 @@ static int pmic_gpio_probe(struct platform_device *pdev) state->dev = &pdev->dev; state->map = dev_get_regmap(dev->parent, NULL); + parent_spmi_dev = to_spmi_device(dev->parent); + state->usid = parent_spmi_dev->usid; + state->pid_base = reg >> 8; pindesc = devm_kcalloc(dev, npins, sizeof(*pindesc), GFP_KERNEL); if (!pindesc) @@ -1059,7 +1090,7 @@ static int pmic_gpio_probe(struct platform_device *pdev) girq->fwnode = of_node_to_fwnode(state->dev->of_node); girq->parent_domain = parent_domain; girq->child_to_parent_hwirq = pmic_gpio_child_to_parent_hwirq; - girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_fourcell; + girq->populate_parent_alloc_arg = pmic_gpio_populate_parent_fwspec; girq->child_offset_to_irq = pmic_gpio_child_offset_to_irq; girq->child_irq_domain_ops.translate = pmic_gpio_domain_translate; diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index 3dd519dfc473..d0096cd7096a 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -15,8 +15,6 @@ #include #include -struct pvclock_vsyscall_time_info *hv_clock; - static phys_addr_t clock_pair_gpa; static struct kvm_clock_pairing clock_pair; @@ -28,8 +26,7 @@ int kvm_arch_ptp_init(void) return -ENODEV; clock_pair_gpa = slow_virt_to_phys(&clock_pair); - hv_clock = pvclock_get_pvti_cpu0_va(); - if (!hv_clock) + if (!pvclock_get_pvti_cpu0_va()) return -ENODEV; ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, @@ -64,10 +61,8 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, struct pvclock_vcpu_time_info *src; unsigned int version; long ret; - int cpu; - cpu = smp_processor_id(); - src = &hv_clock[cpu].pvti; + src = this_cpu_pvti(); do { /* diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index f3c656975e05..93695d535380 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -262,10 +262,12 @@ static int blacklist_parse_proc_parameters(char *buf) if (strcmp("free", parm) == 0) { rc = blacklist_parse_parameters(buf, free, 0); - /* There could be subchannels without proper devices connected. - * evaluate all the entries + /* + * Evaluate the subchannels without an online device. This way, + * no path-verification will be triggered on those subchannels + * and it avoids unnecessary delays. */ - css_schedule_eval_all(); + css_schedule_eval_cond(CSS_EVAL_NOT_ONLINE, 0); } else if (strcmp("add", parm) == 0) rc = blacklist_parse_parameters(buf, add, 0); else if (strcmp("purge", parm) == 0) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 3377097e65de..44461928aab8 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -788,27 +788,49 @@ static int __unset_registered(struct device *dev, void *data) return 0; } -void css_schedule_eval_all_unreg(unsigned long delay) +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) + idset_sch_del(set, sch->schid); + + return 0; +} + +void css_schedule_eval_cond(enum css_eval_cond cond, unsigned long delay) { unsigned long flags; - struct idset *unreg_set; + struct idset *set; /* Find unregistered subchannels. */ - unreg_set = idset_sch_new(); - if (!unreg_set) { + set = idset_sch_new(); + if (!set) { /* Fallback. */ css_schedule_eval_all(); return; } - idset_fill(unreg_set); - bus_for_each_dev(&css_bus_type, NULL, unreg_set, __unset_registered); + idset_fill(set); + switch (cond) { + case CSS_EVAL_UNREG: + bus_for_each_dev(&css_bus_type, NULL, set, __unset_registered); + break; + case CSS_EVAL_NOT_ONLINE: + bus_for_each_dev(&css_bus_type, NULL, set, __unset_online); + break; + default: + break; + } + /* Apply to slow_subchannel_set. */ spin_lock_irqsave(&slow_subchannel_lock, flags); - idset_add_set(slow_subchannel_set, unreg_set); + idset_add_set(slow_subchannel_set, set); atomic_set(&css_eval_scheduled, 1); queue_delayed_work(cio_work_q, &slow_path_work, delay); spin_unlock_irqrestore(&slow_subchannel_lock, flags); - idset_free(unreg_set); + idset_free(set); } void css_wait_for_slow_path(void) @@ -820,7 +842,7 @@ void css_wait_for_slow_path(void) void css_schedule_reprobe(void) { /* Schedule with a delay to allow merging of subsequent calls. */ - css_schedule_eval_all_unreg(1 * HZ); + css_schedule_eval_cond(CSS_EVAL_UNREG, 1 * HZ); } EXPORT_SYMBOL_GPL(css_schedule_reprobe); diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h index c98522cbe276..ede0b905bc6f 100644 --- a/drivers/s390/cio/css.h +++ b/drivers/s390/cio/css.h @@ -34,6 +34,14 @@ #define SNID_STATE3_MULTI_PATH 1 #define SNID_STATE3_SINGLE_PATH 0 +/* + * Conditions used to specify which subchannels need evaluation + */ +enum css_eval_cond { + CSS_EVAL_UNREG, /* unregistered subchannels */ + CSS_EVAL_NOT_ONLINE /* sch without an online-device */ +}; + struct path_state { __u8 state1 : 2; /* path state value 1 */ __u8 state2 : 2; /* path state value 2 */ @@ -136,7 +144,7 @@ static inline struct channel_subsystem *css_by_id(u8 cssid) /* Helper functions to build lists for the slow path. */ void css_schedule_eval(struct subchannel_id schid); void css_schedule_eval_all(void); -void css_schedule_eval_all_unreg(unsigned long delay); +void css_schedule_eval_cond(enum css_eval_cond, unsigned long delay); int css_complete_work(void); int sch_is_pseudo_sch(struct subchannel *); diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 118939a7729a..623d5269a52c 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -361,6 +361,7 @@ err_list: mutex_lock(&matrix_dev->lock); list_del(&matrix_mdev->node); mutex_unlock(&matrix_dev->lock); + vfio_uninit_group_dev(&matrix_mdev->vdev); kfree(matrix_mdev); err_dec_available: atomic_inc(&matrix_dev->available_instances); @@ -376,9 +377,10 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev) mutex_lock(&matrix_dev->lock); vfio_ap_mdev_reset_queues(matrix_mdev); list_del(&matrix_mdev->node); + mutex_unlock(&matrix_dev->lock); + vfio_uninit_group_dev(&matrix_mdev->vdev); kfree(matrix_mdev); atomic_inc(&matrix_dev->available_instances); - mutex_unlock(&matrix_dev->lock); } static ssize_t name_show(struct mdev_type *mtype, diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c index 390b07bf92b9..ccbded3353bd 100644 --- a/drivers/scsi/csiostor/csio_init.c +++ b/drivers/scsi/csiostor/csio_init.c @@ -1254,3 +1254,4 @@ MODULE_DEVICE_TABLE(pci, csio_pci_tbl); MODULE_VERSION(CSIO_DRV_VERSION); MODULE_FIRMWARE(FW_FNAME_T5); MODULE_FIRMWARE(FW_FNAME_T6); +MODULE_SOFTDEP("pre: cxgb4"); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index ece60267b971..b26f2699adb2 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2634,7 +2634,7 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, } if (unlikely(logit)) - ql_log(ql_log_warn, fcport->vha, 0x5060, + ql_log(ql_dbg_io, fcport->vha, 0x5060, "NVME-%s ERR Handling - hdl=%x status(%x) tr_len:%x resid=%x ox_id=%x\n", sp->name, sp->handle, comp_status, fd->transferred_length, le32_to_cpu(sts->residual_len), @@ -3491,7 +3491,7 @@ check_scsi_status: out: if (logit) - ql_log(ql_log_warn, fcport->vha, 0x3022, + ql_log(ql_dbg_io, fcport->vha, 0x3022, "FCP command status: 0x%x-0x%x (0x%x) nexus=%ld:%d:%llu portid=%02x%02x%02x oxid=0x%x cdb=%10phN len=0x%x rsp_info=0x%x resid=0x%x fw_resid=0x%x sp=%p cp=%p.\n", comp_status, scsi_status, res, vha->host_no, cp->device->id, cp->device->lun, fcport->d_id.b.domain, diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 43e682297fd5..0a1734f34587 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -118,7 +118,7 @@ static int ses_recv_diag(struct scsi_device *sdev, int page_code, static int ses_send_diag(struct scsi_device *sdev, int page_code, void *buf, int bufflen) { - u32 result; + int result; unsigned char cmd[] = { SEND_DIAGNOSTIC, diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 029c9631ec2b..188de6f91050 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -318,8 +318,7 @@ static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag, enum ufs_trace_str_t str_t) { - int off = (int)tag - hba->nutrs; - struct utp_task_req_desc *descp = &hba->utmrdl_base_addr[off]; + struct utp_task_req_desc *descp = &hba->utmrdl_base_addr[tag]; if (!trace_ufshcd_upiu_enabled()) return; diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index c25ce8f0e0af..07d0250f17c3 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -300,7 +300,7 @@ static void virtscsi_handle_transport_reset(struct virtio_scsi *vscsi, } break; default: - pr_info("Unsupport virtio scsi event reason %x\n", event->reason); + pr_info("Unsupported virtio scsi event reason %x\n", event->reason); } } @@ -392,7 +392,7 @@ static void virtscsi_handle_event(struct work_struct *work) virtscsi_handle_param_change(vscsi, event); break; default: - pr_err("Unsupport virtio scsi event %x\n", event->event); + pr_err("Unsupported virtio scsi event %x\n", event->event); } virtscsi_kick_event(vscsi, event_node); } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 294ba05e6fc9..bd56de7484dc 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1714,6 +1714,9 @@ static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; + if (!mvdev->actual_features) + return; + if (!is_index_valid(mvdev, idx)) return; @@ -2145,6 +2148,8 @@ static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) for (i = 0; i < ndev->mvdev.max_vqs; i++) ndev->vqs[i].ready = false; + + ndev->mvdev.cvq.ready = false; } static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 29a38ecba19e..26e3d90d1e7c 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -665,13 +665,11 @@ static void vduse_vdpa_set_config(struct vdpa_device *vdpa, unsigned int offset, static int vduse_vdpa_reset(struct vdpa_device *vdpa) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - - if (vduse_dev_set_status(dev, 0)) - return -EIO; + int ret = vduse_dev_set_status(dev, 0); vduse_dev_reset(dev); - return 0; + return ret; } static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa) @@ -1593,8 +1591,10 @@ static int vduse_init(void) vduse_irq_wq = alloc_workqueue("vduse-irq", WQ_HIGHPRI | WQ_SYSFS | WQ_UNBOUND, 0); - if (!vduse_irq_wq) + if (!vduse_irq_wq) { + ret = -ENOMEM; goto err_wq; + } ret = vduse_domain_init(); if (ret) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 68198e0f2a63..a03b5a99c2da 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -565,7 +565,7 @@ static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot) } struct vfio_pci_walk_info { - int (*fn)(struct pci_dev *, void *data); + int (*fn)(struct pci_dev *pdev, void *data); void *data; struct pci_dev *pdev; bool slot; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index f41d081777f5..35927ceb26ff 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -640,7 +640,7 @@ static int vhost_vdpa_va_map(struct vhost_vdpa *v, u64 offset, map_size, map_iova = iova; struct vdpa_map_file *map_file; struct vm_area_struct *vma; - int ret; + int ret = 0; mmap_read_lock(dev->mm); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 588e02fb91d3..0a5b54034d4b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -345,8 +345,13 @@ static int virtio_device_of_init(struct virtio_device *dev) ret = snprintf(compat, sizeof(compat), "virtio,device%x", dev->id.device); BUG_ON(ret >= sizeof(compat)); + /* + * On powerpc/pseries virtio devices are PCI devices so PCI + * vendor/device ids play the role of the "compatible" property. + * Simply don't init of_node in this case. + */ if (!of_device_is_compatible(np, compat)) { - ret = -EINVAL; + ret = 0; goto out; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 69d900a8473d..a813b70f594e 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -630,7 +630,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) - elf_type |= MAP_FIXED_NOREPLACE; + elf_type |= MAP_FIXED; else if (no_base && interp_elf_ex->e_type == ET_DYN) load_addr = -vaddr; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 8129a430d789..2f117c57160d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -528,7 +528,7 @@ void debugfs_create_file_size(const char *name, umode_t mode, { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); - if (de) + if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index ffb295aa891c..74b172a4adda 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -551,7 +551,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; - int ret; + int ret = 0; if (!info) { info = ext4_htree_create_dir_info(file, ctx->pos); @@ -599,7 +599,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) info->curr_minor_hash, &info->next_hash); if (ret < 0) - return ret; + goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; @@ -630,7 +630,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) } finished: info->last_pos = ctx->pos; - return 0; + return ret < 0 ? ret : 0; } static int ext4_release_dir(struct inode *inode, struct file *filp) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 90ff5acaf11f..3825195539d7 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3593,9 +3593,6 @@ extern int ext4_da_write_inline_data_begin(struct address_space *mapping, unsigned flags, struct page **pagep, void **fsdata); -extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, - unsigned len, unsigned copied, - struct page *page); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c0de30f25185..0e02571f2f82 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5916,7 +5916,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) } /* Check if *cur is a hole and if it is, skip it */ -static void skip_hole(struct inode *inode, ext4_lblk_t *cur) +static int skip_hole(struct inode *inode, ext4_lblk_t *cur) { int ret; struct ext4_map_blocks map; @@ -5925,9 +5925,12 @@ static void skip_hole(struct inode *inode, ext4_lblk_t *cur) map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + return ret; if (ret != 0) - return; + return 0; *cur = *cur + map.m_len; + return 0; } /* Count number of blocks used by this inode and update i_blocks */ @@ -5976,7 +5979,9 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) * iblocks by total number of differences found. */ cur = 0; - skip_hole(inode, &cur); + ret = skip_hole(inode, &cur); + if (ret < 0) + goto out; path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) goto out; @@ -5995,8 +6000,12 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) } cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); - skip_hole(inode, &cur); - + ret = skip_hole(inode, &cur); + if (ret < 0) { + ext4_ext_drop_refs(path); + kfree(path); + break; + } path2 = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path2)) { ext4_ext_drop_refs(path); diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 8e610a381862..8ea5a81e6554 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -892,6 +892,12 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) sizeof(lrange), (u8 *)&lrange, crc)) return -ENOSPC; } else { + unsigned int max = (map.m_flags & EXT4_MAP_UNWRITTEN) ? + EXT_UNWRITTEN_MAX_LEN : EXT_INIT_MAX_LEN; + + /* Limit the number of blocks in one extent */ + map.m_len = min(max, map.m_len); + fc_ext.fc_ino = cpu_to_le32(inode->i_ino); ex = (struct ext4_extent *)&fc_ext.fc_ex; ex->ee_block = cpu_to_le32(map.m_lblk); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 82bf4ff6be28..39a1ab129fdc 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "ext4_jbd2.h" #include "ext4.h" @@ -733,45 +734,83 @@ convert: int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int ret, no_expand; + handle_t *handle = ext4_journal_current_handle(); + int no_expand; void *kaddr; struct ext4_iloc iloc; + int ret = 0, ret2; - if (unlikely(copied < len)) { - if (!PageUptodate(page)) { - copied = 0; + if (unlikely(copied < len) && !PageUptodate(page)) + copied = 0; + + if (likely(copied)) { + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) { + unlock_page(page); + put_page(page); + ext4_std_error(inode->i_sb, ret); goto out; } - } + ext4_write_lock_xattr(inode, &no_expand); + BUG_ON(!ext4_has_inline_data(inode)); - ret = ext4_get_inode_loc(inode, &iloc); - if (ret) { - ext4_std_error(inode->i_sb, ret); - copied = 0; - goto out; - } + /* + * ei->i_inline_off may have changed since + * ext4_write_begin() called + * ext4_try_to_write_inline_data() + */ + (void) ext4_find_inline_data_nolock(inode); - ext4_write_lock_xattr(inode, &no_expand); - BUG_ON(!ext4_has_inline_data(inode)); + kaddr = kmap_atomic(page); + ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); + kunmap_atomic(kaddr); + SetPageUptodate(page); + /* clear page dirty so that writepages wouldn't work for us. */ + ClearPageDirty(page); + + ext4_write_unlock_xattr(inode, &no_expand); + brelse(iloc.bh); + + /* + * It's important to update i_size while still holding page + * lock: page writeout could otherwise come in and zero + * beyond i_size. + */ + ext4_update_inode_size(inode, pos + copied); + } + unlock_page(page); + put_page(page); /* - * ei->i_inline_off may have changed since ext4_write_begin() - * called ext4_try_to_write_inline_data() + * Don't mark the inode dirty under page lock. First, it unnecessarily + * makes the holding time of page lock longer. Second, it forces lock + * ordering of page lock and transaction start for journaling + * filesystems. */ - (void) ext4_find_inline_data_nolock(inode); - - kaddr = kmap_atomic(page); - ext4_write_inline_data(inode, &iloc, kaddr, pos, len); - kunmap_atomic(kaddr); - SetPageUptodate(page); - /* clear page dirty so that writepages wouldn't work for us. */ - ClearPageDirty(page); - - ext4_write_unlock_xattr(inode, &no_expand); - brelse(iloc.bh); - mark_inode_dirty(inode); + if (likely(copied)) + mark_inode_dirty(inode); out: - return copied; + /* + * If we didn't copy as much data as expected, we need to trim back + * size of xattr containing inline data. + */ + if (pos + len > inode->i_size && ext4_can_truncate(inode)) + ext4_orphan_add(handle, inode); + + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + if (pos + len > inode->i_size) { + ext4_truncate_failed_write(inode); + /* + * If truncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + return ret ? ret : copied; } struct buffer_head * @@ -953,43 +992,6 @@ out: return ret; } -int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, - unsigned len, unsigned copied, - struct page *page) -{ - int ret; - - ret = ext4_write_inline_data_end(inode, pos, len, copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - return ret; - } - copied = ret; - - /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. - * - * But it's important to update i_size while still holding page lock: - * page writeout could otherwise come in and zero beyond i_size. - */ - if (pos+copied > inode->i_size) - i_size_write(inode, pos+copied); - unlock_page(page); - put_page(page); - - /* - * Don't mark the inode dirty under page lock. First, it unnecessarily - * makes the holding time of page lock longer. Second, it forces lock - * ordering of page lock and transaction start for journaling - * filesystems. - */ - mark_inode_dirty(inode); - - return copied; -} - #ifdef INLINE_DIR_DEBUG void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, void *inline_start, int inline_size) @@ -1917,6 +1919,24 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) EXT4_I(inode)->i_disksize = i_size; if (i_size < inline_size) { + /* + * if there's inline data to truncate and this file was + * converted to extents after that inline data was written, + * the extent status cache must be cleared to avoid leaving + * behind stale delayed allocated extent entries + */ + if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { +retry: + err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); + if (err == -ENOMEM) { + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + if (err) + goto out_error; + } + /* Clear the content in the xattr space. */ if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) { if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d18852d6029c..0f06305167d5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1284,22 +1284,14 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; - int inline_data = ext4_has_inline_data(inode); bool verity = ext4_verity_in_progress(inode); trace_ext4_write_end(inode, pos, len, copied); - if (inline_data) { - ret = ext4_write_inline_data_end(inode, pos, len, - copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - goto errout; - } - copied = ret; - } else - copied = block_write_end(file, mapping, pos, - len, copied, page, fsdata); + + if (ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. @@ -1320,7 +1312,7 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed || inline_data) + if (i_size_changed) ret = ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) @@ -1329,7 +1321,7 @@ static int ext4_write_end(struct file *file, * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); -errout: + ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -1395,7 +1387,6 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; - int inline_data = ext4_has_inline_data(inode); bool verity = ext4_verity_in_progress(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); @@ -1404,16 +1395,10 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (inline_data) { - ret = ext4_write_inline_data_end(inode, pos, len, - copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - goto errout; - } - copied = ret; - } else if (unlikely(copied < len) && !PageUptodate(page)) { + if (ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + + if (unlikely(copied < len) && !PageUptodate(page)) { copied = 0; ext4_journalled_zero_new_buffers(handle, inode, page, from, to); } else { @@ -1436,7 +1421,7 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos && !verity) pagecache_isize_extended(inode, old_size, pos); - if (size_changed || inline_data) { + if (size_changed) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -1449,7 +1434,6 @@ static int ext4_journalled_write_end(struct file *file, */ ext4_orphan_add(handle, inode); -errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -1644,6 +1628,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int ret; bool allocated = false; + bool reserved = false; /* * If the cluster containing lblk is shared with a delayed, @@ -1660,6 +1645,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) ret = ext4_da_reserve_space(inode); if (ret != 0) /* ENOSPC */ goto errout; + reserved = true; } else { /* bigalloc */ if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) { if (!ext4_es_scan_clu(inode, @@ -1672,6 +1658,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) ret = ext4_da_reserve_space(inode); if (ret != 0) /* ENOSPC */ goto errout; + reserved = true; } else { allocated = true; } @@ -1682,6 +1669,8 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) } ret = ext4_es_insert_delayed_block(inode, lblk, allocated); + if (ret && reserved) + ext4_da_release_space(inode, 1); errout: return ret; @@ -1722,13 +1711,16 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, } /* - * Delayed extent could be allocated by fallocate. - * So we need to check it. + * the buffer head associated with a delayed and not unwritten + * block found in the extent status cache must contain an + * invalid block number and have its BH_New and BH_Delay bits + * set, reflecting the state assigned when the block was + * initially delayed allocated */ - if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) { - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); + if (ext4_es_is_delonly(&es)) { + BUG_ON(bh->b_blocknr != invalid_block); + BUG_ON(!buffer_new(bh)); + BUG_ON(!buffer_delay(bh)); return 0; } @@ -2932,19 +2924,6 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } -/* We always reserve for an inode update; the superblock could be there too */ -static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) -{ - if (likely(ext4_has_feature_large_file(inode->i_sb))) - return 1; - - if (pos + len <= 0x7fffffffULL) - return 1; - - /* We might need to update the superblock to set LARGE_FILE */ - return 2; -} - static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2953,7 +2932,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, struct page *page; pgoff_t index; struct inode *inode = mapping->host; - handle_t *handle; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; @@ -2979,41 +2957,11 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, return 0; } - /* - * grab_cache_page_write_begin() can take a long time if the - * system is thrashing due to memory pressure, or if the page - * is being written back. So grab it first before we start - * the transaction handle. This also allows us to allocate - * the page (if needed) without using GFP_NOFS. - */ -retry_grab: +retry: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; - unlock_page(page); - /* - * With delayed allocation, we don't log the i_disksize update - * if there is delayed block allocation. But we still need - * to journalling the i_disksize update if writes to the end - * of file which has an already mapped buffer. - */ -retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, - ext4_da_write_credits(inode, pos, len)); - if (IS_ERR(handle)) { - put_page(page); - return PTR_ERR(handle); - } - - lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - unlock_page(page); - put_page(page); - ext4_journal_stop(handle); - goto retry_grab; - } /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); @@ -3025,20 +2973,18 @@ retry_journal: #endif if (ret < 0) { unlock_page(page); - ext4_journal_stop(handle); + put_page(page); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold inode lock. */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry_journal; - - put_page(page); + goto retry; return ret; } @@ -3075,8 +3021,6 @@ static int ext4_da_write_end(struct file *file, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - int ret = 0, ret2; - handle_t *handle = ext4_journal_current_handle(); loff_t new_i_size; unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; @@ -3086,44 +3030,36 @@ static int ext4_da_write_end(struct file *file, len, copied, page, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); - start = pos & (PAGE_SIZE - 1); - end = start + copied - 1; - - /* - * generic_write_end() will run mark_inode_dirty() if i_size - * changes. So let's piggyback the i_disksize mark_inode_dirty - * into that. - */ - new_i_size = pos + copied; - if (copied && new_i_size > EXT4_I(inode)->i_disksize) { - if (ext4_has_inline_data(inode) || - ext4_da_should_update_i_disksize(page, end)) { - ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ret = ext4_mark_inode_dirty(handle, inode); - } - } if (write_mode != CONVERT_INLINE_DATA && ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && ext4_has_inline_data(inode)) - ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied, - page); - else - ret2 = generic_write_end(file, mapping, pos, len, copied, - page, fsdata); + return ext4_write_inline_data_end(inode, pos, len, copied, page); - copied = ret2; - if (ret2 < 0) - ret = ret2; - ret2 = ext4_journal_stop(handle); - if (unlikely(ret2 && !ret)) - ret = ret2; + start = pos & (PAGE_SIZE - 1); + end = start + copied - 1; - return ret ? ret : copied; + /* + * Since we are holding inode lock, we are sure i_disksize <= + * i_size. We also know that if i_disksize < i_size, there are + * delalloc writes pending in the range upto i_size. If the end of + * the current write is <= i_size, there's no need to touch + * i_disksize since writeback will push i_disksize upto i_size + * eventually. If the end of the current write is > i_size and + * inside an allocated block (ext4_da_should_update_i_disksize() + * check), we need to update i_disksize here as neither + * ext4_writepage() nor certain ext4_writepages() paths not + * allocating blocks update i_disksize. + * + * Note that we defer inode dirtying to generic_write_end() / + * ext4_da_write_inline_data_end(). + */ + new_i_size = pos + copied; + if (copied && new_i_size > inode->i_size && + ext4_da_should_update_i_disksize(page, end)) + ext4_update_i_disksize(inode, new_i_size); + + return generic_write_end(file, mapping, pos, len, copied, page, fsdata); } /* @@ -4340,6 +4276,12 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, goto has_buffer; lock_buffer(bh); + if (ext4_buffer_uptodate(bh)) { + /* Someone brought it uptodate while we waited */ + unlock_buffer(bh); + goto has_buffer; + } + /* * If we have all information of the inode in memory and this * is the only valid inode in the block, we need not read the diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0775950ee84e..88d5d274a868 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -658,7 +658,7 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, * constraints, it may not be safe to do it right here so we * defer superblock flushing to a workqueue. */ - if (continue_fs) + if (continue_fs && journal) schedule_work(&EXT4_SB(sb)->s_error_work); else ext4_commit_super(sb); @@ -1350,6 +1350,12 @@ static void ext4_destroy_inode(struct inode *inode) true); dump_stack(); } + + if (EXT4_I(inode)->i_reserved_data_blocks) + ext4_msg(inode->i_sb, KERN_ERR, + "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!", + inode->i_ino, EXT4_I(inode), + EXT4_I(inode)->i_reserved_data_blocks); } static void init_once(void *foo) @@ -3021,17 +3027,17 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { - loff_t res = EXT4_NDIR_BLOCKS; + unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; - loff_t upper_limit; - /* This is calculated to be the largest file size for a dense, block + + /* + * This is calculated to be the largest file size for a dense, block * mapped file such that the file's total number of 512-byte sectors, * including data and all indirect blocks, does not exceed (2^48 - 1). * * __u32 i_blocks_lo and _u16 i_blocks_high represent the total * number of 512-byte sectors of the file. */ - if (!has_huge_files) { /* * !has_huge_files or implies that the inode i_block field @@ -3074,7 +3080,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; - return res; + return (loff_t)res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, @@ -5042,12 +5048,15 @@ failed_mount_wq: sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { + /* flush s_error_work before journal destroy. */ + flush_work(&sbi->s_error_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: + /* flush s_error_work before sbi destroy */ flush_work(&sbi->s_error_work); del_timer_sync(&sbi->s_err_report); ext4_stop_mmpd(sbi); diff --git a/fs/io-wq.c b/fs/io-wq.c index c2360cdc403d..5bf8aa81715e 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -584,10 +584,7 @@ loop: if (!get_signal(&ksig)) continue; - if (fatal_signal_pending(current) || - signal_group_exit(current->signal)) - break; - continue; + break; } last_timeout = !ret; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 82f867983bb3..6b9e70208782 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -403,7 +403,6 @@ struct io_ring_ctx { struct wait_queue_head cq_wait; unsigned cq_extra; atomic_t cq_timeouts; - struct fasync_struct *cq_fasync; unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; @@ -1614,10 +1613,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) { + if (waitqueue_active(&ctx->poll_wait)) wake_up_interruptible(&ctx->poll_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } } static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) @@ -1631,10 +1628,8 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) } if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) { + if (waitqueue_active(&ctx->poll_wait)) wake_up_interruptible(&ctx->poll_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } } /* Returns true if there are no backlogged entries after the flush */ @@ -9345,13 +9340,6 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) return mask; } -static int io_uring_fasync(int fd, struct file *file, int on) -{ - struct io_ring_ctx *ctx = file->private_data; - - return fasync_helper(fd, file, on, &ctx->cq_fasync); -} - static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { const struct cred *creds; @@ -10145,7 +10133,6 @@ static const struct file_operations io_uring_fops = { .mmap_capabilities = io_uring_nommu_mmap_capabilities, #endif .poll = io_uring_poll, - .fasync = io_uring_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, #endif diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index ba581429bf7b..cfc3ce8b815a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1116,8 +1116,13 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, if (!inode) inode = ERR_PTR(-ENOMEM); } - /* Needed only for negative dentry validation */ - if (!inode) + /* + * Needed for negative dentry validation. + * The negative dentry can be created in kernfs_iop_lookup() + * or transforms from positive dentry in dentry_unlink_inode() + * called from vfs_rmdir(). + */ + if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); up_read(&kernfs_rwsem); diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index de36f12070bf..71c989f1568d 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -68,125 +68,6 @@ void ksmbd_copy_gss_neg_header(void *buf) memcpy(buf, NEGOTIATE_GSS_HEADER, AUTH_GSS_LENGTH); } -static void -str_to_key(unsigned char *str, unsigned char *key) -{ - int i; - - key[0] = str[0] >> 1; - key[1] = ((str[0] & 0x01) << 6) | (str[1] >> 2); - key[2] = ((str[1] & 0x03) << 5) | (str[2] >> 3); - key[3] = ((str[2] & 0x07) << 4) | (str[3] >> 4); - key[4] = ((str[3] & 0x0F) << 3) | (str[4] >> 5); - key[5] = ((str[4] & 0x1F) << 2) | (str[5] >> 6); - key[6] = ((str[5] & 0x3F) << 1) | (str[6] >> 7); - key[7] = str[6] & 0x7F; - for (i = 0; i < 8; i++) - key[i] = (key[i] << 1); -} - -static int -smbhash(unsigned char *out, const unsigned char *in, unsigned char *key) -{ - unsigned char key2[8]; - struct des_ctx ctx; - - if (fips_enabled) { - ksmbd_debug(AUTH, "FIPS compliance enabled: DES not permitted\n"); - return -ENOENT; - } - - str_to_key(key, key2); - des_expand_key(&ctx, key2, DES_KEY_SIZE); - des_encrypt(&ctx, out, in); - memzero_explicit(&ctx, sizeof(ctx)); - return 0; -} - -static int ksmbd_enc_p24(unsigned char *p21, const unsigned char *c8, unsigned char *p24) -{ - int rc; - - rc = smbhash(p24, c8, p21); - if (rc) - return rc; - rc = smbhash(p24 + 8, c8, p21 + 7); - if (rc) - return rc; - return smbhash(p24 + 16, c8, p21 + 14); -} - -/* produce a md4 message digest from data of length n bytes */ -static int ksmbd_enc_md4(unsigned char *md4_hash, unsigned char *link_str, - int link_len) -{ - int rc; - struct ksmbd_crypto_ctx *ctx; - - ctx = ksmbd_crypto_ctx_find_md4(); - if (!ctx) { - ksmbd_debug(AUTH, "Crypto md4 allocation error\n"); - return -ENOMEM; - } - - rc = crypto_shash_init(CRYPTO_MD4(ctx)); - if (rc) { - ksmbd_debug(AUTH, "Could not init md4 shash\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD4(ctx), link_str, link_len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with link_str\n"); - goto out; - } - - rc = crypto_shash_final(CRYPTO_MD4(ctx), md4_hash); - if (rc) - ksmbd_debug(AUTH, "Could not generate md4 hash\n"); -out: - ksmbd_release_crypto_ctx(ctx); - return rc; -} - -static int ksmbd_enc_update_sess_key(unsigned char *md5_hash, char *nonce, - char *server_challenge, int len) -{ - int rc; - struct ksmbd_crypto_ctx *ctx; - - ctx = ksmbd_crypto_ctx_find_md5(); - if (!ctx) { - ksmbd_debug(AUTH, "Crypto md5 allocation error\n"); - return -ENOMEM; - } - - rc = crypto_shash_init(CRYPTO_MD5(ctx)); - if (rc) { - ksmbd_debug(AUTH, "Could not init md5 shash\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD5(ctx), server_challenge, len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with challenge\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD5(ctx), nonce, len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with nonce\n"); - goto out; - } - - rc = crypto_shash_final(CRYPTO_MD5(ctx), md5_hash); - if (rc) - ksmbd_debug(AUTH, "Could not generate md5 hash\n"); -out: - ksmbd_release_crypto_ctx(ctx); - return rc; -} - /** * ksmbd_gen_sess_key() - function to generate session key * @sess: session of connection @@ -324,43 +205,6 @@ out: return ret; } -/** - * ksmbd_auth_ntlm() - NTLM authentication handler - * @sess: session of connection - * @pw_buf: NTLM challenge response - * @passkey: user password - * - * Return: 0 on success, error number on error - */ -int ksmbd_auth_ntlm(struct ksmbd_session *sess, char *pw_buf) -{ - int rc; - unsigned char p21[21]; - char key[CIFS_AUTH_RESP_SIZE]; - - memset(p21, '\0', 21); - memcpy(p21, user_passkey(sess->user), CIFS_NTHASH_SIZE); - rc = ksmbd_enc_p24(p21, sess->ntlmssp.cryptkey, key); - if (rc) { - pr_err("password processing failed\n"); - return rc; - } - - ksmbd_enc_md4(sess->sess_key, user_passkey(sess->user), - CIFS_SMB1_SESSKEY_SIZE); - memcpy(sess->sess_key + CIFS_SMB1_SESSKEY_SIZE, key, - CIFS_AUTH_RESP_SIZE); - sess->sequence_number = 1; - - if (strncmp(pw_buf, key, CIFS_AUTH_RESP_SIZE) != 0) { - ksmbd_debug(AUTH, "ntlmv1 authentication failed\n"); - return -EINVAL; - } - - ksmbd_debug(AUTH, "ntlmv1 authentication pass\n"); - return 0; -} - /** * ksmbd_auth_ntlmv2() - NTLMv2 authentication handler * @sess: session of connection @@ -441,44 +285,6 @@ out: return rc; } -/** - * __ksmbd_auth_ntlmv2() - NTLM2(extended security) authentication handler - * @sess: session of connection - * @client_nonce: client nonce from LM response. - * @ntlm_resp: ntlm response data from client. - * - * Return: 0 on success, error number on error - */ -static int __ksmbd_auth_ntlmv2(struct ksmbd_session *sess, char *client_nonce, - char *ntlm_resp) -{ - char sess_key[CIFS_SMB1_SESSKEY_SIZE] = {0}; - int rc; - unsigned char p21[21]; - char key[CIFS_AUTH_RESP_SIZE]; - - rc = ksmbd_enc_update_sess_key(sess_key, - client_nonce, - (char *)sess->ntlmssp.cryptkey, 8); - if (rc) { - pr_err("password processing failed\n"); - goto out; - } - - memset(p21, '\0', 21); - memcpy(p21, user_passkey(sess->user), CIFS_NTHASH_SIZE); - rc = ksmbd_enc_p24(p21, sess_key, key); - if (rc) { - pr_err("password processing failed\n"); - goto out; - } - - if (memcmp(ntlm_resp, key, CIFS_AUTH_RESP_SIZE) != 0) - rc = -EINVAL; -out: - return rc; -} - /** * ksmbd_decode_ntlmssp_auth_blob() - helper function to construct * authenticate blob @@ -512,17 +318,6 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, nt_off = le32_to_cpu(authblob->NtChallengeResponse.BufferOffset); nt_len = le16_to_cpu(authblob->NtChallengeResponse.Length); - /* process NTLM authentication */ - if (nt_len == CIFS_AUTH_RESP_SIZE) { - if (le32_to_cpu(authblob->NegotiateFlags) & - NTLMSSP_NEGOTIATE_EXTENDED_SEC) - return __ksmbd_auth_ntlmv2(sess, (char *)authblob + - lm_off, (char *)authblob + nt_off); - else - return ksmbd_auth_ntlm(sess, (char *)authblob + - nt_off); - } - /* TODO : use domain name that imported from configuration file */ domain_name = smb_strndup_from_utf16((const char *)authblob + le32_to_cpu(authblob->DomainName.BufferOffset), diff --git a/fs/ksmbd/crypto_ctx.c b/fs/ksmbd/crypto_ctx.c index 5f4b1008d17e..81488d04199d 100644 --- a/fs/ksmbd/crypto_ctx.c +++ b/fs/ksmbd/crypto_ctx.c @@ -81,12 +81,6 @@ static struct shash_desc *alloc_shash_desc(int id) case CRYPTO_SHASH_SHA512: tfm = crypto_alloc_shash("sha512", 0, 0); break; - case CRYPTO_SHASH_MD4: - tfm = crypto_alloc_shash("md4", 0, 0); - break; - case CRYPTO_SHASH_MD5: - tfm = crypto_alloc_shash("md5", 0, 0); - break; default: return NULL; } @@ -214,16 +208,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void) return ____crypto_shash_ctx_find(CRYPTO_SHASH_SHA512); } -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md4(void) -{ - return ____crypto_shash_ctx_find(CRYPTO_SHASH_MD4); -} - -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md5(void) -{ - return ____crypto_shash_ctx_find(CRYPTO_SHASH_MD5); -} - static struct ksmbd_crypto_ctx *____crypto_aead_ctx_find(int id) { struct ksmbd_crypto_ctx *ctx; diff --git a/fs/ksmbd/crypto_ctx.h b/fs/ksmbd/crypto_ctx.h index ef11154b43df..4a367c62f653 100644 --- a/fs/ksmbd/crypto_ctx.h +++ b/fs/ksmbd/crypto_ctx.h @@ -15,8 +15,6 @@ enum { CRYPTO_SHASH_CMACAES, CRYPTO_SHASH_SHA256, CRYPTO_SHASH_SHA512, - CRYPTO_SHASH_MD4, - CRYPTO_SHASH_MD5, CRYPTO_SHASH_MAX, }; @@ -43,8 +41,6 @@ struct ksmbd_crypto_ctx { #define CRYPTO_CMACAES(c) ((c)->desc[CRYPTO_SHASH_CMACAES]) #define CRYPTO_SHA256(c) ((c)->desc[CRYPTO_SHASH_SHA256]) #define CRYPTO_SHA512(c) ((c)->desc[CRYPTO_SHASH_SHA512]) -#define CRYPTO_MD4(c) ((c)->desc[CRYPTO_SHASH_MD4]) -#define CRYPTO_MD5(c) ((c)->desc[CRYPTO_SHASH_MD5]) #define CRYPTO_HMACMD5_TFM(c) ((c)->desc[CRYPTO_SHASH_HMACMD5]->tfm) #define CRYPTO_HMACSHA256_TFM(c)\ @@ -52,8 +48,6 @@ struct ksmbd_crypto_ctx { #define CRYPTO_CMACAES_TFM(c) ((c)->desc[CRYPTO_SHASH_CMACAES]->tfm) #define CRYPTO_SHA256_TFM(c) ((c)->desc[CRYPTO_SHASH_SHA256]->tfm) #define CRYPTO_SHA512_TFM(c) ((c)->desc[CRYPTO_SHASH_SHA512]->tfm) -#define CRYPTO_MD4_TFM(c) ((c)->desc[CRYPTO_SHASH_MD4]->tfm) -#define CRYPTO_MD5_TFM(c) ((c)->desc[CRYPTO_SHASH_MD5]->tfm) #define CRYPTO_GCM(c) ((c)->ccmaes[CRYPTO_AEAD_AES_GCM]) #define CRYPTO_CCM(c) ((c)->ccmaes[CRYPTO_AEAD_AES_CCM]) @@ -64,8 +58,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_hmacsha256(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_cmacaes(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha256(void); -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md4(void); -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md5(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_gcm(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_ccm(void); void ksmbd_crypto_destroy(void); diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 6a19f4bc692d..60e7ac62c917 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -162,17 +162,14 @@ char *convert_to_nt_pathname(char *filename) { char *ab_pathname; - if (strlen(filename) == 0) { - ab_pathname = kmalloc(2, GFP_KERNEL); - ab_pathname[0] = '\\'; - ab_pathname[1] = '\0'; - } else { - ab_pathname = kstrdup(filename, GFP_KERNEL); - if (!ab_pathname) - return NULL; + if (strlen(filename) == 0) + filename = "\\"; - ksmbd_conv_path_to_windows(ab_pathname); - } + ab_pathname = kstrdup(filename, GFP_KERNEL); + if (!ab_pathname) + return NULL; + + ksmbd_conv_path_to_windows(ab_pathname); return ab_pathname; } diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 16b6236d1bd2..f9dae6ef2115 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1451,26 +1451,47 @@ struct lease_ctx_info *parse_lease_state(void *open_req) */ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) { - char *data_offset; struct create_context *cc; unsigned int next = 0; char *name; struct smb2_create_req *req = (struct smb2_create_req *)open_req; + unsigned int remain_len, name_off, name_len, value_off, value_len, + cc_len; - data_offset = (char *)req + 4 + le32_to_cpu(req->CreateContextsOffset); - cc = (struct create_context *)data_offset; + /* + * CreateContextsOffset and CreateContextsLength are guaranteed to + * be valid because of ksmbd_smb2_check_message(). + */ + cc = (struct create_context *)((char *)req + 4 + + le32_to_cpu(req->CreateContextsOffset)); + remain_len = le32_to_cpu(req->CreateContextsLength); do { - int val; - cc = (struct create_context *)((char *)cc + next); - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - val = le16_to_cpu(cc->NameLength); - if (val < 4) + if (remain_len < offsetof(struct create_context, Buffer)) return ERR_PTR(-EINVAL); - if (memcmp(name, tag, val) == 0) - return cc; next = le32_to_cpu(cc->Next); + name_off = le16_to_cpu(cc->NameOffset); + name_len = le16_to_cpu(cc->NameLength); + value_off = le16_to_cpu(cc->DataOffset); + value_len = le32_to_cpu(cc->DataLength); + cc_len = next ? next : remain_len; + + if ((next & 0x7) != 0 || + next > remain_len || + name_off != offsetof(struct create_context, Buffer) || + name_len < 4 || + name_off + name_len > cc_len || + (value_off & 0x7) != 0 || + (value_off && (value_off < name_off + name_len)) || + ((u64)value_off + value_len > cc_len)) + return ERR_PTR(-EINVAL); + + name = (char *)cc + name_off; + if (memcmp(name, tag, name_len) == 0) + return cc; + + remain_len -= next; } while (next != 0); return NULL; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 761e12171dc4..dcf907738610 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -459,13 +459,22 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) bool is_chained_smb2_message(struct ksmbd_work *work) { struct smb2_hdr *hdr = work->request_buf; - unsigned int len; + unsigned int len, next_cmd; if (hdr->ProtocolId != SMB2_PROTO_NUMBER) return false; hdr = ksmbd_req_buf_next(work); - if (le32_to_cpu(hdr->NextCommand) > 0) { + next_cmd = le32_to_cpu(hdr->NextCommand); + if (next_cmd > 0) { + if ((u64)work->next_smb2_rcv_hdr_off + next_cmd + + __SMB2_HEADER_STRUCTURE_SIZE > + get_rfc1002_len(work->request_buf)) { + pr_err("next command(%u) offset exceeds smb msg size\n", + next_cmd); + return false; + } + ksmbd_debug(SMB, "got SMB2 chained command\n"); init_chained_smb2_rsp(work); return true; @@ -1058,6 +1067,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) struct smb2_negotiate_req *req = work->request_buf; struct smb2_negotiate_rsp *rsp = work->response_buf; int rc = 0; + unsigned int smb2_buf_len, smb2_neg_size; __le32 status; ksmbd_debug(SMB, "Received negotiate request\n"); @@ -1075,6 +1085,44 @@ int smb2_handle_negotiate(struct ksmbd_work *work) goto err_out; } + smb2_buf_len = get_rfc1002_len(work->request_buf); + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects) - 4; + if (smb2_neg_size > smb2_buf_len) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (conn->dialect == SMB311_PROT_ID) { + unsigned int nego_ctxt_off = le32_to_cpu(req->NegotiateContextOffset); + + if (smb2_buf_len < nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (smb2_neg_size > nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + } else { + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + smb2_buf_len) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + } + conn->cli_cap = le32_to_cpu(req->Capabilities); switch (conn->dialect) { case SMB311_PROT_ID: @@ -2093,16 +2141,22 @@ out: * smb2_set_ea() - handler for setting extended attributes using set * info command * @eabuf: set info command buffer + * @buf_len: set info command buffer length * @path: dentry path for get ea * * Return: 0 on success, otherwise error */ -static int smb2_set_ea(struct smb2_ea_info *eabuf, struct path *path) +static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, + struct path *path) { struct user_namespace *user_ns = mnt_user_ns(path->mnt); char *attr_name = NULL, *value; int rc = 0; - int next = 0; + unsigned int next = 0; + + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + le16_to_cpu(eabuf->EaValueLength)) + return -EINVAL; attr_name = kmalloc(XATTR_NAME_MAX + 1, GFP_KERNEL); if (!attr_name) @@ -2167,7 +2221,13 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, struct path *path) next: next = le32_to_cpu(eabuf->NextEntryOffset); + if (next == 0 || buf_len < next) + break; + buf_len -= next; eabuf = (struct smb2_ea_info *)((char *)eabuf + next); + if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength)) + break; + } while (next != 0); kfree(attr_name); @@ -2367,6 +2427,10 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, ksmbd_debug(SMB, "Set ACLs using SMB2_CREATE_SD_BUFFER context\n"); sd_buf = (struct create_sd_buf_req *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_sd_buf_req)) + return -EINVAL; return set_info_sec(work->conn, work->tcon, path, &sd_buf->ntsd, le32_to_cpu(sd_buf->ccontext.DataLength), true); } @@ -2561,6 +2625,12 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } else if (context) { ea_buf = (struct create_ea_buf_req *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_ea_buf_req)) { + rc = -EINVAL; + goto err_out1; + } if (req->CreateOptions & FILE_NO_EA_KNOWLEDGE_LE) { rsp->hdr.Status = STATUS_ACCESS_DENIED; rc = -EACCES; @@ -2599,6 +2669,12 @@ int smb2_open(struct ksmbd_work *work) } else if (context) { struct create_posix *posix = (struct create_posix *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_posix)) { + rc = -EINVAL; + goto err_out1; + } ksmbd_debug(SMB, "get posix context\n"); posix_mode = le32_to_cpu(posix->Mode); @@ -2748,7 +2824,15 @@ int smb2_open(struct ksmbd_work *work) created = true; user_ns = mnt_user_ns(path.mnt); if (ea_buf) { - rc = smb2_set_ea(&ea_buf->ea, &path); + if (le32_to_cpu(ea_buf->ccontext.DataLength) < + sizeof(struct smb2_ea_info)) { + rc = -EINVAL; + goto err_out; + } + + rc = smb2_set_ea(&ea_buf->ea, + le32_to_cpu(ea_buf->ccontext.DataLength), + &path); if (rc == -EOPNOTSUPP) rc = 0; else if (rc) @@ -2981,9 +3065,16 @@ int smb2_open(struct ksmbd_work *work) rc = PTR_ERR(az_req); goto err_out; } else if (az_req) { - loff_t alloc_size = le64_to_cpu(az_req->AllocationSize); + loff_t alloc_size; int err; + if (le16_to_cpu(az_req->ccontext.DataOffset) + + le32_to_cpu(az_req->ccontext.DataLength) < + sizeof(struct create_alloc_size_req)) { + rc = -EINVAL; + goto err_out; + } + alloc_size = le64_to_cpu(az_req->AllocationSize); ksmbd_debug(SMB, "request smb2 create allocate size : %llu\n", alloc_size); @@ -4152,7 +4243,7 @@ static void get_file_access_info(struct smb2_query_info_rsp *rsp, static int get_file_basic_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { - struct smb2_file_all_info *basic_info; + struct smb2_file_basic_info *basic_info; struct kstat stat; u64 time; @@ -4162,7 +4253,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return -EACCES; } - basic_info = (struct smb2_file_all_info *)rsp->Buffer; + basic_info = (struct smb2_file_basic_info *)rsp->Buffer; generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), &stat); basic_info->CreationTime = cpu_to_le64(fp->create_time); @@ -4175,9 +4266,8 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, basic_info->Attributes = fp->f_ci->m_fattr; basic_info->Pad1 = 0; rsp->OutputBufferLength = - cpu_to_le32(offsetof(struct smb2_file_all_info, AllocationSize)); - inc_rfc1001_len(rsp_org, offsetof(struct smb2_file_all_info, - AllocationSize)); + cpu_to_le32(sizeof(struct smb2_file_basic_info)); + inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_basic_info)); return 0; } @@ -5333,7 +5423,7 @@ out: static int smb2_create_link(struct ksmbd_work *work, struct ksmbd_share_config *share, struct smb2_file_link_info *file_info, - struct file *filp, + unsigned int buf_len, struct file *filp, struct nls_table *local_nls) { char *link_name = NULL, *target_name = NULL, *pathname = NULL; @@ -5341,6 +5431,10 @@ static int smb2_create_link(struct ksmbd_work *work, bool file_present = true; int rc; + if (buf_len < (u64)sizeof(struct smb2_file_link_info) + + le32_to_cpu(file_info->FileNameLength)) + return -EINVAL; + ksmbd_debug(SMB, "setting FILE_LINK_INFORMATION\n"); pathname = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathname) @@ -5400,10 +5494,10 @@ out: return rc; } -static int set_file_basic_info(struct ksmbd_file *fp, char *buf, +static int set_file_basic_info(struct ksmbd_file *fp, + struct smb2_file_basic_info *file_info, struct ksmbd_share_config *share) { - struct smb2_file_all_info *file_info; struct iattr attrs; struct timespec64 ctime; struct file *filp; @@ -5414,7 +5508,6 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, if (!(fp->daccess & FILE_WRITE_ATTRIBUTES_LE)) return -EACCES; - file_info = (struct smb2_file_all_info *)buf; attrs.ia_valid = 0; filp = fp->filp; inode = file_inode(filp); @@ -5491,7 +5584,8 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, } static int set_file_allocation_info(struct ksmbd_work *work, - struct ksmbd_file *fp, char *buf) + struct ksmbd_file *fp, + struct smb2_file_alloc_info *file_alloc_info) { /* * TODO : It's working fine only when store dos attributes @@ -5499,7 +5593,6 @@ static int set_file_allocation_info(struct ksmbd_work *work, * properly with any smb.conf option */ - struct smb2_file_alloc_info *file_alloc_info; loff_t alloc_blks; struct inode *inode; int rc; @@ -5507,7 +5600,6 @@ static int set_file_allocation_info(struct ksmbd_work *work, if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; - file_alloc_info = (struct smb2_file_alloc_info *)buf; alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); @@ -5543,9 +5635,8 @@ static int set_file_allocation_info(struct ksmbd_work *work, } static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, - char *buf) + struct smb2_file_eof_info *file_eof_info) { - struct smb2_file_eof_info *file_eof_info; loff_t newsize; struct inode *inode; int rc; @@ -5553,7 +5644,6 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; - file_eof_info = (struct smb2_file_eof_info *)buf; newsize = le64_to_cpu(file_eof_info->EndOfFile); inode = file_inode(fp->filp); @@ -5580,7 +5670,8 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, } static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, - char *buf) + struct smb2_file_rename_info *rename_info, + unsigned int buf_len) { struct user_namespace *user_ns; struct ksmbd_file *parent_fp; @@ -5593,6 +5684,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, return -EACCES; } + if (buf_len < (u64)sizeof(struct smb2_file_rename_info) + + le32_to_cpu(rename_info->FileNameLength)) + return -EINVAL; + user_ns = file_mnt_user_ns(fp->filp); if (ksmbd_stream_fd(fp)) goto next; @@ -5615,14 +5710,13 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, } } next: - return smb2_rename(work, fp, user_ns, - (struct smb2_file_rename_info *)buf, + return smb2_rename(work, fp, user_ns, rename_info, work->sess->conn->local_nls); } -static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) +static int set_file_disposition_info(struct ksmbd_file *fp, + struct smb2_file_disposition_info *file_info) { - struct smb2_file_disposition_info *file_info; struct inode *inode; if (!(fp->daccess & FILE_DELETE_LE)) { @@ -5631,7 +5725,6 @@ static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) } inode = file_inode(fp->filp); - file_info = (struct smb2_file_disposition_info *)buf; if (file_info->DeletePending) { if (S_ISDIR(inode->i_mode) && ksmbd_vfs_empty_dir(fp) == -ENOTEMPTY) @@ -5643,15 +5736,14 @@ static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) return 0; } -static int set_file_position_info(struct ksmbd_file *fp, char *buf) +static int set_file_position_info(struct ksmbd_file *fp, + struct smb2_file_pos_info *file_info) { - struct smb2_file_pos_info *file_info; loff_t current_byte_offset; unsigned long sector_size; struct inode *inode; inode = file_inode(fp->filp); - file_info = (struct smb2_file_pos_info *)buf; current_byte_offset = le64_to_cpu(file_info->CurrentByteOffset); sector_size = inode->i_sb->s_blocksize; @@ -5667,12 +5759,11 @@ static int set_file_position_info(struct ksmbd_file *fp, char *buf) return 0; } -static int set_file_mode_info(struct ksmbd_file *fp, char *buf) +static int set_file_mode_info(struct ksmbd_file *fp, + struct smb2_file_mode_info *file_info) { - struct smb2_file_mode_info *file_info; __le32 mode; - file_info = (struct smb2_file_mode_info *)buf; mode = file_info->Mode; if ((mode & ~FILE_MODE_INFO_MASK) || @@ -5702,40 +5793,74 @@ static int set_file_mode_info(struct ksmbd_file *fp, char *buf) * TODO: need to implement an error handling for STATUS_INFO_LENGTH_MISMATCH */ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, - int info_class, char *buf, + struct smb2_set_info_req *req, struct ksmbd_share_config *share) { - switch (info_class) { + unsigned int buf_len = le32_to_cpu(req->BufferLength); + + switch (req->FileInfoClass) { case FILE_BASIC_INFORMATION: - return set_file_basic_info(fp, buf, share); + { + if (buf_len < sizeof(struct smb2_file_basic_info)) + return -EINVAL; + return set_file_basic_info(fp, (struct smb2_file_basic_info *)req->Buffer, share); + } case FILE_ALLOCATION_INFORMATION: - return set_file_allocation_info(work, fp, buf); + { + if (buf_len < sizeof(struct smb2_file_alloc_info)) + return -EINVAL; + return set_file_allocation_info(work, fp, + (struct smb2_file_alloc_info *)req->Buffer); + } case FILE_END_OF_FILE_INFORMATION: - return set_end_of_file_info(work, fp, buf); + { + if (buf_len < sizeof(struct smb2_file_eof_info)) + return -EINVAL; + return set_end_of_file_info(work, fp, + (struct smb2_file_eof_info *)req->Buffer); + } case FILE_RENAME_INFORMATION: + { if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { ksmbd_debug(SMB, "User does not have write permission\n"); return -EACCES; } - return set_rename_info(work, fp, buf); + if (buf_len < sizeof(struct smb2_file_rename_info)) + return -EINVAL; + + return set_rename_info(work, fp, + (struct smb2_file_rename_info *)req->Buffer, + buf_len); + } case FILE_LINK_INFORMATION: - return smb2_create_link(work, work->tcon->share_conf, - (struct smb2_file_link_info *)buf, fp->filp, - work->sess->conn->local_nls); + { + if (buf_len < sizeof(struct smb2_file_link_info)) + return -EINVAL; + return smb2_create_link(work, work->tcon->share_conf, + (struct smb2_file_link_info *)req->Buffer, + buf_len, fp->filp, + work->sess->conn->local_nls); + } case FILE_DISPOSITION_INFORMATION: + { if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { ksmbd_debug(SMB, "User does not have write permission\n"); return -EACCES; } - return set_file_disposition_info(fp, buf); + if (buf_len < sizeof(struct smb2_file_disposition_info)) + return -EINVAL; + + return set_file_disposition_info(fp, + (struct smb2_file_disposition_info *)req->Buffer); + } case FILE_FULL_EA_INFORMATION: { if (!(fp->daccess & FILE_WRITE_EA_LE)) { @@ -5744,18 +5869,29 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EACCES; } - return smb2_set_ea((struct smb2_ea_info *)buf, - &fp->filp->f_path); - } + if (buf_len < sizeof(struct smb2_ea_info)) + return -EINVAL; + return smb2_set_ea((struct smb2_ea_info *)req->Buffer, + buf_len, &fp->filp->f_path); + } case FILE_POSITION_INFORMATION: - return set_file_position_info(fp, buf); + { + if (buf_len < sizeof(struct smb2_file_pos_info)) + return -EINVAL; + return set_file_position_info(fp, (struct smb2_file_pos_info *)req->Buffer); + } case FILE_MODE_INFORMATION: - return set_file_mode_info(fp, buf); + { + if (buf_len < sizeof(struct smb2_file_mode_info)) + return -EINVAL; + + return set_file_mode_info(fp, (struct smb2_file_mode_info *)req->Buffer); + } } - pr_err("Unimplemented Fileinfoclass :%d\n", info_class); + pr_err("Unimplemented Fileinfoclass :%d\n", req->FileInfoClass); return -EOPNOTSUPP; } @@ -5816,8 +5952,7 @@ int smb2_set_info(struct ksmbd_work *work) switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); - rc = smb2_set_info_file(work, fp, req->FileInfoClass, - req->Buffer, work->tcon->share_conf); + rc = smb2_set_info_file(work, fp, req, work->tcon->share_conf); break; case SMB2_O_INFO_SECURITY: ksmbd_debug(SMB, "GOT SMB2_O_INFO_SECURITY\n"); @@ -8171,7 +8306,8 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); - if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE) + if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE && + conn->preauth_info) ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp, conn->preauth_info->Preauth_HashValue); @@ -8278,16 +8414,8 @@ int smb3_decrypt_req(struct ksmbd_work *work) unsigned int buf_data_size = pdu_length + 4 - sizeof(struct smb2_transform_hdr); struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf; - unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize); int rc = 0; - sess = ksmbd_session_lookup_all(conn, le64_to_cpu(tr_hdr->SessionId)); - if (!sess) { - pr_err("invalid session id(%llx) in transform header\n", - le64_to_cpu(tr_hdr->SessionId)); - return -ECONNABORTED; - } - if (pdu_length + 4 < sizeof(struct smb2_transform_hdr) + sizeof(struct smb2_hdr)) { pr_err("Transform message is too small (%u)\n", @@ -8295,11 +8423,19 @@ int smb3_decrypt_req(struct ksmbd_work *work) return -ECONNABORTED; } - if (pdu_length + 4 < orig_len + sizeof(struct smb2_transform_hdr)) { + if (pdu_length + 4 < + le32_to_cpu(tr_hdr->OriginalMessageSize) + sizeof(struct smb2_transform_hdr)) { pr_err("Transform message is broken\n"); return -ECONNABORTED; } + sess = ksmbd_session_lookup_all(conn, le64_to_cpu(tr_hdr->SessionId)); + if (!sess) { + pr_err("invalid session id(%llx) in transform header\n", + le64_to_cpu(tr_hdr->SessionId)); + return -ECONNABORTED; + } + iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr); iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index bcec845b03f3..261825d06391 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -1464,6 +1464,15 @@ struct smb2_file_all_info { /* data block encoding of response to level 18 */ char FileName[1]; } __packed; /* level 18 Query */ +struct smb2_file_basic_info { /* data block encoding of response to level 18 */ + __le64 CreationTime; /* Beginning of FILE_BASIC_INFO equivalent */ + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le32 Attributes; + __u32 Pad1; /* End of FILE_BASIC_INFO_INFO equivalent */ +} __packed; + struct smb2_file_alt_name_info { __le32 FileNameLength; char FileName[0]; diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 40f4fafa2e11..db8042a173d0 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -155,20 +155,7 @@ int ksmbd_verify_smb_message(struct ksmbd_work *work) */ bool ksmbd_smb_request(struct ksmbd_conn *conn) { - int type = *(char *)conn->request_buf; - - switch (type) { - case RFC1002_SESSION_MESSAGE: - /* Regular SMB request */ - return true; - case RFC1002_SESSION_KEEP_ALIVE: - ksmbd_debug(SMB, "RFC 1002 session keep alive\n"); - break; - default: - ksmbd_debug(SMB, "RFC 1002 unknown request type 0x%x\n", type); - } - - return false; + return conn->request_buf[0] == 0; } static bool supported_protocol(int idx) @@ -182,10 +169,12 @@ static bool supported_protocol(int idx) idx <= server_conf.max_protocol); } -static char *next_dialect(char *dialect, int *next_off) +static char *next_dialect(char *dialect, int *next_off, int bcount) { dialect = dialect + *next_off; - *next_off = strlen(dialect); + *next_off = strnlen(dialect, bcount); + if (dialect[*next_off] != '\0') + return NULL; return dialect; } @@ -200,7 +189,9 @@ static int ksmbd_lookup_dialect_by_name(char *cli_dialects, __le16 byte_count) dialect = cli_dialects; bcount = le16_to_cpu(byte_count); do { - dialect = next_dialect(dialect, &next); + dialect = next_dialect(dialect, &next, bcount); + if (!dialect) + break; ksmbd_debug(SMB, "client requested dialect %s\n", dialect); if (!strcmp(dialect, smb1_protos[i].name)) { @@ -248,13 +239,22 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count) static int ksmbd_negotiate_smb_dialect(void *buf) { - __le32 proto; + int smb_buf_length = get_rfc1002_len(buf); + __le32 proto = ((struct smb2_hdr *)buf)->ProtocolId; - proto = ((struct smb2_hdr *)buf)->ProtocolId; if (proto == SMB2_PROTO_NUMBER) { struct smb2_negotiate_req *req; + int smb2_neg_size = + offsetof(struct smb2_negotiate_req, Dialects) - 4; req = (struct smb2_negotiate_req *)buf; + if (smb2_neg_size > smb_buf_length) + goto err_out; + + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + smb_buf_length) + goto err_out; + return ksmbd_lookup_dialect_by_id(req->Dialects, req->DialectCount); } @@ -264,10 +264,19 @@ static int ksmbd_negotiate_smb_dialect(void *buf) struct smb_negotiate_req *req; req = (struct smb_negotiate_req *)buf; + if (le16_to_cpu(req->ByteCount) < 2) + goto err_out; + + if (offsetof(struct smb_negotiate_req, DialectsArray) - 4 + + le16_to_cpu(req->ByteCount) > smb_buf_length) { + goto err_out; + } + return ksmbd_lookup_dialect_by_name(req->DialectsArray, req->ByteCount); } +err_out: return BAD_PROT_ID; } diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index 0a6af447cc45..994abede27e9 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -48,14 +48,6 @@ #define CIFS_DEFAULT_IOSIZE (64 * 1024) #define MAX_CIFS_SMALL_BUFFER_SIZE 448 /* big enough for most */ -/* RFC 1002 session packet types */ -#define RFC1002_SESSION_MESSAGE 0x00 -#define RFC1002_SESSION_REQUEST 0x81 -#define RFC1002_POSITIVE_SESSION_RESPONSE 0x82 -#define RFC1002_NEGATIVE_SESSION_RESPONSE 0x83 -#define RFC1002_RETARGET_SESSION_RESPONSE 0x84 -#define RFC1002_SESSION_KEEP_ALIVE 0x85 - /* Responses when opening a file. */ #define F_SUPERSEDED 0 #define F_OPENED 1 diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index 0a95cdec8c80..bd792db32623 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -380,7 +380,7 @@ static void parse_dacl(struct user_namespace *user_ns, { int i, ret; int num_aces = 0; - int acl_size; + unsigned int acl_size; char *acl_base; struct smb_ace **ppace; struct posix_acl_entry *cf_pace, *cf_pdace; @@ -392,7 +392,7 @@ static void parse_dacl(struct user_namespace *user_ns, return; /* validate that we do not go past end of acl */ - if (end_of_acl <= (char *)pdacl || + if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); return; @@ -431,8 +431,22 @@ static void parse_dacl(struct user_namespace *user_ns, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { + if (end_of_acl - acl_base < acl_size) + break; + ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; + acl_size = offsetof(struct smb_ace, sid) + + offsetof(struct smb_sid, sub_auth); + + if (end_of_acl - acl_base < acl_size || + ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || + (end_of_acl - acl_base < + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || + (le16_to_cpu(ppace[i]->size) < + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) + break; + acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = smb_map_generic_desired_access(ppace[i]->access_req); @@ -807,6 +821,9 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, if (!pntsd) return -EIO; + if (acl_len < sizeof(struct smb_ntsd)) + return -EINVAL; + owner_sid_ptr = (struct smb_sid *)((char *)pntsd + le32_to_cpu(pntsd->osidoffset)); group_sid_ptr = (struct smb_sid *)((char *)pntsd + diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index dc15a5ecd2e0..c14320e03b69 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -215,7 +215,7 @@ out_error: * ksmbd_kthread_fn() - listen to new SMB connections and callback server * @p: arguments to forker thread * - * Return: Returns a task_struct or ERR_PTR + * Return: 0 on success, error number otherwise */ static int ksmbd_kthread_fn(void *p) { @@ -387,7 +387,7 @@ static void tcp_destroy_socket(struct socket *ksmbd_socket) /** * create_socket - create socket for ksmbd/0 * - * Return: Returns a task_struct or ERR_PTR + * Return: 0 on success, error number otherwise */ static int create_socket(struct interface *iface) { diff --git a/fs/verity/enable.c b/fs/verity/enable.c index 77e159a0346b..60a4372aa4d7 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -177,7 +177,7 @@ static int build_merkle_tree(struct file *filp, * (level 0) and ascending to the root node (level 'num_levels - 1'). * Then at the end (level 'num_levels'), calculate the root hash. */ - blocks = (inode->i_size + params->block_size - 1) >> + blocks = ((u64)inode->i_size + params->block_size - 1) >> params->log_blocksize; for (level = 0; level <= params->num_levels; level++) { err = build_merkle_tree_level(filp, level, blocks, params, diff --git a/fs/verity/open.c b/fs/verity/open.c index 60ff8af7219f..92df87f5fa38 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -89,7 +89,7 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, */ /* Compute number of levels and the number of blocks in each level */ - blocks = (inode->i_size + params->block_size - 1) >> log_blocksize; + blocks = ((u64)inode->i_size + params->block_size - 1) >> log_blocksize; pr_debug("Data is %lld bytes (%llu blocks)\n", inode->i_size, blocks); while (blocks > 1) { if (params->num_levels >= FS_VERITY_MAX_LEVELS) { diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 864b9997efb2..90f21898aad8 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -61,7 +61,6 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); -int kvm_pmu_probe_pmuver(void); #else struct kvm_pmu { }; @@ -118,8 +117,6 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return 0; } -static inline int kvm_pmu_probe_pmuver(void) { return 0xf; } - #endif #endif diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f4c16f19f83e..020a7d5bf470 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -578,11 +578,12 @@ struct btf_func_model { * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) - /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) +/* Return the return value of fentry prog. Only used by bpf_struct_ops. */ +#define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 5d4d07a9e1ed..1e7399fc69c0 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -996,14 +996,15 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * - * Returns the length of how many bytes have been copied. + * Returns the length of how many bytes have been copied, excluding + * terminating '\0'. */ static inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } /** @@ -1018,7 +1019,7 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 59828516ebaf..9f4ad719bfe3 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -22,10 +22,15 @@ struct device; * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. * NOT_DEVICE: The fwnode will never be populated as a struct device. * INITIALIZED: The hardware corresponding to fwnode has been initialized. + * NEEDS_CHILD_BOUND_ON_ADD: For this fwnode/device to probe successfully, its + * driver needs its child devices to be bound with + * their respective drivers as soon as they are + * added. */ -#define FWNODE_FLAG_LINKS_ADDED BIT(0) -#define FWNODE_FLAG_NOT_DEVICE BIT(1) -#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_LINKS_ADDED BIT(0) +#define FWNODE_FLAG_NOT_DEVICE BIT(1) +#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD BIT(3) struct fwnode_handle { struct fwnode_handle *secondary; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 041ca7f15ea4..0f18df7fe874 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -608,7 +608,6 @@ struct kvm { unsigned long mmu_notifier_range_start; unsigned long mmu_notifier_range_end; #endif - long tlbs_dirty; struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; @@ -721,11 +720,6 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) -{ - return vcpu->vcpu_idx; -} - #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ memslot < slots->memslots + slots->used_slots; memslot++) \ diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 505480217cf1..2512e2f9cd4e 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -163,6 +163,12 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn); static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } #endif +#ifdef CONFIG_KVM +void kvm_host_pmu_init(struct arm_pmu *pmu); +#else +#define kvm_host_pmu_init(x) do { } while(0) +#endif + /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); struct arm_pmu *armpmu_alloc_atomic(void); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fe156a8170aa..9b60bb89d86a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -683,7 +683,9 @@ struct perf_event { /* * timestamp shadows the actual context timing but it can * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in. + * context time as it was when the event was last scheduled in, + * or when ctx_sched_in failed to schedule the event because we + * run out of PMC. * * ctx_time already accounts for ctx->timestamp. Therefore to * compute ctx_time for a sample, simply add perf_clock(). diff --git a/include/linux/sched.h b/include/linux/sched.h index 39039ce8ac4c..c1a927ddec64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1720,7 +1720,7 @@ extern struct pid *cad_pid; #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -static inline bool is_percpu_thread(void) +static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && diff --git a/include/media/tuner.h b/include/media/tuner.h index ff85d7227f91..a7796e0a3659 100644 --- a/include/media/tuner.h +++ b/include/media/tuner.h @@ -132,6 +132,7 @@ #define TUNER_SONY_BTF_PG472Z 89 /* PAL+SECAM */ #define TUNER_SONY_BTF_PK467Z 90 /* NTSC_JP */ #define TUNER_SONY_BTF_PB463Z 91 /* NTSC */ +#define TUNER_SI2157 92 /* tv card specific */ #define TDA9887_PRESENT (1<<0) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 21c5386d4a6d..ab5348e57db1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -597,5 +597,5 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, - int nh_weight, u8 rt_family); + int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index af0fc13cea34..618d1f427cb2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2818,13 +2818,13 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag * when they are able to replace in-use PTK keys according to the following * requirements: - * 1) They do not hand over frames decrypted with the old key to - mac80211 once the call to set_key() with command %DISABLE_KEY has been - completed when also setting @IEEE80211_KEY_FLAG_GENERATE_IV for any key, + * 1) They do not hand over frames decrypted with the old key to mac80211 + once the call to set_key() with command %DISABLE_KEY has been completed, 2) either drop or continue to use the old key for any outgoing frames queued at the time of the key deletion (including re-transmits), 3) never send out a frame queued prior to the set_key() %SET_KEY command - encrypted with the new key and + encrypted with the new key when also needing + @IEEE80211_KEY_FLAG_GENERATE_IV and 4) never send out a frame unencrypted when it should be encrypted. Mac80211 will not queue any new frames for a deleted key to the driver. */ diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 10e1777877e6..28085b995ddc 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -325,7 +325,7 @@ int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; - if (fib_add_nexthop(skb, nhc, weight, rt_family) < 0) + if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 6d7b12cba015..bf79f3a890af 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -11,6 +11,7 @@ #include #define DEFAULT_TX_QUEUE_LEN 1000 +#define STAB_SIZE_LOG_MAX 30 struct qdisc_walker { int stop; diff --git a/include/net/sock.h b/include/net/sock.h index c005c3c750e8..ae929e21a376 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -488,8 +488,10 @@ struct sock { u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; #endif + spinlock_t sk_peer_lock; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; + long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 @@ -1623,7 +1625,36 @@ void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); + +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken: + * + * sk_lock.slock locked, owned = 0, BH disabled + * + * return true if slow path is taken: + * + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +static inline bool lock_sock_fast(struct sock *sk) +{ + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} + +/* fast socket lock variant for caller already holding a [different] socket lock */ +static inline bool lock_sock_fast_nested(struct sock *sk) +{ + mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} /** * unlock_sock_fast - complement of lock_sock_fast diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 989e1517332d..7a08ed2acd60 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -98,6 +98,7 @@ struct snd_rawmidi_file { struct snd_rawmidi *rmidi; struct snd_rawmidi_substream *input; struct snd_rawmidi_substream *output; + unsigned int user_pversion; /* supported protocol version */ }; struct snd_rawmidi_str { diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 9a448fe9355d..695bfdbfdcad 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -305,7 +305,7 @@ TRACE_EVENT(cachefiles_mark_buried, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->why = why; ), diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 1d84ec9db93b..5859ca0a1439 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -784,6 +784,7 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) +#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) #define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params) #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index d6731c32864e..9abcc33f02cf 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -368,6 +368,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, const struct btf_type *mtype, *ptype; struct bpf_prog *prog; u32 moff; + u32 flags; moff = btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); @@ -431,10 +432,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + flags = st_ops->func_models[i].ret_size > 0 ? + BPF_TRAMP_F_RET_FENTRY_RET : 0; err = arch_prepare_bpf_trampoline(NULL, image, st_map->image + PAGE_SIZE, - &st_ops->func_models[i], 0, - tprogs, NULL); + &st_ops->func_models[i], + flags, tprogs, NULL); if (err < 0) goto reset_unlock; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f4636d021b1..d6b7dfdd8066 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -827,7 +827,7 @@ int bpf_jit_charge_modmem(u32 pages) { if (atomic_long_add_return(pages, &bpf_jit_current) > (bpf_jit_limit >> PAGE_SHIFT)) { - if (!capable(CAP_SYS_ADMIN)) { + if (!bpf_capable()) { atomic_long_sub(pages, &bpf_jit_current); return -EPERM; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8afa8690d288..570b0c97392a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6574,22 +6574,29 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - /* Don't associate the sock with unrelated interrupted task's cgroup. */ - if (in_interrupt()) - return; + struct cgroup *cgroup; rcu_read_lock(); + /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) { + cgroup = &cgrp_dfl_root.cgrp; + cgroup_get(cgroup); + goto out; + } + while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->cgroup = cset->dfl_cgrp; - cgroup_bpf_get(cset->dfl_cgrp); + cgroup = cset->dfl_cgrp; break; } cpu_relax(); } +out: + skcd->cgroup = cgroup; + cgroup_bpf_get(cgroup); rcu_read_unlock(); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 0c000cb01eeb..f23ca260307f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3707,6 +3707,29 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +static inline bool event_update_userpage(struct perf_event *event) +{ + if (likely(!atomic_read(&event->mmap_count))) + return false; + + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); + perf_event_update_userpage(event); + + return true; +} + +static inline void group_update_userpage(struct perf_event *group_event) +{ + struct perf_event *event; + + if (!event_update_userpage(group_event)) + return; + + for_each_sibling_event(event, group_event) + event_update_userpage(event); +} + static int merge_sched_in(struct perf_event *event, void *data) { struct perf_event_context *ctx = event->ctx; @@ -3725,14 +3748,15 @@ static int merge_sched_in(struct perf_event *event, void *data) } if (event->state == PERF_EVENT_STATE_INACTIVE) { + *can_add_hw = 0; if (event->attr.pinned) { perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } else { + ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); + group_update_userpage(event); } - - *can_add_hw = 0; - ctx->rotate_necessary = 1; - perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6324,6 +6348,8 @@ accounting: ring_buffer_attach(event, rb); + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 49716228efb4..17a653b67006 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -173,16 +173,22 @@ static ssize_t sched_scaling_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[16]; + unsigned int scaling; if (cnt > 15) cnt = 15; if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; + buf[cnt] = '\0'; - if (kstrtouint(buf, 10, &sysctl_sched_tunable_scaling)) + if (kstrtouint(buf, 10, &scaling)) return -EINVAL; + if (scaling >= SCHED_TUNABLESCALING_END) + return -EINVAL; + + sysctl_sched_tunable_scaling = scaling; if (sched_update_scaling()) return -EINVAL; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ff69f245b939..f6a05d9b5443 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4936,8 +4936,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); - if (!cfs_rq->load.weight) + /* Nothing to run but something to decay (on_list)? Complete the branch */ + if (!cfs_rq->load.weight) { + if (cfs_rq->on_list) + goto unthrottle_throttle; return; + } task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2eb0e55ef54d..b5f4ef35357c 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -552,6 +552,12 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) __skb->gso_segs = skb_shinfo(skb)->gso_segs; } +static struct proto bpf_dummy_proto = { + .name = "bpf_dummy", + .owner = THIS_MODULE, + .obj_size = sizeof(struct sock), +}; + int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { @@ -596,20 +602,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, break; } - sk = kzalloc(sizeof(struct sock), GFP_USER); + sk = sk_alloc(net, AF_UNSPEC, GFP_USER, &bpf_dummy_proto, 1); if (!sk) { kfree(data); kfree(ctx); return -ENOMEM; } - sock_net_set(sk, net); sock_init_data(NULL, sk); skb = build_skb(data, 0); if (!skb) { kfree(data); kfree(ctx); - kfree(sk); + sk_free(sk); return -ENOMEM; } skb->sk = sk; @@ -682,8 +687,7 @@ out: if (dev && dev != net->loopback_dev) dev_put(dev); kfree_skb(skb); - bpf_sk_storage_free(sk); - kfree(sk); + sk_free(sk); kfree(ctx); return ret; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3523c8c7068f..f3d751105343 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1677,8 +1677,6 @@ static void br_multicast_update_querier(struct net_bridge_mcast *brmctx, int ifindex, struct br_ip *saddr) { - lockdep_assert_held_once(&brmctx->br->multicast_lock); - write_seqcount_begin(&querier->seq); querier->port_ifidx = ifindex; memcpy(&querier->addr, saddr, sizeof(*saddr)); @@ -3867,13 +3865,13 @@ void br_multicast_ctx_init(struct net_bridge *br, brmctx->ip4_other_query.delay_time = 0; brmctx->ip4_querier.port_ifidx = 0; - seqcount_init(&brmctx->ip4_querier.seq); + seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; brmctx->ip6_other_query.delay_time = 0; brmctx->ip6_querier.port_ifidx = 0; - seqcount_init(&brmctx->ip6_querier.seq); + seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif timer_setup(&brmctx->ip4_mc_router_timer, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b4cef3a97f12..e8136db44462 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -82,7 +82,7 @@ struct bridge_mcast_other_query { struct bridge_mcast_querier { struct br_ip addr; int port_ifidx; - seqcount_t seq; + seqcount_spinlock_t seq; }; /* IGMP/MLD statistics */ diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 8c39283c26ae..f0cb38344126 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -50,6 +50,11 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, if (addr_len > MAX_ADDR_LEN) return -EINVAL; + ha = list_first_entry(&list->list, struct netdev_hw_addr, list); + if (ha && !memcmp(addr, ha->addr, addr_len) && + (!addr_type || addr_type == ha->type)) + goto found_it; + while (*ins_point) { int diff; @@ -64,6 +69,7 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, } else if (diff > 0) { ins_point = &parent->rb_right; } else { +found_it: if (exclusive) return -EEXIST; if (global) { diff --git a/net/core/sock.c b/net/core/sock.c index 512e629f9780..c1601f75ec4b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1376,6 +1376,16 @@ set_sndbuf: } EXPORT_SYMBOL(sock_setsockopt); +static const struct cred *sk_get_peer_cred(struct sock *sk) +{ + const struct cred *cred; + + spin_lock(&sk->sk_peer_lock); + cred = get_cred(sk->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + return cred; +} static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) @@ -1552,7 +1562,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); + + spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + spin_unlock(&sk->sk_peer_lock); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; @@ -1560,20 +1574,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_PEERGROUPS: { + const struct cred *cred; int ret, n; - if (!sk->sk_peer_cred) + cred = sk_get_peer_cred(sk); + if (!cred) return -ENODATA; - n = sk->sk_peer_cred->group_info->ngroups; + n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); + put_cred(cred); return put_user(len, optlen) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, - sk->sk_peer_cred->group_info); + ret = groups_to_user((gid_t __user *)optval, cred->group_info); + put_cred(cred); if (ret) return ret; goto lenout; @@ -1935,9 +1952,10 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_frag.page = NULL; } - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ + put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); + if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); @@ -3145,6 +3163,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; + spin_lock_init(&sk->sk_peer_lock); + sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; @@ -3210,24 +3230,8 @@ void release_sock(struct sock *sk) } EXPORT_SYMBOL(release_sock); -/** - * lock_sock_fast - fast version of lock_sock - * @sk: socket - * - * This version should be used for very small section, where process wont block - * return false if fast path is taken: - * - * sk_lock.slock locked, owned = 0, BH disabled - * - * return true if slow path is taken: - * - * sk_lock.slock unlocked, owned = 1, BH enabled - */ -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { - /* The sk_lock has mutex_lock() semantics here. */ - mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); - might_sleep(); spin_lock_bh(&sk->sk_lock.slock); @@ -3256,7 +3260,7 @@ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) spin_unlock_bh(&sk->sk_lock.slock); return true; } -EXPORT_SYMBOL(lock_sock_fast); +EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b42c429cebbe..3364cb9c67e0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1661,7 +1661,7 @@ EXPORT_SYMBOL_GPL(fib_nexthop_info); #if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6) int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, - int nh_weight, u8 rt_family) + int nh_weight, u8 rt_family, u32 nh_tclassid) { const struct net_device *dev = nhc->nhc_dev; struct rtnexthop *rtnh; @@ -1679,6 +1679,9 @@ int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, rtnh->rtnh_flags = flags; + if (nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh_tclassid)) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; @@ -1706,14 +1709,13 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) } for_nexthops(fi) { - if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, - AF_INET) < 0) - goto nla_put_failure; + u32 nh_tclassid = 0; #ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid && - nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) - goto nla_put_failure; + nh_tclassid = nh->nh_tclassid; #endif + if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, + AF_INET, nh_tclassid) < 0) + goto nla_put_failure; } endfor_nexthops(fi); mp_end: diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index b88e0f36cd05..8265c6765705 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -42,7 +42,7 @@ iptable_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init iptable_raw_table_init(struct net *net) +static int iptable_raw_table_init(struct net *net) { struct ipt_replace *repl; const struct xt_table *table = &packet_raw; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8851c9463b4b..2a7825a5b842 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1053,7 +1053,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; @@ -1361,7 +1361,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, } up->len += size; - if (!(up->corkflag || (flags&MSG_MORE))) + if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) ret = udp_push_pending_frames(sk); if (!ret) ret = size; @@ -2662,9 +2662,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: if (val != 0) { - up->corkflag = 1; + WRITE_ONCE(up->corkflag, 1); } else { - up->corkflag = 0; + WRITE_ONCE(up->corkflag, 0); lock_sock(sk); push_pending_frames(sk); release_sock(sk); @@ -2787,7 +2787,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: - val = up->corkflag; + val = READ_ONCE(up->corkflag); break; case UDP_ENCAP: diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index de2cf3943b91..a579ea14a69b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -273,6 +273,7 @@ ip6t_do_table(struct sk_buff *skb, * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ + acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dbc224023977..9b9ef09382ab 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5681,14 +5681,15 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, - rt->fib6_nh->fib_nh_weight, AF_INET6) < 0) + rt->fib6_nh->fib_nh_weight, AF_INET6, + 0) < 0) goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6) < 0) + AF_INET6, 0) < 0) goto nla_put_failure; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index ea53847b5b7e..e505bb007e9f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1303,7 +1303,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index efbefcbac3ac..7cab1cf09bf1 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -60,7 +60,10 @@ static struct mesh_table *mesh_table_alloc(void) atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); spin_lock_init(&newtbl->walk_lock); - rhashtable_init(&newtbl->rhead, &mesh_rht_params); + if (rhashtable_init(&newtbl->rhead, &mesh_rht_params)) { + kfree(newtbl); + return NULL; + } return newtbl; } diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 204830a55240..3fbd0b9ff913 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -2,6 +2,7 @@ /* * Copyright 2012-2013, Marco Porsch * Copyright 2012-2013, cozybit Inc. + * Copyright (C) 2021 Intel Corporation */ #include "mesh.h" @@ -588,7 +589,7 @@ void ieee80211_mps_frame_release(struct sta_info *sta, /* only transmit to PS STA with announced, non-zero awake window */ if (test_sta_flag(sta, WLAN_STA_PS_STA) && - (!elems->awake_window || !le16_to_cpu(*elems->awake_window))) + (!elems->awake_window || !get_unaligned_le16(elems->awake_window))) return; if (!test_sta_flag(sta, WLAN_STA_MPSP_OWNER)) diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index e5935e3d7a07..8c6416129d5b 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -392,10 +392,6 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta, int mcast_rate; bool use_basicrate = false; - if (ieee80211_is_tx_data(txrc->skb) && - info->flags & IEEE80211_TX_CTL_NO_ACK) - return false; - if (!pubsta || rc_no_data_or_no_ack_use_min(txrc)) { __rate_control_send_low(txrc->hw, sband, pubsta, info, txrc->rate_idx_mask); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 99ed68f7dc36..c4071b015c18 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4131,7 +4131,8 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) if (!bssid) return false; if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || - ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) + ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2) || + !is_valid_ether_addr(hdr->addr2)) return false; if (ieee80211_is_beacon(hdr->frame_control)) return true; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2d1193ed3eb5..8921088a5df6 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2209,7 +2209,11 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, } vht_mcs = iterator.this_arg[4] >> 4; + if (vht_mcs > 11) + vht_mcs = 0; vht_nss = iterator.this_arg[4] & 0xF; + if (!vht_nss || vht_nss > 8) + vht_nss = 1; break; /* @@ -3380,6 +3384,14 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) goto out; + /* If n == 2, the "while (*frag_tail)" loop above didn't execute + * and frag_tail should be &skb_shinfo(head)->frag_list. + * However, ieee80211_amsdu_prepare_head() can reallocate it. + * Reload frag_tail to have it pointing to the correct place. + */ + if (n == 2) + frag_tail = &skb_shinfo(head)->frag_list; + /* * Pad out the previous subframe to a multiple of 4 by adding the * padding to the next one, that's being added. Note that head->len diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index bca47fad5a16..4eed23e27610 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -520,6 +520,9 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; @@ -749,6 +752,9 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index f48eb6315bbb..292374fb0779 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -36,7 +36,7 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb, struct sock *sk; net = sock_net(in_skb->sk); - msk = mptcp_token_get_sock(req->id.idiag_cookie[0]); + msk = mptcp_token_get_sock(net, req->id.idiag_cookie[0]); if (!msk) goto out_nosk; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index c4f9a5ce3815..050eea231528 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1718,9 +1718,7 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) list_for_each_entry(entry, &pernet->local_addr_list, list) { if (addresses_equal(&entry->addr, &addr.addr, true)) { - ret = mptcp_nl_addr_backup(net, &entry->addr, bkup); - if (ret) - return ret; + mptcp_nl_addr_backup(net, &entry->addr, bkup); if (bkup) entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index dbcebf56798f..e5df0b5971c8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2735,7 +2735,7 @@ cleanup: inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(mptcp_sk(sk), subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow = lock_sock_fast(ssk); + bool slow = lock_sock_fast_nested(ssk); sock_orphan(ssk); unlock_sock_fast(ssk, slow); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index d3e6fd1615f1..dc984676c5eb 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -709,7 +709,7 @@ int mptcp_token_new_connect(struct sock *sk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); bool mptcp_token_exists(u32 token); -struct mptcp_sock *mptcp_token_get_sock(u32 token); +struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token); struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, long *s_num); void mptcp_token_destroy(struct mptcp_sock *msk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 1de7ce883c37..6172f380dfb7 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -86,7 +86,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) struct mptcp_sock *msk; int local_id; - msk = mptcp_token_get_sock(subflow_req->token); + msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token); if (!msk) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN); return NULL; diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index 37127781aee9..7f22526346a7 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -108,18 +108,12 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl e->valid = 0; - msk = mptcp_token_get_sock(e->token); + msk = mptcp_token_get_sock(net, e->token); if (!msk) { spin_unlock_bh(&join_entry_locks[i]); return false; } - /* If this fails, the token got re-used in the mean time by another - * mptcp socket in a different netns, i.e. entry is outdated. - */ - if (!net_eq(sock_net((struct sock *)msk), net)) - goto err_put; - subflow_req->remote_nonce = e->remote_nonce; subflow_req->local_nonce = e->local_nonce; subflow_req->backup = e->backup; @@ -128,11 +122,6 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl subflow_req->msk = msk; spin_unlock_bh(&join_entry_locks[i]); return true; - -err_put: - spin_unlock_bh(&join_entry_locks[i]); - sock_put((struct sock *)msk); - return false; } void __init mptcp_join_cookie_init(void) diff --git a/net/mptcp/token.c b/net/mptcp/token.c index a98e554b034f..e581b341c5be 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -231,6 +231,7 @@ found: /** * mptcp_token_get_sock - retrieve mptcp connection sock using its token + * @net: restrict to this namespace * @token: token of the mptcp connection to retrieve * * This function returns the mptcp connection structure with the given token. @@ -238,7 +239,7 @@ found: * * returns NULL if no connection with the given token value exists. */ -struct mptcp_sock *mptcp_token_get_sock(u32 token) +struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token) { struct hlist_nulls_node *pos; struct token_bucket *bucket; @@ -251,11 +252,15 @@ struct mptcp_sock *mptcp_token_get_sock(u32 token) again: sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { msk = mptcp_sk(sk); - if (READ_ONCE(msk->token) != token) + if (READ_ONCE(msk->token) != token || + !net_eq(sock_net(sk), net)) continue; + if (!refcount_inc_not_zero(&sk->sk_refcnt)) goto not_found; - if (READ_ONCE(msk->token) != token) { + + if (READ_ONCE(msk->token) != token || + !net_eq(sock_net(sk), net)) { sock_put(sk); goto again; } diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index e1bd6f0a0676..5d984bec1cd8 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -11,6 +11,7 @@ static struct mptcp_subflow_request_sock *build_req_sock(struct kunit *test) GFP_USER); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, req); mptcp_token_init_request((struct request_sock *)req); + sock_net_set((struct sock *)req, &init_net); return req; } @@ -22,7 +23,7 @@ static void mptcp_token_test_req_basic(struct kunit *test) KUNIT_ASSERT_EQ(test, 0, mptcp_token_new_request((struct request_sock *)req)); KUNIT_EXPECT_NE(test, 0, (int)req->token); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(req->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, req->token)); /* cleanup */ mptcp_token_destroy_request((struct request_sock *)req); @@ -55,6 +56,7 @@ static struct mptcp_sock *build_msk(struct kunit *test) msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk); refcount_set(&((struct sock *)msk)->sk_refcnt, 1); + sock_net_set((struct sock *)msk, &init_net); return msk; } @@ -74,11 +76,11 @@ static void mptcp_token_test_msk_basic(struct kunit *test) mptcp_token_new_connect((struct sock *)icsk)); KUNIT_EXPECT_NE(test, 0, (int)ctx->token); KUNIT_EXPECT_EQ(test, ctx->token, msk->token); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(ctx->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, ctx->token)); KUNIT_EXPECT_EQ(test, 2, (int)refcount_read(&sk->sk_refcnt)); mptcp_token_destroy(msk); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(ctx->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, ctx->token)); } static void mptcp_token_test_accept(struct kunit *test) @@ -90,11 +92,11 @@ static void mptcp_token_test_accept(struct kunit *test) mptcp_token_new_request((struct request_sock *)req)); msk->token = req->token; mptcp_token_accept(req, msk); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token)); /* this is now a no-op */ mptcp_token_destroy_request((struct request_sock *)req); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token)); /* cleanup */ mptcp_token_destroy(msk); @@ -116,7 +118,7 @@ static void mptcp_token_test_destroyed(struct kunit *test) /* simulate race on removal */ refcount_set(&sk->sk_refcnt, 0); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, msk->token)); /* cleanup */ mptcp_token_destroy(msk); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 6186358eac7c..6e391308431d 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -130,11 +130,11 @@ htable_size(u8 hbits) { size_t hsize; - /* We must fit both into u32 in jhash and size_t */ + /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */ if (hbits > 31) return 0; hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *) + if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *) < hsize) return 0; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c100c6b112c8..2c467c422dc6 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1468,6 +1468,10 @@ int __init ip_vs_conn_init(void) int idx; /* Compute size and mask */ + if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) { + pr_info("conn_tab_bits not in [8, 20]. Using default value\n"); + ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; + } ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 94e18fb9690d..770a63103c7a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -74,10 +74,14 @@ static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; +/* serialize hash resizes and nf_ct_iterate_cleanup */ +static DEFINE_MUTEX(nf_conntrack_mutex); + #define GC_SCAN_INTERVAL (120u * HZ) #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) -#define MAX_CHAINLEN 64u +#define MIN_CHAINLEN 8u +#define MAX_CHAINLEN (32u - MIN_CHAINLEN) static struct conntrack_gc_work conntrack_gc_work; @@ -188,11 +192,13 @@ seqcount_spinlock_t nf_conntrack_generation __read_mostly; static siphash_key_t nf_conntrack_hash_rnd __read_mostly; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, const struct net *net) { struct { struct nf_conntrack_man src; union nf_inet_addr dst_addr; + unsigned int zone; u32 net_mix; u16 dport; u16 proto; @@ -205,6 +211,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, /* The direction must be ignored, so handle usable members manually. */ combined.src = tuple->src; combined.dst_addr = tuple->dst.u3; + combined.zone = zoneid; combined.net_mix = net_hash_mix(net); combined.dport = (__force __u16)tuple->dst.u.all; combined.proto = tuple->dst.protonum; @@ -219,15 +226,17 @@ static u32 scale_hash(u32 hash) static u32 __hash_conntrack(const struct net *net, const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, unsigned int size) { - return reciprocal_scale(hash_conntrack_raw(tuple, net), size); + return reciprocal_scale(hash_conntrack_raw(tuple, zoneid, net), size); } static u32 hash_conntrack(const struct net *net, - const struct nf_conntrack_tuple *tuple) + const struct nf_conntrack_tuple *tuple, + unsigned int zoneid) { - return scale_hash(hash_conntrack_raw(tuple, net)); + return scale_hash(hash_conntrack_raw(tuple, zoneid, net)); } static bool nf_ct_get_tuple_ports(const struct sk_buff *skb, @@ -650,9 +659,11 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); clean_from_lists(ct); @@ -819,8 +830,20 @@ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - return __nf_conntrack_find_get(net, zone, tuple, - hash_conntrack_raw(tuple, net)); + unsigned int rid, zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + struct nf_conntrack_tuple_hash *thash; + + thash = __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, zone_id, net)); + + if (thash) + return thash; + + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (rid != zone_id) + return __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, rid, net)); + return thash; } EXPORT_SYMBOL_GPL(nf_conntrack_find_get); @@ -842,6 +865,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; + unsigned int max_chainlen; unsigned int chainlen = 0; unsigned int sequence; int err = -EEXIST; @@ -852,18 +876,22 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); + /* See if there's one in the list already, including reverse */ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -873,7 +901,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1103,8 +1131,8 @@ drop: int __nf_conntrack_confirm(struct sk_buff *skb) { + unsigned int chainlen = 0, sequence, max_chainlen; const struct nf_conntrack_zone *zone; - unsigned int chainlen = 0, sequence; unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; @@ -1133,8 +1161,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; hash = scale_hash(hash); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* We're not in hash table, and we refuse to set up related @@ -1168,6 +1196,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) goto dying; } + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ @@ -1175,7 +1204,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1184,7 +1213,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) { + if (chainlen++ > max_chainlen) { chaintoolong: nf_ct_add_to_dying_list(ct); NF_CT_STAT_INC(net, chaintoolong); @@ -1246,7 +1275,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, rcu_read_lock(); begin: nf_conntrack_get_ht(&ct_hash, &hsize); - hash = __hash_conntrack(net, tuple, hsize); + hash = __hash_conntrack(net, tuple, nf_ct_zone_id(zone, IP_CT_DIR_REPLY), hsize); hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); @@ -1687,8 +1716,8 @@ resolve_normal_ct(struct nf_conn *tmpl, struct nf_conntrack_tuple_hash *h; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; + u32 hash, zone_id, rid; struct nf_conn *ct; - u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, state->pf, protonum, state->net, @@ -1699,8 +1728,20 @@ resolve_normal_ct(struct nf_conn *tmpl, /* look for tuple match */ zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); - hash = hash_conntrack_raw(&tuple, state->net); + + zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + hash = hash_conntrack_raw(&tuple, zone_id, state->net); h = __nf_conntrack_find_get(state->net, zone, &tuple, hash); + + if (!h) { + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (zone_id != rid) { + u32 tmp = hash_conntrack_raw(&tuple, rid, state->net); + + h = __nf_conntrack_find_get(state->net, zone, &tuple, tmp); + } + } + if (!h) { h = init_conntrack(state->net, tmpl, &tuple, skb, dataoff, hash); @@ -2225,28 +2266,31 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), spinlock_t *lockp; for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { + struct hlist_nulls_head *hslot = &nf_conntrack_hash[*bucket]; + + if (hlist_nulls_empty(hslot)) + continue; + lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; local_bh_disable(); nf_conntrack_lock(lockp); - if (*bucket < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) - continue; - /* All nf_conn objects are added to hash table twice, one - * for original direction tuple, once for the reply tuple. - * - * Exception: In the IPS_NAT_CLASH case, only the reply - * tuple is added (the original tuple already existed for - * a different object). - * - * We only need to call the iterator once for each - * conntrack, so we just use the 'reply' direction - * tuple while iterating. - */ - ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - goto found; - } + hlist_nulls_for_each_entry(h, n, hslot, hnnode) { + if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) + continue; + /* All nf_conn objects are added to hash table twice, one + * for original direction tuple, once for the reply tuple. + * + * Exception: In the IPS_NAT_CLASH case, only the reply + * tuple is added (the original tuple already existed for + * a different object). + * + * We only need to call the iterator once for each + * conntrack, so we just use the 'reply' direction + * tuple while iterating. + */ + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; } spin_unlock(lockp); local_bh_enable(); @@ -2264,26 +2308,20 @@ found: static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { - unsigned int bucket = 0, sequence; + unsigned int bucket = 0; struct nf_conn *ct; might_sleep(); - for (;;) { - sequence = read_seqcount_begin(&nf_conntrack_generation); + mutex_lock(&nf_conntrack_mutex); + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { + /* Time to push up daises... */ - while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { - /* Time to push up daises... */ - - nf_ct_delete(ct, portid, report); - nf_ct_put(ct); - cond_resched(); - } - - if (!read_seqcount_retry(&nf_conntrack_generation, sequence)) - break; - bucket = 0; + nf_ct_delete(ct, portid, report); + nf_ct_put(ct); + cond_resched(); } + mutex_unlock(&nf_conntrack_mutex); } struct iter_data { @@ -2519,8 +2557,10 @@ int nf_conntrack_hash_resize(unsigned int hashsize) if (!hash) return -ENOMEM; + mutex_lock(&nf_conntrack_mutex); old_size = nf_conntrack_htable_size; if (old_size == hashsize) { + mutex_unlock(&nf_conntrack_mutex); kvfree(hash); return 0; } @@ -2537,12 +2577,16 @@ int nf_conntrack_hash_resize(unsigned int hashsize) for (i = 0; i < nf_conntrack_htable_size; i++) { while (!hlist_nulls_empty(&nf_conntrack_hash[i])) { + unsigned int zone_id; + h = hlist_nulls_entry(nf_conntrack_hash[i].first, struct nf_conntrack_tuple_hash, hnnode); ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); + + zone_id = nf_ct_zone_id(nf_ct_zone(ct), NF_CT_DIRECTION(h)); bucket = __hash_conntrack(nf_ct_net(ct), - &h->tuple, hashsize); + &h->tuple, zone_id, hashsize); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } @@ -2556,6 +2600,8 @@ int nf_conntrack_hash_resize(unsigned int hashsize) nf_conntrack_all_unlock(); local_bh_enable(); + mutex_unlock(&nf_conntrack_mutex); + synchronize_net(); kvfree(old_hash); return 0; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 7008961f5cb0..273117683922 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -150,13 +150,16 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) /* We keep an extra hash for each conntrack, for fast searching. */ static unsigned int -hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, + const struct nf_conntrack_zone *zone, + const struct nf_conntrack_tuple *tuple) { unsigned int hash; struct { struct nf_conntrack_man src; u32 net_mix; u32 protonum; + u32 zone; } __aligned(SIPHASH_ALIGNMENT) combined; get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); @@ -165,9 +168,13 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) /* Original src, to ensure we map it consistently if poss. */ combined.src = tuple->src; - combined.net_mix = net_hash_mix(n); + combined.net_mix = net_hash_mix(net); combined.protonum = tuple->dst.protonum; + /* Zone ID can be used provided its valid for both directions */ + if (zone->dir == NF_CT_DEFAULT_ZONE_DIR) + combined.zone = zone->id; + hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd); return reciprocal_scale(hash, nf_nat_htable_size); @@ -272,7 +279,7 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range2 *range) { - unsigned int h = hash_by_src(net, tuple); + unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn *ct; hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) { @@ -619,7 +626,7 @@ nf_nat_setup_info(struct nf_conn *ct, unsigned int srchash; spinlock_t *lock; - srchash = hash_by_src(net, + srchash = hash_by_src(net, nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS]; spin_lock_bh(lock); @@ -788,7 +795,7 @@ static void __nf_nat_cleanup_conntrack(struct nf_conn *ct) { unsigned int h; - h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + h = hash_by_src(nf_ct_net(ct), nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); hlist_del_rcu(&ct->nat_bysource); spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c index 8e8a65d46345..acd73f717a08 100644 --- a/net/netfilter/nf_nat_masquerade.c +++ b/net/netfilter/nf_nat_masquerade.c @@ -9,8 +9,19 @@ #include +struct masq_dev_work { + struct work_struct work; + struct net *net; + union nf_inet_addr addr; + int ifindex; + int (*iter)(struct nf_conn *i, void *data); +}; + +#define MAX_MASQ_WORKER_COUNT 16 + static DEFINE_MUTEX(masq_mutex); static unsigned int masq_refcnt __read_mostly; +static atomic_t masq_worker_count __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, @@ -63,13 +74,71 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4); -static int device_cmp(struct nf_conn *i, void *ifindex) +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + + w = container_of(work, struct masq_dev_work, work); + + nf_ct_iterate_cleanup_net(w->net, w->iter, (void *)w, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&masq_worker_count); + module_put(THIS_MODULE); +} + +/* Iterate conntrack table in the background and remove conntrack entries + * that use the device/address being removed. + * + * In case too many work items have been queued already or memory allocation + * fails iteration is skipped, conntrack entries will time out eventually. + */ +static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, + int ifindex, + int (*iter)(struct nf_conn *i, void *data), + gfp_t gfp_flags) +{ + struct masq_dev_work *w; + + if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT) + return; + + net = maybe_get_net(net); + if (!net) + return; + + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kzalloc(sizeof(*w), gfp_flags); + if (w) { + /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */ + atomic_inc(&masq_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = ifindex; + w->net = net; + w->iter = iter; + if (addr) + w->addr = *addr; + schedule_work(&w->work); + return; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); +} + +static int device_cmp(struct nf_conn *i, void *arg) { const struct nf_conn_nat *nat = nfct_nat(i); + const struct masq_dev_work *w = arg; if (!nat) return 0; - return nat->masq_index == (int)(long)ifindex; + return nat->masq_index == w->ifindex; } static int masq_device_event(struct notifier_block *this, @@ -85,8 +154,8 @@ static int masq_device_event(struct notifier_block *this, * and forget them. */ - nf_ct_iterate_cleanup_net(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_nat_masq_schedule(net, NULL, dev->ifindex, + device_cmp, GFP_KERNEL); } return NOTIFY_DONE; @@ -94,35 +163,45 @@ static int masq_device_event(struct notifier_block *this, static int inet_cmp(struct nf_conn *ct, void *ptr) { - struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - struct net_device *dev = ifa->ifa_dev->dev; struct nf_conntrack_tuple *tuple; + struct masq_dev_work *w = ptr; - if (!device_cmp(ct, (void *)(long)dev->ifindex)) + if (!device_cmp(ct, ptr)) return 0; tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - return ifa->ifa_address == tuple->dst.u3.ip; + return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev; - struct net *net = dev_net(idev->dev); + const struct in_ifaddr *ifa = ptr; + const struct in_device *idev; + const struct net_device *dev; + union nf_inet_addr addr; + + if (event != NETDEV_DOWN) + return NOTIFY_DONE; /* The masq_dev_notifier will catch the case of the device going * down. So if the inetdev is dead and being destroyed we have * no work to do. Otherwise this is an individual address removal * and we have to perform the flush. */ + idev = ifa->ifa_dev; if (idev->dead) return NOTIFY_DONE; - if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup_net(net, inet_cmp, ptr, 0, 0); + memset(&addr, 0, sizeof(addr)); + + addr.ip = ifa->ifa_address; + + dev = idev->dev; + nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex, + inet_cmp, GFP_KERNEL); return NOTIFY_DONE; } @@ -136,8 +215,6 @@ static struct notifier_block masq_inet_notifier = { }; #if IS_ENABLED(CONFIG_IPV6) -static atomic_t v6_worker_count __read_mostly; - static int nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, @@ -187,40 +264,6 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); -struct masq_dev_work { - struct work_struct work; - struct net *net; - struct in6_addr addr; - int ifindex; -}; - -static int inet6_cmp(struct nf_conn *ct, void *work) -{ - struct masq_dev_work *w = (struct masq_dev_work *)work; - struct nf_conntrack_tuple *tuple; - - if (!device_cmp(ct, (void *)(long)w->ifindex)) - return 0; - - tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - - return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6); -} - -static void iterate_cleanup_work(struct work_struct *work) -{ - struct masq_dev_work *w; - - w = container_of(work, struct masq_dev_work, work); - - nf_ct_iterate_cleanup_net(w->net, inet6_cmp, (void *)w, 0, 0); - - put_net(w->net); - kfree(w); - atomic_dec(&v6_worker_count); - module_put(THIS_MODULE); -} - /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). * * Defer it to the system workqueue. @@ -233,36 +276,19 @@ static int masq_inet6_event(struct notifier_block *this, { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; - struct masq_dev_work *w; - struct net *net; + union nf_inet_addr addr; - if (event != NETDEV_DOWN || atomic_read(&v6_worker_count) >= 16) + if (event != NETDEV_DOWN) return NOTIFY_DONE; dev = ifa->idev->dev; - net = maybe_get_net(dev_net(dev)); - if (!net) - return NOTIFY_DONE; - if (!try_module_get(THIS_MODULE)) - goto err_module; + memset(&addr, 0, sizeof(addr)); - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - atomic_inc(&v6_worker_count); + addr.in6 = ifa->addr; - INIT_WORK(&w->work, iterate_cleanup_work); - w->ifindex = dev->ifindex; - w->net = net; - w->addr = ifa->addr; - schedule_work(&w->work); - - return NOTIFY_DONE; - } - - module_put(THIS_MODULE); - err_module: - put_net(net); + nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp, + GFP_ATOMIC); return NOTIFY_DONE; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 081437dd75b7..b9546defdc28 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4336,7 +4336,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (ops->privsize != NULL) size = ops->privsize(nla, &desc); alloc_size = sizeof(*set) + size + udlen; - if (alloc_size < size) + if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; set = kvzalloc(alloc_size, GFP_KERNEL); if (!set) @@ -9599,7 +9599,6 @@ static void __nft_release_table(struct net *net, struct nft_table *table) table->use--; nf_tables_chain_destroy(&ctx); } - list_del(&table->list); nf_tables_table_destroy(&ctx); } @@ -9612,6 +9611,8 @@ static void __nft_release_tables(struct net *net) if (nft_table_has_owner(table)) continue; + list_del(&table->list); + __nft_release_table(net, table); } } @@ -9619,31 +9620,38 @@ static void __nft_release_tables(struct net *net) static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { + struct nft_table *table, *to_delete[8]; struct nftables_pernet *nft_net; struct netlink_notify *n = ptr; - struct nft_table *table, *nt; struct net *net = n->net; - bool release = false; + unsigned int deleted; + bool restart = false; if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; nft_net = nft_pernet(net); + deleted = 0; mutex_lock(&nft_net->commit_mutex); +again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { __nft_release_hook(net, table); - release = true; + list_del_rcu(&table->list); + to_delete[deleted++] = table; + if (deleted >= ARRAY_SIZE(to_delete)) + break; } } - if (release) { + if (deleted) { + restart = deleted >= ARRAY_SIZE(to_delete); synchronize_rcu(); - list_for_each_entry_safe(table, nt, &nft_net->tables, list) { - if (nft_table_has_owner(table) && - n->portid == table->nlpid) - __nft_release_table(net, table); - } + while (deleted) + __nft_release_table(net, to_delete[--deleted]); + + if (restart) + goto again; } mutex_unlock(&nft_net->commit_mutex); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 272bcdb1392d..f69cc73c5813 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -19,6 +19,7 @@ #include #include #include +#include /* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 @@ -257,8 +258,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); - if (ret < 0) + if (ret < 0) { + if (ret == -ENOENT) { + const char *modname = NULL; + + if (strcmp(target->name, "LOG") == 0) + modname = "nf_log_syslog"; + else if (strcmp(target->name, "NFLOG") == 0) + modname = "nfnetlink_log"; + + if (modname && + nft_request_module(ctx->net, "%s", modname) == -EAGAIN) + return -EAGAIN; + } + return ret; + } /* The standard target cannot be used */ if (!target->target) diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index 2ff75f7637b0..f39244f9c0ed 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -44,6 +44,7 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par) static int log_tg_check(const struct xt_tgchk_param *par) { const struct xt_log_info *loginfo = par->targinfo; + int ret; if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) return -EINVAL; @@ -58,7 +59,14 @@ static int log_tg_check(const struct xt_tgchk_param *par) return -EINVAL; } - return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nf_log_syslog"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + } + + return ret; } static void log_tg_destroy(const struct xt_tgdtor_param *par) diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index fb5793208059..e660c3710a10 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -42,13 +42,21 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) static int nflog_tg_check(const struct xt_tgchk_param *par) { const struct xt_nflog_info *info = par->targinfo; + int ret; if (info->flags & ~XT_NFLOG_MASK) return -EINVAL; if (info->prefix[sizeof(info->prefix) - 1] != '\0') return -EINVAL; - return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nfnetlink_log"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + } + + return ret; } static void nflog_tg_destroy(const struct xt_tgdtor_param *par) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 23b21253b3c3..eb6345a027e1 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2188,18 +2188,24 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, arg->count = arg->skip; + rcu_read_lock(); idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) { /* don't return filters that are being deleted */ if (!refcount_inc_not_zero(&f->refcnt)) continue; + rcu_read_unlock(); + if (arg->fn(tp, f, arg) < 0) { __fl_put(f); arg->stop = 1; + rcu_read_lock(); break; } __fl_put(f); arg->count++; + rcu_read_lock(); } + rcu_read_unlock(); arg->cookie = id; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 5e90e9b160e3..12f39a2dffd4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -513,6 +513,12 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, return stab; } + if (s->size_log > STAB_SIZE_LOG_MAX || + s->cell_log > STAB_SIZE_LOG_MAX) { + NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); + return ERR_PTR(-EINVAL); + } + stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); diff --git a/net/sctp/input.c b/net/sctp/input.c index 5ef86fdb1176..1f1786021d9c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -702,7 +702,7 @@ static int sctp_rcv_ootb(struct sk_buff *skb) ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(_ch)) + if (!ch || ntohs(ch->length) < sizeof(_ch)) break; ch_end = offset + SCTP_PAD4(ntohs(ch->length)); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 92345c9bb60c..efac5989edb5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -608,20 +608,42 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + spin_lock(&sk->sk_peer_lock); + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(task_tgid(current)); sk->sk_peer_cred = get_current_cred(); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static void copy_peercred(struct sock *sk, struct sock *peersk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + if (sk < peersk) { + spin_lock(&sk->sk_peer_lock); + spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&peersk->sk_peer_lock); + spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); + + spin_unlock(&sk->sk_peer_lock); + spin_unlock(&peersk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) @@ -828,20 +850,25 @@ struct proto unix_stream_proto = { static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type) { - struct sock *sk = NULL; struct unix_sock *u; + struct sock *sk; + int err; atomic_long_inc(&unix_nr_socks); - if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) - goto out; + if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) { + err = -ENFILE; + goto err; + } if (type == SOCK_STREAM) sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern); else /*dgram and seqpacket */ sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern); - if (!sk) - goto out; + if (!sk) { + err = -ENOMEM; + goto err; + } sock_init_data(sock, sk); @@ -861,20 +888,23 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); memset(&u->scm_stat, 0, sizeof(struct scm_stat)); unix_insert_socket(unix_sockets_unbound(sk), sk); -out: - if (sk == NULL) - atomic_long_dec(&unix_nr_socks); - else { - local_bh_disable(); - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - local_bh_enable(); - } + + local_bh_disable(); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + local_bh_enable(); + return sk; + +err: + atomic_long_dec(&unix_nr_socks); + return ERR_PTR(err); } static int unix_create(struct net *net, struct socket *sock, int protocol, int kern) { + struct sock *sk; + if (protocol && protocol != PF_UNIX) return -EPROTONOSUPPORT; @@ -901,7 +931,11 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, return -ESOCKTNOSUPPORT; } - return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM; + sk = unix_create1(net, sock, kern, sock->type); + if (IS_ERR(sk)) + return PTR_ERR(sk); + + return 0; } static int unix_release(struct socket *sock) @@ -1314,12 +1348,15 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, we will have to recheck all again in any case. */ - err = -ENOMEM; - /* create new sock for complete connection */ newsk = unix_create1(sock_net(sk), NULL, 0, sock->type); - if (newsk == NULL) + if (IS_ERR(newsk)) { + err = PTR_ERR(newsk); + newsk = NULL; goto out; + } + + err = -ENOMEM; /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 6c0a4a67ad2e..6f30231bdb88 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -873,12 +873,21 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long return -EINVAL; } } + case SNDRV_RAWMIDI_IOCTL_USER_PVERSION: + if (get_user(rfile->user_pversion, (unsigned int __user *)arg)) + return -EFAULT; + return 0; + case SNDRV_RAWMIDI_IOCTL_PARAMS: { struct snd_rawmidi_params params; if (copy_from_user(¶ms, argp, sizeof(struct snd_rawmidi_params))) return -EFAULT; + if (rfile->user_pversion < SNDRV_PROTOCOL_VERSION(2, 0, 2)) { + params.mode = 0; + memset(params.reserved, 0, sizeof(params.reserved)); + } switch (params.stream) { case SNDRV_RAWMIDI_STREAM_OUTPUT: if (rfile->output == NULL) diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c index ed40d0f7432c..773db4bf0876 100644 --- a/sound/drivers/pcsp/pcsp_lib.c +++ b/sound/drivers/pcsp/pcsp_lib.c @@ -143,7 +143,7 @@ enum hrtimer_restart pcsp_do_timer(struct hrtimer *handle) if (pointer_update) pcsp_pointer_update(chip); - hrtimer_forward(handle, hrtimer_get_expires(handle), ns_to_ktime(ns)); + hrtimer_forward_now(handle, ns_to_ktime(ns)); return HRTIMER_RESTART; } diff --git a/sound/firewire/motu/amdtp-motu.c b/sound/firewire/motu/amdtp-motu.c index 5388b85fb60e..a18c2c033e83 100644 --- a/sound/firewire/motu/amdtp-motu.c +++ b/sound/firewire/motu/amdtp-motu.c @@ -276,10 +276,11 @@ static void __maybe_unused copy_message(u64 *frames, __be32 *buffer, /* This is just for v2/v3 protocol. */ for (i = 0; i < data_blocks; ++i) { - *frames = (be32_to_cpu(buffer[1]) << 16) | - (be32_to_cpu(buffer[2]) >> 16); + *frames = be32_to_cpu(buffer[1]); + *frames <<= 16; + *frames |= be32_to_cpu(buffer[2]) >> 16; + ++frames; buffer += data_block_quadlets; - frames++; } } diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index cb5b5e3a481b..daf731364695 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -184,13 +184,16 @@ static int detect_quirks(struct snd_oxfw *oxfw, const struct ieee1394_device_id model = val; } - /* - * Mackie Onyx Satellite with base station has a quirk to report a wrong - * value in 'dbs' field of CIP header against its format information. - */ - if (vendor == VENDOR_LOUD && model == MODEL_SATELLITE) + if (vendor == VENDOR_LOUD) { + // Mackie Onyx Satellite with base station has a quirk to report a wrong + // value in 'dbs' field of CIP header against its format information. oxfw->quirks |= SND_OXFW_QUIRK_WRONG_DBS; + // OXFW971-based models may transfer events by blocking method. + if (!(oxfw->quirks & SND_OXFW_QUIRK_JUMBO_PAYLOAD)) + oxfw->quirks |= SND_OXFW_QUIRK_BLOCKING_TRANSMISSION; + } + return 0; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 3aa432d814a2..47777439961c 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -883,10 +883,11 @@ static unsigned int azx_get_pos_skl(struct azx *chip, struct azx_dev *azx_dev) return azx_get_pos_posbuf(chip, azx_dev); } -static void azx_shutdown_chip(struct azx *chip) +static void __azx_shutdown_chip(struct azx *chip, bool skip_link_reset) { azx_stop_chip(chip); - azx_enter_link_reset(chip); + if (!skip_link_reset) + azx_enter_link_reset(chip); azx_clear_irq_pending(chip); display_power(chip, false); } @@ -895,6 +896,11 @@ static void azx_shutdown_chip(struct azx *chip) static DEFINE_MUTEX(card_list_lock); static LIST_HEAD(card_list); +static void azx_shutdown_chip(struct azx *chip) +{ + __azx_shutdown_chip(chip, false); +} + static void azx_add_card_list(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); @@ -2357,7 +2363,7 @@ static void azx_shutdown(struct pci_dev *pci) return; chip = card->private_data; if (chip && chip->running) - azx_shutdown_chip(chip); + __azx_shutdown_chip(chip, true); } /* PCI IDs */ diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 3c7ef55d016e..31ff11ab868e 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -1207,6 +1207,9 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac snd_hda_jack_add_kctl(codec, DOLPHIN_LO_PIN_NID, "Line Out", true, SND_JACK_HEADPHONE, NULL); + snd_hda_jack_add_kctl(codec, DOLPHIN_AMIC_PIN_NID, "Microphone", true, + SND_JACK_MICROPHONE, NULL); + cs8409_fix_caps(codec, DOLPHIN_HP_PIN_NID); cs8409_fix_caps(codec, DOLPHIN_LO_PIN_NID); cs8409_fix_caps(codec, DOLPHIN_AMIC_PIN_NID); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8b7a389b6aed..4407f7da57c4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6429,6 +6429,20 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec, hda_fixup_thinkpad_acpi(codec, fix, action); } +/* Fixup for Lenovo Legion 15IMHg05 speaker output on headset removal. */ +static void alc287_fixup_legion_15imhg05_speakers(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + spec->gen.suppress_auto_mute = 1; + break; + } +} + /* for alc295_fixup_hp_top_speakers */ #include "hp_x360_helper.c" @@ -6646,6 +6660,10 @@ enum { ALC623_FIXUP_LENOVO_THINKSTATION_P340, ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, ALC236_FIXUP_HP_LIMIT_INT_MIC_BOOST, + ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS, + ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, + ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, + ALC287_FIXUP_13S_GEN2_SPEAKERS }; static const struct hda_fixup alc269_fixups[] = { @@ -8236,6 +8254,113 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, }, + [ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS] = { + .type = HDA_FIXUP_VERBS, + //.v.verbs = legion_15imhg05_coefs, + .v.verbs = (const struct hda_verb[]) { + // set left speaker Legion 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x41 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x1a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + // set right speaker Legion 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x42 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + {} + }, + .chained = true, + .chain_id = ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, + }, + [ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_legion_15imhg05_speakers, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE, + }, + [ALC287_FIXUP_YOGA7_14ITL_SPEAKERS] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + // set left speaker Yoga 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x41 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x1a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + // set right speaker Yoga 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x46 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE, + }, + [ALC287_FIXUP_13S_GEN2_SPEAKERS] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x41 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x42 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8630,6 +8755,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), + SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), diff --git a/sound/pci/pcxhr/pcxhr_core.c b/sound/pci/pcxhr/pcxhr_core.c index 87d24224c042..23f253effb4f 100644 --- a/sound/pci/pcxhr/pcxhr_core.c +++ b/sound/pci/pcxhr/pcxhr_core.c @@ -52,7 +52,7 @@ #define PCXHR_DSP 2 #if (PCXHR_DSP_OFFSET_MAX > PCXHR_PLX_OFFSET_MIN) -#undef PCXHR_REG_TO_PORT(x) +#error PCXHR_REG_TO_PORT(x) #else #define PCXHR_REG_TO_PORT(x) ((x)>PCXHR_DSP_OFFSET_MAX ? PCXHR_PLX : PCXHR_DSP) #endif diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index a961f837cd09..bda66b30e063 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -1073,6 +1073,16 @@ static int fsl_esai_probe(struct platform_device *pdev) if (ret < 0) goto err_pm_get_sync; + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = imx_pcm_dma_init(pdev, IMX_ESAI_DMABUF_SIZE); + if (ret) { + dev_err(&pdev->dev, "failed to init imx pcm dma: %d\n", ret); + goto err_pm_get_sync; + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component, &fsl_esai_dai, 1); if (ret) { @@ -1082,12 +1092,6 @@ static int fsl_esai_probe(struct platform_device *pdev) INIT_WORK(&esai_priv->work, fsl_esai_hw_reset); - ret = imx_pcm_dma_init(pdev, IMX_ESAI_DMABUF_SIZE); - if (ret) { - dev_err(&pdev->dev, "failed to init imx pcm dma: %d\n", ret); - goto err_pm_get_sync; - } - return ret; err_pm_get_sync: diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 8c0c75ce9490..9f90989ac59a 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -737,18 +737,23 @@ static int fsl_micfil_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); regcache_cache_only(micfil->regmap, true); + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); + if (ret) { + dev_err(&pdev->dev, "failed to pcm register\n"); + return ret; + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_micfil_component, &fsl_micfil_dai, 1); if (ret) { dev_err(&pdev->dev, "failed to register component %s\n", fsl_micfil_component.name); - return ret; } - ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); - if (ret) - dev_err(&pdev->dev, "failed to pcm register\n"); - return ret; } diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 223fcd15bfcc..38f6362099d5 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -1152,11 +1152,10 @@ static int fsl_sai_probe(struct platform_device *pdev) if (ret < 0) goto err_pm_get_sync; - ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, - &sai->cpu_dai_drv, 1); - if (ret) - goto err_pm_get_sync; - + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ if (sai->soc_data->use_imx_pcm) { ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE); if (ret) @@ -1167,6 +1166,11 @@ static int fsl_sai_probe(struct platform_device *pdev) goto err_pm_get_sync; } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, + &sai->cpu_dai_drv, 1); + if (ret) + goto err_pm_get_sync; + return ret; err_pm_get_sync: diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c index 8ffb1a6048d6..1c53719bb61e 100644 --- a/sound/soc/fsl/fsl_spdif.c +++ b/sound/soc/fsl/fsl_spdif.c @@ -1434,6 +1434,16 @@ static int fsl_spdif_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); regcache_cache_only(spdif_priv->regmap, true); + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = imx_pcm_dma_init(pdev, IMX_SPDIF_DMABUF_SIZE); + if (ret) { + dev_err_probe(&pdev->dev, ret, "imx_pcm_dma_init failed\n"); + goto err_pm_disable; + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_spdif_component, &spdif_priv->cpu_dai_drv, 1); if (ret) { @@ -1441,12 +1451,6 @@ static int fsl_spdif_probe(struct platform_device *pdev) goto err_pm_disable; } - ret = imx_pcm_dma_init(pdev, IMX_SPDIF_DMABUF_SIZE); - if (ret) { - dev_err_probe(&pdev->dev, ret, "imx_pcm_dma_init failed\n"); - goto err_pm_disable; - } - return ret; err_pm_disable: diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index 31c5ee641fe7..7ba2fd15132d 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -1215,18 +1215,23 @@ static int fsl_xcvr_probe(struct platform_device *pdev) pm_runtime_enable(dev); regcache_cache_only(xcvr->regmap, true); + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = devm_snd_dmaengine_pcm_register(dev, NULL, 0); + if (ret) { + dev_err(dev, "failed to pcm register\n"); + return ret; + } + ret = devm_snd_soc_register_component(dev, &fsl_xcvr_comp, &fsl_xcvr_dai, 1); if (ret) { dev_err(dev, "failed to register component %s\n", fsl_xcvr_comp.name); - return ret; } - ret = devm_snd_dmaengine_pcm_register(dev, NULL, 0); - if (ret) - dev_err(dev, "failed to pcm register\n"); - return ret; } diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 6602eda89e8e..6b06248a9327 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -929,6 +929,11 @@ static int create_sdw_dailink(struct snd_soc_card *card, cpus + *cpu_id, cpu_dai_num, codecs, codec_num, NULL, &sdw_ops); + /* + * SoundWire DAILINKs use 'stream' functions and Bank Switch operations + * based on wait_for_completion(), tag them as 'nonatomic'. + */ + dai_links[*be_index].nonatomic = true; ret = set_codec_init_func(card, link, dai_links + (*be_index)++, playback, group_id); diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig index 5a2f4667d50b..81ad2dcee9eb 100644 --- a/sound/soc/mediatek/Kconfig +++ b/sound/soc/mediatek/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config SND_SOC_MEDIATEK tristate + select REGMAP_MMIO config SND_SOC_MT2701 tristate "ASoC support for Mediatek MT2701 chip" @@ -188,7 +189,9 @@ config SND_SOC_MT8192_MT6359_RT1015_RT5682 config SND_SOC_MT8195 tristate "ASoC support for Mediatek MT8195 chip" depends on ARCH_MEDIATEK || COMPILE_TEST + depends on COMMON_CLK select SND_SOC_MEDIATEK + select MFD_SYSCON if SND_SOC_MT6359 help This adds ASoC platform driver support for Mediatek MT8195 chip that can be used with other codecs. diff --git a/sound/soc/mediatek/common/mtk-afe-fe-dai.c b/sound/soc/mediatek/common/mtk-afe-fe-dai.c index baaa5881b1d4..e95c7c018e7d 100644 --- a/sound/soc/mediatek/common/mtk-afe-fe-dai.c +++ b/sound/soc/mediatek/common/mtk-afe-fe-dai.c @@ -334,9 +334,11 @@ int mtk_afe_suspend(struct snd_soc_component *component) devm_kcalloc(dev, afe->reg_back_up_list_num, sizeof(unsigned int), GFP_KERNEL); - for (i = 0; i < afe->reg_back_up_list_num; i++) - regmap_read(regmap, afe->reg_back_up_list[i], - &afe->reg_back_up[i]); + if (afe->reg_back_up) { + for (i = 0; i < afe->reg_back_up_list_num; i++) + regmap_read(regmap, afe->reg_back_up_list[i], + &afe->reg_back_up[i]); + } afe->suspended = true; afe->runtime_suspend(dev); @@ -356,12 +358,13 @@ int mtk_afe_resume(struct snd_soc_component *component) afe->runtime_resume(dev); - if (!afe->reg_back_up) + if (!afe->reg_back_up) { dev_dbg(dev, "%s no reg_backup\n", __func__); - - for (i = 0; i < afe->reg_back_up_list_num; i++) - mtk_regmap_write(regmap, afe->reg_back_up_list[i], - afe->reg_back_up[i]); + } else { + for (i = 0; i < afe->reg_back_up_list_num; i++) + mtk_regmap_write(regmap, afe->reg_back_up_list[i], + afe->reg_back_up[i]); + } afe->suspended = false; return 0; diff --git a/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c b/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c index c97ace7387b4..de09f67c0450 100644 --- a/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c +++ b/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c @@ -424,8 +424,8 @@ static int mt8195_hdmi_codec_init(struct snd_soc_pcm_runtime *rtd) return snd_soc_component_set_jack(cmpnt_codec, &priv->hdmi_jack, NULL); } -static int mt8195_hdmitx_dptx_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, - struct snd_pcm_hw_params *params) +static int mt8195_dptx_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, + struct snd_pcm_hw_params *params) { /* fix BE i2s format to 32bit, clean param mask first */ @@ -902,7 +902,7 @@ static struct snd_soc_dai_link mt8195_mt6359_rt1019_rt5682_dai_links[] = { .no_pcm = 1, .dpcm_playback = 1, .ops = &mt8195_dptx_ops, - .be_hw_params_fixup = mt8195_hdmitx_dptx_hw_params_fixup, + .be_hw_params_fixup = mt8195_dptx_hw_params_fixup, SND_SOC_DAILINK_REG(DPTX_BE), }, [DAI_LINK_ETDM1_IN_BE] = { @@ -953,7 +953,6 @@ static struct snd_soc_dai_link mt8195_mt6359_rt1019_rt5682_dai_links[] = { SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBS_CFS, .dpcm_playback = 1, - .be_hw_params_fixup = mt8195_hdmitx_dptx_hw_params_fixup, SND_SOC_DAILINK_REG(ETDM3_OUT_BE), }, [DAI_LINK_PCM1_BE] = { diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 3e4dd4a86363..59d0d7b2b55c 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -371,7 +371,6 @@ int snd_sof_device_remove(struct device *dev) dev_warn(dev, "error: %d failed to prepare DSP for device removal", ret); - snd_sof_fw_unload(sdev); snd_sof_ipc_free(sdev); snd_sof_free_debug(sdev); snd_sof_free_trace(sdev); @@ -394,8 +393,7 @@ int snd_sof_device_remove(struct device *dev) snd_sof_remove(sdev); /* release firmware */ - release_firmware(pdata->fw); - pdata->fw = NULL; + snd_sof_fw_unload(sdev); return 0; } diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c index 12fedf0984bd..7e9723a10d02 100644 --- a/sound/soc/sof/imx/imx8.c +++ b/sound/soc/sof/imx/imx8.c @@ -365,7 +365,14 @@ static int imx8_remove(struct snd_sof_dev *sdev) /* on i.MX8 there is 1 to 1 match between type and BAR idx */ static int imx8_get_bar_index(struct snd_sof_dev *sdev, u32 type) { - return type; + /* Only IRAM and SRAM bars are valid */ + switch (type) { + case SOF_FW_BLK_TYPE_IRAM: + case SOF_FW_BLK_TYPE_SRAM: + return type; + default: + return -EINVAL; + } } static void imx8_ipc_msg_data(struct snd_sof_dev *sdev, diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c index cb822d953767..892e1482f97f 100644 --- a/sound/soc/sof/imx/imx8m.c +++ b/sound/soc/sof/imx/imx8m.c @@ -228,7 +228,14 @@ static int imx8m_remove(struct snd_sof_dev *sdev) /* on i.MX8 there is 1 to 1 match between type and BAR idx */ static int imx8m_get_bar_index(struct snd_sof_dev *sdev, u32 type) { - return type; + /* Only IRAM and SRAM bars are valid */ + switch (type) { + case SOF_FW_BLK_TYPE_IRAM: + case SOF_FW_BLK_TYPE_SRAM: + return type; + default: + return -EINVAL; + } } static void imx8m_ipc_msg_data(struct snd_sof_dev *sdev, diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index 2b38a77cd594..bb79c77775b3 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -729,10 +729,10 @@ int snd_sof_load_firmware_raw(struct snd_sof_dev *sdev) ret = request_firmware(&plat_data->fw, fw_filename, sdev->dev); if (ret < 0) { - dev_err(sdev->dev, "error: request firmware %s failed err: %d\n", - fw_filename, ret); dev_err(sdev->dev, - "you may need to download the firmware from https://github.com/thesofproject/sof-bin/\n"); + "error: sof firmware file is missing, you might need to\n"); + dev_err(sdev->dev, + " download it from https://github.com/thesofproject/sof-bin/\n"); goto err; } else { dev_dbg(sdev->dev, "request_firmware %s successful\n", @@ -880,5 +880,7 @@ EXPORT_SYMBOL(snd_sof_run_firmware); void snd_sof_fw_unload(struct snd_sof_dev *sdev) { /* TODO: support module unloading at runtime */ + release_firmware(sdev->pdata->fw); + sdev->pdata->fw = NULL; } EXPORT_SYMBOL(snd_sof_fw_unload); diff --git a/sound/soc/sof/trace.c b/sound/soc/sof/trace.c index f72a6e83e6af..58f6ca5cf491 100644 --- a/sound/soc/sof/trace.c +++ b/sound/soc/sof/trace.c @@ -530,7 +530,6 @@ void snd_sof_trace_notify_for_error(struct snd_sof_dev *sdev) return; if (sdev->dtrace_is_enabled) { - dev_err(sdev->dev, "error: waking up any trace sleepers\n"); sdev->dtrace_error = true; wake_up(&sdev->trace_sleep); } diff --git a/sound/soc/sof/xtensa/core.c b/sound/soc/sof/xtensa/core.c index bbb9a2282ed9..f6e3411b33cf 100644 --- a/sound/soc/sof/xtensa/core.c +++ b/sound/soc/sof/xtensa/core.c @@ -122,9 +122,9 @@ static void xtensa_stack(struct snd_sof_dev *sdev, void *oops, u32 *stack, * 0x0049fbb0: 8000f2d0 0049fc00 6f6c6c61 00632e63 */ for (i = 0; i < stack_words; i += 4) { - hex_dump_to_buffer(stack + i * 4, 16, 16, 4, + hex_dump_to_buffer(stack + i, 16, 16, 4, buf, sizeof(buf), false); - dev_err(sdev->dev, "0x%08x: %s\n", stack_ptr + i, buf); + dev_err(sdev->dev, "0x%08x: %s\n", stack_ptr + i * 4, buf); } } diff --git a/sound/usb/card.c b/sound/usb/card.c index fd570a42f043..1764b9302d46 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -1054,7 +1054,7 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message) return 0; } -static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume) +static int usb_audio_resume(struct usb_interface *intf) { struct snd_usb_audio *chip = usb_get_intfdata(intf); struct snd_usb_stream *as; @@ -1080,7 +1080,7 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume) * we just notify and restart the mixers */ list_for_each_entry(mixer, &chip->mixer_list, list) { - err = snd_usb_mixer_resume(mixer, reset_resume); + err = snd_usb_mixer_resume(mixer); if (err < 0) goto err_out; } @@ -1100,20 +1100,10 @@ err_out: atomic_dec(&chip->active); /* allow autopm after this point */ return err; } - -static int usb_audio_resume(struct usb_interface *intf) -{ - return __usb_audio_resume(intf, false); -} - -static int usb_audio_reset_resume(struct usb_interface *intf) -{ - return __usb_audio_resume(intf, true); -} #else #define usb_audio_suspend NULL #define usb_audio_resume NULL -#define usb_audio_reset_resume NULL +#define usb_audio_resume NULL #endif /* CONFIG_PM */ static const struct usb_device_id usb_audio_ids [] = { @@ -1135,7 +1125,7 @@ static struct usb_driver usb_audio_driver = { .disconnect = usb_audio_disconnect, .suspend = usb_audio_suspend, .resume = usb_audio_resume, - .reset_resume = usb_audio_reset_resume, + .reset_resume = usb_audio_resume, .id_table = usb_audio_ids, .supports_autosuspend = 1, }; diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 43bc59575a6e..a2ce535df14b 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -3653,33 +3653,16 @@ static int restore_mixer_value(struct usb_mixer_elem_list *list) return 0; } -static int default_mixer_reset_resume(struct usb_mixer_elem_list *list) -{ - int err; - - if (list->resume) { - err = list->resume(list); - if (err < 0) - return err; - } - return restore_mixer_value(list); -} - -int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume) +int snd_usb_mixer_resume(struct usb_mixer_interface *mixer) { struct usb_mixer_elem_list *list; - usb_mixer_elem_resume_func_t f; int id, err; /* restore cached mixer values */ for (id = 0; id < MAX_ID_ELEMS; id++) { for_each_mixer_elem(list, mixer, id) { - if (reset_resume) - f = list->reset_resume; - else - f = list->resume; - if (f) { - err = f(list); + if (list->resume) { + err = list->resume(list); if (err < 0) return err; } @@ -3700,7 +3683,6 @@ void snd_usb_mixer_elem_init_std(struct usb_mixer_elem_list *list, list->id = unitid; list->dump = snd_usb_mixer_dump_cval; #ifdef CONFIG_PM - list->resume = NULL; - list->reset_resume = default_mixer_reset_resume; + list->resume = restore_mixer_value; #endif } diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index 876bbc9a71ad..98ea24d91d80 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -70,7 +70,6 @@ struct usb_mixer_elem_list { bool is_std_info; usb_mixer_elem_dump_func_t dump; usb_mixer_elem_resume_func_t resume; - usb_mixer_elem_resume_func_t reset_resume; }; /* iterate over mixer element list of the given unit id */ @@ -121,7 +120,7 @@ int snd_usb_mixer_vol_tlv(struct snd_kcontrol *kcontrol, int op_flag, #ifdef CONFIG_PM int snd_usb_mixer_suspend(struct usb_mixer_interface *mixer); -int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume); +int snd_usb_mixer_resume(struct usb_mixer_interface *mixer); #endif int snd_usb_set_cur_mix_value(struct usb_mixer_elem_info *cval, int channel, diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index a66ce0375fd9..46082dc57be0 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -151,7 +151,7 @@ static int add_single_ctl_with_resume(struct usb_mixer_interface *mixer, *listp = list; list->mixer = mixer; list->id = id; - list->reset_resume = resume; + list->resume = resume; kctl = snd_ctl_new1(knew, list); if (!kctl) { kfree(list); diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 10911a8cad0f..2df880cefdae 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -1649,11 +1649,17 @@ static bool btf_is_non_static(const struct btf_type *t) static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name, int *out_btf_sec_id, int *out_btf_id) { - int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0; + int i, j, n, m, btf_id = 0; const struct btf_type *t; const struct btf_var_secinfo *vi; const char *name; + if (!obj->btf) { + pr_warn("failed to find BTF info for object '%s'\n", obj->filename); + return -EINVAL; + } + + n = btf__get_nr_types(obj->btf); for (i = 1; i <= n; i++) { t = btf__type_by_id(obj->btf, i); diff --git a/tools/objtool/special.c b/tools/objtool/special.c index bc925cf19e2d..f1428e32a505 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -58,6 +58,24 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { } +static bool reloc2sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) +{ + switch (reloc->sym->type) { + case STT_FUNC: + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; + return true; + + case STT_SECTION: + *sec = reloc->sym->sec; + *off = reloc->addend; + return true; + + default: + return false; + } +} + static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) @@ -91,15 +109,14 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_reloc->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section reloc symbol %s", - sec, offset + entry->orig, orig_reloc->sym->name); + if (!reloc2sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off)) { + WARN_FUNC("don't know how to handle reloc symbol type %d: %s", + sec, offset + entry->orig, + orig_reloc->sym->type, + orig_reloc->sym->name); return -1; } - alt->orig_sec = orig_reloc->sym->sec; - alt->orig_off = orig_reloc->addend; - if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); if (!new_reloc) { @@ -116,8 +133,13 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, if (arch_is_retpoline(new_reloc->sym)) return 1; - alt->new_sec = new_reloc->sym->sec; - alt->new_off = (unsigned int)new_reloc->addend; + if (!reloc2sec_off(new_reloc, &alt->new_sec, &alt->new_off)) { + WARN_FUNC("don't know how to handle reloc symbol type %d: %s", + sec, offset + entry->new, + new_reloc->sym->type, + new_reloc->sym->name); + return -1; + } /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt index 52152d156ad9..79936355d819 100644 --- a/tools/perf/Documentation/jitdump-specification.txt +++ b/tools/perf/Documentation/jitdump-specification.txt @@ -164,7 +164,7 @@ const char unwinding_data[n]: an array of unwinding data, consisting of the EH F The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html -The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html +The EH Frame follows the LSB specification as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information. diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index de6beedb7283..3b6a2c84ea02 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -261,7 +261,7 @@ COALESCE User can specify how to sort offsets for cacheline. Following fields are available and governs the final -output fields set for caheline offsets output: +output fields set for cacheline offsets output: tid - coalesced by process TIDs pid - coalesced by process PIDs diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 184ba62420f0..db465fa7ee91 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -883,7 +883,7 @@ and "r" can be combined to get calls and returns. "Transactions" events correspond to the start or end of transactions. The 'flags' field can be used in perf script to determine whether the event is a -tranasaction start, commit or abort. +transaction start, commit or abort. Note that "instructions", "branches" and "transactions" events depend on code flow packets which can be disabled by using the config term "branch=0". Refer diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 74d774592196..1b4d452923d7 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -44,7 +44,7 @@ COMMON OPTIONS -f:: --force:: - Don't complan, do it. + Don't complain, do it. REPORT OPTIONS -------------- diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 5a1f68122f50..fa4f39d305a7 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -54,7 +54,7 @@ all sched_wakeup events in the system: Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. -The format file for the sched_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 0250dc61cf98..cf4b7f4b625a 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -448,7 +448,7 @@ all sched_wakeup events in the system: Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. -The format file for the sched_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 4c9310be6acc..7e6fb7cbc0f4 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -385,7 +385,7 @@ Aggregate counts per physical processor for system-wide mode measurements. Print metrics or metricgroups specified in a comma separated list. For a group all metrics from the group are added. The events from the metrics are automatically measured. -See perf list output for the possble metrics and metricgroups. +See perf list output for the possible metrics and metricgroups. -A:: --no-aggr:: diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt index c6302df4cf29..a15b93fdcf50 100644 --- a/tools/perf/Documentation/topdown.txt +++ b/tools/perf/Documentation/topdown.txt @@ -2,7 +2,7 @@ Using TopDown metrics in user space ----------------------------------- Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown -methology to break down CPU pipeline execution into 4 bottlenecks: +methodology to break down CPU pipeline execution into 4 bottlenecks: frontend bound, backend bound, bad speculation, retiring. For more details on Topdown see [1][5] diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index c7c7ec0812d5..5fc6a2a3dbc5 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -8,10 +8,10 @@ #include #include -#include "../../util/auxtrace.h" -#include "../../util/debug.h" -#include "../../util/evlist.h" -#include "../../util/pmu.h" +#include "../../../util/auxtrace.h" +#include "../../../util/debug.h" +#include "../../../util/evlist.h" +#include "../../../util/pmu.h" #include "cs-etm.h" #include "arm-spe.h" diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 515aae470e23..293a23bf8be3 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -16,19 +16,19 @@ #include #include "cs-etm.h" -#include "../../util/debug.h" -#include "../../util/record.h" -#include "../../util/auxtrace.h" -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evlist.h" -#include "../../util/evsel.h" -#include "../../util/perf_api_probe.h" -#include "../../util/evsel_config.h" -#include "../../util/pmu.h" -#include "../../util/cs-etm.h" +#include "../../../util/debug.h" +#include "../../../util/record.h" +#include "../../../util/auxtrace.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/perf_api_probe.h" +#include "../../../util/evsel_config.h" +#include "../../../util/pmu.h" +#include "../../../util/cs-etm.h" #include // page_size -#include "../../util/session.h" +#include "../../../util/session.h" #include #include diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c index 2864e2e3776d..2833e101a7c6 100644 --- a/tools/perf/arch/arm/util/perf_regs.c +++ b/tools/perf/arch/arm/util/perf_regs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../util/perf_regs.h" +#include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index bbc297a7e2e3..b8b23b9dc598 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,7 +10,7 @@ #include #include "arm-spe.h" -#include "../../util/pmu.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index 36ba4c69c3c5..b7692cb0c733 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/event.h" +#include "../../../util/unwind-libdw.h" +#include "../../../util/perf_regs.h" +#include "../../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index 3a550225dfaf..438906bf0014 100644 --- a/tools/perf/arch/arm/util/unwind-libunwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -3,8 +3,8 @@ #include #include #include "perf_regs.h" -#include "../../util/unwind.h" -#include "../../util/debug.h" +#include "../../../util/unwind.h" +#include "../../../util/debug.h" int libunwind__arch_reg_id(int regnum) { diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index eeafe97b8105..792cd75ade33 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -432,7 +432,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, u8 die = ((struct iio_root_port *)evsel->priv)->die; struct perf_counts_values *count = perf_counts(evsel->counts, die, 0); - if (count->run && count->ena) { + if (count && count->run && count->ena) { if (evsel->prev_raw_counts && !out->force_header) { struct perf_counts_values *prev_count = perf_counts(evsel->prev_raw_counts, die, 0); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f6e87b7be5fa..f0ecfda34ece 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2408,6 +2408,8 @@ int cmd_stat(int argc, const char **argv) goto out; } else if (verbose) iostat_list(evsel_list, &stat_config); + if (iostat_mode == IOSTAT_RUN && !target__has_cpu(&target)) + target.system_wide = true; } if (add_default_attributes()) diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json index 84a0cedf1fd9..f1f2965f6775 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json @@ -1046,7 +1046,7 @@ { "EventCode": "0x4e010", "EventName": "PM_GCT_NOSLOT_IC_L3MISS", - "BriefDescription": "Gct empty for this thread due to icach l3 miss", + "BriefDescription": "Gct empty for this thread due to icache l3 miss", "PublicDescription": "" }, { diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9866cddebf23..9b4a765e4b73 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -229,8 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, struct thread *thread, struct state *state) { struct addr_location al; - unsigned char buf1[BUFSZ]; - unsigned char buf2[BUFSZ]; + unsigned char buf1[BUFSZ] = {0}; + unsigned char buf2[BUFSZ] = {0}; size_t ret_len; u64 objdump_addr; const char *objdump_name; diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index a288035eb362..c756284b3b13 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -20,6 +20,23 @@ /* For bsearch. We try to unwind functions in shared object. */ #include +/* + * The test will assert frames are on the stack but tail call optimizations lose + * the frame of the caller. Clang can disable this optimization on a called + * function but GCC currently (11/2020) lacks this attribute. The barrier is + * used to inhibit tail calls in these cases. + */ +#ifdef __has_attribute +#if __has_attribute(disable_tail_calls) +#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls)) +#define NO_TAIL_CALL_BARRIER +#endif +#endif +#ifndef NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory"); +#endif + static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -91,7 +108,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -noinline int test_dwarf_unwind__thread(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -122,7 +139,7 @@ noinline int test_dwarf_unwind__thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -noinline int test_dwarf_unwind__compare(void *p1, void *p2) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -141,7 +158,7 @@ noinline int test_dwarf_unwind__compare(void *p1, void *p2) return p1 - p2; } -noinline int test_dwarf_unwind__krava_3(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -160,14 +177,22 @@ noinline int test_dwarf_unwind__krava_3(struct thread *thread) return global_unwind_retval; } -noinline int test_dwarf_unwind__krava_2(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread) { - return test_dwarf_unwind__krava_3(thread); + int ret; + + ret = test_dwarf_unwind__krava_3(thread); + NO_TAIL_CALL_BARRIER; + return ret; } -noinline int test_dwarf_unwind__krava_1(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread) { - return test_dwarf_unwind__krava_2(thread); + int ret; + + ret = test_dwarf_unwind__krava_2(thread); + NO_TAIL_CALL_BARRIER; + return ret; } int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 4fb5e90d7a57..60ce5908c664 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -801,7 +801,7 @@ int perf_config_set(struct perf_config_set *set, section->name, item->name); ret = fn(key, value, data); if (ret < 0) { - pr_err("Error: wrong config key-value pair %s=%s\n", + pr_err("Error in the given config file: wrong config key-value pair %s=%s\n", key, value); /* * Can't be just a 'break', as perf_config_set__for_each_entry() diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 866531c08e4f..799b88152e9e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -375,7 +375,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ $$(INCLUDE_DIR)/vmlinux.h \ - $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT) + $(wildcard $(BPFDIR)/bpf_*.h) \ + | $(TRUNNER_OUTPUT) $$(BPFOBJ) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS)) diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index 59ea56945e6c..b497bb85b667 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -112,6 +112,14 @@ setup() ip netns add "${NS2}" ip netns add "${NS3}" + # rp_filter gets confused by what these tests are doing, so disable it + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip link add veth1 type veth peer name veth2 ip link add veth3 type veth peer name veth4 ip link add veth5 type veth peer name veth6 @@ -236,11 +244,6 @@ setup() ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF} ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF} - # rp_filter gets confused by what these tests are doing, so disable it - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 - TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX) sleep 1 # reduce flakiness diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 618bf9bc7f3f..b8dbabe24ac2 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -24,6 +24,7 @@ /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test +/x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/userspace_msr_exit_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 9ac325cfc94a..d1774f461393 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -56,6 +56,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 71e277c7c3f3..5d95113c7b7c 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -371,9 +371,7 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); exit(0); } @@ -381,7 +379,7 @@ static void help(char *name) int main(int argc, char *argv[]) { struct test_params params = { - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, .vcpus = 1, }; diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index e79c1b64977f..1510b21e6306 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -179,7 +179,7 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } - if (!pollfd[0].revents & POLLIN) + if (!(pollfd[0].revents & POLLIN)) continue; r = read(uffd, &msg, sizeof(msg)); @@ -416,7 +416,7 @@ static void help(char *name) { puts(""); printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" - " [-b memory] [-t type] [-v vcpus] [-o]\n", name); + " [-b memory] [-s type] [-v vcpus] [-o]\n", name); guest_modes_help(); printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); @@ -426,8 +426,7 @@ static void help(char *name) printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); - printf(" -t: The type of backing memory to use. Default: anonymous\n"); - backing_src_help(); + backing_src_help("-s"); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -439,14 +438,14 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, .partition_vcpu_memory_access = true, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -465,7 +464,7 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; - case 't': + case 's': p.src_type = parse_backing_src_type(optarg); break; case 'v': @@ -485,7 +484,7 @@ int main(int argc, char *argv[]) if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && !backing_src_is_shared(p.src_type)) { - TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s"); } for_each_guest_mode(run_test, &p); diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 479868570d59..7ffab5bd5ce5 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -118,42 +118,64 @@ static inline void disable_dirty_logging(struct kvm_vm *vm, int slots) toggle_dirty_logging(vm, slots, false); } -static void get_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_get_dirty_log(vm, slot, slot_bitmap); + kvm_vm_get_dirty_log(vm, slot, bitmaps[i]); } } -static void clear_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], + int slots, uint64_t pages_per_slot) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_clear_dirty_log(vm, slot, slot_bitmap, 0, slot_pages); + kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot); } } +static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot) +{ + unsigned long **bitmaps; + int i; + + bitmaps = malloc(slots * sizeof(bitmaps[0])); + TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array."); + + for (i = 0; i < slots; i++) { + bitmaps[i] = bitmap_zalloc(pages_per_slot); + TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap."); + } + + return bitmaps; +} + +static void free_bitmaps(unsigned long *bitmaps[], int slots) +{ + int i; + + for (i = 0; i < slots; i++) + free(bitmaps[i]); + + free(bitmaps); +} + static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; pthread_t *vcpu_threads; struct kvm_vm *vm; - unsigned long *bmap; + unsigned long **bitmaps; uint64_t guest_num_pages; uint64_t host_num_pages; + uint64_t pages_per_slot; int vcpu_id; struct timespec start; struct timespec ts_diff; @@ -171,7 +193,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); host_num_pages = vm_num_host_pages(mode, guest_num_pages); - bmap = bitmap_zalloc(host_num_pages); + pages_per_slot = host_num_pages / p->slots; + + bitmaps = alloc_bitmaps(p->slots, pages_per_slot); if (dirty_log_manual_caps) { cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; @@ -239,7 +263,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) iteration, ts_diff.tv_sec, ts_diff.tv_nsec); clock_gettime(CLOCK_MONOTONIC, &start); - get_dirty_log(vm, p->slots, bmap, host_num_pages); + get_dirty_log(vm, bitmaps, p->slots); ts_diff = timespec_elapsed(start); get_dirty_log_total = timespec_add(get_dirty_log_total, ts_diff); @@ -248,7 +272,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (dirty_log_manual_caps) { clock_gettime(CLOCK_MONOTONIC, &start); - clear_dirty_log(vm, p->slots, bmap, host_num_pages); + clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot); ts_diff = timespec_elapsed(start); clear_dirty_log_total = timespec_add(clear_dirty_log_total, ts_diff); @@ -281,7 +305,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); } - free(bmap); + free_bitmaps(bitmaps, p->slots); free(vcpu_threads); perf_test_destroy_vm(vm); } @@ -308,11 +332,9 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); + backing_src_help("-s"); printf(" -x: Split the memory region into this number of memslots.\n" - " (default: 1)"); - backing_src_help(); + " (default: 1)\n"); puts(""); exit(0); } @@ -324,7 +346,7 @@ int main(int argc, char *argv[]) .iterations = TEST_HOST_LOOP_N, .wr_fract = 1, .partition_vcpu_memory_access = true, - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .slots = 1, }; int opt; diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 451fed5ce8e7..f8fddc84c0d3 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -90,6 +90,8 @@ enum vm_mem_backing_src_type { NUM_SRC_TYPES, }; +#define DEFAULT_VM_MEM_SRC VM_MEM_SRC_ANONYMOUS + struct vm_mem_backing_src_alias { const char *name; uint32_t flag; @@ -102,7 +104,7 @@ size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); -void backing_src_help(void); +void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); long get_run_delay(void); diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 242ae8e09a65..05e65ca1c30c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -312,37 +312,37 @@ static inline void set_xmm(int n, unsigned long val) } } -typedef unsigned long v1di __attribute__ ((vector_size (8))); +#define GET_XMM(__xmm) \ +({ \ + unsigned long __val; \ + asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \ + __val; \ +}) + static inline unsigned long get_xmm(int n) { assert(n >= 0 && n <= 7); - register v1di xmm0 __asm__("%xmm0"); - register v1di xmm1 __asm__("%xmm1"); - register v1di xmm2 __asm__("%xmm2"); - register v1di xmm3 __asm__("%xmm3"); - register v1di xmm4 __asm__("%xmm4"); - register v1di xmm5 __asm__("%xmm5"); - register v1di xmm6 __asm__("%xmm6"); - register v1di xmm7 __asm__("%xmm7"); switch (n) { case 0: - return (unsigned long)xmm0; + return GET_XMM(xmm0); case 1: - return (unsigned long)xmm1; + return GET_XMM(xmm1); case 2: - return (unsigned long)xmm2; + return GET_XMM(xmm2); case 3: - return (unsigned long)xmm3; + return GET_XMM(xmm3); case 4: - return (unsigned long)xmm4; + return GET_XMM(xmm4); case 5: - return (unsigned long)xmm5; + return GET_XMM(xmm5); case 6: - return (unsigned long)xmm6; + return GET_XMM(xmm6); case 7: - return (unsigned long)xmm7; + return GET_XMM(xmm7); } + + /* never reached */ return 0; } diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 0d04a7db7f24..36407cb0ec85 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -456,10 +456,7 @@ static void help(char *name) " (default: 1G)\n"); printf(" -v: specify the number of vCPUs to run\n" " (default: 1)\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n" - " (default: anonymous)\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); } @@ -468,7 +465,7 @@ int main(int argc, char *argv[]) int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { .test_mem_size = DEFAULT_TEST_MEM_SIZE, - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, }; int opt; diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index a9107bfae402..b72429108993 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -283,13 +283,22 @@ size_t get_backing_src_pagesz(uint32_t i) } } -void backing_src_help(void) +static void print_available_backing_src_types(const char *prefix) { int i; - printf("Available backing src types:\n"); + printf("%sAvailable backing src types:\n", prefix); + for (i = 0; i < NUM_SRC_TYPES; i++) - printf("\t%s\n", vm_mem_backing_src_alias(i)->name); + printf("%s %s\n", prefix, vm_mem_backing_src_alias(i)->name); +} + +void backing_src_help(const char *flag) +{ + printf(" %s: specify the type of memory that should be used to\n" + " back the guest data region. (default: %s)\n", + flag, vm_mem_backing_src_alias(DEFAULT_VM_MEM_SRC)->name); + print_available_backing_src_types(" "); } enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) @@ -300,7 +309,7 @@ enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) if (!strcmp(type_name, vm_mem_backing_src_alias(i)->name)) return i; - backing_src_help(); + print_available_backing_src_types(""); TEST_FAIL("Unknown backing src type: %s", type_name); return -1; } diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 060538bd405a..4158da0da2bb 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -39,6 +40,7 @@ static __thread volatile struct rseq __rseq = { static pthread_t migration_thread; static cpu_set_t possible_mask; +static int min_cpu, max_cpu; static bool done; static atomic_t seq_cnt; @@ -57,20 +59,37 @@ static void sys_rseq(int flags) TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); } +static int next_cpu(int cpu) +{ + /* + * Advance to the next CPU, skipping those that weren't in the original + * affinity set. Sadly, there is no CPU_SET_FOR_EACH, and cpu_set_t's + * data storage is considered as opaque. Note, if this task is pinned + * to a small set of discontigous CPUs, e.g. 2 and 1023, this loop will + * burn a lot cycles and the test will take longer than normal to + * complete. + */ + do { + cpu++; + if (cpu > max_cpu) { + cpu = min_cpu; + TEST_ASSERT(CPU_ISSET(cpu, &possible_mask), + "Min CPU = %d must always be usable", cpu); + break; + } + } while (!CPU_ISSET(cpu, &possible_mask)); + + return cpu; +} + static void *migration_worker(void *ign) { cpu_set_t allowed_mask; - int r, i, nr_cpus, cpu; + int r, i, cpu; CPU_ZERO(&allowed_mask); - nr_cpus = CPU_COUNT(&possible_mask); - - for (i = 0; i < NR_TASK_MIGRATIONS; i++) { - cpu = i % nr_cpus; - if (!CPU_ISSET(cpu, &possible_mask)) - continue; - + for (i = 0, cpu = min_cpu; i < NR_TASK_MIGRATIONS; i++, cpu = next_cpu(cpu)) { CPU_SET(cpu, &allowed_mask); /* @@ -154,6 +173,36 @@ static void *migration_worker(void *ign) return NULL; } +static int calc_min_max_cpu(void) +{ + int i, cnt, nproc; + + if (CPU_COUNT(&possible_mask) < 2) + return -EINVAL; + + /* + * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that + * this task is affined to in order to reduce the time spent querying + * unusable CPUs, e.g. if this task is pinned to a small percentage of + * total CPUs. + */ + nproc = get_nprocs_conf(); + min_cpu = -1; + max_cpu = -1; + cnt = 0; + + for (i = 0; i < nproc; i++) { + if (!CPU_ISSET(i, &possible_mask)) + continue; + if (min_cpu == -1) + min_cpu = i; + max_cpu = i; + cnt++; + } + + return (cnt < 2) ? -EINVAL : 0; +} + int main(int argc, char *argv[]) { int r, i, snapshot; @@ -167,8 +216,8 @@ int main(int argc, char *argv[]) TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, strerror(errno)); - if (CPU_COUNT(&possible_mask) < 2) { - print_skip("Only one CPU, task migration not possible\n"); + if (calc_min_max_cpu()) { + print_skip("Only one usable CPU, task migration not possible"); exit(KSFT_SKIP); } @@ -180,6 +229,7 @@ int main(int argc, char *argv[]) * CPU affinity. */ vm = vm_create_default(VCPU_ID, 0, guest_code); + ucall_init(vm, NULL); pthread_create(&migration_thread, NULL, migration_worker, 0); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 2172d65b85e4..62f2eb9ee3d5 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -116,12 +116,12 @@ struct st_time { uint64_t st_time; }; -static int64_t smccc(uint32_t func, uint32_t arg) +static int64_t smccc(uint32_t func, uint64_t arg) { unsigned long ret; asm volatile( - "mov x0, %1\n" + "mov w0, %w1\n" "mov x1, %2\n" "hvc #0\n" "mov %0, x0\n" diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c new file mode 100644 index 000000000000..df04f56ce859 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_int_ctl_test + * + * Copyright (C) 2021, Red Hat, Inc. + * + * Nested SVM testing: test simultaneous use of V_IRQ from L1 and L0. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "apic.h" + +#define VCPU_ID 0 + +static struct kvm_vm *vm; + +bool vintr_irq_called; +bool intr_irq_called; + +#define VINTR_IRQ_NUMBER 0x20 +#define INTR_IRQ_NUMBER 0x30 + +static void vintr_irq_handler(struct ex_regs *regs) +{ + vintr_irq_called = true; +} + +static void intr_irq_handler(struct ex_regs *regs) +{ + x2apic_write_reg(APIC_EOI, 0x00); + intr_irq_called = true; +} + +static void l2_guest_code(struct svm_test_data *svm) +{ + /* This code raises interrupt INTR_IRQ_NUMBER in the L1's LAPIC, + * and since L1 didn't enable virtual interrupt masking, + * L2 should receive it and not L1. + * + * L2 also has virtual interrupt 'VINTR_IRQ_NUMBER' pending in V_IRQ + * so it should also receive it after the following 'sti'. + */ + x2apic_write_reg(APIC_ICR, + APIC_DEST_SELF | APIC_INT_ASSERT | INTR_IRQ_NUMBER); + + __asm__ __volatile__( + "sti\n" + "nop\n" + ); + + GUEST_ASSERT(vintr_irq_called); + GUEST_ASSERT(intr_irq_called); + + __asm__ __volatile__( + "vmcall\n" + ); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + x2apic_enable(); + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* No virtual interrupt masking */ + vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; + + /* No intercepts for real and virtual interrupts */ + vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + + /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ + vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); + vmcb->control.int_vector = VINTR_IRQ_NUMBER; + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t svm_gva; + + nested_svm_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); + vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); + + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *)uc.args[0]); + break; + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/netfilter/nft_nat_zones.sh b/tools/testing/selftests/netfilter/nft_nat_zones.sh new file mode 100755 index 000000000000..b9ab37380f33 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat_zones.sh @@ -0,0 +1,309 @@ +#!/bin/bash +# +# Test connection tracking zone and NAT source port reallocation support. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# Don't increase too much, 2000 clients should work +# just fine but script can then take several minutes with +# KASAN/debug builds. +maxclients=100 + +have_iperf=1 +ret=0 + +# client1---. +# veth1-. +# | +# NAT Gateway --veth0--> Server +# | | +# veth2-' | +# client2---' | +# .... | +# clientX----vethX---' + +# All clients share identical IP address. +# NAT Gateway uses policy routing and conntrack zones to isolate client +# namespaces. Each client connects to Server, each with colliding tuples: +# clientsaddr:10000 -> serveraddr:dport +# NAT Gateway is supposed to do port reallocation for each of the +# connections. + +sfx=$(mktemp -u "XXXXXXXX") +gw="ns-gw-$sfx" +cl1="ns-cl1-$sfx" +cl2="ns-cl2-$sfx" +srv="ns-srv-$sfx" + +v4gc1=$(sysctl -n net.ipv4.neigh.default.gc_thresh1 2>/dev/null) +v4gc2=$(sysctl -n net.ipv4.neigh.default.gc_thresh2 2>/dev/null) +v4gc3=$(sysctl -n net.ipv4.neigh.default.gc_thresh3 2>/dev/null) +v6gc1=$(sysctl -n net.ipv6.neigh.default.gc_thresh1 2>/dev/null) +v6gc2=$(sysctl -n net.ipv6.neigh.default.gc_thresh2 2>/dev/null) +v6gc3=$(sysctl -n net.ipv6.neigh.default.gc_thresh3 2>/dev/null) + +cleanup() +{ + ip netns del $gw + ip netns del $srv + for i in $(seq 1 $maxclients); do + ip netns del ns-cl$i-$sfx 2>/dev/null + done + + sysctl -q net.ipv4.neigh.default.gc_thresh1=$v4gc1 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh2=$v4gc2 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh3=$v4gc3 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh1=$v6gc1 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh2=$v6gc2 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh3=$v6gc3 2>/dev/null +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +conntrack -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without conntrack tool" + exit $ksft_skip +fi + +iperf3 -v >/dev/null 2>&1 +if [ $? -ne 0 ];then + have_iperf=0 +fi + +ip netns add "$gw" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi +ip -net "$gw" link set lo up + +trap cleanup EXIT + +ip netns add "$srv" +if [ $? -ne 0 ];then + echo "SKIP: Could not create server netns $srv" + exit $ksft_skip +fi + +ip link add veth0 netns "$gw" type veth peer name eth0 netns "$srv" +ip -net "$gw" link set veth0 up +ip -net "$srv" link set lo up +ip -net "$srv" link set eth0 up + +sysctl -q net.ipv6.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh3=4096 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh3=4096 2>/dev/null + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + + ip netns add "$cl" + if [ $? -ne 0 ];then + echo "SKIP: Could not create client netns $cl" + exit $ksft_skip + fi + ip link add veth$i netns "$gw" type veth peer name eth0 netns "$cl" > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip + fi +done + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + echo netns exec "$cl" ip link set lo up + echo netns exec "$cl" ip link set eth0 up + echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2 + echo netns exec "$gw" ip link set veth$i up + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.arp_ignore=2 + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.rp_filter=0 + + # clients have same IP addresses. + echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0 + echo netns exec "$cl" ip addr add dead:1::3/64 dev eth0 + echo netns exec "$cl" ip route add default via 10.1.0.2 dev eth0 + echo netns exec "$cl" ip route add default via dead:1::2 dev eth0 + + # NB: same addresses on client-facing interfaces. + echo netns exec "$gw" ip addr add 10.1.0.2/24 dev veth$i + echo netns exec "$gw" ip addr add dead:1::2/64 dev veth$i + + # gw: policy routing + echo netns exec "$gw" ip route add 10.1.0.0/24 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add dead:1::0/64 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add 10.3.0.0/24 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip route add dead:3::0/64 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip rule add fwmark $i lookup $((1000+i)) +done | ip -batch /dev/stdin + +ip -net "$gw" addr add 10.3.0.1/24 dev veth0 +ip -net "$gw" addr add dead:3::1/64 dev veth0 + +ip -net "$srv" addr add 10.3.0.99/24 dev eth0 +ip -net "$srv" addr add dead:3::99/64 dev eth0 + +ip netns exec $gw nft -f /dev/stdin< /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null + +# useful for debugging: allows to use 'ping' from clients to gateway. +ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.fwmark_reflect=1 > /dev/null + +for i in $(seq 1 $maxclients); do + cl="ns-cl$i-$sfx" + ip netns exec $cl ping -i 0.5 -q -c 3 10.3.0.99 > /dev/null 2>&1 & + if [ $? -ne 0 ]; then + echo FAIL: Ping failure from $cl 1>&2 + ret=1 + break + fi +done + +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" | grep -q "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 counter packets 3 bytes 252 }" + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth$i" 1>&2 + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" 1>&2 + break + fi +done + +ip netns exec $gw nft get element inet raw inicmp "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 }" | grep -q "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth0: { 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" + ip netns exec $gw nft get element inet raw inicmp "{ 10.3.99 . \"veth0\" . 10.3.0.1 }" 1>&2 +fi + +if [ $ret -eq 0 ]; then + echo "PASS: ping test from all $maxclients namespaces" +fi + +if [ $have_iperf -eq 0 ];then + echo "SKIP: iperf3 not installed" + if [ $ret -ne 0 ];then + exit $ret + fi + exit $ksft_skip +fi + +ip netns exec $srv iperf3 -s > /dev/null 2>&1 & +iperfpid=$! +sleep 1 + +for i in $(seq 1 $maxclients); do + if [ $ret -ne 0 ]; then + break + fi + cl="ns-cl$i-$sfx" + ip netns exec $cl iperf3 -c 10.3.0.99 --cport 10000 -n 1 > /dev/null + if [ $? -ne 0 ]; then + echo FAIL: Failure to connect for $cl 1>&2 + ip netns exec $gw conntrack -S 1>&2 + ret=1 + fi +done +if [ $ret -eq 0 ];then + echo "PASS: iperf3 connections for all $maxclients net namespaces" +fi + +kill $iperfpid +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inflows "{ 10.1.0.3 . 10000 . \"veth$i\" . 10.3.0.99 . 5201 }" > /dev/null + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: can't find expected tcp entry for veth$i" 1>&2 + break + fi +done +if [ $ret -eq 0 ];then + echo "PASS: Found client connection for all $maxclients net namespaces" +fi + +ip netns exec $gw nft get element inet raw inflows "{ 10.3.0.99 . 5201 . \"veth0\" . 10.3.0.1 . 10000 }" > /dev/null +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: cannot find return entry on veth0" 1>&2 +fi + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh new file mode 100755 index 000000000000..ac646376eb01 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -0,0 +1,156 @@ +#!/bin/bash + +# Test insertion speed for packets with identical addresses/ports +# that are all placed in distinct conntrack zones. + +sfx=$(mktemp -u "XXXXXXXX") +ns="ns-$sfx" + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +zones=20000 +have_ct_tool=0 +ret=0 + +cleanup() +{ + ip netns del $ns +} + +ip netns add $ns +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi + +trap cleanup EXIT + +conntrack -V > /dev/null 2>&1 +if [ $? -eq 0 ];then + have_ct_tool=1 +fi + +ip -net "$ns" link set lo up + +test_zones() { + local max_zones=$1 + +ip netns exec $ns sysctl -q net.netfilter.nf_conntrack_udp_timeout=3600 +ip netns exec $ns nft -f /dev/stdin</dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null + if [ $? -ne 0 ] ;then + ret=1 + break + fi + + stop=$(date +%s%3N) + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + done + + if [ $have_ct_tool -eq 1 ]; then + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries from packet path in $duration ms total" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries from packet path in $duration ms total, expected $max_zones entries" + ret=1 + fi + fi + + if [ $ret -ne 0 ];then + echo "FAIL: insert $max_zones entries from packet path" 1>&2 + fi +} + +test_conntrack_tool() { + local max_zones=$1 + + ip netns exec $ns conntrack -F >/dev/null 2>/dev/null + + local outerstart=$(date +%s%3N) + local start=$(date +%s%3N) + local stop=$start + local i=0 + while [ $i -lt $max_zones ]; do + i=$((i + 1)) + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i >/dev/null 2>&1 + if [ $? -ne 0 ];then + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i > /dev/null + echo "FAIL: conntrack -I returned an error" + ret=1 + break + fi + + if [ $((i%10000)) -eq 0 ];then + stop=$(date +%s%3N) + + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total)" + start=$stop + fi + done + + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries via ctnetlink in $duration ms" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries via ctnetlink in $duration ms, expected $max_zones entries ($duration ms)" + ret=1 + fi +} + +test_zones $zones + +if [ $have_ct_tool -eq 1 ];then + test_conntrack_tool $zones +else + echo "SKIP: Could not run ctnetlink insertion test without conntrack tool" + if [ $ret -eq 0 ];then + exit $ksft_skip + fi +fi + +exit $ret diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 439d3b4cd1a9..7851f3a1b5f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -235,9 +235,13 @@ static void ack_flush(void *_completed) { } -static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) +static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait) { - if (unlikely(!cpus)) + const struct cpumask *cpus; + + if (likely(cpumask_available(tmp))) + cpus = tmp; + else cpus = cpu_online_mask; if (cpumask_empty(cpus)) @@ -263,14 +267,34 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, continue; kvm_make_request(req, vcpu); - cpu = vcpu->cpu; if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) continue; - if (tmp != NULL && cpu != -1 && cpu != me && - kvm_request_needs_ipi(vcpu, req)) - __cpumask_set_cpu(cpu, tmp); + /* + * tmp can be "unavailable" if cpumasks are allocated off stack + * as allocation of the mask is deliberately not fatal and is + * handled by falling back to kicking all online CPUs. + */ + if (!cpumask_available(tmp)) + continue; + + /* + * Note, the vCPU could get migrated to a different pCPU at any + * point after kvm_request_needs_ipi(), which could result in + * sending an IPI to the previous pCPU. But, that's ok because + * the purpose of the IPI is to ensure the vCPU returns to + * OUTSIDE_GUEST_MODE, which is satisfied if the vCPU migrates. + * Entering READING_SHADOW_PAGE_TABLES after this point is also + * ok, as the requirement is only that KVM wait for vCPUs that + * were reading SPTEs _before_ any changes were finalized. See + * kvm_vcpu_kick() for more details on handling requests. + */ + if (kvm_request_needs_ipi(vcpu, req)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != -1 && cpu != me) + __cpumask_set_cpu(cpu, tmp); + } } called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); @@ -302,13 +326,8 @@ EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) { - /* - * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in - * kvm_make_all_cpus_request. - */ - long dirty_count = smp_load_acquire(&kvm->tlbs_dirty); - ++kvm->stat.generic.remote_tlb_flush_requests; + /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. @@ -323,7 +342,6 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) if (!kvm_arch_flush_remote_tlb(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.generic.remote_tlb_flush; - cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif @@ -528,7 +546,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, } } - if (range->flush_on_ret && (ret || kvm->tlbs_dirty)) + if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); if (locked) @@ -3134,15 +3152,19 @@ out: static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { - unsigned int old, val, shrink; + unsigned int old, val, shrink, grow_start; old = val = vcpu->halt_poll_ns; shrink = READ_ONCE(halt_poll_ns_shrink); + grow_start = READ_ONCE(halt_poll_ns_grow_start); if (shrink == 0) val = 0; else val /= shrink; + if (val < grow_start) + val = 0; + vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); } @@ -3290,16 +3312,24 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int me; - int cpu = vcpu->cpu; + int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_arch_vcpu_should_kick(), which could result in sending an + * IPI to the previous pCPU. But, that's ok because the purpose of the + * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the + * vCPU also requires it to leave IN_GUEST_MODE. + */ me = get_cpu(); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (kvm_arch_vcpu_should_kick(vcpu)) + if (kvm_arch_vcpu_should_kick(vcpu)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); + } put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick);