diff options
207 files changed, 2236 insertions, 615 deletions
diff --git a/Documentation/networking/e100.rst b/Documentation/networking/e100.rst index d4d837027925..9708f5fa76de 100644 --- a/Documentation/networking/e100.rst +++ b/Documentation/networking/e100.rst @@ -1,3 +1,4 @@ +============================================================== Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters ============================================================== @@ -86,83 +87,84 @@ Event Log Message Level: The driver uses the message level flag to log events Additional Configurations ========================= - Configuring the Driver on Different Distributions - ------------------------------------------------- +Configuring the Driver on Different Distributions +------------------------------------------------- - Configuring a network driver to load properly when the system is started is - distribution dependent. Typically, the configuration process involves adding - an alias line to /etc/modprobe.d/*.conf as well as editing other system - startup scripts and/or configuration files. Many popular Linux - distributions ship with tools to make these changes for you. To learn the - proper way to configure a network device for your system, refer to your - distribution documentation. If during this process you are asked for the - driver or module name, the name for the Linux Base Driver for the Intel - PRO/100 Family of Adapters is e100. +Configuring a network driver to load properly when the system is started +is distribution dependent. Typically, the configuration process involves +adding an alias line to /etc/modprobe.d/*.conf as well as editing other +system startup scripts and/or configuration files. Many popular Linux +distributions ship with tools to make these changes for you. To learn +the proper way to configure a network device for your system, refer to +your distribution documentation. If during this process you are asked +for the driver or module name, the name for the Linux Base Driver for +the Intel PRO/100 Family of Adapters is e100. - As an example, if you install the e100 driver for two PRO/100 adapters - (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/ +As an example, if you install the e100 driver for two PRO/100 adapters +(eth0 and eth1), add the following to a configuration file in +/etc/modprobe.d/:: alias eth0 e100 alias eth1 e100 - Viewing Link Messages - --------------------- - In order to see link messages and other Intel driver information on your - console, you must set the dmesg level up to six. This can be done by - entering the following on the command line before loading the e100 driver:: - - dmesg -n 6 +Viewing Link Messages +--------------------- - If you wish to see all messages issued by the driver, including debug - messages, set the dmesg level to eight. +In order to see link messages and other Intel driver information on your +console, you must set the dmesg level up to six. This can be done by +entering the following on the command line before loading the e100 +driver:: - NOTE: This setting is not saved across reboots. + dmesg -n 6 +If you wish to see all messages issued by the driver, including debug +messages, set the dmesg level to eight. - ethtool - ------- +NOTE: This setting is not saved across reboots. - The driver utilizes the ethtool interface for driver configuration and - diagnostics, as well as displaying statistical information. The ethtool - version 1.6 or later is required for this functionality. +ethtool +------- - The latest release of ethtool can be found from - https://www.kernel.org/pub/software/network/ethtool/ +The driver utilizes the ethtool interface for driver configuration and +diagnostics, as well as displaying statistical information. The ethtool +version 1.6 or later is required for this functionality. - Enabling Wake on LAN* (WoL) - --------------------------- - WoL is provided through the ethtool* utility. For instructions on enabling - WoL with ethtool, refer to the ethtool man page. +The latest release of ethtool can be found from +https://www.kernel.org/pub/software/network/ethtool/ - WoL will be enabled on the system during the next shut down or reboot. For - this driver version, in order to enable WoL, the e100 driver must be - loaded when shutting down or rebooting the system. +Enabling Wake on LAN* (WoL) +--------------------------- +WoL is provided through the ethtool* utility. For instructions on +enabling WoL with ethtool, refer to the ethtool man page. WoL will be +enabled on the system during the next shut down or reboot. For this +driver version, in order to enable WoL, the e100 driver must be loaded +when shutting down or rebooting the system. - NAPI - ---- +NAPI +---- - NAPI (Rx polling mode) is supported in the e100 driver. +NAPI (Rx polling mode) is supported in the e100 driver. - See https://wiki.linuxfoundation.org/networking/napi for more information - on NAPI. +See https://wiki.linuxfoundation.org/networking/napi for more +information on NAPI. - Multiple Interfaces on Same Ethernet Broadcast Network - ------------------------------------------------------ +Multiple Interfaces on Same Ethernet Broadcast Network +------------------------------------------------------ - Due to the default ARP behavior on Linux, it is not possible to have - one system on two IP networks in the same Ethernet broadcast domain - (non-partitioned switch) behave as expected. All Ethernet interfaces - will respond to IP traffic for any IP address assigned to the system. - This results in unbalanced receive traffic. +Due to the default ARP behavior on Linux, it is not possible to have one +system on two IP networks in the same Ethernet broadcast domain +(non-partitioned switch) behave as expected. All Ethernet interfaces +will respond to IP traffic for any IP address assigned to the system. +This results in unbalanced receive traffic. - If you have multiple interfaces in a server, either turn on ARP - filtering by +If you have multiple interfaces in a server, either turn on ARP +filtering by - (1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter - (this only works if your kernel's version is higher than 2.4.5), or +(1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter + (this only works if your kernel's version is higher than 2.4.5), or - (2) installing the interfaces in separate broadcast domains (either - in different switches or in a switch partitioned to VLANs). +(2) installing the interfaces in separate broadcast domains (either + in different switches or in a switch partitioned to VLANs). Support diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/e1000.rst index 616848940e63..144b87eef153 100644 --- a/Documentation/networking/e1000.rst +++ b/Documentation/networking/e1000.rst @@ -1,3 +1,4 @@ +=========================================================== Linux* Base Driver for Intel(R) Ethernet Network Connection =========================================================== @@ -354,57 +355,58 @@ previously mentioned to force the adapter to the same speed and duplex. Additional Configurations ========================= - Jumbo Frames - ------------ - Jumbo Frames support is enabled by changing the MTU to a value larger than - the default of 1500. Use the ifconfig command to increase the MTU size. - For example:: +Jumbo Frames +------------ +Jumbo Frames support is enabled by changing the MTU to a value larger +than the default of 1500. Use the ifconfig command to increase the MTU +size. For example:: ifconfig eth<x> mtu 9000 up - This setting is not saved across reboots. It can be made permanent if - you add:: +This setting is not saved across reboots. It can be made permanent if +you add:: MTU=9000 - to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example - applies to the Red Hat distributions; other distributions may store this - setting in a different location. +to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>. This example +applies to the Red Hat distributions; other distributions may store this +setting in a different location. + +Notes: Degradation in throughput performance may be observed in some +Jumbo frames environments. If this is observed, increasing the +application's socket buffer size and/or increasing the +/proc/sys/net/ipv4/tcp_*mem entry values may help. See the specific +application manual and /usr/src/linux*/Documentation/ +networking/ip-sysctl.txt for more details. - Notes: - Degradation in throughput performance may be observed in some Jumbo frames - environments. If this is observed, increasing the application's socket buffer - size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. - See the specific application manual and /usr/src/linux*/Documentation/ - networking/ip-sysctl.txt for more details. +- The maximum MTU setting for Jumbo Frames is 16110. This value + coincides with the maximum Jumbo Frames size of 16128. - - The maximum MTU setting for Jumbo Frames is 16110. This value coincides - with the maximum Jumbo Frames size of 16128. +- Using Jumbo frames at 10 or 100 Mbps is not supported and may result + in poor performance or loss of link. - - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in - poor performance or loss of link. +- Adapters based on the Intel(R) 82542 and 82573V/E controller do not + support Jumbo Frames. These correspond to the following product names: + Intel(R) PRO/1000 Gigabit Server Adapter Intel(R) PRO/1000 PM Network + Connection - - Adapters based on the Intel(R) 82542 and 82573V/E controller do not - support Jumbo Frames. These correspond to the following product names: - Intel(R) PRO/1000 Gigabit Server Adapter - Intel(R) PRO/1000 PM Network Connection +ethtool +------- +The driver utilizes the ethtool interface for driver configuration and +diagnostics, as well as displaying statistical information. The ethtool +version 1.6 or later is required for this functionality. - ethtool - ------- - The driver utilizes the ethtool interface for driver configuration and - diagnostics, as well as displaying statistical information. The ethtool - version 1.6 or later is required for this functionality. +The latest release of ethtool can be found from +https://www.kernel.org/pub/software/network/ethtool/ - The latest release of ethtool can be found from - https://www.kernel.org/pub/software/network/ethtool/ +Enabling Wake on LAN* (WoL) +--------------------------- +WoL is configured through the ethtool* utility. - Enabling Wake on LAN* (WoL) - --------------------------- - WoL is configured through the ethtool* utility. +WoL will be enabled on the system during the next shut down or reboot. +For this driver version, in order to enable WoL, the e1000 driver must be +loaded when shutting down or rebooting the system. - WoL will be enabled on the system during the next shut down or reboot. - For this driver version, in order to enable WoL, the e1000 driver must be - loaded when shutting down or rebooting the system. Support ======= diff --git a/Documentation/networking/strparser.txt b/Documentation/networking/strparser.txt index 13081b3decef..a7d354ddda7b 100644 --- a/Documentation/networking/strparser.txt +++ b/Documentation/networking/strparser.txt @@ -48,7 +48,7 @@ void strp_pause(struct strparser *strp) Temporarily pause a stream parser. Message parsing is suspended and no new messages are delivered to the upper layer. -void strp_pause(struct strparser *strp) +void strp_unpause(struct strparser *strp) Unpause a paused stream parser. diff --git a/Documentation/trace/histogram.txt b/Documentation/trace/histogram.txt index e73bcf9cb5f3..7ffea6aa22e3 100644 --- a/Documentation/trace/histogram.txt +++ b/Documentation/trace/histogram.txt @@ -1729,35 +1729,35 @@ If a variable isn't a key variable or prefixed with 'vals=', the associated event field will be saved in a variable but won't be summed as a value: - # echo 'hist:keys=next_pid:ts1=common_timestamp ... >> event/trigger + # echo 'hist:keys=next_pid:ts1=common_timestamp ...' >> event/trigger Multiple variables can be assigned at the same time. The below would result in both ts0 and b being created as variables, with both common_timestamp and field1 additionally being summed as values: - # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ... >> \ + # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ...' >> \ event/trigger Note that variable assignments can appear either preceding or following their use. The command below behaves identically to the command above: - # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ... >> \ + # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ...' >> \ event/trigger Any number of variables not bound to a 'vals=' prefix can also be assigned by simply separating them with colons. Below is the same thing but without the values being summed in the histogram: - # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ... >> event/trigger + # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ...' >> event/trigger Variables set as above can be referenced and used in expressions on another event. For example, here's how a latency can be calculated: - # echo 'hist:keys=pid,prio:ts0=common_timestamp ... >> event1/trigger - # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ... >> event2/trigger + # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger + # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger In the first line above, the event's timetamp is saved into the variable ts0. In the next line, ts0 is subtracted from the second @@ -1766,7 +1766,7 @@ yet another variable, 'wakeup_lat'. The hist trigger below in turn makes use of the wakeup_lat variable to compute a combined latency using the same key and variable from yet another event: - # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ... >> event3/trigger + # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ...' >> event3/trigger 2.2.2 Synthetic Events ---------------------- @@ -1807,10 +1807,11 @@ the command that defined it with a '!': At this point, there isn't yet an actual 'wakeup_latency' event instantiated in the event subsytem - for this to happen, a 'hist trigger action' needs to be instantiated and bound to actual fields -and variables defined on other events (see Section 6.3.3 below). +and variables defined on other events (see Section 2.2.3 below on +how that is done using hist trigger 'onmatch' action). Once that is +done, the 'wakeup_latency' synthetic event instance is created. -Once that is done, an event instance is created, and a histogram can -be defined using it: +A histogram can now be defined for the new synthetic event: # echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \ /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger @@ -1960,7 +1961,7 @@ hist trigger specification. back to that pid, the timestamp difference is calculated. If the resulting latency, stored in wakeup_lat, exceeds the current maximum latency, the values specified in the save() fields are - recoreded: + recorded: # echo 'hist:keys=pid:ts0=common_timestamp.usecs \ if comm=="cyclictest"' >> \ diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 495b7742ab58..d10944e619d3 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4610,7 +4610,7 @@ This capability indicates that kvm will implement the interfaces to handle reset, migration and nested KVM for branch prediction blocking. The stfle facility 82 should not be provided to the guest without this capability. -8.14 KVM_CAP_HYPERV_TLBFLUSH +8.18 KVM_CAP_HYPERV_TLBFLUSH Architectures: x86 diff --git a/MAINTAINERS b/MAINTAINERS index edf3cf5ea691..e19ec6d90a44 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9882,6 +9882,7 @@ M: Andrew Lunn <andrew@lunn.ch> M: Vivien Didelot <vivien.didelot@savoirfairelinux.com> M: Florian Fainelli <f.fainelli@gmail.com> S: Maintained +F: Documentation/devicetree/bindings/net/dsa/ F: net/dsa/ F: include/net/dsa.h F: include/linux/dsa/ @@ -15572,6 +15573,7 @@ M: x86@kernel.org L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core S: Maintained +F: Documentation/devicetree/bindings/x86/ F: Documentation/x86/ F: arch/x86/ @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 0c4805a572c8..04a4a138ed13 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -555,11 +555,6 @@ config SMP If you don't know what to do here, say N. -config HAVE_DEC_LOCK - bool - depends on SMP - default y - config NR_CPUS int "Maximum number of CPUs (2-32)" range 2 32 diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile index 04f9729de57c..854d5e79979e 100644 --- a/arch/alpha/lib/Makefile +++ b/arch/alpha/lib/Makefile @@ -35,8 +35,6 @@ lib-y = __divqu.o __remqu.o __divlu.o __remlu.o \ callback_srm.o srm_puts.o srm_printk.o \ fls.o -lib-$(CONFIG_SMP) += dec_and_lock.o - # The division routines are built from single source, with different defines. AFLAGS___divqu.o = -DDIV AFLAGS___remqu.o = -DREM diff --git a/arch/alpha/lib/dec_and_lock.c b/arch/alpha/lib/dec_and_lock.c deleted file mode 100644 index a117707f57fe..000000000000 --- a/arch/alpha/lib/dec_and_lock.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * arch/alpha/lib/dec_and_lock.c - * - * ll/sc version of atomic_dec_and_lock() - * - */ - -#include <linux/spinlock.h> -#include <linux/atomic.h> -#include <linux/export.h> - - asm (".text \n\ - .global _atomic_dec_and_lock \n\ - .ent _atomic_dec_and_lock \n\ - .align 4 \n\ -_atomic_dec_and_lock: \n\ - .prologue 0 \n\ -1: ldl_l $1, 0($16) \n\ - subl $1, 1, $1 \n\ - beq $1, 2f \n\ - stl_c $1, 0($16) \n\ - beq $1, 4f \n\ - mb \n\ - clr $0 \n\ - ret \n\ -2: br $29, 3f \n\ -3: ldgp $29, 0($29) \n\ - br $atomic_dec_and_lock_1..ng \n\ - .subsection 2 \n\ -4: br 1b \n\ - .previous \n\ - .end _atomic_dec_and_lock"); - -static int __used atomic_dec_and_lock_1(atomic_t *atomic, spinlock_t *lock) -{ - /* Slow path */ - spin_lock(lock); - if (atomic_dec_and_test(atomic)) - return 1; - spin_unlock(lock); - return 0; -} -EXPORT_SYMBOL(_atomic_dec_and_lock); diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index f09e9d66d605..dec130e7078c 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -544,7 +544,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) * Increment event counter and perform fixup for the pre-signal * frame. */ - rseq_signal_deliver(regs); + rseq_signal_deliver(ksig, regs); /* * Set up the stack frame @@ -666,7 +666,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) } else { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } } local_irq_disable(); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 8073625371f5..07060e5b5864 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -59,6 +59,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; static __read_mostly unsigned int xen_events_irq; +uint32_t xen_start_flags; +EXPORT_SYMBOL(xen_start_flags); + int xen_remap_domain_gfn_array(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *gfn, int nr, @@ -293,9 +296,7 @@ void __init xen_early_init(void) xen_setup_features(); if (xen_feature(XENFEAT_dom0)) - xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; - else - xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED); + xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; if (!console_set_on_cmdline && !xen_initial_domain()) add_preferred_console("hvc", 0, NULL); diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 253188fb8cb0..e3e50950a863 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -223,8 +223,8 @@ static int ctr_encrypt(struct skcipher_request *req) kernel_neon_begin(); aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr, (u8 *)ctx->key_enc, rounds, blocks, walk.iv); - err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); kernel_neon_end(); + err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } if (walk.nbytes) { u8 __aligned(8) tail[AES_BLOCK_SIZE]; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index fda9a8ca48be..fe8777b12f86 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -306,6 +306,7 @@ struct kvm_vcpu_arch { #define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */ #define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */ #define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */ +#define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */ #define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 6171178075dc..a8f84812c6e8 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -728,6 +728,17 @@ asm( asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \ } while (0) +/* + * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the + * set mask are set. Other bits are left as-is. + */ +#define sysreg_clear_set(sysreg, clear, set) do { \ + u64 __scs_val = read_sysreg(sysreg); \ + u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \ + if (__scs_new != __scs_val) \ + write_sysreg(__scs_new, sysreg); \ +} while (0) + static inline void config_sctlr_el1(u32 clear, u32 set) { u32 val; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d2856b129097..f24892a40d2c 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -937,7 +937,7 @@ static int __init parse_kpti(char *str) __kpti_forced = enabled ? 1 : -1; return 0; } -__setup("kpti=", parse_kpti); +early_param("kpti", parse_kpti); #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ #ifdef CONFIG_ARM64_HW_AFDBM diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f3e2e3aec0b0..2faa9863d2e5 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -179,7 +179,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) * This is the secondary CPU boot entry. We're using this CPUs * idle thread stack, but a set of temporary page tables. */ -asmlinkage void secondary_start_kernel(void) +asmlinkage notrace void secondary_start_kernel(void) { u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; struct mm_struct *mm = &init_mm; diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index dc6ecfa5a2d2..aac7808ce216 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -5,13 +5,14 @@ * Copyright 2018 Arm Limited * Author: Dave Martin <Dave.Martin@arm.com> */ -#include <linux/bottom_half.h> +#include <linux/irqflags.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <linux/kvm_host.h> #include <asm/kvm_asm.h> #include <asm/kvm_host.h> #include <asm/kvm_mmu.h> +#include <asm/sysreg.h> /* * Called on entry to KVM_RUN unless this vcpu previously ran at least @@ -61,10 +62,16 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) { BUG_ON(!current->mm); - vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE); + vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | + KVM_ARM64_HOST_SVE_IN_USE | + KVM_ARM64_HOST_SVE_ENABLED); vcpu->arch.flags |= KVM_ARM64_FP_HOST; + if (test_thread_flag(TIF_SVE)) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE; + + if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) + vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; } /* @@ -92,19 +99,30 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) */ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) { - local_bh_disable(); + unsigned long flags; - update_thread_flag(TIF_SVE, - vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + local_irq_save(flags); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { /* Clean guest FP state to memory and invalidate cpu view */ fpsimd_save(); fpsimd_flush_cpu_state(); - } else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { - /* Ensure user trap controls are correctly restored */ - fpsimd_bind_task_to_cpu(); + } else if (system_supports_sve()) { + /* + * The FPSIMD/SVE state in the CPU has not been touched, and we + * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been + * reset to CPACR_EL1_DEFAULT by the Hyp code, disabling SVE + * for EL0. To avoid spurious traps, restore the trap state + * seen by kvm_arch_vcpu_load_fp(): + */ + if (vcpu->arch.flags & KVM_ARM64_HOST_SVE_ENABLED) + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); + else + sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } - local_bh_enable(); + update_thread_flag(TIF_SVE, + vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + + local_irq_restore(flags); } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 49e217ac7e1e..61e93f0b5482 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -583,13 +583,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, size >> PAGE_SHIFT); return NULL; } - if (!coherent) - __dma_flush_area(page_to_virt(page), iosize); - addr = dma_common_contiguous_remap(page, size, VM_USERMAP, prot, __builtin_return_address(0)); - if (!addr) { + if (addr) { + memset(addr, 0, size); + if (!coherent) + __dma_flush_area(page_to_virt(page), iosize); + } else { iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs); dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 5f9a73a4452c..03646e6a2ef4 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -217,8 +217,9 @@ ENDPROC(idmap_cpu_replace_ttbr1) .macro __idmap_kpti_put_pgtable_ent_ng, type orr \type, \type, #PTE_NG // Same bit for blocks and pages - str \type, [cur_\()\type\()p] // Update the entry and ensure it - dc civac, cur_\()\type\()p // is visible to all CPUs. + str \type, [cur_\()\type\()p] // Update the entry and ensure + dmb sy // that it is visible to all + dc civac, cur_\()\type\()p // CPUs. .endm /* diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3f9deec70b92..08c10c518f83 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -65,6 +65,7 @@ config MIPS select HAVE_OPROFILE select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RSEQ select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP diff --git a/arch/mips/ath79/mach-pb44.c b/arch/mips/ath79/mach-pb44.c index 6b2c6f3baefa..75fb96ca61db 100644 --- a/arch/mips/ath79/mach-pb44.c +++ b/arch/mips/ath79/mach-pb44.c @@ -34,7 +34,7 @@ #define PB44_KEYS_DEBOUNCE_INTERVAL (3 * PB44_KEYS_POLL_INTERVAL) static struct gpiod_lookup_table pb44_i2c_gpiod_table = { - .dev_id = "i2c-gpio", + .dev_id = "i2c-gpio.0", .table = { GPIO_LOOKUP_IDX("ath79-gpio", PB44_GPIO_I2C_SDA, NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 6054d49e608e..8c9cbf13d32a 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -212,6 +212,12 @@ static int __init bcm47xx_cpu_fixes(void) */ if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706) cpu_wait = NULL; + + /* + * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail" + * Enable ExternalSync for sync instruction to take effect + */ + set_c0_config7(MIPS_CONF7_ES); break; #endif } diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index a7d0b836f2f7..cea8ad864b3f 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -414,6 +414,8 @@ static inline type pfx##in##bwlq##p(unsigned long port) \ __val = *__addr; \ slow; \ \ + /* prevent prefetching of coherent DMA data prematurely */ \ + rmb(); \ return pfx##ioswab##bwlq(__addr, __val); \ } diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index ae461d91cd1f..0bc270806ec5 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -681,6 +681,8 @@ #define MIPS_CONF7_WII (_ULCAST_(1) << 31) #define MIPS_CONF7_RPS (_ULCAST_(1) << 2) +/* ExternalSync */ +#define MIPS_CONF7_ES (_ULCAST_(1) << 8) #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) @@ -2765,6 +2767,7 @@ __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) __BUILD_SET_C0(config5) +__BUILD_SET_C0(config7) __BUILD_SET_C0(intcontrol) __BUILD_SET_C0(intctl) __BUILD_SET_C0(srsmap) diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index bb05e9916a5f..f25dd1d83fb7 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -388,17 +388,19 @@ #define __NR_pkey_alloc (__NR_Linux + 364) #define __NR_pkey_free (__NR_Linux + 365) #define __NR_statx (__NR_Linux + 366) +#define __NR_rseq (__NR_Linux + 367) +#define __NR_io_pgetevents (__NR_Linux + 368) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 366 +#define __NR_Linux_syscalls 368 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 366 +#define __NR_O32_Linux_syscalls 368 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -733,16 +735,18 @@ #define __NR_pkey_alloc (__NR_Linux + 324) #define __NR_pkey_free (__NR_Linux + 325) #define __NR_statx (__NR_Linux + 326) +#define __NR_rseq (__NR_Linux + 327) +#define __NR_io_pgetevents (__NR_Linux + 328) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 326 +#define __NR_Linux_syscalls 328 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 326 +#define __NR_64_Linux_syscalls 328 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -1081,15 +1085,17 @@ #define __NR_pkey_alloc (__NR_Linux + 328) #define __NR_pkey_free (__NR_Linux + 329) #define __NR_statx (__NR_Linux + 330) +#define __NR_rseq (__NR_Linux + 331) +#define __NR_io_pgetevents (__NR_Linux + 332) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 330 +#define __NR_Linux_syscalls 332 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 330 +#define __NR_N32_Linux_syscalls 332 #endif /* _UAPI_ASM_UNISTD_H */ diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index 38a302919e6b..d7de8adcfcc8 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -79,6 +79,10 @@ FEXPORT(ret_from_fork) jal schedule_tail # a0 = struct task_struct *prev FEXPORT(syscall_exit) +#ifdef CONFIG_DEBUG_RSEQ + move a0, sp + jal rseq_syscall +#endif local_irq_disable # make sure need_resched and # signals dont change between # sampling and return @@ -141,6 +145,10 @@ work_notifysig: # deal with pending signals and j resume_userspace_check FEXPORT(syscall_exit_partial) +#ifdef CONFIG_DEBUG_RSEQ + move a0, sp + jal rseq_syscall +#endif local_irq_disable # make sure need_resched doesn't # change between and return LONG_L a2, TI_FLAGS($28) # current->work diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index f2ee7e1e3342..cff52b283e03 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -119,10 +119,20 @@ NESTED(_mcount, PT_SIZE, ra) EXPORT_SYMBOL(_mcount) PTR_LA t1, ftrace_stub PTR_L t2, ftrace_trace_function /* Prepare t2 for (1) */ - bne t1, t2, static_trace + beq t1, t2, fgraph_trace nop + MCOUNT_SAVE_REGS + + move a0, ra /* arg1: self return address */ + jalr t2 /* (1) call *ftrace_trace_function */ + move a1, AT /* arg2: parent's return address */ + + MCOUNT_RESTORE_REGS + +fgraph_trace: #ifdef CONFIG_FUNCTION_GRAPH_TRACER + PTR_LA t1, ftrace_stub PTR_L t3, ftrace_graph_return bne t1, t3, ftrace_graph_caller nop @@ -131,24 +141,11 @@ EXPORT_SYMBOL(_mcount) bne t1, t3, ftrace_graph_caller nop #endif - b ftrace_stub -#ifdef CONFIG_32BIT - addiu sp, sp, 8 -#else - nop -#endif -static_trace: - MCOUNT_SAVE_REGS - - move a0, ra /* arg1: self return address */ - jalr t2 /* (1) call *ftrace_trace_function */ - move a1, AT /* arg2: parent's return address */ - - MCOUNT_RESTORE_REGS #ifdef CONFIG_32BIT addiu sp, sp, 8 #endif + .globl ftrace_stub ftrace_stub: RETURN_BACK diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index a9a7d78803cd..91d3c8c46097 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -590,3 +590,5 @@ EXPORT(sys_call_table) PTR sys_pkey_alloc PTR sys_pkey_free /* 4365 */ PTR sys_statx + PTR sys_rseq + PTR sys_io_pgetevents diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 65d5aeeb9bdb..358d9599983d 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -439,4 +439,6 @@ EXPORT(sys_call_table) PTR sys_pkey_alloc PTR sys_pkey_free /* 5325 */ PTR sys_statx + PTR sys_rseq + PTR sys_io_pgetevents .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index cbf190ef9e8a..c65eaacc1abf 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -434,4 +434,6 @@ EXPORT(sysn32_call_table) PTR sys_pkey_alloc PTR sys_pkey_free PTR sys_statx /* 6330 */ + PTR sys_rseq + PTR compat_sys_io_pgetevents .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 9ebe3e2403b1..73913f072e39 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -583,4 +583,6 @@ EXPORT(sys32_call_table) PTR sys_pkey_alloc PTR sys_pkey_free /* 4365 */ PTR sys_statx + PTR sys_rseq + PTR compat_sys_io_pgetevents .size sys32_call_table,.-sys32_call_table diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 9e224469c788..00f2535d2226 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -801,6 +801,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->regs[0] = 0; /* Don't deal with this again. */ } + rseq_signal_deliver(regs); + if (sig_uses_siginfo(&ksig->ka, abi)) ret = abi->setup_rt_frame(vdso + abi->vdso->off_rt_sigreturn, ksig, regs, oldset); @@ -868,6 +870,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); + rseq_handle_notify_resume(regs); } user_enter(); diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index bd06a3ccda31..2ea575cb3401 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -244,6 +244,7 @@ cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4 +cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc) KBUILD_AFLAGS += $(cpu-as-y) KBUILD_CFLAGS += $(cpu-as-y) diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 6a6673907e45..e4633803fe43 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -108,6 +108,7 @@ static inline void pgtable_free(void *table, unsigned index_size) } #define check_pgt_cache() do { } while (0) +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index af5f2baac80f..a069dfcac9a9 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -49,6 +49,27 @@ static inline int hugepd_ok(hugepd_t hpd) } #define is_hugepd(hpd) (hugepd_ok(hpd)) +/* + * 16M and 16G huge page directory tables are allocated from slab cache + * + */ +#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24) +#define H_16G_CACHE_INDEX \ + (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34) + +static inline int get_hugepd_cache_index(int index) +{ + switch (index) { + case H_16M_CACHE_INDEX: + return HTLB_16M_INDEX; + case H_16G_CACHE_INDEX: + return HTLB_16G_INDEX; + default: + BUG(); + } + /* should not reach */ +} + #else /* !CONFIG_HUGETLB_PAGE */ static inline int pmd_huge(pmd_t pmd) { return 0; } static inline int pud_huge(pud_t pud) { return 0; } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index fb4b3ba52339..d7ee249d6890 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -45,8 +45,17 @@ static inline int hugepd_ok(hugepd_t hpd) { return 0; } + #define is_hugepd(pdep) 0 +/* + * This should never get called + */ +static inline int get_hugepd_cache_index(int index) +{ + BUG(); +} + #else /* !CONFIG_HUGETLB_PAGE */ static inline int pmd_huge(pmd_t pmd) { return 0; } static inline int pud_huge(pud_t pud) { return 0; } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 63cee159022b..42aafba7a308 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -287,6 +287,11 @@ enum pgtable_index { PMD_INDEX, PUD_INDEX, PGD_INDEX, + /* + * Below are used with 4k page size and hugetlb + */ + HTLB_16M_INDEX, + HTLB_16G_INDEX, }; extern unsigned long __vmalloc_start; diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 0f571e0ebca1..bd9ba8defd72 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -8,7 +8,7 @@ extern void arch_touch_nmi_watchdog(void); static inline void arch_touch_nmi_watchdog(void) {} #endif -#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_STACKTRACE) +#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE) extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h index 1707781d2f20..9de40eb614da 100644 --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h @@ -109,6 +109,7 @@ static inline void pgtable_free(void *table, unsigned index_size) } #define check_pgt_cache() do { } while (0) +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 0e693f322cb2..e2d62d033708 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -141,6 +141,7 @@ static inline void pgtable_free(void *table, int shift) } } +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 4be1c0de9406..96dd3d871986 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -711,7 +711,8 @@ static __init void cpufeatures_cpu_quirks(void) cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; - } else /* DD2.1 and up have DD2_1 */ + } else if ((version & 0xffff0000) == 0x004e0000) + /* DD2.1 and up have DD2_1 */ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; if ((version & 0xffff0000) == 0x004e0000) { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 62b1a40d8957..40b44bb53a4e 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -701,11 +701,18 @@ static int ppc_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { /* + * panic does a local_irq_disable, but we really + * want interrupts to be hard disabled. + */ + hard_irq_disable(); + + /* * If firmware-assisted dump has been registered then trigger * firmware-assisted dump and let firmware handle everything else. */ crash_fadump(NULL, ptr); - ppc_md.panic(ptr); /* May not return */ + if (ppc_md.panic) + ppc_md.panic(ptr); /* May not return */ return NOTIFY_DONE; } @@ -716,7 +723,8 @@ static struct notifier_block ppc_panic_block = { void __init setup_panic(void) { - if (!ppc_md.panic) + /* PPC64 always does a hard irq disable in its panic handler */ + if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic) return; atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 7a7ce8ad455e..225bc5f91049 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -387,6 +387,14 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ +void panic_smp_self_stop(void) +{ + hard_irq_disable(); + spin_begin(); + while (1) + spin_cpu_relax(); +} + #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) static bool use_spinloop(void) { diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 17fe4339ba59..b3e8db376ecd 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -134,7 +134,7 @@ static void do_signal(struct task_struct *tsk) /* Re-enable the breakpoints for the signal stack */ thread_change_pc(tsk, tsk->thread.regs); - rseq_signal_deliver(tsk->thread.regs); + rseq_signal_deliver(&ksig, tsk->thread.regs); if (is32) { if (ksig.ka.sa.sa_flags & SA_SIGINFO) @@ -170,7 +170,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } user_enter(); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5eadfffabe35..4794d6b4f4d2 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -600,9 +600,6 @@ static void nmi_stop_this_cpu(struct pt_regs *regs) nmi_ipi_busy_count--; nmi_ipi_unlock(); - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - spin_begin(); while (1) spin_cpu_relax(); @@ -617,9 +614,6 @@ void smp_send_stop(void) static void stop_this_cpu(void *dummy) { - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - hard_irq_disable(); spin_begin(); while (1) diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 07e97f289c52..e2c50b55138f 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -196,7 +196,7 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable); #endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ -#ifdef CONFIG_PPC_BOOK3S_64 +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) static void handle_backtrace_ipi(struct pt_regs *regs) { nmi_cpu_backtrace(regs); @@ -242,4 +242,4 @@ void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); } -#endif /* CONFIG_PPC64 */ +#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7c5f479c5c00..8a9a49c13865 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -337,7 +337,8 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else - pgtable_free_tlb(tlb, hugepte, pdshift - shift); + pgtable_free_tlb(tlb, hugepte, + get_hugepd_cache_index(pdshift - shift)); } static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index c1f4ca45c93a..4afbfbb64bfd 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -409,6 +409,18 @@ static inline void pgtable_free(void *table, int index) case PUD_INDEX: kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table); break; +#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE) + /* 16M hugepd directory at pud level */ + case HTLB_16M_INDEX: + BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0); + kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table); + break; + /* 16G hugepd directory at the pgd level */ + case HTLB_16G_INDEX: + BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0); + kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table); + break; +#endif /* We don't free pgd table via RCU callback */ default: BUG(); diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 67a6e86d3e7e..1135b43a597c 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -689,22 +689,17 @@ EXPORT_SYMBOL(radix__flush_tlb_kernel_range); static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2; -void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) +static inline void __radix__flush_tlb_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + bool flush_all_sizes) { - struct mm_struct *mm = vma->vm_mm; unsigned long pid; unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift; unsigned long page_size = 1UL << page_shift; unsigned long nr_pages = (end - start) >> page_shift; bool local, full; -#ifdef CONFIG_HUGETLB_PAGE - if (is_vm_hugetlb_page(vma)) - return radix__flush_hugetlb_tlb_range(vma, start, end); -#endif - pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) return; @@ -738,37 +733,64 @@ is_local: _tlbie_pid(pid, RIC_FLUSH_TLB); } } else { - bool hflush = false; + bool hflush = flush_all_sizes; + bool gflush = flush_all_sizes; unsigned long hstart, hend; + unsigned long gstart, gend; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT; - hend = end >> HPAGE_PMD_SHIFT; - if (hstart < hend) { - hstart <<= HPAGE_PMD_SHIFT; - hend <<= HPAGE_PMD_SHIFT; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) hflush = true; + + if (hflush) { + hstart = (start + PMD_SIZE - 1) & PMD_MASK; + hend = end & PMD_MASK; + if (hstart == hend) + hflush = false; + } + + if (gflush) { + gstart = (start + PUD_SIZE - 1) & PUD_MASK; + gend = end & PUD_MASK; + if (gstart == gend) + gflush = false; } -#endif asm volatile("ptesync": : :"memory"); if (local) { __tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbiel_va_range(hstart, hend, pid, - HPAGE_PMD_SIZE, MMU_PAGE_2M); + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbiel_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); asm volatile("ptesync": : :"memory"); } else { __tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbie_va_range(hstart, hend, pid, - HPAGE_PMD_SIZE, MMU_PAGE_2M); + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbie_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); fixup_tlbie(); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } } preempt_enable(); } + +void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) + +{ +#ifdef CONFIG_HUGETLB_PAGE + if (is_vm_hugetlb_page(vma)) + return radix__flush_hugetlb_tlb_range(vma, start, end); +#endif + + __radix__flush_tlb_range(vma->vm_mm, start, end, false); +} EXPORT_SYMBOL(radix__flush_tlb_range); static int radix_get_mmu_psize(int page_size) @@ -837,6 +859,8 @@ void radix__tlb_flush(struct mmu_gather *tlb) int psize = 0; struct mm_struct *mm = tlb->mm; int page_size = tlb->page_size; + unsigned long start = tlb->start; + unsigned long end = tlb->end; /* * if page size is not something we understand, do a full mm flush @@ -847,15 +871,45 @@ void radix__tlb_flush(struct mmu_gather *tlb) */ if (tlb->fullmm) { __flush_all_mm(mm, true); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) + } else if (mm_tlb_flush_nested(mm)) { + /* + * If there is a concurrent invalidation that is clearing ptes, + * then it's possible this invalidation will miss one of those + * cleared ptes and miss flushing the TLB. If this invalidate + * returns before the other one flushes TLBs, that can result + * in it returning while there are still valid TLBs inside the + * range to be invalidated. + * + * See mm/memory.c:tlb_finish_mmu() for more details. + * + * The solution to this is ensure the entire range is always + * flushed here. The problem for powerpc is that the flushes + * are page size specific, so this "forced flush" would not + * do the right thing if there are a mix of page sizes in + * the range to be invalidated. So use __flush_tlb_range + * which invalidates all possible page sizes in the range. + * + * PWC flush probably is not be required because the core code + * shouldn't free page tables in this path, but accounting + * for the possibility makes us a bit more robust. + * + * need_flush_all is an uncommon case because page table + * teardown should be done with exclusive locks held (but + * after locks are dropped another invalidate could come + * in), it could be optimized further if necessary. + */ + if (!tlb->need_flush_all) + __radix__flush_tlb_range(mm, start, end, true); + else + radix__flush_all_mm(mm); +#endif } else if ( (psize = radix_get_mmu_psize(page_size)) == -1) { if (!tlb->need_flush_all) radix__flush_tlb_mm(mm); else radix__flush_all_mm(mm); } else { - unsigned long start = tlb->start; - unsigned long end = tlb->end; - if (!tlb->need_flush_all) radix__flush_tlb_range_psize(mm, start, end, psize); else @@ -1043,6 +1097,8 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) { if (sib == cpu) continue; + if (!cpu_possible(sib)) + continue; if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu) flush = true; } diff --git a/arch/x86/Makefile b/arch/x86/Makefile index f0a6ea22429d..a08e82856563 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -258,11 +258,6 @@ archscripts: scripts_basic archheaders: $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all -archprepare: -ifeq ($(CONFIG_KEXEC_FILE),y) - $(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c -endif - ### # Kernel objects @@ -327,7 +322,6 @@ archclean: $(Q)rm -rf $(objtree)/arch/x86_64 $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=arch/x86/tools - $(Q)$(MAKE) $(clean)=arch/x86/purgatory define archhelp echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)' diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index a8a8642d2b0b..e57665b4ba1c 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -118,7 +118,7 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) void *romimage; status = efi_call_proto(efi_pci_io_protocol, attributes, pci, - EfiPciIoAttributeOperationGet, 0, 0, + EfiPciIoAttributeOperationGet, 0ULL, &attributes); if (status != EFI_SUCCESS) return status; diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 92190879b228..3b2490b81918 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -164,7 +164,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) if (cached_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } if (cached_flags & _TIF_USER_RETURN_NOTIFY) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 042b5e892ed1..14de0432d288 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -38,7 +38,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, { unsigned long mask; - asm ("cmp %1,%2; sbb %0,%0;" + asm volatile ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) :"g"(size),"r" (index) :"cc"); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 425e6b8b9547..6aa8499e1f62 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -114,6 +114,7 @@ #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f #define VMX_MISC_SAVE_EFER_LMA 0x00000020 #define VMX_MISC_ACTIVITY_HLT 0x00000040 +#define VMX_MISC_ZERO_LEN_INS 0x40000000 /* VMFUNC functions */ #define VMX_VMFUNC_EPTP_SWITCHING 0x00000001 @@ -351,11 +352,13 @@ enum vmcs_field { #define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ +#define INTR_TYPE_RESERVED (1 << 8) /* reserved */ #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ #define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ #define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ #define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ +#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index efaf2d4f9c3c..d492752f79e1 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/reboot.h> +#include <linux/memory.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> @@ -392,6 +393,51 @@ extern int uv_hub_info_version(void) } EXPORT_SYMBOL(uv_hub_info_version); +/* Default UV memory block size is 2GB */ +static unsigned long mem_block_size = (2UL << 30); + +/* Kernel parameter to specify UV mem block size */ +static int parse_mem_block_size(char *ptr) +{ + unsigned long size = memparse(ptr, NULL); + + /* Size will be rounded down by set_block_size() below */ + mem_block_size = size; + return 0; +} +early_param("uv_memblksize", parse_mem_block_size); + +static __init int adj_blksize(u32 lgre) +{ + unsigned long base = (unsigned long)lgre << UV_GAM_RANGE_SHFT; + unsigned long size; + + for (size = mem_block_size; size > MIN_MEMORY_BLOCK_SIZE; size >>= 1) + if (IS_ALIGNED(base, size)) + break; + + if (size >= mem_block_size) + return 0; + + mem_block_size = size; + return 1; +} + +static __init void set_block_size(void) +{ + unsigned int order = ffs(mem_block_size); + + if (order) { + /* adjust for ffs return of 1..64 */ + set_memory_block_size_order(order - 1); + pr_info("UV: mem_block_size set to 0x%lx\n", mem_block_size); + } else { + /* bad or zero value, default to 1UL << 31 (2GB) */ + pr_err("UV: mem_block_size error with 0x%lx\n", mem_block_size); + set_memory_block_size_order(31); + } +} + /* Build GAM range lookup table: */ static __init void build_uv_gr_table(void) { @@ -1180,23 +1226,30 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) << UV_GAM_RANGE_SHFT); int order = 0; char suffix[] = " KMGTPE"; + int flag = ' '; while (size > 9999 && order < sizeof(suffix)) { size /= 1024; order++; } + /* adjust max block size to current range start */ + if (gre->type == 1 || gre->type == 2) + if (adj_blksize(lgre)) + flag = '*'; + if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); + pr_info("UV: # %20s %14s %6s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx%c %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - size, suffix[order], + flag, size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); + /* update to next range start */ lgre = gre->limit; if (sock_min > gre->sockid) sock_min = gre->sockid; @@ -1427,6 +1480,7 @@ static void __init uv_system_init_hub(void) build_socket_tables(); build_uv_gr_table(); + set_block_size(); uv_init_hub_info(&hub_info); uv_possible_blades = num_possible_nodes(); if (!_node_to_pnode) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index cd0fda1fff6d..404df26b7de8 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -27,6 +27,7 @@ #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/intel-family.h> +#include <asm/hypervisor.h> static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); @@ -664,6 +665,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr if (boot_cpu_has(X86_FEATURE_PTI)) return sprintf(buf, "Mitigation: PTI\n"); + if (hypervisor_is_type(X86_HYPER_XEN_PV)) + return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + break; case X86_BUG_SPECTRE_V1: diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 38354c66df81..0c5fcbd998cf 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -671,7 +671,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) num_sharing_cache = ((eax >> 14) & 0xfff) + 1; if (num_sharing_cache) { - int bits = get_count_order(num_sharing_cache) - 1; + int bits = get_count_order(num_sharing_cache); per_cpu(cpu_llc_id, cpu) = c->apicid >> bits; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0df7151cfef4..eb4cb3efd20e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,3 +1,6 @@ +/* cpu_feature_enabled() cannot be used this early */ +#define USE_EARLY_PGTABLE_L5 + #include <linux/bootmem.h> #include <linux/linkage.h> #include <linux/bitops.h> diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 5bbd06f38ff6..f34d89c01edc 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -160,6 +160,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), USER ), + MCESEV( + PANIC, "Data load in unrecoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index e4cf6ff1c2e1..c102ad51025e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -772,23 +772,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - int i, ret = 0; char *tmp; + int i; for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(msr_ops.status(i)); - if (m->status & MCI_STATUS_VAL) { - __set_bit(i, validp); - if (quirk_no_way_out) - quirk_no_way_out(i, m, regs); - } + if (!(m->status & MCI_STATUS_VAL)) + continue; + + __set_bit(i, validp); + if (quirk_no_way_out) + quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + mce_read_aux(m, i); *msg = tmp; - ret = 1; + return 1; } } - return ret; + return 0; } /* @@ -1205,13 +1207,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* + * Local machine check may already know that we have to panic. + * Broadcast machine check begins rendezvous in mce_start() * Go through all banks in exclusion of the other CPUs. This way we * don't report duplicated events on shared banks because the first one - * to see it will clear it. If this is a Local MCE, then no need to - * perform rendezvous. + * to see it will clear it. */ - if (!lmce) + if (lmce) { + if (no_way_out) + mce_panic("Fatal local machine check", &m, msg); + } else { order = mce_start(&no_way_out); + } for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); @@ -1287,12 +1294,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) no_way_out = worst >= MCE_PANIC_SEVERITY; } else { /* - * Local MCE skipped calling mce_reign() - * If we found a fatal error, we need to panic here. + * If there was a fatal machine check we should have + * already called mce_panic earlier in this function. + * Since we re-read the banks, we might have found + * something new. Check again to see if we found a + * fatal error. We call "mce_severity()" again to + * make sure we have the right "msg". */ - if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Machine check from unknown source", - NULL, NULL); + if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { + mce_severity(&m, cfg->tolerant, &msg, true); + mce_panic("Local fatal machine check!", &m, msg); + } } /* diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 1c2cfa0644aa..97ccf4c3b45b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -190,8 +190,11 @@ static void save_microcode_patch(void *data, unsigned int size) p = memdup_patch(data, size); if (!p) pr_err("Error allocating buffer %p\n", data); - else + else { list_replace(&iter->plist, &p->plist); + kfree(iter->data); + kfree(iter); + } } } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index a21d6ace648e..8047379e575a 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -44,7 +44,7 @@ static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); #ifdef CONFIG_X86_5LEVEL -unsigned int __pgtable_l5_enabled __initdata; +unsigned int __pgtable_l5_enabled __ro_after_init; unsigned int pgdir_shift __ro_after_init = 39; EXPORT_SYMBOL(pgdir_shift); unsigned int ptrs_per_p4d __ro_after_init = 1; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 697a4ce04308..736348ead421 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -645,12 +645,19 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) /* Skylake */ static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev) { - u32 capid0; + u32 capid0, capid5; pci_read_config_dword(pdev, 0x84, &capid0); + pci_read_config_dword(pdev, 0x98, &capid5); - if ((capid0 & 0xc0) == 0xc0) + /* + * CAPID0{7:6} indicate whether this is an advanced RAS SKU + * CAPID5{8:5} indicate that various NVDIMM usage modes are + * enabled, so memory machine check recovery is also enabled. + */ + if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0)) static_branch_inc(&mcsafe_key); + } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 445ca11ff863..92a3b312a53c 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -692,7 +692,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) * Increment event counter and perform fixup for the pre-signal * frame. */ - rseq_signal_deliver(regs); + rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a535dd64de63..e6db475164ed 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -835,16 +835,18 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP) - return; cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (!fixup_exception(regs, trapnr)) { - task->thread.error_code = error_code; - task->thread.trap_nr = trapnr; + if (fixup_exception(regs, trapnr)) + return; + + task->thread.error_code = error_code; + task->thread.trap_nr = trapnr; + + if (notify_die(DIE_TRAP, str, regs, error_code, + trapnr, SIGFPE) != NOTIFY_STOP) die(str, regs, error_code); - } return; } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 58d8d800875d..deb576b23b7c 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -293,7 +293,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64); /* has the side-effect of processing the entire instruction */ insn_get_length(insn); - if (WARN_ON_ONCE(!insn_complete(insn))) + if (!insn_complete(insn)) return -ENOEXEC; if (is_prefix_bad(insn)) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 559a12b6184d..1689f433f3a0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1705,6 +1705,17 @@ static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } +static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS; +} + +static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.procbased_ctls_high & + CPU_BASED_MONITOR_TRAP_FLAG; +} + static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit) { return vmcs12->cpu_based_vm_exec_control & bit; @@ -11620,6 +11631,62 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) !nested_cr3_valid(vcpu, vmcs12->host_cr3)) return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD; + /* + * From the Intel SDM, volume 3: + * Fields relevant to VM-entry event injection must be set properly. + * These fields are the VM-entry interruption-information field, the + * VM-entry exception error code, and the VM-entry instruction length. + */ + if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) { + u32 intr_info = vmcs12->vm_entry_intr_info_field; + u8 vector = intr_info & INTR_INFO_VECTOR_MASK; + u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK; + bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK; + bool should_have_error_code; + bool urg = nested_cpu_has2(vmcs12, + SECONDARY_EXEC_UNRESTRICTED_GUEST); + bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; + + /* VM-entry interruption-info field: interruption type */ + if (intr_type == INTR_TYPE_RESERVED || + (intr_type == INTR_TYPE_OTHER_EVENT && + !nested_cpu_supports_monitor_trap_flag(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: vector */ + if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || + (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || + (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: deliver error code */ + should_have_error_code = + intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && + x86_exception_has_error_code(vector); + if (has_error_code != should_have_error_code) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry exception error code */ + if (has_error_code && + vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: reserved bits */ + if (intr_info & INTR_INFO_RESVD_BITS_MASK) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry instruction length */ + switch (intr_type) { + case INTR_TYPE_SOFT_EXCEPTION: + case INTR_TYPE_SOFT_INTR: + case INTR_TYPE_PRIV_SW_EXCEPTION: + if ((vmcs12->vm_entry_instruction_len > 15) || + (vmcs12->vm_entry_instruction_len == 0 && + !nested_cpu_has_zero_length_injection(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + } + } + return 0; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 331993c49dae..257f27620bc2 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -110,6 +110,15 @@ static inline bool is_la57_mode(struct kvm_vcpu *vcpu) #endif } +static inline bool x86_exception_has_error_code(unsigned int vector) +{ + static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | + BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) | + BIT(PF_VECTOR) | BIT(AC_VECTOR); + + return (1U << vector) & exception_has_error_code; +} + static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) { return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 045f492d5f68..a688617c727e 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1350,16 +1350,28 @@ int kern_addr_valid(unsigned long addr) /* Amount of ram needed to start using large blocks */ #define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30) +/* Adjustable memory block size */ +static unsigned long set_memory_block_size; +int __init set_memory_block_size_order(unsigned int order) +{ + unsigned long size = 1UL << order; + + if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE) + return -EINVAL; + + set_memory_block_size = size; + return 0; +} + static unsigned long probe_memory_block_size(void) { unsigned long boot_mem_end = max_pfn << PAGE_SHIFT; unsigned long bz; - /* If this is UV system, always set 2G block size */ - if (is_uv_system()) { - bz = MAX_BLOCK_SIZE; + /* If memory block size has been set, then use it */ + bz = set_memory_block_size; + if (bz) goto done; - } /* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */ if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) { diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c9081c6671f0..3b5318505c69 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -65,6 +65,13 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* + * NB: needs to live in .data because it's used by xen_prepare_pvh which runs + * before clearing the bss. + */ +uint32_t xen_start_flags __attribute__((section(".data"))) = 0; +EXPORT_SYMBOL(xen_start_flags); + +/* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 357969a3697c..8d4e2e1ae60b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1203,6 +1203,7 @@ asmlinkage __visible void __init xen_start_kernel(void) return; xen_domain_type = XEN_PV_DOMAIN; + xen_start_flags = xen_start_info->flags; xen_setup_features(); diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index aa1c6a6831a9..c85d1a88f476 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -97,6 +97,7 @@ void __init xen_prepare_pvh(void) } xen_pvh = 1; + xen_start_flags = pvh_start_info.flags; msr = cpuid_ebx(xen_cpuid_base() + 2); pfn = __pa(hypercall_page); diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 2e20ae2fa2d6..e3b18ad49889 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -32,6 +32,7 @@ #include <xen/interface/vcpu.h> #include <xen/interface/xenpmu.h> +#include <asm/spec-ctrl.h> #include <asm/xen/interface.h> #include <asm/xen/hypercall.h> @@ -70,6 +71,8 @@ static void cpu_bringup(void) cpu_data(cpu).x86_max_cores = 1; set_cpu_sibling_map(cpu); + speculative_store_bypass_ht_init(); + xen_setup_cpu_clockevents(); notify_cpu_starting(cpu); @@ -250,6 +253,8 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) } set_cpu_sibling_map(0); + speculative_store_bypass_ht_init(); + xen_pmu_init(0); if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0)) diff --git a/block/bio.c b/block/bio.c index 9710e275f230..67eff5eddc49 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1807,9 +1807,6 @@ again: if (!bio_integrity_endio(bio)) return; - if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL")) - bio->bi_next = NULL; - /* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that diff --git a/block/blk-core.c b/block/blk-core.c index cf0ee764b908..afd2596ea3d3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -273,10 +273,6 @@ static void req_bio_endio(struct request *rq, struct bio *bio, bio_advance(bio, nbytes); /* don't actually finish bio if it's part of flush sequence */ - /* - * XXX this code looks suspicious - it's not consistent with advancing - * req->bio in caller - */ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); } @@ -3081,10 +3077,8 @@ bool blk_update_request(struct request *req, blk_status_t error, struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); - if (bio_bytes == bio->bi_iter.bi_size) { + if (bio_bytes == bio->bi_iter.bi_size) req->bio = bio->bi_next; - bio->bi_next = NULL; - } /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index ffa622366922..1c4532e92938 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -356,7 +356,7 @@ static const char *const blk_mq_rq_state_name_array[] = { static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state) { - if (WARN_ON_ONCE((unsigned int)rq_state > + if (WARN_ON_ONCE((unsigned int)rq_state >= ARRAY_SIZE(blk_mq_rq_state_name_array))) return "(?)"; return blk_mq_rq_state_name_array[rq_state]; diff --git a/block/blk-mq.c b/block/blk-mq.c index 70c65bb6c013..b429d515b568 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -781,7 +781,6 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved) WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); } - req->rq_flags &= ~RQF_TIMED_OUT; blk_add_timer(req); } diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 01e2b353a2b9..15c1f5e12eb8 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -144,6 +144,7 @@ do_local: local_irq_restore(flags); } +EXPORT_SYMBOL(__blk_complete_request); /** * blk_complete_request - end I/O on a request diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 4b8a48d48ba1..f2cfd56e1606 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -210,6 +210,7 @@ void blk_add_timer(struct request *req) if (!req->timeout) req->timeout = q->rq_timeout; + req->rq_flags &= ~RQF_TIMED_OUT; blk_rq_set_deadline(req, jiffies + req->timeout); /* diff --git a/block/sed-opal.c b/block/sed-opal.c index 945f4b8610e0..e0de4dd448b3 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -877,7 +877,7 @@ static size_t response_get_string(const struct parsed_resp *resp, int n, return 0; } - if (n > resp->num) { + if (n >= resp->num) { pr_debug("Response has %d tokens. Can't access %d\n", resp->num, n); return 0; @@ -916,7 +916,7 @@ static u64 response_get_u64(const struct parsed_resp *resp, int n) return 0; } - if (n > resp->num) { + if (n >= resp->num) { pr_debug("Response has %d tokens. Can't access %d\n", resp->num, n); return 0; diff --git a/crypto/morus640.c b/crypto/morus640.c index 9fbcde307daf..5eede3749e64 100644 --- a/crypto/morus640.c +++ b/crypto/morus640.c @@ -274,8 +274,9 @@ static void crypto_morus640_decrypt_chunk(struct morus640_state *state, u8 *dst, union morus640_block_in tail; memcpy(tail.bytes, src, size); + memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size); - crypto_morus640_load_a(&m, src); + crypto_morus640_load_a(&m, tail.bytes); crypto_morus640_core(state, &m); crypto_morus640_store_a(tail.bytes, &m); memset(tail.bytes + size, 0, MORUS640_BLOCK_SIZE - size); diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c index 264ec12c0b9c..7f6735d9003f 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -152,7 +152,7 @@ static SHA3_INLINE void keccakf_round(u64 st[25]) st[24] ^= bc[ 4]; } -static void __optimize("O3") keccakf(u64 st[25]) +static void keccakf(u64 st[25]) { int round; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3b7083b8ecbb..74a05561b620 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -76,6 +76,7 @@ struct link_dead_args { #define NBD_HAS_CONFIG_REF 4 #define NBD_BOUND 5 #define NBD_DESTROY_ON_DISCONNECT 6 +#define NBD_DISCONNECT_ON_CLOSE 7 struct nbd_config { u32 flags; @@ -138,6 +139,7 @@ static void nbd_config_put(struct nbd_device *nbd); static void nbd_connect_reply(struct genl_info *info, int index); static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info); static void nbd_dead_link_work(struct work_struct *work); +static void nbd_disconnect_and_put(struct nbd_device *nbd); static inline struct device *nbd_to_dev(struct nbd_device *nbd) { @@ -1305,6 +1307,12 @@ out: static void nbd_release(struct gendisk *disk, fmode_t mode) { struct nbd_device *nbd = disk->private_data; + struct block_device *bdev = bdget_disk(disk, 0); + + if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && + bdev->bd_openers == 0) + nbd_disconnect_and_put(nbd); + nbd_config_put(nbd); nbd_put(nbd); } @@ -1705,6 +1713,10 @@ again: &config->runtime_flags); put_dev = true; } + if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { + set_bit(NBD_DISCONNECT_ON_CLOSE, + &config->runtime_flags); + } } if (info->attrs[NBD_ATTR_SOCKETS]) { @@ -1749,6 +1761,17 @@ out: return ret; } +static void nbd_disconnect_and_put(struct nbd_device *nbd) +{ + mutex_lock(&nbd->config_lock); + nbd_disconnect(nbd); + nbd_clear_sock(nbd); + mutex_unlock(&nbd->config_lock); + if (test_and_clear_bit(NBD_HAS_CONFIG_REF, + &nbd->config->runtime_flags)) + nbd_config_put(nbd); +} + static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd; @@ -1781,13 +1804,7 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) nbd_put(nbd); return 0; } - mutex_lock(&nbd->config_lock); - nbd_disconnect(nbd); - nbd_clear_sock(nbd); - mutex_unlock(&nbd->config_lock); - if (test_and_clear_bit(NBD_HAS_CONFIG_REF, - &nbd->config->runtime_flags)) - nbd_config_put(nbd); + nbd_disconnect_and_put(nbd); nbd_config_put(nbd); nbd_put(nbd); return 0; @@ -1798,7 +1815,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) struct nbd_device *nbd = NULL; struct nbd_config *config; int index; - int ret = -EINVAL; + int ret = 0; bool put_dev = false; if (!netlink_capable(skb, CAP_SYS_ADMIN)) @@ -1838,6 +1855,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) !nbd->task_recv) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); + ret = -EINVAL; goto out; } @@ -1862,6 +1880,14 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) &config->runtime_flags)) refcount_inc(&nbd->refs); } + + if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { + set_bit(NBD_DISCONNECT_ON_CLOSE, + &config->runtime_flags); + } else { + clear_bit(NBD_DISCONNECT_ON_CLOSE, + &config->runtime_flags); + } } if (info->attrs[NBD_ATTR_SOCKETS]) { diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 7948049f6c43..042c778e5a4e 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -1365,7 +1365,7 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio) static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq) { pr_info("null: rq %p timed out\n", rq); - blk_mq_complete_request(rq); + __blk_complete_request(rq); return BLK_EH_DONE; } diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 91bb98c42a1c..aaf9e5afaad4 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -516,11 +516,18 @@ EXPORT_SYMBOL_GPL(hwrng_register); void hwrng_unregister(struct hwrng *rng) { + int err; + mutex_lock(&rng_mutex); list_del(&rng->list); - if (current_rng == rng) - enable_best_rng(); + if (current_rng == rng) { + err = enable_best_rng(); + if (err) { + drop_current_rng(); + cur_rng_set_by_user = 0; + } + } if (list_empty(&rng_list)) { mutex_unlock(&rng_mutex); diff --git a/drivers/clocksource/timer-stm32.c b/drivers/clocksource/timer-stm32.c index e5cdc3af684c..2717f88c7904 100644 --- a/drivers/clocksource/timer-stm32.c +++ b/drivers/clocksource/timer-stm32.c @@ -304,8 +304,10 @@ static int __init stm32_timer_init(struct device_node *node) to->private_data = kzalloc(sizeof(struct stm32_timer_private), GFP_KERNEL); - if (!to->private_data) + if (!to->private_data) { + ret = -ENOMEM; goto deinit; + } rstc = of_reset_control_get(node, NULL); if (!IS_ERR(rstc)) { diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index 00c7aab8e7d0..afebbd87c4aa 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -1548,15 +1548,14 @@ skip_copy: tp->urg_data = 0; if ((avail + offset) >= skb->len) { - if (likely(skb)) - chtls_free_skb(sk, skb); - buffers_freed++; if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) { tp->copied_seq += skb->len; hws->rcvpld = skb->hdr_len; } else { tp->copied_seq += hws->rcvpld; } + chtls_free_skb(sk, skb); + buffers_freed++; hws->copied_seq = 0; if (copied >= target && !skb_peek(&sk->sk_receive_queue)) diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c index caa37a6dd9d4..a90b0b8fc69a 100644 --- a/drivers/firmware/efi/libstub/tpm.c +++ b/drivers/firmware/efi/libstub/tpm.c @@ -64,7 +64,7 @@ static void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg) efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID; efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID; efi_status_t status; - efi_physical_addr_t log_location, log_last_entry; + efi_physical_addr_t log_location = 0, log_last_entry = 0; struct linux_efi_tpm_eventlog *log_tbl = NULL; unsigned long first_entry_addr, last_entry_addr; size_t log_size, last_entry_size; diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index 0f52d44b3f69..f5fe0100f9ff 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -199,7 +199,7 @@ static int gicv2m_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, fail: irq_domain_free_irqs_parent(domain, virq, nr_irqs); - gicv2m_unalloc_msi(v2m, hwirq, get_count_order(nr_irqs)); + gicv2m_unalloc_msi(v2m, hwirq, nr_irqs); return err; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 5377d7e2afba..d7842d312d3e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -182,6 +182,22 @@ static struct its_collection *dev_event_to_col(struct its_device *its_dev, return its->collections + its_dev->event_map.col_map[event]; } +static struct its_collection *valid_col(struct its_collection *col) +{ + if (WARN_ON_ONCE(col->target_address & GENMASK_ULL(0, 15))) + return NULL; + + return col; +} + +static struct its_vpe *valid_vpe(struct its_node *its, struct its_vpe *vpe) +{ + if (valid_col(its->collections + vpe->col_idx)) + return vpe; + + return NULL; +} + /* * ITS command descriptors - parameters to be encoded in a command * block. @@ -439,7 +455,7 @@ static struct its_collection *its_build_mapti_cmd(struct its_node *its, its_fixup_cmd(cmd); - return col; + return valid_col(col); } static struct its_collection *its_build_movi_cmd(struct its_node *its, @@ -458,7 +474,7 @@ static struct its_collection *its_build_movi_cmd(struct its_node *its, its_fixup_cmd(cmd); - return col; + return valid_col(col); } static struct its_collection *its_build_discard_cmd(struct its_node *its, @@ -476,7 +492,7 @@ static struct its_collection *its_build_discard_cmd(struct its_node *its, its_fixup_cmd(cmd); - return col; + return valid_col(col); } static struct its_collection *its_build_inv_cmd(struct its_node *its, @@ -494,7 +510,7 @@ static struct its_collection *its_build_inv_cmd(struct its_node *its, its_fixup_cmd(cmd); - return col; + return valid_col(col); } static struct its_collection *its_build_int_cmd(struct its_node *its, @@ -512,7 +528,7 @@ static struct its_collection *its_build_int_cmd(struct its_node *its, its_fixup_cmd(cmd); - return col; + return valid_col(col); } static struct its_collection *its_build_clear_cmd(struct its_node *its, @@ -530,7 +546,7 @@ static struct its_collection *its_build_clear_cmd(struct its_node *its, its_fixup_cmd(cmd); - return col; + return valid_col(col); } static struct its_collection *its_build_invall_cmd(struct its_node *its, @@ -554,7 +570,7 @@ static struct its_vpe *its_build_vinvall_cmd(struct its_node *its, its_fixup_cmd(cmd); - return desc->its_vinvall_cmd.vpe; + return valid_vpe(its, desc->its_vinvall_cmd.vpe); } static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, @@ -576,7 +592,7 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, its_fixup_cmd(cmd); - return desc->its_vmapp_cmd.vpe; + return valid_vpe(its, desc->its_vmapp_cmd.vpe); } static struct its_vpe *its_build_vmapti_cmd(struct its_node *its, @@ -599,7 +615,7 @@ static struct its_vpe *its_build_vmapti_cmd(struct its_node *its, its_fixup_cmd(cmd); - return desc->its_vmapti_cmd.vpe; + return valid_vpe(its, desc->its_vmapti_cmd.vpe); } static struct its_vpe *its_build_vmovi_cmd(struct its_node *its, @@ -622,7 +638,7 @@ static struct its_vpe *its_build_vmovi_cmd(struct its_node *its, its_fixup_cmd(cmd); - return desc->its_vmovi_cmd.vpe; + return valid_vpe(its, desc->its_vmovi_cmd.vpe); } static struct its_vpe *its_build_vmovp_cmd(struct its_node *its, @@ -640,7 +656,7 @@ static struct its_vpe *its_build_vmovp_cmd(struct its_node *its, its_fixup_cmd(cmd); - return desc->its_vmovp_cmd.vpe; + return valid_vpe(its, desc->its_vmovp_cmd.vpe); } static u64 its_cmd_ptr_to_offset(struct its_node *its, @@ -1824,11 +1840,16 @@ static int its_alloc_tables(struct its_node *its) static int its_alloc_collections(struct its_node *its) { + int i; + its->collections = kcalloc(nr_cpu_ids, sizeof(*its->collections), GFP_KERNEL); if (!its->collections) return -ENOMEM; + for (i = 0; i < nr_cpu_ids; i++) + its->collections[i].target_address = ~0ULL; + return 0; } @@ -2310,7 +2331,14 @@ static int its_irq_domain_activate(struct irq_domain *domain, cpu_mask = cpumask_of_node(its_dev->its->numa_node); /* Bind the LPI to the first possible CPU */ - cpu = cpumask_first(cpu_mask); + cpu = cpumask_first_and(cpu_mask, cpu_online_mask); + if (cpu >= nr_cpu_ids) { + if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) + return -EINVAL; + + cpu = cpumask_first(cpu_online_mask); + } + its_dev->event_map.col_map[event] = cpu; irq_data_update_effective_affinity(d, cpumask_of(cpu)); @@ -3399,6 +3427,16 @@ static int redist_disable_lpis(void) u64 timeout = USEC_PER_SEC; u64 val; + /* + * If coming via a CPU hotplug event, we don't need to disable + * LPIs before trying to re-enable them. They are already + * configured and all is well in the world. Detect this case + * by checking the allocation of the pending table for the + * current CPU. + */ + if (gic_data_rdist()->pend_page) + return 0; + if (!gic_rdists_supports_plpis()) { pr_info("CPU%d: LPIs not supported\n", smp_processor_id()); return -ENXIO; diff --git a/drivers/irqchip/irq-ls-scfg-msi.c b/drivers/irqchip/irq-ls-scfg-msi.c index 1ec3bfe56693..c671b3212010 100644 --- a/drivers/irqchip/irq-ls-scfg-msi.c +++ b/drivers/irqchip/irq-ls-scfg-msi.c @@ -93,8 +93,12 @@ static void ls_scfg_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) msg->address_lo = lower_32_bits(msi_data->msiir_addr); msg->data = data->hwirq; - if (msi_affinity_flag) - msg->data |= cpumask_first(data->common->affinity); + if (msi_affinity_flag) { + const struct cpumask *mask; + + mask = irq_data_get_effective_affinity_mask(data); + msg->data |= cpumask_first(mask); + } iommu_dma_map_msi_msg(data->irq, msg); } @@ -121,7 +125,7 @@ static int ls_scfg_msi_set_affinity(struct irq_data *irq_data, return -EINVAL; } - cpumask_copy(irq_data->common->affinity, mask); + irq_data_update_effective_affinity(irq_data, cpumask_of(cpu)); return IRQ_SET_MASK_OK; } diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig index 10c08982185a..9c03f35d9df1 100644 --- a/drivers/lightnvm/Kconfig +++ b/drivers/lightnvm/Kconfig @@ -4,7 +4,7 @@ menuconfig NVM bool "Open-Channel SSD target support" - depends on BLOCK && HAS_DMA && PCI + depends on BLOCK && PCI select BLK_DEV_NVME help Say Y here to get to enable Open-channel SSDs. diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index d5c15e8bb3de..f273af136fc7 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -173,7 +173,7 @@ config SUNLANCE config AMD_XGBE tristate "AMD 10GbE Ethernet driver" - depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM && HAS_DMA + depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM depends on X86 || ARM64 || COMPILE_TEST select BITREVERSE select CRC32 diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig index 1205861b6318..eedd3f3dd22e 100644 --- a/drivers/net/ethernet/apm/xgene-v2/Kconfig +++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig @@ -1,6 +1,5 @@ config NET_XGENE_V2 tristate "APM X-Gene SoC Ethernet-v2 Driver" - depends on HAS_DMA depends on ARCH_XGENE || COMPILE_TEST help This is the Ethernet driver for the on-chip ethernet interface diff --git a/drivers/net/ethernet/apm/xgene/Kconfig b/drivers/net/ethernet/apm/xgene/Kconfig index afccb033177b..e4e33c900b57 100644 --- a/drivers/net/ethernet/apm/xgene/Kconfig +++ b/drivers/net/ethernet/apm/xgene/Kconfig @@ -1,6 +1,5 @@ config NET_XGENE tristate "APM X-Gene SoC Ethernet Driver" - depends on HAS_DMA depends on ARCH_XGENE || COMPILE_TEST select PHYLIB select MDIO_XGENE diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig index e743ddf46343..5d0ab8e74b68 100644 --- a/drivers/net/ethernet/arc/Kconfig +++ b/drivers/net/ethernet/arc/Kconfig @@ -24,7 +24,8 @@ config ARC_EMAC_CORE config ARC_EMAC tristate "ARC EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ && OF_NET && HAS_DMA && (ARC || COMPILE_TEST) + depends on OF_IRQ && OF_NET + depends on ARC || COMPILE_TEST ---help--- On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x non-standard on-chip ethernet device ARC EMAC 10/100 is used. @@ -33,7 +34,8 @@ config ARC_EMAC config EMAC_ROCKCHIP tristate "Rockchip EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ && OF_NET && REGULATOR && HAS_DMA && (ARCH_ROCKCHIP || COMPILE_TEST) + depends on OF_IRQ && OF_NET && REGULATOR + depends on ARCH_ROCKCHIP || COMPILE_TEST ---help--- Support for Rockchip RK3036/RK3066/RK3188 EMAC ethernet controllers. This selects Rockchip SoC glue layer support for the diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index af75156919ed..4c3bfde6e8de 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -157,7 +157,6 @@ config BGMAC config BGMAC_BCMA tristate "Broadcom iProc GBit BCMA support" depends on BCMA && BCMA_HOST_SOC - depends on HAS_DMA depends on BCM47XX || ARCH_BCM_5301X || COMPILE_TEST select BGMAC select PHYLIB @@ -170,7 +169,6 @@ config BGMAC_BCMA config BGMAC_PLATFORM tristate "Broadcom iProc GBit platform support" - depends on HAS_DMA depends on ARCH_BCM_IPROC || COMPILE_TEST depends on OF select BGMAC diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 2220c771092b..678835136bf8 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -170,10 +170,7 @@ static int gem_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) if (delta > TSU_NSEC_MAX_VAL) { gem_tsu_get_time(&bp->ptp_clock_info, &now); - if (sign) - now = timespec64_sub(now, then); - else - now = timespec64_add(now, then); + now = timespec64_add(now, then); gem_tsu_set_time(&bp->ptp_clock_info, (const struct timespec64 *)&now); diff --git a/drivers/net/ethernet/calxeda/Kconfig b/drivers/net/ethernet/calxeda/Kconfig index 07d2201530d2..9fdd496b90ff 100644 --- a/drivers/net/ethernet/calxeda/Kconfig +++ b/drivers/net/ethernet/calxeda/Kconfig @@ -1,6 +1,6 @@ config NET_CALXEDA_XGMAC tristate "Calxeda 1G/10G XGMAC Ethernet driver" - depends on HAS_IOMEM && HAS_DMA + depends on HAS_IOMEM depends on ARCH_HIGHBANK || COMPILE_TEST select CRC32 help diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index dd04a2f89ce6..bc03c175a3cd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -263,7 +263,7 @@ static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable) "Can't %s DCB Priority on port %d, TX Queue %d: err=%d\n", enable ? "set" : "unset", pi->port_id, i, -err); else - txq->dcb_prio = value; + txq->dcb_prio = enable ? value : 0; } } diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 8bcf470ff5f3..fb1a7251f45d 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -5,7 +5,7 @@ config NET_VENDOR_HISILICON bool "Hisilicon devices" default y - depends on (OF || ACPI) && HAS_DMA + depends on OF || ACPI depends on ARM || ARM64 || COMPILE_TEST ---help--- If you have a network (Ethernet) card belonging to this class, say Y. diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index cc2f7701e71e..f33fd22b351c 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -18,8 +18,8 @@ if NET_VENDOR_MARVELL config MV643XX_ETH tristate "Marvell Discovery (643XX) and Orion ethernet support" - depends on (MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST) && INET - depends on HAS_DMA + depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST + depends on INET select PHYLIB select MVMDIO ---help--- @@ -58,7 +58,6 @@ config MVNETA_BM_ENABLE config MVNETA tristate "Marvell Armada 370/38x/XP/37xx network interface support" depends on ARCH_MVEBU || COMPILE_TEST - depends on HAS_DMA select MVMDIO select PHYLINK ---help--- @@ -84,7 +83,6 @@ config MVNETA_BM config MVPP2 tristate "Marvell Armada 375/7K/8K network interface support" depends on ARCH_MVEBU || COMPILE_TEST - depends on HAS_DMA select MVMDIO select PHYLINK ---help--- @@ -93,7 +91,7 @@ config MVPP2 config PXA168_ETH tristate "Marvell pxa168 ethernet support" - depends on HAS_IOMEM && HAS_DMA + depends on HAS_IOMEM depends on CPU_PXA168 || ARCH_BERLIN || COMPILE_TEST select PHYLIB ---help--- diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 17a904cc6a5e..0ad2f3f7da85 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1932,7 +1932,7 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo, rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE); index = rx_desc - rxq->descs; data = rxq->buf_virt_addr[index]; - phys_addr = rx_desc->buf_phys_addr; + phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction; if (!mvneta_rxq_desc_is_first_last(rx_status) || (rx_status & MVNETA_RXD_ERR_SUMMARY)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index f4d9c9975ac3..82827a8d3d67 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -30,7 +30,7 @@ config MLXSW_CORE_THERMAL config MLXSW_PCI tristate "PCI bus implementation for Mellanox Technologies Switch ASICs" - depends on PCI && HAS_DMA && HAS_IOMEM && MLXSW_CORE + depends on PCI && HAS_IOMEM && MLXSW_CORE default m ---help--- This is PCI bus implementation for Mellanox Technologies Switch ASICs. diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index fb2c8f8071e6..776a8a9be8e3 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -344,10 +344,9 @@ static int ocelot_port_stop(struct net_device *dev) static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info) { ifh[0] = IFH_INJ_BYPASS; - ifh[1] = (0xff00 & info->port) >> 8; + ifh[1] = (0xf00 & info->port) >> 8; ifh[2] = (0xff & info->port) << 24; - ifh[3] = IFH_INJ_POP_CNT_DISABLE | (info->cpuq << 20) | - (info->tag_type << 16) | info->vid; + ifh[3] = (info->tag_type << 16) | info->vid; return 0; } @@ -370,11 +369,13 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); info.port = BIT(port->chip_port); - info.cpuq = 0xff; + info.tag_type = IFH_TAG_TYPE_C; + info.vid = skb_vlan_tag_get(skb); ocelot_gen_ifh(ifh, &info); for (i = 0; i < IFH_LEN; i++) - ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); + ocelot_write_rix(ocelot, (__force u32)cpu_to_be32(ifh[i]), + QS_INJ_WR, grp); count = (skb->len + 3) / 4; last = skb->len % 4; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 75dfac0248f4..f4cae2be0fda 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7148,7 +7148,7 @@ static void rtl8169_netpoll(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); - rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), dev); + rtl8169_interrupt(pci_irq_vector(tp->pci_dev, 0), tp); } #endif diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index 27be51f0a421..f3f7477043ce 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -17,7 +17,6 @@ if NET_VENDOR_RENESAS config SH_ETH tristate "Renesas SuperH Ethernet support" - depends on HAS_DMA depends on ARCH_RENESAS || SUPERH || COMPILE_TEST select CRC32 select MII @@ -31,7 +30,6 @@ config SH_ETH config RAVB tristate "Renesas Ethernet AVB support" - depends on HAS_DMA depends on ARCH_RENESAS || COMPILE_TEST select CRC32 select MII diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index ad4a354ce570..570ec72266f3 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -3180,6 +3180,7 @@ bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx, return true; } +static struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx, const struct efx_filter_spec *spec) { diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index cdbddf16dd29..4f1267477aa4 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -205,7 +205,7 @@ static void cpdma_desc_pool_destroy(struct cpdma_ctlr *ctlr) * devices (e.g. cpsw switches) use plain old memory. Descriptor pools * abstract out these details */ -int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr) +static int cpdma_desc_pool_create(struct cpdma_ctlr *ctlr) { struct cpdma_params *cpdma_params = &ctlr->params; struct cpdma_desc_pool *pool; diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index a1a6445b5a7e..f270beebb428 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1387,6 +1387,10 @@ static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd) static int match_first_device(struct device *dev, void *data) { + if (dev->parent && dev->parent->of_node) + return of_device_is_compatible(dev->parent->of_node, + "ti,davinci_mdio"); + return !strncmp(dev_name(dev), "davinci_mdio", 12); } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index d02f0a7c534e..23c1d6600241 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -594,7 +594,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan->phy_dev = phy_dev; ipvlan->dev = dev; ipvlan->sfeatures = IPVLAN_FEATURES; - ipvlan_adjust_mtu(ipvlan, phy_dev); + if (!tb[IFLA_MTU]) + ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); spin_lock_init(&ipvlan->addrs_lock); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8e8b51f171f4..8fac8e132c5b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1246,6 +1246,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig index 9d99eb42d917..6acba67bca07 100644 --- a/drivers/net/wireless/broadcom/brcm80211/Kconfig +++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig @@ -60,7 +60,6 @@ config BRCMFMAC_PCIE bool "PCIE bus interface support for FullMAC driver" depends on BRCMFMAC depends on PCI - depends on HAS_DMA select BRCMFMAC_PROTO_MSGBUF select FW_LOADER ---help--- diff --git a/drivers/net/wireless/quantenna/qtnfmac/Kconfig b/drivers/net/wireless/quantenna/qtnfmac/Kconfig index 025fa6018550..8d1492a90bd1 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/Kconfig +++ b/drivers/net/wireless/quantenna/qtnfmac/Kconfig @@ -7,7 +7,7 @@ config QTNFMAC config QTNFMAC_PEARL_PCIE tristate "Quantenna QSR10g PCIe support" default n - depends on HAS_DMA && PCI && CFG80211 + depends on PCI && CFG80211 select QTNFMAC select FW_LOADER select CRC32 diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 922ce0abf5cf..a57daecf1d57 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1810,7 +1810,7 @@ static int talk_to_netback(struct xenbus_device *dev, err = xen_net_read_mac(dev, info->netdev->dev_addr); if (err) { xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename); - goto out; + goto out_unlocked; } rtnl_lock(); @@ -1925,6 +1925,7 @@ abort_transaction_no_dev_fatal: xennet_destroy_queues(info); out: rtnl_unlock(); +out_unlocked: device_unregister(&dev->dev); return err; } @@ -1950,10 +1951,6 @@ static int xennet_connect(struct net_device *dev) /* talk_to_netback() sets the correct number of queues */ num_queues = dev->real_num_tx_queues; - rtnl_lock(); - netdev_update_features(dev); - rtnl_unlock(); - if (dev->reg_state == NETREG_UNINITIALIZED) { err = register_netdev(dev); if (err) { @@ -1963,6 +1960,10 @@ static int xennet_connect(struct net_device *dev) } } + rtnl_lock(); + netdev_update_features(dev); + rtnl_unlock(); + /* * All public and private state should now be sane. Get * ready to start sending and receiving packets and give the driver diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 21710a7460c8..46df030b2c3f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1808,6 +1808,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, u32 max_segments = (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1; + max_segments = min_not_zero(max_segments, ctrl->max_segments); blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b528a2f5826c..41d45a1b5c62 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2790,6 +2790,9 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) /* re-enable the admin_q so anything new can fast fail */ blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); + /* resume the io queues so that things will fast fail */ + nvme_start_queues(&ctrl->ctrl); + nvme_fc_ctlr_inactive_on_rport(ctrl); } @@ -2804,9 +2807,6 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) * waiting for io to terminate */ nvme_fc_delete_association(ctrl); - - /* resume the io queues so that things will fast fail */ - nvme_start_queues(nctrl); } static void diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 231807cbc849..0c4a33df3b2f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -170,6 +170,7 @@ struct nvme_ctrl { u64 cap; u32 page_size; u32 max_hw_sectors; + u32 max_segments; u16 oncs; u16 oacs; u16 nssa; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fc33804662e7..ba943f211687 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -38,6 +38,13 @@ #define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc)) +/* + * These can be higher, but we need to ensure that any command doesn't + * require an sg allocation that needs more than a page of data. + */ +#define NVME_MAX_KB_SZ 4096 +#define NVME_MAX_SEGS 127 + static int use_threaded_interrupts; module_param(use_threaded_interrupts, int, 0); @@ -100,6 +107,8 @@ struct nvme_dev { struct nvme_ctrl ctrl; struct completion ioq_wait; + mempool_t *iod_mempool; + /* shadow doorbell buffer support: */ u32 *dbbuf_dbs; dma_addr_t dbbuf_dbs_dma_addr; @@ -477,10 +486,7 @@ static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev) iod->use_sgl = nvme_pci_use_sgls(dev, rq); if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) { - size_t alloc_size = nvme_pci_iod_alloc_size(dev, size, nseg, - iod->use_sgl); - - iod->sg = kmalloc(alloc_size, GFP_ATOMIC); + iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC); if (!iod->sg) return BLK_STS_RESOURCE; } else { @@ -526,7 +532,7 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req) } if (iod->sg != iod->inline_sg) - kfree(iod->sg); + mempool_free(iod->sg, dev->iod_mempool); } #ifdef CONFIG_BLK_DEV_INTEGRITY @@ -2280,6 +2286,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) blk_put_queue(dev->ctrl.admin_q); kfree(dev->queues); free_opal_dev(dev->ctrl.opal_dev); + mempool_destroy(dev->iod_mempool); kfree(dev); } @@ -2289,6 +2296,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) nvme_get_ctrl(&dev->ctrl); nvme_dev_disable(dev, false); + nvme_kill_queues(&dev->ctrl); if (!queue_work(nvme_wq, &dev->remove_work)) nvme_put_ctrl(&dev->ctrl); } @@ -2333,6 +2341,13 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out; + /* + * Limit the max command size to prevent iod->sg allocations going + * over a single page. + */ + dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1; + dev->ctrl.max_segments = NVME_MAX_SEGS; + result = nvme_init_identify(&dev->ctrl); if (result) goto out; @@ -2405,7 +2420,6 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work) struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work); struct pci_dev *pdev = to_pci_dev(dev->dev); - nvme_kill_queues(&dev->ctrl); if (pci_get_drvdata(pdev)) device_release_driver(&pdev->dev); nvme_put_ctrl(&dev->ctrl); @@ -2509,6 +2523,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) int node, result = -ENOMEM; struct nvme_dev *dev; unsigned long quirks = id->driver_data; + size_t alloc_size; node = dev_to_node(&pdev->dev); if (node == NUMA_NO_NODE) @@ -2546,6 +2561,23 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (result) goto release_pools; + /* + * Double check that our mempool alloc size will cover the biggest + * command we support. + */ + alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ, + NVME_MAX_SEGS, true); + WARN_ON_ONCE(alloc_size > PAGE_SIZE); + + dev->iod_mempool = mempool_create_node(1, mempool_kmalloc, + mempool_kfree, + (void *) alloc_size, + GFP_KERNEL, node); + if (!dev->iod_mempool) { + result = -ENOMEM; + goto release_pools; + } + dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); nvme_get_ctrl(&dev->ctrl); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index c9424da0d23e..9544625c0b7d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -560,12 +560,6 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) return; - if (nvme_rdma_queue_idx(queue) == 0) { - nvme_rdma_free_qe(queue->device->dev, - &queue->ctrl->async_event_sqe, - sizeof(struct nvme_command), DMA_TO_DEVICE); - } - nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); } @@ -698,7 +692,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, set = &ctrl->tag_set; memset(set, 0, sizeof(*set)); set->ops = &nvme_rdma_mq_ops; - set->queue_depth = nctrl->opts->queue_size; + set->queue_depth = nctrl->sqsize + 1; set->reserved_tags = 1; /* fabric connect */ set->numa_node = NUMA_NO_NODE; set->flags = BLK_MQ_F_SHOULD_MERGE; @@ -734,11 +728,12 @@ out: static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl, bool remove) { - nvme_rdma_stop_queue(&ctrl->queues[0]); if (remove) { blk_cleanup_queue(ctrl->ctrl.admin_q); nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset); } + nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, + sizeof(struct nvme_command), DMA_TO_DEVICE); nvme_rdma_free_queue(&ctrl->queues[0]); } @@ -755,11 +750,16 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev); + error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe, + sizeof(struct nvme_command), DMA_TO_DEVICE); + if (error) + goto out_free_queue; + if (new) { ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true); if (IS_ERR(ctrl->ctrl.admin_tagset)) { error = PTR_ERR(ctrl->ctrl.admin_tagset); - goto out_free_queue; + goto out_free_async_qe; } ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); @@ -795,12 +795,6 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, if (error) goto out_stop_queue; - error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev, - &ctrl->async_event_sqe, sizeof(struct nvme_command), - DMA_TO_DEVICE); - if (error) - goto out_stop_queue; - return 0; out_stop_queue: @@ -811,6 +805,9 @@ out_cleanup_queue: out_free_tagset: if (new) nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset); +out_free_async_qe: + nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, + sizeof(struct nvme_command), DMA_TO_DEVICE); out_free_queue: nvme_rdma_free_queue(&ctrl->queues[0]); return error; @@ -819,7 +816,6 @@ out_free_queue: static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl, bool remove) { - nvme_rdma_stop_io_queues(ctrl); if (remove) { blk_cleanup_queue(ctrl->ctrl.connect_q); nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset); @@ -888,9 +884,9 @@ static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) list_del(&ctrl->list); mutex_unlock(&nvme_rdma_ctrl_mutex); - kfree(ctrl->queues); nvmf_free_options(nctrl->opts); free_ctrl: + kfree(ctrl->queues); kfree(ctrl); } @@ -949,6 +945,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) return; destroy_admin: + nvme_rdma_stop_queue(&ctrl->queues[0]); nvme_rdma_destroy_admin_queue(ctrl, false); requeue: dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n", @@ -965,12 +962,14 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); + nvme_rdma_stop_io_queues(ctrl); blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request, &ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, false); } blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + nvme_rdma_stop_queue(&ctrl->queues[0]); blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request, &ctrl->ctrl); nvme_rdma_destroy_admin_queue(ctrl, false); @@ -1736,6 +1735,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) { if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); + nvme_rdma_stop_io_queues(ctrl); blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request, &ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, shutdown); @@ -1747,6 +1747,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + nvme_rdma_stop_queue(&ctrl->queues[0]); blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request, &ctrl->ctrl); blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); @@ -1932,11 +1933,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, goto out_free_ctrl; } - ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops, - 0 /* no quirks, we're perfect! */); - if (ret) - goto out_free_ctrl; - INIT_DELAYED_WORK(&ctrl->reconnect_work, nvme_rdma_reconnect_ctrl_work); INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work); @@ -1950,14 +1946,19 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues), GFP_KERNEL); if (!ctrl->queues) - goto out_uninit_ctrl; + goto out_free_ctrl; + + ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops, + 0 /* no quirks, we're perfect! */); + if (ret) + goto out_kfree_queues; changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING); WARN_ON_ONCE(!changed); ret = nvme_rdma_configure_admin_queue(ctrl, true); if (ret) - goto out_kfree_queues; + goto out_uninit_ctrl; /* sanity check icdoff */ if (ctrl->ctrl.icdoff) { @@ -1974,20 +1975,19 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, goto out_remove_admin_queue; } - if (opts->queue_size > ctrl->ctrl.maxcmd) { - /* warn if maxcmd is lower than queue_size */ - dev_warn(ctrl->ctrl.device, - "queue_size %zu > ctrl maxcmd %u, clamping down\n", - opts->queue_size, ctrl->ctrl.maxcmd); - opts->queue_size = ctrl->ctrl.maxcmd; - } - + /* only warn if argument is too large here, will clamp later */ if (opts->queue_size > ctrl->ctrl.sqsize + 1) { - /* warn if sqsize is lower than queue_size */ dev_warn(ctrl->ctrl.device, "queue_size %zu > ctrl sqsize %u, clamping down\n", opts->queue_size, ctrl->ctrl.sqsize + 1); - opts->queue_size = ctrl->ctrl.sqsize + 1; + } + + /* warn if maxcmd is lower than sqsize+1 */ + if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) { + dev_warn(ctrl->ctrl.device, + "sqsize %u > ctrl maxcmd %u, clamping down\n", + ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd); + ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1; } if (opts->nr_io_queues) { @@ -2013,15 +2013,16 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, return &ctrl->ctrl; out_remove_admin_queue: + nvme_rdma_stop_queue(&ctrl->queues[0]); nvme_rdma_destroy_admin_queue(ctrl, true); -out_kfree_queues: - kfree(ctrl->queues); out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); if (ret > 0) ret = -EIO; return ERR_PTR(ret); +out_kfree_queues: + kfree(ctrl->queues); out_free_ctrl: kfree(ctrl); return ERR_PTR(ret); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index a03da764ecae..74d4b785d2da 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -686,6 +686,14 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) } ctrl->csts = NVME_CSTS_RDY; + + /* + * Controllers that are not yet enabled should not really enforce the + * keep alive timeout, but we still want to track a timeout and cleanup + * in case a host died before it enabled the controller. Hence, simply + * reset the keep alive timer when the controller is enabled. + */ + mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ); } static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl) diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index 1da3d71e9f61..13948102ca29 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -3592,7 +3592,7 @@ fc_bsg_job_timeout(struct request *req) /* the blk_end_sync_io() doesn't check the error */ if (inflight) - blk_mq_complete_request(req); + __blk_complete_request(req); return BLK_EH_DONE; } diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 36f59a1be7e9..61389bdc7926 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -654,10 +654,17 @@ static int scsifront_dev_reset_handler(struct scsi_cmnd *sc) static int scsifront_sdev_configure(struct scsi_device *sdev) { struct vscsifrnt_info *info = shost_priv(sdev->host); + int err; - if (info && current == info->curr) - xenbus_printf(XBT_NIL, info->dev->nodename, + if (info && current == info->curr) { + err = xenbus_printf(XBT_NIL, info->dev->nodename, info->dev_state_path, "%d", XenbusStateConnected); + if (err) { + xenbus_dev_error(info->dev, err, + "%s: writing dev_state_path", __func__); + return err; + } + } return 0; } @@ -665,10 +672,15 @@ static int scsifront_sdev_configure(struct scsi_device *sdev) static void scsifront_sdev_destroy(struct scsi_device *sdev) { struct vscsifrnt_info *info = shost_priv(sdev->host); + int err; - if (info && current == info->curr) - xenbus_printf(XBT_NIL, info->dev->nodename, + if (info && current == info->curr) { + err = xenbus_printf(XBT_NIL, info->dev->nodename, info->dev_state_path, "%d", XenbusStateClosed); + if (err) + xenbus_dev_error(info->dev, err, + "%s: writing dev_state_path", __func__); + } } static struct scsi_host_template scsifront_sht = { @@ -1003,9 +1015,12 @@ static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op) if (scsi_add_device(info->host, chn, tgt, lun)) { dev_err(&dev->dev, "scsi_add_device\n"); - xenbus_printf(XBT_NIL, dev->nodename, + err = xenbus_printf(XBT_NIL, dev->nodename, info->dev_state_path, "%d", XenbusStateClosed); + if (err) + xenbus_dev_error(dev, err, + "%s: writing dev_state_path", __func__); } break; case VSCSIFRONT_OP_DEL_LUN: @@ -1019,10 +1034,14 @@ static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op) } break; case VSCSIFRONT_OP_READD_LUN: - if (device_state == XenbusStateConnected) - xenbus_printf(XBT_NIL, dev->nodename, + if (device_state == XenbusStateConnected) { + err = xenbus_printf(XBT_NIL, dev->nodename, info->dev_state_path, "%d", XenbusStateConnected); + if (err) + xenbus_dev_error(dev, err, + "%s: writing dev_state_path", __func__); + } break; default: break; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 686dc670fd29..29756d88799b 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1226,7 +1226,8 @@ err_used: if (ubufs) vhost_net_ubuf_put_wait_and_free(ubufs); err_ubufs: - sockfd_put(sock); + if (sock) + sockfd_put(sock); err_vq: mutex_unlock(&vq->mutex); err: diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 451e833f5931..48b154276179 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -41,4 +41,4 @@ obj-$(CONFIG_XEN_PVCALLS_FRONTEND) += pvcalls-front.o xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o xen-gntalloc-y := gntalloc.o -xen-privcmd-y := privcmd.o +xen-privcmd-y := privcmd.o privcmd-buf.o diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 762378f1811c..08e4af04d6f2 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -628,8 +628,6 @@ static void __unbind_from_irq(unsigned int irq) xen_irq_info_cleanup(info); } - BUG_ON(info_for_irq(irq)->type == IRQT_UNBOUND); - xen_free_irq(irq); } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 2473b0a9e6e4..ba9f3eec2bd0 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -799,7 +799,7 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages) return 0; } -EXPORT_SYMBOL(gnttab_alloc_pages); +EXPORT_SYMBOL_GPL(gnttab_alloc_pages); /** * gnttab_free_pages - free pages allocated by gnttab_alloc_pages() @@ -820,7 +820,7 @@ void gnttab_free_pages(int nr_pages, struct page **pages) } free_xenballooned_pages(nr_pages, pages); } -EXPORT_SYMBOL(gnttab_free_pages); +EXPORT_SYMBOL_GPL(gnttab_free_pages); /* Handling of paged out grant targets (GNTST_eagain) */ #define MAX_DELAY 256 diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 8835065029d3..c93d8ef8df34 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -289,8 +289,15 @@ static void sysrq_handler(struct xenbus_watch *watch, const char *path, return; } - if (sysrq_key != '\0') - xenbus_printf(xbt, "control", "sysrq", "%c", '\0'); + if (sysrq_key != '\0') { + err = xenbus_printf(xbt, "control", "sysrq", "%c", '\0'); + if (err) { + pr_err("%s: Error %d writing sysrq in control/sysrq\n", + __func__, err); + xenbus_transaction_end(xbt, 1); + return; + } + } err = xenbus_transaction_end(xbt, 0); if (err == -EAGAIN) @@ -342,7 +349,12 @@ static int setup_shutdown_watcher(void) continue; snprintf(node, FEATURE_PATH_SIZE, "feature-%s", shutdown_handlers[idx].command); - xenbus_printf(XBT_NIL, "control", node, "%u", 1); + err = xenbus_printf(XBT_NIL, "control", node, "%u", 1); + if (err) { + pr_err("%s: Error %d writing %s\n", __func__, + err, node); + return err; + } } return 0; diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c new file mode 100644 index 000000000000..df1ed37c3269 --- /dev/null +++ b/drivers/xen/privcmd-buf.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +/****************************************************************************** + * privcmd-buf.c + * + * Mmap of hypercall buffers. + * + * Copyright (c) 2018 Juergen Gross + */ + +#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/miscdevice.h> +#include <linux/mm.h> +#include <linux/slab.h> + +#include "privcmd.h" + +MODULE_LICENSE("GPL"); + +static unsigned int limit = 64; +module_param(limit, uint, 0644); +MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by " + "the privcmd-buf device per open file"); + +struct privcmd_buf_private { + struct mutex lock; + struct list_head list; + unsigned int allocated; +}; + +struct privcmd_buf_vma_private { + struct privcmd_buf_private *file_priv; + struct list_head list; + unsigned int users; + unsigned int n_pages; + struct page *pages[]; +}; + +static int privcmd_buf_open(struct inode *ino, struct file *file) +{ + struct privcmd_buf_private *file_priv; + + file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL); + if (!file_priv) + return -ENOMEM; + + mutex_init(&file_priv->lock); + INIT_LIST_HEAD(&file_priv->list); + + file->private_data = file_priv; + + return 0; +} + +static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv) +{ + unsigned int i; + + vma_priv->file_priv->allocated -= vma_priv->n_pages; + + list_del(&vma_priv->list); + + for (i = 0; i < vma_priv->n_pages; i++) + if (vma_priv->pages[i]) + __free_page(vma_priv->pages[i]); + + kfree(vma_priv); +} + +static int privcmd_buf_release(struct inode *ino, struct file *file) +{ + struct privcmd_buf_private *file_priv = file->private_data; + struct privcmd_buf_vma_private *vma_priv; + + mutex_lock(&file_priv->lock); + + while (!list_empty(&file_priv->list)) { + vma_priv = list_first_entry(&file_priv->list, + struct privcmd_buf_vma_private, + list); + privcmd_buf_vmapriv_free(vma_priv); + } + + mutex_unlock(&file_priv->lock); + + kfree(file_priv); + + return 0; +} + +static void privcmd_buf_vma_open(struct vm_area_struct *vma) +{ + struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data; + + if (!vma_priv) + return; + + mutex_lock(&vma_priv->file_priv->lock); + vma_priv->users++; + mutex_unlock(&vma_priv->file_priv->lock); +} + +static void privcmd_buf_vma_close(struct vm_area_struct *vma) +{ + struct privcmd_buf_vma_private *vma_priv = vma->vm_private_data; + struct privcmd_buf_private *file_priv; + + if (!vma_priv) + return; + + file_priv = vma_priv->file_priv; + + mutex_lock(&file_priv->lock); + + vma_priv->users--; + if (!vma_priv->users) + privcmd_buf_vmapriv_free(vma_priv); + + mutex_unlock(&file_priv->lock); +} + +static vm_fault_t privcmd_buf_vma_fault(struct vm_fault *vmf) +{ + pr_debug("fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n", + vmf->vma, vmf->vma->vm_start, vmf->vma->vm_end, + vmf->pgoff, (void *)vmf->address); + + return VM_FAULT_SIGBUS; +} + +static const struct vm_operations_struct privcmd_buf_vm_ops = { + .open = privcmd_buf_vma_open, + .close = privcmd_buf_vma_close, + .fault = privcmd_buf_vma_fault, +}; + +static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct privcmd_buf_private *file_priv = file->private_data; + struct privcmd_buf_vma_private *vma_priv; + unsigned long count = vma_pages(vma); + unsigned int i; + int ret = 0; + + if (!(vma->vm_flags & VM_SHARED) || count > limit || + file_priv->allocated + count > limit) + return -EINVAL; + + vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *), + GFP_KERNEL); + if (!vma_priv) + return -ENOMEM; + + vma_priv->n_pages = count; + count = 0; + for (i = 0; i < vma_priv->n_pages; i++) { + vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!vma_priv->pages[i]) + break; + count++; + } + + mutex_lock(&file_priv->lock); + + file_priv->allocated += count; + + vma_priv->file_priv = file_priv; + vma_priv->users = 1; + + vma->vm_flags |= VM_IO | VM_DONTEXPAND; + vma->vm_ops = &privcmd_buf_vm_ops; + vma->vm_private_data = vma_priv; + + list_add(&vma_priv->list, &file_priv->list); + + if (vma_priv->n_pages != count) + ret = -ENOMEM; + else + for (i = 0; i < vma_priv->n_pages; i++) { + ret = vm_insert_page(vma, vma->vm_start + i * PAGE_SIZE, + vma_priv->pages[i]); + if (ret) + break; + } + + if (ret) + privcmd_buf_vmapriv_free(vma_priv); + + mutex_unlock(&file_priv->lock); + + return ret; +} + +const struct file_operations xen_privcmdbuf_fops = { + .owner = THIS_MODULE, + .open = privcmd_buf_open, + .release = privcmd_buf_release, + .mmap = privcmd_buf_mmap, +}; +EXPORT_SYMBOL_GPL(xen_privcmdbuf_fops); + +struct miscdevice xen_privcmdbuf_dev = { + .minor = MISC_DYNAMIC_MINOR, + .name = "xen/hypercall", + .fops = &xen_privcmdbuf_fops, +}; diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 8ae0349d9f0a..7e6e682104dc 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -1007,12 +1007,21 @@ static int __init privcmd_init(void) pr_err("Could not register Xen privcmd device\n"); return err; } + + err = misc_register(&xen_privcmdbuf_dev); + if (err != 0) { + pr_err("Could not register Xen hypercall-buf device\n"); + misc_deregister(&privcmd_dev); + return err; + } + return 0; } static void __exit privcmd_exit(void) { misc_deregister(&privcmd_dev); + misc_deregister(&xen_privcmdbuf_dev); } module_init(privcmd_init); diff --git a/drivers/xen/privcmd.h b/drivers/xen/privcmd.h index 14facaeed36f..0dd9f8f67ee3 100644 --- a/drivers/xen/privcmd.h +++ b/drivers/xen/privcmd.h @@ -1,3 +1,6 @@ #include <linux/fs.h> extern const struct file_operations xen_privcmd_fops; +extern const struct file_operations xen_privcmdbuf_fops; + +extern struct miscdevice xen_privcmdbuf_dev; diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 7bc88fd43cfc..e2f3e8b0fba9 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1012,6 +1012,7 @@ static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, { struct v2p_entry *entry; unsigned long flags; + int err; if (try) { spin_lock_irqsave(&info->v2p_lock, flags); @@ -1027,8 +1028,11 @@ static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, scsiback_del_translation_entry(info, vir); } } else if (!try) { - xenbus_printf(XBT_NIL, info->dev->nodename, state, + err = xenbus_printf(XBT_NIL, info->dev->nodename, state, "%d", XenbusStateClosed); + if (err) + xenbus_dev_error(info->dev, err, + "%s: writing %s", __func__, state); } } @@ -1067,8 +1071,11 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op, snprintf(str, sizeof(str), "vscsi-devs/%s/p-dev", ent); val = xenbus_read(XBT_NIL, dev->nodename, str, NULL); if (IS_ERR(val)) { - xenbus_printf(XBT_NIL, dev->nodename, state, + err = xenbus_printf(XBT_NIL, dev->nodename, state, "%d", XenbusStateClosed); + if (err) + xenbus_dev_error(info->dev, err, + "%s: writing %s", __func__, state); return; } strlcpy(phy, val, VSCSI_NAMELEN); @@ -1079,8 +1086,11 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op, err = xenbus_scanf(XBT_NIL, dev->nodename, str, "%u:%u:%u:%u", &vir.hst, &vir.chn, &vir.tgt, &vir.lun); if (XENBUS_EXIST_ERR(err)) { - xenbus_printf(XBT_NIL, dev->nodename, state, + err = xenbus_printf(XBT_NIL, dev->nodename, state, "%d", XenbusStateClosed); + if (err) + xenbus_dev_error(info->dev, err, + "%s: writing %s", __func__, state); return; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index cce6087d6880..e55843f536bc 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4542,8 +4542,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, offset_in_extent = em_start - em->start; em_end = extent_map_end(em); em_len = em_end - em_start; - disko = em->block_start + offset_in_extent; flags = 0; + if (em->block_start < EXTENT_MAP_LAST_BYTE) + disko = em->block_start + offset_in_extent; + else + disko = 0; /* * bump off for our next call to get_extent diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e9482f0db9d0..be98dfc8d0f8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9443,6 +9443,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, u64 new_idx = 0; u64 root_objectid; int ret; + int ret2; bool root_log_pinned = false; bool dest_log_pinned = false; @@ -9639,7 +9640,8 @@ out_fail: dest_log_pinned = false; } } - ret = btrfs_end_transaction(trans); + ret2 = btrfs_end_transaction(trans); + ret = ret ? ret : ret2; out_notrans: if (new_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c2837a32d689..43ecbe620dea 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3577,7 +3577,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN, dst, dst_loff, &cmp); if (ret) - goto out_unlock; + goto out_free; loff += BTRFS_MAX_DEDUPE_LEN; dst_loff += BTRFS_MAX_DEDUPE_LEN; @@ -3587,16 +3587,16 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, ret = btrfs_extent_same_range(src, loff, tail_len, dst, dst_loff, &cmp); +out_free: + kvfree(cmp.src_pages); + kvfree(cmp.dst_pages); + out_unlock: if (same_inode) inode_unlock(src); else btrfs_double_inode_unlock(src, dst); -out_free: - kvfree(cmp.src_pages); - kvfree(cmp.dst_pages); - return ret; } diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h index 0763f065b975..d10f1e7d6ba8 100644 --- a/include/asm-generic/qspinlock_types.h +++ b/include/asm-generic/qspinlock_types.h @@ -63,7 +63,7 @@ typedef struct qspinlock { /* * Initializier */ -#define __ARCH_SPIN_LOCK_UNLOCKED { .val = ATOMIC_INIT(0) } +#define __ARCH_SPIN_LOCK_UNLOCKED { { .val = ATOMIC_INIT(0) } } /* * Bitfields in the atomic value: diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 0bd432a4d7bd..24251762c20c 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -22,7 +22,6 @@ struct dentry; */ enum wb_state { WB_registered, /* bdi_register() was done */ - WB_shutting_down, /* wb_shutdown() in progress */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ @@ -189,6 +188,7 @@ struct backing_dev_info { #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ + struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ #else struct bdi_writeback_congested *wb_congested; #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index b615df57b7d5..20f2659dd829 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -472,7 +472,9 @@ struct sock_fprog_kern { struct bpf_binary_header { u16 pages; u16 locked:1; - u8 image[]; + + /* Some arches need word alignment for their instructions */ + u8 image[] __aligned(4); }; struct bpf_prog { diff --git a/include/linux/irq.h b/include/linux/irq.h index 4bd2f34947f4..201de12a9957 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -503,6 +503,7 @@ struct irq_chip { * IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip * IRQCHIP_ONESHOT_SAFE: One shot does not require mask/unmask * IRQCHIP_EOI_THREADED: Chip requires eoi() on unmask in threaded mode + * IRQCHIP_SUPPORTS_LEVEL_MSI Chip can provide two doorbells for Level MSIs */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 25b33b664537..dd1e40ddac7d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -145,11 +145,6 @@ static inline void *irq_desc_get_handler_data(struct irq_desc *desc) return desc->irq_common_data.handler_data; } -static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) -{ - return desc->irq_common_data.msi_desc; -} - /* * Architectures call this to let the generic IRQ layer * handle an interrupt. diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d23123238534..941dc0a5a877 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -666,7 +666,7 @@ do { \ * your code. (Extra memory is used for special buffers that are * allocated when trace_printk() is used.) * - * A little optization trick is done here. If there's only one + * A little optimization trick is done here. If there's only one * argument, there's no need to scan the string for printf formats. * The trace_puts() will suffice. But how can we take advantage of * using trace_puts() when trace_printk() has only one argument? diff --git a/include/linux/memory.h b/include/linux/memory.h index 31ca3e28b0eb..a6ddefc60517 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -38,6 +38,7 @@ struct memory_block { int arch_get_memory_phys_device(unsigned long start_pfn); unsigned long memory_block_size_bytes(void); +int set_memory_block_size_order(unsigned int order); /* These states are exposed to userspace as text strings in sysfs */ #define MEM_ONLINE (1<<0) /* exposed to userspace */ diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 4193c41e383a..a685da2c4522 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -98,5 +98,7 @@ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); - +extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, + spinlock_t *lock, + unsigned long *flags); #endif /* _LINUX_REFCOUNT_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 87bf02d93a27..9256118bd40c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1799,20 +1799,22 @@ static inline void rseq_set_notify_resume(struct task_struct *t) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } -void __rseq_handle_notify_resume(struct pt_regs *regs); +void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); -static inline void rseq_handle_notify_resume(struct pt_regs *regs) +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) { if (current->rseq) - __rseq_handle_notify_resume(regs); + __rseq_handle_notify_resume(ksig, regs); } -static inline void rseq_signal_deliver(struct pt_regs *regs) +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ @@ -1831,9 +1833,7 @@ static inline void rseq_migrate(struct task_struct *t) /* * If parent process has a registered restartable sequences area, the - * child inherits. Only applies when forking a process, not a thread. In - * case a parent fork() in the middle of a restartable sequence, set the - * resume notifier to force the child to retry. + * child inherits. Only applies when forking a process, not a thread. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { @@ -1847,7 +1847,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; - rseq_preempt(t); } } @@ -1864,10 +1863,12 @@ static inline void rseq_execve(struct task_struct *t) static inline void rseq_set_notify_resume(struct task_struct *t) { } -static inline void rseq_handle_notify_resume(struct pt_regs *regs) +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) { } -static inline void rseq_signal_deliver(struct pt_regs *regs) +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1e8a46435838..fd57888d4942 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -427,6 +427,11 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) +extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, + unsigned long *flags); +#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ + __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) + int alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp); diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h index 85a3fb65e40a..20d6cc91435d 100644 --- a/include/uapi/linux/nbd.h +++ b/include/uapi/linux/nbd.h @@ -53,6 +53,9 @@ enum { /* These are client behavior specific flags. */ #define NBD_CFLAG_DESTROY_ON_DISCONNECT (1 << 0) /* delete the nbd device on disconnect. */ +#define NBD_CFLAG_DISCONNECT_ON_CLOSE (1 << 1) /* disconnect the nbd device on + * close by last opener. + */ /* userspace doesn't need the nbd_device structure */ diff --git a/include/xen/xen.h b/include/xen/xen.h index 9d4340c907d1..1e1d9bd0bd37 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -25,12 +25,16 @@ extern bool xen_pvh; #define xen_hvm_domain() (xen_domain_type == XEN_HVM_DOMAIN) #define xen_pvh_domain() (xen_pvh) +#include <linux/types.h> + +extern uint32_t xen_start_flags; + #ifdef CONFIG_XEN_DOM0 #include <xen/interface/xen.h> #include <asm/xen/hypervisor.h> #define xen_initial_domain() (xen_domain() && \ - xen_start_info && xen_start_info->flags & SIF_INITDOMAIN) + (xen_start_flags & SIF_INITDOMAIN)) #else /* !CONFIG_XEN_DOM0 */ #define xen_initial_domain() (0) #endif /* CONFIG_XEN_DOM0 */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 045a37e9ddee..5d3cf407e374 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -103,7 +103,7 @@ out: preempt_enable(); } -static bool __always_inline +static __always_inline bool ring_buffer_has_space(unsigned long head, unsigned long tail, unsigned long data_size, unsigned int size, bool backward) @@ -114,7 +114,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail, return CIRC_SPACE(tail, head, data_size) >= size; } -static int __always_inline +static __always_inline int __perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size, bool backward) @@ -414,7 +414,7 @@ err: } EXPORT_SYMBOL_GPL(perf_aux_output_begin); -static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +static __always_inline bool rb_need_aux_wakeup(struct ring_buffer *rb) { if (rb->aux_overwrite) return false; diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 4dadeb3d6666..6f636136cccc 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -55,6 +55,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE), BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE), BIT_MASK_DESCR(IRQCHIP_EOI_THREADED), + BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI), }; static void diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index edcac5de7ebc..5fa4d3138bf1 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1265,11 +1265,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class) this.parent = NULL; this.class = class; - local_irq_save(flags); + raw_local_irq_save(flags); arch_spin_lock(&lockdep_lock); ret = __lockdep_count_forward_deps(&this); arch_spin_unlock(&lockdep_lock); - local_irq_restore(flags); + raw_local_irq_restore(flags); return ret; } @@ -1292,11 +1292,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class) this.parent = NULL; this.class = class; - local_irq_save(flags); + raw_local_irq_save(flags); arch_spin_lock(&lockdep_lock); ret = __lockdep_count_backward_deps(&this); arch_spin_unlock(&lockdep_lock); - local_irq_restore(flags); + raw_local_irq_restore(flags); return ret; } @@ -4411,7 +4411,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) if (unlikely(!debug_locks)) return; - local_irq_save(flags); + raw_local_irq_save(flags); for (i = 0; i < curr->lockdep_depth; i++) { hlock = curr->held_locks + i; @@ -4422,7 +4422,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock); break; } - local_irq_restore(flags); + raw_local_irq_restore(flags); } EXPORT_SYMBOL_GPL(debug_check_no_locks_freed); diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index bc1e507be9ff..776308d2fa9e 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -181,6 +181,7 @@ void down_read_non_owner(struct rw_semaphore *sem) might_sleep(); __down_read(sem); + rwsem_set_reader_owned(sem); } EXPORT_SYMBOL(down_read_non_owner); diff --git a/kernel/rseq.c b/kernel/rseq.c index ae306f90c514..22b6acf1ad63 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -251,10 +251,10 @@ static int rseq_ip_fixup(struct pt_regs *regs) * respect to other threads scheduled on the same CPU, and with respect * to signal handlers. */ -void __rseq_handle_notify_resume(struct pt_regs *regs) +void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { struct task_struct *t = current; - int ret; + int ret, sig; if (unlikely(t->flags & PF_EXITING)) return; @@ -268,7 +268,8 @@ void __rseq_handle_notify_resume(struct pt_regs *regs) return; error: - force_sig(SIGSEGV, t); + sig = ksig ? ksig->sig : 0; + force_sigsegv(sig, t); } #ifdef CONFIG_DEBUG_RSEQ diff --git a/kernel/softirq.c b/kernel/softirq.c index de2f57fddc04..900dcfee542c 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -139,9 +139,13 @@ static void __local_bh_enable(unsigned int cnt) { lockdep_assert_irqs_disabled(); + if (preempt_count() == cnt) + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); + if (softirq_count() == (cnt & SOFTIRQ_MASK)) trace_softirqs_on(_RET_IP_); - preempt_count_sub(cnt); + + __preempt_count_sub(cnt); } /* diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 055a4a728c00..3e93c54bd3a1 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1659,7 +1659,7 @@ EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 5a6251ac6f7a..9cdf54b04ca8 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -604,7 +604,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, /* * Disarm any old timer after extracting its expiry time. */ - lockdep_assert_irqs_disabled(); ret = 0; old_incr = timer->it.cpu.incr; @@ -1049,7 +1048,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer) /* * Now re-arm for the new expiry time. */ - lockdep_assert_irqs_disabled(); arm_timer(timer); unlock: unlock_task_sighand(p, &flags); diff --git a/kernel/time/time.c b/kernel/time/time.c index 6fa99213fc72..2b41e8e2d31d 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -28,6 +28,7 @@ */ #include <linux/export.h> +#include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> @@ -314,9 +315,10 @@ unsigned int jiffies_to_msecs(const unsigned long j) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 - return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32; + return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> + HZ_TO_MSEC_SHR32; # else - return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN; + return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c9336e98ac59..a0079b4c7a49 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1360,8 +1360,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct ring_buffer *buf; - if (tr->stop_count) return; @@ -1375,9 +1373,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); - buf = tr->trace_buffer.buffer; - tr->trace_buffer.buffer = tr->max_buffer.buffer; - tr->max_buffer.buffer = buf; + swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index e1c818dbc0d7..0dceb77d1d42 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -78,7 +78,8 @@ static const char * ops[] = { OPS }; C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \ C(INVALID_FILTER, "Meaningless filter expression"), \ C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \ - C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), + C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \ + C(NO_FILTER, "No filter found"), #undef C #define C(a, b) FILT_ERR_##a @@ -550,6 +551,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, goto out_free; } + if (!N) { + /* No program? */ + ret = -EINVAL; + parse_error(pe, FILT_ERR_NO_FILTER, ptr - str); + goto out_free; + } + prog[N].pred = NULL; /* #13 */ prog[N].target = 1; /* TRUE */ prog[N+1].pred = NULL; diff --git a/lib/Makefile b/lib/Makefile index 8153fdab287f..90dc5520b784 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -23,7 +23,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ sha1.o chacha20.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ - earlycpio.o seq_buf.o siphash.o \ + earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ nmi_backtrace.o nodemask.o win_minmax.o lib-$(CONFIG_PRINTK) += dump_stack.o @@ -95,10 +95,6 @@ obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o obj-$(CONFIG_DEBUG_LIST) += list_debug.o obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o -ifneq ($(CONFIG_HAVE_DEC_LOCK),y) - lib-y += dec_and_lock.o -endif - obj-$(CONFIG_BITREVERSE) += bitrev.o obj-$(CONFIG_RATIONAL) += rational.o obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c index 347fa7ac2e8a..9555b68bb774 100644 --- a/lib/dec_and_lock.c +++ b/lib/dec_and_lock.c @@ -33,3 +33,19 @@ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) } EXPORT_SYMBOL(_atomic_dec_and_lock); + +int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, + unsigned long *flags) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + spin_lock_irqsave(lock, *flags); + if (atomic_dec_and_test(atomic)) + return 1; + spin_unlock_irqrestore(lock, *flags); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); diff --git a/lib/refcount.c b/lib/refcount.c index 0eb48353abe3..d3b81cefce91 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -350,3 +350,31 @@ bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) } EXPORT_SYMBOL(refcount_dec_and_lock); +/** + * refcount_dec_and_lock_irqsave - return holding spinlock with disabled + * interrupts if able to decrement refcount to 0 + * @r: the refcount + * @lock: the spinlock to be locked + * @flags: saved IRQ-flags if the is acquired + * + * Same as refcount_dec_and_lock() above except that the spinlock is acquired + * with disabled interupts. + * + * Return: true and hold spinlock if able to decrement refcount to 0, false + * otherwise + */ +bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, + unsigned long *flags) +{ + if (refcount_dec_not_one(r)) + return false; + + spin_lock_irqsave(lock, *flags); + if (!refcount_dec_and_test(r)) { + spin_unlock_irqrestore(lock, *flags); + return false; + } + + return true; +} +EXPORT_SYMBOL(refcount_dec_and_lock_irqsave); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 347cc834c04a..2e5d3df0853d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -359,15 +359,8 @@ static void wb_shutdown(struct bdi_writeback *wb) spin_lock_bh(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_bh(&wb->work_lock); - /* - * Wait for wb shutdown to finish if someone else is just - * running wb_shutdown(). Otherwise we could proceed to wb / - * bdi destruction before wb_shutdown() is finished. - */ - wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE); return; } - set_bit(WB_shutting_down, &wb->state); spin_unlock_bh(&wb->work_lock); cgwb_remove_from_bdi_list(wb); @@ -379,12 +372,6 @@ static void wb_shutdown(struct bdi_writeback *wb) mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); - /* - * Make sure bit gets cleared after shutdown is finished. Matches with - * the barrier provided by test_and_clear_bit() above. - */ - smp_wmb(); - clear_and_wake_up_bit(WB_shutting_down, &wb->state); } static void wb_exit(struct bdi_writeback *wb) @@ -508,10 +495,12 @@ static void cgwb_release_workfn(struct work_struct *work) struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); + mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); + mutex_unlock(&wb->bdi->cgwb_release_mutex); fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); @@ -697,6 +686,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; + mutex_init(&bdi->cgwb_release_mutex); ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { @@ -717,7 +707,10 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); + spin_unlock_irq(&cgwb_lock); + mutex_lock(&bdi->cgwb_release_mutex); + spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); @@ -726,6 +719,7 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); + mutex_unlock(&bdi->cgwb_release_mutex); } /** diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index dd86b022eff0..051dc18b8ccb 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -22,7 +22,7 @@ endif quiet_cmd_copy_umh = GEN $@ cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \ $(OBJCOPY) -I binary \ - `LC_ALL=C objdump -f net/bpfilter/bpfilter_umh \ + `LC_ALL=C $(OBJDUMP) -f net/bpfilter/bpfilter_umh \ |awk -F' |,' '/file format/{print "-O",$$NF} \ /^architecture:/{print "-B",$$2}'` \ --rename-section .data=.init.rodata $< $@ diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 8b5ba6dffac7..12877a1514e7 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -600,7 +600,7 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - ktime_t now = ktime_get_real(); + ktime_t now = ktime_get(); s64 delta = 0; switch (fbtype) { @@ -625,15 +625,14 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, case CCID3_FBACK_PERIODIC: delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) - DCCP_BUG("delta (%ld) <= 0", (long)delta); - else - hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); + delta = 1; + hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); break; default: return; } - ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta, + ccid3_pr_debug("Interval %lldusec, X_recv=%u, 1/p=%u\n", delta, hc->rx_x_recv, hc->rx_pinv); hc->rx_tstamp_last_feedback = now; @@ -680,7 +679,8 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) static u32 ccid3_first_li(struct sock *sk) { struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); - u32 x_recv, p, delta; + u32 x_recv, p; + s64 delta; u64 fval; if (hc->rx_rtt == 0) { @@ -688,7 +688,9 @@ static u32 ccid3_first_li(struct sock *sk) hc->rx_rtt = DCCP_FALLBACK_RTT; } - delta = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback)); + delta = ktime_us_delta(ktime_get(), hc->rx_tstamp_last_feedback); + if (delta <= 0) + delta = 1; x_recv = scaled_div32(hc->rx_bytes_recv, delta); if (x_recv == 0) { /* would also trigger divide-by-zero */ DCCP_WARN("X_recv==0\n"); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 975021df7c1c..c0c74088f2af 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2082,7 +2082,8 @@ void ipv6_mc_dad_complete(struct inet6_dev *idev) mld_send_initial_cr(idev); idev->mc_dad_count--; if (idev->mc_dad_count) - mld_dad_start_timer(idev, idev->mc_maxdelay); + mld_dad_start_timer(idev, + unsolicited_report_interval(idev)); } } @@ -2094,7 +2095,8 @@ static void mld_dad_timer_expire(struct timer_list *t) if (idev->mc_dad_count) { idev->mc_dad_count--; if (idev->mc_dad_count) - mld_dad_start_timer(idev, idev->mc_maxdelay); + mld_dad_start_timer(idev, + unsolicited_report_interval(idev)); } in6_dev_put(idev); } @@ -2452,7 +2454,8 @@ static void mld_ifc_timer_expire(struct timer_list *t) if (idev->mc_ifc_count) { idev->mc_ifc_count--; if (idev->mc_ifc_count) - mld_ifc_start_timer(idev, idev->mc_maxdelay); + mld_ifc_start_timer(idev, + unsolicited_report_interval(idev)); } in6_dev_put(idev); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 50809748c127..ff8e7e245c37 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2262,6 +2262,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (po->stats.stats1.tp_drops) status |= TP_STATUS_LOSING; } + + if (do_vnet && + virtio_net_hdr_from_skb(skb, h.raw + macoff - + sizeof(struct virtio_net_hdr), + vio_le(), true, 0)) + goto drop_n_account; + po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; @@ -2269,15 +2276,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } spin_unlock(&sk->sk_receive_queue.lock); - if (do_vnet) { - if (virtio_net_hdr_from_skb(skb, h.raw + macoff - - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) { - spin_lock(&sk->sk_receive_queue.lock); - goto drop_n_account; - } - } - skb_copy_bits(skb, 0, h.raw + macoff, snaplen); if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 2b5be42a9f1c..9e8b26a80fb3 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -66,7 +66,7 @@ struct fl_flow_mask { struct rhashtable_params filter_ht_params; struct flow_dissector dissector; struct list_head filters; - struct rcu_head rcu; + struct rcu_work rwork; struct list_head list; }; @@ -203,6 +203,20 @@ static int fl_init(struct tcf_proto *tp) return rhashtable_init(&head->ht, &mask_ht_params); } +static void fl_mask_free(struct fl_flow_mask *mask) +{ + rhashtable_destroy(&mask->ht); + kfree(mask); +} + +static void fl_mask_free_work(struct work_struct *work) +{ + struct fl_flow_mask *mask = container_of(to_rcu_work(work), + struct fl_flow_mask, rwork); + + fl_mask_free(mask); +} + static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask, bool async) { @@ -210,12 +224,11 @@ static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask, return false; rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params); - rhashtable_destroy(&mask->ht); list_del_rcu(&mask->list); if (async) - kfree_rcu(mask, rcu); + tcf_queue_work(&mask->rwork, fl_mask_free_work); else - kfree(mask); + fl_mask_free(mask); return true; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3ae9877ea205..3278a76f6861 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1385,8 +1385,8 @@ hfsc_schedule_watchdog(struct Qdisc *sch) if (next_time == 0 || next_time > q->root.cl_cfmin) next_time = q->root.cl_cfmin; } - WARN_ON(next_time == 0); - qdisc_watchdog_schedule(&q->watchdog, next_time); + if (next_time) + qdisc_watchdog_schedule(&q->watchdog, next_time); } static int diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 79daa98208c3..bfb9f812e2ef 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -237,7 +237,9 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, /* Account for a different sized first fragment */ if (msg_len >= first_len) { msg->can_delay = 0; - SCTP_INC_STATS(sock_net(asoc->base.sk), SCTP_MIB_FRAGUSRMSGS); + if (msg_len > first_len) + SCTP_INC_STATS(sock_net(asoc->base.sk), + SCTP_MIB_FRAGUSRMSGS); } else { /* Which may be the only one... */ first_len = msg_len; diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 1a9695183599..373836615c57 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -392,7 +392,7 @@ static int strp_read_sock(struct strparser *strp) /* Lower sock lock held */ void strp_data_ready(struct strparser *strp) { - if (unlikely(strp->stopped)) + if (unlikely(strp->stopped) || strp->paused) return; /* This check is needed to synchronize with do_strp_work. @@ -407,9 +407,6 @@ void strp_data_ready(struct strparser *strp) return; } - if (strp->paused) - return; - if (strp->need_bytes) { if (strp_peek_len(strp) < strp->need_bytes) return; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 8e03bd3f3668..5d3cce9e8744 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -201,7 +201,7 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) return -ENODEV; } - if (le32_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) + if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) return virtio_transport_send_pkt_loopback(vsock, pkt); if (pkt->reply) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 34d9e9ce97c2..e7889f486ca1 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -239,6 +239,7 @@ cmd_record_mcount = \ "$(CC_FLAGS_FTRACE)" ]; then \ $(sub_cmd_record_mcount) \ fi; +endif # -record-mcount endif # CONFIG_FTRACE_MCOUNT_RECORD ifdef CONFIG_STACK_VALIDATION @@ -263,7 +264,6 @@ ifneq ($(RETPOLINE_CFLAGS),) objtool_args += --retpoline endif endif -endif ifdef CONFIG_MODVERSIONS diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 38047c6aa575..f4a25bd1871f 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -164,6 +164,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, "lbug_with_loc", "fortify_panic", "usercopy_abort", + "machine_real_restart", }; if (func->bind == STB_WEAK) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 5dfe102fb5b5..b10a90b6a718 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -178,6 +178,9 @@ Print count deltas for fixed number of times. This option should be used together with "-I" option. example: 'perf stat -I 1000 --interval-count 2 -e cycles -a' +--interval-clear:: +Clear the screen before next interval. + --timeout msecs:: Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms). This option is not supported with the "-I" option. diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 307b3594525f..6a8738f7ead3 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -56,16 +56,16 @@ struct c2c_hist_entry { struct compute_stats cstats; + unsigned long paddr; + unsigned long paddr_cnt; + bool paddr_zero; + char *nodestr; + /* * must be at the end, * because of its callchain dynamic entry */ struct hist_entry he; - - unsigned long paddr; - unsigned long paddr_cnt; - bool paddr_zero; - char *nodestr; }; static char const *coalesce_default = "pid,iaddr"; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index b3bf35512d21..a31d7082188e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -180,6 +180,18 @@ static struct { PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE }, + [PERF_TYPE_HW_CACHE] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, + [PERF_TYPE_RAW] = { .user_set = false, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 096ccb25c11f..22547a490e1f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -65,6 +65,7 @@ #include "util/tool.h" #include "util/string2.h" #include "util/metricgroup.h" +#include "util/top.h" #include "asm/bug.h" #include <linux/time64.h> @@ -144,6 +145,8 @@ static struct target target = { typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu); +#define METRIC_ONLY_LEN 20 + static int run_count = 1; static bool no_inherit = false; static volatile pid_t child_pid = -1; @@ -173,6 +176,7 @@ static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; static bool append_file; static bool interval_count; +static bool interval_clear; static const char *output_name; static int output_fd; static int print_free_counters_hint; @@ -180,6 +184,7 @@ static int print_mixed_hw_group_error; static u64 *walltime_run; static bool ru_display = false; static struct rusage ru_data; +static unsigned int metric_only_len = METRIC_ONLY_LEN; struct perf_stat { bool record; @@ -967,8 +972,6 @@ static void print_metric_csv(void *ctx, fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit); } -#define METRIC_ONLY_LEN 20 - /* Filter out some columns that don't work well in metrics only mode */ static bool valid_only_metric(const char *unit) @@ -999,22 +1002,20 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt, { struct outstate *os = ctx; FILE *out = os->fh; - int n; - char buf[1024]; - unsigned mlen = METRIC_ONLY_LEN; + char buf[1024], str[1024]; + unsigned mlen = metric_only_len; if (!valid_only_metric(unit)) return; unit = fixunit(buf, os->evsel, unit); - if (color) - n = color_fprintf(out, color, fmt, val); - else - n = fprintf(out, fmt, val); - if (n > METRIC_ONLY_LEN) - n = METRIC_ONLY_LEN; if (mlen < strlen(unit)) mlen = strlen(unit) + 1; - fprintf(out, "%*s", mlen - n, ""); + + if (color) + mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; + + color_snprintf(str, sizeof(str), color ?: "", fmt, val); + fprintf(out, "%*s ", mlen, str); } static void print_metric_only_csv(void *ctx, const char *color __maybe_unused, @@ -1054,7 +1055,7 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused, if (csv_output) fprintf(os->fh, "%s%s", unit, csv_sep); else - fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit); + fprintf(os->fh, "%*s ", metric_only_len, unit); } static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) @@ -1704,9 +1705,12 @@ static void print_interval(char *prefix, struct timespec *ts) FILE *output = stat_config.output; static int num_print_interval; + if (interval_clear) + puts(CONSOLE_CLEAR); + sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep); - if (num_print_interval == 0 && !csv_output) { + if ((num_print_interval == 0 && !csv_output) || interval_clear) { switch (stat_config.aggr_mode) { case AGGR_SOCKET: fprintf(output, "# time socket cpus"); @@ -1719,7 +1723,7 @@ static void print_interval(char *prefix, struct timespec *ts) fprintf(output, " counts %*s events\n", unit_width, "unit"); break; case AGGR_NONE: - fprintf(output, "# time CPU"); + fprintf(output, "# time CPU "); if (!metric_only) fprintf(output, " counts %*s events\n", unit_width, "unit"); break; @@ -1738,7 +1742,7 @@ static void print_interval(char *prefix, struct timespec *ts) } } - if (num_print_interval == 0 && metric_only) + if ((num_print_interval == 0 && metric_only) || interval_clear) print_metric_headers(" ", true); if (++num_print_interval == 25) num_print_interval = 0; @@ -2057,6 +2061,8 @@ static const struct option stat_options[] = { "(overhead is possible for values <= 100ms)"), OPT_INTEGER(0, "interval-count", &stat_config.times, "print counts for fixed number of times"), + OPT_BOOLEAN(0, "interval-clear", &interval_clear, + "clear screen in between new interval"), OPT_UINTEGER(0, "timeout", &stat_config.timeout, "stop workload and print counts after a timeout period in ms (>= 10ms)"), OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode, @@ -2436,14 +2442,13 @@ static int add_default_attributes(void) (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, }; + struct parse_events_error errinfo; /* Set attrs if no event is selected and !null_run: */ if (null_run) return 0; if (transaction_run) { - struct parse_events_error errinfo; - if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) err = parse_events(evsel_list, transaction_attrs, @@ -2454,6 +2459,7 @@ static int add_default_attributes(void) &errinfo); if (err) { fprintf(stderr, "Cannot set up transaction events\n"); + parse_events_print_error(&errinfo, transaction_attrs); return -1; } return 0; @@ -2479,10 +2485,11 @@ static int add_default_attributes(void) pmu_have_event("msr", "smi")) { if (!force_metric_only) metric_only = true; - err = parse_events(evsel_list, smi_cost_attrs, NULL); + err = parse_events(evsel_list, smi_cost_attrs, &errinfo); } else { fprintf(stderr, "To measure SMI cost, it needs " "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); + parse_events_print_error(&errinfo, smi_cost_attrs); return -1; } if (err) { @@ -2517,12 +2524,13 @@ static int add_default_attributes(void) if (topdown_attrs[0] && str) { if (warn) arch_topdown_group_warn(); - err = parse_events(evsel_list, str, NULL); + err = parse_events(evsel_list, str, &errinfo); if (err) { fprintf(stderr, "Cannot set up top down events %s: %d\n", str, err); free(str); + parse_events_print_error(&errinfo, str); return -1; } } else { diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index b085f1b3e34d..4ab663ec3e5e 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -382,7 +382,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, gtk_tree_store_set(store, &iter, col_idx++, s, -1); } - if (hists__has_callchains(hists) && + if (hist_entry__has_callchains(h) && symbol_conf.use_callchain && hists__has(hists, sym)) { if (callchain_param.mode == CHAIN_GRAPH_REL) total = symbol_conf.cumulate_callchain ? diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 52e8fda93a47..828cb9794c76 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -370,9 +370,11 @@ void hists__delete_entries(struct hists *hists) static int hist_entry__init(struct hist_entry *he, struct hist_entry *template, - bool sample_self) + bool sample_self, + size_t callchain_size) { *he = *template; + he->callchain_size = callchain_size; if (symbol_conf.cumulate_callchain) { he->stat_acc = malloc(sizeof(he->stat)); @@ -473,7 +475,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, he = ops->new(callchain_size); if (he) { - err = hist_entry__init(he, template, sample_self); + err = hist_entry__init(he, template, sample_self, callchain_size); if (err) { ops->free(he); he = NULL; @@ -619,9 +621,11 @@ __hists__add_entry(struct hists *hists, .raw_data = sample->raw_data, .raw_size = sample->raw_size, .ops = ops, - }; + }, *he = hists__findnew_entry(hists, &entry, al, sample_self); - return hists__findnew_entry(hists, &entry, al, sample_self); + if (!hists->has_callchains && he && he->callchain_size != 0) + hists->has_callchains = true; + return he; } struct hist_entry *hists__add_entry(struct hists *hists, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 06607c434949..73049f7f0f60 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -85,6 +85,7 @@ struct hists { struct events_stats stats; u64 event_stream; u16 col_len[HISTC_NR_COLS]; + bool has_callchains; int socket_filter; struct perf_hpp_list *hpp_list; struct list_head hpp_formats; @@ -222,8 +223,7 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) static __pure inline bool hists__has_callchains(struct hists *hists) { - const struct perf_evsel *evsel = hists_to_evsel(hists); - return evsel__has_callchain(evsel); + return hists->has_callchains; } int hists__init(void); diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 155d2570274f..da8fe57691b8 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -227,11 +227,16 @@ event_def: event_pmu | event_pmu: PE_NAME opt_pmu_config { + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list, *orig_terms, *terms; if (parse_events_copy_term_list($2, &orig_terms)) YYABORT; + if (error) + error->idx = @1.first_column; + ALLOC_LIST(list); if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { struct perf_pmu *pmu = NULL; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7cf2d5cc038e..8bf302cafcec 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -112,6 +112,8 @@ struct hist_entry { char level; u8 filtered; + + u16 callchain_size; union { /* * Since perf diff only supports the stdio output, TUI @@ -153,7 +155,7 @@ struct hist_entry { static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) { - return hists__has_callchains(he->hists); + return he->callchain_size != 0; } static inline bool hist_entry__has_pairs(struct hist_entry *he) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 128e548aa377..1a0ac3a29ec5 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -12,3 +12,4 @@ tcp_mmap udpgso udpgso_bench_rx udpgso_bench_tx +tcp_inq diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 7ba089b33e8b..cd3a2f1545b5 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -12,3 +12,5 @@ CONFIG_NET_IPVTI=y CONFIG_INET6_XFRM_MODE_TUNNEL=y CONFIG_IPV6_VTI=y CONFIG_DUMMY=y +CONFIG_BRIDGE=y +CONFIG_VLAN_8021Q=y diff --git a/tools/testing/selftests/pstore/pstore_post_reboot_tests b/tools/testing/selftests/pstore/pstore_post_reboot_tests index 6ccb154cb4aa..22f8df1ad7d4 100755 --- a/tools/testing/selftests/pstore/pstore_post_reboot_tests +++ b/tools/testing/selftests/pstore/pstore_post_reboot_tests @@ -7,13 +7,16 @@ # # Released under the terms of the GPL v2. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + . ./common_tests if [ -e $REBOOT_FLAG ]; then rm $REBOOT_FLAG else prlog "pstore_crash_test has not been executed yet. we skip further tests." - exit 0 + exit $ksft_skip fi prlog -n "Mounting pstore filesystem ... " diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 6a9f602a8718..615252331813 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -137,6 +137,30 @@ unsigned int yield_mod_cnt, nr_abort; "subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \ "bne 222b\n\t" \ "333:\n\t" + +#elif defined(__mips__) + +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) + +#define INJECT_ASM_REG "$5" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "lw " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "beqz " INJECT_ASM_REG ", 333f\n\t" \ + "222:\n\t" \ + "addiu " INJECT_ASM_REG ", -1\n\t" \ + "bnez " INJECT_ASM_REG ", 222b\n\t" \ + "333:\n\t" + #else #error unsupported target #endif diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h index 3b055f9aeaab..3cea19877227 100644 --- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -57,6 +57,7 @@ do { \ #define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \ abort_label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ + ".balign 32\n\t" \ __rseq_str(table_label) ":\n\t" \ ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ ".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \ diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h new file mode 100644 index 000000000000..7f48ecf46994 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-mips.h @@ -0,0 +1,725 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Author: Paul Burton <paul.burton@mips.com> + * (C) Copyright 2018 MIPS Tech LLC + * + * Based on rseq-arm.h: + * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com> + */ + +#define RSEQ_SIG 0x53053053 + +#define rseq_smp_mb() __asm__ __volatile__ ("sync" ::: "memory") +#define rseq_smp_rmb() rseq_smp_mb() +#define rseq_smp_wmb() rseq_smp_mb() + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + __typeof(*p) ____p1 = RSEQ_READ_ONCE(*p); \ + rseq_smp_mb(); \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() + +#define rseq_smp_store_release(p, v) \ +do { \ + rseq_smp_mb(); \ + RSEQ_WRITE_ONCE(*p, v); \ +} while (0) + +#ifdef RSEQ_SKIP_FASTPATH +#include "rseq-skip.h" +#else /* !RSEQ_SKIP_FASTPATH */ + +#if _MIPS_SZLONG == 64 +# define LONG ".dword" +# define LONG_LA "dla" +# define LONG_L "ld" +# define LONG_S "sd" +# define LONG_ADDI "daddiu" +# define U32_U64_PAD(x) x +#elif _MIPS_SZLONG == 32 +# define LONG ".word" +# define LONG_LA "la" +# define LONG_L "lw" +# define LONG_S "sw" +# define LONG_ADDI "addiu" +# ifdef __BIG_ENDIAN +# define U32_U64_PAD(x) "0x0, " x +# else +# define U32_U64_PAD(x) x ", 0x0" +# endif +#else +# error unsupported _MIPS_SZLONG +#endif + +#define __RSEQ_ASM_DEFINE_TABLE(version, flags, start_ip, \ + post_commit_offset, abort_ip) \ + ".pushsection __rseq_table, \"aw\"\n\t" \ + ".balign 32\n\t" \ + ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \ + LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \ + LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \ + ".popsection\n\t" + +#define RSEQ_ASM_DEFINE_TABLE(start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(0x0, 0x0, start_ip, \ + (post_commit_ip - start_ip), abort_ip) + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + LONG_LA " $4, " __rseq_str(cs_label) "\n\t" \ + LONG_S " $4, %[" __rseq_str(rseq_cs) "]\n\t" \ + __rseq_str(label) ":\n\t" + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + "lw $4, %[" __rseq_str(current_cpu_id) "]\n\t" \ + "bne $4, %[" __rseq_str(cpu_id) "], " __rseq_str(label) "\n\t" + +#define __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \ + abort_label, version, flags, \ + start_ip, post_commit_offset, abort_ip) \ + ".balign 32\n\t" \ + __rseq_str(table_label) ":\n\t" \ + ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ + LONG " " U32_U64_PAD(__rseq_str(start_ip)) "\n\t" \ + LONG " " U32_U64_PAD(__rseq_str(post_commit_offset)) "\n\t" \ + LONG " " U32_U64_PAD(__rseq_str(abort_ip)) "\n\t" \ + ".word " __rseq_str(RSEQ_SIG) "\n\t" \ + __rseq_str(label) ":\n\t" \ + teardown \ + "b %l[" __rseq_str(abort_label) "]\n\t" + +#define RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, abort_label, \ + start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_ABORT(table_label, label, teardown, \ + abort_label, 0x0, 0x0, start_ip, \ + (post_commit_ip - start_ip), abort_ip) + +#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label) \ + __rseq_str(label) ":\n\t" \ + teardown \ + "b %l[" __rseq_str(cmpfail_label) "]\n\t" + +#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("") + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[error2]\n\t" +#endif + /* final store */ + LONG_S " %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + LONG_L " $4, %[v]\n\t" + "beq $4, %[expectnot], %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + LONG_L " $4, %[v]\n\t" + "beq $4, %[expectnot], %l[error2]\n\t" +#endif + LONG_S " $4, %[load]\n\t" + LONG_ADDI " $4, %[voffp]\n\t" + LONG_L " $4, 0($4)\n\t" + /* final store */ + LONG_S " $4, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(5) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expectnot] "r" (expectnot), + [voffp] "Ir" (voffp), + [load] "m" (*load) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_addv(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) +#endif + LONG_L " $4, %[v]\n\t" + LONG_ADDI " $4, %[count]\n\t" + /* final store */ + LONG_S " $4, %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(4) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + [v] "m" (*v), + [count] "Ir" (count) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[error2]\n\t" +#endif + /* try store */ + LONG_S " %[newv2], %[v2]\n\t" + RSEQ_INJECT_ASM(5) + /* final store */ + LONG_S " %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[error2]\n\t" +#endif + /* try store */ + LONG_S " %[newv2], %[v2]\n\t" + RSEQ_INJECT_ASM(5) + "sync\n\t" /* full sync provides store-release */ + /* final store */ + LONG_S " %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* try store input */ + [v2] "m" (*v2), + [newv2] "r" (newv2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(4) + LONG_L " $4, %[v2]\n\t" + "bne $4, %[expect2], %l[cmpfail]\n\t" + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1]) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], %l[error2]\n\t" + LONG_L " $4, %[v2]\n\t" + "bne $4, %[expect2], %l[error3]\n\t" +#endif + /* final store */ + LONG_S " %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + "b 5f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, "", abort, 1b, 2b, 4f) + "5:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* cmp2 input */ + [v2] "m" (*v2), + [expect2] "r" (expect2), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("1st expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + uintptr_t rseq_scratch[3]; + + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + LONG_S " %[src], %[rseq_scratch0]\n\t" + LONG_S " %[dst], %[rseq_scratch1]\n\t" + LONG_S " %[len], %[rseq_scratch2]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], 5f\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], 7f\n\t" +#endif + /* try memcpy */ + "beqz %[len], 333f\n\t" \ + "222:\n\t" \ + "lb $4, 0(%[src])\n\t" \ + "sb $4, 0(%[dst])\n\t" \ + LONG_ADDI " %[src], 1\n\t" \ + LONG_ADDI " %[dst], 1\n\t" \ + LONG_ADDI " %[len], -1\n\t" \ + "bnez %[len], 222b\n\t" \ + "333:\n\t" \ + RSEQ_INJECT_ASM(5) + /* final store */ + LONG_S " %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t" + "b 8f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + abort, 1b, 2b, 4f) + RSEQ_ASM_DEFINE_CMPFAIL(5, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + cmpfail) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_CMPFAIL(6, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + error1) + RSEQ_ASM_DEFINE_CMPFAIL(7, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + error2) +#endif + "8:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len), + [rseq_scratch0] "m" (rseq_scratch[0]), + [rseq_scratch1] "m" (rseq_scratch[1]), + [rseq_scratch2] "m" (rseq_scratch[2]) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("cpu_id comparison failed"); +error2: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __attribute__((always_inline)) +int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + uintptr_t rseq_scratch[3]; + + RSEQ_INJECT_C(9) + + rseq_workaround_gcc_asm_size_guess(); + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(1f, 2f, 4f) /* start, commit, abort */ + LONG_S " %[src], %[rseq_scratch0]\n\t" + LONG_S " %[dst], %[rseq_scratch1]\n\t" + LONG_S " %[len], %[rseq_scratch2]\n\t" + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3f, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], 5f\n\t" + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f) + LONG_L " $4, %[v]\n\t" + "bne $4, %[expect], 7f\n\t" +#endif + /* try memcpy */ + "beqz %[len], 333f\n\t" \ + "222:\n\t" \ + "lb $4, 0(%[src])\n\t" \ + "sb $4, 0(%[dst])\n\t" \ + LONG_ADDI " %[src], 1\n\t" \ + LONG_ADDI " %[dst], 1\n\t" \ + LONG_ADDI " %[len], -1\n\t" \ + "bnez %[len], 222b\n\t" \ + "333:\n\t" \ + RSEQ_INJECT_ASM(5) + "sync\n\t" /* full sync provides store-release */ + /* final store */ + LONG_S " %[newv], %[v]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(6) + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t" + "b 8f\n\t" + RSEQ_ASM_DEFINE_ABORT(3, 4, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + abort, 1b, 2b, 4f) + RSEQ_ASM_DEFINE_CMPFAIL(5, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + cmpfail) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_CMPFAIL(6, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + error1) + RSEQ_ASM_DEFINE_CMPFAIL(7, + /* teardown */ + LONG_L " %[len], %[rseq_scratch2]\n\t" + LONG_L " %[dst], %[rseq_scratch1]\n\t" + LONG_L " %[src], %[rseq_scratch0]\n\t", + error2) +#endif + "8:\n\t" + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (__rseq_abi.cpu_id), + [rseq_cs] "m" (__rseq_abi.rseq_cs), + /* final store input */ + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv), + /* try memcpy input */ + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len), + [rseq_scratch0] "m" (rseq_scratch[0]), + [rseq_scratch1] "m" (rseq_scratch[1]), + [rseq_scratch2] "m" (rseq_scratch[2]) + RSEQ_INJECT_INPUT + : "$4", "memory" + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + rseq_workaround_gcc_asm_size_guess(); + return 0; +abort: + rseq_workaround_gcc_asm_size_guess(); + RSEQ_INJECT_FAILED + return -1; +cmpfail: + rseq_workaround_gcc_asm_size_guess(); + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("cpu_id comparison failed"); +error2: + rseq_workaround_gcc_asm_size_guess(); + rseq_bug("expected value comparison failed"); +#endif +} + +#endif /* !RSEQ_SKIP_FASTPATH */ diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 0a808575cbc4..a4684112676c 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -73,6 +73,8 @@ extern __thread volatile struct rseq __rseq_abi; #include <rseq-arm.h> #elif defined(__PPC__) #include <rseq-ppc.h> +#elif defined(__mips__) +#include <rseq-mips.h> #else #error unsupported target #endif diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh index 3acd6d75ff9f..3acd6d75ff9f 100644..100755 --- a/tools/testing/selftests/rseq/run_param_test.sh +++ b/tools/testing/selftests/rseq/run_param_test.sh diff --git a/tools/testing/selftests/sparc64/Makefile b/tools/testing/selftests/sparc64/Makefile index 2082eeffd779..a19531dba4dc 100644 --- a/tools/testing/selftests/sparc64/Makefile +++ b/tools/testing/selftests/sparc64/Makefile @@ -1,7 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0 +uname_M := $(shell uname -m 2>/dev/null || echo not) +ARCH ?= $(shell echo $(uname_M) | sed -e s/x86_64/x86/) + +ifneq ($(ARCH),sparc64) +nothing: +.PHONY: all clean run_tests install +.SILENT: +else + SUBDIRS := drivers TEST_PROGS := run.sh + .PHONY: all clean include ../lib.mk @@ -18,10 +29,6 @@ all: fi \ done -override define RUN_TESTS - @cd $(OUTPUT); ./run.sh -endef - override define INSTALL_RULE mkdir -p $(INSTALL_PATH) install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) @@ -33,10 +40,6 @@ override define INSTALL_RULE done; endef -override define EMIT_TESTS - echo "./run.sh" -endef - override define CLEAN @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ @@ -44,3 +47,4 @@ override define CLEAN make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ done endef +endif diff --git a/tools/testing/selftests/sparc64/drivers/Makefile b/tools/testing/selftests/sparc64/drivers/Makefile index 6264f40bbdbc..deb0df415565 100644 --- a/tools/testing/selftests/sparc64/drivers/Makefile +++ b/tools/testing/selftests/sparc64/drivers/Makefile @@ -1,4 +1,4 @@ - +# SPDX-License-Identifier: GPL-2.0 INCLUDEDIR := -I. CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g diff --git a/tools/testing/selftests/static_keys/test_static_keys.sh b/tools/testing/selftests/static_keys/test_static_keys.sh index 24cff498b31a..fc9f8cde7d42 100755 --- a/tools/testing/selftests/static_keys/test_static_keys.sh +++ b/tools/testing/selftests/static_keys/test_static_keys.sh @@ -2,6 +2,19 @@ # SPDX-License-Identifier: GPL-2.0 # Runs static keys kernel module tests +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if ! /sbin/modprobe -q -n test_static_key_base; then + echo "static_key: module test_static_key_base is not found [SKIP]" + exit $ksft_skip +fi + +if ! /sbin/modprobe -q -n test_static_keys; then + echo "static_key: module test_static_keys is not found [SKIP]" + exit $ksft_skip +fi + if /sbin/modprobe -q test_static_key_base; then if /sbin/modprobe -q test_static_keys; then echo "static_key: ok" diff --git a/tools/testing/selftests/sync/config b/tools/testing/selftests/sync/config new file mode 100644 index 000000000000..1ab7e8130db2 --- /dev/null +++ b/tools/testing/selftests/sync/config @@ -0,0 +1,4 @@ +CONFIG_STAGING=y +CONFIG_ANDROID=y +CONFIG_SYNC=y +CONFIG_SW_SYNC=y diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index ec232c3cfcaa..584eb8ea780a 100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -14,6 +14,9 @@ # This performs a series tests against the proc sysctl interface. +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + TEST_NAME="sysctl" TEST_DRIVER="test_${TEST_NAME}" TEST_DIR=$(dirname $0) @@ -41,7 +44,7 @@ test_modprobe() echo "$0: $DIR not present" >&2 echo "You must have the following enabled in your kernel:" >&2 cat $TEST_DIR/config >&2 - exit 1 + exit $ksft_skip fi } @@ -98,28 +101,30 @@ test_reqs() uid=$(id -u) if [ $uid -ne 0 ]; then echo $msg must be run as root >&2 - exit 0 + exit $ksft_skip fi if ! which perl 2> /dev/null > /dev/null; then echo "$0: You need perl installed" - exit 1 + exit $ksft_skip fi if ! which getconf 2> /dev/null > /dev/null; then echo "$0: You need getconf installed" - exit 1 + exit $ksft_skip fi if ! which diff 2> /dev/null > /dev/null; then echo "$0: You need diff installed" - exit 1 + exit $ksft_skip fi } function load_req_mod() { - trap "test_modprobe" EXIT - if [ ! -d $DIR ]; then + if ! modprobe -q -n $TEST_DRIVER; then + echo "$0: module $TEST_DRIVER not found [SKIP]" + exit $ksft_skip + fi modprobe $TEST_DRIVER if [ $? -ne 0 ]; then exit @@ -765,6 +770,7 @@ function parse_args() test_reqs allow_user_defaults check_production_sysctl_writes_strict +test_modprobe load_req_mod trap "test_finish" EXIT diff --git a/tools/testing/selftests/user/test_user_copy.sh b/tools/testing/selftests/user/test_user_copy.sh index d60506fc77f8..f9b31a57439b 100755 --- a/tools/testing/selftests/user/test_user_copy.sh +++ b/tools/testing/selftests/user/test_user_copy.sh @@ -2,6 +2,13 @@ # SPDX-License-Identifier: GPL-2.0 # Runs copy_to/from_user infrastructure using test_user_copy kernel module +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if ! /sbin/modprobe -q -n test_user_copy; then + echo "user: module test_user_copy is not found [SKIP]" + exit $ksft_skip +fi if /sbin/modprobe -q test_user_copy; then /sbin/modprobe -q -r test_user_copy echo "user_copy: ok" diff --git a/tools/testing/selftests/vm/compaction_test.c b/tools/testing/selftests/vm/compaction_test.c index 1097f04e4d80..bcec71250873 100644 --- a/tools/testing/selftests/vm/compaction_test.c +++ b/tools/testing/selftests/vm/compaction_test.c @@ -16,6 +16,8 @@ #include <unistd.h> #include <string.h> +#include "../kselftest.h" + #define MAP_SIZE 1048576 struct map_list { @@ -169,7 +171,7 @@ int main(int argc, char **argv) printf("Either the sysctl compact_unevictable_allowed is not\n" "set to 1 or couldn't read the proc file.\n" "Skipping the test\n"); - return 0; + return KSFT_SKIP; } lim.rlim_cur = RLIM_INFINITY; diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c index 4997b9222cfa..637b6d0ac0d0 100644 --- a/tools/testing/selftests/vm/mlock2-tests.c +++ b/tools/testing/selftests/vm/mlock2-tests.c @@ -9,6 +9,8 @@ #include <stdbool.h> #include "mlock2.h" +#include "../kselftest.h" + struct vm_boundaries { unsigned long start; unsigned long end; @@ -303,7 +305,7 @@ static int test_mlock_lock() if (mlock2_(map, 2 * page_size, 0)) { if (errno == ENOSYS) { printf("Cannot call new mlock family, skipping test\n"); - _exit(0); + _exit(KSFT_SKIP); } perror("mlock2(0)"); goto unmap; @@ -412,7 +414,7 @@ static int test_mlock_onfault() if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) { if (errno == ENOSYS) { printf("Cannot call new mlock family, skipping test\n"); - _exit(0); + _exit(KSFT_SKIP); } perror("mlock2(MLOCK_ONFAULT)"); goto unmap; @@ -425,7 +427,7 @@ static int test_mlock_onfault() if (munlock(map, 2 * page_size)) { if (errno == ENOSYS) { printf("Cannot call new mlock family, skipping test\n"); - _exit(0); + _exit(KSFT_SKIP); } perror("munlock()"); goto unmap; @@ -457,7 +459,7 @@ static int test_lock_onfault_of_present() if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) { if (errno == ENOSYS) { printf("Cannot call new mlock family, skipping test\n"); - _exit(0); + _exit(KSFT_SKIP); } perror("mlock2(MLOCK_ONFAULT)"); goto unmap; @@ -583,7 +585,7 @@ static int test_vma_management(bool call_mlock) if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) { if (errno == ENOSYS) { printf("Cannot call new mlock family, skipping test\n"); - _exit(0); + _exit(KSFT_SKIP); } perror("mlock(ONFAULT)\n"); goto out; diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index 22d564673830..88cbe5575f0c 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -2,6 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 #please run as root +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + mnt=./huge exitcode=0 @@ -36,7 +39,7 @@ if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages if [ $? -ne 0 ]; then echo "Please run this test as root" - exit 1 + exit $ksft_skip fi while read name size unit; do if [ "$name" = "HugePages_Free:" ]; then diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index de2f9ec8a87f..7b8171e3128a 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -69,6 +69,8 @@ #include <setjmp.h> #include <stdbool.h> +#include "../kselftest.h" + #ifdef __NR_userfaultfd static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; @@ -1322,7 +1324,7 @@ int main(int argc, char **argv) int main(void) { printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n"); - return 0; + return KSFT_SKIP; } #endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh index 754de7da426a..232e958ec454 100755 --- a/tools/testing/selftests/zram/zram.sh +++ b/tools/testing/selftests/zram/zram.sh @@ -2,6 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 TCID="zram.sh" +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + . ./zram_lib.sh run_zram () { @@ -24,5 +27,5 @@ elif [ -b /dev/zram0 ]; then else echo "$TCID : No zram.ko module or /dev/zram0 device file not found" echo "$TCID : CONFIG_ZRAM is not set" - exit 1 + exit $ksft_skip fi diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index f6a9c73e7a44..9e73a4fb9b0a 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -18,6 +18,9 @@ MODULE=0 dev_makeswap=-1 dev_mounted=-1 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + trap INT check_prereqs() @@ -27,7 +30,7 @@ check_prereqs() if [ $uid -ne 0 ]; then echo $msg must be run as root >&2 - exit 0 + exit $ksft_skip fi } diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 72143cfaf6ec..ea434ddc8499 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -47,7 +47,7 @@ config KVM_GENERIC_DIRTYLOG_READ_PROTECT config KVM_COMPAT def_bool y - depends on KVM && COMPAT && !S390 + depends on KVM && COMPAT && !(S390 || ARM64) config HAVE_KVM_IRQ_BYPASS bool diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 8d90de213ce9..1d90d79706bd 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -297,6 +297,8 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) phys_addr_t next; assert_spin_locked(&kvm->mmu_lock); + WARN_ON(size & ~PAGE_MASK); + pgd = kvm->arch.pgd + stage2_pgd_index(addr); do { /* diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index ff7dc890941a..cdce653e3c47 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -617,11 +617,6 @@ int vgic_v3_probe(const struct gic_kvm_info *info) pr_warn("GICV physical address 0x%llx not page aligned\n", (unsigned long long)info->vcpu.start); kvm_vgic_global_state.vcpu_base = 0; - } else if (!PAGE_ALIGNED(resource_size(&info->vcpu))) { - pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n", - (unsigned long long)resource_size(&info->vcpu), - PAGE_SIZE); - kvm_vgic_global_state.vcpu_base = 0; } else { kvm_vgic_global_state.vcpu_base = info->vcpu.start; kvm_vgic_global_state.can_emulate_gicv2 = true; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ada21f47f22b..8b47507faab5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -116,6 +116,11 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, #ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); +#define KVM_COMPAT(c) .compat_ioctl = (c) +#else +static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl, + unsigned long arg) { return -EINVAL; } +#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl #endif static int hardware_enable_all(void); static void hardware_disable_all(void); @@ -2396,11 +2401,9 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp) static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, -#ifdef CONFIG_KVM_COMPAT - .compat_ioctl = kvm_vcpu_compat_ioctl, -#endif .mmap = kvm_vcpu_mmap, .llseek = noop_llseek, + KVM_COMPAT(kvm_vcpu_compat_ioctl), }; /* @@ -2824,10 +2827,8 @@ static int kvm_device_release(struct inode *inode, struct file *filp) static const struct file_operations kvm_device_fops = { .unlocked_ioctl = kvm_device_ioctl, -#ifdef CONFIG_KVM_COMPAT - .compat_ioctl = kvm_device_ioctl, -#endif .release = kvm_device_release, + KVM_COMPAT(kvm_device_ioctl), }; struct kvm_device *kvm_device_from_filp(struct file *filp) @@ -3165,10 +3166,8 @@ static long kvm_vm_compat_ioctl(struct file *filp, static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, -#ifdef CONFIG_KVM_COMPAT - .compat_ioctl = kvm_vm_compat_ioctl, -#endif .llseek = noop_llseek, + KVM_COMPAT(kvm_vm_compat_ioctl), }; static int kvm_dev_ioctl_create_vm(unsigned long type) @@ -3259,8 +3258,8 @@ out: static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, - .compat_ioctl = kvm_dev_ioctl, .llseek = noop_llseek, + KVM_COMPAT(kvm_dev_ioctl), }; static struct miscdevice kvm_dev = { |